Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1282280
| From | Dan Williams <dan.j.williams@intel.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping |
| Date | 2015-12-02 20:10 +0100 |
| Message-ID | <qBkWS-2Tg-29@gated-at.bofh.it> (permalink) |
| References | (3 earlier) <qB6Ax-1Pr-1@gated-at.bofh.it> <qBiLp-1hG-39@gated-at.bofh.it> <qBjxL-1Sz-1@gated-at.bofh.it> <qBk0P-2jf-25@gated-at.bofh.it> <qBktP-2ty-1@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On Wed, Dec 2, 2015 at 11:26 AM, Toshi Kani <toshi.kani@hpe.com> wrote:
> On Wed, 2015-12-02 at 10:06 -0800, Dan Williams wrote:
>> On Wed, Dec 2, 2015 at 9:01 AM, Dan Williams <dan.j.williams@intel.com> wrote:
>> > On Wed, Dec 2, 2015 at 9:43 AM, Toshi Kani <toshi.kani@hpe.com> wrote:
>> > > Oh, I see. I will setup the memmap array and run the tests again.
>> > >
>> > > But, why does the PMD mapping depend on the memmap array? We have
>> > > observed major performance improvement with PMD. This feature should
>> > > always be enabled with DAX regardless of the option to allocate the memmap
>> > > array.
>> > >
>> >
>> > Several factors drove this decision, I'm open to considering
>> > alternatives but here's the reasoning:
>> >
>> > 1/ DAX pmd mappings caused crashes in the get_user_pages path leading
>> > to commit e82c9ed41e8 "dax: disable pmd mappings". The reason pte
>> > mappings don't crash and instead trigger -EFAULT is due to the
>> > _PAGE_SPECIAL pte bit.
>> >
>> > 2/ To enable get_user_pages for DAX, in both the page and huge-page
>> > case, we need a new pte bit _PAGE_DEVMAP.
>> >
>> > 3/ Given the pte bits are hard to come I'm assuming we won't get two,
>> > i.e. both _PAGE_DEVMAP and a new _PAGE_SPECIAL for pmds. Even if we
>> > could get a _PAGE_SPECIAL for pmds I'm not in favor of pursuing it.
>>
>> Actually, Dave says they aren't that hard to come by for pmds, so we
>> could go add _PMD_SPECIAL if we really wanted to support the limited
>> page-less DAX-pmd case.
>>
>> But I'm still of the opinion that we run away from the page-less case
>> until it can be made a full class citizen with O_DIRECT for pfn
>> support.
>
> I may be missing something, but per vm_normal_page(), I think _PAGE_SPECIAL can
> be substituted by the following check when we do not have the memmap.
>
> if ((vma->vm_flags & VM_PFNMAP) ||
> ((vma->vm_flags & VM_MIXEDMAP) && (!pfn_valid(pfn)))) {
>
> This is what I did in this patch for follow_trans_huge_pmd(), although I missed
> the pfn_valid() check.
That works for __get_user_pages but not __get_user_pages_fast where we
don't have access to the vma.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-11-30 23:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-02 02:30 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-02 04:50 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-02 17:50 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-02 18:40 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-02 19:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-02 19:40 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-02 20:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-02 20:20 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-02 21:00 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-02 21:50 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-02 22:00 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-02 22:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-04 00:50 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-04 17:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dave Hansen <dave.hansen@intel.com> - 2015-12-02 23:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dave Hansen <dave.hansen@intel.com> - 2015-12-02 23:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-02 23:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-02 20:10 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Toshi Kani <toshi.kani@hpe.com> - 2015-12-03 00:30 +0100
Re: [PATCH] mm: Fix mmap MAP_POPULATE for DAX pmd mapping Dan Williams <dan.j.williams@intel.com> - 2015-12-03 00:40 +0100
csiph-web