x86: KVM guest: disable clock before rebooting.

This patch writes 0 (actually, what really matters is that the
LSB is cleared) to the system time msr before shutting down
the machine for kexec.

Without it, we can have a random memory location being written
when the guest comes back

It overrides the functions shutdown, used in the path of kernel_kexec() (sys.c)
and crash_shutdown, used in the path of crash_kexec() (kexec.c)

Signed-off-by: Glauber Costa <gcosta@redhat.com>
Signed-off-by: Avi Kivity <avi@qumranet.com>

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index b999f5e5b3bfd9dae4996798cebca7e1cf87cfaf..ddee04043aeb36716bc0910f5830e48d852c8b6a 100644 (file)
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -22,6 +22,7 @@
 #include <asm/msr.h>
 #include <asm/apic.h>
 #include <linux/percpu.h>
+#include <asm/reboot.h>
 
 #define KVM_SCALE 22
 
@@ -143,6 +144,28 @@ static void kvm_setup_secondary_clock(void)
        setup_secondary_APIC_clock();
 }
 
+/*
+ * After the clock is registered, the host will keep writing to the
+ * registered memory location. If the guest happens to shutdown, this memory
+ * won't be valid. In cases like kexec, in which you install a new kernel, this
+ * means a random memory location will be kept being written. So before any
+ * kind of shutdown from our side, we unregister the clock by writting anything
+ * that does not have the 'enable' bit set in the msr
+ */
+#ifdef CONFIG_KEXEC
+static void kvm_crash_shutdown(struct pt_regs *regs)
+{
+       native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+       native_machine_crash_shutdown(regs);
+}
+#endif
+
+static void kvm_shutdown(void)
+{
+       native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+       native_machine_shutdown();
+}
+
 void __init kvmclock_init(void)
 {
        if (!kvm_para_available())
@@ -155,6 +178,10 @@ void __init kvmclock_init(void)
                pv_time_ops.set_wallclock = kvm_set_wallclock;
                pv_time_ops.sched_clock = kvm_clock_read;
                pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+               machine_ops.shutdown  = kvm_shutdown;
+#ifdef CONFIG_KEXEC
+               machine_ops.crash_shutdown  = kvm_crash_shutdown;
+#endif
                clocksource_register(&kvm_clock);
        }
 }