[PATCH v5 18/34] KVM: x86: Improve synchronization in kvm_synchronize_tsc()

[David Woodhouse <dwmw2@infradead.org>]

From: David Woodhouse <dwmw@amazon.co.uk>

When synchronizing to an existing TSC (either by explicitly writing
zero, or the legacy hack where the TSC is written within one second's
worth of the previously written TSC), the last_tsc_write and
last_tsc_nsec values were being misrecorded by __kvm_synchronize_tsc().
The *unsynchronized* value of the TSC (perhaps even zero) was being
recorded, along with the current time at which kvm_synchronize_tsc()
was called. This could cause *subsequent* writes to fail to synchronize
correctly.

Fix that by resetting {data, ns} to the previous values before passing
them to __kvm_synchronize_tsc() when synchronization is detected.
Except in the case where the TSC is unstable and *has* to be synthesised
from the host clock, in which case attempt to create a nsec/tsc pair
which is on the correct line.

Furthermore, there were *three* different TSC reads used for calculating
the "current" time, all slightly different from each other. Fix that by
using kvm_get_time_and_clockread() where possible and using the same
host_tsc value in all cases.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>
---
 arch/x86/kvm/x86.c | 33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bce4c7a6a6fe..c8c0633263fb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -203,6 +203,9 @@ module_param(mitigate_smt_rsb, bool, 0444);
  * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
  * returns to userspace, i.e. the kernel can run with the guest's value.
  */
+#ifdef CONFIG_X86_64
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp);
+#endif
 #define KVM_MAX_NR_USER_RETURN_MSRS 16
 
 struct kvm_user_return_msrs {
@@ -2854,14 +2857,23 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
 {
 	u64 data = user_value ? *user_value : 0;
 	struct kvm *kvm = vcpu->kvm;
-	u64 offset, ns, elapsed;
+	u64 offset, host_tsc, elapsed;
+	s64 ns;
 	unsigned long flags;
 	bool matched = false;
 	bool synchronizing = false;
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
-	offset = kvm_compute_l1_tsc_offset(vcpu, rdtsc(), data);
-	ns = get_kvmclock_base_ns();
+
+#ifdef CONFIG_X86_64
+	if (!kvm_get_time_and_clockread(&ns, &host_tsc))
+#endif
+	{
+		host_tsc = rdtsc();
+		ns = get_kvmclock_base_ns();
+	}
+
+	offset = kvm_compute_l1_tsc_offset(vcpu, host_tsc, data);
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
@@ -2904,12 +2916,25 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
          */
 	if (synchronizing &&
 	    vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
+		/*
+		 * If synchronizing, the "last written" TSC value/time
+		 * recorded by __kvm_synchronize_tsc() should not change
+		 * (i.e. should be precisely the same as the existing
+		 * generation).
+		 */
+		data = kvm->arch.last_tsc_write;
+
 		if (!kvm_check_tsc_unstable()) {
 			offset = kvm->arch.cur_tsc_offset;
+			ns = kvm->arch.cur_tsc_nsec;
 		} else {
+			/*
+			 * ...unless the TSC is unstable and has to be
+			 * synthesised from the host clock in nanoseconds.
+			 */
 			u64 delta = nsec_to_cycles(vcpu, elapsed);
 			data += delta;
-			offset = kvm_compute_l1_tsc_offset(vcpu, rdtsc(), data);
+			offset = kvm_compute_l1_tsc_offset(vcpu, host_tsc, data);
 		}
 		matched = true;
 	}
-- 
2.54.0