x86/kvm: Disable kvmclock on all CPUs on shutdown

Currenly, we disable kvmclock from machine_shutdown() hook and this
only happens for boot CPU. We need to disable it for all CPUs to
guard against memory corruption e.g. on restore from hibernate.

Note, writing '0' to kvmclock MSR doesn't clear memory location, it
just prevents hypervisor from updating the location so for the short
while after write and while CPU is still alive, the clock remains usable
and correct so we don't need to switch to some other clocksource.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20210414123544.1060604-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 3381198..9c56e0d 100644 (file)
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -7,8 +7,6 @@
 #include <linux/interrupt.h>
 #include <uapi/asm/kvm_para.h>
 
-extern void kvmclock_init(void);
-
 #ifdef CONFIG_KVM_GUEST
 bool kvm_check_and_clear_guest_paused(void);
 #else
@@ -86,6 +84,8 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 }
 
 #ifdef CONFIG_KVM_GUEST
+void kvmclock_init(void);
+void kvmclock_disable(void);
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
 unsigned int kvm_arch_para_hints(void);

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 9d5f963..25dd126 100644 (file)
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -459,6 +459,7 @@ static void kvm_guest_cpu_offline(void)
                wrmsrl(MSR_KVM_PV_EOI_EN, 0);
        kvm_pv_disable_apf();
        apf_task_wake_all();
+       kvmclock_disable();
 }
 
 static int kvm_cpu_online(unsigned int cpu)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d37ed4e..081686d 100644 (file)
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -220,11 +220,9 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
-static void kvm_shutdown(void)
+void kvmclock_disable(void)
 {
        native_write_msr(msr_kvm_system_time, 0, 0);
-       kvm_disable_steal_time();
-       native_machine_shutdown();
 }
 
 static void __init kvmclock_init_mem(void)
@@ -351,7 +349,6 @@ void __init kvmclock_init(void)
 #endif
        x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
        x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
-       machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC_CORE
        machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif