linux-kernel - Re: [patch 03/13] io-accounting: write accounting

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: <1166004294.32332.93.camel@twins>
Date:	Wed, 13 Dec 2006 11:04:54 +0100
From:	Peter Zijlstra <a.p.zijlstra@...llo.nl>
To:	Andrew Morton <akpm@...l.org>
Cc:	Suleiman Souhlal <ssouhlal@...eBSD.org>,
	linux-kernel@...r.kernel.org, balbir@...ibm.com, csturtiv@....com,
	daw@....com, guillaume.thouvenin@...l.net, jlan@....com,
	nagar@...son.ibm.com, tee@....com
Subject: Re: [patch 03/13] io-accounting: write accounting

On Wed, 2006-12-13 at 00:59 -0800, Andrew Morton wrote:
> On Wed, 13 Dec 2006 00:45:50 -0800
> Suleiman Souhlal <ssouhlal@...eBSD.org> wrote:
> 
> > akpm@...l.org wrote:
> > > From: Andrew Morton <akpm@...l.org>
> > > 
> > > Accounting writes is fairly simple: whenever a process flips a
> page from clean
> > > to dirty, we accuse it of having caused a write to underlying
> storage of
> > > PAGE_CACHE_SIZE bytes.
> > 
> > On architectures where dirtying a page doesn't cause a page fault
> (like i386), couldn't you end up billing the wrong process (in fact, I
> think that even on other archituctures set_page_dirty() doesn't get
> called immediately in the page fault handler)? 
> 
> Yes, that would be a problem in 2.6.18 and earlier.
> 
> In 2.6.19 and later, we do take a fault when transitioning a page from
> pte-clean to pte-dirty.  That was done to get the dirty-page
> accounting
> right - to avoid the
> all-of-memory-is-dirty-but-the-kernel-doesn't-know-it
> problem.
> 
> 
> > AFAICS, set_page_dirty() is mostly called when trying to unmap a
> page when trying to shrink LRU lists, and there is no guarantee that
> this happens under the process that dirtied it (in fact, the
> set_page_dirty() is often done by kswapd).

we're talking:

  shrink_page_list()
    TestSetPageLock()
    try_to_unmap()
      try_to_unmap_file()
        try_to_unmap_one()
          set_page_dirty()

Which, because its run under the page lock, should always be false,
right? perhaps a WARN_ON might do.

> hm, that code is still there in zap_pte_range().  If all is well, that
> set_page_dirty() call should never return true.  


exit_mmap(), do_unmap()
  unmap_vmas()
    unmap_page_range()
      zap_{pud,pmd,pte}_range()

vmtruncate()
  unmap_mapping_range()
    unmap_mapping_range_*()
      unmap_mapping_range_vma(), madvise_dontneed()
        zap_page_range()
          unmap_vmas()
            unmap_page_range()
              zap_{pud,pmd,pte}_range()

Which is all ran without the page lock, so might be open for a race;
however, I don't see that hurting because the whole page is un-accounted
pretty soon afterwards.

> Peter did, you ever test for that?

Nope

> (Well, it might return true in rare races, because zap_pte_range()
> doesn't lock the pages)



-
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/