diff mbox series

[v2,09/15] KVM: x86: Fix software TSC upscaling in kvm_update_guest_time()

Message ID 20240427111929.9600-10-dwmw2@infradead.org (mailing list archive)
State New
Headers show
Series [v2,01/15] KVM: x86/xen: Do not corrupt KVM clock in kvm_xen_shared_info_init() | expand

Commit Message

David Woodhouse April 27, 2024, 11:05 a.m. UTC
From: David Woodhouse <dwmw@amazon.co.uk>

There was some confusion in kvm_update_guest_time() when software needs
to advance the guest TSC.

In master clock mode, there are two points of time which need to be taken
into account. First there is the master clock reference point, stored in
kvm->arch.master_kernel_ns (and associated host TSC ->master_cycle_now).
Secondly, there is the time *now*, at the point kvm_update_guest_time()
is being called.

With software TSC upscaling, the guest TSC is getting further and further
ahead of the host TSC as time elapses. So at time "now", the guest TSC
should be further ahead of the host, than it was at master_kernel_ns.

The adjustment in kvm_update_guest_time() was not taking that into
account, and was only advancing the guest TSC by the appropriate amount
for master_kernel_ns, *not* the current time.

Fix it to calculate them both correctly.

Since the KVM clock reference point in master_kernel_ns might actually
be *earlier* than the reference point used for the guest TSC
(vcpu->last_tsc_nsec), this might lead to a negative delta. Fix the
compute_guest_tsc() function to cope with negative numbers, which
then means there is no need to force a master clock update when the
guest TSC is written.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 arch/x86/kvm/x86.c | 73 +++++++++++++++++++++++++++++++++++-----------
 1 file changed, 56 insertions(+), 17 deletions(-)
diff mbox series

Patch

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 89918ba266cd..e09dc44978ea 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2491,10 +2491,19 @@  static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
 
 static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
 {
-	u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec,
-				      vcpu->arch.virtual_tsc_mult,
-				      vcpu->arch.virtual_tsc_shift);
-	tsc += vcpu->arch.this_tsc_write;
+	s64 delta = kernel_ns - vcpu->arch.this_tsc_nsec;
+	u64 tsc = vcpu->arch.this_tsc_write;
+
+	/* pvclock_scale_delta cannot cope with negative deltas */
+	if (delta >= 0)
+		tsc += pvclock_scale_delta(delta,
+					   vcpu->arch.virtual_tsc_mult,
+					   vcpu->arch.virtual_tsc_shift);
+	else
+		tsc -= pvclock_scale_delta(-delta,
+					   vcpu->arch.virtual_tsc_mult,
+					   vcpu->arch.virtual_tsc_shift);
+
 	return tsc;
 }
 
@@ -2505,7 +2514,7 @@  static inline bool gtod_is_based_on_tsc(int mode)
 }
 #endif
 
-static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation)
+static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64
 	struct kvm_arch *ka = &vcpu->kvm->arch;
@@ -2522,12 +2531,9 @@  static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation)
 
 	/*
 	 * Request a masterclock update if the masterclock needs to be toggled
-	 * on/off, or when starting a new generation and the masterclock is
-	 * enabled (compute_guest_tsc() requires the masterclock snapshot to be
-	 * taken _after_ the new generation is created).
+	 * on/off.
 	 */
-	if ((ka->use_master_clock && new_generation) ||
-	    (ka->use_master_clock != use_master_clock))
+	if ((ka->use_master_clock != use_master_clock))
 		kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 	trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -2705,7 +2711,7 @@  static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
 	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
 	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
 
-	kvm_track_tsc_matching(vcpu, !matched);
+	kvm_track_tsc_matching(vcpu);
 }
 
 static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value)
@@ -3300,8 +3306,6 @@  static int kvm_guest_time_update(struct kvm_vcpu *v)
 		kernel_ns = get_kvmclock_base_ns();
 	}
 
-	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
-
 	/*
 	 * We may have to catch up the TSC to match elapsed wall clock
 	 * time for two reasons, even if kvmclock is used.
@@ -3313,11 +3317,46 @@  static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 *	very slowly.
 	 */
 	if (vcpu->tsc_catchup) {
-		u64 tsc = compute_guest_tsc(v, kernel_ns);
-		if (tsc > tsc_timestamp) {
-			adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
-			tsc_timestamp = tsc;
+		uint64_t now_host_tsc, now_guest_tsc;
+		int64_t adjustment;
+
+		/*
+		 * First, calculate what the guest TSC should be at the
+		 * time (kernel_ns) which will be placed in the hvclock.
+		 * This may be the *current* time, or it may be the time
+		 * of the master clock reference. This is 'tsc_timestamp'.
+		 */
+		tsc_timestamp = compute_guest_tsc(v, kernel_ns);
+
+		now_guest_tsc = tsc_timestamp;
+		now_host_tsc = host_tsc;
+
+#ifdef CONFIG_X86_64
+		/*
+		 * If the master clock was used, calculate what the guest
+		 * TSC should be *now* in order to advance to that.
+		 */
+		if (use_master_clock) {
+			int64_t now_kernel_ns;
+
+			if (!kvm_get_time_and_clockread(&now_kernel_ns,
+							&now_host_tsc)) {
+				now_kernel_ns = get_kvmclock_base_ns();
+				now_host_tsc = rdtsc();
+			}
+			now_guest_tsc = compute_guest_tsc(v, now_kernel_ns);
 		}
+#endif
+		/*
+		 * Calculate the delta between what the guest TSC *should* be,
+		 * and what it actually is according to kvm_read_l1_tsc().
+		 */
+		adjustment = now_guest_tsc - kvm_read_l1_tsc(v, now_host_tsc);
+
+		if (adjustment > 0)
+			adjust_tsc_offset_guest(v, adjustment);
+	} else {
+		tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
 	}
 
 	local_irq_restore(flags);