Merge branch kvm-arm64/vgic-sre-traps into kvmarm-master/next

* kvm-arm64/vgic-sre-traps:
  : .
  : Fix the multiple of cases where KVM/arm64 doesn't correctly
  : handle the guest trying to use a GICv3 that isn't advertised.
  :
  : From the cover letter:
  :
  : "It recently appeared that, when running on a GICv3-equipped platform
  : (which is what non-ancient arm64 HW has), *not* configuring a GICv3
  : for the guest could result in less than desirable outcomes.
  :
  : We have multiple issues to fix:
  :
  : - for registers that *always* trap (the SGI registers) or that *may*
  :   trap (the SRE register), we need to check whether a GICv3 has been
  :   instantiated before acting upon the trap.
  :
  : - for registers that only conditionally trap, we must actively trap
  :   them even in the absence of a GICv3 being instantiated, and handle
  :   those traps accordingly.
  :
  : - finally, ID registers must reflect the absence of a GICv3, so that
  :   we are consistent.
  :
  : This series goes through all these requirements. The main complexity
  : here is to apply a GICv3 configuration on the host in the absence of a
  : GICv3 in the guest. This is pretty hackish, but I don't have a much
  : better solution so far.
  :
  : As part of making wider use of of the trap bits, we fully define the
  : trap routing as per the architecture, something that we eventually
  : need for NV anyway."
  : .
  KVM: arm64: selftests: Cope with lack of GICv3 in set_id_regs
  KVM: arm64: Add selftest checking how the absence of GICv3 is handled
  KVM: arm64: Unify UNDEF injection helpers
  KVM: arm64: Make most GICv3 accesses UNDEF if they trap
  KVM: arm64: Honor guest requested traps in GICv3 emulation
  KVM: arm64: Add trap routing information for ICH_HCR_EL2
  KVM: arm64: Add ICH_HCR_EL2 to the vcpu state
  KVM: arm64: Zero ID_AA64PFR0_EL1.GIC when no GICv3 is presented to the guest
  KVM: arm64: Add helper for last ditch idreg adjustments
  KVM: arm64: Force GICv3 trap activation when no irqchip is configured on VHE
  KVM: arm64: Force SRE traps when SRE access is not enabled
  KVM: arm64: Move GICv3 trap configuration to kvm_calculate_traps()

Signed-off-by: Marc Zyngier <maz@kernel.org>

Author: Marc Zyngier

arch/arm64/include/asm/kvm_host.h

@@ -534,6 +534,8 @@ enum vcpu_sysreg {
 	VNCR(CNTP_CVAL_EL0),
 	VNCR(CNTP_CTL_EL0),
 
+	VNCR(ICH_HCR_EL2),
+
 	NR_SYS_REGS	/* Nothing after this line! */
 };
 

arch/arm64/kvm/arm.c

@@ -46,6 +46,8 @@
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_psci.h>
 
+#include "sys_regs.h"
+
 static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT;
 
 enum kvm_wfx_trap_policy {
@@ -821,15 +823,13 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 			return ret;
 	}
 
-	if (vcpu_has_nv(vcpu)) {
-		ret = kvm_init_nv_sysregs(vcpu->kvm);
-		if (ret)
-			return ret;
-	}
+	ret = kvm_finalize_sys_regs(vcpu);
+	if (ret)
+		return ret;
 
 	/*
-	 * This needs to happen after NV has imposed its own restrictions on
-	 * the feature set
+	 * This needs to happen after any restriction has been applied
+	 * to the feature set.
 	 */
 	kvm_calculate_traps(vcpu);
 

arch/arm64/kvm/emulate-nested.c

@@ -86,12 +86,17 @@ enum cgt_group_id {
 	CGT_HCRX_EnFPM,
 	CGT_HCRX_TCR2En,
 
+	CGT_ICH_HCR_TC,
+	CGT_ICH_HCR_TALL0,
+	CGT_ICH_HCR_TALL1,
+	CGT_ICH_HCR_TDIR,
+
 	/*
 	 * Anything after this point is a combination of coarse trap
 	 * controls, which must all be evaluated to decide what to do.
 	 */
 	__MULTIPLE_CONTROL_BITS__,
-	CGT_HCR_IMO_FMO = __MULTIPLE_CONTROL_BITS__,
+	CGT_HCR_IMO_FMO_ICH_HCR_TC = __MULTIPLE_CONTROL_BITS__,
 	CGT_HCR_TID2_TID4,
 	CGT_HCR_TTLB_TTLBIS,
 	CGT_HCR_TTLB_TTLBOS,
@@ -106,6 +111,8 @@ enum cgt_group_id {
 	CGT_MDCR_TDE_TDRA,
 	CGT_MDCR_TDCC_TDE_TDA,
 
+	CGT_ICH_HCR_TC_TDIR,
+
 	/*
 	 * Anything after this point requires a callback evaluating a
 	 * complex trap condition. Ugly stuff.
@@ -385,6 +392,30 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= HCRX_EL2_TCR2En,
 		.behaviour	= BEHAVE_FORWARD_ANY,
 	},
+	[CGT_ICH_HCR_TC] = {
+		.index		= ICH_HCR_EL2,
+		.value		= ICH_HCR_TC,
+		.mask		= ICH_HCR_TC,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_ICH_HCR_TALL0] = {
+		.index		= ICH_HCR_EL2,
+		.value		= ICH_HCR_TALL0,
+		.mask		= ICH_HCR_TALL0,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_ICH_HCR_TALL1] = {
+		.index		= ICH_HCR_EL2,
+		.value		= ICH_HCR_TALL1,
+		.mask		= ICH_HCR_TALL1,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
+	[CGT_ICH_HCR_TDIR] = {
+		.index		= ICH_HCR_EL2,
+		.value		= ICH_HCR_TDIR,
+		.mask		= ICH_HCR_TDIR,
+		.behaviour	= BEHAVE_FORWARD_ANY,
+	},
 };
 
 #define MCB(id, ...)						\
@@ -394,7 +425,6 @@ static const struct trap_bits coarse_trap_bits[] = {
 		}
 
 static const enum cgt_group_id *coarse_control_combo[] = {
-	MCB(CGT_HCR_IMO_FMO,		CGT_HCR_IMO, CGT_HCR_FMO),
 	MCB(CGT_HCR_TID2_TID4,		CGT_HCR_TID2, CGT_HCR_TID4),
 	MCB(CGT_HCR_TTLB_TTLBIS,	CGT_HCR_TTLB, CGT_HCR_TTLBIS),
 	MCB(CGT_HCR_TTLB_TTLBOS,	CGT_HCR_TTLB, CGT_HCR_TTLBOS),
@@ -409,6 +439,9 @@ static const enum cgt_group_id *coarse_control_combo[] = {
 	MCB(CGT_MDCR_TDE_TDOSA,		CGT_MDCR_TDE, CGT_MDCR_TDOSA),
 	MCB(CGT_MDCR_TDE_TDRA,		CGT_MDCR_TDE, CGT_MDCR_TDRA),
 	MCB(CGT_MDCR_TDCC_TDE_TDA,	CGT_MDCR_TDCC, CGT_MDCR_TDE, CGT_MDCR_TDA),
+
+	MCB(CGT_HCR_IMO_FMO_ICH_HCR_TC,	CGT_HCR_IMO, CGT_HCR_FMO, CGT_ICH_HCR_TC),
+	MCB(CGT_ICH_HCR_TC_TDIR,	CGT_ICH_HCR_TC, CGT_ICH_HCR_TDIR),
 };
 
 typedef enum trap_behaviour (*complex_condition_check)(struct kvm_vcpu *);
@@ -543,9 +576,9 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_CSSELR_EL1,		CGT_HCR_TID2_TID4),
 	SR_RANGE_TRAP(SYS_ID_PFR0_EL1,
 		      sys_reg(3, 0, 0, 7, 7), CGT_HCR_TID3),
-	SR_TRAP(SYS_ICC_SGI0R_EL1,	CGT_HCR_IMO_FMO),
-	SR_TRAP(SYS_ICC_ASGI1R_EL1,	CGT_HCR_IMO_FMO),
-	SR_TRAP(SYS_ICC_SGI1R_EL1,	CGT_HCR_IMO_FMO),
+	SR_TRAP(SYS_ICC_SGI0R_EL1,	CGT_HCR_IMO_FMO_ICH_HCR_TC),
+	SR_TRAP(SYS_ICC_ASGI1R_EL1,	CGT_HCR_IMO_FMO_ICH_HCR_TC),
+	SR_TRAP(SYS_ICC_SGI1R_EL1,	CGT_HCR_IMO_FMO_ICH_HCR_TC),
 	SR_RANGE_TRAP(sys_reg(3, 0, 11, 0, 0),
 		      sys_reg(3, 0, 11, 15, 7), CGT_HCR_TIDCP),
 	SR_RANGE_TRAP(sys_reg(3, 1, 11, 0, 0),
@@ -1116,6 +1149,34 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_CNTPCT_EL0,		CGT_CNTHCTL_EL1PCTEN),
 	SR_TRAP(SYS_CNTPCTSS_EL0,	CGT_CNTHCTL_EL1PCTEN),
 	SR_TRAP(SYS_FPMR,		CGT_HCRX_EnFPM),
+	/*
+	 * IMPDEF choice:
+	 * We treat ICC_SRE_EL2.{SRE,Enable) and ICV_SRE_EL1.SRE as
+	 * RAO/WI. We therefore never consider ICC_SRE_EL2.Enable for
+	 * ICC_SRE_EL1 access, and always handle it locally.
+	 */
+	SR_TRAP(SYS_ICC_AP0R0_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_AP0R1_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_AP0R2_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_AP0R3_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_AP1R0_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_AP1R1_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_AP1R2_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_AP1R3_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_BPR0_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_BPR1_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_CTLR_EL1,	CGT_ICH_HCR_TC),
+	SR_TRAP(SYS_ICC_DIR_EL1,	CGT_ICH_HCR_TC_TDIR),
+	SR_TRAP(SYS_ICC_EOIR0_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_EOIR1_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_HPPIR0_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_HPPIR1_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_IAR0_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_IAR1_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_IGRPEN0_EL1,	CGT_ICH_HCR_TALL0),
+	SR_TRAP(SYS_ICC_IGRPEN1_EL1,	CGT_ICH_HCR_TALL1),
+	SR_TRAP(SYS_ICC_PMR_EL1,	CGT_ICH_HCR_TC),
+	SR_TRAP(SYS_ICC_RPR_EL1,	CGT_ICH_HCR_TC),
 };
 
 static DEFINE_XARRAY(sr_forward_xa);

arch/arm64/kvm/hyp/vgic-v3-sr.c

@@ -268,8 +268,16 @@ void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 	 * starting to mess with the rest of the GIC, and VMCR_EL2 in
 	 * particular.  This logic must be called before
 	 * __vgic_v3_restore_state().
+	 *
+	 * However, if the vgic is disabled (ICH_HCR_EL2.EN==0), no GIC is
+	 * provisioned at all. In order to prevent illegal accesses to the
+	 * system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1
+	 * so that the trap bits can take effect. Yes, we *loves* the GIC.
 	 */
-	if (!cpu_if->vgic_sre) {
+	if (!(cpu_if->vgic_hcr & ICH_HCR_EN)) {
+		write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1);
+		isb();
+	} else if (!cpu_if->vgic_sre) {
 		write_gicreg(0, ICC_SRE_EL1);
 		isb();
 		write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2);
@@ -288,19 +296,21 @@ void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if)
 	}
 
 	/*
-	 * Prevent the guest from touching the GIC system registers if
-	 * SRE isn't enabled for GICv3 emulation.
+	 * Prevent the guest from touching the ICC_SRE_EL1 system
+	 * register. Note that this may not have any effect, as
+	 * ICC_SRE_EL2.Enable being RAO/WI is a valid implementation.
 	 */
 	write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE,
 		     ICC_SRE_EL2);
 
 	/*
 	 * If we need to trap system registers, we must write
 	 * ICH_HCR_EL2 anyway, even if no interrupts are being
-	 * injected,
+	 * injected. Note that this also applies if we don't expect
+	 * any system register access (no vgic at all).
 	 */
 	if (static_branch_unlikely(&vgic_v3_cpuif_trap) ||
-	    cpu_if->its_vpe.its_vm)
+	    cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre)
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 }
 
@@ -326,7 +336,7 @@ void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if)
 	 * no interrupts were being injected, and we disable it again here.
 	 */
 	if (static_branch_unlikely(&vgic_v3_cpuif_trap) ||
-	    cpu_if->its_vpe.its_vm)
+	    cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre)
 		write_gicreg(0, ICH_HCR_EL2);
 }
 
@@ -1032,6 +1042,75 @@ static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
 	write_gicreg(vmcr, ICH_VMCR_EL2);
 }
 
+static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
+					    u32 sysreg, bool is_read)
+{
+	u64 ich_hcr;
+
+	if (!vcpu_has_nv(vcpu) || is_hyp_ctxt(vcpu))
+		return false;
+
+	ich_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
+
+	switch (sysreg) {
+	case SYS_ICC_IGRPEN0_EL1:
+		if (is_read &&
+		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+			return true;
+
+		if (!is_read &&
+		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+			return true;
+
+		fallthrough;
+
+	case SYS_ICC_AP0Rn_EL1(0):
+	case SYS_ICC_AP0Rn_EL1(1):
+	case SYS_ICC_AP0Rn_EL1(2):
+	case SYS_ICC_AP0Rn_EL1(3):
+	case SYS_ICC_BPR0_EL1:
+	case SYS_ICC_EOIR0_EL1:
+	case SYS_ICC_HPPIR0_EL1:
+	case SYS_ICC_IAR0_EL1:
+		return ich_hcr & ICH_HCR_TALL0;
+
+	case SYS_ICC_IGRPEN1_EL1:
+		if (is_read &&
+		    (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+			return true;
+
+		if (!is_read &&
+		    (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+			return true;
+
+		fallthrough;
+
+	case SYS_ICC_AP1Rn_EL1(0):
+	case SYS_ICC_AP1Rn_EL1(1):
+	case SYS_ICC_AP1Rn_EL1(2):
+	case SYS_ICC_AP1Rn_EL1(3):
+	case SYS_ICC_BPR1_EL1:
+	case SYS_ICC_EOIR1_EL1:
+	case SYS_ICC_HPPIR1_EL1:
+	case SYS_ICC_IAR1_EL1:
+		return ich_hcr & ICH_HCR_TALL1;
+
+	case SYS_ICC_DIR_EL1:
+		if (ich_hcr & ICH_HCR_TDIR)
+			return true;
+
+		fallthrough;
+
+	case SYS_ICC_RPR_EL1:
+	case SYS_ICC_CTLR_EL1:
+	case SYS_ICC_PMR_EL1:
+		return ich_hcr & ICH_HCR_TC;
+
+	default:
+		return false;
+	}
+}
+
 int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 {
 	int rt;
@@ -1041,6 +1120,9 @@ int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 	bool is_read;
 	u32 sysreg;
 
+	if (kern_hyp_va(vcpu->kvm)->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3)
+		return 0;
+
 	esr = kvm_vcpu_get_esr(vcpu);
 	if (vcpu_mode_is_32bit(vcpu)) {
 		if (!kvm_condition_valid(vcpu)) {
@@ -1055,6 +1137,9 @@ int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu)
 
 	is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ;
 
+	if (__vgic_v3_check_trap_forwarding(vcpu, sysreg, is_read))
+		return 0;
+
 	switch (sysreg) {
 	case SYS_ICC_IAR0_EL1:
 	case SYS_ICC_IAR1_EL1:

arch/arm64/kvm/nested.c

@@ -954,19 +954,16 @@ static void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1)
 int kvm_init_nv_sysregs(struct kvm *kvm)
 {
 	u64 res0, res1;
-	int ret = 0;
 
-	mutex_lock(&kvm->arch.config_lock);
+	lockdep_assert_held(&kvm->arch.config_lock);
 
 	if (kvm->arch.sysreg_masks)
-		goto out;
+		return 0;
 
 	kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)),
 					 GFP_KERNEL_ACCOUNT);
-	if (!kvm->arch.sysreg_masks) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!kvm->arch.sysreg_masks)
+		return -ENOMEM;
 
 	limit_nv_id_regs(kvm);
 
@@ -1195,8 +1192,6 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 	if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1))
 		res0 |= ~(res0 | res1);
 	set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1);
-out:
-	mutex_unlock(&kvm->arch.config_lock);
 
-	return ret;
+	return 0;
 }