Re: [PATCH v4 3/3] mm: fix double page fault on arm64 if PTE_AF is cleared

["Kirill A. Shutemov" <kirill@shutemov.name>]

On Wed, Sep 18, 2019 at 09:19:14PM +0800, Jia He wrote:
> When we tested pmdk unit test [1] vmmalloc_fork TEST1 in arm64 guest, there
> will be a double page fault in __copy_from_user_inatomic of cow_user_page.
> 
> Below call trace is from arm64 do_page_fault for debugging purpose
> [  110.016195] Call trace:
> [  110.016826]  do_page_fault+0x5a4/0x690
> [  110.017812]  do_mem_abort+0x50/0xb0
> [  110.018726]  el1_da+0x20/0xc4
> [  110.019492]  __arch_copy_from_user+0x180/0x280
> [  110.020646]  do_wp_page+0xb0/0x860
> [  110.021517]  __handle_mm_fault+0x994/0x1338
> [  110.022606]  handle_mm_fault+0xe8/0x180
> [  110.023584]  do_page_fault+0x240/0x690
> [  110.024535]  do_mem_abort+0x50/0xb0
> [  110.025423]  el0_da+0x20/0x24
> 
> The pte info before __copy_from_user_inatomic is (PTE_AF is cleared):
> [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3
> 
> As told by Catalin: "On arm64 without hardware Access Flag, copying from
> user will fail because the pte is old and cannot be marked young. So we
> always end up with zeroed page after fork() + CoW for pfn mappings. we
> don't always have a hardware-managed access flag on arm64."
> 
> This patch fix it by calling pte_mkyoung. Also, the parameter is
> changed because vmf should be passed to cow_user_page()
> 
> [1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork
> 
> Reported-by: Yibo Cai <Yibo.Cai@arm.com>
> Signed-off-by: Jia He <justin.he@arm.com>
> ---
>  mm/memory.c | 35 ++++++++++++++++++++++++++++++-----
>  1 file changed, 30 insertions(+), 5 deletions(-)
> 
> diff --git a/mm/memory.c b/mm/memory.c
> index e2bb51b6242e..d2c130a5883b 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -118,6 +118,13 @@ int randomize_va_space __read_mostly =
>  					2;
>  #endif
>  
> +#ifndef arch_faults_on_old_pte
> +static inline bool arch_faults_on_old_pte(void)
> +{
> +	return false;
> +}
> +#endif
> +
>  static int __init disable_randmaps(char *s)
>  {
>  	randomize_va_space = 0;
> @@ -2140,8 +2147,12 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
>  	return same;
>  }
>  
> -static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
> +static inline void cow_user_page(struct page *dst, struct page *src,
> +				 struct vm_fault *vmf)
>  {
> +	struct vm_area_struct *vma = vmf->vma;
> +	unsigned long addr = vmf->address;
> +
>  	debug_dma_assert_idle(src);
>  
>  	/*
> @@ -2152,20 +2163,34 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
>  	 */
>  	if (unlikely(!src)) {
>  		void *kaddr = kmap_atomic(dst);
> -		void __user *uaddr = (void __user *)(va & PAGE_MASK);
> +		void __user *uaddr = (void __user *)(addr & PAGE_MASK);
> +		pte_t entry;
>  
>  		/*
>  		 * This really shouldn't fail, because the page is there
>  		 * in the page tables. But it might just be unreadable,
>  		 * in which case we just give up and fill the result with
> -		 * zeroes.
> +		 * zeroes. On architectures with software "accessed" bits,
> +		 * we would take a double page fault here, so mark it
> +		 * accessed here.
>  		 */
> +		if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
> +			spin_lock(vmf->ptl);
> +			if (likely(pte_same(*vmf->pte, vmf->orig_pte))) {
> +				entry = pte_mkyoung(vmf->orig_pte);
> +				if (ptep_set_access_flags(vma, addr,
> +							  vmf->pte, entry, 0))
> +					update_mmu_cache(vma, addr, vmf->pte);
> +			}

I don't follow.

So if pte has changed under you, you don't set the accessed bit, but never
the less copy from the user.

What makes you think it will not trigger the same problem?

I think we need to make cow_user_page() fail in this case and caller --
wp_page_copy() -- return zero. If the fault was solved by other thread, we
are fine. If not userspace would re-fault on the same address and we will
handle the fault from the second attempt.

> +			spin_unlock(vmf->ptl);
> +		}
> +
>  		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
>  			clear_page(kaddr);
>  		kunmap_atomic(kaddr);
>  		flush_dcache_page(dst);
>  	} else
> -		copy_user_highpage(dst, src, va, vma);
> +		copy_user_highpage(dst, src, addr, vma);
>  }
>  
>  static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
> @@ -2318,7 +2343,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
>  				vmf->address);
>  		if (!new_page)
>  			goto oom;
> -		cow_user_page(new_page, old_page, vmf->address, vma);
> +		cow_user_page(new_page, old_page, vmf);
>  	}
>  
>  	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
> -- 
> 2.17.1
> 
> 

-- 
 Kirill A. Shutemov