KVM x86/xen: add an override for PVCLOCK_TSC_STABLE_BIT

Unless explicitly told to do so (by passing 'clocksource=tsc' and
'tsc=stable:socket', and then jumping through some hoops concerning
potential CPU hotplug) Xen will never use TSC as its clocksource.
Hence, by default, a Xen guest will not see PVCLOCK_TSC_STABLE_BIT set
in either the primary or secondary pvclock memory areas. This has
led to bugs in some guest kernels which only become evident if
PVCLOCK_TSC_STABLE_BIT *is* set in the pvclocks. Hence, to support
such guests, give the VMM a new Xen HVM config flag to tell KVM to
forcibly clear the bit in the Xen pvclocks.

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lore.kernel.org/r/20231102162128.2353459-1-paul@xen.org
Signed-off-by: Sean Christopherson <seanjc@google.com>

4 files changed, 38 insertions, 6 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 926241e23aeb..dca83c65d97f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8562,6 +8562,7 @@ PVHVM guests. Valid flags are::
   #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL		(1 << 4)
   #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
   #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+  #define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
 ioctl is available, for the guest to set its hypercall page.
@@ -8605,6 +8606,11 @@ behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless
 specifically enabled (by the guest making the hypercall, causing the VMM
 to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute).
 
+The KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag indicates that KVM supports
+clearing the PVCLOCK_TSC_STABLE_BIT flag in Xen pvclock sources. This will be
+done when the KVM_CAP_XEN_HVM ioctl sets the
+KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE flag.
+
 8.31 KVM_CAP_PPC_MULTITCE
 -------------------------
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6d0772b47041..aa7cea9600b0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3104,7 +3104,8 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 
 static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 				    struct gfn_to_pfn_cache *gpc,
-				    unsigned int offset)
+				    unsigned int offset,
+				    bool force_tsc_unstable)
 {
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct pvclock_vcpu_time_info *guest_hv_clock;
@@ -3141,6 +3142,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
 	}
 
 	memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
+
+	if (force_tsc_unstable)
+		guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT;
+
 	smp_wmb();
 
 	guest_hv_clock->version = ++vcpu->hv_clock.version;
@@ -3161,6 +3166,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	u64 tsc_timestamp, host_tsc;
 	u8 pvclock_flags;
 	bool use_master_clock;
+#ifdef CONFIG_KVM_XEN
+	/*
+	 * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless
+	 * explicitly told to use TSC as its clocksource Xen will not set this bit.
+	 * This default behaviour led to bugs in some guest kernels which cause
+	 * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags.
+	 */
+	bool xen_pvclock_tsc_unstable =
+		ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+#endif
 
 	kernel_ns = 0;
 	host_tsc = 0;
@@ -3239,13 +3254,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.flags = pvclock_flags;
 
 	if (vcpu->pv_time.active)
-		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false);
 #ifdef CONFIG_KVM_XEN
 	if (vcpu->xen.vcpu_info_cache.active)
 		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
-					offsetof(struct compat_vcpu_info, time));
+					offsetof(struct compat_vcpu_info, time),
+					xen_pvclock_tsc_unstable);
 	if (vcpu->xen.vcpu_time_info_cache.active)
-		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0);
+		kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0,
+					xen_pvclock_tsc_unstable);
 #endif
 	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
 	return 0;
@@ -4646,7 +4663,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		    KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
 		    KVM_XEN_HVM_CONFIG_SHARED_INFO |
 		    KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL |
-		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		    KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		    KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
 		if (sched_info_on())
 			r |= KVM_XEN_HVM_CONFIG_RUNSTATE |
 			     KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG;
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index e53fad915a62..e43948b87f94 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1162,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 {
 	/* Only some feature flags need to be *enabled* by userspace */
 	u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
-		KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
+		KVM_XEN_HVM_CONFIG_EVTCHN_SEND |
+		KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE;
+	u32 old_flags;
 
 	if (xhc->flags & ~permitted_flags)
 		return -EINVAL;
@@ -1183,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc)
 	else if (!xhc->msr && kvm->arch.xen_hvm_config.msr)
 		static_branch_slow_dec_deferred(&kvm_xen_enabled);
 
+	old_flags = kvm->arch.xen_hvm_config.flags;
 	memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
 
 	mutex_unlock(&kvm->arch.xen.xen_lock);
+
+	if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
+
 	return 0;
 }
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e9cb2df67a1d..175420b26e36 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1318,6 +1318,7 @@ struct kvm_x86_mce {
 #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL	(1 << 4)
 #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND		(1 << 5)
 #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG	(1 << 6)
+#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE	(1 << 7)
 
 struct kvm_xen_hvm_config {
 	__u32 flags;