Merge branch kvm-arm64/hvhe into kvmarm/next

* kvm-arm64/hvhe:
  : Support for running split-hypervisor w/VHE, courtesy of Marc Zyngier
  :
  : From the cover letter:
  :
  : KVM (on ARMv8.0) and pKVM (on all revisions of the architecture) use
  : the split hypervisor model that makes the EL2 code more or less
  : standalone. In the later case, we totally ignore the VHE mode and
  : stick with the good old v8.0 EL2 setup.
  :
  : We introduce a new "mode" for KVM called hVHE, in reference to the
  : nVHE mode, and indicating that only the hypervisor is using VHE.
  KVM: arm64: Fix hVHE init on CPUs where HCR_EL2.E2H is not RES1
  arm64: Allow arm64_sw.hvhe on command line
  KVM: arm64: Force HCR_E2H in guest context when ARM64_KVM_HVHE is set
  KVM: arm64: Program the timer traps with VHE layout in hVHE mode
  KVM: arm64: Rework CPTR_EL2 programming for HVHE configuration
  KVM: arm64: Adjust EL2 stage-1 leaf AP bits when ARM64_KVM_HVHE is set
  KVM: arm64: Disable TTBR1_EL2 when using ARM64_KVM_HVHE
  KVM: arm64: Force HCR_EL2.E2H when ARM64_KVM_HVHE is set
  KVM: arm64: Key use of VHE instructions in nVHE code off ARM64_KVM_HVHE
  KVM: arm64: Remove alternatives from sysreg accessors in VHE hypervisor context
  arm64: Use CPACR_EL1 format to set CPTR_EL2 when E2H is set
  arm64: Allow EL1 physical timer access when running VHE
  arm64: Don't enable VHE for the kernel if OVERRIDE_HVHE is set
  arm64: Add KVM_HVHE capability and has_hvhe() predicate
  arm64: Turn kaslr_feature_override into a generic SW feature override
  arm64: Prevent the use of is_kernel_in_hyp_mode() in hypervisor code
  KVM: arm64: Drop is_kernel_in_hyp_mode() from __invalidate_icache_guest_page()
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

arch/arm64/include/asm/cpufeature.h

@@ -15,6 +15,9 @@
 #define MAX_CPU_FEATURES	128
 #define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
+#define ARM64_SW_FEATURE_OVERRIDE_NOKASLR	0
+#define ARM64_SW_FEATURE_OVERRIDE_HVHE		4
+
 #ifndef __ASSEMBLY__
 
 #include <linux/bug.h>
@@ -925,6 +928,8 @@ extern struct arm64_ftr_override id_aa64smfr0_override;
 extern struct arm64_ftr_override id_aa64isar1_override;
 extern struct arm64_ftr_override id_aa64isar2_override;
 
+extern struct arm64_ftr_override arm64_sw_feature_override;
+
 u32 get_kvm_ipa_limit(void);
 void dump_cpu_features(void);
 

arch/arm64/include/asm/el2_setup.h

@@ -34,6 +34,11 @@
  */
 .macro __init_el2_timers
 	mov	x0, #3				// Enable EL1 physical timers
+	mrs	x1, hcr_el2
+	and	x1, x1, #HCR_E2H
+	cbz	x1, .LnVHE_\@
+	lsl	x0, x0, #10
+.LnVHE_\@:
 	msr	cnthctl_el2, x0
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 .endm
@@ -124,8 +129,15 @@
 .endm
 
 /* Coprocessor traps */
-.macro __init_el2_nvhe_cptr
+.macro __init_el2_cptr
+	mrs	x1, hcr_el2
+	and	x1, x1, #HCR_E2H
+	cbz	x1, .LnVHE_\@
+	mov	x0, #(CPACR_EL1_FPEN_EL1EN | CPACR_EL1_FPEN_EL0EN)
+	b	.Lset_cptr_\@
+.LnVHE_\@:
 	mov	x0, #0x33ff
+.Lset_cptr_\@:
 	msr	cptr_el2, x0			// Disable copro. traps to EL2
 .endm
 
@@ -191,9 +203,8 @@
 	__init_el2_gicv3
 	__init_el2_hstr
 	__init_el2_nvhe_idregs
-	__init_el2_nvhe_cptr
+	__init_el2_cptr
 	__init_el2_fgt
-	__init_el2_nvhe_prepare_eret
 .endm
 
 #ifndef __KVM_NVHE_HYPERVISOR__
@@ -239,7 +250,17 @@
 
 .Linit_sve_\@:	/* SVE register access */
 	mrs	x0, cptr_el2			// Disable SVE traps
+	mrs	x1, hcr_el2
+	and	x1, x1, #HCR_E2H
+	cbz	x1, .Lcptr_nvhe_\@
+
+	// VHE case
+	orr	x0, x0, #(CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
+	b	.Lset_cptr_\@
+
+.Lcptr_nvhe_\@: // nVHE case
 	bic	x0, x0, #CPTR_EL2_TZ
+.Lset_cptr_\@:
 	msr	cptr_el2, x0
 	isb
 	mov	x1, #ZCR_ELx_LEN_MASK		// SVE: Enable full vector

arch/arm64/include/asm/kvm_arm.h

@@ -285,7 +285,6 @@
 #define CPTR_EL2_TFP	(1 << CPTR_EL2_TFP_SHIFT)
 #define CPTR_EL2_TZ	(1 << 8)
 #define CPTR_NVHE_EL2_RES1	0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */
-#define CPTR_EL2_DEFAULT	CPTR_NVHE_EL2_RES1
 #define CPTR_NVHE_EL2_RES0	(GENMASK(63, 32) |	\
 				 GENMASK(29, 21) |	\
 				 GENMASK(19, 14) |	\
@@ -347,8 +346,7 @@
 	ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
 	ECN(BKPT32), ECN(VECTOR32), ECN(BRK64), ECN(ERET)
 
-#define CPACR_EL1_DEFAULT	(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |\
-				 CPACR_EL1_ZEN_EL1EN)
+#define CPACR_EL1_TTA		(1 << 28)
 
 #define kvm_mode_names				\
 	{ PSR_MODE_EL0t,	"EL0t" },	\

arch/arm64/include/asm/kvm_emulate.h

@@ -74,7 +74,7 @@ static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
-	if (is_kernel_in_hyp_mode())
+	if (has_vhe() || has_hvhe())
 		vcpu->arch.hcr_el2 |= HCR_E2H;
 	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) {
 		/* route synchronous external abort exceptions to EL2 */
@@ -570,4 +570,35 @@ static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature)
 	return test_bit(feature, vcpu->arch.features);
 }
 
+static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	if (has_vhe()) {
+		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
+		       CPACR_EL1_ZEN_EL1EN);
+	} else if (has_hvhe()) {
+		val = (CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
+	} else {
+		val = CPTR_NVHE_EL2_RES1;
+
+		if (vcpu_has_sve(vcpu) &&
+		    (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED))
+			val |= CPTR_EL2_TZ;
+		if (cpus_have_final_cap(ARM64_SME))
+			val &= ~CPTR_EL2_TSM;
+	}
+
+	return val;
+}
+
+static __always_inline void kvm_reset_cptr_el2(struct kvm_vcpu *vcpu)
+{
+	u64 val = kvm_get_reset_cptr_el2(vcpu);
+
+	if (has_vhe() || has_hvhe())
+		write_sysreg(val, cpacr_el1);
+	else
+		write_sysreg(val, cptr_el2);
+}
 #endif /* __ARM64_KVM_EMULATE_H__ */

