Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Peter Xu <peterx@redhat.com>
To: Axel Rasmussen <axelrasmussen@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Hugh Dickins <hughd@google.com>,
	Jerome Glisse <jglisse@redhat.com>, Joe Perches <joe@perches.com>,
	Lokesh Gidra <lokeshgidra@google.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Mike Rapoport <rppt@linux.vnet.ibm.com>, Shaohua Li <shli@fb.com>,
	Shuah Khan <shuah@kernel.org>,
	Stephen Rothwell <sfr@canb.auug.org.au>,
	Wang Qing <wangqing@vivo.com>,
	linux-api@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	linux-mm@kvack.org, Brian Geffon <bgeffon@google.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	Mina Almasry <almasrymina@google.com>,
	Oliver Upton <oupton@google.com>
Subject: Re: [PATCH v4 09/10] userfaultfd/shmem: modify shmem_mcopy_atomic_pte to use install_pte()
Date: Tue, 20 Apr 2021 21:02:05 -0400
Message-ID: <20210421010205.GH4440@xz-x1> (raw)
In-Reply-To: <20210420220804.486803-10-axelrasmussen@google.com>

On Tue, Apr 20, 2021 at 03:08:03PM -0700, Axel Rasmussen wrote:
> In a previous commit, we added the mcopy_atomic_install_pte() helper.
> This helper does the job of setting up PTEs for an existing page, to map
> it into a given VMA. It deals with both the anon and shmem cases, as
> well as the shared and private cases.
> 
> In other words, shmem_mcopy_atomic_pte() duplicates a case it already
> handles. So, expose it, and let shmem_mcopy_atomic_pte() use it
> directly, to reduce code duplication.
> 
> This requires that we refactor shmem_mcopy_atomic_pte() a bit:
> 
> Instead of doing accounting (shmem_recalc_inode() et al) part-way
> through the PTE setup, do it beforehand. This frees up
> mcopy_atomic_install_pte() from having to care about this accounting,
> but it does mean we need to clean it up if we get a failure afterwards
> (shmem_uncharge()).
> 
> We can *almost* use shmem_charge() to do this, reducing code
> duplication. But, it does `inode->i_mapping->nrpages++`, which would
> double-count since shmem_add_to_page_cache() also does this.

Missing to mention the lru_cache_add() replacement comment as Hugh commented on
this?

> 
> Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
> ---
>  include/linux/userfaultfd_k.h |  5 ++++
>  mm/shmem.c                    | 53 ++++++++---------------------------
>  mm/userfaultfd.c              | 17 ++++-------
>  3 files changed, 22 insertions(+), 53 deletions(-)
> 
> diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
> index 794d1538b8ba..39c094cc6641 100644
> --- a/include/linux/userfaultfd_k.h
> +++ b/include/linux/userfaultfd_k.h
> @@ -53,6 +53,11 @@ enum mcopy_atomic_mode {
>  	MCOPY_ATOMIC_CONTINUE,
>  };
>  
> +extern int mcopy_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
> +				    struct vm_area_struct *dst_vma,
> +				    unsigned long dst_addr, struct page *page,
> +				    bool newly_allocated, bool wp_copy);
> +
>  extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
>  			    unsigned long src_start, unsigned long len,
>  			    bool *mmap_changing, __u64 mode);
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 30c0bb501dc9..9bfa80fcd414 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -2378,10 +2378,8 @@ int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
>  	struct address_space *mapping = inode->i_mapping;
>  	gfp_t gfp = mapping_gfp_mask(mapping);
>  	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
> -	spinlock_t *ptl;
>  	void *page_kaddr;
>  	struct page *page;
> -	pte_t _dst_pte, *dst_pte;
>  	int ret;
>  	pgoff_t max_off;
>  
> @@ -2391,8 +2389,10 @@ int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
>  
>  	if (!*pagep) {
>  		page = shmem_alloc_page(gfp, info, pgoff);
> -		if (!page)
> -			goto out_unacct_blocks;
> +		if (!page) {
> +			shmem_inode_unacct_blocks(inode, 1);
> +			goto out;
> +		}
>  
>  		if (!zeropage) {	/* COPY */
>  			page_kaddr = kmap_atomic(page);
> @@ -2432,59 +2432,28 @@ int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
>  	if (ret)
>  		goto out_release;
>  
> -	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
> -	if (dst_vma->vm_flags & VM_WRITE)
> -		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
> -	else {
> -		/*
> -		 * We don't set the pte dirty if the vma has no
> -		 * VM_WRITE permission, so mark the page dirty or it
> -		 * could be freed from under us. We could do it
> -		 * unconditionally before unlock_page(), but doing it
> -		 * only if VM_WRITE is not set is faster.
> -		 */
> -		set_page_dirty(page);
> -	}
> -
> -	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
> -
> -	ret = -EFAULT;
> -	max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
> -	if (unlikely(pgoff >= max_off))
> -		goto out_release_unlock;
> -
> -	ret = -EEXIST;
> -	if (!pte_none(*dst_pte))
> -		goto out_release_unlock;
> -
> -	lru_cache_add(page);
> -
>  	spin_lock_irq(&info->lock);
>  	info->alloced++;
>  	inode->i_blocks += BLOCKS_PER_PAGE;
>  	shmem_recalc_inode(inode);
>  	spin_unlock_irq(&info->lock);
>  
> -	inc_mm_counter(dst_mm, mm_counter_file(page));
> -	page_add_file_rmap(page, false);
> -	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
> +	ret = mcopy_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
> +				       page, true, false);
> +	if (ret)
> +		goto out_release_uncharge;
>  
> -	/* No need to invalidate - it was non-present before */
> -	update_mmu_cache(dst_vma, dst_addr, dst_pte);
> -	pte_unmap_unlock(dst_pte, ptl);
> +	SetPageDirty(page);
>  	unlock_page(page);
>  	ret = 0;
>  out:
>  	return ret;
> -out_release_unlock:
> -	pte_unmap_unlock(dst_pte, ptl);
> -	ClearPageDirty(page);
> +out_release_uncharge:
>  	delete_from_page_cache(page);
> +	shmem_uncharge(inode, 1);
>  out_release:
>  	unlock_page(page);
>  	put_page(page);
> -out_unacct_blocks:

Will all the "goto out_release" miss one call to shmem_inode_unacct_blocks()?

