2 files changed, 90 insertions, 12 deletions

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 2ad57b117385..84ec4e100fbb 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -298,7 +298,7 @@ static inline void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
 		u64 val;						\
 									\
 		ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg);	\
-		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))		\
+		if (is_nested_ctxt(vcpu))				\
 			compute_clr_set(vcpu, reg, c, s);		\
 									\
 		compute_undef_clr_set(vcpu, kvm, reg, c, s);		\
@@ -436,7 +436,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 
 	if (cpus_have_final_cap(ARM64_HAS_HCX)) {
 		u64 hcrx = vcpu->arch.hcrx_el2;
-		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
+		if (is_nested_ctxt(vcpu)) {
 			u64 val = __vcpu_sys_reg(vcpu, HCRX_EL2);
 			hcrx |= val & __HCRX_EL2_MASK;
 			hcrx &= ~(~val & __HCRX_EL2_nMASK);
@@ -476,21 +476,56 @@ static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr)
 
 	write_sysreg_hcr(hcr);
 
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
-		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) {
+		u64 vsesr;
+
+		/*
+		 * When HCR_EL2.AMO is set, physical SErrors are taken to EL2
+		 * and vSError injection is enabled for EL1. Conveniently, for
+		 * NV this means that it is never the case where a 'physical'
+		 * SError (injected by KVM or userspace) and vSError are
+		 * deliverable to the same context.
+		 *
+		 * As such, we can trivially select between the host or guest's
+		 * VSESR_EL2. Except for the case that FEAT_RAS hasn't been
+		 * exposed to the guest, where ESR propagation in hardware
+		 * occurs unconditionally.
+		 *
+		 * Paper over the architectural wart and use an IMPLEMENTATION
+		 * DEFINED ESR value in case FEAT_RAS is hidden from the guest.
+		 */
+		if (!vserror_state_is_nested(vcpu))
+			vsesr = vcpu->arch.vsesr_el2;
+		else if (kvm_has_ras(kern_hyp_va(vcpu->kvm)))
+			vsesr = __vcpu_sys_reg(vcpu, VSESR_EL2);
+		else
+			vsesr = ESR_ELx_ISV;
+
+		write_sysreg_s(vsesr, SYS_VSESR_EL2);
+	}
 }
 
 static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
 {
+	u64 *hcr;
+
+	if (vserror_state_is_nested(vcpu))
+		hcr = __ctxt_sys_reg(&vcpu->arch.ctxt, HCR_EL2);
+	else
+		hcr = &vcpu->arch.hcr_el2;
+
 	/*
 	 * If we pended a virtual abort, preserve it until it gets
 	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
 	 * the crucial bit is "On taking a vSError interrupt,
 	 * HCR_EL2.VSE is cleared to 0."
+	 *
+	 * Additionally, when in a nested context we need to propagate the
+	 * updated state to the guest hypervisor's HCR_EL2.
 	 */
-	if (vcpu->arch.hcr_el2 & HCR_VSE) {
-		vcpu->arch.hcr_el2 &= ~HCR_VSE;
-		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+	if (*hcr & HCR_VSE) {
+		*hcr &= ~HCR_VSE;
+		*hcr |= read_sysreg(hcr_el2) & HCR_VSE;
 	}
 }
 
@@ -531,7 +566,7 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 	 * nested guest, as the guest hypervisor could select a smaller VL. Slap
 	 * that into hardware before wrapping up.
 	 */
-	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
+	if (is_nested_ctxt(vcpu))
 		sve_cond_update_zcr_vq(__vcpu_sys_reg(vcpu, ZCR_EL2), SYS_ZCR_EL2);
 
 	write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR);
@@ -557,7 +592,7 @@ static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu)
 
 	if (vcpu_has_sve(vcpu)) {
 		/* A guest hypervisor may restrict the effective max VL. */
-		if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
+		if (is_nested_ctxt(vcpu))
 			zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2);
 		else
 			zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 4d0dbea4c56f..a17cbe7582de 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -109,6 +109,28 @@ static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt)
 	return kvm_has_s1poe(kern_hyp_va(vcpu->kvm));
 }
 
+static inline bool ctxt_has_ras(struct kvm_cpu_context *ctxt)
+{
+	struct kvm_vcpu *vcpu;
+
+	if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		return false;
+
+	vcpu = ctxt_to_vcpu(ctxt);
+	return kvm_has_ras(kern_hyp_va(vcpu->kvm));
+}
+
+static inline bool ctxt_has_sctlr2(struct kvm_cpu_context *ctxt)
+{
+	struct kvm_vcpu *vcpu;
+
+	if (!cpus_have_final_cap(ARM64_HAS_SCTLR2))
+		return false;
+
+	vcpu = ctxt_to_vcpu(ctxt);
+	return kvm_has_sctlr2(kern_hyp_va(vcpu->kvm));
+}
+
 static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt_sys_reg(ctxt, SCTLR_EL1)	= read_sysreg_el1(SYS_SCTLR);
@@ -147,6 +169,9 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
 	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
 	ctxt_sys_reg(ctxt, SPSR_EL1)	= read_sysreg_el1(SYS_SPSR);
+
+	if (ctxt_has_sctlr2(ctxt))
+		ctxt_sys_reg(ctxt, SCTLR2_EL1) = read_sysreg_el1(SYS_SCTLR2);
 }
 
 static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
@@ -159,8 +184,13 @@ static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt)
 	if (!has_vhe() && ctxt->__hyp_running_vcpu)
 		ctxt->regs.pstate	= read_sysreg_el2(SYS_SPSR);
 
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+	if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		return;
+
+	if (!vserror_state_is_nested(ctxt_to_vcpu(ctxt)))
 		ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2);
+	else if (ctxt_has_ras(ctxt))
+		ctxt_sys_reg(ctxt, VDISR_EL2) = read_sysreg_s(SYS_VDISR_EL2);
 }
 
 static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt)
@@ -252,6 +282,9 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt,
 	write_sysreg(ctxt_sys_reg(ctxt, SP_EL1),	sp_el1);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1),	SYS_ELR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1),	SYS_SPSR);
+
+	if (ctxt_has_sctlr2(ctxt))
+		write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR2_EL1), SYS_SCTLR2);
 }
 
 /* Read the VCPU state's PSTATE, but translate (v)EL2 to EL1. */
@@ -275,6 +308,7 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 {
 	u64 pstate = to_hw_pstate(ctxt);
 	u64 mode = pstate & PSR_AA32_MODE_MASK;
+	u64 vdisr;
 
 	/*
 	 * Safety check to ensure we're setting the CPU up to enter the guest
@@ -293,8 +327,17 @@ static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctx
 	write_sysreg_el2(ctxt->regs.pc,			SYS_ELR);
 	write_sysreg_el2(pstate,			SYS_SPSR);
 
-	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
-		write_sysreg_s(ctxt_sys_reg(ctxt, DISR_EL1), SYS_VDISR_EL2);
+	if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
+		return;
+
+	if (!vserror_state_is_nested(ctxt_to_vcpu(ctxt)))
+		vdisr = ctxt_sys_reg(ctxt, DISR_EL1);
+	else if (ctxt_has_ras(ctxt))
+		vdisr = ctxt_sys_reg(ctxt, VDISR_EL2);
+	else
+		vdisr = 0;
+
+	write_sysreg_s(vdisr, SYS_VDISR_EL2);
 }
 
 static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)