arch/arm64/include/asm/kvm_hyp.h

@@ -16,12 +16,35 @@ DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 DECLARE_PER_CPU(unsigned long, kvm_hyp_vector);
 DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 
+/*
+ * Unified accessors for registers that have a different encoding
+ * between VHE and non-VHE. They must be specified without their "ELx"
+ * encoding, but with the SYS_ prefix, as defined in asm/sysreg.h.
+ */
+
+#if defined(__KVM_VHE_HYPERVISOR__)
+
+#define read_sysreg_el0(r)	read_sysreg_s(r##_EL02)
+#define write_sysreg_el0(v,r)	write_sysreg_s(v, r##_EL02)
+#define read_sysreg_el1(r)	read_sysreg_s(r##_EL12)
+#define write_sysreg_el1(v,r)	write_sysreg_s(v, r##_EL12)
+#define read_sysreg_el2(r)	read_sysreg_s(r##_EL1)
+#define write_sysreg_el2(v,r)	write_sysreg_s(v, r##_EL1)
+
+#else // !__KVM_VHE_HYPERVISOR__
+
+#if defined(__KVM_NVHE_HYPERVISOR__)
+#define VHE_ALT_KEY	ARM64_KVM_HVHE
+#else
+#define VHE_ALT_KEY	ARM64_HAS_VIRT_HOST_EXTN
+#endif
+
 #define read_sysreg_elx(r,nvh,vh)					\
 	({								\
 		u64 reg;						\
-		asm volatile(ALTERNATIVE(__mrs_s("%0", r##nvh),	\
+		asm volatile(ALTERNATIVE(__mrs_s("%0", r##nvh),		\
 					 __mrs_s("%0", r##vh),		\
-					 ARM64_HAS_VIRT_HOST_EXTN)	\
+					 VHE_ALT_KEY)			\
 			     : "=r" (reg));				\
 		reg;							\
 	})
@@ -31,16 +54,10 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 		u64 __val = (u64)(v);					\
 		asm volatile(ALTERNATIVE(__msr_s(r##nvh, "%x0"),	\
 					 __msr_s(r##vh, "%x0"),		\
-					 ARM64_HAS_VIRT_HOST_EXTN)	\
+					 VHE_ALT_KEY)			\
 					 : : "rZ" (__val));		\
 	} while (0)
 
-/*
- * Unified accessors for registers that have a different encoding
- * between VHE and non-VHE. They must be specified without their "ELx"
- * encoding, but with the SYS_ prefix, as defined in asm/sysreg.h.
- */
-
 #define read_sysreg_el0(r)	read_sysreg_elx(r, _EL0, _EL02)
 #define write_sysreg_el0(v,r)	write_sysreg_elx(v, r, _EL0, _EL02)
 #define read_sysreg_el1(r)	read_sysreg_elx(r, _EL1, _EL12)
@@ -48,6 +65,8 @@ DECLARE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params);
 #define read_sysreg_el2(r)	read_sysreg_elx(r, _EL2, _EL1)
 #define write_sysreg_el2(v,r)	write_sysreg_elx(v, r, _EL2, _EL1)
 
+#endif	// __KVM_VHE_HYPERVISOR__
+
 /*
  * Without an __arch_swab32(), we fall back to ___constant_swab32(), but the
  * static inline can allow the compiler to out-of-line this. KVM always wants

arch/arm64/include/asm/kvm_mmu.h

@@ -228,7 +228,8 @@ static inline void __invalidate_icache_guest_page(void *va, size_t size)
 	if (icache_is_aliasing()) {
 		/* any kind of VIPT cache */
 		icache_inval_all_pou();
-	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
+	} else if (read_sysreg(CurrentEL) != CurrentEL_EL1 ||
+		   !icache_is_vpipt()) {
 		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
 		icache_inval_pou((unsigned long)va, (unsigned long)va + size);
 	}

arch/arm64/include/asm/virt.h

@@ -110,8 +110,10 @@ static inline bool is_hyp_mode_mismatched(void)
 	return __boot_cpu_mode[0] != __boot_cpu_mode[1];
 }
 
-static inline bool is_kernel_in_hyp_mode(void)
+static __always_inline bool is_kernel_in_hyp_mode(void)
 {
+	BUILD_BUG_ON(__is_defined(__KVM_NVHE_HYPERVISOR__) ||
+		     __is_defined(__KVM_VHE_HYPERVISOR__));
 	return read_sysreg(CurrentEL) == CurrentEL_EL2;
 }
 
@@ -140,6 +142,14 @@ static __always_inline bool is_protected_kvm_enabled(void)
 		return cpus_have_final_cap(ARM64_KVM_PROTECTED_MODE);
 }
 
+static __always_inline bool has_hvhe(void)
+{
+	if (is_vhe_hyp_code())
+		return false;
+
+	return cpus_have_final_cap(ARM64_KVM_HVHE);
+}
+
 static inline bool is_hyp_nvhe(void)
 {
 	return is_hyp_mode_available() && !is_kernel_in_hyp_mode();

arch/arm64/kernel/cpufeature.c

@@ -664,6 +664,8 @@ struct arm64_ftr_override __ro_after_init id_aa64smfr0_override;
 struct arm64_ftr_override __ro_after_init id_aa64isar1_override;
 struct arm64_ftr_override __ro_after_init id_aa64isar2_override;
 
+struct arm64_ftr_override arm64_sw_feature_override;
+
 static const struct __ftr_reg_entry {
 	u32			sys_id;
 	struct arm64_ftr_reg 	*reg;
@@ -1996,6 +1998,19 @@ static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap,
 	return true;
 }
 
+static bool hvhe_possible(const struct arm64_cpu_capabilities *entry,
+			  int __unused)
+{
+	u64 val;
+
+	val = read_sysreg(id_aa64mmfr1_el1);
+	if (!cpuid_feature_extract_unsigned_field(val, ID_AA64MMFR1_EL1_VH_SHIFT))
+		return false;
+
+	val = arm64_sw_feature_override.val & arm64_sw_feature_override.mask;
+	return cpuid_feature_extract_unsigned_field(val, ARM64_SW_FEATURE_OVERRIDE_HVHE);
+}
+
 #ifdef CONFIG_ARM64_PAN
 static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
 {
@@ -2641,6 +2656,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_enable_dit,
 		ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, DIT, IMP)
 	},
+	{
+		.desc = "VHE for hypervisor only",
+		.capability = ARM64_KVM_HVHE,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = hvhe_possible,
+	},
 	{},
 };
 

arch/arm64/kernel/head.S

@@ -603,6 +603,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el1, x1
 	mov	x2, xzr
 2:
+	__init_el2_nvhe_prepare_eret
+
 	mov	w0, #BOOT_CPU_MODE_EL2
 	orr	x0, x0, x2
 	eret

arch/arm64/kernel/hyp-stub.S

@@ -82,7 +82,15 @@ SYM_CODE_START_LOCAL(__finalise_el2)
 	tbnz	x1, #0, 1f
 
 	// Needs to be VHE capable, obviously
-	check_override id_aa64mmfr1 ID_AA64MMFR1_EL1_VH_SHIFT 2f 1f x1 x2
+	check_override id_aa64mmfr1 ID_AA64MMFR1_EL1_VH_SHIFT 0f 1f x1 x2
+
+0:	// Check whether we only want the hypervisor to run VHE, not the kernel
+	adr_l	x1, arm64_sw_feature_override
+	ldr	x2, [x1, FTR_OVR_VAL_OFFSET]
+	ldr	x1, [x1, FTR_OVR_MASK_OFFSET]
+	and	x2, x2, x1
+	ubfx	x2, x2, #ARM64_SW_FEATURE_OVERRIDE_HVHE, #4
+	cbz	x2, 2f
 
 1:	mov_q	x0, HVC_STUB_ERR
 	eret

arch/arm64/kernel/idreg-override.c

@@ -138,15 +138,22 @@ static const struct ftr_set_desc smfr0 __initconst = {
 	},
 };
 
-extern struct arm64_ftr_override kaslr_feature_override;
+static bool __init hvhe_filter(u64 val)
+{
+	u64 mmfr1 = read_sysreg(id_aa64mmfr1_el1);
+
+	return (val == 1 &&
+		lower_32_bits(__boot_status) == BOOT_CPU_MODE_EL2 &&
+		cpuid_feature_extract_unsigned_field(mmfr1,
+						     ID_AA64MMFR1_EL1_VH_SHIFT));
+}
 
-static const struct ftr_set_desc kaslr __initconst = {
-	.name		= "kaslr",
-#ifdef CONFIG_RANDOMIZE_BASE
-	.override	= &kaslr_feature_override,
-#endif
+static const struct ftr_set_desc sw_features __initconst = {
+	.name		= "arm64_sw",
+	.override	= &arm64_sw_feature_override,
 	.fields		= {
-		FIELD("disabled", 0, NULL),
+		FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL),
+		FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter),
 		{}
 	},
 };
@@ -158,7 +165,7 @@ static const struct ftr_set_desc * const regs[] __initconst = {
 	&isar1,
 	&isar2,
 	&smfr0,
-	&kaslr,
+	&sw_features,
 };
 
 static const struct {
@@ -175,7 +182,7 @@ static const struct {
 	  "id_aa64isar1.api=0 id_aa64isar1.apa=0 "
 	  "id_aa64isar2.gpa3=0 id_aa64isar2.apa3=0"	   },
 	{ "arm64.nomte",		"id_aa64pfr1.mte=0" },
-	{ "nokaslr",			"kaslr.disabled=1" },
+	{ "nokaslr",			"arm64_sw.nokaslr=1" },
 };
 
 static int __init parse_nokaslr(char *unused)

arch/arm64/kernel/kaslr.c

@@ -23,8 +23,6 @@
 u64 __ro_after_init module_alloc_base;
 u16 __initdata memstart_offset_seed;
 
