kernel-fxtec-pro1x/include/linux/sched.h
Linus Torvalds 654443e20d Merge branch 'perf-uprobes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull user-space probe instrumentation from Ingo Molnar:
 "The uprobes code originates from SystemTap and has been used for years
  in Fedora and RHEL kernels.  This version is much rewritten, reviews
  from PeterZ, Oleg and myself shaped the end result.

  This tree includes uprobes support in 'perf probe' - but SystemTap
  (and other tools) can take advantage of user probe points as well.

  Sample usage of uprobes via perf, for example to profile malloc()
  calls without modifying user-space binaries.

  First boot a new kernel with CONFIG_UPROBE_EVENT=y enabled.

  If you don't know which function you want to probe you can pick one
  from 'perf top' or can get a list all functions that can be probed
  within libc (binaries can be specified as well):

	$ perf probe -F -x /lib/libc.so.6

  To probe libc's malloc():

	$ perf probe -x /lib64/libc.so.6 malloc
	Added new event:
	probe_libc:malloc    (on 0x7eac0)

  You can now use it in all perf tools, such as:

	perf record -e probe_libc:malloc -aR sleep 1

  Make use of it to create a call graph (as the flat profile is going to
  look very boring):

	$ perf record -e probe_libc:malloc -gR make
	[ perf record: Woken up 173 times to write data ]
	[ perf record: Captured and wrote 44.190 MB perf.data (~1930712

	$ perf report | less

	  32.03%            git  libc-2.15.so   [.] malloc
	                    |
	                    --- malloc

	  29.49%            cc1  libc-2.15.so   [.] malloc
	                    |
	                    --- malloc
	                       |
	                       |--0.95%-- 0x208eb1000000000
	                       |
	                       |--0.63%-- htab_traverse_noresize

	  11.04%             as  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |

	   7.15%             ld  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |

	   5.07%             sh  libc-2.15.so   [.] malloc
	                     |
	                     --- malloc
	                        |
	   4.99%  python-config  libc-2.15.so   [.] malloc
	          |
	          --- malloc
	             |
	   4.54%           make  libc-2.15.so   [.] malloc
	                   |
	                   --- malloc
	                      |
	                      |--7.34%-- glob
	                      |          |
	                      |          |--93.18%-- 0x41588f
	                      |          |
	                      |           --6.82%-- glob
	                      |                     0x41588f

	   ...

  Or:

	$ perf report -g flat | less

	# Overhead        Command  Shared Object      Symbol
	# ........  .............  .............  ..........
	#
	  32.03%            git  libc-2.15.so   [.] malloc
	          27.19%
	              malloc

	  29.49%            cc1  libc-2.15.so   [.] malloc
	          24.77%
	              malloc

	  11.04%             as  libc-2.15.so   [.] malloc
	          11.02%
	              malloc

	   7.15%             ld  libc-2.15.so   [.] malloc
	           6.57%
	              malloc

	 ...

  The core uprobes design is fairly straightforward: uprobes probe
  points register themselves at (inode:offset) addresses of
  libraries/binaries, after which all existing (or new) vmas that map
  that address will have a software breakpoint injected at that address.
  vmas are COW-ed to preserve original content.  The probe points are
  kept in an rbtree.

  If user-space executes the probed inode:offset instruction address
  then an event is generated which can be recovered from the regular
  perf event channels and mmap-ed ring-buffer.

  Multiple probes at the same address are supported, they create a
  dynamic callback list of event consumers.

  The basic model is further complicated by the XOL speedup: the
  original instruction that is probed is copied (in an architecture
  specific fashion) and executed out of line when the probe triggers.
  The XOL area is a single vma per process, with a fixed number of
  entries (which limits probe execution parallelism).

  The API: uprobes are installed/removed via
  /sys/kernel/debug/tracing/uprobe_events, the API is integrated to
  align with the kprobes interface as much as possible, but is separate
  to it.

  Injecting a probe point is privileged operation, which can be relaxed
  by setting perf_paranoid to -1.

  You can use multiple probes as well and mix them with kprobes and
  regular PMU events or tracepoints, when instrumenting a task."

Fix up trivial conflicts in mm/memory.c due to previous cleanup of
unmap_single_vma().

* 'perf-uprobes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  perf probe: Detect probe target when m/x options are absent
  perf probe: Provide perf interface for uprobes
  tracing: Fix kconfig warning due to a typo
  tracing: Provide trace events interface for uprobes
  tracing: Extract out common code for kprobes/uprobes trace events
  tracing: Modify is_delete, is_return from int to bool
  uprobes/core: Decrement uprobe count before the pages are unmapped
  uprobes/core: Make background page replacement logic account for rss_stat counters
  uprobes/core: Optimize probe hits with the help of a counter
  uprobes/core: Allocate XOL slots for uprobes use
  uprobes/core: Handle breakpoint and singlestep exceptions
  uprobes/core: Rename bkpt to swbp
  uprobes/core: Make order of function parameters consistent across functions
  uprobes/core: Make macro names consistent
  uprobes: Update copyright notices
  uprobes/core: Move insn to arch specific structure
  uprobes/core: Remove uprobe_opcode_sz
  uprobes/core: Make instruction tables volatile
  uprobes: Move to kernel/events/
  uprobes/core: Clean up, refactor and improve the code
  ...
2012-05-24 11:39:34 -07:00

