02.进程原理与系统调用

1.进程

定义:（英语：process），是指计算机中已执行的程序。进程曾经是分时系统的基本运作单位。在面向进程设计的系统（如早期的UNIX，Linux 2.4及更早的版本）中，进程是程序的基本执行实体；在面向线程设计的系统（如当代多数操作系统、Linux 2.6及更新的版本）中，进程本身不是基本执行单位，而是线程的容器。

进程状态之间的转换

进程的四个要素:

• 有一段程序代其执行
• 有进程专用的系统堆栈空间
• 内核有task_struct数据结构
• 进程有独立的存储空间,有专门的用户空间

注意:如果缺少第四条,称之为"线程",如果完全没有用户空间,称为"内核线程",如果有共享空间,则称之为"线程空间";

2.进程描述符task_struct数据结构分析

//进程描述符
struct task_struct {
	//进程的状态: -1 就绪态 0:运行态 >0停止态
	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
	void *stack; //指向内核栈指针
	atomic_t usage; //有多少进程使用此结构
	unsigned int flags;	/* per process flags, defined below */ 	//标记
	unsigned int ptrace; //ptrace系统调用,实现断点调试,跟踪进程的运行

//条件编译多处理器
#ifdef CONFIG_SMP
	struct llist_node wake_entry;
	int on_cpu;
	unsigned int wakee_flips;
	unsigned long wakee_flip_decay_ts;
	struct task_struct *last_wakee;

	int wake_cpu;
#endif
	//运行队列和进程调试相关程序
	int on_rq;

	int prio, static_prio, normal_prio; //关于进程调试
	unsigned int rt_priority;  //优先级

	//关于进程
	const struct sched_class *sched_class;
	struct sched_entity se;
	struct sched_rt_entity rt;

	//结构体链表
#ifdef CONFIG_CGROUP_SCHED
	struct task_group *sched_task_group;
#endif
	struct sched_dl_entity dl;

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

#ifdef CONFIG_BLK_DEV_IO_TRACE
	unsigned int btrace_seq;
#endif
    
//块设备I/O层的跟踪工具
#ifdef CONFIG_BLK_DEV_IO_TRACE
	unsigned int btrace_seq;
#endif

	//进程调试策略相关的字段
	unsigned int policy;
	int nr_cpus_allowed;
	cpumask_t cpus_allowed;

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

#ifdef CONFIG_SCHED_INFO
	struct sched_info sched_info;
#endif

//进程架构链表
	struct list_head tasks;
#ifdef CONFIG_SMP
	struct plist_node pushable_tasks;
	struct rb_node pushable_dl_tasks;
#endif
    
	struct mm_struct *mm, *active_mm;
	//进程管理的地址空间,每个进程有着独立的地址空间4G,32位x86
	/* per-thread vma caching */
	u32 vmacache_seqnum;
	struct vm_area_struct *vmacache[VMACACHE_SIZE];
#if defined(SPLIT_RSS_COUNTING)
	struct task_rss_stat	rss_stat;
#endif

//进程状态参数
/* task state */
	int exit_state;
	int exit_code, exit_signal;
	//接受父进程终止时就会发出信号
	int pdeath_signal;  /*  The signal sent when the parent dies  */
	unsigned long jobctl;	/* JOBCTL_*, siglock protected */

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

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

	/* unserialized, strictly 'current' */
	unsigned in_execve:1; /* bit to tell LSMs we're in execve */
	unsigned in_iowait:1;
#ifdef CONFIG_MEMCG
	unsigned memcg_may_oom:1;
#endif
#ifdef CONFIG_MEMCG_KMEM
	unsigned memcg_kmem_skip_account:1;
#endif
#ifdef CONFIG_COMPAT_BRK
	unsigned brk_randomized:1;
#endif

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

	struct restart_block restart_block;


//进程pid,父进程tgid
	pid_t pid;
	pid_t tgid;
	//防止内核堆栈的溢出
#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)
	 */
	
	//初始化父进程
	struct task_struct __rcu *real_parent; /* real parent process */
	//终止接受进程
	struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
	/*
	 * children/sibling forms the list of my natural children
	 */
	//维护子进程链表
	struct list_head children;	/* list of my children */
	//兄弟进程链表
	struct list_head sibling;	/* linkage in my parent's children list */
	//线程组组长
	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.
	 */

	//系统调用 关于断开调试
	struct list_head ptraced;
	struct list_head ptrace_entry;

	/* PID/PID hash table linkage. */
	//PID/PID散列表的关系
	struct pid_link pids[PIDTYPE_MAX];
	struct list_head thread_group;
	struct list_head thread_node;
    
