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, 72 insertions, 26 deletions

diff --git a/kernel/signal.c b/kernel/signal.c
index 8d8a940422a8..cfa9d10e731a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -172,6 +172,17 @@ void recalc_sigpending(void)
 
 }
 
+void calculate_sigpending(void)
+{
+	/* Have any signals or users of TIF_SIGPENDING been delayed
+	 * until after fork?
+	 */
+	spin_lock_irq(&current->sighand->siglock);
+	set_tsk_thread_flag(current, TIF_SIGPENDING);
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+}
+
 /* Given the mask, find the first available signal that should be serviced. */
 
 #define SYNCHRONOUS_MASK \
@@ -362,6 +373,20 @@ static bool task_participate_group_stop(struct task_struct *task)
 	return false;
 }
 
+void task_join_group_stop(struct task_struct *task)
+{
+	/* Have the new thread join an on-going signal group stop */
+	unsigned long jobctl = current->jobctl;
+	if (jobctl & JOBCTL_STOP_PENDING) {
+		struct signal_struct *sig = current->signal;
+		unsigned long signr = jobctl & JOBCTL_STOP_SIGMASK;
+		unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME;
+		if (task_set_jobctl_pending(task, signr | gstop)) {
+			sig->group_stop_count++;
+		}
+	}
+}
+
 /*
  * allocate a new signal queue record
  * - this may be called without locks if and only if t == current, otherwise an
@@ -895,7 +920,7 @@ static inline int wants_signal(int sig, struct task_struct *p)
 	return task_curr(p) || !signal_pending(p);
 }
 
-static void complete_signal(int sig, struct task_struct *p, int group)
+static void complete_signal(int sig, struct task_struct *p, enum pid_type type)
 {
 	struct signal_struct *signal = p->signal;
 	struct task_struct *t;
@@ -908,7 +933,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
 	 */
 	if (wants_signal(sig, p))
 		t = p;
-	else if (!group || thread_group_empty(p))
+	else if ((type == PIDTYPE_PID) || thread_group_empty(p))
 		/*
 		 * There is just one thread and it does not need to be woken.
 		 * It will dequeue unblocked signals before it runs again.
@@ -998,7 +1023,7 @@ static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_str
 #endif
 
 static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
-			int group, int from_ancestor_ns)
+			enum pid_type type, int from_ancestor_ns)
 {
 	struct sigpending *pending;
 	struct sigqueue *q;
@@ -1012,7 +1037,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			from_ancestor_ns || (info == SEND_SIG_FORCED)))
 		goto ret;
 
-	pending = group ? &t->signal->shared_pending : &t->pending;
+	pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
 	/*
 	 * Short-circuit ignored signals and support queuing
 	 * exactly one non-rt signal, so that we can get more
@@ -1096,14 +1121,29 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
 out_set:
 	signalfd_notify(t, sig);
 	sigaddset(&pending->signal, sig);
-	complete_signal(sig, t, group);
+
+	/* Let multiprocess signals appear after on-going forks */
+	if (type > PIDTYPE_TGID) {
+		struct multiprocess_signals *delayed;
+		hlist_for_each_entry(delayed, &t->signal->multiprocess, node) {
+			sigset_t *signal = &delayed->signal;
+			/* Can't queue both a stop and a continue signal */
+			if (sig == SIGCONT)
+				sigdelsetmask(signal, SIG_KERNEL_STOP_MASK);
+			else if (sig_kernel_stop(sig))
+				sigdelset(signal, SIGCONT);
+			sigaddset(signal, sig);
+		}
+	}
+
+	complete_signal(sig, t, type);
 ret:
-	trace_signal_generate(sig, info, t, group, result);
+	trace_signal_generate(sig, info, t, type != PIDTYPE_PID, result);
 	return ret;
 }
 
 static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
-			int group)
+			enum pid_type type)
 {
 	int from_ancestor_ns = 0;
 
@@ -1112,7 +1152,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			   !task_pid_nr_ns(current, task_active_pid_ns(t));
 #endif
 
-	return __send_signal(sig, info, t, group, from_ancestor_ns);
+	return __send_signal(sig, info, t, type, from_ancestor_ns);
 }
 
 static void print_fatal_signal(int signr)
@@ -1151,23 +1191,23 @@ __setup("print-fatal-signals=", setup_print_fatal_signals);
 int
 __group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 {
-	return send_signal(sig, info, p, 1);
+	return send_signal(sig, info, p, PIDTYPE_TGID);
 }
 
 static int
 specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t)
 {
-	return send_signal(sig, info, t, 0);
+	return send_signal(sig, info, t, PIDTYPE_PID);
 }
 
 int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
-			bool group)
+			enum pid_type type)
 {
 	unsigned long flags;
 	int ret = -ESRCH;
 
 	if (lock_task_sighand(p, &flags)) {
-		ret = send_signal(sig, info, p, group);
+		ret = send_signal(sig, info, p, type);
 		unlock_task_sighand(p, &flags);
 	}
 
@@ -1274,7 +1314,8 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 /*
  * send signal info to all the members of a group
  */
-int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
+int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p,
+			enum pid_type type)
 {
 	int ret;
 
@@ -1283,7 +1324,7 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 	rcu_read_unlock();
 
 	if (!ret && sig)
-		ret = do_send_sig_info(sig, info, p, true);
+		ret = do_send_sig_info(sig, info, p, type);
 
 	return ret;
 }
@@ -1301,7 +1342,7 @@ int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp)
 	success = 0;
 	retval = -ESRCH;
 	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
-		int err = group_send_sig_info(sig, info, p);
+		int err = group_send_sig_info(sig, info, p, PIDTYPE_PGID);
 		success |= !err;
 		retval = err;
 	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
@@ -1317,7 +1358,7 @@ int kill_pid_info(int sig, struct siginfo *info, struct pid *pid)
 		rcu_read_lock();
 		p = pid_task(pid, PIDTYPE_PID);
 		if (p)
-			error = group_send_sig_info(sig, info, p);
+			error = group_send_sig_info(sig, info, p, PIDTYPE_TGID);
 		rcu_read_unlock();
 		if (likely(!p || error != -ESRCH))
 			return error;
@@ -1376,7 +1417,7 @@ int kill_pid_info_as_cred(int sig, struct siginfo *info, struct pid *pid,
 
 	if (sig) {
 		if (lock_task_sighand(p, &flags)) {
-			ret = __send_signal(sig, info, p, 1, 0);
+			ret = __send_signal(sig, info, p, PIDTYPE_TGID, 0);
 			unlock_task_sighand(p, &flags);
 		} else
 			ret = -ESRCH;
@@ -1420,7 +1461,8 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid)
 		for_each_process(p) {
 			if (task_pid_vnr(p) > 1 &&
 					!same_thread_group(p, current)) {
-				int err = group_send_sig_info(sig, info, p);
+				int err = group_send_sig_info(sig, info, p,
+							      PIDTYPE_MAX);
 				++count;
 				if (err != -EPERM)
 					retval = err;
@@ -1446,7 +1488,7 @@ int send_sig_info(int sig, struct siginfo *info, struct task_struct *p)
 	if (!valid_signal(sig))
 		return -EINVAL;
 
-	return do_send_sig_info(sig, info, p, false);
+	return do_send_sig_info(sig, info, p, PIDTYPE_PID);
 }
 
 #define __si_special(priv) \
@@ -1664,17 +1706,20 @@ void sigqueue_free(struct sigqueue *q)
 		__sigqueue_free(q);
 }
 
-int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
+int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
 {
 	int sig = q->info.si_signo;
 	struct sigpending *pending;
+	struct task_struct *t;
 	unsigned long flags;
 	int ret, result;
 
 	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
 
 	ret = -1;
-	if (!likely(lock_task_sighand(t, &flags)))
+	rcu_read_lock();
+	t = pid_task(pid, type);
+	if (!t || !likely(lock_task_sighand(t, &flags)))
 		goto ret;
 
 	ret = 1; /* the signal is ignored */
@@ -1696,15 +1741,16 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
 	q->info.si_overrun = 0;
 
 	signalfd_notify(t, sig);
-	pending = group ? &t->signal->shared_pending : &t->pending;
+	pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending;
 	list_add_tail(&q->list, &pending->list);
 	sigaddset(&pending->signal, sig);
-	complete_signal(sig, t, group);
+	complete_signal(sig, t, type);
 	result = TRACE_SIGNAL_DELIVERED;
 out:
-	trace_signal_generate(sig, &q->info, t, group, result);
+	trace_signal_generate(sig, &q->info, t, type != PIDTYPE_PID, result);
 	unlock_task_sighand(t, &flags);
 ret:
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -3193,7 +3239,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info)
 		 * probe.  No signal is actually delivered.
 		 */
 		if (!error && sig) {
-			error = do_send_sig_info(sig, info, p, false);
+			error = do_send_sig_info(sig, info, p, PIDTYPE_PID);
 			/*
 			 * If lock_task_sighand() failed we pretend the task
 			 * dies after receiving the signal. The window is tiny,
@@ -3960,7 +4006,7 @@ void kdb_send_sig(struct task_struct *t, int sig)
 			   "the deadlock.\n");
 		return;
 	}
-	ret = send_signal(sig, SEND_SIG_PRIV, t, false);
+	ret = send_signal(sig, SEND_SIG_PRIV, t, PIDTYPE_PID);
 	spin_unlock(&t->sighand->siglock);
 	if (ret)
 		kdb_printf("Fail to deliver Signal %d to process %d.\n",