linux-kernel - [PATCH 3/4] locking/rwbase: Fix rwbase_write_lock() vs __rwbase_read

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]

Date:   Thu, 09 Sep 2021 12:59:18 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     tglx@...utronix.de, boqun.feng@...il.com
Cc:     linux-kernel@...r.kernel.org, peterz@...radead.org,
        Ingo Molnar <mingo@...nel.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Davidlohr Bueso <dave@...olabs.net>,
        Will Deacon <will@...nel.org>,
        Waiman Long <longman@...hat.com>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Mike Galbraith <efault@....de>,
        Daniel Bristot de Oliveira <bristot@...hat.com>
Subject: [PATCH 3/4] locking/rwbase: Fix rwbase_write_lock() vs __rwbase_read_lock()

Boqun noticed that the write-trylock sequence of load+set is broken in
rwbase_write_lock()'s wait-loop since they're not both under the same
wait_lock instance.

Restructure the code to make this more obvious and correct.

Reported-by: Boqun Feng <boqun.feng@...il.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 kernel/locking/rwbase_rt.c |   44 ++++++++++++++++++++++++++------------------
 1 file changed, 26 insertions(+), 18 deletions(-)

--- a/kernel/locking/rwbase_rt.c
+++ b/kernel/locking/rwbase_rt.c
@@ -196,6 +196,19 @@ static inline void rwbase_write_downgrad
 	__rwbase_write_unlock(rwb, WRITER_BIAS - 1, flags);
 }
 
+static inline bool __rwbase_write_trylock(struct rwbase_rt *rwb)
+{
+	/* Can do without CAS because we're serialized by wait_lock. */
+	lockdep_assert_held(&rwb->rtmutex.wait_lock);
+
+	if (!atomic_read(&rwb->readers)) {
+		atomic_set(&rwb->readers, WRITER_BIAS);
+		return 1;
+	}
+
+	return 0;
+}
+
 static int __sched rwbase_write_lock(struct rwbase_rt *rwb,
 				     unsigned int state)
 {
@@ -210,34 +223,30 @@ static int __sched rwbase_write_lock(str
 	atomic_sub(READER_BIAS, &rwb->readers);
 
 	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
-	/*
-	 * set_current_state() for rw_semaphore
-	 * current_save_and_set_rtlock_wait_state() for rwlock
-	 */
-	rwbase_set_and_save_current_state(state);
+	if (__rwbase_write_trylock(rwb))
+		goto out_unlock;
 
-	/* Block until all readers have left the critical section. */
-	for (; atomic_read(&rwb->readers);) {
+	rwbase_set_and_save_current_state(state);
+	for (;;) {
 		/* Optimized out for rwlocks */
 		if (rwbase_signal_pending_state(state, current)) {
 			rwbase_restore_current_state();
 			__rwbase_write_unlock(rwb, 0, flags);
 			return -EINTR;
 		}
+
+		if (__rwbase_write_trylock(rwb))
+			break;
+
 		raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
+		rwbase_schedule();
+		raw_spin_lock_irqsave(&rtm->wait_lock, flags);
 
-		/*
-		 * Schedule and wait for the readers to leave the critical
-		 * section. The last reader leaving it wakes the waiter.
-		 */
-		if (atomic_read(&rwb->readers) != 0)
-			rwbase_schedule();
 		set_current_state(state);
-		raw_spin_lock_irqsave(&rtm->wait_lock, flags);
 	}
-
-	atomic_set(&rwb->readers, WRITER_BIAS);
 	rwbase_restore_current_state();
+
+out_unlock:
 	raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
 	return 0;
 }
@@ -253,8 +262,7 @@ static inline int rwbase_write_trylock(s
 	atomic_sub(READER_BIAS, &rwb->readers);
 
 	raw_spin_lock_irqsave(&rtm->wait_lock, flags);
-	if (!atomic_read(&rwb->readers)) {
-		atomic_set(&rwb->readers, WRITER_BIAS);
+	if (__rwbase_write_trylock(rwb)) {
 		raw_spin_unlock_irqrestore(&rtm->wait_lock, flags);
 		return 1;
 	}