标签：another process hold cfs read ica tick 异常 numa
struct task_struct {
struct thread_info thread_info;
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped: */
void *stack; /* 堆指针 */
atomic_t usage; /* 进程描述符使用计数，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 */
unsigned int flags; /* Per task flags (PF_*), defined further below: */
unsigned int ptrace; /* ptrace系统调用，成员ptrace被设置为0时表示不需要被跟踪 */
/* SMP CPU: */
struct llist_node wake_entry;
int on_cpu; /* 在SMP上帮助实现无加锁的进程切换 */
unsigned int cpu;
/* end: */
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;
int prio, static_prio, normal_prio; /* prio: 调度器考虑的优先级保存在prio*/
/* static_prio: 用于保存进程的"静态优先级*/
/* normal_prio: 表示基于进程的"静态优先级"和"调度策略"计算出的优先级*/
unsigned int rt_priority; /* rt_priority:表示实时进程的优先级，需要明白的是，
"实时进程优先级"和"普通进程优先级"有两个独立的范畴，
实时进程即使是最低优先级也高于普通进程，最低的实时优先级为0，
最高的优先级为99，值越大，表明优先级越高*/
const struct sched_class *sched_class; /* sched_class: 该进程所属的调度类*/
struct sched_entity se;
struct sched_rt_entity rt; /* rt: 用于实时进程的调用实体 */
struct task_group *sched_task_group; /* 组调度*/
struct sched_dl_entity dl;
/* List of struct preempt_notifier: */
struct hlist_head preempt_notifiers;
unsigned int btrace_seq;
unsigned int policy; /* policy表示进程的调度策略 */
int nr_cpus_allowed;
cpumask_t cpus_allowed;
#ifdef CONFIG_PREEMPT_RCU /* RCU同步原语 */
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 */
struct sched_info sched_info; /* sched_info：用于调度器统计进程的运行信息*/
struct list_head tasks; /* 通过list_head将当前进程的task_struct串联进内核的进程列表中，
构建；linux进程链表*/
struct plist_node pushable_tasks; / * limit pushing to one attempt */
struct rb_node pushable_dl_tasks;
struct mm_struct *mm; /* mm: 指向进程所拥有的内存描述符*/
struct mm_struct *active_mm; /* active_mm: active_mm指向进程运行时所使用的内存描述符*/
/* Per-thread vma caching: */
struct vmacache vmacache;
#ifdef SPLIT_RSS_COUNTING
struct task_rss_stat rss_stat;
#endif
int exit_state; /* 进程退出状态码*/
int exit_code; /* exit_code ：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_signal; /* exit_signal被置为-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 pdeath_signal; /* pdeath_signal用于判断父进程终止时发送信号 */
/* JOBCTL_*, siglock protected: */
unsigned long jobctl;
unsigned int personality; /* Used for emulating ABI behavior
of previous Linux versions: */
/* personality用于处理不同的ABI */
/* 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;
#ifdef CONFIG_PSI
unsigned sched_psi_wake_requeue:1;
#endif
/* Force alignment to the next boundary: */
unsigned :0;
/* Unserialized, strictly 'current' */
/* in_execve用于通知LSM是否被do_execve()函数所调用 */
unsigned in_execve:1;
unsigned in_iowait:1; /* in_iowait用于判断是否进行iowait计数 */
#ifndef TIF_RESTORE_SIGMASK
unsigned restore_sigmask:1;
#endif
unsigned in_user_fault:1;
#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;
pid_t pid;
pid_t tgid;
进程标识符(PID)
在CONFIG_BASE_SMALL配置为0的情况下，PID的取值范围是0到32767，即系统中的进程数最大为32768个
#define PID_MAX_DEFAULT (CONFIG_BASE_SMALL ? 0x1000 : 0x8000)
在Linux系统中，一个线程组中的所有线程使用和该线程组的领头线程
(该组中的第一个轻量级进程)相同的PID，并被存放在tgid成员中。
只有线程组的领头线程的pid成员才会被设置为与tgid相同的值。
注意，getpid()系统调用返回的是当前进程的tgid值而不是pid值
/* 防止内核堆栈溢出，在GCC编译内核时，需要加上-fstack-protector选项 */
unsigned long stack_canary;
/*
* Pointers to the (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->real_parent->pid)
*/
/* 表示进程亲属关系的成员*/
struct task_struct __rcu *real_parent; /* 指向其父进程，如果创建它的父进程不再存在，则指向PID为1的init进程 */
/* Recipient of SIGCHLD, wait4() reports: */
struct task_struct __rcu *parent; /* parent: 指向其父进程，当它终止时，必须向它的父进程发送信号。
它的值通常与real_parent相同*/
/*
* Children/sibling form the list of natural children:
*/
struct list_head children; /* children: 表示链表的头部，链表中的所有元素都是它的子进程(子进程链表)*/
struct list_head sibling; /* sibling: 用于把当前进程插入到兄弟链表中(连接到父进程的子进程链表(兄弟链表)*/
struct task_struct *group_leader; /* group_leader: 指向其所在进程组的领头进程*/
/*
* '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.
