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

Pull kvm updates from Paolo Bonzini:
 "ARM:

   - Initial infrastructure for shadow stage-2 MMUs, as part of nested
     virtualization enablement

   - Support for userspace changes to the guest CTR_EL0 value, enabling
     (in part) migration of VMs between heterogenous hardware

   - Fixes + improvements to pKVM's FF-A proxy, adding support for v1.1
     of the protocol

   - FPSIMD/SVE support for nested, including merged trap configuration
     and exception routing

   - New command-line parameter to control the WFx trap behavior under
     KVM

   - Introduce kCFI hardening in the EL2 hypervisor

   - Fixes + cleanups for handling presence/absence of FEAT_TCRX

   - Miscellaneous fixes + documentation updates

  LoongArch:

   - Add paravirt steal time support

   - Add support for KVM_DIRTY_LOG_INITIALLY_SET

   - Add perf kvm-stat support for loongarch

  RISC-V:

   - Redirect AMO load/store access fault traps to guest

   - perf kvm stat support

   - Use guest files for IMSIC virtualization, when available

  s390:

   - Assortment of tiny fixes which are not time critical

  x86:

   - Fixes for Xen emulation

   - Add a global struct to consolidate tracking of host values, e.g.
     EFER

   - Add KVM_CAP_X86_APIC_BUS_CYCLES_NS to allow configuring the
     effective APIC bus frequency, because TDX

   - Print the name of the APICv/AVIC inhibits in the relevant
     tracepoint

   - Clean up KVM's handling of vendor specific emulation to
     consistently act on "compatible with Intel/AMD", versus checking
     for a specific vendor

   - Drop MTRR virtualization, and instead always honor guest PAT on
     CPUs that support self-snoop

   - Update to the newfangled Intel CPU FMS infrastructure

   - Don't advertise IA32_PERF_GLOBAL_OVF_CTRL as an MSR-to-be-saved, as
     it reads '0' and writes from userspace are ignored

   - Misc cleanups

  x86 - MMU:

   - Small cleanups, renames and refactoring extracted from the upcoming
     Intel TDX support

   - Don't allocate kvm_mmu_page.shadowed_translation for shadow pages
     that can't hold leafs SPTEs

   - Unconditionally drop mmu_lock when allocating TDP MMU page tables
     for eager page splitting, to avoid stalling vCPUs when splitting
     huge pages

   - Bug the VM instead of simply warning if KVM tries to split a SPTE
     that is non-present or not-huge. KVM is guaranteed to end up in a
     broken state because the callers fully expect a valid SPTE, it's
     all but dangerous to let more MMU changes happen afterwards

  x86 - AMD:

   - Make per-CPU save_area allocations NUMA-aware

   - Force sev_es_host_save_area() to be inlined to avoid calling into
     an instrumentable function from noinstr code

   - Base support for running SEV-SNP guests. API-wise, this includes a
     new KVM_X86_SNP_VM type, encrypting/measure the initial image into
     guest memory, and finalizing it before launching it. Internally,
     there are some gmem/mmu hooks needed to prepare gmem-allocated
     pages before mapping them into guest private memory ranges

     This includes basic support for attestation guest requests, enough
     to say that KVM supports the GHCB 2.0 specification

     There is no support yet for loading into the firmware those signing
     keys to be used for attestation requests, and therefore no need yet
     for the host to provide certificate data for those keys.

     To support fetching certificate data from userspace, a new KVM exit
     type will be needed to handle fetching the certificate from
     userspace.

     An attempt to define a new KVM_EXIT_COCO / KVM_EXIT_COCO_REQ_CERTS
     exit type to handle this was introduced in v1 of this patchset, but
     is still being discussed by community, so for now this patchset
     only implements a stub version of SNP Extended Guest Requests that
     does not provide certificate data

  x86 - Intel:

   - Remove an unnecessary EPT TLB flush when enabling hardware

   - Fix a series of bugs that cause KVM to fail to detect nested
     pending posted interrupts as valid wake eents for a vCPU executing
     HLT in L2 (with HLT-exiting disable by L1)

   - KVM: x86: Suppress MMIO that is triggered during task switch
     emulation

     Explicitly suppress userspace emulated MMIO exits that are
     triggered when emulating a task switch as KVM doesn't support
     userspace MMIO during complex (multi-step) emulation

     Silently ignoring the exit request can result in the
     WARN_ON_ONCE(vcpu->mmio_needed) firing if KVM exits to userspace
     for some other reason prior to purging mmio_needed

     See commit 0dc902267cb3 ("KVM: x86: Suppress pending MMIO write
     exits if emulator detects exception") for more details on KVM's
     limitations with respect to emulated MMIO during complex emulator
     flows

  Generic:

   - Rename the AS_UNMOVABLE flag that was introduced for KVM to
     AS_INACCESSIBLE, because the special casing needed by these pages
     is not due to just unmovability (and in fact they are only
     unmovable because the CPU cannot access them)

   - New ioctl to populate the KVM page tables in advance, which is
     useful to mitigate KVM page faults during guest boot or after live
     migration. The code will also be used by TDX, but (probably) not
     through the ioctl

   - Enable halt poll shrinking by default, as Intel found it to be a
     clear win

   - Setup empty IRQ routing when creating a VM to avoid having to
     synchronize SRCU when creating a split IRQCHIP on x86

   - Rework the sched_in/out() paths to replace kvm_arch_sched_in() with
     a flag that arch code can use for hooking both sched_in() and
     sched_out()

   - Take the vCPU @id as an "unsigned long" instead of "u32" to avoid
     truncating a bogus value from userspace, e.g. to help userspace
     detect bugs

   - Mark a vCPU as preempted if and only if it's scheduled out while in
     the KVM_RUN loop, e.g. to avoid marking it preempted and thus
     writing guest memory when retrieving guest state during live
     migration blackout

  Selftests:

   - Remove dead code in the memslot modification stress test

   - Treat "branch instructions retired" as supported on all AMD Family
     17h+ CPUs

   - Print the guest pseudo-RNG seed only when it changes, to avoid
     spamming the log for tests that create lots of VMs

   - Make the PMU counters test less flaky when counting LLC cache
     misses by doing CLFLUSH{OPT} in every loop iteration"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  crypto: ccp: Add the SNP_VLEK_LOAD command
  KVM: x86/pmu: Add kvm_pmu_call() to simplify static calls of kvm_pmu_ops
  KVM: x86: Introduce kvm_x86_call() to simplify static calls of kvm_x86_ops
  KVM: x86: Replace static_call_cond() with static_call()
  KVM: SEV: Provide support for SNP_EXTENDED_GUEST_REQUEST NAE event
  x86/sev: Move sev_guest.h into common SEV header
  KVM: SEV: Provide support for SNP_GUEST_REQUEST NAE event
  KVM: x86: Suppress MMIO that is triggered during task switch emulation
  KVM: x86/mmu: Clean up make_huge_page_split_spte() definition and intro
  KVM: x86/mmu: Bug the VM if KVM tries to split a !hugepage SPTE
  KVM: selftests: x86: Add test for KVM_PRE_FAULT_MEMORY
  KVM: x86: Implement kvm_arch_vcpu_pre_fault_memory()
  KVM: x86/mmu: Make kvm_mmu_do_page_fault() return mapped level
  KVM: x86/mmu: Account pf_{fixed,emulate,spurious} in callers of "do page fault"
  KVM: x86/mmu: Bump pf_taken stat only in the "real" page fault handler
  KVM: Add KVM_PRE_FAULT_MEMORY vcpu ioctl to pre-populate guest memory
  KVM: Document KVM_PRE_FAULT_MEMORY ioctl
  mm, virt: merge AS_UNMOVABLE and AS_INACCESSIBLE
  perf kvm: Add kvm-stat for loongarch64
  LoongArch: KVM: Add PV steal time support in guest side
  ...

12 files changed, 559 insertions, 96 deletions

diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index f3aa7738b477..4433a234aa9b 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -83,6 +83,14 @@ alternative_else_nop_endif
 	eret
 	sb
 
+SYM_INNER_LABEL(__guest_exit_restore_elr_and_panic, SYM_L_GLOBAL)
+	// x2-x29,lr: vcpu regs
+	// vcpu x0-x1 on the stack
+
+	adr_this_cpu x0, kvm_hyp_ctxt, x1
+	ldr	x0, [x0, #CPU_ELR_EL2]
+	msr	elr_el2, x0
+
 SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL)
 	// x2-x29,lr: vcpu regs
 	// vcpu x0-x1 on the stack
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 0c4de44534b7..f59ccfe11ab9 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -314,11 +314,24 @@ static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * The vCPU's saved SVE state layout always matches the max VL of the
+	 * vCPU. Start off with the max VL so we can load the SVE state.
+	 */
 	sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
 	__sve_restore_state(vcpu_sve_pffr(vcpu),
 			    &vcpu->arch.ctxt.fp_regs.fpsr,
 			    true);
-	write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
+
+	/*
+	 * The effective VL for a VM could differ from the max VL when running a
+	 * nested guest, as the guest hypervisor could select a smaller VL. Slap
+	 * that into hardware before wrapping up.
+	 */
+	if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
+		sve_cond_update_zcr_vq(__vcpu_sys_reg(vcpu, ZCR_EL2), SYS_ZCR_EL2);
+
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR);
 }
 
 static inline void __hyp_sve_save_host(void)
@@ -354,10 +367,19 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Only handle traps the vCPU can support here: */
 	switch (esr_ec) {
 	case ESR_ELx_EC_FP_ASIMD:
+		/* Forward traps to the guest hypervisor as required */
+		if (guest_hyp_fpsimd_traps_enabled(vcpu))
+			return false;
 		break;
+	case ESR_ELx_EC_SYS64:
+		if (WARN_ON_ONCE(!is_hyp_ctxt(vcpu)))
+			return false;
+		fallthrough;
 	case ESR_ELx_EC_SVE:
 		if (!sve_guest)
 			return false;
+		if (guest_hyp_sve_traps_enabled(vcpu))
+			return false;
 		break;
 	default:
 		return false;
@@ -693,7 +715,7 @@ guest:
 
 static inline void __kvm_unexpected_el2_exception(void)
 {
-	extern char __guest_exit_panic[];
+	extern char __guest_exit_restore_elr_and_panic[];
 	unsigned long addr, fixup;
 	struct kvm_exception_table_entry *entry, *end;
 	unsigned long elr_el2 = read_sysreg(elr_el2);
@@ -715,7 +737,8 @@ static inline void __kvm_unexpected_el2_exception(void)
 	}
 
 	/* Trigger a panic after restoring the hyp context. */
-	write_sysreg(__guest_exit_panic, elr_el2);
+	this_cpu_ptr(&kvm_hyp_ctxt)->sys_regs[ELR_EL2] = elr_el2;
+	write_sysreg(__guest_exit_restore_elr_and_panic, elr_el2);
 }
 
 #endif /* __ARM64_KVM_HYP_SWITCH_H__ */
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index 4be6a7fa0070..4c0fdabaf8ae 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -55,6 +55,17 @@ static inline bool ctxt_has_s1pie(struct kvm_cpu_context *ctxt)
 	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, S1PIE, IMP);
 }
 
+static inline bool ctxt_has_tcrx(struct kvm_cpu_context *ctxt)
+{
+	struct kvm_vcpu *vcpu;
+
+	if (!cpus_have_final_cap(ARM64_HAS_TCR2))
+		return false;
+
+	vcpu = ctxt_to_vcpu(ctxt);
+	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64MMFR3_EL1, TCRX, IMP);
+}
+
 static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 {
 	ctxt_sys_reg(ctxt, SCTLR_EL1)	= read_sysreg_el1(SYS_SCTLR);
@@ -62,8 +73,14 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, TTBR0_EL1)	= read_sysreg_el1(SYS_TTBR0);
 	ctxt_sys_reg(ctxt, TTBR1_EL1)	= read_sysreg_el1(SYS_TTBR1);
 	ctxt_sys_reg(ctxt, TCR_EL1)	= read_sysreg_el1(SYS_TCR);
-	if (cpus_have_final_cap(ARM64_HAS_TCR2))
+	if (ctxt_has_tcrx(ctxt)) {
 		ctxt_sys_reg(ctxt, TCR2_EL1)	= read_sysreg_el1(SYS_TCR2);
+
+		if (ctxt_has_s1pie(ctxt)) {
+			ctxt_sys_reg(ctxt, PIR_EL1)	= read_sysreg_el1(SYS_PIR);
+			ctxt_sys_reg(ctxt, PIRE0_EL1)	= read_sysreg_el1(SYS_PIRE0);
+		}
+	}
 	ctxt_sys_reg(ctxt, ESR_EL1)	= read_sysreg_el1(SYS_ESR);
 	ctxt_sys_reg(ctxt, AFSR0_EL1)	= read_sysreg_el1(SYS_AFSR0);
 	ctxt_sys_reg(ctxt, AFSR1_EL1)	= read_sysreg_el1(SYS_AFSR1);
@@ -73,10 +90,6 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
 	ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR);
 	ctxt_sys_reg(ctxt, AMAIR_EL1)	= read_sysreg_el1(SYS_AMAIR);
 	ctxt_sys_reg(ctxt, CNTKCTL_EL1)	= read_sysreg_el1(SYS_CNTKCTL);
-	if (ctxt_has_s1pie(ctxt)) {
-		ctxt_sys_reg(ctxt, PIR_EL1)	= read_sysreg_el1(SYS_PIR);
-		ctxt_sys_reg(ctxt, PIRE0_EL1)	= read_sysreg_el1(SYS_PIRE0);
-	}
 	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg_par();
 	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
 
@@ -138,8 +151,14 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt_sys_reg(ctxt, CPACR_EL1),	SYS_CPACR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1),	SYS_TTBR0);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1),	SYS_TTBR1);
-	if (cpus_have_final_cap(ARM64_HAS_TCR2))
+	if (ctxt_has_tcrx(ctxt)) {
 		write_sysreg_el1(ctxt_sys_reg(ctxt, TCR2_EL1),	SYS_TCR2);
+
+		if (ctxt_has_s1pie(ctxt)) {
+			write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1),	SYS_PIR);
+			write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1),	SYS_PIRE0);
+		}
+	}
 	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1),	SYS_ESR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1),	SYS_AFSR0);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL1),	SYS_AFSR1);
@@ -149,10 +168,6 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
 	write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1),	SYS_AMAIR);
 	write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL);
-	if (ctxt_has_s1pie(ctxt)) {
-		write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1),	SYS_PIR);
-		write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1),	SYS_PIRE0);
-	}
 	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
 	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
 
diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
index d9fd5e6c7d3c..146e0aebfa1c 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/ffa.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
@@ -9,7 +9,7 @@
 #include <asm/kvm_host.h>
 
 #define FFA_MIN_FUNC_NUM 0x60
-#define FFA_MAX_FUNC_NUM 0x7F
+#define FFA_MAX_FUNC_NUM 0xFF
 
 int hyp_ffa_init(void *pages);
 bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 50fa0ffb6b7e..782b34b004be 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -89,9 +89,9 @@ quiet_cmd_hyprel = HYPREL  $@
 quiet_cmd_hypcopy = HYPCOPY $@
       cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@
 
