Linux 文件页反向映射

0. 引言

操作系统中与匿名页相对的是文件页，文件页的反向映射对比匿名页的反向映射更为简单。如果还不清楚匿名页反向映射逻辑的，请移步 匿名页反向映射

1. 文件页反向映射数据结构

struct file： 用户进程每open()一次文件，则会生成一个file对象，file->f_mapping指向该管理该文件页面对象

struct file {
   
	union {
   
		struct llist_node	fu_llist;
		struct rcu_head 	fu_rcuhead;
	} f_u;
	struct path		f_path;
	struct inode		*f_inode;	/* cached value */
	const struct file_operations	*f_op;

	/*
	 * Protects f_ep_links, f_flags.
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
	enum rw_hint		f_write_hint;
	atomic_long_t		f_count;
	unsigned int 		f_flags;
	fmode_t			f_mode;
	struct mutex		f_pos_lock;
	loff_t			f_pos;
	struct fown_struct	f_owner;
	const struct cred	*f_cred;
	struct file_ra_state	f_ra;

	u64			f_version;
#ifdef CONFIG_SECURITY
	void			*f_security;
#endif
	/* needed for tty driver, and maybe others */
	void			*private_data;

#ifdef CONFIG_EPOLL
	/* Used by fs/eventpoll.c to link all the hooks to this file */
	struct list_head	f_ep_links;
	struct list_head	f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping; // 文件页缓冲区，文件页都放在该对象中进行管理
	errseq_t		f_wb_err;
	errseq_t		f_sb_err; /* for syncfs */
} __randomize_layout
  __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */

struct address_space： 用来管理一个文件所有内容页面，一个真实的文件只对应一个address_space结构，其中address_space->i_pages是保存页面的结构，address_space->i_mmap是一个红黑树，红黑树上挂载着映射该文件的所有vma对象。

/**
 * struct address_space - Contents of a cacheable, mappable object.
 * @host: Owner, either the inode or the block_device.
 * @i_pages: Cached pages.
 * @gfp_mask: Memory allocation flags to use for allocating pages.
 * @i_mmap_writable: Number of VM_SHARED mappings.
 * @nr_thps: Number of THPs in the pagecache (non-shmem only).
 * @i_mmap: Tree of private and shared mappings.
 * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
 * @nrpages: Number of page entries, protected by the i_pages lock.
 * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock.
 * @writeback_index: Writeback starts here.
 * @a_ops: Methods.
 * @flags: Error bits and flags (AS_*).
 * @wb_err: The most recent error which has occurred.
 * @private_lock: For use by the owner of the address_space.
 * @private_list: For use by the owner of the address_space.
 * @private_data: For use by the owner of the address_space.
 */
struct address_space {
   
	struct inode		*host;
	struct xarray		i_pages;
	gfp_t			gfp_mask;
	atomic_t		i_mmap_writable;
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
	/* number of thp, only for non-shmem files */
	atomic_t		nr_thps;
#endif
	struct rb_root_cached	i_mmap;
	struct rw_semaphore	i_mmap_rwsem;
	unsigned long		nrpages;
	unsigned long		nrexceptional;
	pgoff_t			writeback_index;
	const struct address_space_operations *a_ops;
	unsigned long		flags;
	errseq_t		wb_err;
	spinlock_t		private_lock;
	struct list_head	private_list;
	void			*private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;

struct vm_area_struct： 用来描述用户进程的一段虚拟地址空间，其中vma->vm_start表示映射的起始虚拟地址，vma->vm_end表示映射的结束虚拟地址，vma->vm_file指向映射的文件对象，vma->vm_pgoff表示从文件哪里进行映射（以页面为单位）。

/*
 * This struct describes a virtual 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. */

	unsigned long vm_start;		/* Our start address within vm_mm. */ // 映射的起始虚拟地址
	unsigned long vm_end;		/* The first byte after our end address
					   within vm_mm. */ // 映射的结束虚拟地址

	/* 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. */

	/*
	 * Access permissions of this VMA.
	 * See vmf_insert_mixed_prot() for discussion.
	 */
	pgprot_t vm_page_prot;
	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.
	 */
	struct list_head anon_vma_chain; /* Serialized by mmap_lock &
					  * 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 */ // 该vma从文件哪里开始映射，以页面为单位
	struct file * vm_file;		/* File we map to (can be NULL). */ // 映射的文件对象
	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;

2. 数据结构关系图

3. 建立文件反向映射流程

我们都是通过一个path去打开一个文件，然后再通过mmap()去将文件映射到进程的虚拟地址空间，后续通过访存这块虚拟地址空间来达到读写文件的目的。

int fd = open("/path/to/your/file", O_RDWR | O_CREAT, S_IRUSR | S_IWUSR);
void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
// do something
munmap(ptr, size);
close(fd);

现在让我们从mmap()映射文件描述符这里看起。
arm64体系结构下，且内核是linux-5.10版本：

SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
		unsigned long, prot, unsigned long, flags,
		unsigned long, fd, unsigned long, off)
{
   
	if (offset_in_page(off) != 0)
		return -EINVAL;

	return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT