From: Liran Alon <liran.alon@oracle.com>
To: Barret Rhoden <brho@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
Dan Williams <dan.j.williams@intel.com>,
David Hildenbrand <david@redhat.com>,
Dave Jiang <dave.jiang@intel.com>,
Alexander Duyck <alexander.h.duyck@linux.intel.com>,
Sean Christopherson <sean.j.christopherson@intel.com>,
linux-nvdimm@lists.01.org, x86@kernel.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org, jason.zeng@intel.com
Subject: Re: [PATCH v5 2/2] kvm: Use huge pages for DAX-backed files
Date: Fri, 13 Dec 2019 03:07:31 +0200 [thread overview]
Message-ID: <65FB6CC1-3AD2-4D6F-9481-500BD7037203@oracle.com> (raw)
In-Reply-To: <f8e948ff-6a2a-a6d6-9d8e-92b93003354a@google.com>
> On 12 Dec 2019, at 21:55, Barret Rhoden <brho@google.com> wrote:
>
> Hi -
>
> On 12/12/19 1:49 PM, Liran Alon wrote:
>>> On 12 Dec 2019, at 20:47, Liran Alon <liran.alon@oracle.com> wrote:
>>>
>>>
>>>
>>>> On 12 Dec 2019, at 20:22, Barret Rhoden <brho@google.com> wrote:
>>>>
>>>> This change allows KVM to map DAX-backed files made of huge pages with
>>>> huge mappings in the EPT/TDP.
>>>
>>> This change isn’t only relevant for TDP. It also affects when KVM use shadow-paging.
>>> See how FNAME(page_fault)() calls transparent_hugepage_adjust().
>
> Cool, I'll drop references to the EPT/TDP from the commit message.
>
>>>> DAX pages are not PageTransCompound. The existing check is trying to
>>>> determine if the mapping for the pfn is a huge mapping or not.
>>>
>>> I would rephrase “The existing check is trying to determine if the pfn
>>> is mapped as part of a transparent huge-page”.
>
> Can do.
>
>>>
>>>> For
>>>> non-DAX maps, e.g. hugetlbfs, that means checking PageTransCompound.
>>>
>>> This is not related to hugetlbfs but rather THP.
>
> I thought that PageTransCompound also returned true for hugetlbfs (based off of comments in page-flags.h). Though I do see the comment about the 'level == PT_PAGE_TABLE_LEVEL' check excluding hugetlbfs pages.
>
> Anyway, I'll remove the "e.g. hugetlbfs" from the commit message.
>
>>>
>>>> For DAX, we can check the page table itself.
>>>>
>>>> Note that KVM already faulted in the page (or huge page) in the host's
>>>> page table, and we hold the KVM mmu spinlock. We grabbed that lock in
>>>> kvm_mmu_notifier_invalidate_range_end, before checking the mmu seq.
>>>>
>>>> Signed-off-by: Barret Rhoden <brho@google.com>
>>>
>>> I don’t think the right place to change for this functionality is transparent_hugepage_adjust()
>>> which is meant to handle PFNs that are mapped as part of a transparent huge-page.
>>>
>>> For example, this would prevent mapping DAX-backed file page as 1GB.
>>> As transparent_hugepage_adjust() only handles the case (level == PT_PAGE_TABLE_LEVEL).
>>>
>>> As you are parsing the page-tables to discover the page-size the PFN is mapped in,
>>> I think you should instead modify kvm_host_page_size() to parse page-tables instead
>>> of rely on vma_kernel_pagesize() (Which relies on vma->vm_ops->pagesize()) in case
>>> of is_zone_device_page().
>>> The main complication though of doing this is that at this point you don’t yet have the PFN
>>> that is retrieved by try_async_pf(). So maybe you should consider modifying the order of calls
>>> in tdp_page_fault() & FNAME(page_fault)().
>>>
>>> -Liran
>> Or alternatively when thinking about it more, maybe just rename transparent_hugepage_adjust()
>> to not be specific to THP and better handle the case of parsing page-tables changing mapping-level to 1GB.
>> That is probably easier and more elegant.
>
> I can rename it to hugepage_adjust(), since it's not just THP anymore.
Sounds good.
>
> I was a little hesitant to change the this to handle 1 GB pages with this patchset at first. I didn't want to break the non-DAX case stuff by doing so.
Why would it affect non-DAX case?
Your patch should just make hugepage_adjust() to parse page-tables only in case is_zone_device_page(). Otherwise, page tables shouldn’t be parsed.
i.e. THP merged pages should still be detected by PageTransCompoundMap().
>
> Specifically, can a THP page be 1 GB, and if so, how can you tell? If you can't tell easily, I could walk the page table for all cases, instead of just zone_device().
I prefer to walk page-tables only for is_zone_device_page().
>
> I'd also have to drop the "level == PT_PAGE_TABLE_LEVEL" check, I think, which would open this up to hugetlbfs pages (based on the comments). Is there any reason why that would be a bad idea?
KVM already supports mapping 1GB hugetlbfs pages. As level is set to PUD-level by tdp_page_fault()->mapping_level()->host_mapping_level()->kvm_host_page_size()->vma_kernel_pagesize(). As VMA which is mmap of hugetlbfs sets vma->vm_ops to hugetlb_vm_ops() where hugetlb_vm_op_pagesize() will return appropriate page-size.
Specifically, I don’t think THP ever merges small pages to 1GB pages. I think this is why transparent_hugepage_adjust() checks PageTransCompoundMap() only in case level == PT_PAGE_TABLE_LEVEL. I think you should keep this check in the case of !is_zone_device_page().
-Liran
>
> Thanks,
>
> Barret
>
next prev parent reply other threads:[~2019-12-13 1:07 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-12 18:22 [PATCH v5 0/2] kvm: Use huge pages for DAX-backed files Barret Rhoden
2019-12-12 18:22 ` [PATCH v5 1/2] mm: make dev_pagemap_mapping_shift() externally visible Barret Rhoden
2019-12-13 17:47 ` Sean Christopherson
2019-12-13 18:13 ` Dan Williams
2019-12-16 17:59 ` Barret Rhoden
2019-12-18 0:18 ` Sean Christopherson
2020-01-15 18:33 ` Paolo Bonzini
2019-12-12 18:22 ` [PATCH v5 2/2] kvm: Use huge pages for DAX-backed files Barret Rhoden
2019-12-12 18:47 ` Liran Alon
2019-12-12 18:49 ` Liran Alon
2019-12-12 19:55 ` Barret Rhoden
2019-12-13 1:07 ` Liran Alon [this message]
2019-12-13 14:13 ` Barret Rhoden
2019-12-13 17:19 ` Sean Christopherson
2019-12-13 17:31 ` Liran Alon
2019-12-13 17:50 ` Sean Christopherson
2019-12-13 18:08 ` Liran Alon
2019-12-16 16:05 ` Barret Rhoden
2020-01-07 19:05 ` Sean Christopherson
2020-01-07 19:19 ` Barret Rhoden
2020-01-08 1:20 ` Sean Christopherson
2020-01-08 1:39 ` Dan Williams
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=65FB6CC1-3AD2-4D6F-9481-500BD7037203@oracle.com \
--to=liran.alon@oracle.com \
--cc=alexander.h.duyck@linux.intel.com \
--cc=brho@google.com \
--cc=dan.j.williams@intel.com \
--cc=dave.jiang@intel.com \
--cc=david@redhat.com \
--cc=jason.zeng@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=pbonzini@redhat.com \
--cc=sean.j.christopherson@intel.com \
--cc=x86@kernel.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).