2791 lines
82 KiB
C

#ifndef _LINUX_SCHED_H
#define _LINUX_SCHED_H
/*
* cloning flags:
*/
#define CSIGNAL 0x000000ff /* signal mask to be sent at exit */
#define CLONE_VM 0x00000100 /* set if VM shared between processes */
#define CLONE_FS 0x00000200 /* set if fs info shared between processes */
#define CLONE_FILES 0x00000400 /* set if open files shared between processes */
#define CLONE_SIGHAND 0x00000800 /* set if signal handlers and blocked signals shared */
#define CLONE_PTRACE 0x00002000 /* set if we want to let tracing continue on the child too */
#define CLONE_VFORK 0x00004000 /* set if the parent wants the child to wake it up on mm_release */
#define CLONE_PARENT 0x00008000 /* set if we want to have the same parent as the cloner */
#define CLONE_THREAD 0x00010000 /* Same thread group? */
#define CLONE_NEWNS 0x00020000 /* New namespace group? */
#define CLONE_SYSVSEM 0x00040000 /* share system V SEM_UNDO semantics */
#define CLONE_SETTLS 0x00080000 /* create a new TLS for the child */
#define CLONE_PARENT_SETTID 0x00100000 /* set the TID in the parent */
#define CLONE_CHILD_CLEARTID 0x00200000 /* clear the TID in the child */
#define CLONE_DETACHED 0x00400000 /* Unused, ignored */
#define CLONE_UNTRACED 0x00800000 /* set if the tracing process can't force CLONE_PTRACE on this clone */
#define CLONE_CHILD_SETTID 0x01000000 /* set the TID in the child */
/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
and is now available for re-use. */
#define CLONE_NEWUTS 0x04000000 /* New utsname group? */
#define CLONE_NEWIPC 0x08000000 /* New ipcs */
#define CLONE_NEWUSER 0x10000000 /* New user namespace */
#define CLONE_NEWPID 0x20000000 /* New pid namespace */
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
/*
* Scheduling policies
*/
#define SCHED_NORMAL 0
#define SCHED_FIFO 1
#define SCHED_RR 2
#define SCHED_BATCH 3
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE 5
/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
#define SCHED_RESET_ON_FORK 0x40000000
#ifdef __KERNEL__
struct sched_param {
int sched_priority;
};
#include <asm/param.h> /* for HZ */
#include <linux/capability.h>
#include <linux/threads.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/timex.h>
#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/thread_info.h>
#include <linux/cpumask.h>
#include <linux/errno.h>
#include <linux/nodemask.h>
#include <linux/mm_types.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/cputime.h>
#include <linux/smp.h>
#include <linux/sem.h>
#include <linux/signal.h>
#include <linux/compiler.h>
#include <linux/completion.h>
#include <linux/pid.h>
#include <linux/percpu.h>
#include <linux/topology.h>
#include <linux/proportions.h>
#include <linux/seccomp.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/rtmutex.h>
#include <linux/time.h>
#include <linux/param.h>
#include <linux/resource.h>
#include <linux/timer.h>
#include <linux/hrtimer.h>
#include <linux/task_io_accounting.h>
#include <linux/latencytop.h>
#include <linux/cred.h>
#include <linux/llist.h>
#include <linux/uidgid.h>
#include <asm/processor.h>
struct exec_domain;
struct futex_pi_state;
struct robust_list_head;
struct bio_list;
struct fs_struct;
struct perf_event_context;
struct blk_plug;
/*
* List of flags we want to share for kernel threads,
* if only because they are not used by them anyway.
*/
#define CLONE_KERNEL (CLONE_FS | CLONE_FILES | CLONE_SIGHAND)
/*
* These are the constant used to fake the fixed-point load-average
* counting. Some notes:
* - 11 bit fractions expand to 22 bits by the multiplies: this gives
* a load-average precision of 10 bits integer + 11 bits fractional
* - if you want to count load-averages more often, you need more
* precision, or rounding will get you. With 2-second counting freq,
* the EXP_n values would be 1981, 2034 and 2043 if still using only
* 11 bit fractions.
*/
extern unsigned long avenrun[]; /* Load averages */
extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
#define FSHIFT 11 /* nr of bits of precision */
#define FIXED_1 (1<<FSHIFT) /* 1.0 as fixed-point */
#define LOAD_FREQ (5*HZ+1) /* 5 sec intervals */
#define EXP_1 1884 /* 1/exp(5sec/1min) as fixed-point */
#define EXP_5 2014 /* 1/exp(5sec/5min) */
#define EXP_15 2037 /* 1/exp(5sec/15min) */
#define CALC_LOAD(load,exp,n) \
load *= exp; \
load += n*(FIXED_1-exp); \
load >>= FSHIFT;
extern unsigned long total_forks;
extern int nr_threads;
DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_iowait(void);
extern unsigned long nr_iowait_cpu(int cpu);
extern unsigned long this_cpu_load(void);
extern void calc_global_load(unsigned long ticks);
extern unsigned long get_parent_ip(unsigned long addr);
struct seq_file;
struct cfs_rq;
struct task_group;
#ifdef CONFIG_SCHED_DEBUG
extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
extern void proc_sched_set_task(struct task_struct *p);
extern void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
#else
static inline void
proc_sched_show_task(struct task_struct *p, struct seq_file *m)
{
}
static inline void proc_sched_set_task(struct task_struct *p)
{
}
static inline void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
}
#endif
/*
* 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_ZOMBIE 16
#define EXIT_DEAD 32
/* in tsk->state again */
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_STATE_MAX 512
#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
extern char ___assert_task_state[1 - 2*!!(
sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
/* Convenience macros for the sake of set_task_state */
#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
#define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED)
#define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED)
/* 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)
#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0)
#define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0)
#define task_is_dead(task) ((task)->exit_state != 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)
#define __set_task_state(tsk, state_value) \
do { (tsk)->state = (state_value); } while (0)
#define set_task_state(tsk, state_value) \
set_mb((tsk)->state, (state_value))
/*
* 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:
*
* set_current_state(TASK_UNINTERRUPTIBLE);
* if (do_i_need_to_sleep())
* schedule();
*
* If the caller does not need such serialisation then use __set_current_state()
*/
#define __set_current_state(state_value) \
do { current->state = (state_value); } while (0)
#define set_current_state(state_value) \
set_mb(current->state, (state_value))
/* Task command name length */
#define TASK_COMM_LEN 16
#include <linux/spinlock.h>
/*
* This serializes "schedule()" and also protects
* the run-queue from deletions/modifications (but
* _adding_ to the beginning of the run-queue has
* a separate lock).
*/
extern rwlock_t tasklist_lock;
extern spinlock_t mmlist_lock;
struct task_struct;
#ifdef CONFIG_PROVE_RCU
extern int lockdep_tasklist_lock_is_held(void);
#endif /* #ifdef CONFIG_PROVE_RCU */
extern void sched_init(void);
extern void sched_init_smp(void);
extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern void init_idle_bootup_task(struct task_struct *idle);
extern int runqueue_is_locked(int cpu);
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
extern void select_nohz_load_balancer(int stop_tick);
extern void set_cpu_sd_state_idle(void);
extern int get_nohz_timer_target(void);
#else
static inline void select_nohz_load_balancer(int stop_tick) { }
static inline void set_cpu_sd_state_idle(void) { }
#endif
/*
* Only dump TASK_* tasks. (0 for all tasks)
*/
extern void show_state_filter(unsigned long state_filter);
static inline void show_state(void)
{
show_state_filter(0);
}
extern void show_regs(struct pt_regs *);
/*
* TASK is a pointer to the task whose backtrace we want to see (or NULL for current
* task), SP is the stack pointer of the first frame that should be shown in the back
* trace (or NULL if the entire call-chain of the task should be shown).
*/
extern void show_stack(struct task_struct *task, unsigned long *sp);
void io_schedule(void);
long io_schedule_timeout(long timeout);
extern void cpu_init (void);
extern void trap_init(void);
extern void update_process_times(int user);
extern void scheduler_tick(void);
