struct inode结构体存在Linux内核中,表示一个静态文件,每个文件都会对应唯一的struct inode结构体
struct inode {
umode_t i_mode; // 文件权限
unsigned short i_opflags;
kuid_t i_uid; //用户id(可用id linux查看)
kgid_t i_gid; //组id(在 /etc/passworld 和 /etc/group 中)
unsigned int i_flags; //inode号
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
#endif
const struct inode_operations *i_op;
struct super_block *i_sb;
struct address_space *i_mapping;
#ifdef CONFIG_SECURITY
void *i_security;
#endif
/* Stat data, not accessed from path walking */
unsigned long i_ino;
/*
* Filesystems may only read i_nlink directly. They shall use the
* following functions for modification:
*
* (set|clear|inc|drop)_nlink
* inode_(inc|dec)_link_count
*/
union {
const unsigned int i_nlink;
unsigned int __i_nlink;
};
dev_t i_rdev; //设备号
loff_t i_size;
struct timespec64 i_atime;
struct timespec64 i_mtime;
struct timespec64 i_ctime;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
u8 i_blkbits;
u8 i_write_hint;
blkcnt_t i_blocks;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
#endif
/* Misc */
unsigned long i_state;
struct rw_semaphore i_rwsem;
unsigned long dirtied_when; /* jiffies of first dirtying */
unsigned long dirtied_time_when;
struct hlist_node i_hash;
struct list_head i_io_list; /* backing dev IO list */
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *i_wb; /* the associated cgroup wb */
/* foreign inode detection, see wbc_detach_inode() */
int i_wb_frn_winner;
u16 i_wb_frn_avg_time;
u16 i_wb_frn_history;
#endif
struct list_head i_lru; /* inode LRU list */
struct list_head i_sb_list;
struct list_head i_wb_list; /* backing dev writeback list */
union {
struct hlist_head i_dentry;
struct rcu_head i_rcu;
};
atomic64_t i_version;
atomic64_t i_sequence; /* see futex */
atomic_t i_count;
atomic_t i_dio_count;
atomic_t i_writecount;
#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
atomic_t i_readcount; /* struct files open RO */
#endif
union {
const struct file_operations *i_fop; //操作方法结构体
void (*free_inode)(struct inode *);
};
struct file_lock_context *i_flctx;
struct address_space i_data;
struct list_head i_devices;
union { //表明设备类型(联合体只能填一种)
struct pipe_inode_info *i_pipe;//管道文件
struct block_device *i_bdev; //块设备
struct cdev *i_cdev; //字符设备
char *i_link;
unsigned i_dir_seq;
};
__u32 i_generation;
#ifdef CONFIG_FSNOTIFY
__u32 i_fsnotify_mask; /* all events this inode cares about */
struct fsnotify_mark_connector __rcu *i_fsnotify_marks;
#endif
#ifdef CONFIG_FS_ENCRYPTION
struct fscrypt_info *i_crypt_info;
#endif
#ifdef CONFIG_FS_VERITY
struct fsverity_info *i_verity_info;
#endif
void *i_private; //私有数据
} __randomize_layout;
struct file结构体存在Linux内核中,表示一个被打开的文件,它由内核在打开文件时创建,传递给正在操作文件的函数,每open一次就会生成一个struct file结构体,所以一个struct inode结构体可以对应多个struct file结构体,当文件被关闭时,内核释放该结构体
struct file {
union {
struct llist_node fu_llist; //用于通用文件对象链表的指针
struct rcu_head fu_rcuhead; //linux2.6内核新的锁机制
} f_u;
struct path f_path;
struct inode *f_inode; /* cached value */
const struct file_operations *f_op; //该文件的操作方法
/*
* Protects f_ep_links, f_flags.
