深入Linux内核（内存篇）—用户内存空间之VMA

最新推荐文章于 2025-03-10 07:45:38 发布

迷途小生

最新推荐文章于 2025-03-10 07:45:38 发布

阅读量7k

点赞数 8

分类专栏：深入Linux内核文章标签：链表算法 c语言 linux

本文链接：https://blog.csdn.net/liyuewuwunaile/article/details/107272123

版权

用户内存空间之VMA

一、VMA
二、VMA Flag
三、VMA Find
四、VMA Insert
五、VMA Merge

内核管理用户空间的数据结构是struct vm_area_struct，简称VMA。

一、VMA

用户进程拥有用户空间的地址，其可以通过malloc和mmap等函数来申请内存。malloc和mmap等函数的实现都基于进程线性区描述struct vm_area_struct。
内核管理进程地址空间使用的数据结构是struct vm_area_struct，简称VMA。
对于每个进程的内存描述符mm_struct mm，都有各自的VMA，通过mm->mmap链表将进程所有的VMA管理起来，同时会记录到mm->mm_rb红黑树，用于高效查找合并VMA等操作。

struct mm_struct {
   
	struct vm_area_struct *mmap;		/* list of VMAs */
	struct rb_root mm_rb;
	int map_count;			/* number of VMAs */
	……
}

mmap形成vm_area_struct 有序单链表，记录进程所有的VMA，mm->mmap即为该链表表头。该有序单链表按照VMA->vm_start递增方式组织。
mm_rb是VMA红黑树根节点，将进程所有的VMA记录到红黑树中，以提高查找效率。
map_count记录进程mm所拥有的VMA数量。

VMA的数据结构vm_area_struct如下。

/*
 * 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).
 */
struct vm_area_struct {
   
	/* The first cache line has the info for VMA tree walking. */

	/* VMA描述的线性地址空间的起始地址和结束地址（虚拟地址） */
	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 */
	/* 进程VMA链表，分别指向前一个和后一个VMA。链表按虚拟地址大小排序 */
	struct vm_area_struct *vm_next, *vm_prev;

	/* VMA作为一个节点加入mm->mm_rb红黑树 */
	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. */
	/* 指向VMA所属的mm_struct mm */
	struct mm_struct *vm_mm;	/* The address space we belong to. */

	/*
	 * Access permissions of this VMA.
	 * See vmf_insert_mixed_prot() for discussion.
	 */
	/* VMA访问权限 */
	pgprot_t vm_page_prot;
	/* VMA标志位 */
	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.
	 */
	struct {
   
		struct rb_node rb;
		unsigned long rb_subtree_last;
	} 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.
	 */
	/* 用于管理RMAP反向映射 */
	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. */
	/* VMA方法，open/close VMA等方法 */
	const struct vm_operations_struct *vm_ops;

	/* Information about our backing store: */
	/* 文件映射的偏移量，单位为PAGE_SIZE.对于匿名页面，指vm_start/PAGE_SIZE */
	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE units */
	/* 指向映射文件的文件对象 */			   
	struct file * vm_file;		/* File we map to (can be NULL). */
	void * vm_private_data;		/* was vm_pte (shared mem) */

#ifdef CONFIG_SWAP
	atomic_long_t swap_readahead_info;
#endif
#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;
} __randomize_layout;

二、VMA Flag

/*
 * vm_flags in vm_area_struct, see mm_types.h.
 * When changing, update also include/trace/events/mmflags.h
 */
#define VM_NONE		0x00000000

/* 页可读，可写，可执行，可以多个进程共享 */
#define VM_READ		0x00000001	/* currently active flags */
#define VM_WRITE	0x00000002
#define VM_EXEC		0x00000004
#define VM_SHARED	0x00000008

/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
#define VM_MAYREAD	0x00000010	/* limits for mprotect() etc */
#define VM_MAYWRITE	0x00000020
#define VM_MAYEXEC	0x00000040
#define VM_MAYSHARE	0x00000080

#define VM_GROWSDOWN	0x00000100	/* general info on the segment */
#define VM_UFFD_MISSING	0x00000200	/* missing pages tracking */
#define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
#define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */
#define VM_UFFD_WP	0x00001000	/* wrprotect pages tracking */

#define VM_LOCKED	0x00002000
#define VM_IO           0x00004000	/* Memory mapped I/O or similar */

					/* Used by sys_madvise() */
#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */

#define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
#define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
#define VM_LOCKONFAULT	0x00080000	/* Lock the pages covered when they are faulted in */
#define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
#define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
#define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
#define VM_SYNC		0x00800000	/* Synchronous page faults */
#define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
#define VM_WIPEONFORK	0x02000000	/* Wipe VMA contents in child. */
#define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */

#ifdef CONFIG_MEM_SOFT_DIRTY
# define VM_SOFTDIRTY	0x08000000	/* Not soft dirty clean area */
#else
# define VM_SOFTDIRTY	0
#endif

#define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
#define VM_HUGEPAGE	0x20000000	/* MADV_HUGEPAGE marked this vma */
#define VM_NOHUGEPAGE	0x40000000	/* MADV_NOHUGEPAGE marked this vma */
#define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */