1、進程狀態
- volatile long state;
- int exit_state;
state成員的可能取值如下:
- #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_ZOMBIE 16
- #define EXIT_DEAD 32
- /* in tsk->state again */
- #define TASK_DEAD 64
- #define TASK_WAKEKILL 128
- #define TASK_WAKING 256
系統中的每個進程都必然處於以上所列進程狀態中的一種。
TASK_RUNNING表示進程要么正在執行,要么正要准備執行。
TASK_INTERRUPTIBLE表示進程被阻塞(睡眠),直到某個條件變為真。條件一旦達成,進程的狀態就被設置為TASK_RUNNING。
TASK_UNINTERRUPTIBLE的意義與TASK_INTERRUPTIBLE類似,除了不能通過接受一個信號來喚醒以外。
__TASK_STOPPED表示進程被停止執行。
__TASK_TRACED表示進程被debugger等進程監視。
EXIT_ZOMBIE表示進程的執行被終止,但是其父進程還沒有使用wait()等系統調用來獲知它的終止信息。
EXIT_DEAD表示進程的最終狀態。
EXIT_ZOMBIE和EXIT_DEAD也可以存放在exit_state成員中。
2、進程標識符(PID)
- pid_t pid;
- pid_t tgid;
在CONFIG_BASE_SMALL配置為0的情況下,PID的取值范圍是0到32767,即系統中的進程數最大為32768個。
- /* linux-2.6.38.8/include/linux/threads.h */
- #define PID_MAX_DEFAULT (CONFIG_BASE_SMALL ? 0x1000 : 0x8000)
在Linux系統中,一個線程組中的所有線程使用和該線程組的領頭線程(該組中的第一個輕量級進程)相同的PID,並被存放在tgid成員中。只有線程組的領頭線程的pid成員才會被設置為與tgid相同的值。注意,getpid()系統調用返回的是當前進程的tgid值而不是pid值。
3、進程內核棧
- void *stack;
進程通過alloc_thread_info函數分配它的內核棧,通過free_thread_info函數釋放所分配的內核棧。
- /* linux-2.6.38.8/kernel/fork.c */
- static inline struct thread_info *alloc_thread_info(struct task_struct *tsk)
- {
- #ifdef CONFIG_DEBUG_STACK_USAGE
- gfp_t mask = GFP_KERNEL | __GFP_ZERO;
- #else
- gfp_t mask = GFP_KERNEL;
- #endif
- return (struct thread_info *)__get_free_pages(mask, THREAD_SIZE_ORDER);
- }
- static inline void free_thread_info(struct thread_info *ti)
- {
- free_pages((unsigned long)ti, THREAD_SIZE_ORDER);
- }
其中,THREAD_SIZE_ORDER宏在linux-2.6.38.8/arch/arm/include/asm/thread_info.h文件中被定義為1,也就是說alloc_thread_info函數通過調用__get_free_pages函數分配2個頁的內存(它的首地址是8192 字節對齊的)。
Linux內核通過thread_union聯合體來表示進程的內核棧,其中THREAD_SIZE宏的大小為8192。
- union thread_union {
- struct thread_info thread_info;
- unsigned long stack[THREAD_SIZE/sizeof(long)];
- };
當進程從用戶態切換到內核態時,進程的內核棧總是空的,所以ARM的sp寄存器指向這個棧的頂端。因此,內核能夠輕易地通過sp寄存器獲得當前正在CPU上運行的進程。
- /* linux-2.6.38.8/arch/arm/include/asm/current.h */
- static inline struct task_struct *get_current(void)
- {
- return current_thread_info()->task;
- }
- #define current (get_current())
- /* linux-2.6.38.8/arch/arm/include/asm/thread_info.h */
- static inline struct thread_info *current_thread_info(void)
- {
- register unsigned long sp asm ("sp");
- return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
- }
4、標記
- unsigned int flags; /* per process flags, defined below */
flags成員的可能取值如下:
- #define PF_KSOFTIRQD 0x00000001 /* I am ksoftirqd */
- #define PF_STARTING 0x00000002 /* being created */
- #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_USED_MATH 0x00002000 /* if unset the fpu must be initialized before use */
- #define PF_FREEZING 0x00004000 /* freeze in progress. do not account to load */
- #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_OOM_ORIGIN 0x00080000 /* Allocating much memory to others */
- #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_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */
- #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */
- #define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */
- #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
- #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */
- #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_FREEZER_NOSIG 0x80000000 /* Freezer won't send signals to it */
5、表示進程親屬關系的成員
- struct task_struct *real_parent; /* real parent process */
- struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
- 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 */
在Linux系統中,所有進程之間都有着直接或間接地聯系,每個進程都有其父進程,也可能有零個或多個子進程。擁有同一父進程的所有進程具有兄弟關系。
real_parent指向其父進程,如果創建它的父進程不再存在,則指向PID為1的init進程。
parent指向其父進程,當它終止時,必須向它的父進程發送信號。它的值通常與real_parent相同。
children表示鏈表的頭部,鏈表中的所有元素都是它的子進程。
sibling用於把當前進程插入到兄弟鏈表中。
group_leader指向其所在進程組的領頭進程。
6、ptrace系統調用
- unsigned int ptrace;
- struct list_head ptraced;
- struct list_head ptrace_entry;
- unsigned long ptrace_message;
- siginfo_t *last_siginfo; /* For ptrace use. */
- ifdef CONFIG_HAVE_HW_BREAKPOINT
- atomic_t ptrace_bp_refcnt;
- endif
