//task_struct保存任务的基本信息
/*1, 进程状态 ,将纪录进程在等待,运行,或死锁
2, 调度信息, 由哪个调度函数调度,怎样调度等
3, 进程的通讯状况
4, 因为要插入进程树,必须有联系父子兄弟的指针, 当然是task_struct型
5, 时间信息, 比如计算好执行的时间, 以便cpu 分配
6, 标号 ,决定改进程归属
7, 可以读写打开的一些文件信息
8, 进程上下文和内核上下文
9, 处理器上下文
10,内存信息 因为每一个PCB都是这样的, 只有这些结构, 才能满足一个进程的所有要求.
*/
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_SMP
struct llist_node wake_entry;
int on_cpu;
struct task_struct *last_wakee;
unsigned long wakee_flips;
unsigned long wakee_flip_decay_ts;
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_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;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_PREEMPT_RCU
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 */
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
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;
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
/* 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
/* 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 */
/* Used for emulating ABI behavior of previous Linux versions */
unsigned int personality;
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_MEMCG_KMEM
unsigned memcg_kmem_skip_account:1;
#endif
unsigned long atomic_flags; /* Flags needing atomic access. */
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;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
struct cputime prev_cputime;
#endif
#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 */
int link_count, total_link_count;
#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
/* 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 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;
#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;
/* 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_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. 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[2];
unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */
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.
*/
unsigned long timer_slack_ns;
unsigned long default_timer_slack_ns;
#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_MEMCG
struct memcg_oom_info {
struct mem_cgroup *memcg;
gfp_t gfp_mask;
int order;
unsigned int may_oom:1;
} memcg_oom;
#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
};
//进程号，枚举变量，
/*PIDTYPE_PID 进程号
PIDTYPE_PGID 进程组 领头羊进程 的进程号
PIDTYPE_SID 会话 领头羊进程 的进程号
*/
enum pid_type
{
PIDTYPE_PID,
PIDTYPE_PGID,
PIDTYPE_SID,
PIDTYPE_MAX
};
//进程命名空间信息的描述
/*kerf引用计数器，代表命名空间在多少进程中被使用
pidmap[]记录当前系统的PID使用情况
last_pid记录上一次分配给进程的PID值
child_reaper保存指向该进程的task_struct的指针
pid_cachep指向该进程在Cache中分配的空间
parent指向父命名空间的指针
level较为重要，表示当前命名空间在整个命名空间层次结构中的深度，初始时为0，子空间为1，下一个
子空间为2。高level的namespace中的ID对低level的namespace是可见的，通过给定的level设置，内核
可以推断出一个进程会关联到多少个ID
*/
struct pid_namespace {
struct kref kref;
struct pidmap pidmap[PIDMAP_ENTRIES];
struct rcu_head rcu;
int last_pid;
unsigned int nr_hashed;
struct task_struct *child_reaper;
struct kmem_cache *pid_cachep;
unsigned int level; //最为重要
struct pid_namespace *parent;
#ifdef CONFIG_PROC_FS
struct vfsmount *proc_mnt;
struct dentry *proc_self;
struct dentry *proc_thread_self;
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
struct bsd_acct_struct *bacct;
#endif
struct user_namespace *user_ns;
struct work_struct proc_work;
kgid_t pid_gid;
int hide_pid;
int reboot; /* group exit code if this pidns was rebooted */
struct ns_common ns;
};
//根本功能是获取进程号
/*如果type不等于PIDTYPE_PID，则task用其任务组中的第一个任务赋值，否则task不变
保证进程描述符的pid_namespace和参数ns相同
*/
