From 416eb33cd60ef405e2860a186364e57bcb2d89f6 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 7 Oct 2011 16:31:02 -0700 Subject: [PATCH] rcu: Fix early call to rcu_idle_enter() On the irq exit path, tick_nohz_irq_exit() may raise a softirq, which action leads to the wake up path and select_task_rq_fair() that makes use of rcu to iterate the domains. This is an illegal use of RCU because we may be in RCU extended quiescent state if we interrupted an RCU-idle window in the idle loop: [ 132.978883] =============================== [ 132.978883] [ INFO: suspicious RCU usage. ] [ 132.978883] ------------------------------- [ 132.978883] kernel/sched_fair.c:1707 suspicious rcu_dereference_check() usage! [ 132.978883] [ 132.978883] other info that might help us debug this: [ 132.978883] [ 132.978883] [ 132.978883] rcu_scheduler_active = 1, debug_locks = 0 [ 132.978883] RCU used illegally from extended quiescent state! [ 132.978883] 2 locks held by swapper/0: [ 132.978883] #0: (&p->pi_lock){-.-.-.}, at: [] try_to_wake_up+0x39/0x2f0 [ 132.978883] #1: (rcu_read_lock){.+.+..}, at: [] select_task_rq_fair+0x6a/0xec0 [ 132.978883] [ 132.978883] stack backtrace: [ 132.978883] Pid: 0, comm: swapper Tainted: G W 3.0.0+ #178 [ 132.978883] Call Trace: [ 132.978883] [] lockdep_rcu_suspicious+0xe6/0x100 [ 132.978883] [] select_task_rq_fair+0x749/0xec0 [ 132.978883] [] ? select_task_rq_fair+0x6a/0xec0 [ 132.978883] [] ? do_raw_spin_lock+0x54/0x150 [ 132.978883] [] ? trace_hardirqs_on+0xd/0x10 [ 132.978883] [] try_to_wake_up+0xd3/0x2f0 [ 132.978883] [] ? ktime_get+0x68/0xf0 [ 132.978883] [] wake_up_process+0x15/0x20 [ 132.978883] [] raise_softirq_irqoff+0x65/0x110 [ 132.978883] [] __hrtimer_start_range_ns+0x415/0x5a0 [ 132.978883] [] ? do_raw_spin_unlock+0x5e/0xb0 [ 132.978883] [] hrtimer_start+0x18/0x20 [ 132.978883] [] tick_nohz_stop_sched_tick+0x393/0x450 [ 132.978883] [] irq_exit+0xd2/0x100 [ 132.978883] [] do_IRQ+0x66/0xe0 [ 132.978883] [] common_interrupt+0x13/0x13 [ 132.978883] [] ? native_safe_halt+0xb/0x10 [ 132.978883] [] ? trace_hardirqs_on+0xd/0x10 [ 132.978883] [] default_idle+0xba/0x370 [ 132.978883] [] amd_e400_idle+0x5e/0x130 [ 132.978883] [] cpu_idle+0xb6/0x120 [ 132.978883] [] rest_init+0xef/0x150 [ 132.978883] [] ? rest_init+0x52/0x150 [ 132.978883] [] start_kernel+0x3da/0x3e5 [ 132.978883] [] x86_64_start_reservations+0x131/0x135 [ 132.978883] [] x86_64_start_kernel+0x103/0x112 Fix this by calling rcu_idle_enter() after tick_nohz_irq_exit(). Signed-off-by: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/softirq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/softirq.c b/kernel/softirq.c index f9f2aa81ce53..4eb3a0fa351e 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -347,12 +347,12 @@ void irq_exit(void) if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); - rcu_irq_exit(); #ifdef CONFIG_NO_HZ /* Make sure that timer wheel updates are propagated */ if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) tick_nohz_irq_exit(); #endif + rcu_irq_exit(); preempt_enable_no_resched(); }