x86: KVM guest: Try using new kvm clock msrs

We now added a new set of clock-related msrs in replacement of the old
ones. In theory, we could just try to use them and get a return value
indicating they do not exist, due to our use of kvm_write_msr_save.

However, kvm clock registration happens very early, and if we ever
try to write to a non-existant MSR, we raise a lethal #GP, since our
idt handlers are not in place yet.

So this patch tests for a cpuid feature exported by the host to
decide which set of msrs are supported.

Signed-off-by: Glauber Costa <glommer@redhat.com>
Acked-by: Zachary Amsden <zamsden@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

1 files changed, 32 insertions, 21 deletions

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index feaeb0d3aa4f..59c740fcb9b3 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -29,6 +29,8 @@
 #define KVM_SCALE 22
 
 static int kvmclock = 1;
+static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -54,7 +56,8 @@ static unsigned long kvm_get_wallclock(void)
 
         low = (int)__pa_symbol(&wall_clock);
         high = ((u64)__pa_symbol(&wall_clock) >> 32);
-        native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
+
+        native_write_msr(msr_kvm_wall_clock, low, high);
 
         vcpu_time = &get_cpu_var(hv_clock);
         pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
@@ -130,7 +133,8 @@ static int kvm_register_clock(char *txt)
         high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
         printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
                cpu, high, low, txt);
-        return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
+
+        return native_write_msr_safe(msr_kvm_system_time, low, high);
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -165,14 +169,14 @@ static void __init kvm_smp_prepare_boot_cpu(void)
 #ifdef CONFIG_KEXEC
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
-        native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+        native_write_msr(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_write_msr(msr_kvm_system_time, 0, 0);
         native_machine_shutdown();
 }
 
@@ -181,27 +185,34 @@ void __init kvmclock_init(void)
         if (!kvm_para_available())
                 return;
 
-        if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-                if (kvm_register_clock("boot clock"))
-                        return;
-                pv_time_ops.sched_clock = kvm_clock_read;
-                x86_platform.calibrate_tsc = kvm_get_tsc_khz;
-                x86_platform.get_wallclock = kvm_get_wallclock;
-                x86_platform.set_wallclock = kvm_set_wallclock;
+        if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+                msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
+                msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
+        } else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
+                return;
+
+        printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+                msr_kvm_system_time, msr_kvm_wall_clock);
+
+        if (kvm_register_clock("boot clock"))
+                return;
+        pv_time_ops.sched_clock = kvm_clock_read;
+        x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+        x86_platform.get_wallclock = kvm_get_wallclock;
+        x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-                x86_cpuinit.setup_percpu_clockev =
-                        kvm_setup_secondary_clock;
+        x86_cpuinit.setup_percpu_clockev =
+                kvm_setup_secondary_clock;
 #endif
 #ifdef CONFIG_SMP
-                smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+        smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
-                machine_ops.shutdown  = kvm_shutdown;
+        machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
-                machine_ops.crash_shutdown  = kvm_crash_shutdown;
+        machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
-                kvm_get_preset_lpj();
-                clocksource_register(&kvm_clock);
-                pv_info.paravirt_enabled = 1;
-                pv_info.name = "KVM";
-        }
+        kvm_get_preset_lpj();
+        clocksource_register(&kvm_clock);
+        pv_info.paravirt_enabled = 1;
+        pv_info.name = "KVM";
 }