Re: [RFC PATCH v3 3/4] mm: add do_set_pte_range()

["Yin, Fengwei" <fengwei.yin@intel.com>]

On 2/3/2023 9:32 PM, Chih-En Lin wrote:
> On Fri, Feb 03, 2023 at 09:16:35PM +0800, Yin Fengwei wrote:
>> do_set_pte_range() allows to setup page table entries for a
>> specific range. It calls folio_add_file_rmap_range() to take
>> advantage of batched rmap update for large folio.
>>
>> Signed-off-by: Yin Fengwei <fengwei.yin@intel.com>
>> ---
>>  include/linux/mm.h |  3 +++
>>  mm/filemap.c       |  1 -
>>  mm/memory.c        | 59 ++++++++++++++++++++++++++++++----------------
>>  3 files changed, 42 insertions(+), 21 deletions(-)
>>
>> diff --git a/include/linux/mm.h b/include/linux/mm.h
>> index d6f8f41514cc..93192f04b276 100644
>> --- a/include/linux/mm.h
>> +++ b/include/linux/mm.h
>> @@ -1162,6 +1162,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
>>  
>>  vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
>>  void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr);
>> +void do_set_pte_range(struct vm_fault *vmf, struct folio *folio,
>> +		unsigned long addr, pte_t *pte,
>> +		unsigned long start, unsigned int nr);
>>  
>>  vm_fault_t finish_fault(struct vm_fault *vmf);
>>  vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
>> diff --git a/mm/filemap.c b/mm/filemap.c
>> index f444684db9f2..74046a3a0ff5 100644
>> --- a/mm/filemap.c
>> +++ b/mm/filemap.c
>> @@ -3386,7 +3386,6 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
>>  
>>  		ref_count++;
>>  		do_set_pte(vmf, page, addr);
>> -		update_mmu_cache(vma, addr, vmf->pte);
>>  	} while (vmf->pte++, page++, addr += PAGE_SIZE, ++count < nr_pages);
>>  
>>  	/* Restore the vmf->pte */
>> diff --git a/mm/memory.c b/mm/memory.c
>> index 7a04a1130ec1..3754b2ef166a 100644
>> --- a/mm/memory.c
>> +++ b/mm/memory.c
>> @@ -4257,36 +4257,58 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
>>  }
>>  #endif
>>  
>> -void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
>> +void do_set_pte_range(struct vm_fault *vmf, struct folio *folio,
>> +		unsigned long addr, pte_t *pte,
>> +		unsigned long start, unsigned int nr)
>>  {
>>  	struct vm_area_struct *vma = vmf->vma;
>>  	bool uffd_wp = pte_marker_uffd_wp(vmf->orig_pte);
>>  	bool write = vmf->flags & FAULT_FLAG_WRITE;
>> +	bool cow = write && !(vma->vm_flags & VM_SHARED);
> 
> Why don't use is_cow_mapping()?
> Is there anything messed up with VM_MAYWRITE?
My understanding is it's not related with the mapping. It's related with
what operation triggers fault here. Say, if it's a writable mapping, and
if the read operation triggers fault here, no cow or maybe_mkwrite() needed
here. Thanks.


Regards
Yin, Fengwei

> 
>>  	bool prefault = vmf->address != addr;
>> +	struct page *page = folio_page(folio, start);
>>  	pte_t entry;
>>  
>> -	flush_icache_page(vma, page);
>> -	entry = mk_pte(page, vma->vm_page_prot);
>> +	if (!cow) {
>> +		folio_add_file_rmap_range(folio, start, nr, vma, false);
>> +		add_mm_counter(vma->vm_mm, mm_counter_file(page), nr);
>> +	}
>>  
>> -	if (prefault && arch_wants_old_prefaulted_pte())
>> -		entry = pte_mkold(entry);
>> -	else
>> -		entry = pte_sw_mkyoung(entry);
>> +	do {
>> +		flush_icache_page(vma, page);
>> +		entry = mk_pte(page, vma->vm_page_prot);
>>  
>> -	if (write)
>> -		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
>> -	if (unlikely(uffd_wp))
>> -		entry = pte_mkuffd_wp(entry);
>> -	/* copy-on-write page */
>> -	if (write && !(vma->vm_flags & VM_SHARED)) {
>> +		if (prefault && arch_wants_old_prefaulted_pte())
>> +			entry = pte_mkold(entry);
>> +		else
>> +			entry = pte_sw_mkyoung(entry);
>> +
>> +		if (write)
>> +			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
>> +		if (unlikely(uffd_wp))
>> +			entry = pte_mkuffd_wp(entry);
>> +		set_pte_at(vma->vm_mm, addr, pte, entry);
>> +
>> +		/* no need to invalidate: a not-present page won't be cached */
>> +		update_mmu_cache(vma, addr, pte);
>> +	} while (pte++, page++, addr += PAGE_SIZE, --nr > 0);
>> +}
>> +
>> +void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
>> +{
>> +	struct folio *folio = page_folio(page);
>> +	struct vm_area_struct *vma = vmf->vma;
>> +	bool cow = (vmf->flags & FAULT_FLAG_WRITE) &&
>> +			!(vma->vm_flags & VM_SHARED);
> 
> Here too.
> 
>> +
>> +	if (cow) {
>>  		inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
>>  		page_add_new_anon_rmap(page, vma, addr);
>>  		lru_cache_add_inactive_or_unevictable(page, vma);
>> -	} else {
>> -		inc_mm_counter(vma->vm_mm, mm_counter_file(page));
>> -		page_add_file_rmap(page, vma, false);
>>  	}
>> -	set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
>> +
>> +	do_set_pte_range(vmf, folio, addr, vmf->pte,
>> +			folio_page_idx(folio, page), 1);
>>  }
>>  
>>  static bool vmf_pte_changed(struct vm_fault *vmf)
>> @@ -4361,9 +4383,6 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
>>  	if (likely(!vmf_pte_changed(vmf))) {
>>  		do_set_pte(vmf, page, vmf->address);
>>  
>> -		/* no need to invalidate: a not-present page won't be cached */
>> -		update_mmu_cache(vma, vmf->address, vmf->pte);
>> -
>>  		ret = 0;
>>  	} else {
>>  		update_mmu_tlb(vma, vmf->address, vmf->pte);
>> -- 
>> 2.30.2
>>
>>
> 
> Thanks,
> Chih-En Lin
>