[PATCH v4 16/16] arm64/mm: Implement clear_ptes() to optimize exit, munmap, dontneed

Alistair Popple apopple at nvidia.com
Tue Dec 19 21:28:25 PST 2023


Ryan Roberts <ryan.roberts at arm.com> writes:

> With the core-mm changes in place to batch-clear ptes during
> zap_pte_range(), we can take advantage of this in arm64 to greatly
> reduce the number of tlbis we have to issue, and recover the lost
> performance in exit, munmap and madvise(DONTNEED) incured when adding
> support for transparent contiguous ptes.
>
> If we are clearing a whole contpte range, we can elide first unfolding
> that range and save the tlbis. We just clear the whole range.
>
> The following microbenchmark results demonstate the effect of this
> change on madvise(DONTNEED) performance for large pte-mapped folios.
> madvise(dontneed) is called for each page of a 1G populated mapping and
> the total time is measured. 100 iterations per run, 8 runs performed on
> both Apple M2 (VM) and Ampere Altra (bare metal). Tests performed for
> case where 1G memory is comprised of pte-mapped order-9 folios. Negative
> is faster, positive is slower, compared to baseline upon which the
> series is based:
>
> | dontneed      |    Apple M2 VM    |    Ampere Altra   |
> | order-9       |-------------------|-------------------|
> | (pte-map)     |    mean |   stdev |    mean |   stdev |
> |---------------|---------|---------|---------|---------|
> | baseline      |    0.0% |    7.9% |    0.0% |    0.0% |
> | before-change |   -1.3% |    7.0% |   13.0% |    0.0% |
> | after-change  |   -9.9% |    0.9% |   14.1% |    0.0% |
>
> The memory is initially all contpte-mapped and has to be unfolded (which
> requires tlbi for the whole block) when the first page is touched (since
> the test is madvise-ing 1 page at a time). Ampere Altra has high cost
> for tlbi; this is why cost increases there.
>
> The following microbenchmark results demonstate the recovery (and
> overall improvement) of munmap performance for large pte-mapped folios.
> munmap is called for a 1G populated mapping and the function runtime is
> measured. 100 iterations per run, 8 runs performed on both Apple M2 (VM)
> and Ampere Altra (bare metal). Tests performed for case where 1G memory
> is comprised of pte-mapped order-9 folios. Negative is faster, positive
> is slower, compared to baseline upon which the series is based:
>
> | munmap        |    Apple M2 VM    |    Ampere Altra   |
> | order-9       |-------------------|-------------------|
> | (pte-map)     |    mean |   stdev |    mean |   stdev |
> |---------------|---------|---------|---------|---------|
> | baseline      |    0.0% |    6.4% |    0.0% |    0.1% |
> | before-change |   43.3% |    1.9% |  375.2% |    0.0% |
> | after-change  |   -6.0% |    1.4% |   -0.6% |    0.2% |
>
> Tested-by: John Hubbard <jhubbard at nvidia.com>
> Signed-off-by: Ryan Roberts <ryan.roberts at arm.com>
> ---
>  arch/arm64/include/asm/pgtable.h | 42 +++++++++++++++++++++++++++++
>  arch/arm64/mm/contpte.c          | 45 ++++++++++++++++++++++++++++++++
>  2 files changed, 87 insertions(+)
>
> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> index d4805f73b9db..f5bf059291c3 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -953,6 +953,29 @@ static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
>  	return pte;
>  }
>  
> +static inline pte_t __clear_ptes(struct mm_struct *mm,
> +				 unsigned long address, pte_t *ptep,
> +				 unsigned int nr, int full)

Ping on my previous comment - why not just use the generic version
defined in patch 3 which is basically identical to this?

