kvm: kvmclock: let KVM_GET_CLOCK return whether the master clock is in use

Userspace can read the exact value of kvmclock by reading the TSC
and fetching the timekeeping parameters out of guest memory.  This
however is brittle and not necessary anymore with KVM 4.11.  Provide
a mechanism that lets userspace know if the new KVM_GET_CLOCK
semantics are in effect, and---since we are at it---if the clock
is stable across all VCPUs.

Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>

Author: bonzini

Documentation/virtual/kvm/api.txt

@@ -777,6 +777,17 @@ Gets the current timestamp of kvmclock as seen by the current guest. In
 conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
 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.
+
 struct kvm_clock_data {
 	__u64 clock;  /* kvmclock current value */
 	__u32 flags;

arch/x86/kvm/x86.c

@@ -2610,7 +2610,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_XEN_HVM:
-	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
@@ -2637,6 +2636,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 		r = 1;
 		break;
+	case KVM_CAP_ADJUST_CLOCK:
+		r = KVM_CLOCK_TSC_STABLE;
+		break;
 	case KVM_CAP_X86_SMM:
 		/* SMBASE is usually relocated above 1M on modern chipsets,
 		 * and SMM handlers might indeed rely on 4G segment limits,
@@ -4117,9 +4119,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
-		now_ns = get_kvmclock_ns(kvm);
+		local_irq_disable();
+		now_ns = __get_kvmclock_ns(kvm);
 		user_ns.clock = now_ns;
-		user_ns.flags = 0;
+		user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0;
+		local_irq_enable();
 		memset(&user_ns.pad, 0, sizeof(user_ns.pad));
 
 		r = -EFAULT;

include/uapi/linux/kvm.h

@@ -972,12 +972,19 @@ struct kvm_irqfd {
 	__u8  pad[16];
 };
 
+/* For KVM_CAP_ADJUST_CLOCK */
+
+/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags.  */
+#define KVM_CLOCK_TSC_STABLE		2
+
 struct kvm_clock_data {
 	__u64 clock;
 	__u32 flags;
 	__u32 pad[9];
 };
 
+/* For KVM_CAP_SW_TLB */
+
 #define KVM_MMU_FSL_BOOKE_NOHV		0
 #define KVM_MMU_FSL_BOOKE_HV		1