pid namespaces: allow cloning of new namespace

When clone() is invoked with CLONE_NEWPID, create a new pid namespace and then
create a new struct pid for the new process.  Allocate pid_t's for the new
process in the new pid namespace and all ancestor pid namespaces.  Make the
newly cloned process the session and process group leader.

Since the active pid namespace is special and expected to be the first entry
in pid->upid_list, preserve the order of pid namespaces.

The size of 'struct pid' is dependent on the the number of pid namespaces the
process exists in, so we use multiple pid-caches'.  Only one pid cache is
created during system startup and this used by processes that exist only in
init_pid_ns.

When a process clones its pid namespace, we create additional pid caches as
necessary and use the pid cache to allocate 'struct pids' for that depth.

Note, that with this patch the newly created namespace won't work, since the
rest of the kernel still uses global pids, but this is to be fixed soon.  Init
pid namespace still works.

[oleg@tv-sign.ru: merge fix]
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 112 insertions, 22 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index bab34192799..f252784f933 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -973,7 +973,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 					unsigned long stack_start,
 					struct pt_regs *regs,
 					unsigned long stack_size,
-					int __user *parent_tidptr,
 					int __user *child_tidptr,
 					struct pid *pid)
 {
@@ -1043,11 +1042,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->did_exec = 0;
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
 	copy_flags(clone_flags, p);
-	retval = -EFAULT;
-	if (clone_flags & CLONE_PARENT_SETTID)
-		if (put_user(p->pid, parent_tidptr))
-			goto bad_fork_cleanup_delays_binfmt;
-
 	INIT_LIST_HEAD(&p->children);
 	INIT_LIST_HEAD(&p->sibling);
 	p->vfork_done = NULL;
@@ -1289,11 +1283,22 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			__ptrace_link(p, current->parent);
 
 		if (thread_group_leader(p)) {
-			p->signal->tty = current->signal->tty;
-			p->signal->pgrp = task_pgrp_nr(current);
-			set_task_session(p, task_session_nr(current));
-			attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
-			attach_pid(p, PIDTYPE_SID, task_session(current));
+			if (clone_flags & CLONE_NEWPID) {
+				p->nsproxy->pid_ns->child_reaper = p;
+				p->signal->tty = NULL;
+				p->signal->pgrp = p->pid;
+				set_task_session(p, p->pid);
+				attach_pid(p, PIDTYPE_PGID, pid);
+				attach_pid(p, PIDTYPE_SID, pid);
+			} else {
+				p->signal->tty = current->signal->tty;
+				p->signal->pgrp = task_pgrp_nr(current);
+				set_task_session(p, task_session_nr(current));
+				attach_pid(p, PIDTYPE_PGID,
+						task_pgrp(current));
+				attach_pid(p, PIDTYPE_SID,
+						task_session(current));
+			}
 
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
 			__get_cpu_var(process_counts)++;
@@ -1339,7 +1344,6 @@ bad_fork_cleanup_policy:
 bad_fork_cleanup_cgroup:
 #endif
 	cgroup_exit(p, cgroup_callbacks_done);
-bad_fork_cleanup_delays_binfmt:
 	delayacct_tsk_free(p);
 	if (p->binfmt)
 		module_put(p->binfmt->module);
@@ -1366,7 +1370,7 @@ struct task_struct * __cpuinit fork_idle(int cpu)
 	struct task_struct *task;
 	struct pt_regs regs;
 
-	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL, NULL,
+	task = copy_process(CLONE_VM, 0, idle_regs(&regs), 0, NULL,
 				&init_struct_pid);
 	if (!IS_ERR(task))
 		init_idle(task, cpu);
@@ -1414,7 +1418,7 @@ long do_fork(unsigned long clone_flags,
 	}
 
 	p = copy_process(clone_flags, stack_start, regs, stack_size,
-			parent_tidptr, child_tidptr, NULL);
+			child_tidptr, NULL);
 	/*
 	 * Do this prior waking up the new thread - the thread pointer
 	 * might get invalid after that point, if the thread exits quickly.
@@ -1422,7 +1426,16 @@ long do_fork(unsigned long clone_flags,
 	if (!IS_ERR(p)) {
 		struct completion vfork;
 
-		nr = pid_nr(task_pid(p));
+		/*
+		 * this is enough to call pid_nr_ns here, but this if
+		 * improves optimisation of regular fork()
+		 */
+		nr = (clone_flags & CLONE_NEWPID) ?
+			task_pid_nr_ns(p, current->nsproxy->pid_ns) :
+				task_pid_vnr(p);
+
+		if (clone_flags & CLONE_PARENT_SETTID)
+			put_user(nr, parent_tidptr);
 
 		if (clone_flags & CLONE_VFORK) {
 			p->vfork_done = &vfork;
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index c8ef7c2992e..79f871bc0ef 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -129,7 +129,8 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk)
 
 	get_nsproxy(old_ns);
 
-	if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWUSER | CLONE_NEWNET)))
+	if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
+				CLONE_NEWUSER | CLONE_NEWPID | CLONE_NEWNET)))
 		return 0;
 
 	if (!capable(CAP_SYS_ADMIN)) {
diff --git a/kernel/pid.c b/kernel/pid.c
index 4b17acdb862..f76097c6047 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -18,6 +18,12 @@
  * allocation scenario when all but one out of 1 million PIDs possible are
  * allocated already: the scanning of 32 list entries and at most PAGE_SIZE
  * bytes. The typical fastpath is a single successful setbit. Freeing is O(1).
+ *
+ * Pid namespaces:
+ *    (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/mm.h>
@@ -456,8 +462,8 @@ static struct kmem_cache *create_pid_cachep(int nr_ids)
 
 	snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
 	cachep = kmem_cache_create(pcache->name,
-			/* FIXME add numerical ids here */
-			sizeof(struct pid), 0, SLAB_HWCACHE_ALIGN, NULL);
+			sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid),
+			0, SLAB_HWCACHE_ALIGN, NULL);
 	if (cachep == NULL)
 		goto err_cachep;
 
@@ -475,19 +481,89 @@ err_alloc:
 	return NULL;
 }
 
+static struct pid_namespace *create_pid_namespace(int level)
+{
+	struct pid_namespace *ns;
+	int i;
+
+	ns = kmalloc(sizeof(struct pid_namespace), GFP_KERNEL);
+	if (ns == NULL)
+		goto out;
+
+	ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!ns->pidmap[0].page)
+		goto out_free;
+
+	ns->pid_cachep = create_pid_cachep(level + 1);
+	if (ns->pid_cachep == NULL)
+		goto out_free_map;
+
+	kref_init(&ns->kref);
+	ns->last_pid = 0;
+	ns->child_reaper = NULL;
+	ns->level = level;
+
+	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++) {
+		ns->pidmap[i].page = 0;
+		atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
+	}
+
+	return ns;
+
+out_free_map:
+	kfree(ns->pidmap[0].page);
+out_free:
+	kfree(ns);
+out:
+	return ERR_PTR(-ENOMEM);
+}
+
+static void destroy_pid_namespace(struct pid_namespace *ns)
+{
+	int i;
+
+	for (i = 0; i < PIDMAP_ENTRIES; i++)
+		kfree(ns->pidmap[i].page);
+	kfree(ns);
+}
+
 struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
 {
+	struct pid_namespace *new_ns;
+
 	BUG_ON(!old_ns);
-	get_pid_ns(old_ns);
-	return old_ns;
+	new_ns = get_pid_ns(old_ns);
+	if (!(flags & CLONE_NEWPID))
+		goto out;
+
+	new_ns = ERR_PTR(-EINVAL);
+	if (flags & CLONE_THREAD)
+		goto out_put;
+
+	new_ns = create_pid_namespace(old_ns->level + 1);
+	if (!IS_ERR(new_ns))
+		new_ns->parent = get_pid_ns(old_ns);
+
+out_put:
+	put_pid_ns(old_ns);
+out:
+	return new_ns;
 }
 
 void free_pid_ns(struct kref *kref)
 {
-	struct pid_namespace *ns;
+	struct pid_namespace *ns, *parent;
 
 	ns = container_of(kref, struct pid_namespace, kref);
-	kfree(ns);
+
+	parent = ns->parent;
+	destroy_pid_namespace(ns);
+
+	if (parent != NULL)
+		put_pid_ns(parent);
 }
 
 /*