-# Remove ftrace, Shadow Call Stack, and CFI CFLAGS.
-# This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations.
-KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
+# Remove ftrace and Shadow Call Stack CFLAGS.
+# This is equivalent to the 'notrace' and '__noscs' annotations.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS))
 # Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile'
 # when profile optimization is applied. gen-hyprel does not support SHT_REL and
 # causes a build failure. Remove profile optimization flags.
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index efb053af331c..e715c157c2c4 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -67,6 +67,9 @@ struct kvm_ffa_buffers {
  */
 static struct kvm_ffa_buffers hyp_buffers;
 static struct kvm_ffa_buffers host_buffers;
+static u32 hyp_ffa_version;
+static bool has_version_negotiated;
+static hyp_spinlock_t version_lock;
 
 static void ffa_to_smccc_error(struct arm_smccc_res *res, u64 ffa_errno)
 {
@@ -462,7 +465,7 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id,
 	memcpy(buf, host_buffers.tx, fraglen);
 
 	ep_mem_access = (void *)buf +
-			ffa_mem_desc_offset(buf, 0, FFA_VERSION_1_0);
+			ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
 	offset = ep_mem_access->composite_off;
 	if (!offset || buf->ep_count != 1 || buf->sender_id != HOST_FFA_ID) {
 		ret = FFA_RET_INVALID_PARAMETERS;
@@ -541,7 +544,7 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res,
 	fraglen = res->a2;
 
 	ep_mem_access = (void *)buf +
-			ffa_mem_desc_offset(buf, 0, FFA_VERSION_1_0);
+			ffa_mem_desc_offset(buf, 0, hyp_ffa_version);
 	offset = ep_mem_access->composite_off;
 	/*
 	 * We can trust the SPMD to get this right, but let's at least
@@ -651,6 +654,132 @@ out_handled:
 	return true;
 }
 
+static int hyp_ffa_post_init(void)
+{
+	size_t min_rxtx_sz;
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_smc(FFA_ID_GET, 0, 0, 0, 0, 0, 0, 0, &res);
+	if (res.a0 != FFA_SUCCESS)
+		return -EOPNOTSUPP;
+
+	if (res.a2 != HOST_FFA_ID)
+		return -EINVAL;
+
+	arm_smccc_1_1_smc(FFA_FEATURES, FFA_FN64_RXTX_MAP,
+			  0, 0, 0, 0, 0, 0, &res);
+	if (res.a0 != FFA_SUCCESS)
+		return -EOPNOTSUPP;
+
+	switch (res.a2) {
+	case FFA_FEAT_RXTX_MIN_SZ_4K:
+		min_rxtx_sz = SZ_4K;
+		break;
+	case FFA_FEAT_RXTX_MIN_SZ_16K:
+		min_rxtx_sz = SZ_16K;
+		break;
+	case FFA_FEAT_RXTX_MIN_SZ_64K:
+		min_rxtx_sz = SZ_64K;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (min_rxtx_sz > PAGE_SIZE)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static void do_ffa_version(struct arm_smccc_res *res,
+			   struct kvm_cpu_context *ctxt)
+{
+	DECLARE_REG(u32, ffa_req_version, ctxt, 1);
+
+	if (FFA_MAJOR_VERSION(ffa_req_version) != 1) {
+		res->a0 = FFA_RET_NOT_SUPPORTED;
+		return;
+	}
+
+	hyp_spin_lock(&version_lock);
+	if (has_version_negotiated) {
+		res->a0 = hyp_ffa_version;
+		goto unlock;
+	}
+
+	/*
+	 * If the client driver tries to downgrade the version, we need to ask
+	 * first if TEE supports it.
+	 */
+	if (FFA_MINOR_VERSION(ffa_req_version) < FFA_MINOR_VERSION(hyp_ffa_version)) {
+		arm_smccc_1_1_smc(FFA_VERSION, ffa_req_version, 0,
+				  0, 0, 0, 0, 0,
+				  res);
+		if (res->a0 == FFA_RET_NOT_SUPPORTED)
+			goto unlock;
+
+		hyp_ffa_version = ffa_req_version;
+	}
+
+	if (hyp_ffa_post_init())
+		res->a0 = FFA_RET_NOT_SUPPORTED;
+	else {
+		has_version_negotiated = true;
+		res->a0 = hyp_ffa_version;
+	}
+unlock:
+	hyp_spin_unlock(&version_lock);
+}
+
+static void do_ffa_part_get(struct arm_smccc_res *res,
+			    struct kvm_cpu_context *ctxt)
+{
+	DECLARE_REG(u32, uuid0, ctxt, 1);
+	DECLARE_REG(u32, uuid1, ctxt, 2);
+	DECLARE_REG(u32, uuid2, ctxt, 3);
+	DECLARE_REG(u32, uuid3, ctxt, 4);
+	DECLARE_REG(u32, flags, ctxt, 5);
+	u32 count, partition_sz, copy_sz;
+
+	hyp_spin_lock(&host_buffers.lock);
+	if (!host_buffers.rx) {
+		ffa_to_smccc_res(res, FFA_RET_BUSY);
+		goto out_unlock;
+	}
+
+	arm_smccc_1_1_smc(FFA_PARTITION_INFO_GET, uuid0, uuid1,
+			  uuid2, uuid3, flags, 0, 0,
+			  res);
+
+	if (res->a0 != FFA_SUCCESS)
+		goto out_unlock;
+
+	count = res->a2;
+	if (!count)
+		goto out_unlock;
+
+	if (hyp_ffa_version > FFA_VERSION_1_0) {
+		/* Get the number of partitions deployed in the system */
+		if (flags & 0x1)
+			goto out_unlock;
+
+		partition_sz  = res->a3;
+	} else {
+		/* FFA_VERSION_1_0 lacks the size in the response */
+		partition_sz = FFA_1_0_PARTITON_INFO_SZ;
+	}
+
+	copy_sz = partition_sz * count;
+	if (copy_sz > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) {
+		ffa_to_smccc_res(res, FFA_RET_ABORTED);
+		goto out_unlock;
+	}
+
+	memcpy(host_buffers.rx, hyp_buffers.rx, copy_sz);
+out_unlock:
+	hyp_spin_unlock(&host_buffers.lock);
+}
+
 bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 {
 	struct arm_smccc_res res;
@@ -671,6 +800,11 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 	if (!is_ffa_call(func_id))
 		return false;
 
+	if (!has_version_negotiated && func_id != FFA_VERSION) {
+		ffa_to_smccc_error(&res, FFA_RET_INVALID_PARAMETERS);
+		goto out_handled;
+	}
+
 	switch (func_id) {
 	case FFA_FEATURES:
 		if (!do_ffa_features(&res, host_ctxt))
@@ -697,6 +831,12 @@ bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 	case FFA_MEM_FRAG_TX:
 		do_ffa_mem_frag_tx(&res, host_ctxt);
 		goto out_handled;
+	case FFA_VERSION:
+		do_ffa_version(&res, host_ctxt);
+		goto out_handled;
+	case FFA_PARTITION_INFO_GET:
+		do_ffa_part_get(&res, host_ctxt);
+		goto out_handled;
 	}
 
 	if (ffa_call_supported(func_id))
@@ -711,13 +851,12 @@ out_handled:
 int hyp_ffa_init(void *pages)
 {
 	struct arm_smccc_res res;
-	size_t min_rxtx_sz;
 	void *tx, *rx;
 
 	if (kvm_host_psci_config.smccc_version < ARM_SMCCC_VERSION_1_2)
 		return 0;
 
-	arm_smccc_1_1_smc(FFA_VERSION, FFA_VERSION_1_0, 0, 0, 0, 0, 0, 0, &res);
+	arm_smccc_1_1_smc(FFA_VERSION, FFA_VERSION_1_1, 0, 0, 0, 0, 0, 0, &res);
 	if (res.a0 == FFA_RET_NOT_SUPPORTED)
 		return 0;
 
@@ -737,34 +876,10 @@ int hyp_ffa_init(void *pages)
 	if (FFA_MAJOR_VERSION(res.a0) != 1)
 		return -EOPNOTSUPP;
 
-	arm_smccc_1_1_smc(FFA_ID_GET, 0, 0, 0, 0, 0, 0, 0, &res);
-	if (res.a0 != FFA_SUCCESS)
-		return -EOPNOTSUPP;
-
-	if (res.a2 != HOST_FFA_ID)
-		return -EINVAL;
-
-	arm_smccc_1_1_smc(FFA_FEATURES, FFA_FN64_RXTX_MAP,
-			  0, 0, 0, 0, 0, 0, &res);
-	if (res.a0 != FFA_SUCCESS)
-		return -EOPNOTSUPP;
-
-	switch (res.a2) {
-	case FFA_FEAT_RXTX_MIN_SZ_4K:
-		min_rxtx_sz = SZ_4K;
-		break;
-	case FFA_FEAT_RXTX_MIN_SZ_16K:
-		min_rxtx_sz = SZ_16K;
-		break;
-	case FFA_FEAT_RXTX_MIN_SZ_64K:
-		min_rxtx_sz = SZ_64K;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (min_rxtx_sz > PAGE_SIZE)
-		return -EOPNOTSUPP;
+	if (FFA_MINOR_VERSION(res.a0) < FFA_MINOR_VERSION(FFA_VERSION_1_1))
+		hyp_ffa_version = res.a0;
+	else
+		hyp_ffa_version = FFA_VERSION_1_1;
 
 	tx = pages;
 	pages += KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE;
@@ -787,5 +902,6 @@ int hyp_ffa_init(void *pages)
 		.lock	= __HYP_SPIN_LOCK_UNLOCKED,
 	};
 
+	version_lock = __HYP_SPIN_LOCK_UNLOCKED;
 	return 0;
 }
diff --git a/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
index 6bc88a756cb7..b63f4e1c1033 100644
--- a/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
+++ b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c
@@ -50,6 +50,9 @@
 #ifndef R_AARCH64_ABS64
 #define R_AARCH64_ABS64			257
 #endif
+#ifndef R_AARCH64_ABS32
+#define R_AARCH64_ABS32			258
+#endif
 #ifndef R_AARCH64_PREL64
 #define R_AARCH64_PREL64		260
 #endif
@@ -383,6 +386,9 @@ static void emit_rela_section(Elf64_Shdr *sh_rela)
 		case R_AARCH64_ABS64:
 			emit_rela_abs64(rela, sh_orig_name);
 			break;
+		/* Allow 32-bit absolute relocation, for kCFI type hashes. */
+		case R_AARCH64_ABS32:
+			break;
 		/* Allow position-relative data relocations. */
 		case R_AARCH64_PREL64:
 		case R_AARCH64_PREL32:
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 135cfb294ee5..3d610fc51f4d 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -197,12 +197,6 @@ SYM_FUNC_END(__host_hvc)
 	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
 	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
 
-	/* If a guest is loaded, panic out of it. */
-	stp	x0, x1, [sp, #-16]!
-	get_loaded_vcpu x0, x1
-	cbnz	x0, __guest_exit_panic
-	add	sp, sp, #16
-
 	/*
 	 * The panic may not be clean if the exception is taken before the host
 	 * context has been saved by __host_exit or after the hyp context has
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 2994878d68ea..07120b37da35 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -5,6 +5,7 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/cfi_types.h>
 #include <linux/linkage.h>
 
 #include <asm/alternative.h>
@@ -265,33 +266,38 @@ alternative_else_nop_endif
 
 SYM_CODE_END(__kvm_handle_stub_hvc)
 
-SYM_FUNC_START(__pkvm_init_switch_pgd)
+/*
+ * void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp,
+ *                             void (*fn)(void));
+ *
+ * SYM_TYPED_FUNC_START() allows C to call this ID-mapped function indirectly
+ * using a physical pointer without triggering a kCFI failure.
+ */
+SYM_TYPED_FUNC_START(__pkvm_init_switch_pgd)
 	/* Turn the MMU off */
 	pre_disable_mmu_workaround
-	mrs	x2, sctlr_el2
-	bic	x3, x2, #SCTLR_ELx_M
-	msr	sctlr_el2, x3
+	mrs	x3, sctlr_el2
+	bic	x4, x3, #SCTLR_ELx_M
+	msr	sctlr_el2, x4
 	isb
 
 	tlbi	alle2
 
 	/* Install the new pgtables */
-	ldr	x3, [x0, #NVHE_INIT_PGD_PA]
-	phys_to_ttbr x4, x3
+	phys_to_ttbr x5, x0
 alternative_if ARM64_HAS_CNP
-	orr	x4, x4, #TTBR_CNP_BIT
+	orr	x5, x5, #TTBR_CNP_BIT
 alternative_else_nop_endif
-	msr	ttbr0_el2, x4
+	msr	ttbr0_el2, x5
 
 	/* Set the new stack pointer */
-	ldr	x0, [x0, #NVHE_INIT_STACK_HYP_VA]
-	mov	sp, x0
+	mov	sp, x1
 
 	/* And turn the MMU back on! */
 	dsb	nsh
 	isb
-	set_sctlr_el2	x2
-	ret	x1
+	set_sctlr_el2	x3
+	ret	x2
 SYM_FUNC_END(__pkvm_init_switch_pgd)
 
 	.popsection
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index f4350ba07b0b..174007f3fadd 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -339,7 +339,7 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 {
 	struct kvm_nvhe_init_params *params;
 	void *virt = hyp_phys_to_virt(phys);
-	void (*fn)(phys_addr_t params_pa, void *finalize_fn_va);
+	typeof(__pkvm_init_switch_pgd) *fn;
 	int ret;
 
 	BUG_ON(kvm_check_pvm_sysreg_table());
@@ -363,7 +363,7 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
 	/* Jump in the idmap page to switch to the new page-tables */
 	params = this_cpu_ptr(&kvm_init_params);
 	fn = (typeof(fn))__hyp_pa(__pkvm_init_switch_pgd);
-	fn(__hyp_pa(params), __pkvm_init_finalise);
+	fn(params->pgd_pa, params->stack_hyp_va, __pkvm_init_finalise);
 
 	unreachable();
 }
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 8fbb6a2e0559..77010b76c150 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -65,6 +65,77 @@ static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 	return hcr | (__vcpu_sys_reg(vcpu, HCR_EL2) & ~NV_HCR_GUEST_EXCLUDE);
 }
 
+static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	u64 cptr;
+
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+	u64 val = CPACR_ELx_TTA | CPTR_EL2_TAM;
+
+	if (guest_owns_fp_regs()) {
+		val |= CPACR_ELx_FPEN;
+		if (vcpu_has_sve(vcpu))
+			val |= CPACR_ELx_ZEN;
+	} else {
+		__activate_traps_fpsimd32(vcpu);
+	}
+
+	if (!vcpu_has_nv(vcpu))
+		goto write;
+
+	/*
+	 * The architecture is a bit crap (what a surprise): an EL2 guest
+	 * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
+	 * as they are RES0 in the guest's view. To work around it, trap the
+	 * sucker using the very same bit it can't set...
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
+		val |= CPTR_EL2_TCPAC;
+
+	/*
+	 * Layer the guest hypervisor's trap configuration on top of our own if
+	 * we're in a nested context.
+	 */
+	if (is_hyp_ctxt(vcpu))
+		goto write;
+
+	cptr = vcpu_sanitised_cptr_el2(vcpu);
+
+	/*
+	 * Pay attention, there's some interesting detail here.
+	 *
+	 * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
+	 * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
+	 *
+	 *  - CPTR_EL2.xEN = x0, traps are enabled
+	 *  - CPTR_EL2.xEN = x1, traps are disabled
+	 *
+	 * In other words, bit[0] determines if guest accesses trap or not. In
+	 * the interest of simplicity, clear the entire field if the guest
+	 * hypervisor has traps enabled to dispel any illusion of something more
+	 * complicated taking place.
+	 */
+	if (!(SYS_FIELD_GET(CPACR_ELx, FPEN, cptr) & BIT(0)))
+		val &= ~CPACR_ELx_FPEN;
+	if (!(SYS_FIELD_GET(CPACR_ELx, ZEN, cptr) & BIT(0)))
+		val &= ~CPACR_ELx_ZEN;
+
+	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
+		val |= cptr & CPACR_ELx_E0POE;
+
+	val |= cptr & CPTR_EL2_TCPAC;
+
+write:
+	write_sysreg(val, cpacr_el1);
+}
+
 static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;
@@ -91,30 +162,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	val = read_sysreg(cpacr_el1);
-	val |= CPACR_ELx_TTA;
-	val &= ~(CPACR_ELx_ZEN | CPACR_ELx_SMEN);
-
-	/*
-	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
-	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
-	 * except for some missing controls, such as TAM.
-	 * In this case, CPTR_EL2.TAM has the same position with or without
-	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
-	 * shift value for trapping the AMU accesses.
-	 */
-
-	val |= CPTR_EL2_TAM;
-
-	if (guest_owns_fp_regs()) {
-		if (vcpu_has_sve(vcpu))
-			val |= CPACR_ELx_ZEN;
-	} else {
-		val &= ~CPACR_ELx_FPEN;
-		__activate_traps_fpsimd32(vcpu);
-	}
-
-	write_sysreg(val, cpacr_el1);
+	__activate_cptr_traps(vcpu);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
 }
@@ -266,10 +314,111 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
 	__fpsimd_save_state(*host_data_ptr(fpsimd_state));
 }
 
+static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	int ret = -EINVAL;
+	u32 instr;
+	u64 val;
+
+	/*
+	 * Ideally, we would never trap on EL2 S1 TLB invalidations using
+	 * the EL1 instructions when the guest's HCR_EL2.{E2H,TGE}=={1,1}.
+	 * But "thanks" to FEAT_NV2, we don't trap writes to HCR_EL2,
+	 * meaning that we can't track changes to the virtual TGE bit. So we
+	 * have to leave HCR_EL2.TTLB set on the host. Oopsie...
+	 *
+	 * Try and handle these invalidation as quickly as possible, without
+	 * fully exiting. Note that we don't need to consider any forwarding
+	 * here, as having E2H+TGE set is the very definition of being
+	 * InHost.
+	 *
+	 * For the lesser hypervisors out there that have failed to get on
+	 * with the VHE program, we can also handle the nVHE style of EL2
+	 * invalidation.
+	 */
+	if (!(is_hyp_ctxt(vcpu)))
+		return false;
+
+	instr = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+	val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
+
+	if ((kvm_supported_tlbi_s1e1_op(vcpu, instr) &&
+	     vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) ||
+	    kvm_supported_tlbi_s1e2_op (vcpu, instr))
+		ret = __kvm_tlbi_s1e2(NULL, val, instr);
+
+	if (ret)
+		return false;
+
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_cpacr_el1(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	int rt;
+
+	if (!is_hyp_ctxt(vcpu) || esr_sys64_to_sysreg(esr) != SYS_CPACR_EL1)
+		return false;
+
+	rt = kvm_vcpu_sys_get_rt(vcpu);
+
+	if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ) {
+		vcpu_set_reg(vcpu, rt, __vcpu_sys_reg(vcpu, CPTR_EL2));
+	} else {
+		vcpu_write_sys_reg(vcpu, vcpu_get_reg(vcpu, rt), CPTR_EL2);
+		__activate_cptr_traps(vcpu);
+	}
+
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_zcr_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+
+	if (!vcpu_has_nv(vcpu))
+		return false;
+
+	if (sysreg != SYS_ZCR_EL2)
+		return false;
+
+	if (guest_owns_fp_regs())
+		return false;
+
+	/*
+	 * ZCR_EL2 traps are handled in the slow path, with the expectation
+	 * that the guest's FP context has already been loaded onto the CPU.
+	 *
+	 * Load the guest's FP context and unconditionally forward to the
+	 * slow path for handling (i.e. return false).
+	 */
+	kvm_hyp_handle_fpsimd(vcpu, exit_code);
+	return false;
+}
+
+static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code))
+		return true;
+
+	if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code))
+		return true;
+
+	if (kvm_hyp_handle_zcr_el2(vcpu, exit_code))
+		return true;
+
+	return kvm_hyp_handle_sysreg(vcpu, exit_code);
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
-	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg,
+	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg_vhe,
 	[ESR_ELx_EC_SVE]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
@@ -388,7 +537,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static void __hyp_call_panic(u64 spsr, u64 elr, u64 par)
+static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
@@ -413,7 +562,6 @@ void __noreturn hyp_panic(void)
 	u64 par = read_sysreg_par();
 
