Linux 内核结构体(进程内存)
struct task_struct {
volatile long state; //说明了该进程是否可以执行,还是可中断等信息
unsigned long flags; //Flage 是进程号,在调用fork()时给出
int sigpending; //进程上是否有待处理的信号
mm_segment_t addr_limit; //进程地址空间,区分内核进程与普通进程在内存存放的位置不同
//0-0xBFFFFFFF for user-thead
//0-0xFFFFFFFF for kernel-thread
//调度标志,表示该进程是否需要重新调度,若非0,则当从内核态返回到用户态,会发生调度
volatile long need_resched;
int lock_depth; //锁深度
long nice; //进程的基本时间片
//进程的调度策略,有三种,实时进程:SCHED_FIFO,SCHED_RR, 分时进程:SCHED_OTHER
unsigned long policy;
struct mm_struct *mm; //进程内存管理信息
int processor;
//若进程不在任何CPU上运行, cpus_runnable 的值是0，否则是1 这个值在运行队列被锁时更新
unsigned long cpus_runnable, cpus_allowed;
struct list_head run_list; //指向运行队列的指针
unsigned long sleep_time; //进程的睡眠时间
//用于将系统中所有的进程连成一个双向循环链表, 其根是init_task
struct task_struct *next_task, *prev_task;
struct mm_struct *active_mm;
struct list_head local_pages; //指向本地页面
unsigned int allocation_order, nr_local_pages;
struct linux_binfmt *binfmt; //进程所运行的可执行文件的格式
int exit_code, exit_signal;
int pdeath_signal; //父进程终止时向子进程发送的信号
unsigned long personality;
//Linux可以运行由其他UNIX操作系统生成的符合iBCS2标准的程序
int did_exec:1;
pid_t pid; //进程标识符,用来代表一个进程
pid_t pgrp; //进程组标识,表示进程所属的进程组
pid_t tty_old_pgrp; //进程控制终端所在的组标识
pid_t session; //进程的会话标识
pid_t tgid;
int leader; //表示进程是否为会话主管
struct task_struct *p_opptr,*p_pptr,*p_cptr,*p_ysptr,*p_osptr;
struct list_head thread_group; //线程链表
struct task_struct *pidhash_next; //用于将进程链入HASH表
struct task_struct **pidhash_pprev;
wait_queue_head_t wait_chldexit; //供wait4()使用
struct completion *vfork_done; //供vfork() 使用
unsigned long rt_priority; //实时优先级，用它计算实时进程调度时的weight值
//it_real_value，it_real_incr用于REAL定时器，单位为jiffies, 系统根据it_real_value
//设置定时器的第一个终止时间. 在定时器到期时，向进程发送SIGALRM信号，同时根据
//it_real_incr重置终止时间，it_prof_value，it_prof_incr用于Profile定时器，单位为jiffies。
//当进程运行时，不管在何种状态下，每个tick都使it_prof_value值减一，当减到0时，向进程发送
//信号SIGPROF，并根据it_prof_incr重置时间.
//it_virt_value，it_virt_value用于Virtual定时器，单位为jiffies。当进程运行时，不管在何种
//状态下，每个tick都使it_virt_value值减一当减到0时，向进程发送信号SIGVTALRM，根据
//it_virt_incr重置初值。
unsigned long it_real_value, it_prof_value, it_virt_value;
unsigned long it_real_incr, it_prof_incr, it_virt_value;
struct timer_list real_timer; //指向实时定时器的指针
struct tms times; //记录进程消耗的时间
unsigned long start_time; //进程创建的时间
//记录进程在每个CPU上所消耗的用户态时间和核心态时间
long per_cpu_utime[NR_CPUS], per_cpu_stime[NR_CPUS];
//内存缺页和交换信息:
//min_flt, maj_flt累计进程的次缺页数（Copy on Write页和匿名页）和主缺页数（从映射文件或交换
//设备读入的页面数）； nswap记录进程累计换出的页面数，即写到交换设备上的页面数。
//cmin_flt, cmaj_flt, cnswap记录本进程为祖先的所有子孙进程的累计次缺页数，主缺页数和换出页面数。
//在父进程回收终止的子进程时，父进程会将子进程的这些信息累计到自己结构的这些域中
unsigned long min_flt, maj_flt, nswap, cmin_flt, cmaj_flt, cnswap;
int swappable:1; //表示进程的虚拟地址空间是否允许换出
//进程认证信息
//uid,gid为运行该进程的用户的用户标识符和组标识符，通常是进程创建者的uid，gid
//euid，egid为有效uid,gid
//fsuid，fsgid为文件系统uid,gid，这两个ID号通常与有效uid,gid相等，在检查对于文件
//系统的访问权限时使用他们。
//suid，sgid为备份uid,gid
uid_t uid,euid,suid,fsuid;
gid_t gid,egid,sgid,fsgid;
int ngroups; //记录进程在多少个用户组中
gid_t groups[NGROUPS]; //记录进程所在的组
//进程的权能，分别是有效位集合，继承位集合，允许位集合
kernel_cap_t cap_effective, cap_inheritable, cap_permitted;
int keep_capabilities:1;
struct user_struct *user;
struct rlimit rlim[RLIM_NLIMITS]; //与进程相关的资源限制信息
unsigned short used_math; //是否使用FPU
char comm[16]; //进程正在运行的可执行文件名
//文件系统信息
int link_count, total_link_count;
//NULL if no tty 进程所在的控制终端，如果不需要控制终端，则该指针为空
struct tty_struct *tty;
unsigned int locks;
//进程间通信信息
struct sem_undo *semundo; //进程在信号灯上的所有undo操作
struct sem_queue *semsleeping; //当进程因为信号灯操作而挂起时，他在该队列中记录等待的操作
//进程的CPU状态，切换时，要保存到停止进程的task_struct中
struct thread_struct thread;
//文件系统信息
struct fs_struct *fs;
//打开文件信息
struct files_struct *files;
//信号处理函数
spinlock_t sigmask_lock;
struct signal_struct *sig; //信号处理函数
sigset_t blocked; //进程当前要阻塞的信号，每个信号对应一位
struct sigpending pending; //进程上是否有待处理的信号
unsigned long sas_ss_sp;
size_t sas_ss_size;
int (*notifier)(void *priv);
void *notifier_data;
sigset_t *notifier_mask;
u32 parent_exec_id;
u32 self_exec_id;
spinlock_t alloc_lock;
void *journal_info;
};
<include/linux/mm_types.h>
struct mm_struct {
struct {
struct vm_area_struct *mmap; /* list of VMAs */
/*虚拟内存描述符链表，整个地址空间被分成不连续的内存，每片由vm_area_struct管理，所有vma按地址大小链表起来*/
struct rb_root mm_rb;
/*方便增删，把vma传入到红黑树中*/
u64 vmacache_seqnum; /* per-thread vmacache */
#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
rwlock_t mm_rb_lock; /* Speculative page fault field */
#endif
#ifdef CONFIG_MMU
/*函数指针，MMU芯片对应架构自己的分配虚拟内存函数*/
unsigned long (*get_unmapped_area) (struct file *filp,
unsigned long addr, unsigned long len,
unsigned long pgoff, unsigned long flags);
#endif
unsigned long mmap_base; /* base of mmap area */
/*mmap开始映射地址*/
unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */
/*控制上下分配*/
#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
/* Base adresses for compatible mmap() */
unsigned long mmap_compat_base;
unsigned long mmap_compat_legacy_base;
#endif
unsigned long task_size; /* size of task vm space */
/*虚拟地址空间大小*/
unsigned long highest_vm_end; /* highest vma end address */
/*最后一个vma的vm_end值*/
pgd_t * pgd;
/*进程的页全局目录地址*/
/**
* @mm_users: The number of users including userspace.
