linux-kernel - [PATCH for 5.8] sched: Fix unreliable rseq cpu

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-next>] [day] [month] [year] [list]

Date:   Tue,  7 Jul 2020 16:15:05 -0400
From:   Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
To:     Thomas Gleixner <tglx@...utronix.de>
Cc:     linux-kernel@...r.kernel.org,
        Peter Zijlstra <peterz@...radead.org>,
        "Paul E . McKenney" <paulmck@...ux.ibm.com>,
        Boqun Feng <boqun.feng@...il.com>,
        "H . Peter Anvin" <hpa@...or.com>, Paul Turner <pjt@...gle.com>,
        linux-api@...r.kernel.org, Florian Weimer <fw@...eb.enyo.de>,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        Dmitry Vyukov <dvyukov@...gle.com>,
        Neel Natu <neelnatu@...gle.com>, stable@...r.kernel.org
Subject: [PATCH for 5.8] sched: Fix unreliable rseq cpu_id for new tasks

While integrating rseq into glibc and replacing glibc's sched_getcpu
implementation with rseq, glibc's tests discovered an issue with
incorrect __rseq_abi.cpu_id field value right after the first time
a newly created process issues sched_setaffinity.

For the records, it triggers after building glibc and running tests, and
then issuing:

  for x in {1..2000} ; do posix/tst-affinity-static  & done

and shows up as:

error: Unexpected CPU 2, expected 0
error: Unexpected CPU 2, expected 0
error: Unexpected CPU 2, expected 0
error: Unexpected CPU 2, expected 0
error: Unexpected CPU 138, expected 0
error: Unexpected CPU 138, expected 0
error: Unexpected CPU 138, expected 0
error: Unexpected CPU 138, expected 0

This is caused by the scheduler invoking __set_task_cpu() directly from
sched_fork() and wake_up_new_task(), thus bypassing rseq_migrate() which
is done by set_task_cpu().

Add the missing rseq_migrate() to both functions. The only other direct
use of __set_task_cpu() is done by init_idle(), which does not involve a
user-space task.

Based on my testing with the glibc test-case, just adding rseq_migrate()
to wake_up_new_task() is sufficient to fix the observed issue. Also add
it to sched_fork() to keep things consistent.

The reason why this never triggered so far with the rseq/basic_test
selftest is unclear.

The current use of sched_getcpu(3) does not typically require it to be
always accurate. However, use of the __rseq_abi.cpu_id field within rseq
critical sections requires it to be accurate. If it is not accurate, it
can cause corruption in the per-cpu data targeted by rseq critical
sections in user-space.

Link: https://sourceware.org/pipermail/libc-alpha/2020-July/115816.html
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Tested-By: Florian Weimer <fweimer@...hat.com>
Cc: Peter Zijlstra (Intel) <peterz@...radead.org>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Florian Weimer <fw@...eb.enyo.de>
Cc: "Paul E. McKenney" <paulmck@...ux.ibm.com>
Cc: Boqun Feng <boqun.feng@...il.com>
Cc: "H . Peter Anvin" <hpa@...or.com>
Cc: Paul Turner <pjt@...gle.com>
Cc: Dmitry Vyukov <dvyukov@...gle.com>
Cc: Neel Natu <neelnatu@...gle.com>
Cc: linux-api@...r.kernel.org
Cc: stable@...r.kernel.org # v4.18+
---
 kernel/sched/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ca5db40392d4..86a855bd4d90 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2962,6 +2962,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -3026,6 +3027,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
-- 
2.17.1