extern void sched_show_task(struct task_struct *p);
#ifdef CONFIG_LOCKUP_DETECTOR
extern void touch_softlockup_watchdog(void);
extern void touch_softlockup_watchdog_sync(void);
extern void touch_all_softlockup_watchdogs(void);
extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos);
extern unsigned int softlockup_panic;
void lockup_detector_init(void);
#else
static inline void touch_softlockup_watchdog(void)
{
}
static inline void touch_softlockup_watchdog_sync(void)
{
}
static inline void touch_all_softlockup_watchdogs(void)
{
}
static inline void lockup_detector_init(void)
{
}
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
extern unsigned int sysctl_hung_task_panic;
extern unsigned long sysctl_hung_task_check_count;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_warnings;
extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos);
#else
/* Avoid need for ifdefs elsewhere in the code */
enum { sysctl_hung_task_timeout_secs = 0 };
#endif
/* Attach to any functions which should be ignored in wchan output. */
#define __sched __attribute__((__section__(".sched.text")))
/* Linker adds these: start and end of __sched functions */
extern char __sched_text_start[], __sched_text_end[];
/* Is this address in the __sched functions? */
extern int in_sched_functions(unsigned long addr);
#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);
asmlinkage void schedule(void);
extern void schedule_preempt_disabled(void);
extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
struct nsproxy;
struct user_namespace;
/*
* Default maximum number of active map areas, this limits the number of vmas
* per mm struct. Users can overwrite this number by sysctl but there is a
* problem.
*
* When a program's coredump is generated as ELF format, a section is created
* per a vma. In ELF, the number of sections is represented in unsigned short.
* This means the number of sections should be smaller than 65535 at coredump.
* Because the kernel adds some informative sections to a image of program at
* generating coredump, we need some margin. The number of extra sections is
* 1-3 now and depends on arch. We use "5" as safe margin, here.
*/
#define MAPCOUNT_ELF_CORE_MARGIN (5)
#define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
extern int sysctl_max_map_count;
#include <linux/aio.h>
#ifdef CONFIG_MMU
extern void arch_pick_mmap_layout(struct mm_struct *mm);
extern unsigned long
arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
unsigned long, unsigned long);
extern unsigned long
arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
extern void arch_unmap_area(struct mm_struct *, unsigned long);
extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
#else
static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
#endif
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
/* mm flags */
/* dumpable bits */
#define MMF_DUMPABLE 0 /* core dump is permitted */
#define MMF_DUMP_SECURELY 1 /* core file is readable only by root */
#define MMF_DUMPABLE_BITS 2
#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
/* coredump filter bits */
#define MMF_DUMP_ANON_PRIVATE 2
#define MMF_DUMP_ANON_SHARED 3
#define MMF_DUMP_MAPPED_PRIVATE 4
#define MMF_DUMP_MAPPED_SHARED 5
#define MMF_DUMP_ELF_HEADERS 6
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED 8
#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS 7
#define MMF_DUMP_FILTER_MASK \
(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
#define MMF_DUMP_FILTER_DEFAULT \
((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\
(1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS)
#else
# define MMF_DUMP_MASK_DEFAULT_ELF 0
#endif
/* leave room for more dump flags */
#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
struct sighand_struct {
atomic_t count;
struct k_sigaction action[_NSIG];
spinlock_t siglock;
wait_queue_head_t signalfd_wqh;
};
struct pacct_struct {
int ac_flag;
long ac_exitcode;
unsigned long ac_mem;
cputime_t ac_utime, ac_stime;
unsigned long ac_minflt, ac_majflt;
};
struct cpu_itimer {
cputime_t expires;
cputime_t incr;
u32 error;
u32 incr_error;
};
/**
* struct task_cputime - collected CPU time counts
* @utime: time spent in user mode, in &cputime_t units
* @stime: time spent in kernel mode, in &cputime_t units
* @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 {
cputime_t utime;
cputime_t stime;
unsigned long long sum_exec_runtime;
};
/* Alternate field names when used to cache expirations. */
#define prof_exp stime
#define virt_exp utime
#define sched_exp sum_exec_runtime
#define INIT_CPUTIME \
(struct task_cputime) { \
.utime = 0, \
.stime = 0, \
.sum_exec_runtime = 0, \
}
/*
* Disable preemption until the scheduler is running.
* Reset by start_kernel()->sched_init()->init_idle().
*
* We include PREEMPT_ACTIVE to avoid cond_resched() from working
* before the scheduler is active -- see should_resched().
*/
#define INIT_PREEMPT_COUNT (1 + PREEMPT_ACTIVE)
/**
* struct thread_group_cputimer - thread group interval timer counts
* @cputime: thread group interval timers.
* @running: non-zero when there are timers running and
* @cputime receives updates.
* @lock: lock for fields in this struct.
*
* This structure contains the version of task_cputime, above, that is
* used for thread group CPU timer calculations.
*/
struct thread_group_cputimer {
struct task_cputime cputime;
int running;
raw_spinlock_t lock;
};
#include <linux/rwsem.h>
struct autogroup;
/*
* NOTE! "signal_struct" does not have its own
* locking, because a shared signal_struct always
* implies a shared sighand_struct, so locking
* sighand_struct is always a proper superset of
* the locking of signal_struct.
*/
struct signal_struct {
atomic_t sigcnt;
atomic_t live;
int nr_threads;
wait_queue_head_t wait_chldexit; /* for wait4() */
/* current thread group signal load-balancing target: */
struct task_struct *curr_target;
/* shared signal handling: */
struct sigpending shared_pending;
/* thread group exit support */
int group_exit_code;
/* overloaded:
* - notify group_exit_task when ->count is equal to notify_count
* - everyone except group_exit_task is stopped during signal delivery
* of fatal signals, group_exit_task processes the signal.
*/
int notify_count;
struct task_struct *group_exit_task;
/* thread group stop support, overloads group_exit_code too */
int group_stop_count;
unsigned int flags; /* see SIGNAL_* flags below */
/*
* PR_SET_CHILD_SUBREAPER marks a process, like a service
* manager, to re-parent orphan (double-forking) child processes
* to this process instead of 'init'. The service manager is
* able to receive SIGCHLD signals and is able to investigate
* the process until it calls wait(). All children of this
* process will inherit a flag if they should look for a
* child_subreaper process at exit.
*/
unsigned int is_child_subreaper:1;
unsigned int has_child_subreaper:1;
/* POSIX.1b Interval Timers */
struct list_head posix_timers;
/* ITIMER_REAL timer for the process */
struct hrtimer real_timer;
struct pid *leader_pid;
ktime_t it_real_incr;
/*
* ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
* CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
* values are defined to 0 and 1 respectively
*/
struct cpu_itimer it[2];
/*
* Thread group totals for process CPU timers.
* See thread_group_cputimer(), et al, for details.
*/
struct thread_group_cputimer cputimer;
/* Earliest-expiration cache. */
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
struct pid *tty_old_pgrp;
/* boolean value for session group leader */
int leader;
struct tty_struct *tty; /* NULL if no tty */
#ifdef CONFIG_SCHED_AUTOGROUP
struct autogroup *autogroup;
#endif
/*
* Cumulative resource counters for dead threads in the group,
* and for reaped dead child processes forked by this group.
* Live threads maintain their own counters and add to these
* in __exit_signal, except for the group leader.
*/
cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
cputime_t prev_utime, prev_stime;
#endif
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
unsigned long inblock, oublock, cinblock, coublock;
unsigned long maxrss, cmaxrss;
struct task_io_accounting ioac;
/*
* Cumulative ns of schedule CPU time fo dead threads in the
* group, not including a zombie group leader, (This only differs
* from jiffies_to_ns(utime + stime) if sched_clock uses something
* other than jiffies.)
*/
unsigned long long sum_sched_runtime;
/*
* We don't bother to synchronize most readers of this at all,
* because there is no reader checking a limit that actually needs
* to get both rlim_cur and rlim_max atomically, and either one
* alone is a single word that can safely be read normally.
* getrlimit/setrlimit use task_lock(current->group_leader) to
* protect this instead of the siglock, because they really
* have no need to disable irqs.
*/
struct rlimit rlim[RLIM_NLIMITS];
#ifdef CONFIG_BSD_PROCESS_ACCT
struct pacct_struct pacct; /* per-process accounting information */
#endif
#ifdef CONFIG_TASKSTATS
struct taskstats *stats;
#endif
#ifdef CONFIG_AUDIT
unsigned audit_tty;
struct tty_audit_buf *tty_audit_buf;
#endif
#ifdef CONFIG_CGROUPS
/*
* group_rwsem prevents new tasks from entering the threadgroup and
* member tasks from exiting,a more specifically, setting of
* PF_EXITING. fork and exit paths are protected with this rwsem
* using threadgroup_change_begin/end(). Users which require
* threadgroup to remain stable should use threadgroup_[un]lock()
* which also takes care of exec path. Currently, cgroup is the
* only user.
*/
struct rw_semaphore group_rwsem;
#endif
int oom_adj; /* OOM kill score adjustment (bit shift) */
int oom_score_adj; /* OOM kill score adjustment */
int oom_score_adj_min; /* OOM kill score adjustment minimum value.
* Only settable by CAP_SYS_RESOURCE. */
struct mutex cred_guard_mutex; /* guard against foreign influences on
* credential calculations
* (notably. ptrace) */
};
/* Context switch must be unlocked if interrupts are to be enabled */
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
# define __ARCH_WANT_UNLOCKED_CTXSW
#endif
/*
* Bits in flags field of signal_struct.
*/
#define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */
#define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */
#define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */
/*
* Pending notifications to parent.
*/
#define SIGNAL_CLD_STOPPED 0x00000010
#define SIGNAL_CLD_CONTINUED 0x00000020
#define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED)
#define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */
/* If true, all threads except ->group_exit_task have pending SIGKILL */
static inline int signal_group_exit(const struct signal_struct *sig)
{
return (sig->flags & SIGNAL_GROUP_EXIT) ||
(sig->group_exit_task != NULL);
}
/*
* Some day this will be a full-fledged user tracking system..
*/
struct user_struct {
atomic_t __count; /* reference count */
atomic_t processes; /* How many processes does this user have? */
atomic_t files; /* How many open files does this user have? */
atomic_t sigpending; /* How many pending signals does this user have? */
#ifdef CONFIG_INOTIFY_USER
atomic_t inotify_watches; /* How many inotify watches does this user have? */
atomic_t inotify_devs; /* How many inotify devs does this user have opened? */
#endif
#ifdef CONFIG_FANOTIFY
atomic_t fanotify_listeners;
#endif
#ifdef CONFIG_EPOLL
atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
#endif
#ifdef CONFIG_POSIX_MQUEUE
/* protected by mq_lock */
unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */
#endif
unsigned long locked_shm; /* How many pages of mlocked shm ? */
#ifdef CONFIG_KEYS
struct key *uid_keyring; /* UID specific keyring */
struct key *session_keyring; /* UID's default session keyring */
#endif
/* Hash table maintenance information */
struct hlist_node uidhash_node;
kuid_t uid;
#ifdef CONFIG_PERF_EVENTS
atomic_long_t locked_vm;
#endif
};
extern int uids_sysfs_init(void);
extern struct user_struct *find_user(kuid_t);
extern struct user_struct root_user;
#define INIT_USER (&root_user)
struct backing_dev_info;
struct reclaim_state;
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
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 /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info {
spinlock_t lock;
unsigned int flags; /* Private per-task flags */
/* For each stat XXX, add following, aligned appropriately
*
* struct timespec XXX_start, XXX_end;
* u64 XXX_delay;
* u32 XXX_count;
*
* Atomicity of updates to XXX_delay, XXX_count protected by
* single lock above (split into XXX_lock if contention is an issue).
*/
/*
* XXX_count is incremented on every XXX operation, the delay
* associated with the operation is added to XXX_delay.
* XXX_delay contains the accumulated delay time in nanoseconds.
*/
struct timespec blkio_start, blkio_end; /* Shared by blkio, swapin */
u64 blkio_delay; /* wait for sync block io completion */
u64 swapin_delay; /* wait for swapin block io completion */
u32 blkio_count; /* total count of the number of sync block */
/* io operations performed */
u32 swapin_count; /* total count of the number of swapin block */
/* io operations performed */
struct timespec freepages_start, freepages_end;
u64 freepages_delay; /* wait for memory reclaim */
u32 freepages_count; /* total count of memory reclaim */
};
#endif /* CONFIG_TASK_DELAY_ACCT */
static inline int sched_info_on(void)
{
#ifdef CONFIG_SCHEDSTATS
return 1;
#elif defined(CONFIG_TASK_DELAY_ACCT)
extern int delayacct_on;
return delayacct_on;
#else
return 0;
#endif
}
enum cpu_idle_type {
CPU_IDLE,
CPU_NOT_IDLE,
CPU_NEWLY_IDLE,
CPU_MAX_IDLE_TYPES
};
/*
* Increase resolution of nice-level calculations for 64-bit architectures.
* The extra resolution improves shares distribution and load balancing of
* low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
* hierarchies, especially on larger systems. This is not a user-visible change
* and does not change the user-interface for setting shares/weights.
*
* We increase resolution only if we have enough bits to allow this increased
* resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
* when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
* increased costs.
*/
#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */
# define SCHED_LOAD_RESOLUTION 10
# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION)
# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION)
#else
# define SCHED_LOAD_RESOLUTION 0
# define scale_load(w) (w)
# define scale_load_down(w) (w)
#endif
#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION)
#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT)
/*
* Increase resolution of cpu_power calculations
*/
#define SCHED_POWER_SHIFT 10
#define SCHED_POWER_SCALE (1L << SCHED_POWER_SHIFT)
/*
* sched-domains (multiprocessor balancing) declarations:
*/
#ifdef CONFIG_SMP
#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */
#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */
#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */
#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */
#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
#define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */
#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */
#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
extern int __weak arch_sd_sibiling_asym_packing(void);
struct sched_group_power {
atomic_t ref;
/*
* CPU power of this group, SCHED_LOAD_SCALE being max power for a
* single CPU.
*/
unsigned int power, power_orig;
unsigned long next_update;
/*
* Number of busy cpus in this group.
*/
atomic_t nr_busy_cpus;
};
struct sched_group {
struct sched_group *next; /* Must be a circular list */
atomic_t ref;
unsigned int group_weight;
struct sched_group_power *sgp;
/*
* The CPUs this group covers.
*
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
*/
unsigned long cpumask[0];
};
static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
return to_cpumask(sg->cpumask);
}
/**
* group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
* @group: The group whose first cpu is to be returned.
*/
static inline unsigned int group_first_cpu(struct sched_group *group)
{
return cpumask_first(sched_group_cpus(group));
}
struct sched_domain_attr {
int relax_domain_level;
};
#define SD_ATTR_INIT (struct sched_domain_attr) { \
.relax_domain_level = -1, \
}
extern int sched_domain_level_max;
struct sched_domain {
/* These fields must be setup */
struct sched_domain *parent; /* top domain must be null terminated */
struct sched_domain *child; /* bottom domain must be null terminated */
struct sched_group *groups; /* the balancing groups of the domain */
