@@ -993,20 +993,34 @@ 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.
+FLAGS:
+
+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];
};
@@ -1023,12 +1037,22 @@ 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.
+FLAGS:
+
+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.
+
::
struct kvm_clock_data {
__u64 clock; /* kvmclock current value */
__u32 flags;
- __u32 pad[9];
+ __u32 pad0;
+ __u64 realtime;
+ __u64 host_tsc;
+ __u32 pad[4];
};
@@ -1916,4 +1916,7 @@ 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 */
@@ -2809,10 +2809,20 @@ 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;
}
@@ -4052,7 +4062,7 @@ 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 |
@@ -5837,14 +5847,8 @@ static int kvm_vm_ioctl_get_clock(struct kvm *kvm, void __user *argp)
{
struct kvm_clock_data data;
- /*
- * Zero flags as it is accessed RMW, leave everything else
- * uninitialized as clock is always written and no other fields
- * are consumed.
- */
- data.flags = 0;
+ memset(&data, 0, sizeof(data));
get_kvmclock(kvm, &data);
- memset(&data.pad, 0, sizeof(data.pad));
if (copy_to_user(argp, &data, sizeof(data)))
return -EFAULT;
@@ -5861,13 +5865,23 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp)
if (copy_from_user(&data, argp, sizeof(data)))
return -EFAULT;
- if (data.flags)
+ if (data.flags & ~KVM_CLOCK_REALTIME)
return -EINVAL;
kvm_hv_invalidate_tsc_page(kvm);
kvm_start_pvclock_update(kvm);
pvclock_update_vm_gtod_copy(kvm);
+ 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;
+ }
+
/*
* This pairs with kvm_guest_time_update(): when masterclock is
* in use, we use master_kernel_ns + kvmclock_offset to set
@@ -1223,11 +1223,16 @@ 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 */
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> --- Documentation/virt/kvm/api.rst | 42 ++++++++++++++++++++++++++------- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/x86.c | 34 ++++++++++++++++++-------- include/uapi/linux/kvm.h | 7 +++++- 4 files changed, 66 insertions(+), 20 deletions(-)