Merge branch 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull core signal handling updates from Eric Biederman:
 "It was observed that a periodic timer in combination with a
  sufficiently expensive fork could prevent fork from every completing.
  This contains the changes to remove the need for that restart.

  This set of changes is split into several parts:

   - The first part makes PIDTYPE_TGID a proper pid type instead
     something only for very special cases. The part starts using
     PIDTYPE_TGID enough so that in __send_signal where signals are
     actually delivered we know if the signal is being sent to a a group
     of processes or just a single process.

   - With that prep work out of the way the logic in fork is modified so
     that fork logically makes signals received while it is running
     appear to be received after the fork completes"

* 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (22 commits)
  signal: Don't send signals to tasks that don't exist
  signal: Don't restart fork when signals come in.
  fork: Have new threads join on-going signal group stops
  fork: Skip setting TIF_SIGPENDING in ptrace_init_task
  signal: Add calculate_sigpending()
  fork: Unconditionally exit if a fatal signal is pending
  fork: Move and describe why the code examines PIDNS_ADDING
  signal: Push pid type down into complete_signal.
  signal: Push pid type down into __send_signal
  signal: Push pid type down into send_signal
  signal: Pass pid type into do_send_sig_info
  signal: Pass pid type into send_sigio_to_task & send_sigurg_to_task
  signal: Pass pid type into group_send_sig_info
  signal: Pass pid and pid type into send_sigqueue
  posix-timers: Noralize good_sigevent
  signal: Use PIDTYPE_TGID to clearly store where file signals will be sent
  pid: Implement PIDTYPE_TGID
  pids: Move the pgrp and session pid pointers from task_struct to signal_struct
  kvm: Don't open code task_pid in kvm_vcpu_ioctl
  pids: Compute task_tgid using signal->leader_pid
  ...

1 files changed, 54 insertions, 21 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 5ee74c113381..ff5037be7771 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1487,6 +1487,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
+	INIT_HLIST_HEAD(&sig->multiprocess);
 	seqlock_init(&sig->stats_lock);
 	prev_cputime_init(&sig->prev_cputime);
 
@@ -1580,10 +1581,22 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
 static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
 #endif
 
+static inline void init_task_pid_links(struct task_struct *task)
+{
+	enum pid_type type;
+
+	for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
+		INIT_HLIST_NODE(&task->pid_links[type]);
+	}
+}
+
 static inline void
 init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
 {
-	 task->pids[type].pid = pid;
+	if (type == PIDTYPE_PID)
+		task->thread_pid = pid;
+	else
+		task->signal->pids[type] = pid;
 }
 
 static inline void rcu_copy_process(struct task_struct *p)
@@ -1621,6 +1634,7 @@ static __latent_entropy struct task_struct *copy_process(
 {
 	int retval;
 	struct task_struct *p;
+	struct multiprocess_signals delayed;
 
 	/*
 	 * Don't allow sharing the root directory with processes in a different
@@ -1668,6 +1682,24 @@ static __latent_entropy struct task_struct *copy_process(
 			return ERR_PTR(-EINVAL);
 	}
 
+	/*
+	 * Force any signals received before this point to be delivered
+	 * before the fork happens.  Collect up signals sent to multiple
+	 * processes that happen during the fork and delay them so that
+	 * they appear to happen after the fork.
+	 */
+	sigemptyset(&delayed.signal);
+	INIT_HLIST_NODE(&delayed.node);
+
+	spin_lock_irq(&current->sighand->siglock);
+	if (!(clone_flags & CLONE_THREAD))
+		hlist_add_head(&delayed.node, &current->signal->multiprocess);
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+	retval = -ERESTARTNOINTR;
+	if (signal_pending(current))
+		goto fork_out;
+
 	retval = -ENOMEM;
 	p = dup_task_struct(current, node);
 	if (!p)
@@ -1941,29 +1973,26 @@ static __latent_entropy struct task_struct *copy_process(
 
 	rseq_fork(p, clone_flags);
 
-	/*
-	 * Process group and session signals need to be delivered to just the
-	 * parent before the fork or both the parent and the child after the
-	 * fork. Restart if a signal comes in before we add the new process to
-	 * it's process group.
-	 * A fatal signal pending means that current will exit, so the new
-	 * thread can't slip out of an OOM kill (or normal SIGKILL).
-	*/
-	recalc_sigpending();
-	if (signal_pending(current)) {
-		retval = -ERESTARTNOINTR;
-		goto bad_fork_cancel_cgroup;
-	}
+	/* Don't start children in a dying pid namespace */
 	if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
 		retval = -ENOMEM;
 		goto bad_fork_cancel_cgroup;
 	}
 
+	/* Let kill terminate clone/fork in the middle */
+	if (fatal_signal_pending(current)) {
+		retval = -EINTR;
+		goto bad_fork_cancel_cgroup;
+	}
+
+
+	init_task_pid_links(p);
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
 
 		init_task_pid(p, PIDTYPE_PID, pid);
 		if (thread_group_leader(p)) {
+			init_task_pid(p, PIDTYPE_TGID, pid);
 			init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
 			init_task_pid(p, PIDTYPE_SID, task_session(current));
 
@@ -1971,8 +2000,7 @@ static __latent_entropy struct task_struct *copy_process(
 				ns_of_pid(pid)->child_reaper = p;
 				p->signal->flags |= SIGNAL_UNKILLABLE;
 			}
-
-			p->signal->leader_pid = pid;
+			p->signal->shared_pending.signal = delayed.signal;
 			p->signal->tty = tty_kref_get(current->signal->tty);
 			/*
 			 * Inherit has_child_subreaper flag under the same
@@ -1983,6 +2011,7 @@ static __latent_entropy struct task_struct *copy_process(
 							 p->real_parent->signal->is_child_subreaper;
 			list_add_tail(&p->sibling, &p->real_parent->children);
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
+			attach_pid(p, PIDTYPE_TGID);
 			attach_pid(p, PIDTYPE_PGID);
 			attach_pid(p, PIDTYPE_SID);
 			__this_cpu_inc(process_counts);
@@ -1990,6 +2019,7 @@ static __latent_entropy struct task_struct *copy_process(
 			current->signal->nr_threads++;
 			atomic_inc(&current->signal->live);
 			atomic_inc(&current->signal->sigcnt);
+			task_join_group_stop(p);
 			list_add_tail_rcu(&p->thread_group,
 					  &p->group_leader->thread_group);
 			list_add_tail_rcu(&p->thread_node,
@@ -1998,8 +2028,8 @@ static __latent_entropy struct task_struct *copy_process(
 		attach_pid(p, PIDTYPE_PID);
 		nr_threads++;
 	}
-
 	total_forks++;
+	hlist_del_init(&delayed.node);
 	spin_unlock(&current->sighand->siglock);
 	syscall_tracepoint_update(p);
 	write_unlock_irq(&tasklist_lock);
@@ -2064,16 +2094,19 @@ bad_fork_free:
 	put_task_stack(p);
 	free_task(p);
 fork_out:
+	spin_lock_irq(&current->sighand->siglock);
+	hlist_del_init(&delayed.node);
+	spin_unlock_irq(&current->sighand->siglock);
 	return ERR_PTR(retval);
 }
 
-static inline void init_idle_pids(struct pid_link *links)
+static inline void init_idle_pids(struct task_struct *idle)
 {
 	enum pid_type type;
 
 	for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
-		INIT_HLIST_NODE(&links[type].node); /* not really needed */
-		links[type].pid = &init_struct_pid;
+		INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */
+		init_task_pid(idle, type, &init_struct_pid);
 	}
 }
 
@@ -2083,7 +2116,7 @@ struct task_struct *fork_idle(int cpu)
 	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
 			    cpu_to_node(cpu));
 	if (!IS_ERR(task)) {
-		init_idle_pids(task->pids);
+		init_idle_pids(task);
 		init_idle(task, cpu);
 	}