Received-SPF: pass (google.com: domain of linux-kernel+bounces-57523-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Date: Thu, 8 Feb 2024 08:29:21 +0200
From: Mike Rapoport <rppt@kernel.org>
To: David Hildenbrand <david@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Matthew Wilcox <willy@infradead.org>,
	Ryan Roberts <ryan.roberts@arm.com>,
	Russell King <linux@armlinux.org.uk>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>, Dinh Nguyen <dinguyen@kernel.org>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Nicholas Piggin <npiggin@gmail.com>,
	Christophe Leroy <christophe.leroy@csgroup.eu>,
	"Aneesh Kumar K.V" <aneesh.kumar@kernel.org>,
	"Naveen N. Rao" <naveen.n.rao@linux.ibm.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Albert Ou <aou@eecs.berkeley.edu>,
	Alexander Gordeev <agordeev@linux.ibm.com>,
	Gerald Schaefer <gerald.schaefer@linux.ibm.com>,
	Heiko Carstens <hca@linux.ibm.com>,
	Vasily Gorbik <gor@linux.ibm.com>,
	Christian Borntraeger <borntraeger@linux.ibm.com>,
	Sven Schnelle <svens@linux.ibm.com>,
	"David S. Miller" <davem@davemloft.net>,
	linux-arm-kernel@lists.infradead.org, linuxppc-dev@lists.ozlabs.org,
	linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org,
	sparclinux@vger.kernel.org
Subject: Re: [PATCH v3 11/15] mm/memory: factor out copying the actual PTE in
 copy_present_pte()
Message-ID: <ZcR0waPgUzfQgyGQ@kernel.org>
References: <20240129124649.189745-1-david@redhat.com>
 <20240129124649.189745-12-david@redhat.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240129124649.189745-12-david@redhat.com>

On Mon, Jan 29, 2024 at 01:46:45PM +0100, David Hildenbrand wrote:
> Let's prepare for further changes.
> 
> Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
> Signed-off-by: David Hildenbrand <david@redhat.com>

Reviewed-by: Mike Rapoport (IBM) <rppt@kernel.org>

> ---
>  mm/memory.c | 63 ++++++++++++++++++++++++++++-------------------------
>  1 file changed, 33 insertions(+), 30 deletions(-)
> 
> diff --git a/mm/memory.c b/mm/memory.c
> index 8d14ba440929..a3bdb25f4c8d 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -930,6 +930,29 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
>  	return 0;
>  }
>  
> +static inline void __copy_present_pte(struct vm_area_struct *dst_vma,
> +		struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte,
> +		pte_t pte, unsigned long addr)
> +{
> +	struct mm_struct *src_mm = src_vma->vm_mm;
> +
> +	/* If it's a COW mapping, write protect it both processes. */
> +	if (is_cow_mapping(src_vma->vm_flags) && pte_write(pte)) {
> +		ptep_set_wrprotect(src_mm, addr, src_pte);
> +		pte = pte_wrprotect(pte);
> +	}
> +
> +	/* If it's a shared mapping, mark it clean in the child. */
> +	if (src_vma->vm_flags & VM_SHARED)
> +		pte = pte_mkclean(pte);
> +	pte = pte_mkold(pte);
> +
> +	if (!userfaultfd_wp(dst_vma))
> +		pte = pte_clear_uffd_wp(pte);
> +
> +	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
> +}
> +
>  /*
>   * Copy one pte.  Returns 0 if succeeded, or -EAGAIN if one preallocated page
>   * is required to copy this pte.
> @@ -939,23 +962,23 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
>  		 pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
>  		 struct folio **prealloc)
>  {
> -	struct mm_struct *src_mm = src_vma->vm_mm;
> -	unsigned long vm_flags = src_vma->vm_flags;
>  	pte_t pte = ptep_get(src_pte);
>  	struct page *page;
>  	struct folio *folio;
>  
>  	page = vm_normal_page(src_vma, addr, pte);
> -	if (page)
> -		folio = page_folio(page);
> -	if (page && folio_test_anon(folio)) {
> +	if (unlikely(!page))
> +		goto copy_pte;
> +
> +	folio = page_folio(page);
> +	folio_get(folio);
> +	if (folio_test_anon(folio)) {
>  		/*
>  		 * If this page may have been pinned by the parent process,
>  		 * copy the page immediately for the child so that we'll always
>  		 * guarantee the pinned page won't be randomly replaced in the
>  		 * future.
>  		 */
> -		folio_get(folio);
>  		if (unlikely(folio_try_dup_anon_rmap_pte(folio, page, src_vma))) {
>  			/* Page may be pinned, we have to copy. */
>  			folio_put(folio);
> @@ -963,34 +986,14 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
>  						 addr, rss, prealloc, page);
>  		}
>  		rss[MM_ANONPAGES]++;
> -	} else if (page) {
> -		folio_get(folio);
> +		VM_WARN_ON_FOLIO(PageAnonExclusive(page), folio);
> +	} else {
>  		folio_dup_file_rmap_pte(folio, page);
>  		rss[mm_counter_file(folio)]++;
>  	}
>  
> -	/*
> -	 * If it's a COW mapping, write protect it both
> -	 * in the parent and the child
> -	 */
> -	if (is_cow_mapping(vm_flags) && pte_write(pte)) {
> -		ptep_set_wrprotect(src_mm, addr, src_pte);
> -		pte = pte_wrprotect(pte);
> -	}
> -	VM_BUG_ON(page && folio_test_anon(folio) && PageAnonExclusive(page));
> -
> -	/*
> -	 * If it's a shared mapping, mark it clean in
> -	 * the child
> -	 */
> -	if (vm_flags & VM_SHARED)
> -		pte = pte_mkclean(pte);
> -	pte = pte_mkold(pte);
> -
> -	if (!userfaultfd_wp(dst_vma))
> -		pte = pte_clear_uffd_wp(pte);
> -
> -	set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte);
> +copy_pte:
> +	__copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, pte, addr);
>  	return 0;
>  }
>  
> -- 
> 2.43.0
> 
> 

-- 
Sincerely yours,
Mike.