From: Sean Christopherson <seanjc@google.com>
To: Naveen N Rao <naveen@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 2/5] KVM: SVM: Always intercept RDMSR for TMCCT (current APIC timer count)
Date: Fri, 8 May 2026 09:56:19 -0700 [thread overview]
Message-ID: <af4Vs5PHGOeFm5DW@google.com> (raw)
In-Reply-To: <af4Q2wkQPtYhwC1n@blrnaveerao1>
On Fri, May 08, 2026, Naveen N Rao wrote:
> On Thu, May 07, 2026 at 11:26:15AM -0700, Sean Christopherson wrote:
> > The only reg that's at all hot is Timer Initial Count Register, and (a) it's a
> > moot point with TSC Deadline mode, and (b) the cost to program hrtimers is so high
> > than shaving ~10 cycles is completely meaningless.
>
> Thanks for the checking this - this was something I wanted to check. And
> I agree with your assessment. None of those registers look to be
> commonly written to, and ~10 cycles is almost in the noise. If we ever
> come across a performance issue, it should be fairly simple to pass
> additional registers through (with good reason, of course).
>
> On a side note, how did you measure this? My naive attempt showed a lot
> of variation between runs.
I hacked the x86/vmexit.c test in KUT, and then ran it with and without x2APIC:
./x86/run x86/vmexit.flat -smp 2 -cpu qemu64,+x2apic -append apic_wr_lvt0
./x86/run x86/vmexit.flat -smp 2 -cpu qemu64,-x2apic -append apic_wr_lvt0
That test super useful for micro-benchmarking single instructions and/or short
sequences. Even without pinning vCPUs, it does a decent job of generating stable
results.
diff --git a/x86/vmexit.c b/x86/vmexit.c
index 5296ed38..1749cbd8 100644
--- a/x86/vmexit.c
+++ b/x86/vmexit.c
@@ -22,6 +22,7 @@ struct test {
static int nr_cpus;
static u64 cr4_shadow;
+static u32 lvt0;
static void cpuid_test(void)
{
@@ -447,6 +448,11 @@ static void tscdeadline(void)
while (x == 0) barrier();
}
+static void apic_wr_lvt0(void)
+{
+ apic_write(APIC_LVT0, lvt0);
+}
+
static void wr_tsx_ctrl_msr(void)
{
wrmsr(MSR_IA32_TSX_CTRL, 0);
@@ -501,6 +507,7 @@ static struct test tests[] = {
{ mov_from_cr8, "mov_from_cr8", .parallel = 1, },
{ mov_to_cr8, "mov_to_cr8" , .parallel = 1, },
#endif
+ { apic_wr_lvt0, "apic_wr_lvt0", .parallel = 1, },
{ inl_pmtimer, "inl_from_pmtimer", .parallel = 1, },
{ inl_nop_qemu, "inl_from_qemu", .parallel = 1 },
{ inl_nop_kernel, "inl_from_kernel", .parallel = 1 },
@@ -618,6 +625,7 @@ int main(int ac, char **av)
setup_vm();
cr4_shadow = read_cr4();
+ lvt0 = apic_read(APIC_LVT0);
handle_irq(IPI_TEST_VECTOR, self_ipi_isr);
nr_cpus = cpu_count();
next prev parent reply other threads:[~2026-05-08 16:56 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-06 18:47 [PATCH v2 0/5] KVM: SVM: Fix x2AVIC MSR interception issues Sean Christopherson
2026-05-06 18:47 ` [PATCH v2 1/5] KVM: SVM: Disable x2AVIC RDMSR interception for MSRs KVM actually supports Sean Christopherson
2026-05-07 13:56 ` Naveen N Rao
2026-05-07 14:27 ` Sean Christopherson
2026-05-08 16:35 ` Naveen N Rao
2026-05-06 18:47 ` [PATCH v2 2/5] KVM: SVM: Always intercept RDMSR for TMCCT (current APIC timer count) Sean Christopherson
2026-05-07 14:19 ` Naveen N Rao
2026-05-07 15:44 ` Sean Christopherson
2026-05-07 18:26 ` Sean Christopherson
2026-05-08 16:41 ` Naveen N Rao
2026-05-08 16:56 ` Sean Christopherson [this message]
2026-05-06 18:47 ` [PATCH v2 3/5] KVM: SVM: Only disable x2AVIC WRMSR interception for MSRs that are accelerated Sean Christopherson
2026-05-08 16:59 ` Naveen N Rao
2026-05-06 18:47 ` [PATCH v2 4/5] *** DO NOT MERGE *** KVM: x86: Hack in a stat to track guest-induced exits (for testing) Sean Christopherson
2026-05-08 17:14 ` Naveen N Rao
2026-05-08 17:49 ` Sean Christopherson
2026-05-09 5:08 ` Naveen N Rao
2026-05-06 18:47 ` [PATCH v2 5/5] *** DO NOT MERGE *** KVM: selftests: Add hacky test to verify x2APIC MSR interception Sean Christopherson
2026-05-09 5:10 ` [PATCH v2 0/5] KVM: SVM: Fix x2AVIC MSR interception issues Naveen N Rao
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=af4Vs5PHGOeFm5DW@google.com \
--to=seanjc@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=naveen@kernel.org \
--cc=pbonzini@redhat.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