unsigned long min_interval; /* Minimum balance interval ms */
unsigned long max_interval; /* Maximum balance interval ms */
unsigned int busy_factor; /* less balancing by factor if busy */
unsigned int imbalance_pct; /* No balance until over watermark */
unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */
unsigned int busy_idx;
unsigned int idle_idx;
unsigned int newidle_idx;
unsigned int wake_idx;
unsigned int forkexec_idx;
unsigned int smt_gain;
int flags; /* See SD_* */
int level;
/* Runtime fields. */
unsigned long last_balance; /* init to jiffies. units in jiffies */
unsigned int balance_interval; /* initialise to 1. units in ms. */
unsigned int nr_balance_failed; /* initialise to 0 */
u64 last_update;
#ifdef CONFIG_SCHEDSTATS
/* load_balance() stats */
unsigned int lb_count[CPU_MAX_IDLE_TYPES];
unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
unsigned int lb_nobusyq[CPU_MAX_IDLE_TYPES];
/* Active load balancing */
unsigned int alb_count;
unsigned int alb_failed;
unsigned int alb_pushed;
/* SD_BALANCE_EXEC stats */
unsigned int sbe_count;
unsigned int sbe_balanced;
unsigned int sbe_pushed;
/* SD_BALANCE_FORK stats */
unsigned int sbf_count;
unsigned int sbf_balanced;
unsigned int sbf_pushed;
/* try_to_wake_up() stats */
unsigned int ttwu_wake_remote;
unsigned int ttwu_move_affine;
unsigned int ttwu_move_balance;
#endif
#ifdef CONFIG_SCHED_DEBUG
char *name;
#endif
union {
void *private; /* used during construction */
struct rcu_head rcu; /* used during destruction */
};
unsigned int span_weight;
/*
* Span of all CPUs in this domain.
*
* NOTE: this field is variable length. (Allocated dynamically
* by attaching extra space to the end of the structure,
* depending on how many CPUs the kernel has booted up with)
*/
unsigned long span[0];
};
static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
{
return to_cpumask(sd->span);
}
extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new);
/* Allocate an array of sched domains, for partition_sched_domains(). */
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
/* Test a flag in parent sched domain */
static inline int test_sd_parent(struct sched_domain *sd, int flag)
{
if (sd->parent && (sd->parent->flags & flag))
return 1;
return 0;
}
unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
bool cpus_share_cache(int this_cpu, int that_cpu);
#else /* CONFIG_SMP */
struct sched_domain_attr;
static inline void
partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
}
static inline bool cpus_share_cache(int this_cpu, int that_cpu)
{
return true;
}
#endif /* !CONFIG_SMP */
struct io_context; /* See blkdev.h */
#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 audit_context; /* See audit.c */
struct mempolicy;
struct pipe_inode_info;
struct uts_namespace;
struct rq;
struct sched_domain;
/*
* wake flags
*/
#define WF_SYNC 0x01 /* waker goes to sleep after wakup */
#define WF_FORK 0x02 /* child wakeup after fork */
#define WF_MIGRATED 0x04 /* internal use, task got migrated */
#define ENQUEUE_WAKEUP 1
#define ENQUEUE_HEAD 2
#ifdef CONFIG_SMP
#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */
#else
#define ENQUEUE_WAKING 0
#endif
#define DEQUEUE_SLEEP 1
struct sched_class {
const struct sched_class *next;
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*yield_task) (struct rq *rq);
bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
struct task_struct * (*pick_next_task) (struct rq *rq);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
void (*post_schedule) (struct rq *this_rq);
void (*task_waking) (struct task_struct *task);
void (*task_woken) (struct rq *this_rq, struct task_struct *task);
void (*set_cpus_allowed)(struct task_struct *p,
const struct cpumask *newmask);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
#endif
void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
void (*task_fork) (struct task_struct *p);
void (*switched_from) (struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
int oldprio);
unsigned int (*get_rr_interval) (struct rq *rq,
struct task_struct *task);
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*task_move_group) (struct task_struct *p, int on_rq);
#endif
};
struct load_weight {
unsigned long weight, inv_weight;
};
#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
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
};
struct sched_rt_entity {
struct list_head run_list;
unsigned long timeout;
unsigned int time_slice;
int nr_cpus_allowed;
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
};
/*
* default timeslice is 100 msecs (used only for SCHED_RR tasks).
* Timeslices get refilled after they expire.
*/
#define RR_TIMESLICE (100 * HZ / 1000)
struct rcu_node;
enum perf_event_task_context {
perf_invalid_context = -1,
perf_hw_context = 0,
perf_sw_context,
perf_nr_task_contexts,
};
struct task_struct {
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;
#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_PREEMPT_NOTIFIERS
/* list of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
#endif
/*
* fpu_counter contains the number of consecutive context switches
* that the FPU is used. If this is over a threshold, the lazy fpu
* saving becomes unlazy to save the trap. This is an unsigned char
* so that after 256 times the counter wraps and the behavior turns
* lazy again; this to deal with bursty apps that only use FPU for
* a short time
*/
unsigned char fpu_counter;
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
unsigned int policy;
cpumask_t cpus_allowed;
#ifdef CONFIG_PREEMPT_RCU
int rcu_read_lock_nesting;
char rcu_read_unlock_special;
struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCU
struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
struct rt_mutex *rcu_boost_mutex;
#endif /* #ifdef CONFIG_RCU_BOOST */
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info sched_info;
#endif
struct list_head tasks;
#ifdef CONFIG_SMP
struct plist_node pushable_tasks;
#endif
struct mm_struct *mm, *active_mm;
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
#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 int jobctl; /* JOBCTL_*, siglock protected */
/* ??? */
unsigned int personality;
unsigned did_exec:1;
unsigned in_execve:1; /* Tell the LSMs that the process is doing an
* execve */
unsigned in_iowait:1;
/* task may not gain privileges */
unsigned no_new_privs:1;
/* Revert to default priority/policy when forking */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
#ifdef CONFIG_GENERIC_HARDIRQS
/* IRQ handler threads */
unsigned irq_thread:1;
#endif
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 completion *vfork_done; /* for vfork() */
int __user *set_child_tid; /* CLONE_CHILD_SETTID */
int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
cputime_t utime, stime, utimescaled, stimescaled;
cputime_t gtime;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
cputime_t prev_utime, prev_stime;
#endif
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
struct timespec real_start_time; /* boot based time */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
unsigned long min_flt, maj_flt;
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
/* process credentials */
const struct cred __rcu *real_cred; /* objective and real subjective task
* credentials (COW) */
const struct cred __rcu *cred; /* effective (overridable) subjective task
* credentials (COW) */
struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
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 */
int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
struct sysv_sem sysvsem;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
unsigned long last_switch_count;
#endif
/* CPU-specific state of this task */
struct thread_struct thread;
/* 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;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
uid_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;
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task */
struct plist_head pi_waiters;
/* 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
/* 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 */
cputime_t 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_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_NUMA
struct mempolicy *mempolicy; /* Protected by alloc_lock */
short il_next;
short pref_node_fork;
#endif
struct rcu_head rcu;
