Linux 的 Virtual Memory Areas（VMA）：基本概念介紹

由 user process 角度來說明的話，VMA 是 user process 裡一段 virtual address space 區塊；virtual address space 是連續的記憶體空間，當然 VMA 也會是連續的空間。VMA 對 Linux 的主要好處是，可以記憶體的使用更有效率，並且更容易管理user process address space。

從另一個觀念來看，VMA 可以讓 Linux kernel 以 process 的角度來管理 virtual address space。Process 的 VMA 對映，可以由 _/proc//map_s 檔案查詢；例如 pid 1（init）的 VMA mapping 為：

$ cat /proc/1/maps
08048000-0804e000 r-xp 00000000 08:01 12118      /sbin/init
0804e000-08050000 rw-p 00005000 08:01 12118      /sbin/init
08050000-08054000 rwxp 00000000 00:00 0
40000000-40016000 r-xp 00000000 08:01 52297      /lib/ld-2.2.4.so
40016000-40017000 rw-p 00015000 08:01 52297      /lib/ld-2.2.4.so
40024000-40025000 rw-p 00000000 00:00 0
40025000-40157000 r-xp 00000000 08:01 58241      /lib/i686/libc-2.2.4.so
40157000-4015c000 rw-p 00131000 08:01 58241      /lib/i686/libc-2.2.4.so
4015c000-40160000 rw-p 00000000 00:00 0
bfffe000-c0000000 rwxp fffff000 00:00 0

列表中的欄位格式如下：

start-end perm offset major:minor inode image

Linux 以 struct vm_area_struct 資料結構來紀錄每一「區塊」的 VMA 資訊（_include/linux/mm.h_）：

struct vm_area_struct {
        struct mm_struct * vm_mm;
        unsigned long vm_start;
        unsigned long vm_end;

struct vm_area_struct *vm_next;

pgprot_t vm_page_prot;
unsigned long vm_flags;

rb_node_t vm_rb;

struct vm_area_struct *vm_next_share;
struct vm_area_struct **vm_pprev_share;

struct vm_operations_struct * vm_ops;

unsigned long vm_pgoff;

struct file * vm_file;
unsigned long vm_raend;
void * vm_private_data;
};

struct vm_area_struct 裡有 3 個欄位，用來來維護 VMA 資料結構：

˙ _unsigned long vm_start_：記錄此 VMA 區塊的開始位址（start address）。˙ _unsigned long vm_end_：記錄此 VMA 區塊的結束位址（end address）。
˙ _struct vm_area_struct *vm_next_：指向下一個 VMA 區塊結構的指標（Linux 以 linked list 資料結構維護每一個 VMA 區塊）。

VMA 的實作主要是為了能更有效率地管理記憶體，並且是基於 paging 系統之上所發展出的；VMA 是比原始 paging 理論更高階的記憶體管理方法。

Linux 的 Virtual Memory Areas（VMA）：基本概念介紹

圖：Process 與 VMA 整體觀念

Memory Descriptor

Linux 的「Process Descriptor」資料結構為 struct task_struct_（include/linux/sched.h）。Process descriptor 裡的_mm field 紀錄了 process 的 VMA 資訊：

struct task_struct {
          ...
          struct mm_struct *mm;
          ...
}

struct mm_struct 即是 Linux 提供的「Memory Descriptor」資料結構，以下是 struct mm_struct 的原型宣告：

struct mm_struct {
          struct vm_area_struct * mmap;       /* list of VMAs */
          struct rb_root mm_rb;
          struct vm_area_struct * mmap_cache;      /* last find_vma result */
          unsigned long (*get_unmapped_area) (struct file *filp,
                                         unsigned long addr, unsigned long len,
                                         unsigned long pgoff, unsigned long flags);
          void (*unmap_area) (struct mm_struct *mm, unsigned long addr);
          unsigned long mmap_base;                 /* base of mmap area */
          unsigned long task_size;                 /* size of task vm space */
          unsigned long cached_hole_size;      /* if non-zero, the largest hole below free_area_cache */
          unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */
          pgd_t * pgd;
          atomic_t mm_users;                       /* How many users with user space? */
          atomic_t mm_count;                       /* How many references to "struct mm_struct" (users count as 1) */
          int map_count;                                     /* number of VMAs */
          struct rw_semaphore mmap_sem;
          spinlock_t page_table_lock;              /* Protects page tables and some counters */

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
                                                    */

/* Special counters, in some configurations protected by the
           * page_table_lock, in other configurations by being atomic.
           */
          mm_counter_t _file_rss;
          mm_counter_t _anon_rss;

unsigned long hiwater_rss; /* High-watermark of RSS usage */
unsigned long hiwater_vm; /* High-water virtual memory usage */

unsigned long total_vm, locked_vm, shared_vm, exec_vm;
          unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
          unsigned long start_code, end_code, start_data, end_data;
          unsigned long start_brk, brk, start_stack;
          unsigned long arg_start, arg_end, env_start, env_end;

unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */

unsigned dumpable:2;
cpumask_t cpu_vm_mask;

/* Architecture-specific MM context */
mm_context_t context;

/* Token based thrashing protection. */
unsigned long swap_token_time;
char recent_pagein;

/* coredumping support */
int core_waiters;
struct completion *core_startup_done, core_done;

/* aio bits */
rwlock_t ioctx_list_lock;
struct kioctx *ioctx_list;
};

Memory descriptor 故名思義，是用來描述 process 記憶體資訊的資料結構。由 struct mm_struct 裡可以看到一個稱為_mmap_ 的 field，mmap 的 data type 為 _struct vm_area_struct_，這個資料結構即是我們在「Linux 的 Virtual Memory Areas（VMA****）：基本概念介紹」所介紹的 VMA 資料結構。

VMA 與 ELF Image 的對映關係

在「Linux 的 Virtual Memory Areas（VMA****）：基本概念介紹」曾經介紹過，Process 的 VMA 對映，可以由_/proc//map_s 檔案查詢；例如 pid 1（init）的 VMA mapping 為：