From 379d9ecb3cc9d5d043216185904c00e54c736a96 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 30 Jun 2016 10:37:20 -0700 Subject: [PATCH] sched: Make wake_up_nohz_cpu() handle CPUs going offline Both timers and hrtimers are maintained on the outgoing CPU until CPU_DEAD time, at which point they are migrated to a surviving CPU. If a mod_timer() executes between CPU_DYING and CPU_DEAD time, x86 systems will splat in native_smp_send_reschedule() when attempting to wake up the just-now-offlined CPU, as shown below from a NO_HZ_FULL kernel: [ 7976.741556] WARNING: CPU: 0 PID: 661 at /home/paulmck/public_git/linux-rcu/arch/x86/kernel/smp.c:125 native_smp_send_reschedule+0x39/0x40 [ 7976.741595] Modules linked in: [ 7976.741595] CPU: 0 PID: 661 Comm: rcu_torture_rea Not tainted 4.7.0-rc2+ #1 [ 7976.741595] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 [ 7976.741595] 0000000000000000 ffff88000002fcc8 ffffffff8138ab2e 0000000000000000 [ 7976.741595] 0000000000000000 ffff88000002fd08 ffffffff8105cabc 0000007d1fd0ee18 [ 7976.741595] 0000000000000001 ffff88001fd16d40 ffff88001fd0ee00 ffff88001fd0ee00 [ 7976.741595] Call Trace: [ 7976.741595] [] dump_stack+0x67/0x99 [ 7976.741595] [] __warn+0xcc/0xf0 [ 7976.741595] [] warn_slowpath_null+0x18/0x20 [ 7976.741595] [] native_smp_send_reschedule+0x39/0x40 [ 7976.741595] [] wake_up_nohz_cpu+0x82/0x190 [ 7976.741595] [] internal_add_timer+0x7a/0x80 [ 7976.741595] [] mod_timer+0x187/0x2b0 [ 7976.741595] [] rcu_torture_reader+0x33d/0x380 [ 7976.741595] [] ? sched_torture_read_unlock+0x30/0x30 [ 7976.741595] [] ? rcu_bh_torture_read_lock+0x80/0x80 [ 7976.741595] [] kthread+0xdf/0x100 [ 7976.741595] [] ret_from_fork+0x1f/0x40 [ 7976.741595] [] ? kthread_create_on_node+0x200/0x200 However, in this case, the wakeup is redundant, because the timer migration will reprogram timer hardware as needed. Note that the fact that preemption is disabled does not avoid the splat, as the offline operation has already passed both the synchronize_sched() and the stop_machine() that would be blocked by disabled preemption. This commit therefore modifies wake_up_nohz_cpu() to avoid attempting to wake up offline CPUs. It also adds a comment stating that the caller must tolerate lost wakeups when the target CPU is going offline, and suggesting the CPU_DEAD notifier as a recovery mechanism. Signed-off-by: Paul E. McKenney Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Thomas Gleixner --- kernel/sched/core.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5c883fe8e440..2a18856f00ab 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -580,6 +580,8 @@ static bool wake_up_full_nohz_cpu(int cpu) * If needed we can still optimize that later with an * empty IRQ. */ + if (cpu_is_offline(cpu)) + return true; /* Don't try to wake offline CPUs. */ if (tick_nohz_full_cpu(cpu)) { if (cpu != smp_processor_id() || tick_nohz_tick_stopped()) @@ -590,6 +592,11 @@ static bool wake_up_full_nohz_cpu(int cpu) return false; } +/* + * Wake up the specified CPU. If the CPU is going offline, it is the + * caller's responsibility to deal with the lost wakeup, for example, + * by hooking into the CPU_DEAD notifier like timers and hrtimers do. + */ void wake_up_nohz_cpu(int cpu) { if (!wake_up_full_nohz_cpu(cpu)) -- GitLab