1 files changed, 19 insertions, 15 deletions

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 9793322751e0..40d2473836c9 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode)
         cycle_t ret;
         u64 last;
         u32 version;
+        u32 migrate_count;
         u8 flags;
         unsigned cpu, cpu1;
 
 
         /*
-         * Note: hypervisor must guarantee that:
-         * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
-         * 2. that per-CPU pvclock time info is updated if the
-         *    underlying CPU changes.
-         * 3. that version is increased whenever underlying CPU
-         *    changes.
-         *
+         * When looping to get a consistent (time-info, tsc) pair, we
+         * also need to deal with the possibility we can switch vcpus,
+         * so make sure we always re-fetch time-info for the current vcpu.
          */
         do {
                 cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -102,20 +99,27 @@ static notrace cycle_t vread_pvclock(int *mode)
                  * __getcpu() calls (Gleb).
                  */
 
-                pvti = get_pvti(cpu);
+                /* Make sure migrate_count will change if we leave the VCPU. */
+                do {
+                        pvti = get_pvti(cpu);
+                        migrate_count = pvti->migrate_count;
+
+                        cpu1 = cpu;
+                        cpu = __getcpu() & VGETCPU_CPU_MASK;
+                } while (unlikely(cpu != cpu1));
 
                 version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
 
                 /*
                  * Test we're still on the cpu as well as the version.
-                 * We could have been migrated just after the first
-                 * vgetcpu but before fetching the version, so we
-                 * wouldn't notice a version change.
+                 * - We must read TSC of pvti's VCPU.
+                 * - KVM doesn't follow the versioning protocol, so data could
+                 *   change before version if we left the VCPU.
                  */
-                cpu1 = __getcpu() & VGETCPU_CPU_MASK;
-        } while (unlikely(cpu != cpu1 ||
-                          (pvti->pvti.version & 1) ||
-                          pvti->pvti.version != version));
+                smp_rmb();
+        } while (unlikely((pvti->pvti.version & 1) ||
+                          pvti->pvti.version != version ||
+                          pvti->migrate_count != migrate_count));
 
         if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
                 *mode = VCLOCK_NONE;