成員ptrace被設置為0時表示不需要被跟蹤,它的可能取值如下:
- /* linux-2.6.38.8/include/linux/ptrace.h */
- #define PT_PTRACED 0x00000001
- #define PT_DTRACE 0x00000002 /* delayed trace (used on m68k, i386) */
- #define PT_TRACESYSGOOD 0x00000004
- #define PT_PTRACE_CAP 0x00000008 /* ptracer can follow suid-exec */
- #define PT_TRACE_FORK 0x00000010
- #define PT_TRACE_VFORK 0x00000020
- #define PT_TRACE_CLONE 0x00000040
- #define PT_TRACE_EXEC 0x00000080
- #define PT_TRACE_VFORK_DONE 0x00000100
- #define PT_TRACE_EXIT 0x00000200
7、Performance Event
- #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
Performance Event是一款隨 Linux 內核代碼一同發布和維護的性能診斷工具。這些成員用於幫助PerformanceEvent分析進程的性能問題。
8、進程調度
- 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;
- unsigned int policy;
- cpumask_t cpus_allowed;
實時優先級范圍是0到MAX_RT_PRIO-1(即99),而普通進程的靜態優先級范圍是從MAX_RT_PRIO到MAX_PRIO-1(即100到139)。值越大靜態優先級越低。
- /* linux-2.6.38.8/include/linux/sched.h */
- #define MAX_USER_RT_PRIO 100
- #define MAX_RT_PRIO MAX_USER_RT_PRIO
- #define MAX_PRIO (MAX_RT_PRIO + 40)
- #define DEFAULT_PRIO (MAX_RT_PRIO + 20)
static_prio用於保存靜態優先級,可以通過nice系統調用來進行修改。
rt_priority用於保存實時優先級。
normal_prio的值取決於靜態優先級和調度策略。
prio用於保存動態優先級。
policy表示進程的調度策略,目前主要有以下五種:
- #define SCHED_NORMAL 0
- #define SCHED_FIFO 1
- #define SCHED_RR 2
- #define SCHED_BATCH 3
- /* SCHED_ISO: reserved but not implemented yet */
- #define SCHED_IDLE 5
SCHED_NORMAL用於普通進程,通過CFS調度器實現。SCHED_BATCH用於非交互的處理器消耗型進程。SCHED_IDLE是在系統負載很低時使用。
SCHED_FIFO(先入先出調度算法)和SCHED_RR(輪流調度算法)都是實時調度策略。
sched_class結構體表示調度類,目前內核中有實現以下四種:
- /* linux-2.6.38.8/kernel/sched_fair.c */
- static const struct sched_class fair_sched_class;
- /* linux-2.6.38.8/kernel/sched_rt.c */
- static const struct sched_class rt_sched_class;
- /* linux-2.6.38.8/kernel/sched_idletask.c */
- static const struct sched_class idle_sched_class;
- /* linux-2.6.38.8/kernel/sched_stoptask.c */
- static const struct sched_class stop_sched_class;
se和rt都是調用實體,一個用於普通進程,一個用於實時進程,每個進程都有其中之一的實體。
cpus_allowed用於控制進程可以在哪里處理器上運行。
9、進程地址空間
- struct mm_struct *mm, *active_mm;
- #ifdef CONFIG_COMPAT_BRK
- unsigned brk_randomized:1;
- #endif
- #if defined(SPLIT_RSS_COUNTING)
- struct task_rss_stat rss_stat;
- #endif
mm指向進程所擁有的內存描述符,而active_mm指向進程運行時所使用的內存描述符。對於普通進程而言,這兩個指針變量的值相同。但是,內核線程不擁有任何內存描述符,所以它們的mm成員總是為NULL。當內核線程得以運行時,它的active_mm成員被初始化為前一個運行進程的 active_mm值。
rss_stat用來記錄緩沖信息。
10、判斷標志
- 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;
exit_code用於設置進程的終止代號,這個值要么是_exit()或exit_group()系統調用參數(正常終止),要么是由內核提供的一個錯誤代號(異常終止)。
exit_signal被置為-1時表示是某個線程組中的一員。只有當線程組的最后一個成員終止時,才會產生一個信號,以通知線程組的領頭進程的父進程。
pdeath_signal用於判斷父進程終止時發送信號。
personality用於處理不同的ABI,它的可能取值如下:
- enum {
- PER_LINUX = 0x0000,
- PER_LINUX_32BIT = 0x0000 | ADDR_LIMIT_32BIT,
- PER_LINUX_FDPIC = 0x0000 | FDPIC_FUNCPTRS,
- PER_SVR4 = 0x0001 | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
- PER_SVR3 = 0x0002 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_SCOSVR3 = 0x0003 | STICKY_TIMEOUTS |
- WHOLE_SECONDS | SHORT_INODE,
- PER_OSR5 = 0x0003 | STICKY_TIMEOUTS | WHOLE_SECONDS,
- PER_WYSEV386 = 0x0004 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_ISCR4 = 0x0005 | STICKY_TIMEOUTS,
- PER_BSD = 0x0006,
- PER_SUNOS = 0x0006 | STICKY_TIMEOUTS,
- PER_XENIX = 0x0007 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_LINUX32 = 0x0008,
- PER_LINUX32_3GB = 0x0008 | ADDR_LIMIT_3GB,
- PER_IRIX32 = 0x0009 | STICKY_TIMEOUTS,/* IRIX5 32-bit */
- PER_IRIXN32 = 0x000a | STICKY_TIMEOUTS,/* IRIX6 new 32-bit */
- PER_IRIX64 = 0x000b | STICKY_TIMEOUTS,/* IRIX6 64-bit */
- PER_RISCOS = 0x000c,
- PER_SOLARIS = 0x000d | STICKY_TIMEOUTS,
- PER_UW7 = 0x000e | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
- PER_OSF4 = 0x000f, /* OSF/1 v4 */
- PER_HPUX = 0x0010,
- PER_MASK = 0x00ff,
- };
did_exec用於記錄進程代碼是否被execve()函數所執行。
in_iowait用於判斷是否進行iowait計數。
sched_reset_on_fork用於判斷是否恢復默認的優先級或調度策略。
11、時間
- 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 */
- struct task_cputime cputime_expires;
- struct list_head cpu_timers[3];
- #ifdef CONFIG_DETECT_HUNG_TASK
- /* hung task detection */
