Re: [PATCH 04/31] mm/pgtable: allow pte_offset_map[_lock]() to fail

[Qi Zheng]

Hi Hugh,

On 2023/5/22 12:53, Hugh Dickins wrote:

[...]

>   
> @@ -229,3 +231,57 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
>   }
>   #endif
>   #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
> +
> +pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
> +{
> +	pmd_t pmdval;
> +
> +	/* rcu_read_lock() to be added later */
> +	pmdval = pmdp_get_lockless(pmd);
> +	if (pmdvalp)
> +		*pmdvalp = pmdval;
> +	if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
> +		goto nomap;
> +	if (unlikely(pmd_trans_huge(pmdval) || pmd_devmap(pmdval)))
> +		goto nomap;

Will the follow-up patch deal with the above situation specially?
Otherwise, maybe it can be changed to the following check method?

	if (unlikely(pmd_none(pmdval) || pmd_leaf(pmdval)))
		goto nomap;

> +	if (unlikely(pmd_bad(pmdval))) {
> +		pmd_clear_bad(pmd);
> +		goto nomap;
> +	}
> +	return __pte_map(&pmdval, addr);
> +nomap:
> +	/* rcu_read_unlock() to be added later */
> +	return NULL;
> +}
> +
> +pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd,
> +			     unsigned long addr, spinlock_t **ptlp)
> +{
> +	pmd_t pmdval;
> +	pte_t *pte;
> +
> +	pte = __pte_offset_map(pmd, addr, &pmdval);
> +	if (likely(pte))
> +		*ptlp = pte_lockptr(mm, &pmdval);
> +	return pte;
> +}
> +
> +pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
> +			     unsigned long addr, spinlock_t **ptlp)
> +{
> +	spinlock_t *ptl;
> +	pmd_t pmdval;
> +	pte_t *pte;
> +again:
> +	pte = __pte_offset_map(pmd, addr, &pmdval);
> +	if (unlikely(!pte))
> +		return pte;
> +	ptl = pte_lockptr(mm, &pmdval);
> +	spin_lock(ptl);
> +	if (likely(pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
> +		*ptlp = ptl;
> +		return pte;
> +	}
> +	pte_unmap_unlock(pte, ptl);
> +	goto again;
> +}

--
Thanks,
Qi