diff options
Diffstat (limited to 'fs/autofs4')
| -rw-r--r-- | fs/autofs4/Kconfig | 20 | ||||
| -rw-r--r-- | fs/autofs4/Makefile | 2 | ||||
| -rw-r--r-- | fs/autofs4/autofs_i.h | 246 | ||||
| -rw-r--r-- | fs/autofs4/dev-ioctl.c | 758 | ||||
| -rw-r--r-- | fs/autofs4/expire.c | 356 | ||||
| -rw-r--r-- | fs/autofs4/init.c | 20 | ||||
| -rw-r--r-- | fs/autofs4/inode.c | 302 | ||||
| -rw-r--r-- | fs/autofs4/root.c | 1122 | ||||
| -rw-r--r-- | fs/autofs4/symlink.c | 5 | ||||
| -rw-r--r-- | fs/autofs4/waitq.c | 368 |
10 files changed, 2083 insertions, 1116 deletions
diff --git a/fs/autofs4/Kconfig b/fs/autofs4/Kconfig new file mode 100644 index 00000000000..1204d6384d3 --- /dev/null +++ b/fs/autofs4/Kconfig @@ -0,0 +1,20 @@ +config AUTOFS4_FS + tristate "Kernel automounter version 4 support (also supports v3)" + help + The automounter is a tool to automatically mount remote file systems + on demand. This implementation is partially kernel-based to reduce + overhead in the already-mounted case; this is unlike the BSD + automounter (amd), which is a pure user space daemon. + + To use the automounter you need the user-space tools from + <ftp://ftp.kernel.org/pub/linux/daemons/autofs/v4/>; you also + want to answer Y to "NFS file system support", below. + + To compile this support as a module, choose M here: the module will be + called autofs4. You will need to add "alias autofs autofs4" to your + modules configuration file. + + If you are not a part of a fairly large, distributed network or + don't have a laptop which needs to dynamically reconfigure to the + local network, you probably do not need an automounter, and can say + N here. diff --git a/fs/autofs4/Makefile b/fs/autofs4/Makefile index f2c3b79e94d..a811c1f7d9a 100644 --- a/fs/autofs4/Makefile +++ b/fs/autofs4/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_AUTOFS4_FS) += autofs4.o -autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o +autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index 2d4ae40718d..acf32054edd 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -14,13 +14,18 @@ /* Internal header file for autofs */ #include <linux/auto_fs4.h> +#include <linux/auto_dev-ioctl.h> #include <linux/mutex.h> +#include <linux/spinlock.h> #include <linux/list.h> /* This is the range of ioctl() numbers we claim as ours */ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY #define AUTOFS_IOC_COUNT 32 +#define AUTOFS_DEV_IOCTL_IOC_FIRST (AUTOFS_DEV_IOCTL_VERSION) +#define AUTOFS_DEV_IOCTL_IOC_COUNT (AUTOFS_IOC_COUNT - 11) + #include <linux/kernel.h> #include <linux/slab.h> #include <linux/time.h> @@ -34,11 +39,17 @@ /* #define DEBUG */ -#ifdef DEBUG -#define DPRINTK(fmt,args...) do { printk(KERN_DEBUG "pid %d: %s: " fmt "\n" , current->pid , __FUNCTION__ , ##args); } while(0) -#else -#define DPRINTK(fmt,args...) do {} while(0) -#endif +#define DPRINTK(fmt, ...) \ + pr_debug("pid %d: %s: " fmt "\n", \ + current->pid, __func__, ##__VA_ARGS__) + +#define AUTOFS_WARN(fmt, ...) \ + printk(KERN_WARNING "pid %d: %s: " fmt "\n", \ + current->pid, __func__, ##__VA_ARGS__) + +#define AUTOFS_ERROR(fmt, ...) \ + printk(KERN_ERR "pid %d: %s: " fmt "\n", \ + current->pid, __func__, ##__VA_ARGS__) /* Unified info structure. This is pointed to by both the dentry and inode structures. Each file in the filesystem has an instance of this @@ -52,53 +63,48 @@ struct autofs_info { int flags; - struct list_head rehash; + struct completion expire_complete; + + struct list_head active; + int active_count; + + struct list_head expiring; struct autofs_sb_info *sbi; unsigned long last_used; atomic_t count; - mode_t mode; - size_t size; - - void (*free)(struct autofs_info *); - union { - const char *symlink; - } u; + kuid_t uid; + kgid_t gid; }; #define AUTOFS_INF_EXPIRING (1<<0) /* dentry is in the process of expiring */ +#define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */ struct autofs_wait_queue { wait_queue_head_t queue; struct autofs_wait_queue *next; autofs_wqt_t wait_queue_token; /* We use the following to see what we are waiting for */ - unsigned int hash; - unsigned int len; - char *name; + struct qstr name; u32 dev; u64 ino; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; pid_t pid; pid_t tgid; /* This is for status reporting upon return */ int status; - atomic_t wait_ctr; + unsigned int wait_ctr; }; #define AUTOFS_SBI_MAGIC 0x6d4a556d -#define AUTOFS_TYPE_INDIRECT 0x0001 -#define AUTOFS_TYPE_DIRECT 0x0002 -#define AUTOFS_TYPE_OFFSET 0x0004 - struct autofs_sb_info { u32 magic; int pipefd; struct file *pipe; - pid_t oz_pgrp; + struct pid *oz_pgrp; int catatonic; int version; int sub_version; @@ -110,10 +116,13 @@ struct autofs_sb_info { int needs_reghost; struct super_block *sb; struct mutex wq_mutex; + struct mutex pipe_mutex; spinlock_t fs_lock; struct autofs_wait_queue *queues; /* Wait queue pointer */ - spinlock_t rehash_lock; - struct list_head rehash_list; + spinlock_t lookup_lock; + struct list_head active_list; + struct list_head expiring_list; + struct rcu_head rcu; }; static inline struct autofs_sb_info *autofs4_sbi(struct super_block *sb) @@ -131,59 +140,146 @@ static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry) filesystem without "magic".) */ static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) { - return sbi->catatonic || task_pgrp_nr(current) == sbi->oz_pgrp; + return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp; } /* Does a dentry have some pending activity? */ static inline int autofs4_ispending(struct dentry *dentry) { struct autofs_info *inf = autofs4_dentry_ino(dentry); - int pending = 0; - if (dentry->d_flags & DCACHE_AUTOFS_PENDING) + if (inf->flags & AUTOFS_INF_PENDING) return 1; - if (inf) { - spin_lock(&inf->sbi->fs_lock); - pending = inf->flags & AUTOFS_INF_EXPIRING; - spin_unlock(&inf->sbi->fs_lock); - } - - return pending; -} + if (inf->flags & AUTOFS_INF_EXPIRING) + return 1; -static inline void autofs4_copy_atime(struct file *src, struct file *dst) -{ - dst->f_path.dentry->d_inode->i_atime = - src->f_path.dentry->d_inode->i_atime; - return; + return 0; } -struct inode *autofs4_get_inode(struct super_block *, struct autofs_info *); +struct inode *autofs4_get_inode(struct super_block *, umode_t); void autofs4_free_ino(struct autofs_info *); /* Expiration */ int is_autofs4_dentry(struct dentry *); +int autofs4_expire_wait(struct dentry *dentry); int autofs4_expire_run(struct super_block *, struct vfsmount *, struct autofs_sb_info *, struct autofs_packet_expire __user *); +int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int when); int autofs4_expire_multi(struct super_block *, struct vfsmount *, struct autofs_sb_info *, int __user *); +struct dentry *autofs4_expire_direct(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, int how); +struct dentry *autofs4_expire_indirect(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, int how); + +/* Device node initialization */ + +int autofs_dev_ioctl_init(void); +void autofs_dev_ioctl_exit(void); /* Operations structures */ extern const struct inode_operations autofs4_symlink_inode_operations; extern const struct inode_operations autofs4_dir_inode_operations; -extern const struct inode_operations autofs4_root_inode_operations; -extern const struct inode_operations autofs4_indirect_root_inode_operations; -extern const struct inode_operations autofs4_direct_root_inode_operations; extern const struct file_operations autofs4_dir_operations; extern const struct file_operations autofs4_root_operations; +extern const struct dentry_operations autofs4_dentry_operations; + +/* VFS automount flags management functions */ + +static inline void __managed_dentry_set_automount(struct dentry *dentry) +{ + dentry->d_flags |= DCACHE_NEED_AUTOMOUNT; +} + +static inline void managed_dentry_set_automount(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + __managed_dentry_set_automount(dentry); + spin_unlock(&dentry->d_lock); +} + +static inline void __managed_dentry_clear_automount(struct dentry *dentry) +{ + dentry->d_flags &= ~DCACHE_NEED_AUTOMOUNT; +} + +static inline void managed_dentry_clear_automount(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + __managed_dentry_clear_automount(dentry); + spin_unlock(&dentry->d_lock); +} + +static inline void __managed_dentry_set_transit(struct dentry *dentry) +{ + dentry->d_flags |= DCACHE_MANAGE_TRANSIT; +} + +static inline void managed_dentry_set_transit(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + __managed_dentry_set_transit(dentry); + spin_unlock(&dentry->d_lock); +} + +static inline void __managed_dentry_clear_transit(struct dentry *dentry) +{ + dentry->d_flags &= ~DCACHE_MANAGE_TRANSIT; +} + +static inline void managed_dentry_clear_transit(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + __managed_dentry_clear_transit(dentry); + spin_unlock(&dentry->d_lock); +} + +static inline void __managed_dentry_set_managed(struct dentry *dentry) +{ + dentry->d_flags |= (DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT); +} + +static inline void managed_dentry_set_managed(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + __managed_dentry_set_managed(dentry); + spin_unlock(&dentry->d_lock); +} + +static inline void __managed_dentry_clear_managed(struct dentry *dentry) +{ + dentry->d_flags &= ~(DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT); +} + +static inline void managed_dentry_clear_managed(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + __managed_dentry_clear_managed(dentry); + spin_unlock(&dentry->d_lock); +} /* Initializing function */ int autofs4_fill_super(struct super_block *, void *, int); -struct autofs_info *autofs4_init_ino(struct autofs_info *, struct autofs_sb_info *sbi, mode_t mode); +struct autofs_info *autofs4_new_ino(struct autofs_sb_info *); +void autofs4_clean_ino(struct autofs_info *); + +static inline int autofs_prepare_pipe(struct file *pipe) +{ + if (!pipe->f_op->write) + return -EINVAL; + if (!S_ISFIFO(file_inode(pipe)->i_mode)) + return -EINVAL; + /* We want a packet pipe */ + pipe->f_flags |= O_DIRECT; + return 0; +} /* Queue management functions */ @@ -191,19 +287,6 @@ int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify); int autofs4_wait_release(struct autofs_sb_info *,autofs_wqt_t,int); void autofs4_catatonic_mode(struct autofs_sb_info *); -static inline int autofs4_follow_mount(struct vfsmount **mnt, struct dentry **dentry) -{ - int res = 0; - - while (d_mountpoint(*dentry)) { - int followed = follow_down(mnt, dentry); - if (!followed) - break; - res = 1; - } - return res; -} - static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi) { return new_encode_dev(sbi->sb->s_dev); @@ -219,18 +302,41 @@ static inline int simple_positive(struct dentry *dentry) return dentry->d_inode && !d_unhashed(dentry); } -static inline int __simple_empty(struct dentry *dentry) +static inline void __autofs4_add_expiring(struct dentry *dentry) { - struct dentry *child; - int ret = 0; + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + if (ino) { + if (list_empty(&ino->expiring)) + list_add(&ino->expiring, &sbi->expiring_list); + } + return; +} - list_for_each_entry(child, &dentry->d_subdirs, d_u.d_child) - if (simple_positive(child)) - goto out; - ret = 1; -out: - return ret; +static inline void autofs4_add_expiring(struct dentry *dentry) +{ + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + if (ino) { + spin_lock(&sbi->lookup_lock); + if (list_empty(&ino->expiring)) + list_add(&ino->expiring, &sbi->expiring_list); + spin_unlock(&sbi->lookup_lock); + } + return; +} + +static inline void autofs4_del_expiring(struct dentry *dentry) +{ + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + if (ino) { + spin_lock(&sbi->lookup_lock); + if (!list_empty(&ino->expiring)) + list_del_init(&ino->expiring); + spin_unlock(&sbi->lookup_lock); + } + return; } -void autofs4_dentry_release(struct dentry *); extern void autofs4_kill_sb(struct super_block *); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c new file mode 100644 index 00000000000..5b570b6efa2 --- /dev/null +++ b/fs/autofs4/dev-ioctl.c @@ -0,0 +1,758 @@ +/* + * Copyright 2008 Red Hat, Inc. All rights reserved. + * Copyright 2008 Ian Kent <raven@themaw.net> + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + */ + +#include <linux/module.h> +#include <linux/vmalloc.h> +#include <linux/miscdevice.h> +#include <linux/init.h> +#include <linux/wait.h> +#include <linux/namei.h> +#include <linux/fcntl.h> +#include <linux/file.h> +#include <linux/fdtable.h> +#include <linux/sched.h> +#include <linux/compat.h> +#include <linux/syscalls.h> +#include <linux/magic.h> +#include <linux/dcache.h> +#include <linux/uaccess.h> +#include <linux/slab.h> + +#include "autofs_i.h" + +/* + * This module implements an interface for routing autofs ioctl control + * commands via a miscellaneous device file. + * + * The alternate interface is needed because we need to be able open + * an ioctl file descriptor on an autofs mount that may be covered by + * another mount. This situation arises when starting automount(8) + * or other user space daemon which uses direct mounts or offset + * mounts (used for autofs lazy mount/umount of nested mount trees), + * which have been left busy at at service shutdown. + */ + +#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) + +typedef int (*ioctl_fn)(struct file *, struct autofs_sb_info *, + struct autofs_dev_ioctl *); + +static int check_name(const char *name) +{ + if (!strchr(name, '/')) + return -EINVAL; + return 0; +} + +/* + * Check a string doesn't overrun the chunk of + * memory we copied from user land. + */ +static int invalid_str(char *str, size_t size) +{ + if (memchr(str, 0, size)) + return 0; + return -EINVAL; +} + +/* + * Check that the user compiled against correct version of autofs + * misc device code. + * + * As well as checking the version compatibility this always copies + * the kernel interface version out. + */ +static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) +{ + int err = 0; + + if ((AUTOFS_DEV_IOCTL_VERSION_MAJOR != param->ver_major) || + (AUTOFS_DEV_IOCTL_VERSION_MINOR < param->ver_minor)) { + AUTOFS_WARN("ioctl control interface version mismatch: " + "kernel(%u.%u), user(%u.%u), cmd(%d)", + AUTOFS_DEV_IOCTL_VERSION_MAJOR, + AUTOFS_DEV_IOCTL_VERSION_MINOR, + param->ver_major, param->ver_minor, cmd); + err = -EINVAL; + } + + /* Fill in the kernel version. */ + param->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; + param->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; + + return err; +} + +/* + * Copy parameter control struct, including a possible path allocated + * at the end of the struct. + */ +static struct autofs_dev_ioctl *copy_dev_ioctl(struct autofs_dev_ioctl __user *in) +{ + struct autofs_dev_ioctl tmp; + + if (copy_from_user(&tmp, in, sizeof(tmp))) + return ERR_PTR(-EFAULT); + + if (tmp.size < sizeof(tmp)) + return ERR_PTR(-EINVAL); + + if (tmp.size > (PATH_MAX + sizeof(tmp))) + return ERR_PTR(-ENAMETOOLONG); + + return memdup_user(in, tmp.size); +} + +static inline void free_dev_ioctl(struct autofs_dev_ioctl *param) +{ + kfree(param); + return; +} + +/* + * Check sanity of parameter control fields and if a path is present + * check that it is terminated and contains at least one "/". + */ +static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) +{ + int err; + + err = check_dev_ioctl_version(cmd, param); + if (err) { + AUTOFS_WARN("invalid device control module version " + "supplied for cmd(0x%08x)", cmd); + goto out; + } + + if (param->size > sizeof(*param)) { + err = invalid_str(param->path, param->size - sizeof(*param)); + if (err) { + AUTOFS_WARN( + "path string terminator missing for cmd(0x%08x)", + cmd); + goto out; + } + + err = check_name(param->path); + if (err) { + AUTOFS_WARN("invalid path supplied for cmd(0x%08x)", + cmd); + goto out; + } + } + + err = 0; +out: + return err; +} + +/* + * Get the autofs super block info struct from the file opened on + * the autofs mount point. + */ +static struct autofs_sb_info *autofs_dev_ioctl_sbi(struct file *f) +{ + struct autofs_sb_info *sbi = NULL; + struct inode *inode; + + if (f) { + inode = file_inode(f); + sbi = autofs4_sbi(inode->i_sb); + } + return sbi; +} + +/* Return autofs module protocol version */ +static int autofs_dev_ioctl_protover(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + param->protover.version = sbi->version; + return 0; +} + +/* Return autofs module protocol sub version */ +static int autofs_dev_ioctl_protosubver(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + param->protosubver.sub_version = sbi->sub_version; + return 0; +} + +/* Find the topmost mount satisfying test() */ +static int find_autofs_mount(const char *pathname, + struct path *res, + int test(struct path *path, void *data), + void *data) +{ + struct path path; + int err = kern_path_mountpoint(AT_FDCWD, pathname, &path, 0); + if (err) + return err; + err = -ENOENT; + while (path.dentry == path.mnt->mnt_root) { + if (path.dentry->d_sb->s_magic == AUTOFS_SUPER_MAGIC) { + if (test(&path, data)) { + path_get(&path); + *res = path; + err = 0; + break; + } + } + if (!follow_up(&path)) + break; + } + path_put(&path); + return err; +} + +static int test_by_dev(struct path *path, void *p) +{ + return path->dentry->d_sb->s_dev == *(dev_t *)p; +} + +static int test_by_type(struct path *path, void *p) +{ + struct autofs_info *ino = autofs4_dentry_ino(path->dentry); + return ino && ino->sbi->type & *(unsigned *)p; +} + +/* + * Open a file descriptor on the autofs mount point corresponding + * to the given path and device number (aka. new_encode_dev(sb->s_dev)). + */ +static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid) +{ + int err, fd; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (likely(fd >= 0)) { + struct file *filp; + struct path path; + + err = find_autofs_mount(name, &path, test_by_dev, &devid); + if (err) + goto out; + + /* + * Find autofs super block that has the device number + * corresponding to the autofs fs we want to open. + */ + + filp = dentry_open(&path, O_RDONLY, current_cred()); + path_put(&path); + if (IS_ERR(filp)) { + err = PTR_ERR(filp); + goto out; + } + + fd_install(fd, filp); + } + + return fd; + +out: + put_unused_fd(fd); + return err; +} + +/* Open a file descriptor on an autofs mount point */ +static int autofs_dev_ioctl_openmount(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + const char *path; + dev_t devid; + int err, fd; + + /* param->path has already been checked */ + if (!param->openmount.devid) + return -EINVAL; + + param->ioctlfd = -1; + + path = param->path; + devid = new_decode_dev(param->openmount.devid); + + err = 0; + fd = autofs_dev_ioctl_open_mountpoint(path, devid); + if (unlikely(fd < 0)) { + err = fd; + goto out; + } + + param->ioctlfd = fd; +out: + return err; +} + +/* Close file descriptor allocated above (user can also use close(2)). */ +static int autofs_dev_ioctl_closemount(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + return sys_close(param->ioctlfd); +} + +/* + * Send "ready" status for an existing wait (either a mount or an expire + * request). + */ +static int autofs_dev_ioctl_ready(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + autofs_wqt_t token; + + token = (autofs_wqt_t) param->ready.token; + return autofs4_wait_release(sbi, token, 0); +} + +/* + * Send "fail" status for an existing wait (either a mount or an expire + * request). + */ +static int autofs_dev_ioctl_fail(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + autofs_wqt_t token; + int status; + + token = (autofs_wqt_t) param->fail.token; + status = param->fail.status ? param->fail.status : -ENOENT; + return autofs4_wait_release(sbi, token, status); +} + +/* + * Set the pipe fd for kernel communication to the daemon. + * + * Normally this is set at mount using an option but if we + * are reconnecting to a busy mount then we need to use this + * to tell the autofs mount about the new kernel pipe fd. In + * order to protect mounts against incorrectly setting the + * pipefd we also require that the autofs mount be catatonic. + * + * This also sets the process group id used to identify the + * controlling process (eg. the owning automount(8) daemon). + */ +static int autofs_dev_ioctl_setpipefd(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + int pipefd; + int err = 0; + struct pid *new_pid = NULL; + + if (param->setpipefd.pipefd == -1) + return -EINVAL; + + pipefd = param->setpipefd.pipefd; + + mutex_lock(&sbi->wq_mutex); + if (!sbi->catatonic) { + mutex_unlock(&sbi->wq_mutex); + return -EBUSY; + } else { + struct file *pipe; + + new_pid = get_task_pid(current, PIDTYPE_PGID); + + if (ns_of_pid(new_pid) != ns_of_pid(sbi->oz_pgrp)) { + AUTOFS_WARN("Not allowed to change PID namespace"); + err = -EINVAL; + goto out; + } + + pipe = fget(pipefd); + if (!pipe) { + err = -EBADF; + goto out; + } + if (autofs_prepare_pipe(pipe) < 0) { + err = -EPIPE; + fput(pipe); + goto out; + } + swap(sbi->oz_pgrp, new_pid); + sbi->pipefd = pipefd; + sbi->pipe = pipe; + sbi->catatonic = 0; + } +out: + put_pid(new_pid); + mutex_unlock(&sbi->wq_mutex); + return err; +} + +/* + * Make the autofs mount point catatonic, no longer responsive to + * mount requests. Also closes the kernel pipe file descriptor. + */ +static int autofs_dev_ioctl_catatonic(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + autofs4_catatonic_mode(sbi); + return 0; +} + +/* Set the autofs mount timeout */ +static int autofs_dev_ioctl_timeout(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + unsigned long timeout; + + timeout = param->timeout.timeout; + param->timeout.timeout = sbi->exp_timeout / HZ; + sbi->exp_timeout = timeout * HZ; + return 0; +} + +/* + * Return the uid and gid of the last request for the mount + * + * When reconstructing an autofs mount tree with active mounts + * we need to re-connect to mounts that may have used the original + * process uid and gid (or string variations of them) for mount + * lookups within the map entry. + */ +static int autofs_dev_ioctl_requester(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + struct autofs_info *ino; + struct path path; + dev_t devid; + int err = -ENOENT; + + if (param->size <= sizeof(*param)) { + err = -EINVAL; + goto out; + } + + devid = sbi->sb->s_dev; + + param->requester.uid = param->requester.gid = -1; + + err = find_autofs_mount(param->path, &path, test_by_dev, &devid); + if (err) + goto out; + + ino = autofs4_dentry_ino(path.dentry); + if (ino) { + err = 0; + autofs4_expire_wait(path.dentry); + spin_lock(&sbi->fs_lock); + param->requester.uid = from_kuid_munged(current_user_ns(), ino->uid); + param->requester.gid = from_kgid_munged(current_user_ns(), ino->gid); + spin_unlock(&sbi->fs_lock); + } + path_put(&path); +out: + return err; +} + +/* + * Call repeatedly until it returns -EAGAIN, meaning there's nothing + * more that can be done. + */ +static int autofs_dev_ioctl_expire(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + struct vfsmount *mnt; + int how; + + how = param->expire.how; + mnt = fp->f_path.mnt; + + return autofs4_do_expire_multi(sbi->sb, mnt, sbi, how); +} + +/* Check if autofs mount point is in use */ +static int autofs_dev_ioctl_askumount(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + param->askumount.may_umount = 0; + if (may_umount(fp->f_path.mnt)) + param->askumount.may_umount = 1; + return 0; +} + +/* + * Check if the given path is a mountpoint. + * + * If we are supplied with the file descriptor of an autofs + * mount we're looking for a specific mount. In this case + * the path is considered a mountpoint if it is itself a + * mountpoint or contains a mount, such as a multi-mount + * without a root mount. In this case we return 1 if the + * path is a mount point and the super magic of the covering + * mount if there is one or 0 if it isn't a mountpoint. + * + * If we aren't supplied with a file descriptor then we + * lookup the path and check if it is the root of a mount. + * If a type is given we are looking for a particular autofs + * mount and if we don't find a match we return fail. If the + * located path is the root of a mount we return 1 along with + * the super magic of the mount or 0 otherwise. + * + * In both cases the the device number (as returned by + * new_encode_dev()) is also returned. + */ +static int autofs_dev_ioctl_ismountpoint(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + struct path path; + const char *name; + unsigned int type; + unsigned int devid, magic; + int err = -ENOENT; + + if (param->size <= sizeof(*param)) { + err = -EINVAL; + goto out; + } + + name = param->path; + type = param->ismountpoint.in.type; + + param->ismountpoint.out.devid = devid = 0; + param->ismountpoint.out.magic = magic = 0; + + if (!fp || param->ioctlfd == -1) { + if (autofs_type_any(type)) + err = kern_path_mountpoint(AT_FDCWD, + name, &path, LOOKUP_FOLLOW); + else + err = find_autofs_mount(name, &path, + test_by_type, &type); + if (err) + goto out; + devid = new_encode_dev(path.dentry->d_sb->s_dev); + err = 0; + if (path.mnt->mnt_root == path.dentry) { + err = 1; + magic = path.dentry->d_sb->s_magic; + } + } else { + dev_t dev = sbi->sb->s_dev; + + err = find_autofs_mount(name, &path, test_by_dev, &dev); + if (err) + goto out; + + devid = new_encode_dev(dev); + + err = have_submounts(path.dentry); + + if (follow_down_one(&path)) + magic = path.dentry->d_sb->s_magic; + } + + param->ismountpoint.out.devid = devid; + param->ismountpoint.out.magic = magic; + path_put(&path); +out: + return err; +} + +/* + * Our range of ioctl numbers isn't 0 based so we need to shift + * the array index by _IOC_NR(AUTOFS_CTL_IOC_FIRST) for the table + * lookup. + */ +#define cmd_idx(cmd) (cmd - _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST)) + +static ioctl_fn lookup_dev_ioctl(unsigned int cmd) +{ + static struct { + int cmd; + ioctl_fn fn; + } _ioctls[] = { + {cmd_idx(AUTOFS_DEV_IOCTL_VERSION_CMD), NULL}, + {cmd_idx(AUTOFS_DEV_IOCTL_PROTOVER_CMD), + autofs_dev_ioctl_protover}, + {cmd_idx(AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD), + autofs_dev_ioctl_protosubver}, + {cmd_idx(AUTOFS_DEV_IOCTL_OPENMOUNT_CMD), + autofs_dev_ioctl_openmount}, + {cmd_idx(AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD), + autofs_dev_ioctl_closemount}, + {cmd_idx(AUTOFS_DEV_IOCTL_READY_CMD), + autofs_dev_ioctl_ready}, + {cmd_idx(AUTOFS_DEV_IOCTL_FAIL_CMD), + autofs_dev_ioctl_fail}, + {cmd_idx(AUTOFS_DEV_IOCTL_SETPIPEFD_CMD), + autofs_dev_ioctl_setpipefd}, + {cmd_idx(AUTOFS_DEV_IOCTL_CATATONIC_CMD), + autofs_dev_ioctl_catatonic}, + {cmd_idx(AUTOFS_DEV_IOCTL_TIMEOUT_CMD), + autofs_dev_ioctl_timeout}, + {cmd_idx(AUTOFS_DEV_IOCTL_REQUESTER_CMD), + autofs_dev_ioctl_requester}, + {cmd_idx(AUTOFS_DEV_IOCTL_EXPIRE_CMD), + autofs_dev_ioctl_expire}, + {cmd_idx(AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD), + autofs_dev_ioctl_askumount}, + {cmd_idx(AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD), + autofs_dev_ioctl_ismountpoint} + }; + unsigned int idx = cmd_idx(cmd); + + return (idx >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[idx].fn; +} + +/* ioctl dispatcher */ +static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __user *user) +{ + struct autofs_dev_ioctl *param; + struct file *fp; + struct autofs_sb_info *sbi; + unsigned int cmd_first, cmd; + ioctl_fn fn = NULL; + int err = 0; + + /* only root can play with this */ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + cmd_first = _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST); + cmd = _IOC_NR(command); + + if (_IOC_TYPE(command) != _IOC_TYPE(AUTOFS_DEV_IOCTL_IOC_FIRST) || + cmd - cmd_first >= AUTOFS_DEV_IOCTL_IOC_COUNT) { + return -ENOTTY; + } + + /* Copy the parameters into kernel space. */ + param = copy_dev_ioctl(user); + if (IS_ERR(param)) + return PTR_ERR(param); + + err = validate_dev_ioctl(command, param); + if (err) + goto out; + + /* The validate routine above always sets the version */ + if (cmd == AUTOFS_DEV_IOCTL_VERSION_CMD) + goto done; + + fn = lookup_dev_ioctl(cmd); + if (!fn) { + AUTOFS_WARN("unknown command 