Various PV features (Async PF, PV EOI, steal time) work through memory
shared with hypervisor and when we restore from hibernation we must
properly teardown all these features to make sure hypervisor doesn't
write to stale locations after we jump to the previously hibernated kernel
(which can try to place anything there). For secondary CPUs the job is
already done by kvm_cpu_down_prepare(), register syscore ops to do
the same for boot CPU.
Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
arch/x86/kernel/kvm.c | 32 ++++++++++++++++++++++++++++----
1 file changed, 28 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 79dddcc178e3..6b16a9bb4ecd 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -26,6 +26,7 @@
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/swait.h>
+#include <linux/syscore_ops.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
@@ -598,17 +599,21 @@ static void kvm_guest_cpu_offline(void)
static int kvm_cpu_online(unsigned int cpu)
{
- local_irq_disable();
+ unsigned long flags;
+
+ local_irq_save(flags);
kvm_guest_cpu_init();
- local_irq_enable();
+ local_irq_restore(flags);
return 0;
}
static int kvm_cpu_down_prepare(unsigned int cpu)
{
- local_irq_disable();
+ unsigned long flags;
+
+ local_irq_save(flags);
kvm_guest_cpu_offline();
- local_irq_enable();
+ local_irq_restore(flags);
return 0;
}
#endif
@@ -639,6 +644,23 @@ static void kvm_flush_tlb_others(const struct cpumask *cpumask,
native_flush_tlb_others(flushmask, info);
}
+static int kvm_suspend(void)
+{
+ kvm_guest_cpu_offline();
+
+ return 0;
+}
+
+static void kvm_resume(void)
+{
+ kvm_cpu_online(raw_smp_processor_id());
+}
+
+static struct syscore_ops kvm_syscore_ops = {
+ .suspend = kvm_suspend,
+ .resume = kvm_resume,
+};
+
static void __init kvm_guest_init(void)
{
int i;
@@ -681,6 +703,8 @@ static void __init kvm_guest_init(void)
kvm_guest_cpu_init();
#endif
+ register_syscore_ops(&kvm_syscore_ops);
+
/*
* Hard lockup detection is enabled by default. Disable it, as guests
* can get false positives too easily, for example if the host is
--
2.30.2
