Re: [PATCH 2/8] mm: memory: extend finish_fault() to support large folio

[Ryan Roberts <ryan.roberts@arm.com>]

On 06/05/2024 09:46, Baolin Wang wrote:
> Add large folio mapping establishment support for finish_fault() as a preparation,
> to support multi-size THP allocation of anonymous shmem pages in the following
> patches.
> 
> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> ---
>  mm/memory.c | 43 +++++++++++++++++++++++++++++++++----------
>  1 file changed, 33 insertions(+), 10 deletions(-)
> 
> diff --git a/mm/memory.c b/mm/memory.c
> index eea6e4984eae..936377220b77 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -4747,9 +4747,12 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
>  {
>  	struct vm_area_struct *vma = vmf->vma;
>  	struct page *page;
> +	struct folio *folio;
>  	vm_fault_t ret;
>  	bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) &&
>  		      !(vma->vm_flags & VM_SHARED);
> +	int type, nr_pages, i;
> +	unsigned long addr = vmf->address;
>  
>  	/* Did we COW the page? */
>  	if (is_cow)
> @@ -4780,24 +4783,44 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
>  			return VM_FAULT_OOM;
>  	}
>  
> +	folio = page_folio(page);
> +	nr_pages = folio_nr_pages(folio);
> +
> +	if (unlikely(userfaultfd_armed(vma))) {
> +		nr_pages = 1;
> +	} else if (nr_pages > 1) {
> +		unsigned long start = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
> +		unsigned long end = start + nr_pages * PAGE_SIZE;
> +
> +		/* In case the folio size in page cache beyond the VMA limits. */
> +		addr = max(start, vma->vm_start);
> +		nr_pages = (min(end, vma->vm_end) - addr) >> PAGE_SHIFT;
> +
> +		page = folio_page(folio, (addr - start) >> PAGE_SHIFT);

I still don't really follow the logic in this else if block. Isn't it possible
that finish_fault() gets called with a page from a folio that isn't aligned with
vmf->address?

For example, let's say we have a file who's size is 64K and which is cached in a
single large folio in the page cache. But the file is mapped into a process at
VA 16K to 80K. Let's say we fault on the first page (VA=16K). You will calculate
start=0 and end=64K I think?

Additionally, I think this path will end up mapping the entire folio (as long as
it fits in the VMA). But this bypasses the fault-around configuration. As I
think I mentioned against the RFC, this will inflate the RSS of the process and
can cause behavioural changes as a result. I believe the current advice is to
disable fault-around to prevent this kind of bloat when needed.

It might be that you need a special variant of finish_fault() for shmem?


> +	}
>  	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
> -				      vmf->address, &vmf->ptl);
> +				       addr, &vmf->ptl);
>  	if (!vmf->pte)
>  		return VM_FAULT_NOPAGE;
>  
>  	/* Re-check under ptl */
> -	if (likely(!vmf_pte_changed(vmf))) {
> -		struct folio *folio = page_folio(page);
> -		int type = is_cow ? MM_ANONPAGES : mm_counter_file(folio);
> -
> -		set_pte_range(vmf, folio, page, 1, vmf->address);
> -		add_mm_counter(vma->vm_mm, type, 1);
> -		ret = 0;
> -	} else {
> -		update_mmu_tlb(vma, vmf->address, vmf->pte);
> +	if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) {
> +		update_mmu_tlb(vma, addr, vmf->pte);
> +		ret = VM_FAULT_NOPAGE;
> +		goto unlock;
> +	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
> +		for (i = 0; i < nr_pages; i++)
> +			update_mmu_tlb(vma, addr + PAGE_SIZE * i, vmf->pte + i);
>  		ret = VM_FAULT_NOPAGE;
> +		goto unlock;
>  	}
>  
> +	set_pte_range(vmf, folio, page, nr_pages, addr);
> +	type = is_cow ? MM_ANONPAGES : mm_counter_file(folio);
> +	add_mm_counter(vma->vm_mm, type, nr_pages);
> +	ret = 0;
> +
> +unlock:
>  	pte_unmap_unlock(vmf->pte, vmf->ptl);
>  	return ret;
>  }