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

Pull KVM updates from Paolo Bonzini:
 "Small update for KVM:

  ARM:
   - lazy context-switching of FPSIMD registers on arm64
   - "split" regions for vGIC redistributor

  s390:
   - cleanups for nested
   - clock handling
   - crypto
   - storage keys
   - control register bits

  x86:
   - many bugfixes
   - implement more Hyper-V super powers
   - implement lapic_timer_advance_ns even when the LAPIC timer is
     emulated using the processor's VMX preemption timer.
   - two security-related bugfixes at the top of the branch"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (79 commits)
  kvm: fix typo in flag name
  kvm: x86: use correct privilege level for sgdt/sidt/fxsave/fxrstor access
  KVM: x86: pass kvm_vcpu to kvm_read_guest_virt and kvm_write_guest_virt_system
  KVM: x86: introduce linear_{read,write}_system
  kvm: nVMX: Enforce cpl=0 for VMX instructions
  kvm: nVMX: Add support for "VMWRITE to any supported field"
  kvm: nVMX: Restrict VMX capability MSR changes
  KVM: VMX: Optimize tscdeadline timer latency
  KVM: docs: nVMX: Remove known limitations as they do not exist now
  KVM: docs: mmu: KVM support exposing SLAT to guests
  kvm: no need to check return value of debugfs_create functions
  kvm: Make VM ioctl do valloc for some archs
  kvm: Change return type to vm_fault_t
  KVM: docs: mmu: Fix link to NPT presentation from KVM Forum 2008
  kvm: x86: Amend the KVM_GET_SUPPORTED_CPUID API documentation
  KVM: x86: hyperv: declare KVM_CAP_HYPERV_TLBFLUSH capability
  KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}_EX implementation
  KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} implementation
  KVM: introduce kvm_make_vcpus_request_mask() API
  KVM: x86: hyperv: do rep check for each hypercall separately
  ...

10 files changed, 211 insertions, 115 deletions

diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index a2e3a5af1113..47b23bf617c7 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -39,6 +39,7 @@ config KVM
 	select HAVE_KVM_IRQ_ROUTING
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
+	select HAVE_KVM_VCPU_RUN_PID_CHANGE
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 93afff91cb7c..0f2a135ba15b 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -19,7 +19,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
 kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o
 kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
 kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o
-kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o
+kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o fpsimd.o
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o
 
 kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index a1f4ebdfe6d3..00d422336a45 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -103,7 +103,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
  *
  * Additionally, KVM only traps guest accesses to the debug registers if
  * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY
- * flag on vcpu->arch.debug_flags).  Since the guest must not interfere
+ * flag on vcpu->arch.flags).  Since the guest must not interfere
  * with the hardware state when debugging the guest, we must ensure that
  * trapping is enabled whenever we are debugging the guest using the
  * debug registers.
@@ -111,7 +111,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
 
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 {
-	bool trap_debug = !(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY);
+	bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY);
 	unsigned long mdscr;
 
 	trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug);
@@ -184,7 +184,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 			vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1);
 
 			vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state;
-			vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+			vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 			trap_debug = true;
 
