| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 22 Aug 2011 10:02:31 +0800
From: Guan Xuetao <gxt@...c.pku.edu.cn>
To: Frederic Weisbecker <fweisbec@...il.com>
Cc: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
LKML <linux-kernel@...r.kernel.org>,
David Miller <davem@...emloft.net>,
Chris Metcalf <cmetcalf@...era.com>,
Hans-Christian Egtvedt <hans-christian.egtvedt@...el.com>,
Mike Frysinger <vapier@...too.org>,
Ralf Baechle <ralf@...ux-mips.org>,
Ingo Molnar <mingo@...e.hu>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Thomas Gleixner <tglx@...utronix.de>,
"H. Peter Anvin" <hpa@...or.com>,
Russell King <linux@....linux.org.uk>,
Paul Mackerras <paulus@...ba.org>,
Heiko Carstens <heiko.carstens@...ibm.com>,
Paul Mundt <lethal@...ux-sh.org>
Subject: Re: [PATCH 1/4] nohz: Split extended quiescent state handling from
nohz switch
Acked-by: Guan Xuetao <gxt@...c.pku.edu.cn>
Thanks,
Guan Xuetao
On Sat, 2011-08-20 at 19:30 +0200, Frederic Weisbecker wrote:
> It is assumed that rcu won't be used once we switch to tickless
> mode and until we restart the tick. However this is not always
> true, as in x86-64 where we dereference the idle notifiers after
> the tick is stopped.
>
> To prepare for fixing this, split the tickless mode switching and
> RCU extended quiescent state logics.
> Make tick_nohz_stop/restart_sched_tick() RCU agnostic but provide
> a new pair of APIs tick_nohz_enter/exit_idle() that keep the
> old behaviour by handling both the nohz mode and RCU extended
> quiescent states, then convert every archs to use these.
>
> Archs that want to switch to RCU extended QS to some custom points
> can do it later by changing the parameter in tick_nohz_enter,exit_idle()
> to false and call rcu_enter,exit() separately.
>
> Signed-off-by: Frederic Weisbecker <fweisbec@...il.com>
> Cc: David Miller <davem@...emloft.net>
> Cc: Chris Metcalf <cmetcalf@...era.com>
> Cc: Guan Xuetao <gxt@...c.pku.edu.cn>
> Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@...el.com>
> Cc: Mike Frysinger <vapier@...too.org>
> Cc: Ralf Baechle <ralf@...ux-mips.org>
> Cc: Paul E. McKenney <paulmck@...ux.vnet.ibm.com>
> Cc: Ingo Molnar <mingo@...e.hu>
> Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>
> Cc: Thomas Gleixner <tglx@...utronix.de>
> Cc: H. Peter Anvin <hpa@...or.com>
> Cc: Russell King <linux@....linux.org.uk>
> Cc: Paul Mackerras <paulus@...ba.org>
> Cc: Heiko Carstens <heiko.carstens@...ibm.com>
> Cc: Paul Mundt <lethal@...ux-sh.org>
> ---
> arch/arm/kernel/process.c | 4 ++--
> arch/avr32/kernel/process.c | 4 ++--
> arch/blackfin/kernel/process.c | 4 ++--
> arch/microblaze/kernel/process.c | 4 ++--
> arch/mips/kernel/process.c | 4 ++--
> arch/powerpc/kernel/idle.c | 4 ++--
> arch/powerpc/platforms/iseries/setup.c | 8 ++++----
> arch/s390/kernel/process.c | 4 ++--
> arch/sh/kernel/idle.c | 2 +-
> arch/sparc/kernel/process_64.c | 4 ++--
> arch/tile/kernel/process.c | 4 ++--
> arch/um/kernel/process.c | 4 ++--
> arch/unicore32/kernel/process.c | 4 ++--
> arch/x86/kernel/process_32.c | 4 ++--
> arch/x86/kernel/process_64.c | 4 ++--
> include/linux/tick.h | 9 +++++----
> kernel/time/tick-sched.c | 31 ++++++++++++++++++++++++++-----
> 17 files changed, 62 insertions(+), 40 deletions(-)
>
> diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
> index 5e1e541..4d2e33e 100644
> --- a/arch/arm/kernel/process.c
> +++ b/arch/arm/kernel/process.c
> @@ -182,7 +182,7 @@ void cpu_idle(void)
>
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> leds_event(led_idle_start);
> while (!need_resched()) {
> #ifdef CONFIG_HOTPLUG_CPU
> @@ -208,7 +208,7 @@ void cpu_idle(void)
> }
> }
> leds_event(led_idle_end);
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
> index ef5a2a0..a8fd60b 100644
> --- a/arch/avr32/kernel/process.c
> +++ b/arch/avr32/kernel/process.c
> @@ -34,10 +34,10 @@ void cpu_idle(void)
> {
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched())
> cpu_idle_sleep();
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
> index 6a660fa..e032471 100644
> --- a/arch/blackfin/kernel/process.c
> +++ b/arch/blackfin/kernel/process.c
> @@ -88,10 +88,10 @@ void cpu_idle(void)
> #endif
> if (!idle)
> idle = default_idle;
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched())
> idle();
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
> index 968648a..7134887 100644
> --- a/arch/microblaze/kernel/process.c
> +++ b/arch/microblaze/kernel/process.c
> @@ -103,10 +103,10 @@ void cpu_idle(void)
