linux-kernel - Re: [PATCH 1/4] mm: Trial do_wp

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <42bc9a68-ef9e-2542-0b21-392a7f47bd74@virtuozzo.com>
Date:   Mon, 24 Aug 2020 11:36:22 +0300
From:   Kirill Tkhai <ktkhai@...tuozzo.com>
To:     Peter Xu <peterx@...hat.com>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org
Cc:     "Maya B . Gokhale" <gokhale2@...l.gov>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Yang Shi <yang.shi@...ux.alibaba.com>,
        Marty Mcfadden <mcfadden8@...l.gov>,
        Kirill Shutemov <kirill@...temov.name>,
        Oleg Nesterov <oleg@...hat.com>, Jann Horn <jannh@...gle.com>,
        Jan Kara <jack@...e.cz>,
        Andrea Arcangeli <aarcange@...hat.com>,
        Christoph Hellwig <hch@....de>,
        Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: [PATCH 1/4] mm: Trial do_wp_page() simplification

On 22.08.2020 02:49, Peter Xu wrote:
> From: Linus Torvalds <torvalds@...ux-foundation.org>
> 
> How about we just make sure we're the only possible valid user fo the
> page before we bother to reuse it?
> 
> Simplify, simplify, simplify.
> 
> And get rid of the nasty serialization on the page lock at the same time.
> 
> Signed-off-by: Linus Torvalds <torvalds@...ux-foundation.org>
> [peterx: add subject prefix]
> Signed-off-by: Peter Xu <peterx@...hat.com>
> ---
>  mm/memory.c | 59 +++++++++++++++--------------------------------------
>  1 file changed, 17 insertions(+), 42 deletions(-)
> 
> diff --git a/mm/memory.c b/mm/memory.c
> index 602f4283122f..cb9006189d22 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -2927,50 +2927,25 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
>  	 * not dirty accountable.
>  	 */
>  	if (PageAnon(vmf->page)) {
> -		int total_map_swapcount;
> -		if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) ||
> -					   page_count(vmf->page) != 1))
> +		struct page *page = vmf->page;
> +
> +		/* PageKsm() doesn't necessarily raise the page refcount */

No, this is wrong. PageKSM() always raises refcount. There was another problem:
KSM may raise refcount without lock_page(), and only then it takes the lock.
See get_ksm_page(GET_KSM_PAGE_NOLOCK) for the details.

So, reliable protection against parallel access requires to freeze page counter,
which is made in reuse_ksm_page().

> +		if (PageKsm(page) || page_count(page) != 1)
> +			goto copy;
> +		if (!trylock_page(page))
> +			goto copy;
> +		if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) {
> +			unlock_page(page);
>  			goto copy;
> -		if (!trylock_page(vmf->page)) {
> -			get_page(vmf->page);
> -			pte_unmap_unlock(vmf->pte, vmf->ptl);
> -			lock_page(vmf->page);
> -			vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
> -					vmf->address, &vmf->ptl);
> -			if (!pte_same(*vmf->pte, vmf->orig_pte)) {
> -				update_mmu_tlb(vma, vmf->address, vmf->pte);
> -				unlock_page(vmf->page);
> -				pte_unmap_unlock(vmf->pte, vmf->ptl);
> -				put_page(vmf->page);
> -				return 0;
> -			}
> -			put_page(vmf->page);
> -		}
> -		if (PageKsm(vmf->page)) {
> -			bool reused = reuse_ksm_page(vmf->page, vmf->vma,
> -						     vmf->address);
> -			unlock_page(vmf->page);
> -			if (!reused)
> -				goto copy;
> -			wp_page_reuse(vmf);
> -			return VM_FAULT_WRITE;
> -		}
> -		if (reuse_swap_page(vmf->page, &total_map_swapcount)) {
> -			if (total_map_swapcount == 1) {
> -				/*
> -				 * The page is all ours. Move it to
> -				 * our anon_vma so the rmap code will
> -				 * not search our parent or siblings.
> -				 * Protected against the rmap code by
> -				 * the page lock.
> -				 */
> -				page_move_anon_rmap(vmf->page, vma);
> -			}
> -			unlock_page(vmf->page);
> -			wp_page_reuse(vmf);
> -			return VM_FAULT_WRITE;
>  		}
> -		unlock_page(vmf->page);
> +		/*
> +		 * Ok, we've got the only map reference, and the only
> +		 * page count reference, and the page is locked,
> +		 * it's dark out, and we're wearing sunglasses. Hit it.
> +		 */
> +		wp_page_reuse(vmf);
> +		unlock_page(page);
> +		return VM_FAULT_WRITE;
>  	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
>  					(VM_WRITE|VM_SHARED))) {
>  		return wp_page_shared(vmf);
>