*/
struct list_head ptraced;
struct list_head ptrace_entry;
/* PID/PID hash table linkage. */
struct pid *thread_pid;
struct hlist_node pid_links[PIDTYPE_MAX]; /* PID散列表和链表*/
struct list_head thread_group; /* 线程组中所有进程的链表*/
struct list_head thread_node;
/* do_fork函数*/
struct completion *vfork_done; /* 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*/
/* CLONE_CHILD_SETTID: */
int __user *set_child_tid;
/* CLONE_CHILD_CLEARTID: */
int __user *clear_child_tid;
/* 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*/
u64 utime;
u64 stime;
u64 utimescaled;
u64 stimescaled;
/* 1) utime
用于记录进程在"用户态"下所经过的节拍数(定时器)
2) stime
用于记录进程在"内核态"下所经过的节拍数(定时器)
3) utimescaled
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
4) stimescaled
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 gtime; /* 以节拍计数的虚拟机运行时间(guest time)*/
struct prev_cputime prev_cputime; /* prev_utime、prev_stime是先前的运行时间*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
struct vtime vtime;
#endif
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#endif
/* Context switch counts: */
unsigned long nvcsw; /* 自愿(voluntary)上下文切换计数*/
unsigned long nivcsw; /* 非自愿(involuntary)上下文切换计数*/
/* Monotonic time in nsecs: */
u64 start_time; /* 进程创建时间*/
/* Boot based time in nsecs: */
u64 real_start_time; /* 进程睡眠时间，还包含了进程睡眠时间，常用于/proc/pid/stat*/
/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
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;
/*
* 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 /* 进程通信(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
/* Filesystem information: */
struct fs_struct *fs; /* 用来表示进程与文件系统的联系，包括当前目录和根目录*/
/* Open file information: */
struct files_struct *files; /* 表示进程当前打开的文件*/
/* 命名空间 : */ /* 进程通信(SYSVIPC)*/
struct nsproxy *nsproxy;
/* Signal handlers: */
struct signal_struct *signal; /* signal: 指向进程的信号描述符*/
struct sighand_struct *sighand; /* sighand: 指向进程的信号处理程序描述符*/
sigset_t blocked; /* 表示被阻塞信号的掩码*/
sigset_t real_blocked; /* 表示临时掩码*/
/* Restored if set_restore_sigmask() was used: */
sigset_t saved_sigmask;
struct sigpending pending; /* 存放私有挂起信号的数据结构*/
unsigned long sas_ss_sp; /* 信号处理程序备用堆栈的地址*/
size_t sas_ss_size; /* 表示堆栈的大小*/
unsigned int sas_ss_flags;
struct callback_head *task_works;
/* 进程审计 */
struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
kuid_t loginuid;
unsigned int sessionid;
#endif
struct seccomp seccomp; /* secure computing*/
/* Thread group tracking: */ /* 用于copy_process函数使用CLONE_PARENT标记时 */
u32 parent_exec_id;
u32 self_exec_id;
/* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */
spinlock_t alloc_lock; /* 用于保护资源分配或释放的自旋锁*/
/* Protection of the PI data structures: */
raw_spinlock_t pi_lock; * task_rq_lock函数所使用的锁*/
struct wake_q_node wake_q;
#ifdef CONFIG_RT_MUTEXES /* 基于PI协议的等待互斥锁，其中PI指的是priority inheritance/9优先级继承)*/
