Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1383804

Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault()

Show all headers | View raw

Hi Hugh,

On Sat, 16 Apr 2016 16:41:33 -0700 (PDT) Hugh Dickins <hughd@google.com> wrote:
>
> The pmd_fault() method gives the filesystem an opportunity to place
> a trans huge pmd entry at *pmd, before any pagetable is exposed (and
> an opportunity to split it on COW fault): now use it for huge tmpfs.
> 
> This patch is a little raw: with more time before LSF/MM, I would
> probably want to dress it up better - the shmem_mapping() calls look
> a bit ugly; it's odd to want FAULT_FLAG_MAY_HUGE and VM_FAULT_HUGE just
> for a private conversation between shmem_fault() and shmem_pmd_fault();
> and there might be a better distribution of work between those two, but
> prising apart that series of huge tests is not to be done in a hurry.
> 
> Good for now, presents the new way, but might be improved later.
> 
> This patch still leaves the huge tmpfs map_team_by_pmd() allocating a
> pagetable while holding page lock, but other filesystems are no longer
> doing so; and we've not yet settled whether huge tmpfs should (like anon
> THP) or should not (like DAX) participate in deposit/withdraw protocol.
> 
> Signed-off-by: Hugh Dickins <hughd@google.com>
> ---
> I've been testing with this applied on top of mmotm plus 1-4/5,
> but I suppose the right place for it is immediately after
> huge-tmpfs-map-shmem-by-huge-page-pmd-or-by-page-team-ptes.patch
> with a view to perhaps merging it into that in the future.
> 
>  mm/huge_memory.c |    4 ++--
>  mm/memory.c      |   13 +++++++++----
>  mm/shmem.c       |   33 +++++++++++++++++++++++++++++++++
>  3 files changed, 44 insertions(+), 6 deletions(-)

I added this to the end of mmotm in linux-next today.

-- 
Cheers,
Stephen Rothwell

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH mmotm 1/5] huge tmpfs: try to allocate huge pages split into  a team fix Hugh Dickins <hughd@google.com> - 2016-04-17 01:30 +0200
  [PATCH mmotm 2/5] huge tmpfs: fix mlocked meminfo track huge unhuge  mlocks fix Hugh Dickins <hughd@google.com> - 2016-04-17 01:40 +0200
    Re: [PATCH mmotm 2/5] huge tmpfs: fix mlocked meminfo track huge  unhuge mlocks fix Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 01:50 +0200
  [PATCH mmotm 4/5] huge tmpfs: avoid premature exposure of new  pagetable revert Hugh Dickins <hughd@google.com> - 2016-04-17 01:40 +0200
    Re: [PATCH mmotm 4/5] huge tmpfs: avoid premature exposure of new  pagetable revert Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 02:00 +0200
  [PATCH mmotm 3/5] huge tmpfs recovery: tweak shmem_getpage_gfp to  fill team fix Hugh Dickins <hughd@google.com> - 2016-04-17 01:40 +0200
    Re: [PATCH mmotm 3/5] huge tmpfs recovery: tweak shmem_getpage_gfp  to fill team fix Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 02:00 +0200
  [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() Hugh Dickins <hughd@google.com> - 2016-04-17 01:50 +0200
    Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() "Kirill A. Shutemov" <kirill@shutemov.name> - 2016-04-17 02:50 +0200
      Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() Hugh Dickins <hughd@google.com> - 2016-04-17 03:30 +0200
    Re: [PATCH mmotm 5/5] huge tmpfs: add shmem_pmd_fault() Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 02:00 +0200
  Re: [PATCH mmotm 1/5] huge tmpfs: try to allocate huge pages split  into a team fix Stephen Rothwell <sfr@canb.auug.org.au> - 2016-04-21 01:50 +0200

csiph-web