*
* Use mmget()/mmget_not_zero()/mmput() to modify. When this
* drops to 0 (i.e. when the task exits and there are no other
* temporary reference holders), we also release a reference on
* @mm_count (which may then free the &struct mm_struct if
* @mm_count also drops to 0).
*/
atomic_t mm_users;
/*共享同一个用户虚拟地址空间的任务个数，为0的时候释放这个引用*/
/**
* @mm_count: The number of references to &struct mm_struct
* (@mm_users count as 1).
*
* Use mmgrab()/mmdrop() to modify. When this drops to 0, the
* &struct mm_struct is freed.
*/
atomic_t mm_count;
/*mm被引用的计数，为0时，释放这个结构体*/
#ifdef CONFIG_MMU /*打开的*/
atomic_long_t pgtables_bytes; /* PTE page table pages */
#endif
int map_count; /* number of VMAs */
/*mm中vma的个数*/
spinlock_t page_table_lock; /* Protects page tables and some
* counters
*/
/*自旋锁，保护页表和计数器*/
struct rw_semaphore mmap_sem;
/*操作mmap和mm_rb时，通过锁保护防止并发，读写锁，所以使用信号量*/
struct list_head mmlist; /* List of maybe swapped mm's. These
* are globally strung together off
* init_mm.mmlist, and are protected
* by mmlist_lock
*/
unsigned long hiwater_rss; /* High-watermark of RSS usage */
unsigned long hiwater_vm; /* High-water virtual memory usage */
unsigned long total_vm; /* Total pages mapped */
unsigned long locked_vm; /* Pages that have PG_mlocked set */
unsigned long pinned_vm; /* Refcount permanently increased */
unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
unsigned long stack_vm; /* VM_STACK */
unsigned long def_flags;
spinlock_t arg_lock; /* protect the below fields */
unsigned long start_code, end_code, start_data, end_data;
/*代码段和数据段的起始地址和结束地址*/
unsigned long start_brk, brk, start_stack;
/*堆的起始、结束地址，brk的值通过sys_brk系统调用调整；用户态栈的起始地址*/
unsigned long arg_start, arg_end, env_start, env_end;
/*进程在应用程序启动时传递参数字符串的起始、结束地址；环境变量的起始、结束地址*/
unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
/*
* Special counters, in some configurations protected by the
* page_table_lock, in other configurations by being atomic.
*/
struct mm_rss_stat rss_stat;
struct linux_binfmt *binfmt;
/* Architecture-specific MM context */
mm_context_t context;
unsigned long flags; /* Must use atomic bitops to access */
struct core_state *core_state; /* coredumping support */
#ifdef CONFIG_MEMBARRIER //打开
atomic_t membarrier_state;
#endif
#ifdef CONFIG_AIO //打开
spinlock_t ioctx_lock;
struct kioctx_table __rcu *ioctx_table;
#endif
#ifdef CONFIG_MEMCG //打开
/*
* "owner" points to a task that is regarded as the canonical规范的
* user/owner of this mm. All of the following must be true in
* order for it to be changed:
*
* current == mm->owner
* current->mm != mm
* new_owner->mm == mm
* new_owner->alloc_lock is held
*/
struct task_struct __rcu *owner;
#endif
struct user_namespace *user_ns;
/* store ref to file /proc/<pid>/exe symlink points to */
struct file __rcu *exe_file;
#ifdef CONFIG_MMU_NOTIFIER //打开
struct mmu_notifier_mm *mmu_notifier_mm;
#endif
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS 关闭
pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#endif
#ifdef CONFIG_NUMA_BALANCING //关
/*
* numa_next_scan is the next time that the PTEs will be marked
* pte_numa. NUMA hinting faults will gather statistics and
* migrate pages to new nodes if necessary.