- unsigned long last_switch_count;
- #endif
utime/stime用於記錄進程在用戶態/內核態下所經過的節拍數(定時器)
utimescaled/stimescaled也是用於記錄進程在用戶態/內核態的運行時間,但它們以處理器的頻率為刻度。
gtime是以節拍計數的虛擬機運行時間(guest time)。
nvcsw/nivcsw是自願(voluntary)/非自願(involuntary)上下文切換計數。last_switch_count是nvcsw和nivcsw的總和。
start_time和real_start_time都是進程創建時間,real_start_time還包含了進程睡眠時間,常用於/proc/pid/stat,
cputime_expires用來統計進程或進程組被跟蹤的處理器時間,其中的三個成員對應着cpu_timers[3]的三個鏈表。
12、信號處理
- /* 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;
signal指向進程的信號描述符。
sighand指向進程的信號處理程序描述符。
blocked表示被阻塞信號的掩碼,real_blocked表示臨時掩碼。
pending存放私有掛起信號的數據結構。
sas_ss_sp是信號處理程序備用堆棧的地址,sas_ss_size表示堆棧的大小。
設備驅動程序常用notifier指向的函數來阻塞進程的某些信號(notifier_mask是這些信號的位掩碼),notifier_data指的是notifier所指向的函數可能使用的數據。
13、其他
(1)、用於保護資源分配或釋放的自旋鎖
- /* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
- * mempolicy */
- spinlock_t alloc_lock;
(2)、進程描述符使用計數,被置為2時,表示進程描述符正在被使用而且其相應的進程處於活動狀態。
- atomic_t usage;
(3)、用於表示獲取大內核鎖的次數,如果進程未獲得過鎖,則置為-1。
- int lock_depth; /* BKL lock depth */
(4)、在SMP上幫助實現無加鎖的進程切換(unlocked context switches)
- #ifdef CONFIG_SMP
- #ifdef __ARCH_WANT_UNLOCKED_CTXSW
- int oncpu;
- #endif
- #endif
(5)、preempt_notifier結構體鏈表
- #ifdef CONFIG_PREEMPT_NOTIFIERS
- /* list of struct preempt_notifier: */
- struct hlist_head preempt_notifiers;
- #endif
(6)、FPU使用計數
- unsigned char fpu_counter;
(7)、blktrace是一個針對Linux內核中塊設備I/O層的跟蹤工具。
- #ifdef CONFIG_BLK_DEV_IO_TRACE
- unsigned int btrace_seq;
- #endif
(8)、RCU同步原語
- #ifdef CONFIG_PREEMPT_RCU
- int rcu_read_lock_nesting;
- char rcu_read_unlock_special;
- struct list_head rcu_node_entry;
- #endif /* #ifdef CONFIG_PREEMPT_RCU */
- #ifdef CONFIG_TREE_PREEMPT_RCU
- struct rcu_node *rcu_blocked_node;
- #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
- #ifdef CONFIG_RCU_BOOST
- struct rt_mutex *rcu_boost_mutex;
- #endif /* #ifdef CONFIG_RCU_BOOST */
(9)、用於調度器統計進程的運行信息
- #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
- struct sched_info sched_info;
- #endif
(10)、用於構建進程鏈表
- struct list_head tasks;
(11)、to limit pushing to one attempt
- #ifdef CONFIG_SMP
- struct plist_node pushable_tasks;
- #endif
(12)、防止內核堆棧溢出
- #ifdef CONFIG_CC_STACKPROTECTOR
- /* Canary value for the -fstack-protector gcc feature */
- unsigned long stack_canary;
- #endif
在GCC編譯內核時,需要加上-fstack-protector選項。
(13)、PID散列表和鏈表
- /* PID/PID hash table linkage. */
- struct pid_link pids[PIDTYPE_MAX];
- struct list_head thread_group; //線程組中所有進程的鏈表
(14)、do_fork函數
- struct completion *vfork_done; /* for vfork() */
- int __user *set_child_tid; /* CLONE_CHILD_SETTID */
- int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
在執行do_fork()時,如果給定特別標志,則vfork_done會指向一個特殊地址。
如果copy_process函數的clone_flags參數的值被置為CLONE_CHILD_SETTID或 CLONE_CHILD_CLEARTID,則會把child_tidptr參數的值分別復制到set_child_tid和 clear_child_tid成員。這些標志說明必須改變子進程用戶態地址空間的child_tidptr所指向的變量的值。
(15)、缺頁統計
- /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
- unsigned long min_flt, maj_flt;
(16)、進程權能
- const struct cred __rcu *real_cred; /* objective and real subjective task
- * credentials (COW) */
- const struct cred __rcu *cred; /* effective (overridable) subjective task
- * credentials (COW) */
- struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
(17)、相應的程序名
- char comm[TASK_COMM_LEN];
(18)、文件
- /* file system info */
- int link_count, total_link_count;
- /* filesystem information */
- struct fs_struct *fs;
- /* open file information */
- struct files_struct *files;
fs用來表示進程與文件系統的聯系,包括當前目錄和根目錄。
files表示進程當前打開的文件。
(19)、進程通信(SYSVIPC)
- #ifdef CONFIG_SYSVIPC
- /* ipc stuff */
- struct sysv_sem sysvsem;
- #endif
(20)、處理器特有數據
- /* CPU-specific state of this task */
- struct thread_struct thread;
(21)、命名空間
- /* namespaces */
- struct nsproxy *nsproxy;
(22)、進程審計
- struct audit_context *audit_context;
- #ifdef CONFIG_AUDITSYSCALL
- uid_t loginuid;
- unsigned int sessionid;
- #endif
(23)、secure computing
- seccomp_t seccomp;
(24)、用於copy_process函數使用CLONE_PARENT 標記時
- /* Thread group tracking */
- u32 parent_exec_id;
- u32 self_exec_id;
(25)、中斷
- #ifdef CONFIG_GENERIC_HARDIRQS
- /* IRQ handler threads */
