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

Pull more KVM updates from Paolo Bonzini:
 "PPC:
   - Improvements and bugfixes for secure VM support, giving reduced
     startup time and memory hotplug support.

   - Locking fixes in nested KVM code

   - Increase number of guests supported by HV KVM to 4094

   - Preliminary POWER10 support

  ARM:
   - Split the VHE and nVHE hypervisor code bases, build the EL2 code
     separately, allowing for the VHE code to now be built with
     instrumentation

   - Level-based TLB invalidation support

   - Restructure of the vcpu register storage to accomodate the NV code

   - Pointer Authentication available for guests on nVHE hosts

   - Simplification of the system register table parsing

   - MMU cleanups and fixes

   - A number of post-32bit cleanups and other fixes

  MIPS:
   - compilation fixes

  x86:
   - bugfixes

   - support for the SERIALIZE instruction"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (70 commits)
  KVM: MIPS/VZ: Fix build error caused by 'kvm_run' cleanup
  x86/kvm/hyper-v: Synic default SCONTROL MSR needs to be enabled
  MIPS: KVM: Convert a fallthrough comment to fallthrough
  MIPS: VZ: Only include loongson_regs.h for CPU_LOONGSON64
  x86: Expose SERIALIZE for supported cpuid
  KVM: x86: Don't attempt to load PDPTRs when 64-bit mode is enabled
  KVM: arm64: Move S1PTW S2 fault logic out of io_mem_abort()
  KVM: arm64: Don't skip cache maintenance for read-only memslots
  KVM: arm64: Handle data and instruction external aborts the same way
  KVM: arm64: Rename kvm_vcpu_dabt_isextabt()
  KVM: arm: Add trace name for ARM_NISV
  KVM: arm64: Ensure that all nVHE hyp code is in .hyp.text
  KVM: arm64: Substitute RANDOMIZE_BASE for HARDEN_EL2_VECTORS
  KVM: arm64: Make nVHE ASLR conditional on RANDOMIZE_BASE
  KVM: PPC: Book3S HV: Rework secure mem slot dropping
  KVM: PPC: Book3S HV: Move kvmppc_svm_page_out up
  KVM: PPC: Book3S HV: Migrate hot plugged memory
  KVM: PPC: Book3S HV: In H_SVM_INIT_DONE, migrate remaining normal-GFNs to secure-GFNs
  KVM: PPC: Book3S HV: Track the state GFNs associated with secure VMs
  KVM: PPC: Book3S HV: Disable page merging in H_SVM_INIT_START
  ...

27 files changed, 2162 insertions, 1702 deletions

diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 8c9880783839..f54f0e89a71c 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -3,18 +3,12 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
-		$(DISABLE_STACKLEAK_PLUGIN)
-
-obj-$(CONFIG_KVM) += hyp.o
-
-hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \
-	 debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o
-
-# KVM code is run at a different exception code with a different map, so
-# compiler instrumentation that inserts callbacks or checks into the code may
-# cause crashes. Just disable it.
-GCOV_PROFILE	:= n
-KASAN_SANITIZE	:= n
-UBSAN_SANITIZE	:= n
-KCOV_INSTRUMENT	:= n
+incdir := $(srctree)/$(src)/include
+subdir-asflags-y := -I$(incdir)
+subdir-ccflags-y := -I$(incdir)				\
+		    -fno-stack-protector		\
+		    -DDISABLE_BRANCH_PROFILING		\
+		    $(DISABLE_STACKLEAK_PLUGIN)
+
+obj-$(CONFIG_KVM) += vhe/ nvhe/
+obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o
diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c
index 25c0e47d57cb..ae56d8a4b382 100644
--- a/arch/arm64/kvm/hyp/aarch32.c
+++ b/arch/arm64/kvm/hyp/aarch32.c
@@ -44,14 +44,14 @@ static const unsigned short cc_map[16] = {
 /*
  * Check if a trapped instruction should have been executed or not.
  */
-bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu)
 {
 	unsigned long cpsr;
 	u32 cpsr_cond;
 	int cond;
 
 	/* Top two bits non-zero?  Unconditional. */
-	if (kvm_vcpu_get_hsr(vcpu) >> 30)
+	if (kvm_vcpu_get_esr(vcpu) >> 30)
 		return true;
 
 	/* Is condition field valid? */
@@ -93,7 +93,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu)
  *
  * IT[7:0] -> CPSR[26:25],CPSR[15:10]
  */
-static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
+static void kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 {
 	unsigned long itbits, cond;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
  * kvm_skip_instr - skip a trapped instruction and proceed to the next
  * @vcpu: The vcpu pointer
  */
-void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
 	u32 pc = *vcpu_pc(vcpu);
 	bool is_thumb;
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 90186cf6473e..ee32a7743389 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -16,12 +16,10 @@
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_ptrauth.h>
 
-#define CPU_GP_REG_OFFSET(x)	(CPU_GP_REGS + x)
-#define CPU_XREG_OFFSET(x)	CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x)
+#define CPU_XREG_OFFSET(x)	(CPU_USER_PT_REGS + 8*x)
 #define CPU_SP_EL0_OFFSET	(CPU_XREG_OFFSET(30) + 8)
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 /*
  * We treat x18 as callee-saved as the host may use it as a platform
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 5b8ff517ff10..01f114aa47b0 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -9,7 +9,6 @@
 #include <asm/fpsimdmacros.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 SYM_FUNC_START(__fpsimd_save_state)
 	fpsimd_save	x0, 1
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 9c5cfb04170e..689fccbc9de7 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -16,7 +16,6 @@
 #include <asm/mmu.h>
 
 	.text
-	.pushsection	.hyp.text, "ax"
 
 .macro do_el2_call
 	/*
@@ -40,6 +39,7 @@ el1_sync:				// Guest trapped into EL2
 	ccmp	x0, #ESR_ELx_EC_HVC32, #4, ne
 	b.ne	el1_trap
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 	mrs	x1, vttbr_el2		// If vttbr is valid, the guest
 	cbnz	x1, el1_hvc_guest	// called HVC
 
@@ -74,6 +74,7 @@ el1_sync:				// Guest trapped into EL2
 
 	eret
 	sb
+#endif /* __KVM_NVHE_HYPERVISOR__ */
 
 el1_hvc_guest:
 	/*
@@ -180,6 +181,7 @@ el2_error:
 	eret
 	sb
 
+#ifdef __KVM_NVHE_HYPERVISOR__
 SYM_FUNC_START(__hyp_do_panic)
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
 		      PSR_MODE_EL1h)
@@ -189,6 +191,7 @@ SYM_FUNC_START(__hyp_do_panic)
 	eret
 	sb
 SYM_FUNC_END(__hyp_do_panic)
+#endif
 
 SYM_CODE_START(__hyp_panic)
 	get_host_ctxt x0, x1
@@ -318,20 +321,4 @@ SYM_CODE_START(__bp_harden_hyp_vecs)
 1:	.org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
 	.org 1b
 SYM_CODE_END(__bp_harden_hyp_vecs)
-
-	.popsection
-
-SYM_CODE_START(__smccc_workaround_1_smc)
-	esb
-	sub	sp, sp, #(8 * 4)
-	stp	x2, x3, [sp, #(8 * 0)]
-	stp	x0, x1, [sp, #(8 * 2)]
-	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
-	smc	#0
-	ldp	x2, x3, [sp, #(8 * 0)]
-	ldp	x0, x1, [sp, #(8 * 2)]
-	add	sp, sp, #(8 * 4)
-1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
-	.org 1b
-SYM_CODE_END(__smccc_workaround_1_smc)
 #endif
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index e95af204fec7..0297dc63988c 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -4,6 +4,9 @@
  * Author: Marc Zyngier <marc.zyngier@arm.com>
  */
 
+#ifndef __ARM64_KVM_HYP_DEBUG_SR_H__
+#define __ARM64_KVM_HYP_DEBUG_SR_H__
+
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 
@@ -85,53 +88,8 @@
 	default:	write_debug(ptr[0], reg, 0);			\
 	}
 