/*
* cache last used pipe for splice
*/
struct pipe_inode_info *splice_pipe;
#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.
*/
unsigned long timer_slack_ns;
unsigned long default_timer_slack_ns;
struct list_head *scm_work_list;
#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_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
struct memcg_batch_info {
int do_batch; /* incremented when batch uncharge started */
struct mem_cgroup *memcg; /* target memcg of uncharge */
unsigned long nr_pages; /* uncharged usage */
unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
} memcg_batch;
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
atomic_t ptrace_bp_refcnt;
#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
int uprobe_srcu_id;
#endif
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
/*
* Priority of a process goes from 0..MAX_PRIO-1, valid RT
* priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
* tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
* values are inverted: lower p->prio value means higher priority.
*
* The MAX_USER_RT_PRIO value allows the actual maximum
* RT priority to be separate from the value exported to
* user-space. This allows kernel threads to set their
* priority to a value higher than any user task. Note:
* MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
*/
#define MAX_USER_RT_PRIO 100
#define MAX_RT_PRIO MAX_USER_RT_PRIO
#define MAX_PRIO (MAX_RT_PRIO + 40)
#define DEFAULT_PRIO (MAX_RT_PRIO + 20)
static inline int rt_prio(int prio)
{
if (unlikely(prio < MAX_RT_PRIO))
return 1;
return 0;
}
static inline int rt_task(struct task_struct *p)
{
return rt_prio(p->prio);
}
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;
}
struct pid_namespace;
/*
* 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 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.
*/
static inline int pid_alive(struct task_struct *p)
{
return p->pids[PIDTYPE_PID].pid != NULL;
}
/**
* is_global_init - check if a task structure is init
* @tsk: Task structure to be checked.
*
* Check if a task structure is the first user space task the kernel created.
*/
static inline int is_global_init(struct task_struct *tsk)
{
return tsk->pid == 1;
}
/*
* is_container_init:
* check whether in the task is init in its own pid namespace.
*/
extern int is_container_init(struct task_struct *tsk);
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);
}
extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
/*
* Per process flags
*/
#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_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_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_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */
#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */
#define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
/*
* 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)
/*
* task->jobctl flags
*/
#define JOBCTL_STOP_SIGMASK 0xffff /* signr of the last group stop */
#define JOBCTL_STOP_DEQUEUED_BIT 16 /* stop signal dequeued */
#define JOBCTL_STOP_PENDING_BIT 17 /* task should stop for group stop */
#define JOBCTL_STOP_CONSUME_BIT 18 /* consume group stop count */
#define JOBCTL_TRAP_STOP_BIT 19 /* trap for STOP */
#define JOBCTL_TRAP_NOTIFY_BIT 20 /* trap for NOTIFY */
#define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */
#define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */
#define JOBCTL_STOP_DEQUEUED (1 << JOBCTL_STOP_DEQUEUED_BIT)
#define JOBCTL_STOP_PENDING (1 << JOBCTL_STOP_PENDING_BIT)
#define JOBCTL_STOP_CONSUME (1 << JOBCTL_STOP_CONSUME_BIT)
#define JOBCTL_TRAP_STOP (1 << JOBCTL_TRAP_STOP_BIT)
#define JOBCTL_TRAP_NOTIFY (1 << JOBCTL_TRAP_NOTIFY_BIT)
#define JOBCTL_TRAPPING (1 << JOBCTL_TRAPPING_BIT)
#define JOBCTL_LISTENING (1 << JOBCTL_LISTENING_BIT)
#define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
#define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
extern bool task_set_jobctl_pending(struct task_struct *task,
unsigned int mask);
extern void task_clear_jobctl_trapping(struct task_struct *task);
extern void task_clear_jobctl_pending(struct task_struct *task,
unsigned int mask);
#ifdef CONFIG_PREEMPT_RCU
#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
static inline void rcu_copy_process(struct task_struct *p)
{
p->rcu_read_lock_nesting = 0;
p->rcu_read_unlock_special = 0;
#ifdef CONFIG_TREE_PREEMPT_RCU
p->rcu_blocked_node = NULL;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOST
p->rcu_boost_mutex = NULL;
#endif /* #ifdef CONFIG_RCU_BOOST */
INIT_LIST_HEAD(&p->rcu_node_entry);
}
static inline void rcu_switch_from(struct task_struct *prev)
{
if (prev->rcu_read_lock_nesting != 0)
rcu_preempt_note_context_switch();
}
#else
static inline void rcu_copy_process(struct task_struct *p)
{
}
static inline void rcu_switch_from(struct task_struct *prev)
{
}
#endif
#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 CONFIG_CPUMASK_OFFSTACK
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
return set_cpus_allowed_ptr(p, &new_mask);
}
#endif
/*
* Do not use outside of architecture code which knows its limitations.
*
* sched_clock() has no promise of monotonicity or bounded drift between
* CPUs, use (which you should not) requires disabling IRQs.
*
* Please use one of the three interfaces below.
*/
extern unsigned long long notrace sched_clock(void);
/*
* See the comment in kernel/sched/clock.c
*/
extern u64 cpu_clock(int cpu);
extern u64 local_clock(void);
extern u64 sched_clock_cpu(int cpu);
extern void sched_clock_init(void);
#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
static inline void sched_clock_tick(void)
{
}
static inline void sched_clock_idle_sleep_event(void)
{
}
static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
{
}
#else
/*
* Architectures can set this to 1 if they have specified
* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
* but then during bootup it turns out that sched_clock()
* is reliable after all:
*/
extern int sched_clock_stable;
extern void sched_clock_tick(void);
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/*
* An i/f to runtime opt-in for irq time accounting based off of sched_clock.
* The reason for this explicit opt-in is not to have perf penalty with
* slow sched_clocks.
*/
extern void enable_sched_clock_irqtime(void);
extern void disable_sched_clock_irqtime(void);
#else
static inline void enable_sched_clock_irqtime(void) {}
static inline void disable_sched_clock_irqtime(void) {}
#endif
extern unsigned long long
task_sched_runtime(struct task_struct *task);
/* sched_exec is called by processes performing an exec */
#ifdef CONFIG_SMP
extern void sched_exec(void);
#else
#define sched_exec() {}
#endif
extern void sched_clock_idle_sleep_event(void);
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#ifdef CONFIG_HOTPLUG_CPU
extern void idle_task_exit(void);
#else
static inline void idle_task_exit(void) {}
#endif
#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
extern void wake_up_idle_cpu(int cpu);
#else
static inline void wake_up_idle_cpu(int cpu) { }
#endif
extern unsigned int sysctl_sched_latency;
extern unsigned int sysctl_sched_min_granularity;
extern unsigned int sysctl_sched_wakeup_granularity;
extern unsigned int sysctl_sched_child_runs_first;
enum sched_tunable_scaling {
SCHED_TUNABLESCALING_NONE,
SCHED_TUNABLESCALING_LOG,
SCHED_TUNABLESCALING_LINEAR,
SCHED_TUNABLESCALING_END,
};
extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
#ifdef CONFIG_SCHED_DEBUG
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
extern unsigned int sysctl_sched_time_avg;
extern unsigned int sysctl_timer_migration;
extern unsigned int sysctl_sched_shares_window;
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
loff_t *ppos);
#endif
#ifdef CONFIG_SCHED_DEBUG
static inline unsigned int get_sysctl_timer_migration(void)
{
return sysctl_timer_migration;
}
#else
static inline unsigned int get_sysctl_timer_migration(void)
{
return 1;
}
#endif
extern unsigned int sysctl_sched_rt_period;
extern int sysctl_sched_rt_runtime;
int sched_rt_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
#ifdef CONFIG_SCHED_AUTOGROUP
extern unsigned int sysctl_sched_autogroup_enabled;
extern void sched_autogroup_create_attach(struct task_struct *p);
extern void sched_autogroup_detach(struct task_struct *p);
