mmc: sdhci-pci: Stop calling sdhci_enable_irq_wakeups()

[linux/fpc-iii.git] / kernel / pid_namespace.c

/*
 * Pid namespaces
 *
 * Authors:
 *    (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
 *    (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
 *     Many thanks to Oleg Nesterov for comments and help
 *
 */

#include <linux/pid.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/syscalls.h>
#include <linux/cred.h>
#include <linux/err.h>
#include <linux/acct.h>
#include <linux/slab.h>
#include <linux/proc_ns.h>
#include <linux/reboot.h>
#include <linux/export.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
#include <linux/idr.h>

struct pid_cache {
        int nr_ids;
        char name[16];
        struct kmem_cache *cachep;
        struct list_head list;
};

static LIST_HEAD(pid_caches_lh);
static DEFINE_MUTEX(pid_caches_mutex);
static struct kmem_cache *pid_ns_cachep;

/*
 * creates the kmem cache to allocate pids from.
 * @nr_ids: the number of numerical ids this pid will have to carry
 */

static struct kmem_cache *create_pid_cachep(int nr_ids)
{
        struct pid_cache *pcache;
        struct kmem_cache *cachep;

        mutex_lock(&pid_caches_mutex);
        list_for_each_entry(pcache, &pid_caches_lh, list)
                if (pcache->nr_ids == nr_ids)
                        goto out;

        pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL);
        if (pcache == NULL)
                goto err_alloc;

        snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
        cachep = kmem_cache_create(pcache->name,
                        sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid),
                        0, SLAB_HWCACHE_ALIGN, NULL);
        if (cachep == NULL)
                goto err_cachep;

        pcache->nr_ids = nr_ids;
        pcache->cachep = cachep;
        list_add(&pcache->list, &pid_caches_lh);
out:
        mutex_unlock(&pid_caches_mutex);
        return pcache->cachep;

err_cachep:
        kfree(pcache);
err_alloc:
        mutex_unlock(&pid_caches_mutex);
        return NULL;
}

static void proc_cleanup_work(struct work_struct *work)
{
        struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work);
        pid_ns_release_proc(ns);
}

/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */
#define MAX_PID_NS_LEVEL 32

static struct ucounts *inc_pid_namespaces(struct user_namespace *ns)
{
        return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES);
}

static void dec_pid_namespaces(struct ucounts *ucounts)
{
        dec_ucount(ucounts, UCOUNT_PID_NAMESPACES);
}

static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns,
        struct pid_namespace *parent_pid_ns)
{
        struct pid_namespace *ns;
        unsigned int level = parent_pid_ns->level + 1;
        struct ucounts *ucounts;
        int err;

        err = -EINVAL;
        if (!in_userns(parent_pid_ns->user_ns, user_ns))
                goto out;

        err = -ENOSPC;
        if (level > MAX_PID_NS_LEVEL)
                goto out;
        ucounts = inc_pid_namespaces(user_ns);
        if (!ucounts)
                goto out;

        err = -ENOMEM;
        ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
        if (ns == NULL)
                goto out_dec;

        idr_init(&ns->idr);

        ns->pid_cachep = create_pid_cachep(level + 1);
        if (ns->pid_cachep == NULL)
                goto out_free_idr;

        err = ns_alloc_inum(&ns->ns);
        if (err)
                goto out_free_idr;
        ns->ns.ops = &pidns_operations;

        kref_init(&ns->kref);
        ns->level = level;
        ns->parent = get_pid_ns(parent_pid_ns);
        ns->user_ns = get_user_ns(user_ns);
        ns->ucounts = ucounts;
        ns->pid_allocated = PIDNS_ADDING;
        INIT_WORK(&ns->proc_work, proc_cleanup_work);

        return ns;

out_free_idr:
        idr_destroy(&ns->idr);
        kmem_cache_free(pid_ns_cachep, ns);
out_dec:
        dec_pid_namespaces(ucounts);
out:
        return ERR_PTR(err);
}

static void delayed_free_pidns(struct rcu_head *p)
{
        struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu);

        dec_pid_namespaces(ns->ucounts);
        put_user_ns(ns->user_ns);

        kmem_cache_free(pid_ns_cachep, ns);
}

static void destroy_pid_namespace(struct pid_namespace *ns)
{
        ns_free_inum(&ns->ns);

        idr_destroy(&ns->idr);
        call_rcu(&ns->rcu, delayed_free_pidns);
}

struct pid_namespace *copy_pid_ns(unsigned long flags,
        struct user_namespace *user_ns, struct pid_namespace *old_ns)
{
        if (!(flags & CLONE_NEWPID))
                return get_pid_ns(old_ns);
        if (task_active_pid_ns(current) != old_ns)
                return ERR_PTR(-EINVAL);
        return create_pid_namespace(user_ns, old_ns);
}

static void free_pid_ns(struct kref *kref)
{
        struct pid_namespace *ns;

        ns = container_of(kref, struct pid_namespace, kref);
        destroy_pid_namespace(ns);
}

void put_pid_ns(struct pid_namespace *ns)
{
        struct pid_namespace *parent;

        while (ns != &init_pid_ns) {
                parent = ns->parent;
                if (!kref_put(&ns->kref, free_pid_ns))
                        break;
                ns = parent;
        }
}
EXPORT_SYMBOL_GPL(put_pid_ns);

void zap_pid_ns_processes(struct pid_namespace *pid_ns)
{
        int nr;
        int rc;
        struct task_struct *task, *me = current;
        int init_pids = thread_group_leader(me) ? 1 : 2;
        struct pid *pid;

        /* Don't allow any more processes into the pid namespace */
        disable_pid_allocation(pid_ns);

        /*
         * Ignore SIGCHLD causing any terminated children to autoreap.
         * This speeds up the namespace shutdown, plus see the comment
         * below.
         */
        spin_lock_irq(&me->sighand->siglock);
        me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
        spin_unlock_irq(&me->sighand->siglock);

        /*
         * The last thread in the cgroup-init thread group is terminating.
         * Find remaining pid_ts in the namespace, signal and wait for them
         * to exit.
         *
         * Note:  This signals each threads in the namespace - even those that
         *        belong to the same thread group, To avoid this, we would have
         *        to walk the entire tasklist looking a processes in this
         *        namespace, but that could be unnecessarily expensive if the
         *        pid namespace has just a few processes. Or we need to
         *        maintain a tasklist for each pid namespace.
         *
         */
        rcu_read_lock();
        read_lock(&tasklist_lock);
        nr = 2;
        idr_for_each_entry_continue(&pid_ns->idr, pid, nr) {
                task = pid_task(pid, PIDTYPE_PID);
                if (task && !__fatal_signal_pending(task))
                        send_sig_info(SIGKILL, SEND_SIG_FORCED, task);
        }
        read_unlock(&tasklist_lock);
        rcu_read_unlock();

        /*
         * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
         * sys_wait4() will also block until our children traced from the
         * parent namespace are detached and become EXIT_DEAD.
         */
        do {
                clear_thread_flag(TIF_SIGPENDING);
                rc = sys_wait4(-1, NULL, __WALL, NULL);
        } while (rc != -ECHILD);

        /*
         * sys_wait4() above can't reap the EXIT_DEAD children but we do not
         * really care, we could reparent them to the global init. We could
         * exit and reap ->child_reaper even if it is not the last thread in
         * this pid_ns, free_pid(pid_allocated == 0) calls proc_cleanup_work(),
         * pid_ns can not go away until proc_kill_sb() drops the reference.
         *
         * But this ns can also have other tasks injected by setns()+fork().
         * Again, ignoring the user visible semantics we do not really need
         * to wait until they are all reaped, but they can be reparented to
         * us and thus we need to ensure that pid->child_reaper stays valid
         * until they all go away. See free_pid()->wake_up_process().
         *
         * We rely on ignored SIGCHLD, an injected zombie must be autoreaped
         * if reparented.
         */
        for (;;) {
                set_current_state(TASK_INTERRUPTIBLE);
                if (pid_ns->pid_allocated == init_pids)
                        break;
                schedule();
        }
        __set_current_state(TASK_RUNNING);

        if (pid_ns->reboot)
                current->signal->group_exit_code = pid_ns->reboot;

        acct_exit_ns(pid_ns);
        return;
}

#ifdef CONFIG_CHECKPOINT_RESTORE
static int pid_ns_ctl_handler(struct ctl_table *table, int write,
                void __user *buffer, size_t *lenp, loff_t *ppos)
{
        struct pid_namespace *pid_ns = task_active_pid_ns(current);
        struct ctl_table tmp = *table;
        int ret, next;

        if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
                return -EPERM;

