diff options
Diffstat (limited to 'include/linux/sched.h')
-rw-r--r-- | include/linux/sched.h | 225 |
1 files changed, 171 insertions, 54 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index ec8d07d88641..6f6f8f340a0f 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) @@ -121,8 +124,6 @@ struct task_group; #define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) -#ifdef CONFIG_DEBUG_ATOMIC_SLEEP - /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). @@ -130,30 +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_; \ - WRITE_ONCE(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_; \ - WRITE_ONCE(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 @@ -192,26 +200,77 @@ struct task_group; * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ - WRITE_ONCE(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); \ + 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) @@ -230,6 +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); @@ -441,6 +503,8 @@ struct sched_statistics { u64 block_start; u64 block_max; + s64 sum_block_runtime; + u64 exec_max; u64 slice_max; @@ -460,7 +524,7 @@ struct sched_statistics { u64 nr_wakeups_passive; u64 nr_wakeups_idle; #endif -}; +} ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ @@ -476,8 +540,6 @@ struct sched_entity { u64 nr_migrations; - struct sched_statistics statistics; - #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; @@ -668,6 +730,11 @@ struct task_struct { #endif 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 * scheduling-critical items should be added above here. @@ -683,10 +750,6 @@ struct task_struct { #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; -#ifdef CONFIG_THREAD_INFO_IN_TASK - /* Current CPU: */ - unsigned int cpu; -#endif unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; @@ -708,10 +771,10 @@ struct task_struct { int normal_prio; unsigned int rt_priority; - const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; + const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; @@ -736,6 +799,8 @@ struct task_struct { struct uclamp_se uclamp[UCLAMP_CNT]; #endif + struct sched_statistics stats; + #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; @@ -748,6 +813,7 @@ 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 @@ -863,6 +929,10 @@ 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. */ @@ -1088,10 +1158,8 @@ struct task_struct { /* Stacked block device info: */ struct bio_list *bio_list; -#ifdef CONFIG_BLOCK /* Stack plugging: */ struct blk_plug *plug; -#endif /* VM state: */ struct reclaim_state *reclaim_state; @@ -1357,6 +1425,9 @@ 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 @@ -1379,6 +1450,8 @@ 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 @@ -1394,12 +1467,23 @@ struct task_struct { mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; + int mce_count; #endif #ifdef CONFIG_KRETPROBES 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. @@ -1632,7 +1716,7 @@ extern struct pid *cad_pid; #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -static inline bool is_percpu_thread(void) +static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && @@ -1705,6 +1789,11 @@ 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) { @@ -1715,6 +1804,21 @@ 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); @@ -1778,10 +1882,7 @@ extern struct thread_info init_thread_info; extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK -static inline struct thread_info *task_thread_info(struct task_struct *task) -{ - return &task->thread_info; -} +# define task_thread_info(task) (&(task)->thread_info) #elif !defined(__HAVE_THREAD_FUNCTIONS) # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif @@ -1931,7 +2032,7 @@ static inline int _cond_resched(void) { return 0; } #endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ #define cond_resched() ({ \ - ___might_sleep(__FILE__, __LINE__, 0); \ + __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) @@ -1939,19 +2040,38 @@ extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); -#define cond_resched_lock(lock) ({ \ - ___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\ - __cond_resched_lock(lock); \ +#define MIGHT_RESCHED_RCU_SHIFT 8 +#define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) + +#ifndef CONFIG_PREEMPT_RT +/* + * Non RT kernels have an elevated preempt count due to the held lock, + * but are not allowed to be inside a RCU read side critical section + */ +# define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET +#else +/* + * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in + * cond_resched*lock() has to take that into account because it checks for + * preempt_count() and rcu_preempt_depth(). + */ +# define PREEMPT_LOCK_RESCHED_OFFSETS \ + (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) +#endif + +#define cond_resched_lock(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ + __cond_resched_lock(lock); \ }) -#define cond_resched_rwlock_read(lock) ({ \ - __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ - __cond_resched_rwlock_read(lock); \ +#define cond_resched_rwlock_read(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ + __cond_resched_rwlock_read(lock); \ }) -#define cond_resched_rwlock_write(lock) ({ \ - __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ - __cond_resched_rwlock_write(lock); \ +#define cond_resched_rwlock_write(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ + __cond_resched_rwlock_write(lock); \ }) static inline void cond_resched_rcu(void) @@ -2006,11 +2126,7 @@ static __always_inline bool need_resched(void) static inline unsigned int task_cpu(const struct task_struct *p) { -#ifdef CONFIG_THREAD_INFO_IN_TASK - return READ_ONCE(p->cpu); -#else return READ_ONCE(task_thread_info(p)->cpu); -#endif } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); @@ -2029,6 +2145,7 @@ 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); +extern unsigned long get_wchan(struct task_struct *p); /* * In order to reduce various lock holder preemption latencies provide an |