> if (!idle)
> idle = default_idle;
>
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched())
> idle();
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
>
> preempt_enable_no_resched();
> schedule();
> diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
> index d2112d3..d79e7d3 100644
> --- a/arch/mips/kernel/process.c
> +++ b/arch/mips/kernel/process.c
> @@ -56,7 +56,7 @@ void __noreturn cpu_idle(void)
>
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched() && cpu_online(cpu)) {
> #ifdef CONFIG_MIPS_MT_SMTC
> extern void smtc_idle_loop_hook(void);
> @@ -77,7 +77,7 @@ void __noreturn cpu_idle(void)
> system_state == SYSTEM_BOOTING))
> play_dead();
> #endif
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
> index 39a2baa..b30ddf1 100644
> --- a/arch/powerpc/kernel/idle.c
> +++ b/arch/powerpc/kernel/idle.c
> @@ -56,7 +56,7 @@ void cpu_idle(void)
>
> set_thread_flag(TIF_POLLING_NRFLAG);
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched() && !cpu_should_die()) {
> ppc64_runlatch_off();
>
> @@ -93,7 +93,7 @@ void cpu_idle(void)
>
> HMT_medium();
> ppc64_runlatch_on();
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> if (cpu_should_die())
> cpu_die();
> diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
> index c25a081..aa2be7d 100644
> --- a/arch/powerpc/platforms/iseries/setup.c
> +++ b/arch/powerpc/platforms/iseries/setup.c
> @@ -562,7 +562,7 @@ static void yield_shared_processor(void)
> static void iseries_shared_idle(void)
> {
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched() && !hvlpevent_is_pending()) {
> local_irq_disable();
> ppc64_runlatch_off();
> @@ -576,7 +576,7 @@ static void iseries_shared_idle(void)
> }
>
> ppc64_runlatch_on();
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
>
> if (hvlpevent_is_pending())
> process_iSeries_events();
> @@ -592,7 +592,7 @@ static void iseries_dedicated_idle(void)
> set_thread_flag(TIF_POLLING_NRFLAG);
>
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> if (!need_resched()) {
> while (!need_resched()) {
> ppc64_runlatch_off();
> @@ -609,7 +609,7 @@ static void iseries_dedicated_idle(void)
> }
>
> ppc64_runlatch_on();
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
> index 541a750..b19f7b2 100644
> --- a/arch/s390/kernel/process.c
> +++ b/arch/s390/kernel/process.c
> @@ -90,10 +90,10 @@ static void default_idle(void)
> void cpu_idle(void)
> {
> for (;;) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched())
> default_idle();
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
> index 425d604..d8997ac 100644
> --- a/arch/sh/kernel/idle.c
> +++ b/arch/sh/kernel/idle.c
> @@ -88,7 +88,7 @@ void cpu_idle(void)
>
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
>
> while (!need_resched()) {
> check_pgt_cache();
> diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
> index c158a95..986d019 100644
> --- a/arch/sparc/kernel/process_64.c
> +++ b/arch/sparc/kernel/process_64.c
> @@ -95,12 +95,12 @@ void cpu_idle(void)
> set_thread_flag(TIF_POLLING_NRFLAG);
>
> while(1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
>
> while (!need_resched() && !cpu_is_offline(cpu))
> sparc64_yield(cpu);
>
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
>
> preempt_enable_no_resched();
>
> diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
> index 9c45d8b..63fc9c0 100644
> --- a/arch/tile/kernel/process.c
> +++ b/arch/tile/kernel/process.c
> @@ -85,7 +85,7 @@ void cpu_idle(void)
>
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched()) {
> if (cpu_is_offline(cpu))
> BUG(); /* no HOTPLUG_CPU */
> @@ -105,7 +105,7 @@ void cpu_idle(void)
> local_irq_enable();
> current_thread_info()->status |= TS_POLLING;
> }
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
> index fab4371..c18786f 100644
> --- a/arch/um/kernel/process.c
> +++ b/arch/um/kernel/process.c
> @@ -245,10 +245,10 @@ void default_idle(void)
> if (need_resched())
> schedule();
>
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> nsecs = disable_timer();
> idle_sleep(nsecs);
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> }
> }
>
> diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
> index ba401df..353b047 100644
> --- a/arch/unicore32/kernel/process.c
> +++ b/arch/unicore32/kernel/process.c
> @@ -55,7 +55,7 @@ void cpu_idle(void)
> {
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched()) {
> local_irq_disable();
> stop_critical_timings();
> @@ -63,7 +63,7 @@ void cpu_idle(void)
> local_irq_enable();