-struct arm64_ftr_override kaslr_feature_override __initdata;
-
 static int __init kaslr_init(void)
 {
 	u64 module_range;
@@ -36,7 +34,9 @@ static int __init kaslr_init(void)
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
 
-	if (kaslr_feature_override.val & kaslr_feature_override.mask & 0xf) {
+	if (cpuid_feature_extract_unsigned_field(arm64_sw_feature_override.val &
+						 arm64_sw_feature_override.mask,
+						 ARM64_SW_FEATURE_OVERRIDE_NOKASLR)) {
 		pr_info("KASLR disabled on command line\n");
 		return 0;
 	}

arch/arm64/kvm/arm.c

@@ -1268,7 +1268,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	}
 
 	vcpu_reset_hcr(vcpu);
-	vcpu->arch.cptr_el2 = CPTR_EL2_DEFAULT;
+	vcpu->arch.cptr_el2 = kvm_get_reset_cptr_el2(vcpu);
 
 	/*
 	 * Handle the "start in power-off" case.
@@ -1694,7 +1694,13 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 
 	params->mair_el2 = read_sysreg(mair_el1);
 
-	tcr = (read_sysreg(tcr_el1) & TCR_EL2_MASK) | TCR_EL2_RES1;
+	tcr = read_sysreg(tcr_el1);
+	if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
+		tcr |= TCR_EPD1_MASK;
+	} else {
+		tcr &= TCR_EL2_MASK;
+		tcr |= TCR_EL2_RES1;
+	}
 	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
 	params->tcr_el2 = tcr;
@@ -1704,6 +1710,8 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 		params->hcr_el2 = HCR_HOST_NVHE_PROTECTED_FLAGS;
 	else
 		params->hcr_el2 = HCR_HOST_NVHE_FLAGS;
+	if (cpus_have_final_cap(ARM64_KVM_HVHE))
+		params->hcr_el2 |= HCR_E2H;
 	params->vttbr = params->vtcr = 0;
 
 	/*

arch/arm64/kvm/fpsimd.c

@@ -180,7 +180,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 
 	/*
 	 * If we have VHE then the Hyp code will reset CPACR_EL1 to
-	 * CPACR_EL1_DEFAULT and we need to reenable SME.
+	 * the default value and we need to reenable SME.
 	 */
 	if (has_vhe() && system_supports_sme()) {
 		/* Also restore EL0 state seen on entry */
@@ -210,7 +210,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 		/*
 		 * The FPSIMD/SVE state in the CPU has not been touched, and we
 		 * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been
-		 * reset to CPACR_EL1_DEFAULT by the Hyp code, disabling SVE
+		 * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE
 		 * for EL0.  To avoid spurious traps, restore the trap state
 		 * seen by kvm_arch_vcpu_load_fp():
 		 */

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -192,7 +192,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Valid trap.  Switch the context: */
 
 	/* First disable enough traps to allow us to update the registers */
-	if (has_vhe()) {
+	if (has_vhe() || has_hvhe()) {
 		reg = CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN;
 		if (sve_guest)
 			reg |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;

arch/arm64/kvm/hyp/nvhe/hyp-init.S

@@ -83,9 +83,6 @@ SYM_CODE_END(__kvm_hyp_init)
  * x0: struct kvm_nvhe_init_params PA
  */
 SYM_CODE_START_LOCAL(___kvm_hyp_init)
-	ldr	x1, [x0, #NVHE_INIT_TPIDR_EL2]
-	msr	tpidr_el2, x1
-
 	ldr	x1, [x0, #NVHE_INIT_STACK_HYP_VA]
 	mov	sp, x1
 
@@ -95,6 +92,22 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
 	ldr	x1, [x0, #NVHE_INIT_HCR_EL2]
 	msr	hcr_el2, x1
 
