diff options
30 files changed, 938 insertions, 115 deletions
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index e38b8df3d72..8e9359de1d2 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -191,7 +191,7 @@ o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that o A hardware or software issue shuts off the scheduler-clock interrupt on a CPU that is not in dyntick-idle mode. This problem really has happened, and seems to be most likely to - result in RCU CPU stall warnings for CONFIG_NO_HZ=n kernels. + result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels. o A bug in the RCU implementation. diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt index c7a2eb8450c..e3e5d9ae50c 100644 --- a/Documentation/cpu-freq/governors.txt +++ b/Documentation/cpu-freq/governors.txt @@ -131,8 +131,8 @@ sampling_rate_min: The sampling rate is limited by the HW transition latency: transition_latency * 100 Or by kernel restrictions: -If CONFIG_NO_HZ is set, the limit is 10ms fixed. -If CONFIG_NO_HZ is not set or nohz=off boot parameter is used, the +If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed. +If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is used, the limits depend on the CONFIG_HZ option: HZ=1000: min=20000us (20ms) HZ=250: min=80000us (80ms) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index de12397b60a..7d55ebb5660 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1951,6 +1951,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Valid arguments: on, off Default: on + nohz_full= [KNL,BOOT] + In kernels built with CONFIG_NO_HZ_FULL=y, set + the specified list of CPUs whose tick will be stopped + whenever possible. The boot CPU will be forced outside + the range to maintain the timekeeping. + The CPUs in this range must also be included in the + rcu_nocbs= set. + noiotrap [SH] Disables trapped I/O port accesses. noirqdebug [X86-32] Disables the code which attempts to detect and diff --git a/Documentation/timers/NO_HZ.txt b/Documentation/timers/NO_HZ.txt new file mode 100644 index 00000000000..5b532202406 --- /dev/null +++ b/Documentation/timers/NO_HZ.txt @@ -0,0 +1,273 @@ + NO_HZ: Reducing Scheduling-Clock Ticks + + +This document describes Kconfig options and boot parameters that can +reduce the number of scheduling-clock interrupts, thereby improving energy +efficiency and reducing OS jitter. Reducing OS jitter is important for +some types of computationally intensive high-performance computing (HPC) +applications and for real-time applications. + +There are two main contexts in which the number of scheduling-clock +interrupts can be reduced compared to the old-school approach of sending +a scheduling-clock interrupt to all CPUs every jiffy whether they need +it or not (CONFIG_HZ_PERIODIC=y or CONFIG_NO_HZ=n for older kernels): + +1. Idle CPUs (CONFIG_NO_HZ_IDLE=y or CONFIG_NO_HZ=y for older kernels). + +2. CPUs having only one runnable task (CONFIG_NO_HZ_FULL=y). + +These two cases are described in the following two sections, followed +by a third section on RCU-specific considerations and a fourth and final +section listing known issues. + + +IDLE CPUs + +If a CPU is idle, there is little point in sending it a scheduling-clock +interrupt. After all, the primary purpose of a scheduling-clock interrupt +is to force a busy CPU to shift its attention among multiple duties, +and an idle CPU has no duties to shift its attention among. + +The CONFIG_NO_HZ_IDLE=y Kconfig option causes the kernel to avoid sending +scheduling-clock interrupts to idle CPUs, which is critically important +both to battery-powered devices and to highly virtualized mainframes. +A battery-powered device running a CONFIG_HZ_PERIODIC=y kernel would +drain its battery very quickly, easily 2-3 times as fast as would the +same device running a CONFIG_NO_HZ_IDLE=y kernel. A mainframe running +1,500 OS instances might find that half of its CPU time was consumed by +unnecessary scheduling-clock interrupts. In these situations, there +is strong motivation to avoid sending scheduling-clock interrupts to +idle CPUs. That said, dyntick-idle mode is not free: + +1. It increases the number of instructions executed on the path + to and from the idle loop. + +2. On many architectures, dyntick-idle mode also increases the + number of expensive clock-reprogramming operations. + +Therefore, systems with aggressive real-time response constraints often +run CONFIG_HZ_PERIODIC=y kernels (or CONFIG_NO_HZ=n for older kernels) +in order to avoid degrading from-idle transition latencies. + +An idle CPU that is not receiving scheduling-clock interrupts is said to +be "dyntick-idle", "in dyntick-idle mode", "in nohz mode", or "running +tickless". The remainder of this document will use "dyntick-idle mode". + +There is also a boot parameter "nohz=" that can be used to disable +dyntick-idle mode in CONFIG_NO_HZ_IDLE=y kernels by specifying "nohz=off". +By default, CONFIG_NO_HZ_IDLE=y kernels boot with "nohz=on", enabling +dyntick-idle mode. + + +CPUs WITH ONLY ONE RUNNABLE TASK + +If a CPU has only one runnable task, there is little point in sending it +a scheduling-clock interrupt because there is no other task to switch to. + +The CONFIG_NO_HZ_FULL=y Kconfig option causes the kernel to avoid +sending scheduling-clock interrupts to CPUs with a single runnable task, +and such CPUs are said to be "adaptive-ticks CPUs". This is important +for applications with aggressive real-time response constraints because +it allows them to improve their worst-case response times by the maximum +duration of a scheduling-clock interrupt. It is also important for +computationally intensive short-iteration workloads: If any CPU is +delayed during a given iteration, all the other CPUs will be forced to +wait idle while the delayed CPU finishes. Thus, the delay is multiplied +by one less than the number of CPUs. In these situations, there is +again strong motivation to avoid sending scheduling-clock interrupts. + +By default, no CPU will be an adaptive-ticks CPU. The "nohz_full=" +boot parameter specifies the adaptive-ticks CPUs. For example, +"nohz_full=1,6-8" says that CPUs 1, 6, 7, and 8 are to be adaptive-ticks +CPUs. Note that you are prohibited from marking all of the CPUs as +adaptive-tick CPUs: At least one non-adaptive-tick CPU must remain +online to handle timekeeping tasks in order to ensure that system calls +like gettimeofday() returns accurate values on adaptive-tick CPUs. +(This is not an issue for CONFIG_NO_HZ_IDLE=y because there are no +running user processes to observe slight drifts in clock rate.) +Therefore, the boot CPU is prohibited from entering adaptive-ticks +mode. Specifying a "nohz_full=" mask that includes the boot CPU will +result in a boot-time error message, and the boot CPU will be removed +from the mask. + +Alternatively, the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter specifies +that all CPUs other than the boot CPU are adaptive-ticks CPUs. This +Kconfig parameter will be overridden by the "nohz_full=" boot parameter, +so that if both the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter and +the "nohz_full=1" boot parameter is specified, the boot parameter will +prevail so that only CPU 1 will be an adaptive-ticks CPU. + +Finally, adaptive-ticks CPUs must have their RCU callbacks offloaded. +This is covered in the "RCU IMPLICATIONS" section below. + +Normally, a CPU remains in adaptive-ticks mode as long as possible. +In particular, transitioning to kernel mode does not automatically change +the mode. Instead, the CPU will exit adaptive-ticks mode only if needed, +for example, if that CPU enqueues an RCU callback. + +Just as with dyntick-idle mode, the benefits of adaptive-tick mode do +not come for free: + +1. CONFIG_NO_HZ_FULL selects CONFIG_NO_HZ_COMMON, so you cannot run + adaptive ticks without also running dyntick idle. This dependency + extends down into the implementation, so that all of the costs + of CONFIG_NO_HZ_IDLE are also incurred by CONFIG_NO_HZ_FULL. + +2. The user/kernel transitions are slightly more expensive due + to the need to inform kernel subsystems (such as RCU) about + the change in mode. + +3. POSIX CPU timers on adaptive-tick CPUs may miss their deadlines + (perhaps indefinitely) because they currently rely on + scheduling-tick interrupts. This will likely be fixed in + one of two ways: (1) Prevent CPUs with POSIX CPU timers from + entering adaptive-tick mode, or (2) Use hrtimers or other + adaptive-ticks-immune mechanism to cause the POSIX CPU timer to + fire properly. + +4. If there are more perf events pending than the hardware can + accommodate, they are normally round-robined so as to collect + all of them over time. Adaptive-tick mode may prevent this + round-robining from happening. This will likely be fixed by + preventing CPUs with large numbers of perf events pending from + entering adaptive-tick mode. + +5. Scheduler statistics for adaptive-tick CPUs may be computed + slightly differently than those for non-adaptive-tick CPUs. + This might in turn perturb load-balancing of real-time tasks. + +6. The LB_BIAS scheduler feature is disabled by adaptive ticks. + +Although improvements are expected over time, adaptive ticks is quite +useful for many types of real-time and compute-intensive applications. +However, the drawbacks listed above mean that adaptive ticks should not +(yet) be enabled by default. + + +RCU IMPLICATIONS + +There are situations in which idle CPUs cannot be permitted to +enter either dyntick-idle mode or adaptive-tick mode, the most +common being when that CPU has RCU callbacks pending. + +The CONFIG_RCU_FAST_NO_HZ=y Kconfig option may be used to cause such CPUs +to enter dyntick-idle mode or adaptive-tick mode anyway. In this case, +a timer will awaken these CPUs every four jiffies in order to ensure +that the RCU callbacks are processed in a timely fashion. + +Another approach is to offload RCU callback processing to "rcuo" kthreads +using the CONFIG_RCU_NOCB_CPU=y Kconfig option. The specific CPUs to +offload may be selected via several methods: + +1. One of three mutually exclusive Kconfig options specify a + build-time default for the CPUs to offload: + + a. The CONFIG_RCU_NOCB_CPU_NONE=y Kconfig option results in + no CPUs being offloaded. + + b. The CONFIG_RCU_NOCB_CPU_ZERO=y Kconfig option causes + CPU 0 to be offloaded. + + c. The CONFIG_RCU_NOCB_CPU_ALL=y Kconfig option causes all + CPUs to be offloaded. Note that the callbacks will be + offloaded to "rcuo" kthreads, and that those kthreads + will in fact run on some CPU. However, this approach + gives fine-grained control on exactly which CPUs the + callbacks run on, along with their scheduling priority + (including the default of SCHED_OTHER), and it further + allows this control to be varied dynamically at runtime. + +2. The "rcu_nocbs=" kernel boot parameter, which takes a comma-separated + list of CPUs and CPU ranges, for example, "1,3-5" selects CPUs 1, + 3, 4, and 5. The specified CPUs will be offloaded in addition to + any CPUs specified as offloaded by CONFIG_RCU_NOCB_CPU_ZERO=y or + CONFIG_RCU_NOCB_CPU_ALL=y. This means that the "rcu_nocbs=" boot + parameter has no effect for kernels built with RCU_NOCB_CPU_ALL=y. + +The offloaded CPUs will never queue RCU callbacks, and therefore RCU +never prevents offloaded CPUs from entering either dyntick-idle mode +or adaptive-tick mode. That said, note that it is up to userspace to +pin the "rcuo" kthreads to specific CPUs if desired. Otherwise, the +scheduler will decide where to run them, which might or might not be +where you want them to run. + + +KNOWN ISSUES + +o Dyntick-idle slows transitions to and from idle slightly. + In practice, this has not been a problem except for the most + aggressive real-time workloads, which have the option of disabling + dyntick-idle mode, an option that most of them take. However, + some workloads will no doubt want to use adaptive ticks to + eliminate scheduling-clock interrupt latencies. Here are some + options for these workloads: + + a. Use PMQOS from userspace to inform the kernel of your + latency requirements (preferred). + + b. On x86 systems, use the "idle=mwait" boot parameter. + + c. On x86 systems, use the "intel_idle.max_cstate=" to limit + ` the maximum C-state depth. + + d. On x86 systems, use the "idle=poll" boot parameter. + However, please note that use of this parameter can cause + your CPU to overheat, which may cause thermal throttling + to degrade your latencies -- and that this degradation can + be even worse than that of dyntick-idle. Furthermore, + this parameter effectively disables Turbo Mode on Intel + CPUs, which can significantly reduce maximum performance. + +o Adaptive-ticks slows user/kernel transitions slightly. + This is not expected to be a problem for computationally intensive + workloads, which have few such transitions. Careful benchmarking + will be required to determine whether or not other workloads + are significantly affected by this effect. + +o Adaptive-ticks does not do anything unless there is only one + runnable task for a given CPU, even though there are a number + of other situations where the scheduling-clock tick is not + needed. To give but one example, consider a CPU that has one + runnable high-priority SCHED_FIFO task and an arbitrary number + of low-priority SCHED_OTHER tasks. In this case, the CPU is + required to run the SCHED_FIFO task until it either blocks or + some other higher-priority task awakens on (or is assigned to) + this CPU, so there is no point in sending a scheduling-clock + interrupt to this CPU. However, the current implementation + nevertheless sends scheduling-clock interrupts to CPUs having a + single runnable SCHED_FIFO task and multiple runnable SCHED_OTHER + tasks, even though these interrupts are unnecessary. + + Better handling of these sorts of situations is future work. + +o A reboot is required to reconfigure both adaptive idle and RCU + callback offloading. Runtime reconfiguration could be provided + if needed, however, due to the complexity of reconfiguring RCU at + runtime, there would need to be an earthshakingly good reason. + Especially given that you have the straightforward option of + simply offloading RCU callbacks from all CPUs and pinning them + where you want them whenever you want them pinned. + +o Additional configuration is required to deal with other sources + of OS jitter, including interrupts and system-utility tasks + and processes. This configuration normally involves binding + interrupts and tasks to particular CPUs. + +o Some sources of OS jitter can currently be eliminated only by + constraining the workload. For example, the only way to eliminate + OS jitter due to global TLB shootdowns is to avoid the unmapping + operations (such as kernel module unload operations) that + result in these shootdowns. For another example, page faults + and TLB misses can be reduced (and in some cases eliminated) by + using huge pages and by constraining the amount of memory used + by the application. Pre-faulting the working set can also be + helpful, especially when combined with the mlock() and mlockall() + system calls. + +o Unless all CPUs are idle, at least one CPU must keep the + scheduling-clock interrupt going in order to support accurate + timekeeping. + +o If there are adaptive-ticks CPUs, there will be at least one + CPU keeping the scheduling-clock interrupt going, even if all + CPUs are otherwise idle. diff --git a/arch/um/include/shared/common-offsets.h b/arch/um/include/shared/common-offsets.h index 2df313b6a58..c9230680902 100644 --- a/arch/um/include/shared/common-offsets.h +++ b/arch/um/include/shared/common-offsets.h @@ -30,8 +30,8 @@ DEFINE(UM_NSEC_PER_USEC, NSEC_PER_USEC); #ifdef CONFIG_PRINTK DEFINE(UML_CONFIG_PRINTK, CONFIG_PRINTK); #endif -#ifdef CONFIG_NO_HZ -DEFINE(UML_CONFIG_NO_HZ, CONFIG_NO_HZ); +#ifdef CONFIG_NO_HZ_COMMON +DEFINE(UML_CONFIG_NO_HZ_COMMON, CONFIG_NO_HZ_COMMON); #endif #ifdef CONFIG_UML_X86 DEFINE(UML_CONFIG_UML_X86, CONFIG_UML_X86); diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c index fac388cb464..e9824d5dd7d 100644 --- a/arch/um/os-Linux/time.c +++ b/arch/um/os-Linux/time.c @@ -79,7 +79,7 @@ long long os_nsecs(void) return timeval_to_ns(&tv); } -#ifdef UML_CONFIG_NO_HZ +#ifdef UML_CONFIG_NO_HZ_COMMON static int after_sleep_interval(struct timespec *ts) { return 0; diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h index a8ece9a33ae..2c9e62c2bfd 100644 --- a/include/asm-generic/cputime_nsecs.h +++ b/include/asm-generic/cputime_nsecs.h @@ -16,21 +16,27 @@ #ifndef _ASM_GENERIC_CPUTIME_NSECS_H #define _ASM_GENERIC_CPUTIME_NSECS_H +#include <linux/math64.h> + typedef u64 __nocast cputime_t; typedef u64 __nocast cputime64_t; #define cputime_one_jiffy jiffies_to_cputime(1) +#define cputime_div(__ct, divisor) div_u64((__force u64)__ct, divisor) +#define cputime_div_rem(__ct, divisor, remainder) \ + div_u64_rem((__force u64)__ct, divisor, remainder); + /* * Convert cputime <-> jiffies (HZ) */ #define cputime_to_jiffies(__ct) \ - ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) + cputime_div(__ct, NSEC_PER_SEC / HZ) #define cputime_to_scaled(__ct) (__ct) #define jiffies_to_cputime(__jif) \ (__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ)) #define cputime64_to_jiffies64(__ct) \ - ((__force u64)(__ct) / (NSEC_PER_SEC / HZ)) + cputime_div(__ct, NSEC_PER_SEC / HZ) #define jiffies64_to_cputime64(__jif) \ (__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ)) @@ -45,7 +51,7 @@ typedef u64 __nocast cputime64_t; * Convert cputime <-> microseconds */ #define cputime_to_usecs(__ct) \ - ((__force u64)(__ct) / NSEC_PER_USEC) + cputime_div(__ct, NSEC_PER_USEC) #define usecs_to_cputime(__usecs) \ (__force cputime_t)((__usecs) * NSEC_PER_USEC) #define usecs_to_cputime64(__usecs) \ @@ -55,7 +61,7 @@ typedef u64 __nocast cputime64_t; * Convert cputime <-> seconds */ #define cputime_to_secs(__ct) \ - ((__force u64)(__ct) / NSEC_PER_SEC) + cputime_div(__ct, NSEC_PER_SEC) #define secs_to_cputime(__secs) \ (__force cputime_t)((__secs) * NSEC_PER_SEC) @@ -69,8 +75,10 @@ static inline cputime_t timespec_to_cputime(const struct timespec *val) } static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) { - val->tv_sec = (__force u64) ct / NSEC_PER_SEC; - val->tv_nsec = (__force u64) ct % NSEC_PER_SEC; + u32 rem; + + val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem); + val->tv_nsec = rem; } /* @@ -83,15 +91,17 @@ static inline cputime_t timeval_to_cputime(const struct timeval *val) } static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val) { - val->tv_sec = (__force u64) ct / NSEC_PER_SEC; - val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC; + u32 rem; + + val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem); + val->tv_usec = rem / NSEC_PER_USEC; } /* * Convert cputime <-> clock (USER_HZ) */ #define cputime_to_clock_t(__ct) \ - ((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ)) + cputime_div(__ct, (NSEC_PER_SEC / USER_HZ)) #define clock_t_to_cputime(__x) \ (__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ)) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e0373d26c24..f463a46424e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -788,6 +788,12 @@ static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } #endif +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL) +extern bool perf_event_can_stop_tick(void); +#else +static inline bool perf_event_can_stop_tick(void) { return true; } +#endif + #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 042058fdb0a..3698d9d0897 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -122,6 +122,8 @@ void run_posix_cpu_timers(struct task_struct *task); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); +bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk); + void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9ed2c9a4de4..4ccd68e49b0 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1000,4 +1000,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) +#ifdef CONFIG_RCU_NOCB_CPU +extern bool rcu_is_nocb_cpu(int cpu); +#else +static inline bool rcu_is_nocb_cpu(int cpu) { return false; } +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ + + #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 981ab688725..ebf7095158a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -231,7 +231,7 @@ extern void init_idle_bootup_task(struct task_struct *idle); extern int runqueue_is_locked(int cpu); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); extern int