Linux进程数据结构
文章目录
- 前言
- 一、task_struct的定义
- 二、 解析task_struct
-
- 1.任务ID
- 2.信号处理
- 3.任务状态
- 4.进程调度
- 总结
前言
进程是处于执行期的程序以及它所管理的资源（如打开的文件、挂起的信号、进程状态、地址空间等等）的总称。注意，程序并不是进程，实际上两个或多个进程不仅有可能执行同一程序，而且还有可能共享地址空间等资源。
Linux 里面，无论是进程，还是线程，到了内核里面，我们统一都叫任务（Task），由一个统一的结构 task_struct 进行管理。
一、task_struct的定义
task_struct的定义位于内核代码：include/linux/sched.h文件中。
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
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_SMP
struct llist_node wake_entry;
int on_cpu;
#ifdef CONFIG_THREAD_INFO_IN_TASK
unsigned int cpu; /* current CPU */
#endif
unsigned int wakee_flips;
unsigned long wakee_flip_decay_ts;
struct task_struct *last_wakee;
int wake_cpu;
#endif
int 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_SCHED_WALT
struct ravg ravg;
/*
* 'init_load_pct' represents the initial task load assigned to children
* of this task
*/
u32 init_load_pct;
u64 last_sleep_ts;
#endif
#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
unsigned int policy;
int nr_cpus_allowed;
cpumask_t cpus_allowed;
#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
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;
/* per-thread vma caching */
u64 vmacache_seqnum;
struct vm_area_struct *vmacache[VMACACHE_SIZE];
#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 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 sched_remote_wakeup:1;
#ifdef CONFIG_PSI
unsigned sched_psi_wake_requeue:1;
#endif
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;
#if !defined(TIF_RESTORE_SIGMASK)
unsigned restore_sigmask:1;
#endif
#ifdef CONFIG_MEMCG
unsigned memcg_may_oom:1;
#ifndef CONFIG_SLOB
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
unsigned long atomic_flags; /* Flags needing atomic access. */
struct restart_block restart_block;
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, 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 list_head thread_node;
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;
#ifdef CONFIG_CPU_FREQ_TIMES
u64 *time_in_state;
unsigned int max_state;
#endif
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
seqcount_t vtime_seqcount;
unsigned long long vtime_snap;
enum {
/* Task is sleeping or running in a CPU with VTIME inactive */
VTIME_INACTIVE = 0,
/* Task runs in userspace in a CPU with VTIME active */
VTIME_USER,
/* Task runs in kernelspace in a CPU with VTIME active */
VTIME_SYS,
} vtime_snap_whence;
#endif
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#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 *ptracer_cred; /* Tracer's credentials at attach */
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;
unsigned sas_ss_flags;
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
#ifdef CONFIG_UBSAN
unsigned int in_ubsan;
#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;
#ifdef CONFIG_PSI
/* Pressure stall state */
unsigned int psi_flags;
#endif
#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
#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
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;
/*
* cache last used pipe for splice
*/
struct pipe_inode_info *splice_pipe;
struct page_frag task_frag;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
int 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_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;
/* 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_KCOV
/* Coverage collection mode enabled for this task (0 if disabled). */
enum kcov_mode kcov_mode;
/* Size of the kcov_area. */
unsigned kcov_size;
/* Buffer for coverage collection. */
void *kcov_area;
/* kcov desciptor 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;
#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
/* 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!
*/
};
单从代码来看，结构体task_struct还是很复杂的，所以我们将其进行拆解，从几个维度上去进行分析和记忆。
二、 解析task_struct
1.任务ID
代码如下（示例）：
pid_t pid;
pid_t tgid;
struct task_struct *group_leader; /* threadgroup leader */
pid是proceess id，tgid是thread group id，group_leader是一个地址指向主线程ID。
既然ID是唯一标识，为何要弄出pid，tgid和group_leader?
