Merge branch kvm-arm64/nv-s1pie-s1poe into kvmarm/next

* kvm-arm64/nv-s1pie-s1poe: (36 commits) : NV support for S1PIE/S1POE, courtesy of Marc Zyngier : : Complete support for S1PIE/S1POE at vEL2, including: : : - Save/restore of the vEL2 sysreg context : : - Use the S1PIE/S1POE context for fast-path AT emulation : : - Enlightening the software walker to the behavior of S1PIE/S1POE : : - Like any other good NV series, some trap routing descriptions KVM: arm64: Handle WXN attribute KVM: arm64: Handle stage-1 permission overlays KVM: arm64: Make PAN conditions part of the S1 walk context KVM: arm64: Disable hierarchical permissions when POE is enabled KVM: arm64: Add POE save/restore for AT emulation fast-path KVM: arm64: Add save/restore support for POR_EL2 KVM: arm64: Add basic support for POR_EL2 KVM: arm64: Add kvm_has_s1poe() helper KVM: arm64: Subject S1PIE/S1POE registers to HCR_EL2.{TVM,TRVM} KVM: arm64: Drop bogus CPTR_EL2.E0POE trap routing arm64: Add encoding for POR_EL2 KVM: arm64: Rely on visibility to let PIR*_ELx/TCR2_ELx UNDEF KVM: arm64: Hide S1PIE registers from userspace when disabled for guests KVM: arm64: Hide TCR2_EL1 from userspace when disabled for guests KVM: arm64: Define helper for EL2 registers with custom visibility KVM: arm64: Add a composite EL2 visibility helper KVM: arm64: Implement AT S1PIE support KVM: arm64: Disable hierarchical permissions when S1PIE is enabled KVM: arm64: Split S1 permission evaluation into direct and hierarchical parts KVM: arm64: Add AT fast-path support for S1PIE ... Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
2026-05-03 10:02:20 -04:00 · 2024-11-11 18:36:12 +00:00
parent 8198375843 1c6801d565
commit 2865463442
11 changed files with 778 additions and 125 deletions
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -374,7 +374,7 @@ struct kvm_arch {

 	u64 ctr_el0;

-	/* Masks for VNCR-baked sysregs */
+	/* Masks for VNCR-backed and general EL2 sysregs */
 	struct kvm_sysreg_masks	*sysreg_masks;

 	/*
@@ -408,6 +408,9 @@ struct kvm_vcpu_fault_info {
 	r = __VNCR_START__ + ((VNCR_ ## r) / 8),	\
 	__after_##r = __MAX__(__before_##r - 1, r)

+#define MARKER(m)				\
+	m, __after_##m = m - 1
+
 enum vcpu_sysreg {
 	__INVALID_SYSREG__,   /* 0 is reserved as an invalid value */
 	MPIDR_EL1,	/* MultiProcessor Affinity Register */
@@ -475,6 +478,9 @@ enum vcpu_sysreg {
 	TTBR0_EL2,	/* Translation Table Base Register 0 (EL2) */
 	TTBR1_EL2,	/* Translation Table Base Register 1 (EL2) */
 	TCR_EL2,	/* Translation Control Register (EL2) */
+	PIRE0_EL2,	/* Permission Indirection Register 0 (EL2) */
+	PIR_EL2,	/* Permission Indirection Register 1 (EL2) */
+	POR_EL2,	/* Permission Overlay Register 2 (EL2) */
 	SPSR_EL2,	/* EL2 saved program status register */
 	ELR_EL2,	/* EL2 exception link register */
 	AFSR0_EL2,	/* Auxiliary Fault Status Register 0 (EL2) */
@@ -494,7 +500,12 @@ enum vcpu_sysreg {
 	CNTHV_CTL_EL2,
 	CNTHV_CVAL_EL2,

-	__VNCR_START__,	/* Any VNCR-capable reg goes after this point */
+	/* Anything from this can be RES0/RES1 sanitised */
+	MARKER(__SANITISED_REG_START__),
+	TCR2_EL2,	/* Extended Translation Control Register (EL2) */
+
+	/* Any VNCR-capable reg goes after this point */
+	MARKER(__VNCR_START__),

 	VNCR(SCTLR_EL1),/* System Control Register */
 	VNCR(ACTLR_EL1),/* Auxiliary Control Register */
@@ -554,7 +565,7 @@ struct kvm_sysreg_masks {
 	struct {
 		u64	res0;
 		u64	res1;
-	} mask[NR_SYS_REGS - __VNCR_START__];
+	} mask[NR_SYS_REGS - __SANITISED_REG_START__];
 };

 struct kvm_cpu_context {
@@ -1002,13 +1013,13 @@ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)

 #define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))

-u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
+u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 #define __vcpu_sys_reg(v,r)						\
 	(*({								\
 		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
 		u64 *__r = __ctxt_sys_reg(ctxt, (r));			\
-		if (vcpu_has_nv((v)) && (r) >= __VNCR_START__)		\
-			*__r = kvm_vcpu_sanitise_vncr_reg((v), (r));	\
+		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
+			*__r = kvm_vcpu_apply_reg_masks((v), (r), *__r);\
 		__r;							\
 	}))

@@ -1037,6 +1048,10 @@ static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
 	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
 	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
+	case TCR2_EL1:		*val = read_sysreg_s(SYS_TCR2_EL12);	break;
+	case PIR_EL1:		*val = read_sysreg_s(SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		*val = read_sysreg_s(SYS_PIRE0_EL12);	break;
+	case POR_EL1:		*val = read_sysreg_s(SYS_POR_EL12);	break;
 	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
 	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
 	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
@@ -1083,6 +1098,10 @@ static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
 	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
 	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
 	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
+	case TCR2_EL1:		write_sysreg_s(val, SYS_TCR2_EL12);	break;
+	case PIR_EL1:		write_sysreg_s(val, SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		write_sysreg_s(val, SYS_PIRE0_EL12);	break;
+	case POR_EL1:		write_sysreg_s(val, SYS_POR_EL12);	break;
 	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
 	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
 	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
@@ -1503,4 +1522,13 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
 	(system_supports_fpmr() &&			\
 	 kvm_has_feat((k), ID_AA64PFR2_EL1, FPMR, IMP))