> -	shmem_inode_unacct_blocks(inode, 1);
>  	goto out;
>  }
>  #endif /* CONFIG_USERFAULTFD */
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index 51d8c0127161..3a9ddbb2dbbd 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -51,18 +51,13 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm,
>  /*
>   * Install PTEs, to map dst_addr (within dst_vma) to page.
>   *
> - * This function handles MCOPY_ATOMIC_CONTINUE (which is always file-backed),
> - * whether or not dst_vma is VM_SHARED. It also handles the more general
> - * MCOPY_ATOMIC_NORMAL case, when dst_vma is *not* VM_SHARED (it may be file
> - * backed, or not).
> - *
> - * Note that MCOPY_ATOMIC_NORMAL for a VM_SHARED dst_vma is handled by
> - * shmem_mcopy_atomic_pte instead.
> + * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem
> + * and anon, and for both shared and private VMAs.
>   */
> -static int mcopy_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
> -				    struct vm_area_struct *dst_vma,
> -				    unsigned long dst_addr, struct page *page,
> -				    bool newly_allocated, bool wp_copy)
> +int mcopy_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
> +			     struct vm_area_struct *dst_vma,
> +			     unsigned long dst_addr, struct page *page,
> +			     bool newly_allocated, bool wp_copy)
>  {
>  	int ret;
>  	pte_t _dst_pte, *dst_pte;
> -- 
> 2.31.1.368.gbe11c130af-goog
> 

-- 
Peter Xu


  reply index

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-20 22:07 [PATCH v4 00/10] userfaultfd: add minor fault handling for shmem Axel Rasmussen
2021-04-20 22:07 ` [PATCH v4 01/10] userfaultfd/hugetlbfs: avoid including userfaultfd_k.h in hugetlb.h Axel Rasmussen
2021-04-27  2:05   ` Hugh Dickins
2021-04-20 22:07 ` [PATCH v4 02/10] userfaultfd/shmem: combine shmem_{mcopy_atomic,mfill_zeropage}_pte Axel Rasmussen
2021-04-20 22:07 ` [PATCH v4 03/10] userfaultfd/shmem: support UFFDIO_CONTINUE for shmem Axel Rasmussen
2021-04-22 20:22   ` Axel Rasmussen
2021-04-22 21:18     ` Peter Xu
2021-04-22 22:05       ` Axel Rasmussen
2021-04-27  2:19   ` Hugh Dickins
2021-04-27 15:54     ` Peter Xu
2021-04-27 16:57       ` Axel Rasmussen
2021-04-27 18:03         ` Peter Xu
2021-04-27 20:29           ` Axel Rasmussen
2021-04-27 20:42             ` Peter Xu
2021-04-27 20:59               ` Hugh Dickins
2021-04-20 22:07 ` [PATCH v4 04/10] userfaultfd/shmem: support minor fault registration " Axel Rasmussen
2021-04-27  2:23   ` Hugh Dickins
2021-04-27 15:57     ` Peter Xu
2021-04-27 17:03       ` Axel Rasmussen
2021-04-20 22:07 ` [PATCH v4 05/10] userfaultfd/selftests: use memfd_create for shmem test type Axel Rasmussen
2021-04-20 22:08 ` [PATCH v4 06/10] userfaultfd/selftests: create alias mappings in the shmem test Axel Rasmussen
2021-04-20 22:08 ` [PATCH v4 07/10] userfaultfd/selftests: reinitialize test context in each test Axel Rasmussen
2021-04-20 22:08 ` [PATCH v4 08/10] userfaultfd/selftests: exercise minor fault handling shmem support Axel Rasmussen
2021-04-20 22:08 ` [PATCH v4 09/10] userfaultfd/shmem: modify shmem_mcopy_atomic_pte to use install_pte() Axel Rasmussen
2021-04-21  1:02   ` Peter Xu [this message]
2021-04-27  2:59     ` Hugh Dickins
2021-04-20 22:08 ` [PATCH v4 10/10] userfaultfd: update documentation to mention shmem minor faults Axel Rasmussen
2021-04-27  2:27   ` Hugh Dickins

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210421010205.GH4440@xz-x1 \
    --to=peterx@redhat.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=almasrymina@google.com \
    --cc=axelrasmussen@google.com \
    --cc=bgeffon@google.com \
    --cc=dgilbert@redhat.com \
    --cc=hughd@google.com \
    --cc=jglisse@redhat.com \
    --cc=joe@perches.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lokeshgidra@google.com \
    --cc=mike.kravetz@oracle.com \
    --cc=oupton@google.com \
    --cc=rppt@linux.vnet.ibm.com \
    --cc=sfr@canb.auug.org.au \
    --cc=shli@fb.com \
    --cc=shuah@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=wangqing@vivo.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-fsdevel linux-fsdevel/ https://lore.kernel.org/linux-fsdevel \
		linux-fsdevel@vger.kernel.org
	public-inbox-index linux-fsdevel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-fsdevel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git