linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Anshuman Khandual <anshuman.khandual@arm.com>
To: Will Deacon <will.deacon@arm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>,
	Zi Yan <zi.yan@cs.rutgers.edu>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	kirill.shutemov@linux.intel.com, akpm@linux-foundation.org,
	mhocko@suse.com, Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Subject: Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry
Date: Tue, 6 Nov 2018 15:21:46 +0530	[thread overview]
Message-ID: <9370f2b9-0fcd-6bbb-fa29-568bbd9aba59@arm.com> (raw)
In-Reply-To: <20181106003509.GA27283@brain-police>



On 11/06/2018 06:05 AM, Will Deacon wrote:
> On Fri, Nov 02, 2018 at 11:45:00AM +0530, Anshuman Khandual wrote:
>> On 10/17/2018 07:39 AM, Andrea Arcangeli wrote:
>>> What we need to do during split is an invalidate of the huge TLB.
>>> There's no pmd_trans_splitting anymore, so we only clear the present
>>> bit in the PTE despite pmd_present still returns true (just like
>>> PROT_NONE, nothing new in this respect). pmd_present never meant the
>>
>> On arm64, the problem is that pmd_present() is tied with pte_present() which
>> checks for PTE_VALID (also PTE_PROT_NONE) but which gets cleared during PTE
>> invalidation. pmd_present() returns false just after the first step of PMD
>> splitting. So pmd_present() needs to be decoupled from PTE_VALID which is
>> same as PMD_SECT_VALID and instead should depend upon a pte bit which sticks
>> around like PAGE_PSE as in case of x86. I am working towards a solution.
> 
> Could we not just go via a PROT_NONE mapping during the split, instead of
> having to allocate a new software bit to treat these invalid ptes as
> present?

The problem might occur during page fault (i.e __handle_mm_fault). As discussed
previously on this thread any potential PTE sticky bit would be used for both
pmd_trans_huge() and pmd_present() wrappers to maintain existing semantics. At
present, PMD state analysis during page fault has conditional block like this.

                if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
                        if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
                                return do_huge_pmd_numa_page(&vmf, orig_pmd);

Using PROT_NONE for pmd_trans_huge() might force PMD page fault to go through
NUMA fault handling all the time as both pmd_trans_huge() and pmd_protnone()
will return true in that situation.

      reply	other threads:[~2018-11-06  9:51 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-09  3:58 Anshuman Khandual
2018-10-09 13:04 ` Kirill A. Shutemov
2018-10-09 13:18   ` Will Deacon
2018-10-12  8:02     ` Anshuman Khandual
2018-10-15  8:32       ` Aneesh Kumar K.V
2018-10-16 13:16         ` Anshuman Khandual
2018-10-09 13:42   ` Anshuman Khandual
2018-10-09 13:58 ` Zi Yan
2018-10-10  4:05   ` Anshuman Khandual
2018-10-10 12:43     ` Zi Yan
2018-10-12  8:00       ` Anshuman Khandual
2018-10-15  0:53         ` Zi Yan
2018-10-15  4:06           ` Anshuman Khandual
2018-10-16 14:31             ` Zi Yan
2018-10-18  2:17               ` Naoya Horiguchi
2018-11-02  5:22                 ` Anshuman Khandual
2018-10-25  8:10               ` Anshuman Khandual
2018-10-25 18:45                 ` Zi Yan
2018-10-26  1:39                   ` Anshuman Khandual
2018-10-17  2:09           ` Andrea Arcangeli
2018-10-22 14:00             ` Zi Yan
2018-11-02  6:15             ` Anshuman Khandual
2018-11-06  0:35               ` Will Deacon
2018-11-06  9:51                 ` Anshuman Khandual [this message]

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=9370f2b9-0fcd-6bbb-fa29-568bbd9aba59@arm.com \
    --to=anshuman.khandual@arm.com \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=n-horiguchi@ah.jp.nec.com \
    --cc=will.deacon@arm.com \
    --cc=zi.yan@cs.rutgers.edu \
    --subject='Re: [PATCH] mm/thp: Correctly differentiate between mapped THP and PMD migration entry' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).