-static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
-{
-	u64 reg;
-
-	/* Clear pmscr in case of early return */
-	*pmscr_el1 = 0;
-
-	/* SPE present on this CPU? */
-	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
-						  ID_AA64DFR0_PMSVER_SHIFT))
-		return;
-
-	/* Yes; is it owned by EL3? */
-	reg = read_sysreg_s(SYS_PMBIDR_EL1);
-	if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT))
-		return;
-
-	/* No; is the host actually using the thing? */
-	reg = read_sysreg_s(SYS_PMBLIMITR_EL1);
-	if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT)))
-		return;
-
-	/* Yes; save the control register and disable data generation */
-	*pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1);
-	write_sysreg_s(0, SYS_PMSCR_EL1);
-	isb();
-
-	/* Now drain all buffered data to memory */
-	psb_csync();
-	dsb(nsh);
-}
-
-static void __hyp_text __debug_restore_spe_nvhe(u64 pmscr_el1)
-{
-	if (!pmscr_el1)
-		return;
-
-	/* The host page table is installed, but not yet synchronised */
-	isb();
-
-	/* Re-enable data generation */
-	write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
-}
-
-static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
-					  struct kvm_guest_debug_arch *dbg,
-					  struct kvm_cpu_context *ctxt)
+static void __debug_save_state(struct kvm_guest_debug_arch *dbg,
+			       struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -145,12 +103,11 @@ static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu,
 	save_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	save_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1);
+	ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1);
 }
 
-static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
-					     struct kvm_guest_debug_arch *dbg,
-					     struct kvm_cpu_context *ctxt)
+static void __debug_restore_state(struct kvm_guest_debug_arch *dbg,
+				  struct kvm_cpu_context *ctxt)
 {
 	u64 aa64dfr0;
 	int brps, wrps;
@@ -165,23 +122,16 @@ static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu,
 	restore_debug(dbg->dbg_wcr, dbgwcr, wrps);
 	restore_debug(dbg->dbg_wvr, dbgwvr, wrps);
 
-	write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1);
+	write_sysreg(ctxt_sys_reg(ctxt, MDCCINT_EL1), mdccint_el1);
 }
 
-void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	/*
-	 * Non-VHE: Disable and flush SPE data generation
-	 * VHE: The vcpu can run, but it can't hide.
-	 */
-	if (!has_vhe())
-		__debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
-
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
@@ -190,20 +140,17 @@ void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, host_dbg, host_ctxt);
-	__debug_restore_state(vcpu, guest_dbg, guest_ctxt);
+	__debug_save_state(host_dbg, host_ctxt);
+	__debug_restore_state(guest_dbg, guest_ctxt);
 }
 
-void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
+static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
 	struct kvm_guest_debug_arch *host_dbg;
 	struct kvm_guest_debug_arch *guest_dbg;
 
-	if (!has_vhe())
-		__debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1);
-
 	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
@@ -212,13 +159,10 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
 	host_dbg = &vcpu->arch.host_debug_state.regs;
 	guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr);
 
-	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
-	__debug_restore_state(vcpu, host_dbg, host_ctxt);
+	__debug_save_state(guest_dbg, guest_ctxt);
+	__debug_restore_state(host_dbg, host_ctxt);
 
