Linux进程与线程的内核实现

进程描述符task_struct

  • 进程描述符(struct task_struct)
  • pid与tgid
  • 进程id编号分配规则
  • 内存管理mm_struct
  • 进程与文件,文件系统

进程,线程创建的本质

  • clone函数原型
  • 线程创建的实现
  • 进程创建的实现

总结

进程描述符task_struct

进程描述符(struct task_struct)

task_struct称为进程描述符结构,该结构定义在<include/linux/sched.h>文件中。进程描述符中包含一个具体进程的所有信息
进程描述符中包含的数据能完整地描述一个正在执行的程序:它打开的文件,进程的地址空间,挂起的信号,进程的状态等

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_SMPstruct llist_node wake_entry;int on_cpu;
#endifint on_rq;int prio, static_prio, normal_prio;unsigned int rt_priority;const struct sched_class *sched_class;struct sched_entity se;struct sched_rt_entity rt;
#ifdef CONFIG_CGROUP_SCHEDstruct task_group *sched_task_group;
#endif#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_TRACEunsigned int btrace_seq;
#endifunsigned int policy;cpumask_t cpus_allowed;#ifdef CONFIG_PREEMPT_RCUint rcu_read_lock_nesting;char rcu_read_unlock_special;struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TREE_PREEMPT_RCUstruct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#ifdef CONFIG_RCU_BOOSTstruct rt_mutex *rcu_boost_mutex;
#endif /* #ifdef CONFIG_RCU_BOOST */#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)struct sched_info sched_info;
#endifstruct list_head tasks;
#ifdef CONFIG_SMPstruct plist_node pushable_tasks;
#endifstruct mm_struct *mm, *active_mm;
#ifdef CONFIG_COMPAT_BRKunsigned 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;/* 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;
#endifpid_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_ACCOUNTINGcputime_t prev_utime, prev_stime;
#endifunsigned 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 lockit 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_AUDITSYSCALLuid_t loginuid;unsigned int sessionid;
#endifseccomp_t 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_IRQFLAGSunsigned 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 48ULu64 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_CPUSETSnodemask_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_FUTEXstruct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPATstruct compat_robust_list_head __user *compat_robust_list;
#endifstruct list_head pi_state_list;struct futex_pi_state *pi_state_cache;
#endif
#ifdef CONFIG_PERF_EVENTSstruct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];struct mutex perf_event_mutex;struct list_head perf_event_list;
#endif
#ifdef CONFIG_NUMAstruct mempolicy *mempolicy;	/* Protected by alloc_lock */short il_next;short pref_node_fork;
#endifstruct rcu_head rcu;/** cache last used pipe for splice*/struct pipe_inode_info *splice_pipe;
#ifdef	CONFIG_TASK_DELAY_ACCTstruct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTIONint 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_LATENCYTOPint 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_BREAKPOINTatomic_t ptrace_bp_refcnt;
#endif
};

pid与tgid

image-20231022134040327

tgid全名thread group ID,一个内部有多线程的进程,进程中每个线程的id都不一样,但是对外表现出同一个进程整体

struct task_struct{pid_t pid;//进程的唯一标识pid_t tgid;// 线程组的领头线程的pid成员的值
};

进程id编号分配规则

Linux 内核限制进程号需小于等于 32767。新进程创建时,内核会按顺序将下一个可用的进程号分配给其使用。每当进程号达到 32767 的限制时,内核将重置进程号计数器,以便从小整数开始分配。

一旦进程号达到 32767,会将进程号计数器重置为 300,而不是 1。之所以如此,是因为低数值的进程号为系统进程和守护进程所长期占用,在此范围内搜索尚未使用的进程号只会是浪费时间。

内存管理mm_struct

struct task_struct{struct mm_struct* mm;
}

每个进程都有自己独立的虚拟地址空间,使用mm_struct结构体来管理内存,这里的mm指针指向了mm_struct结构体,包含了内存资源的页表,内存映射等

 struct mm_struct{struct vm_area_struct* mmap;struct re_root mm_rb;//...pgd_t* pgd;  }

进程与文件,文件系统

task_struct与文件相关的字段最常用的下面这两个

struct task_struct{//文件系统的信息的指针,包含了进程运行的目录信息struct fs_struct* fs;//打开的文件描述符资源表struct files_struct* files;
}

进程,线程创建的本质

fork()和pthread_create()函数最后都会进入clone()系统调用

image-20231022135531221.png

clone函数原型

  • fn:表示clone生成的子进程的起始调用函数,参数由第四个参数arg指定
  • stack:表示生成的子进程的栈空间
  • flags:关键参数,用于区分生成的子进程与父进程如何共享资源(内存,打开文件描述符等)
  • 剩下的参数与线程实现有关
int clone(int (*fn)(void *), void *stack, int flags, void *arg, .../* pid_t *parent_tid, void *tls, pid_t *child_tid */ );

线程创建的实现pthread_create()

#include <fcntl.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <pthread.h>void* run(void* arg){}int main()
{pthread_t t1;pthread_create(&t1, 0, &run, 0);pthread_join(t1, 0);return 0;
}

此时clone系统调用的flags=CLONE_VM | CLONE_FS | CLONE_FILES | CLONE_SIGHAND | CLONE_THREAD | …

标志含义
CLONE_VM共享虚拟内存
CLONE_FS共享文件与系统相关的属性
CLONE_FILES共享打开的文件描述符
CLONE_SIGHAND共享对信号的处置
CLONE_THREAD置于父进程所属的线程组中

进程创建的实现fork()

#include <sys/wait.h>
#include <unistd.h>int main()
{pid_t pid;pid = fork();if(pid == 0){//此处是子进程的代码分支}else if(pid > 0){//此处是父进程的代码分支}return 0;
}

此时clone系统调用的flags=CLONE_SIGCHLD | …

本质:不共享资源,使用cow,任何一个修改都会造成分裂

标志含义
CLONE_SIGCHLD接收子进程退出的信号

总结

  • fork()和pthread_create()创建进程或者线程都会调用clone()系统调用
  • pthread_create()调用clone()时传入的flags参数会设置共享虚拟内存,共享文件与系统相关的属性,共享打开的文件描述符,共享对信号的处置,置于父进程所属的线程组中
  • fork()调用clone()时传入的flags参数只会设置接收子进程退出的信号
  • 在内核态中没有进程和线程的概念,内核不会区分进程和线程的操作

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:http://www.rhkb.cn/news/166916.html

如若内容造成侵权/违法违规/事实不符,请联系长河编程网进行投诉反馈email:809451989@qq.com,一经查实,立即删除!

相关文章

YOLOv5算法改进(19)— 手把手教你去更换NMS(DIoU-NMS/CIoU-NMS/EIoU-NMS/GIoU-NMS/SIoU-NMS)

前言:Hello大家好,我是小哥谈。YOLOv5中的NMS指非极大值抑制(Non-Maximum Suppression),它是一种用于目标检测算法中的后处理技术。在检测到多个重叠的边界框时,NMS可以帮助选择最佳的边界框。NMS的工作原理是首先根据预测边界框的置信度对它们进行排序,然后从置信度最高…

clion本地调试nginx-1.22.1

1 概述 nginx是一个多进程模型的流量代理软件&#xff0c;在本地调试时需要将它设置为单进程模式。 2 下载nginx源码 mkdir -p /opt/third-party cd /opt/third-party wget http://nginx.org/download/nginx-1.22.1.tar.gz tar xf nginx-1.22.1.tar.gz ls /opt/third-party…

SLAM中相机姿态估计算法推导基础数学总结

相机模型 基本模型 内参 外参 对极几何 对极约束 外积符号 基础矩阵F和本质矩阵E 相机姿态估计问题分为如下两步: 本质矩阵 E t ∧ R Et^{\wedge}R Et∧R因为 t ∧ t^{\wedge} t∧其实就是个3x3的反对称矩阵&#xff0c;所以 E E E也是一个3x3的矩阵 用八点法估计E…

JVM第十六讲:调试排错 - Java 线程分析之线程Dump分析

调试排错 - Java 线程分析之线程Dump分析 本文是JVM第十六讲&#xff0c;Java 线程分析之线程Dump分析。Thread Dump是非常有用的诊断Java应用问题的工具。 文章目录 调试排错 - Java 线程分析之线程Dump分析1、Thread Dump介绍1.1、什么是Thread Dump1.2、Thread Dump特点1.3、…

算法通过村第十六关-滑动窗口|青铜笔记|滑动很简单

文章目录 前言滑动窗口的基本思想入门题目练习子数组最大平均数最长连续递增序列 总结 前言 提示&#xff1a;我宁愿做自己&#xff0c;做卑微的自己&#xff0c;也不愿做别人&#xff0c;无论那会多么快乐。 --《美丽新世界》 我们在数组和链表的部分就已经接触到了双指针的思…

实现vue项目和springboot项目前后端数据交互

1、安装node.js 太高版本的win7不支持 这里安装node-v12.16.2-x64.msi&#xff0c;指定安装位置后直接按下一步就可以。npm是node内置的工具 这里配置npm的镜像cnpm&#xff08;提高下载速度&#xff0c;以后用到npm的命令都可以用cnpm命令替换&#xff09;不指定cnpm版本使用…

【USMA】N1CTF2022-praymoon

前言 本题主要利用 USMA 解题&#xff0c;当然还有其他做法&#xff0c;暂时不表 程序分析 启动脚本就不看了&#xff0c;该开的保护都开了。看下文件系统初始化脚本&#xff1a; #!/bin/shmkdir /tmp mount -t proc none /proc mount -t sysfs none /sys mount -t devtmpf…

JS加密/解密之闭包的运用

深入探讨JavaScript闭包的演变与应用 摘要&#xff1a; 本文将深入探讨JavaScript闭包的概念、特性以及其在实际开发中的应用。我们将从闭包的起源开始&#xff0c;探讨它在JavaScript编程中的重要性&#xff0c;并通过实例展示闭包在不同场景下的灵活应用。 引言 JavaScrip…

CSS3 渐变

CSS3 渐变可以让你在两个或多个指定的颜色之间显示平稳的过渡。 CSS3渐变有两种类型&#xff1a;线性渐变&#xff08;Linear Gradients&#xff09;和径向渐变&#xff08;Radial Gradients&#xff09;。 线性渐变&#xff08;Linear Gradients&#xff09;&#xff1a; 线性…

点击查看详情 | 网页版微信客户管理系统如何操作试用?

