KVM: x86: Report host tsc and realtime values in KVM_GET_CLOCK

Handling the migration of TSCs correctly is difficult, in part because
Linux does not provide userspace with the ability to retrieve a (TSC,
realtime) clock pair for a single instant in time. In lieu of a more
convenient facility, KVM can report similar information in the kvm_clock
structure.

Provide userspace with a host TSC & realtime pair iff the realtime clock
is based on the TSC. If userspace provides KVM_SET_CLOCK with a valid
realtime value, advance the KVM clock by the amount of elapsed time. Do
not step the KVM clock backwards, though, as it is a monotonic
oscillator.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Oliver Upton <oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210916181538.968978-5-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -1010,20 +1010,37 @@ such as migration.
 When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
 set of bits that KVM can return in struct kvm_clock_data's flag member.
 
-The only flag defined now is KVM_CLOCK_TSC_STABLE.  If set, the returned
-value is the exact kvmclock value seen by all VCPUs at the instant
-when KVM_GET_CLOCK was called.  If clear, the returned value is simply
-CLOCK_MONOTONIC plus a constant offset; the offset can be modified
-with KVM_SET_CLOCK.  KVM will try to make all VCPUs follow this clock,
-but the exact value read by each VCPU could differ, because the host
-TSC is not stable.
+The following flags are defined:
+
+KVM_CLOCK_TSC_STABLE
+  If set, the returned value is the exact kvmclock
+  value seen by all VCPUs at the instant when KVM_GET_CLOCK was called.
+  If clear, the returned value is simply CLOCK_MONOTONIC plus a constant
+  offset; the offset can be modified with KVM_SET_CLOCK.  KVM will try
+  to make all VCPUs follow this clock, but the exact value read by each
+  VCPU could differ, because the host TSC is not stable.
+
+KVM_CLOCK_REALTIME
+  If set, the `realtime` field in the kvm_clock_data
+  structure is populated with the value of the host's real time
+  clocksource at the instant when KVM_GET_CLOCK was called. If clear,
+  the `realtime` field does not contain a value.
+
+KVM_CLOCK_HOST_TSC
+  If set, the `host_tsc` field in the kvm_clock_data
+  structure is populated with the value of the host's timestamp counter (TSC)
+  at the instant when KVM_GET_CLOCK was called. If clear, the `host_tsc` field
+  does not contain a value.
 
 ::
 
   struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;
-	__u32 pad[9];
+	__u32 pad0;
+	__u64 realtime;
+	__u64 host_tsc;
+	__u32 pad[4];
   };
 
 
@@ -1040,12 +1057,25 @@ Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
+The following flags can be passed:
+
+KVM_CLOCK_REALTIME
+  If set, KVM will compare the value of the `realtime` field
+  with the value of the host's real time clocksource at the instant when
+  KVM_SET_CLOCK was called. The difference in elapsed time is added to the final
+  kvmclock value that will be provided to guests.
+
+Other flags returned by ``KVM_GET_CLOCK`` are accepted but ignored.
+
 ::
 
   struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;
-	__u32 pad[9];
+	__u32 pad0;
+	__u64 realtime;
+	__u64 host_tsc;
+	__u32 pad[4];
   };
 
 

arch/x86/include/asm/kvm_host.h

@@ -1942,4 +1942,7 @@ int kvm_cpu_dirty_log_size(void);
 
 int alloc_all_memslots_rmaps(struct kvm *kvm);
 
+#define KVM_CLOCK_VALID_FLAGS						\
+	(KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC)
+
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/kvm/x86.c

@@ -2787,6 +2787,7 @@ static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned long flags;
 
+	data->flags = 0;
 	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	if (!ka->use_master_clock) {
 		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
@@ -2803,10 +2804,20 @@ static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 	get_cpu();
 
 	if (__this_cpu_read(cpu_tsc_khz)) {
+#ifdef CONFIG_X86_64
+		struct timespec64 ts;
+
+		if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) {
+			data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec;
+			data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC;
+		} else
+#endif
+		data->host_tsc = rdtsc();
+
 		kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
 				   &hv_clock.tsc_shift,
 				   &hv_clock.tsc_to_system_mul);
-		data->clock = __pvclock_read_cycles(&hv_clock, rdtsc());
+		data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc);
 	} else {
 		data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset;
 	}
@@ -2818,12 +2829,6 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 {
 	struct kvm_clock_data data;
 
-	/*
-	 * Zero flags as it's accessed RMW, leave everything else uninitialized
-	 * as clock is always written and no other fields are consumed.
-	 */
-	data.flags = 0;
-
 	get_kvmclock(kvm, &data);
 	return data.clock;
 }
@@ -4050,7 +4055,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_SYNC_X86_VALID_FIELDS;
 		break;
 	case KVM_CAP_ADJUST_CLOCK:
-		r = KVM_CLOCK_TSC_STABLE;
+		r = KVM_CLOCK_VALID_FLAGS;
 		break;
 	case KVM_CAP_X86_DISABLE_EXITS:
 		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE |
@@ -5847,12 +5852,16 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_arch *ka = &kvm->arch;
 	struct kvm_clock_data data;
-	u64 now_ns;
+	u64 now_raw_ns;
 
 	if (copy_from_user(&data, argp, sizeof(data)))
 		return -EFAULT;
 
-	if (data.flags)
+	/*
+	 * Only KVM_CLOCK_REALTIME is used, but allow passing the
+	 * result of KVM_GET_CLOCK back to KVM_SET_CLOCK.
+	 */
+	if (data.flags & ~KVM_CLOCK_VALID_FLAGS)
 		return -EINVAL;
 
 	kvm_hv_invalidate_tsc_page(kvm);
@@ -5866,11 +5875,21 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp)
 	 * is slightly ahead) here we risk going negative on unsigned
 	 * 'system_time' when 'data.clock' is very small.
 	 */
-	if (kvm->arch.use_master_clock)
-		now_ns = ka->master_kernel_ns;
+	if (data.flags & KVM_CLOCK_REALTIME) {
+		u64 now_real_ns = ktime_get_real_ns();
+
+		/*
+		 * Avoid stepping the kvmclock backwards.
+		 */
+		if (now_real_ns > data.realtime)
+			data.clock += now_real_ns - data.realtime;
+	}
+
+	if (ka->use_master_clock)
+		now_raw_ns = ka->master_kernel_ns;
 	else
-		now_ns = get_kvmclock_base_ns();
-	ka->kvmclock_offset = data.clock - now_ns;
+		now_raw_ns = get_kvmclock_base_ns();
+	ka->kvmclock_offset = data.clock - now_raw_ns;
 	kvm_end_pvclock_update(kvm);
 	return 0;
 }

include/uapi/linux/kvm.h

@@ -1231,11 +1231,16 @@ struct kvm_irqfd {
 
 /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
 #define KVM_CLOCK_TSC_STABLE		2
+#define KVM_CLOCK_REALTIME		(1 << 2)
+#define KVM_CLOCK_HOST_TSC		(1 << 3)
 
 struct kvm_clock_data {
 	__u64 clock;
 	__u32 flags;
-	__u32 pad[9];
+	__u32 pad0;
+	__u64 realtime;
+	__u64 host_tsc;
+	__u32 pad[4];
 };
 
 /* For KVM_CAP_SW_TLB */