From d689fe222a858c767cb8594faf280048e532b53f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 13 Nov 2013 21:01:57 +0100 Subject: NOHZ: Check for nohz active instead of nohz enabled RCU and the fine grained idle time accounting functions check tick_nohz_enabled. But that variable is merily telling that NOHZ has been enabled in the config and not been disabled on the command line. But it does not tell anything about nohz being active. That's what all this should check for. Matthew reported, that the idle accounting on his old P1 machine showed bogus values, when he enabled NOHZ in the config and did not disable it on the kernel command line. The reason is that his machine uses (refined) jiffies as a clocksource which explains why the "fine" grained accounting went into lala land, because it depends on when the system goes and leaves idle relative to the jiffies increment. Provide a tick_nohz_active indicator and let RCU and the accounting code use this instead of tick_nohz_enable. Reported-and-tested-by: Matthew Whitehead Signed-off-by: Thomas Gleixner Reviewed-by: Steven Rostedt Reviewed-by: Paul E. McKenney Cc: john.stultz@linaro.org Cc: mwhitehe@redhat.com Link: http://lkml.kernel.org/r/alpine.DEB.2.02.1311132052240.30673@ionos.tec.linutronix.de --- kernel/time/tick-sched.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) (limited to 'kernel/time/tick-sched.c') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 3612fc77f834..a12df5abde0b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -361,8 +361,8 @@ void __init tick_nohz_init(void) /* * NO HZ enabled ? */ -int tick_nohz_enabled __read_mostly = 1; - +static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ @@ -465,7 +465,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t now, idle; - if (!tick_nohz_enabled) + if (!tick_nohz_active) return -1; now = ktime_get(); @@ -506,7 +506,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); ktime_t now, iowait; - if (!tick_nohz_enabled) + if (!tick_nohz_active) return -1; now = ktime_get(); @@ -799,11 +799,6 @@ void tick_nohz_idle_enter(void) local_irq_disable(); ts = &__get_cpu_var(tick_cpu_sched); - /* - * set ts->inidle unconditionally. even if the system did not - * switch to nohz mode the cpu frequency governers rely on the - * update of the idle time accounting in tick_nohz_start_idle(). - */ ts->inidle = 1; __tick_nohz_idle_enter(ts); @@ -973,7 +968,7 @@ static void tick_nohz_switch_to_nohz(void) struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); ktime_t next; - if (!tick_nohz_enabled) + if (!tick_nohz_active) return; local_irq_disable(); @@ -981,7 +976,7 @@ static void tick_nohz_switch_to_nohz(void) local_irq_enable(); return; } - + tick_nohz_active = 1; ts->nohz_mode = NOHZ_MODE_LOWRES; /* @@ -1139,8 +1134,10 @@ void tick_setup_sched_timer(void) } #ifdef CONFIG_NO_HZ_COMMON - if (tick_nohz_enabled) + if (tick_nohz_enabled) { ts->nohz_mode = NOHZ_MODE_HIGHRES; + tick_nohz_active = 1; + } #endif } #endif /* HIGH_RES_TIMERS */ -- cgit From 0e576acbc1d9600cf2d9b4a141a2554639959d50 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 29 Nov 2013 12:18:13 +0100 Subject: nohz: Fix another inconsistency between CONFIG_NO_HZ=n and nohz=off If CONFIG_NO_HZ=n tick_nohz_get_sleep_length() returns NSEC_PER_SEC/HZ. If CONFIG_NO_HZ=y and the nohz functionality is disabled via the command line option "nohz=off" or not enabled due to missing hardware support, then tick_nohz_get_sleep_length() returns 0. That happens because ts->sleep_length is never set in that case. Set it to NSEC_PER_SEC/HZ when the NOHZ mode is inactive. Reported-by: Michal Hocko Reported-by: Borislav Petkov Signed-off-by: Thomas Gleixner --- kernel/time/tick-sched.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/time/tick-sched.c') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index a12df5abde0b..ea20f7d1ac2c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -711,8 +711,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) + if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) { + ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ }; return false; + } if (need_resched()) return false; -- cgit