0x%08x", command); + return -ENOTTY; + } + + fp = NULL; + sbi = NULL; + + /* + * For obvious reasons the openmount can't have a file + * descriptor yet. We don't take a reference to the + * file during close to allow for immediate release. + */ + if (cmd != AUTOFS_DEV_IOCTL_OPENMOUNT_CMD && + cmd != AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD) { + fp = fget(param->ioctlfd); + if (!fp) { + if (cmd == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) + goto cont; + err = -EBADF; + goto out; + } + + sbi = autofs_dev_ioctl_sbi(fp); + if (!sbi || sbi->magic != AUTOFS_SBI_MAGIC) { + err = -EINVAL; + fput(fp); + goto out; + } + + /* + * Admin needs to be able to set the mount catatonic in + * order to be able to perform the re-open. + */ + if (!autofs4_oz_mode(sbi) && + cmd != AUTOFS_DEV_IOCTL_CATATONIC_CMD) { + err = -EACCES; + fput(fp); + goto out; + } + } +cont: + err = fn(fp, sbi, param); + + if (fp) + fput(fp); +done: + if (err >= 0 && copy_to_user(user, param, AUTOFS_DEV_IOCTL_SIZE)) + err = -EFAULT; +out: + free_dev_ioctl(param); + return err; +} + +static long autofs_dev_ioctl(struct file *file, uint command, ulong u) +{ + int err; + err = _autofs_dev_ioctl(command, (struct autofs_dev_ioctl __user *) u); + return (long) err; +} + +#ifdef CONFIG_COMPAT +static long autofs_dev_ioctl_compat(struct file *file, uint command, ulong u) +{ + return (long) autofs_dev_ioctl(file, command, (ulong) compat_ptr(u)); +} +#else +#define autofs_dev_ioctl_compat NULL +#endif + +static const struct file_operations _dev_ioctl_fops = { + .unlocked_ioctl = autofs_dev_ioctl, + .compat_ioctl = autofs_dev_ioctl_compat, + .owner = THIS_MODULE, + .llseek = noop_llseek, +}; + +static struct miscdevice _autofs_dev_ioctl_misc = { + .minor = AUTOFS_MINOR, + .name = AUTOFS_DEVICE_NAME, + .fops = &_dev_ioctl_fops +}; + +MODULE_ALIAS_MISCDEV(AUTOFS_MINOR); +MODULE_ALIAS("devname:autofs"); + +/* Register/deregister misc character device */ +int __init autofs_dev_ioctl_init(void) +{ + int r; + + r = misc_register(&_autofs_dev_ioctl_misc); + if (r) { + AUTOFS_ERROR("misc_register failed for control device"); + return r; + } + + return 0; +} + +void autofs_dev_ioctl_exit(void) +{ + misc_deregister(&_autofs_dev_ioctl_misc); + return; +} + diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index d96e5c14a9c..394e90b02c5 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -26,10 +26,6 @@ static inline int autofs4_can_expire(struct dentry *dentry, if (ino == NULL) return 0; - /* No point expiring a pending mount */ - if (dentry->d_flags & DCACHE_AUTOFS_PENDING) - return 0; - if (!do_now) { /* Too young to die */ if (!timeout || time_after(ino->last_used + timeout, now)) @@ -48,23 +44,27 @@ static inline int autofs4_can_expire(struct dentry *dentry, static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry) { struct dentry *top = dentry; + struct path path = {.mnt = mnt, .dentry = dentry}; int status = 1; DPRINTK("dentry %p %.*s", dentry, (int)dentry->d_name.len, dentry->d_name.name); - mntget(mnt); - dget(dentry); + path_get(&path); - if (!autofs4_follow_mount(&mnt, &dentry)) + if (!follow_down_one(&path)) goto done; - /* This is an autofs submount, we can't expire it */ - if (is_autofs4_dentry(dentry)) - goto done; + if (is_autofs4_dentry(path.dentry)) { + struct autofs_sb_info *sbi = autofs4_sbi(path.dentry->d_sb); + + /* This is an autofs submount, we can't expire it */ + if (autofs_type_indirect(sbi->type)) + goto done; + } /* Update the expiry counter if fs is busy */ - if (!may_umount_tree(mnt)) { + if (!may_umount_tree(path.mnt)) { struct autofs_info *ino = autofs4_dentry_ino(top); ino->last_used = jiffies; goto done; @@ -73,30 +73,118 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry) status = 0; done: DPRINTK("returning = %d", status); - mntput(mnt); - dput(dentry); + path_put(&path); return status; } /* - * Calculate next entry in top down tree traversal. - * From next_mnt in namespace.c - elegant. + * Calculate and dget next entry in the subdirs list under root. */ -static struct dentry *next_dentry(struct dentry *p, struct dentry *root) +static struct dentry *get_next_positive_subdir(struct dentry *prev, + struct dentry *root) { - struct list_head *next = p->d_subdirs.next; + struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); + struct list_head *next; + struct dentry *q; + + spin_lock(&sbi->lookup_lock); + spin_lock(&root->d_lock); + + if (prev) + next = prev->d_u.d_child.next; + else { + prev = dget_dlock(root); + next = prev->d_subdirs.next; + } +cont: + if (next == &root->d_subdirs) { + spin_unlock(&root->d_lock); + spin_unlock(&sbi->lookup_lock); + dput(prev); + return NULL; + } + + q = list_entry(next, struct dentry, d_u.d_child); + + spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); + /* Already gone or negative dentry (under construction) - try next */ + if (!d_count(q) || !simple_positive(q)) { + spin_unlock(&q->d_lock); + next = q->d_u.d_child.next; + goto cont; + } + dget_dlock(q); + spin_unlock(&q->d_lock); + spin_unlock(&root->d_lock); + spin_unlock(&sbi->lookup_lock); + + dput(prev); + + return q; +} + +/* + * Calculate and dget next entry in top down tree traversal. + */ +static struct dentry *get_next_positive_dentry(struct dentry *prev, + struct dentry *root) +{ + struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); + struct list_head *next; + struct dentry *p, *ret; + + if (prev == NULL) + return dget(root); + + spin_lock(&sbi->lookup_lock); +relock: + p = prev; + spin_lock(&p->d_lock); +again: + next = p->d_subdirs.next; if (next == &p->d_subdirs) { while (1) { - if (p == root) + struct dentry *parent; + + if (p == root) { + spin_unlock(&p->d_lock); + spin_unlock(&sbi->lookup_lock); + dput(prev); return NULL; + } + + parent = p->d_parent; + if (!spin_trylock(&parent->d_lock)) { + spin_unlock(&p->d_lock); + cpu_relax(); + goto relock; + } + spin_unlock(&p->d_lock); next = p->d_u.d_child.next; - if (next != &p->d_parent->d_subdirs) + p = parent; + if (next != &parent->d_subdirs) break; - p = p->d_parent; } } - return list_entry(next, struct dentry, d_u.d_child); + ret = list_entry(next, struct dentry, d_u.d_child); + + spin_lock_nested(&ret->d_lock, DENTRY_D_LOCK_NESTED); + /* Negative dentry - try next */ + if (!simple_positive(ret)) { + spin_unlock(&p->d_lock); + lock_set_subclass(&ret->d_lock.dep_map, 0, _RET_IP_); + p = ret; + goto again; + } + dget_dlock(ret); + spin_unlock(&ret->d_lock); + spin_unlock(&p->d_lock); + spin_unlock(&sbi->lookup_lock); + + dput(prev); + + return ret; } /* @@ -146,18 +234,11 @@ static int autofs4_tree_busy(struct vfsmount *mnt, if (!simple_positive(top)) return 1; - spin_lock(&dcache_lock); - for (p = top; p; p = next_dentry(p, top)) { - /* Negative dentry - give up */ - if (!simple_positive(p)) - continue; - + p = NULL; + while ((p = get_next_positive_dentry(p, top))) { DPRINTK("dentry %p %.*s", p, (int) p->d_name.len, p->d_name.name); - p = dget(p); - spin_unlock(&dcache_lock); - /* * Is someone visiting anywhere in the subtree ? * If there's no mount we need to check the usage @@ -186,16 +267,13 @@ static int autofs4_tree_busy(struct vfsmount *mnt, else ino_count++; - if (atomic_read(&p->d_count) > ino_count) { + if (d_count(p) > ino_count) { top_ino->last_used = jiffies; dput(p); return 1; } } - dput(p); - spin_lock(&dcache_lock); } - spin_unlock(&dcache_lock); /* Timeout of a tree mount is ultimately determined by its top dentry */ if (!autofs4_can_expire(top, timeout, do_now)) @@ -214,44 +292,34 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt, DPRINTK("parent %p %.*s", parent, (int)parent->d_name.len, parent->d_name.name); - spin_lock(&dcache_lock); - for (p = parent; p; p = next_dentry(p, parent)) { - /* Negative dentry - give up */ - if (!simple_positive(p)) - continue; - + p = NULL; + while ((p = get_next_positive_dentry(p, parent))) { DPRINTK("dentry %p %.*s", p, (int) p->d_name.len, p->d_name.name); - p = dget(p); - spin_unlock(&dcache_lock); - if (d_mountpoint(p)) { /* Can we umount this guy */ if (autofs4_mount_busy(mnt, p)) - goto cont; + continue; /* Can we expire this guy */ if (autofs4_can_expire(p, timeout, do_now)) return p; } -cont: - dput(p); - spin_lock(&dcache_lock); } - spin_unlock(&dcache_lock); return NULL; } /* Check if we can expire a direct mount (possibly a tree) */ -static struct dentry *autofs4_expire_direct(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, - int how) +struct dentry *autofs4_expire_direct(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, + int how) { unsigned long timeout; struct dentry *root = dget(sb->s_root); int do_now = how & AUTOFS_EXP_IMMEDIATE; + struct autofs_info *ino; if (!root) return NULL; @@ -259,16 +327,19 @@ static struct dentry *autofs4_expire_direct(struct super_block *sb, now = jiffies; timeout = sbi->exp_timeout; - /* Lock the tree as we must expire as a whole */ spin_lock(&sbi->fs_lock); + ino = autofs4_dentry_ino(root); + /* No point expiring a pending mount */ + if (ino->flags & AUTOFS_INF_PENDING) + goto out; if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { struct autofs_info *ino = autofs4_dentry_ino(root); - - /* Set this flag early to catch sys_chdir and the like */ ino->flags |= AUTOFS_INF_EXPIRING; + init_completion(&ino->expire_complete); spin_unlock(&sbi->fs_lock); return root; } +out: spin_unlock(&sbi->fs_lock); dput(root); @@ -281,17 +352,19 @@ static struct dentry *autofs4_expire_direct(struct super_block *sb, * - it is unused by any user process * - it has been unused for exp_timeout time */ -static struct dentry *autofs4_expire_indirect(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, - int how) +struct dentry *autofs4_expire_indirect(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, + int how) { unsigned long timeout; struct dentry *root = sb->s_root; + struct dentry *dentry; struct dentry *expired = NULL; - struct list_head *next; int do_now = how & AUTOFS_EXP_IMMEDIATE; int exp_leaves = how & AUTOFS_EXP_LEAVES; + struct autofs_info *ino; + unsigned int ino_count; if (!root) return NULL; @@ -299,22 +372,13 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb, now = jiffies; timeout = sbi->exp_timeout; - spin_lock(&dcache_lock); - next = root->d_subdirs.next; - - /* On exit from the loop expire is set to a dgot dentry - * to expire or it's NULL */ - while ( next != &root->d_subdirs ) { - struct dentry *dentry = list_entry(next, struct dentry, d_u.d_child); - - /* Negative dentry - give up */ - if (!simple_positive(dentry)) { - next = next->next; - continue; - } - - dentry = dget(dentry); - spin_unlock(&dcache_lock); + dentry = NULL; + while ((dentry = get_next_positive_subdir(dentry, root))) { + spin_lock(&sbi->fs_lock); + ino = autofs4_dentry_ino(dentry); + /* No point expiring a pending mount */ + if (ino->flags & AUTOFS_INF_PENDING) + goto next; /* * Case 1: (i) indirect mount or top level pseudo direct mount @@ -333,7 +397,21 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb, /* Can we expire this guy */ if (autofs4_can_expire(dentry, timeout, do_now)) { expired = dentry; - break; + goto found; + } + goto next; + } + + if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) { + DPRINTK("checking symlink %p %.*s", + dentry, (int)dentry->d_name.len, dentry->d_name.name); + /* + * A symlink can't be "busy" in the usual sense so + * just check last used for expire timeout. + */ + if (autofs4_can_expire(dentry, timeout, do_now)) { + expired = dentry; + goto found; } goto next; } @@ -343,46 +421,80 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb, /* Case 2: tree mount, expire iff entire tree is not busy */ if (!exp_leaves) { - /* Lock the tree as we must expire as a whole */ - spin_lock(&sbi->fs_lock); - if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) { - struct autofs_info *inf = autofs4_dentry_ino(dentry); + /* Path walk currently on this dentry? */ + ino_count = atomic_read(&ino->count) + 1; + if (d_count(dentry) > ino_count) + goto next; - /* Set this flag early to catch sys_chdir and the like */ - inf->flags |= AUTOFS_INF_EXPIRING; - spin_unlock(&sbi->fs_lock); + if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) { expired = dentry; - break; + goto found; } - spin_unlock(&sbi->fs_lock); /* * Case 3: pseudo direct mount, expire individual leaves * (autofs-4.1). */ } else { + /* Path walk currently on this dentry? */ + ino_count = atomic_read(&ino->count) + 1; + if (d_count(dentry) > ino_count) + goto next; + expired = autofs4_check_leaves(mnt, dentry, timeout, do_now); if (expired) { dput(dentry); - break; + goto found; } } next: - dput(dentry); - spin_lock(&dcache_lock); - next = next->next; + spin_unlock(&sbi->fs_lock); } + return NULL; + +found: + DPRINTK("returning %p %.*s", + expired, (int)expired->d_name.len, expired->d_name.name); + ino = autofs4_dentry_ino(expired); + ino->flags |= AUTOFS_INF_EXPIRING; + init_completion(&ino->expire_complete); + spin_unlock(&sbi->fs_lock); + spin_lock(&sbi->lookup_lock); + spin_lock(&expired->d_parent->d_lock); + spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED); + list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); + spin_unlock(&expired->d_lock); + spin_unlock(&expired->d_parent->d_lock); + spin_unlock(&sbi->lookup_lock); + return expired; +} - if (expired) { - DPRINTK("returning %p %.*s", - expired, (int)expired->d_name.len, expired->d_name.name); - spin_lock(&dcache_lock); - list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child); - spin_unlock(&dcache_lock); - return expired; +int autofs4_expire_wait(struct dentry *dentry) +{ + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + int status; + + /* Block on any pending expire */ + spin_lock(&sbi->fs_lock); + if (ino->flags & AUTOFS_INF_EXPIRING) { + spin_unlock(&sbi->fs_lock); + + DPRINTK("waiting for expire %p name=%.