Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM64:

   - Eager page splitting optimization for dirty logging, optionally
     allowing for a VM to avoid the cost of hugepage splitting in the
     stage-2 fault path.

   - Arm FF-A proxy for pKVM, allowing a pKVM host to safely interact
     with services that live in the Secure world. pKVM intervenes on
     FF-A calls to guarantee the host doesn't misuse memory donated to
     the hyp or a pKVM guest.

   - Support for running the split hypervisor with VHE enabled, known as
     'hVHE' mode. This is extremely useful for testing the split
     hypervisor on VHE-only systems, and paves the way for new use cases
     that depend on having two TTBRs available at EL2.

   - Generalized framework for configurable ID registers from userspace.
     KVM/arm64 currently prevents arbitrary CPU feature set
     configuration from userspace, but the intent is to relax this
     limitation and allow userspace to select a feature set consistent
     with the CPU.

   - Enable the use of Branch Target Identification (FEAT_BTI) in the
     hypervisor.

   - Use a separate set of pointer authentication keys for the
     hypervisor when running in protected mode, as the host is untrusted
     at runtime.

   - Ensure timer IRQs are consistently released in the init failure
     paths.

   - Avoid trapping CTR_EL0 on systems with Enhanced Virtualization
     Traps (FEAT_EVT), as it is a register commonly read from userspace.

   - Erratum workaround for the upcoming AmpereOne part, which has
     broken hardware A/D state management.

  RISC-V:

   - Redirect AMO load/store misaligned traps to KVM guest

   - Trap-n-emulate AIA in-kernel irqchip for KVM guest

   - Svnapot support for KVM Guest

  s390:

   - New uvdevice secret API

   - CMM selftest and fixes

   - fix racy access to target CPU for diag 9c

  x86:

   - Fix missing/incorrect #GP checks on ENCLS

   - Use standard mmu_notifier hooks for handling APIC access page

   - Drop now unnecessary TR/TSS load after VM-Exit on AMD

   - Print more descriptive information about the status of SEV and
     SEV-ES during module load

   - Add a test for splitting and reconstituting hugepages during and
     after dirty logging

   - Add support for CPU pinning in demand paging test

   - Add support for AMD PerfMonV2, with a variety of cleanups and minor
     fixes included along the way

   - Add a "nx_huge_pages=never" option to effectively avoid creating NX
     hugepage recovery threads (because nx_huge_pages=off can be toggled
     at runtime)

   - Move handling of PAT out of MTRR code and dedup SVM+VMX code

   - Fix output of PIC poll command emulation when there's an interrupt

   - Add a maintainer's handbook to document KVM x86 processes,
     preferred coding style, testing expectations, etc.

   - Misc cleanups, fixes and comments

  Generic:

   - Miscellaneous bugfixes and cleanups

  Selftests:

   - Generate dependency files so that partial rebuilds work as
     expected"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (153 commits)
  Documentation/process: Add a maintainer handbook for KVM x86
  Documentation/process: Add a label for the tip tree handbook's coding style
  KVM: arm64: Fix misuse of KVM_ARM_VCPU_POWER_OFF bit index
  RISC-V: KVM: Remove unneeded semicolon
  RISC-V: KVM: Allow Svnapot extension for Guest/VM
  riscv: kvm: define vcpu_sbi_ext_pmu in header
  RISC-V: KVM: Expose IMSIC registers as attributes of AIA irqchip
  RISC-V: KVM: Add in-kernel virtualization of AIA IMSIC
  RISC-V: KVM: Expose APLIC registers as attributes of AIA irqchip
  RISC-V: KVM: Add in-kernel emulation of AIA APLIC
  RISC-V: KVM: Implement device interface for AIA irqchip
  RISC-V: KVM: Skeletal in-kernel AIA irqchip support
  RISC-V: KVM: Set kvm_riscv_aia_nr_hgei to zero
  RISC-V: KVM: Add APLIC related defines
  RISC-V: KVM: Add IMSIC related defines
  RISC-V: KVM: Implement guest external interrupt line management
  KVM: x86: Remove PRIx* definitions as they are solely for user space
  s390/uv: Update query for secret-UVCs
  s390/uv: replace scnprintf with sysfs_emit
  s390/uvdevice: Add 'Lock Secret Store' UVC
  ...

12 files changed, 256 insertions, 49 deletions

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 7a95c324e52a..96e50227f940 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/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>
@@ -905,6 +908,7 @@ static inline unsigned int get_vmid_bits(u64 mmfr1)
 	return 8;
 }
 
+s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur);
 struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id);
 
 extern struct arm64_ftr_override id_aa64mmfr1_override;
@@ -915,6 +919,8 @@ 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);
 
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index f4c3d30bf746..8e5ffb58f83e 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -43,6 +43,11 @@
  */
 .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
@@ -133,8 +138,15 @@
 .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
 
@@ -210,9 +222,8 @@
 	__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__
@@ -258,7 +269,17 @@
 
 .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
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index c6e12e8f2751..58e5eb27da68 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -19,6 +19,7 @@
 #define HCR_ATA_SHIFT	56
 #define HCR_ATA		(UL(1) << HCR_ATA_SHIFT)
 #define HCR_AMVOFFEN	(UL(1) << 51)
+#define HCR_TID4	(UL(1) << 49)
 #define HCR_FIEN	(UL(1) << 47)
 #define HCR_FWB		(UL(1) << 46)
 #define HCR_API		(UL(1) << 41)
@@ -87,7 +88,7 @@
 #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
 			 HCR_BSU_IS | HCR_FB | HCR_TACR | \
 			 HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
-			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID2)
+			 HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3)
 #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
 #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA)
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
@@ -289,7 +290,6 @@
 #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) |	\
@@ -351,8 +351,7 @@
 	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" },	\
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 86042afa86c3..7d170aaa2db4 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -68,6 +68,7 @@ enum __kvm_host_smccc_func {
 	__KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
+	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa_nsh,
 	__KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
 	__KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
 	__KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
@@ -225,6 +226,9 @@ extern void __kvm_flush_vm_context(void);
 extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
 extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
 				     int level);
+extern void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
+					 phys_addr_t ipa,
+					 int level);
 extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
 
 extern void __kvm_timer_set_cntvoff(u64 cntvoff);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index b31b32ecbe2d..efc0b45d79c3 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -62,19 +62,14 @@ static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 #else
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
-	struct kvm *kvm = vcpu->kvm;
-
-	WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED,
-			       &kvm->arch.flags));
-
-	return test_bit(KVM_ARCH_FLAG_EL1_32BIT, &kvm->arch.flags);
+	return test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features);
 }
 #endif
 
 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 */
@@ -95,6 +90,12 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 		vcpu->arch.hcr_el2 |= HCR_TVM;
 	}
 
+	if (cpus_have_final_cap(ARM64_HAS_EVT) &&
+	    !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE))
+		vcpu->arch.hcr_el2 |= HCR_TID4;
+	else
+		vcpu->arch.hcr_el2 |= HCR_TID2;
+
 	if (vcpu_el1_is_32bit(vcpu))
 		vcpu->arch.hcr_el2 &= ~HCR_RW;
 
@@ -570,4 +571,35 @@ 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__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d48609d95423..8b6096753740 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -39,6 +39,7 @@
 #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
 
 #define KVM_VCPU_MAX_FEATURES 7
+#define KVM_VCPU_VALID_FEATURES	(BIT(KVM_VCPU_MAX_FEATURES) - 1)
 
 #define KVM_REQ_SLEEP \
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
@@ -159,6 +160,21 @@ struct kvm_s2_mmu {
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
+#define KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT 0
+	/*
+	 * Memory cache used to split
+	 * KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE worth of huge pages. It
+	 * is used to allocate stage2 page tables while splitting huge
+	 * pages. The choice of KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE
+	 * influences both the capacity of the split page cache, and
+	 * how often KVM reschedules. Be wary of raising CHUNK_SIZE
+	 * too high.
+	 *
+	 * Protected by kvm->slots_lock.
+	 */
+	struct kvm_mmu_memory_cache split_page_cache;
+	uint64_t split_page_chunk_size;
+
 	struct kvm_arch *arch;
 };
 
@@ -214,25 +230,23 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_MTE_ENABLED			1
 	/* At least one vCPU has ran in the VM */
 #define KVM_ARCH_FLAG_HAS_RAN_ONCE			2
-	/*
-	 * The following two bits are used to indicate the guest's EL1
-	 * register width configuration. A value of KVM_ARCH_FLAG_EL1_32BIT
-	 * bit is valid only when KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED is set.
-	 * Otherwise, the guest's EL1 register width has not yet been
-	 * determined yet.
-	 */
-#define KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED		3
-#define KVM_ARCH_FLAG_EL1_32BIT				4
+	/* The vCPU feature set for the VM is configured */
+#define KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED		3
 	/* PSCI SYSTEM_SUSPEND enabled for the guest */
-#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED		5
+#define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED		4
 	/* VM counter offset */
-#define KVM_ARCH_FLAG_VM_COUNTER_OFFSET			6
+#define KVM_ARCH_FLAG_VM_COUNTER_OFFSET			5
 	/* Timer PPIs made immutable */
-#define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		7
+#define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		6
 	/* SMCCC filter initialized for the VM */
-#define KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED		8
+#define KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED		7
+	/* Initial ID reg values loaded */
+#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		8
 	unsigned long flags;
 
+	/* VM-wide vCPU feature set */
+	DECLARE_BITMAP(vcpu_features, KVM_VCPU_MAX_FEATURES);
+
 	/*
 	 * VM-wide PMU filter, implemented as a bitmap and big enough for
 	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).
@@ -242,18 +256,24 @@ struct kvm_arch {
 
 	cpumask_var_t supported_cpus;
 
-	u8 pfr0_csv2;
-	u8 pfr0_csv3;
-	struct {
-		u8 imp:4;
-		u8 unimp:4;
-	} dfr0_pmuver;
-
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;
 	struct maple_tree smccc_filter;
 
 	/*
+	 * Emulated CPU ID registers per VM
+	 * (Op0, Op1, CRn, CRm, Op2) of the ID registers to be saved in it
+	 * is (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8.
+	 *
+	 * These emulated idregs are VM-wide, but accessed from the context of a vCPU.
+	 * Atomic access to multiple idregs are guarded by kvm_arch.config_lock.
+	 */
+#define IDREG_IDX(id)		(((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id))
+#define IDREG(kvm, id)		((kvm)->arch.id_regs[IDREG_IDX(id)])
+#define KVM_ARM_ID_REG_NUM	(IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1)
+	u64 id_regs[KVM_ARM_ID_REG_NUM];
+
+	/*
 	 * For an untrusted host VM, 'pkvm.handle' is used to lookup
 	 * the associated pKVM instance in the hypervisor.
 	 */
@@ -410,6 +430,7 @@ struct kvm_host_data {
 struct kvm_host_psci_config {
 	/* PSCI version used by host. */
 	u32 version;
+	u32 smccc_version;
 
 	/* Function IDs used by host if version is v0.1. */
 	struct psci_0_1_function_ids function_ids_0_1;
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index bdd9cf546d95..b7238c72a04c 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/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
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 27e63c111f78..0e1e1ab17b4d 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -172,6 +172,7 @@ void __init free_hyp_pgds(void);
 
 void stage2_unmap_vm(struct kvm *kvm);
 int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type);
+void kvm_uninit_stage2_mmu(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
@@ -227,7 +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);
 	}
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 93bd0975b15f..8294a9a7e566 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -92,6 +92,24 @@ static inline bool kvm_level_supports_block_mapping(u32 level)
 	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
 }
 
+static inline u32 kvm_supported_block_sizes(void)
+{
+	u32 level = KVM_PGTABLE_MIN_BLOCK_LEVEL;
+	u32 r = 0;
+
+	for (; level < KVM_PGTABLE_MAX_LEVELS; level++)
+		r |= BIT(kvm_granule_shift(level));
+
+	return r;
+}
+
+static inline bool kvm_is_block_size_supported(u64 size)
+{
+	bool is_power_of_two = IS_ALIGNED(size, size);
+
+	return is_power_of_two && (size & kvm_supported_block_sizes());
+}
+
 /**
  * struct kvm_pgtable_mm_ops - Memory management callbacks.
  * @zalloc_page:		Allocate a single zeroed memory page.
@@ -104,7 +122,7 @@ static inline bool kvm_level_supports_block_mapping(u32 level)
  *				allocation is physically contiguous.
  * @free_pages_exact:		Free an exact number of memory pages previously
  *				allocated by zalloc_pages_exact.
- * @free_removed_table:		Free a removed paging structure by unlinking and
+ * @free_unlinked_table:	Free an unlinked paging structure by unlinking and
  *				dropping references.
  * @get_page:			Increment the refcount on a page.
  * @put_page:			Decrement the refcount on a page. When the
@@ -124,7 +142,7 @@ struct kvm_pgtable_mm_ops {
 	void*		(*zalloc_page)(void *arg);
 	void*		(*zalloc_pages_exact)(size_t size);
 	void		(*free_pages_exact)(void *addr, size_t size);
-	void		(*free_removed_table)(void *addr, u32 level);
+	void		(*free_unlinked_table)(void *addr, u32 level);
 	void		(*get_page)(void *addr);
 	void		(*put_page)(void *addr);
 	int		(*page_count)(void *addr);
@@ -195,6 +213,12 @@ typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
  *					with other software walkers.
  * @KVM_PGTABLE_WALK_HANDLE_FAULT:	Indicates the page-table walk was
  *					invoked from a fault handler.
+ * @KVM_PGTABLE_WALK_SKIP_BBM_TLBI:	Visit and update table entries
+ *					without Break-before-make's
+ *					TLB invalidation.
+ * @KVM_PGTABLE_WALK_SKIP_CMO:		Visit and update table entries
+ *					without Cache maintenance
+ *					operations required.
  */
 enum kvm_pgtable_walk_flags {
 	KVM_PGTABLE_WALK_LEAF			= BIT(0),
@@ -202,6 +226,8 @@ enum kvm_pgtable_walk_flags {
 	KVM_PGTABLE_WALK_TABLE_POST		= BIT(2),
 	KVM_PGTABLE_WALK_SHARED			= BIT(3),
 	KVM_PGTABLE_WALK_HANDLE_FAULT		= BIT(4),
+	KVM_PGTABLE_WALK_SKIP_BBM_TLBI		= BIT(5),
+	KVM_PGTABLE_WALK_SKIP_CMO		= BIT(6),
 };
 
 struct kvm_pgtable_visit_ctx {
@@ -441,7 +467,7 @@ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
 
 /**
- * kvm_pgtable_stage2_free_removed() - Free a removed stage-2 paging structure.
+ * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure.
  * @mm_ops:	Memory management callbacks.
  * @pgtable:	Unlinked stage-2 paging structure to be freed.
  * @level:	Level of the stage-2 paging structure to be freed.
@@ -449,7 +475,33 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
  * The page-table is assumed to be unreachable by any hardware walkers prior to
  * freeing and therefore no TLB invalidation is performed.
  */
-void kvm_pgtable_stage2_free_removed(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, u32 level);
+
+/**
+ * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @phys:	Physical address of the memory to map.
+ * @level:	Starting level of the stage-2 paging structure to be created.
+ * @prot:	Permissions and attributes for the mapping.
+ * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
+ *		page-table pages.
+ * @force_pte:  Force mappings to PAGE_SIZE granularity.
+ *
+ * Returns an unlinked page-table tree.  This new page-table tree is
+ * not reachable (i.e., it is unlinked) from the root pgd and it's
+ * therefore unreachableby the hardware page-table walker. No TLB
+ * invalidation or CMOs are performed.
+ *
+ * If device attributes are not explicitly requested in @prot, then the
+ * mapping will be normal, cacheable.
+ *
+ * Return: The fully populated (unlinked) stage-2 paging structure, or
+ * an ERR_PTR(error) on failure.
+ */
+kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt,
+					      u64 phys, u32 level,
+					      enum kvm_pgtable_prot prot,
+					      void *mc, bool force_pte);
 
 /**
  * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table.
@@ -621,6 +673,25 @@ bool kvm_pgtable_stage2_is_young(struct kvm_pgtable *pgt, u64 addr);
 int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size);
 
 /**
+ * kvm_pgtable_stage2_split() - Split a range of huge pages into leaf PTEs pointing
+ *				to PAGE_SIZE guest pages.
+ * @pgt:	 Page-table structure initialised by kvm_pgtable_stage2_init().
+ * @addr:	 Intermediate physical address from which to split.
+ * @size:	 Size of the range.
+ * @mc:		 Cache of pre-allocated and zeroed memory from which to allocate
+ *		 page-table pages.
+ *
+ * The function tries to split any level 1 or 2 entry that overlaps
+ * with the input range (given by @addr and @size).
+ *
+ * Return: 0 on success, negative error code on failure. Note that
+ * kvm_pgtable_stage2_split() is best effort: it tries to break as many
+ * blocks in the input range as allowed by @mc_capacity.
+ */
+int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size,
+			     struct kvm_mmu_memory_cache *mc);
+
+/**
  * kvm_pgtable_walk() - Walk a page-table.
  * @pgt:	Page-table structure initialised by kvm_pgtable_*_init().
  * @addr:	Input address for the start of the walk.
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index 01129b0d4c68..e46250a02017 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -6,7 +6,9 @@
 #ifndef __ARM64_KVM_PKVM_H__
 #define __ARM64_KVM_PKVM_H__
 
+#include <linux/arm_ffa.h>
 #include <linux/memblock.h>
+#include <linux/scatterlist.h>
 #include <asm/kvm_pgtable.h>
 
 /* Maximum number of VMs that can co-exist under pKVM. */
@@ -106,4 +108,23 @@ static inline unsigned long host_s2_pgtable_pages(void)
 	return res;
 }
 
+#define KVM_FFA_MBOX_NR_PAGES	1
+
+static inline unsigned long hyp_ffa_proxy_pages(void)
+{
+	size_t desc_max;
+
+	/*
+	 * The hypervisor FFA proxy needs enough memory to buffer a fragmented
+	 * descriptor returned from EL3 in response to a RETRIEVE_REQ call.
+	 */
+	desc_max = sizeof(struct ffa_mem_region) +
+		   sizeof(struct ffa_mem_region_attributes) +
+		   sizeof(struct ffa_composite_mem_region) +
+		   SG_MAX_SEGMENTS * sizeof(struct ffa_mem_region_addr_range);
+
+	/* Plus a page each for the hypervisor's RX and TX mailboxes. */
+	return (2 * KVM_FFA_MBOX_NR_PAGES) + DIV_ROUND_UP(desc_max, PAGE_SIZE);
+}
+
 #endif	/* __ARM64_KVM_PKVM_H__ */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 7a1e62631814..b481935e9314 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -510,6 +510,7 @@
 			 (BIT(18)) | (BIT(22)) | (BIT(23)) | (BIT(28)) | \
 			 (BIT(29)))
 
+#define SCTLR_EL2_BT	(BIT(36))
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL2		SCTLR_ELx_EE
 #else
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 4eb601e7de50..5227db7640c8 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/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();