Re: [PATCH v6 2/2] mm/arm64: override clear_young_dirty_ptes() batch helper

From: Ryan Roberts
Date: Mon Apr 15 2024 - 04:59:28 EST


On 13/04/2024 01:22, Lance Yang wrote:
> The per-pte get_and_clear/modify/set approach would result in
> unfolding/refolding for contpte mappings on arm64. So we need
> to override clear_young_dirty_ptes() for arm64 to avoid it.
>
> Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
> Suggested-by: Barry Song <21cnbao@xxxxxxxxx>
> Signed-off-by: Ryan Roberts <ryan.roberts@xxxxxxx>

No, afraid I haven't signed off yet!

> Signed-off-by: Lance Yang <ioworker0@xxxxxxxxx>
> ---
> arch/arm64/include/asm/pgtable.h | 37 ++++++++++++++++++++++++++++++++
> arch/arm64/mm/contpte.c | 28 ++++++++++++++++++++++++
> 2 files changed, 65 insertions(+)
>
> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> index 9fd8613b2db2..f951774dd2d6 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -1223,6 +1223,28 @@ static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address,
> __ptep_set_wrprotect(mm, address, ptep);
> }
>
> +static inline void __clear_young_dirty_ptes(struct mm_struct *mm,
> + unsigned long addr, pte_t *ptep,
> + unsigned int nr, cydp_t flags)
> +{
> + pte_t pte;
> +
> + for (;;) {
> + pte = __ptep_get(ptep);
> +
> + if (flags | CYDP_CLEAR_YOUNG)

bug: should be bitwise AND (&).

> + pte = pte_mkold(pte);
> + if (flags | CYDP_CLEAR_DIRTY)
> + pte = pte_mkclean(pte);
> +
> + __set_pte(ptep, pte);

The __ptep_get() and __set_pte() are not atomic. This is only safe when you are
clearing BOTH access and dirty (as I explained in the previous version). If you
are only clearing one of the flags, you will need a similar cmpxchg loop as for
__ptep_test_and_clear_young(). Otherwise you can race with the HW and lose
information.

> + if (--nr == 0)
> + break;
> + ptep++;
> + addr += PAGE_SIZE;
> + }
> +}
> +
> #ifdef CONFIG_TRANSPARENT_HUGEPAGE
> #define __HAVE_ARCH_PMDP_SET_WRPROTECT
> static inline void pmdp_set_wrprotect(struct mm_struct *mm,
> @@ -1379,6 +1401,9 @@ extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
> extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
> unsigned long addr, pte_t *ptep,
> pte_t entry, int dirty);
> +extern void contpte_clear_young_dirty_ptes(struct mm_struct *mm,
> + unsigned long addr, pte_t *ptep,
> + unsigned int nr, cydp_t flags);
>
> static __always_inline void contpte_try_fold(struct mm_struct *mm,
> unsigned long addr, pte_t *ptep, pte_t pte)
> @@ -1603,6 +1628,17 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
> return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty);
> }
>
> +#define clear_young_dirty_ptes clear_young_dirty_ptes
> +static inline void clear_young_dirty_ptes(struct mm_struct *mm,
> + unsigned long addr, pte_t *ptep,
> + unsigned int nr, cydp_t flags)
> +{
> + if (likely(nr == 1 && !pte_cont(__ptep_get(ptep))))
> + __clear_young_dirty_ptes(mm, addr, ptep, nr, flags);
> + else
> + contpte_clear_young_dirty_ptes(mm, addr, ptep, nr, flags);
> +}
> +
> #else /* CONFIG_ARM64_CONTPTE */
>
> #define ptep_get __ptep_get
> @@ -1622,6 +1658,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
> #define wrprotect_ptes __wrprotect_ptes
> #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
> #define ptep_set_access_flags __ptep_set_access_flags
> +#define clear_young_dirty_ptes __clear_young_dirty_ptes
>
> #endif /* CONFIG_ARM64_CONTPTE */
>
> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
> index 1b64b4c3f8bf..bf3b089d9641 100644
> --- a/arch/arm64/mm/contpte.c
> +++ b/arch/arm64/mm/contpte.c
> @@ -361,6 +361,34 @@ void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
> }
> EXPORT_SYMBOL_GPL(contpte_wrprotect_ptes);
>
> +void contpte_clear_young_dirty_ptes(struct mm_struct *mm, unsigned long addr,
> + pte_t *ptep, unsigned int nr, cydp_t flags)
> +{
> + /*
> + * We can safely clear access/dirty without needing to unfold from
> + * the architectures perspective, even when contpte is set. If the
> + * range starts or ends midway through a contpte block, we can just
> + * expand to include the full contpte block. While this is not
> + * exactly what the core-mm asked for, it tracks access/dirty per
> + * folio, not per page. And since we only create a contpte block
> + * when it is covered by a single folio, we can get away with
> + * clearing access/dirty for the whole block.
> + */
> + unsigned int start = addr;
> + unsigned int end = start + nr;

There are addresses; they should be unsigned long. May have been my error
originally when I sent you the example snippet.

Thanks,
Ryan

> +
> + if (pte_cont(__ptep_get(ptep + nr - 1)))
> + end = ALIGN(end, CONT_PTE_SIZE);
> +
> + if (pte_cont(__ptep_get(ptep))) {
> + start = ALIGN_DOWN(start, CONT_PTE_SIZE);
> + ptep = contpte_align_down(ptep);
> + }
> +
> + __clear_young_dirty_ptes(mm, start, ptep, end - start, flags);
> +}
> +EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);
> +
> int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
> unsigned long addr, pte_t *ptep,
> pte_t entry, int dirty)