 	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
 }
 
-u32 __hyp_text __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}
+#endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
new file mode 100644
index 000000000000..426ef65601dd
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -0,0 +1,511 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SWITCH_H__
+#define __ARM64_KVM_HYP_SWITCH_H__
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <linux/types.h>
+#include <linux/jump_label.h>
+#include <uapi/linux/psci.h>
+
+#include <kvm/arm_psci.h>
+
+#include <asm/barrier.h>
+#include <asm/cpufeature.h>
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+#include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
+#include <asm/processor.h>
+#include <asm/thread_info.h>
+
+extern const char __hyp_panic_string[];
+
+/* Check whether the FP regs were dirtied while in the host-side run loop: */
+static inline bool update_fp_enabled(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When the system doesn't support FP/SIMD, we cannot rely on
+	 * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an
+	 * abort on the very first access to FP and thus we should never
+	 * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always
+	 * trap the accesses.
+	 */
+	if (!system_supports_fpsimd() ||
+	    vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+				      KVM_ARM64_FP_HOST);
+
+	return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
+}
+
+/* Save the 32-bit only FPSIMD system register state */
+static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
+{
+	if (!vcpu_el1_is_32bit(vcpu))
+		return;
+
+	__vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
+}
+
+static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * We are about to set CPTR_EL2.TFP to trap all floating point
+	 * register accesses to EL2, however, the ARM ARM clearly states that
+	 * traps are only taken to EL2 if the operation would not otherwise
+	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
+	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
+	 * it will cause an exception.
+	 */
+	if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) {
+		write_sysreg(1 << 30, fpexc32_el2);
+		isb();
+	}
+}
+
+static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
+{
+	/* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */
+	write_sysreg(1 << 15, hstr_el2);
+
+	/*
+	 * Make sure we trap PMU access from EL0 to EL2. Also sanitize
+	 * PMSELR_EL0 to make sure it never contains the cycle
+	 * counter, which could make a PMXEVCNTR_EL0 access UNDEF at
+	 * EL1 instead of being trapped to EL2.
+	 */
+	write_sysreg(0, pmselr_el0);
+	write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+}
+
+static inline void __deactivate_traps_common(void)
+{
+	write_sysreg(0, hstr_el2);
+	write_sysreg(0, pmuserenr_el0);
+}
+
+static inline void ___activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 hcr = vcpu->arch.hcr_el2;
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+		hcr |= HCR_TVM;
+
+	write_sysreg(hcr, hcr_el2);
+
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+		write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
+}
+
+static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * If we pended a virtual abort, preserve it until it gets
+	 * cleared. See D1.14.3 (Virtual Interrupts) for details, but
+	 * the crucial bit is "On taking a vSError interrupt,
+	 * HCR_EL2.VSE is cleared to 0."
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_VSE) {
+		vcpu->arch.hcr_el2 &= ~HCR_VSE;
+		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+	}
+}
+
+static inline void __activate_vm(struct kvm_s2_mmu *mmu)
+{
+	__load_guest_stage2(mmu);
+}
+
+static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+	u64 par, tmp;
+
+	/*
+	 * Resolve the IPA the hard way using the guest VA.
+	 *
+	 * Stage-1 translation already validated the memory access
+	 * rights. As such, we can use the EL1 translation regime, and
+	 * don't have to distinguish between EL0 and EL1 access.
+	 *
+	 * We do need to save/restore PAR_EL1 though, as we haven't
+	 * saved the guest context yet, and we may return early...
+	 */
+	par = read_sysreg(par_el1);
+	asm volatile("at s1e1r, %0" : : "r" (far));
+	isb();
+
+	tmp = read_sysreg(par_el1);
+	write_sysreg(par, par_el1);
+
+	if (unlikely(tmp & SYS_PAR_EL1_F))
+		return false; /* Translation failed, back to guest */
+
+	/* Convert PAR to HPFAR format */
+	*hpfar = PAR_TO_HPFAR(tmp);
+	return true;
+}
+
+static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
+{
+	u8 ec;
+	u64 esr;
+	u64 hpfar, far;
