Kernel KVM virtualization development
 help / color / mirror / Atom feed
From: Dongli Zhang <dongli.zhang@oracle.com>
To: kvm@vger.kernel.org, x86@kernel.org, linux-kselftest@vger.kernel.org
Cc: seanjc@google.com, pbonzini@redhat.com, vkuznets@redhat.com,
	tglx@kernel.org, mingo@redhat.com, bp@alien8.de,
	dave.hansen@linux.intel.com, shuah@kernel.org, hpa@zytor.com,
	peterz@infradead.org, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	vschneid@redhat.com, kprateek.nayak@amd.com, jgross@suse.com,
	dwmw2@infradead.org, joe.jin@oracle.com
Subject: [PATCH 1/5] x86/kvm: Reset prev_steal_time and prev_steal_time_rq when enabling steal time
Date: Mon,  4 May 2026 17:30:14 -0700	[thread overview]
Message-ID: <20260505003044.78693-2-dongli.zhang@oracle.com> (raw)
In-Reply-To: <20260505003044.78693-1-dongli.zhang@oracle.com>

kvm_steal_clock() is not guaranteed to be monotonic, especially during vCPU
hotplug, and may restart from a small value due to a KVM bug.

Since per-vCPU prev_steal_time and prev_steal_time_rq are not reset on vCPU
hotplug, they can become larger than the value returned by
paravirt_steal_clock(), leading to incorrect accounting.

Reset both prev_steal_time and prev_steal_time_rq when enabling KVM steal
time paravirtualization to avoid this issue.

A fix for the underlying KVM hypervisor steal time accounting bug will be
addressed in a subsequent patch.

Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
---
 arch/x86/kernel/kvm.c         | 40 ++++++++++++++++++++---------------
 include/linux/sched/cputime.h |  2 ++
 kernel/sched/cputime.c        | 10 +++++++++
 3 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 29226d112029..819abd3a9a26 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -328,6 +328,23 @@ static void __init paravirt_ops_setup(void)
 #endif
 }
 
+static u64 kvm_steal_clock(int cpu)
+{
+	u64 steal;
+	struct kvm_steal_time *src;
+	int version;
+
+	src = &per_cpu(steal_time, cpu);
+	do {
+		version = src->version;
+		virt_rmb();
+		steal = src->steal;
+		virt_rmb();
+	} while ((version & 1) || (version != src->version));
+
+	return steal;
+}
+
 static void kvm_register_steal_time(void)
 {
 	int cpu = smp_processor_id();
@@ -337,6 +354,12 @@ static void kvm_register_steal_time(void)
 		return;
 
 	wrmsrq(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
+
+	/*
+	 * This CPU is not ready to be scheduled yet.
+	 */
+	sched_steal_time_cpu_init(cpu, kvm_steal_clock(cpu));
+
 	pr_debug("stealtime: cpu %d, msr %llx\n", cpu,
 		(unsigned long long) slow_virt_to_phys(st));
 }
@@ -411,23 +434,6 @@ static void kvm_disable_steal_time(void)
 	wrmsrq(MSR_KVM_STEAL_TIME, 0);
 }
 
-static u64 kvm_steal_clock(int cpu)
-{
-	u64 steal;
-	struct kvm_steal_time *src;
-	int version;
-
-	src = &per_cpu(steal_time, cpu);
-	do {
-		version = src->version;
-		virt_rmb();
-		steal = src->steal;
-		virt_rmb();
-	} while ((version & 1) || (version != src->version));
-
-	return steal;
-}
-
 static inline __init void __set_percpu_decrypted(void *ptr, unsigned long size)
 {
 	early_set_memory_decrypted((unsigned long) ptr, size);
diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index e90efaf6d26e..7a0313bd053a 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -186,6 +186,8 @@ struct static_key;
 extern struct static_key paravirt_steal_enabled;
 extern struct static_key paravirt_steal_rq_enabled;
 
+void sched_steal_time_cpu_init(int cpu, u64 steal);
+
 #ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN
 u64 dummy_steal_clock(int cpu);
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index fbf31db0d2f3..1490d1bcf3b4 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -255,6 +255,16 @@ void __account_forceidle_time(struct task_struct *p, u64 delta)
 #ifdef CONFIG_PARAVIRT
 struct static_key paravirt_steal_enabled;
 
+void sched_steal_time_cpu_init(int cpu, u64 steal)
+{
+	struct rq *rq = cpu_rq(cpu);
+
+	rq->prev_steal_time = steal;
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	rq->prev_steal_time_rq = steal;
+#endif
+}
+
 #ifdef CONFIG_HAVE_PV_STEAL_CLOCK_GEN
 static u64 native_steal_clock(int cpu)
 {
-- 
2.39.3


  reply	other threads:[~2026-05-05  0:32 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-05  0:30 [PATCH 0/5] Fix and enhance KVM steal accounting for both guest and host Dongli Zhang
2026-05-05  0:30 ` Dongli Zhang [this message]
2026-05-05  0:30 ` [PATCH 2/5] KVM: x86: Reset vcpu->arch.st.last_steal when enabling steal time Dongli Zhang
2026-05-08 22:40   ` Sean Christopherson
2026-05-10 17:09     ` David Woodhouse
2026-05-10 18:40       ` David Woodhouse
2026-05-05  0:30 ` [PATCH 3/5] KVM: x86: account KVM_SET_CLOCK downtime in " Dongli Zhang
2026-05-10 18:54   ` David Woodhouse
2026-05-10 19:11     ` H. Peter Anvin
2026-05-10 20:13       ` David Woodhouse
2026-05-05  0:30 ` [PATCH 4/5] KVM: selftests: Test steal time when re-adding a vCPU on a new thread Dongli Zhang
2026-05-05  0:30 ` [PATCH 5/5] KVM: selftests: Test KVM_SET_CLOCK downtime in steal time Dongli Zhang

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=20260505003044.78693-2-dongli.zhang@oracle.com \
    --to=dongli.zhang@oracle.com \
    --cc=bp@alien8.de \
    --cc=bsegall@google.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=dwmw2@infradead.org \
    --cc=hpa@zytor.com \
    --cc=jgross@suse.com \
    --cc=joe.jin@oracle.com \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=seanjc@google.com \
    --cc=shuah@kernel.org \
    --cc=tglx@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vkuznets@redhat.com \
    --cc=vschneid@redhat.com \
    --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