sched.h

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H

#include <uapi/linux/sched.h>

#include <linux/sched/prio.h>

#include <linux/capability.h>
#include <linux/mutex.h>
#include <linux/plist.h>
#include <linux/mm_types_task.h>
#include <asm/ptrace.h>

#include <linux/sem.h>
#include <linux/shm.h>
#include <linux/signal.h>
#include <linux/signal_types.h>
#include <linux/pid.h>
#include <linux/seccomp.h>
#include <linux/rculist.h>
#include <linux/rtmutex.h>

#include <linux/resource.h>
#include <linux/hrtimer.h>
#include <linux/kcov.h>
#include <linux/task_io_accounting.h>
#include <linux/latencytop.h>
#include <linux/cred.h>
#include <linux/gfp.h>
#include <linux/topology.h>
#include <linux/magic.h>
#include <linux/cgroup-defs.h>

#include <asm/current.h>

/* task_struct member predeclarations: */
struct audit_context;
struct autogroup;
struct backing_dev_info;
struct bio_list;
struct blk_plug;
struct cfs_rq;
struct filename;
struct fs_struct;
struct futex_pi_state;
struct io_context;
struct mempolicy;
struct nameidata;
struct nsproxy;
struct perf_event_context;
struct pid_namespace;
struct pipe_inode_info;
struct rcu_node;
struct reclaim_state;
struct robust_list_head;
struct sched_attr;
struct sched_param;
struct seq_file;
struct sighand_struct;
struct signal_struct;
struct task_delay_info;
struct task_group;
struct task_struct;
struct uts_namespace;

/*
 * Task state bitmask. NOTE! These bits are also
 * encoded in fs/proc/array.c: get_task_state().
 *
 * We have two separate sets of flags: task->state
 * is about runnability, while task->exit_state are
 * about the task exiting. Confusing, but this way
 * modifying one set can't modify the other one by
 * mistake.
 */
#define TASK_RUNNING		0
#define TASK_INTERRUPTIBLE	1
#define TASK_UNINTERRUPTIBLE	2
#define __TASK_STOPPED		4
#define __TASK_TRACED		8
/* in tsk->exit_state */
#define EXIT_DEAD		16
#define EXIT_ZOMBIE		32
#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
/* in tsk->state again */
#define TASK_DEAD		64
#define TASK_WAKEKILL		128
#define TASK_WAKING		256
#define TASK_PARKED		512
#define TASK_NOLOAD		1024
#define TASK_NEW		2048
#define TASK_STATE_MAX		4096

#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn"

/* 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_IDLE		(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)

/* Convenience macros for the sake of wake_up */
#define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)

/* get_task_state() */
#define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
				 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)

#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
#define task_is_stopped_or_traced(task)	\
			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
#define task_contributes_to_load(task)	\
				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
				 (task->flags & PF_FROZEN) == 0 && \
				 (task->state & TASK_NOLOAD) == 0)

#ifdef CONFIG_DEBUG_ATOMIC_SLEEP

#define __set_current_state(state_value)			\
	do {							\
		current->task_state_change = _THIS_IP_;		\
		current->state = (state_value);			\
	} while (0)
#define set_current_state(state_value)				\
	do {							\
		current->task_state_change = _THIS_IP_;		\
		smp_store_mb(current->state, (state_value));	\
	} while (0)

#else
/*
 * 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
 * actually sleep:
 *
 *   for (;;) {
 *	set_current_state(TASK_UNINTERRUPTIBLE);
 *	if (!need_sleep)
 *		break;
 *
 *	schedule();
 *   }
 *   __set_current_state(TASK_RUNNING);
 *
 * If the caller does not need such serialisation (because, for instance, the
 * condition test and condition change and wakeup are under the same lock) then
 * use __set_current_state().
 *
 * The above is typically ordered against the wakeup, which does:
 *
 *	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.
 *
 * 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).
 *
 * This is obviously fine, since they both store the exact same value.
 *
 * Also see the comments of try_to_wake_up().
 */
#define __set_current_state(state_value)		\
	do { current->state = (state_value); } while (0)
#define set_current_state(state_value)			\
	smp_store_mb(current->state, (state_value))

#endif

/* Task command name length */
#define TASK_COMM_LEN 16

extern void sched_init(void);
extern void sched_init_smp(void);

extern cpumask_var_t cpu_isolated_map;

extern int runqueue_is_locked(int cpu);

extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void scheduler_tick(void);

#define	MAX_SCHEDULE_TIMEOUT	LONG_MAX
extern signed long schedule_timeout(signed long timeout);
extern signed long schedule_timeout_interruptible(signed long timeout);
extern signed long schedule_timeout_killable(signed long timeout);
extern signed long schedule_timeout_uninterruptible(signed long timeout);
extern signed long schedule_timeout_idle(signed long timeout);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);

extern int __must_check io_schedule_prepare(void);
extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
extern void io_schedule(void);

/**
 * struct prev_cputime - snaphsot of system and user cputime
 * @utime: time spent in user mode
 * @stime: time spent in system mode
 * @lock: protects the above two fields
 *
 * Stores previous user/system time values such that we can guarantee
 * monotonicity.
 */
struct prev_cputime {
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
	u64 utime;
	u64 stime;
	raw_spinlock_t lock;
#endif
};

/**
 * struct task_cputime - collected CPU time counts
 * @utime:		time spent in user mode, in nanoseconds
 * @stime:		time spent in kernel mode, in nanoseconds
 * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
 *
 * This structure groups together three kinds of CPU time that are tracked for
 * threads and thread groups.  Most things considering CPU time want to group
 * these counts together and treat all three of them in parallel.
 */
struct task_cputime {
	u64 utime;
	u64 stime;
	unsigned long long sum_exec_runtime;
};

/* Alternate field names when used to cache expirations. */
#define virt_exp	utime
#define prof_exp	stime
#define sched_exp	sum_exec_runtime

#include <linux/rwsem.h>

#ifdef CONFIG_SCHED_INFO
struct sched_info {
	/* cumulative counters */
	unsigned long pcount;	      /* # of times run on this cpu */
	unsigned long long run_delay; /* time spent waiting on a runqueue */

	/* timestamps */
	unsigned long long last_arrival,/* when we last ran on a cpu */
			   last_queued;	/* when we were last queued to run */
};
#endif /* CONFIG_SCHED_INFO */

/*
 * Integer metrics need fixed point arithmetic, e.g., sched/fair
 * has a few: load, load_avg, util_avg, freq, and capacity.
 *
 * We define a basic fixed point arithmetic range, and then formalize
 * all these metrics based on that basic range.
 */
# define SCHED_FIXEDPOINT_SHIFT	10
# define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)

#ifdef ARCH_HAS_PREFETCH_SWITCH_STACK
extern void prefetch_stack(struct task_struct *t);
#else
static inline void prefetch_stack(struct task_struct *t) { }
#endif

struct load_weight {
	unsigned long weight;
	u32 inv_weight;
};

/*
 * The load_avg/util_avg accumulates an infinite geometric series
 * (see __update_load_avg() in kernel/sched/fair.c).
 *
 * [load_avg definition]
 *
 *   load_avg = runnable% * scale_load_down(load)
 *
 * where runnable% is the time ratio that a sched_entity is runnable.
 * For cfs_rq, it is the aggregated load_avg of all runnable and
 * blocked sched_entities.
 *
 * load_avg may also take frequency scaling into account:
 *
 *   load_avg = runnable% * scale_load_down(load) * freq%
 *
 * where freq% is the CPU frequency normalized to the highest frequency.
 *
 * [util_avg definition]
 *
 *   util_avg = running% * SCHED_CAPACITY_SCALE
 *
 * where running% is the time ratio that a sched_entity is running on
 * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
 * and blocked sched_entities.
 *
 * util_avg may also factor frequency scaling and CPU capacity scaling:
 *
 *   util_avg = running% * SCHED_CAPACITY_SCALE * freq% * capacity%
 *
 * where freq% is the same as above, and capacity% is the CPU capacity
 * normalized to the greatest capacity (due to uarch differences, etc).
 *
 * N.B., the above ratios (runnable%, running%, freq%, and capacity%)
 * themselves are in the range of [0, 1]. To do fixed point arithmetics,
 * we therefore scale them to as large a range as necessary. This is for
 * example reflected by util_avg's SCHED_CAPACITY_SCALE.
 *
 * [Overflow issue]
 *
 * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities
 * with the highest load (=88761), always runnable on a single cfs_rq,
 * and should not overflow as the number already hits PID_MAX_LIMIT.
 *
 * For all other cases (including 32-bit kernels), struct load_weight's
 * weight will overflow first before we do, because:
 *
 *    Max(load_avg) <= Max(load.weight)
 *
 * Then it is the load_weight's responsibility to consider overflow
 * issues.
 */
struct sched_avg {
	u64 last_update_time, load_sum;
	u32 util_sum, period_contrib;
	unsigned long load_avg, util_avg;
};