*s", + dentry, dentry->d_name.len, dentry->d_name.name); + + status = autofs4_wait(sbi, dentry, NFY_NONE); + wait_for_completion(&ino->expire_complete); + + DPRINTK("expire done status=%d", status); + + if (d_unhashed(dentry)) + return -EAGAIN; + + return status; } - spin_unlock(&dcache_lock); + spin_unlock(&sbi->fs_lock); - return NULL; + return 0; } /* Perform an expiry operation */ @@ -392,7 +504,9 @@ int autofs4_expire_run(struct super_block *sb, struct autofs_packet_expire __user *pkt_p) { struct autofs_packet_expire pkt; + struct autofs_info *ino; struct dentry *dentry; + int ret = 0; memset(&pkt,0,sizeof pkt); @@ -408,39 +522,55 @@ int autofs4_expire_run(struct super_block *sb, dput(dentry); if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) ) - return -EFAULT; + ret = -EFAULT; - return 0; + spin_lock(&sbi->fs_lock); + ino = autofs4_dentry_ino(dentry); + ino->flags &= ~AUTOFS_INF_EXPIRING; + complete_all(&ino->expire_complete); + spin_unlock(&sbi->fs_lock); + + return ret; } -/* Call repeatedly until it returns -EAGAIN, meaning there's nothing - more to be done */ -int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt, - struct autofs_sb_info *sbi, int __user *arg) +int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int when) { struct dentry *dentry; int ret = -EAGAIN; - int do_now = 0; - if (arg && get_user(do_now, arg)) - return -EFAULT; - - if (sbi->type & AUTOFS_TYPE_DIRECT) - dentry = autofs4_expire_direct(sb, mnt, sbi, do_now); + if (autofs_type_trigger(sbi->type)) + dentry = autofs4_expire_direct(sb, mnt, sbi, when); else - dentry = autofs4_expire_indirect(sb, mnt, sbi, do_now); + dentry = autofs4_expire_indirect(sb, mnt, sbi, when); if (dentry) { struct autofs_info *ino = autofs4_dentry_ino(dentry); /* This is synchronous because it makes the daemon a little easier */ - ino->flags |= AUTOFS_INF_EXPIRING; ret = autofs4_wait(sbi, dentry, NFY_EXPIRE); + + spin_lock(&sbi->fs_lock); ino->flags &= ~AUTOFS_INF_EXPIRING; + complete_all(&ino->expire_complete); + spin_unlock(&sbi->fs_lock); dput(dentry); } return ret; } +/* Call repeatedly until it returns -EAGAIN, meaning there's nothing + more to be done */ +int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int __user *arg) +{ + int do_now = 0; + + if (arg && get_user(do_now, arg)) + return -EFAULT; + + return autofs4_do_expire_multi(sb, mnt, sbi, do_now); +} + diff --git a/fs/autofs4/init.c b/fs/autofs4/init.c index 723a1c5e361..b3db517e89e 100644 --- a/fs/autofs4/init.c +++ b/fs/autofs4/init.c @@ -14,26 +14,36 @@ #include <linux/init.h> #include "autofs_i.h" -static int autofs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, struct vfsmount *mnt) +static struct dentry *autofs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) { - return get_sb_nodev(fs_type, flags, data, autofs4_fill_super, mnt); + return mount_nodev(fs_type, flags, data, autofs4_fill_super); } static struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", - .get_sb = autofs_get_sb, + .mount = autofs_mount, .kill_sb = autofs4_kill_sb, }; +MODULE_ALIAS_FS("autofs"); static int __init init_autofs4_fs(void) { - return register_filesystem(&autofs_fs_type); + int err; + + autofs_dev_ioctl_init(); + + err = register_filesystem(&autofs_fs_type); + if (err) + autofs_dev_ioctl_exit(); + + return err; } static void __exit exit_autofs4_fs(void) { + autofs_dev_ioctl_exit(); unregister_filesystem(&autofs_fs_type); } diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 2fdcf5e1d23..1c55388ae63 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -22,130 +22,30 @@ #include "autofs_i.h" #include <linux/module.h> -static void ino_lnkfree(struct autofs_info *ino) +struct autofs_info *autofs4_new_ino(struct autofs_sb_info *sbi) { - kfree(ino->u.symlink); - ino->u.symlink = NULL; + struct autofs_info *ino = kzalloc(sizeof(*ino), GFP_KERNEL); + if (ino) { + INIT_LIST_HEAD(&ino->active); + INIT_LIST_HEAD(&ino->expiring); + ino->last_used = jiffies; + ino->sbi = sbi; + } + return ino; } -struct autofs_info *autofs4_init_ino(struct autofs_info *ino, - struct autofs_sb_info *sbi, mode_t mode) +void autofs4_clean_ino(struct autofs_info *ino) { - int reinit = 1; - - if (ino == NULL) { - reinit = 0; - ino = kmalloc(sizeof(*ino), GFP_KERNEL); - } - - if (ino == NULL) - return NULL; - - ino->flags = 0; - ino->mode = mode; - ino->inode = NULL; - ino->dentry = NULL; - ino->size = 0; - - INIT_LIST_HEAD(&ino->rehash); - + ino->uid = GLOBAL_ROOT_UID; + ino->gid = GLOBAL_ROOT_GID; ino->last_used = jiffies; - atomic_set(&ino->count, 0); - - ino->sbi = sbi; - - if (reinit && ino->free) - (ino->free)(ino); - - memset(&ino->u, 0, sizeof(ino->u)); - - ino->free = NULL; - - if (S_ISLNK(mode)) - ino->free = ino_lnkfree; - - return ino; } void autofs4_free_ino(struct autofs_info *ino) { - struct autofs_info *p_ino; - - if (ino->dentry) { - ino->dentry->d_fsdata = NULL; - if (ino->dentry->d_inode) { - struct dentry *parent = ino->dentry->d_parent; - if (atomic_dec_and_test(&ino->count)) { - p_ino = autofs4_dentry_ino(parent); - if (p_ino && parent != ino->dentry) - atomic_dec(&p_ino->count); - } - dput(ino->dentry); - } - ino->dentry = NULL; - } - if (ino->free) - (ino->free)(ino); kfree(ino); } -/* - * Deal with the infamous "Busy inodes after umount ..." message. - * - * Clean up the dentry tree. This happens with autofs if the user - * space program goes away due to a SIGKILL, SIGSEGV etc. - */ -static void autofs4_force_release(struct autofs_sb_info *sbi) -{ - struct dentry *this_parent = sbi->sb->s_root; - struct list_head *next; - - if (!sbi->sb->s_root) - return; - - spin_lock(&dcache_lock); -repeat: - next = this_parent->d_subdirs.next; -resume: - while (next != &this_parent->d_subdirs) { - struct dentry *dentry = list_entry(next, struct dentry, d_u.d_child); - - /* Negative dentry - don`t care */ - if (!simple_positive(dentry)) { - next = next->next; - continue; - } - - if (!list_empty(&dentry->d_subdirs)) { - this_parent = dentry; - goto repeat; - } - - next = next->next; - spin_unlock(&dcache_lock); - - DPRINTK("dentry %p %.*s", - dentry, (int)dentry->d_name.len, dentry->d_name.name); - - dput(dentry); - spin_lock(&dcache_lock); - } - - if (this_parent != sbi->sb->s_root) { - struct dentry *dentry = this_parent; - - next = this_parent->d_u.d_child.next; - this_parent = this_parent->d_parent; - spin_unlock(&dcache_lock); - DPRINTK("parent dentry %p %.*s", - dentry, (int)dentry->d_name.len, dentry->d_name.name); - dput(dentry); - spin_lock(&dcache_lock); - goto resume; - } - spin_unlock(&dcache_lock); -} - void autofs4_kill_sb(struct super_block *sb) { struct autofs_sb_info *sbi = autofs4_sbi(sb); @@ -156,44 +56,41 @@ void autofs4_kill_sb(struct super_block *sb) * just call kill_anon_super when we are called from * deactivate_super. */ - if (!sbi) - goto out_kill_sb; - - if (!sbi->catatonic) - autofs4_catatonic_mode(sbi); /* Free wait queues, close pipe */ - - /* Clean up and release dangling references */ - autofs4_force_release(sbi); - - sb->s_fs_info = NULL; - kfree(sbi); + if (sbi) { + /* Free wait queues, close pipe */ + autofs4_catatonic_mode(sbi); + put_pid(sbi->oz_pgrp); + } -out_kill_sb: DPRINTK("shutting down"); - kill_anon_super(sb); + kill_litter_super(sb); + if (sbi) + kfree_rcu(sbi, rcu); } -static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt) +static int autofs4_show_options(struct seq_file *m, struct dentry *root) { - struct autofs_sb_info *sbi = autofs4_sbi(mnt->mnt_sb); - struct inode *root_inode = mnt->mnt_sb->s_root->d_inode; + struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); + struct inode *root_inode = root->d_sb->s_root->d_inode; if (!sbi) return 0; seq_printf(m, ",fd=%d", sbi->pipefd); - if (root_inode->i_uid != 0) - seq_printf(m, ",uid=%u", root_inode->i_uid); - if (root_inode->i_gid != 0) - seq_printf(m, ",gid=%u", root_inode->i_gid); - seq_printf(m, ",pgrp=%d", sbi->oz_pgrp); + if (!uid_eq(root_inode->i_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, root_inode->i_uid)); + if (!gid_eq(root_inode->i_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, root_inode->i_gid)); + seq_printf(m, ",pgrp=%d", pid_vnr(sbi->oz_pgrp)); seq_printf(m, ",timeout=%lu", sbi->exp_timeout/HZ); seq_printf(m, ",minproto=%d", sbi->min_proto); seq_printf(m, ",maxproto=%d", sbi->max_proto); - if (sbi->type & AUTOFS_TYPE_OFFSET) + if (autofs_type_offset(sbi->type)) seq_printf(m, ",offset"); - else if (sbi->type & AUTOFS_TYPE_DIRECT) + else if (autofs_type_direct(sbi->type)) seq_printf(m, ",direct"); else seq_printf(m, ",indirect"); @@ -201,15 +98,22 @@ static int autofs4_show_options(struct seq_file *m, struct vfsmount *mnt) return 0; } +static void autofs4_evict_inode(struct inode *inode) +{ + clear_inode(inode); + kfree(inode->i_private); +} + static const struct super_operations autofs4_sops = { .statfs = simple_statfs, .show_options = autofs4_show_options, + .evict_inode = autofs4_evict_inode, }; enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto, Opt_indirect, Opt_direct, Opt_offset}; -static match_table_t tokens = { +static const match_table_t tokens = { {Opt_fd, "fd=%u"}, {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, @@ -222,16 +126,16 @@ static match_table_t tokens = { {Opt_err, NULL} }; -static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, - pid_t *pgrp, unsigned int *type, int *minproto, int *maxproto) +static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid, + int *pgrp, bool *pgrp_set, unsigned int *type, + int *minproto, int *maxproto) { char *p; substring_t args[MAX_OPT_ARGS]; int option; - *uid = current->uid; - *gid = current->gid; - *pgrp = task_pgrp_nr(current); + *uid = current_uid(); + *gid = current_gid(); *minproto = AUTOFS_MIN_PROTO_VERSION; *maxproto = AUTOFS_MAX_PROTO_VERSION; @@ -255,17 +159,22 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, case Opt_uid: if (match_int(args, &option)) return 1; - *uid = option; + *uid = make_kuid(current_user_ns(), option); + if (!uid_valid(*uid)) + return 1; break; case Opt_gid: if (match_int(args, &option)) return 1; - *gid = option; + *gid = make_kgid(current_user_ns(), option); + if (!gid_valid(*gid)) + return 1; break; case Opt_pgrp: if (match_int(args, &option)) return 1; *pgrp = option; + *pgrp_set = true; break; case Opt_minproto: if (match_int(args, &option)) @@ -278,13 +187,13 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, *maxproto = option; break; case Opt_indirect: - *type = AUTOFS_TYPE_INDIRECT; + set_autofs_type_indirect(type); break; case Opt_direct: - *type = AUTOFS_TYPE_DIRECT; + set_autofs_type_direct(type); break; case Opt_offset: - *type = AUTOFS_TYPE_DIRECT | AUTOFS_TYPE_OFFSET; + set_autofs_type_offset(type); break; default: return 1; @@ -293,21 +202,6 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, return (*pipefd < 0); } -static struct autofs_info *autofs4_mkroot(struct autofs_sb_info *sbi) -{ - struct autofs_info *ino; - - ino = autofs4_init_ino(NULL, sbi, S_IFDIR | 0755); - if (!ino) - return NULL; - - return ino; -} - -static struct dentry_operations autofs4_sb_dentry_operations = { - .d_release = autofs4_dentry_release, -}; - int autofs4_fill_super(struct super_block *s, void *data, int silent) { struct inode * root_inode; @@ -316,10 +210,13 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) int pipefd; struct autofs_sb_info *sbi; struct autofs_info *ino; + int pgrp = 0; + bool pgrp_set = false; + int ret = -EINVAL; sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) - goto fail_unlock; + return -ENOMEM; DPRINTK("starting up, sbi = %p",sbi); s->s_fs_info = sbi; @@ -328,54 +225,67 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->pipe = NULL; sbi->catatonic = 1; sbi->exp_timeout = 0; - sbi->oz_pgrp = task_pgrp_nr(current); + sbi->oz_pgrp = NULL; sbi->sb = s; sbi->version = 0; sbi->sub_version = 0; - sbi->type = 0; + set_autofs_type_indirect(&sbi->type); sbi->min_proto = 0; sbi->max_proto = 0; mutex_init(&sbi->wq_mutex); + mutex_init(&sbi->pipe_mutex); spin_lock_init(&sbi->fs_lock); sbi->queues = NULL; - spin_lock_init(&sbi->rehash_lock); - INIT_LIST_HEAD(&sbi->rehash_list); + spin_lock_init(&sbi->lookup_lock); + INIT_LIST_HEAD(&sbi->active_list); + INIT_LIST_HEAD(&sbi->expiring_list); s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = AUTOFS_SUPER_MAGIC; s->s_op = &autofs4_sops; + s->s_d_op = &autofs4_dentry_operations; s->s_time_gran = 1; /* * Get the root inode and dentry, but defer checking for errors. */ - ino = autofs4_mkroot(sbi); - if (!ino) + ino = autofs4_new_ino(sbi); + if (!ino) { + ret = -ENOMEM; goto fail_free; - root_inode = autofs4_get_inode(s, ino); - if (!root_inode) - goto fail_ino; - - root = d_alloc_root(root_inode); + } + root_inode = autofs4_get_inode(s, S_IFDIR | 0755); + root = d_make_root(root_inode); if (!root) - goto fail_iput; + goto fail_ino; pipe = NULL; - root->d_op = &autofs4_sb_dentry_operations; root->d_fsdata = ino; /* Can this call block? */ if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid, - &sbi->oz_pgrp, &sbi->type, &sbi->min_proto, - &sbi->max_proto)) { + &pgrp, &pgrp_set, &sbi->type, &sbi->min_proto, + &sbi->max_proto)) { printk("autofs: called with bogus options\n"); goto fail_dput; } + if (pgrp_set) { + sbi->oz_pgrp = find_get_pid(pgrp); + if (!sbi->oz_pgrp) { + pr_warn("autofs: could not find process group %d\n", + pgrp); + goto fail_dput; + } + } else { + sbi->oz_pgrp = get_task_pid(current, PIDTYPE_PGID); + } + + if (autofs_type_trigger(sbi->type)) + __managed_dentry_set_managed(root); + root_inode->i_fop = &autofs4_root_operations; - root_inode->i_op = sbi->type & AUTOFS_TYPE_DIRECT ? - &autofs4_direct_root_inode_operations : - &autofs4_indirect_root_inode_operations; + root_inode->i_op = &autofs4_dir_inode_operations; /* Couldn't this be tested earlier? */ if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION || @@ -394,14 +304,15 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) sbi->version = sbi->max_proto; sbi->sub_version = AUTOFS_PROTO_SUBVERSION; - DPRINTK("pipe fd = %d, pgrp = %u", pipefd, sbi->oz_pgrp); + DPRINTK("pipe fd = %d, pgrp = %u", pipefd, pid_nr(sbi->oz_pgrp)); pipe = fget(pipefd); - + if (!pipe) { printk("autofs: could not open pipe file descriptor\n"); goto fail_dput; } - if (!pipe->f_op || !pipe->f_op->write) + ret = autofs_prepare_pipe(pipe); + if (ret < 0) goto fail_fput; sbi->pipe = pipe; sbi->pipefd = pipefd; @@ -423,44 +334,35 @@ fail_fput: fail_dput: dput(root); goto fail_free; -fail_iput: - printk("autofs: get root dentry failed\n"); - iput(root_inode); fail_ino: kfree(ino); fail_free: + put_pid(sbi->oz_pgrp); kfree(sbi); s->s_fs_info = NULL; -fail_unlock: - return -EINVAL; + return ret; } -struct inode *autofs4_get_inode(struct super_block *sb, - struct autofs_info *inf) +struct inode *autofs4_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (inode == NULL) return NULL; - inf->inode = inode; - inode->i_mode = inf->mode; + inode->i_mode = mode; if (sb->s_root) { inode->i_uid = sb->s_root->d_inode->i_uid; inode->i_gid = sb->s_root->d_inode->i_gid; - } else { - inode->i_uid = 0; - inode->i_gid = 0; } - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_ino = get_next_ino(); - if (S_ISDIR(inf->mode)) { - inode->i_nlink = 2; + if (S_ISDIR(mode)) { + set_nlink(inode, 2); inode->i_op = &autofs4_dir_inode_operations; inode->i_fop = &autofs4_dir_operations; - } else if (S_ISLNK(inf->mode)) { - inode->i_size = inf->size; + } else if (S_ISLNK(mode)) { inode->i_op = &autofs4_symlink_inode_operations; } diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index a54a946a50a..cc87c1abac9 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -15,38 +15,49 @@ #include <linux/capability.h> #include <linux/errno.h> #include <linux/stat.h> +#include <linux/slab.h> #include <linux/param.h> #include <linux/time.h> +#include <linux/compat.h> +#include <linux/mutex.h> + #include "autofs_i.h" static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *); static int autofs4_dir_unlink(struct inode *,struct dentry *); static int autofs4_dir_rmdir(struct inode *,struct dentry *); -static int autofs4_dir_mkdir(struct inode *,struct dentry *,int); -static int autofs4_root_ioctl(struct inode *, struct file *,unsigned int,unsigned long); +static int autofs4_dir_mkdir(struct inode *,struct dentry *,umode_t); +static long autofs4_root_ioctl(struct file *,unsigned int,unsigned long); +#ifdef CONFIG_COMPAT +static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long); +#endif static int autofs4_dir_open(struct inode *inode, struct file *file); -static int autofs4_dir_close(struct inode *inode, struct file *file); -static int autofs4_dir_readdir(struct file * filp, void * dirent, filldir_t filldir); -static int autofs4_root_readdir(struct file * filp, void * dirent, filldir_t filldir); -static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *); -static void *autofs4_follow_link(struct dentry *, struct nameidata *); +static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int); +static struct vfsmount *autofs4_d_automount(struct path *); +static int autofs4_d_manage(struct dentry *, bool); +static void autofs4_dentry_release(struct dentry *); const struct file_operations autofs4_root_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .read = generic_read_dir, - .readdir = autofs4_root_readdir, - .ioctl = autofs4_root_ioctl, + .iterate = dcache_readdir, + .llseek = dcache_dir_lseek, + .unlocked_ioctl = autofs4_root_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = autofs4_root_compat_ioctl, +#endif }; const struct file_operations autofs4_dir_operations = { .open = autofs4_dir_open, - .release = autofs4_dir_close, + .release = dcache_dir_close, .read = generic_read_dir, - .readdir = autofs4_dir_readdir, + .iterate = dcache_readdir, + .llseek = dcache_dir_lseek, }; -const struct inode_operations autofs4_indirect_root_inode_operations = { +const struct inode_operations autofs4_dir_inode_operations = { .lookup = autofs4_lookup, .unlink = autofs4_dir_unlink, .symlink = autofs4_dir_symlink, @@ -54,58 +65,48 @@ const struct inode_operations autofs4_indirect_root_inode_operations = { .rmdir = autofs4_dir_rmdir, }; -const struct inode_operations autofs4_direct_root_inode_operations = { - .lookup = autofs4_lookup, - .unlink = autofs4_dir_unlink, - .mkdir = autofs4_dir_mkdir, - .rmdir = autofs4_dir_rmdir, - .follow_link = autofs4_follow_link, -}; - -const struct inode_operations autofs4_dir_inode_operations = { - .lookup = autofs4_lookup, - .unlink = autofs4_dir_unlink, - .symlink = autofs4_dir_symlink, - .mkdir = autofs4_dir_mkdir, - .rmdir = autofs4_dir_rmdir, +const struct dentry_operations autofs4_dentry_operations = { + .d_automount = autofs4_d_automount, + .d_manage = autofs4_d_manage, + .d_release = autofs4_dentry_release, }; -static int autofs4_root_readdir(struct file *file, void *dirent, - filldir_t filldir) +static void autofs4_add_active(struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(file->f_path.dentry->d_sb); - int oz_mode = autofs4_oz_mode(sbi); - - DPRINTK("called, filp->f_pos = %lld", file->f_pos); - - /* - * Don't set reghost flag if: - * 1) f_pos is larger than zero -- we've already been here. - * 2) we haven't even enabled reghosting in the 1st place. - * 3) this is the daemon doing a readdir - */ - if (oz_mode && file->f_pos == 0 && sbi->reghost_enabled) - sbi->needs_reghost = 1; - - DPRINTK("needs_reghost = %d", sbi->needs_reghost); + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + if (ino) { + spin_lock(&sbi->lookup_lock); + if (!ino->active_count) { + if (list_empty(&ino->active)) + list_add(&ino->active, &sbi->active_list); + } + ino->active_count++; + spin_unlock(&sbi->lookup_lock); + } + return; +} - return dcache_readdir(file, dirent, filldir); +static void autofs4_del_active(struct dentry *dentry) +{ + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + if (ino) { + spin_lock(&sbi->lookup_lock); + ino->active_count--; + if (!ino->active_count) { + if (!list_empty(&ino->active)) + list_del_init(&ino->active); + } + spin_unlock(&sbi->lookup_lock); + } + return; } static int autofs4_dir_open(struct inode *inode, struct file *file) { struct dentry *dentry = file->f_path.dentry; - struct vfsmount *mnt = file->f_path.mnt; struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct dentry *cursor; - int status; - - status = dcache_dir_open(inode, file); - if (status) - goto out; - - cursor = file->private_data; - cursor->d_fsdata = NULL; DPRINTK("file=%p dentry=%p %.*s", file, dentry, dentry->d_name.len, dentry->d_name.name); @@ -113,579 +114,404 @@ static int autofs4_dir_open(struct inode *inode, struct file *file) if (autofs4_oz_mode(sbi)) goto out; - if (autofs4_ispending(dentry)) { - DPRINTK("dentry busy"); - dcache_dir_close(inode, file); - status = -EBUSY; - goto out; + /* + * An empty directory in an autofs file system is always a + * mount point. The daemon must have failed to mount this + * during lookup so it doesn't exist. This can happen, for + * example, if user space returns an incorrect status for a + * mount request. Otherwise we're doing a readdir on the + * autofs file system so just let the libfs routines handle + * it. + */ + spin_lock(&sbi->lookup_lock); + if (!d_mountpoint(dentry) && simple_empty(dentry)) { + spin_unlock(&sbi->lookup_lock); + return -ENOENT; } + spin_unlock(&sbi->lookup_lock); - status = -ENOENT; - if (!d_mountpoint(dentry) && dentry->d_op && dentry->d_op->d_revalidate) { - struct nameidata nd; - int empty, ret; +out: + return dcache_dir_open(inode, file); +} - /* In case there are stale directory dentrys from a failed mount */ - spin_lock(&dcache_lock); - empty = list_empty(&dentry->d_subdirs); - spin_unlock(&dcache_lock); +static void autofs4_dentry_release(struct dentry *de) +{ + struct autofs_info *ino = autofs4_dentry_ino(de); + struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb); - if (!empty) - d_invalidate(dentry); + DPRINTK("releasing %p", de); - nd.flags = LOOKUP_DIRECTORY; - ret = (dentry->d_op->d_revalidate)(dentry, &nd); + if (!ino) + return; - if (ret <= 0) { - if (ret < 0) - status = ret; - dcache_dir_close(inode, file); - goto out; - } + if (sbi) { + spin_lock(&sbi->lookup_lock); + if (!list_empty(&ino->active)) + list_del(&ino->active); + if (!list_empty(&ino->expiring)) + list_del(&ino->expiring); + spin_unlock(&sbi->lookup_lock); } - if (d_mountpoint(dentry)) { - struct file *fp = NULL; - struct vfsmount *fp_mnt = mntget(mnt); - struct dentry *fp_dentry = dget(dentry); - - if (!autofs4_follow_mount(&fp_mnt, &fp_dentry)) { - dput(fp_dentry); - mntput(fp_mnt); - dcache_dir_close(inode, file); - goto out; - } - - fp = dentry_open(fp_dentry, fp_mnt, file->f_flags); - status = PTR_ERR(fp); - if (IS_ERR(fp)) { - dcache_dir_close(inode, file); - goto out; - } - cursor->d_fsdata = fp; - } - return 0; -out: - return status; + autofs4_free_ino(ino); } -static int autofs4_dir_close(struct inode *inode, struct file *file) +static struct dentry *autofs4_lookup_active(struct dentry *dentry) { - struct dentry *dentry = file->f_path.dentry; struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct dentry *cursor = file->private_data; - int status = 0; + struct dentry *parent = dentry->d_parent; + struct qstr *name = &dentry->d_name; + unsigned int len = name->len; + unsigned int hash = name->hash; + const unsigned char *str = name->name; + struct list_head *p, *head; - DPRINTK("file=%p dentry=%p %.*s", - file, dentry, dentry->d_name.len, dentry->d_name.name); + spin_lock(&sbi->lookup_lock); + head = &sbi->active_list; + list_for_each(p, head) { + struct autofs_info *ino; + struct dentry *active; + struct qstr *qstr; - if (autofs4_oz_mode(sbi)) - goto out; + ino = list_entry(p, struct autofs_info, active); + active = ino->dentry; - if (autofs4_ispending(dentry)) { - DPRINTK("dentry busy"); - status = -EBUSY; - goto out; - } + spin_lock(&active->d_lock); + + /* Already gone? */ + if ((int) d_count(active) <= 0) + goto next; + + qstr = &active->d_name; - if (d_mountpoint(dentry)) { - struct file *fp = cursor->d_fsdata; - if (!fp) { - status = -ENOENT; - goto out; + if (active->d_name.hash != hash) + goto next; + if (active->d_parent != parent) + goto next; + + if (qstr->len != len) + goto next; + if (memcmp(qstr->name, str, len)) + goto next; + + if (d_unhashed(active)) { + dget_dlock(active); + spin_unlock(&active->d_lock); + spin_unlock(&sbi->lookup_lock); + return active; } - filp_close(fp, current->files); +next: + spin_unlock(&active->d_lock); } -out: - dcache_dir_close(inode, file); - return status; + spin_unlock(&sbi->lookup_lock); + + return NULL; } -static int autofs4_dir_readdir(struct file *file, void *dirent, filldir_t filldir) +static struct dentry *autofs4_lookup_expiring(struct dentry *dentry) { - struct dentry *dentry = file->f_path.dentry; struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct dentry *cursor = file->private_data; - int status; + struct dentry *parent = dentry->d_parent; + struct qstr *name = &dentry->d_name; + unsigned int len = name->len; + unsigned int hash = name->hash; + const unsigned char *str = name->name; + struct list_head *p, *head; - DPRINTK("file=%p dentry=%p %.*s", - file, dentry, dentry->d_name.len, dentry->d_name.name); + spin_lock(&sbi->lookup_lock); + head = &sbi->expiring_list; + list_for_each(p, head) { + struct autofs_info *ino; + struct dentry *expiring; + struct qstr *qstr; - if (autofs4_oz_mode(sbi)) - goto out; + ino = list_entry(p, struct autofs_info, expiring); + expiring = ino->dentry; - if (autofs4_ispending(dentry)) { - DPRINTK("dentry busy"); - return -EBUSY; - } + spin_lock(&expiring->d_lock); - if (d_mountpoint(dentry)) { - struct file *fp = cursor->d_fsdata; + /* We've already been dentry_iput or unlinked */ + if (!expiring->d_inode) + goto next; - if (!fp) - return -ENOENT; + qstr = &expiring->d_name; - if (!fp->f_op || !fp->f_op->readdir) - goto out; + if (expiring->d_name.hash != hash) + goto next; + if (expiring->d_parent != parent) + goto next; - status = vfs_readdir(fp, filldir, dirent); - file->f_pos = fp->f_pos; - if (status) - autofs4_copy_atime(file, fp); - return status; + if (qstr->len != len) + goto next; + if (memcmp(qstr->name, str, len)) + goto next; + + if (d_unhashed(expiring)) { + dget_dlock(expiring); + spin_unlock(&expiring->d_lock); + spin_unlock(&sbi->lookup_lock); + return expiring; + } +next: + spin_unlock(&expiring->d_lock); } -out: - return dcache_readdir(file, dirent, filldir); + spin_unlock(&sbi->lookup_lock); + + return NULL; } -static int try_to_fill_dentry(struct dentry *dentry, int flags) +static int autofs4_mount_wait(struct dentry *dentry) { struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); int status = 0; - /* Block on any pending expiry here; invalidate the dentry - when expiration is done to trigger mount request with a new - dentry */ - if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) { - DPRINTK("waiting for expire %p name=%.*s", - dentry, dentry->d_name.len, dentry->d_name.name); - - status = autofs4_wait(sbi, dentry, NFY_NONE); + if (ino->flags & AUTOFS_INF_PENDING) { + DPRINTK("waiting for mount name=%.*s", + dentry->d_name.len, dentry->d_name.name); + status = autofs4_wait(sbi, dentry, NFY_MOUNT); + DPRINTK("mount wait done status=%d", status); + } + ino->last_used = jiffies; + return status; +} - DPRINTK("expire done status=%d", status); +static int do_expire_wait(struct dentry *dentry) +{ + struct dentry *expiring; + expiring = autofs4_lookup_expiring(dentry); + if (!expiring) + return autofs4_expire_wait(dentry); + else { /* - * If the directory still exists the mount request must - * continue otherwise it can't be followed at the right - * time during the walk. + * If we are racing with expire the request might not + * be quite complete, but the directory has been removed + * so it must have been successful, just wait for it. */ - status = d_invalidate(dentry); - if (status != -EBUSY) - return -EAGAIN; + autofs4_expire_wait(expiring); + autofs4_del_expiring(expiring); + dput(expiring); } + return 0; +} - DPRINTK("dentry=%p %.*s ino=%p", - dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode); +static struct dentry *autofs4_mountpoint_changed(struct path *path) +{ + struct dentry *dentry = path->dentry; + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); /* - * Wait for a pending mount, triggering one if there - * isn't one already + * If this is an indirect mount the dentry could have gone away + * as a result of an expire and a new one created. */ - if (dentry->d_inode == NULL) { - DPRINTK("waiting for mount name=%.