        /*
         * Writing directly to ns' last_pid field is OK, since this field
         * is volatile in a living namespace anyway and a code writing to
         * it should synchronize its usage with external means.
         */

        next = idr_get_cursor(&pid_ns->idr) - 1;

        tmp.data = &next;
        ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
        if (!ret && write)
                idr_set_cursor(&pid_ns->idr, next + 1);

        return ret;
}

extern int pid_max;
static int zero = 0;
static struct ctl_table pid_ns_ctl_table[] = {
        {
                .procname = "ns_last_pid",
                .maxlen = sizeof(int),
                .mode = 0666, /* permissions are checked in the handler */
                .proc_handler = pid_ns_ctl_handler,
                .extra1 = &zero,
                .extra2 = &pid_max,
        },
        { }
};
static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
#endif  /* CONFIG_CHECKPOINT_RESTORE */

int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
{
        if (pid_ns == &init_pid_ns)
                return 0;

        switch (cmd) {
        case LINUX_REBOOT_CMD_RESTART2:
        case LINUX_REBOOT_CMD_RESTART:
                pid_ns->reboot = SIGHUP;
                break;

        case LINUX_REBOOT_CMD_POWER_OFF:
        case LINUX_REBOOT_CMD_HALT:
                pid_ns->reboot = SIGINT;
                break;
        default:
                return -EINVAL;
        }

        read_lock(&tasklist_lock);
        force_sig(SIGKILL, pid_ns->child_reaper);
        read_unlock(&tasklist_lock);

        do_exit(0);

        /* Not reached */
        return 0;
}

static inline struct pid_namespace *to_pid_ns(struct ns_common *ns)
{
        return container_of(ns, struct pid_namespace, ns);
}

static struct ns_common *pidns_get(struct task_struct *task)
{
        struct pid_namespace *ns;

        rcu_read_lock();
        ns = task_active_pid_ns(task);
        if (ns)
                get_pid_ns(ns);
        rcu_read_unlock();

        return ns ? &ns->ns : NULL;
}

static struct ns_common *pidns_for_children_get(struct task_struct *task)
{
        struct pid_namespace *ns = NULL;

        task_lock(task);
        if (task->nsproxy) {
                ns = task->nsproxy->pid_ns_for_children;
                get_pid_ns(ns);
        }
        task_unlock(task);

        if (ns) {
                read_lock(&tasklist_lock);
                if (!ns->child_reaper) {
                        put_pid_ns(ns);
                        ns = NULL;
                }
                read_unlock(&tasklist_lock);
        }

        return ns ? &ns->ns : NULL;
}

static void pidns_put(struct ns_common *ns)
{
        put_pid_ns(to_pid_ns(ns));
}

static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns)
{
        struct pid_namespace *active = task_active_pid_ns(current);
        struct pid_namespace *ancestor, *new = to_pid_ns(ns);

        if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) ||
            !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
                return -EPERM;

        /*
         * Only allow entering the current active pid namespace
         * or a child of the current active pid namespace.
         *
         * This is required for fork to return a usable pid value and
         * this maintains the property that processes and their
         * children can not escape their current pid namespace.
         */
        if (new->level < active->level)
                return -EINVAL;

        ancestor = new;
        while (ancestor->level > active->level)
                ancestor = ancestor->parent;
        if (ancestor != active)
                return -EINVAL;

        put_pid_ns(nsproxy->pid_ns_for_children);
        nsproxy->pid_ns_for_children = get_pid_ns(new);
        return 0;
}

static struct ns_common *pidns_get_parent(struct ns_common *ns)
{
        struct pid_namespace *active = task_active_pid_ns(current);
        struct pid_namespace *pid_ns, *p;

        /* See if the parent is in the current namespace */
        pid_ns = p = to_pid_ns(ns)->parent;
        for (;;) {
                if (!p)
                        return ERR_PTR(-EPERM);
                if (p == active)
                        break;
                p = p->parent;
        }

        return &get_pid_ns(pid_ns)->ns;
}

static struct user_namespace *pidns_owner(struct ns_common *ns)
{
        return to_pid_ns(ns)->user_ns;
}

const struct proc_ns_operations pidns_operations = {
        .name           = "pid",
        .type           = CLONE_NEWPID,
        .get            = pidns_get,
        .put            = pidns_put,
        .install        = pidns_install,
        .owner          = pidns_owner,
        .get_parent     = pidns_get_parent,
};

const struct proc_ns_operations pidns_for_children_operations = {
        .name           = "pid_for_children",
        .real_ns_name   = "pid",
        .type           = CLONE_NEWPID,
        .get            = pidns_for_children_get,
        .put            = pidns_put,
        .install        = pidns_install,
        .owner          = pidns_owner,
        .get_parent     = pidns_get_parent,
};

static __init int pid_namespaces_init(void)
{
        pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);

#ifdef CONFIG_CHECKPOINT_RESTORE
        register_sysctl_paths(kern_path, pid_ns_ctl_table);
#endif
        return 0;
}

__initcall(pid_namespaces_init);