extern void sched_autogroup_fork(struct signal_struct *sig);
extern void sched_autogroup_exit(struct signal_struct *sig);
#ifdef CONFIG_PROC_FS
extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
extern int proc_sched_autogroup_set_nice(struct task_struct *p, int nice);
#endif
#else
static inline void sched_autogroup_create_attach(struct task_struct *p) { }
static inline void sched_autogroup_detach(struct task_struct *p) { }
static inline void sched_autogroup_fork(struct signal_struct *sig) { }
static inline void sched_autogroup_exit(struct signal_struct *sig) { }
#endif
#ifdef CONFIG_CFS_BANDWIDTH
extern unsigned int sysctl_sched_cfs_bandwidth_slice;
#endif
#ifdef CONFIG_RT_MUTEXES
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
extern void rt_mutex_adjust_pi(struct task_struct *p);
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
{
return tsk->pi_blocked_on != NULL;
}
#else
static inline int rt_mutex_getprio(struct task_struct *p)
{
return p->normal_prio;
}
# define rt_mutex_adjust_pi(p) do { } while (0)
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
{
return false;
}
#endif
extern bool 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);
extern 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 sched_setscheduler(struct task_struct *, int,
const struct sched_param *);
extern int sched_setscheduler_nocheck(struct task_struct *, int,
const struct sched_param *);
extern struct task_struct *idle_task(int cpu);
/**
* is_idle_task - is the specified task an idle task?
* @p: the task in question.
*/
static inline bool is_idle_task(const struct task_struct *p)
{
return p->pid == 0;
}
extern struct task_struct *curr_task(int cpu);
extern void set_curr_task(int cpu, struct task_struct *p);
void yield(void);
/*
* The default (Linux) execution domain.
*/
extern struct exec_domain default_exec_domain;
union thread_union {
struct thread_info thread_info;
unsigned long stack[THREAD_SIZE/sizeof(long)];
};
#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 union thread_union init_thread_union;
extern struct task_struct init_task;
extern struct mm_struct init_mm;
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 void __set_special_pids(struct pid *pid);
/* per-UID process charging. */
extern struct user_struct * alloc_uid(kuid_t);
static inline struct user_struct *get_uid(struct user_struct *u)
{
atomic_inc(&u->__count);
return u;
}
extern void free_uid(struct user_struct *);
#include <asm/current.h>
extern void xtime_update(unsigned long ticks);
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 sched_fork(struct task_struct *p);
extern void sched_dead(struct task_struct *p);
extern void proc_caches_init(void);
extern void flush_signals(struct task_struct *);
extern void __flush_signals(struct task_struct *);
extern void ignore_signals(struct task_struct *);
extern void flush_signal_handlers(struct task_struct *, int force_default);
extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&tsk->sighand->siglock, flags);
ret = dequeue_signal(tsk, mask, info);
spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
return ret;
}
extern void block_all_signals(int (*notifier)(void *priv), void *priv,
sigset_t *mask);
extern void unblock_all_signals(void);
extern void release_task(struct task_struct * p);
extern int send_sig_info(int, struct siginfo *, struct task_struct *);
extern int force_sigsegv(int, struct task_struct *);
extern int force_sig_info(int, struct siginfo *, struct task_struct *);
extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp);
extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid);
extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *,
const struct cred *, u32);
extern int kill_pgrp(struct pid *pid, int sig, int priv);
extern int kill_pid(struct pid *pid, int sig, int priv);
extern int kill_proc_info(int, struct siginfo *, pid_t);
extern __must_check bool do_notify_parent(struct task_struct *, int);
extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
extern void force_sig(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
extern int zap_other_threads(struct task_struct *p);
extern struct sigqueue *sigqueue_alloc(void);
extern void sigqueue_free(struct sigqueue *);
extern int send_sigqueue(struct sigqueue *, struct task_struct *, int group);
extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *);
extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned long);
static inline int kill_cad_pid(int sig, int priv)
{
return kill_pid(cad_pid, sig, priv);
}
/* These can be the second arg to send_sig_info/send_group_sig_info. */
#define SEND_SIG_NOINFO ((struct siginfo *) 0)
#define SEND_SIG_PRIV ((struct siginfo *) 1)
#define SEND_SIG_FORCED ((struct siginfo *) 2)
/*
* True if we are on the alternate signal stack.
*/
static inline int on_sig_stack(unsigned long sp)
{
#ifdef CONFIG_STACK_GROWSUP
return sp >= current->sas_ss_sp &&
sp - current->sas_ss_sp < current->sas_ss_size;
#else
return sp > current->sas_ss_sp &&
sp - current->sas_ss_sp <= current->sas_ss_size;
#endif
}
static inline int sas_ss_flags(unsigned long sp)
{
return (current->sas_ss_size == 0 ? SS_DISABLE
: on_sig_stack(sp) ? SS_ONSTACK : 0);
}
/*
* Routines for handling mm_structs
*/
extern struct mm_struct * mm_alloc(void);
/* mmdrop drops the mm and the page tables */
extern void __mmdrop(struct mm_struct *);
static inline void mmdrop(struct mm_struct * mm)
{
if (unlikely(atomic_dec_and_test(&mm->mm_count)))
__mmdrop(mm);
}
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
/*
* Grab a reference to a task's mm, if it is not already going away
* and ptrace_may_access with the mode parameter passed to it
* succeeds.
*/
extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
/* Remove the current tasks stale references to the old mm_struct */
extern void mm_release(struct task_struct *, struct mm_struct *);
/* Allocate a new mm structure and copy contents from tsk->mm */
extern struct mm_struct *dup_mm(struct task_struct *tsk);
extern int copy_thread(unsigned long, unsigned long, unsigned long,
struct task_struct *, struct pt_regs *);
extern void flush_thread(void);
extern void exit_thread(void);
extern void exit_files(struct task_struct *);
extern void __cleanup_sighand(struct sighand_struct *);
extern void exit_itimers(struct signal_struct *);
extern void flush_itimer_signals(void);
extern void do_group_exit(int);
extern void daemonize(const char *, ...);
extern int allow_signal(int);
extern int disallow_signal(int);
extern int do_execve(const char *,
const char __user * const __user *,
const char __user * const __user *, struct pt_regs *);
extern long do_fork(unsigned long, unsigned long, struct pt_regs *, unsigned long, int __user *, int __user *);
struct task_struct *fork_idle(int);
extern void set_task_comm(struct task_struct *tsk, char *from);
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
#define next_task(p) \
list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
extern bool current_is_single_threaded(void);
/*
* Careful: do_each_thread/while_each_thread is a double loop so
* 'break' will not work as expected - use goto instead.
*/
#define do_each_thread(g, t) \
for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do
#define while_each_thread(g, t) \
while ((t = next_thread(t)) != g)
static inline int get_nr_threads(struct task_struct *tsk)
{
return tsk->signal->nr_threads;
}
static inline bool thread_group_leader(struct task_struct *p)
{
return p->exit_signal >= 0;
}
/* Do to the insanities of de_thread it is possible for a process
* to have the pid of the thread group leader without actually being
* the thread group leader. For iteration through the pids in proc
* all we care about is that we have a task with the appropriate
* pid, we don't actually care if we have the right task.
*/
static inline int has_group_leader_pid(struct task_struct *p)
{
return p->pid == p->tgid;
}
static inline
int same_thread_group(struct task_struct *p1, struct task_struct *p2)
{
return p1->tgid == p2->tgid;
}
static inline struct task_struct *next_thread(const struct task_struct *p)
{
return list_entry_rcu(p->thread_group.next,
struct task_struct, thread_group);
}
static inline int thread_group_empty(struct task_struct *p)
{
return list_empty(&p->thread_group);
}
#define delay_group_leader(p) \
(thread_group_leader(p) && !thread_group_empty(p))
