Some
From include/linux/sched.h:
struct task_struct {
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
struct thread_info *thread_info;
atomic_t usage;
unsigned long flags; /* per processプロセス flags, defined below */
unsigned long ptrace;
int lock_depth; /* BKL lock depth */
#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
int oncpu;
#endif
#endif
int load_weight; /* for niceness load balancing purposes */
int prio, static_prio, normal_prio;
struct list_head run_list;
struct prio_array *array;
unsigned short ioprio;
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
unsigned long sleep_avg;
unsigned long long timestamp, last_ran;
unsigned long long sched_time; /* sched_clock time spent running */
enum sleep_type sleep_type;
unsigned long policy;
cpumask_t cpus_allowed;
unsigned int time_slice, first_time_slice;
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info sched_info;
#endif
struct list_head tasks;
/*
* ptrace_list/ptrace_children forms the list of my children
* that were stolen by a ptracer.
*/
struct list_head ptrace_children;
struct list_head ptrace_list;
struct mm_struct *mm, *active_mm;
/* task state */
struct linux_binfmt *binfmt;
long exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
/* ??? */
unsigned long personality;
unsigned did_exec:1;
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プロセス , youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->parent->pid)
*/
struct task_struct *real_parent; /* real parent processプロセス (when being debugged) */
struct task_struct *parent; /* parent processプロセス */
/*
* children/sibling forms the list of my children plus the
* tasks I'm ptracing.
*/
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 */
/* 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 */
unsigned long rt_priority;
cputime_t utime, stime;
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time;
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
unsigned long min_flt, maj_flt;
cputime_t it_prof_expires, it_virt_expires;
unsigned long long it_sched_expires;
struct list_head cpu_timers[3];
/* processプロセス credentials */
uid_t uid,euid,suid,fsuid;
gid_t gid,egid,sgid,fsgid;
struct group_info *group_info;
kernelカーネル _cap_t cap_effective, cap_inheritable, cap_permitted;
unsigned keep_capabilities:1;
struct user_struct *user;
#ifdef CONFIG_KEYS
struct key *request_key_auth; /* assumed request_key authority */
struct key *thread_keyring; /* keyring private to this thread */
unsigned char jit_keyring; /* default keyring to attach requested keys to */
#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;
int oomkilladj; /* OOM kill score adjustment (bit shift). */
char comm[TASK_COMM_LEN]; /* executable name excluding path
- access with [gs]et_task_comm (which lock
it with task_lock())
- initialized normally by flush_old_exec */
/* file system info */
int link_count, total_link_count;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
struct sysv_sem sysvsem;
#endif
/* CPU-specific state of this task */
struct thread_struct thread;
/* filesystem information情報 */
struct fs_struct *fs;
/* open file information情報 */
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; /* To be restored with TIF_RESTORE_SIGMASK */
struct sigpending pending;
unsigned long sas_ss_sp;
size_t sas_ss_size;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
void *security;
struct audit_context *audit_context;
seccomp_t seccomp;
/* Thread group tracking */
u32 parent_exec_id;
u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings */
spinlock_t alloc_lock;
/* Protection of the PI data structures: */
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;
int hardirqs_enabled;
unsigned long hardirq_enable_ip;
unsigned int hardirq_enable_event;
unsigned long hardirq_disable_ip;
unsigned int hardirq_disable_event;
int softirqs_enabled;
unsigned long softirq_disable_ip;
unsigned int softirq_disable_event;
unsigned long softirq_enable_ip;
unsigned int softirq_enable_event;
int hardirq_context;
int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 30UL
u64 curr_chain_key;
int lockdep_depth;
struct held_lock held_locks[MAX_LOCK_DEPTH];
unsigned int lockdep_recursion;
#endif
/* journalling filesystem info */
void *journal_info;
/* 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. */
/*
* current io wait handle: wait queue entry to use for io waits
* If this thread is processプロセス ing aio, this points at the waitqueue
* inside the currently handled kiocb. It may be NULL (i.e. default
* to a stack based synchronous wait) if its doing sync IO.
*/
wait_queue_t *io_wait;
/* i/o counters(bytes read/written, #syscalls */
u64 rchar, wchar, syscr, syscw;
#if defined(CONFIG_TASK_XACCT)
u64 acct_rss_mem1; /* accumulated rss usage */
u64 acct_vm_mem1; /* accumulated virtual memory仮そう記録 usage */
cputime_t acct_stimexpd;/* stime since last update */
#endif
#ifdef CONFIG_NUMA
struct mempolicy *mempolicy;
short il_next;
#endif
#ifdef CONFIG_CPUSETS
struct cpuset *cpuset;
nodemask_t mems_allowed;
int cpuset_mems_generation;
int cpuset_mem_spread_rotor;
#endif
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;
atomic_t fs_excl; /* holding fs exclusive resources */
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
};
fork() is used very frequently. Every time the user
requests execution of a program (via the shell), fork() is
called. The child
Most of the work in Linux is actually done in the
copy_
FromOtherkernelカーネル /fork.c: /* * Ok, this is the main fork-routine. * * It copies theprocessプロセス , and if successful kick-starts * it and waits for it to finish using the VM if required. */ long do_fork(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int __user *parent_tidptr, int __user *child_tidptr) { struct task_struct *p; int trace = 0; struct pid *pid = alloc_pid(); long nr; if (!pid) return -EAGAIN; nr = pid->nr; if (unlikely(current->ptrace)) { trace = fork_traceflag (clone_flags); if (trace) clone_flags |= CLONE_PTRACE; } p = copy_processプロセス (clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr, nr); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ if (!IS_ERR(p)) { struct completion vfork; if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); } if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) { /* * We'll start up with an immediate SIGSTOP. */ sigaddset(&p->pending.signal, SIGSTOP); set_tsk_thread_flag(p, TIF_SIGPENDING); } if (!(clone_flags & CLONE_STOPPED)) wake_up_new_task(p, clone_flags); else p->state = TASK_STOPPED; if (unlikely (trace)) { current->ptrace_message = nr; ptrace_notify ((trace << 8) | SIGTRAP); } if (clone_flags & CLONE_VFORK) { wait_for_completion(&vfork); if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) { current->ptrace_message = nr; ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP); } } } else { free_pid(pid); nr = PTR_ERR(p); } return nr; }
A
Threads can be implemented by the
The POSIX standard defines an API and semantics for threads.
Here is some
PTHREADS(7) Linux Programmer’s Manual PTHREADS(7)
名前
pthreads - POSIX スレッド
説明
POSIX.1 は、一般に POSIX スレッドや Pthreads として知られるスレッド・プ
ログラミングのインタフェース群 (関数、ヘッダファイル) を規定している 。
一 つのプロセスは複数のスレッドを持つことができ、全てのスレッドは同じプ
ログラムを実行する。これらのスレッドは同じ大域メモリ (データとヒープ 領
域) を共有するが、各スレッドは自分専用のスタック (自動変数) を持つ。
POSIX.1 はスレッド間でどのような属性を共有するかについても定めている (
つまり、これらの属性はスレッド単位ではなくプロセス全体で共通である):
- プロセス ID
- 親プロセス ID
- プロセスグループ ID とセッション ID
- 制御端末
- ユーザ ID とグループ ID
- オープンするファイルディスクリプタ
- レコードのロック (fcntl(3) 参照)
- シグナルの配置
- ファイルモード作成マスク (umask(2))
- カレント・ディレクトリ (chdir(2)) とルート・ディレクトリ (chroot(2))
- インターバル・タイマ (setitimer(2)) と POSIX タイマ (timer_create())
- nice 値 (setpriority(2))
- リソース制限 (setrlimit(2))
- CPU 時間 (times(2)) とリソース (getrusage(2)) の消費状況の計測
スタックについても、POSIX.1 はどのような属性が個々のスレッドで独立に 管
理されるかを規定している:
- スレッド ID pthread_t データ型)
- シグナルマスク (pthread_sigmask())
- errno 変数
- 代替シグナルスタック (sigaltstack(2))
- リ ア ル タイム・スケジューリングのポリシーと優先度 (sched_setsched-
uler(2) と sched_setparam(2))
以下の Linux 特有の機能もスレッド単位である:
- ケーパビリティ (capabilities(7) 参照)
- CPU affinity (親和度) (sched_setaffinity(2))
PTHREADS(7) Linux Programmer's Manual PTHREADS(7)
NAME
pthreads - POSIX threads
DESCRIPTION
POSIX.1 specifies a set of interfaces (function機能・関数 s, header files) for
threaded programming commonly known as POSIX threads, or Pthreads. A
single processプロセス can contain multiple threads, all of which are executing
the same program. These threads share the same global memory (data and
heap segments), but each thread has its own stack (automatic vari-
ables).
POSIX.1 also requires that threads share a range of other attributes
(i.e., these attributes are processプロセス -wide rather than per-thread):
- processプロセス ID
- parent processプロセス ID
- processプロセス group ID and session ID
- controlling terminal端末
- user and group IDs
- open file descriptors
- record locks (see fcntl(2))
- signal dispositions
- file mode creation mask (umask(2))
- current directory (chdir(2)) and root directory (chroot(2))
- interval timers (setitimer(2)) and POSIX timers (timer_create())
- nice value (setpriority(2))
- resource limits (setrlimit(2))
- measurements of the consumption of CPU time (times(2)) and resources
(getrusage(2))
As well as the stack, POSIX.1 specifies that various other attributes
are distinct for each thread, including:
- thread ID (the pthread_t data type)
- signal mask (pthread_sigmask())
- the errno variable
- alternate signal stack (sigaltstack(2))
- real-time scheduling policy and priority (sched_setscheduler(2) and
sched_setparam(2))
The following Linux-specific features are also per-thread:
- capabilities (see capabilities(7))
- CPU affinity (sched_setaffinity(2))
Working with threads is very much like writing code for
multitasking
A very useful modern innovation in Unix-style
最初に、POSIX.1-1990 に定義されているシグナルを示す。
シグナル 値 動作 コメント
------------------------------------------------------------------------
SIGHUP 1 Term 制御端末(controlling terminal端末 )のハングアッ
プ検出、または制御しているプロセスの死
SIGINT 2 Term キーボードからの割り込み (Interrupt割り込み )
SIGQUIT 3 Core キーボードによる中止 (Quit)
SIGILL 4 Core 不正な命令
SIGABRT 6 Core abort(3) からの中断 (Abort) シグナル
SIGFPE 8 Core 浮動小数点例外
SIGKILL 9 Term Kill シグナル
SIGSEGV 11 Core 不正なメモリ参照
SIGPIPE 13 Term パイプ破壊: 読み手の無いパイプへの書き出し
SIGALRM 14 Term alarm(2) からのタイマーシグナル
SIGTERM 15 Term 終了 (termination) シグナル
SIGUSR1 30,10,16 Term ユーザ定義シグナル 1
SIGUSR2 31,12,17 Term ユーザ定義シグナル 2
SIGCHLD 20,17,18 Ign 子プロセスの一旦停止 (stop) または終了
SIGCONT 19,18,25 Cont 一旦停止 (stop) からの再開
SIGSTOP 17,19,23 Stop プロセスの一旦停止 (stop)
SIGTSTP 18,20,24 Stop 端末 (tty) より入力された一旦停止 (stop)
SIGTTIN 21,21,26 Stop バックグランドプロセスの tty 入力
SIGTTOU 22,22,27 Stop バックグランドプロセスの tty 出力
シグナル SIGKILL と SIGSTOP はキャッチ、ブロック、無視できない。
次に、 POSIX.1-1990 標準にはないが、 SUSv2 と POSIX.1-2001 に記述されて
いるシグナルを示す。
シグナル 値 動作 コメント
-----------------------------------------------------------------
SIGBUS 10,7,10 Core バスエラー (不正なメモリアクセス)
SIGPOLL Term ポーリング可能なイベント (Sys V)。
SIGIOと同義
SIGPROF 27,27,29 Term profiling タイマの時間切れ
SIGSYS 12,-,12 Core ルーチンへの引数が不正 (SVr4)
SIGTRAP 5 Core トレース/ブレークポイント トラップ
SIGURG 16,23,21 Ign ソケットの緊急事態 (urgent condi-
tion) (4.2BSD)
SIGVTALRM 26,26,28 Term 仮想アラームクロック (4.2BSD)
SIGXCPU 24,24,30 Core CPU時間制限超過 (4.2BSD)
SIGXFSZ 25,25,31 Core ファイルサイズ制限の超過 (4.2BSD)
First the signals described in the original POSIX.1-1990 standard.
Signal Value Action Comment
-------------------------------------------------------------------------
SIGHUP 1 Term Hangup detected on controlling terminal端末
or death of controlling processプロセス
SIGINT 2 Term Interrupt割り込み from keyboard
SIGQUIT 3 Core Quit from keyboard
SIGILL 4 Core Illegal Instruction
SIGABRT 6 Core Abort signal from abort(3)
SIGFPE 8 Core Floating point exception
SIGKILL 9 Term Kill signal
SIGSEGV 11 Core Invalid memory reference
SIGPIPE 13 Term Broken pipe: write to pipe with no readers
SIGALRM 14 Term Timer signal from alarm(2)
SIGTERM 15 Term Termination signal
SIGUSR1 30,10,16 Term User-defined signal 1
SIGUSR2 31,12,17 Term User-defined signal 2
SIGCHLD 20,17,18 Ign Child stopped or terminated
SIGCONT 19,18,25 Cont Continue if stopped
SIGSTOP 17,19,23 Stop Stop processプロセス
SIGTSTP 18,20,24 Stop Stop typed at tty
SIGTTIN 21,21,26 Stop tty input for background processプロセス
SIGTTOU 22,22,27 Stop tty output for background processプロセス
The signals SIGKILL and SIGSTOP cannot be caught, blocked, or ignored.
Next the signals not in the POSIX.1-1990 standard but described in
SUSv2 and POSIX.1-2001.
Signal Value Action Comment
-------------------------------------------------------------------------
SIGBUS 10,7,10 Core Bus error (bad memory access)
SIGPOLL Term Pollable event (Sys V). Synonym of SIGIO
SIGPROF 27,27,29 Term Profiling timer expired
SIGSYS 12,-,12 Core Bad argument to routine (SVr4)
SIGTRAP 5 Core Trace/breakpoint trap
SIGURG 16,23,21 Ign Urgent condition on socket (4.2BSD)
SIGVTALRM 26,26,28 Term Virtual alarm clock (4.2BSD)
SIGXCPU 24,24,30 Core CPU time limit exceeded (4.2BSD)
SIGXFSZ 25,25,31 Core File size limit exceeded (4.2BSD)
第4回 5月13日 プロセス間通信
Lecture 4, May 13: Inter-
Readings for next week:
