Back to Contents

Task Struct

Linux Thread struct

struct thread_struct {
    /* Cached TLS descriptors: */
    struct desc_struct  tls_array[GDT_ENTRY_TLS_ENTRIES];
    unsigned long       sp0;
    unsigned long       sp;
#ifdef CONFIG_X86_32
    unsigned long       sysenter_cs;
    unsigned short      es;
    unsigned short      ds;
    unsigned short      fsindex;
    unsigned short      gsindex;
#ifdef CONFIG_X86_32
    unsigned long       ip;
#ifdef CONFIG_X86_64
    unsigned long       fs;
    unsigned long       gs;

    /* Save middle states of ptrace breakpoints */
    struct perf_event   *ptrace_bps[HBP_NUM];
    /* Debug status used for traps, single steps, etc... */
    unsigned long           debugreg6;
    /* Keep track of the exact dr7 value set by the user */
    unsigned long           ptrace_dr7;
    /* Fault info: */
    unsigned long       cr2;
    unsigned long       trap_nr;
    unsigned long       error_code;
#ifdef CONFIG_VM86
    /* Virtual 86 mode info */
    struct vm86     *vm86;
    /* IO permissions: */
    unsigned long       *io_bitmap_ptr;
    unsigned long       iopl;
    /* Max allowed port in the bitmap, in bytes: */
    unsigned        io_bitmap_max;

    /* Floating point and extended processor state */
    struct fpu      fpu;
     * WARNING: 'fpu' is dynamically-sized.  It *MUST* be at
     * the end.

Linux Task Struct

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;

    struct llist_node wake_entry;
    int on_cpu;
    unsigned int wakee_flips;
    unsigned long wakee_flip_decay_ts;
    struct task_struct *last_wakee;

    int wake_cpu;
    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;
    struct task_group *sched_task_group;
    struct sched_dl_entity dl;

    /* list of struct preempt_notifier: */
    struct hlist_head preempt_notifiers;

    unsigned int btrace_seq;

    unsigned int policy;
    int nr_cpus_allowed;
    cpumask_t cpus_allowed;

    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 */
    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 */

    struct sched_info sched_info;

    struct list_head tasks;
    struct plist_node pushable_tasks;
    struct rb_node pushable_dl_tasks;

    struct mm_struct *mm, *active_mm;
    /* per-thread vma caching */
    u32 vmacache_seqnum;
    struct vm_area_struct *vmacache[VMACACHE_SIZE];
    struct task_rss_stat    rss_stat;
/* task state */
    int exit_state;
    int exit_code, exit_signal;
    int pdeath_signal;  /*  The signal sent when the parent dies  */
    unsigned long jobctl;   /* JOBCTL_*, siglock protected */

    /* Used for emulating ABI behavior of previous Linux versions */
    unsigned int personality;

    /* scheduler bits, serialized by scheduler locks */
    unsigned sched_reset_on_fork:1;
    unsigned sched_contributes_to_load:1;
    unsigned sched_migrated:1;
    unsigned :0; /* force alignment to the next boundary */

    /* unserialized, strictly 'current' */
    unsigned in_execve:1; /* bit to tell LSMs we're in execve */
    unsigned in_iowait:1;
    unsigned memcg_may_oom:1;
    unsigned memcg_kmem_skip_account:1;
    unsigned brk_randomized:1;

    unsigned long atomic_flags; /* Flags needing atomic access. */

    struct restart_block restart_block;

    pid_t pid;
    pid_t tgid;

    /* Canary value for the -fstack-protector gcc feature */
    unsigned long stack_canary;
     * 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;
    struct prev_cputime prev_cputime;
    seqcount_t vtime_seqcount;
    unsigned long long vtime_snap;
    enum {
        /* Task is sleeping or running in a CPU with VTIME inactive */
        VTIME_INACTIVE = 0,
        /* Task runs in userspace in a CPU with VTIME active */
        /* Task runs in kernelspace in a CPU with VTIME active */
    } vtime_snap_whence;
    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 */
    struct nameidata *nameidata;
/* ipc stuff */
    struct sysv_sem sysvsem;
    struct sysv_shm sysvshm;
/* hung task detection */
    unsigned long last_switch_count;
/* 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;

    struct callback_head *task_works;

    struct audit_context *audit_context;
    kuid_t loginuid;
    unsigned int sessionid;
    struct seccomp seccomp;

/* Thread group tracking */
    u32 parent_exec_id;
    u32 self_exec_id;
/* Protection of (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed,
 * mempolicy */
    spinlock_t alloc_lock;

    /* Protection of the PI data structures: */
    raw_spinlock_t pi_lock;

    struct wake_q_node wake_q;

    /* 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;

    /* mutex deadlock detection */
    struct mutex_waiter *blocked_on;
    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;
# 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;
    unsigned int in_ubsan;

/* journalling filesystem info */
    void *journal_info;

/* stacked block device info */
    struct bio_list *bio_list;

/* stack plugging */
    struct blk_plug *plug;

/* 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 */
    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;
    /* 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;
    struct robust_list_head __user *robust_list;
    struct compat_robust_list_head __user *compat_robust_list;
    struct list_head pi_state_list;
    struct futex_pi_state *pi_state_cache;
    struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
    struct mutex perf_event_mutex;
    struct list_head perf_event_list;
    unsigned long preempt_disable_ip;
    struct mempolicy *mempolicy;    /* Protected by alloc_lock */
    short il_next;
    short pref_node_fork;
    int numa_scan_seq;
    unsigned int numa_scan_period;
    unsigned int numa_scan_period_max;
    int numa_preferred_nid;
    unsigned long numa_migrate_retry;
    u64 node_stamp;         /* migration stamp  */
    u64 last_task_numa_placement;
    u64 last_sum_exec_runtime;
    struct callback_head numa_work;

    struct list_head numa_entry;
    struct numa_group *numa_group;

     * numa_faults is an array split into four regions:
     * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
     * in this precise order.
     * faults_memory: Exponential decaying average of faults on a per-node
     * basis. Scheduling placement decisions are made based on these
     * counts. The values remain static for the duration of a PTE scan.
     * faults_cpu: Track the nodes the process was running on when a NUMA
     * hinting fault was incurred.
     * faults_memory_buffer and faults_cpu_buffer: Record faults per node
     * during the current scan window. When the scan completes, the counts
     * in faults_memory and faults_cpu decay and these values are copied.
    unsigned long *numa_faults;
    unsigned long total_numa_faults;

     * numa_faults_locality tracks if faults recorded during the last
     * scan window were remote/local or failed to migrate. The task scan
     * period is adapted based on the locality of the faults with different
     * weights depending on whether they were shared or private faults
    unsigned long numa_faults_locality[3];

    unsigned long numa_pages_migrated;

    struct tlbflush_unmap_batch tlb_ubc;

    struct rcu_head rcu;

     * cache last used pipe for splice
    struct pipe_inode_info *splice_pipe;

    struct page_frag task_frag;

    struct task_delay_info *delays;
    int make_it_fail;
     * 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 */

    int latency_record_count;
    struct latency_record latency_record[LT_SAVECOUNT];
     * 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;

    unsigned int kasan_depth;
    /* 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;
    /* state flags for use by tracers */
    unsigned long trace;
    /* bitmask and counter of trace recursion */
    unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
    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;
    struct uprobe_task *utask;
    unsigned int    sequential_io;
    unsigned int    sequential_io_avg;
    unsigned long   task_state_change;
    int pagefault_disabled;
/* 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!

Back to Contents