Re: [PATCH] mm: mempolicy: make mbind() return -EIO when MPOL_MF_STRICT is specified

[Oscar Salvador <osalvador@xxxxxxx>]

On Wed, Mar 20, 2019 at 02:35:56AM +0800, Yang Shi wrote:
> Fixes: 6f4576e3687b ("mempolicy: apply page table walker on queue_pages_range()")
> Reported-by: Cyril Hrubis <chrubis@xxxxxxx>
> Cc: Vlastimil Babka <vbabka@xxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx
> Suggested-by: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
> Signed-off-by: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Oscar Salvador <osalvador@xxxxxxx>

Hi Yang, thanks for the patch.

Some observations below.

>  	}
>  	page = pmd_page(*pmd);
> @@ -473,8 +480,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
>  	ret = 1;
>  	flags = qp->flags;
>  	/* go to thp migration */
> -	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
> +	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
> +		if (!vma_migratable(walk->vma)) {
> +			ret = -EIO;
> +			goto unlock;
> +		}
> +
>  		migrate_page_add(page, qp->pagelist, flags);
> +	} else
> +		ret = -EIO;

	if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) ||
       	        !vma_migratable(walk->vma)) {
               	ret = -EIO;
                goto unlock;
        }

	migrate_page_add(page, qp->pagelist, flags); 
unlock:
        spin_unlock(ptl);
out:
        return ret;

seems more clean to me?


>  unlock:
>  	spin_unlock(ptl);
>  out:
> @@ -499,8 +513,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
>  	ptl = pmd_trans_huge_lock(pmd, vma);
>  	if (ptl) {
>  		ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
> -		if (ret)
> +		if (ret > 0)
>  			return 0;
> +		else if (ret < 0)
> +			return ret;

I would go with the following, but that's a matter of taste I guess.

if (ret < 0)
	return ret;
else
	return 0;

>  	}
>  
>  	if (pmd_trans_unstable(pmd))
> @@ -521,11 +537,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
>  			continue;
>  		if (!queue_pages_required(page, qp))
>  			continue;
> -		migrate_page_add(page, qp->pagelist, flags);
> +		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
> +			if (!vma_migratable(vma))
> +				break;
> +			migrate_page_add(page, qp->pagelist, flags);
> +		} else
> +			break;

I might be missing something, but AFAICS neither vma nor flags is going to change
while we are in queue_pages_pte_range(), so, could not we move the check just
above the loop?
In that way, 1) we only perform the check once and 2) if we enter the loop
we know that we are going to do some work, so, something like:

index af171ccb56a2..7c0e44389826 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -487,6 +487,9 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
        if (pmd_trans_unstable(pmd))
                return 0;
 
+       if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma))
+               return -EIO;
+
        pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
        for (; addr != end; pte++, addr += PAGE_SIZE) {
                if (!pte_present(*pte))


>  	}
>  	pte_unmap_unlock(pte - 1, ptl);
>  	cond_resched();
> -	return 0;
> +	return addr != end ? -EIO : 0;

If we can do the above, we can leave the return value as it was.

-- 
Oscar Salvador
SUSE L3