《Linux内核设计与实现》读书笔记（十五）- 进程地址空间(kernel 2.6.32.60)

struct mm_struct {
    struct vm_area_struct * mmap;        /* [内存区域]链表 */
    struct rb_root mm_rb;               /* [内存区域]红黑树 */
    struct vm_area_struct * mmap_cache;    /* 最近一次访问的[内存区域] */
    unsigned long (*get_unmapped_area) (struct file *filp,
                unsigned long addr, unsigned long len,
                unsigned long pgoff, unsigned long flags);  /* 获取指定区间内一个还未映射的地址，出错时返回错误码 */
    void (*unmap_area) (struct mm_struct *mm, unsigned long addr);  /* 取消地址 addr 的映射 */
    unsigned long mmap_base;        /* 地址空间中可以用来映射的首地址 */
    unsigned long task_size;        /* 进程的虚拟地址空间大小 */
    unsigned long cached_hole_size;     /* 如果不空的话，就是 free_area_cache 后最大的空洞 */
    unsigned long free_area_cache;        /* 地址空间的第一个空洞 */
    pgd_t * pgd;                        /* 页全局目录 */
    atomic_t mm_users;            /* 使用地址空间的用户数 */
    atomic_t mm_count;            /* 实际使用地址空间的计数， (users count as 1) */
    int map_count;                /* [内存区域]个数 */
    struct rw_semaphore mmap_sem;   /* 内存区域信号量 */
    spinlock_t page_table_lock;        /* 页表锁 */

    struct list_head mmlist;        /* 所有地址空间形成的链表 */

    /* 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; /* 代码段，数据段的开始和结束地址 */
    unsigned long start_brk, brk, start_stack; /* 堆的首地址，尾地址，进程栈首地址 */
    unsigned long arg_start, arg_end, env_start, env_end; /* 命令行参数，环境变量首地址，尾地址 */

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

    struct linux_binfmt *binfmt;

    cpumask_t cpu_vm_mask;

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

    /* Swap token stuff */
    /*
     * Last value of global fault stamp as seen by this process.
     * In other words, this value gives an indication of how long
     * it has been since this task got the token.
     * Look at mm/thrash.c
     */
    unsigned int faultstamp;
    unsigned int token_priority;
    unsigned int last_interval;

    unsigned long flags; /* Must use atomic bitops to access the bits */

    struct core_state *core_state; /* coredumping support */
#ifdef CONFIG_AIO
    spinlock_t        ioctx_lock;
    struct hlist_head    ioctx_list;
#endif
#ifdef CONFIG_MM_OWNER
    /*
     * "owner" points to a task that is regarded as the canonical
     * 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 *owner;
#endif

#ifdef CONFIG_PROC_FS
    /* store ref to file /proc/<pid>/exe symlink points to */
    struct file *exe_file;
    unsigned long num_exe_file_vmas;
#endif
#ifdef CONFIG_MMU_NOTIFIER
    struct mmu_notifier_mm *mmu_notifier_mm;
#endif
};

struct vm_area_struct {
    struct mm_struct * vm_mm;    /* 相关的 mm_struct 结构体 */
    unsigned long vm_start;        /* 内存区域首地址 */
    unsigned long vm_end;        /* 内存区域尾地址 */

    /* linked list of VM areas per task, sorted by address */
    struct vm_area_struct *vm_next, *vm_prev;  /* VMA链表 */

    pgprot_t vm_page_prot;        /* 访问控制权限 */
    unsigned long vm_flags;        /* 标志 */

    struct rb_node vm_rb;       /* 树上的VMA节点 */

    /*
     * For areas with an address space and backing store,
     * linkage into the address_space->i_mmap prio tree, or
     * linkage to the list of like vmas hanging off its node, or
     * linkage of vma in the address_space->i_mmap_nonlinear list.
     */
    union {
        struct {
            struct list_head list;
            void *parent;    /* aligns with prio_tree_node parent */
            struct vm_area_struct *head;
        } vm_set;

        struct raw_prio_tree_node prio_tree_node;
    } shared;

    /*
     * 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_node;    /* Serialized by anon_vma->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;

    /* Information about our backing store: */
    unsigned long vm_pgoff;        /* Offset (within vm_file) in PAGE_SIZE
                       units, *not* PAGE_CACHE_SIZE */
    struct file * vm_file;        /* File we map to (can be NULL). */
    void * vm_private_data;        /* was vm_pte (shared mem) */
    unsigned long vm_truncate_count;/* truncate_count or restart_addr */

#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
};

/*
 * These are the virtual MM functions - opening of an area, closing and
 * unmapping it (needed to keep files on disk up-to-date etc), pointer
 * to the functions called when a no-page or a wp-page exception occurs. 
 */
struct vm_operations_struct {
    void (*open)(struct vm_area_struct * area);  /* 指定内存区域加入到一个地址空间时，该函数被调用 */
    void (*close)(struct vm_area_struct * area); /* 指定内存区域从一个地址空间删除时，该函数被调用 */
    int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); /* 当没有出现在物理页面中的内存被访问时，该函数被调用 */

    /* 当一个之前只读的页面变为可写时，该函数被调用，
     * 如果此函数出错，将导致一个 SIGBUS 信号 */
    int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf);

    /* 当 get_user_pages() 调用失败时, 该函数被 access_process_vm() 函数调用 */
    int (*access)(struct vm_area_struct *vma, unsigned long addr,
              void *buf, int len, int write);
#ifdef CONFIG_NUMA
    /*
     * set_policy() op must add a reference to any non-NULL @new mempolicy
     * to hold the policy upon return.  Caller should pass NULL @new to
     * remove a policy and fall back to surrounding context--i.e. do not
     * install a MPOL_DEFAULT policy, nor the task or system default
     * mempolicy.
     */
    int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);

    /*
     * get_policy() op must add reference [mpol_get()] to any policy at
     * (vma,addr) marked as MPOL_SHARED.  The shared policy infrastructure
     * in mm/mempolicy.c will do this automatically.
     * get_policy() must NOT add a ref if the policy at (vma,addr) is not
     * marked as MPOL_SHARED. vma policies are protected by the mmap_sem.
     * If no [shared/vma] mempolicy exists at the addr, get_policy() op
     * must return NULL--i.e., do not "fallback" to task or system default
     * policy.
     */
    struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
                    unsigned long addr);
    int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
        const nodemask_t *to, unsigned long flags);
#endif
};

/* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
                         struct vm_area_struct **pprev);

/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
   NULL if none.  Assume start_addr < end_addr. */
static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr)
{
    struct vm_area_struct * vma = find_vma(mm,start_addr);

    if (vma && end_addr <= vma->vm_start)
        vma = NULL;
    return vma;
}

static inline unsigned long do_mmap(struct file *file, unsigned long addr,
    unsigned long len, unsigned long prot,
    unsigned long flag, unsigned long offset)
{
    unsigned long ret = -EINVAL;
    if ((offset + PAGE_ALIGN(len)) < offset)
        goto out;
    if (!(offset & ~PAGE_MASK))
        ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
out:
    return ret;
}