+#define kvm_has_tcr2(k)				\
+	(kvm_has_feat((k), ID_AA64MMFR3_EL1, TCRX, IMP))
+
+#define kvm_has_s1pie(k)				\
+	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP))
+
+#define kvm_has_s1poe(k)				\
+	(kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP))
+
 #endif /* __ARM64_KVM_HOST_H__ */
--- a/arch/arm64/include/asm/vncr_mapping.h
+++ b/arch/arm64/include/asm/vncr_mapping.h
@@ -50,7 +50,6 @@
 #define VNCR_VBAR_EL1           0x250
 #define VNCR_TCR2_EL1		0x270
 #define VNCR_PIRE0_EL1		0x290
-#define VNCR_PIRE0_EL2		0x298
 #define VNCR_PIR_EL1		0x2A0
 #define VNCR_POR_EL1		0x2A8
 #define VNCR_ICH_LR0_EL2        0x400
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -24,6 +24,9 @@ struct s1_walk_info {
 	unsigned int		txsz;
 	int 	     		sl;
 	bool	     		hpd;
+	bool			e0poe;
+	bool			poe;
+	bool			pan;
 	bool	     		be;
 	bool	     		s2;
 };
@@ -37,6 +40,16 @@ struct s1_walk_result {
 			u8	APTable;
 			bool	UXNTable;
 			bool	PXNTable;
+			bool	uwxn;
+			bool	uov;
+			bool	ur;
+			bool	uw;
+			bool	ux;
+			bool	pwxn;
+			bool	pov;
+			bool	pr;
+			bool	pw;
+			bool	px;
 		};
 		struct {
 			u8	fst;
@@ -87,6 +100,51 @@ static enum trans_regime compute_translation_regime(struct kvm_vcpu *vcpu, u32 o
 	}
 }

+static bool s1pie_enabled(struct kvm_vcpu *vcpu, enum trans_regime regime)
+{
+	if (!kvm_has_s1pie(vcpu->kvm))
+		return false;
+
+	switch (regime) {
+	case TR_EL2:
+	case TR_EL20:
+		return vcpu_read_sys_reg(vcpu, TCR2_EL2) & TCR2_EL2_PIE;
+	case TR_EL10:
+		return  (__vcpu_sys_reg(vcpu, HCRX_EL2) & HCRX_EL2_TCR2En) &&
+			(__vcpu_sys_reg(vcpu, TCR2_EL1) & TCR2_EL1x_PIE);
+	default:
+		BUG();
+	}
+}
+
+static void compute_s1poe(struct kvm_vcpu *vcpu, struct s1_walk_info *wi)
+{
+	u64 val;
+
+	if (!kvm_has_s1poe(vcpu->kvm)) {
+		wi->poe = wi->e0poe = false;
+		return;
+	}
+
+	switch (wi->regime) {
+	case TR_EL2:
+	case TR_EL20:
+		val = vcpu_read_sys_reg(vcpu, TCR2_EL2);
+		wi->poe = val & TCR2_EL2_POE;
+		wi->e0poe = (wi->regime == TR_EL20) && (val & TCR2_EL2_E0POE);
+		break;
+	case TR_EL10:
+		if (__vcpu_sys_reg(vcpu, HCRX_EL2) & HCRX_EL2_TCR2En) {
+			wi->poe = wi->e0poe = false;
+			return;
+		}
+
+		val = __vcpu_sys_reg(vcpu, TCR2_EL1);
+		wi->poe = val & TCR2_EL1x_POE;
+		wi->e0poe = val & TCR2_EL1x_E0POE;
+	}
+}
+
 static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi,
 			 struct s1_walk_result *wr, u64 va)
 {
@@ -98,6 +156,8 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi,

 	wi->regime = compute_translation_regime(vcpu, op);
 	as_el0 = (op == OP_AT_S1E0R || op == OP_AT_S1E0W);
+	wi->pan = (op == OP_AT_S1E1RP || op == OP_AT_S1E1WP) &&
+		  (*vcpu_cpsr(vcpu) & PSR_PAN_BIT);

 	va55 = va & BIT(55);

@@ -180,6 +240,14 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi,
 		    (va55 ?
 		     FIELD_GET(TCR_HPD1, tcr) :
 		     FIELD_GET(TCR_HPD0, tcr)));
+	/* R_JHSVW */
+	wi->hpd |= s1pie_enabled(vcpu, wi->regime);
+
+	/* Do we have POE? */
+	compute_s1poe(vcpu, wi);
+
+	/* R_BVXDG */
+	wi->hpd |= (wi->poe || wi->e0poe);

 	/* Someone was silly enough to encode TG0/TG1 differently */
 	if (va55) {
@@ -412,6 +480,11 @@ struct mmu_config {
 	u64	ttbr1;
 	u64	tcr;
 	u64	mair;
+	u64	tcr2;
+	u64	pir;
+	u64	pire0;
+	u64	por_el0;
+	u64	por_el1;
 	u64	sctlr;
 	u64	vttbr;
 	u64	vtcr;
@@ -424,6 +497,17 @@ static void __mmu_config_save(struct mmu_config *config)
 	config->ttbr1	= read_sysreg_el1(SYS_TTBR1);
 	config->tcr	= read_sysreg_el1(SYS_TCR);
 	config->mair	= read_sysreg_el1(SYS_MAIR);
+	if (cpus_have_final_cap(ARM64_HAS_TCR2)) {
+		config->tcr2	= read_sysreg_el1(SYS_TCR2);
+		if (cpus_have_final_cap(ARM64_HAS_S1PIE)) {
+			config->pir	= read_sysreg_el1(SYS_PIR);
+			config->pire0	= read_sysreg_el1(SYS_PIRE0);
+		}
+		if (system_supports_poe()) {
+			config->por_el1	= read_sysreg_el1(SYS_POR);
+			config->por_el0	= read_sysreg_s(SYS_POR_EL0);
+		}
+	}
 	config->sctlr	= read_sysreg_el1(SYS_SCTLR);
 	config->vttbr	= read_sysreg(vttbr_el2);
 	config->vtcr	= read_sysreg(vtcr_el2);
@@ -444,6 +528,17 @@ static void __mmu_config_restore(struct mmu_config *config)
 	write_sysreg_el1(config->ttbr1,	SYS_TTBR1);
 	write_sysreg_el1(config->tcr,	SYS_TCR);
 	write_sysreg_el1(config->mair,	SYS_MAIR);
+	if (cpus_have_final_cap(ARM64_HAS_TCR2)) {
+		write_sysreg_el1(config->tcr2, SYS_TCR2);
+		if (cpus_have_final_cap(ARM64_HAS_S1PIE)) {
+			write_sysreg_el1(config->pir, SYS_PIR);
+			write_sysreg_el1(config->pire0, SYS_PIRE0);
+		}
+		if (system_supports_poe()) {
+			write_sysreg_el1(config->por_el1, SYS_POR);
+			write_sysreg_s(config->por_el0, SYS_POR_EL0);
+		}
+	}
 	write_sysreg_el1(config->sctlr,	SYS_SCTLR);
 	write_sysreg(config->vttbr,	vttbr_el2);
 	write_sysreg(config->vtcr,	vtcr_el2);
@@ -739,6 +834,9 @@ static bool pan3_enabled(struct kvm_vcpu *vcpu, enum trans_regime regime)
 	if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR1_EL1, PAN, PAN3))
 		return false;

+	if (s1pie_enabled(vcpu, regime))
+		return true;
+
 	if (regime == TR_EL10)
 		sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
 	else
@@ -747,11 +845,307 @@ static bool pan3_enabled(struct kvm_vcpu *vcpu, enum trans_regime regime)
 	return sctlr & SCTLR_EL1_EPAN;
 }

