[PATCH v12 03/24] KVM: x86: Replace nr_vcpus_matched_tsc count with all_vcpus_matched_tsc bool

[David Woodhouse]

From: David Woodhouse <dwmw@xxxxxxxxxxxx>

Using a count and comparing with kvm->online_vcpus was always racy
because a new vCPU could be created while kvm_track_tsc_matching() was
running and comparing with kvm->online_vcpus. That variable is only
atomic with respect to itself; kvm_arch_vcpu_create() runs before
kvm->online_vcpus is incremented for the new vCPU.

Replace the count with a boolean that is set in kvm_track_tsc_matching()
after comparing the count, and cleared when a new TSC generation starts.
The boolean is consumed by pvclock_update_vm_gtod_copy() under the
tsc_write_lock, which serializes against __kvm_synchronize_tsc().

Keep the count for now as it's still used in the trace event.

Note that the explicit clear of the flag when a new generation starts
is currently overwritten by the unconditional recompute in
kvm_track_tsc_matching() under the same lock; it is preparation for
subsequent patches which consume the previous value of the flag.

Initialize the flag to true at VM creation: a VM whose vCPUs never
reach kvm_track_tsc_matching() — notably with a protected guest TSC
(TDX, SNP Secure TSC), where __kvm_synchronize_tsc() returns early —
would otherwise never be eligible for PVCLOCK_TSC_STABLE_BIT, where
the old read-time computation gave 0 + 1 == 1 for a single-vCPU VM.

Initializing the flag to true means pvclock_update_vm_gtod_copy() now
reaches its scaling path from kvm_arch_init_vm(), where the scaling
ratio is still zero from allocation; initialize it to the default
ratio at the same point, since a zero ratio would zero tsc_hz and turn
the master clock straight back off — permanently for protected-TSC
guests, whose vCPUs never write the ratio in __kvm_synchronize_tsc().

Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/x86.c              | 41 +++++++++++++++++++++++++++++----
 2 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ea48b1949316..1efca01647d2 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1242,6 +1242,7 @@ struct kvm_arch {
 	u64 cur_tsc_write;
 	u64 cur_tsc_offset;
 	u64 cur_tsc_generation;
+	bool all_vcpus_matched_tsc;
 	int nr_vcpus_matched_tsc;
 
 	u32 default_tsc_khz;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 20b84b2e4424..d29e5bc75f7a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1125,8 +1125,10 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation)
 	 * and all vCPUs must have matching TSCs.  Note, the count for matching
 	 * vCPUs doesn't include the reference vCPU, hence "+1".
 	 */
-	bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 ==
-				 atomic_read(&vcpu->kvm->online_vcpus)) &&
+	ka->all_vcpus_matched_tsc = (ka->nr_vcpus_matched_tsc + 1 ==
+				     atomic_read(&vcpu->kvm->online_vcpus));
+
+	bool use_master_clock = ka->all_vcpus_matched_tsc &&
 				gtod_is_based_on_tsc(gtod->clock.vclock_mode);
 
 	/*
@@ -1367,6 +1369,7 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
 		kvm->arch.cur_tsc_write = tsc;
 		kvm->arch.cur_tsc_offset = offset;
 		kvm->arch.nr_vcpus_matched_tsc = 0;
+		kvm->arch.all_vcpus_matched_tsc = false;
 	} else if (vcpu->arch.this_tsc_generation != kvm->arch.cur_tsc_generation) {
 		kvm->arch.nr_vcpus_matched_tsc++;
 	}
@@ -1593,8 +1596,7 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
 	bool host_tsc_clocksource, vcpus_matched;
 
 	lockdep_assert_held(&kvm->arch.tsc_write_lock);
-	vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
-			atomic_read(&kvm->online_vcpus));
+	vcpus_matched = ka->all_vcpus_matched_tsc;
 
 	/*
 	 * If the host uses TSC clock, then passthrough TSC as stable
@@ -9552,8 +9554,23 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
-	if (mutex_lock_killable(&vcpu->mutex))
+	if (mutex_lock_killable(&vcpu->mutex)) {
+		/*
+		 * The new vCPU is already counted in online_vcpus but has
+		 * not been synchronized. Nothing recomputes the cached
+		 * matched state against the raised count until the next
+		 * synchronization, so clear it here rather than leave the
+		 * clock advertised as matched while an unmatched vCPU is
+		 * runnable. It heals when this vCPU first synchronizes.
+		 */
+		struct kvm_arch *ka = &vcpu->kvm->arch;
+		unsigned long flags;
+
+		raw_spin_lock_irqsave(&ka->tsc_write_lock, flags);
+		WRITE_ONCE(ka->all_vcpus_matched_tsc, false);
+		raw_spin_unlock_irqrestore(&ka->tsc_write_lock, flags);
 		return;
+	}
 	vcpu_load(vcpu);
 	kvm_synchronize_tsc(vcpu, NULL);
 	if (kvm_check_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu))
@@ -10029,6 +10046,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	ratelimit_set_flags(&kvm->arch.kvmclock_update_rs, RATELIMIT_MSG_ON_RELEASE);
 	kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
 
+	/*
+	 * Start with all (zero) vCPUs considered matched, so that a VM whose
+	 * vCPUs never reach kvm_track_tsc_matching() — notably when the guest
+	 * TSC is protected (TDX, SNP Secure TSC) and __kvm_synchronize_tsc()
+	 * returns early — is still eligible for PVCLOCK_TSC_STABLE_BIT. The
+	 * scaling ratio must then also be initialized: with vcpus_matched
+	 * now true here, pvclock_update_vm_gtod_copy() reaches the scaling
+	 * path, and a zero ratio would zero tsc_hz and turn the master
+	 * clock straight back off (permanently so for protected-TSC guests,
+	 * which never write the ratio in __kvm_synchronize_tsc()).
+	 */
+	kvm->arch.all_vcpus_matched_tsc = true;
+	kvm->arch.cur_tsc_scaling_ratio = kvm_caps.default_tsc_scaling_ratio;
+
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	pvclock_update_vm_gtod_copy(kvm);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
-- 
2.43.0