#ifdef CONFIG_SCHEDSTATS
struct sched_statistics {
	u64			wait_start;
	u64			wait_max;
	u64			wait_count;
	u64			wait_sum;
	u64			iowait_count;
	u64			iowait_sum;

	u64			sleep_start;
	u64			sleep_max;
	s64			sum_sleep_runtime;

	u64			block_start;
	u64			block_max;
	u64			exec_max;
	u64			slice_max;

	u64			nr_migrations_cold;
	u64			nr_failed_migrations_affine;
	u64			nr_failed_migrations_running;
	u64			nr_failed_migrations_hot;
	u64			nr_forced_migrations;

	u64			nr_wakeups;
	u64			nr_wakeups_sync;
	u64			nr_wakeups_migrate;
	u64			nr_wakeups_local;
	u64			nr_wakeups_remote;
	u64			nr_wakeups_affine;
	u64			nr_wakeups_affine_attempts;
	u64			nr_wakeups_passive;
	u64			nr_wakeups_idle;
};
#endif

struct sched_entity {
	struct load_weight	load;		/* for load-balancing */
	struct rb_node		run_node;
	struct list_head	group_node;
	unsigned int		on_rq;

	u64			exec_start;
	u64			sum_exec_runtime;
	u64			vruntime;
	u64			prev_sum_exec_runtime;

	u64			nr_migrations;

#ifdef CONFIG_SCHEDSTATS
	struct sched_statistics statistics;
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
	int			depth;
	struct sched_entity	*parent;
	/* rq on which this entity is (to be) queued: */
	struct cfs_rq		*cfs_rq;
	/* rq "owned" by this entity/group: */
	struct cfs_rq		*my_q;
#endif

#ifdef CONFIG_SMP
	/*
	 * Per entity load average tracking.
	 *
	 * Put into separate cache line so it does not
	 * collide with read-mostly values above.
	 */
	struct sched_avg	avg ____cacheline_aligned_in_smp;
#endif
};

struct sched_rt_entity {
	struct list_head run_list;
	unsigned long timeout;
	unsigned long watchdog_stamp;
	unsigned int time_slice;
	unsigned short on_rq;
	unsigned short on_list;

	struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
	struct sched_rt_entity	*parent;
	/* rq on which this entity is (to be) queued: */
	struct rt_rq		*rt_rq;
	/* rq "owned" by this entity/group: */
	struct rt_rq		*my_q;
#endif
};

struct sched_dl_entity {
	struct rb_node	rb_node;

	/*
	 * Original scheduling parameters. Copied here from sched_attr
	 * during sched_setattr(), they will remain the same until
	 * the next sched_setattr().
	 */
	u64 dl_runtime;		/* maximum runtime for each instance	*/
	u64 dl_deadline;	/* relative deadline of each instance	*/
	u64 dl_period;		/* separation of two instances (period) */
	u64 dl_bw;		/* dl_runtime / dl_deadline		*/

	/*
	 * Actual scheduling parameters. Initialized with the values above,
	 * they are continously 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	*/
	u64 deadline;		/* absolute deadline for this instance	*/
	unsigned int flags;	/* specifying the scheduler behaviour	*/

	/*
	 * Some bool flags:
	 *
	 * @dl_throttled tells if we exhausted the runtime. If so, the
	 * 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.
	 */
	int dl_throttled, dl_boosted, dl_yielded;

	/*
	 * Bandwidth enforcement timer. Each -deadline task has its
	 * own bandwidth to be enforced, thus we need one timer per task.
	 */
	struct hrtimer dl_timer;
};

union rcu_special {
	struct {
		u8 blocked;
		u8 need_qs;
		u8 exp_need_qs;
		u8 pad;	/* Otherwise the compiler can store garbage here. */
	} b; /* Bits. */
	u32 s; /* Set of bits. */
};

enum perf_event_task_context {
	perf_invalid_context = -1,
	perf_hw_context = 0,
	perf_sw_context,
	perf_nr_task_contexts,
};

struct wake_q_node {
	struct wake_q_node *next;
};

/* Track pages that require TLB flushes */
struct tlbflush_unmap_batch {
	/*
	 * Each bit set is a CPU that potentially has a TLB entry for one of
	 * the PFNs being flushed. See set_tlb_ubc_flush_pending().
	 */
	struct cpumask cpumask;

	/* True if any bit in cpumask is set */
	bool flush_required;

	/*
	 * If true then the PTE was dirty when unmapped. The entry must be
	 * flushed before IO is initiated or a stale TLB entry potentially
	 * allows an update without redirtying the page.
	 */
	bool writable;
};

struct task_struct {
#ifdef CONFIG_THREAD_INFO_IN_TASK
	/*
	 * For reasons of header soup (see current_thread_info()), this
	 * must be the first element of task_struct.
	 */
	struct thread_info thread_info;
#endif
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
	void *stack;
	atomic_t usage;
	unsigned int flags;	/* per process flags, defined below */
	unsigned int ptrace;

#ifdef CONFIG_SMP
	struct llist_node wake_entry;
	int on_cpu;
#ifdef CONFIG_THREAD_INFO_IN_TASK
	unsigned int cpu;	/* current CPU */
#endif
	unsigned int wakee_flips;
	unsigned long wakee_flip_decay_ts;
	struct task_struct *last_wakee;

	int wake_cpu;
#endif
	int on_rq;

	int prio, static_prio, normal_prio;
	unsigned int rt_priority;
	const struct sched_class *sched_class;
	struct sched_entity se;
	struct sched_rt_entity rt;
#ifdef CONFIG_CGROUP_SCHED
	struct task_group *sched_task_group;
#endif
	struct sched_dl_entity dl;

#ifdef CONFIG_PREEMPT_NOTIFIERS
	/* list of struct preempt_notifier: */
	struct hlist_head preempt_notifiers;
#endif

#ifdef CONFIG_BLK_DEV_IO_TRACE
	unsigned int btrace_seq;
#endif

	unsigned int policy;
	int nr_cpus_allowed;
	cpumask_t cpus_allowed;

#ifdef CONFIG_PREEMPT_RCU
	int rcu_read_lock_nesting;
	union rcu_special rcu_read_unlock_special;
	struct list_head rcu_node_entry;
	struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
	unsigned long rcu_tasks_nvcsw;
	bool rcu_tasks_holdout;
	struct list_head rcu_tasks_holdout_list;
	int rcu_tasks_idle_cpu;
#endif /* #ifdef CONFIG_TASKS_RCU */

#ifdef CONFIG_SCHED_INFO
	struct sched_info sched_info;
#endif

	struct list_head tasks;
#ifdef CONFIG_SMP
	struct plist_node pushable_tasks;
	struct rb_node pushable_dl_tasks;
#endif

	struct mm_struct *mm, *active_mm;

	/* Per-thread vma caching: */
	struct vmacache vmacache;

#if defined(SPLIT_RSS_COUNTING)
	struct task_rss_stat	rss_stat;
#endif
/* task state */
	int exit_state;
	int exit_code, exit_signal;
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	unsigned long jobctl;	/* JOBCTL_*, siglock protected */

	/* Used for emulating ABI behavior of previous Linux versions */
	unsigned int personality;

	/* scheduler bits, serialized by scheduler locks */
	unsigned sched_reset_on_fork:1;
	unsigned sched_contributes_to_load:1;
	unsigned sched_migrated:1;
	unsigned sched_remote_wakeup:1;
	unsigned :0; /* force alignment to the next boundary */

	/* unserialized, strictly 'current' */
	unsigned in_execve:1; /* bit to tell LSMs we're in execve */
	unsigned in_iowait:1;
#if !defined(TIF_RESTORE_SIGMASK)
	unsigned restore_sigmask:1;
#endif
#ifdef CONFIG_MEMCG
	unsigned memcg_may_oom:1;
#ifndef CONFIG_SLOB
	unsigned memcg_kmem_skip_account:1;
#endif
#endif
#ifdef CONFIG_COMPAT_BRK
	unsigned brk_randomized:1;
#endif

	unsigned long atomic_flags; /* Flags needing atomic access. */

	struct restart_block restart_block;

	pid_t pid;
	pid_t tgid;

#ifdef CONFIG_CC_STACKPROTECTOR
	/* Canary value for the -fstack-protector gcc feature */
	unsigned long stack_canary;
#endif
	/*
	 * pointers to (original) parent process, youngest child, younger sibling,
	 * older sibling, respectively.  (p->father can be replaced with
	 * p->real_parent->pid)
	 */
	struct task_struct __rcu *real_parent; /* real parent process */
	struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
	/*
	 * children/sibling forms the list of my natural children
	 */
	struct list_head children;	/* list of my children */
	struct list_head sibling;	/* linkage in my parent's children list */
	struct task_struct *group_leader;	/* threadgroup leader */

	/*
	 * ptraced is the list of tasks this task is using ptrace on.
	 * This includes both natural children and PTRACE_ATTACH targets.
	 * p->ptrace_entry is p's link on the p->parent->ptraced list.
	 */
	struct list_head ptraced;
	struct list_head ptrace_entry;

	/* PID/PID hash table linkage. */
	struct pid_link pids[PIDTYPE_MAX];
	struct list_head thread_group;
	struct list_head thread_node;

	struct completion *vfork_done;		/* for vfork() */
	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */

	u64 utime, stime;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
	u64 utimescaled, stimescaled;
#endif
	u64 gtime;
	struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
	seqcount_t vtime_seqcount;
	unsigned long long vtime_snap;
	enum {
		/* Task is sleeping or running in a CPU with VTIME inactive */
		VTIME_INACTIVE = 0,
		/* Task runs in userspace in a CPU with VTIME active */
		VTIME_USER,
		/* Task runs in kernelspace in a CPU with VTIME active */
		VTIME_SYS,
	} vtime_snap_whence;
#endif

#ifdef CONFIG_NO_HZ_FULL
	atomic_t tick_dep_mask;
#endif
	unsigned long nvcsw, nivcsw; /* context switch counts */
	u64 start_time;		/* monotonic time in nsec */
	u64 real_start_time;	/* boot based time in nsec */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt;