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,struct pid_namespace *ns)
{
pid_t nr = 0;
rcu_read_lock();
if (!ns)
ns = task_active_pid_ns(current);
if (likely(pid_alive(task))) {
if (type != PIDTYPE_PID)
task = task->group_leader;
nr = pid_nr_ns(task->pids[type].pid, ns);
}
rcu_read_unlock();
return nr;
}
//进程描述符
/*count代表使用此进程的任务数
level是numbers[]的下标
tasks是使用此进程的任务列表
numbers保存进程的一些相关信息，这个进程号也保存在struct upid里面，numbers[level](level=0)
居然namespcae也保存在这里，一家人果然要整整齐齐
*/
struct pid
{
atomic_t count;
unsigned int level;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct rcu_head rcu;
struct upid numbers[1];
};
struct upid
{
int nr;
struct pid_namespace *ns;
struct hlist_node pid_chain;
};
//给一个进程号，返回进程描述符，并使进程描述符中的字段count值加1，代表该进程的用户数加1
struct pid *find_get_pid(pid_t nr)
{
struct pid *pid;
rcu_read_lock();
pid = get_pid(find_vpid(nr));
rcu_read_unlock();
return pid;
}
//给一个进程号nr，一个进程名字空间ns，获得该进程描述符
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
struct upid *pnr;
hlist_for_each_entry_rcu(pnr,
&pid_hash[pid_hashfn(nr, ns)], pid_chain)
if (pnr->nr == nr && pnr->ns == ns)
return container_of(pnr, struct pid,
numbers[ns->level]);
return NULL;
}
/*给一个进程号，得到进程描述符，是函数 find_get_pid 的实现本体
但是和 find_get_pid 不一样，它不会使进程count值加1，也就是它取进程描述符更加隐蔽
不会被count察觉
【疑问】，find_vpid本质是用的 find_pid_ns ,但是 find_pid_ns 会使得count加1，为什么 find_vpid
却不会*/
struct pid *find_vpid(int nr)
{
return find_pid_ns(nr, task_active_pid_ns(current));
}
//把给进来的进程描述符的count加1后送回，find_pid_ns就是因为这个函数才会和find_vpid不同
static inline struct pid *get_pid(struct pid *pid)
{
if (pid)
atomic_inc(&pid->count);
return pid;
}
/*1, 进程状态 ,将纪录进程在等待,运行,或死锁
2, 调度信息, 由哪个调度函数调度,怎样调度等
3, 进程的通讯状况
4, 因为要插入进程树,必须有联系父子兄弟的指针, 当然是task_struct型
5, 时间信息, 比如计算好执行的时间, 以便cpu 分配
6, 标号 ,决定改进程归属
7, 可以读写打开的一些文件信息
8, 进程上下文和内核上下文
9, 处理器上下文
10,内存信息 因为每一个PCB都是这样的, 只有这些结构, 才能满足一个进程的所有要求.
*/
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_SMP
struct llist_node wake_entry;
int on_cpu;
struct task_struct *last_wakee;
unsigned long wakee_flips;
unsigned long wakee_flip_decay_ts;
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_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;
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_PREEMPT_RCU
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 */
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
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;
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
/* 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
/* 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 */
/* Used for emulating ABI behavior of previous Linux versions */
unsigned int personality;
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_MEMCG_KMEM
unsigned memcg_kmem_skip_account:1;
#endif
unsigned long atomic_flags; /* Flags needing atomic access. */
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;
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
struct cputime prev_cputime;
#endif
#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 */
int link_count, total_link_count;
#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
/* 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 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;
#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;
/* 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_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. 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[2];
unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */
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.