get_nohz_timer_target(void); @@ -1762,13 +1762,13 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, } #endif -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON void calc_load_enter_idle(void); void calc_load_exit_idle(void); #else static inline void calc_load_enter_idle(void) { } static inline void calc_load_exit_idle(void) { } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ #ifndef CONFIG_CPUMASK_OFFSTACK static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask) @@ -1854,10 +1854,16 @@ extern void idle_task_exit(void); static inline void idle_task_exit(void) {} #endif -#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) -extern void wake_up_idle_cpu(int cpu); +#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) +extern void wake_up_nohz_cpu(int cpu); #else -static inline void wake_up_idle_cpu(int cpu) { } +static inline void wake_up_nohz_cpu(int cpu) { } +#endif + +#ifdef CONFIG_NO_HZ_FULL +extern bool sched_can_stop_tick(void); +#else +static inline bool sched_can_stop_tick(void) { return false; } #endif #ifdef CONFIG_SCHED_AUTOGROUP diff --git a/include/linux/tick.h b/include/linux/tick.h index 553272e6af5..9180f4b85e6 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -82,7 +82,7 @@ extern int tick_program_event(ktime_t expires, int force); extern void tick_setup_sched_timer(void); # endif -# if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS +# if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS extern void tick_cancel_sched_timer(int cpu); # else static inline void tick_cancel_sched_timer(int cpu) { } @@ -123,7 +123,7 @@ static inline void tick_check_idle(int cpu) { } static inline int tick_oneshot_mode_active(void) { return 0; } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -# ifdef CONFIG_NO_HZ +# ifdef CONFIG_NO_HZ_COMMON DECLARE_PER_CPU(struct tick_sched, tick_cpu_sched); static inline int tick_nohz_tick_stopped(void) @@ -138,7 +138,7 @@ 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 /* !CONFIG_NO_HZ */ +# else /* !CONFIG_NO_HZ_COMMON */ static inline int tick_nohz_tick_stopped(void) { return 0; @@ -155,7 +155,24 @@ static inline ktime_t tick_nohz_get_sleep_length(void) } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } -# endif /* !NO_HZ */ +# endif /* !CONFIG_NO_HZ_COMMON */ + +#ifdef CONFIG_NO_HZ_FULL +extern void tick_nohz_init(void); +extern int tick_nohz_full_cpu(int cpu); +extern void tick_nohz_full_check(void); +extern void tick_nohz_full_kick(void); +extern void tick_nohz_full_kick_all(void); +extern void tick_nohz_task_switch(struct task_struct *tsk); +#else +static inline void tick_nohz_init(void) { } +static inline int tick_nohz_full_cpu(int cpu) { return 0; } +static inline void tick_nohz_full_check(void) { } +static inline void tick_nohz_full_kick(void) { } +static inline void tick_nohz_full_kick_all(void) { } +static inline void tick_nohz_task_switch(struct task_struct *tsk) { } +#endif + # ifdef CONFIG_CPU_IDLE_GOV_MENU extern void menu_hrtimer_cancel(void); diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 425bcfe56c6..e967dd8a34c 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -323,6 +323,27 @@ TRACE_EVENT(itimer_expire, (int) __entry->pid, (unsigned long long)__entry->now) ); +#ifdef CONFIG_NO_HZ_COMMON +TRACE_EVENT(tick_stop, + + TP_PROTO(int success, char *error_msg), + + TP_ARGS(success, error_msg), + + TP_STRUCT__entry( + __field( int , success ) + __string( msg, error_msg ) + ), + + TP_fast_assign( + __entry->success = success; + __assign_str(msg, error_msg); + ), + + TP_printk("success=%s msg=%s", __entry->success ? "yes" : "no", __get_str(msg)) +); +#endif + #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ diff --git a/init/Kconfig b/init/Kconfig index 4367e137900..66f67afad4f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -302,7 +302,7 @@ choice # Kind of a stub config for the pure tick based cputime accounting config TICK_CPU_ACCOUNTING bool "Simple tick based cputime accounting" - depends on !S390 + depends on !S390 && !NO_HZ_FULL help This is the basic tick based cputime accounting that maintains statistics about user, system and idle time spent on per jiffies @@ -312,7 +312,7 @@ config TICK_CPU_ACCOUNTING config VIRT_CPU_ACCOUNTING_NATIVE bool "Deterministic task and CPU time accounting" - depends on HAVE_VIRT_CPU_ACCOUNTING + depends on HAVE_VIRT_CPU_ACCOUNTING && !NO_HZ_FULL select VIRT_CPU_ACCOUNTING help Select this option to enable more accurate task and CPU time @@ -342,7 +342,7 @@ config VIRT_CPU_ACCOUNTING_GEN config IRQ_TIME_ACCOUNTING bool "Fine granularity task level IRQ time accounting" - depends on HAVE_IRQ_TIME_ACCOUNTING + depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL help Select this option to enable fine granularity task irq time accounting. This is done by reading a timestamp on each @@ -576,7 +576,7 @@ config RCU_FANOUT_EXACT config RCU_FAST_NO_HZ bool "Accelerate last non-dyntick-idle CPU's grace periods" - depends on NO_HZ && SMP + depends on NO_HZ_COMMON && SMP default n help This option permits CPUs to enter dynticks-idle state even if diff --git a/init/main.c b/init/main.c index 12c366944db..1952bf2f687 100644 --- a/init/main.c +++ b/init/main.c @@ -545,6 +545,7 @@ asmlinkage void __init start_kernel(void) idr_init_cache(); perf_event_init(); rcu_init(); + tick_nohz_init(); radix_tree_init(); /* init some links before init_ISA_irqs() */ early_irq_init(); diff --git a/kernel/events/core.c b/kernel/events/core.c index 3820e3cefba..6b41c1899a8 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -18,6 +18,7 @@ #include <linux/poll.h> #include <linux/slab.h> #include <linux/hash.h> +#include <linux/tick.h> #include <linux/sysfs.h> #include <linux/dcache.h> #include <linux/percpu.h> @@ -685,8 +686,12 @@ static void perf_pmu_rotate_start(struct pmu *pmu) WARN_ON(!irqs_disabled()); - if (list_empty(&cpuctx->rotation_list)) + if (list_empty(&cpuctx->rotation_list)) { + int was_empty = list_empty(head); list_add(&cpuctx->rotation_list, head); + if (was_empty) + tick_nohz_full_kick(); + } } static void get_ctx(struct perf_event_context *ctx) @@ -2591,6 +2596,16 @@ done: list_del_init(&cpuctx->rotation_list); } +#ifdef CONFIG_NO_HZ_FULL +bool perf_event_can_stop_tick(void) +{ + if (list_empty(&__get_cpu_var(rotation_list))) + return true; + else + return false; +} +#endif + void perf_event_task_tick(void) { struct list_head *head = &__get_cpu_var(rotation_list); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 14be27feda4..abfd89d687a 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -161,7 +161,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, */ static int hrtimer_get_target(int this_cpu, int pinned) { -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) return get_nohz_timer_target(); #endif @@ -1107,7 +1107,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } EXPORT_SYMBOL_GPL(hrtimer_get_remaining); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 8fd709c9bb5..42670e9b44e 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -10,6 +10,8 @@ #include <linux/kernel_stat.h> #include <trace/events/timer.h> #include <linux/random.h> +#include <linux/tick.h> +#include <linux/workqueue.h> /* * Called after updating RLIMIT_CPU to run cpu timer and update @@ -153,6 +155,21 @@ static void bump_cpu_timer(struct k_itimer *timer, } } +/** + * task_cputime_zero - Check a task_cputime struct for all zero fields. + * + * @cputime: The struct to compare. + * + * Checks @cputime to see if all fields are zero. Returns true if all fields + * are zero, false if any field is nonzero. + */ +static inline int task_cputime_zero(const struct task_cputime *cputime) +{ + if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime) + return 1; + return 0; +} + static inline cputime_t prof_ticks(struct task_struct *p) { cputime_t utime, stime; @@ -636,6 +653,37 @@ static int cpu_timer_sample_group(const clockid_t which_clock, return 0; } +#ifdef CONFIG_NO_HZ_FULL +static void nohz_kick_work_fn(struct work_struct *work) +{ + tick_nohz_full_kick_all(); +} + +static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn); + +/* + * We need the IPIs to be sent from sane process context. + * The posix cpu timers are always set with irqs disabled. + */ +static void posix_cpu_timer_kick_nohz(void) +{ + schedule_work(&nohz_kick_work); +} + +bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk) +{ + if (!task_cputime_zero(&tsk->cputime_expires)) + return false; + + if (tsk->signal->cputimer.running) + return false; + + return true; +} +#else +static inline void posix_cpu_timer_kick_nohz(void) { } +#endif + /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. @@ -794,6 +842,8 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, sample_to_timespec(timer->it_clock, old_incr, &old->it_interval); } + if (!ret) + posix_cpu_timer_kick_nohz(); return ret; } @@ -1008,21 +1058,6 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, } } -/** - * task_cputime_zero - Check a task_cputime struct for all zero fields. - * - * @cputime: The struct to compare. - * - * Checks @cputime to see if all fields are zero. Returns true if all fields - * are zero, false if any field is nonzero. - */ -static inline int task_cputime_zero(const struct task_cputime *cputime) -{ - if (!cputime->utime && !cputime->stime && !cputime->sum_exec_runtime) - return 1; - return 0; -} - /* * Check for any per-thread CPU timers that have fired and move them * off the tsk->*_timers list onto the firing list. Per-thread timers @@ -1336,6 +1371,13 @@ void run_posix_cpu_timers(struct task_struct *tsk) cpu_timer_fire(timer); spin_unlock(&timer->it_lock); } + + /* + * In case some timers were rescheduled after the queue got emptied, + * wake up full dynticks CPUs. + */ + if (tsk->signal->cputimer.running) + posix_cpu_timer_kick_nohz(); } /* @@ -1366,7 +1408,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, } if (!*newval) - return; + goto out; *newval += now.cpu; } @@ -1384,6 +1426,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, tsk->signal->cputime_expires.virt_exp = *newval; break; } +out: + posix_cpu_timer_kick_nohz(); } static int do_cpu_nanosleep(const clockid_t which_clock, int flags, diff --git a/kernel/rcutree.c b/kernel/rcutree.c index d8534308fd0..16ea6792501 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -799,6 +799,16 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) rdp->offline_fqs++; return 1; } + + /* + * There is a possibility that a CPU in adaptive-ticks state + * might run in the kernel with the scheduling-clock tick disabled + * for an extended time period. Invoke rcu_kick_nohz_cpu() to + * force the CPU to restart the scheduling-clock tick in this + * CPU is in this state. + */ + rcu_kick_nohz_cpu(rdp->cpu); + return 0; } @@ -1820,7 +1830,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { /* No-CBs CPUs do not have orphanable callbacks. */ - if (is_nocb_cpu(rdp->cpu)) + if (rcu_is_nocb_cpu(rdp->cpu)) return; /* @@ -2892,10 +2902,10 @@ static void _rcu_barrier(struct rcu_state *rsp) * corresponding CPU's preceding callbacks have been invoked. */ for_each_possible_cpu(cpu) { - if (!cpu_online(cpu) && !is_nocb_cpu(cpu)) + if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu)) continue; rdp = per_cpu_ptr(rsp->rda, cpu); - if (is_nocb_cpu(cpu)) { + if (rcu_is_nocb_cpu(cpu)) { _rcu_barrier_trace(rsp, "OnlineNoCB", cpu, rsp->n_barrier_done); atomic_inc(&rsp->barrier_cpu_count); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 14ee40795d6..da77a8f57ff 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -530,13 +530,13 @@ static int rcu_nocb_needs_gp(struct rcu_state *rsp); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); static void rcu_init_one_nocb(struct rcu_node *rnp); -static bool is_nocb_cpu(int cpu); static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy); static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp); +static void rcu_kick_nohz_cpu(int cpu); static bool init_nocb_callback_list(struct rcu_data *rdp); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index d084ae3f281..71bd7337d0c 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -28,6 +28,7 @@ #include <linux/gfp.h> #include <linux/oom.h> #include <linux/smpboot.h> +#include <linux/tick.h> #define RCU_KTHREAD_PRIO 1 @@ -2052,7 +2053,7 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) } /* Is the specified CPU a no-CPUs CPU? */ -static bool is_nocb_cpu(int cpu) +bool rcu_is_nocb_cpu(int cpu) { if (have_rcu_nocb_mask) return cpumask_test_cpu(cpu, rcu_nocb_mask); @@ -2110,7 +2111,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy) { - if (!is_nocb_cpu(rdp->cpu)) + if (!rcu_is_nocb_cpu(rdp->cpu)) return 0; __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy); if (__is_kfree_rcu_offset((unsigned long)rhp->func)) @@ -2134,7 +2135,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp, long qll = rsp->qlen_lazy; /* If this is not a no-CBs CPU, tell the caller to do it the old way. */ - if (!is_nocb_cpu(smp_processor_id())) + if (!rcu_is_nocb_cpu(smp_processor_id())) return 0; rsp->qlen = 0; rsp->qlen_lazy = 0; @@ -2306,11 +2307,6 @@ static void rcu_init_one_nocb(struct rcu_node *rnp) { } -static bool is_nocb_cpu(int cpu) -{ - return false; -} - static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy) { @@ -2337,3 +2333,20 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ + +/* + * An adaptive-ticks CPU can potentially execute in kernel mode for an + * arbitrarily long period of time with the scheduling-clock tick turned + * off. RCU will be paying attention to this CPU because it is in the + * kernel, but the CPU cannot be guaranteed to be executing the RCU state + * machine because the scheduling-clock tick has been disabled. Therefore, + * if an adaptive-ticks CPU is failing to respond to the current grace + * period and has not be idle from an RCU perspective, kick it. + */ +static void rcu_kick_nohz_cpu(int cpu) +{ +#ifdef CONFIG_NO_HZ_FULL + if (tick_nohz_full_cpu(cpu)) + smp_send_reschedule(cpu); +#endif /* #ifdef CONFIG_NO_HZ_FULL */ +} diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c70a8814a76..e94842d4400 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -544,7 +544,7 @@ void resched_cpu(int cpu) raw_spin_unlock_irqrestore(&rq->lock, flags); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * In the semi idle case, use the nearest busy cpu for migrating timers * from an idle cpu. This is good for power-savings. @@ -582,7 +582,7 @@ unlock: * account when the CPU goes back to idle and evaluates the timer * wheel for the next timer event. */ -void wake_up_idle_cpu(int cpu) +static void wake_up_idle_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -612,20 +612,56 @@ void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } +static bool wake_up_full_nohz_cpu(int cpu) +{ + if (tick_nohz_full_cpu(cpu)) { + if (cpu != smp_processor_id() || + tick_nohz_tick_stopped()) + smp_send_reschedule(cpu); + return true; + } + + return false; +} + +void wake_up_nohz_cpu(int cpu) +{ + if (!wake_up_full_nohz_cpu(cpu)) + wake_up_idle_cpu(cpu); +} + static inline bool got_nohz_idle_kick(void) { int cpu = smp_processor_id(); return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); } -#else /* CONFIG_NO_HZ */ +#else /* CONFIG_NO_HZ_COMMON */ static inline bool got_nohz_idle_kick(void) { return false; } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ + +#ifdef CONFIG_NO_HZ_FULL +bool sched_can_stop_tick(void) +{ + struct rq *rq; + + rq = this_rq(); + + /* Make sure rq->nr_running update is visible after the IPI */ + smp_rmb(); + + /* More than one running task need preemption */ + if (rq->nr_running > 1) + return false; + + return true; +} +#endif /* CONFIG_NO_HZ_FULL */ void sched_avg_update(struct rq *rq) { @@ -1357,7 +1393,8 @@ static void sched_ttwu_pending(void) void scheduler_ipi(void) { - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick() + && !tick_nohz_full_cpu(smp_processor_id())) return; /* @@ -1374,6 +1411,7 @@ void scheduler_ipi(void) * somewhat pessimize the simple resched case. */ irq_enter(); + tick_nohz_full_check(); sched_ttwu_pending(); /* @@ -1855,6 +1893,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) kprobe_flush_task(prev); put_task_struct(prev); } + + tick_nohz_task_switch(current); } #ifdef CONFIG_SMP @@ -2118,7 +2158,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return load >> FSHIFT; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. * @@ -2344,12 +2384,12 @@ static void calc_global_nohz(void) smp_wmb(); calc_load_idx++; } -#else /* !CONFIG_NO_HZ */ +#else /* !CONFIG_NO_HZ_COMMON */ static inline long calc_load_fold_idle(void) { return 0; } static inline void calc_global_nohz(void) { } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ /* * calc_load - update the avenrun load estimates 10 ticks after the @@ -2509,7 +2549,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, sched_avg_update(this_rq); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * There is no sane way to deal with nohz on smp when using jiffies because the * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading @@ -2569,7 +2609,7 @@ void update_cpu_load_nohz(void) } raw_spin_unlock(&this_rq->lock); } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ /* * Called from scheduler_tick() @@ -6950,7 +6990,7 @@ void __init sched_init(void) INIT_LIST_HEAD(&rq->cfs_tasks); rq_attach_root(rq, &def_root_domain); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON rq->nohz_flags = 0; #endif #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8bf7081b1ec..c61a614465c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5355,7 +5355,7 @@ out_unlock: return 0; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * idle load balancing details * - When one of the busy CPUs notice that there may be an idle rebalancing @@ -5572,9 +5572,9 @@ out: rq->next_balance = next_balance; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* - * In CONFIG_NO_HZ case, the idle balance kickee will do the + * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the * rebalancing for all the cpus for whom scheduler ticks are stopped. */ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) @@ -5717,7 +5717,7 @@ void trigger_load_balance(struct rq *rq, int cpu) if (time_after_eq(jiffies, rq->next_balance) && likely(!on_null_domain(cpu))) raise_softirq(SCHED_SOFTIRQ); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu))) nohz_balancer_kick(cpu); #endif @@ -6187,7 +6187,7 @@ __init void init_sched_fair_class(void) #ifdef CONFIG_SMP open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON nohz.next_balance = jiffies; zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); cpu_notifier(sched_ilb_notifier, 0); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4c225c4c711..24dc2989774 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> +#include <linux/tick.h> #include "cpupri.h" #include "cpuacct.h" @@ -405,7 +406,7 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; unsigned long last_load_update_tick; -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON u64 nohz_stamp; unsigned long nohz_flags; #endif @@ -1072,6 +1073,16 @@ static inline u64 steal_ticks(u64 steal) static inline void inc_nr_running(struct rq *rq) { rq->nr_running++; + +#ifdef CONFIG_NO_HZ_FULL + if (rq->nr_running == 2) { + if (tick_nohz_full_cpu(rq->cpu)) { + /* Order rq->nr_running write against the IPI */ + smp_wmb(); + smp_send_reschedule(rq->cpu); + } + } +#endif } static inline void dec_nr_running(struct rq *rq) @@ -1299,7 +1310,7 @@ extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); extern void account_cfs_bandwidth_used(int enabled, int was_enabled); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON enum rq_nohz_flag_bits { NOHZ_TICK_STOPPED, NOHZ_BALANCE_KICK, diff --git a/kernel/softirq.c b/kernel/softirq.c index 14d7758074a..51a09d56e78 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -329,6 +329,19 @@ static inline void invoke_softirq(void) wakeup_softirqd(); } +static inline void tick_irq_exit(void) +{ +#ifdef CONFIG_NO_HZ_COMMON + int cpu = smp_processor_id(); + + /* Make sure that timer wheel updates are propagated */ + if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) { + if (!in_interrupt()) + tick_nohz_irq_exit(); + } +#endif +} + /* * Exit an interrupt context. Process softirqs if needed and possible: */ @@ -346,11 +359,7 @@ void irq_exit(void) if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); -#ifdef CONFIG_NO_HZ - /* Make sure that timer wheel updates are propagated */ - if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) - tick_nohz_irq_exit(); -#endif + tick_irq_exit(); rcu_irq_exit(); } diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 24510d84efd..a2ddd650cb9 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -64,20 +64,89 @@ config GENERIC_CMOS_UPDATE if GENERIC_CLOCKEVENTS menu "Timers subsystem" -# Core internal switch. Selected by NO_HZ / HIGH_RES_TIMERS. This is +# Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is # only related to the tick functionality. Oneshot clockevent devices # are supported independ of this. config TICK_ONESHOT bool -config NO_HZ - bool "Tickless System (Dynamic Ticks)" +config NO_HZ_COMMON + bool depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS select TICK_ONESHOT + +choice + prompt "Timer tick handling" + default NO_HZ_IDLE if NO_HZ + +config HZ_PERIODIC + bool "Periodic timer ticks (constant rate, no dynticks)" + help + This option keeps the tick running periodically at a constant + rate, even when the CPU doesn't need it. + +config NO_HZ_IDLE + bool "Idle dynticks system (tickless idle)" + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + select NO_HZ_COMMON + help + This option enables a tickless idle system: timer interrupts + will only trigger on an as-needed basis when the system is idle. + This is usually interesting for energy saving. + + Most of the time you want to say Y here. + +config NO_HZ_FULL + bool "Full dynticks system (tickless)" + # NO_HZ_COMMON dependency + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + # We need at least one periodic CPU for timekeeping + depends on SMP + # RCU_USER_QS dependency + depends on HAVE_CONTEXT_TRACKING + # VIRT_CPU_ACCOUNTING_GEN dependency + depends on 64BIT + select NO_HZ_COMMON + select RCU_USER_QS + select RCU_NOCB_CPU + select RCU_NOCB_CPU_ALL + select VIRT_CPU_ACCOUNTING_GEN + select CONTEXT_TRACKING_FORCE + select IRQ_WORK + help + Adaptively try to shutdown the tick whenever possible, even when + the CPU is running tasks. Typically this requires running a single + task on the CPU. Chances for running tickless are maximized when + the task mostly runs in userspace and has few kernel activity. + + You need to fill up the nohz_full boot parameter with the + desired range of dynticks CPUs. + + This is implemented at the expense of some overhead in user <-> kernel + transitions: syscalls, exceptions and interrupts. Even when it's + dynamically off. + + Say N. + +endchoice + +config NO_HZ_FULL_ALL + bool "Full dynticks system on all CPUs by default" + depends on NO_HZ_FULL + help + If the user doesn't pass the nohz_full boot option to + define the range of full dynticks CPUs, consider that all + CPUs in the system are full dynticks by default. + Note the boot CPU will still be kept outside the range to + handle the timekeeping duty. + +config NO_HZ + bool "Old Idle dynticks config" + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS help - This option enables a tickless system: timer interrupts will - only trigger on an as-needed basis both when the system is - busy and when the system is idle. + This is the old config entry that enables dynticks idle. + We keep it around for a little while to enforce backward + compatibility with older config files. config HIGH_RES_TIMERS bool "High Resolution Timer Support" diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 7f32fe0e52c..40c10502c9e 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -574,7 +574,8 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) bc->event_handler = tick_handle_oneshot_broadcast; /* Take the do_timer update */ - tick_do_timer_cpu = cpu; + if (!tick_nohz_full_cpu(cpu)) + tick_do_timer_cpu = cpu; /* * We must be careful here. There might be other CPUs diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index b1600a6973f..83f2bd96716 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -163,7 +163,10 @@ static void tick_setup_device(struct tick_device *td, * this cpu: */ if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - tick_do_timer_cpu = cpu; + if (!tick_nohz_full_cpu(cpu)) + tick_do_timer_cpu = cpu; + else + tick_do_timer_cpu = TICK_DO_TIMER_NONE; tick_next_period = ktime_get(); tick_period = ktime_set(0, NSEC_PER_SEC / HZ); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index a19a39952c1..1c9f53b2ddb 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -21,11 +21,15 @@ #include <linux/sched.h> #include <linux/module.h> #include <linux/irq_work.h> +#include <linux/posix-timers.h> +#include <linux/perf_event.h> #include <asm/irq_regs.h> #include "tick-internal.h" +#include <trace/events/timer.h> + /* * Per cpu nohz control structure */ @@ -104,7 +108,7 @@ static void tick_sched_do_timer(ktime_t now) { int cpu = smp_processor_id(); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the cpu in charge went @@ -112,7 +116,8 @@ static void tick_sched_do_timer(ktime_t now) * this duty, then the jiffies update is still serialized by * jiffies_lock. */ - if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE) + && !tick_nohz_full_cpu(cpu)) tick_do_timer_cpu = cpu; #endif @@ -123,7 +128,7 @@ static void tick_sched_do_timer(ktime_t now) static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long @@ -142,10 +147,226 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) profile_tick(CPU_PROFILING); } +#ifdef CONFIG_NO_HZ_FULL +static cpumask_var_t nohz_full_mask; +bool have_nohz_full_mask; + +static bool can_stop_full_tick(void) +{ + WARN_ON_ONCE(!irqs_disabled()); + + if (!sched_can_stop_tick()) { + trace_tick_stop(0, "more than 1 task in runqueue\n"); + return false; + } + + if (!posix_cpu_timers_can_stop_tick(current)) { + trace_tick_stop(0, "posix timers running\n"); + return false; + } + + if (!perf_event_can_stop_tick()) { + trace_tick_stop(0, "perf events running\n"); + return false; + } + + /* sched_clock_tick() needs us? */ +#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK + /* + * TODO: kick full dynticks CPUs when + * sched_clock_stable is set. + */ + if (!sched_clock_stable) { + trace_tick_stop(0, "unstable sched clock\n"); + return false; + } +#endif + + return true; +} + +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) +{ + struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); + + if (tick_nohz_full_cpu(smp_processor_id())) { + if (ts->tick_stopped && !is_idle_task(current)) { + if (!can_stop_full_tick()) + tick_nohz_restart_sched_tick(ts, ktime_get()); + } + } +} + +static void nohz_full_kick_work_func(struct irq_work *work) +{ + tick_nohz_full_check(); +} + +static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { + .func = nohz_full_kick_work_func, +}; + +/* + * Kick the current CPU if it's full dynticks in order to force it to + * re-evaluate its dependency on the tick and restart it if necessary. + */ +void tick_nohz_full_kick(void) +{ + if (tick_nohz_full_cpu(smp_processor_id())) + irq_work_queue(&__get_cpu_var(nohz_full_kick_work)); +} + +static void nohz_full_kick_ipi(void *info) +{ + tick_nohz_full_check(); +} + +/* + * Kick all full dynticks CPUs in order to force these to re-evaluate + * their dependency on the tick and restart it if necessary. + */ +void tick_nohz_full_kick_all(void) +{ + if (!have_nohz_full_mask) + return; + + preempt_disable(); + smp_call_function_many(nohz_full_mask, + nohz_full_kick_ipi, NULL, false); + preempt_enable(); +} + +/* + * Re-evaluate the need for the tick as we switch the current task. + * 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) +{ + unsigned long flags; + + local_irq_save(flags); + + if (!tick_nohz_full_cpu(smp_processor_id())) + goto out; + + if (tick_nohz_tick_stopped() && !can_stop_full_tick()) + tick_nohz_full_kick(); + +out: + local_irq_restore(flags); +} + +int tick_nohz_full_cpu(int cpu) +{ + if (!have_nohz_full_mask) + return 0; + + return cpumask_test_cpu(cpu, nohz_full_mask); +} + +/* Parse the boot-time nohz CPU list from the kernel parameters. */ +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) { + pr_warning("NOHZ: Incorrect nohz_full cpumask\n"); + return 1; + } + + cpu = smp_processor_id(); + if (cpumask_test_cpu(cpu, nohz_full_mask)) { + pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu); + cpumask_clear_cpu(cpu, nohz_full_mask); + } + have_nohz_full_mask = true; + + return 1; +} +__setup("nohz_full=", tick_nohz_full_setup); + +static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + /* + * 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) + return -EINVAL; + break; + } + return NOTIFY_OK; +} + +/* + * Worst case string length in chunks of CPU range seems 2 steps + * separations: 0,2,4,6,... + * This is NR_CPUS + sizeof('\0') + */ +static char __initdata nohz_full_buf[NR_CPUS + 1]; + +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)) { + 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; +#endif + return err; +} + +void __init tick_nohz_init(void) +{ + int cpu; + + if (!have_nohz_full_mask) { + if (tick_nohz_init_all() < 0) + return; + } + + cpu_notifier(tick_nohz_cpu_down_callback, 0); + + /* Make sure full dynticks CPU are also RCU nocbs */ + for_each_cpu(cpu, nohz_full_mask) { + if (!rcu_is_nocb_cpu(cpu)) { + pr_warning("NO_HZ: CPU %d is not RCU nocb: " + "cleared from nohz_full range", cpu); + cpumask_clear_cpu(cpu, nohz_full_mask); + } + } + + cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask); + pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf); +} +#else +#define have_nohz_full_mask (0) +#endif + /* * NOHZ - aka dynamic tick functionality */ -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * NO HZ enabled ? */ @@ -345,11 +566,12 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, delta_jiffies = rcu_delta_jiffies; } } + /* - * Do not stop the tick, if we are only one off - * or if the cpu is required for rcu + * Do not stop the tick, if we are only one off (or less) + * or if the cpu is required for RCU: */ - if (!ts->tick_stopped && delta_jiffies == 1) + if (!ts->tick_stopped && delta_jiffies <= 1) goto out; /* Schedule the tick, if we are at least one jiffie off */ @@ -421,6 +643,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; + trace_tick_stop(1, " "); } /* @@ -457,6 +680,24 @@ out: return ret; } +static void tick_nohz_full_stop_tick(struct tick_sched *ts) +{ +#ifdef CONFIG_NO_HZ_FULL + int cpu = smp_processor_id(); + + if (!tick_nohz_full_cpu(cpu) || is_idle_task(current)) + return; + + if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) + return; + + if (!can_stop_full_tick()) + return; + + tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); +#endif +} + static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { /* @@ -489,6 +730,21 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } + if (have_nohz_full_mask) { + /* + * Keep the tick alive to guarantee timekeeping progression + * if there are full dynticks CPUs around + */ + if (tick_do_timer_cpu == cpu) + return false; + /* + * Boot safety: make sure the timekeeping duty has been + * assigned before entering dyntick-idle mode, + */ + if (tick_do_timer_cpu == TICK_DO_TIMER_NONE) + return false; + } + return true; } @@ -568,12 +824,13 @@ void tick_nohz_irq_exit(void) { struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); - if (!ts->inidle) - return; - - /* Cancel the timer because CPU already waken up from the C-states*/ - menu_hrtimer_cancel(); - __tick_nohz_idle_enter(ts); + if (ts->inidle) { + /* Cancel the timer because CPU already waken up from the C-states*/ + menu_hrtimer_cancel(); + __tick_nohz_idle_enter(ts); + } else { + tick_nohz_full_stop_tick(ts); + } } /** @@ -802,7 +1059,7 @@ static inline void tick_check_nohz(int cpu) static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_check_nohz(int cpu) { } -#endif /* NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ /* * Called from irq_enter to notify about the possible interruption of idle() @@ -887,14 +1144,14 @@ void tick_setup_sched_timer(void) now = ktime_get(); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON if (tick_nohz_enabled) ts->nohz_mode = NOHZ_MODE_HIGHRES; #endif } #endif /* HIGH_RES_TIMERS */ -#if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS +#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS void tick_cancel_sched_timer(int cpu) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); diff --git a/kernel/timer.c b/kernel/timer.c index dbf7a78a1ef..1b7489fdea4 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -738,7 +738,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, cpu = smp_processor_id(); -#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP) +#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) cpu = get_nohz_timer_target(); #endif @@ -930,14 +930,14 @@ void add_timer_on(struct timer_list *timer, int cpu) debug_activate(timer, timer->expires); internal_add_timer(base, timer); /* - * Check whether the other CPU is idle and needs to be - * triggered to reevaluate the timer wheel when nohz is - * active. We are protected against the other CPU fiddling + * Check whether the other CPU is in dynticks mode and needs + * to be triggered to reevaluate the timer wheel. + * We are protected against the other CPU fiddling * with the timer by holding the timer base lock. This also - * makes sure that a CPU on the way to idle can not evaluate - * the timer wheel. + * makes sure that a CPU on the way to stop its tick can not + * evaluate the timer wheel. */ - wake_up_idle_cpu(cpu); + wake_up_nohz_cpu(cpu); spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); @@ -1188,7 +1188,7 @@ static inline void __run_timers(struct tvec_base *base) spin_unlock_irq(&base->lock); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * Find out when the next timer event is due to happen. This * is used on S/390 to stop all activity when a CPU is idle. |