linux-kernel - Re: [patch 00/12] futex: Cure robust/PI futex exit races

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20191107150323.GA24042@redhat.com>
Date:   Thu, 7 Nov 2019 16:03:23 +0100
From:   Oleg Nesterov <oleg@...hat.com>
To:     Thomas Gleixner <tglx@...utronix.de>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...nel.org>,
        Darren Hart <darren@...art.com>,
        Yi Wang <wang.yi59@....com.cn>,
        Yang Tao <yang.tao172@....com.cn>,
        Florian Weimer <fweimer@...hat.com>,
        Carlos O'Donell <carlos@...hat.com>,
        Alexander Viro <viro@...iv.linux.org.uk>
Subject: Re: [patch 00/12] futex: Cure robust/PI futex exit races

On 11/06, Thomas Gleixner wrote:
>
>  fs/exec.c                |    2 
>  include/linux/compat.h   |    2 
>  include/linux/futex.h    |   38 +++--
>  include/linux/sched.h    |    3 
>  include/linux/sched/mm.h |    6 
>  kernel/exit.c            |   30 ----
>  kernel/fork.c            |   40 ++---
>  kernel/futex.c           |  324 ++++++++++++++++++++++++++++++++++++++++-------
>  8 files changed, 330 insertions(+), 115 deletions(-)

The whole series looks good to me.

But I am just curious, what do you all think about the patch below
instead of 10/12 and 12/12 ?

Oleg.


diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9e0de08..ad18433 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -621,6 +621,11 @@ struct wake_q_node {
 	struct wake_q_node *next;
 };
 
+struct wake_q_head {
+	struct wake_q_node *first;
+	struct wake_q_node **lastp;
+};
+
 struct task_struct {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	/*
@@ -1055,6 +1060,7 @@ struct task_struct {
 	struct list_head		pi_state_list;
 	struct futex_pi_state		*pi_state_cache;
 	unsigned int			futex_state;
+	struct wake_q_head		futex_exit_q;
 #endif
 #ifdef CONFIG_PERF_EVENTS
 	struct perf_event_context	*perf_event_ctxp[perf_nr_task_contexts];
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 26a2013..62805b5 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -35,11 +35,6 @@
 
 #include <linux/sched.h>
 
-struct wake_q_head {
-	struct wake_q_node *first;
-	struct wake_q_node **lastp;
-};
-
 #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
 
 #define DEFINE_WAKE_Q(name)				\
diff --git a/kernel/futex.c b/kernel/futex.c
index 4b36bc8..87763c7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1176,6 +1176,24 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
 	return ret;
 }
 
+static void wait_for_owner_exiting(int ret)
+{
+	struct wake_q_node *node = &current->wake_q;
+
+	if (ret != -EBUSY) {
+		WARN_ON_ONCE(node->next); // XXX not really correct ...
+		return;
+	}
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(node->next))
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+}
+
 static int handle_exit_race(u32 __user *uaddr, u32 uval,
 			    struct task_struct *tsk)
 {
@@ -1185,8 +1203,10 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval,
 	 * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the
 	 * caller that the alleged owner is busy.
 	 */
-	if (tsk && tsk->futex_state != FUTEX_STATE_DEAD)
+	if (tsk && tsk->futex_state != FUTEX_STATE_DEAD) {
+		wake_q_add(&tsk->futex_exit_q, current);
 		return -EBUSY;
+	}
 
 	/*
 	 * Reread the user space value to handle the following situation:
@@ -2104,6 +2124,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
+			wait_for_owner_exiting(ret);
 			cond_resched();
 			goto retry;
 		default:
@@ -2855,6 +2876,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 			queue_unlock(hb);
 			put_futex_key(&q.key);
 			cond_resched();
+			wait_for_owner_exiting(ret);
 			goto retry;
 		default:
 			goto out_unlock_put_key;
@@ -3701,6 +3723,7 @@ static void futex_cleanup(struct task_struct *tsk)
 void futex_exit_recursive(struct task_struct *tsk)
 {
 	tsk->futex_state = FUTEX_STATE_DEAD;
+	wake_up_q(&tsk->futex_exit_q);
 }
 
 static void futex_cleanup_begin(struct task_struct *tsk)
@@ -3718,16 +3741,17 @@ static void futex_cleanup_begin(struct task_struct *tsk)
 	 */
 	raw_spin_lock_irq(&tsk->pi_lock);
 	tsk->futex_state = FUTEX_STATE_EXITING;
+	wake_q_init(&tsk->futex_exit_q);
 	raw_spin_unlock_irq(&tsk->pi_lock);
 }
 
 static void futex_cleanup_end(struct task_struct *tsk, int state)
 {
-	/*
-	 * Lockless store. The only side effect is that an observer might
-	 * take another loop until it becomes visible.
-	 */
+	raw_spin_lock_irq(&tsk->pi_lock);
 	tsk->futex_state = state;
+	raw_spin_unlock_irq(&tsk->pi_lock);
+
+	wake_up_q(&tsk->futex_exit_q);
 }
 
 void futex_exec_release(struct task_struct *tsk)