/*
* Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
* subscriptions and synchronises with wait4(). Also used in procfs. Also
* pins the final release of task.io_context. Also protects ->cpuset and
* ->cgroup.subsys[]. And ->vfork_done.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
* neither inside nor outside.
*/
static inline void task_lock(struct task_struct *p)
{
spin_lock(&p->alloc_lock);
}
static inline void task_unlock(struct task_struct *p)
{
spin_unlock(&p->alloc_lock);
}
extern struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
unsigned long *flags);
static inline struct sighand_struct *lock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
{
struct sighand_struct *ret;
ret = __lock_task_sighand(tsk, flags);
(void)__cond_lock(&tsk->sighand->siglock, ret);
return ret;
}
static inline void unlock_task_sighand(struct task_struct *tsk,
unsigned long *flags)
{
spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);
}
#ifdef CONFIG_CGROUPS
static inline void threadgroup_change_begin(struct task_struct *tsk)
{
down_read(&tsk->signal->group_rwsem);
}
static inline void threadgroup_change_end(struct task_struct *tsk)
{
up_read(&tsk->signal->group_rwsem);
}
/**
* threadgroup_lock - lock threadgroup
* @tsk: member task of the threadgroup to lock
*
* Lock the threadgroup @tsk belongs to. No new task is allowed to enter
* and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
* perform exec. This is useful for cases where the threadgroup needs to
* stay stable across blockable operations.
*
* fork and exit paths explicitly call threadgroup_change_{begin|end}() for
* synchronization. While held, no new task will be added to threadgroup
* and no existing live task will have its PF_EXITING set.
*
* During exec, a task goes and puts its thread group through unusual
* changes. After de-threading, exclusive access is assumed to resources
* which are usually shared by tasks in the same group - e.g. sighand may
* be replaced with a new one. Also, the exec'ing task takes over group
* leader role including its pid. Exclude these changes while locked by
* grabbing cred_guard_mutex which is used to synchronize exec path.
*/
static inline void threadgroup_lock(struct task_struct *tsk)
{
/*
* exec uses exit for de-threading nesting group_rwsem inside
* cred_guard_mutex. Grab cred_guard_mutex first.
*/
mutex_lock(&tsk->signal->cred_guard_mutex);
down_write(&tsk->signal->group_rwsem);
}
/**
* threadgroup_unlock - unlock threadgroup
* @tsk: member task of the threadgroup to unlock
*
* Reverse threadgroup_lock().
*/
static inline void threadgroup_unlock(struct task_struct *tsk)
{
up_write(&tsk->signal->group_rwsem);
mutex_unlock(&tsk->signal->cred_guard_mutex);
}
#else
static inline void threadgroup_change_begin(struct task_struct *tsk) {}
static inline void threadgroup_change_end(struct task_struct *tsk) {}
static inline void threadgroup_lock(struct task_struct *tsk) {}
static inline void threadgroup_unlock(struct task_struct *tsk) {}
#endif
#ifndef __HAVE_THREAD_FUNCTIONS
#define task_thread_info(task) ((struct thread_info *)(task)->stack)
#define task_stack_page(task) ((task)->stack)
static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
{
*task_thread_info(p) = *task_thread_info(org);
task_thread_info(p)->task = p;
}
static inline unsigned long *end_of_stack(struct task_struct *p)
{
return (unsigned long *)(task_thread_info(p) + 1);
}
#endif
static inline int object_is_on_stack(void *obj)
{
void *stack = task_stack_page(current);
return (obj >= stack) && (obj < (stack + THREAD_SIZE));
}
extern void thread_info_cache_init(void);
#ifdef CONFIG_DEBUG_STACK_USAGE
static inline unsigned long stack_not_used(struct task_struct *p)
{
unsigned long *n = end_of_stack(p);
do { /* Skip over canary */
n++;
} while (!*n);
return (unsigned long)n - (unsigned long)end_of_stack(p);
}
#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));
}
static inline int restart_syscall(void)
{
set_tsk_thread_flag(current, TIF_SIGPENDING);
return -ERESTARTNOINTR;
}
static inline int signal_pending(struct task_struct *p)
{
return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
static inline int __fatal_signal_pending(struct task_struct *p)
{
return unlikely(sigismember(&p->pending.signal, SIGKILL));
}
static inline int fatal_signal_pending(struct task_struct *p)
{
return signal_pending(p) && __fatal_signal_pending(p);
}
static inline int signal_pending_state(long state, struct task_struct *p)
{
if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL)))
return 0;
if (!signal_pending(p))
return 0;
return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
}
static inline int need_resched(void)
{
return unlikely(test_thread_flag(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.
*/
extern int _cond_resched(void);
#define cond_resched() ({ \
__might_sleep(__FILE__, __LINE__, 0); \
_cond_resched(); \
})
extern int __cond_resched_lock(spinlock_t *lock);
#ifdef CONFIG_PREEMPT_COUNT
#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET
#else
#define PREEMPT_LOCK_OFFSET 0
#endif
#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(); \
})
/*
* 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
}
/*
* Thread group CPU time accounting.
*/
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
static inline void thread_group_cputime_init(struct signal_struct *sig)
{
raw_spin_lock_init(&sig->cputimer.lock);
}
/*
* Reevaluate whether the task has signals pending delivery.
* Wake the task if so.
* This is required every time the blocked sigset_t changes.
* callers must hold sighand->siglock.
*/
extern void recalc_sigpending_and_wake(struct task_struct *t);
extern void recalc_sigpending(void);
extern void signal_wake_up(struct task_struct *t, int resume_stopped);
/*
* 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)
{
return task_thread_info(p)->cpu;
}
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 */
extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
extern void normalize_rt_tasks(void);
#ifdef CONFIG_CGROUP_SCHED
extern struct task_group root_task_group;
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
extern void sched_move_task(struct task_struct *tsk);
#ifdef CONFIG_FAIR_GROUP_SCHED
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
extern unsigned long sched_group_shares(struct task_group *tg);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
extern int sched_group_set_rt_runtime(struct task_group *tg,
long rt_runtime_us);
extern long sched_group_rt_runtime(struct task_group *tg);
extern int sched_group_set_rt_period(struct task_group *tg,
long rt_period_us);
extern long sched_group_rt_period(struct task_group *tg);
extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
#endif
#endif
extern int task_can_switch_user(struct user_struct *up,
struct task_struct *tsk);
#ifdef CONFIG_TASK_XACCT
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
tsk->ioac.rchar += amt;
}
static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
tsk->ioac.wchar += amt;
}
static inline void inc_syscr(struct task_struct *tsk)
{
tsk->ioac.syscr++;
}
static inline void inc_syscw(struct task_struct *tsk)
{
tsk->ioac.syscw++;
}
#else
static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
{
}
static inline void add_wchar(struct task_struct *tsk, ssize_t amt)
{
}
static inline void inc_syscr(struct task_struct *tsk)
{
}
static inline void inc_syscw(struct task_struct *tsk)
{
}
#endif
#ifndef TASK_SIZE_OF
#define TASK_SIZE_OF(tsk) TASK_SIZE
#endif
#ifdef CONFIG_MM_OWNER
extern void mm_update_next_owner(struct mm_struct *mm);
extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
#else
static inline void mm_update_next_owner(struct mm_struct *mm)
{
}
static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
}
#endif /* CONFIG_MM_OWNER */
static inline unsigned long task_rlimit(const struct task_struct *tsk,
unsigned int limit)
{
return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_cur);
}
static inline unsigned long task_rlimit_max(const struct task_struct *tsk,
unsigned int limit)
{
return ACCESS_ONCE(tsk->signal->rlim[limit].rlim_max);
}
static inline unsigned long rlimit(unsigned int limit)
{
return task_rlimit(current, limit);
}
static inline unsigned long rlimit_max(unsigned int limit)
{
return task_rlimit_max(current, limit);
}
#endif /* __KERNEL__ */
#endif