Re: [PATCH v3 14/15] arm64/mm: Implement ptep_set_wrprotects() to optimize fork()

[Alistair Popple <apopple@nvidia.com>]

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

> On 08/12/2023 01:37, Alistair Popple wrote:
>> 
>> Ryan Roberts <ryan.roberts@arm.com> writes:
>> 
>>> With the core-mm changes in place to batch-copy ptes during fork, we can
>>> take advantage of this in arm64 to greatly reduce the number of tlbis we
>>> have to issue, and recover the lost fork performance incured when adding
>>> support for transparent contiguous ptes.
>>>
>>> If we are write-protecting a whole contig range, we can apply the
>>> write-protection to the whole range and know that it won't change
>>> whether the range should have the contiguous bit set or not. For ranges
>>> smaller than the contig range, we will still have to unfold, apply the
>>> write-protection, then fold if the change now means the range is
>>> foldable.
>>>
>>> This optimization is possible thanks to the tightening of the Arm ARM in
>>> respect to the definition and behaviour when 'Misprogramming the
>>> Contiguous bit'. See section D21194 at
>>> https://developer.arm.com/documentation/102105/latest/
>>>
>>> Performance tested with the following test written for the will-it-scale
>>> framework:
>>>
>>> -------
>>>
>>> char *testcase_description = "fork and exit";
>>>
>>> void testcase(unsigned long long *iterations, unsigned long nr)
>>> {
>>> 	int pid;
>>> 	char *mem;
>>>
>>> 	mem = malloc(SZ_128M);
>>> 	assert(mem);
>>> 	memset(mem, 1, SZ_128M);
>>>
>>> 	while (1) {
>>> 		pid = fork();
>>> 		assert(pid >= 0);
>>>
>>> 		if (!pid)
>>> 			exit(0);
>>>
>>> 		waitpid(pid, NULL, 0);
>>>
>>> 		(*iterations)++;
>>> 	}
>>> }
>>>
>>> -------
>>>
>>> I see huge performance regression when PTE_CONT support was added, then
>>> the regression is mostly fixed with the addition of this change. The
>>> following shows regression relative to before PTE_CONT was enabled
>>> (bigger negative value is bigger regression):
>>>
>>> |   cpus |   before opt |   after opt |
>>> |-------:|-------------:|------------:|
>>> |      1 |       -10.4% |       -5.2% |
>>> |      8 |       -15.4% |       -3.5% |
>>> |     16 |       -38.7% |       -3.7% |
>>> |     24 |       -57.0% |       -4.4% |
>>> |     32 |       -65.8% |       -5.4% |
>>>
>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>> ---
>>>  arch/arm64/include/asm/pgtable.h | 30 ++++++++++++++++++++---
>>>  arch/arm64/mm/contpte.c          | 42 ++++++++++++++++++++++++++++++++
>>>  2 files changed, 69 insertions(+), 3 deletions(-)
>>>
>>> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
>>> index 15bc9cf1eef4..9bd2f57a9e11 100644
>>> --- a/arch/arm64/include/asm/pgtable.h
>>> +++ b/arch/arm64/include/asm/pgtable.h
>>> @@ -984,6 +984,16 @@ static inline void __ptep_set_wrprotect(struct mm_struct *mm,
>>>  	} while (pte_val(pte) != pte_val(old_pte));
>>>  }
>>>  
>>> +static inline void __ptep_set_wrprotects(struct mm_struct *mm,
>>> +					unsigned long address, pte_t *ptep,
>>> +					unsigned int nr)
>>> +{
>>> +	unsigned int i;
>>> +
>>> +	for (i = 0; i < nr; i++, address += PAGE_SIZE, ptep++)
>>> +		__ptep_set_wrprotect(mm, address, ptep);
>>> +}
>>> +
>>>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>>>  #define __HAVE_ARCH_PMDP_SET_WRPROTECT
>>>  static inline void pmdp_set_wrprotect(struct mm_struct *mm,
>>> @@ -1139,6 +1149,8 @@ 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,
>>>  				unsigned long addr, pte_t *ptep);
>>> +extern void contpte_set_wrprotects(struct mm_struct *mm, unsigned long addr,
>>> +				pte_t *ptep, unsigned int nr);
>>>  extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
>>>  				unsigned long addr, pte_t *ptep,
>>>  				pte_t entry, int dirty);
>>> @@ -1290,13 +1302,25 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
>>>  	return contpte_ptep_clear_flush_young(vma, addr, ptep);
>>>  }
>>>  
>>> +#define ptep_set_wrprotects ptep_set_wrprotects
>>> +static inline void ptep_set_wrprotects(struct mm_struct *mm, unsigned long addr,
>>> +				pte_t *ptep, unsigned int nr)
>>> +{
>>> +	if (!contpte_is_enabled(mm))
>>> +		__ptep_set_wrprotects(mm, addr, ptep, nr);
>>> +	else if (nr == 1) {
>> 
>> Why do we need the special case here? Couldn't we just call
>> contpte_set_wrprotects() with nr == 1?
>
> My intention is for this to be a fast path for ptep_set_wrprotect(). I'm having
> to work hard to prevent regressing the order-0 folios case.

This ends up calling three functions anyway so I'm curious - does
removing the one function call really make that much of difference?

Either way I think a comment justifying the special case (ie. that this
is simply a fast path for nr == 1) would be good.

Thanks.

>> 
>>> +		contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
>>> +		__ptep_set_wrprotects(mm, addr, ptep, 1);
>>> +		contpte_try_fold(mm, addr, ptep, __ptep_get(ptep));
>>> +	} else
>>> +		contpte_set_wrprotects(mm, addr, ptep, nr);
>>> +}
>>> +
>>>  #define __HAVE_ARCH_PTEP_SET_WRPROTECT
>>>  static inline void ptep_set_wrprotect(struct mm_struct *mm,
>>>  				unsigned long addr, pte_t *ptep)
>>>  {
>>> -	contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
>>> -	__ptep_set_wrprotect(mm, addr, ptep);
>>> -	contpte_try_fold(mm, addr, ptep, __ptep_get(ptep));
>>> +	ptep_set_wrprotects(mm, addr, ptep, 1);
>>>  }
>>>  
>>>  #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
>>> diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
>>> index e079ec61d7d1..2a57df16bf58 100644
>>> --- a/arch/arm64/mm/contpte.c
>>> +++ b/arch/arm64/mm/contpte.c
>>> @@ -303,6 +303,48 @@ int contpte_ptep_clear_flush_young(struct vm_area_struct *vma,
>>>  }
>>>  EXPORT_SYMBOL(contpte_ptep_clear_flush_young);
>>>  
>>> +void contpte_set_wrprotects(struct mm_struct *mm, unsigned long addr,
>>> +					pte_t *ptep, unsigned int nr)
>>> +{
>>> +	unsigned long next;
>>> +	unsigned long end = addr + (nr << PAGE_SHIFT);
>>> +
>>> +	do {
>>> +		next = pte_cont_addr_end(addr, end);
>>> +		nr = (next - addr) >> PAGE_SHIFT;
>>> +
>>> +		/*
>>> +		 * If wrprotecting an entire contig range, we can avoid
>>> +		 * unfolding. Just set wrprotect and wait for the later
>>> +		 * mmu_gather flush to invalidate the tlb. Until the flush, the
>>> +		 * page may or may not be wrprotected. After the flush, it is
>>> +		 * guarranteed wrprotected. If its a partial range though, we
>>> +		 * must unfold, because we can't have a case where CONT_PTE is
>>> +		 * set but wrprotect applies to a subset of the PTEs; this would
>>> +		 * cause it to continue to be unpredictable after the flush.
>>> +		 */
>>> +		if (nr != CONT_PTES)
>>> +			contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep));
>>> +
>>> +		__ptep_set_wrprotects(mm, addr, ptep, nr);
>>> +
>>> +		addr = next;
>>> +		ptep += nr;
>>> +
>>> +		/*
>>> +		 * If applying to a partial contig range, the change could have
>>> +		 * made the range foldable. Use the last pte in the range we
>>> +		 * just set for comparison, since contpte_try_fold() only
>>> +		 * triggers when acting on the last pte in the contig range.
>>> +		 */
>>> +		if (nr != CONT_PTES)
>>> +			contpte_try_fold(mm, addr - PAGE_SIZE, ptep - 1,
>>> +					 __ptep_get(ptep - 1));
>>> +
>>> +	} while (addr != end);
>>> +}
>>> +EXPORT_SYMBOL(contpte_set_wrprotects);
>>> +
>>>  int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
>>>  					unsigned long addr, pte_t *ptep,
>>>  					pte_t entry, int dirty)
>>