linux内核源码解析04–用户进程页表创建

进程是独立的资源空间，每个进程都有自己独立的页表；

用户进程创建页表发生在三个时刻： 创建进程fork时； 缺页异常时； 进程切换时；

1.创建进程fork

核心函数

__do_fork()
 -->copy_process
  -->dup_mm()

dum_mm函数

static struct mm_struct *dup_mm(struct task_struct *tsk,
				struct mm_struct *oldmm)
{
	struct mm_struct *mm;
	int err;

	mm = allocate_mm();
	if (!mm)
		goto fail_nomem;

	memcpy(mm, oldmm, sizeof(*mm));

	if (!mm_init(mm, tsk, mm->user_ns))   ///分配私有的pgd页面
		goto fail_nomem;

	err = dup_mmap(mm, oldmm);            ///拷贝父进程页表
	...
}

第一步 分配pgd物理页面

pgd_alloc函数

mm_init()->mm_alloc_pgd()->pgd_alloc()

pgd_t *pgd_alloc(struct mm_struct *mm)
{
	gfp_t gfp = GFP_PGTABLE_USER;

	if (PGD_SIZE == PAGE_SIZE)
		return (pgd_t *)__get_free_page(gfp);  ///从伙伴系统分配物理页
	else
		return kmem_cache_alloc(pgd_cache, gfp);
}

第二步 拷贝父进程页表

拷贝vma

依次调用

copy_mm()
	->dum_mm()
	->dum_mmap()
	->copy_page_range()

int
copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
{
	...
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(src_pgd))
			continue;
		if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
					    addr, next))) {   ///遍历拷贝页表
			ret = -ENOMEM;
			break;
		}
	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
	...
}

拷贝pte页

依次调用

copy_p4d_range()
	->copy_pud_range()
	->copy_pmd_range()
	->copy_pte_range()
	->copy_present_pte()
	

/*
 * Copy one pte.  Returns 0 if succeeded, or -EAGAIN if one preallocated page
 * is required to copy this pte.
 */
static inline int
copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
		 pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
		 struct page **prealloc)
{
	...
	/*
	 * If it's a COW mapping, write protect it both
	 * in the parent and the child
	 */
	if (is_cow_mapping(vm_flags) && pte_write(pte)) {  ///如果是COW页，父进程，子进程页面都设置为只读
		ptep_set_wrprotect(src_mm, addr, src_pte);
		pte = pte_wrprotect(pte);
	}
	...
	return 0;
}

这样所有页表拷贝完毕，等进程写只读vma时，写时拷贝，触发缺页异常，在异常服务里真正分配物理页面；

2 缺页异常

wp_page_copy

写时复制引起的缺页异常，核心处理函数

static vm_fault_t wp_page_copy(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	struct mm_struct *mm = vma->vm_mm;
	struct page *old_page = vmf->page;
	struct page *new_page = NULL;
	pte_t entry;
	int page_copied = 0;
	struct mmu_notifier_range range;

	if (unlikely(anon_vma_prepare(vma))) ///检查VMA是否初始化了RMAP
		goto oom;

	if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { ///PTE如果是系统零页，分配一个内容全零的页面
		new_page = alloc_zeroed_user_highpage_movable(vma,
							      vmf->address);
		if (!new_page)
			goto oom;
	} else {   ///分配一个新物理页面，并且把old_page内容复制到new_page中
		new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
				vmf->address);
		if (!new_page)
			goto oom;

		if (!cow_user_page(new_page, old_page, vmf)) {
			/*
			 * COW failed, if the fault was solved by other,
			 * it's fine. If not, userspace would re-fault on
			 * the same address and we will handle the fault
			 * from the second attempt.
			 */
			put_page(new_page);
			if (old_page)
				put_page(old_page);
			return 0;
		}
	}

	if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
		goto oom_free_new;
	cgroup_throttle_swaprate(new_page, GFP_KERNEL);

	__SetPageUptodate(new_page);   ///设置PG_uptodate, 表示内容有效
	///注册一个mmu_notifier，并告知系统使dd_page无效
	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
				vmf->address & PAGE_MASK,
				(vmf->address & PAGE_MASK) + PAGE_SIZE);
	mmu_notifier_invalidate_range_start(&range);

	/*
	 * Re-check the pte - we dropped the lock
	 */ ///重新读取PTE，并判定是否修改
	vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl);
	if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
		if (old_page) {
			if (!PageAnon(old_page)) {
				dec_mm_counter_fast(mm,
						mm_counter_file(old_page));
				inc_mm_counter_fast(mm, MM_ANONPAGES);
			}
		} else {
			inc_mm_counter_fast(mm, MM_ANONPAGES);
		}
		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
		entry = mk_pte(new_page, vma->vm_page_prot);
		entry = maybe_mkwrite(pte_mkdirty(entry), vma);  ///生成一个新PTE

