diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 206 |
1 files changed, 171 insertions, 35 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index d2c881384517..e12b524426b0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -42,6 +42,7 @@ struct backing_dev_info; struct bio_list; struct blk_plug; struct bpf_local_storage; +struct bpf_run_ctx; struct capture_control; struct cfs_rq; struct fs_struct; @@ -95,7 +96,9 @@ struct task_group; #define TASK_WAKING 0x0200 #define TASK_NOLOAD 0x0400 #define TASK_NEW 0x0800 -#define TASK_STATE_MAX 0x1000 +/* RT specific auxilliary flag to mark RT lock waiters */ +#define TASK_RTLOCK_WAIT 0x1000 +#define TASK_STATE_MAX 0x2000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) @@ -113,13 +116,13 @@ struct task_group; __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) -#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) +#define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) -#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) +#define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) -#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) +#define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) -#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +#define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See @@ -128,30 +131,37 @@ struct task_group; #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) -#define __set_current_state(state_value) \ - do { \ - WARN_ON_ONCE(is_special_task_state(state_value));\ - current->task_state_change = _THIS_IP_; \ - current->state = (state_value); \ - } while (0) - -#define set_current_state(state_value) \ - do { \ - WARN_ON_ONCE(is_special_task_state(state_value));\ - current->task_state_change = _THIS_IP_; \ - smp_store_mb(current->state, (state_value)); \ +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +# define debug_normal_state_change(state_value) \ + do { \ + WARN_ON_ONCE(is_special_task_state(state_value)); \ + current->task_state_change = _THIS_IP_; \ } while (0) -#define set_special_state(state_value) \ +# define debug_special_state_change(state_value) \ do { \ - unsigned long flags; /* may shadow */ \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ - raw_spin_lock_irqsave(¤t->pi_lock, flags); \ current->task_state_change = _THIS_IP_; \ - current->state = (state_value); \ - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) + +# define debug_rtlock_wait_set_state() \ + do { \ + current->saved_state_change = current->task_state_change;\ + current->task_state_change = _THIS_IP_; \ + } while (0) + +# define debug_rtlock_wait_restore_state() \ + do { \ + current->task_state_change = current->saved_state_change;\ + } while (0) + #else +# define debug_normal_state_change(cond) do { } while (0) +# define debug_special_state_change(cond) do { } while (0) +# define debug_rtlock_wait_set_state() do { } while (0) +# define debug_rtlock_wait_restore_state() do { } while (0) +#endif + /* * set_current_state() includes a barrier so that the write of current->state * is correctly serialised wrt the caller's subsequent test of whether to @@ -190,26 +200,79 @@ struct task_group; * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ - current->state = (state_value) + do { \ + debug_normal_state_change((state_value)); \ + WRITE_ONCE(current->__state, (state_value)); \ + } while (0) #define set_current_state(state_value) \ - smp_store_mb(current->state, (state_value)) + do { \ + debug_normal_state_change((state_value)); \ + smp_store_mb(current->__state, (state_value)); \ + } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must - * serialize against wakeups such that any possible in-flight TASK_RUNNING stores - * will not collide with our state change. + * serialize against wakeups such that any possible in-flight TASK_RUNNING + * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ + \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ - current->state = (state_value); \ + debug_special_state_change((state_value)); \ + WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) -#endif +/* + * PREEMPT_RT specific variants for "sleeping" spin/rwlocks + * + * RT's spin/rwlock substitutions are state preserving. The state of the + * task when blocking on the lock is saved in task_struct::saved_state and + * restored after the lock has been acquired. These operations are + * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT + * lock related wakeups while the task is blocked on the lock are + * redirected to operate on task_struct::saved_state to ensure that these + * are not dropped. On restore task_struct::saved_state is set to + * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. + * + * The lock operation looks like this: + * + * current_save_and_set_rtlock_wait_state(); + * for (;;) { + * if (try_lock()) + * break; + * raw_spin_unlock_irq(&lock->wait_lock); + * schedule_rtlock(); + * raw_spin_lock_irq(&lock->wait_lock); + * set_current_state(TASK_RTLOCK_WAIT); + * } + * current_restore_rtlock_saved_state(); + */ +#define current_save_and_set_rtlock_wait_state() \ + do { \ + lockdep_assert_irqs_disabled(); \ + raw_spin_lock(¤t->pi_lock); \ + current->saved_state = current->__state; \ + debug_rtlock_wait_set_state(); \ + WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + +#define current_restore_rtlock_saved_state() \ + do { \ + lockdep_assert_irqs_disabled(); \ + raw_spin_lock(¤t->pi_lock); \ + debug_rtlock_wait_restore_state(); \ + WRITE_ONCE(current->__state, current->saved_state); \ + current->saved_state = TASK_RUNNING; \ + raw_spin_unlock(¤t->pi_lock); \ + } while (0); + +#define get_current_state() READ_ONCE(current->__state) /* Task command name length: */ #define TASK_COMM_LEN 16 @@ -226,6 +289,9 @@ extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); +#ifdef CONFIG_PREEMPT_RT + extern void schedule_rtlock(void); +#endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); @@ -350,11 +416,19 @@ struct load_weight { * Only for tasks we track a moving average of the past instantaneous * estimated utilization. This allows to absorb sporadic drops in utilization * of an otherwise almost periodic task. + * + * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg + * updates. When a task is dequeued, its util_est should not be updated if its + * util_avg has not been updated in the meantime. + * This information is mapped into the MSB bit of util_est.enqueued at dequeue + * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg + * for a task) it is safe to use MSB. */ struct util_est { unsigned int enqueued; unsigned int ewma; #define UTIL_EST_WEIGHT_SHIFT 2 +#define UTIL_AVG_UNCHANGED 0x80000000 } __attribute__((__aligned__(sizeof(u64)))); /* @@ -654,8 +728,12 @@ struct task_struct { */ struct thread_info thread_info; #endif - /* -1 unrunnable, 0 runnable, >0 stopped: */ - volatile long state; + unsigned int __state; + +#ifdef CONFIG_PREEMPT_RT + /* saved state for "spinlock sleepers" */ + unsigned int saved_state; +#endif /* * This begins the randomizable portion of task_struct. Only @@ -700,10 +778,17 @@ struct task_struct { const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; + struct sched_dl_entity dl; + +#ifdef CONFIG_SCHED_CORE + struct rb_node core_node; + unsigned long core_cookie; + unsigned int core_occupation; +#endif + #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif - struct sched_dl_entity dl; #ifdef CONFIG_UCLAMP_TASK /* @@ -730,6 +815,7 @@ struct task_struct { unsigned int policy; int nr_cpus_allowed; const cpumask_t *cpus_ptr; + cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP @@ -845,6 +931,10 @@ struct task_struct { /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif +#ifdef CONFIG_EVENTFD + /* Recursion prevention for eventfd_signal() */ + unsigned in_eventfd_signal:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -989,7 +1079,6 @@ struct task_struct { /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; - struct sigqueue *sigqueue_cache; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ @@ -1340,6 +1429,9 @@ struct task_struct { struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; +# ifdef CONFIG_PREEMPT_RT + unsigned long saved_state_change; +# endif #endif int pagefault_disabled; #ifdef CONFIG_MMU @@ -1362,6 +1454,8 @@ struct task_struct { #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; + /* Used for BPF run context */ + struct bpf_run_ctx *bpf_ctx; #endif #ifdef CONFIG_GCC_PLUGIN_STACKLEAK @@ -1383,6 +1477,16 @@ struct task_struct { struct llist_head kretprobe_instances; #endif +#ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH + /* + * If L1D flush is supported on mm context switch + * then we use this callback head to queue kill work + * to kill tasks that are not running on SMT disabled + * cores + */ + struct callback_head l1d_flush_kill; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. @@ -1513,7 +1617,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) static inline unsigned int task_state_index(struct task_struct *tsk) { - unsigned int tsk_state = READ_ONCE(tsk->state); + unsigned int tsk_state = READ_ONCE(tsk->__state); unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); @@ -1688,6 +1792,11 @@ extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_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); +extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); +extern void release_user_cpus_ptr(struct task_struct *p); +extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); +extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); +extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { @@ -1698,6 +1807,21 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpuma return -EINVAL; return 0; } +static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) +{ + if (src->user_cpus_ptr) + return -EINVAL; + return 0; +} +static inline void release_user_cpus_ptr(struct task_struct *p) +{ + WARN_ON(p->user_cpus_ptr); +} + +static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) +{ + return 0; +} #endif extern int yield_to(struct task_struct *p, bool preempt); @@ -1821,10 +1945,10 @@ static __always_inline void scheduler_ipi(void) */ preempt_fold_need_resched(); } -extern unsigned long wait_task_inactive(struct task_struct *, long match_state); +extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); #else static inline void scheduler_ipi(void) { } -static inline unsigned long wait_task_inactive(struct task_struct *p, long match_state) +static inline unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) { return 1; } @@ -2011,6 +2135,8 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +extern bool sched_task_on_rq(struct task_struct *p); + /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. @@ -2172,4 +2298,14 @@ 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); +extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, + unsigned long uaddr); +#else +static inline void sched_core_free(struct task_struct *tsk) { } +static inline void sched_core_fork(struct task_struct *p) { } +#endif + #endif |