Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   "Eric W. Biederman" <ebiederm@xmission.com>
To:     Oleg Nesterov <oleg@redhat.com>
Cc:     linux-kernel@vger.kernel.org, mingo@kernel.org,
        bigeasy@linutronix.de, Peter Zijlstra <peterz@infradead.org>,
        Jann Horn <jannh@google.com>,
        Kees Cook <keescook@chromium.org>,
        Alexander Gordeev <agordeev@linux.ibm.com>,
        Robert O'Callahan <roc@pernos.co>, Kyle Huey <khuey@pernos.co>,
        Keno Fischer <keno@juliacomputing.com>
References: <20220421150248.667412396@infradead.org>
        <20220421150654.817117821@infradead.org>
        <87czhap9dy.fsf@email.froward.int.ebiederm.org>
        <878rrrh32q.fsf_-_@email.froward.int.ebiederm.org>
        <87k0b7v9yk.fsf_-_@email.froward.int.ebiederm.org>
        <87k0b0apne.fsf_-_@email.froward.int.ebiederm.org>
        <87a6bv6dl6.fsf_-_@email.froward.int.ebiederm.org>
        <87r13gd4xy.fsf_-_@email.froward.int.ebiederm.org>
Date:   Wed, 22 Jun 2022 11:46:23 -0500
In-Reply-To: <87r13gd4xy.fsf_-_@email.froward.int.ebiederm.org> (Eric
        W. Biederman's message of "Wed, 22 Jun 2022 11:43:37 -0500")
Message-ID: <87bkukd4tc.fsf_-_@email.froward.int.ebiederm.org>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/27.1 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain
Subject: [PATCH 2/3] signal: Guarantee that SIGNAL_GROUP_EXIT is set on
 process exit
Precedence: bulk


Track how many threads have not started exiting and when the last
thread starts exiting set SIGNAL_GROUP_EXIT.

This guarantees that SIGNAL_GROUP_EXIT will get set when a process
exits.  In practice this achieves nothing as glibc's implementation of
_exit calls sys_group_exit then sys_exit.  While glibc's implemenation
of pthread_exit calls exit (which cleansup and calls _exit) if it is
the last thread and sys_exit if it is the last thread.

This means the only way the kernel might observe a process that does
not set call exit_group is if the language runtime does not use glibc.

With more cleanups I hope to move the decrement of quick_threads
earlier.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/sched/signal.h |  1 +
 kernel/exit.c                | 18 ++++++++++++++++++
 kernel/fork.c                |  2 ++
 3 files changed, 21 insertions(+)

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index cafbe03eed01..20099268fa25 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -94,6 +94,7 @@ struct signal_struct {
 	refcount_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	int			quick_threads;
 	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
diff --git a/kernel/exit.c b/kernel/exit.c
index 96e4b12edea8..beaedb867bd3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -733,11 +733,29 @@ static void check_stack_usage(void)
 static inline void check_stack_usage(void) {}
 #endif
 
+static void synchronize_group_exit(struct task_struct *tsk, long code)
+{
+	struct sighand_struct *sighand = tsk->sighand;
+	struct signal_struct *signal = tsk->signal;
+
+	spin_lock_irq(&sighand->siglock);
+	signal->quick_threads--;
+	if ((signal->quick_threads == 0) &&
+	    !(signal->flags & SIGNAL_GROUP_EXIT)) {
+		signal->flags = SIGNAL_GROUP_EXIT;
+		signal->group_exit_code = code;
+		signal->group_stop_count = 0;
+	}
+	spin_unlock_irq(&sighand->siglock);
+}
+
 void __noreturn do_exit(long code)
 {
 	struct task_struct *tsk = current;
 	int group_dead;
 
+	synchronize_group_exit(tsk, code);
+
 	WARN_ON(tsk->plug);
 
 	kcov_task_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 9d44f2d46c69..67813b25a567 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1692,6 +1692,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 		return -ENOMEM;
 
 	sig->nr_threads = 1;
+	sig->quick_threads = 1;
 	atomic_set(&sig->live, 1);
 	refcount_set(&sig->sigcnt, 1);
 
@@ -2444,6 +2445,7 @@ static __latent_entropy struct task_struct *copy_process(
 			__this_cpu_inc(process_counts);
 		} else {
 			current->signal->nr_threads++;
+			current->signal->quick_threads++;
 			atomic_inc(&current->signal->live);
 			refcount_inc(&current->signal->sigcnt);
 			task_join_group_stop(p);
-- 
2.35.3