From 71f87b2fc64c2e9b6d53cb817f28711b959d3dfe Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 3 Mar 2016 10:52:10 +0100 Subject: cpu/hotplug: Plug death reporting race Paul noticed that the conversion of the death reporting introduced a race where the outgoing cpu might be delayed after waking the controll processor, so it might not be able to call rcu_report_dead() before being physically removed, leading to RCU stalls. We cant call complete after rcu_report_dead(), so instead of going back to busy polling, simply issue a function call to do the completion. Fixes: 27d50c7eeb0f "rcu: Make CPU_DYING_IDLE an explicit call" Reported-by: Paul E. McKenney Link: http://lkml.kernel.org/r/20160302201127.GA23440@linux.vnet.ibm.com Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra --- kernel/cpu.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'kernel/cpu.c') diff --git a/kernel/cpu.c b/kernel/cpu.c index ff8059b76a85..93e9d89bb0ab 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -755,14 +755,26 @@ static int notify_dead(unsigned int cpu) return 0; } +static void cpuhp_complete_idle_dead(void *arg) +{ + struct cpuhp_cpu_state *st = arg; + + complete(&st->done); +} + void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); - st->state = CPUHP_AP_IDLE_DEAD; - complete(&st->done); rcu_report_dead(smp_processor_id()); + st->state = CPUHP_AP_IDLE_DEAD; + /* + * We cannot call complete after rcu_report_dead() so we delegate it + * to an online cpu. + */ + smp_call_function_single(cpumask_first(cpu_online_mask), + cpuhp_complete_idle_dead, st, 0); } #else -- cgit v1.2.3-55-g7522