- struct irqaction *irqaction;
- #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
(26)、task_rq_lock函數所使用的鎖
- /* Protection of the PI data structures: */
- raw_spinlock_t pi_lock;
(27)、基於PI協議的等待互斥鎖,其中PI指的是priority inheritance(優先級繼承)
- #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
(28)、死鎖檢測
- #ifdef CONFIG_DEBUG_MUTEXES
- /* mutex deadlock detection */
- struct mutex_waiter *blocked_on;
- #endif
(29)、lockdep,參見內核說明文檔linux-2.6.38.8/Documentation/lockdep-design.txt
- #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
(30)、JFS文件系統
- /* journalling filesystem info */
- void *journal_info;
(31)、塊設備鏈表
- /* stacked block device info */
- struct bio_list *bio_list;
(32)、內存回收
- struct reclaim_state *reclaim_state;
(33)、存放塊設備I/O數據流量信息
- struct backing_dev_info *backing_dev_info;
(34)、I/O調度器所使用的信息
- struct io_context *io_context;
(35)、記錄進程的I/O計數
- 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
在Ubuntu 11.04上,執行cat獲得進程1的I/O計數如下:
- $ sudo cat /proc/1/io
- rchar: 164258906
- wchar: 455212837
- syscr: 388847
- syscw: 92563
- read_bytes: 439251968
- write_bytes: 14143488
- cancelled_write_bytes: 2134016
輸出的數據項剛好是task_io_accounting結構體的所有成員。
(36)、CPUSET功能
- #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
(37)、Control Groups
- #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_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
(38)、futex同步機制
- #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
(39)、非一致內存訪問(NUMA Non-Uniform Memory Access)
- #ifdef CONFIG_NUMA
- struct mempolicy *mempolicy; /* Protected by alloc_lock */
- short il_next;
- #endif
(40)、文件系統互斥資源
- atomic_t fs_excl; /* holding fs exclusive resources */
(41)、RCU鏈表
- struct rcu_head rcu;
(42)、管道
- struct pipe_inode_info *splice_pipe;
(43)、延遲計數
- #ifdef CONFIG_TASK_DELAY_ACCT
- struct task_delay_info *delays;
- #endif
(44)、fault injection
[cpp] view plain copy
- #ifdef CONFIG_FAULT_INJECTION
- int make_it_fail;
- #endif
(45)、FLoating proportions
- struct prop_local_single dirties;
(46)、Infrastructure for displayinglatency
- #ifdef CONFIG_LATENCYTOP
- int latency_record_count;
- struct latency_record latency_record[LT_SAVECOUNT];
- #endif
(47)、time slack values,常用於poll和select函數
- unsigned long timer_slack_ns;
- unsigned long default_timer_slack_ns;
(48)、socket控制消息(control message)
- struct list_head *scm_work_list;
(49)、ftrace跟蹤器
- #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 */
9、進程地址空間
- struct mm_struct *mm, *active_mm;
- #ifdef CONFIG_COMPAT_BRK
- unsigned brk_randomized:1;
- #endif
- #if defined(SPLIT_RSS_COUNTING)
- struct task_rss_stat rss_stat;
- #endif
mm指向進程所擁有的內存描述符,而active_mm指向進程運行時所使用的內存描述符。對於普通進程而言,這兩個指針變量的值相同。但是,內核線程不擁有任何內存描述符,所以它們的mm成員總是為NULL。當內核線程得以運行時,它的active_mm成員被初始化為前一個運行進程的 active_mm值。
rss_stat用來記錄緩沖信息。
10、判斷標志
- 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;
exit_code用於設置進程的終止代號,這個值要么是_exit()或exit_group()系統調用參數(正常終止),要么是由內核提供的一個錯誤代號(異常終止)。
exit_signal被置為-1時表示是某個線程組中的一員。只有當線程組的最后一個成員終止時,才會產生一個信號,以通知線程組的領頭進程的父進程。
pdeath_signal用於判斷父進程終止時發送信號。
personality用於處理不同的ABI,它的可能取值如下:
- enum {
- PER_LINUX = 0x0000,
- PER_LINUX_32BIT = 0x0000 | ADDR_LIMIT_32BIT,
- PER_LINUX_FDPIC = 0x0000 | FDPIC_FUNCPTRS,
- PER_SVR4 = 0x0001 | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
- PER_SVR3 = 0x0002 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_SCOSVR3 = 0x0003 | STICKY_TIMEOUTS |
- WHOLE_SECONDS | SHORT_INODE,
- PER_OSR5 = 0x0003 | STICKY_TIMEOUTS | WHOLE_SECONDS,
- PER_WYSEV386 = 0x0004 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_ISCR4 = 0x0005 | STICKY_TIMEOUTS,
- PER_BSD = 0x0006,
- PER_SUNOS = 0x0006 | STICKY_TIMEOUTS,
- PER_XENIX = 0x0007 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_LINUX32 = 0x0008,
- PER_LINUX32_3GB = 0x0008 | ADDR_LIMIT_3GB,
- PER_IRIX32 = 0x0009 | STICKY_TIMEOUTS,/* IRIX5 32-bit */
- PER_IRIXN32 = 0x000a | STICKY_TIMEOUTS,/* IRIX6 new 32-bit */
- PER_IRIX64 = 0x000b | STICKY_TIMEOUTS,/* IRIX6 64-bit */
- PER_RISCOS = 0x000c,
- PER_SOLARIS = 0x000d | STICKY_TIMEOUTS,
- PER_UW7 = 0x000e | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
- PER_OSF4 = 0x000f, /* OSF/1 v4 */
- PER_HPUX = 0x0010,
- PER_MASK = 0x00ff,
- };
did_exec用於記錄進程代碼是否被execve()函數所執行。
in_execve用於通知LSM是否被do_execve()函數所調用。
-
in_iowait用於判斷是否進行iowait計數。
sched_reset_on_fork用於判斷是否恢復默認的優先級或調度策略。
11、時間
- 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 */
- struct task_cputime cputime_expires;
- struct list_head cpu_timers[3];
- #ifdef CONFIG_DETECT_HUNG_TASK
- /* hung task detection */
- unsigned long last_switch_count;
- #endif
utime/stime用於記錄進程在用戶態/內核態下所經過的節拍數(定時器)。
-
utimescaled/stimescaled也是用於記錄進程在用戶態/內核態的運行時間,但它們以處理器的頻率為刻度。
gtime是以節拍計數的虛擬機運行時間(guest time)。
nvcsw/nivcsw是自願(voluntary)/非自願(involuntary)上下文切換計數。last_switch_count是nvcsw和nivcsw的總和。
start_time和real_start_time都是進程創建時間,real_start_time還包含了進程睡眠時間,常用於/proc/pid/stat,補丁說明請參考http://lkml.indiana.edu/hypermail/linux/kernel/0705.0/2094.html。
cputime_expires用來統計進程或進程組被跟蹤的處理器時間,其中的三個成員對應着cpu_timers[3]的三個鏈表。
12、信號處理
- /* 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;
signal指向進程的信號描述符。
sighand指向進程的信號處理程序描述符。
blocked表示被阻塞信號的掩碼,real_blocked表示臨時掩碼。
pending存放私有掛起信號的數據結構。
sas_ss_sp是信號處理程序備用堆棧的地址,sas_ss_size表示堆棧的大小。
設備驅動程序常用notifier指向的函數來阻塞進程的某些信號(notifier_mask是這些信號的位掩碼),notifier_data指的是notifier所指向的函數可能使用的數據。
13、其他
(1)、用於保護資源分配或釋放的自旋鎖
- /* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
- * mempolicy */
- spinlock_t alloc_lock;
(2)、進程描述符使用計數,被置為2時,表示進程描述符正在被使用而且其相應的進程處於活動狀態。
- atomic_t usage;
(3)、用於表示獲取大內核鎖的次數,如果進程未獲得過鎖,則置為-1。
- int lock_depth; /* BKL lock depth */
(4)、在SMP上幫助實現無加鎖的進程切換(unlocked context switches)
- #ifdef CONFIG_SMP
- #ifdef __ARCH_WANT_UNLOCKED_CTXSW
- int oncpu;
- #endif
- #endif
(5)、preempt_notifier結構體鏈表
- #ifdef CONFIG_PREEMPT_NOTIFIERS
- /* list of struct preempt_notifier: */
- struct hlist_head preempt_notifiers;
- #endif
(6)、FPU使用計數
- unsigned char fpu_counter;
(7)、blktrace是一個針對Linux內核中塊設備I/O層的跟蹤工具。
- #ifdef CONFIG_BLK_DEV_IO_TRACE
- unsigned int btrace_seq;
- #endif
(8)、RCU同步原語
- #ifdef CONFIG_PREEMPT_RCU
- int rcu_read_lock_nesting;
- char rcu_read_unlock_special;
- struct list_head rcu_node_entry;
- #endif /* #ifdef CONFIG_PREEMPT_RCU */
- #ifdef CONFIG_TREE_PREEMPT_RCU
- struct rcu_node *rcu_blocked_node;
- #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
- #ifdef CONFIG_RCU_BOOST
- struct rt_mutex *rcu_boost_mutex;
- #endif /* #ifdef CONFIG_RCU_BOOST */
(9)、用於調度器統計進程的運行信息
- #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
- struct sched_info sched_info;
- #endif
(10)、用於構建進程鏈表
- struct list_head tasks;
(11)、to limit pushing to one attempt
- #ifdef CONFIG_SMP
- struct plist_node pushable_tasks;
- #endif
補丁說明請參考:http://lkml.indiana.edu/hypermail/linux/kernel/0808.3/0503.html
(12)、防止內核堆棧溢出
- #ifdef CONFIG_CC_STACKPROTECTOR
- /* Canary value for the -fstack-protector gcc feature */
- unsigned long stack_canary;
- #endif
在GCC編譯內核時,需要加上-fstack-protector選項。
(13)、PID散列表和鏈表
- /* PID/PID hash table linkage. */
- struct pid_link pids[PIDTYPE_MAX];
- struct list_head thread_group; //線程組中所有進程的鏈表
(14)、do_fork函數
- struct completion *vfork_done; /* for vfork() */
- int __user *set_child_tid; /* CLONE_CHILD_SETTID */
- int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
在執行do_fork()時,如果給定特別標志,則vfork_done會指向一個特殊地址。
如果copy_process函數的clone_flags參數的值被置為CLONE_CHILD_SETTID或 CLONE_CHILD_CLEARTID,則會把child_tidptr參數的值分別復制到set_child_tid和 clear_child_tid成員。這些標志說明必須改變子進程用戶態地址空間的child_tidptr所指向的變量的值。
(15)、缺頁統計
- /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
- unsigned long min_flt, maj_flt;
(16)、進程權能
- const struct cred __rcu *real_cred; /* objective and real subjective task
- * credentials (COW) */
- const struct cred __rcu *cred; /* effective (overridable) subjective task
- * credentials (COW) */
- struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
(17)、相應的程序名
- char comm[TASK_COMM_LEN];
(18)、文件
- /* file system info */
- int link_count, total_link_count;
- /* filesystem information */
- struct fs_struct *fs;
- /* open file information */
- struct files_struct *files;
fs用來表示進程與文件系統的聯系,包括當前目錄和根目錄。
files表示進程當前打開的文件。
(19)、進程通信(SYSVIPC)
- #ifdef CONFIG_SYSVIPC
- /* ipc stuff */
- struct sysv_sem sysvsem;
- #endif
(20)、處理器特有數據
- /* CPU-specific state of this task */
- struct thread_struct thread;
(21)、命名空間
- /* namespaces */
- struct nsproxy *nsproxy;
(22)、進程審計
- struct audit_context *audit_context;
- #ifdef CONFIG_AUDITSYSCALL
- uid_t loginuid;
- unsigned int sessionid;
- #endif
(23)、secure computing
- seccomp_t seccomp;
(24)、用於copy_process函數使用CLONE_PARENT 標記時
- /* Thread group tracking */
- u32 parent_exec_id;
- u32 self_exec_id;
(25)、中斷
- #ifdef CONFIG_GENERIC_HARDIRQS
- /* IRQ handler threads */
- struct irqaction *irqaction;
- #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
(26)、task_rq_lock函數所使用的鎖
- /* Protection of the PI data structures: */
- raw_spinlock_t pi_lock;
(27)、基於PI協議的等待互斥鎖,其中PI指的是priority inheritance(優先級繼承)
- #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
(28)、死鎖檢測
- #ifdef CONFIG_DEBUG_MUTEXES
- /* mutex deadlock detection */
- struct mutex_waiter *blocked_on;
- #endif
(29)、lockdep,參見內核說明文檔linux-2.6.38.8/Documentation/lockdep-design.txt
- #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
(30)、JFS文件系統
- /* journalling filesystem info */
- void *journal_info;
(31)、塊設備鏈表
- /* stacked block device info */
- struct bio_list *bio_list;
(32)、內存回收
- struct reclaim_state *reclaim_state;
(33)、存放塊設備I/O數據流量信息
- struct backing_dev_info *backing_dev_info;
- struct io_context *io_context;
(35)、記錄進程的I/O計數
- 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
在Ubuntu 11.04上,執行cat獲得進程1的I/O計數如下:
- $ sudo cat /proc/1/io
- rchar: 164258906
- wchar: 455212837
- syscr: 388847
- syscw: 92563
- read_bytes: 439251968
- write_bytes: 14143488
- cancelled_write_bytes: 2134016
輸出的數據項剛好是task_io_accounting結構體的所有成員。
(36)、CPUSET功能
- #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
(37)、Control Groups
- #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_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
(38)、futex同步機制
- #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
(39)、非一致內存訪問(NUMA Non-Uniform Memory Access)
- #ifdef CONFIG_NUMA
- struct mempolicy *mempolicy; /* Protected by alloc_lock */
- short il_next;
- #endif
(40)、文件系統互斥資源
- atomic_t fs_excl; /* holding fs exclusive resources */
(41)、RCU鏈表
- struct rcu_head rcu;
(42)、管道
- struct pipe_inode_info *splice_pipe;
(43)、延遲計數
- #ifdef CONFIG_TASK_DELAY_ACCT
- struct task_delay_info *delays;
- #endif
(44)、fault injection,參考內核說明文件linux-2.6.38.8/Documentation/fault-injection/fault-injection.txt
- #ifdef CONFIG_FAULT_INJECTION
- int make_it_fail;
- #endif
(45)、FLoating proportions
- struct prop_local_single dirties;
(46)、Infrastructure for displayinglatency
- #ifdef CONFIG_LATENCYTOP
- int latency_record_count;
- struct latency_record latency_record[LT_SAVECOUNT];
- #endif
(47)、time slack values,常用於poll和select函數
- unsigned long timer_slack_ns;
- unsigned long default_timer_slack_ns;
(48)、socket控制消息(control message)
- struct list_head *scm_work_list;
(49)、ftrace跟蹤器
- #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 */
9、進程地址空間
- struct mm_struct *mm, *active_mm;
- #ifdef CONFIG_COMPAT_BRK
- unsigned brk_randomized:1;
- #endif
- #if defined(SPLIT_RSS_COUNTING)
- struct task_rss_stat rss_stat;
- #endif
mm指向進程所擁有的內存描述符,而active_mm指向進程運行時所使用的內存描述符。對於普通進程而言,這兩個指針變量的值相同。但是,內核線程不擁有任何內存描述符,所以它們的mm成員總是為NULL。當內核線程得以運行時,它的active_mm成員被初始化為前一個運行進程的 active_mm值。
brk_randomized的用法在http://lkml.indiana.edu/hypermail/linux/kernel/1104.1/00196.html上有介紹,用來確定對隨機堆內存的探測。
rss_stat用來記錄緩沖信息。
10、判斷標志
- 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;
exit_code用於設置進程的終止代號,這個值要么是_exit()或exit_group()系統調用參數(正常終止),要么是由內核提供的一個錯誤代號(異常終止)。
exit_signal被置為-1時表示是某個線程組中的一員。只有當線程組的最后一個成員終止時,才會產生一個信號,以通知線程組的領頭進程的父進程。
pdeath_signal用於判斷父進程終止時發送信號。
personality用於處理不同的ABI,它的可能取值如下:
- enum {
- PER_LINUX = 0x0000,
- PER_LINUX_32BIT = 0x0000 | ADDR_LIMIT_32BIT,
- PER_LINUX_FDPIC = 0x0000 | FDPIC_FUNCPTRS,
- PER_SVR4 = 0x0001 | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
- PER_SVR3 = 0x0002 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_SCOSVR3 = 0x0003 | STICKY_TIMEOUTS |
- WHOLE_SECONDS | SHORT_INODE,
- PER_OSR5 = 0x0003 | STICKY_TIMEOUTS | WHOLE_SECONDS,
- PER_WYSEV386 = 0x0004 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_ISCR4 = 0x0005 | STICKY_TIMEOUTS,
- PER_BSD = 0x0006,
- PER_SUNOS = 0x0006 | STICKY_TIMEOUTS,
- PER_XENIX = 0x0007 | STICKY_TIMEOUTS | SHORT_INODE,
- PER_LINUX32 = 0x0008,
- PER_LINUX32_3GB = 0x0008 | ADDR_LIMIT_3GB,
- PER_IRIX32 = 0x0009 | STICKY_TIMEOUTS,/* IRIX5 32-bit */
- PER_IRIXN32 = 0x000a | STICKY_TIMEOUTS,/* IRIX6 new 32-bit */
- PER_IRIX64 = 0x000b | STICKY_TIMEOUTS,/* IRIX6 64-bit */
- PER_RISCOS = 0x000c,
- PER_SOLARIS = 0x000d | STICKY_TIMEOUTS,
- PER_UW7 = 0x000e | STICKY_TIMEOUTS | MMAP_PAGE_ZERO,
- PER_OSF4 = 0x000f, /* OSF/1 v4 */
- PER_HPUX = 0x0010,
- PER_MASK = 0x00ff,
- };
did_exec用於記錄進程代碼是否被execve()函數所執行。
in_execve用於通知LSM是否被do_execve()函數所調用。詳見補丁說明:http://lkml.indiana.edu/hypermail/linux/kernel/0901.1/00014.html。
in_iowait用於判斷是否進行iowait計數。
sched_reset_on_fork用於判斷是否恢復默認的優先級或調度策略。
11、時間
- 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 */
- struct task_cputime cputime_expires;
- struct list_head cpu_timers[3];
- #ifdef CONFIG_DETECT_HUNG_TASK
- /* hung task detection */
- unsigned long last_switch_count;
- #endif
utime/stime用於記錄進程在用戶態/內核態下所經過的節拍數(定時器)。prev_utime/prev_stime是先前的運行時間,請參考補丁說明http://lkml.indiana.edu/hypermail/linux/kernel/1003.3/02431.html。
utimescaled/stimescaled也是用於記錄進程在用戶態/內核態的運行時間,但它們以處理器的頻率為刻度。
gtime是以節拍計數的虛擬機運行時間(guest time)。
nvcsw/nivcsw是自願(voluntary)/非自願(involuntary)上下文切換計數。last_switch_count是nvcsw和nivcsw的總和。
start_time和real_start_time都是進程創建時間,real_start_time還包含了進程睡眠時間,常用於/proc/pid/stat,補丁說明請參考http://lkml.indiana.edu/hypermail/linux/kernel/0705.0/2094.html。
cputime_expires用來統計進程或進程組被跟蹤的處理器時間,其中的三個成員對應着cpu_timers[3]的三個鏈表。
12、信號處理
- /* 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;
signal指向進程的信號描述符。
sighand指向進程的信號處理程序描述符。
blocked表示被阻塞信號的掩碼,real_blocked表示臨時掩碼。
pending存放私有掛起信號的數據結構。
sas_ss_sp是信號處理程序備用堆棧的地址,sas_ss_size表示堆棧的大小。
設備驅動程序常用notifier指向的函數來阻塞進程的某些信號(notifier_mask是這些信號的位掩碼),notifier_data指的是notifier所指向的函數可能使用的數據。
13、其他
(1)、用於保護資源分配或釋放的自旋鎖
- /* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
- * mempolicy */
- spinlock_t alloc_lock;
(2)、進程描述符使用計數,被置為2時,表示進程描述符正在被使用而且其相應的進程處於活動狀態。
- atomic_t usage;
(3)、用於表示獲取大內核鎖的次數,如果進程未獲得過鎖,則置為-1。
- int lock_depth; /* BKL lock depth */
(4)、在SMP上幫助實現無加鎖的進程切換(unlocked context switches)
- #ifdef CONFIG_SMP
- #ifdef __ARCH_WANT_UNLOCKED_CTXSW
- int oncpu;
- #endif
- #endif
(5)、preempt_notifier結構體鏈表
- #ifdef CONFIG_PREEMPT_NOTIFIERS
- /* list of struct preempt_notifier: */
- struct hlist_head preempt_notifiers;
- #endif
(6)、FPU使用計數
- unsigned char fpu_counter;
(7)、blktrace是一個針對Linux內核中塊設備I/O層的跟蹤工具。
- #ifdef CONFIG_BLK_DEV_IO_TRACE
- unsigned int btrace_seq;
- #endif
(8)、RCU同步原語
- #ifdef CONFIG_PREEMPT_RCU
- int rcu_read_lock_nesting;
- char rcu_read_unlock_special;
- struct list_head rcu_node_entry;
- #endif /* #ifdef CONFIG_PREEMPT_RCU */
- #ifdef CONFIG_TREE_PREEMPT_RCU
- struct rcu_node *rcu_blocked_node;
- #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
- #ifdef CONFIG_RCU_BOOST
- struct rt_mutex *rcu_boost_mutex;
- #endif /* #ifdef CONFIG_RCU_BOOST */
(9)、用於調度器統計進程的運行信息
- #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
- struct sched_info sched_info;
- #endif
(10)、用於構建進程鏈表
- struct list_head tasks;
(11)、to limit pushing to one attempt
- #ifdef CONFIG_SMP
- struct plist_node pushable_tasks;
- #endif
補丁說明請參考:http://lkml.indiana.edu/hypermail/linux/kernel/0808.3/0503.html
(12)、防止內核堆棧溢出
- #ifdef CONFIG_CC_STACKPROTECTOR
- /* Canary value for the -fstack-protector gcc feature */
- unsigned long stack_canary;
- #endif
在GCC編譯內核時,需要加上-fstack-protector選項。
(13)、PID散列表和鏈表
- /* PID/PID hash table linkage. */
- struct pid_link pids[PIDTYPE_MAX];
- struct list_head thread_group; //線程組中所有進程的鏈表
(14)、do_fork函數
- struct completion *vfork_done; /* for vfork() */
- int __user *set_child_tid; /* CLONE_CHILD_SETTID */