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
enum rw_hint f_write_hint;
atomic_long_t f_count;
unsigned int f_flags; //标志位,按bit位表示,对应open的int flags参数,
//其中包含有驱动程序是否支持非阻塞操作的标志位
fmode_t f_mode; //打开文件的权限
struct mutex f_pos_lock;
loff_t f_pos; //文件指针的偏移量
struct fown_struct f_owner;
const struct cred *f_cred;
struct file_ra_state f_ra;
u64 f_version;
#ifdef CONFIG_SECURITY
void *f_security;
#endif
/* needed for tty driver, and maybe others */
void *private_data; //私有数据
#ifdef CONFIG_EPOLL
/* Used by fs/eventpoll.c to link all the hooks to this file */
struct list_head f_ep_links;
struct list_head f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
errseq_t f_wb_err;
errseq_t f_sb_err; /* for syncfs */
}
FILE结构体存在用户空间中,定义在C库stdio.h中,专门用于操作文件(文件I/O)的结构体,每fopen打开一个文件就会生成一个FILE结构体,记录被打开文件的各种信息,每个正在运行的程序中都默认生成三个FILE结构体stdin、stdout、stderr
typedef struct _IO_FILE FILE;
struct _IO_FILE {
int _flags; /* High-order word is _IO_MAGIC; rest is flags. */
#define _IO_file_flags _flags
/* The following pointers correspond to the C++ streambuf protocol. */
/* Note: Tk uses the _IO_read_ptr and _IO_read_end fields directly. */
char* _IO_read_ptr; /* Current read pointer */
char* _IO_read_end; /* End of get area. */
char* _IO_read_base; /* Start of putback+get area. */
char* _IO_write_base; /* Start of put area. */
char* _IO_write_ptr; /* Current put pointer. */
char* _IO_write_end; /* End of put area. */
char* _IO_buf_base; /* Start of reserve area. */
char* _IO_buf_end; /* End of reserve area. */
/* The following fields are used to support backing up and undo. */
char *_IO_save_base; /* Pointer to start of non-current get area. */
char *_IO_backup_base; /* Pointer to first valid character of backup area */
char *_IO_save_end; /* Pointer to end of non-current get area. */
struct _IO_marker *_markers;
struct _IO_FILE *_chain;
int _fileno;
#if 0
int _blksize;
#else
int _flags2;
#endif
_IO_off_t _old_offset; /* This used to be _offset but it's too small. */
#define __HAVE_COLUMN /* temporary */
/* 1+column number of pbase(); 0 is unknown. */
unsigned short _cur_column;
signed char _vtable_offset;
char _shortbuf[1];
/* char* _save_gptr; char* _save_egptr; */
_IO_lock_t *_lock;
#ifdef _IO_USE_OLD_IO_FILE
};
struct stat结构体存在用户空间中,专门用于记录一个文件的属性,供int stat((const char *)pathname, struct stat *statbuf)函数使用,从内核struct inode结构体获取到文件信息后存入struct stat结构体
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
struct stat
{
__dev_t st_dev; //硬件设备号,内核识别驱动的唯一凭证
#ifndef __x86_64__
unsigned short int __pad1;
#endif
#if defined __x86_64__ || !defined __USE_FILE_OFFSET64
__ino_t st_ino; //标号,文件系统识别文件的唯一凭证
#else
__ino_t __st_ino; /* 32bit file serial number. */
#endif
#ifndef __x86_64__
__mode_t st_mode; /* File mode. */
__nlink_t st_nlink; /* Link count. */
#else
__nlink_t st_nlink; //文件硬链接数
__mode_t st_mode; //文件类型和权限
#endif
__uid_t st_uid; //用户识别号
__gid_t st_gid; //组识别号
#ifdef __x86_64__
int __pad0;
#endif
__dev_t st_rdev; //驱动设备号
#ifndef __x86_64__
unsigned short int __pad2;
#endif
#if defined __x86_64__ || !defined __USE_FILE_OFFSET64
__off_t st_size; //文件字节数
#else
__off64_t st_size; //文件字节数
#endif
__blksize_t st_blksize; //包含该文件的磁盘大小
#if defined __x86_64__ || !defined __USE_FILE_OFFSET64
__blkcnt_t st_blocks; //占磁盘块数
#else
__blkcnt64_t st_blocks; //占磁盘块数
#endif
#ifdef __USE_XOPEN2K8
/* Nanosecond resolution timestamps are stored in a format
equivalent to 'struct timespec'. This is the type used
whenever possible but the Unix namespace rules do not allow the
identifier 'timespec' to appear in the <sys/stat.h> header.
Therefore we have to handle the use of this header in strictly
standard-compliant sources special. */
struct timespec st_atim; //最后一次访问时间
struct timespec st_mtim; /* Time of last modification. */
struct timespec st_ctim; //最后一次修改时间
# define st_atime st_atim.tv_sec /* Backward compatibility. */
# define st_mtime st_mtim.tv_sec
# define st_ctime st_ctim.tv_sec
#else
__time_t st_atime; /* Time of last access. */
__syscall_ulong_t st_atimensec; /* Nscecs of last access. */
__time_t st_mtime; /* Time of last modification. */
__syscall_ulong_t st_mtimensec; /* Nsecs of last modification. */
__time_t st_ctime; /* Time of last status change. */
__syscall_ulong_t st_ctimensec; /* Nsecs of last status change. */
#endif
#ifdef __x86_64__
__syscall_slong_t __glibc_reserved[3];
#else
# ifndef __USE_FILE_OFFSET64
unsigned long int __glibc_reserved4;
unsigned long int __glibc_reserved5;
# else
__ino64_t st_ino; /* File serial number. */
# endif
#endif
};
#ifdef __USE_LARGEFILE64
/* Note stat64 has the same shape as stat for x86-64. */
struct stat64
{
__dev_t st_dev; /* Device. */
# ifdef __x86_64__
__ino64_t st_ino; /* File serial number. */
__nlink_t st_nlink; /* Link count. */
__mode_t st_mode; /* File mode. */
# else
unsigned int __pad1;
__ino_t __st_ino; /* 32bit file serial number. */
__mode_t st_mode; /* File mode. */
__nlink_t st_nlink; /* Link count. */
# endif
__uid_t st_uid; /* User ID of the file's owner. */
__gid_t st_gid; /* Group ID of the file's group.*/
# ifdef __x86_64__
int __pad0;
__dev_t st_rdev; /* Device number, if device. */
__off_t st_size; /* Size of file, in bytes. */
# else
__dev_t st_rdev; /* Device number, if device. */
unsigned int __pad2;
__off64_t st_size; /* Size of file, in bytes. */
# endif
__blksize_t st_blksize; /* Optimal block size for I/O. */
__blkcnt64_t st_blocks; /* Nr. 512-byte blocks allocated. */
# ifdef __USE_XOPEN2K8
/* Nanosecond resolution timestamps are stored in a format
equivalent to 'struct timespec'. This is the type used
whenever possible but the Unix namespace rules do not allow the
identifier 'timespec' to appear in the <sys/stat.h> header.
Therefore we have to handle the use of this header in strictly
standard-compliant sources special. */
struct timespec st_atim; /* Time of last access. */
struct timespec st_mtim; /* Time of last modification. */
struct timespec st_ctim; /* Time of last status change. */
# else
__time_t st_atime; /* Time of last access. */
__syscall_ulong_t st_atimensec; /* Nscecs of last access. */
__time_t st_mtime; /* Time of last modification. */
__syscall_ulong_t st_mtimensec; /* Nsecs of last modification. */
__time_t st_ctime; /* Time of last status change. */
__syscall_ulong_t st_ctimensec; /* Nsecs of last status change. */
# endif
# ifdef __x86_64__
__syscall_slong_t __glibc_reserved[3];
# else
__ino64_t st_ino; /* File serial number. */
# endif
};
struct dirent结构体存在Linux内核中,表示一个目录文件,只起索引作用,文件具体信息还是在struct inode结构体中
struct dirent
{
#ifndef __USE_FILE_OFFSET64
__ino_t d_ino; //文件inode号
__off_t d_off; //在目录文件中的偏移量
#else
__ino64_t d_ino;
__off64_t d_off;
#endif
unsigned short int d_reclen;//direct结构体长度
unsigned char d_type; //文件类型
char d_name[256]; //文件名
};
#ifdef __USE_LARGEFILE64
struct dirent64
{
__ino64_t d_ino;
__off64_t d_off;
unsigned short int d_reclen;
unsigned char d_type;
char d_name[256]; /* We must not include limits.h! */
};
DIR结构体存在用户空间中,专门用于操作目录(文件I/O)的结构体
typedef struct __dirstream DIR;
struct __dirstream{
void *__fd; /* `struct hurd_fd' pointer for descriptor. */
char *__data; /* Directory block. */
int __entry_data; /* Entry number `__data' corresponds to. */
char *__ptr; /* Current pointer into the block. */
int __entry_ptr; /* Entry number `__ptr' corresponds to. */
size_t __allocation; /* Space allocated for the block. */
size_t __size; /* Total valid data in the block. */
__libc_lock_define (, __lock) /* Mutex lock for this structure. */
};
task_struct结构体存在Linux内核中,表示一个进程。在Linux中 ,因为线程没有其调度算法和数据结构,所以线程都是当做进程来实现的,task_struct结构体也用来表示线程
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
/* -1 unrunnable, 0 runnable, >0 stopped: */
volatile long state;
/*
* This begins the randomizable portion of task_struct. Only
* scheduling-critical items should be added above here.
*/
randomized_struct_fields_start
void *stack;
refcount_t usage;
/* Per task flags (PF_*), defined further below: */
unsigned int flags;
unsigned int ptrace;
#ifdef CONFIG_SMP
struct llist_node wake_entry;
int on_cpu;
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* Current CPU: */
unsigned int cpu;
#endif
unsigned int wakee_flips;
unsigned long wakee_flip_decay_ts;
struct task_struct *last_wakee;
/*
* recent_used_cpu is initially set as the last CPU used by a task
* that wakes affine another task. Waker/wakee relationships can
* push tasks around a CPU where each wakeup moves to the next one.
* Tracking a recently used CPU allows a quick search for a recently
* used CPU that may be idle.
*/
int recent_used_cpu;
int wake_cpu;
#endif
int on_rq;
int prio;
int static_prio;
int 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_UCLAMP_TASK
/* Clamp values requested for a scheduling entity */
struct uclamp_se uclamp_req[UCLAMP_CNT];
/* Effective clamp values used for a scheduling entity */
struct uclamp_se uclamp[UCLAMP_CNT];
#endif
#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;
const cpumask_t *cpus_ptr;
cpumask_t cpus_mask;
#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;
u8 rcu_tasks_holdout;
u8 rcu_tasks_idx;
int rcu_tasks_idle_cpu;
struct list_head rcu_tasks_holdout_list;
#endif /* #ifdef CONFIG_TASKS_RCU */
struct sched_info sched_info;