*s", - dentry->d_name.len, dentry->d_name.name); - - status = autofs4_wait(sbi, dentry, NFY_MOUNT); - - DPRINTK("mount done status=%d", status); - - /* Turn this into a real negative dentry? */ - if (status == -ENOENT) { - spin_lock(&dentry->d_lock); - dentry->d_flags &= ~DCACHE_AUTOFS_PENDING; - spin_unlock(&dentry->d_lock); - return status; - } else if (status) { - /* Return a negative dentry, but leave it "pending" */ - return status; - } - /* Trigger mount for path component or follow link */ - } else if (flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY) || - current->link_count) { - DPRINTK("waiting for mount name=%.*s", - dentry->d_name.len, dentry->d_name.name); - - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_AUTOFS_PENDING; - spin_unlock(&dentry->d_lock); - status = autofs4_wait(sbi, dentry, NFY_MOUNT); - - DPRINTK("mount done status=%d", status); - - if (status) { - spin_lock(&dentry->d_lock); - dentry->d_flags &= ~DCACHE_AUTOFS_PENDING; - spin_unlock(&dentry->d_lock); - return status; - } - } - - /* Initialize expiry counter after successful mount */ - if (ino) + if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) { + struct dentry *parent = dentry->d_parent; + struct autofs_info *ino; + struct dentry *new = d_lookup(parent, &dentry->d_name); + if (!new) + return NULL; + ino = autofs4_dentry_ino(new); ino->last_used = jiffies; - - spin_lock(&dentry->d_lock); - dentry->d_flags &= ~DCACHE_AUTOFS_PENDING; - spin_unlock(&dentry->d_lock); - return status; + dput(path->dentry); + path->dentry = new; + } + return path->dentry; } -/* For autofs direct mounts the follow link triggers the mount */ -static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd) +static struct vfsmount *autofs4_d_automount(struct path *path) { + struct dentry *dentry = path->dentry; struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); - int oz_mode = autofs4_oz_mode(sbi); - unsigned int lookup_type; int status; - DPRINTK("dentry=%p %.*s oz_mode=%d nd->flags=%d", - dentry, dentry->d_name.len, dentry->d_name.name, oz_mode, - nd->flags); - - /* If it's our master or we shouldn't trigger a mount we're done */ - lookup_type = nd->flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY); - if (oz_mode || !lookup_type) - goto done; - - /* If an expire request is pending wait for it. */ - if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) { - DPRINTK("waiting for active request %p name=%.*s", - dentry, dentry->d_name.len, dentry->d_name.name); + DPRINTK("dentry=%p %.*s", + dentry, dentry->d_name.len, dentry->d_name.name); - status = autofs4_wait(sbi, dentry, NFY_NONE); + /* The daemon never triggers a mount. */ + if (autofs4_oz_mode(sbi)) + return NULL; - DPRINTK("request done status=%d", status); + /* + * If an expire request is pending everyone must wait. + * If the expire fails we're still mounted so continue + * the follow and return. A return of -EAGAIN (which only + * happens with indirect mounts) means the expire completed + * and the directory was removed, so just go ahead and try + * the mount. + */ + status = do_expire_wait(dentry); + if (status && status != -EAGAIN) + return NULL; + + /* Callback to the daemon to perform the mount or wait */ + spin_lock(&sbi->fs_lock); + if (ino->flags & AUTOFS_INF_PENDING) { + spin_unlock(&sbi->fs_lock); + status = autofs4_mount_wait(dentry); + if (status) + return ERR_PTR(status); + goto done; } /* - * If the dentry contains directories then it is an - * autofs multi-mount with no root mount offset. So - * don't try to mount it again. + * If the dentry is a symlink it's equivalent to a directory + * having d_mountpoint() true, so there's no need to call back + * to the daemon. */ - spin_lock(&dcache_lock); - if (!d_mountpoint(dentry) && __simple_empty(dentry)) { - spin_unlock(&dcache_lock); - - status = try_to_fill_dentry(dentry, 0); - if (status) - goto out_error; + if (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)) { + spin_unlock(&sbi->fs_lock); + goto done; + } + if (!d_mountpoint(dentry)) { /* - * The mount succeeded but if there is no root mount - * it must be an autofs multi-mount with no root offset - * so we don't need to follow the mount. + * It's possible that user space hasn't removed directories + * after umounting a rootless multi-mount, although it + * should. For v5 have_submounts() is sufficient to handle + * this because the leaves of the directory tree under the + * mount never trigger mounts themselves (they have an autofs + * trigger mount mounted on them). But v4 pseudo direct mounts + * do need the leaves to to trigger mounts. In this case we + * have no choice but to use the list_empty() check and + * require user space behave. */ - if (d_mountpoint(dentry)) { - if (!autofs4_follow_mount(&nd->path.mnt, - &nd->path.dentry)) { - status = -ENOENT; - goto out_error; + if (sbi->version > 4) { + if (have_submounts(dentry)) { + spin_unlock(&sbi->fs_lock); + goto done; + } + } else { + if (!simple_empty(dentry)) { + spin_unlock(&sbi->fs_lock); + goto done; } } - - goto done; + ino->flags |= AUTOFS_INF_PENDING; + spin_unlock(&sbi->fs_lock); + status = autofs4_mount_wait(dentry); + spin_lock(&sbi->fs_lock); + ino->flags &= ~AUTOFS_INF_PENDING; + if (status) { + spin_unlock(&sbi->fs_lock); + return ERR_PTR(status); + } } - spin_unlock(&dcache_lock); - + spin_unlock(&sbi->fs_lock); done: - return NULL; + /* Mount succeeded, check if we ended up with a new dentry */ + dentry = autofs4_mountpoint_changed(path); + if (!dentry) + return ERR_PTR(-ENOENT); -out_error: - path_put(&nd->path); - return ERR_PTR(status); + return NULL; } -/* - * Revalidate is called on every cache lookup. Some of those - * cache lookups may actually happen while the dentry is not - * yet completely filled in, and revalidate has to delay such - * lookups.. - */ -static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd) +static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk) { - struct inode *dir = dentry->d_parent->d_inode; - struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); - int oz_mode = autofs4_oz_mode(sbi); - int flags = nd ? nd->flags : 0; - int status = 1; - - /* Pending dentry */ - if (autofs4_ispending(dentry)) { - /* The daemon never causes a mount to trigger */ - if (oz_mode) - return 1; + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_info *ino = autofs4_dentry_ino(dentry); + int status; - /* - * A zero status is success otherwise we have a - * negative error code. - */ - status = try_to_fill_dentry(dentry, flags); - if (status == 0) - return 1; + DPRINTK("dentry=%p %.*s", + dentry, dentry->d_name.len, dentry->d_name.name); - /* - * A status of EAGAIN here means that the dentry has gone - * away while waiting for an expire to complete. If we are - * racing with expire lookup will wait for it so this must - * be a revalidate and we need to send it to lookup. - */ - if (status == -EAGAIN) + /* The daemon never waits. */ + if (autofs4_oz_mode(sbi)) { + if (rcu_walk) return 0; - - return status; - } - - /* Negative dentry.. invalidate if "old" */ - if (dentry->d_inode == NULL) + if (!d_mountpoint(dentry)) + return -EISDIR; return 0; - - /* Check for a non-mountpoint directory with no contents */ - spin_lock(&dcache_lock); - if (S_ISDIR(dentry->d_inode->i_mode) && - !d_mountpoint(dentry) && - __simple_empty(dentry)) { - DPRINTK("dentry=%p %.*s, emptydir", - dentry, dentry->d_name.len, dentry->d_name.name); - spin_unlock(&dcache_lock); - /* The daemon never causes a mount to trigger */ - if (oz_mode) - return 1; - - /* - * A zero status is success otherwise we have a - * negative error code. - */ - status = try_to_fill_dentry(dentry, flags); - if (status == 0) - return 1; - - return status; } - spin_unlock(&dcache_lock); - - return 1; -} - -void autofs4_dentry_release(struct dentry *de) -{ - struct autofs_info *inf; - - DPRINTK("releasing %p", de); - - inf = autofs4_dentry_ino(de); - de->d_fsdata = NULL; - - if (inf) { - struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb); - - if (sbi) { - spin_lock(&sbi->rehash_lock); - if (!list_empty(&inf->rehash)) - list_del(&inf->rehash); - spin_unlock(&sbi->rehash_lock); - } - - inf->dentry = NULL; - inf->inode = NULL; - - autofs4_free_ino(inf); - } -} - -/* For dentries of directories in the root dir */ -static struct dentry_operations autofs4_root_dentry_operations = { - .d_revalidate = autofs4_revalidate, - .d_release = autofs4_dentry_release, -}; - -/* For other dentries */ -static struct dentry_operations autofs4_dentry_operations = { - .d_revalidate = autofs4_revalidate, - .d_release = autofs4_dentry_release, -}; - -static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name) -{ - unsigned int len = name->len; - unsigned int hash = name->hash; - const unsigned char *str = name->name; - struct list_head *p, *head; - - spin_lock(&dcache_lock); - spin_lock(&sbi->rehash_lock); - head = &sbi->rehash_list; - list_for_each(p, head) { - struct autofs_info *ino; - struct dentry *dentry; - struct qstr *qstr; - - ino = list_entry(p, struct autofs_info, rehash); - dentry = ino->dentry; - spin_lock(&dentry->d_lock); + /* We need to sleep, so we need pathwalk to be in ref-mode */ + if (rcu_walk) + return -ECHILD; - /* Bad luck, we've already been dentry_iput */ - if (!dentry->d_inode) - goto next; - - qstr = &dentry->d_name; - - if (dentry->d_name.hash != hash) - goto next; - if (dentry->d_parent != parent) - goto next; + /* Wait for pending expires */ + do_expire_wait(dentry); - if (qstr->len != len) - goto next; - if (memcmp(qstr->name, str, len)) - goto next; + /* + * This dentry may be under construction so wait on mount + * completion. + */ + status = autofs4_mount_wait(dentry); + if (status) + return status; - if (d_unhashed(dentry)) { - struct autofs_info *ino = autofs4_dentry_ino(dentry); - struct inode *inode = dentry->d_inode; - - list_del_init(&ino->rehash); - dget(dentry); - /* - * Make the rehashed dentry negative so the VFS - * behaves as it should. - */ - if (inode) { - dentry->d_inode = NULL; - list_del_init(&dentry->d_alias); - spin_unlock(&dentry->d_lock); - spin_unlock(&sbi->rehash_lock); - spin_unlock(&dcache_lock); - iput(inode); - return dentry; - } - spin_unlock(&dentry->d_lock); - spin_unlock(&sbi->rehash_lock); - spin_unlock(&dcache_lock); - return dentry; - } -next: - spin_unlock(&dentry->d_lock); + spin_lock(&sbi->fs_lock); + /* + * If the dentry has been selected for expire while we slept + * on the lock then it might go away. We'll deal with that in + * ->d_automount() and wait on a new mount if the expire + * succeeds or return here if it doesn't (since there's no + * mount to follow with a rootless multi-mount). + */ + if (!(ino->flags & AUTOFS_INF_EXPIRING)) { + /* + * Any needed mounting has been completed and the path + * updated so check if this is a rootless multi-mount so + * we can avoid needless calls ->d_automount() and avoid + * an incorrect ELOOP error return. + */ + if ((!d_mountpoint(dentry) && !simple_empty(dentry)) || + (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode))) + status = -EISDIR; } - spin_unlock(&sbi->rehash_lock); - spin_unlock(&dcache_lock); + spin_unlock(&sbi->fs_lock); - return NULL; + return status; } /* Lookups in the root directory */ -static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) +static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct autofs_sb_info *sbi; - struct dentry *unhashed; - int oz_mode; + struct autofs_info *ino; + struct dentry *active; - DPRINTK("name = %.*s", - dentry->d_name.len, dentry->d_name.name); + DPRINTK("name = %.*s", dentry->d_name.len, dentry->d_name.name); /* File name too long to exist */ if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); sbi = autofs4_sbi(dir->i_sb); - oz_mode = autofs4_oz_mode(sbi); DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d", - current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode); + current->pid, task_pgrp_nr(current), sbi->catatonic, + autofs4_oz_mode(sbi)); - unhashed = autofs4_lookup_unhashed(sbi, dentry->d_parent, &dentry->d_name); - if (!unhashed) { - /* - * Mark the dentry incomplete but don't hash it. We do this - * to serialize our inode creation operations (symlink and - * mkdir) which prevents deadlock during the callback to - * the daemon. Subsequent user space lookups for the same - * dentry are placed on the wait queue while the daemon - * itself is allowed passage unresticted so the create - * operation itself can then hash the dentry. Finally, - * we check for the hashed dentry and return the newly - * hashed dentry. - */ - dentry->d_op = &autofs4_root_dentry_operations; - - dentry->d_fsdata = NULL; - d_instantiate(dentry, NULL); + active = autofs4_lookup_active(dentry); + if (active) { + return active; } else { - struct autofs_info *ino = autofs4_dentry_ino(unhashed); - DPRINTK("rehash %p with %p", dentry, unhashed); /* - * If we are racing with expire the request might not - * be quite complete but the directory has been removed - * so it must have been successful, so just wait for it. - * We need to ensure the AUTOFS_INF_EXPIRING flag is clear - * before continuing as revalidate may fail when calling - * try_to_fill_dentry (returning EAGAIN) if we don't. + * A dentry that is not within the root can never trigger a + * mount operation, unless the directory already exists, so we + * can return fail immediately. The daemon however does need + * to create directories within the file system. */ - while (ino && (ino->flags & AUTOFS_INF_EXPIRING)) { - DPRINTK("wait for incomplete expire %p name=%.