linux-kernel - Re: [PATCH v5 2/2] kvm: Use huge pages for DAX-backed files

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <65FB6CC1-3AD2-4D6F-9481-500BD7037203@oracle.com>
Date:   Fri, 13 Dec 2019 03:07:31 +0200
From:   Liran Alon <liran.alon@...cle.com>
To:     Barret Rhoden <brho@...gle.com>
Cc:     Paolo Bonzini <pbonzini@...hat.com>,
        Dan Williams <dan.j.williams@...el.com>,
        David Hildenbrand <david@...hat.com>,
        Dave Jiang <dave.jiang@...el.com>,
        Alexander Duyck <alexander.h.duyck@...ux.intel.com>,
        Sean Christopherson <sean.j.christopherson@...el.com>,
        linux-nvdimm@...ts.01.org, x86@...nel.org, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, jason.zeng@...el.com
Subject: Re: [PATCH v5 2/2] kvm: Use huge pages for DAX-backed files



> On 12 Dec 2019, at 21:55, Barret Rhoden <brho@...gle.com> wrote:
> 
> Hi -
> 
> On 12/12/19 1:49 PM, Liran Alon wrote:
>>> On 12 Dec 2019, at 20:47, Liran Alon <liran.alon@...cle.com> wrote:
>>> 
>>> 
>>> 
>>>> On 12 Dec 2019, at 20:22, Barret Rhoden <brho@...gle.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@...gle.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
>