struct list_head tasks;
#ifdef CONFIG_SMP
struct plist_node pushable_tasks;
struct rb_node pushable_dl_tasks;
#endif
struct mm_struct *mm;
struct mm_struct *active_mm;
/* Per-thread vma caching: */
struct vmacache vmacache;
#ifdef SPLIT_RSS_COUNTING
struct task_rss_stat rss_stat;
#endif
int exit_state;
int exit_code;
int exit_signal;
/* The signal sent when the parent dies: */
int pdeath_signal;
/* JOBCTL_*, siglock protected: */
unsigned long jobctl;
/* 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
/* Force alignment to the next boundary: */
unsigned :0;
/* Unserialized, strictly 'current' */
/* Bit to tell LSMs we're in execve(): */
unsigned in_execve:1;
unsigned in_iowait:1;
#ifndef TIF_RESTORE_SIGMASK
unsigned restore_sigmask:1;
#endif
#ifdef CONFIG_MEMCG
unsigned in_user_fault:1;
#endif
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
#ifdef CONFIG_CGROUPS
/* disallow userland-initiated cgroup migration */
unsigned no_cgroup_migration:1;
/* task is frozen/stopped (used by the cgroup freezer) */
unsigned frozen:1;
#endif
#ifdef CONFIG_BLK_CGROUP
/* to be used once the psi infrastructure lands upstream. */
unsigned use_memdelay:1;
#endif
unsigned long atomic_flags; /* Flags requiring atomic access. */
struct restart_block restart_block;
pid_t pid;
pid_t tgid;
#ifdef CONFIG_STACKPROTECTOR
/* Canary value for the -fstack-protector GCC feature: */
unsigned long stack_canary;
#endif
/*
* Pointers to the (original) parent process, youngest child, younger sibling,
* older sibling, respectively. (p->father can be replaced with
* p->real_parent->pid)
*/
/* Real parent process: */
struct task_struct __rcu *real_parent;
/* Recipient of SIGCHLD, wait4() reports: */
struct task_struct __rcu *parent;
/*
* Children/sibling form the list of natural children:
*/
struct list_head children;
struct list_head sibling;
struct task_struct *group_leader;
/*
* 'ptraced' is the list of tasks this task is using ptrace() on.
*
* This includes both natural children and PTRACE_ATTACH targets.
* 'ptrace_entry' is this task's link on the p->parent->ptraced list.
*/
struct list_head ptraced;
struct list_head ptrace_entry;
/* PID/PID hash table linkage. */
struct pid *thread_pid;
struct hlist_node pid_links[PIDTYPE_MAX];
struct list_head thread_group;
struct list_head thread_node;
struct completion *vfork_done;
/* CLONE_CHILD_SETTID: */
int __user *set_child_tid;
/* CLONE_CHILD_CLEARTID: */
int __user *clear_child_tid;
u64 utime;
u64 stime;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
u64 utimescaled;
u64 stimescaled;
#endif
u64 gtime;
struct prev_cputime prev_cputime;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
struct vtime vtime;
#endif
#ifdef CONFIG_NO_HZ_FULL
atomic_t tick_dep_mask;
#endif
/* Context switch counts: */
unsigned long nvcsw;
unsigned long nivcsw;
/* Monotonic time in nsecs: */
u64 start_time;
/* Boot based time in nsecs: */
u64 start_boottime;
/* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */
unsigned long min_flt;
unsigned long maj_flt;
/* Empty if CONFIG_POSIX_CPUTIMERS=n */
struct posix_cputimers posix_cputimers;
/* Process credentials: */
/* Tracer's credentials at attach: */
const struct cred __rcu *ptracer_cred;
/* Objective and real subjective task credentials (COW): */
const struct cred __rcu *real_cred;
/* Effective (overridable) subjective task credentials (COW): */
const struct cred __rcu *cred;
#ifdef CONFIG_KEYS
/* Cached requested key. */
struct key *cached_requested_key;
#endif
/*
* executable name, excluding path.
*
* - normally initialized setup_new_exec()
* - access it with [gs]et_task_comm()
* - lock it with task_lock()
*/
char comm[TASK_COMM_LEN];
struct nameidata *nameidata;
#ifdef CONFIG_SYSVIPC
struct sysv_sem sysvsem;
struct sysv_shm sysvshm;
#endif
#ifdef CONFIG_DETECT_HUNG_TASK
unsigned long last_switch_count;
unsigned long last_switch_time;
#endif
/* Filesystem information: */
struct fs_struct *fs;
/* Open file information: */
struct files_struct *files;
/* Namespaces: */
struct nsproxy *nsproxy;
/* Signal handlers: */
struct signal_struct *signal;
struct sighand_struct __rcu *sighand;
sigset_t blocked;
sigset_t real_blocked;
/* Restored if set_restore_sigmask() was used: */
sigset_t saved_sigmask;
struct sigpending pending;
unsigned long sas_ss_sp;
size_t sas_ss_size;
unsigned int sas_ss_flags;
struct callback_head *task_works;
#ifdef CONFIG_AUDIT
#ifdef CONFIG_AUDITSYSCALL
struct audit_context *audit_context;
#endif
kuid_t loginuid;
unsigned int sessionid;
#endif
struct seccomp seccomp;
/* Thread group tracking: */
u64 parent_exec_id;
u64 self_exec_id;
/* Protection against (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_cached pi_waiters;
/* Updated under owner's pi_lock and rq lock */
struct task_struct *pi_top_task;
/* Deadlock detection and priority inheritance handling: */
struct rt_mutex_waiter *pi_blocked_on;
#endif
#ifdef CONFIG_DEBUG_MUTEXES
/* Mutex deadlock detection: */
struct mutex_waiter *blocked_on;
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
int non_block_count;
#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];
#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;
#ifdef CONFIG_COMPACTION
struct capture_control *capture_control;
#endif
/* Ptrace state: */
unsigned long ptrace_message;
kernel_siginfo_t *last_siginfo;
struct task_io_accounting ioac;
#ifdef CONFIG_PSI
/* Pressure stall state */
unsigned int psi_flags;
#endif
#ifdef CONFIG_TASK_XACCT
/* Accumulated RSS usage: */
u64 acct_rss_mem1;
/* Accumulated virtual memory usage: */
u64 acct_vm_mem1;
/* stime + utime since last update: */
u64 acct_timexpd;
#endif
#ifdef CONFIG_CPUSETS
/* Protected by ->alloc_lock: */
nodemask_t mems_allowed;
/* Seqence number to catch updates: */
seqcount_t mems_allowed_seq;
int cpuset_mem_spread_rotor;
int cpuset_slab_spread_rotor;
#endif
#ifdef CONFIG_CGROUPS
/* Control Group info protected by css_set_lock: */
struct css_set __rcu *cgroups;
/* cg_list protected by css_set_lock and tsk->alloc_lock: */
struct list_head cg_list;
#endif
#ifdef CONFIG_X86_CPU_RESCTRL
u32 closid;
u32 rmid;
#endif
#ifdef CONFIG_FUTEX
struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
struct compat_robust_list_head __user *compat_robust_list;
#endif
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
struct mutex futex_exit_mutex;
unsigned int futex_state;
#endif
#ifdef CONFIG_PERF_EVENTS
struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
struct mutex perf_event_mutex;
struct list_head perf_event_list;
#endif
#ifdef CONFIG_DEBUG_PREEMPT
unsigned long preempt_disable_ip;
#endif
#ifdef CONFIG_NUMA
/* Protected by alloc_lock: */
struct mempolicy *mempolicy;
short il_prev;
short pref_node_fork;
#endif
#ifdef CONFIG_NUMA_BALANCING
int numa_scan_seq;
unsigned int numa_scan_period;
unsigned int numa_scan_period_max;
int numa_preferred_nid;
unsigned long numa_migrate_retry;
/* Migration stamp: */
u64 node_stamp;
u64 last_task_numa_placement;
u64 last_sum_exec_runtime;
struct callback_head numa_work;
/*
* This pointer is only modified for current in syscall and
* pagefault context (and for tasks being destroyed), so it can be read
* from any of the following contexts:
* - RCU read-side critical section
* - current->numa_group from everywhere
* - task's runqueue locked, task not running
*/
struct numa_group __rcu *numa_group;
/*
* numa_faults is an array split into four regions:
* faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
* in this precise order.
*
* faults_memory: Exponential decaying average of faults on a per-node
* basis. Scheduling placement decisions are made based on these
* counts. The values remain static for the duration of a PTE scan.
* faults_cpu: Track the nodes the process was running on when a NUMA
* hinting fault was incurred.
