From: Bandan Das <bsd@redhat.com>
To: "Gabriel L. Somlo" <gsomlo@gmail.com>
Cc: Eric Northup <digitaleric@google.com>,
Nadav Amit <namit@cs.technion.ac.il>,
Paolo Bonzini <pbonzini@redhat.com>,
gleb@kernel.org, Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
the arch/x86 maintainers <x86@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
KVM <kvm@vger.kernel.org>,
joro@8bytes.org, mst@redhat.com, agraf@suse.de
Subject: Re: [PATCH 3/3] KVM: x86: correct mwait and monitor emulation
Date: Wed, 18 Jun 2014 15:09:00 -0400 [thread overview]
Message-ID: <jpg38f29gs3.fsf@redhat.com> (raw)
In-Reply-To: 20140618184601.GE1695@ERROL.INI.CMU.EDU
"Gabriel L. Somlo" <gsomlo@gmail.com> writes:
> On Wed, Jun 18, 2014 at 10:59:14AM -0700, Eric Northup wrote:
>> On Wed, Jun 18, 2014 at 7:19 AM, Nadav Amit <namit@cs.technion.ac.il> wrote:
>> > mwait and monitor are currently handled as nop. Considering this behavior, they
>> > should still be handled correctly, i.e., check execution conditions and generate
>> > exceptions when required. mwait and monitor may also be executed in real-mode
>> > and are not handled in that case. This patch performs the emulation of
>> > monitor-mwait according to Intel SDM (other than checking whether interrupt can
>> > be used as a break event).
>> >
>> > Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
>
> How about this instead (details in the commit log below) ? Please let
> me know what you think, and if you'd prefer me to send it out as a
> separate patch rather than a reply to this thread.
I am not saying we should "punish" guests that don't do the right thing.
But if we can't emulate it the right way, we emulate it ?
And the fact that a workaround exists for the guest is all the more better :)
> Thanks,
> --Gabriel
>
>
> From 0375a0aceb54cdbc26a6c0e5b43c46324f830ec3 Mon Sep 17 00:00:00 2001
> From: "Gabriel L. Somlo" <somlo@cmu.edu>
> Date: Wed, 18 Jun 2014 14:39:15 -0400
> Subject: [PATCH] kvm: x86: revert "emulate monitor and mwait instructions as nop"
>
> This reverts commit 87c00572ba05aa8c9db118da75c608f47eb10b9e.
>
> OS X <= 10.7.* are the only known guests which realistically required
> this functionality. As it turns out, OS X can be told to forego using
> monitor/mwait by passing it "idlehalt=0" as a kernel argument, so we're
> better off removing this hack from KVM altogether.
>
> Signed-off-by: Gabriel L. Somlo <somlo@cmu.edu>
> ---
> arch/x86/kvm/cpuid.c | 2 --
> arch/x86/kvm/svm.c | 8 +++-----
> arch/x86/kvm/vmx.c | 10 ++++------
> 3 files changed, 7 insertions(+), 13 deletions(-)
>
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index 38a0afe..17b42fa 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -283,8 +283,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
> 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
> /* cpuid 1.ecx */
> const u32 kvm_supported_word4_x86_features =
> - /* NOTE: MONITOR (and MWAIT) are emulated as NOP,
> - * but *not* advertised to guests via CPUID ! */
> F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
> 0 /* DS-CPL, VMX, SMX, EST */ |
> 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> index ec8366c..0e8ef20 100644
> --- a/arch/x86/kvm/svm.c
> +++ b/arch/x86/kvm/svm.c
> @@ -3274,7 +3274,7 @@ static int pause_interception(struct vcpu_svm *svm)
> return 1;
> }
>
> -static int nop_interception(struct vcpu_svm *svm)
> +static int invalid_op_interception(struct vcpu_svm *svm)
> {
> skip_emulated_instruction(&(svm->vcpu));
> return 1;
> @@ -3282,14 +3282,12 @@ static int nop_interception(struct vcpu_svm *svm)
>
> static int monitor_interception(struct vcpu_svm *svm)
> {
> - printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
> - return nop_interception(svm);
> + return invalid_op_interception(svm);
> }
>
> static int mwait_interception(struct vcpu_svm *svm)
> {
> - printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
> - return nop_interception(svm);
> + return invalid_op_interception(svm);
> }
>
> static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 801332e..577c7df 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -5672,22 +5672,20 @@ static int handle_pause(struct kvm_vcpu *vcpu)
> return 1;
> }
>
> -static int handle_nop(struct kvm_vcpu *vcpu)
> +static int handle_invalid_op(struct kvm_vcpu *vcpu)
> {
> - skip_emulated_instruction(vcpu);
> + kvm_queue_exception(vcpu, UD_VECTOR);
> return 1;
> }
>
> static int handle_mwait(struct kvm_vcpu *vcpu)
> {
> - printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n");
> - return handle_nop(vcpu);
> + return handle_invalid_op(vcpu);
> }
>
> static int handle_monitor(struct kvm_vcpu *vcpu)
> {
> - printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n");
> - return handle_nop(vcpu);
> + return handle_invalid_op(vcpu);
> }
>
> /*
next prev parent reply other threads:[~2014-06-18 19:09 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-18 14:19 [PATCH 0/3] Correct monitor-mwait emulation as nop Nadav Amit
2014-06-18 14:19 ` [PATCH 1/3] KVM: x86: Emulator flag for instruction with no big real mode Nadav Amit
2014-06-18 14:19 ` [PATCH 2/3] KVM: x86: Emulator support for #UD on CPL>0 Nadav Amit
2014-06-18 16:29 ` Paolo Bonzini
2014-06-18 14:19 ` [PATCH 3/3] KVM: x86: correct mwait and monitor emulation Nadav Amit
2014-06-18 16:32 ` Paolo Bonzini
2014-06-18 16:43 ` Bandan Das
2014-06-18 16:44 ` Paolo Bonzini
2014-06-18 17:33 ` Bandan Das
2014-06-18 17:59 ` Eric Northup
2014-06-18 18:23 ` Nadav Amit
2014-06-18 18:30 ` Eric Northup
2014-06-18 18:59 ` Gabriel L. Somlo
2014-06-18 18:46 ` Gabriel L. Somlo
2014-06-18 19:09 ` Bandan Das [this message]
2014-06-19 10:18 ` Michael S. Tsirkin
[not found] ` <1B06E887-9D07-4E85-AE06-75B01787C488@gmail.com>
2014-06-19 11:23 ` Gleb Natapov
2014-06-19 11:52 ` Nadav Amit
2014-06-19 12:01 ` Michael S. Tsirkin
2014-06-19 12:07 ` Gleb Natapov
2014-06-19 12:10 ` Nadav Amit
2014-06-19 12:16 ` Gleb Natapov
2014-06-19 12:17 ` Michael S. Tsirkin
2014-06-19 12:28 ` Nadav Amit
2014-06-19 11:34 ` Paolo Bonzini
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=jpg38f29gs3.fsf@redhat.com \
--to=bsd@redhat.com \
--cc=agraf@suse.de \
--cc=digitaleric@google.com \
--cc=gleb@kernel.org \
--cc=gsomlo@gmail.com \
--cc=hpa@zytor.com \
--cc=joro@8bytes.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=mst@redhat.com \
--cc=namit@cs.technion.ac.il \
--cc=pbonzini@redhat.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