	//do_fork()函数
	struct completion *vfork_done;		/* for vfork() */
	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */

	//描述CPU时间的内容
	//utime 用户态下执行的时间
	//stime 内核态下的执行时间
	cputime_t utime, stime, utimescaled, stimescaled;
	cputime_t gtime;
	struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
	seqlock_t vtime_seqlock;
	unsigned long long vtime_snap;
	enum {
		VTIME_SLEEPING = 0,
		VTIME_USER,
		VTIME_SYS,
	} vtime_snap_whence;
#endif
	unsigned long nvcsw, nivcsw; /* context switch counts */
	u64 start_time;		/* monotonic time in nsec */
	u64 real_start_time;	/* boot based time in nsec */
/* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
	unsigned long min_flt, maj_flt;

	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) */
	char comm[TASK_COMM_LEN]; /* executable name excluding path
				     - access with [gs]et_task_comm (which lock
				       it with task_lock())
				     - initialized normally by setup_new_exec */
/* file system info */
	struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
/* ipc stuff */
	struct sysv_sem sysvsem;
	struct sysv_shm sysvshm;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
	unsigned long last_switch_count;
#endif
/* filesystem information */
	struct fs_struct *fs;
/* open file information */
	struct files_struct *files;
/* namespaces */
	struct nsproxy *nsproxy;
/* signal handlers */
	struct signal_struct *signal;
	struct sighand_struct *sighand;

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

	unsigned long sas_ss_sp;
	size_t sas_ss_size;

	struct callback_head *task_works;

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

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

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

	struct wake_q_node wake_q;

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

#ifdef CONFIG_DEBUG_MUTEXES
	/* mutex deadlock detection */
	struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
	unsigned int irq_events;
	unsigned long hardirq_enable_ip;
	unsigned long hardirq_disable_ip;
	unsigned int hardirq_enable_event;
	unsigned int hardirq_disable_event;
	int hardirqs_enabled;
	int hardirq_context;
	unsigned long softirq_disable_ip;
	unsigned long softirq_enable_ip;
	unsigned int softirq_disable_event;
	unsigned int softirq_enable_event;
	int softirqs_enabled;
	int softirq_context;
#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
	u64 curr_chain_key;
	int lockdep_depth;
	unsigned int lockdep_recursion;
	struct held_lock held_locks[MAX_LOCK_DEPTH];
	gfp_t lockdep_reclaim_gfp;
#endif
    
/* journalling filesystem info */
	
	void *journal_info;  //日志文件系统信息

/* stacked block device info */
	struct bio_list *bio_list;  //块设备链表

#ifdef CONFIG_BLOCK
/* stack plugging */
	struct blk_plug *plug; 
#endif

/* VM state */  //虚拟内存状态参数
	
	struct reclaim_state *reclaim_state; //虚拟内存状态,内存回收

	struct backing_dev_info *backing_dev_info; //存放块设备I/O流量信息

	struct io_context *io_context; //I/O调度器所用的信息

	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
//futex同步机制
#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
//内存检测工具Perfromance Event
#ifdef CONFIG_PERF_EVENTS
	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
	struct mutex perf_event_mutex;
	struct list_head perf_event_list;
#endif
#ifdef CONFIG_DEBUG_PREEMPT
	unsigned long preempt_disable_ip;
#endif
#ifdef CONFIG_NUMA
	struct mempolicy *mempolicy;	/* Protected by alloc_lock */
	short il_next;
	short pref_node_fork;
#endif
#ifdef CONFIG_NUMA_BALANCING
	int numa_scan_seq;
	unsigned int numa_scan_period;
	unsigned int numa_scan_period_max;
	int numa_preferred_nid;
	unsigned long numa_migrate_retry;
	u64 node_stamp;			/* migration stamp  */
	u64 last_task_numa_placement;
	u64 last_sum_exec_runtime;
	struct callback_head numa_work;

	struct list_head numa_entry;
	struct numa_group *numa_group;

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

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

	unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */

#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
	struct tlbflush_unmap_batch tlb_ubc;
#endif

	struct rcu_head rcu; //RCU链表

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

	struct page_frag task_frag;

//延迟计数
#ifdef	CONFIG_TASK_DELAY_ACCT
	struct task_delay_info *delays;
#endif

3.进程系统调用

4.写时复制

核心思想:只有不得不复制数据内容时才去复制内容

内核只为新生成的子进程创建虚拟空间结构,它们复制父进程的虚拟结构,但是不为这些段分配物理内存,他们共享父进程的物理空间,当父进程中有更改相应段的行为发生时,再为子进程相应的段分配物理空间.