[PATCH v2 15/23] s390: allow pte_offset_map_lock() to fail

[Claudio Imbrenda]

On Thu, 8 Jun 2023 12:27:22 -0700 (PDT)
Hugh Dickins <hughd at google.com> wrote:

> In rare transient cases, not yet made possible, pte_offset_map() and
> pte_offset_map_lock() may not find a page table: handle appropriately.
> 
> Add comment on mm's contract with s390 above __zap_zero_pages(),
> and fix old comment there: must be called after THP was disabled.
> 
> Signed-off-by: Hugh Dickins <hughd at google.com>

Acked-by: Claudio Imbrenda <imbrenda at linux.ibm.com>

> ---
>  arch/s390/kernel/uv.c  |  2 ++
>  arch/s390/mm/gmap.c    |  9 ++++++++-
>  arch/s390/mm/pgtable.c | 12 +++++++++---
>  3 files changed, 19 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
> index cb2ee06df286..3c62d1b218b1 100644
> --- a/arch/s390/kernel/uv.c
> +++ b/arch/s390/kernel/uv.c
> @@ -294,6 +294,8 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
>  
>  	rc = -ENXIO;
>  	ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
> +	if (!ptep)
> +		goto out;
>  	if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
>  		page = pte_page(*ptep);
>  		rc = -EAGAIN;
> diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
> index dc90d1eb0d55..3a2a31a15ea8 100644
> --- a/arch/s390/mm/gmap.c
> +++ b/arch/s390/mm/gmap.c
> @@ -2537,7 +2537,12 @@ static inline void thp_split_mm(struct mm_struct *mm)
>   * Remove all empty zero pages from the mapping for lazy refaulting
>   * - This must be called after mm->context.has_pgste is set, to avoid
>   *   future creation of zero pages
> - * - This must be called after THP was enabled
> + * - This must be called after THP was disabled.
> + *
> + * mm contracts with s390, that even if mm were to remove a page table,
> + * racing with the loop below and so causing pte_offset_map_lock() to fail,
> + * it will never insert a page table containing empty zero pages once
> + * mm_forbids_zeropage(mm) i.e. mm->context.has_pgste is set.
>   */
>  static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
>  			   unsigned long end, struct mm_walk *walk)
> @@ -2549,6 +2554,8 @@ static int __zap_zero_pages(pmd_t *pmd, unsigned long start,
>  		spinlock_t *ptl;
>  
>  		ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
> +		if (!ptep)
> +			break;
>  		if (is_zero_pfn(pte_pfn(*ptep)))
>  			ptep_xchg_direct(walk->mm, addr, ptep, __pte(_PAGE_INVALID));
>  		pte_unmap_unlock(ptep, ptl);
> diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
> index 6effb24de6d9..3bd2ab2a9a34 100644
> --- a/arch/s390/mm/pgtable.c
> +++ b/arch/s390/mm/pgtable.c
> @@ -829,7 +829,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
>  	default:
>  		return -EFAULT;
>  	}
> -
> +again:
>  	ptl = pmd_lock(mm, pmdp);
>  	if (!pmd_present(*pmdp)) {
>  		spin_unlock(ptl);
> @@ -850,6 +850,8 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
>  	spin_unlock(ptl);
>  
>  	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
> +	if (!ptep)
> +		goto again;
>  	new = old = pgste_get_lock(ptep);
>  	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
>  			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
> @@ -938,7 +940,7 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
>  	default:
>  		return -EFAULT;
>  	}
> -
> +again:
>  	ptl = pmd_lock(mm, pmdp);
>  	if (!pmd_present(*pmdp)) {
>  		spin_unlock(ptl);
> @@ -955,6 +957,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
>  	spin_unlock(ptl);
>  
>  	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
> +	if (!ptep)
> +		goto again;
>  	new = old = pgste_get_lock(ptep);
>  	/* Reset guest reference bit only */
>  	pgste_val(new) &= ~PGSTE_GR_BIT;
> @@ -1000,7 +1004,7 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
>  	default:
>  		return -EFAULT;
>  	}
> -
> +again:
>  	ptl = pmd_lock(mm, pmdp);
>  	if (!pmd_present(*pmdp)) {
>  		spin_unlock(ptl);
> @@ -1017,6 +1021,8 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
>  	spin_unlock(ptl);
>  
>  	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
> +	if (!ptep)
> +		goto again;
>  	pgste = pgste_get_lock(ptep);
>  	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
>  	paddr = pte_val(*ptep) & PAGE_MASK;