KVM: arm64: nv: Sync nested timer state with FEAT_NV2

Emulating the timers with FEAT_NV2 is a bit odd, as the timers
can be reconfigured behind our back without the hypervisor even
noticing. In the VHE case, that's an actual regression in the
architecture...

Co-developed-by: Christoffer Dall <[email protected]>
Signed-off-by: Christoffer Dall <[email protected]>
Acked-by: Oliver Upton <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Marc Zyngier <[email protected]>

Author: Marc Zyngier

arch/arm64/kvm/arch_timer.c

@@ -905,6 +905,50 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
 		kvm_timer_blocking(vcpu);
 }
 
+void kvm_timer_sync_nested(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When NV2 is on, guest hypervisors have their EL1 timer register
+	 * accesses redirected to the VNCR page. Any guest action taken on
+	 * the timer is postponed until the next exit, leading to a very
+	 * poor quality of emulation.
+	 */
+	if (!is_hyp_ctxt(vcpu))
+		return;
+
+	if (!vcpu_el2_e2h_is_set(vcpu)) {
+		/*
+		 * A non-VHE guest hypervisor doesn't have any direct access
+		 * to its timers: the EL2 registers trap (and the HW is
+		 * fully emulated), while the EL0 registers access memory
+		 * despite the access being notionally direct. Boo.
+		 *
+		 * We update the hardware timer registers with the
+		 * latest value written by the guest to the VNCR page
+		 * and let the hardware take care of the rest.
+		 */
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CTL_EL0),  SYS_CNTV_CTL);
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0), SYS_CNTV_CVAL);
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CTL_EL0),  SYS_CNTP_CTL);
+		write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0), SYS_CNTP_CVAL);
+	} else {
+		/*
+		 * For a VHE guest hypervisor, the EL2 state is directly
+		 * stored in the host EL1 timers, while the emulated EL0
+		 * state is stored in the VNCR page. The latter could have
+		 * been updated behind our back, and we must reset the
+		 * emulation of the timers.
+		 */
+		struct timer_map map;
+		get_timer_map(vcpu, &map);
+
+		soft_timer_cancel(&map.emul_vtimer->hrtimer);
+		soft_timer_cancel(&map.emul_ptimer->hrtimer);
+		timer_emulate(map.emul_vtimer);
+		timer_emulate(map.emul_ptimer);
+	}
+}
+
 /*
  * With a userspace irqchip we have to check if the guest de-asserted the
  * timer and if so, unmask the timer irq signal on the host interrupt

arch/arm64/kvm/arm.c

@@ -1228,6 +1228,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
 			kvm_timer_sync_user(vcpu);
 
+		if (vcpu_has_nv(vcpu))
+			kvm_timer_sync_nested(vcpu);
+
 		kvm_arch_vcpu_ctxsync_fp(vcpu);
 
 		/*

include/kvm/arm_arch_timer.h

@@ -98,6 +98,7 @@ int __init kvm_timer_hyp_init(bool has_gic);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_timer_sync_nested(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_user(struct kvm_vcpu *vcpu);
 bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu);
 void kvm_timer_update_run(struct kvm_vcpu *vcpu);