+static void compute_s1_direct_permissions(struct kvm_vcpu *vcpu,
+					  struct s1_walk_info *wi,
+					  struct s1_walk_result *wr)
+{
+	bool wxn;
+
+	/* Non-hierarchical part of AArch64.S1DirectBasePermissions() */
+	if (wi->regime != TR_EL2) {
+		switch (FIELD_GET(PTE_USER | PTE_RDONLY, wr->desc)) {
+		case 0b00:
+			wr->pr = wr->pw = true;
+			wr->ur = wr->uw = false;
+			break;
+		case 0b01:
+			wr->pr = wr->pw = wr->ur = wr->uw = true;
+			break;
+		case 0b10:
+			wr->pr = true;
+			wr->pw = wr->ur = wr->uw = false;
+			break;
+		case 0b11:
+			wr->pr = wr->ur = true;
+			wr->pw = wr->uw = false;
+			break;
+		}
+
+		/* We don't use px for anything yet, but hey... */
+		wr->px = !((wr->desc & PTE_PXN) || wr->uw);
+		wr->ux = !(wr->desc & PTE_UXN);
+	} else {
+		wr->ur = wr->uw = wr->ux = false;
+
+		if (!(wr->desc & PTE_RDONLY)) {
+			wr->pr = wr->pw = true;
+		} else {
+			wr->pr = true;
+			wr->pw = false;
+		}
+
+		/* XN maps to UXN */
+		wr->px = !(wr->desc & PTE_UXN);
+	}
+
+	switch (wi->regime) {
+	case TR_EL2:
+	case TR_EL20:
+		wxn = (vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_WXN);
+		break;
+	case TR_EL10:
+		wxn = (__vcpu_sys_reg(vcpu, SCTLR_EL1) & SCTLR_ELx_WXN);
+		break;
+	}
+
+	wr->pwxn = wr->uwxn = wxn;
+	wr->pov = wi->poe;
+	wr->uov = wi->e0poe;
+}
+
+static void compute_s1_hierarchical_permissions(struct kvm_vcpu *vcpu,
+						struct s1_walk_info *wi,
+						struct s1_walk_result *wr)
+{
+	/* Hierarchical part of AArch64.S1DirectBasePermissions() */
+	if (wi->regime != TR_EL2) {
+		switch (wr->APTable) {
+		case 0b00:
+			break;
+		case 0b01:
+			wr->ur = wr->uw = false;
+			break;
+		case 0b10:
+			wr->pw = wr->uw = false;
+			break;
+		case 0b11:
+			wr->pw = wr->ur = wr->uw = false;
+			break;
+		}
+
+		wr->px &= !wr->PXNTable;
+		wr->ux &= !wr->UXNTable;
+	} else {
+		if (wr->APTable & BIT(1))
+			wr->pw = false;
+
+		/* XN maps to UXN */
+		wr->px &= !wr->UXNTable;
+	}
+}
+
+#define perm_idx(v, r, i)	((vcpu_read_sys_reg((v), (r)) >> ((i) * 4)) & 0xf)
+
+#define set_priv_perms(wr, r, w, x)	\
+	do {				\
+		(wr)->pr = (r);		\
+		(wr)->pw = (w);		\
+		(wr)->px = (x);		\
+	} while (0)
+
+#define set_unpriv_perms(wr, r, w, x)	\
+	do {				\
+		(wr)->ur = (r);		\
+		(wr)->uw = (w);		\
+		(wr)->ux = (x);		\
+	} while (0)
+
+#define set_priv_wxn(wr, v)		\
+	do {				\
+		(wr)->pwxn = (v);	\
+	} while (0)
+
+#define set_unpriv_wxn(wr, v)		\
+	do {				\
+		(wr)->uwxn = (v);	\
+	} while (0)
+
+/* Similar to AArch64.S1IndirectBasePermissions(), without GCS  */
+#define set_perms(w, wr, ip)						\
+	do {								\
+		/* R_LLZDZ */						\
+		switch ((ip)) {						\
+		case 0b0000:						\
+			set_ ## w ## _perms((wr), false, false, false);	\
+			break;						\
+		case 0b0001:						\
+			set_ ## w ## _perms((wr), true , false, false);	\
+			break;						\
+		case 0b0010:						\
+			set_ ## w ## _perms((wr), false, false, true );	\
+			break;						\
+		case 0b0011:						\
+			set_ ## w ## _perms((wr), true , false, true );	\
+			break;						\
+		case 0b0100:						\
+			set_ ## w ## _perms((wr), false, false, false);	\
+			break;						\
+		case 0b0101:						\
+			set_ ## w ## _perms((wr), true , true , false);	\
+			break;						\
+		case 0b0110:						\
+			set_ ## w ## _perms((wr), true , true , true );	\
+			break;						\
+		case 0b0111:						\
+			set_ ## w ## _perms((wr), true , true , true );	\
+			break;						\
+		case 0b1000:						\
+			set_ ## w ## _perms((wr), true , false, false);	\
+			break;						\
+		case 0b1001:						\
+			set_ ## w ## _perms((wr), true , false, false);	\
+			break;						\
+		case 0b1010:						\
+			set_ ## w ## _perms((wr), true , false, true );	\
+			break;						\
+		case 0b1011:						\
+			set_ ## w ## _perms((wr), false, false, false);	\
+			break;						\
+		case 0b1100:						\
+			set_ ## w ## _perms((wr), true , true , false);	\
+			break;						\
+		case 0b1101:						\
+			set_ ## w ## _perms((wr), false, false, false);	\
+			break;						\
+		case 0b1110:						\
+			set_ ## w ## _perms((wr), true , true , true );	\
+			break;						\
+		case 0b1111:						\
+			set_ ## w ## _perms((wr), false, false, false);	\
+			break;						\
+		}							\
+									\
+		/* R_HJYGR */						\
+		set_ ## w ## _wxn((wr), ((ip) == 0b0110));		\
+									\
+	} while (0)
+
+static void compute_s1_indirect_permissions(struct kvm_vcpu *vcpu,
+					    struct s1_walk_info *wi,
+					    struct s1_walk_result *wr)
+{
+	u8 up, pp, idx;
+
+	idx = pte_pi_index(wr->desc);
+
+	switch (wi->regime) {
+	case TR_EL10:
+		pp = perm_idx(vcpu, PIR_EL1, idx);
+		up = perm_idx(vcpu, PIRE0_EL1, idx);
+		break;
+	case TR_EL20:
+		pp = perm_idx(vcpu, PIR_EL2, idx);
+		up = perm_idx(vcpu, PIRE0_EL2, idx);
+		break;
+	case TR_EL2:
+		pp = perm_idx(vcpu, PIR_EL2, idx);
+		up = 0;
+		break;
+	}
+
+	set_perms(priv, wr, pp);
+
+	if (wi->regime != TR_EL2)
+		set_perms(unpriv, wr, up);
+	else
+		set_unpriv_perms(wr, false, false, false);
+
+	wr->pov = wi->poe && !(pp & BIT(3));
+	wr->uov = wi->e0poe && !(up & BIT(3));
+
+	/* R_VFPJF */
+	if (wr->px && wr->uw) {
+		set_priv_perms(wr, false, false, false);
+		set_unpriv_perms(wr, false, false, false);
+	}
+}
+
+static void compute_s1_overlay_permissions(struct kvm_vcpu *vcpu,
+					   struct s1_walk_info *wi,
+					   struct s1_walk_result *wr)
+{
+	u8 idx, pov_perms, uov_perms;
+
+	idx = FIELD_GET(PTE_PO_IDX_MASK, wr->desc);
+
+	switch (wi->regime) {
+	case TR_EL10:
+		pov_perms = perm_idx(vcpu, POR_EL1, idx);
+		uov_perms = perm_idx(vcpu, POR_EL0, idx);
+		break;
+	case TR_EL20:
+		pov_perms = perm_idx(vcpu, POR_EL2, idx);
+		uov_perms = perm_idx(vcpu, POR_EL0, idx);
+		break;
+	case TR_EL2:
+		pov_perms = perm_idx(vcpu, POR_EL2, idx);
+		uov_perms = 0;
+		break;
+	}
+
+	if (pov_perms & ~POE_RXW)
+		pov_perms = POE_NONE;
+
+	if (wi->poe && wr->pov) {
+		wr->pr &= pov_perms & POE_R;
+		wr->px &= pov_perms & POE_X;
+		wr->pw &= pov_perms & POE_W;
+	}
+
+	if (uov_perms & ~POE_RXW)
+		uov_perms = POE_NONE;
+
+	if (wi->e0poe && wr->uov) {
+		wr->ur &= uov_perms & POE_R;
+		wr->ux &= uov_perms & POE_X;
+		wr->uw &= uov_perms & POE_W;
+	}
+}
+
+static void compute_s1_permissions(struct kvm_vcpu *vcpu,
+				   struct s1_walk_info *wi,
+				   struct s1_walk_result *wr)
+{
+	bool pan;
+
+	if (!s1pie_enabled(vcpu, wi->regime))
+		compute_s1_direct_permissions(vcpu, wi, wr);
+	else
+		compute_s1_indirect_permissions(vcpu, wi, wr);
+
+	if (!wi->hpd)
+		compute_s1_hierarchical_permissions(vcpu, wi, wr);
+
+	if (wi->poe || wi->e0poe)
+		compute_s1_overlay_permissions(vcpu, wi, wr);
+
+	/* R_QXXPC */
+	if (wr->pwxn) {
+		if (!wr->pov && wr->pw)
+			wr->px = false;
+		if (wr->pov && wr->px)
+			wr->pw = false;
+	}
+
+	/* R_NPBXC */
+	if (wr->uwxn) {
+		if (!wr->uov && wr->uw)
+			wr->ux = false;
+		if (wr->uov && wr->ux)
+			wr->uw = false;
+	}
+
+	pan = wi->pan && (wr->ur || wr->uw ||
+			  (pan3_enabled(vcpu, wi->regime) && wr->ux));
+	wr->pw &= !pan;
+	wr->pr &= !pan;
+}
+
 static u64 handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 {
-	bool perm_fail, ur, uw, ux, pr, pw, px;
 	struct s1_walk_result wr = {};
 	struct s1_walk_info wi = {};
+	bool perm_fail = false;
 	int ret, idx;

 	ret = setup_s1_walk(vcpu, op, &wi, &wr, vaddr);
@@ -770,88 +1164,24 @@ static u64 handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 	if (ret)
 		goto compute_par;

-	/* FIXME: revisit when adding indirect permission support */
-	/* AArch64.S1DirectBasePermissions() */
-	if (wi.regime != TR_EL2) {
-		switch (FIELD_GET(PTE_USER | PTE_RDONLY, wr.desc)) {
-		case 0b00:
-			pr = pw = true;
-			ur = uw = false;
-			break;
-		case 0b01:
-			pr = pw = ur = uw = true;
-			break;
-		case 0b10:
-			pr = true;
-			pw = ur = uw = false;
-			break;
-		case 0b11:
-			pr = ur = true;
-			pw = uw = false;
-			break;
-		}
-
-		switch (wr.APTable) {
-		case 0b00:
-			break;
-		case 0b01:
-			ur = uw = false;
-			break;
-		case 0b10:
-			pw = uw = false;
-			break;
-		case 0b11:
-			pw = ur = uw = false;
-			break;
-		}
-
-		/* We don't use px for anything yet, but hey... */
-		px = !((wr.desc & PTE_PXN) || wr.PXNTable || uw);
-		ux = !((wr.desc & PTE_UXN) || wr.UXNTable);
-
-		if (op == OP_AT_S1E1RP || op == OP_AT_S1E1WP) {
-			bool pan;
-
-			pan = *vcpu_cpsr(vcpu) & PSR_PAN_BIT;
-			pan &= ur || uw || (pan3_enabled(vcpu, wi.regime) && ux);
-			pw &= !pan;
-			pr &= !pan;
-		}
-	} else {
-		ur = uw = ux = false;
-
-		if (!(wr.desc & PTE_RDONLY)) {
-			pr = pw = true;
-		} else {
-			pr = true;
-			pw = false;
-		}
-
-		if (wr.APTable & BIT(1))
-			pw = false;
-
-		/* XN maps to UXN */
-		px = !((wr.desc & PTE_UXN) || wr.UXNTable);
-	}
-
-	perm_fail = false;
+	compute_s1_permissions(vcpu, &wi, &wr);

 	switch (op) {
 	case OP_AT_S1E1RP:
 	case OP_AT_S1E1R:
 	case OP_AT_S1E2R:
-		perm_fail = !pr;
+		perm_fail = !wr.pr;
 		break;
 	case OP_AT_S1E1WP:
 	case OP_AT_S1E1W:
 	case OP_AT_S1E2W:
-		perm_fail = !pw;
+		perm_fail = !wr.pw;
 		break;
 	case OP_AT_S1E0R:
-		perm_fail = !ur;
+		perm_fail = !wr.ur;
 		break;
 	case OP_AT_S1E0W:
-		perm_fail = !uw;
+		perm_fail = !wr.uw;
 		break;
 	case OP_AT_S1E1A:
 	case OP_AT_S1E2A:
@@ -914,6 +1244,17 @@ static u64 __kvm_at_s1e01_fast(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 	write_sysreg_el1(vcpu_read_sys_reg(vcpu, TTBR1_EL1),	SYS_TTBR1);
 	write_sysreg_el1(vcpu_read_sys_reg(vcpu, TCR_EL1),	SYS_TCR);
 	write_sysreg_el1(vcpu_read_sys_reg(vcpu, MAIR_EL1),	SYS_MAIR);
+	if (kvm_has_tcr2(vcpu->kvm)) {
+		write_sysreg_el1(vcpu_read_sys_reg(vcpu, TCR2_EL1), SYS_TCR2);
+		if (kvm_has_s1pie(vcpu->kvm)) {
+			write_sysreg_el1(vcpu_read_sys_reg(vcpu, PIR_EL1), SYS_PIR);
+			write_sysreg_el1(vcpu_read_sys_reg(vcpu, PIRE0_EL1), SYS_PIRE0);
+		}
+		if (kvm_has_s1poe(vcpu->kvm)) {
+			write_sysreg_el1(vcpu_read_sys_reg(vcpu, POR_EL1), SYS_POR);
+			write_sysreg_s(vcpu_read_sys_reg(vcpu, POR_EL0), SYS_POR_EL0);
+		}
+	}
 	write_sysreg_el1(vcpu_read_sys_reg(vcpu, SCTLR_EL1),	SYS_SCTLR);
 	__load_stage2(mmu, mmu->arch);

@@ -992,12 +1333,9 @@ void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 	 * switching context behind everybody's back, disable interrupts...
 	 */
 	scoped_guard(write_lock_irqsave, &vcpu->kvm->mmu_lock) {
-		struct kvm_s2_mmu *mmu;
 		u64 val, hcr;
 		bool fail;

-		mmu = &vcpu->kvm->arch.mmu;
-
 		val = hcr = read_sysreg(hcr_el2);
 		val &= ~HCR_TGE;
 		val |= HCR_VM;
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -79,7 +79,6 @@ enum cgt_group_id {
 	CGT_MDCR_E2TB,
 	CGT_MDCR_TDCC,

-	CGT_CPACR_E0POE,
 	CGT_CPTR_TAM,
 	CGT_CPTR_TCPAC,

@@ -362,12 +361,6 @@ static const struct trap_bits coarse_trap_bits[] = {
 		.mask		= MDCR_EL2_TDCC,
 		.behaviour	= BEHAVE_FORWARD_ANY,
 	},
-	[CGT_CPACR_E0POE] = {
-		.index		= CPTR_EL2,
-		.value		= CPACR_ELx_E0POE,
-		.mask		= CPACR_ELx_E0POE,
-		.behaviour	= BEHAVE_FORWARD_ANY,
-	},
 	[CGT_CPTR_TAM] = {
 		.index		= CPTR_EL2,
 		.value		= CPTR_EL2_TAM,
@@ -711,6 +704,10 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_MAIR_EL1,		CGT_HCR_TVM_TRVM),
 	SR_TRAP(SYS_AMAIR_EL1,		CGT_HCR_TVM_TRVM),
 	SR_TRAP(SYS_CONTEXTIDR_EL1,	CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_PIR_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_PIRE0_EL1,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_POR_EL0,		CGT_HCR_TVM_TRVM),
+	SR_TRAP(SYS_POR_EL1,		CGT_HCR_TVM_TRVM),
 	SR_TRAP(SYS_TCR2_EL1,		CGT_HCR_TVM_TRVM_HCRX_TCR2En),
 	SR_TRAP(SYS_DC_ZVA,		CGT_HCR_TDZ),
 	SR_TRAP(SYS_DC_GVA,		CGT_HCR_TDZ),
@@ -1141,7 +1138,6 @@ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = {
 	SR_TRAP(SYS_AMEVTYPER1_EL0(13),	CGT_CPTR_TAM),
 	SR_TRAP(SYS_AMEVTYPER1_EL0(14),	CGT_CPTR_TAM),
 	SR_TRAP(SYS_AMEVTYPER1_EL0(15),	CGT_CPTR_TAM),
-	SR_TRAP(SYS_POR_EL0,		CGT_CPACR_E0POE),
 	/* op0=2, op1=1, and CRn<0b1000 */
 	SR_RANGE_TRAP(sys_reg(2, 1, 0, 0, 0),
 		      sys_reg(2, 1, 7, 15, 7), CGT_CPTR_TTA),
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -58,7 +58,7 @@ static inline bool ctxt_has_s1pie(struct kvm_cpu_context *ctxt)
 		return false;

 	vcpu = ctxt_to_vcpu(ctxt);
-	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, S1PIE, IMP);
+	return kvm_has_s1pie(kern_hyp_va(vcpu->kvm));
 }

 static inline bool ctxt_has_tcrx(struct kvm_cpu_context *ctxt)
@@ -69,7 +69,7 @@ static inline bool ctxt_has_tcrx(struct kvm_cpu_context *ctxt)
 		return false;

 	vcpu = ctxt_to_vcpu(ctxt);
-	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, TCRX, IMP);
+	return kvm_has_tcr2(kern_hyp_va(vcpu->kvm));
 }

 static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt)
@@ -80,7 +80,7 @@ static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt)
 		return false;

 	vcpu = ctxt_to_vcpu(ctxt);
-	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, S1POE, IMP);
+	return kvm_has_s1poe(kern_hyp_va(vcpu->kvm));
 }

 static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
@@ -152,9 +152,10 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
 	write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0),	tpidrro_el0);
 }

-static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
+static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt,
+					      u64 mpidr)
 {
-	write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1),	vmpidr_el2);
+	write_sysreg(mpidr,				vmpidr_el2);

 	if (has_vhe() ||
 	    !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
--- a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c
@@ -28,7 +28,7 @@ void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt)

 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt)
 {
-	__sysreg_restore_el1_state(ctxt);
+	__sysreg_restore_el1_state(ctxt, ctxt_sys_reg(ctxt, MPIDR_EL1));
 	__sysreg_restore_common_state(ctxt);
 	__sysreg_restore_user_state(ctxt);
 	__sysreg_restore_el2_return_state(ctxt);
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -15,6 +15,131 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_nested.h>