- int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */
在執行do_fork()時,如果給定特別標志,則vfork_done會指向一個特殊地址。
如果copy_process函數的clone_flags參數的值被置為CLONE_CHILD_SETTID或 CLONE_CHILD_CLEARTID,則會把child_tidptr參數的值分別復制到set_child_tid和 clear_child_tid成員。這些標志說明必須改變子進程用戶態地址空間的child_tidptr所指向的變量的值。
(15)、缺頁統計
- /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
- unsigned long min_flt, maj_flt;
(16)、進程權能
- const struct cred __rcu *real_cred; /* objective and real subjective task
- * credentials (COW) */
- const struct cred __rcu *cred; /* effective (overridable) subjective task
- * credentials (COW) */
- struct cred *replacement_session_keyring; /* for KEYCTL_SESSION_TO_PARENT */
(17)、相應的程序名
- char comm[TASK_COMM_LEN];
(18)、文件
- /* file system info */
- int link_count, total_link_count;
- /* filesystem information */
- struct fs_struct *fs;
- /* open file information */
- struct files_struct *files;
fs用來表示進程與文件系統的聯系,包括當前目錄和根目錄。
files表示進程當前打開的文件。
(19)、進程通信(SYSVIPC)
- #ifdef CONFIG_SYSVIPC
- /* ipc stuff */
- struct sysv_sem sysvsem;
- #endif
(20)、處理器特有數據
- /* CPU-specific state of this task */
- struct thread_struct thread;
(21)、命名空間
- /* namespaces */
- struct nsproxy *nsproxy;
(22)、進程審計
- struct audit_context *audit_context;
- #ifdef CONFIG_AUDITSYSCALL
- uid_t loginuid;
- unsigned int sessionid;
- #endif
(23)、secure computing
- seccomp_t seccomp;
(24)、用於copy_process函數使用CLONE_PARENT 標記時
- /* Thread group tracking */
- u32 parent_exec_id;
- u32 self_exec_id;
(25)、中斷
- #ifdef CONFIG_GENERIC_HARDIRQS
- /* IRQ handler threads */
- struct irqaction *irqaction;
- #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
(26)、task_rq_lock函數所使用的鎖
- /* Protection of the PI data structures: */
- raw_spinlock_t pi_lock;
(27)、基於PI協議的等待互斥鎖,其中PI指的是priority inheritance(優先級繼承)
- #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
(28)、死鎖檢測
- #ifdef CONFIG_DEBUG_MUTEXES
- /* mutex deadlock detection */
- struct mutex_waiter *blocked_on;
- #endif
(29)、lockdep,參見內核說明文檔linux-2.6.38.8/Documentation/lockdep-design.txt
- #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
(30)、JFS文件系統
- /* journalling filesystem info */
- void *journal_info;
(31)、塊設備鏈表
- /* stacked block device info */
- struct bio_list *bio_list;
(32)、內存回收
- struct reclaim_state *reclaim_state;
(33)、存放塊設備I/O數據流量信息
- struct backing_dev_info *backing_dev_info;
(34)、I/O調度器所使用的信息
- struct io_context *io_context;
(35)、記錄進程的I/O計數
- 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
在Ubuntu 11.04上,執行cat獲得進程1的I/O計數如下:
- $ sudo cat /proc/1/io
- rchar: 164258906
- wchar: 455212837
- syscr: 388847
- syscw: 92563
- read_bytes: 439251968
- write_bytes: 14143488
- cancelled_write_bytes: 2134016
輸出的數據項剛好是task_io_accounting結構體的所有成員。
(36)、CPUSET功能
- #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
(37)、Control Groups
- #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_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
(38)、futex同步機制
- #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
(39)、非一致內存訪問(NUMA Non-Uniform Memory Access)
- #ifdef CONFIG_NUMA
- struct mempolicy *mempolicy; /* Protected by alloc_lock */
- short il_next;
- #endif
(40)、文件系統互斥資源
- atomic_t fs_excl; /* holding fs exclusive resources */
(41)、RCU鏈表
- struct rcu_head rcu;
(42)、管道
- struct pipe_inode_info *splice_pipe;
(43)、延遲計數
- #ifdef CONFIG_TASK_DELAY_ACCT
- struct task_delay_info *delays;
- #endif
(44)、fault injection,參考內核說明文件linux-2.6.38.8/Documentation/fault-injection/fault-injection.txt
- #ifdef CONFIG_FAULT_INJECTION
- int make_it_fail;
- #endif
(45)、FLoating proportions
- struct prop_local_single dirties;
(46)、Infrastructure for displayinglatency
- #ifdef CONFIG_LATENCYTOP
- int latency_record_count;
- struct latency_record latency_record[LT_SAVECOUNT];
- #endif
(47)、time slack values,常用於poll和select函數
- unsigned long timer_slack_ns;
- unsigned long default_timer_slack_ns;
(48)、socket控制消息(control message)
- struct list_head *scm_work_list;
(49)、ftrace跟蹤器
- #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 */