內核學習筆記(一)

火星人 @ 2014-03-26 , reply:0



學習內核我是從進程管理開始,一點點消化學習,整個系統的完成對內核的學習,覺得這樣的收穫還是最大,盲目的學習只會越來越迷茫。

進程也就是處於執行期的程序,一段目標代碼而已,但其中又不僅僅是代碼,還包括其他資源,像信號、處理器狀態、地址空間等。通俗的說進程包含了線程,內核的對象即是線程。Linux的線程是一種特殊的進程。

Linux系統中,一個進程調用fork()系統調用來創建一個子進程,調用結束時,在返回點這個位置,父進程恢復執行,子進程開始執行,fork()調用從內核返回兩次:一次回到父進程,另一次回到誕生的子進程。最終程序通過exit()系統調用退出執行,這個函數會終結進程並釋放資源。

Linux內核通常把進程也叫任務(task)。內核把進程存放在(task list)的雙向循環鏈表中,鏈表中每一項的數據類型都為task_struct的結構中

以下是Linux 2.6部分源碼(include/linux/sched.h)
CODE:
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;

int lock_depth; /* BKL lock depth */

#ifdef CONFIG_SMP
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
int oncpu;
#endif
#endif

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

/*
* fpu_counter contains the number of consecutive context switches
* that the FPU is used. If this is over a threshold, the lazy fpu
* saving becomes unlazy to save the trap. This is an unsigned char
* so that after 256 times the counter wraps and the behavior turns
* lazy again; this to deal with bursty apps that only use FPU for
* a short time
*/
unsigned char fpu_counter;
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif

unsigned int policy;
cpumask_t cpus_allowed;

#ifdef CONFIG_TREE_PREEMPT_RCU
int rcu_read_lock_nesting;
char rcu_read_unlock_special;
struct rcu_node *rcu_blocked_node;
struct list_head rcu_node_entry;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct sched_info sched_info;
#endif

struct list_head tasks;
struct plist_node pushable_tasks;

struct mm_struct *mm, *active_mm;
#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 personality;
unsigned did_exec:1;
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;

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 *real_parent; /* real parent process */
struct task_struct *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 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
cputime_t prev_utime, prev_stime;
#endif
unsigned long nvcsw, nivcsw; /* context switch counts */
struct timespec start_time; /* monotonic time */
struct timespec real_start_time; /* boot based time */
/* 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 *real_cred; /* objective and real subjective task
* credentials (COW) */
const struct cred *cred; /* effective (overridable) subjective task
* credentials (COW) */
struct mutex cred_guard_mutex; /* guard against foreign influences on
* credential calculations
* (notably. ptrace) */
struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */

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;
#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 audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
uid_t loginuid;
unsigned int sessionid;
#endif
seccomp_t 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;

#ifdef CONFIG_GENERIC_HARDIRQS
/* IRQ handler threads */
struct irqaction *irqaction;
#endif

/* 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 plist_head pi_waiters;
/* 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;

/* 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 */
int mems_allowed_change_disable;
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 *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;
struct mutex perf_event_mutex;
struct list_head perf_event_list;
#endif
#ifdef CONFIG_NUMA
struct mempolicy *mempolicy; /* Protected by alloc_lock */
short il_next;
#endif
atomic_t fs_excl; /* holding fs exclusive resources */
struct rcu_head rcu;

/*
* cache last used pipe for splice
*/
struct pipe_inode_info *splice_pipe;
#ifdef CONFIG_TASK_DELAY_ACCT
struct task_delay_info *delays;
#endif
#ifdef CONFIG_FAULT_INJECTION
int make_it_fail;
#endif
struct prop_local_single dirties;
#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;

struct list_head *scm_work_list;
#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 of trace recursion */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
struct memcg_batch_info {
int do_batch; /* incremented when batch uncharge started */
struct mem_cgroup *memcg; /* target memcg of uncharge */
unsigned long bytes; /* uncharged usage */
unsigned long memsw_bytes; /* uncharged mem+swap usage */
} memcg_batch;
#endif
};

可見其中數據類型之複雜,不過我們沒必要關注太多,把最重要的幾個信息掌握即可。task_struct結構縱然複雜,但又是什麼分配這個龐大的結構呢,答曰:slab分配器。答對了,這樣做的最大優點是可以快速創建進程,且佔用資源較少。內核通過PID來識別進程,是pid pid_t類型(實際為int類型),在task_struct結構中有定義。




[火星人 via ] 內核學習筆記(一)已經有247次圍觀

http://www.coctec.com/docs/linux/show-post-183126.html