@@ -157,6 +157,8 @@ struct kvm_arch {
 
 	/* Memory Tagging Extension enabled for the guest */
 	bool mte_enabled;
+
+	struct kvm_spe spe;
 };
 
 struct kvm_vcpu_fault_info {

@@ -21,6 +21,10 @@ struct kvm_vcpu_spe {
 	int irq_num;		/* Buffer management interrut number */
 };
 
+struct kvm_spe {
+	bool perfmon_capable;	/* Is the VM perfmon_capable()? */
+};
+
 void kvm_spe_init_supported_cpus(void);
 void kvm_spe_vm_init(struct kvm *kvm);
 int kvm_spe_vcpu_first_run_init(struct kvm_vcpu *vcpu);

@@ -41,6 +45,9 @@ int kvm_spe_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
 struct kvm_vcpu_spe {
 };
 
+struct kvm_spe {
+};
+
 static inline void kvm_spe_init_supported_cpus(void) {}
 static inline void kvm_spe_vm_init(struct kvm *kvm) {}
 static inline int kvm_spe_vcpu_first_run_init(struct kvm_vcpu *vcpu) { return -ENOEXEC; }

@@ -83,5 +83,5 @@ void __spe_restore_guest_state_nvhe(struct kvm_vcpu *vcpu,
 	write_sysreg_s(ctxt_sys_reg(guest_ctxt, PMBSR_EL1), SYS_PMBSR_EL1);
 	write_sysreg_s(ctxt_sys_reg(guest_ctxt, PMBLIMITR_EL1), SYS_PMBLIMITR_EL1);
 	write_sysreg_s(ctxt_sys_reg(guest_ctxt, PMSCR_EL1), SYS_PMSCR_EL1);
-	write_sysreg_el2(0, SYS_PMSCR);
+	write_sysreg_el2(ctxt_sys_reg(guest_ctxt, PMSCR_EL2), SYS_PMSCR);
 }

@@ -21,7 +21,7 @@ void __spe_save_host_state_vhe(struct kvm_vcpu *vcpu,
 
 	/* Disable profiling while the SPE context is being switched. */
 	pmscr_el2 = read_sysreg_el2(SYS_PMSCR);
-	write_sysreg_el2(0, SYS_PMSCR);
+	write_sysreg_el2(__vcpu_sys_reg(vcpu, PMSCR_EL2), SYS_PMSCR);
 	isb();
 
 	pmblimitr = read_sysreg_s(SYS_PMBLIMITR_EL1);

@@ -3,6 +3,7 @@
  * Copyright (C) 2021 - ARM Ltd
  */
 
+#include <linux/capability.h>
 #include <linux/cpumask.h>
 #include <linux/kvm_host.h>
 #include <linux/perf/arm_pmu.h>

@@ -29,6 +30,16 @@ void kvm_spe_vm_init(struct kvm *kvm)
 {
 	/* Set supported_cpus if it isn't already initialized. */
 	kvm_spe_init_supported_cpus();
+
+	/*
+	 * Allow the guest to use the physical timer for timestamps only if the
+	 * VMM is perfmon_capable(), similar to what the SPE driver allows.
+	 *
+	 * CAP_PERFMON can be changed during the lifetime of the VM, so record
+	 * its value when the VM is created to avoid situations where only some
+	 * VCPUs allow physical timer timestamps, while others don't.
+	 */
+	kvm->arch.spe.perfmon_capable = perfmon_capable();
 }
 
 static int kvm_spe_check_supported_cpus(struct kvm_vcpu *vcpu)

@@ -54,6 +65,9 @@ int kvm_spe_vcpu_first_run_init(struct kvm_vcpu *vcpu)
 	if (!vcpu->arch.spe.initialized)
 		return -EPERM;
 
+	if (vcpu->kvm->arch.spe.perfmon_capable)
+		__vcpu_sys_reg(vcpu, PMSCR_EL2) = BIT(SYS_PMSCR_EL1_PCT_SHIFT);
+
 	return 0;
 }