From: "Kirill A. Shutemov" <kirill@shutemov.name>
To: Dave Hansen <dave.hansen@intel.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Hugh Dickins <hughd@google.com>,
Andrea Arcangeli <aarcange@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Vlastimil Babka <vbabka@suse.cz>,
Christoph Lameter <cl@gentwo.org>,
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
Jerome Marchand <jmarchan@redhat.com>,
Yang Shi <yang.shi@linaro.org>,
Sasha Levin <sasha.levin@oracle.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCHv2 17/28] thp: skip file huge pmd on copy_huge_pmd()
Date: Thu, 18 Feb 2016 14:41:44 +0200 [thread overview]
Message-ID: <20160218124143.GB28184@node.shutemov.name> (raw)
In-Reply-To: <56C3445D.3040305@intel.com>
On Tue, Feb 16, 2016 at 07:46:37AM -0800, Dave Hansen wrote:
> On 02/16/2016 02:14 AM, Kirill A. Shutemov wrote:
> > On Fri, Feb 12, 2016 at 10:42:09AM -0800, Dave Hansen wrote:
> >> On 02/11/2016 06:21 AM, Kirill A. Shutemov wrote:
> >>> File pmds can be safely skip on copy_huge_pmd(), we can re-fault them
> >>> later. COW for file mappings handled on pte level.
> >>
> >> Is this different from 4k pages? I figured we might skip copying
> >> file-backed ptes on fork, but I couldn't find the code.
> >
> > Currently, we only filter out on per-VMA basis. See first comment in
> > copy_page_range().
> >
> > Here we handle PMD mapped file pages in COW mapping. File THP can be
> > mapped into COW mapping as result of read page fault.
>
> OK... So, copy_page_range() has a check for "Don't copy ptes where a
> page fault will fill them correctly." Seems sane enough, but the check
> is implemented using a check for the VMA having !vma->anon_vma, which is
> a head-scratcher for a moment. Why does that apply to huge tmpfs?
>
> Ahh, MAP_PRIVATE. MAP_PRIVATE vmas have ->anon_vma because they have
> essentially-anonymous pages for when they do a COW, so they don't hit
> that check and they go through the copy_*() functions, including
> copy_huge_pmd().
>
> We don't handle 2M COW operations yet so we simply decline to copy these
> pages. Might cost us page faults down the road, but it makes things
> easier to implement for now.
>
> Did I get that right?
Yep.
> Any chance we could get a bit of that into the patch descriptions so
> that the next hapless reviewer can spend their time looking at your code
> instead of relearning the fork() handling for MAP_PRIVATE?
Sure.
--
Kirill A. Shutemov
next prev parent reply other threads:[~2016-02-18 12:41 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-11 14:21 [PATCHv2 00/28] huge tmpfs implementation using compound pages Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 01/28] thp, dax: do not try to withdraw pgtable from non-anon VMA Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 02/28] rmap: introduce rmap_walk_locked() Kirill A. Shutemov
2016-02-11 18:52 ` Andi Kleen
2016-02-16 9:36 ` Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 03/28] rmap: extend try_to_unmap() to be usable by split_huge_page() Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 04/28] mm: make remove_migration_ptes() beyond mm/migration.c Kirill A. Shutemov
2016-02-12 16:54 ` Dave Hansen
2016-02-16 9:54 ` Kirill A. Shutemov
2016-02-16 15:29 ` Dave Hansen
2016-02-11 14:21 ` [PATCHv2 05/28] thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 06/28] mm: do not pass mm_struct into handle_mm_fault Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 07/28] mm: introduce fault_env Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 08/28] mm: postpone page table allocation until do_set_pte() Kirill A. Shutemov
2016-02-12 17:44 ` Dave Hansen
2016-02-16 14:26 ` Kirill A. Shutemov
2016-02-16 17:17 ` Dave Hansen
2016-02-23 13:05 ` Kirill A. Shutemov
2016-02-16 17:38 ` Dave Hansen
2016-02-23 22:58 ` Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 09/28] rmap: support file thp Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 10/28] mm: introduce do_set_pmd() Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 11/28] mm, rmap: account file thp pages Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 12/28] thp, vmstats: add counters for huge file pages Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 13/28] thp: support file pages in zap_huge_pmd() Kirill A. Shutemov
2016-02-12 18:33 ` Dave Hansen
2016-02-16 10:00 ` Kirill A. Shutemov
2016-02-16 15:31 ` Dave Hansen
2016-02-18 12:19 ` Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 14/28] thp: handle file pages in split_huge_pmd() Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 15/28] thp: handle file COW faults Kirill A. Shutemov
2016-02-12 18:36 ` Dave Hansen
2016-02-16 10:08 ` Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 16/28] thp: handle file pages in mremap() Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 17/28] thp: skip file huge pmd on copy_huge_pmd() Kirill A. Shutemov
2016-02-12 18:42 ` Dave Hansen
2016-02-16 10:14 ` Kirill A. Shutemov
2016-02-16 15:46 ` Dave Hansen
2016-02-18 12:41 ` Kirill A. Shutemov [this message]
2016-02-11 14:21 ` [PATCHv2 18/28] thp: prepare change_huge_pmd() for file thp Kirill A. Shutemov
2016-02-12 18:48 ` Dave Hansen
2016-02-16 10:15 ` Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 19/28] thp: run vma_adjust_trans_huge() outside i_mmap_rwsem Kirill A. Shutemov
2016-02-12 18:50 ` Dave Hansen
2016-02-16 10:16 ` Kirill A. Shutemov
2016-02-16 15:49 ` Dave Hansen
2016-02-11 14:21 ` [PATCHv2 20/28] thp: file pages support for split_huge_page() Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 21/28] vmscan: split file huge pages before paging them out Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 22/28] page-flags: relax policy for PG_mappedtodisk and PG_reclaim Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 23/28] radix-tree: implement radix_tree_maybe_preload_order() Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 24/28] filemap: prepare find and delete operations for huge pages Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 25/28] truncate: handle file thp Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 26/28] shmem: prepare huge=N mount option and /proc/sys/vm/shmem_huge Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 27/28] shmem: get_unmapped_area align huge page Kirill A. Shutemov
2016-02-11 14:21 ` [PATCHv2 28/28] shmem: add huge pages support Kirill A. Shutemov
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=20160218124143.GB28184@node.shutemov.name \
--to=kirill@shutemov.name \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@gentwo.org \
--cc=dave.hansen@intel.com \
--cc=hughd@google.com \
--cc=jmarchan@redhat.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=n-horiguchi@ah.jp.nec.com \
--cc=sasha.levin@oracle.com \
--cc=vbabka@suse.cz \
--cc=yang.shi@linaro.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).