kvmclock: Ensure time in migration never goes backward

When we migrate we ask the kernel about its current belief on what the guest
time would be. However, I've seen cases where the kvmclock guest structure
indicates a time more recent than the kvm returned time.

To make sure we never go backwards, calculate what the guest would have seen as time at the point of migration and use that value instead of the kernel returned one when it's more recent.
This bases the view of the kvmclock after migration on the
same foundation in host as well as guest.

Signed-off-by: Alexander Graf <agraf@suse.de>
Cc: qemu-stable@nongnu.org
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 49 insertions, 0 deletions

diff --git a/hw/i386/kvm/clock.c b/hw/i386/kvm/clock.c
index 9d657662b2..1ac60d6cdd 100644
--- a/hw/i386/kvm/clock.c
+++ b/hw/i386/kvm/clock.c
@@ -14,6 +14,7 @@
  */
 
 #include "qemu-common.h"
+#include "qemu/host-utils.h"
 #include "sysemu/sysemu.h"
 #include "sysemu/kvm.h"
 #include "sysemu/cpus.h"
@@ -35,6 +36,48 @@ typedef struct KVMClockState {
     bool clock_valid;
 } KVMClockState;
 
+struct pvclock_vcpu_time_info {
+    uint32_t   version;
+    uint32_t   pad0;
+    uint64_t   tsc_timestamp;
+    uint64_t   system_time;
+    uint32_t   tsc_to_system_mul;
+    int8_t     tsc_shift;
+    uint8_t    flags;
+    uint8_t    pad[2];
+} __attribute__((__packed__)); /* 32 bytes */
+
+static uint64_t kvmclock_current_nsec(KVMClockState *s)
+{
+    CPUState *cpu = first_cpu;
+    CPUX86State *env = cpu->env_ptr;
+    hwaddr kvmclock_struct_pa = env->system_time_msr & ~1ULL;
+    uint64_t migration_tsc = env->tsc;
+    struct pvclock_vcpu_time_info time;
+    uint64_t delta;
+    uint64_t nsec_lo;
+    uint64_t nsec_hi;
+    uint64_t nsec;
+
+    if (!(env->system_time_msr & 1ULL)) {
+        /* KVM clock not active */
+        return 0;
+    }
+
+    cpu_physical_memory_read(kvmclock_struct_pa, &time, sizeof(time));
+
+    assert(time.tsc_timestamp <= migration_tsc);
+    delta = migration_tsc - time.tsc_timestamp;
+    if (time.tsc_shift < 0) {
+        delta >>= -time.tsc_shift;
+    } else {
+        delta <<= time.tsc_shift;
+    }
+
+    mulu64(&nsec_lo, &nsec_hi, delta, time.tsc_to_system_mul);
+    nsec = (nsec_lo >> 32) | (nsec_hi << 32);
+    return nsec + time.system_time;
+}
 
 static void kvmclock_vm_state_change(void *opaque, int running,
                                      RunState state)
@@ -46,9 +89,15 @@ static void kvmclock_vm_state_change(void *opaque, int running,
 
     if (running) {
         struct kvm_clock_data data;
+        uint64_t time_at_migration = kvmclock_current_nsec(s);
 
         s->clock_valid = false;
 
+        /* We can't rely on the migrated clock value, just discard it */
+        if (time_at_migration) {
+            s->clock = time_at_migration;
+        }
+
         data.clock = s->clock;
         data.flags = 0;
         ret = kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);