+	mov	x2, #HCR_E2H
+	and	x2, x1, x2
+	cbz	x2, 1f
+
+	// hVHE: Replay the EL2 setup to account for the E2H bit
+	// TPIDR_EL2 is used to preserve x0 across the macro maze...
+	isb
+	msr	tpidr_el2, x0
+	init_el2_state
+	finalise_el2_state
+	mrs	x0, tpidr_el2
+
+1:
+	ldr	x1, [x0, #NVHE_INIT_TPIDR_EL2]
+	msr	tpidr_el2, x1
+
 	ldr	x1, [x0, #NVHE_INIT_VTTBR]
 	msr	vttbr_el2, x1
 
@@ -184,6 +197,7 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 	/* Initialize EL2 CPU state to sane values. */
 	init_el2_state				// Clobbers x0..x2
 	finalise_el2_state
+	__init_el2_nvhe_prepare_eret
 
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28

arch/arm64/kvm/hyp/nvhe/hyp-main.c

@@ -405,7 +405,11 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
 		handle_host_smc(host_ctxt);
 		break;
 	case ESR_ELx_EC_SVE:
-		sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
+		if (has_hvhe())
+			sysreg_clear_set(cpacr_el1, 0, (CPACR_EL1_ZEN_EL1EN |
+							CPACR_EL1_ZEN_EL0EN));
+		else
+			sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
 		isb();
 		sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
 		break;

arch/arm64/kvm/hyp/nvhe/pkvm.c

@@ -27,6 +27,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
 	u64 hcr_set = HCR_RW;
 	u64 hcr_clear = 0;
 	u64 cptr_set = 0;
+	u64 cptr_clear = 0;
 
 	/* Protected KVM does not support AArch32 guests. */
 	BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0),
@@ -43,6 +44,9 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AdvSIMD),
 				PVM_ID_AA64PFR0_ALLOW));
 
+	if (has_hvhe())
+		hcr_set |= HCR_E2H;
+
 	/* Trap RAS unless all current versions are supported */
 	if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_RAS), feature_ids) <
 	    ID_AA64PFR0_EL1_RAS_V1P1) {
@@ -57,12 +61,17 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
 	}
 
 	/* Trap SVE */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids))
-		cptr_set |= CPTR_EL2_TZ;
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) {
+		if (has_hvhe())
+			cptr_clear |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+		else
+			cptr_set |= CPTR_EL2_TZ;
+	}
 
 	vcpu->arch.hcr_el2 |= hcr_set;
 	vcpu->arch.hcr_el2 &= ~hcr_clear;
 	vcpu->arch.cptr_el2 |= cptr_set;
+	vcpu->arch.cptr_el2 &= ~cptr_clear;
 }
 
 /*
@@ -120,8 +129,12 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
 		mdcr_set |= MDCR_EL2_TTRF;
 
 	/* Trap Trace */
-	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceVer), feature_ids))
-		cptr_set |= CPTR_EL2_TTA;
+	if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceVer), feature_ids)) {
+		if (has_hvhe())
+			cptr_set |= CPACR_EL1_TTA;
+		else
+			cptr_set |= CPTR_EL2_TTA;
+	}
 
 	vcpu->arch.mdcr_el2 |= mdcr_set;
 	vcpu->arch.mdcr_el2 &= ~mdcr_clear;
@@ -176,8 +189,10 @@ static void pvm_init_trap_regs(struct kvm_vcpu *vcpu)
 	/* Clear res0 and set res1 bits to trap potential new features. */
 	vcpu->arch.hcr_el2 &= ~(HCR_RES0);
 	vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0);
-	vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1;
-	vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0);
+	if (!has_hvhe()) {
+		vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1;
+		vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0);
+	}
 }
 
 /*

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -44,13 +44,24 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	__activate_traps_common(vcpu);
 
 	val = vcpu->arch.cptr_el2;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TAM;
+	val |= CPTR_EL2_TAM;	/* Same bit irrespective of E2H */
+	val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA;
+	if (cpus_have_final_cap(ARM64_SME)) {
+		if (has_hvhe())
+			val &= ~(CPACR_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN);
+		else
+			val |= CPTR_EL2_TSM;
+	}
+
 	if (!guest_owns_fp_regs(vcpu)) {
-		val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
+		if (has_hvhe())
+			val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN |
+				 CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN);
+		else
+			val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
+
 		__activate_traps_fpsimd32(vcpu);
 	}
-	if (cpus_have_final_cap(ARM64_SME))
-		val |= CPTR_EL2_TSM;
 
 	write_sysreg(val, cptr_el2);
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
@@ -73,7 +84,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 static void __deactivate_traps(struct kvm_vcpu *vcpu)
 {
 	extern char __kvm_hyp_host_vector[];
-	u64 cptr;
 