*s", - unhashed, unhashed->d_name.len, - unhashed->d_name.name); - autofs4_wait(sbi, unhashed, NFY_NONE); - DPRINTK("request completed"); - } - dentry = unhashed; - } + if (!autofs4_oz_mode(sbi) && !IS_ROOT(dentry->d_parent)) + return ERR_PTR(-ENOENT); - if (!oz_mode) { - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_AUTOFS_PENDING; - spin_unlock(&dentry->d_lock); - } + /* Mark entries in the root as mount triggers */ + if (autofs_type_indirect(sbi->type) && IS_ROOT(dentry->d_parent)) + __managed_dentry_set_managed(dentry); - if (dentry->d_op && dentry->d_op->d_revalidate) { - mutex_unlock(&dir->i_mutex); - (dentry->d_op->d_revalidate)(dentry, nd); - mutex_lock(&dir->i_mutex); - } + ino = autofs4_new_ino(sbi); + if (!ino) + return ERR_PTR(-ENOMEM); - /* - * If we are still pending, check if we had to handle - * a signal. If so we can force a restart.. - */ - if (dentry->d_flags & DCACHE_AUTOFS_PENDING) { - /* See if we were interrupted */ - if (signal_pending(current)) { - sigset_t *sigset = ¤t->pending.signal; - if (sigismember (sigset, SIGKILL) || - sigismember (sigset, SIGQUIT) || - sigismember (sigset, SIGINT)) { - if (unhashed) - dput(unhashed); - return ERR_PTR(-ERESTARTNOINTR); - } - } - spin_lock(&dentry->d_lock); - dentry->d_flags &= ~DCACHE_AUTOFS_PENDING; - spin_unlock(&dentry->d_lock); - } + dentry->d_fsdata = ino; + ino->dentry = dentry; - /* - * If this dentry is unhashed, then we shouldn't honour this - * lookup. Returning ENOENT here doesn't do the right thing - * for all system calls, but it should be OK for the operations - * we permit from an autofs. - */ - if (!oz_mode && d_unhashed(dentry)) { - /* - * A user space application can (and has done in the past) - * remove and re-create this directory during the callback. - * This can leave us with an unhashed dentry, but a - * successful mount! So we need to perform another - * cached lookup in case the dentry now exists. - */ - struct dentry *parent = dentry->d_parent; - struct dentry *new = d_lookup(parent, &dentry->d_name); - if (new != NULL) - dentry = new; - else - dentry = ERR_PTR(-ENOENT); + autofs4_add_active(dentry); - if (unhashed) - dput(unhashed); - - return dentry; + d_instantiate(dentry, NULL); } - - if (unhashed) - return dentry; - return NULL; } @@ -697,6 +523,7 @@ static int autofs4_dir_symlink(struct inode *dir, struct autofs_info *ino = autofs4_dentry_ino(dentry); struct autofs_info *p_ino; struct inode *inode; + size_t size = strlen(symname); char *cp; DPRINTK("%s <- %.*s", symname, @@ -705,35 +532,34 @@ static int autofs4_dir_symlink(struct inode *dir, if (!autofs4_oz_mode(sbi)) return -EACCES; - ino = autofs4_init_ino(ino, sbi, S_IFLNK | 0555); - if (ino == NULL) - return -ENOSPC; + BUG_ON(!ino); - ino->size = strlen(symname); - ino->u.symlink = cp = kmalloc(ino->size + 1, GFP_KERNEL); + autofs4_clean_ino(ino); - if (cp == NULL) { - kfree(ino); - return -ENOSPC; - } + autofs4_del_active(dentry); + + cp = kmalloc(size + 1, GFP_KERNEL); + if (!cp) + return -ENOMEM; strcpy(cp, symname); - inode = autofs4_get_inode(dir->i_sb, ino); + inode = autofs4_get_inode(dir->i_sb, S_IFLNK | 0555); + if (!inode) { + kfree(cp); + if (!dentry->d_fsdata) + kfree(ino); + return -ENOMEM; + } + inode->i_private = cp; + inode->i_size = size; d_add(dentry, inode); - if (dir == dir->i_sb->s_root->d_inode) - dentry->d_op = &autofs4_root_dentry_operations; - else - dentry->d_op = &autofs4_dentry_operations; - - dentry->d_fsdata = ino; - ino->dentry = dget(dentry); + dget(dentry); atomic_inc(&ino->count); p_ino = autofs4_dentry_ino(dentry->d_parent); - if (p_ino && dentry->d_parent != dentry) + if (p_ino && !IS_ROOT(dentry)) atomic_inc(&p_ino->count); - ino->inode = inode; dir->i_mtime = CURRENT_TIME; @@ -747,9 +573,8 @@ static int autofs4_dir_symlink(struct inode *dir, * that the file no longer exists. However, doing that means that the * VFS layer can turn the dentry into a negative dentry. We don't want * this, because the unlink is probably the result of an expire. - * We simply d_drop it and add it to a rehash candidates list in the - * super block, which allows the dentry lookup to reuse it retaining - * the flags, such as expire in progress, in case we're racing with expire. + * We simply d_drop it and add it to a expiring list in the super block, + * which allows the dentry lookup to check for an incomplete expire. * * If a process is blocked on the dentry waiting for the expire to finish, * it will invalidate the dentry and try to mount with a new one. @@ -764,11 +589,11 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) /* This allows root to remove symlinks */ if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) - return -EACCES; + return -EPERM; if (atomic_dec_and_test(&ino->count)) { p_ino = autofs4_dentry_ino(dentry->d_parent); - if (p_ino && dentry->d_parent != dentry) + if (p_ino && !IS_ROOT(dentry)) atomic_dec(&p_ino->count); } dput(ino->dentry); @@ -778,18 +603,66 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) dir->i_mtime = CURRENT_TIME; - spin_lock(&dcache_lock); - spin_lock(&sbi->rehash_lock); - list_add(&ino->rehash, &sbi->rehash_list); - spin_unlock(&sbi->rehash_lock); - spin_lock(&dentry->d_lock); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - spin_unlock(&dcache_lock); + spin_lock(&sbi->lookup_lock); + __autofs4_add_expiring(dentry); + d_drop(dentry); + spin_unlock(&sbi->lookup_lock); return 0; } +/* + * Version 4 of autofs provides a pseudo direct mount implementation + * that relies on directories at the leaves of a directory tree under + * an indirect mount to trigger mounts. To allow for this we need to + * set the DMANAGED_AUTOMOUNT and DMANAGED_TRANSIT flags on the leaves + * of the directory tree. There is no need to clear the automount flag + * following a mount or restore it after an expire because these mounts + * are always covered. However, it is necessary to ensure that these + * flags are clear on non-empty directories to avoid unnecessary calls + * during path walks. + */ +static void autofs_set_leaf_automount_flags(struct dentry *dentry) +{ + struct dentry *parent; + + /* root and dentrys in the root are already handled */ + if (IS_ROOT(dentry->d_parent)) + return; + + managed_dentry_set_managed(dentry); + + parent = dentry->d_parent; + /* only consider parents below dentrys in the root */ + if (IS_ROOT(parent->d_parent)) + return; + managed_dentry_clear_managed(parent); + return; +} + +static void autofs_clear_leaf_automount_flags(struct dentry *dentry) +{ + struct list_head *d_child; + struct dentry *parent; + + /* flags for dentrys in the root are handled elsewhere */ + if (IS_ROOT(dentry->d_parent)) + return; + + managed_dentry_clear_managed(dentry); + + parent = dentry->d_parent; + /* only consider parents below dentrys in the root */ + if (IS_ROOT(parent->d_parent)) + return; + d_child = &dentry->d_u.d_child; + /* Set parent managed if it's becoming empty */ + if (d_child->next == &parent->d_subdirs && + d_child->prev == &parent->d_subdirs) + managed_dentry_set_managed(parent); + return; +} + static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) { struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); @@ -802,18 +675,17 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) if (!autofs4_oz_mode(sbi)) return -EACCES; - spin_lock(&dcache_lock); - if (!list_empty(&dentry->d_subdirs)) { - spin_unlock(&dcache_lock); + spin_lock(&sbi->lookup_lock); + if (!simple_empty(dentry)) { + spin_unlock(&sbi->lookup_lock); return -ENOTEMPTY; } - spin_lock(&sbi->rehash_lock); - list_add(&ino->rehash, &sbi->rehash_list); - spin_unlock(&sbi->rehash_lock); - spin_lock(&dentry->d_lock); - __d_drop(dentry); - spin_unlock(&dentry->d_lock); - spin_unlock(&dcache_lock); + __autofs4_add_expiring(dentry); + d_drop(dentry); + spin_unlock(&sbi->lookup_lock); + + if (sbi->version < 5) + autofs_clear_leaf_automount_flags(dentry); if (atomic_dec_and_test(&ino->count)) { p_ino = autofs4_dentry_ino(dentry->d_parent); @@ -830,7 +702,7 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) return 0; } -static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode) +static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); @@ -843,25 +715,25 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode) DPRINTK("dentry %p, creating %.*s", dentry, dentry->d_name.len, dentry->d_name.name); - ino = autofs4_init_ino(ino, sbi, S_IFDIR | 0555); - if (ino == NULL) - return -ENOSPC; + BUG_ON(!ino); + + autofs4_clean_ino(ino); - inode = autofs4_get_inode(dir->i_sb, ino); + autofs4_del_active(dentry); + + inode = autofs4_get_inode(dir->i_sb, S_IFDIR | 0555); + if (!inode) + return -ENOMEM; d_add(dentry, inode); - if (dir == dir->i_sb->s_root->d_inode) - dentry->d_op = &autofs4_root_dentry_operations; - else - dentry->d_op = &autofs4_dentry_operations; + if (sbi->version < 5) + autofs_set_leaf_automount_flags(dentry); - dentry->d_fsdata = ino; - ino->dentry = dget(dentry); + dget(dentry); atomic_inc(&ino->count); p_ino = autofs4_dentry_ino(dentry->d_parent); - if (p_ino && dentry->d_parent != dentry) + if (p_ino && !IS_ROOT(dentry)) atomic_inc(&p_ino->count); - ino->inode = inode; inc_nlink(dir); dir->i_mtime = CURRENT_TIME; @@ -869,6 +741,26 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode) } /* Get/set timeout ioctl() operation */ +#ifdef CONFIG_COMPAT +static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi, + compat_ulong_t __user *p) +{ + int rv; + unsigned long ntimeout; + + if ((rv = get_user(ntimeout, p)) || + (rv = put_user(sbi->exp_timeout/HZ, p))) + return rv; + + if (ntimeout > UINT_MAX/HZ) + sbi->exp_timeout = 0; + else + sbi->exp_timeout = ntimeout * HZ; + + return 0; +} +#endif + static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi, unsigned long __user *p) { @@ -900,44 +792,6 @@ static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, int __user } /* - * Tells the daemon whether we need to reghost or not. Also, clears - * the reghost_needed flag. - */ -static inline int autofs4_ask_reghost(struct autofs_sb_info *sbi, int __user *p) -{ - int status; - - DPRINTK("returning %d", sbi->needs_reghost); - - status = put_user(sbi->needs_reghost, p); - if (status) - return status; - - sbi->needs_reghost = 0; - return 0; -} - -/* - * Enable / Disable reghosting ioctl() operation - */ -static inline int autofs4_toggle_reghost(struct autofs_sb_info *sbi, int __user *p) -{ - int status; - int val; - - status = get_user(val, p); - - DPRINTK("reghost = %d", val); - - if (status) - return status; - - /* turn on/off reghosting, with the val */ - sbi->reghost_enabled = val; - return 0; -} - -/* * Tells the daemon whether it can umount the autofs mount. */ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p) @@ -961,8 +815,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p) int is_autofs4_dentry(struct dentry *dentry) { return dentry && dentry->d_inode && - (dentry->d_op == &autofs4_root_dentry_operations || - dentry->d_op == &autofs4_dentry_operations) && + dentry->d_op == &autofs4_dentry_operations && dentry->d_fsdata != NULL; } @@ -970,8 +823,8 @@ int is_autofs4_dentry(struct dentry *dentry) * ioctl()'s on the root directory is the chief method for the daemon to * generate kernel reactions */ -static int autofs4_root_ioctl(struct inode *inode, struct file *filp, - unsigned int cmd, unsigned long arg) +static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp, + unsigned int cmd, unsigned long arg) { struct autofs_sb_info *sbi = autofs4_sbi(inode->i_sb); void __user *p = (void __user *)arg; @@ -1000,11 +853,10 @@ static int autofs4_root_ioctl(struct inode *inode, struct file *filp, return autofs4_get_protosubver(sbi, p); case AUTOFS_IOC_SETTIMEOUT: return autofs4_get_set_timeout(sbi, p); - - case AUTOFS_IOC_TOGGLEREGHOST: - return autofs4_toggle_reghost(sbi, p); - case AUTOFS_IOC_ASKREGHOST: - return autofs4_ask_reghost(sbi, p); +#ifdef CONFIG_COMPAT + case AUTOFS_IOC_SETTIMEOUT32: + return autofs4_compat_get_set_timeout(sbi, p); +#endif case AUTOFS_IOC_ASKUMOUNT: return autofs4_ask_umount(filp->f_path.mnt, p); @@ -1020,3 +872,27 @@ static int autofs4_root_ioctl(struct inode *inode, struct file *filp, return -ENOSYS; } } + +static long autofs4_root_ioctl(struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg); +} + +#ifdef CONFIG_COMPAT +static long autofs4_root_compat_ioctl(struct file *filp, + unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + int ret; + + if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL) + ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg); + else + ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, + (unsigned long)compat_ptr(arg)); + + return ret; +} +#endif diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c index b4ea82934d2..1e8ea192be2 100644 --- a/fs/autofs4/symlink.c +++ b/fs/autofs4/symlink.c @@ -14,8 +14,11 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd) { + struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); struct autofs_info *ino = autofs4_dentry_ino(dentry); - nd_set_link(nd, (char *)ino->u.symlink); + if (ino && !autofs4_oz_mode(sbi)) + ino->last_used = jiffies; + nd_set_link(nd, dentry->d_inode->i_private); return NULL; } diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 1fe28e4754c..116fd38ee47 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -28,6 +28,12 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi) { struct autofs_wait_queue *wq, *nwq; + mutex_lock(&sbi->wq_mutex); + if (sbi->catatonic) { + mutex_unlock(&sbi->wq_mutex); + return; + } + DPRINTK("entering catatonic mode"); sbi->catatonic = 1; @@ -36,35 +42,39 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi) while (wq) { nwq = wq->next; wq->status = -ENOENT; /* Magic is gone - report failure */ - kfree(wq->name); - wq->name = NULL; + kfree(wq->name.name); + wq->name.name = NULL; + wq->wait_ctr--; wake_up_interruptible(&wq->queue); wq = nwq; } fput(sbi->pipe); /* Close the pipe */ sbi->pipe = NULL; + sbi->pipefd = -1; + mutex_unlock(&sbi->wq_mutex); } -static int autofs4_write(struct file *file, const void *addr, int bytes) +static int autofs4_write(struct autofs_sb_info *sbi, + struct file *file, const void *addr, int bytes) { unsigned long sigpipe, flags; mm_segment_t fs; const char *data = (const char *)addr; ssize_t wr = 0; - /** WARNING: this is not safe for writing more than PIPE_BUF bytes! **/ - sigpipe = sigismember(¤t->pending.signal, SIGPIPE); /* Save pointer to user space and point back to kernel space */ fs = get_fs(); set_fs(KERNEL_DS); + mutex_lock(&sbi->pipe_mutex); while (bytes && (wr = file->f_op->write(file,data,bytes,&file->f_pos)) > 0) { data += wr; bytes -= wr; } + mutex_unlock(&sbi->pipe_mutex); set_fs(fs); @@ -89,15 +99,17 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, union autofs_packet_union v4_pkt; union autofs_v5_packet_union v5_pkt; } pkt; + struct file *pipe = NULL; size_t pktsz; DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d", - wq->wait_queue_token, wq->len, wq->name, type); + (unsigned long) wq->wait_queue_token, wq->name.len, wq->name.name, type); memset(&pkt,0,sizeof pkt); /* For security reasons */ pkt.hdr.proto_version = sbi->version; pkt.hdr.type = type; + switch (type) { /* Kernel protocol v4 missing and expire packets */ case autofs_ptype_missing: @@ -107,9 +119,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, pktsz = sizeof(*mp); mp->wait_queue_token = wq->wait_queue_token; - mp->len = wq->len; - memcpy(mp->name, wq->name, wq->len); - mp->name[wq->len] = '\0'; + mp->len = wq->name.len; + memcpy(mp->name, wq->name.name, wq->name.len); + mp->name[wq->name.len] = '\0'; break; } case autofs_ptype_expire_multi: @@ -119,9 +131,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, pktsz = sizeof(*ep); ep->wait_queue_token = wq->wait_queue_token; - ep->len = wq->len; - memcpy(ep->name, wq->name, wq->len); - ep->name[wq->len] = '\0'; + ep->len = wq->name.len; + memcpy(ep->name, wq->name.name, wq->name.len); + ep->name[wq->name.len] = '\0'; break; } /* @@ -134,28 +146,35 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, case autofs_ptype_expire_direct: { struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet; + struct user_namespace *user_ns = sbi->pipe->f_cred->user_ns; pktsz = sizeof(*packet); packet->wait_queue_token = wq->wait_queue_token; - packet->len = wq->len; - memcpy(packet->name, wq->name, wq->len); - packet->name[wq->len] = '\0'; + packet->len = wq->name.len; + memcpy(packet->name, wq->name.name, wq->name.len); + packet->name[wq->name.len] = '\0'; packet->dev = wq->dev; packet->ino = wq->ino; - packet->uid = wq->uid; - packet->gid = wq->gid; + packet->uid = from_kuid_munged(user_ns, wq->uid); + packet->gid = from_kgid_munged(user_ns, wq->gid); packet->pid = wq->pid; packet->tgid = wq->tgid; break; } default: printk("autofs4_notify_daemon: bad type %d!\n", type); + mutex_unlock(&sbi->wq_mutex); return; } - if (autofs4_write(sbi->pipe, &pkt, pktsz)) + pipe = get_file(sbi->pipe); + + mutex_unlock(&sbi->wq_mutex); + + if (autofs4_write(sbi, pipe, &pkt, pktsz)) autofs4_catatonic_mode(sbi); + fput(pipe); } static int autofs4_getpath(struct autofs_sb_info *sbi, @@ -163,16 +182,26 @@ static int autofs4_getpath(struct autofs_sb_info *sbi, { struct dentry *root = sbi->sb->s_root; struct dentry *tmp; - char *buf = *name; + char *buf; char *p; - int len = 0; + int len; + unsigned seq; + +rename_retry: + buf = *name; + len = 0; - spin_lock(&dcache_lock); + seq = read_seqbegin(&rename_lock); + rcu_read_lock(); + spin_lock(&sbi->fs_lock); for (tmp = dentry ; tmp != root ; tmp = tmp->d_parent) len += tmp->d_name.len + 1; - if (--len > NAME_MAX) { - spin_unlock(&dcache_lock); + if (!len || --len > NAME_MAX) { + spin_unlock(&sbi->fs_lock); + rcu_read_unlock(); + if (read_seqretry(&rename_lock, seq)) + goto rename_retry; return 0; } @@ -185,64 +214,67 @@ static int autofs4_getpath(struct autofs_sb_info *sbi, p -= tmp->d_name.len; strncpy(p, tmp->d_name.name, tmp->d_name.len); } - spin_unlock(&dcache_lock); + spin_unlock(&sbi->fs_lock); + rcu_read_unlock(); + if (read_seqretry(&rename_lock, seq)) + goto rename_retry; return len; } static struct autofs_wait_queue * -autofs4_find_wait(struct autofs_sb_info *sbi, - char *name, unsigned int hash, unsigned int len) +autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr) { struct autofs_wait_queue *wq; for (wq = sbi->queues; wq; wq = wq->next) { - if (wq->hash == hash && - wq->len == len && - wq->name && !memcmp(wq->name, name, len)) + if (wq->name.hash == qstr->hash && + wq->name.len == qstr->len && + wq->name.name && + !memcmp(wq->name.name, qstr->name, qstr->len)) break; } return wq; } -int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, - enum autofs_notify notify) +/* + * Check if we have a valid request. + * Returns + * 1 if the request should continue. + * In this case we can return an autofs_wait_queue entry if one is + * found or NULL to idicate a new wait needs to be created. + * 0 or a negative errno if the request shouldn't continue. + */ +static int validate_request(struct autofs_wait_queue **wait, + struct autofs_sb_info *sbi, + struct qstr *qstr, + struct dentry*dentry, enum autofs_notify notify) { - struct autofs_info *ino; struct autofs_wait_queue *wq; - char *name; - unsigned int len = 0; - unsigned int hash = 0; - int status, type; + struct autofs_info *ino; - /* In catatonic mode, we don't wait for nobody */ if (sbi->catatonic) return -ENOENT; - - name = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!name) - return -ENOMEM; - /* If this is a direct mount request create a dummy name */ - if (IS_ROOT(dentry) && (sbi->type & AUTOFS_TYPE_DIRECT)) - len = sprintf(name, "%p", dentry); - else { - len = autofs4_getpath(sbi, dentry, &name); - if (!len) { - kfree(name); - return -ENOENT; - } + /* Wait in progress, continue; */ + wq = autofs4_find_wait(sbi, qstr); + if (wq) { + *wait = wq; + return 1; } - hash = full_name_hash(name, len); - if (mutex_lock_interruptible(&sbi->wq_mutex)) { - kfree(name); - return -EINTR; - } + *wait = NULL; - wq = autofs4_find_wait(sbi, name, hash, len); + /* If we don't yet have any info this is a new request */ ino = autofs4_dentry_ino(dentry); - if (!wq && ino && notify == NFY_NONE) { + if (!ino) + return 1; + + /* + * If we've been asked to wait on an existing expire (NFY_NONE) + * but there is no wait in the queue ... + */ + if (notify == NFY_NONE) { /* * Either we've betean the pending expire to post it's * wait or it finished while we waited on the mutex. @@ -253,13 +285,17 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, while (ino->flags & AUTOFS_INF_EXPIRING) { mutex_unlock(&sbi->wq_mutex); schedule_timeout_interruptible(HZ/10); - if (mutex_lock_interruptible(&sbi->wq_mutex)) { - kfree(name); + if (mutex_lock_interruptible(&sbi->wq_mutex)) return -EINTR; + + if (sbi->catatonic) + return -ENOENT; + + wq = autofs4_find_wait(sbi, qstr); + if (wq) { + *wait = wq; + return 1; } - wq = autofs4_find_wait(sbi, name, hash, len); - if (wq) - break; } /* @@ -267,18 +303,117 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, * cases where we wait on NFY_NONE neither depend on the * return status of the wait. */ - if (!wq) { + return 0; + } + + /* + * If we've been asked to trigger a mount and the request + * completed while we waited on the mutex ... + */ + if (notify == NFY_MOUNT) { + struct dentry *new = NULL; + int valid = 1; + + /* + * If the dentry was successfully mounted while we slept + * on the wait queue mutex we can return success. If it + * isn't mounted (doesn't have submounts for the case of + * a multi-mount with no mount at it's base) we can + * continue on and create a new request. + */ + if (!IS_ROOT(dentry)) { + if (dentry->d_inode && d_unhashed(dentry)) { + struct dentry *parent = dentry->d_parent; + new = d_lookup(parent, &dentry->d_name); + if (new) + dentry = new; + } + } + if (have_submounts(dentry)) + valid = 0; + + if (new) + dput(new); + return valid; + } + + return 1; +} + +int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, + enum autofs_notify notify) +{ + struct autofs_wait_queue *wq; + struct qstr qstr; + char *name; + int status, ret, type; + pid_t pid; + pid_t tgid; + + /* In catatonic mode, we don't wait for nobody */ + if (sbi->catatonic) + return -ENOENT; + + /* + * Try translating pids to the namespace of the daemon. + * + * Zero means failure: we are in an unrelated pid namespace. + */ + pid = task_pid_nr_ns(current, ns_of_pid(sbi->oz_pgrp)); + tgid = task_tgid_nr_ns(current, ns_of_pid(sbi->oz_pgrp)); + if (pid == 0 || tgid == 0) + return -ENOENT; + + if (!dentry->d_inode) { + /* + * A wait for a negative dentry is invalid for certain + * cases. A direct or offset mount "always" has its mount + * point directory created and so the request dentry must + * be positive or the map key doesn't exist. The situation + * is very similar for indirect mounts except only dentrys + * in the root of the autofs file system may be negative. + */ + if (autofs_type_trigger(sbi->type)) + return -ENOENT; + else if (!IS_ROOT(dentry->d_parent)) + return -ENOENT; + } + + name = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!name) + return -ENOMEM; + + /* If this is a direct mount request create a dummy name */ + if (IS_ROOT(dentry) && autofs_type_trigger(sbi->type)) + qstr.len = sprintf(name, "%p", dentry); + else { + qstr.len = autofs4_getpath(sbi, dentry, &name); + if (!qstr.len) { kfree(name); - mutex_unlock(&sbi->wq_mutex); - return 0; + return -ENOENT; } } + qstr.name = name; + qstr.hash = full_name_hash(name, qstr.len); + + if (mutex_lock_interruptible(&sbi->wq_mutex)) { + kfree(qstr.name); + return -EINTR; + } + + ret = validate_request(&wq, sbi, &qstr, dentry, notify); + if (ret <= 0) { + if (ret != -EINTR) + mutex_unlock(&sbi->wq_mutex); + kfree(qstr.name); + return ret; + } if (!wq) { /* Create a new wait queue */ wq = kmalloc(sizeof(struct autofs_wait_queue),GFP_KERNEL); if (!wq) { - kfree(name); + kfree(qstr.name); mutex_unlock(&sbi->wq_mutex); return -ENOMEM; } @@ -289,18 +424,15 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, wq->next = sbi->queues; sbi->queues = wq; init_waitqueue_head(&wq->queue); - wq->hash = hash; - wq->name = name; - wq->len = len; + memcpy(&wq->name, &qstr, sizeof(struct qstr)); wq->dev = autofs4_get_dev(sbi); wq->ino = autofs4_get_ino(sbi); - wq->uid = current->uid; - wq->gid = current->gid; - wq->pid = current->pid; - wq->tgid = current->tgid; + wq->uid = current_uid(); + wq->gid = current_gid(); + wq->pid = pid; + wq->tgid = tgid; wq->status = -EINTR; /* Status return if interrupted */ - atomic_set(&wq->wait_ctr, 2); - mutex_unlock(&sbi->wq_mutex); + wq->wait_ctr = 2; if (sbi->version < 5) { if (notify == NFY_MOUNT) @@ -309,38 +441,35 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, type = autofs_ptype_expire_multi; } else { if (notify == NFY_MOUNT) - type = (sbi->type & AUTOFS_TYPE_DIRECT) ? + type = autofs_type_trigger(sbi->type) ? autofs_ptype_missing_direct : autofs_ptype_missing_indirect; else - type = (sbi->type & AUTOFS_TYPE_DIRECT) ? + type = autofs_type_trigger(sbi->type) ? autofs_ptype_expire_direct : autofs_ptype_expire_indirect; } DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n", - (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify); + (unsigned long) wq->wait_queue_token, wq->name.len, + wq->name.name, notify); - /* autofs4_notify_daemon() may block */ + /* autofs4_notify_daemon() may block; it will unlock ->wq_mutex */ autofs4_notify_daemon(sbi, wq, type); } else { - atomic_inc(&wq->wait_ctr); - mutex_unlock(&sbi->wq_mutex); - kfree(name); + wq->wait_ctr++; DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d", - (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify); - } - - /* wq->name is NULL if and only if the lock is already released */ - - if (sbi->catatonic) { - /* We might have slept, so check again for catatonic mode */ - wq->status = -ENOENT; - kfree(wq->name); - wq->name = NULL; + (unsigned long) wq->wait_queue_token, wq->name.len, + wq->name.name, notify); + mutex_unlock(&sbi->wq_mutex); + kfree(qstr.name); } - if (wq->name) { + /* + * wq->name.name is NULL iff the lock is already released + * or the mount has been made catatonic. + */ + if (wq->name.name) { /* Block all but "shutdown" signals while waiting */ sigset_t oldset; unsigned long irqflags; @@ -351,7 +480,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, recalc_sigpending(); spin_unlock_irqrestore(¤t->sighand->siglock, irqflags); - wait_event_interruptible(wq->queue, wq->name == NULL); + wait_event_interruptible(wq->queue, wq->name.name == NULL); spin_lock_irqsave(¤t->sighand->siglock, irqflags); current->blocked = oldset; @@ -363,9 +492,45 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, status = wq->status; + /* + * For direct and offset mounts we need to track the requester's + * uid and gid in the dentry info struct. This is so it can be + * supplied, on request, by the misc device ioctl interface. + * This is needed during daemon resatart when reconnecting + * to existing, active, autofs mounts. The uid and gid (and + * related string values) may be used for macro substitution + * in autofs mount maps. + */ + if (!status) { + struct autofs_info *ino; + struct dentry *de = NULL; + + /* direct mount or browsable map */ + ino = autofs4_dentry_ino(dentry); + if (!ino) { + /* If not lookup actual dentry used */ + de = d_lookup(dentry->d_parent, &dentry->d_name); + if (de) + ino = autofs4_dentry_ino(de); + } + + /* Set mount requester */ + if (ino) { + spin_lock(&sbi->fs_lock); + ino->uid = wq->uid; + ino->gid = wq->gid; + spin_unlock(&sbi->fs_lock); + } + + if (de) + dput(de); + } + /* Are we the last process to need status? */ - if (atomic_dec_and_test(&wq->wait_ctr)) + mutex_lock(&sbi->wq_mutex); + if (!--wq->wait_ctr) kfree(wq); + mutex_unlock(&sbi->wq_mutex); return status; } @@ -387,16 +552,13 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok } *wql = wq->next; /* Unlink from chain */ - mutex_unlock(&sbi->wq_mutex); - kfree(wq->name); - wq->name = NULL; /* Do not wait on this queue */ - + kfree(wq->name.name); + wq->name.name = NULL; /* Do not wait on this queue */ wq->status = status; - - if (atomic_dec_and_test(&wq->wait_ctr)) /* Is anyone still waiting for this guy? */ + wake_up_interruptible(&wq->queue); + if (!--wq->wait_ctr) kfree(wq); - else - wake_up_interruptible(&wq->queue); + mutex_unlock(&sbi->wq_mutex); return 0; } |