*/
unsigned long timer_slack_ns;
unsigned long default_timer_slack_ns;
#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_MEMCG
struct memcg_oom_info {
struct mem_cgroup *memcg;
gfp_t gfp_mask;
int order;
unsigned int may_oom:1;
} memcg_oom;
#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
};
//进程号，枚举变量，
/*PIDTYPE_PID 进程号
PIDTYPE_PGID 进程组 领头羊进程 的进程号
PIDTYPE_SID 会话 领头羊进程 的进程号
*/
enum pid_type
{
PIDTYPE_PID,
PIDTYPE_PGID,
PIDTYPE_SID,
PIDTYPE_MAX
};
//进程命名空间信息的描述
/*kerf引用计数器，代表命名空间在多少进程中被使用
pidmap[]记录当前系统的PID使用情况
last_pid记录上一次分配给进程的PID值
child_reaper保存指向该进程的task_struct的指针
pid_cachep指向该进程在Cache中分配的空间
parent指向父命名空间的指针
level较为重要，表示当前命名空间在整个命名空间层次结构中的深度，初始时为0，子空间为1，下一个
子空间为2。高level的namespace中的ID对低level的namespace是可见的，通过给定的level设置，内核
可以推断出一个进程会关联到多少个ID
*/
struct pid_namespace {
struct kref kref;
struct pidmap pidmap[PIDMAP_ENTRIES];
struct rcu_head rcu;
int last_pid;
unsigned int nr_hashed;
struct task_struct *child_reaper;
struct kmem_cache *pid_cachep;
unsigned int level; //最为重要
struct pid_namespace *parent;
#ifdef CONFIG_PROC_FS
struct vfsmount *proc_mnt;
struct dentry *proc_self;
struct dentry *proc_thread_self;
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
struct bsd_acct_struct *bacct;
#endif
struct user_namespace *user_ns;
struct work_struct proc_work;
kgid_t pid_gid;
int hide_pid;
int reboot; /* group exit code if this pidns was rebooted */
struct ns_common ns;
};
//根本功能是获取进程号
/*如果type不等于PIDTYPE_PID，则task用其任务组中的第一个任务赋值，否则task不变
保证进程描述符的pid_namespace和参数ns相同
*/
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,struct pid_namespace *ns)
{
pid_t nr = 0;
rcu_read_lock();
if (!ns)
ns = task_active_pid_ns(current);
if (likely(pid_alive(task))) {
if (type != PIDTYPE_PID)
task = task->group_leader;
nr = pid_nr_ns(task->pids[type].pid, ns);
}
rcu_read_unlock();
return nr;
}
//进程描述符
/*count代表使用此进程的任务数
level是numbers[]的下标
tasks是使用此进程的任务列表
numbers保存进程的一些相关信息，这个进程号也保存在struct upid里面，numbers[level](level=0)
居然namespcae也保存在这里，一家人果然要整整齐齐
*/
struct pid
{
atomic_t count;
unsigned int level;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct rcu_head rcu;
struct upid numbers[1];
};
struct upid
{
int nr;
struct pid_namespace *ns;
struct hlist_node pid_chain;
};
//给一个进程号，返回进程描述符，并使进程描述符中的字段count值加1，代表该进程的用户数加1
struct pid *find_get_pid(pid_t nr)
{
struct pid *pid;
rcu_read_lock();
pid = get_pid(find_vpid(nr));
rcu_read_unlock();
return pid;
}
//给一个进程号nr，一个进程名字空间ns，获得该进程描述符
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
struct upid *pnr;
hlist_for_each_entry_rcu(pnr,
&pid_hash[pid_hashfn(nr, ns)], pid_chain)
if (pnr->nr == nr && pnr->ns == ns)
return container_of(pnr, struct pid,
numbers[ns->level]);
return NULL;
}
/*给一个进程号，得到进程描述符，是函数 find_get_pid 的实现本体
但是和 find_get_pid 不一样，它不会使进程count值加1，也就是它取进程描述符更加隐蔽
不会被count察觉
【疑问】，find_vpid本质是用的 find_pid_ns ,但是 find_pid_ns 会使得count加1，为什么 find_vpid
却不会*/
struct pid *find_vpid(int nr)
{
return find_pid_ns(nr, task_active_pid_ns(current));
}
//把给进来的进程描述符的count加1后送回，find_pid_ns就是因为这个函数才会和find_vpid不同
static inline struct pid *get_pid(struct pid *pid)
{
if (pid)
atomic_inc(&pid->count);
return pid;
}