+
+	esr = vcpu->arch.fault.esr_el2;
+	ec = ESR_ELx_EC(esr);
+
+	if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
+		return true;
+
+	far = read_sysreg_el2(SYS_FAR);
+
+	/*
+	 * The HPFAR can be invalid if the stage 2 fault did not
+	 * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+	 * bit is clear) and one of the two following cases are true:
+	 *   1. The fault was due to a permission fault
+	 *   2. The processor carries errata 834220
+	 *
+	 * Therefore, for all non S1PTW faults where we either have a
+	 * permission fault or the errata workaround is enabled, we
+	 * resolve the IPA using the AT instruction.
+	 */
+	if (!(esr & ESR_ELx_S1PTW) &&
+	    (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
+	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+		if (!__translate_far_to_hpfar(far, &hpfar))
+			return false;
+	} else {
+		hpfar = read_sysreg(hpfar_el2);
+	}
+
+	vcpu->arch.fault.far_el2 = far;
+	vcpu->arch.fault.hpfar_el2 = hpfar;
+	return true;
+}
+
+/* Check for an FPSIMD/SVE trap and handle as appropriate */
+static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+{
+	bool vhe, sve_guest, sve_host;
+	u8 esr_ec;
+
+	if (!system_supports_fpsimd())
+		return false;
+
+	/*
+	 * Currently system_supports_sve() currently implies has_vhe(),
+	 * so the check is redundant. However, has_vhe() can be determined
+	 * statically and helps the compiler remove dead code.
+	 */
+	if (has_vhe() && system_supports_sve()) {
+		sve_guest = vcpu_has_sve(vcpu);
+		sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE;
+		vhe = true;
+	} else {
+		sve_guest = false;
+		sve_host = false;
+		vhe = has_vhe();
+	}
+
+	esr_ec = kvm_vcpu_trap_get_class(vcpu);
+	if (esr_ec != ESR_ELx_EC_FP_ASIMD &&
+	    esr_ec != ESR_ELx_EC_SVE)
+		return false;
+
+	/* Don't handle SVE traps for non-SVE vcpus here: */
+	if (!sve_guest)
+		if (esr_ec != ESR_ELx_EC_FP_ASIMD)
+			return false;
+
+	/* Valid trap.  Switch the context: */
+
+	if (vhe) {
+		u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN;
+
+		if (sve_guest)
+			reg |= CPACR_EL1_ZEN;
+
+		write_sysreg(reg, cpacr_el1);
+	} else {
+		write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP,
+			     cptr_el2);
+	}
+
+	isb();
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_HOST) {
+		/*
+		 * In the SVE case, VHE is assumed: it is enforced by
+		 * Kconfig and kvm_arch_init().
+		 */
+		if (sve_host) {
+			struct thread_struct *thread = container_of(
+				vcpu->arch.host_fpsimd_state,
+				struct thread_struct, uw.fpsimd_state);
+
+			sve_save_state(sve_pffr(thread),
+				       &vcpu->arch.host_fpsimd_state->fpsr);
+		} else {
+			__fpsimd_save_state(vcpu->arch.host_fpsimd_state);
+		}
+
+		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+	}
+
+	if (sve_guest) {
+		sve_load_state(vcpu_sve_pffr(vcpu),
+			       &vcpu->arch.ctxt.fp_regs.fpsr,
+			       sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1);
+		write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12);
+	} else {
+		__fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);
+	}
+
+	/* Skip restoring fpexc32 for AArch64 guests */
+	if (!(read_sysreg(hcr_el2) & HCR_RW))
+		write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);
+
+	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
+
+	return true;
+}
+
+static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+	int rt = kvm_vcpu_sys_get_rt(vcpu);
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	/*
+	 * The normal sysreg handling code expects to see the traps,
+	 * let's not do anything here.
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_TVM)
+		return false;
+
+	switch (sysreg) {
+	case SYS_SCTLR_EL1:
+		write_sysreg_el1(val, SYS_SCTLR);
+		break;
+	case SYS_TTBR0_EL1:
+		write_sysreg_el1(val, SYS_TTBR0);
+		break;
+	case SYS_TTBR1_EL1:
+		write_sysreg_el1(val, SYS_TTBR1);
+		break;
+	case SYS_TCR_EL1:
+		write_sysreg_el1(val, SYS_TCR);
+		break;
+	case SYS_ESR_EL1:
+		write_sysreg_el1(val, SYS_ESR);
+		break;
+	case SYS_FAR_EL1:
+		write_sysreg_el1(val, SYS_FAR);
+		break;
+	case SYS_AFSR0_EL1:
+		write_sysreg_el1(val, SYS_AFSR0);
+		break;
+	case SYS_AFSR1_EL1:
+		write_sysreg_el1(val, SYS_AFSR1);
+		break;
+	case SYS_MAIR_EL1:
+		write_sysreg_el1(val, SYS_MAIR);
+		break;
+	case SYS_AMAIR_EL1:
+		write_sysreg_el1(val, SYS_AMAIR);
+		break;
+	case SYS_CONTEXTIDR_EL1:
+		write_sysreg_el1(val, SYS_CONTEXTIDR);
+		break;
+	default:
+		return false;
+	}
+
+	__kvm_skip_instr(vcpu);
+	return true;
+}
+
+static inline bool esr_is_ptrauth_trap(u32 esr)
+{
+	u32 ec = ESR_ELx_EC(esr);
+
+	if (ec == ESR_ELx_EC_PAC)
+		return true;
