diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 254 |
1 files changed, 203 insertions, 51 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index ca3f3eae8980..89541d248893 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,8 +25,10 @@ #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/signal_types.h> +#include <linux/psi_types.h> #include <linux/mm_types_task.h> #include <linux/task_io_accounting.h> +#include <linux/rseq.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -117,7 +119,7 @@ struct task_group; * the comment with set_special_state(). */ #define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD)) + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) #define __set_current_state(state_value) \ do { \ @@ -166,15 +168,15 @@ struct task_group; * need_sleep = false; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * - * Where wake_up_state() (and all other wakeup primitives) imply enough - * barriers to order the store of the variable against wakeup. + * where wake_up_state() executes a full memory barrier before accessing the + * task state. * * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can - * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not + * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * @@ -513,7 +515,7 @@ struct sched_dl_entity { /* * Actual scheduling parameters. Initialized with the values above, - * they are continously updated during task execution. Note that + * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ @@ -570,10 +572,8 @@ union rcu_special { struct { u8 blocked; u8 need_qs; - u8 exp_need_qs; - - /* Otherwise the compiler can store garbage here: */ - u8 pad; + u8 exp_hint; /* Hint for performance. */ + u8 pad; /* No garbage from compiler! */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; @@ -709,6 +709,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -721,10 +725,7 @@ struct task_struct { unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG - unsigned memcg_may_oom:1; -#ifndef CONFIG_SLOB - unsigned memcg_kmem_skip_account:1; -#endif + unsigned in_user_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; @@ -733,6 +734,16 @@ struct task_struct { /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; #endif +#ifdef CONFIG_BLK_CGROUP + /* to be used once the psi infrastructure lands upstream. */ + unsigned use_memdelay:1; +#endif + + /* + * May usercopy functions fault on kernel addresses? + * This is not just a single bit because this can potentially nest. + */ + unsigned int kernel_uaccess_faults_ok; unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -741,7 +752,7 @@ struct task_struct { pid_t pid; pid_t tgid; -#ifdef CONFIG_CC_STACKPROTECTOR +#ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif @@ -774,7 +785,8 @@ struct task_struct { struct list_head ptrace_entry; /* PID/PID hash table linkage. */ - struct pid_link pids[PIDTYPE_MAX]; + struct pid *thread_pid; + struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_group; struct list_head thread_node; @@ -848,6 +860,7 @@ struct task_struct { #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; + unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; @@ -953,9 +966,13 @@ struct task_struct { /* Ptrace state: */ unsigned long ptrace_message; - siginfo_t *last_siginfo; + kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -978,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_INTEL_RDT +#ifdef CONFIG_RESCTRL u32 closid; u32 rmid; #endif @@ -1016,7 +1033,6 @@ struct task_struct { u64 last_sum_exec_runtime; struct callback_head numa_work; - struct list_head numa_entry; struct numa_group *numa_group; /* @@ -1047,6 +1063,17 @@ struct task_struct { unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_RSEQ + struct rseq __user *rseq; + u32 rseq_len; + u32 rseq_sig; + /* + * RmW on rseq_event_mask must be performed atomically + * with respect to preemption. + */ + unsigned long rseq_event_mask; +#endif + struct tlbflush_unmap_batch tlb_ubc; struct rcu_head rcu; @@ -1091,6 +1118,7 @@ struct task_struct { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; + int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; @@ -1118,7 +1146,7 @@ struct task_struct { #ifdef CONFIG_KCOV /* Coverage collection mode enabled for this task (0 if disabled): */ - enum kcov_mode kcov_mode; + unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; @@ -1137,6 +1165,13 @@ struct task_struct { /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; + + /* Used by memcontrol for targeted memcg charge: */ + struct mem_cgroup *active_memcg; +#endif + +#ifdef CONFIG_BLK_CGROUP + struct request_queue *throttle_queue; #endif #ifdef CONFIG_UPROBES @@ -1168,6 +1203,11 @@ struct task_struct { void *security; #endif +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + unsigned long lowest_stack; + unsigned long prev_lowest_stack; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. @@ -1187,27 +1227,7 @@ struct task_struct { static inline struct pid *task_pid(struct task_struct *task) { - return task->pids[PIDTYPE_PID].pid; -} - -static inline struct pid *task_tgid(struct task_struct *task) -{ - return task->group_leader->pids[PIDTYPE_PID].pid; -} - -/* - * Without tasklist or RCU lock it is not safe to dereference - * the result of task_pgrp/task_session even if task == current, - * we can race with another thread doing sys_setsid/sys_setpgid. - */ -static inline struct pid *task_pgrp(struct task_struct *task) -{ - return task->group_leader->pids[PIDTYPE_PGID].pid; -} - -static inline struct pid *task_session(struct task_struct *task) -{ - return task->group_leader->pids[PIDTYPE_SID].pid; + return task->thread_pid; } /* @@ -1256,7 +1276,7 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) */ static inline int pid_alive(const struct task_struct *p) { - return p->pids[PIDTYPE_PID].pid != NULL; + return p->thread_pid != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) @@ -1282,12 +1302,12 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { - return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns); + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); } static inline pid_t task_tgid_vnr(struct task_struct *tsk) { - return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL); + return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); } static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) @@ -1385,6 +1405,7 @@ extern struct pid *cad_pid; #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_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ @@ -1435,6 +1456,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1466,6 +1489,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { @@ -1512,6 +1542,7 @@ static inline int task_nice(const struct task_struct *p) extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); +extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern int sched_setattr(struct task_struct *, const struct sched_attr *); @@ -1626,6 +1657,12 @@ static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) clear_ti_thread_flag(task_thread_info(tsk), flag); } +static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, + bool value) +{ + update_ti_thread_flag(task_thread_info(tsk), flag, value); +} + static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); @@ -1661,7 +1698,6 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, - * cond_resched_softirq() will enable bhs before scheduling. */ #ifndef CONFIG_PREEMPT extern int _cond_resched(void); @@ -1681,13 +1717,6 @@ extern int __cond_resched_lock(spinlock_t *lock); __cond_resched_lock(lock); \ }) -extern int __cond_resched_softirq(void); - -#define cond_resched_softirq() ({ \ - ___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \ - __cond_resched_softirq(); \ -}) - static inline void cond_resched_rcu(void) { #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) @@ -1764,4 +1793,127 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #define TASK_SIZE_OF(tsk) TASK_SIZE #endif +#ifdef CONFIG_RSEQ + +/* + * Map the event mask on the user-space ABI enum rseq_cs_flags + * for direct mask checks. + */ +enum rseq_event_mask_bits { + RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, + RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, + RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, +}; + +enum rseq_event_mask { + RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), + RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), + RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), +}; + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ + if (t->rseq) + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); +} + +void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); + +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) +{ + if (current->rseq) + __rseq_handle_notify_resume(ksig, regs); +} + +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) +{ + preempt_disable(); + __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); + preempt_enable(); + rseq_handle_notify_resume(ksig, regs); +} + +/* rseq_preempt() requires preemption to be disabled. */ +static inline void rseq_preempt(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* rseq_migrate() requires preemption to be disabled. */ +static inline void rseq_migrate(struct task_struct *t) +{ + __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); + rseq_set_notify_resume(t); +} + +/* + * If parent process has a registered restartable sequences area, the + * child inherits. Only applies when forking a process, not a thread. + */ +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ + if (clone_flags & CLONE_THREAD) { + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; + } else { + t->rseq = current->rseq; + t->rseq_len = current->rseq_len; + t->rseq_sig = current->rseq_sig; + t->rseq_event_mask = current->rseq_event_mask; + } +} + +static inline void rseq_execve(struct task_struct *t) +{ + t->rseq = NULL; + t->rseq_len = 0; + t->rseq_sig = 0; + t->rseq_event_mask = 0; +} + +#else + +static inline void rseq_set_notify_resume(struct task_struct *t) +{ +} +static inline void rseq_handle_notify_resume(struct ksignal *ksig, + struct pt_regs *regs) +{ +} +static inline void rseq_signal_deliver(struct ksignal *ksig, + struct pt_regs *regs) +{ +} +static inline void rseq_preempt(struct task_struct *t) +{ +} +static inline void rseq_migrate(struct task_struct *t) +{ +} +static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) +{ +} +static inline void rseq_execve(struct task_struct *t) +{ +} + +#endif + +#ifdef CONFIG_DEBUG_RSEQ + +void rseq_syscall(struct pt_regs *regs); + +#else + +static inline void rseq_syscall(struct pt_regs *regs) +{ +} + +#endif + #endif |