From 8038dad7e888581266c76df15d70ca457a3c5910 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 25 Feb 2015 10:34:39 -0800 Subject: smpboot: Add common code for notification from dying CPU RCU ignores offlined CPUs, so they cannot safely run RCU read-side code. (They -can- use SRCU, but not RCU.) This means that any use of RCU during or after the call to arch_cpu_idle_dead(). Unfortunately, commit 2ed53c0d6cc99 added a complete() call, which will contain RCU read-side critical sections if there is a task waiting to be awakened. Which, as it turns out, there almost never is. In my qemu/KVM testing, the to-be-awakened task is not yet asleep more than 99.5% of the time. In current mainline, failure is even harder to reproduce, requiring a virtualized environment that delays the outgoing CPU by at least three jiffies between the time it exits its stop_machine() task at CPU_DYING time and the time it calls arch_cpu_idle_dead() from the idle loop. However, this problem really can occur, especially in virtualized environments, and therefore really does need to be fixed This suggests moving back to the polling loop, but using a much shorter wait, with gentle exponential backoff instead of the old 100-millisecond wait. Most of the time, the loop will exit without waiting at all, and almost all of the remaining uses will wait only five microseconds. If the outgoing CPU is preempted, a loop will wait one jiffy, then increase the wait by a factor of 11/10ths, rounding up. As before, there is a five-second timeout. This commit therefore provides common-code infrastructure to do the dying-to-surviving CPU handoff in a safe manner. This code also provides an indication at CPU-online of whether the CPU to be onlined previously timed out on offline. The new cpu_check_up_prepare() function returns -EBUSY if this CPU previously took more than five seconds to go offline, or -EAGAIN if it has not yet managed to go offline. The rationale for -EAGAIN is that it might still be preempted, so an additional wait might well find it correctly offlined. Architecture-specific code can decide how to handle these conditions. Systems in which CPUs take themselves completely offline might respond to an -EBUSY return as if it was a zero (success) return. Systems in which the surviving CPU must take some action might take it at this time, or might simply mark the other CPU as unusable. Note that architectures that take the easy way out and simply pass the -EBUSY and -EAGAIN upwards will change the sysfs API. Signed-off-by: Paul E. McKenney Cc: Cc: [ paulmck: Fixed state machine for architectures that don't check earlier CPU-hotplug results as suggested by James Hogan. ] --- kernel/smpboot.c | 156 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 156 insertions(+) (limited to 'kernel/smpboot.c') diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 40190f28db35..c697f73d82d6 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -314,3 +315,158 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) put_online_cpus(); } EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); + +static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); + +/* + * Called to poll specified CPU's state, for example, when waiting for + * a CPU to come online. + */ +int cpu_report_state(int cpu) +{ + return atomic_read(&per_cpu(cpu_hotplug_state, cpu)); +} + +/* + * If CPU has died properly, set its state to CPU_UP_PREPARE and + * return success. Otherwise, return -EBUSY if the CPU died after + * cpu_wait_death() timed out. And yet otherwise again, return -EAGAIN + * if cpu_wait_death() timed out and the CPU still hasn't gotten around + * to dying. In the latter two cases, the CPU might not be set up + * properly, but it is up to the arch-specific code to decide. + * Finally, -EIO indicates an unanticipated problem. + * + * Note that it is permissible to omit this call entirely, as is + * done in architectures that do no CPU-hotplug error checking. + */ +int cpu_check_up_prepare(int cpu) +{ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) { + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); + return 0; + } + + switch (atomic_read(&per_cpu(cpu_hotplug_state, cpu))) { + + case CPU_POST_DEAD: + + /* The CPU died properly, so just start it up again. */ + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_UP_PREPARE); + return 0; + + case CPU_DEAD_FROZEN: + + /* + * Timeout during CPU death, so let caller know. + * The outgoing CPU completed its processing, but after + * cpu_wait_death() timed out and reported the error. The + * caller is free to proceed, in which case the state + * will be reset properly by cpu_set_state_online(). + * Proceeding despite this -EBUSY return makes sense + * for systems where the outgoing CPUs take themselves + * offline, with no post-death manipulation required from + * a surviving CPU. + */ + return -EBUSY; + + case CPU_BROKEN: + + /* + * The most likely reason we got here is that there was + * a timeout during CPU death, and the outgoing CPU never + * did complete its processing. This could happen on + * a virtualized system if the outgoing VCPU gets preempted + * for more than five seconds, and the user attempts to + * immediately online that same CPU. Trying again later + * might return -EBUSY above, hence -EAGAIN. + */ + return -EAGAIN; + + default: + + /* Should not happen. Famous last words. */ + return -EIO; + } +} + +/* + * Mark the specified CPU online. + * + * Note that it is permissible to omit this call entirely, as is + * done in architectures that do no CPU-hotplug error checking. + */ +void cpu_set_state_online(int cpu) +{ + (void)atomic_xchg(&per_cpu(cpu_hotplug_state, cpu), CPU_ONLINE); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Wait for the specified CPU to exit the idle loop and die. + */ +bool cpu_wait_death(unsigned int cpu, int seconds) +{ + int jf_left = seconds * HZ; + int oldstate; + bool ret = true; + int sleep_jf = 1; + + might_sleep(); + + /* The outgoing CPU will normally get done quite quickly. */ + if (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) == CPU_DEAD) + goto update_state; + udelay(5); + + /* But if the outgoing CPU dawdles, wait increasingly long times. */ + while (atomic_read(&per_cpu(cpu_hotplug_state, cpu)) != CPU_DEAD) { + schedule_timeout_uninterruptible(sleep_jf); + jf_left -= sleep_jf; + if (jf_left <= 0) + break; + sleep_jf = DIV_ROUND_UP(sleep_jf * 11, 10); + } +update_state: + oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); + if (oldstate == CPU_DEAD) { + /* Outgoing CPU died normally, update state. */ + smp_mb(); /* atomic_read() before update. */ + atomic_set(&per_cpu(cpu_hotplug_state, cpu), CPU_POST_DEAD); + } else { + /* Outgoing CPU still hasn't died, set state accordingly. */ + if (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), + oldstate, CPU_BROKEN) != oldstate) + goto update_state; + ret = false; + } + return ret; +} + +/* + * Called by the outgoing CPU to report its successful death. Return + * false if this report follows the surviving CPU's timing out. + * + * A separate "CPU_DEAD_FROZEN" is used when the surviving CPU + * timed out. This approach allows architectures to omit calls to + * cpu_check_up_prepare() and cpu_set_state_online() without defeating + * the next cpu_wait_death()'s polling loop. + */ +bool cpu_report_death(void) +{ + int oldstate; + int newstate; + int cpu = smp_processor_id(); + + do { + oldstate = atomic_read(&per_cpu(cpu_hotplug_state, cpu)); + if (oldstate != CPU_BROKEN) + newstate = CPU_DEAD; + else + newstate = CPU_DEAD_FROZEN; + } while (atomic_cmpxchg(&per_cpu(cpu_hotplug_state, cpu), + oldstate, newstate) != oldstate); + return newstate == CPU_DEAD; +} + +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ -- cgit v1.2.2