主要是解决两个问题：
一是任务展示，可以选择展示当前用户创建的任务，而不是列出所有的任务。
二是给任务下发指令，若使用kill给多线程中的1个线程发送信号，不能只退出这个线程，而是应该退出整个进程。
一个进程，如果只有主线程，pid是自己，tgid是自己，group_leader也是指向自己。
一个进程，如果创建了多个线程，除主线程外的其它线程会有自己的pid，tgid是进程的主线程pid，group_leader指向的就是进程的主线程。
2.信号处理
代码如下（示例）：
/* 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;
unsigned sas_ss_flags;
此处定义了信号不同的处理方式：阻塞暂不处理(blocked)，等待处理(pending)，正在通过信号处理函数进行处理(sighand)。
信号处理函数默认使用用户态的函数栈，此处以外，也可以开辟新的栈专门用于信号处理，sas_ss开头的三个变量就用于开辟新的栈。
3.任务状态
代码如下（示例）：
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
unsigned int flags; /* per process flags, defined below */
/* task state */
int exit_state;
int exit_code, exit_signal;
state的取值定义在includ/linux/sched.h中
#define TASK_RUNNING 0
#define TASK_INTERRUPTIBLE 1
#define TASK_UNINTERRUPTIBLE 2
#define __TASK_STOPPED 4
#define __TASK_TRACED 8
/* in tsk->exit_state */
#define EXIT_DEAD 16
#define EXIT_ZOMBIE 32
#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD)
/* in tsk->state again */
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
#define TASK_WAKING 256
#define TASK_PARKED 512
#define TASK_NOLOAD 1024
#define TASK_NEW 2048
#define TASK_STATE_MAX 4096
state的值是通过bitset的方式设置的，state的每1个bit就代表一种状态。
TASK_RUNNING 并不是说进程正在运行，而是表示进程在时刻准备运行的状态。当处于这个状态的进程获得时间片的时候，就是在运行中；如果没有获得时间片，就说明它被其他进程抢占了，在等待再次分配时间片。
任务标记，反应进程状态的信息，但不是运行状态，用于内核识别进程的当前状态，以进行下一步操作。
flags的取值如下，定义在include/linux/sched.h中
/*
* Per process flags
*/
#define PF_EXITING 0x00000004 /* getting shut down */
#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
#define PF_VCPU 0x00000010 /* I'm a virtual CPU */
#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */
#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
#define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */
#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
#define PF_DUMPCORE 0x00000200 /* dumped core */
#define PF_SIGNALED 0x00000400 /* killed by a signal */
#define PF_MEMALLOC 0x00000800 /* Allocating memory */
#define PF_NPROC_EXCEEDED 0x00001000 /* set_user noticed that RLIMIT_NPROC was exceeded */
#define PF_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */
#define PF_USED_ASYNC 0x00004000 /* used async_schedule*(), used by module init */
#define PF_NOFREEZE 0x00008000 /* this thread should not be frozen */
#define PF_FROZEN 0x00010000 /* frozen for system suspend */
#define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */
#define PF_KSWAPD 0x00040000 /* I am kswapd */
#define PF_MEMALLOC_NOIO 0x00080000 /* Allocating memory without IO involved */
#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */
#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */
#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK 0x80000000 /* this thread called freeze_processes and should not be frozen */
4.进程调度
进程的状态涉及调度，task_struct中和调度相关的字段
int on_rq; //是否运行在队列上
int prio, static_prio, normal_prio; //优先级;静态优先级可以通过nice来修改
unsigned int rt_priority; //实时优先级
const struct sched_class *sched_class; //调度器类
//调度实体
struct sched_entity se; //普通进程的调度实体
struct sched_rt_entity rt; //实时进程的调度实体
#ifdef CONFIG_SCHED_WALT
struct ravg ravg;
/*
* 'init_load_pct' represents the initial task load assigned to children
* of this task
*/
u32 init_load_pct;
u64 last_sleep_ts;
#endif
#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
//调度策略
unsigned int policy;
//可以使用的cpu
int nr_cpus_allowed;
cpumask_t cpus_allowed;
#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