sched, time: Fix lock inversion in thread_group_cputime()

The sig->stats_lock nests inside the tasklist_lock and the
sighand->siglock in __exit_signal and wait_task_zombie.

However, both of those locks can be taken from irq context,
which means we need to use the interrupt safe variant of
read_seqbegin_or_lock. This blocks interrupts when the "lock"
branch is taken (seq is odd), preventing the lock inversion.

On the first (lockless) pass through the loop, irqs are not
blocked.

Reported-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: prarit@redhat.com
Cc: oleg@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1410527535-9814-3-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2b57031afc19fd064db4bd11258f9ea9cef3df38..64492dff8a819fc56ac37c656ac6831c1209d58b 100644 (file)
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -289,13 +289,14 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
        cputime_t utime, stime;
        struct task_struct *t;
        unsigned int seq, nextseq;
+       unsigned long flags;
 
        rcu_read_lock();
        /* Attempt a lockless read on the first round. */
        nextseq = 0;
        do {
                seq = nextseq;
-               read_seqbegin_or_lock(&sig->stats_lock, &seq);
+               flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
                times->utime = sig->utime;
                times->stime = sig->stime;
                times->sum_exec_runtime = sig->sum_sched_runtime;
@@ -309,7 +310,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
                /* If lockless access failed, take the lock. */
                nextseq = 1;
        } while (need_seqretry(&sig->stats_lock, seq));
-       done_seqretry(&sig->stats_lock, seq);
+       done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
        rcu_read_unlock();
 }