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 <[email protected]>
---
 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 via email to