From: Andy Lutomirski <luto@kernel.org>
To: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: "Andy Lutomirski" <luto@kernel.org>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Radim Krčmář" <rkrcmar@redhat.com>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Ingo Molnar" <mingo@redhat.com>,
"Borislav Petkov" <bp@alien8.de>, "X86 ML" <x86@kernel.org>,
"Jarkko Sakkinen" <jarkko.sakkinen@linux.intel.com>,
"Joerg Roedel" <joro@8bytes.org>,
"H. Peter Anvin" <hpa@zytor.com>,
"kvm list" <kvm@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
linux-sgx@vger.kernel.org
Subject: Re: [RFC PATCH 08/21] KVM: x86: Add kvm_x86_ops hook to short circuit emulation
Date: Mon, 19 Aug 2019 18:34:07 -0700 [thread overview]
Message-ID: <CALCETrX6bmhFm62GyCF8Z2DGtb10Ua7xi6h3PoCUiP_es74M8A@mail.gmail.com> (raw)
In-Reply-To: <20190819220150.GE1916@linux.intel.com>
On Mon, Aug 19, 2019 at 3:01 PM Sean Christopherson
<sean.j.christopherson@intel.com> wrote:
>
> On Thu, Aug 15, 2019 at 05:47:12PM -0700, Andy Lutomirski wrote:
> >
> >
> > >> On Jul 29, 2019, at 7:49 PM, Sean Christopherson <sean.j.christopherson@intel.com> wrote:
> > >>
> > >> On Sat, Jul 27, 2019 at 10:38:03AM -0700, Andy Lutomirski wrote:
> > >> On Fri, Jul 26, 2019 at 10:52 PM Sean Christopherson
> > >> <sean.j.christopherson@intel.com> wrote:
> > >>>
> > >>> Similar to the existing AMD #NPF case where emulation of the current
> > >>> instruction is not possible due to lack of information, virtualization
> > >>> of Intel SGX will introduce a scenario where emulation is not possible
> > >>> due to the VMExit occurring in an SGX enclave. And again similar to
> > >>> the AMD case, emulation can be initiated by kvm_mmu_page_fault(), i.e.
> > >>> outside of the control of the vendor-specific code.
> > >>>
> > >>> While the cause and architecturally visible behavior of the two cases
> > >>> is different, e.g. Intel SGX will inject a #UD whereas AMD #NPF is a
> > >>> clean resume or complete shutdown, the impact on the common emulation
> > >>> code is identical: KVM must stop emulation immediately and resume the
> > >>> guest.
> > >>>
> > >>> Replace the exisiting need_emulation_on_page_fault() with a more generic
> > >>> is_emulatable() kvm_x86_ops callback, which is called unconditionally
> > >>> by x86_emulate_instruction().
> > >>
> > >> Having recently noticed that emulate_ud() is broken when the guest's
> > >> TF is set, I suppose I should ask: does your new code function
> > >> sensibly when TF is set?
> > >
> > > Barring a VMX fault injection interaction I'm not thinking of, yes. The
> > > SGX reaction to the #UD VM-Exit is to inject a #UD and resume the guest,
> > > pending breakpoints shouldn't be affected in any way (unless some other
> > > part of KVM mucks with them, e.g. when guest single-stepping is enabled).
> >
> > What I mean is: does the code actually do what you think it does if TF is
> > set? Right now, as I understand it, the KVM emulation code has a bug in
> > which some emulated faults also inject #DB despite the fact that the
> > instruction faulted, and the #DB seems to take precedence over the original
> > fault. This confuses the guest.
>
> Yes. The proposed change is to inject the #UD instead of calling into the
> emulator, and by inspection I've verified that all code that injects a #DB
> is either contained within the emulator or is mutually exclusive with an
> intercepted #UD. It's a qualified yes because I don't have an actual
> testcase to verify my literacy. I'll look into adding a test, either to
> the selftest/x86/sgx or to kvm-unit-tests.
I wrote one, and it fails:
# ./tools/testing/selftests/x86/syscall_arg_fault_32
[RUN] SYSENTER with invalid state
[OK] Seems okay
[RUN] SYSCALL with invalid state
[SKIP] Illegal instruction
[RUN] SYSENTER with TF and invalid state
[OK] Seems okay
[RUN] SYSCALL with TF and invalid state
[WARN] Got stuck single-stepping -- you probably have a KVM bug
emulate_ud() is buggy.
next prev parent reply other threads:[~2019-08-20 1:34 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-27 5:51 [RFC PATCH 00/21] x86/sgx: KVM: Add SGX virtualization Sean Christopherson
2019-07-27 5:51 ` [RFC PATCH 01/21] x86/sgx: Add defines for SGX device minor numbers Sean Christopherson
2019-07-27 5:51 ` [RFC PATCH 02/21] x86/sgx: Move bus registration and device init to common code Sean Christopherson
2019-07-27 5:51 ` [RFC PATCH 03/21] x86/sgx: Move provisioning device " Sean Christopherson
2019-07-27 5:51 ` [RFC PATCH 04/21] x86/sgx: Add /dev/sgx/virt_epc device to allocate "raw" EPC for VMs Sean Christopherson
2019-07-27 17:44 ` Andy Lutomirski
2019-07-29 17:05 ` Sean Christopherson
2019-07-27 5:51 ` [RFC PATCH 05/21] x86/sgx: Expose SGX architectural definitions to the kernel Sean Christopherson
2019-07-27 5:51 ` [RFC PATCH 06/21] KVM: x86: Add SGX sub-features leaf to reverse CPUID table Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 07/21] KVM: x86: Add WARN_ON_ONCE(index!=0) in __do_cpuid_ent Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 08/21] KVM: x86: Add kvm_x86_ops hook to short circuit emulation Sean Christopherson
2019-07-27 17:38 ` Andy Lutomirski
2019-07-30 2:49 ` Sean Christopherson
2019-08-16 0:47 ` Andy Lutomirski
2019-08-19 22:01 ` Sean Christopherson
2019-08-20 1:34 ` Andy Lutomirski [this message]
2019-08-20 1:41 ` Sean Christopherson
2019-07-30 3:08 ` Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 09/21] KVM: VMX: Add basic handling of VM-Exit from SGX enclave Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 10/21] KVM: x86: Export kvm_mmu_gva_to_gpa_{read,write}() for VMX/SGX Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 11/21] KVM: x86: Export kvm_propagate_fault (as kvm_propagate_page_fault) Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 12/21] KVM: x86: Define new #PF SGX error code bit Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 13/21] x86/sgx: Move the intermediate EINIT helper into the driver Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 14/21] x86/sgx: Add helpers to expose ECREATE and EINIT to KVM Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 15/21] KVM: VMX: Add SGX ENCLS[ECREATE] handler to enforce CPUID restrictions Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 16/21] KVM: VMX: Edd emulation of SGX Launch Control LE hash MSRs Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 17/21] KVM: VMX: Add handler for ENCLS[EINIT] to support SGX Launch Control Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 18/21] KVM: x86: Invoke kvm_x86_ops->cpuid_update() after kvm_update_cpuid() Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 19/21] KVM: VMX: Enable SGX virtualization for SGX1, SGX2 and LC Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 20/21] x86/sgx: Export sgx_set_attribute() for use by KVM Sean Christopherson
2019-07-27 5:52 ` [RFC PATCH 21/21] KVM: x86: Add capability to grant VM access to privileged SGX attribute Sean Christopherson
2019-07-27 17:32 ` Andy Lutomirski
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=CALCETrX6bmhFm62GyCF8Z2DGtb10Ua7xi6h3PoCUiP_es74M8A@mail.gmail.com \
--to=luto@kernel.org \
--cc=bp@alien8.de \
--cc=hpa@zytor.com \
--cc=jarkko.sakkinen@linux.intel.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-sgx@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.com \
--cc=sean.j.christopherson@intel.com \
--cc=tglx@linutronix.de \
--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).