KVM: arm64: nv: Handle CNTHCTL_EL2 specially

Accessing CNTHCTL_EL2 is fraught with danger if running with
HCR_EL2.E2H=1: half of the bits are held in CNTKCTL_EL1, and
thus can be changed behind our back, while the rest lives
in the CNTHCTL_EL2 shadow copy that is memory-based.

Yes, this is a lot of fun!

Make sure that we merge the two on read access, while we can
write to CNTKCTL_EL1 in a more straightforward manner.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20241023145345.1613824-7-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

Author: Marc Zyngier

arch/arm64/kvm/sys_regs.c

@@ -157,6 +157,21 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 		if (!is_hyp_ctxt(vcpu))
 			goto memory_read;
 
+		/*
+		 * CNTHCTL_EL2 requires some special treatment to
+		 * account for the bits that can be set via CNTKCTL_EL1.
+		 */
+		switch (reg) {
+		case CNTHCTL_EL2:
+			if (vcpu_el2_e2h_is_set(vcpu)) {
+				val = read_sysreg_el1(SYS_CNTKCTL);
+				val &= CNTKCTL_VALID_BITS;
+				val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS;
+				return val;
+			}
+			break;
+		}
+
 		/*
 		 * If this register does not have an EL1 counterpart,
 		 * then read the stored EL2 version.
@@ -207,6 +222,19 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 		 */
 		__vcpu_sys_reg(vcpu, reg) = val;
 
+		switch (reg) {
+		case CNTHCTL_EL2:
+			/*
+			 * If E2H=0, CNHTCTL_EL2 is a pure shadow register.
+			 * Otherwise, some of the bits are backed by
+			 * CNTKCTL_EL1, while the rest is kept in memory.
+			 * Yes, this is fun stuff.
+			 */
+			if (vcpu_el2_e2h_is_set(vcpu))
+				write_sysreg_el1(val, SYS_CNTKCTL);
+			return;
+		}
+
 		/* No EL1 counterpart? We're done here.? */
 		if (reg == el1r)
 			return;

include/kvm/arm_arch_timer.h

@@ -147,6 +147,9 @@ u64 timer_get_cval(struct arch_timer_context *ctxt);
 void kvm_timer_cpu_up(void);
 void kvm_timer_cpu_down(void);
 
+/* CNTKCTL_EL1 valid bits as of DDI0487J.a */
+#define CNTKCTL_VALID_BITS	(BIT(17) | GENMASK_ULL(9, 0))
+
 static inline bool has_cntpoff(void)
 {
 	return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF));