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@xxxxxxxxxx>
Signed-off-by: Oliver Upton <oupton@xxxxxxxxxx>
---
Documentation/virt/kvm/api.rst | 42 ++++++++---
arch/x86/include/asm/kvm_host.h | 3 +
arch/x86/kvm/x86.c | 127 ++++++++++++++++++--------------
include/uapi/linux/kvm.h | 7 +-
4 files changed, 112 insertions(+), 67 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index dae68e68ca23..8d4a3471ad9e 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -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];
};
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 6818095dd157..d6376ca8efce 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1926,4 +1926,7 @@ 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 */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 34287c522f4e..26f1fa263192 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2804,10 +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;
}
@@ -4047,7 +4057,7 @@ 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 |
@@ -5834,6 +5844,60 @@ int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state)
}
#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */
+static int kvm_vm_ioctl_get_clock(struct kvm *kvm, void __user *argp)
+{
+ struct kvm_clock_data data;
+
+ memset(&data, 0, sizeof(data));
+ get_kvmclock(kvm, &data);
+
+ if (copy_to_user(argp, &data, sizeof(data)))
+ return -EFAULT;
+
+ return 0;
+}
+
+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_raw_ns;
+
+ if (copy_from_user(&data, argp, sizeof(data)))
+ return -EFAULT;
+
+ if (data.flags & ~KVM_CLOCK_REALTIME)
+ return -EINVAL;
+
+ /*
+ * TODO: userspace has to take care of races with VCPU_RUN, so
+ * kvm_gen_update_masterclock() can be cut down to locked
+ * pvclock_update_vm_gtod_copy().
+ */
+ kvm_gen_update_masterclock(kvm);
+
+ spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+ 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_raw_ns = get_kvmclock_base_ns();
+ ka->kvmclock_offset = data.clock - now_raw_ns;
+ spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+
+ kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
+ return 0;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -6077,63 +6141,12 @@ long kvm_arch_vm_ioctl(struct file *filp,
break;
}
#endif
- case KVM_SET_CLOCK: {
- struct kvm_arch *ka = &kvm->arch;
- struct kvm_clock_data user_ns;
- u64 now_ns;
-
- r = -EFAULT;
- if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
- goto out;
-
- r = -EINVAL;
- if (user_ns.flags)
- goto out;
-
- r = 0;
- /*
- * TODO: userspace has to take care of races with VCPU_RUN, so
- * kvm_gen_update_masterclock() can be cut down to locked
- * pvclock_update_vm_gtod_copy().
- */
- kvm_gen_update_masterclock(kvm);
-
- /*
- * This pairs with kvm_guest_time_update(): when masterclock is
- * in use, we use master_kernel_ns + kvmclock_offset to set
- * unsigned 'system_time' so if we use get_kvmclock_ns() (which
- * is slightly ahead) here we risk going negative on unsigned
- * 'system_time' when 'user_ns.clock' is very small.
- */
- spin_lock_irq(&ka->pvclock_gtod_sync_lock);
- if (kvm->arch.use_master_clock)
- now_ns = ka->master_kernel_ns;
- else
- now_ns = get_kvmclock_base_ns();
- ka->kvmclock_offset = user_ns.clock - now_ns;
- spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
-
- kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
+ case KVM_SET_CLOCK:
+ r = kvm_vm_ioctl_set_clock(kvm, argp);
break;
- }
- case KVM_GET_CLOCK: {
- struct kvm_clock_data user_ns;
-
- /*
- * Zero flags as it is accessed RMW, leave everything else
- * uninitialized as clock is always written and no other fields
- * are consumed.
- */
- user_ns.flags = 0;
- get_kvmclock(kvm, &user_ns);
- memset(&user_ns.pad, 0, sizeof(user_ns.pad));
-
- r = -EFAULT;
- if (copy_to_user(argp, &user_ns, sizeof(user_ns)))
- goto out;
- r = 0;
+ case KVM_GET_CLOCK:
+ r = kvm_vm_ioctl_get_clock(kvm, argp);
break;
- }
case KVM_MEMORY_ENCRYPT_OP: {
r = -ENOTTY;
if (kvm_x86_ops.mem_enc_op)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index d9e4aabcb31a..53a49cb8616a 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -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 */
--
2.32.0.605.g8dce9f2422-goog
