diff options
Diffstat (limited to 'include/linux/sched')
26 files changed, 2248 insertions, 14 deletions
diff --git a/include/linux/sched/autogroup.h b/include/linux/sched/autogroup.h new file mode 100644 index 000000000000..55cd496df884 --- /dev/null +++ b/include/linux/sched/autogroup.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_SCHED_AUTOGROUP_H +#define _LINUX_SCHED_AUTOGROUP_H + +struct signal_struct; +struct task_struct; +struct task_group; +struct seq_file; + +#ifdef CONFIG_SCHED_AUTOGROUP +extern void sched_autogroup_create_attach(struct task_struct *p); +extern void sched_autogroup_detach(struct task_struct *p); +extern void sched_autogroup_fork(struct signal_struct *sig); +extern void sched_autogroup_exit(struct signal_struct *sig); +extern void sched_autogroup_exit_task(struct task_struct *p); +#ifdef CONFIG_PROC_FS +extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m); +extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice); +#endif +#else +static inline void sched_autogroup_create_attach(struct task_struct *p) { } +static inline void sched_autogroup_detach(struct task_struct *p) { } +static inline void sched_autogroup_fork(struct signal_struct *sig) { } +static inline void sched_autogroup_exit(struct signal_struct *sig) { } +static inline void sched_autogroup_exit_task(struct task_struct *p) { } +#endif + +#ifdef CONFIG_CGROUP_SCHED +extern struct task_group root_task_group; +#endif /* CONFIG_CGROUP_SCHED */ + +#endif /* _LINUX_SCHED_AUTOGROUP_H */ diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h new file mode 100644 index 000000000000..34fe92ce1ebd --- /dev/null +++ b/include/linux/sched/clock.h @@ -0,0 +1,105 @@ +#ifndef _LINUX_SCHED_CLOCK_H +#define _LINUX_SCHED_CLOCK_H + +#include <linux/smp.h> + +/* + * Do not use outside of architecture code which knows its limitations. + * + * sched_clock() has no promise of monotonicity or bounded drift between + * CPUs, use (which you should not) requires disabling IRQs. + * + * Please use one of the three interfaces below. + */ +extern unsigned long long notrace sched_clock(void); + +/* + * See the comment in kernel/sched/clock.c + */ +extern u64 running_clock(void); +extern u64 sched_clock_cpu(int cpu); + + +extern void sched_clock_init(void); + +#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +static inline void sched_clock_init_late(void) +{ +} + +static inline void sched_clock_tick(void) +{ +} + +static inline void clear_sched_clock_stable(void) +{ +} + +static inline void sched_clock_idle_sleep_event(void) +{ +} + +static inline void sched_clock_idle_wakeup_event(u64 delta_ns) +{ +} + +static inline u64 cpu_clock(int cpu) +{ + return sched_clock(); +} + +static inline u64 local_clock(void) +{ + return sched_clock(); +} +#else +extern void sched_clock_init_late(void); +extern int sched_clock_stable(void); +extern void clear_sched_clock_stable(void); + +/* + * When sched_clock_stable(), __sched_clock_offset provides the offset + * between local_clock() and sched_clock(). + */ +extern u64 __sched_clock_offset; + + +extern void sched_clock_tick(void); +extern void sched_clock_idle_sleep_event(void); +extern void sched_clock_idle_wakeup_event(u64 delta_ns); + +/* + * As outlined in clock.c, provides a fast, high resolution, nanosecond + * time source that is monotonic per cpu argument and has bounded drift + * between cpus. + * + * ######################### BIG FAT WARNING ########################## + * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # + * # go backwards !! # + * #################################################################### + */ +static inline u64 cpu_clock(int cpu) +{ + return sched_clock_cpu(cpu); +} + +static inline u64 local_clock(void) +{ + return sched_clock_cpu(raw_smp_processor_id()); +} +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * An i/f to runtime opt-in for irq time accounting based off of sched_clock. + * The reason for this explicit opt-in is not to have perf penalty with + * slow sched_clocks. + */ +extern void enable_sched_clock_irqtime(void); +extern void disable_sched_clock_irqtime(void); +#else +static inline void enable_sched_clock_irqtime(void) {} +static inline void disable_sched_clock_irqtime(void) {} +#endif + +#endif /* _LINUX_SCHED_CLOCK_H */ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h new file mode 100644 index 000000000000..69eedcef8f03 --- /dev/null +++ b/include/linux/sched/coredump.h @@ -0,0 +1,74 @@ +#ifndef _LINUX_SCHED_COREDUMP_H +#define _LINUX_SCHED_COREDUMP_H + +#include <linux/mm_types.h> + +#define SUID_DUMP_DISABLE 0 /* No setuid dumping */ +#define SUID_DUMP_USER 1 /* Dump as user of process */ +#define SUID_DUMP_ROOT 2 /* Dump as root */ + +/* mm flags */ + +/* for SUID_DUMP_* above */ +#define MMF_DUMPABLE_BITS 2 +#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1) + +extern void set_dumpable(struct mm_struct *mm, int value); +/* + * This returns the actual value of the suid_dumpable flag. For things + * that are using this for checking for privilege transitions, it must + * test against SUID_DUMP_USER rather than treating it as a boolean + * value. + */ +static inline int __get_dumpable(unsigned long mm_flags) +{ + return mm_flags & MMF_DUMPABLE_MASK; +} + +static inline int get_dumpable(struct mm_struct *mm) +{ + return __get_dumpable(mm->flags); +} + +/* coredump filter bits */ +#define MMF_DUMP_ANON_PRIVATE 2 +#define MMF_DUMP_ANON_SHARED 3 +#define MMF_DUMP_MAPPED_PRIVATE 4 +#define MMF_DUMP_MAPPED_SHARED 5 +#define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_HUGETLB_PRIVATE 7 +#define MMF_DUMP_HUGETLB_SHARED 8 +#define MMF_DUMP_DAX_PRIVATE 9 +#define MMF_DUMP_DAX_SHARED 10 + +#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS +#define MMF_DUMP_FILTER_BITS 9 +#define MMF_DUMP_FILTER_MASK \ + (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) +#define MMF_DUMP_FILTER_DEFAULT \ + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ + (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + +#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS +# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +#else +# define MMF_DUMP_MASK_DEFAULT_ELF 0 +#endif + /* leave room for more dump flags */ +#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */ +#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */ +/* + * This one-shot flag is dropped due to necessity of changing exe once again + * on NFS restore + */ +//#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */ + +#define MMF_HAS_UPROBES 19 /* has uprobes */ +#define MMF_RECALC_UPROBES 20 /* MMF_HAS_UPROBES can be wrong */ +#define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ +#define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ +#define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ + +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) + +#endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h new file mode 100644 index 000000000000..d2be2ccbb372 --- /dev/null +++ b/include/linux/sched/cpufreq.h @@ -0,0 +1,27 @@ +#ifndef _LINUX_SCHED_CPUFREQ_H +#define _LINUX_SCHED_CPUFREQ_H + +#include <linux/types.h> + +/* + * Interface between cpufreq drivers and the scheduler: + */ + +#define SCHED_CPUFREQ_RT (1U << 0) +#define SCHED_CPUFREQ_DL (1U << 1) +#define SCHED_CPUFREQ_IOWAIT (1U << 2) + +#define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL) + +#ifdef CONFIG_CPU_FREQ +struct update_util_data { + void (*func)(struct update_util_data *data, u64 time, unsigned int flags); +}; + +void cpufreq_add_update_util_hook(int cpu, struct update_util_data *data, + void (*func)(struct update_util_data *data, u64 time, + unsigned int flags)); +void cpufreq_remove_update_util_hook(int cpu); +#endif /* CONFIG_CPU_FREQ */ + +#endif /* _LINUX_SCHED_CPUFREQ_H */ diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h new file mode 100644 index 000000000000..4c5b9735c1ae --- /dev/null +++ b/include/linux/sched/cputime.h @@ -0,0 +1,187 @@ +#ifndef _LINUX_SCHED_CPUTIME_H +#define _LINUX_SCHED_CPUTIME_H + +#include <linux/sched/signal.h> + +/* + * cputime accounting APIs: + */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +#include <asm/cputime.h> + +#ifndef cputime_to_nsecs +# define cputime_to_nsecs(__ct) \ + (cputime_to_usecs(__ct) * NSEC_PER_USEC) +#endif +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +extern void task_cputime(struct task_struct *t, + u64 *utime, u64 *stime); +extern u64 task_gtime(struct task_struct *t); +#else +static inline void task_cputime(struct task_struct *t, + u64 *utime, u64 *stime) +{ + *utime = t->utime; + *stime = t->stime; +} + +static inline u64 task_gtime(struct task_struct *t) +{ + return t->gtime; +} +#endif + +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME +static inline void task_cputime_scaled(struct task_struct *t, + u64 *utimescaled, + u64 *stimescaled) +{ + *utimescaled = t->utimescaled; + *stimescaled = t->stimescaled; +} +#else +static inline void task_cputime_scaled(struct task_struct *t, + u64 *utimescaled, + u64 *stimescaled) +{ + task_cputime(t, utimescaled, stimescaled); +} +#endif + +extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); +extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st); + + +/* + * Thread group CPU time accounting. + */ +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times); +void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); + + +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +/** + * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running + * + * @tsk: Pointer to target task. + */ +#ifdef CONFIG_POSIX_TIMERS +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + /* Check if cputimer isn't running. This is accessed without locking. */ + if (!READ_ONCE(cputimer->running)) + return NULL; + + /* + * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime + * in __exit_signal(), we won't account to the signal struct further + * cputime consumed by that task, even though the task can still be + * ticking after __exit_signal(). + * + * In order to keep a consistent behaviour between thread group cputime + * and thread group cputimer accounting, lets also ignore the cputime + * elapsing after __exit_signal() in any thread group timer running. + * + * This makes sure that POSIX CPU clocks and timers are synchronized, so + * that a POSIX CPU timer won't expire while the corresponding POSIX CPU + * clock delta is behind the expiring timer value. + */ + if (unlikely(!tsk->sighand)) + return NULL; + + return cputimer; +} +#else +static inline +struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk) +{ + return NULL; +} +#endif + +/** + * account_group_user_time - Maintain utime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void account_group_user_time(struct task_struct *tsk, + u64 cputime) +{ + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); + + if (!cputimer) + return; + + atomic64_add(cputime, &cputimer->cputime_atomic.utime); +} + +/** + * account_group_system_time - Maintain stime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void account_group_system_time(struct task_struct *tsk, + u64 cputime) +{ + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); + + if (!cputimer) + return; + + atomic64_add(cputime, &cputimer->cputime_atomic.stime); +} + +/** + * account_group_exec_runtime - Maintain exec runtime for a thread group. + * + * @tsk: Pointer to task structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of the thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct thread_group_cputimer *cputimer = get_running_cputimer(tsk); + + if (!cputimer) + return; + + atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); +} + +static inline void prev_cputime_init(struct prev_cputime *prev) +{ +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + prev->utime = prev->stime = 0; + raw_spin_lock_init(&prev->lock); +#endif +} + +extern unsigned long long +task_sched_runtime(struct task_struct *task); + +#endif /* _LINUX_SCHED_CPUTIME_H */ diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 9089a2ae913d..975be862e083 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -1,5 +1,7 @@ -#ifndef _SCHED_DEADLINE_H -#define _SCHED_DEADLINE_H +#ifndef _LINUX_SCHED_DEADLINE_H +#define _LINUX_SCHED_DEADLINE_H + +#include <linux/sched.h> /* * SCHED_DEADLINE tasks has negative priorities, reflecting @@ -26,4 +28,4 @@ static inline bool dl_time_before(u64 a, u64 b) return (s64)(a - b) < 0; } -#endif /* _SCHED_DEADLINE_H */ +#endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h new file mode 100644 index 000000000000..e0eaee54c5a4 --- /dev/null +++ b/include/linux/sched/debug.h @@ -0,0 +1,50 @@ +#ifndef _LINUX_SCHED_DEBUG_H +#define _LINUX_SCHED_DEBUG_H + +/* + * Various scheduler/task debugging interfaces: + */ + +struct task_struct; + +extern void dump_cpu_task(int cpu); + +/* + * Only dump TASK_* tasks. (0 for all tasks) + */ +extern void show_state_filter(unsigned long state_filter); + +static inline void show_state(void) +{ + show_state_filter(0); +} + +struct pt_regs; + +extern void show_regs(struct pt_regs *); + +/* + * TASK is a pointer to the task whose backtrace we want to see (or NULL for current + * task), SP is the stack pointer of the first frame that should be shown in the back + * trace (or NULL if the entire call-chain of the task should be shown). + */ +extern void show_stack(struct task_struct *task, unsigned long *sp); + +extern void sched_show_task(struct task_struct *p); + +#ifdef CONFIG_SCHED_DEBUG +struct seq_file; +extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); +extern void proc_sched_set_task(struct task_struct *p); +#endif + +/* Attach to any functions which should be ignored in wchan output. */ +#define __sched __attribute__((__section__(".sched.text"))) + +/* Linker adds these: start and end of __sched functions */ +extern char __sched_text_start[], __sched_text_end[]; + +/* Is this address in the __sched functions? */ +extern int in_sched_functions(unsigned long addr); + +#endif /* _LINUX_SCHED_DEBUG_H */ diff --git a/include/linux/sched/hotplug.h b/include/linux/sched/hotplug.h new file mode 100644 index 000000000000..752ac7e628d7 --- /dev/null +++ b/include/linux/sched/hotplug.h @@ -0,0 +1,24 @@ +#ifndef _LINUX_SCHED_HOTPLUG_H +#define _LINUX_SCHED_HOTPLUG_H + +/* + * Scheduler interfaces for hotplug CPU support: + */ + +extern int sched_cpu_starting(unsigned int cpu); +extern int sched_cpu_activate(unsigned int cpu); +extern int sched_cpu_deactivate(unsigned int cpu); + +#ifdef CONFIG_HOTPLUG_CPU +extern int sched_cpu_dying(unsigned int cpu); +#else +# define sched_cpu_dying NULL +#endif + +#ifdef CONFIG_HOTPLUG_CPU +extern void idle_task_exit(void); +#else +static inline void idle_task_exit(void) {} +#endif + +#endif /* _LINUX_SCHED_HOTPLUG_H */ diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h new file mode 100644 index 000000000000..5ca63ebad6b4 --- /dev/null +++ b/include/linux/sched/idle.h @@ -0,0 +1,86 @@ +#ifndef _LINUX_SCHED_IDLE_H +#define _LINUX_SCHED_IDLE_H + +#include <linux/sched.h> + +enum cpu_idle_type { + CPU_IDLE, + CPU_NOT_IDLE, + CPU_NEWLY_IDLE, + CPU_MAX_IDLE_TYPES +}; + +extern void wake_up_if_idle(int cpu); + +/* + * Idle thread specific functions to determine the need_resched + * polling state. + */ +#ifdef TIF_POLLING_NRFLAG + +static inline void __current_set_polling(void) +{ + set_thread_flag(TIF_POLLING_NRFLAG); +} + +static inline bool __must_check current_set_polling_and_test(void) +{ + __current_set_polling(); + + /* + * Polling state must be visible before we test NEED_RESCHED, + * paired by resched_curr() + */ + smp_mb__after_atomic(); + + return unlikely(tif_need_resched()); +} + +static inline void __current_clr_polling(void) +{ + clear_thread_flag(TIF_POLLING_NRFLAG); +} + +static inline bool __must_check current_clr_polling_and_test(void) +{ + __current_clr_polling(); + + /* + * Polling state must be visible before we test NEED_RESCHED, + * paired by resched_curr() + */ + smp_mb__after_atomic(); + + return unlikely(tif_need_resched()); +} + +#else +static inline void __current_set_polling(void) { } +static inline void __current_clr_polling(void) { } + +static inline bool __must_check current_set_polling_and_test(void) +{ + return unlikely(tif_need_resched()); +} +static inline bool __must_check current_clr_polling_and_test(void) +{ + return unlikely(tif_need_resched()); +} +#endif + +static inline void current_clr_polling(void) +{ + __current_clr_polling(); + + /* + * Ensure we check TIF_NEED_RESCHED after we clear the polling bit. + * Once the bit is cleared, we'll get IPIs with every new + * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also + * fold. + */ + smp_mb(); /* paired with resched_curr() */ + + preempt_fold_need_resched(); +} + +#endif /* _LINUX_SCHED_IDLE_H */ diff --git a/include/linux/sched/init.h