#ifdef CONFIG_POSIX_TIMERS
	struct task_cputime cputime_expires;
	struct list_head cpu_timers[3];
#endif

/* process credentials */
	const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */
	const struct cred __rcu *real_cred; /* objective and real subjective task
					 * credentials (COW) */
	const struct cred __rcu *cred;	/* effective (overridable) subjective task
					 * credentials (COW) */
	char comm[TASK_COMM_LEN]; /* executable name excluding path
				     - access with [gs]et_task_comm (which lock
				       it with task_lock())
				     - initialized normally by setup_new_exec */
/* file system info */
	struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
	struct sysv_sem sysvsem;
	struct sysv_shm sysvshm;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
	unsigned long last_switch_count;
#endif
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
/* namespaces */
	struct nsproxy *nsproxy;
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

	sigset_t blocked, real_blocked;
	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
	struct sigpending pending;

	unsigned long sas_ss_sp;
	size_t sas_ss_size;
	unsigned sas_ss_flags;

	struct callback_head *task_works;

	struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
	kuid_t loginuid;
	unsigned int sessionid;
#endif
	struct seccomp seccomp;

/* Thread group tracking */
   	u32 parent_exec_id;
   	u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
	spinlock_t alloc_lock;

	/* Protection of the PI data structures: */
	raw_spinlock_t pi_lock;

	struct wake_q_node wake_q;

#ifdef CONFIG_RT_MUTEXES
	/* PI waiters blocked on a rt_mutex held by this task */
	struct rb_root pi_waiters;
	struct rb_node *pi_waiters_leftmost;
	/* Deadlock detection and priority inheritance handling */
	struct rt_mutex_waiter *pi_blocked_on;
#endif

#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
	unsigned int irq_events;
	unsigned long hardirq_enable_ip;
	unsigned long hardirq_disable_ip;
	unsigned int hardirq_enable_event;
	unsigned int hardirq_disable_event;
	int hardirqs_enabled;
	int hardirq_context;
	unsigned long softirq_disable_ip;
	unsigned long softirq_enable_ip;
	unsigned int softirq_disable_event;
	unsigned int softirq_enable_event;
	int softirqs_enabled;
	int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
	u64 curr_chain_key;
	int lockdep_depth;
	unsigned int lockdep_recursion;
	struct held_lock held_locks[MAX_LOCK_DEPTH];
	gfp_t lockdep_reclaim_gfp;
#endif
#ifdef CONFIG_UBSAN
	unsigned int in_ubsan;
#endif

/* journalling filesystem info */
	void *journal_info;

/* 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;

	struct backing_dev_info *backing_dev_info;

	struct io_context *io_context;

	unsigned long ptrace_message;
	siginfo_t *last_siginfo; /* For ptrace use.  */
	struct task_io_accounting ioac;
#if defined(CONFIG_TASK_XACCT)
	u64 acct_rss_mem1;	/* accumulated rss usage */
	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
	u64 acct_timexpd;	/* stime + utime since last update */
#endif
#ifdef CONFIG_CPUSETS
	nodemask_t mems_allowed;	/* Protected by alloc_lock */
	seqcount_t mems_allowed_seq;	/* Seqence no to catch updates */
	int cpuset_mem_spread_rotor;
	int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
	/* Control Group info protected by css_set_lock */
	struct css_set __rcu *cgroups;
	/* cg_list protected by css_set_lock and tsk->alloc_lock */
	struct list_head cg_list;
#endif
#ifdef CONFIG_INTEL_RDT_A
	int closid;
#endif
#ifdef CONFIG_FUTEX
	struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
	struct compat_robust_list_head __user *compat_robust_list;
#endif
	struct list_head pi_state_list;
	struct futex_pi_state *pi_state_cache;
#endif
#ifdef CONFIG_PERF_EVENTS
	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
	struct mutex perf_event_mutex;
	struct list_head perf_event_list;
#endif
#ifdef CONFIG_DEBUG_PREEMPT
	unsigned long preempt_disable_ip;
#endif
#ifdef CONFIG_NUMA
	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
	short il_next;
	short pref_node_fork;
#endif
#ifdef CONFIG_NUMA_BALANCING
	int numa_scan_seq;
	unsigned int numa_scan_period;
	unsigned int numa_scan_period_max;
	int numa_preferred_nid;
	unsigned long numa_migrate_retry;
	u64 node_stamp;			/* migration stamp  */
	u64 last_task_numa_placement;
	u64 last_sum_exec_runtime;
	struct callback_head numa_work;

	struct list_head numa_entry;
	struct numa_group *numa_group;

