From 62cb1188ed86a9cf082fd2f757d4dd9b54741f24 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 29 Aug 2017 15:07:54 +0200 Subject: sched/idle: Move quiet_vmstate() into the NOHZ code quiet_vmstat() is an expensive function that only makes sense when we go into NOHZ. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: aubrey.li@linux.intel.com Cc: cl@linux.com Cc: fweisbec@gmail.com Signed-off-by: Ingo Molnar --- kernel/time/tick-sched.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/time') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index c7a899c5ce64..7b258c59d78a 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -787,6 +788,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, if (!ts->tick_stopped) { calc_load_nohz_start(); cpu_load_update_nohz_start(); + quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; -- cgit v1.2.3 From 7863406143d8bbbbda07a61285c5f4c217908dfd Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:28 +0200 Subject: sched/isolation: Move housekeeping related code to its own file The housekeeping code is currently tied to the NOHZ code. As we are planning to make housekeeping independent from it, start with moving the relevant code to its own file. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Acked-by: Paul E. McKenney Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-2-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- drivers/net/ethernet/tile/tilegx.c | 2 +- include/linux/sched/isolation.h | 56 ++++++++++++++++++++++++++++++++++++++ include/linux/tick.h | 37 ------------------------- init/main.c | 2 ++ kernel/rcu/tree_plugin.h | 1 + kernel/rcu/update.c | 1 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 1 + kernel/sched/fair.c | 1 + kernel/sched/isolation.c | 33 ++++++++++++++++++++++ kernel/time/tick-sched.c | 18 ------------ kernel/watchdog.c | 1 + 12 files changed, 98 insertions(+), 56 deletions(-) create mode 100644 include/linux/sched/isolation.h create mode 100644 kernel/sched/isolation.c (limited to 'kernel/time') diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index c00102b8145a..27a3272dcd48 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -40,7 +40,7 @@ #include #include #include -#include +#include #include #include diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h new file mode 100644 index 000000000000..b7cfbc46286c --- /dev/null +++ b/include/linux/sched/isolation.h @@ -0,0 +1,56 @@ +#ifndef _LINUX_SCHED_ISOLATION_H +#define _LINUX_SCHED_ISOLATION_H + +#include +#include +#include + +#ifdef CONFIG_NO_HZ_FULL +extern cpumask_var_t housekeeping_mask; + +static inline int housekeeping_any_cpu(void) +{ + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +} + +extern void __init housekeeping_init(void); + +#else + +static inline int housekeeping_any_cpu(void) +{ + return smp_processor_id(); +} + +static inline void housekeeping_init(void) { } +#endif /* CONFIG_NO_HZ_FULL */ + + +static inline const struct cpumask *housekeeping_cpumask(void) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return housekeeping_mask; +#endif + return cpu_possible_mask; +} + +static inline bool is_housekeeping_cpu(int cpu) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + return cpumask_test_cpu(cpu, housekeeping_mask); +#endif + return true; +} + +static inline void housekeeping_affine(struct task_struct *t) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_enabled()) + set_cpus_allowed_ptr(t, housekeeping_mask); + +#endif +} + +#endif /* _LINUX_SCHED_ISOLATION_H */ diff --git a/include/linux/tick.h b/include/linux/tick.h index fe01e68bf520..68afc09aa8ac 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -137,7 +137,6 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; extern cpumask_var_t tick_nohz_full_mask; -extern cpumask_var_t housekeeping_mask; static inline bool tick_nohz_full_enabled(void) { @@ -161,11 +160,6 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) cpumask_or(mask, mask, tick_nohz_full_mask); } -static inline int housekeeping_any_cpu(void) -{ - return cpumask_any_and(housekeeping_mask, cpu_online_mask); -} - extern void tick_nohz_dep_set(enum tick_dep_bits bit); extern void tick_nohz_dep_clear(enum tick_dep_bits bit); extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit); @@ -235,10 +229,6 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal, extern void tick_nohz_full_kick_cpu(int cpu); extern void __tick_nohz_task_switch(void); #else -static inline int housekeeping_any_cpu(void) -{ - return smp_processor_id(); -} static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } @@ -260,33 +250,6 @@ static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void __tick_nohz_task_switch(void) { } #endif -static inline const struct cpumask *housekeeping_cpumask(void) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - return housekeeping_mask; -#endif - return cpu_possible_mask; -} - -static inline bool is_housekeeping_cpu(int cpu) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - return cpumask_test_cpu(cpu, housekeeping_mask); -#endif - return true; -} - -static inline void housekeeping_affine(struct task_struct *t) -{ -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_enabled()) - set_cpus_allowed_ptr(t, housekeeping_mask); - -#endif -} - static inline void tick_nohz_task_switch(void) { if (tick_nohz_full_enabled()) diff --git a/init/main.c b/init/main.c index 0ee9c6866ada..4610c99ae306 100644 --- a/init/main.c +++ b/init/main.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #include #include @@ -606,6 +607,7 @@ asmlinkage __visible void __init start_kernel(void) early_irq_init(); init_IRQ(); tick_init(); + housekeeping_init(); rcu_init_nohz(); init_timers(); hrtimers_init(); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e012b9be777e..c7632f51c5a0 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "../time/tick-internal.h" diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5033b66d2753..79abeb0ca329 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -51,6 +51,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 78f54932ea1d..871d43d73375 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -26,3 +26,4 @@ obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o +obj-$(CONFIG_NO_HZ_FULL) += isolation.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2288a145bf01..ad188acb7636 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 56f343b8e749..591481db8c6a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -32,6 +32,7 @@ #include #include #include +#include #include diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c new file mode 100644 index 000000000000..3589252ed476 --- /dev/null +++ b/kernel/sched/isolation.c @@ -0,0 +1,33 @@ +/* + * Housekeeping management. Manage the targets for routine code that can run on + * any CPU: unbound workqueues, timers, kthreads and any offloadable work. + * + * Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker + * + */ + +#include +#include +#include +#include + +cpumask_var_t housekeeping_mask; + +void __init housekeeping_init(void) +{ + if (!tick_nohz_full_enabled()) + return; + + if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { + WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); + cpumask_clear(tick_nohz_full_mask); + tick_nohz_full_running = false; + return; + } + + cpumask_andnot(housekeeping_mask, + cpu_possible_mask, tick_nohz_full_mask); + + /* We need at least one CPU to handle housekeeping work */ + WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); +} diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 7b258c59d78a..27d7d522ac4e 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -166,7 +166,6 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; -cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; static atomic_t tick_dep_mask; @@ -438,13 +437,6 @@ void __init tick_nohz_init(void) return; } - if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { - WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); - cpumask_clear(tick_nohz_full_mask); - tick_nohz_full_running = false; - return; - } - /* * Full dynticks uses irq work to drive the tick rescheduling on safe * locking contexts. But then we need irq work to raise its own @@ -453,7 +445,6 @@ void __init tick_nohz_init(void) if (!arch_irq_work_has_interrupt()) { pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n"); cpumask_clear(tick_nohz_full_mask); - cpumask_copy(housekeeping_mask, cpu_possible_mask); tick_nohz_full_running = false; return; } @@ -466,9 +457,6 @@ void __init tick_nohz_init(void) cpumask_clear_cpu(cpu, tick_nohz_full_mask); } - cpumask_andnot(housekeeping_mask, - cpu_possible_mask, tick_nohz_full_mask); - for_each_cpu(cpu, tick_nohz_full_mask) context_tracking_cpu_set(cpu); @@ -478,12 +466,6 @@ void __init tick_nohz_init(void) WARN_ON(ret < 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); - - /* - * We need at least one CPU to handle housekeeping work such - * as timekeeping, unbound timers, workqueues, ... - */ - WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); } #endif diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 6bcb854909c0..3c44dbaa4b9f 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From 6f1982fedd59856bcc42a9b521be4c3ffd2f60a7 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:36 +0200 Subject: sched/isolation: Handle the nohz_full= parameter We want to centralize the isolation management, done by the housekeeping subsystem. Therefore we need to handle the nohz_full= parameter from there. Since nohz_full= so far has involved unbound timers, watchdog, RCU and tilegx NAPI isolation, we keep that default behaviour. nohz_full= will be deprecated in the future. We want to control the isolation features from the isolcpus= parameter. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-10-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- include/linux/sched/isolation.h | 1 + include/linux/tick.h | 2 ++ init/Kconfig | 1 - kernel/sched/isolation.c | 42 +++++++++++++++++++++++++++++------------ kernel/time/tick-sched.c | 13 +++---------- 5 files changed, 36 insertions(+), 23 deletions(-) (limited to 'kernel/time') diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 9bb753eece3b..e53cfa96e91e 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -10,6 +10,7 @@ enum hk_flags { HK_FLAG_RCU = (1 << 1), HK_FLAG_MISC = (1 << 2), HK_FLAG_SCHED = (1 << 3), + HK_FLAG_TICK = (1 << 4), }; #ifdef CONFIG_CPU_ISOLATION diff --git a/include/linux/tick.h b/include/linux/tick.h index 68afc09aa8ac..e2a163a9f96c 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -228,6 +228,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal, extern void tick_nohz_full_kick_cpu(int cpu); extern void __tick_nohz_task_switch(void); +extern void __init tick_nohz_full_setup(cpumask_var_t cpumask); #else static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } @@ -248,6 +249,7 @@ static inline void tick_dep_clear_signal(struct signal_struct *signal, static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void __tick_nohz_task_switch(void) { } +static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { } #endif static inline void tick_nohz_task_switch(void) diff --git a/init/Kconfig b/init/Kconfig index 6f52e6f4bd9d..f8564df58d0a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -474,7 +474,6 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" - depends on NO_HZ_FULL help Make sure that CPUs running critical tasks are not disturbed by any source of "noise" such as unbound workqueues, timers, kthreads... diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 37a138a780ff..1f61e440358d 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -54,23 +54,41 @@ EXPORT_SYMBOL_GPL(housekeeping_test_cpu); void __init housekeeping_init(void) { - if (!tick_nohz_full_enabled()) + if (!housekeeping_flags) return; - if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) { - WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n"); - cpumask_clear(tick_nohz_full_mask); - tick_nohz_full_running = false; - return; + static_branch_enable(&housekeeping_overriden); + + /* We need at least one CPU to handle housekeeping work */ + WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); +} + +#ifdef CONFIG_NO_HZ_FULL +static int __init housekeeping_nohz_full_setup(char *str) +{ + cpumask_var_t non_housekeeping_mask; + + alloc_bootmem_cpumask_var(&non_housekeeping_mask); + if (cpulist_parse(str, non_housekeeping_mask) < 0) { + pr_warn("Housekeeping: Incorrect nohz_full cpumask\n"); + free_bootmem_cpumask_var(non_housekeeping_mask); + return 0; } - cpumask_andnot(housekeeping_mask, - cpu_possible_mask, tick_nohz_full_mask); + alloc_bootmem_cpumask_var(&housekeeping_mask); + cpumask_andnot(housekeeping_mask, cpu_possible_mask, non_housekeeping_mask); - housekeeping_flags = HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC; + if (cpumask_empty(housekeeping_mask)) + cpumask_set_cpu(smp_processor_id(), housekeeping_mask); - static_branch_enable(&housekeeping_overriden); + housekeeping_flags = HK_FLAG_TICK | HK_FLAG_TIMER | + HK_FLAG_RCU | HK_FLAG_MISC; - /* We need at least one CPU to handle housekeeping work */ - WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); + tick_nohz_full_setup(non_housekeeping_mask); + + free_bootmem_cpumask_var(non_housekeeping_mask); + + return 1; } +__setup("nohz_full=", housekeeping_nohz_full_setup); +#endif diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 27d7d522ac4e..69f3dbe38984 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -385,20 +385,13 @@ out: local_irq_restore(flags); } -/* Parse the boot-time nohz CPU list from the kernel parameters. */ -static int __init tick_nohz_full_setup(char *str) +/* Get the boot-time nohz CPU list from the kernel parameters. */ +void __init tick_nohz_full_setup(cpumask_var_t cpumask) { alloc_bootmem_cpumask_var(&tick_nohz_full_mask); - if (cpulist_parse(str, tick_nohz_full_mask) < 0) { - pr_warn("NO_HZ: Incorrect nohz_full cpumask\n"); - free_bootmem_cpumask_var(tick_nohz_full_mask); - return 1; - } + cpumask_copy(tick_nohz_full_mask, cpumask); tick_nohz_full_running = true; - - return 1; } -__setup("nohz_full=", tick_nohz_full_setup); static int tick_nohz_cpu_down(unsigned int cpu) { -- cgit v1.2.3