b/include/linux/sched/init.h new file mode 100644 index 000000000000..127215045285 --- /dev/null +++ b/include/linux/sched/init.h @@ -0,0 +1,11 @@ +#ifndef _LINUX_SCHED_INIT_H +#define _LINUX_SCHED_INIT_H + +/* + * Scheduler init related prototypes: + */ + +extern void sched_init(void); +extern void sched_init_smp(void); + +#endif /* _LINUX_SCHED_INIT_H */ diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h new file mode 100644 index 000000000000..016afa0fb3bb --- /dev/null +++ b/include/linux/sched/jobctl.h @@ -0,0 +1,36 @@ +#ifndef _LINUX_SCHED_JOBCTL_H +#define _LINUX_SCHED_JOBCTL_H + +#include <linux/types.h> + +struct task_struct; + +/* + * task->jobctl flags + */ +#define JOBCTL_STOP_SIGMASK 0xffff /* signr of the last group stop */ + +#define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */ +#define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */ +#define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */ +#define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */ +#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */ +#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ +#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ + +#define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) +#define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) +#define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) +#define JOBCTL_TRAP_STOP (1UL << JOBCTL_TRAP_STOP_BIT) +#define JOBCTL_TRAP_NOTIFY (1UL << JOBCTL_TRAP_NOTIFY_BIT) +#define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) +#define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) + +#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) +#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) + +extern bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask); +extern void task_clear_jobctl_trapping(struct task_struct *task); +extern void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask); + +#endif /* _LINUX_SCHED_JOBCTL_H */ diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h new file mode 100644 index 000000000000..4264bc6b2c27 --- /dev/null +++ b/include/linux/sched/loadavg.h @@ -0,0 +1,31 @@ +#ifndef _LINUX_SCHED_LOADAVG_H +#define _LINUX_SCHED_LOADAVG_H + +/* + * These are the constant used to fake the fixed-point load-average + * counting. Some notes: + * - 11 bit fractions expand to 22 bits by the multiplies: this gives + * a load-average precision of 10 bits integer + 11 bits fractional + * - if you want to count load-averages more often, you need more + * precision, or rounding will get you. With 2-second counting freq, + * the EXP_n values would be 1981, 2034 and 2043 if still using only + * 11 bit fractions. + */ +extern unsigned long avenrun[]; /* Load averages */ +extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); + +#define FSHIFT 11 /* nr of bits of precision */ +#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */ +#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */ +#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */ +#define EXP_5 2014 /* 1/exp(5sec/5min) */ +#define EXP_15 2037 /* 1/exp(5sec/15min) */ + +#define CALC_LOAD(load,exp,n) \ + load *= exp; \ + load += n*(FIXED_1-exp); \ + load >>= FSHIFT; + +extern void calc_global_load(unsigned long ticks); + +#endif /* _LINUX_SCHED_LOADAVG_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h new file mode 100644 index 000000000000..830953ebb391 --- /dev/null +++ b/include/linux/sched/mm.h @@ -0,0 +1,174 @@ +#ifndef _LINUX_SCHED_MM_H +#define _LINUX_SCHED_MM_H + +#include <linux/kernel.h> +#include <linux/atomic.h> +#include <linux/sched.h> +#include <linux/mm_types.h> +#include <linux/gfp.h> + +/* + * Routines for handling mm_structs + */ +extern struct mm_struct * mm_alloc(void); + +/** + * mmgrab() - Pin a &struct mm_struct. + * @mm: The &struct mm_struct to pin. + * + * Make sure that @mm will not get freed even after the owning task + * exits. This doesn't guarantee that the associated address space + * will still exist later on and mmget_not_zero() has to be used before + * accessing it. + * + * This is a preferred way to to pin @mm for a longer/unbounded amount + * of time. + * + * Use mmdrop() to release the reference acquired by mmgrab(). + * + * See also <Documentation/vm/active_mm.txt> for an in-depth explanation + * of &mm_struct.mm_count vs &mm_struct.mm_users. + */ +static inline void mmgrab(struct mm_struct *mm) +{ + atomic_inc(&mm->mm_count); +} + +/* mmdrop drops the mm and the page tables */ +extern void __mmdrop(struct mm_struct *); +static inline void mmdrop(struct mm_struct *mm) +{ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) + __mmdrop(mm); +} + +static inline void mmdrop_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); + __mmdrop(mm); +} + +static inline void mmdrop_async(struct mm_struct *mm) +{ + if (unlikely(atomic_dec_and_test(&mm->mm_count))) { + INIT_WORK(&mm->async_put_work, mmdrop_async_fn); + schedule_work(&mm->async_put_work); + } +} + +/** + * mmget() - Pin the address space associated with a &struct mm_struct. + * @mm: The address space to pin. + * + * Make sure that the address space of the given &struct mm_struct doesn't + * go away. This does not protect against parts of the address space being + * modified or freed, however. + * + * Never use this function to pin this address space for an + * unbounded/indefinite amount of time. + * + * Use mmput() to release the reference acquired by mmget(). + * + * See also <Documentation/vm/active_mm.txt> for an in-depth explanation + * of &mm_struct.mm_count vs &mm_struct.mm_users. + */ +static inline void mmget(struct mm_struct *mm) +{ + atomic_inc(&mm->mm_users); +} + +static inline bool mmget_not_zero(struct mm_struct *mm) +{ + return atomic_inc_not_zero(&mm->mm_users); +} + +/* mmput gets rid of the mappings and all user-space */ +extern void mmput(struct mm_struct *); +#ifdef CONFIG_MMU +/* same as above but performs the slow path from the async context. Can + * be called from the atomic context as well + */ +extern void mmput_async(struct mm_struct *); +#endif + +/* Grab a reference to a task's mm, if it is not already going away */ +extern struct mm_struct *get_task_mm(struct task_struct *task); +/* + * Grab a reference to a task's mm, if it is not already going away + * and ptrace_may_access with the mode parameter passed to it + * succeeds. + */ +extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); +/* Remove the current tasks stale references to the old mm_struct */ +extern void mm_release(struct task_struct *, struct mm_struct *); + +#ifdef CONFIG_MEMCG +extern void mm_update_next_owner(struct mm_struct *mm); +#else +static inline void mm_update_next_owner(struct mm_struct *mm) +{ +} +#endif /* CONFIG_MEMCG */ + +#ifdef CONFIG_MMU +extern void arch_pick_mmap_layout(struct mm_struct *mm); +extern unsigned long +arch_get_unmapped_area(struct file *, unsigned long, unsigned long, + unsigned long, unsigned long); +extern unsigned long +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +#else +static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} +#endif + +static inline bool in_vfork(struct task_struct *tsk) +{ + bool ret; + + /* + * need RCU to access ->real_parent if CLONE_VM was used along with + * CLONE_PARENT. + * + * We check real_parent->mm == tsk->mm because CLONE_VFORK does not + * imply CLONE_VM + * + * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus + * ->real_parent is not necessarily the task doing vfork(), so in + * theory we can't rely on task_lock() if we want to dereference it. + * + * And in this case we can't trust the real_parent->mm == tsk->mm + * check, it can be false negative. But we do not care, if init or + * another oom-unkillable task does this it should blame itself. + */ + rcu_read_lock(); + ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm; + rcu_read_unlock(); + + return ret; +} + +/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags + * __GFP_FS is also cleared as it implies __GFP_IO. + */ +static inline gfp_t memalloc_noio_flags(gfp_t flags) +{ + if (unlikely(current->flags & PF_MEMALLOC_NOIO)) + flags &= ~(__GFP_IO | __GFP_FS); + return flags; +} + +static inline unsigned int memalloc_noio_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOIO; + current->flags |= PF_MEMALLOC_NOIO; + return flags; +} + +static inline void memalloc_noio_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; +} + +#endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h new file mode 100644 index 000000000000..4995b717500b --- /dev/null +++ b/include/linux/sched/nohz.h @@ -0,0 +1,43 @@ +#ifndef _LINUX_SCHED_NOHZ_H +#define _LINUX_SCHED_NOHZ_H + +/* + * This is the interface between the scheduler and nohz/dyntics: + */ + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void cpu_load_update_nohz_start(void); +extern void cpu_load_update_nohz_stop(void); +#else +static inline void cpu_load_update_nohz_start(void) { } +static inline void cpu_load_update_nohz_stop(void) { } +#endif + +#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); +#else +static inline void nohz_balance_enter_idle(int cpu) { } +static inline void set_cpu_sd_state_idle(void) { } +#endif + +#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_COMMON */ + +#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) +extern void wake_up_nohz_cpu(int cpu); +#else +static inline void wake_up_nohz_cpu(int cpu) { } +#endif + +#ifdef CONFIG_NO_HZ_FULL +extern u64 scheduler_tick_max_deferment(void); +#endif + +#endif /* _LINUX_SCHED_NOHZ_H */ diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h new file mode 100644 index 000000000000..35d5fc77b4be --- /dev/null +++ b/include/linux/sched/numa_balancing.h @@ -0,0 +1,46 @@ +#ifndef _LINUX_SCHED_NUMA_BALANCING_H +#define _LINUX_SCHED_NUMA_BALANCING_H + +/* + * This is the interface between the scheduler and the MM that + * implements memory access pattern based NUMA-balancing: + */ + +#include <linux/sched.h> + +#define TNF_MIGRATED 0x01 +#define TNF_NO_GROUP 0x02 +#define TNF_SHARED 0x04 +#define TNF_FAULT_LOCAL 0x08 +#define TNF_MIGRATE_FAIL 0x10 + +#ifdef CONFIG_NUMA_BALANCING +extern void task_numa_fault(int last_node, int node, int pages, int flags); +extern pid_t task_numa_group_id(struct task_struct *p); +extern void set_numabalancing_state(bool enabled); +extern void task_numa_free(struct task_struct *p); +extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, + int src_nid, int dst_cpu); +#else +static inline void task_numa_fault(int last_node, int node, int pages, + int flags) +{ +} +static inline pid_t task_numa_group_id(struct task_struct *p) +{ + return 0; +} +static inline void set_numabalancing_state(bool enabled) +{ +} +static inline void task_numa_free(struct task_struct *p) +{ +} +static inline bool should_numa_migrate_memory(struct task_struct *p, + struct page *page, int src_nid, int dst_cpu) +{ + return true; +} +#endif + +#endif /* _LINUX_SCHED_NUMA_BALANCING_H */ diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h index d9cf5a5762d9..2cc450f6ec54 100644 --- a/include/linux/sched/prio.h +++ b/include/linux/sched/prio.h @@ -1,5 +1,5 @@ -#ifndef _SCHED_PRIO_H -#define _SCHED_PRIO_H +#ifndef _LINUX_SCHED_PRIO_H +#define _LINUX_SCHED_PRIO_H #define MAX_NICE 19 #define MIN_NICE -20 @@ -57,4 +57,4 @@ static inline long rlimit_to_nice(long prio) return (MAX_NICE - prio + 1); } -#endif /* _SCHED_PRIO_H */ +#endif /* _LINUX_SCHED_PRIO_H */ diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index a30b172df6e1..3bd668414f61 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -1,7 +1,9 @@ -#ifndef _SCHED_RT_H -#define _SCHED_RT_H +#ifndef _LINUX_SCHED_RT_H +#define _LINUX_SCHED_RT_H -#include <linux/sched/prio.h> +#include <linux/sched.h> + +struct task_struct; static inline int rt_prio(int prio) { @@ -57,4 +59,4 @@ extern void normalize_rt_tasks(void); */ #define RR_TIMESLICE (100 * HZ / 1000) -#endif /* _SCHED_RT_H */ +#endif /* _LINUX_SCHED_RT_H */ diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h new file mode 100644 index 000000000000..2cf446704cd4 --- /dev/null +++ b/include/linux/sched/signal.h @@ -0,0 +1,613 @@ +#ifndef _LINUX_SCHED_SIGNAL_H +#define _LINUX_SCHED_SIGNAL_H + +#include <linux/rculist.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/sched/jobctl.h> +#include <linux/sched/task.h> +#include <linux/cred.h> + +/* + * Types defining task->signal and task->sighand and APIs using them: + */ + +struct sighand_struct { + atomic_t count; + struct k_sigaction action[_NSIG]; + spinlock_t siglock; + wait_queue_head_t signalfd_wqh; +}; + +/* + * Per-process accounting stats: + */ +struct pacct_struct { + int ac_flag; + long ac_exitcode; + unsigned long ac_mem; + u64 ac_utime, ac_stime; + unsigned long ac_minflt, ac_majflt; +}; + +struct cpu_itimer { + u64 expires; + u64 incr; +}; + +/* + * This is the atomic variant of task_cputime, which can be used for + * storing and updating task_cputime statistics without locking. + */ +struct task_cputime_atomic { + atomic64_t utime; + atomic64_t stime; + atomic64_t sum_exec_runtime; +}; + +#define INIT_CPUTIME_ATOMIC \ + (struct task_cputime_atomic) { \ + .utime = ATOMIC64_INIT(0), \ + .stime = ATOMIC64_INIT(0), \ + .sum_exec_runtime = ATOMIC64_INIT(0), \ + } +/** + * struct thread_group_cputimer - thread group interval timer counts + * @cputime_atomic: atomic thread group interval timers. + * @running: true when there are timers running and + * @cputime_atomic receives updates. + * @checking_timer: true when a thread in the group is in the + * process of checking for thread group timers. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU timer calculations. + */ +struct thread_group_cputimer { + struct task_cputime_atomic cputime_atomic; + bool running; + bool checking_timer; +}; + +/* + * NOTE! "signal_struct" does not have its own + * locking, because a shared signal_struct always + * implies a shared sighand_struct, so locking + * sighand_struct is always a proper superset of + * the locking of signal_struct. + */ +struct signal_struct { + atomic_t sigcnt; + atomic_t live; + int nr_threads; + struct list_head thread_head; + + wait_queue_head_t wait_chldexit; /* for wait4() */ + + /* current thread group signal load-balancing target: */ + struct task_struct *curr_target; + + /* shared signal handling: */ + struct sigpending shared_pending; + + /* thread group exit support */ + int group_exit_code; + /* overloaded: + * - notify group_exit_task when ->count is equal to notify_count + * - everyone except group_exit_task is stopped during signal delivery + * of fatal signals, group_exit_task processes the signal. + */ + int notify_count; + struct task_struct *group_exit_task; + + /* thread group stop support, overloads group_exit_code too */ + int group_stop_count; + unsigned int flags; /* see SIGNAL_* flags below */ + + /* + * PR_SET_CHILD_SUBREAPER marks a process, like a service + * manager, to re-parent orphan (double-forking) child processes + * to this process instead of 'init'. The service manager is + * able to receive SIGCHLD signals and is able to investigate + * the process until it calls wait(). All children of this + * process will inherit a flag if they should look for a + * child_subreaper process at exit. + */ + unsigned int is_child_subreaper:1; + unsigned int has_child_subreaper:1; + +#ifdef CONFIG_POSIX_TIMERS + + /* POSIX.1b Interval Timers */ + int posix_timer_id; + struct list_head posix_timers; + + /* ITIMER_REAL timer for the process */ + struct hrtimer real_timer; + ktime_t it_real_incr; + + /* + * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use + * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these + * values are defined to 0 and 1 respectively + */ + struct cpu_itimer it[2]; + + /* + * Thread group totals for process CPU timers. + * See thread_group_cputimer(), et al, for details. + */ + struct thread_group_cputimer cputimer; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + +#endif + + struct pid *leader_pid; + +#ifdef CONFIG_NO_HZ_FULL + atomic_t tick_dep_mask; +#endif + + struct pid *tty_old_pgrp; + + /* boolean value for session group leader */ + int leader; + + struct tty_struct *tty; /* NULL if no tty */ + +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif + /* + * Cumulative resource counters for dead threads in the group, + * and for reaped dead child processes forked by this group. + * Live threads maintain their own counters and add to these + * in __exit_signal, except for the group leader. + */ + seqlock_t stats_lock; + u64 utime, stime, cutime, cstime; + u64 gtime; + u64 cgtime; + struct prev_cputime prev_cputime; + unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; + unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; + unsigned long inblock, oublock, cinblock, coublock; + unsigned long maxrss, cmaxrss; + struct task_io_accounting ioac; + + /* + * Cumulative ns of schedule CPU time fo dead threads in the + * group, not including a zombie group leader, (This only differs + * from jiffies_to_ns(utime + stime) if sched_clock uses something + * other than jiffies.) + */ + unsigned long long sum_sched_runtime; + + /* + * We don't bother to synchronize most readers of this at all, + * because there is no reader checking a limit that actually needs + * to get both rlim_cur and rlim_max atomically, and either one + * alone is a single word that can safely be read normally. + * getrlimit/setrlimit use task_lock(current->group_leader) to + * protect this instead of the siglock, because they really + * have no need to disable irqs. + */ + struct rlimit rlim[RLIM_NLIMITS]; + +#ifdef CONFIG_BSD_PROCESS_ACCT + struct pacct_struct pacct; /* per-process accounting information */ +#endif +#ifdef CONFIG_TASKSTATS + struct taskstats *stats; +#endif +#ifdef CONFIG_AUDIT + unsigned audit_tty; + struct tty_audit_buf *tty_audit_buf; +#endif + + /* + * Thread is the potential origin of an oom condition; kill first on + * oom + */ + bool oom_flag_origin; + short oom_score_adj; /* OOM kill score adjustment */ + short oom_score_adj_min; /* OOM kill score adjustment min value. + * Only settable by CAP_SYS_RESOURCE. */ + struct mm_struct *oom_mm; /* recorded mm when the thread group got + * killed by the oom killer */ + + struct mutex cred_guard_mutex; /* guard against foreign influences on + * credential calculations + * (notably. ptrace) */ +}; + +/* + * Bits in flags field of signal_struct. + */ +#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ +#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ +#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ +#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ +/* + * Pending notifications to parent. + */ +#define SIGNAL_CLD_STOPPED 0x00000010 +#define SIGNAL_CLD_CONTINUED 0x00000020 +#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) + +#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ + +#define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ + SIGNAL_STOP_CONTINUED) + +static inline void signal_set_stop_flags(struct signal_struct *sig, + unsigned int flags) +{ + WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; +} + +/* If true, all threads except ->group_exit_task have pending SIGKILL */ +static inline int signal_group_exit(const struct signal_struct *sig) +{ + return (sig->flags & SIGNAL_GROUP_EXIT) || + (sig->group_exit_task != NULL); +} + +extern void flush_signals(struct task_struct *); +extern void ignore_signals(struct task_struct *); +extern void flush_signal_handlers(struct task_struct *, int force_default); +extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info); + +static inline int kernel_dequeue_signal(siginfo_t *info) +{ + struct task_struct *tsk = current; + siginfo_t __info; + int ret; + + spin_lock_irq(&tsk->sighand->siglock); + ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info); + spin_unlock_irq(&tsk->sighand->siglock); + + return ret; +} + +static inline void kernel_signal_stop(void) +{ + spin_lock_irq(¤t->sighand->siglock); + if (current->jobctl & JOBCTL_STOP_DEQUEUED) + __set_current_state(TASK_STOPPED); + spin_unlock_irq(¤t->sighand->siglock); + + schedule(); +} +extern int send_sig_info(int, struct siginfo *, struct task_struct *); +extern int force_sigsegv(int, struct task_struct *); +extern int force_sig_info(int, struct siginfo *, struct task_struct *); +extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); +extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); +extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *, + const struct cred *, u32); +extern int kill_pgrp(struct pid *pid, int sig, int priv); +extern int kill_pid(struct pid *pid, int sig, int priv); +extern int kill_proc_info(int, struct siginfo *, pid_t); +extern __must_check bool do_notify_parent(struct task_struct *, int); +extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); +extern void force_sig(int, struct task_struct *); +extern int send_sig(int, struct task_struct *, int); +extern int zap_other_threads(struct task_struct *p); +extern struct sigqueue *sigqueue_alloc(void); +extern void sigqueue_free(struct sigqueue *); +extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group); +extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); + +static inline int restart_syscall(void) +{ + set_tsk_thread_flag(current, TIF_SIGPENDING); + return -ERESTARTNOINTR; +} + +static inline int signal_pending(struct task_struct *p) +{ + return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); +} + +static inline int __fatal_signal_pending(struct task_struct *p) +{ + return unlikely(sigismember(&p->pending.signal, SIGKILL)); +} + +static inline int fatal_signal_pending(struct task_struct *p) +{ + return signal_pending(p) && __fatal_signal_pending(p); +} + +static inline int signal_pending_state(long state, struct task_struct *p) +{ + if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) + return 0; + if (!signal_pending(p)) + return 0; + + return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); +} + +/* + * Reevaluate whether the task has signals pending delivery. + * Wake the task if so. + * This is required every time the blocked sigset_t changes. + * callers must hold sighand->siglock. + */ +extern void recalc_sigpending_and_wake(struct task_struct *t); +extern void recalc_sigpending(void); + +extern void signal_wake_up_state(struct task_struct *t, unsigned int state); + +static inline void signal_wake_up(struct task_struct *t, bool resume) +{ + signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); +} +static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) +{ + signal_wake_up_state(t, resume ? __TASK_TRACED : 0); +} + +#ifdef TIF_RESTORE_SIGMASK +/* + * Legacy restore_sigmask accessors. These are inefficient on + * SMP architectures because they require atomic operations. + */ + +/** + * set_restore_sigmask() - make sure saved_sigmask processing gets done + * + * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code + * will run before returning to user mode, to process the flag. For + * all callers, TIF_SIGPENDING is already set or it's no harm to set + * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the + * arch code will notice on return to user mode, in case those bits + * are scarce. We set TIF_SIGPENDING here to ensure that the arch + * signal code always gets run when TIF_RESTORE_SIGMASK is set. + */ +static inline void set_restore_sigmask(void) +{ + set_thread_flag(TIF_RESTORE_SIGMASK); + WARN_ON(!test_thread_flag(TIF_SIGPENDING)); +} +static inline void clear_restore_sigmask(void) +{ + clear_thread_flag(TIF_RESTORE_SIGMASK); +} +static inline bool test_restore_sigmask(void) +{ + return test_thread_flag(TIF_RESTORE_SIGMASK); +} +static inline bool test_and_clear_restore_sigmask(void) +{ + return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); +} + +#else /* TIF_RESTORE_SIGMASK */ + +/* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ +static inline void set_restore_sigmask(void) +{ + current->restore_sigmask = true; + WARN_ON(!test_thread_flag(TIF_SIGPENDING)); +} +static inline void clear_restore_sigmask(void) +{ + current->restore_sigmask = false; +} +static inline bool test_restore_sigmask(void) +{ + return current->restore_sigmask; +} +static inline bool test_and_clear_restore_sigmask(void) +{ + if (!current->restore_sigmask) + return false; + current->restore_sigmask = false; + return true; +} +#endif + +static inline void restore_saved_sigmask(void) +{ + if (test_and_clear_restore_sigmask()) + __set_current_blocked(¤t->saved_sigmask); +} + +static inline sigset_t *sigmask_to_save(void) +{ + sigset_t *res = ¤t->blocked; + if (unlikely(test_restore_sigmask())) + res = ¤t->saved_sigmask; + return res; +} + +static inline int kill_cad_pid(int sig, int priv) +{ + return kill_pid(cad_pid, sig, priv); +} + +/* These can be the second arg to send_sig_info/send_group_sig_info. */ +#define SEND_SIG_NOINFO ((struct siginfo *) 0) +#define SEND_SIG_PRIV ((struct siginfo *) 1) +#define SEND_SIG_FORCED ((struct siginfo *) 2) + +/* + * True if we are on the alternate signal stack. + */ +static inline int on_sig_stack(unsigned long sp) +{ + /* + * If the signal stack is SS_AUTODISARM then, by construction, we + * can't be on the signal stack unless user code deliberately set + * SS_AUTODISARM when we were already on it. + * + * This improves reliability: if user state gets corrupted such that + * the stack pointer points very close to the end of the signal stack, + * then this check will enable the signal to be handled anyway. + */ + if (current->sas_ss_flags & SS_AUTODISARM) + return 0; + +#ifdef CONFIG_STACK_GROWSUP + return sp >= current->sas_ss_sp && + sp - current->sas_ss_sp < current->sas_ss_size; +#else + return sp > current->sas_ss_sp && + sp - current->sas_ss_sp <= current->sas_ss_size; +#endif +} + +static inline int sas_ss_flags(unsigned long sp) +{ + if (!current->sas_ss_size) + return SS_DISABLE; + + return on_sig_stack(sp) ? SS_ONSTACK : 0; +} + +static inline void sas_ss_reset(struct task_struct *p) +{ + p->sas_ss_sp = 0; + p->sas_ss_size = 0; + p->sas_ss_flags = SS_DISABLE; +} + +static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) +{ + if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) +#ifdef CONFIG_STACK_GROWSUP + return current->sas_ss_sp; +#else + return current->sas_ss_sp + current->sas_ss_size; +#endif + return sp; +} + +extern void __cleanup_sighand(struct sighand_struct *); +extern void flush_itimer_signals(void); + +#define tasklist_empty() \ + list_empty(&init_task.tasks) + +#define next_task(p) \ + list_entry_rcu((p)->tasks.next, struct task_struct, tasks) + +#define for_each_process(p) \ + for (p = &init_task ; (p = next_task(p)) != &init_task ; ) + +extern bool current_is_single_threaded(void); + +/* + * Careful: do_each_thread/while_each_thread is a double loop so + * 'break' will not work as expected - use goto instead. + */ +#define do_each_thread(g, t) \ + for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do + +#define while_each_thread(g, t) \ + while ((t = next_thread(t)) != g) + +#define __for_each_thread(signal, t) \ + list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) + +#define for_each_thread(p, t) \ + __for_each_thread((p)->signal, t) + +/* Careful: this is a double loop, 'break' won't work as expected. */ +#define for_each_process_thread(p, t) \ + for_each_process(p) for_each_thread(p, t) + +typedef int (*proc_visitor)(struct task_struct *p, void *data); +void walk_process_tree(struct task_struct *top, proc_visitor, void *); + +static inline int get_nr_threads(struct task_struct *tsk) +{ + return tsk->signal->nr_threads; +} + +static inline bool thread_group_leader(struct task_struct *p) +{ + return p->exit_signal >= 0; +} + +/* Do to the insanities of de_thread it is possible for a process + * to have the pid of the thread group leader without actually being + * the thread group leader. For iteration through the pids in proc + * all we care about is that we have a task with the appropriate + * pid, we don't actually care if we have the right task. + */ +static inline bool has_group_leader_pid(struct task_struct *p) +{ + return task_pid(p) == p->signal->leader_pid; +} + +static inline +bool same_thread_group(struct task_struct *p1, struct task_struct *p2) +{ + return p1->signal == p2->signal; +} + +static inline struct task_struct *next_thread(const struct task_struct *p) +{ + return list_entry_rcu(p->thread_group.next, + struct task_struct, thread_group); +} + +static inline int thread_group_empty(struct task_struct *p) +{ + return list_empty(&p->thread_group); +} + +#define delay_group_leader(p) \ + (thread_group_leader(p) && !thread_group_empty(p)) + +extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, + unsigned long *flags); + +static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + struct sighand_struct *ret; + + ret = __lock_task_sighand(tsk, flags); + (void)__cond_lock(&tsk->sighand->siglock, ret); + return ret; +} + +static inline void unlock_task_sighand(struct task_struct *tsk, + unsigned long *flags) +{ + spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); +} + +static inline unsigned long task_rlimit(const struct task_struct *tsk, + unsigned int limit) +{ + return READ_ONCE(tsk->signal->rlim[limit].rlim_cur); +} + +static inline unsigned long task_rlimit_max(const struct task_struct *tsk, + unsigned int limit) +{ + return READ_ONCE(tsk->signal->rlim[limit].rlim_max); +} + +static inline unsigned long rlimit(unsigned int limit) +{ + return task_rlimit(current, limit); +} + +static inline unsigned long rlimit_max(unsigned int limit) +{ + return task_rlimit_max(current, limit); +} + +#endif /* _LINUX_SCHED_SIGNAL_H */ diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h new file mode 100644 index 000000000000..141b74c53fad --- /dev/null +++ b/include/linux/sched/stat.h @@ -0,0 +1,40 @@ +#ifndef _LINUX_SCHED_STAT_H +#define _LINUX_SCHED_STAT_H + +#include <linux/percpu.h> + +/* + * Various counters maintained by the scheduler and fork(), + * exposed via /proc, sys.c or used by drivers via these APIs. + * + * ( Note that all these values are aquired without locking, + * so they can only be relied on in narrow circumstances. ) + */ + +extern unsigned long total_forks; +extern int nr_threads; +DECLARE_PER_CPU(unsigned long, process_counts); +extern int nr_processes(void); +extern unsigned long nr_running(void); +extern bool single_task_running(void); +extern unsigned long nr_iowait(void); +extern unsigned long nr_iowait_cpu(int cpu); +extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); + +static inline int sched_info_on(void) +{ +#ifdef CONFIG_SCHEDSTATS + return 1; +#elif defined(CONFIG_TASK_DELAY_ACCT) + extern int delayacct_on; + return delayacct_on; +#else + return 0; +#endif +} + +#ifdef CONFIG_SCHEDSTATS +void force_schedstat_enabled(void); +#endif + +#endif /* _LINUX_SCHED_STAT_H */ diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 22db1e63707e..0f5ecd4d298e 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -1,5 +1,9 @@ -#ifndef _SCHED_SYSCTL_H -#define _SCHED_SYSCTL_H +#ifndef _LINUX_SCHED_SYSCTL_H +#define _LINUX_SCHED_SYSCTL_H + +#include <linux/types.h> + +struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK extern int sysctl_hung_task_check_count; @@ -36,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size; extern unsigned int sysctl_sched_migration_cost; extern unsigned int sysctl_sched_nr_migrate; extern unsigned int sysctl_sched_time_avg; -extern unsigned int sysctl_sched_shares_window; int sched_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, @@ -60,6 +63,7 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice; extern unsigned int sysctl_sched_autogroup_enabled; #endif +extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; extern int sched_rr_handler(struct ctl_table *table, int write, @@ -78,4 +82,4 @@ extern int sysctl_schedstats(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -#endif /* _SCHED_SYSCTL_H */ +#endif /* _LINUX_SCHED_SYSCTL_H */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h new file mode 100644 index 000000000000..a978d7189cfd --- /dev/null +++ b/include/linux/sched/task.h @@ -0,0 +1,139 @@ +#ifndef _LINUX_SCHED_TASK_H +#define _LINUX_SCHED_TASK_H + +/* + * Interface between the scheduler and various task lifetime (fork()/exit()) + * functionality: + */ + +#include <linux/sched.h> + +struct task_struct; +union thread_union; + +/* + * This serializes "schedule()" and also protects + * the run-queue from deletions/modifications (but + * _adding_ to the beginning of the run-queue has + * a separate lock). + */ +extern rwlock_t tasklist_lock; +extern spinlock_t mmlist_lock; + +extern union thread_union init_thread_union; +extern struct task_struct init_task; + +#ifdef CONFIG_PROVE_RCU +extern int lockdep_tasklist_lock_is_held(void); +#endif /* #ifdef CONFIG_PROVE_RCU */ + +extern asmlinkage void schedule_tail(struct task_struct *prev); +extern void init_idle(struct task_struct *idle, int cpu); +extern void init_idle_bootup_task(struct task_struct *idle); + +extern int sched_fork(unsigned long clone_flags, struct task_struct *p); +extern void sched_dead(struct task_struct *p); + +void __noreturn do_task_dead(void); + +extern void proc_caches_init(void); + +extern void release_task(struct task_struct * p); + +#ifdef CONFIG_HAVE_COPY_THREAD_TLS +extern int copy_thread_tls(unsigned long, unsigned long, unsigned long, + struct task_struct *, unsigned long); +#else +extern int copy_thread(unsigned long, unsigned long, unsigned long, + struct task_struct *); + +/* Architectures that haven't opted into copy_thread_tls get the tls argument + * via pt_regs, so ignore the tls argument passed via C. */ +static inline int copy_thread_tls( + unsigned long clone_flags, unsigned long sp, unsigned long arg, + struct task_struct *p, unsigned long tls) +{ + return copy_thread(clone_flags, sp, arg, p); +} +#endif +extern void flush_thread(void); + +#ifdef CONFIG_HAVE_EXIT_THREAD +extern void exit_thread(struct task_struct *tsk); +#else +static inline void exit_thread(struct task_struct *tsk) +{ +} +#endif +extern void do_group_exit(int); + +extern void exit_files(struct task_struct *); +extern void exit_itimers(struct signal_struct *); + +extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); +extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); +struct task_struct *fork_idle(int); +extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); + +extern void free_task(struct task_struct *tsk); + +/* sched_exec is called by processes performing an exec */ +#ifdef CONFIG_SMP +extern void sched_exec(void); +#else +#define sched_exec() {} +#endif + +#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) + +extern void __put_task_struct(struct task_struct *t); + +static inline void put_task_struct(struct task_struct *t) +{ + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); +} + +struct task_struct *task_rcu_dereference(struct task_struct **ptask); +struct task_struct *try_get_task_struct(struct task_struct **ptask); + + +#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +extern int arch_task_struct_size __read_mostly; +#else +# define arch_task_struct_size (sizeof(struct task_struct)) +#endif + +#ifdef CONFIG_VMAP_STACK +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return t->stack_vm_area; +} +#else +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return NULL; +} +#endif + +/* + * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring + * subscriptions and synchronises with wait4(). Also used in procfs. Also + * pins the final release of task.io_context. Also protects ->cpuset and + * ->cgroup.subsys[]. And ->vfork_done. + * + * Nests both inside and outside of read_lock(&tasklist_lock). + * It must not be nested with write_lock_irq(&tasklist_lock), + * neither inside nor outside. + */ +static inline void task_lock(struct task_struct *p) +{ + spin_lock(&p->alloc_lock); +} + +static inline void task_unlock(struct task_struct *p) +{ + spin_unlock(&p->alloc_lock); +} + +#endif /* _LINUX_SCHED_TASK_H */ diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h new file mode 100644 index 000000000000..df6ea6665b31 --- /dev/null +++ b/include/linux/sched/task_stack.h @@ -0,0 +1,121 @@ +#ifndef _LINUX_SCHED_TASK_STACK_H +#define _LINUX_SCHED_TASK_STACK_H + +/* + * task->stack (kernel stack) handling interfaces: + */ + +#include <linux/sched.h> +#include <linux/magic.h> + +#ifdef CONFIG_THREAD_INFO_IN_TASK + +/* + * When accessing the stack of a non-current task that might exit, use + * try_get_task_stack() instead. task_stack_page will return a pointer + * that could get freed out from under you. + */ +static inline void *task_stack_page(const struct task_struct *task) +{ + return task->stack; +} + +#define setup_thread_stack(new,old) do { } while(0) + +static inline unsigned long *end_of_stack(const struct task_struct *task) +{ + return task->stack; +} + +#elif !defined(__HAVE_THREAD_FUNCTIONS) + +#define task_stack_page(task) ((void *)(task)->stack) + +static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) +{ + *task_thread_info(p) = *task_thread_info(org); + task_thread_info(p)->task = p; +} + +/* + * Return the address of the last usable long on the stack. + * + * When the stack grows down, this is just above the thread + * info struct. Going any lower will corrupt the threadinfo. + * + * When the stack grows up, this is the highest address. + * Beyond that position, we corrupt data on the next page. + */ +static inline unsigned long *end_of_stack(struct task_struct *p) +{ +#ifdef CONFIG_STACK_GROWSUP + return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; +#else + return (unsigned long *)(task_thread_info(p) + 1); +#endif +} + +#endif + +#ifdef CONFIG_THREAD_INFO_IN_TASK +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return atomic_inc_not_zero(&tsk->stack_refcount) ? + task_stack_page(tsk) : NULL; +} + +extern void put_task_stack(struct task_struct *tsk); +#else +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return task_stack_page(tsk); +} + +static inline void put_task_stack(struct task_struct *tsk) {} +#endif + +#define task_stack_end_corrupted(task) \ + (*(end_of_stack(task)) != STACK_END_MAGIC) + +static inline int object_is_on_stack(void *obj) +{ + void *stack = task_stack_page(current); + + return (obj >= stack) && (obj < (stack + THREAD_SIZE)); +} + +extern void thread_stack_cache_init(void); + +#ifdef CONFIG_DEBUG_STACK_USAGE +static inline unsigned long stack_not_used(struct task_struct *p) +{ + unsigned long *n = end_of_stack(p); + + do { /* Skip over canary */ +# ifdef CONFIG_STACK_GROWSUP + n--; +# else + n++; +# endif + } while (!*n); + +# ifdef CONFIG_STACK_GROWSUP + return (unsigned long)end_of_stack(p) - (unsigned long)n; +# else + return (unsigned long)n - (unsigned long)end_of_stack(p); +# endif +} +#endif +extern void set_task_stack_end_magic(struct task_struct *tsk); + +#ifndef __HAVE_ARCH_KSTACK_END +static inline int kstack_end(void *addr) +{ + /* Reliable end of stack detection: + * Some APM bios versions misalign the stack + */ + return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); +} +#endif + +#endif /* _LINUX_SCHED_TASK_STACK_H */ diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h new file mode 100644 index 000000000000..7d065abc7a47 --- /dev/null +++ b/include/linux/sched/topology.h @@ -0,0 +1,226 @@ +#ifndef _LINUX_SCHED_TOPOLOGY_H +#define _LINUX_SCHED_TOPOLOGY_H + +#include <linux/topology.h> + +#include <linux/sched/idle.h> + +/* + * sched-domains (multiprocessor balancing) declarations: + */ +#ifdef CONFIG_SMP + +#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */ +#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */ +#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */ +#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */ +#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */ +#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */ +#define SD_ASYM_CPUCAPACITY 0x0040 /* Groups have different max cpu capacities */ +#define SD_SHARE_CPUCAPACITY 0x0080 /* Domain members share cpu capacity */ +#define SD_SHARE_POWERDOMAIN 0x0100 /* Domain members share power domain */ +#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */ +#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ +#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ +#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ +#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ +#define SD_NUMA 0x4000 /* cross-node balancing */ + +/* + * Increase resolution of cpu_capacity calculations + */ +#define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT +#define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) + +#ifdef CONFIG_SCHED_SMT +static inline int cpu_smt_flags(void) +{ + return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_SCHED_MC +static inline int cpu_core_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} +#endif + +#ifdef CONFIG_NUMA +static inline int cpu_numa_flags(void) +{ + return SD_NUMA; +} +#endif + +extern int arch_asym_cpu_priority(int cpu); + +struct sched_domain_attr { + int relax_domain_level; +}; + +#define SD_ATTR_INIT (struct sched_domain_attr) { \ + .relax_domain_level = -1, \ +} + +extern int sched_domain_level_max; + +struct sched_group; + +struct sched_domain_shared { + atomic_t ref; + atomic_t nr_busy_cpus; + int has_idle_cores; +}; + +struct sched_domain { + /* These fields must be setup */ + struct sched_domain *parent; /* top domain must be null terminated */ + struct sched_domain *child; /* bottom domain must be null terminated */ + struct sched_group *groups; /* the balancing groups of the domain */ + unsigned long min_interval; /* Minimum balance interval ms */ + unsigned long max_interval; /* Maximum balance interval ms */ + unsigned int busy_factor; /* less balancing by factor if busy */ + unsigned int imbalance_pct; /* No balance until over watermark */ + unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ + unsigned int busy_idx; + unsigned int idle_idx; + unsigned int newidle_idx; + unsigned int wake_idx; + unsigned int forkexec_idx; + unsigned int smt_gain; + + int nohz_idle; /* NOHZ IDLE status */ + int flags; /* See SD_* */ + int level; + + /* Runtime fields. */ + unsigned long last_balance; /* init to jiffies. units in jiffies */ + unsigned int balance_interval; /* initialise to 1. units in ms. */ + unsigned int nr_balance_failed; /* initialise to 0 */ + + /* idle_balance() stats */ + u64 max_newidle_lb_cost; + unsigned long next_decay_max_lb_cost; + + u64 avg_scan_cost; /* select_idle_sibling */ + +#ifdef CONFIG_SCHEDSTATS + /* load_balance() stats */ + unsigned int lb_count[CPU_MAX_IDLE_TYPES]; + unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; + unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; + unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES]; + unsigned int lb_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES]; + unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES]; + + /* Active load balancing */ + unsigned int alb_count; + unsigned int alb_failed; + unsigned int alb_pushed; + + /* SD_BALANCE_EXEC stats */ + unsigned int sbe_count; + unsigned int sbe_balanced; + unsigned int sbe_pushed; + + /* SD_BALANCE_FORK stats */ + unsigned int sbf_count; + unsigned int sbf_balanced; + unsigned int sbf_pushed; + + /* try_to_wake_up() stats */ + unsigned int ttwu_wake_remote; + unsigned int ttwu_move_affine; + unsigned int ttwu_move_balance; +#endif +#ifdef CONFIG_SCHED_DEBUG + char *name; +#endif + union { + void *private; /* used during construction */ + struct rcu_head rcu; /* used during destruction */ + }; + struct sched_domain_shared *shared; + + unsigned int span_weight; + /* + * Span of all CPUs in this domain. + * + * NOTE: this field is variable length. (Allocated dynamically + * by attaching extra space to the end of the structure, + * depending on how many CPUs the kernel has booted up with) + */ + unsigned long span[0]; +}; + +static inline struct cpumask *sched_domain_span(struct sched_domain *sd) +{ + return to_cpumask(sd->span); +} + +extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new); + +/* Allocate an array of sched domains, for partition_sched_domains(). */ +cpumask_var_t *alloc_sched_domains(unsigned int ndoms); +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); + +bool cpus_share_cache(int this_cpu, int that_cpu); + +typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +typedef int (*sched_domain_flags_f)(void); + +#define SDTL_OVERLAP 0x01 + +struct sd_data { + struct sched_domain **__percpu sd; + struct sched_domain_shared **__percpu sds; + struct sched_group **__percpu sg; + struct sched_group_capacity **__percpu sgc; +}; + +struct sched_domain_topology_level { + sched_domain_mask_f mask; + sched_domain_flags_f sd_flags; + int flags; + int numa_level; + struct sd_data data; +#ifdef CONFIG_SCHED_DEBUG + char *name; +#endif +}; + +extern void set_sched_topology(struct sched_domain_topology_level *tl); + +#ifdef CONFIG_SCHED_DEBUG +# define SD_INIT_NAME(type) .name = #type +#else +# define SD_INIT_NAME(type) +#endif + +#else /* CONFIG_SMP */ + +struct sched_domain_attr; + +static inline void +partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ +} + +static inline bool cpus_share_cache(int this_cpu, int that_cpu) +{ + return true; +} + +#endif /* !CONFIG_SMP */ + +static inline int task_node(const struct task_struct *p) +{ + return cpu_to_node(task_cpu(p)); +} + +#endif /* _LINUX_SCHED_TOPOLOGY_H */ diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h new file mode 100644 index 000000000000..5d5415e129d4 --- /dev/null +++ b/include/linux/sched/user.h @@ -0,0 +1,61 @@ +#ifndef _LINUX_SCHED_USER_H +#define _LINUX_SCHED_USER_H + +#include <linux/uidgid.h> +#include <linux/atomic.h> + +struct key; + +/* + * Some day this will be a full-fledged user tracking system.. + */ +struct user_struct { + atomic_t __count; /* reference count */ + atomic_t processes; /* How many processes does this user have? */ + atomic_t sigpending; /* How many pending signals does this user have? */ +#ifdef CONFIG_FANOTIFY + atomic_t fanotify_listeners; +#endif +#ifdef CONFIG_EPOLL + atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ +#endif +#ifdef CONFIG_POSIX_MQUEUE + /* protected by mq_lock */ + unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ +#endif + unsigned long locked_shm; /* How many pages of mlocked shm ? */ + unsigned long unix_inflight; /* How many files in flight in unix sockets */ + atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ + +#ifdef CONFIG_KEYS + struct key *uid_keyring; /* UID specific keyring */ + struct key *session_keyring; /* UID's default session keyring */ +#endif + + /* Hash table maintenance information */ + struct hlist_node uidhash_node; + kuid_t uid; + +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) + atomic_long_t locked_vm; +#endif +}; + +extern int uids_sysfs_init(void); + +extern struct user_struct *find_user(kuid_t); + +extern struct user_struct root_user; +#define INIT_USER (&root_user) + + +/* per-UID process charging. */ +extern struct user_struct * alloc_uid(kuid_t); +static inline struct user_struct *get_uid(struct user_struct *u) +{ + atomic_inc(&u->__count); + return u; +} +extern void free_uid(struct user_struct *); + +#endif /* _LINUX_SCHED_USER_H */ diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h new file mode 100644 index 000000000000..d03d8a9047dc --- /dev/null +++ b/include/linux/sched/wake_q.h @@ -0,0 +1,53 @@ +#ifndef _LINUX_SCHED_WAKE_Q_H +#define _LINUX_SCHED_WAKE_Q_H + +/* + * Wake-queues are lists of tasks with a pending wakeup, whose + * callers have already marked the task as woken internally, + * and can thus carry on. A common use case is being able to + * do the wakeups once the corresponding user lock as been + * released. + * + * We hold reference to each task in the list across the wakeup, + * thus guaranteeing that the memory is still valid by the time + * the actual wakeups are performed in wake_up_q(). + * + * One per task suffices, because there's never a need for a task to be + * in two wake queues simultaneously; it is forbidden to abandon a task + * in a wake queue (a call to wake_up_q() _must_ follow), so if a task is + * already in a wake queue, the wakeup will happen soon and the second + * waker can just skip it. + * + * The DEFINE_WAKE_Q macro declares and initializes the list head. + * wake_up_q() does NOT reinitialize the list; it's expected to be + * called near the end of a function. Otherwise, the list can be + * re-initialized for later re-use by wake_q_init(). + * + * Note that this can cause spurious wakeups. schedule() callers + * must ensure the call is done inside a loop, confirming that the + * wakeup condition has in fact occurred. + */ + +#include <linux/sched.h> + +struct wake_q_head { + struct wake_q_node *first; + struct wake_q_node **lastp; +}; + +#define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) + +#define DEFINE_WAKE_Q(name) \ + struct wake_q_head name = { WAKE_Q_TAIL, &name.first } + +static inline void wake_q_init(struct wake_q_head *head) +{ + head->first = WAKE_Q_TAIL; + head->lastp = &head->first; +} + +extern void wake_q_add(struct wake_q_head *head, + struct task_struct *task); +extern void wake_up_q(struct wake_q_head *head); + +#endif /* _LINUX_SCHED_WAKE_Q_H */ diff --git a/include/linux/sched/xacct.h b/include/linux/sched/xacct.h new file mode 100644 index 000000000000..a28156a0d34a --- /dev/null +++ b/include/linux/sched/xacct.h @@ -0,0 +1,48 @@ +#ifndef _LINUX_SCHED_XACCT_H +#define _LINUX_SCHED_XACCT_H + +/* + * Extended task accounting methods: + */ + +#include <linux/sched.h> + +#ifdef CONFIG_TASK_XACCT +static inline void add_rchar(struct task_struct *tsk, ssize_t amt) +{ + tsk->ioac.rchar += amt; +} + +static inline void add_wchar(struct task_struct *tsk, ssize_t amt) +{ + tsk->ioac.wchar += amt; +} + +static inline void inc_syscr(struct task_struct *tsk) +{ + tsk->ioac.syscr++; +} + +static inline void inc_syscw(struct task_struct *tsk) +{ + tsk->ioac.syscw++; +} +#else +static inline void add_rchar(struct task_struct *tsk, ssize_t amt) +{ +} + +static inline void add_wchar(struct task_struct *tsk, ssize_t amt) +{ +} + +static inline void inc_syscr(struct task_struct *tsk) +{ +} + +static inline void inc_syscw(struct task_struct *tsk) +{ +} +#endif + +#endif /* _LINUX_SCHED_XACCT_H */ |
