[Linux][内核学习笔记]--匿名页面缺页中断

1 简介

 在缺页中断处理中，匿名页面处理的核心函数是 do_anonymous_page() , 其代码实现在 mm/memory.c 中。在Linux内核中没有关联到文件映射的页面称为匿名映射——Anonymous Page , 简称 anon page。

2 源码解析

static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	struct mem_cgroup *memcg;
	struct page *page;
	vm_fault_t ret = 0;
	pte_t entry;

	/* File mapping without ->vm_ops ? */
	/*如果是共享则意味着之前以及通过mmap方式在其他进程申请过物理内存，vma应该存在对应物理内存映射，不应该再发生page fault*/
	if (vma->vm_flags & VM_SHARED)
		return VM_FAULT_SIGBUS;

	/*
	 * Use pte_alloc() instead of pte_alloc_map().  We can't run
	 * pte_offset_map() on pmds where a huge pmd might be created
	 * from a different thread.
	 *
	 * pte_alloc_map() is safe to use under down_write(mmap_sem) or when
	 * parallel threads are excluded by other means.
	 *
	 * Here we only have down_read(mmap_sem).
	 */
	 /*如果pte不存在，则分配pte，并建立pmd与pte的关系*/
	if (pte_alloc(vma->vm_mm, vmf->pmd, vmf->address))
		return VM_FAULT_OOM;

	/* See the comment in pte_alloc_one_map() */
	
	if (unlikely(pmd_trans_unstable(vmf->pmd)))
		return 0;

	/* Use the zero-page for reads */
	/*如果是读操作触发的缺页，并且没有禁止zero page，则映射到零页面*/
	if (!(vmf->flags & FAULT_FLAG_WRITE) &&
			!mm_forbids_zeropage(vma->vm_mm)) {
		entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address),
						vma->vm_page_prot));//生成一个特殊页表项，映射到专有的0页，一页大小
		vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
				vmf->address, &vmf->ptl);//据pmd,address找到pte表对应的一个表项，并且lock住
		if (!pte_none(*vmf->pte))//如果页表项不为空。第一次访问，应该为空，所以可能别的进程在使用此物理地址，跳unlock
			goto unlock;
		ret = check_stable_address_space(vma->vm_mm);//对vma地址空间进行检查
		if (ret)
			goto unlock;
		/* Deliver the page fault to userland, check inside PT lock */
		if (userfaultfd_missing(vma)) {
			pte_unmap_unlock(vmf->pte, vmf->ptl);
			return handle_userfault(vmf, VM_UFFD_MISSING);
		}
		goto setpte;
	}

	/* Allocate our own private page. */
	if (unlikely(anon_vma_prepare(vma)))//对vma进行预处理，主要是创建anon_vma和anon_vma_chain，为后续反向映射做准备
		goto oom;
	page = alloc_zeroed_user_highpage_movable(vma, vmf->address);//分配一个物理页面，优先从highmem分配
	if (!page)
		goto oom;

	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg,
					false))//申请内存成功之后，将新申请的page加入到mcgroup管理
		goto oom_free_page;

	/*
	 * The memory barrier inside __SetPageUptodate makes sure that
	 * preceeding stores to the page contents become visible before
	 * the set_pte_at() write.
	 */
	__SetPageUptodate(page);//更新page flag为PG_uptodate，意味着page 内容已经更新

	entry = mk_pte(page, vma->vm_page_prot);//获取pte 并重新按照需求构建entry
	if (vma->vm_flags & VM_WRITE)
		entry = pte_mkwrite(pte_mkdirty(entry));

	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
			&vmf->ptl);//将pte lock防止同时更新和更多虚拟内存对物理内存映射
	if (!pte_none(*vmf->pte))
		goto release;

	ret = check_stable_address_space(vma->vm_mm);//对vma地址空间进行检查
	if (ret)
		goto release;

	/* Deliver the page fault to userland, check inside PT lock */
	if (userfaultfd_missing(vma)) {
		pte_unmap_unlock(vmf->pte, vmf->ptl);
		mem_cgroup_cancel_charge(page, memcg, false);
		put_page(page);
		return handle_userfault(vmf, VM_UFFD_MISSING);
	}

	inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);//增加mm_countrt应用计数
	page_add_new_anon_rmap(page, vma, vmf->address, false);//将此页添加到LRU链表中去，回收的时候使用
	mem_cgroup_commit_charge(page, memcg, false, false);
	lru_cache_add_active_or_unevictable(page, vma);
setpte:
	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry);//设置页表项

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(vma, vmf->address, vmf->pte);//更新mmu的cache
unlock:
	pte_unmap_unlock(vmf->pte, vmf->ptl);
	return ret;
release:
	mem_cgroup_cancel_charge(page, memcg, false);
	put_page(page);
	goto unlock;
oom_free_page:
	put_page(page);
oom:
	return VM_FAULT_OOM;
}

该函数的主要逻辑是根据flags是否具有可写属性，分为读操作触发缺页和写操作触发缺页两部分：

• 读操作触发缺页：映射到一个全填充为0的零页面（ZERO_PAGE）。
• 写操作触发缺页：alloc_zeroed_user_highpage_movable()函数分配一个可写的页面，其分配掩码是 GFP_HIGHUSER | __GFP_MOVABLE ，意味着会优先从高端内存中分配，每次分配一页，假设需要分配多页，则会触发多次缺页中断。继续往下追踪，会看到最终调用到伙伴系统的核心函数 alloc_pages()来分配物理页面。然后通过 mk_pte()、pte_mkdirty() 和 pte_mkwrite()等宏生成一个新的pte entry，并通过set_pte_at()函数设置到硬件硬件页表中。

3 代码流程分析