struct task_struct{
#ifdef CONFIG_THREAD_INFO_IN_TASK
/*
* For reasons of header soup (see current_thread_info()), this
* must be the first element of task_struct.
*/
struct thread_info thread_info;
#endif
/* -1 unrunnable不可运行, 0 runnable可运行, >0 stopped已经停止: */
/* 进程状态TASK_RUNNING、TASK_INTERRUPTIBLE、TASK_UNINTERRUPTIBLE、TASK_STOPPED、TASK_TRACED */
volatile long state;
/*
* This begins the randomizable portion of task_struct. Only
* scheduling-critical items should be added above here.
*/
randomized_struct_fields_start
/* 进程内核栈。Linux内核通过thread_union联合体来表示进程的内核栈,其中THREAD_SIZE宏的大小为8192.通过
alloc_thread_info函数分配它的内核栈,通过free_thread_info函数释放所分配的内核栈 */
void *stack;
/*进程描述符的使用计数,被置为2时,表示进程描述符正在被使用而且其相应的进程处于活动状态 */
atomic_t usage;
/
/* Per task flags (PF_*), defined further below: */
/* 进程标志。进程当前的标志状态,但不是运行状态,用于内核识别进程当前的状态,以备下一步操作PF_FORKNOEXEC、PF_SUPERPRIV、PF_DUMPCORE */
unsigned int flags;
unsigned int ptrace;
#ifdef CONFIG_SMP
struct llist_node wake_entry;
/* 在SMP上帮助实现无加锁的进程切换 */
int on_cpu;
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* Current CPU: */
unsigned int cpu;
#endif
unsigned int wakee_flips;
unsigned long wakee_flip_decay_ts;
struct task_struct *last_wakee;
/*
* recent_used_cpu is initially set as the last CPU used by a task
* that wakes affine another task. Waker/wakee relationships can
* push tasks around a CPU where each wakeup moves to the next one.
* Tracking a recently used CPU allows a quick search for a recently
* used CPU that may be idle.
*/
int recent_used_cpu;
int wake_cpu;
#endif
int on_rq;
/* 表示动态优先级,根据static_prio和交互性奖罚算出 */
int prio;
/* 进程的静态优先级,在进程创建时确定,范围从-20到19,值越小,优先级越高 */
int static_prio;
/* 该优先级取决于静态优先级和调度策略 */
int normal_prio;
/* 用于保存实时优先级,范围是0到MAX_RT_PRIO-1(即99) */
unsigned int rt_priority;
/* 调度类 */
const struct sched_class *sched_class;
/* 普通进程的调用实体,每个进程都有其中之一的实体 */
struct sched_entity se;
/* 实时进程的调用实体,每个进程都有其中之一的实体 */
struct sched_rt_entity rt;
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
struct sched_dl_entity dl;
#ifdef CONFIG_PREEMPT_NOTIFIERS
/* List of struct preempt_notifier: */
/* preempt_notifiers结构体链表 */
struct hlist_head preempt_notifiers;
#endif
#ifdef CONFIG_BLK_DEV_IO_TRACE
/* blktrace是一个针对Linux内核中块设备IO层的跟踪工具 */
unsigned int btrace_seq;
#endif
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;
u8 rcu_tasks_holdout;
u8 rcu_tasks_idx;
int rcu_tasks_idle_cpu;
struct list_head rcu_tasks_holdout_list;
#endif /* #ifdef CONFIG_TASKS_RCU */
/* 用于调度器统计进程的运行信息 */
struct sched_info sched_info;
/* 用于构建进程链表 */
struct list_head tasks;
#ifdef CONFIG_SMP
struct plist_node pushable_tasks;
struct rb_node pushable_dl_tasks;
#endif
/* 进程所拥有的用户空间内存描述符,内核线程无的mm为NULL */
struct mm_struct *mm;
/* 指向进程运行时所使用的内存描述符,对于普通进程而言,这两个指针变量的值相同。但是内核线程kernel thread
是没有进程地址空间的,所以内核线程的tsk->mm域是空NULL。但是内核必须知道用户空间包含了什么,因此它的active_mm
成员被初始化为前一个运行进程的active_mm值*/
struct mm_struct *active_mm;
/* Per-thread vma caching: */
struct vmacache vmacache;
#ifdef SPLIT_RSS_COUNTING
struct task_rss_stat rss_stat;
#endif
int exit_state;
/* 用于设置进程的终止代号,这个值要么是_exit()或exit_group()系统调用参数(正常终止),要么是由内核提供的一个错误代号(异常终止) */
int exit_code;
/* 被设置为-1时表示是某个线程组中的一员。只有当线程组的最后一个成员终止时,才会产生一个信号,以通知线程组的领头进程的父进程 */
int exit_signal;
/* The signal sent when the parent dies: */
int pdeath_signal;
/* JOBCTL_*, siglock protected: */
unsigned long jobctl;
/* Used for emulating ABI behavior of previous Linux versions: */
/* 用于处理不同的ABI,参见linux-man */
unsigned int personality;
/* Scheduler bits, serialized by scheduler locks: */
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
unsigned sched_remote_wakeup:1;
/* Force alignment to the next boundary: */
unsigned :0;
/* Unserialized, strictly 'current' */
/* Bit to tell LSMs we're in execve(): */
/* 用于通知LSM是否被do_execve()函数所调用 */
unsigned in_execve:1;
/* 用于判断是否进行iowait计数 */
unsigned in_iowait:1;
#ifndef TIF_RESTORE_SIGMASK
unsigned restore_sigmask:1;
#endif
#ifdef CONFIG_MEMCG
unsigned in_user_fault:1;
#ifdef CONFIG_MEMCG_KMEM
unsigned memcg_kmem_skip_account:1;
#endif
#endif
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
#ifdef CONFIG_CGROUPS
/* disallow userland-initiated cgroup migration */
unsigned no_cgroup_migration:1;
#endif
#ifdef CONFIG_BLK_CGROUP
/* to be used once the psi infrastructure lands upstream. */
unsigned use_memdelay:1;
#endif
unsigned long atomic_flags; /* Flags requiring atomic access. */
struct restart_block restart_block;
/* 进程标识符,相当于每一个学生的学号一样,标识符唯一标识进程 */
pid_t pid;
/* P所在进程组的领头进程的PID */
pid_t tgid;
#ifdef CONFIG_STACKPROTECTOR
/* Canary value for the -fstack-protector GCC feature: */
/* 防止内核堆栈溢出 */
unsigned long stack_canary;
#endif
/*
* Pointers to the (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->real_parent->pid)
*/
/* Real parent process: */
/* 指向创建了P的进程的描述符,如果P的父进程不再存在,就指向进程1(init)的描述符(因此,如果用户运行一个后台进程而且退出了shell,后台进程就会成为init的子进程 */
struct task_struct __rcu *real_parent;
/* Recipient of SIGCHLD, wait4() reports: */
/* 指向P的当前父进程(这种进程的子进程终止时,必须向父进程发信号)。它的值通常与real_parent一致,但偶尔也可以不同,例如,当另一个进程发出监控P的ptrace()系统调用请求 */
struct task_struct __rcu *parent;
/*
* Children/sibling form the list of natural children:
*/
/* 链表的头部,链表中的所有元素都是P创建的子进程 */
struct list_head children;
/* 指向兄弟进程链表中的下一个元素或前一个元素的指针,这些兄弟进程的父进程都是P */
struct list_head sibling;
/* P所在进程组的领头进程的描述符指 */
struct task_struct *group_leader;
/*
* 'ptraced' is the list of tasks this task is using ptrace() on.
*
* This includes both natural children and PTRACE_ATTACH targets.
* 'ptrace_entry' is this task's link on the p->parent->ptraced list.
*/
/* ptrace系统调用。提供了一种父进程可以控制子进程运行并可检查和改变它的核心image。它主要用于实现断点调试。一个被
跟踪的进程运行中,直到发生一个信号,则进程被中止,并且通知其父进程。在进程中止的状态下,进程的内存空间可以被读写。父进程还可以
使子进程继续执行,并选择是否忽略引起中止的信号。成员ptrace被设置为0时表示不需要被跟踪 */
struct list_head ptraced;
/* 指向所跟踪进程其实际父进程链表的前一个和下一个元素(用于P被跟踪的时候)*/
struct list_head ptrace_entry;
/* PID/PID hash table linkage. */
struct pid *thread_pid;
struct hlist_node pid_links[PIDTYPE_MAX];
/* 线程组中所有进程的链表 */
struct list_head thread_group;
struct list_head thread_node;
/* 在执行do_fork()时,如果给定特别标志,则vfork_done会指向一个特殊地址 */
struct completion *vfork_done;
/* CLONE_CHILD_SETTID: */
/* 如果copy_process函数的clone_flags参数的值被置为CLONE_CHILD_SETTID或CLONE_CHILD_CLEARTID,则会把
child_tidptr参数的值分别复制到set_child_tid和clear_child_tid成员。这些标志说明必须改变子进程用户态地址空间的
child_tidptr所指向的变量的值*/
int __user *set_child_tid;
/* CLONE_CHILD_CLEARTID: */
int __user *clear_child_tid;
/* 用于记录进程在用户态下所经过的节拍数(定时器) */
u64 utime;
/* 用于记录进程在内核态下所经过的节拍数(定时器) */
u64 stime;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
/* 用于记录进程在用户态的运行时间,但它们以处理器的频率为刻度 */
u64 utimescaled;
/* 用于记录进程在内核态的运行时间,但它们以处理器的频率为刻度 */
u64 stimescaled;
#endif
/* 以节拍计数的虚拟机运行时间 */
u64 gtime;
/* 先前的运行时间 */
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
struct vtime vtime;
#endif
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#endif
/* Context switch counts: */
/* 自愿/非自愿上下文切换计数 */
unsigned long nvcsw;
unsigned long nivcsw;
/* Monotonic time in nsecs: 进程创建时间 */
u64 start_time;
/* Boot based time in nsecs: 进程创建时间,还包含了进程睡眠时间 */
u64 real_start_time;
/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
/* 缺页统计 */
unsigned long min_flt;
unsigned long maj_flt;
#ifdef CONFIG_POSIX_TIMERS
/* 用来统计进程或进程组被跟踪的处理器时间,其中的三个成员对应着cpu_timers[3]的三个链表 */
struct task_cputime cputime_expires;
struct list_head cpu_timers[3];
#endif
/* Process credentials: */
/* Tracer's credentials at attach: */
const struct cred __rcu *ptracer_cred;
/* Objective and real subjective task credentials (COW): */
const struct cred __rcu *real_cred;
/* Effective (overridable) subjective task credentials (COW): */
const struct cred __rcu *cred;
/* 相应的程序名
* executable name, excluding path.
*
* - normally initialized setup_new_exec()
* - access it with [gs]et_task_comm()
* - lock it with task_lock()
*/
char comm[TASK_COMM_LEN];
struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
struct sysv_sem sysvsem;
struct sysv_shm sysvshm;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
unsigned long last_switch_count;
unsigned long last_switch_time;
#endif
/* 用来表示进程与文件系统的联系,包括当前目录和根目录 Filesystem information: */
struct fs_struct *fs;
/* 表示进程当前打开的文件 Open file information: */
struct files_struct *files;
/* 命名空间 Namespaces: */
struct nsproxy *nsproxy;
/* Signal handlers: */
/* 指向进程的信号描述符的指针 */
struct signal_struct *signal;
/* 指向进程的信号处理程序描述符的指针 */
struct sighand_struct *sighand;
/* 被阻塞信号的掩码.也就是存放进程当前所屏蔽的信号 */
sigset_t blocked;
/* 被阻塞信号的临时掩码(由rt_sigtimedwait()系统调用使用) */
sigset_t real_blocked;
/* Restored if set_restore_sigmask() was used: */
sigset_t saved_sigmask;
/* 存放私有挂起信号的数据结构 */
struct sigpending pending;
/* 信号处理程序备用堆栈的地址 */
unsigned long sas_ss_sp;
/* 信号处理程序备用堆栈的大小 */
size_t sas_ss_size;
unsigned int sas_ss_flags;
struct callback_head *task_works;
struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
kuid_t loginuid;
unsigned int sessionid;/*会话领头进程的PID*/
#endif
struct seccomp seccomp;
/* Thread group tracking: */
u32 parent_exec_id;
u32 self_exec_id;
/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
/* 用于保护资源分配和释放的自旋锁 */
spinlock_t alloc_lock;
/* task_rq_lock函数所使用的锁 Protection of the PI data structures: */
raw_spinlock_t pi_lock;
struct wake_q_node wake_q;
/* 基于PI协议的等待互斥锁,其中PI指的是priority inheritance(优先级继承) */
#ifdef CONFIG_RT_MUTEXES
/* PI waiters blocked on a rt_mutex held by this task: */
struct rb_root_cached pi_waiters;
/* Updated under owner's pi_lock and rq lock */
struct task_struct *pi_top_task;
/* Deadlock detection and priority inheritance handling: */
struct rt_mutex_waiter *pi_blocked_on;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
/* 死锁检测 Mutex deadlock detection: */
struct mutex_waiter *blocked_on;
#endif
/* 中断 */
#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];
#endif
#ifdef CONFIG_UBSAN
unsigned int in_ubsan;
#endif
/* ISF文件系统 Journalling filesystem info: */
void *journal_info;
/* 块设备链表 Stacked block device info: */
struct bio_list *bio_list;
#ifdef CONFIG_BLOCK
/* Stack plugging: */
struct blk_plug *plug;
#endif
/* 内存回收 VM state: */
struct reclaim_state *reclaim_state;
/* 存放块设备IO数据流量信息 */
struct backing_dev_info *backing_dev_info;
/* IO调度器所使用的信息 */
struct io_context *io_context;
/* Ptrace state: */
unsigned long ptrace_message;
siginfo_t *last_siginfo;
struct task_io_accounting ioac;
#ifdef CONFIG_TASK_XACCT
/* Accumulated RSS usage: */
u64 acct_rss_mem1;
/* Accumulated virtual memory usage: */
u64 acct_vm_mem1;
/* stime + utime since last update: */
u64 acct_timexpd;
#endif
/* CPUSET功能 */
#ifdef CONFIG_CPUSETS
/* Protected by ->alloc_lock: */
nodemask_t mems_allowed;
/* Seqence number to catch updates: */
seqcount_t mems_allowed_seq;
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
/* Control Group info protected by css_set_lock: */
struct css_set __rcu *cgroups;
/* cg_list protected by css_set_lock and tsk->alloc_lock: */
struct list_head cg_list;
#endif
#ifdef CONFIG_INTEL_RDT
u32 closid;
u32 rmid;
#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
#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
/* 非一致内存访问Non-Uniform Memory Access */
#ifdef CONFIG_NUMA
/* Protected by alloc_lock: */
struct mempolicy *mempolicy;
short il_prev;
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;
/* Migration stamp: */
u64 node_stamp;
u64 last_task_numa_placement;
u64 last_sum_exec_runtime;
struct callback_head numa_work;
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_RSEQ
struct rseq __user *rseq;
u32 rseq_len;
u32 rseq_sig;
/*
* RmW on rseq_event_mask must be performed atomically
* with respect to preemption.
*/
unsigned long rseq_event_mask;
#endif
struct tlbflush_unmap_batch tlb_ubc;
/* RCU链表 */
struct rcu_head rcu;
/* 管道Cache last used pipe for splice(): */
struct pipe_inode_info *splice_pipe;
struct page_frag task_frag;
#ifdef CONFIG_TASK_DELAY_ACCT
/* 延迟计数 */
struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
unsigned int fail_nth;
#endif
/*
* When (nr_dirtied >= nr_dirtied_pause), it's time to call
* balance_dirty_pages() for a dirty throttling pause:
*/
int nr_dirtied;
int nr_dirtied_pause;
/* Start of a write-and-pause period: */
unsigned long dirty_paused_when;
#ifdef CONFIG_LATENCYTOP
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
#endif
/*
* Time slack values; these are used to round up poll() and
* select() etc timeout values. These are in nanoseconds.
*/
u64 timer_slack_ns;
u64 default_timer_slack_ns;
#ifdef CONFIG_KASAN
unsigned int kasan_depth;
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/* Index of current stored address in ret_stack: */
int curr_ret_stack;
/* Stack of return addresses for return function tracing: */
struct ftrace_ret_stack *ret_stack;
/* Timestamp 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 tracing: */
atomic_t tracing_graph_pause;
#endif
#ifdef CONFIG_TRACING
/* State flags for use by tracers: */
unsigned long trace;
/* Bitmask and counter of trace recursion: */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_KCOV
/* Coverage collection mode enabled for this task (0 if disabled): */
unsigned int kcov_mode;
/* Size of the kcov_area: */
unsigned int kcov_size;
/* Buffer for coverage collection: */
void *kcov_area;
/* KCOV descriptor wired with this task or NULL: */
struct kcov *kcov;
#endif
#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg_in_oom;
gfp_t memcg_oom_gfp_mask;
int memcg_oom_order;
/* Number of pages to reclaim on returning to userland: */
unsigned int memcg_nr_pages_over_high;
/* Used by memcontrol for targeted memcg charge: */
struct mem_cgroup *active_memcg;
#endif
#ifdef CONFIG_BLK_CGROUP
struct request_queue *throttle_queue;
#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
#endif
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
unsigned int sequential_io;
unsigned int sequential_io_avg;
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
unsigned long task_state_change;
#endif
int pagefault_disabled;
#ifdef CONFIG_MMU
struct task_struct *oom_reaper_list;
#endif
#ifdef CONFIG_VMAP_STACK
struct vm_struct *stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* A live task holds one reference: */
atomic_t stack_refcount;
#endif
#ifdef CONFIG_LIVEPATCH
int patch_state;
#endif
#ifdef CONFIG_SECURITY
/* Used by LSM modules for access restriction: */
void *security;
#endif
/*
* New fields for task_struct should be added above here, so that
* they are included in the randomized portion of task_struct.
*/
randomized_struct_fields_end
/* CPU-specific state of this task: */
struct thread_struct thread;
/*
* WARNING: on x86, 'thread_struct' contains a variable-sized
* structure. It *MUST* be at the end of 'task_struct'.
*
* Do not put anything below here!
*/
}