Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760384AbXIOJt5 (ORCPT ); Sat, 15 Sep 2007 05:49:57 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753634AbXIOJtu (ORCPT ); Sat, 15 Sep 2007 05:49:50 -0400 Received: from www.osadl.org ([213.239.205.134]:53730 "EHLO mail.tglx.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753238AbXIOJtt (ORCPT ); Sat, 15 Sep 2007 05:49:49 -0400 Subject: Re: cpu hotplug support broken in 2.6.23-rc3 From: Thomas Gleixner To: Pavel Machek Cc: "Rafael J. Wysocki" , Jeff Chua , rusty@rustycorp.com.au, vatsa@in.ibm.com, zwane@arm.linux.org.uk, kernel list , Len Brown In-Reply-To: <1189775743.3100.9.camel@chaos> References: <20070827104350.GA2073@elf.ucw.cz> <20070903034720.GB3655@ucw.cz> <200709031219.12846.rjw@sisk.pl> <1188822917.3406.0.camel@chaos> <20070904072744.GA30474@atrey.karlin.mff.cuni.cz> <1189713695.3974.23.camel@chaos> <20070914123816.GE1671@elf.ucw.cz> <1189774257.3100.7.camel@chaos> <1189775743.3100.9.camel@chaos> Content-Type: text/plain Date: Sat, 15 Sep 2007 11:49:41 +0200 Message-Id: <1189849781.4319.5.camel@chaos> Mime-Version: 1.0 X-Mailer: Evolution 2.11.92 (2.11.92-1.fc8) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6437 Lines: 196 Pavel, On Fri, 2007-09-14 at 15:15 +0200, Thomas Gleixner wrote: > > Venki sent me an initial patch, but it has issues with the notify > > ordering. Find below my "cache the broadcast flags" version for testing. > > Hmmpf, the flag is still cleared when the cpu goes offline. Need to take > a closer look. I finally tracked it down. There were several ways to turn the box into a brick. Sigh ! Can you please test the combo patch below ? The details are available from the for-2.6.23 branch of my hrt git repo: http://git.kernel.org/?p=linux/kernel/git/tglx/linux-2.6-hrt.git;a=shortlog;h=for-2.6.23 Thanks, tglx Index: linux-2.6/kernel/time/timekeeping.c =================================================================== --- linux-2.6.orig/kernel/time/timekeeping.c 2007-09-15 11:42:09.000000000 +0200 +++ linux-2.6/kernel/time/timekeeping.c 2007-09-15 11:43:03.000000000 +0200 @@ -217,6 +217,7 @@ static void change_clocksource(void) } #else static inline void change_clocksource(void) { } +static inline s64 __get_nsec_offset(void) { return 0; } #endif /** @@ -280,6 +281,8 @@ void __init timekeeping_init(void) static int timekeeping_suspended; /* time in seconds when suspend began */ static unsigned long timekeeping_suspend_time; +/* xtime offset when we went into suspend */ +static s64 timekeeping_suspend_nsecs; /** * timekeeping_resume - Resumes the generic timekeeping subsystem. @@ -305,6 +308,8 @@ static int timekeeping_resume(struct sys wall_to_monotonic.tv_sec -= sleep_length; total_sleep_time += sleep_length; } + /* Make sure that we have the correct xtime reference */ + timespec_add_ns(&xtime, timekeeping_suspend_nsecs); /* re-base the last cycle value */ clock->cycle_last = clocksource_read(clock); clock->error = 0; @@ -325,9 +330,12 @@ static int timekeeping_suspend(struct sy { unsigned long flags; + timekeeping_suspend_time = read_persistent_clock(); + write_seqlock_irqsave(&xtime_lock, flags); + /* Get the current xtime offset */ + timekeeping_suspend_nsecs = __get_nsec_offset(); timekeeping_suspended = 1; - timekeeping_suspend_time = read_persistent_clock(); write_sequnlock_irqrestore(&xtime_lock, flags); clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); Index: linux-2.6/drivers/acpi/processor_core.c =================================================================== --- linux-2.6.orig/drivers/acpi/processor_core.c 2007-09-15 11:42:09.000000000 +0200 +++ linux-2.6/drivers/acpi/processor_core.c 2007-09-15 11:43:03.000000000 +0200 @@ -724,6 +724,25 @@ static void acpi_processor_notify(acpi_h return; } +static int acpi_cpu_soft_notify(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + struct acpi_processor *pr = processors[cpu]; + + if (action == CPU_ONLINE && pr) { + acpi_processor_ppc_has_changed(pr); + acpi_processor_cst_has_changed(pr); + acpi_processor_tstate_has_changed(pr); + } + return NOTIFY_OK; +} + +static struct notifier_block acpi_cpu_notifier = +{ + .notifier_call = acpi_cpu_soft_notify, +}; + static int acpi_processor_add(struct acpi_device *device) { struct acpi_processor *pr = NULL; @@ -987,6 +1006,7 @@ void acpi_processor_install_hotplug_noti ACPI_UINT32_MAX, processor_walk_namespace_cb, &action, NULL); #endif + register_hotcpu_notifier(&acpi_cpu_notifier); } static @@ -999,6 +1019,7 @@ void acpi_processor_uninstall_hotplug_no ACPI_UINT32_MAX, processor_walk_namespace_cb, &action, NULL); #endif + unregister_hotcpu_notifier(&acpi_cpu_notifier); } /* Index: linux-2.6/kernel/time/tick-broadcast.c =================================================================== --- linux-2.6.orig/kernel/time/tick-broadcast.c 2007-09-15 11:42:09.000000000 +0200 +++ linux-2.6/kernel/time/tick-broadcast.c 2007-09-15 11:43:03.000000000 +0200 @@ -382,12 +382,23 @@ static int tick_broadcast_set_event(ktim int tick_resume_broadcast_oneshot(struct clock_event_device *bc) { + int cpu = smp_processor_id(); + + /* + * If the CPU is marked for broadcast, enforce oneshot + * broadcast mode. The jinxed VAIO does not resume otherwise. + * No idea why it ends up in a lower C State during resume + * without notifying the clock events layer. + */ + if (cpu_isset(cpu, tick_broadcast_mask)) + cpu_set(cpu, tick_broadcast_oneshot_mask); + clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT); if(!cpus_empty(tick_broadcast_oneshot_mask)) tick_broadcast_set_event(ktime_get(), 1); - return cpu_isset(smp_processor_id(), tick_broadcast_oneshot_mask); + return cpu_isset(cpu, tick_broadcast_oneshot_mask); } /* @@ -549,20 +560,17 @@ void tick_broadcast_switch_to_oneshot(vo */ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { - struct clock_event_device *bc; unsigned long flags; unsigned int cpu = *cpup; spin_lock_irqsave(&tick_broadcast_lock, flags); - bc = tick_broadcast_device.evtdev; + /* + * Clear the broadcast mask flag for the dead cpu, but do not + * stop the broadcast device! + */ cpu_clear(cpu, tick_broadcast_oneshot_mask); - if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) { - if (bc && cpus_empty(tick_broadcast_oneshot_mask)) - clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN); - } - spin_unlock_irqrestore(&tick_broadcast_lock, flags); } Index: linux-2.6/kernel/time/tick-sched.c =================================================================== --- linux-2.6.orig/kernel/time/tick-sched.c 2007-09-15 11:42:09.000000000 +0200 +++ linux-2.6/kernel/time/tick-sched.c 2007-09-15 11:43:41.000000000 +0200 @@ -160,6 +160,18 @@ void tick_nohz_stop_sched_tick(void) cpu = smp_processor_id(); ts = &per_cpu(tick_cpu_sched, cpu); + /* + * If this cpu is offline and it is the one which updates + * jiffies, then give up the assignment and let it be taken by + * the cpu which runs the tick timer next. If we don't drop + * this here the jiffies might be stale and do_timer() never + * invoked. + */ + if (unlikely(!cpu_online(cpu))) { + if (cpu == tick_do_timer_cpu) + tick_do_timer_cpu = -1; + } + if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) goto end; - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/