	/*
	 * numa_faults is an array split into four regions:
	 * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
	 * in this precise order.
	 *
	 * faults_memory: Exponential decaying average of faults on a per-node
	 * basis. Scheduling placement decisions are made based on these
	 * counts. The values remain static for the duration of a PTE scan.
	 * faults_cpu: Track the nodes the process was running on when a NUMA
	 * hinting fault was incurred.
	 * faults_memory_buffer and faults_cpu_buffer: Record faults per node
	 * during the current scan window. When the scan completes, the counts
	 * in faults_memory and faults_cpu decay and these values are copied.
	 */
	unsigned long *numa_faults;
	unsigned long total_numa_faults;

	/*
	 * numa_faults_locality tracks if faults recorded during the last
	 * scan window were remote/local or failed to migrate. The task scan
	 * period is adapted based on the locality of the faults with different
	 * weights depending on whether they were shared or private faults
	 */
	unsigned long numa_faults_locality[3];

	unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
	struct tlbflush_unmap_batch tlb_ubc;
#endif

	struct rcu_head rcu;

	/*
	 * cache last used pipe for splice
	 */
	struct pipe_inode_info *splice_pipe;

	struct page_frag task_frag;

#ifdef CONFIG_TASK_DELAY_ACCT
	struct task_delay_info		*delays;
#endif

#ifdef CONFIG_FAULT_INJECTION
	int make_it_fail;
#endif
	/*
	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
	 * balance_dirty_pages() for some dirty throttling pause
	 */
	int nr_dirtied;
	int nr_dirtied_pause;
	unsigned long dirty_paused_when; /* start of a write-and-pause period */

#ifdef CONFIG_LATENCYTOP
	int latency_record_count;
	struct latency_record latency_record[LT_SAVECOUNT];
#endif
	/*
	 * time slack values; these are used to round up poll() and
	 * select() etc timeout values. These are in nanoseconds.
	 */
	u64 timer_slack_ns;
	u64 default_timer_slack_ns;

#ifdef CONFIG_KASAN
	unsigned int kasan_depth;
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
	/* Index of current stored address in ret_stack */
	int curr_ret_stack;
	/* Stack of return addresses for return function tracing */
	struct ftrace_ret_stack	*ret_stack;
	/* time stamp for last schedule */
	unsigned long long ftrace_timestamp;
	/*
	 * Number of functions that haven't been traced
	 * because of depth overrun.
	 */
	atomic_t trace_overrun;
	/* Pause for the tracing */
	atomic_t tracing_graph_pause;
#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 */
#ifdef CONFIG_KCOV
	/* Coverage collection mode enabled for this task (0 if disabled). */
	enum kcov_mode kcov_mode;
	/* Size of the kcov_area. */
	unsigned	kcov_size;
	/* Buffer for coverage collection. */
	void		*kcov_area;
	/* kcov desciptor wired with this task or NULL. */
	struct kcov	*kcov;
#endif
#ifdef CONFIG_MEMCG
	struct mem_cgroup *memcg_in_oom;
	gfp_t memcg_oom_gfp_mask;
	int memcg_oom_order;

	/* number of pages to reclaim on returning to userland */
	unsigned int memcg_nr_pages_over_high;
#endif
#ifdef CONFIG_UPROBES
	struct uprobe_task *utask;
#endif
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
	unsigned int	sequential_io;
	unsigned int	sequential_io_avg;
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
	unsigned long	task_state_change;
#endif
	int pagefault_disabled;
#ifdef CONFIG_MMU
	struct task_struct *oom_reaper_list;
#endif
#ifdef CONFIG_VMAP_STACK
	struct vm_struct *stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
	/* A live task holds one reference. */
	atomic_t stack_refcount;
#endif
/* CPU-specific state of this task */
	struct thread_struct thread;
/*
 * WARNING: on x86, 'thread_struct' contains a variable-sized
 * structure.  It *MUST* be at the end of 'task_struct'.
 *
 * Do not put anything below here!
 */
};

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;
}

/*
 * 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;
 *
 * set_task_vxid()   : assigns a virtual id to a task;
 *
 * 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_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);

static inline pid_t task_tgid_vnr(struct task_struct *tsk)
{
	return pid_vnr(task_tgid(tsk));
}


static inline int pid_alive(const struct task_struct *p);
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);
}

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);
}

/* obsolete, do not use */
static inline pid_t task_pgrp_nr(struct task_struct *tsk)
{
	return task_pgrp_nr_ns(tsk, &init_pid_ns);
}

/**
 * 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->pids[PIDTYPE_PID].pid != NULL;
}

/**
 * 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;

extern void free_task(struct task_struct *tsk);
#define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)

extern void __put_task_struct(struct task_struct *t);

static inline void put_task_struct(struct task_struct *t)
{
	if (atomic_dec_and_test(&t->usage))
		__put_task_struct(t);
}

struct task_struct *task_rcu_dereference(struct task_struct **ptask);
struct task_struct *try_get_task_struct(struct task_struct **ptask);

/*
 * Per process flags
 */
#define PF_IDLE		0x00000002	/* I am an IDLE thread */
#define PF_EXITING	0x00000004	/* getting shut down */
#define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
#define PF_VCPU		0x00000010	/* I'm a virtual CPU */
#define PF_WQ_WORKER	0x00000020	/* I'm a workqueue worker */
#define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
#define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
#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_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_NOFREEZE	0x00008000	/* this thread should not be frozen */
#define PF_FROZEN	0x00010000	/* frozen for system suspend */
#define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
#define PF_KSWAPD	0x00040000	/* I am kswapd */
#define PF_MEMALLOC_NOIO 0x00080000	/* Allocating memory without IO involved */
#define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
#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_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 */
#define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK 0x80000000      /* this thread called freeze_processes and should not be frozen */

/*
 * Only the _current_ task can read/write to tsk->flags, but other
 * tasks can access tsk->flags in readonly mode for example
 * with tsk_used_math (like during threaded core dumping).
 * There is however an exception to this rule during ptrace
 * or during fork: the ptracer task is allowed to write to the
 * child->flags of its traced child (same goes for fork, the parent
 * can write to the child->flags), because we're guaranteed the
 * child is not running and in turn not changing child->flags
 * at the same time the parent does it.
 */
#define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0)
#define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0)
#define clear_used_math() clear_stopped_child_used_math(current)
#define set_used_math() set_stopped_child_used_math(current)
#define conditional_stopped_child_used_math(condition, child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0)
#define conditional_used_math(condition) \
	conditional_stopped_child_used_math(condition, current)
#define copy_to_stopped_child_used_math(child) \
	do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0)
/* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)

/* Per-process atomic flags. */
#define PFA_NO_NEW_PRIVS 0	/* May not gain new privileges. */
#define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */
#define PFA_SPREAD_SLAB  2      /* Spread some slab caches over cpuset */
#define PFA_LMK_WAITING  3      /* Lowmemorykiller is waiting */


#define TASK_PFA_TEST(name, func)					\
	static inline bool task_##func(struct task_struct *p)		\
	{ return test_bit(PFA_##name, &p->atomic_flags); }
#define TASK_PFA_SET(name, func)					\
	static inline void task_set_##func(struct task_struct *p)	\
	{ set_bit(PFA_##name, &p->atomic_flags); }
#define TASK_PFA_CLEAR(name, func)					\
	static inline void task_clear_##func(struct task_struct *p)	\
	{ clear_bit(PFA_##name, &p->atomic_flags); }

TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs)
TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs)

TASK_PFA_TEST(SPREAD_PAGE, spread_page)
TASK_PFA_SET(SPREAD_PAGE, spread_page)
TASK_PFA_CLEAR(SPREAD_PAGE, spread_page)

TASK_PFA_TEST(SPREAD_SLAB, spread_slab)
TASK_PFA_SET(SPREAD_SLAB, spread_slab)
TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab)

TASK_PFA_TEST(LMK_WAITING, lmk_waiting)
TASK_PFA_SET(LMK_WAITING, lmk_waiting)

static inline void tsk_restore_flags(struct task_struct *task,
				unsigned long orig_flags, unsigned long flags)
{
	task->flags &= ~flags;
	task->flags |= orig_flags & 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);
#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);
#else
static inline void do_set_cpus_allowed(struct task_struct *p,
				      const struct cpumask *new_mask)
{
}
static inline int set_cpus_allowed_ptr(struct task_struct *p,
				       const struct cpumask *new_mask)
{
	if (!cpumask_test_cpu(0, new_mask))
		return -EINVAL;
	return 0;
}
#endif

#ifndef cpu_relax_yield
#define cpu_relax_yield() cpu_relax()
#endif

/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_exec(void);
#else
#define sched_exec()   {}
#endif

extern int yield_to(struct task_struct *p, bool preempt);
extern void set_user_nice(struct task_struct *p, long nice);
extern int task_prio(const struct task_struct *p);
/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 *
 * Return: The nice value [ -20 ... 0 ... 19 ].
 */
static inline int task_nice(const struct task_struct *p)
{
	return PRIO_TO_NICE((p)->static_prio);
}
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 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 *);
extern struct task_struct *idle_task(int cpu);
/**
 * is_idle_task - is the specified task an idle task?
 * @p: the task in question.
 *
 * Return: 1 if @p is an idle task. 0 otherwise.
 */
static inline bool is_idle_task(const struct task_struct *p)
{
	return !!(p->flags & PF_IDLE);
}
extern struct task_struct *curr_task(int cpu);
extern void ia64_set_curr_task(int cpu, struct task_struct *p);

void yield(void);

union thread_union {
#ifndef CONFIG_THREAD_INFO_IN_TASK
	struct thread_info thread_info;
#endif
	unsigned long stack[THREAD_SIZE/sizeof(long)];
};

#ifdef CONFIG_THREAD_INFO_IN_TASK
static inline struct thread_info *task_thread_info(struct task_struct *task)
{
	return &task->thread_info;
}
#elif !defined(__HAVE_THREAD_FUNCTIONS)
# define task_thread_info(task)	((struct thread_info *)(task)->stack)
#endif

#ifndef __HAVE_ARCH_KSTACK_END
static inline int kstack_end(void *addr)
{
	/* Reliable end of stack detection:
	 * Some APM bios versions misalign the stack
	 */
	return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*)));
}
#endif

extern struct pid_namespace init_pid_ns;

/*
 * find a task by one of its numerical ids
 *
 * find_task_by_pid_ns():
 *      finds a task by its pid in the specified namespace
 * find_task_by_vpid():
 *      finds a task by its virtual pid
 *
 * see also find_vpid() etc in include/linux/pid.h
 */

extern struct task_struct *find_task_by_vpid(pid_t nr);
extern struct task_struct *find_task_by_pid_ns(pid_t nr,
		struct pid_namespace *ns);

extern int wake_up_state(struct task_struct *tsk, unsigned int state);
extern int wake_up_process(struct task_struct *tsk);
extern void wake_up_new_task(struct task_struct *tsk);
#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
#else
 static inline void kick_process(struct task_struct *tsk) { }
#endif

extern void exit_files(struct task_struct *);

extern void exit_itimers(struct signal_struct *);

extern int do_execve(struct filename *,
		     const char __user * const __user *,
		     const char __user * const __user *);
extern int do_execveat(int, struct filename *,
		       const char __user * const __user *,
		       const char __user * const __user *,
		       int);

extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
static inline void set_task_comm(struct task_struct *tsk, const char *from)
{
	__set_task_comm(tsk, from, false);
}
extern char *get_task_comm(char *to, struct task_struct *tsk);

#ifdef CONFIG_SMP
void scheduler_ipi(void);
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
#else
static inline void scheduler_ipi(void) { }
static inline unsigned long wait_task_inactive(struct task_struct *p,
					       long match_state)
{
	return 1;
}
#endif

/* set thread flags in other task's structures
 * - see asm/thread_info.h for TIF_xxxx flags available
 */
static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	set_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	clear_ti_thread_flag(task_thread_info(tsk), flag);
}

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);
}

static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
{
	return test_ti_thread_flag(task_thread_info(tsk), flag);
}

static inline void set_tsk_need_resched(struct task_struct *tsk)
{
	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}

static inline void clear_tsk_need_resched(struct task_struct *tsk)
{
	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}

static inline int test_tsk_need_resched(struct task_struct *tsk)
{
	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
}

/*
 * cond_resched() and cond_resched_lock(): latency reduction via
 * 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);
#else
static inline int _cond_resched(void) { return 0; }
#endif

#define cond_resched() ({			\
	___might_sleep(__FILE__, __LINE__, 0);	\
	_cond_resched();			\
})

extern int __cond_resched_lock(spinlock_t *lock);

#define cond_resched_lock(lock) ({				\
	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
	__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)
	rcu_read_unlock();
	cond_resched();
	rcu_read_lock();
#endif
}

/*
 * Does a critical section need to be broken due to another
 * task waiting?: (technically does not depend on CONFIG_PREEMPT,
 * but a general need for low latency)
 */
static inline int spin_needbreak(spinlock_t *lock)
{
#ifdef CONFIG_PREEMPT
	return spin_is_contended(lock);
#else
	return 0;
#endif
}

static __always_inline bool need_resched(void)
{
	return unlikely(tif_need_resched());
}

/*
 * Wrappers for p->thread_info->cpu access. No-op on UP.
 */
#ifdef CONFIG_SMP

static inline unsigned int task_cpu(const struct task_struct *p)
{
#ifdef CONFIG_THREAD_INFO_IN_TASK
	return p->cpu;
#else
	return task_thread_info(p)->cpu;
#endif
}

static inline int task_node(const struct task_struct *p)
{
	return cpu_to_node(task_cpu(p));
}

extern void set_task_cpu(struct task_struct *p, unsigned int cpu);

#else

static inline unsigned int task_cpu(const struct task_struct *p)
{
	return 0;
}

static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
{
}

#endif /* CONFIG_SMP */

/*
 * In order to reduce various lock holder preemption latencies provide an
 * interface to see if a vCPU is currently running or not.
 *
 * This allows us to terminate optimistic spin loops and block, analogous to
 * the native optimistic spin heuristic of testing if the lock owner task is
 * running or not.
 */
#ifndef vcpu_is_preempted
# define vcpu_is_preempted(cpu)	false
#endif

extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);

extern int task_can_switch_user(struct user_struct *up,
					struct task_struct *tsk);

#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk)	TASK_SIZE
#endif

#endif