> +{
> +	pte_t orig_pte = __ptep_get_and_clear(mm, address, ptep);
> +	unsigned int i;
> +	pte_t pte;
> +
> +	for (i = 1; i < nr; i++) {
> +		address += PAGE_SIZE;
> +		ptep++;
> +		pte = __ptep_get_and_clear(mm, address, ptep);
> +
> +		if (pte_dirty(pte))
> +			orig_pte = pte_mkdirty(orig_pte);
> +
> +		if (pte_young(pte))
> +			orig_pte = pte_mkyoung(orig_pte);
> +	}
> +
> +	return orig_pte;
> +}
> +
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
>  static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
> @@ -1151,6 +1174,8 @@ extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte);
>  extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep);
>  extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr,
>  				pte_t *ptep, pte_t pte, unsigned int nr);
> +extern pte_t contpte_clear_ptes(struct mm_struct *mm, unsigned long addr,
> +				pte_t *ptep, unsigned int nr, int full);
>  extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
>  				unsigned long addr, pte_t *ptep);
>  extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
> @@ -1279,6 +1304,22 @@ static inline void pte_clear(struct mm_struct *mm,
>  	__pte_clear(mm, addr, ptep);
>  }
>  
> +#define clear_ptes clear_ptes
> +static inline pte_t clear_ptes(struct mm_struct *mm,
> +				unsigned long addr, pte_t *ptep,
> +				unsigned int nr, int full)
> +{
> +	pte_t pte;
> +
> +	if (nr == 1) {
> +		contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
> +		pte = __ptep_get_and_clear(mm, addr, ptep);
> +	} else
> +		pte = contpte_clear_ptes(mm, addr, ptep, nr, full);
> +
> +	return pte;
> +}
> +
>  #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
>  static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
>  				unsigned long addr, pte_t *ptep)
> @@ -1366,6 +1407,7 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
>  #define set_pte					__set_pte
>  #define set_ptes				__set_ptes
>  #define pte_clear				__pte_clear
> +#define clear_ptes				__clear_ptes
>  #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
>  #define ptep_get_and_clear			__ptep_get_and_clear
>  #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
> index 72e672024785..6f2a15ac5163 100644
> --- a/arch/arm64/mm/contpte.c
> +++ b/arch/arm64/mm/contpte.c
> @@ -293,6 +293,51 @@ void contpte_set_ptes(struct mm_struct *mm, unsigned long addr,
>  }
>  EXPORT_SYMBOL(contpte_set_ptes);
>  
> +pte_t contpte_clear_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
> +					unsigned int nr, int full)
> +{
> +	/*
> +	 * If we cover a partial contpte block at the beginning or end of the
> +	 * batch, unfold if currently folded. This makes it safe to clear some
> +	 * of the entries while keeping others. contpte blocks in the middle of
> +	 * the range, which are fully covered don't need to be unfolded because
> +	 * we will clear the full block.
> +	 */
> +
> +	unsigned int i;
> +	pte_t pte;
> +	pte_t tail;
> +
> +	if (!mm_is_user(mm))
> +		return __clear_ptes(mm, addr, ptep, nr, full);
> +
> +	if (ptep != contpte_align_down(ptep) || nr < CONT_PTES)
> +		contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
> +
> +	if (ptep + nr != contpte_align_down(ptep + nr))
> +		contpte_try_unfold(mm, addr + PAGE_SIZE * (nr - 1),
> +				   ptep + nr - 1,
> +				   __ptep_get(ptep + nr - 1));
> +
> +	pte = __ptep_get_and_clear(mm, addr, ptep);
> +
> +	for (i = 1; i < nr; i++) {
> +		addr += PAGE_SIZE;
> +		ptep++;
> +
> +		tail = __ptep_get_and_clear(mm, addr, ptep);
> +
> +		if (pte_dirty(tail))
> +			pte = pte_mkdirty(pte);
> +
> +		if (pte_young(tail))
> +			pte = pte_mkyoung(pte);
> +	}
> +
> +	return pte;
> +}
> +EXPORT_SYMBOL(contpte_clear_ptes);
> +
>  int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma,
>  					unsigned long addr, pte_t *ptep)
>  {




More information about the linux-arm-kernel mailing list