Re: [PATCH v3 03/14] mm: use pmd lock instead of racy checks in zap_pmd_range()

[Hillf Danton]

On February 06, 2017 12:13 AM Zi Yan wrote: 
> 
> @@ -1233,33 +1233,31 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
>  				struct zap_details *details)
>  {
>  	pmd_t *pmd;
> +	spinlock_t *ptl;
>  	unsigned long next;
> 
>  	pmd = pmd_offset(pud, addr);
> +	ptl = pmd_lock(vma->vm_mm, pmd);
>  	do {
>  		next = pmd_addr_end(addr, end);
>  		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
>  			if (next - addr != HPAGE_PMD_SIZE) {
>  				VM_BUG_ON_VMA(vma_is_anonymous(vma) &&
>  				    !rwsem_is_locked(&tlb->mm->mmap_sem), vma);
> -				__split_huge_pmd(vma, pmd, addr, false, NULL);
> -			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
> -				goto next;
> +				__split_huge_pmd_locked(vma, pmd, addr, false);
> +			} else if (__zap_huge_pmd_locked(tlb, vma, pmd, addr))
> +				continue;
>  			/* fall through */
>  		}
> -		/*
> -		 * Here there can be other concurrent MADV_DONTNEED or
> -		 * trans huge page faults running, and if the pmd is
> -		 * none or trans huge it can change under us. This is
> -		 * because MADV_DONTNEED holds the mmap_sem in read
> -		 * mode.
> -		 */
> -		if (pmd_none_or_trans_huge_or_clear_bad(pmd))
> -			goto next;
> +
> +		if (pmd_none_or_clear_bad(pmd))
> +			continue;
> +		spin_unlock(ptl);
>  		next = zap_pte_range(tlb, vma, pmd, addr, next, details);
> -next:
>  		cond_resched();
> +		spin_lock(ptl);
>  	} while (pmd++, addr = next, addr != end);

spin_lock() is appointed to the bench of pmd_lock().

> +	spin_unlock(ptl);
> 
>  	return addr;
>  }