Posted on 

the virtual address of process

之前读 ULKe3 并没有配合最近版本的源码一起食用，导致理解不够深刻。后来又读了一遍 Linux kernel development，感觉虽然成文内容有点老，但是结构非常清晰，但是细节少。于是凭借着对 Linux kernel development 的理解又拿去 ULK 和 kernel 3.10 读了一遍，整理如下。

kernel task_struct 中 struct mm_struct *mm, *active_mm 是记录映射用户态地址空间的，结构体里面移除了一部分关于 numa 的字段，虽然 numa 是现代计算机非常重要的部分，但是引入了太多额外的细节对核心的理解有点干扰，还是移除了简单一点，有机会单独梳理一下 numa 吧。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
struct mm_struct {
	struct vm_area_struct * mmap;		// 指向内存区域链表头部的指针
	struct rb_root mm_rb; // 指向内存区域对象组织的红黑树的根节点
	struct vm_area_struct * mmap_cache;	// 指向最后一个内存区域对象
#ifdef CONFIG_MMU
	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);
#endif
	unsigned long mmap_base;		// 
	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 */
	unsigned long highest_vm_end;		/* highest vma end address */
	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 */

	spinlock_t page_table_lock;		/* Protects page tables and some counters */
	struct rw_semaphore mmap_sem;

	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 shared_vm;	/* Shared pages (files) */
	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE */
	unsigned long stack_vm;		/* VM_GROWSUP/DOWN */
	unsigned long def_flags;
	unsigned long nr_ptes;		/* Page table pages */
	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 */

	/*
	 * 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;

	cpumask_var_t cpu_vm_mask_var;

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

	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 __rcu *owner;
#endif

	/* store ref to file /proc/<pid>/exe symlink points to */
	struct file *exe_file;
...
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
#endif
#ifdef CONFIG_CPUMASK_OFFSTACK
	struct cpumask cpumask_allocation;
#endif
...
	struct uprobes_state uprobes_state;
};

This struct defines a memory VMM memory area. There is one of these per VM-area/task. A VM area is any part of the process virtual memory space that has a special rule for the page-fault handlers (ie a shared library, the executable area etc).

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
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. */

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

	struct rb_node vm_rb;

	/*
	 * 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;

	/* Second cache line starts here. */

	struct mm_struct *vm_mm;	/* The address space we belong to. */
	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
	unsigned long vm_flags;		/* Flags, see mm.h. */

	/*
	 * For areas with an address space and backing store,
	 * linkage into the address_space->i_mmap interval tree, or
	 * linkage of vma in the address_space->i_mmap_nonlinear list.
	 */
	union {
		struct {
			struct rb_node rb;
			unsigned long rb_subtree_last;
		} linear;
		struct list_head nonlinear;
	} 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_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;

	/* 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) */

#ifndef CONFIG_MMU
	struct vm_region *vm_region;	/* NOMMU mapping region */
#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.

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
struct vm_operations_struct {
	void (*open)(struct vm_area_struct * area);
	void (*close)(struct vm_area_struct * area);
	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);

	/* notification that a previously read-only page is about to become
	 * writable, if an error is returned it will cause a SIGBUS */
	int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf);

	/* called by access_process_vm when get_user_pages() fails, typically
	 * for use by special VMAs that can switch between memory and hardware
	 */
	int (*access)(struct vm_area_struct *vma, unsigned long addr,
		      void *buf, int len, int write);
...
	/* called by sys_remap_file_pages() to populate non-linear mapping */
	int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,
			   unsigned long size, pgoff_t pgoff);
};
License

本文采用 署名-非商业性使用-相同方式共享 4.0 国际 许可协议，转载请注明出处。

Join the discussion