 	__hyp_call_panic(spsr, elr, par);
-	unreachable();
 }
 
 asmlinkage void kvm_unexpected_el2_exception(void)
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 5fa0359f3a87..3d50a1bd2bdb 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -219,3 +219,150 @@ void __kvm_flush_vm_context(void)
 	__tlbi(alle1is);
 	dsb(ish);
 }
+
+/*
+ * TLB invalidation emulation for NV. For any given instruction, we
+ * perform the following transformtions:
+ *
+ * - a TLBI targeting EL2 S1 is remapped to EL1 S1
+ * - a non-shareable TLBI is upgraded to being inner-shareable
+ * - an outer-shareable TLBI is also mapped to inner-shareable
+ * - an nXS TLBI is upgraded to XS
+ */
+int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
+{
+	struct tlb_inv_context cxt;
+	int ret = 0;
+
+	/*
+	 * The guest will have provided its own DSB ISHST before trapping.
+	 * If it hasn't, that's its own problem, and we won't paper over it
+	 * (plus, there is plenty of extra synchronisation before we even
+	 * get here...).
+	 */
+
+	if (mmu)
+		enter_vmid_context(mmu, &cxt);
+
+	switch (sys_encoding) {
+	case OP_TLBI_ALLE2:
+	case OP_TLBI_ALLE2IS:
+	case OP_TLBI_ALLE2OS:
+	case OP_TLBI_VMALLE1:
+	case OP_TLBI_VMALLE1IS:
+	case OP_TLBI_VMALLE1OS:
+	case OP_TLBI_ALLE2NXS:
+	case OP_TLBI_ALLE2ISNXS:
+	case OP_TLBI_ALLE2OSNXS:
+	case OP_TLBI_VMALLE1NXS:
+	case OP_TLBI_VMALLE1ISNXS:
+	case OP_TLBI_VMALLE1OSNXS:
+		__tlbi(vmalle1is);
+		break;
+	case OP_TLBI_VAE2:
+	case OP_TLBI_VAE2IS:
+	case OP_TLBI_VAE2OS:
+	case OP_TLBI_VAE1:
+	case OP_TLBI_VAE1IS:
+	case OP_TLBI_VAE1OS:
+	case OP_TLBI_VAE2NXS:
+	case OP_TLBI_VAE2ISNXS:
+	case OP_TLBI_VAE2OSNXS:
+	case OP_TLBI_VAE1NXS:
+	case OP_TLBI_VAE1ISNXS:
+	case OP_TLBI_VAE1OSNXS:
+		__tlbi(vae1is, va);
+		break;
+	case OP_TLBI_VALE2:
+	case OP_TLBI_VALE2IS:
+	case OP_TLBI_VALE2OS:
+	case OP_TLBI_VALE1:
+	case OP_TLBI_VALE1IS:
+	case OP_TLBI_VALE1OS:
+	case OP_TLBI_VALE2NXS:
+	case OP_TLBI_VALE2ISNXS:
+	case OP_TLBI_VALE2OSNXS:
+	case OP_TLBI_VALE1NXS:
+	case OP_TLBI_VALE1ISNXS:
+	case OP_TLBI_VALE1OSNXS:
+		__tlbi(vale1is, va);
+		break;
+	case OP_TLBI_ASIDE1:
+	case OP_TLBI_ASIDE1IS:
+	case OP_TLBI_ASIDE1OS:
+	case OP_TLBI_ASIDE1NXS:
+	case OP_TLBI_ASIDE1ISNXS:
+	case OP_TLBI_ASIDE1OSNXS:
+		__tlbi(aside1is, va);
+		break;
+	case OP_TLBI_VAAE1:
+	case OP_TLBI_VAAE1IS:
+	case OP_TLBI_VAAE1OS:
+	case OP_TLBI_VAAE1NXS:
+	case OP_TLBI_VAAE1ISNXS:
+	case OP_TLBI_VAAE1OSNXS:
+		__tlbi(vaae1is, va);
+		break;
+	case OP_TLBI_VAALE1:
+	case OP_TLBI_VAALE1IS:
+	case OP_TLBI_VAALE1OS:
+	case OP_TLBI_VAALE1NXS:
+	case OP_TLBI_VAALE1ISNXS:
+	case OP_TLBI_VAALE1OSNXS:
+		__tlbi(vaale1is, va);
+		break;
+	case OP_TLBI_RVAE2:
+	case OP_TLBI_RVAE2IS:
+	case OP_TLBI_RVAE2OS:
+	case OP_TLBI_RVAE1:
+	case OP_TLBI_RVAE1IS:
+	case OP_TLBI_RVAE1OS:
+	case OP_TLBI_RVAE2NXS:
+	case OP_TLBI_RVAE2ISNXS:
+	case OP_TLBI_RVAE2OSNXS:
+	case OP_TLBI_RVAE1NXS:
+	case OP_TLBI_RVAE1ISNXS:
+	case OP_TLBI_RVAE1OSNXS:
+		__tlbi(rvae1is, va);
+		break;
+	case OP_TLBI_RVALE2:
+	case OP_TLBI_RVALE2IS:
+	case OP_TLBI_RVALE2OS:
+	case OP_TLBI_RVALE1:
+	case OP_TLBI_RVALE1IS:
+	case OP_TLBI_RVALE1OS:
+	case OP_TLBI_RVALE2NXS:
+	case OP_TLBI_RVALE2ISNXS:
+	case OP_TLBI_RVALE2OSNXS:
+	case OP_TLBI_RVALE1NXS:
+	case OP_TLBI_RVALE1ISNXS:
+	case OP_TLBI_RVALE1OSNXS:
+		__tlbi(rvale1is, va);
+		break;
+	case OP_TLBI_RVAAE1:
+	case OP_TLBI_RVAAE1IS:
+	case OP_TLBI_RVAAE1OS:
+	case OP_TLBI_RVAAE1NXS:
+	case OP_TLBI_RVAAE1ISNXS:
+	case OP_TLBI_RVAAE1OSNXS:
+		__tlbi(rvaae1is, va);
+		break;
+	case OP_TLBI_RVAALE1:
+	case OP_TLBI_RVAALE1IS:
+	case OP_TLBI_RVAALE1OS:
+	case OP_TLBI_RVAALE1NXS:
+	case OP_TLBI_RVAALE1ISNXS:
+	case OP_TLBI_RVAALE1OSNXS:
+		__tlbi(rvaale1is, va);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	dsb(ish);
+	isb();
+
+	if (mmu)
+		exit_vmid_context(&cxt);
+
+	return ret;
+}