+static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
+{
+	/* These registers are common with EL1 */
+	__vcpu_sys_reg(vcpu, PAR_EL1)	= read_sysreg(par_el1);
+	__vcpu_sys_reg(vcpu, TPIDR_EL1)	= read_sysreg(tpidr_el1);
+
+	__vcpu_sys_reg(vcpu, ESR_EL2)	= read_sysreg_el1(SYS_ESR);
+	__vcpu_sys_reg(vcpu, AFSR0_EL2)	= read_sysreg_el1(SYS_AFSR0);
+	__vcpu_sys_reg(vcpu, AFSR1_EL2)	= read_sysreg_el1(SYS_AFSR1);
+	__vcpu_sys_reg(vcpu, FAR_EL2)	= read_sysreg_el1(SYS_FAR);
+	__vcpu_sys_reg(vcpu, MAIR_EL2)	= read_sysreg_el1(SYS_MAIR);
+	__vcpu_sys_reg(vcpu, VBAR_EL2)	= read_sysreg_el1(SYS_VBAR);
+	__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
+	__vcpu_sys_reg(vcpu, AMAIR_EL2)	= read_sysreg_el1(SYS_AMAIR);
+
+	/*
+	 * In VHE mode those registers are compatible between EL1 and EL2,
+	 * and the guest uses the _EL1 versions on the CPU naturally.
+	 * So we save them into their _EL2 versions here.
+	 * For nVHE mode we trap accesses to those registers, so our
+	 * _EL2 copy in sys_regs[] is always up-to-date and we don't need
+	 * to save anything here.
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu)) {
+		u64 val;
+
+		/*
+		 * We don't save CPTR_EL2, as accesses to CPACR_EL1
+		 * are always trapped, ensuring that the in-memory
+		 * copy is always up-to-date. A small blessing...
+		 */
+		__vcpu_sys_reg(vcpu, SCTLR_EL2)	= read_sysreg_el1(SYS_SCTLR);
+		__vcpu_sys_reg(vcpu, TTBR0_EL2)	= read_sysreg_el1(SYS_TTBR0);
+		__vcpu_sys_reg(vcpu, TTBR1_EL2)	= read_sysreg_el1(SYS_TTBR1);
+		__vcpu_sys_reg(vcpu, TCR_EL2)	= read_sysreg_el1(SYS_TCR);
+
+		if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
+			__vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2);
+
+			if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
+				__vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0);
+				__vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR);
+			}
+
+			if (ctxt_has_s1poe(&vcpu->arch.ctxt))
+				__vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR);
+		}
+
+		/*
+		 * The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where
+		 * the interesting CNTHCTL_EL2 bits live. So preserve these
+		 * bits when reading back the guest-visible value.
+		 */
+		val = read_sysreg_el1(SYS_CNTKCTL);
+		val &= CNTKCTL_VALID_BITS;
+		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS;
+		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val;
+	}
+
+	__vcpu_sys_reg(vcpu, SP_EL2)	= read_sysreg(sp_el1);
+	__vcpu_sys_reg(vcpu, ELR_EL2)	= read_sysreg_el1(SYS_ELR);
+	__vcpu_sys_reg(vcpu, SPSR_EL2)	= read_sysreg_el1(SYS_SPSR);
+}
+
+static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	/* These registers are common with EL1 */
+	write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1),	par_el1);
+	write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1),	tpidr_el1);
+
+	write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1),		vmpidr_el2);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2),	SYS_MAIR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2),	SYS_VBAR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2),	SYS_CONTEXTIDR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2),	SYS_AMAIR);
+
+	if (vcpu_el2_e2h_is_set(vcpu)) {
+		/*
+		 * In VHE mode those registers are compatible between
+		 * EL1 and EL2.
+		 */
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2),   SYS_SCTLR);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2),    SYS_CPACR);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2),   SYS_TTBR0);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2),   SYS_TTBR1);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2),	    SYS_TCR);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, CNTHCTL_EL2), SYS_CNTKCTL);
+	} else {
+		/*
+		 * CNTHCTL_EL2 only affects EL1 when running nVHE, so
+		 * no need to restore it.
+		 */
+		val = translate_sctlr_el2_to_sctlr_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2));
+		write_sysreg_el1(val, SYS_SCTLR);
+		val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2));
+		write_sysreg_el1(val, SYS_CPACR);
+		val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2));
+		write_sysreg_el1(val, SYS_TTBR0);
+		val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2));
+		write_sysreg_el1(val, SYS_TCR);
+	}
+
+	if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR2_EL2), SYS_TCR2);
+
+		if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
+			write_sysreg_el1(__vcpu_sys_reg(vcpu, PIR_EL2), SYS_PIR);
+			write_sysreg_el1(__vcpu_sys_reg(vcpu, PIRE0_EL2), SYS_PIRE0);
+		}
+
+		if (ctxt_has_s1poe(&vcpu->arch.ctxt))
+			write_sysreg_el1(__vcpu_sys_reg(vcpu, POR_EL2), SYS_POR);
+	}
+
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2),		SYS_ESR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2),	SYS_AFSR0);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2),	SYS_AFSR1);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2),		SYS_FAR);
+	write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2),		sp_el1);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2),		SYS_ELR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, SPSR_EL2),	SYS_SPSR);
+}
+
 /*
 * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
 * pstate, which are handled as part of the el2 return state) on every
@@ -66,6 +191,7 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
+	u64 mpidr;

 	host_ctxt = host_data_ptr(host_ctxt);
 	__sysreg_save_user_state(host_ctxt);
@@ -89,7 +215,29 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_user_state(guest_ctxt);
-	__sysreg_restore_el1_state(guest_ctxt);
+
+	if (unlikely(__is_hyp_ctxt(guest_ctxt))) {
+		__sysreg_restore_vel2_state(vcpu);
+	} else {
+		if (vcpu_has_nv(vcpu)) {
+			/*
+			 * Use the guest hypervisor's VPIDR_EL2 when in a
+			 * nested state. The hardware value of MIDR_EL1 gets
+			 * restored on put.
+			 */
+			write_sysreg(ctxt_sys_reg(guest_ctxt, VPIDR_EL2), vpidr_el2);
+
+			/*
+			 * As we're restoring a nested guest, set the value
+			 * provided by the guest hypervisor.
+			 */
+			mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2);
+		} else {
+			mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1);
+		}
+
+		__sysreg_restore_el1_state(guest_ctxt, mpidr);
+	}

 	vcpu_set_flag(vcpu, SYSREGS_ON_CPU);
 }
@@ -112,12 +260,20 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)

 	host_ctxt = host_data_ptr(host_ctxt);

-	__sysreg_save_el1_state(guest_ctxt);
+	if (unlikely(__is_hyp_ctxt(guest_ctxt)))
+		__sysreg_save_vel2_state(vcpu);
+	else
+		__sysreg_save_el1_state(guest_ctxt);
+
 	__sysreg_save_user_state(guest_ctxt);
 	__sysreg32_save_state(vcpu);

 	/* Restore host user state */
 	__sysreg_restore_user_state(host_ctxt);

+	/* If leaving a nesting guest, restore MIDR_EL1 default view */
+	if (vcpu_has_nv(vcpu))
+		write_sysreg(read_cpuid_id(),	vpidr_el2);
+
 	vcpu_clear_flag(vcpu, SYSREGS_ON_CPU);
 }
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -933,15 +933,15 @@ static void limit_nv_id_regs(struct kvm *kvm)
 	kvm_set_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1, val);
 }

-u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr)
+u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu,
+			     enum vcpu_sysreg sr, u64 v)
 {
-	u64 v = ctxt_sys_reg(&vcpu->arch.ctxt, sr);
 	struct kvm_sysreg_masks *masks;

 	masks = vcpu->kvm->arch.sysreg_masks;

 	if (masks) {
-		sr -= __VNCR_START__;
+		sr -= __SANITISED_REG_START__;

 		v &= ~masks->mask[sr].res0;
 		v |= masks->mask[sr].res1;
@@ -952,7 +952,11 @@ u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr)

 static void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1)
 {
-	int i = sr - __VNCR_START__;
+	int i = sr - __SANITISED_REG_START__;
+
+	BUILD_BUG_ON(!__builtin_constant_p(sr));
+	BUILD_BUG_ON(sr < __SANITISED_REG_START__);
+	BUILD_BUG_ON(sr >= NR_SYS_REGS);

 	kvm->arch.sysreg_masks->mask[i].res0 = res0;
 	kvm->arch.sysreg_masks->mask[i].res1 = res1;
@@ -1050,7 +1054,7 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 		res0 |= HCRX_EL2_PTTWI;
 	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SCTLRX, IMP))
 		res0 |= HCRX_EL2_SCTLR2En;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
+	if (!kvm_has_tcr2(kvm))
 		res0 |= HCRX_EL2_TCR2En;
 	if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
 		res0 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
@@ -1101,9 +1105,9 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 		res0 |= (HFGxTR_EL2_nSMPRI_EL1 | HFGxTR_EL2_nTPIDR2_EL0);
 	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
 		res0 |= HFGxTR_EL2_nRCWMASK_EL1;
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1PIE, IMP))
+	if (!kvm_has_s1pie(kvm))
 		res0 |= (HFGxTR_EL2_nPIRE0_EL1 | HFGxTR_EL2_nPIR_EL1);
-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1POE, IMP))
+	if (!kvm_has_s1poe(kvm))
 		res0 |= (HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nPOR_EL1);
 	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
 		res0 |= HFGxTR_EL2_nS2POR_EL1;
@@ -1200,6 +1204,28 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
 		res0 |= ~(res0 | res1);
 	set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1);

+	/* TCR2_EL2 */
+	res0 = TCR2_EL2_RES0;
+	res1 = TCR2_EL2_RES1;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP))
+		res0 |= (TCR2_EL2_DisCH0 | TCR2_EL2_DisCH1 | TCR2_EL2_D128);
+	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, MEC, IMP))
+		res0 |= TCR2_EL2_AMEC1 | TCR2_EL2_AMEC0;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, HAFDBS, HAFT))
+		res0 |= TCR2_EL2_HAFT;
+	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
+		res0 |= TCR2_EL2_PTTWI | TCR2_EL2_PnCH;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP))
+		res0 |= TCR2_EL2_AIE;
+	if (!kvm_has_s1poe(kvm))
+		res0 |= TCR2_EL2_POE | TCR2_EL2_E0POE;
+	if (!kvm_has_s1pie(kvm))
+		res0 |= TCR2_EL2_PIE;
+	if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP))
+		res0 |= (TCR2_EL2_E0POE | TCR2_EL2_D128 |
+			 TCR2_EL2_AMEC1 | TCR2_EL2_DisCH0 | TCR2_EL2_DisCH1);
+	set_sysreg_masks(kvm, TCR2_EL2, res0, res1);
+
 	/* SCTLR_EL1 */
 	res0 = SCTLR_EL1_RES0;
 	res1 = SCTLR_EL1_RES1;
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -110,6 +110,14 @@ static bool get_el2_to_el1_mapping(unsigned int reg,
 		PURE_EL2_SYSREG(  RVBAR_EL2	);
 		PURE_EL2_SYSREG(  TPIDR_EL2	);
 		PURE_EL2_SYSREG(  HPFAR_EL2	);
+		PURE_EL2_SYSREG(  HCRX_EL2	);
+		PURE_EL2_SYSREG(  HFGRTR_EL2	);
+		PURE_EL2_SYSREG(  HFGWTR_EL2	);
+		PURE_EL2_SYSREG(  HFGITR_EL2	);
+		PURE_EL2_SYSREG(  HDFGRTR_EL2	);
+		PURE_EL2_SYSREG(  HDFGWTR_EL2	);
+		PURE_EL2_SYSREG(  HAFGRTR_EL2	);
+		PURE_EL2_SYSREG(  CNTVOFF_EL2	);
 		PURE_EL2_SYSREG(  CNTHCTL_EL2	);
 		MAPPED_EL2_SYSREG(SCTLR_EL2,   SCTLR_EL1,
 				  translate_sctlr_el2_to_sctlr_el1	     );
@@ -126,10 +134,15 @@ static bool get_el2_to_el1_mapping(unsigned int reg,
 		MAPPED_EL2_SYSREG(ESR_EL2,     ESR_EL1,     NULL	     );
 		MAPPED_EL2_SYSREG(FAR_EL2,     FAR_EL1,     NULL	     );
 		MAPPED_EL2_SYSREG(MAIR_EL2,    MAIR_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(TCR2_EL2,    TCR2_EL1,    NULL	     );
+		MAPPED_EL2_SYSREG(PIR_EL2,     PIR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(PIRE0_EL2,   PIRE0_EL1,   NULL	     );
+		MAPPED_EL2_SYSREG(POR_EL2,     POR_EL1,     NULL	     );
 		MAPPED_EL2_SYSREG(AMAIR_EL2,   AMAIR_EL1,   NULL	     );
 		MAPPED_EL2_SYSREG(ELR_EL2,     ELR_EL1,	    NULL	     );
 		MAPPED_EL2_SYSREG(SPSR_EL2,    SPSR_EL1,    NULL	     );
 		MAPPED_EL2_SYSREG(ZCR_EL2,     ZCR_EL1,     NULL	     );
+		MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1, NULL	     );
 	default:
 		return false;
 	}
@@ -148,6 +161,21 @@ 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.
@@ -165,6 +193,9 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)

 		/* Get the current version of the EL1 counterpart. */
 		WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
+		if (reg >= __SANITISED_REG_START__)
+			val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
+
 		return val;
 	}

@@ -198,6 +229,19 @@ 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;
@@ -390,10 +434,6 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu,
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 	u64 val, mask, shift;

-	if (reg_to_encoding(r) == SYS_TCR2_EL1 &&
-	    !kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
-		return undef_access(vcpu, p, r);
-
 	BUG_ON(!p->is_write);

 	get_access_mask(r, &mask, &shift);
@@ -2104,6 +2144,15 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
 	.val = v,				\
 }

+#define EL2_REG_FILTERED(name, acc, rst, v, filter) {	\
+	SYS_DESC(SYS_##name),			\
+	.access = acc,				\
+	.reset = rst,				\
+	.reg = name,				\
+	.visibility = filter,			\
+	.val = v,				\
+}
+
 #define EL2_REG_VNCR(name, rst, v)	EL2_REG(name, bad_vncr_trap, rst, v)
 #define EL2_REG_REDIR(name, rst, v)	EL2_REG(name, bad_redir_trap, rst, v)

@@ -2236,16 +2285,18 @@ static u64 reset_hcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	return __vcpu_sys_reg(vcpu, r->reg) = val;
 }