> start_critical_timings();
> }
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
> index a3d0dc5..2cbf235 100644
> --- a/arch/x86/kernel/process_32.c
> +++ b/arch/x86/kernel/process_32.c
> @@ -97,7 +97,7 @@ void cpu_idle(void)
>
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched()) {
>
> check_pgt_cache();
> @@ -112,7 +112,7 @@ void cpu_idle(void)
> pm_idle();
> start_critical_timings();
> }
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
> index ca6f7ab..3d56f0d 100644
> --- a/arch/x86/kernel/process_64.c
> +++ b/arch/x86/kernel/process_64.c
> @@ -120,7 +120,7 @@ void cpu_idle(void)
>
> /* endless idle loop with no priority at all */
> while (1) {
> - tick_nohz_stop_sched_tick(1);
> + tick_nohz_enter_idle(true);
> while (!need_resched()) {
>
> rmb();
> @@ -145,7 +145,7 @@ void cpu_idle(void)
> __exit_idle();
> }
>
> - tick_nohz_restart_sched_tick();
> + tick_nohz_exit_idle(true);
> preempt_enable_no_resched();
> schedule();
> preempt_disable();
> diff --git a/include/linux/tick.h b/include/linux/tick.h
> index b232ccc..4cbbcbb 100644
> --- a/include/linux/tick.h
> +++ b/include/linux/tick.h
> @@ -121,14 +121,15 @@ static inline int tick_oneshot_mode_active(void) { return 0; }
> #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
>
> # ifdef CONFIG_NO_HZ
> -extern void tick_nohz_stop_sched_tick(int inidle);
> -extern void tick_nohz_restart_sched_tick(void);
> +extern bool tick_nohz_stop_sched_tick(int inidle);
> +extern void tick_nohz_enter_idle(bool rcu_ext_qs);
> +extern void tick_nohz_exit_idle(bool rcu_ext_qs);
> extern ktime_t tick_nohz_get_sleep_length(void);
> extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
> extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
> # else
> -static inline void tick_nohz_stop_sched_tick(int inidle) { }
> -static inline void tick_nohz_restart_sched_tick(void) { }
> +static inline void tick_nohz_enter_idle(bool rcu_ext_qs) { }
> +static inline void tick_nohz_exit_idle(bool rcu_ext_qs) { }
> static inline ktime_t tick_nohz_get_sleep_length(void)
> {
> ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index eb98e55..609bb20 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -253,12 +253,13 @@ EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
> * Called either from the idle loop or from irq_exit() when an idle period was
> * just interrupted by an interrupt which did not cause a reschedule.
> */
> -void tick_nohz_stop_sched_tick(int inidle)
> +bool tick_nohz_stop_sched_tick(int inidle)
> {
> unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags;
> struct tick_sched *ts;
> ktime_t last_update, expires, now;
> struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
> + int stopped = false;
> u64 time_delta;
> int cpu;
>
> @@ -405,7 +406,7 @@ void tick_nohz_stop_sched_tick(int inidle)
> ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
> ts->tick_stopped = 1;
> ts->idle_jiffies = last_jiffies;
> - rcu_enter_nohz();
> + stopped = true;
> }
>
> ts->idle_sleeps++;
> @@ -445,6 +446,24 @@ out:
> ts->sleep_length = ktime_sub(dev->next_event, now);
> end:
> local_irq_restore(flags);
> +
> + return stopped;
> +}
> +
> +
> +/**
> + * tick_nohz_enter_idle - stop the tick from the idle task
> + * @rcu_ext_qs: enter rcu dynticks idle mode
> + *
> + * When an arch doesn't make any use of rcu read side critical section
> + * between tick_nohz_enter_idle() and tick_nohz_exit_idle() it can set
> + * rcu_ext_qs to 1. Otherwise it needs to call rcu_enter_nohz() itself
> + * later before the CPU goes to sleep.
> + */
> +void tick_nohz_enter_idle(bool rcu_ext_qs)
> +{
> + if (tick_nohz_stop_sched_tick(1) && rcu_ext_qs)
> + rcu_enter_nohz();
> }
>
> /**
> @@ -486,11 +505,12 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
> }
>
> /**
> - * tick_nohz_restart_sched_tick - restart the idle tick from the idle task
> + * tick_nohz_exit_idle - restart the idle tick from the idle task
> + * @rcu_ext_qs: exit rcu dynticks idle mode
> *
> * Restart the idle tick when the CPU is woken up from idle
> */
> -void tick_nohz_restart_sched_tick(void)
> +void tick_nohz_exit_idle(bool rcu_ext_qs)
> {
> int cpu = smp_processor_id();
> struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
> @@ -514,7 +534,8 @@ void tick_nohz_restart_sched_tick(void)
>
> ts->inidle = 0;
>
> - rcu_exit_nohz();
> + if (rcu_ext_qs)
> + rcu_exit_nohz();
>
> /* Update jiffies first */
> select_nohz_load_balancer(0);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists