From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
To: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>,
Jon Kohler <jon@nutanix.com>,
Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
X86 ML <x86@kernel.org>, "H. Peter Anvin" <hpa@zytor.com>,
"Peter Zijlstra (Intel)" <peterz@infradead.org>,
Daniel Sneddon <daniel.sneddon@linux.intel.com>,
"kvm @ vger . kernel . org" <kvm@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] KVM: VMX: remove LFENCE in vmx_spec_ctrl_restore_host()
Date: Wed, 31 May 2023 18:24:29 -0700 [thread overview]
Message-ID: <20230601012323.36te7hfv366danpf@desk> (raw)
In-Reply-To: <846dd0c5-d431-e20e-fdb3-a4a26b6a22ca@citrix.com>
On Thu, Jun 01, 2023 at 01:50:48AM +0100, Andrew Cooper wrote:
> On 01/06/2023 1:42 am, Josh Poimboeuf wrote:
> > So each LFENCE has a distinct purpose. That said, there are no indirect
> > branches or unbalanced RETs between them.
>
> How lucky are you feeling?
>
> You're in C at this point, which means the compiler could have emitted a
> call to mem{cpy,cmp}() in place of a simple assignment/comparison.
Moving the second LFENCE to the else part of WRMSR should be possible?
So that the serialization can be achived either by WRMSR or LFENCE. This
saves an LFENCE when host and guest value of MSR_SPEC_CTRL differ.
---
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d2d6e1b6c788..d32e6d172dd6 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7157,8 +7157,8 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) ||
vmx->spec_ctrl != hostval)
native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval);
-
- barrier_nospec();
+ else
+ barrier_nospec();
}
static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
next prev parent reply other threads:[~2023-06-01 1:24 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-31 15:01 [PATCH] KVM: VMX: remove LFENCE in vmx_spec_ctrl_restore_host() Jon Kohler
2023-05-31 23:18 ` Josh Poimboeuf
2023-05-31 23:58 ` Jon Kohler
2023-06-01 0:42 ` Josh Poimboeuf
2023-06-01 0:50 ` Andrew Cooper
2023-06-01 0:56 ` Josh Poimboeuf
2023-06-01 1:24 ` Pawan Gupta [this message]
2023-06-01 4:23 ` Josh Poimboeuf
2023-06-05 14:29 ` Jon Kohler
2023-06-05 16:35 ` Josh Poimboeuf
2023-06-05 16:39 ` Jon Kohler
2023-06-05 17:31 ` Pawan Gupta
2023-06-05 18:31 ` Sean Christopherson
2023-06-05 19:57 ` Jon Kohler
2023-06-05 20:01 ` Josh Poimboeuf
2023-06-06 0:20 ` Andrew Cooper
2023-06-06 3:59 ` Josh Poimboeuf
2023-06-01 0:29 ` Andrew Cooper
2023-06-01 0:53 ` Josh Poimboeuf
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=20230601012323.36te7hfv366danpf@desk \
--to=pawan.kumar.gupta@linux.intel.com \
--cc=andrew.cooper3@citrix.com \
--cc=bp@alien8.de \
--cc=daniel.sneddon@linux.intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=jon@nutanix.com \
--cc=jpoimboe@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=seanjc@google.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