		/*
		 * Clear the pte entry and flush it first, before updating the
		 * pte with the new entry, to keep TLBs on different CPUs in
		 * sync. This code used to set the new PTE then flush TLBs, but
		 * that left a window where the new PTE could be loaded into
		 * some TLBs while the old PTE remains in others.
		 */
		ptep_clear_flush_notify(vma, vmf->address, vmf->pte);        ///刷新这个页面的TLB
		page_add_new_anon_rmap(new_page, vma, vmf->address, false);  ///new_page添加到RMAP系统中
		lru_cache_add_inactive_or_unevictable(new_page, vma);        ///new_page添加到LRU链表中
		/*
		 * We call the notify macro here because, when using secondary
		 * mmu page tables (such as kvm shadow page tables), we want the
		 * new page to be mapped directly into the secondary page table.
		 */
		set_pte_at_notify(mm, vmf->address, vmf->pte, entry);  ///新pte设置到硬件PTE中
		update_mmu_cache(vma, vmf->address, vmf->pte);
		if (old_page) {
			/*
			 * Only after switching the pte to the new page may
			 * we remove the mapcount here. Otherwise another
			 * process may come and find the rmap count decremented
			 * before the pte is switched to the new page, and
			 * "reuse" the old page writing into it while our pte
			 * here still points into it and can be read by other
			 * threads.
			 *
			 * The critical issue is to order this
			 * page_remove_rmap with the ptp_clear_flush above.
			 * Those stores are ordered by (if nothing else,)
			 * the barrier present in the atomic_add_negative
			 * in page_remove_rmap.
			 *
			 * Then the TLB flush in ptep_clear_flush ensures that
			 * no process can access the old page before the
			 * decremented mapcount is visible. And the old page
			 * cannot be reused until after the decremented
			 * mapcount is visible. So transitively, TLBs to
			 * old page will be flushed before it can be reused.
			 */
			page_remove_rmap(old_page, false);
		}

		/* Free the old page.. */
		new_page = old_page;
		page_copied = 1;
	} else {
		update_mmu_tlb(vma, vmf->address, vmf->pte);
	}

	if (new_page)
		put_page(new_page);

	pte_unmap_unlock(vmf->pte, vmf->ptl);
	/*
	 * No need to double call mmu_notifier->invalidate_range() callback as
	 * the above ptep_clear_flush_notify() did already call it.
	 */
	mmu_notifier_invalidate_range_only_end(&range);
	if (old_page) {
		/*
		 * Don't let another task, with possibly unlocked vma,
		 * keep the mlocked page.
		 */
		if (page_copied && (vma->vm_flags & VM_LOCKED)) {
			lock_page(old_page);	/* LRU manipulation */
			if (PageMlocked(old_page))
				munlock_vma_page(old_page);
			unlock_page(old_page);
		}
		put_page(old_page);
	}
	return page_copied ? VM_FAULT_WRITE : 0;
oom_free_new:
	put_page(new_page);
oom:
	if (old_page)
		put_page(old_page);
	return VM_FAULT_OOM;
}

3.进程切换

用户进程切换时，内存相关的主要做两件事情： (1)设置进程的ASID到ttbr1_el1; (2)设置mm->pgd到ttbr0_el1完成地址空间切换；

依次调用

context_switch()
	->switch_mm_irqs_off()
	->switch_mm()
	->__switch_mm()
	->check_and_switch_context()
	->cpu_switch_mm()
	->cpu_do_switch_mm()

void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm)
{
	unsigned long ttbr1 = read_sysreg(ttbr1_el1);
	unsigned long asid = ASID(mm);
	unsigned long ttbr0 = phys_to_ttbr(pgd_phys);

	/* Skip CNP for the reserved ASID */
	if (system_supports_cnp() && asid)
		ttbr0 |= TTBR_CNP_BIT;

	/* SW PAN needs a copy of the ASID in TTBR0 for entry */
	if (IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN))
		ttbr0 |= FIELD_PREP(TTBR_ASID_MASK, asid);

	/* Set ASID in TTBR1 since TCR.A1 is set */
	ttbr1 &= ~TTBR_ASID_MASK;
	ttbr1 |= FIELD_PREP(TTBR_ASID_MASK, asid);

	write_sysreg(ttbr1, ttbr1_el1);   ///ASID填入ttbr1_el1
	isb();
	write_sysreg(ttbr0, ttbr0_el1);   ///新进程页表基地址pgd，填入ttbr0_el1
	isb();
	post_ttbr_update_workaround();
}