#include <linux/sched.h>
#include <linux/module.h>
#include <linux/bitops.h>
-#include <linux/smp_lock.h>
+#include <linux/user_namespace.h>
#include <linux/mount.h>
#include <linux/pid_namespace.h>
+#include <linux/parser.h>
#include "internal.h"
-struct proc_dir_entry *proc_bus, *proc_root_fs, *proc_root_driver;
-
static int proc_test_super(struct super_block *sb, void *data)
{
return sb->s_fs_info == data;
static int proc_set_super(struct super_block *sb, void *data)
{
- struct pid_namespace *ns;
+ int err = set_anon_super(sb, NULL);
+ if (!err) {
+ struct pid_namespace *ns = (struct pid_namespace *)data;
+ sb->s_fs_info = get_pid_ns(ns);
+ }
+ return err;
+}
- ns = (struct pid_namespace *)data;
- sb->s_fs_info = get_pid_ns(ns);
- return set_anon_super(sb, NULL);
+enum {
+ Opt_gid, Opt_hidepid, Opt_err,
+};
+
+static const match_table_t tokens = {
+ {Opt_hidepid, "hidepid=%u"},
+ {Opt_gid, "gid=%u"},
+ {Opt_err, NULL},
+};
+
+static int proc_parse_options(char *options, struct pid_namespace *pid)
+{
+ char *p;
+ substring_t args[MAX_OPT_ARGS];
+ int option;
+
+ if (!options)
+ return 1;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+
+ args[0].to = args[0].from = NULL;
+ token = match_token(p, tokens, args);
+ switch (token) {
+ case Opt_gid:
+ if (match_int(&args[0], &option))
+ return 0;
+ pid->pid_gid = make_kgid(current_user_ns(), option);
+ break;
+ case Opt_hidepid:
+ if (match_int(&args[0], &option))
+ return 0;
+ if (option < 0 || option > 2) {
+ pr_err("proc: hidepid value must be between 0 and 2.\n");
+ return 0;
+ }
+ pid->hide_pid = option;
+ break;
+ default:
+ pr_err("proc: unrecognized mount option \"%s\" "
+ "or missing value\n", p);
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+int proc_remount(struct super_block *sb, int *flags, char *data)
+{
+ struct pid_namespace *pid = sb->s_fs_info;
+ return !proc_parse_options(data, pid);
}
-static int proc_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *proc_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
{
int err;
struct super_block *sb;
struct pid_namespace *ns;
- struct proc_inode *ei;
-
- if (proc_mnt) {
- /* Seed the root directory with a pid so it doesn't need
- * to be special in base.c. I would do this earlier but
- * the only task alive when /proc is mounted the first time
- * is the init_task and it doesn't have any pids.
- */
- ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
- if (!ei->pid)
- ei->pid = find_get_pid(1);
- }
+ char *options;
- if (flags & MS_KERNMOUNT)
+ if (flags & MS_KERNMOUNT) {
ns = (struct pid_namespace *)data;
- else
- ns = current->nsproxy->pid_ns;
+ options = NULL;
+ } else {
+ ns = task_active_pid_ns(current);
+ options = data;
+
+ if (!current_user_ns()->may_mount_proc)
+ return ERR_PTR(-EPERM);
+ }
- sb = sget(fs_type, proc_test_super, proc_set_super, ns);
+ sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
if (IS_ERR(sb))
- return PTR_ERR(sb);
+ return ERR_CAST(sb);
+
+ if (!proc_parse_options(options, ns)) {
+ deactivate_locked_super(sb);
+ return ERR_PTR(-EINVAL);
+ }
if (!sb->s_root) {
- sb->s_flags = flags;
err = proc_fill_super(sb);
if (err) {
- up_write(&sb->s_umount);
- deactivate_super(sb);
- return err;
- }
-
- ei = PROC_I(sb->s_root->d_inode);
- if (!ei->pid) {
- rcu_read_lock();
- ei->pid = get_pid(find_pid_ns(1, ns));
- rcu_read_unlock();
+ deactivate_locked_super(sb);
+ return ERR_PTR(err);
}
sb->s_flags |= MS_ACTIVE;
- ns->proc_mnt = mnt;
}
- return simple_set_mnt(mnt, sb);
+ return dget(sb->s_root);
}
static void proc_kill_sb(struct super_block *sb)
static struct file_system_type proc_fs_type = {
.name = "proc",
- .get_sb = proc_get_sb,
+ .mount = proc_mount,
.kill_sb = proc_kill_sb,
+ .fs_flags = FS_USERNS_MOUNT,
};
void __init proc_root_init(void)
{
- int err = proc_init_inodecache();
- if (err)
- return;
+ int err;
+
+ proc_init_inodecache();
err = register_filesystem(&proc_fs_type);
if (err)
return;
- proc_mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
- err = PTR_ERR(proc_mnt);
- if (IS_ERR(proc_mnt)) {
- unregister_filesystem(&proc_fs_type);
- return;
- }
- proc_misc_init();
+ proc_self_init();
+ proc_symlink("mounts", NULL, "self/mounts");
proc_net_init();
#ifdef CONFIG_SYSVIPC
proc_mkdir("sysvipc", NULL);
#endif
- proc_root_fs = proc_mkdir("fs", NULL);
- proc_root_driver = proc_mkdir("driver", NULL);
+ proc_mkdir("fs", NULL);
+ proc_mkdir("driver", NULL);
proc_mkdir("fs/nfsd", NULL); /* somewhere for the nfsd filesystem to be mounted */
#if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE)
/* just give it a mountpoint */
#ifdef CONFIG_PROC_DEVICETREE
proc_device_tree_init();
#endif
- proc_bus = proc_mkdir("bus", NULL);
+ proc_mkdir("bus", NULL);
proc_sys_init();
}
return 0;
}
-static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
- if (!proc_lookup(dir, dentry, nd)) {
+ if (!proc_lookup(dir, dentry, flags))
return NULL;
- }
- return proc_pid_lookup(dir, dentry, nd);
+ return proc_pid_lookup(dir, dentry, flags);
}
static int proc_root_readdir(struct file * filp,
unsigned int nr = filp->f_pos;
int ret;
- lock_kernel();
-
if (nr < FIRST_PROCESS_ENTRY) {
int error = proc_readdir(filp, dirent, filldir);
- if (error <= 0) {
- unlock_kernel();
+ if (error <= 0)
return error;
- }
filp->f_pos = FIRST_PROCESS_ENTRY;
}
- unlock_kernel();
ret = proc_pid_readdir(filp, dirent, filldir);
return ret;
static const struct file_operations proc_root_operations = {
.read = generic_read_dir,
.readdir = proc_root_readdir,
+ .llseek = default_llseek,
};
/*
struct proc_dir_entry proc_root = {
.low_ino = PROC_ROOT_INO,
.namelen = 5,
- .name = "/proc",
.mode = S_IFDIR | S_IRUGO | S_IXUGO,
.nlink = 2,
+ .count = ATOMIC_INIT(1),
.proc_iops = &proc_root_inode_operations,
.proc_fops = &proc_root_operations,
.parent = &proc_root,
+ .name = "/proc",
};
int pid_ns_prepare_proc(struct pid_namespace *ns)
if (IS_ERR(mnt))
return PTR_ERR(mnt);
+ ns->proc_mnt = mnt;
return 0;
}
void pid_ns_release_proc(struct pid_namespace *ns)
{
- mntput(ns->proc_mnt);
+ kern_unmount(ns->proc_mnt);
}
-
-EXPORT_SYMBOL(proc_symlink);
-EXPORT_SYMBOL(proc_mkdir);
-EXPORT_SYMBOL(create_proc_entry);
-EXPORT_SYMBOL(remove_proc_entry);
-EXPORT_SYMBOL(proc_root);
-EXPORT_SYMBOL(proc_root_fs);
-EXPORT_SYMBOL(proc_bus);
-EXPORT_SYMBOL(proc_root_driver);