/* 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
/* Mutex deadlock detection: */
struct mutex_waiter *blocked_on; /* 死锁检测*/
#endif
#ifdef CONFIG_TRACE_IRQFLAGS /* 中断*/
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 /* lockdep*/
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
/* Journalling filesystem info: JFS文件系统 */
void *journal_info;
/* Stacked block device info: 块设备链表*/
struct bio_list *bio_list;
#ifdef CONFIG_BLOCK
/* Stack plugging: */
struct blk_plug *plug;
#endif
/* VM state:内存回收 */
struct reclaim_state *reclaim_state;
/* 存放块设备I/O数据流量信息*/
struct backing_dev_info *backing_dev_info;
/* I/O调度器所使用的信息 */
struct io_context *io_context;
/* Ptrace state: */
unsigned long ptrace_message;
kernel_siginfo_t *last_siginfo;
struct task_io_accounting ioac;
#ifdef CONFIG_PSI
/* Pressure stall state */
unsigned int psi_flags;
#endif
#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
#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_X86_CPU_RESCTRL
u32 closid;
u32 rmid;
#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_DEBUG_PREEMPT
unsigned long preempt_disable_ip;
#endif
#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;
struct rcu_head rcu;
/* Cache last used pipe for splice():管道 */
struct pipe_inode_info *splice_pipe;
struct page_frag task_frag;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays; /* 延迟计数*/
#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.
* time slack values，常用于poll和select函数
*/
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;
int curr_ret_depth;
/* Stack of return addresses for return function tracing:ftrace跟踪器 */
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
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
unsigned long lowest_stack;
unsigned long prev_lowest_stack;
#endif
randomized_struct_fields_start /*M 随机分布,可以提高系统安全,防止黑客入侵 */
randomized_struct_fields_end
/* CPU-specific state of this task: Do not put anything below here! */
struct thread_struct thread;
};
sched_class: 该进程所属的调度类，目前内核中有实现以下四种：
1) static const struct sched_class fair_sched_class;
2) static const struct sched_class rt_sched_class;
3) static const struct sched_class idle_sched_class;
4) static const struct sched_class stop_sched_class;
policy
policy表示进程的调度策略，目前主要有以下五种：
1) #define SCHED_NORMAL 0: 用于普通进程，它们通过完全公平调度器来处理
2) #define SCHED_FIFO 1: 先来先服务调度，由实时调度类处理
3) #define SCHED_RR 2: 时间片轮转调度，由实时调度类处理
4) #define SCHED_BATCH 3: 用于非交互、CPU使用密集的批处理进程，通过完全公平调度器来处理，调度决策对此类进程给与"冷处理"，它们绝不会抢占CFS调度器处理的另一个进程，因此不会干扰交互式进程，如果不打算用nice降低进程的静态优先级，同时又不希望该进程影响系统的交互性，最适合用该调度策略
5) #define SCHED_IDLE 5: 可用于次要的进程，其相对权重总是最小的，也通过完全公平调度器来处理。要注意的是，SCHED_IDLE不负责调度空闲进程，空闲进程由内核提供单独的机制来处理
只有root用户能通过sched_setscheduler()系统调用来改变调度策略
*/
标签：another process hold cfs read ica tick 异常 numa
原文地址：https://www.cnblogs.com/DemonMaster/p/11783530.html
