diff options
Diffstat (limited to 'include/linux/sched.h')
| -rw-r--r-- | include/linux/sched.h | 571 |
1 files changed, 165 insertions, 406 deletions
diff --git a/include/linux/sched.h b/include/linux/sched.h index d4f9d82c69e0..0d1d70aded38 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -10,33 +10,42 @@ #include <uapi/linux/sched.h> #include <asm/current.h> - -#include <linux/pid.h> -#include <linux/sem.h> +#include <asm/processor.h> +#include <linux/thread_info.h> +#include <linux/preempt.h> +#include <linux/cpumask_types.h> + +#include <linux/cache.h> +#include <linux/irqflags_types.h> +#include <linux/smp_types.h> +#include <linux/pid_types.h> +#include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> -#include <linux/mutex.h> -#include <linux/plist.h> -#include <linux/hrtimer.h> -#include <linux/irqflags.h> -#include <linux/seccomp.h> -#include <linux/nodemask.h> -#include <linux/rcupdate.h> -#include <linux/refcount.h> +#include <linux/mutex_types.h> +#include <linux/plist_types.h> +#include <linux/hrtimer_types.h> +#include <linux/timer_types.h> +#include <linux/seccomp_types.h> +#include <linux/nodemask_types.h> +#include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> -#include <linux/syscall_user_dispatch.h> +#include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> +#include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> -#include <linux/posix-timers.h> -#include <linux/rseq.h> -#include <linux/seqlock.h> +#include <linux/posix-timers_types.h> +#include <linux/restart_block.h> +#include <uapi/linux/rseq.h> +#include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> +#include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ @@ -45,6 +54,7 @@ struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; +struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; @@ -63,13 +73,17 @@ struct robust_list_head; struct root_domain; struct rq; struct sched_attr; +struct sched_dl_entity; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; +struct task_struct; struct user_event_mm; +#include <linux/sched/ext.h> + /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). @@ -137,8 +151,9 @@ struct user_event_mm; * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ -#define is_special_task_state(state) \ - ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) +#define is_special_task_state(state) \ + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ + TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ @@ -291,7 +306,7 @@ enum { TASK_COMM_LEN = 16, }; -extern void scheduler_tick(void); +extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX @@ -413,42 +428,6 @@ struct load_weight { u32 inv_weight; }; -/** - * struct util_est - Estimation utilization of FAIR tasks - * @enqueued: instantaneous estimated utilization of a task/cpu - * @ewma: the Exponential Weighted Moving Average (EWMA) - * utilization of a task - * - * Support data structure to track an Exponential Weighted Moving Average - * (EWMA) of a FAIR task's utilization. New samples are added to the moving - * average each time a task completes an activation. Sample's weight is chosen - * so that the EWMA will be relatively insensitive to transient changes to the - * task's workload. - * - * The enqueued attribute has a slightly different meaning for tasks and cpus: - * - task: the task's util_avg at last task dequeue time - * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU - * Thus, the util_est.enqueued of a task represents the contribution on the - * estimated utilization of the CPU where that task is currently enqueued. - * - * 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)))); - /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). @@ -503,9 +482,20 @@ struct sched_avg { unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; - struct util_est util_est; + unsigned int util_est; } ____cacheline_aligned; +/* + * 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 at dequeue time. + * Since max value of util_est for a task is 1024 (PELT util_avg for a task) + * it is safe to use MSB. + */ +#define UTIL_EST_WEIGHT_SHIFT 2 +#define UTIL_AVG_UNCHANGED 0x80000000 + struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; @@ -553,10 +543,15 @@ struct sched_entity { struct load_weight load; struct rb_node run_node; u64 deadline; - u64 min_deadline; + u64 min_vruntime; + u64 min_slice; struct list_head group_node; - unsigned int on_rq; + unsigned char on_rq; + unsigned char sched_delayed; + unsigned char rel_deadline; + unsigned char custom_slice; + /* hole */ u64 exec_start; u64 sum_exec_runtime; @@ -607,6 +602,9 @@ struct sched_rt_entity { #endif } __randomize_layout; +typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); +typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); + struct sched_dl_entity { struct rb_node rb_node; @@ -649,11 +647,33 @@ struct sched_dl_entity { * * @dl_overrun tells if the task asked to be informed about runtime * overruns. + * + * @dl_server tells if this is a server entity. + * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * + * @dl_server_active tells if the dlserver is active(started). + * dlserver is started on first cfs enqueue on an idle runqueue + * and is stopped when a dequeue results in 0 cfs tasks on the + * runqueue. In other words, dlserver is active only when cpu's + * runqueue has atleast one cfs task. + * + * @dl_defer_running tells if the deferrable server is actually + * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; + unsigned int dl_server : 1; + unsigned int dl_server_active : 1; + unsigned int dl_defer : 1; + unsigned int dl_defer_armed : 1; + unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -668,7 +688,20 @@ struct sched_dl_entity { * timer is needed to decrease the active utilization at the correct * time. */ - struct hrtimer inactive_timer; + struct hrtimer inactive_timer; + + /* + * Bits for DL-server functionality. Also see the comment near + * dl_server_update(). + * + * @rq the runqueue this server is for + * + * @server_has_tasks() returns true if @server_pick return a + * runnable task. + */ + struct rq *rq; + dl_server_has_tasks_f server_has_tasks; + dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* @@ -732,6 +765,12 @@ enum perf_event_task_context { perf_nr_task_contexts, }; +/* + * Number of contexts where an event can trigger: + * task, softirq, hardirq, nmi. + */ +#define PERF_NR_CONTEXTS 4 + struct wake_q_node { struct wake_q_node *next; }; @@ -753,10 +792,8 @@ 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 @@ -770,6 +807,10 @@ struct task_struct { unsigned int flags; unsigned int ptrace; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif + #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; @@ -797,6 +838,10 @@ struct task_struct { struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; + struct sched_dl_entity *dl_server; +#ifdef CONFIG_SCHED_CLASS_EXT + struct sched_ext_entity scx; +#endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE @@ -809,6 +854,7 @@ struct task_struct { struct task_group *sched_task_group; #endif + #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. @@ -834,6 +880,7 @@ struct task_struct { #endif unsigned int policy; + unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; @@ -880,6 +927,7 @@ struct task_struct { struct mm_struct *mm; struct mm_struct *active_mm; + struct address_space *faults_disabled_mapping; int exit_state; int exit_code; @@ -896,6 +944,7 @@ struct task_struct { unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; @@ -916,14 +965,17 @@ struct task_struct { * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; +#ifdef CONFIG_RT_MUTEXES + unsigned sched_rt_mutex:1; +#endif - /* Bit to tell LSMs we're in execve(): */ + /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN @@ -954,7 +1006,7 @@ struct task_struct { /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_CPU_SUP_INTEL @@ -964,7 +1016,9 @@ struct task_struct { /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif - +#ifdef CONFIG_PREEMPT_RT + struct netdev_xmit net_xmit; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; @@ -1007,7 +1061,6 @@ struct task_struct { /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; - struct list_head thread_group; struct list_head thread_node; struct completion *vfork_done; @@ -1223,7 +1276,6 @@ struct task_struct { /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; - int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ @@ -1246,6 +1298,7 @@ struct task_struct { unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS + u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; @@ -1257,6 +1310,7 @@ struct task_struct { /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; + u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING @@ -1391,7 +1445,7 @@ struct task_struct { int curr_ret_depth; /* Stack of return addresses for return function tracing: */ - struct ftrace_ret_stack *ret_stack; + unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; @@ -1436,16 +1490,19 @@ struct task_struct { unsigned int kcov_softirq; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; - gfp_t memcg_oom_gfp_mask; - int memcg_oom_order; +#endif +#ifdef CONFIG_MEMCG /* 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; + + /* Cache for current->cgroups->memcg->objcg lookups: */ + struct obj_cgroup *objcg; #endif #ifdef CONFIG_BLK_CGROUP @@ -1493,6 +1550,8 @@ struct task_struct { /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif + /* Used by BPF for per-TASK xdp storage */ + struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; @@ -1558,114 +1617,6 @@ struct task_struct { */ }; -static inline struct pid *task_pid(struct task_struct *task) -{ - return task->thread_pid; -} - -/* - * the helpers to get the task's different pids as they are seen - * from various namespaces - * - * task_xid_nr() : global id, i.e. the id seen from the init namespace; - * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of - * current. - * task_xid_nr_ns() : id seen from the ns specified; - * - * see also pid_nr() etc in include/linux/pid.h - */ -pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); - -static inline pid_t task_pid_nr(struct task_struct *tsk) -{ - return tsk->pid; -} - -static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); -} - -static inline pid_t task_pid_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); -} - - -static inline pid_t task_tgid_nr(struct task_struct *tsk) -{ - return tsk->tgid; -} - -/** - * pid_alive - check that a task structure is not stale - * @p: Task structure to be checked. - * - * Test if a process is not yet dead (at most zombie state) - * If pid_alive fails, then pointers within the task structure - * can be stale and must not be dereferenced. - * - * Return: 1 if the process is alive. 0 otherwise. - */ -static inline int pid_alive(const struct task_struct *p) -{ - return p->thread_pid != NULL; -} - -static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); -} - -static inline pid_t task_pgrp_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); -} - - -static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); -} - -static inline pid_t task_session_vnr(struct task_struct *tsk) -{ - return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); -} - -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); -} - -static inline pid_t task_tgid_vnr(struct task_struct *tsk) -{ - 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) -{ - pid_t pid = 0; - - rcu_read_lock(); - if (pid_alive(tsk)) - pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); - rcu_read_unlock(); - - return pid; -} - -static inline pid_t task_ppid_nr(const struct task_struct *tsk) -{ - return task_ppid_nr_ns(tsk, &init_pid_ns); -} - -/* Obsolete, do not use: */ -static inline pid_t task_pgrp_nr(struct task_struct *tsk) -{ - return task_pgrp_nr_ns(tsk, &init_pid_ns); -} - #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) @@ -1700,7 +1651,7 @@ static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; - BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); + BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } @@ -1710,20 +1661,6 @@ static inline char task_state_to_char(struct task_struct *tsk) return task_index_to_char(task_state_index(tsk)); } -/** - * is_global_init - check if a task structure is init. Since init - * is free to have sub-threads we need to check tgid. - * @tsk: Task structure to be checked. - * - * Check if a task structure is the first user space task the kernel created. - * - * Return: 1 if the task structure is init. 0 otherwise. - */ -static inline int is_global_init(struct task_struct *tsk) -{ - return task_tgid_nr(tsk) == 1; -} - extern struct pid *cad_pid; /* @@ -1740,15 +1677,15 @@ extern struct pid *cad_pid; #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ -#define PF_MEMALLOC 0x00000800 /* Allocating memory */ +#define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #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_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF__HOLE__00010000 0x00010000 +#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #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 */ +#define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ +#define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ @@ -1758,8 +1695,9 @@ extern struct pid *cad_pid; #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__HOLE__20000000 0x20000000 +#define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. + * See memalloc_pin_save() */ +#define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ @@ -1887,7 +1825,8 @@ static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpuma } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { - if (!cpumask_test_cpu(0, new_mask)) + /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ + if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } @@ -1953,9 +1892,7 @@ extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { -#ifndef CONFIG_ARCH_TASK_STRUCT_ON_STACK struct task_struct task; -#endif #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif @@ -2175,87 +2112,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); __cond_resched_rwlock_write(lock); \ }) -static inline void cond_resched_rcu(void) -{ -#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) - rcu_read_unlock(); - cond_resched(); - rcu_read_lock(); -#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, - * but a general need for low latency) - */ -static inline int spin_needbreak(spinlock_t *lock) -{ -#ifdef CONFIG_PREEMPTION - return spin_is_contended(lock); -#else - return 0; -#endif -} - -/* - * Check if a rwlock is contended. - * Returns non-zero if there is another task waiting on the rwlock. - * Returns zero if the lock is not contended or the system / underlying - * rwlock implementation does not support contention detection. - * Technically does not depend on CONFIG_PREEMPTION, but a general need - * for low latency. - */ -static inline int rwlock_needbreak(rwlock_t *lock) -{ -#ifdef CONFIG_PREEMPTION - return rwlock_is_contended(lock); -#else - return 0; -#endif -} - static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); @@ -2286,10 +2142,17 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ +static inline bool task_is_runnable(struct task_struct *p) +{ + return p->on_rq && !p->se.sched_delayed; +} + 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); +#include <linux/spinlock.h> + /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. @@ -2326,129 +2189,6 @@ static inline bool owner_on_cpu(struct task_struct *owner) unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ -#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. Unregister rseq for a clone with CLONE_VM set. - */ -static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) -{ - if (clone_flags & CLONE_VM) { - 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 - #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); @@ -2463,4 +2203,23 @@ static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } extern void sched_set_stop_task(int cpu, struct task_struct *stop); +#ifdef CONFIG_MEM_ALLOC_PROFILING +static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) +{ + swap(current->alloc_tag, tag); + return tag; +} + +static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) +{ +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); +#endif + current->alloc_tag = old; +} +#else +#define alloc_tag_save(_tag) NULL +#define alloc_tag_restore(_tag, _old) do {} while (0) +#endif + #endif |