*/
unsigned long numa_next_scan;
/* Restart point for scanning and setting pte_numa */
unsigned long numa_scan_offset;
/* numa_scan_seq prevents two threads setting pte_numa */
int numa_scan_seq;
#endif
/*
* An operation with batched TLB flushing is going on. Anything
* that can move process memory needs to flush the TLB when
* moving a PROT_NONE or PROT_NUMA mapped page.
*/
atomic_t tlb_flush_pending;
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH //关
/* See flush_tlb_batched_pending() */
bool tlb_flush_batched;
#endif
struct uprobes_state uprobes_state;
#ifdef CONFIG_HUGETLB_PAGE //关
atomic_long_t hugetlb_usage;
#endif
struct work_struct async_put_work;
#if IS_ENABLED(CONFIG_HMM)
/* HMM needs to track a few things per mm */
struct hmm *hmm;
#endif
} __randomize_layout;
/*
* The mm_cpumask needs to be at the end of mm_struct, because it
* is dynamically sized based on nr_cpu_ids.
*/
unsigned long cpu_bitmap[];
};
<include/linux/mm_types.h>
struct vm_area_struct {
/* The first cache line has the info for VMA tree walking. */
unsigned long vm_start; /* Our start address within vm_mm. */
unsigned long vm_end; /* The first byte after our end address
within vm_mm. */
/*[vm_start, vm_end) 这么个情况，表示一块虚拟内存空间*/
/* linked list of VM areas per task, sorted by address */
struct vm_area_struct *vm_next, *vm_prev;
/*在mm->mmap链表中前后节点*/
struct rb_node vm_rb;
/*插入到mm->mm_rb红黑树的节点*/
/*
* Largest free memory gap in bytes to the left of this VMA.
* Either between this VMA and vma->vm_prev, or between one of the
* VMAs below us in the VMA rbtree and its ->vm_prev. This helps
* get_unmapped_area find a free area of the right size.
*/
unsigned long rb_subtree_gap;
/*以当前vma为根，左子树中最大可用虚拟内存区域的大小*/
/* Second cache line starts here. */
struct mm_struct *vm_mm; /* The address space we belong to. */
/*同一进程所有的vma指向的vm_mm是相同的*/
pgprot_t vm_page_prot; /* Access permissions of this VMA. */
/*访问权限*/
unsigned long vm_flags; /* Flags, see mm.h. */
/*属性，详看mm.h*/
/*
* For areas with an address space and backing store,
* linkage into the address_space->i_mmap interval tree.
*
* For private anonymous mappings, a pointer to a null terminated string
* in the user process containing the name given to the vma, or NULL
* if unnamed.
*/
union {
struct {
struct rb_node rb;
unsigned long rb_subtree_last;
} shared;
const char __user *anon_name;
};
/*
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
* list, after a COW of one of the file pages. A MAP_SHARED vma
* can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
* or brk vma (with NULL file) can only be in an anon_vma list.
*/
struct list_head anon_vma_chain; /* Serialized by mmap_sem &
* page_table_lock */
struct anon_vma *anon_vma; /* Serialized by page_table_lock */
/* Function pointers to deal with this struct. */
const struct vm_operations_struct *vm_ops;
/*该vma操作函数，包括打开、关闭、建立映射三个函数*/
/* Information about our backing store: */
unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
units */
struct file * vm_file; /* File we map to (can be NULL). */
/*文件映射的文件信息，匿名映射为NULL*/
void * vm_private_data; /* was vm_pte (shared mem) */
atomic_long_t swap_readahead_info;
#ifndef CONFIG_MMU
struct vm_region *vm_region; /* NOMMU mapping region */
#endif
#ifdef CONFIG_NUMA
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
#endif
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
seqcount_t vm_sequence; /* Speculative page fault field */
atomic_t vm_ref_count; /* see vma_get(), vma_put() */
#endif
} __randomize_layout;