linux-kernel - Re: [PATCH 4/4] mm: prepare page_referenced() and page

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: <20151105092459.GC7614@node.shutemov.name>
Date:	Thu, 5 Nov 2015 11:24:59 +0200
From:	"Kirill A. Shutemov" <kirill@...temov.name>
To:	Vladimir Davydov <vdavydov@...tuozzo.com>
Cc:	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Hugh Dickins <hughd@...gle.com>,
	Naoya Horiguchi <n-horiguchi@...jp.nec.com>,
	Sasha Levin <sasha.levin@...cle.com>,
	Minchan Kim <minchan@...nel.org>, linux-kernel@...r.kernel.org,
	linux-mm@...ck.org
Subject: Re: [PATCH 4/4] mm: prepare page_referenced() and page_idle to new
 THP refcounting

On Thu, Nov 05, 2015 at 12:10:13PM +0300, Vladimir Davydov wrote:
> On Tue, Nov 03, 2015 at 05:26:15PM +0200, Kirill A. Shutemov wrote:
> ...
> > @@ -56,23 +56,69 @@ static int page_idle_clear_pte_refs_one(struct page *page,
> >  {
> >  	struct mm_struct *mm = vma->vm_mm;
> >  	spinlock_t *ptl;
> > +	pgd_t *pgd;
> > +	pud_t *pud;
> >  	pmd_t *pmd;
> >  	pte_t *pte;
> >  	bool referenced = false;
> >  
> > -	if (unlikely(PageTransHuge(page))) {
> > -		pmd = page_check_address_pmd(page, mm, addr, &ptl);
> > -		if (pmd) {
> > -			referenced = pmdp_clear_young_notify(vma, addr, pmd);
> > +	pgd = pgd_offset(mm, addr);
> > +	if (!pgd_present(*pgd))
> > +		return SWAP_AGAIN;
> > +	pud = pud_offset(pgd, addr);
> > +	if (!pud_present(*pud))
> > +		return SWAP_AGAIN;
> > +	pmd = pmd_offset(pud, addr);
> > +
> > +	if (pmd_trans_huge(*pmd)) {
> > +		ptl = pmd_lock(mm, pmd);
> > +                if (!pmd_present(*pmd))
> > +			goto unlock_pmd;
> > +		if (unlikely(!pmd_trans_huge(*pmd))) {
> >  			spin_unlock(ptl);
> > +			goto map_pte;
> >  		}
> > +
> > +		if (pmd_page(*pmd) != page)
> > +			goto unlock_pmd;
> > +
> > +		referenced = pmdp_clear_young_notify(vma, addr, pmd);
> > +		spin_unlock(ptl);
> > +		goto found;
> > +unlock_pmd:
> > +		spin_unlock(ptl);
> > +		return SWAP_AGAIN;
> >  	} else {
> > -		pte = page_check_address(page, mm, addr, &ptl, 0);
> > -		if (pte) {
> > -			referenced = ptep_clear_young_notify(vma, addr, pte);
> > -			pte_unmap_unlock(pte, ptl);
> > -		}
> > +		pmd_t pmde = *pmd;
> > +		barrier();
> > +		if (!pmd_present(pmde) || pmd_trans_huge(pmde))
> > +			return SWAP_AGAIN;
> > +
> > +	}
> > +map_pte:
> > +	pte = pte_offset_map(pmd, addr);
> > +	if (!pte_present(*pte)) {
> > +		pte_unmap(pte);
> > +		return SWAP_AGAIN;
> >  	}
> > +
> > +	ptl = pte_lockptr(mm, pmd);
> > +	spin_lock(ptl);
> > +
> > +	if (!pte_present(*pte)) {
> > +		pte_unmap_unlock(pte, ptl);
> > +		return SWAP_AGAIN;
> > +	}
> > +
> > +	/* THP can be referenced by any subpage */
> > +	if (pte_pfn(*pte) - page_to_pfn(page) >= hpage_nr_pages(page)) {
> > +		pte_unmap_unlock(pte, ptl);
> > +		return SWAP_AGAIN;
> > +	}
> > +
> > +	referenced = ptep_clear_young_notify(vma, addr, pte);
> > +	pte_unmap_unlock(pte, ptl);
> > +found:
> 
> Can't we hide this stuff in a helper function, which would be used by
> both page_referenced_one and page_idle_clear_pte_refs_one, instead of
> duplicating page_referenced_one code here?

I would like to, but there's no obvious way to do that: PMDs and PTEs
require different handling.

Any ideas?

-- 
 Kirill A. Shutemov
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/