微信作为我们日常生活中最常用的社交应用之一&#xff0c;早已成为我们与朋友、家人和同事保持联系的重要工具&#xff0c;也是营销引流的重要平台。 通过微信营销&#xff0c;可以比较精准定向亲近用户。而微信的功能并没有很能满足做微信营销的人群&#xff0c;所以我们需要借…

linux复习笔记02(小滴课堂)

linux下输入输出错误重定向&#xff1a; 输入重定向&#xff1a;< 一个大于号是进行了覆盖。 两个大于号是追加。 输出重定向可以用于以后日志打印。 错误重定向&#xff1a; 错误重定向是不把信息打印到屏幕上而是打印到指定文件中去&#xff1a; 输出重定向其实是用的1…

基于TCP的RPC服务

TCP服务器上的RPC&#xff0c;通过创建一个服务器进程监听传入的tcp连接&#xff0c;并允许用户 通过此TCP流执行RPC命令 -module(tr_server). -author("chen"). -behaviour(gen_server).%% API -export([start_link/1,start_link/0,get_count/0,stop/0 ]).-export(…

Android问题笔记 - 关于SuperNotCalledException报错异常信息的解决方案

点击跳转>Unity3D特效百例点击跳转>案例项目实战源码点击跳转>游戏脚本-辅助自动化点击跳转>Android控件全解手册点击跳转>Scratch编程案例点击跳转>软考全系列 &#x1f449;关于作者 专注于Android/Unity和各种游戏开发技巧&#xff0c;以及各种资源分享&…

屏幕录像推荐:Apeaksoft Screen Recorder 中文 for mac

Apeaksoft Screen Recorder 是一款功能强大的屏幕录制软件&#xff0c;它允许用户在 Windows 和 Mac 系统上捕捉和录制屏幕活动。无论是记录游戏过程、创建教学视频、制作演示文稿还是捕捉在线流媒体内容&#xff0c;该软件都提供了丰富的功能和工具。 以下是 Apeaksoft Scree…

【c++Leetcode】141. Linked List Cycle

问题入口 思想&#xff1a;Floyds Tortoise and Hare 这个算法简单来说就是设置一个慢指针&#xff08;一次移动一个位置&#xff09;和一个快指针&#xff08;一次移动两个位置&#xff09;。在遍历过程中&#xff0c;如果慢指针和快指针都指向同一个元素&#xff0c;证明环…

JAVA基础-String StringBuffer 和 StringBuilder 类(9)

目录 String创建字符串字符串长度连接字符串创建格式化字符串String 方法 **StringBuilder**StringBuffer String 创建字符串 String s1 "Runoob"; // String 直接创建 String s2 "Runoob"; // String 直接创建 String s3 s…

C语言实现模拟 strcmp 字符串比较函数,实现字符串大小的比较

完整代码&#xff1a; // 模拟 strcmp 字符串比较函数&#xff0c;实现字符串大小的比较 #include<stdio.h> //strcmp函数是两个字符串自左向右逐个字符相比&#xff08;按 ASCII 值大小相比较&#xff09;&#xff0c;直到出现不同的字符或遇 \0 为止&#xff0c;如果字…

【RNA folding】RNA折叠算法与生物物理约束

文章目录 RNA折叠RNA folding representation1 DP for simple folds1.1 Nussinov Algorithm objective1.2 energy constraints1.3 The key idea of the algorithm 2 DP for stacking and complex foldsStochastic context free grammars 来自Manolis Kellis教授&#xff08;MIT…

进制转换(二进制、八进制、十进制、十六进制)

目录 一&#xff1a;十进制转换为二进制、八进制、十六进制 &#xff08;1&#xff09;整数转换 &#xff08;2&#xff09;小数转换 1&#xff09;十进制转二进制 2&#xff09;十进制转八进制 3&#xff09;十进制转十六进制 二&#xff1a;二进制、八进制、十六进制转…

安装Sentinel

大家好今天来安装Sentinel . 安装Sentinel 下载 : 大家可以选择相应版本(最新版本1.8.6) 官网下载地址 : Release v1.8.6 alibaba/Sentinel GitHub 链接&#xff1a;Sentinel_免费高速下载|百度网盘-分享无限制 (baidu.com) 提取码&#xff1a;8eh9 运行 : 将jar包放到任…