 	___deactivate_traps(vcpu);
 
@@ -98,13 +108,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
 
-	cptr = CPTR_EL2_DEFAULT;
-	if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED))
-		cptr |= CPTR_EL2_TZ;
-	if (cpus_have_final_cap(ARM64_SME))
-		cptr &= ~CPTR_EL2_TSM;
-
-	write_sysreg(cptr, cptr_el2);
+	kvm_reset_cptr_el2(vcpu);
 	write_sysreg(__kvm_hyp_host_vector, vbar_el2);
 }
 

arch/arm64/kvm/hyp/nvhe/timer-sr.c

@@ -17,21 +17,24 @@ void __kvm_timer_set_cntvoff(u64 cntvoff)
 }
 
 /*
- * Should only be called on non-VHE systems.
+ * Should only be called on non-VHE or hVHE setups.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
 void __timer_disable_traps(struct kvm_vcpu *vcpu)
 {
-	u64 val;
+	u64 val, shift = 0;
+
+	if (has_hvhe())
+		shift = 10;
 
 	/* Allow physical timer/counter access for the host */
 	val = read_sysreg(cnthctl_el2);
-	val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN;
+	val |= (CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN) << shift;
 	write_sysreg(val, cnthctl_el2);
 }
 
 /*
- * Should only be called on non-VHE systems.
+ * Should only be called on non-VHE or hVHE setups.
  * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe().
  */
 void __timer_enable_traps(struct kvm_vcpu *vcpu)
@@ -50,5 +53,10 @@ void __timer_enable_traps(struct kvm_vcpu *vcpu)
 	else
 		clr |= CNTHCTL_EL1PCTEN;
 
+	if (has_hvhe()) {
+		clr <<= 10;
+		set <<= 10;
+	}
+
 	sysreg_clear_set(cnthctl_el2, clr, set);
 }

arch/arm64/kvm/hyp/pgtable.c

@@ -21,8 +21,10 @@
 
 #define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX	GENMASK(4, 2)
 #define KVM_PTE_LEAF_ATTR_LO_S1_AP	GENMASK(7, 6)
-#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO	3
-#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW	1
+#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RO		\
+	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 2 : 3; })
+#define KVM_PTE_LEAF_ATTR_LO_S1_AP_RW		\
+	({ cpus_have_final_cap(ARM64_KVM_HVHE) ? 0 : 1; })
 #define KVM_PTE_LEAF_ATTR_LO_S1_SH	GENMASK(9, 8)
 #define KVM_PTE_LEAF_ATTR_LO_S1_SH_IS	3
 #define KVM_PTE_LEAF_ATTR_LO_S1_AF	BIT(10)

arch/arm64/kvm/hyp/vhe/switch.c

@@ -84,7 +84,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	 */
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
-	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
+	kvm_reset_cptr_el2(vcpu);
 
 	if (!arm64_kernel_unmapped_at_el0())
 		host_vectors = __this_cpu_read(this_cpu_vector);

arch/arm64/kvm/sys_regs.c

@@ -2180,7 +2180,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	EL2_REG(ACTLR_EL2, access_rw, reset_val, 0),
 	EL2_REG(HCR_EL2, access_rw, reset_val, 0),
 	EL2_REG(MDCR_EL2, access_rw, reset_val, 0),
-	EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_EL2_DEFAULT ),
+	EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
 	EL2_REG(HSTR_EL2, access_rw, reset_val, 0),
 	EL2_REG(HACR_EL2, access_rw, reset_val, 0),
 

arch/arm64/tools/cpucaps

@@ -47,6 +47,7 @@ HAS_TLB_RANGE
 HAS_VIRT_HOST_EXTN
 HAS_WFXT
 HW_DBM
+KVM_HVHE
 KVM_PROTECTED_MODE
 MISMATCHED_CACHE_TYPE
 MTE