+static unsigned int __el2_visibility(const struct kvm_vcpu *vcpu,
+				     const struct sys_reg_desc *rd,
+				     unsigned int (*fn)(const struct kvm_vcpu *,
+							const struct sys_reg_desc *))
+{
+	return el2_visibility(vcpu, rd) ?: fn(vcpu, rd);
+}
+
 static unsigned int sve_el2_visibility(const struct kvm_vcpu *vcpu,
 				       const struct sys_reg_desc *rd)
 {
-	unsigned int r;
-
-	r = el2_visibility(vcpu, rd);
-	if (r)
-		return r;
-
-	return sve_visibility(vcpu, rd);
+	return __el2_visibility(vcpu, rd, sve_visibility);
 }

 static bool access_zcr_el2(struct kvm_vcpu *vcpu,
@@ -2273,12 +2324,48 @@ static bool access_zcr_el2(struct kvm_vcpu *vcpu,
 static unsigned int s1poe_visibility(const struct kvm_vcpu *vcpu,
 				     const struct sys_reg_desc *rd)
 {
-	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S1POE, IMP))
+	if (kvm_has_s1poe(vcpu->kvm))
 		return 0;

 	return REG_HIDDEN;
 }

+static unsigned int s1poe_el2_visibility(const struct kvm_vcpu *vcpu,
+					 const struct sys_reg_desc *rd)
+{
+	return __el2_visibility(vcpu, rd, s1poe_visibility);
+}
+
+static unsigned int tcr2_visibility(const struct kvm_vcpu *vcpu,
+				    const struct sys_reg_desc *rd)
+{
+	if (kvm_has_tcr2(vcpu->kvm))
+		return 0;
+
+	return REG_HIDDEN;
+}
+
+static unsigned int tcr2_el2_visibility(const struct kvm_vcpu *vcpu,
+				    const struct sys_reg_desc *rd)
+{
+	return __el2_visibility(vcpu, rd, tcr2_visibility);
+}
+
+static unsigned int s1pie_visibility(const struct kvm_vcpu *vcpu,
+				     const struct sys_reg_desc *rd)
+{
+	if (kvm_has_s1pie(vcpu->kvm))
+		return 0;
+
+	return REG_HIDDEN;
+}
+
+static unsigned int s1pie_el2_visibility(const struct kvm_vcpu *vcpu,
+					 const struct sys_reg_desc *rd)
+{
+	return __el2_visibility(vcpu, rd, s1pie_visibility);
+}
+
 /*
 * Architected system registers.
 * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
@@ -2489,7 +2576,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
 	{ SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
 	{ SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 },
-	{ SYS_DESC(SYS_TCR2_EL1), access_vm_reg, reset_val, TCR2_EL1, 0 },
+	{ SYS_DESC(SYS_TCR2_EL1), access_vm_reg, reset_val, TCR2_EL1, 0,
+	  .visibility = tcr2_visibility },

 	PTRAUTH_KEY(APIA),
 	PTRAUTH_KEY(APIB),
@@ -2543,8 +2631,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi },

 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
-	{ SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1 },
-	{ SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1 },
+	{ SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1,
+	  .visibility = s1pie_visibility },
+	{ SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1,
+	  .visibility = s1pie_visibility },
 	{ SYS_DESC(SYS_POR_EL1), NULL, reset_unknown, POR_EL1,
 	  .visibility = s1poe_visibility },
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
@@ -2818,14 +2908,16 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG_VNCR(HFGITR_EL2, reset_val, 0),
 	EL2_REG_VNCR(HACR_EL2, reset_val, 0),

-	{ SYS_DESC(SYS_ZCR_EL2), .access = access_zcr_el2, .reset = reset_val,
-	  .visibility = sve_el2_visibility, .reg = ZCR_EL2 },
+	EL2_REG_FILTERED(ZCR_EL2, access_zcr_el2, reset_val, 0,
+			 sve_el2_visibility),

 	EL2_REG_VNCR(HCRX_EL2, reset_val, 0),

 	EL2_REG(TTBR0_EL2, access_rw, reset_val, 0),
 	EL2_REG(TTBR1_EL2, access_rw, reset_val, 0),
 	EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1),
+	EL2_REG_FILTERED(TCR2_EL2, access_rw, reset_val, TCR2_EL2_RES1,
+			 tcr2_el2_visibility),
 	EL2_REG_VNCR(VTTBR_EL2, reset_val, 0),
 	EL2_REG_VNCR(VTCR_EL2, reset_val, 0),

@@ -2853,6 +2945,12 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(HPFAR_EL2, access_rw, reset_val, 0),

 	EL2_REG(MAIR_EL2, access_rw, reset_val, 0),
+	EL2_REG_FILTERED(PIRE0_EL2, access_rw, reset_val, 0,
+			 s1pie_el2_visibility),
+	EL2_REG_FILTERED(PIR_EL2, access_rw, reset_val, 0,
+			 s1pie_el2_visibility),
+	EL2_REG_FILTERED(POR_EL2, access_rw, reset_val, 0,
+			 s1poe_el2_visibility),
 	EL2_REG(AMAIR_EL2, access_rw, reset_val, 0),

 	EL2_REG(VBAR_EL2, access_rw, reset_val, 0),
@@ -4719,7 +4817,7 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
 		if (kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
 			vcpu->arch.hcrx_el2 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);

-		if (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
+		if (kvm_has_tcr2(kvm))
 			vcpu->arch.hcrx_el2 |= HCRX_EL2_TCR2En;

 		if (kvm_has_fpmr(kvm))
@@ -4769,11 +4867,11 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
 		kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_ATS1E1RP |
 						HFGITR_EL2_ATS1E1WP);

-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1PIE, IMP))
+	if (!kvm_has_s1pie(kvm))
 		kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPIRE0_EL1 |
 						HFGxTR_EL2_nPIR_EL1);

-	if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S1POE, IMP))
+	if (!kvm_has_s1poe(kvm))
 		kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPOR_EL1 |
 						HFGxTR_EL2_nPOR_EL0);

--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1688,6 +1688,7 @@ UnsignedEnum	3:0	HAFDBS
 	0b0000	NI
 	0b0001	AF
 	0b0010	DBM
+	0b0011	HAFT
 EndEnum
 EndSysreg

@@ -2819,8 +2820,7 @@ Field	13	AMEC1
 Field	12	AMEC0
 Field	11	HAFT
 Field	10	PTTWI
-Field	9:8	SKL1
-Field	7:6	SKL0
+Res0	9:6
 Field	5	D128
 Field	4	AIE
 Field	3	POE
@@ -2883,6 +2883,10 @@ Sysreg	PIRE0_EL12	3	5	10	2	2
 Fields	PIRx_ELx
 EndSysreg

+Sysreg	PIRE0_EL2	3	4	10	2	2
+Fields	PIRx_ELx
+EndSysreg
+
 Sysreg	PIR_EL1		3	0	10	2	3
 Fields	PIRx_ELx
 EndSysreg
@@ -2903,6 +2907,10 @@ Sysreg	POR_EL1		3	0	10	2	4
 Fields	PIRx_ELx
 EndSysreg

+Sysreg	POR_EL2		3	4	10	2	4
+Fields	PIRx_ELx
+EndSysreg
+
 Sysreg	POR_EL12	3	5	10	2	4
 Fields	PIRx_ELx
 EndSysreg
--- a/include/kvm/arm_arch_timer.h
+++ b/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));