From 2e70933866ace52091a3c11a5c104c063ab0c445 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Jul 2013 00:55:25 +0200 Subject: nohz: Only enable context tracking on full dynticks CPUs The context tracking subsystem has the ability to selectively enable the tracking on any defined subset of CPU. This means that we can define a CPU range that doesn't run the context tracking and another range that does. Now what we want in practice is to enable the tracking on full dynticks CPUs only. In order to perform this, we just need to pass our full dynticks CPU range selection from the full dynticks subsystem to the context tracking. This way we can spare the overhead of RCU user extended quiescent state and vtime maintainance on the CPUs that are outside the full dynticks range. Just keep in mind the raw context tracking itself is still necessary everywhere. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- kernel/time/tick-sched.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel/time') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9563c744dad2..91a2528b5f44 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -344,11 +345,16 @@ static int tick_nohz_init_all(void) void __init tick_nohz_init(void) { + int cpu; + if (!have_nohz_full_mask) { if (tick_nohz_init_all() < 0) return; } + for_each_cpu(cpu, nohz_full_mask) + context_tracking_cpu_set(cpu); + cpu_notifier(tick_nohz_cpu_down_callback, 0); cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask); pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); -- cgit v1.2.3 From d84d27a491880b9902b45c09be8d9e9464fb9b74 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 21:59:29 +0200 Subject: context_tracking: Remove full dynticks' hacky dependency on wide context tracking Now that the full dynticks subsystem only enables the context tracking on full dynticks CPUs, lets remove the dependency on CONTEXT_TRACKING_FORCE This dependency was a hack to enable the context tracking widely for the full dynticks susbsystem until the latter becomes able to enable it in a more CPU-finegrained fashion. Now CONTEXT_TRACKING_FORCE only stands for testing on archs that work on support for the context tracking while full dynticks can't be used yet due to unmet dependencies. It simulates a system where all CPUs are full dynticks so that RCU user extended quiescent states and dynticks cputime accounting can be tested on the given arch. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- kernel/time/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/time') diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 70f27e89012b..747bbc70f53b 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -105,7 +105,6 @@ config NO_HZ_FULL select RCU_USER_QS select RCU_NOCB_CPU select VIRT_CPU_ACCOUNTING_GEN - select CONTEXT_TRACKING_FORCE select IRQ_WORK help Adaptively try to shutdown the tick whenever possible, even when -- cgit v1.2.3 From 73867dcd0792ad14fb31bfe73d09d9a4576f7fc2 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:31:00 +0200 Subject: nohz: Rename a few state variables Rename the full dynticks's cpumask and cpumask state variables to some more exportable names. These will be used later from global headers to optimize the main full dynticks APIs in conjunction with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- kernel/time/tick-sched.c | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 91a2528b5f44..b28dee43e644 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -149,8 +149,8 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) } #ifdef CONFIG_NO_HZ_FULL -static cpumask_var_t nohz_full_mask; -bool have_nohz_full_mask; +static cpumask_var_t tick_nohz_full_mask; +bool tick_nohz_full_running; static bool can_stop_full_tick(void) { @@ -183,7 +183,7 @@ static bool can_stop_full_tick(void) * Don't allow the user to think they can get * full NO_HZ with this machine. */ - WARN_ONCE(have_nohz_full_mask, + WARN_ONCE(tick_nohz_full_running, "NO_HZ FULL will not work with unstable sched clock"); return false; } @@ -240,11 +240,11 @@ static void nohz_full_kick_ipi(void *info) */ void tick_nohz_full_kick_all(void) { - if (!have_nohz_full_mask) + if (!tick_nohz_full_running) return; preempt_disable(); - smp_call_function_many(nohz_full_mask, + smp_call_function_many(tick_nohz_full_mask, nohz_full_kick_ipi, NULL, false); preempt_enable(); } @@ -272,10 +272,10 @@ out: int tick_nohz_full_cpu(int cpu) { - if (!have_nohz_full_mask) + if (!tick_nohz_full_running) return 0; - return cpumask_test_cpu(cpu, nohz_full_mask); + return cpumask_test_cpu(cpu, tick_nohz_full_mask); } /* Parse the boot-time nohz CPU list from the kernel parameters. */ @@ -283,18 +283,18 @@ static int __init tick_nohz_full_setup(char *str) { int cpu; - alloc_bootmem_cpumask_var(&nohz_full_mask); - if (cpulist_parse(str, nohz_full_mask) < 0) { + alloc_bootmem_cpumask_var(&tick_nohz_full_mask); + if (cpulist_parse(str, tick_nohz_full_mask) < 0) { pr_warning("NOHZ: Incorrect nohz_full cpumask\n"); return 1; } cpu = smp_processor_id(); - if (cpumask_test_cpu(cpu, nohz_full_mask)) { + if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); - cpumask_clear_cpu(cpu, nohz_full_mask); + cpumask_clear_cpu(cpu, tick_nohz_full_mask); } - have_nohz_full_mask = true; + tick_nohz_full_running = true; return 1; } @@ -312,7 +312,7 @@ static int tick_nohz_cpu_down_callback(struct notifier_block *nfb, * If we handle the timekeeping duty for full dynticks CPUs, * we can't safely shutdown that CPU. */ - if (have_nohz_full_mask && tick_do_timer_cpu == cpu) + if (tick_nohz_full_running && tick_do_timer_cpu == cpu) return NOTIFY_BAD; break; } @@ -331,14 +331,14 @@ static int tick_nohz_init_all(void) int err = -1; #ifdef CONFIG_NO_HZ_FULL_ALL - if (!alloc_cpumask_var(&nohz_full_mask, GFP_KERNEL)) { + if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) { pr_err("NO_HZ: Can't allocate full dynticks cpumask\n"); return err; } err = 0; - cpumask_setall(nohz_full_mask); - cpumask_clear_cpu(smp_processor_id(), nohz_full_mask); - have_nohz_full_mask = true; + cpumask_setall(tick_nohz_full_mask); + cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask); + tick_nohz_full_running = true; #endif return err; } @@ -347,20 +347,20 @@ void __init tick_nohz_init(void) { int cpu; - if (!have_nohz_full_mask) { + if (!tick_nohz_full_running) { if (tick_nohz_init_all() < 0) return; } - for_each_cpu(cpu, nohz_full_mask) + for_each_cpu(cpu, tick_nohz_full_mask) context_tracking_cpu_set(cpu); cpu_notifier(tick_nohz_cpu_down_callback, 0); - cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask); + cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask); pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); } #else -#define have_nohz_full_mask (0) +#define tick_nohz_full_running (0) #endif /* @@ -738,7 +738,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (have_nohz_full_mask) { + if (tick_nohz_full_running) { /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around -- cgit v1.2.3 From 460775df4680b4593d8449bc171008578625a850 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks state checks with static keys These APIs are frequenctly accessed and priority is given to optimize the full dynticks off-case in order to let distros enable this feature without suffering from significant performance regressions. Let's inline these APIs and optimize them with static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- kernel/time/tick-sched.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index b28dee43e644..0b7887389bd2 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -149,7 +149,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) } #ifdef CONFIG_NO_HZ_FULL -static cpumask_var_t tick_nohz_full_mask; +cpumask_var_t tick_nohz_full_mask; bool tick_nohz_full_running; static bool can_stop_full_tick(void) @@ -270,14 +270,6 @@ out: local_irq_restore(flags); } -int tick_nohz_full_cpu(int cpu) -{ - if (!tick_nohz_full_running) - return 0; - - return cpumask_test_cpu(cpu, tick_nohz_full_mask); -} - /* Parse the boot-time nohz CPU list from the kernel parameters. */ static int __init tick_nohz_full_setup(char *str) { @@ -359,8 +351,6 @@ void __init tick_nohz_init(void) cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), tick_nohz_full_mask); pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); } -#else -#define tick_nohz_full_running (0) #endif /* @@ -738,7 +728,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (tick_nohz_full_running) { + if (tick_nohz_full_enabled()) { /* * Keep the tick alive to guarantee timekeeping progression * if there are full dynticks CPUs around -- cgit v1.2.3 From d13508f9440e46dccac6a2dd48d51a73b2207482 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 24 Jul 2013 23:52:27 +0200 Subject: nohz: Optimize full dynticks's sched hooks with static keys Scheduler IPIs and task context switches are serious fast path. Let's try to hide as much as we can the impact of full dynticks APIs' off case that are called on these sites through the use of static keys. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman --- kernel/time/tick-sched.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 0b7887389bd2..0ff6ae710161 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -198,7 +198,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now); * Re-evaluate the need for the tick on the current CPU * and restart it if necessary. */ -void tick_nohz_full_check(void) +void __tick_nohz_full_check(void) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); @@ -212,7 +212,7 @@ void tick_nohz_full_check(void) static void nohz_full_kick_work_func(struct irq_work *work) { - tick_nohz_full_check(); + __tick_nohz_full_check(); } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { @@ -231,7 +231,7 @@ void tick_nohz_full_kick(void) static void nohz_full_kick_ipi(void *info) { - tick_nohz_full_check(); + __tick_nohz_full_check(); } /* @@ -254,7 +254,7 @@ void tick_nohz_full_kick_all(void) * It might need the tick due to per task/process properties: * perf events, posix cpu timers, ... */ -void tick_nohz_task_switch(struct task_struct *tsk) +void __tick_nohz_task_switch(struct task_struct *tsk) { unsigned long flags; -- cgit v1.2.3 From c2e7fcf53c3cb02b4ada1c66a9bc8a4d97d58aba Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 2 Aug 2013 18:29:56 +0200 Subject: nohz: Include local CPU in full dynticks global kick tick_nohz_full_kick_all() is useful to notify all full dynticks CPUs that there is a system state change to checkout before re-evaluating the need for the tick. Unfortunately this is implemented using smp_call_function_many() that ignores the local CPU. This CPU also needs to re-evaluate the tick. on_each_cpu_mask() is not useful either because we don't want to re-evaluate the tick state in place but asynchronously from an IPI to avoid messing up with any random locking scenario. So lets call tick_nohz_full_kick() from tick_nohz_full_kick_all() so that the usual irq work takes care of it. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Paul E. McKenney Cc: Borislav Petkov Cc: Li Zhong Cc: Mike Galbraith Cc: Kevin Hilman Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1375460996-16329-4-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- kernel/time/tick-sched.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/time') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index adea6fc3ba2a..3612fc77f834 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -246,6 +246,7 @@ void tick_nohz_full_kick_all(void) preempt_disable(); smp_call_function_many(tick_nohz_full_mask, nohz_full_kick_ipi, NULL, false); + tick_nohz_full_kick(); preempt_enable(); } -- cgit v1.2.3