diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 224 |
1 files changed, 162 insertions, 62 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index 4d0a12618e3c..ffb6eb55cd13 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -14,6 +14,7 @@ #include <linux/pid.h> #include <linux/sem.h> #include <linux/shm.h> +#include <linux/kmsan_types.h> #include <linux/mutex.h> #include <linux/plist.h> #include <linux/hrtimer.h> @@ -34,6 +35,7 @@ #include <linux/rseq.h> #include <linux/seqlock.h> #include <linux/kcsan.h> +#include <linux/rv.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ @@ -80,30 +82,39 @@ struct task_group; */ /* Used in tsk->state: */ -#define TASK_RUNNING 0x0000 -#define TASK_INTERRUPTIBLE 0x0001 -#define TASK_UNINTERRUPTIBLE 0x0002 -#define __TASK_STOPPED 0x0004 -#define __TASK_TRACED 0x0008 +#define TASK_RUNNING 0x00000000 +#define TASK_INTERRUPTIBLE 0x00000001 +#define TASK_UNINTERRUPTIBLE 0x00000002 +#define __TASK_STOPPED 0x00000004 +#define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ -#define EXIT_DEAD 0x0010 -#define EXIT_ZOMBIE 0x0020 +#define EXIT_DEAD 0x00000010 +#define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ -#define TASK_PARKED 0x0040 -#define TASK_DEAD 0x0080 -#define TASK_WAKEKILL 0x0100 -#define TASK_WAKING 0x0200 -#define TASK_NOLOAD 0x0400 -#define TASK_NEW 0x0800 -/* RT specific auxilliary flag to mark RT lock waiters */ -#define TASK_RTLOCK_WAIT 0x1000 -#define TASK_STATE_MAX 0x2000 +#define TASK_PARKED 0x00000040 +#define TASK_DEAD 0x00000080 +#define TASK_WAKEKILL 0x00000100 +#define TASK_WAKING 0x00000200 +#define TASK_NOLOAD 0x00000400 +#define TASK_NEW 0x00000800 +#define TASK_RTLOCK_WAIT 0x00001000 +#define TASK_FREEZABLE 0x00002000 +#define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) +#define TASK_FROZEN 0x00008000 +#define TASK_STATE_MAX 0x00010000 + +#define TASK_ANY (TASK_STATE_MAX-1) + +/* + * DO NOT ADD ANY NEW USERS ! + */ +#define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) -#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) +#define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) @@ -118,11 +129,9 @@ struct task_group; #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) -#define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) - -#define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) - -#define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) +#define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) +#define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) +#define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See @@ -274,8 +283,13 @@ struct task_group; #define get_current_state() READ_ONCE(current->__state) -/* Task command name length: */ -#define TASK_COMM_LEN 16 +/* + * Define the task command name length as enum, then it can be visible to + * BPF programs. + */ +enum { + TASK_COMM_LEN = 16, +}; extern void scheduler_tick(void); @@ -614,10 +628,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_boosted tells if we are boosted due to DI. If so we are - * outside bandwidth enforcement mechanism (but only until we - * exit the critical section); - * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * @@ -844,8 +854,9 @@ struct task_struct { int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; - bool trc_reader_checked; struct list_head trc_holdout_list; + struct list_head trc_blkd_node; + int trc_blkd_cpu; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; @@ -859,9 +870,6 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; - /* Per-thread vma caching: */ - struct vmacache vmacache; - #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif @@ -913,6 +921,10 @@ struct task_struct { #ifdef CONFIG_MEMCG unsigned in_user_fault:1; #endif +#ifdef CONFIG_LRU_GEN + /* whether the LRU algorithm may apply to this access */ + unsigned in_lru_fault:1; +#endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif @@ -935,7 +947,17 @@ struct task_struct { #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ - unsigned in_eventfd_signal:1; + unsigned in_eventfd:1; +#endif +#ifdef CONFIG_IOMMU_SVA + unsigned pasid_activated:1; +#endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif +#ifdef CONFIG_TASK_DELAY_ACCT + /* delay due to memory thrashing */ + unsigned in_thrashing:1; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -991,8 +1013,8 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; - /* PF_IO_WORKER */ - void *pf_io_worker; + /* PF_KTHREAD | PF_IO_WORKER */ + void *worker_private; u64 utime; u64 stime; @@ -1348,6 +1370,10 @@ struct task_struct { #endif #endif +#ifdef CONFIG_KMSAN + struct kmsan_ctx kmsan_ctx; +#endif + #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif @@ -1374,9 +1400,6 @@ struct task_struct { #endif #ifdef CONFIG_TRACING - /* State flags for use by tracers: */ - unsigned long trace; - /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ @@ -1439,6 +1462,7 @@ struct task_struct { int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; + struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; @@ -1480,6 +1504,9 @@ struct task_struct { #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif +#ifdef CONFIG_RETHOOK + struct llist_head rethooks; +#endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* @@ -1491,6 +1518,16 @@ struct task_struct { struct callback_head l1d_flush_kill; #endif +#ifdef CONFIG_RV + /* + * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. + * If we find justification for more monitors, we can think + * about adding more or developing a dynamic method. So far, + * none of these are justified. + */ + union rv_task_monitor rv[RV_PER_TASK_MONITORS]; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. @@ -1619,19 +1656,32 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) -static inline unsigned int task_state_index(struct task_struct *tsk) +static inline unsigned int __task_state_index(unsigned int tsk_state, + unsigned int tsk_exit_state) { - unsigned int tsk_state = READ_ONCE(tsk->__state); - unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if (tsk_state == TASK_IDLE) state = TASK_REPORT_IDLE; + /* + * We're lying here, but rather than expose a completely new task state + * to userspace, we can make this appear as if the task has gone through + * a regular rt_mutex_lock() call. + */ + if (tsk_state == TASK_RTLOCK_WAIT) + state = TASK_UNINTERRUPTIBLE; + return fls(state); } +static inline unsigned int task_state_index(struct task_struct *tsk) +{ + return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); +} + static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; @@ -1679,9 +1729,9 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ +#define PF__HOLE__00004000 0x00004000 #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF_FROZEN 0x00010000 /* Frozen for system suspend */ +#define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ @@ -1689,11 +1739,14 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ -#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF__HOLE__00800000 0x00800000 +#define PF__HOLE__01000000 0x01000000 +#define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ -#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +#define PF__HOLE__20000000 0x20000000 +#define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* @@ -1793,7 +1846,7 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags) } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); -extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed); +extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); @@ -2015,7 +2068,7 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); -#ifdef CONFIG_PREEMPT_DYNAMIC +#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) DECLARE_STATIC_CALL(cond_resched, __cond_resched); @@ -2024,6 +2077,14 @@ static __always_inline int _cond_resched(void) return static_call_mod(cond_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +extern int dynamic_cond_resched(void); + +static __always_inline int _cond_resched(void) +{ + return dynamic_cond_resched(); +} + #else static inline int _cond_resched(void) @@ -2091,6 +2152,47 @@ static inline void cond_resched_rcu(void) #endif } +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, @@ -2154,6 +2256,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); +extern struct task_struct *cpu_curr_snapshot(int cpu); /* * In order to reduce various lock holder preemption latencies provide an @@ -2178,8 +2281,17 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #endif #ifdef CONFIG_SMP +static inline bool owner_on_cpu(struct task_struct *owner) +{ + /* + * As lock holder preemption issue, we both skip spinning if + * task is not on cpu or its cpu is preempted + */ + return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); +} + /* Returns effective CPU energy utilization, as seen by the scheduler */ -unsigned long sched_cpu_util(int cpu, unsigned long max); +unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_RSEQ @@ -2302,20 +2414,6 @@ static inline void rseq_syscall(struct pt_regs *regs) #endif -const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); -char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); -int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); - -const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); -const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); - -int sched_trace_rq_cpu(struct rq *rq); -int sched_trace_rq_cpu_capacity(struct rq *rq); -int sched_trace_rq_nr_running(struct rq *rq); - -const struct cpumask *sched_trace_rd_span(struct root_domain *rd); - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); @@ -2326,4 +2424,6 @@ static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } #endif +extern void sched_set_stop_task(int cpu, struct task_struct *stop); + #endif |