* faults_memory_buffer and faults_cpu_buffer: Record faults per node
* during the current scan window. When the scan completes, the counts
* in faults_memory and faults_cpu decay and these values are copied.
*/
unsigned long *numa_faults;
unsigned long total_numa_faults;
/*
* numa_faults_locality tracks if faults recorded during the last
* scan window were remote/local or failed to migrate. The task scan
* period is adapted based on the locality of the faults with different
* weights depending on whether they were shared or private faults
*/
unsigned long numa_faults_locality[3];
unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_RSEQ
struct rseq __user *rseq;
u32 rseq_sig;
/*
* RmW on rseq_event_mask must be performed atomically
* with respect to preemption.
*/
unsigned long rseq_event_mask;
#endif
struct tlbflush_unmap_batch tlb_ubc;
union {
refcount_t rcu_users;
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;
unsigned int fail_nth;
#endif
/*
* When (nr_dirtied >= nr_dirtied_pause), it's time to call
* balance_dirty_pages() for a dirty throttling pause:
*/
int nr_dirtied;
int nr_dirtied_pause;
/* Start of a write-and-pause period: */
unsigned long dirty_paused_when;
#ifdef CONFIG_LATENCYTOP
int latency_record_count;
struct latency_record latency_record[LT_SAVECOUNT];
#endif
/*
* Time slack values; these are used to round up poll() and
* select() etc timeout values. These are in nanoseconds.
*/
u64 timer_slack_ns;
u64 default_timer_slack_ns;
#ifdef CONFIG_KASAN
unsigned int kasan_depth;
#endif
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/* Index of current stored address in ret_stack: */
int curr_ret_stack;
int curr_ret_depth;
/* Stack of return addresses for return function tracing: */
struct ftrace_ret_stack *ret_stack;
/* Timestamp for last schedule: */
unsigned long long ftrace_timestamp;
/*
* Number of functions that haven't been traced
* because of depth overrun:
*/
atomic_t trace_overrun;
/* Pause tracing: */
atomic_t tracing_graph_pause;
#endif
#ifdef CONFIG_TRACING
/* State flags for use by tracers: */
unsigned long trace;
/* Bitmask and counter of trace recursion: */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
#ifdef CONFIG_KCOV
/* See kernel/kcov.c for more details. */
/* Coverage collection mode enabled for this task (0 if disabled): */
unsigned int kcov_mode;
/* Size of the kcov_area: */
unsigned int kcov_size;
/* Buffer for coverage collection: */
void *kcov_area;
/* KCOV descriptor wired with this task or NULL: */
struct kcov *kcov;
/* KCOV common handle for remote coverage collection: */
u64 kcov_handle;
/* KCOV sequence number: */
int kcov_sequence;
#endif
#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg_in_oom;
gfp_t memcg_oom_gfp_mask;
int memcg_oom_order;
/* Number of pages to reclaim on returning to userland: */
unsigned int memcg_nr_pages_over_high;
/* Used by memcontrol for targeted memcg charge: */
struct mem_cgroup *active_memcg;
#endif
#ifdef CONFIG_BLK_CGROUP
struct request_queue *throttle_queue;
#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
#endif
#if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE)
unsigned int sequential_io;
unsigned int sequential_io_avg;
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
unsigned long task_state_change;
#endif
int pagefault_disabled;
#ifdef CONFIG_MMU
struct task_struct *oom_reaper_list;
#endif
#ifdef CONFIG_VMAP_STACK
struct vm_struct *stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* A live task holds one reference: */
refcount_t stack_refcount;
#endif
#ifdef CONFIG_LIVEPATCH
int patch_state;
#endif
#ifdef CONFIG_SECURITY
/* Used by LSM modules for access restriction: */
void *security;
#endif
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
unsigned long lowest_stack;
unsigned long prev_lowest_stack;
#endif
/*
* New fields for task_struct should be added above here, so that
* they are included in the randomized portion of task_struct.
*/
randomized_struct_fields_end
/* 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!
*/
};