+
+	if (ec != ESR_ELx_EC_SYS64)
+		return false;
+
+	switch (esr_sys64_to_sysreg(esr)) {
+	case SYS_APIAKEYLO_EL1:
+	case SYS_APIAKEYHI_EL1:
+	case SYS_APIBKEYLO_EL1:
+	case SYS_APIBKEYHI_EL1:
+	case SYS_APDAKEYLO_EL1:
+	case SYS_APDAKEYHI_EL1:
+	case SYS_APDBKEYLO_EL1:
+	case SYS_APDBKEYHI_EL1:
+	case SYS_APGAKEYLO_EL1:
+	case SYS_APGAKEYHI_EL1:
+		return true;
+	}
+
+	return false;
+}
+
+#define __ptrauth_save_key(ctxt, key)					\
+	do {								\
+	u64 __val;                                                      \
+	__val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val;                   \
+	__val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1);                \
+	ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val;                   \
+} while(0)
+
+static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpu_context *ctxt;
+	u64 val;
+
+	if (!vcpu_has_ptrauth(vcpu) ||
+	    !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+		return false;
+
+	ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt;
+	__ptrauth_save_key(ctxt, APIA);
+	__ptrauth_save_key(ctxt, APIB);
+	__ptrauth_save_key(ctxt, APDA);
+	__ptrauth_save_key(ctxt, APDB);
+	__ptrauth_save_key(ctxt, APGA);
+
+	vcpu_ptrauth_enable(vcpu);
+
+	val = read_sysreg(hcr_el2);
+	val |= (HCR_API | HCR_APK);
+	write_sysreg(val, hcr_el2);
+
+	return true;
+}
+
+/*
+ * Return true when we were able to fixup the guest exit and should return to
+ * the guest, false when we should restore the host state and return to the
+ * main run loop.
+ */
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
+		vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
+
+	/*
+	 * We're using the raw exception code in order to only process
+	 * the trap if no SError is pending. We will come back to the
+	 * same PC once the SError has been injected, and replay the
+	 * trapping instruction.
+	 */
+	if (*exit_code != ARM_EXCEPTION_TRAP)
+		goto exit;
+
+	if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
+	/*
+	 * We trap the first access to the FP/SIMD to save the host context
+	 * and restore the guest context lazily.
+	 * If FP/SIMD is not implemented, handle the trap and inject an
+	 * undefined instruction exception to the guest.
+	 * Similarly for trapped SVE accesses.
+	 */
+	if (__hyp_handle_fpsimd(vcpu))
+		return true;
+
+	if (__hyp_handle_ptrauth(vcpu))
+		return true;
+
+	if (!__populate_fault_info(vcpu))
+		return true;
+
+	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+		bool valid;
+
+		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
+			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+			kvm_vcpu_dabt_isvalid(vcpu) &&
+			!kvm_vcpu_abt_issea(vcpu) &&
+			!kvm_vcpu_dabt_iss1tw(vcpu);
+
+		if (valid) {
+			int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+			if (ret == 1)
+				return true;
+
+			/* Promote an illegal access to an SError.*/
+			if (ret == -1)
+				*exit_code = ARM_EXCEPTION_EL1_SERROR;
+
+			goto exit;
+		}
+	}
+
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
+		int ret = __vgic_v3_perform_cpuif_access(vcpu);
+
+		if (ret == 1)
+			return true;
+	}
+
+exit:
+	/* Return to the host kernel and handle the exit */
+	return false;
+}
+
+static inline bool __needs_ssbd_off(struct kvm_vcpu *vcpu)
+{
+	if (!cpus_have_final_cap(ARM64_SSBD))
+		return false;
+
+	return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
+}
+
+static inline void __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * The host runs with the workaround always present. If the
+	 * guest wants it disabled, so be it...
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL);
+#endif
+}
+
+static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ARM64_SSBD
+	/*
+	 * If the guest has disabled the workaround, bring it back on.
+	 */
+	if (__needs_ssbd_off(vcpu) &&
+	    __hyp_this_cpu_read(arm64_ssbd_callback_required))
+		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL);
+#endif
+}
+
+#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
new file mode 100644
index 000000000000..7a986030145f
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -0,0 +1,193 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012-2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_SYSREG_SR_H__
+#define __ARM64_KVM_HYP_SYSREG_SR_H__
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kprobes.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+
+static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt_sys_reg(ctxt, MDSCR_EL1)	= read_sysreg(mdscr_el1);
+}
+
+static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
+{
+	ctxt_sys_reg(ctxt, TPIDR_EL0)	= rea