From: Fuad Tabba <tabba@google.com>
To: Sean Christopherson <seanjc@google.com>
Cc: Chao Peng <chao.p.peng@linux.intel.com>,
David Hildenbrand <david@redhat.com>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
linux-api@vger.kernel.org, linux-doc@vger.kernel.org,
qemu-devel@nongnu.org, Paolo Bonzini <pbonzini@redhat.com>,
Jonathan Corbet <corbet@lwn.net>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
"J . Bruce Fields" <bfields@fieldses.org>,
Andrew Morton <akpm@linux-foundation.org>,
Shuah Khan <shuah@kernel.org>, Mike Rapoport <rppt@kernel.org>,
Steven Price <steven.price@arm.com>,
"Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
Vlastimil Babka <vbabka@suse.cz>,
Vishal Annapurve <vannapurve@google.com>,
Yu Zhang <yu.c.zhang@linux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
ak@linux.intel.com, aarcange@redhat.com, ddutile@redhat.com,
dhildenb@redhat.com, Quentin Perret <qperret@google.com>,
Michael Roth <michael.roth@amd.com>,
mhocko@suse.com, Muchun Song <songmuchun@bytedance.com>,
wei.w.wang@intel.com, Will Deacon <will@kernel.org>,
Marc Zyngier <maz@kernel.org>
Subject: Re: [PATCH v8 1/8] mm/memfd: Introduce userspace inaccessible memfd
Date: Wed, 19 Oct 2022 16:04:57 +0100 [thread overview]
Message-ID: <CA+EHjTwrTe1-ryt0sYx7360qeYmifEQqUa-_T=25eb4s6F0JPw@mail.gmail.com> (raw)
In-Reply-To: <Y030bGhh0mvGS6E1@google.com>
Hi,
On Tue, Oct 18, 2022 at 1:34 AM Sean Christopherson <seanjc@google.com> wrote:
>
> On Fri, Sep 30, 2022, Fuad Tabba wrote:
> > > > > > pKVM would also need a way to make an fd accessible again
> > > > > > when shared back, which I think isn't possible with this patch.
> > > > >
> > > > > But does pKVM really want to mmap/munmap a new region at the page-level,
> > > > > that can cause VMA fragmentation if the conversion is frequent as I see.
> > > > > Even with a KVM ioctl for mapping as mentioned below, I think there will
> > > > > be the same issue.
> > > >
> > > > pKVM doesn't really need to unmap the memory. What is really important
> > > > is that the memory is not GUP'able.
> > >
> > > Well, not entirely unguppable, just unguppable without a magic FOLL_* flag,
> > > otherwise KVM wouldn't be able to get the PFN to map into guest memory.
> > >
> > > The problem is that gup() and "mapped" are tied together. So yes, pKVM doesn't
> > > strictly need to unmap memory _in the untrusted host_, but since mapped==guppable,
> > > the end result is the same.
> > >
> > > Emphasis above because pKVM still needs unmap the memory _somehwere_. IIUC, the
> > > current approach is to do that only in the stage-2 page tables, i.e. only in the
> > > context of the hypervisor. Which is also the source of the gup() problems; the
> > > untrusted kernel is blissfully unaware that the memory is inaccessible.
> > >
> > > Any approach that moves some of that information into the untrusted kernel so that
> > > the kernel can protect itself will incur fragmentation in the VMAs. Well, unless
> > > all of guest memory becomes unguppable, but that's likely not a viable option.
> >
> > Actually, for pKVM, there is no need for the guest memory to be GUP'able at
> > all if we use the new inaccessible_get_pfn().
>
> Ya, I was referring to pKVM without UPM / inaccessible memory.
>
> Jumping back to blocking gup(), what about using the same tricks as secretmem to
> block gup()? E.g. compare vm_ops to block regular gup() and a_ops to block fast
> gup() on struct page? With a Kconfig that's selected by pKVM (which would also
> need its own Kconfig), e.g. CONFIG_INACCESSIBLE_MAPPABLE_MEM, there would be zero
> performance overhead for non-pKVM kernels, i.e. hooking gup() shouldn't be
> controversial.
>
> I suspect the fast gup() path could even be optimized to avoid the page_mapping()
> lookup by adding a PG_inaccessible flag that's defined iff the TBD Kconfig is
> selected. I'm guessing pKVM isn't expected to be deployed on massivve NUMA systems
> anytime soon, so there should be plenty of page flags to go around.
>
> Blocking gup() instead of trying to play refcount games when converting back to
> private would eliminate the need to put heavy restrictions on mapping, as the goal
> of those were purely to simplify the KVM implementation, e.g. the "one mapping per
> memslot" thing would go away entirely.
My implementation of mmap for inaccessible_fops was setting VM_PFNMAP.
That said, I realized that that might be adding an unnecessary
restriction, and now have changed it to do it the secretmem way.
That's straightforward and works well.
> > This of course goes back to what I'd mentioned before in v7; it seems that
> > representing the memslot memory as a file descriptor should be orthogonal to
> > whether the memory is shared or private, rather than a private_fd for private
> > memory and the userspace_addr for shared memory.
>
> I also explored the idea of backing any guest memory with an fd, but came to
> the conclusion that private memory needs a separate handle[1], at least on x86.
>
> For SNP and TDX, even though the GPA is the same (ignoring the fact that SNP and
> TDX steal GPA bits to differentiate private vs. shared), the two types need to be
> treated as separate mappings[2]. Post-boot, converting is lossy in both directions,
> so even conceptually they are two disctint pages that just happen to share (some)
> GPA bits.
>
> To allow conversions, i.e. changing which mapping to use, without memslot updates,
> KVM needs to let userspace provide both mappings in a single memslot. So while
> fd-based memory is an orthogonal concept, e.g. we could add fd-based shared memory,
> KVM would still need a dedicated private handle.
>
> For pKVM, the fd doesn't strictly need to be mutually exclusive with the existing
> userspace_addr, but since the private_fd is going to be added for x86, I think it
> makes sense to use that instead of adding generic fd-based memory for pKVM's use
> case (which is arguably still "private" memory but with special semantics).
>
> [1] https://lore.kernel.org/all/YulTH7bL4MwT5v5K@google.com
> [2] https://lore.kernel.org/all/869622df-5bf6-0fbb-cac4-34c6ae7df119@kernel.org
As long as the API does not impose this limit, which would imply pKVM
is misusing it, then I agree. I think that's why renaming it to
something like "restricted" might be clearer.
Thanks,
/fuad
next prev parent reply other threads:[~2022-10-19 15:13 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-15 14:29 [PATCH v8 0/8] KVM: mm: fd-based approach for supporting KVM Chao Peng
2022-09-15 14:29 ` [PATCH v8 1/8] mm/memfd: Introduce userspace inaccessible memfd Chao Peng
2022-09-19 9:12 ` David Hildenbrand
2022-09-19 19:10 ` Sean Christopherson
2022-09-21 21:10 ` Andy Lutomirski
2022-09-22 13:23 ` Wang, Wei W
2022-09-23 15:20 ` Fuad Tabba
2022-09-23 15:19 ` Fuad Tabba
2022-09-26 14:23 ` Chao Peng
2022-09-26 15:51 ` Fuad Tabba
2022-09-27 22:47 ` Sean Christopherson
2022-09-30 16:19 ` Fuad Tabba
2022-10-13 13:34 ` Chao Peng
2022-10-17 10:31 ` Fuad Tabba
2022-10-17 14:58 ` Chao Peng
2022-10-17 19:05 ` Fuad Tabba
2022-10-19 13:30 ` Chao Peng
2022-10-18 0:33 ` Sean Christopherson
2022-10-19 15:04 ` Fuad Tabba [this message]
2022-09-23 0:58 ` Kirill A . Shutemov
2022-09-26 10:35 ` David Hildenbrand
2022-09-26 14:48 ` Kirill A. Shutemov
2022-09-26 14:53 ` David Hildenbrand
2022-09-27 23:23 ` Sean Christopherson
2022-09-28 13:36 ` Kirill A. Shutemov
2022-09-22 13:26 ` Wang, Wei W
2022-09-22 19:49 ` Sean Christopherson
2022-09-23 0:53 ` Kirill A . Shutemov
2022-09-23 15:20 ` Fuad Tabba
2022-09-30 16:14 ` Fuad Tabba
2022-09-30 16:23 ` Kirill A . Shutemov
2022-10-03 7:33 ` Fuad Tabba
2022-10-03 11:01 ` Kirill A. Shutemov
2022-10-04 15:39 ` Fuad Tabba
2022-10-06 8:50 ` Fuad Tabba
2022-10-06 13:04 ` Kirill A. Shutemov
2022-10-17 13:00 ` Vlastimil Babka
2022-10-17 16:19 ` Kirill A . Shutemov
2022-10-17 16:39 ` Gupta, Pankaj
2022-10-17 21:56 ` Kirill A . Shutemov
2022-10-18 13:42 ` Vishal Annapurve
2022-10-19 15:32 ` Kirill A . Shutemov
2022-10-20 10:50 ` Vishal Annapurve
2022-10-21 13:54 ` Chao Peng
2022-10-21 16:53 ` Sean Christopherson
2022-10-19 12:23 ` Vishal Annapurve
2022-10-21 13:47 ` Chao Peng
2022-10-21 16:18 ` Sean Christopherson
2022-10-24 14:59 ` Kirill A . Shutemov
2022-10-24 15:26 ` David Hildenbrand
2022-11-03 16:27 ` Vishal Annapurve
2022-09-15 14:29 ` [PATCH v8 2/8] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-09-16 9:14 ` Bagas Sanjaya
2022-09-16 9:53 ` Chao Peng
2022-09-26 10:26 ` Fuad Tabba
2022-09-26 14:04 ` Chao Peng
2022-09-29 22:45 ` Isaku Yamahata
2022-09-29 23:22 ` Sean Christopherson
2022-10-05 13:04 ` Jarkko Sakkinen
2022-10-05 22:05 ` Jarkko Sakkinen
2022-10-06 9:00 ` Fuad Tabba
2022-10-06 14:58 ` Jarkko Sakkinen
2022-10-06 15:07 ` Jarkko Sakkinen
2022-10-06 15:34 ` Sean Christopherson
2022-10-07 11:14 ` Jarkko Sakkinen
2022-10-07 14:58 ` Sean Christopherson
2022-10-07 21:54 ` Jarkko Sakkinen
2022-10-08 16:15 ` Jarkko Sakkinen
2022-10-08 17:35 ` Jarkko Sakkinen
2022-10-10 8:25 ` Chao Peng
2022-10-12 8:14 ` Jarkko Sakkinen
2022-09-15 14:29 ` [PATCH v8 3/8] KVM: Add KVM_EXIT_MEMORY_FAULT exit Chao Peng
2022-09-16 9:17 ` Bagas Sanjaya
2022-09-16 9:54 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 4/8] KVM: Use gfn instead of hva for mmu_notifier_retry Chao Peng
2022-09-15 14:29 ` [PATCH v8 5/8] KVM: Register/unregister the guest private memory regions Chao Peng
2022-09-26 10:36 ` Fuad Tabba
2022-09-26 14:07 ` Chao Peng
2022-10-11 9:48 ` Fuad Tabba
2022-10-12 2:35 ` Chao Peng
2022-10-17 10:15 ` Fuad Tabba
2022-10-17 22:17 ` Sean Christopherson
2022-10-19 13:23 ` Chao Peng
2022-10-19 15:02 ` Fuad Tabba
2022-10-19 16:09 ` Sean Christopherson
2022-10-19 18:32 ` Fuad Tabba
2022-09-15 14:29 ` [PATCH v8 6/8] KVM: Update lpage info when private/shared memory are mixed Chao Peng
2022-09-29 16:52 ` Isaku Yamahata
2022-09-30 8:59 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 7/8] KVM: Handle page fault for private memory Chao Peng
2022-10-14 18:57 ` Sean Christopherson
2022-10-17 14:48 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 8/8] KVM: Enable and expose KVM_MEM_PRIVATE Chao Peng
2022-10-04 14:55 ` Jarkko Sakkinen
2022-10-10 8:31 ` Chao Peng
2022-10-06 8:55 ` Fuad Tabba
2022-10-10 8:33 ` Chao Peng
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='CA+EHjTwrTe1-ryt0sYx7360qeYmifEQqUa-_T=25eb4s6F0JPw@mail.gmail.com' \
--to=tabba@google.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=bfields@fieldses.org \
--cc=bp@alien8.de \
--cc=chao.p.peng@linux.intel.com \
--cc=corbet@lwn.net \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=ddutile@redhat.com \
--cc=dhildenb@redhat.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jlayton@kernel.org \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=jun.nakajima@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mail@maciej.szmigiero.name \
--cc=maz@kernel.org \
--cc=mhocko@suse.com \
--cc=michael.roth@amd.com \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qperret@google.com \
--cc=rppt@kernel.org \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=songmuchun@bytedance.com \
--cc=steven.price@arm.com \
--cc=tglx@linutronix.de \
--cc=vannapurve@google.com \
--cc=vbabka@suse.cz \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=wei.w.wang@intel.com \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--cc=yu.c.zhang@linux.intel.com \
/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).