Merge tag 'drm-misc-next-2017-11-30' of git://anongit.freedesktop.org/drm/drm-misc...

[linux.git] / kernel / pid_namespace.c

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 4918314893bc6620ae95660c78588d6d5ac9129c..0b53eef7d34b1a5d60d97c650fbc2354238b9f27 100644 (file)
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -21,6 +21,7 @@
 #include <linux/export.h>
 #include <linux/sched/task.h>
 #include <linux/sched/signal.h>
+#include <linux/idr.h>
 
 struct pid_cache {
        int nr_ids;
@@ -98,7 +99,6 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
        struct pid_namespace *ns;
        unsigned int level = parent_pid_ns->level + 1;
        struct ucounts *ucounts;
-       int i;
        int err;
 
        err = -EINVAL;
@@ -117,17 +117,15 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
        if (ns == NULL)
                goto out_dec;
 
-       ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
-       if (!ns->pidmap[0].page)
-               goto out_free;
+       idr_init(&ns->idr);
 
        ns->pid_cachep = create_pid_cachep(level + 1);
        if (ns->pid_cachep == NULL)
-               goto out_free_map;
+               goto out_free_idr;
 
        err = ns_alloc_inum(&ns->ns);
        if (err)
-               goto out_free_map;
+               goto out_free_idr;
        ns->ns.ops = &pidns_operations;
 
        kref_init(&ns->kref);
@@ -135,20 +133,13 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
        ns->parent = get_pid_ns(parent_pid_ns);
        ns->user_ns = get_user_ns(user_ns);
        ns->ucounts = ucounts;
-       ns->nr_hashed = PIDNS_HASH_ADDING;
+       ns->pid_allocated = PIDNS_ADDING;
        INIT_WORK(&ns->proc_work, proc_cleanup_work);
 
-       set_bit(0, ns->pidmap[0].page);
-       atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
-
-       for (i = 1; i < PIDMAP_ENTRIES; i++)
-               atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
-
        return ns;
 
-out_free_map:
-       kfree(ns->pidmap[0].page);
-out_free:
+out_free_idr:
+       idr_destroy(&ns->idr);
        kmem_cache_free(pid_ns_cachep, ns);
 out_dec:
        dec_pid_namespaces(ucounts);
@@ -168,11 +159,9 @@ static void delayed_free_pidns(struct rcu_head *p)
 
 static void destroy_pid_namespace(struct pid_namespace *ns)
 {
-       int i;
-
        ns_free_inum(&ns->ns);
-       for (i = 0; i < PIDMAP_ENTRIES; i++)
-               kfree(ns->pidmap[i].page);
+
+       idr_destroy(&ns->idr);
        call_rcu(&ns->rcu, delayed_free_pidns);
 }
 
@@ -213,6 +202,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
        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);
@@ -239,20 +229,16 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
         *        maintain a tasklist for each pid namespace.
         *
         */
+       rcu_read_lock();
        read_lock(&tasklist_lock);
-       nr = next_pidmap(pid_ns, 1);
-       while (nr > 0) {
-               rcu_read_lock();
-
-               task = pid_task(find_vpid(nr), PIDTYPE_PID);
+       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);
-
-               rcu_read_unlock();
-
-               nr = next_pidmap(pid_ns, nr);
        }
        read_unlock(&tasklist_lock);
+       rcu_read_unlock();
 
        /*
         * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
@@ -268,7 +254,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
         * 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(nr_hashed == 0) calls proc_cleanup_work(),
+        * 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().
@@ -282,7 +268,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
         */
        for (;;) {
                set_current_state(TASK_INTERRUPTIBLE);
-               if (pid_ns->nr_hashed == init_pids)
+               if (pid_ns->pid_allocated == init_pids)
                        break;
                schedule();
        }
@@ -301,6 +287,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
 {
        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;
@@ -311,8 +298,14 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write,
         * it should synchronize its usage with external means.
         */
 
-       tmp.data = &pid_ns->last_pid;
-       return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+       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;