 			trace_kvm_arm_set_regset("BKPTS", get_num_brps(),
@@ -206,7 +206,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 
 	/* If KDE or MDE are set, perform a full save/restore cycle. */
 	if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE))
-		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 
 	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
 	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1));
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
new file mode 100644
index 000000000000..dc6ecfa5a2d2
--- /dev/null
+++ b/arch/arm64/kvm/fpsimd.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arch/arm64/kvm/fpsimd.c: Guest/host FPSIMD context coordination helpers
+ *
+ * Copyright 2018 Arm Limited
+ * Author: Dave Martin <Dave.Martin@arm.com>
+ */
+#include <linux/bottom_half.h>
+#include <linux/sched.h>
+#include <linux/thread_info.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_asm.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_mmu.h>
+
+/*
+ * Called on entry to KVM_RUN unless this vcpu previously ran at least
+ * once and the most recent prior KVM_RUN for this vcpu was called from
+ * the same task as current (highly likely).
+ *
+ * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu),
+ * such that on entering hyp the relevant parts of current are already
+ * mapped.
+ */
+int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	struct thread_info *ti = &current->thread_info;
+	struct user_fpsimd_state *fpsimd = &current->thread.uw.fpsimd_state;
+
+	/*
+	 * Make sure the host task thread flags and fpsimd state are
+	 * visible to hyp:
+	 */
+	ret = create_hyp_mappings(ti, ti + 1, PAGE_HYP);
+	if (ret)
+		goto error;
+
+	ret = create_hyp_mappings(fpsimd, fpsimd + 1, PAGE_HYP);
+	if (ret)
+		goto error;
+
+	vcpu->arch.host_thread_info = kern_hyp_va(ti);
+	vcpu->arch.host_fpsimd_state = kern_hyp_va(fpsimd);
+error:
+	return ret;
+}
+
+/*
+ * Prepare vcpu for saving the host's FPSIMD state and loading the guest's.
+ * The actual loading is done by the FPSIMD access trap taken to hyp.
+ *
+ * Here, we just set the correct metadata to indicate that the FPSIMD
+ * state in the cpu regs (if any) belongs to current on the host.
+ *
+ * TIF_SVE is backed up here, since it may get clobbered with guest state.
+ * This flag is restored by kvm_arch_vcpu_put_fp(vcpu).
+ */
+void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
+{
+	BUG_ON(!current->mm);
+
+	vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE);
+	vcpu->arch.flags |= KVM_ARM64_FP_HOST;
+	if (test_thread_flag(TIF_SVE))
+		vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE;
+}
+
+/*
+ * If the guest FPSIMD state was loaded, update the host's context
+ * tracking data mark the CPU FPSIMD regs as dirty and belonging to vcpu
+ * so that they will be written back if the kernel clobbers them due to
+ * kernel-mode NEON before re-entry into the guest.
+ */
+void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
+{
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
+		fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs);
+		clear_thread_flag(TIF_FOREIGN_FPSTATE);
+		clear_thread_flag(TIF_SVE);
+	}
+}
+
+/*
+ * Write back the vcpu FPSIMD regs if they are dirty, and invalidate the
+ * cpu FPSIMD regs so that they can't be spuriously reused if this vcpu
+ * disappears and another task or vcpu appears that recycles the same
+ * struct fpsimd_state.
+ */
+void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
+{
+	local_bh_disable();
+
+	update_thread_flag(TIF_SVE,
+			   vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE);
+
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) {
+		/* Clean guest FP state to memory and invalidate cpu view */
+		fpsimd_save();
+		fpsimd_flush_cpu_state();
+	} else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
+		/* Ensure user trap controls are correctly restored */
+		fpsimd_bind_task_to_cpu();
+	}
+
+	local_bh_enable();
+}
diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c
index 3e717f66f011..50009766e5e5 100644
--- a/arch/arm64/kvm/hyp/debug-sr.c
+++ b/arch/arm64/kvm/hyp/debug-sr.c
@@ -163,7 +163,7 @@ void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu)
 	if (!has_vhe())
 		__debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1);
 
-	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
+	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
 	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
@@ -185,7 +185,7 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
 	if (!has_vhe())
 		__debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1);
 
-	if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY))
+	if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY))
 		return;
 
 	host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
@@ -196,7 +196,7 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu)
 	__debug_save_state(vcpu, guest_dbg, guest_ctxt);
 	__debug_restore_state(vcpu, host_dbg, host_ctxt);
 
-	vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY;
+	vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY;
 }
 
 u32 __hyp_text __kvm_get_mdcr_el2(void)
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index e41a161d313a..fad1e164fe48 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -166,46 +166,3 @@ abort_guest_exit_end:
 	orr	x0, x0, x5
 1:	ret
 ENDPROC(__guest_exit)
-
-ENTRY(__fpsimd_guest_restore)
-	// x0: esr
-	// x1: vcpu
-	// x2-x29,lr: vcpu regs
-	// vcpu x0-x1 on the stack
-	stp	x2, x3, [sp, #-16]!
-	stp	x4, lr, [sp, #-16]!
-
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	x2, cptr_el2
-	bic	x2, x2, #CPTR_EL2_TFP
-	msr	cptr_el2, x2
-alternative_else
-	mrs	x2, cpacr_el1
-	orr	x2, x2, #CPACR_EL1_FPEN
-	msr	cpacr_el1, x2
-alternative_endif
-	isb
-
-	mov	x3, x1
-
-	ldr	x0, [x3, #VCPU_HOST_CONTEXT]
-	kern_hyp_va x0
-	add	x0, x0, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
-	bl	__fpsimd_save_state
-
-	add	x2, x3, #VCPU_CONTEXT
-	add	x0, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS)
-	bl	__fpsimd_restore_state
-
-	// Skip restoring fpexc32 for AArch64 guests
-	mrs	x1, hcr_el2
-	tbnz	x1, #HCR_RW_SHIFT, 1f
-	ldr	x4, [x3, #VCPU_FPEXC32_EL2]
-	msr	fpexc32_el2, x4
-1:
-	ldp	x4, lr, [sp], #16
-	ldp	x2, x3, [sp], #16
-	ldp	x0, x1, [sp], #16
-
-	eret
-ENDPROC(__fpsimd_guest_restore)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 05d836979032..24b4fbafe3e4 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -149,25 +149,6 @@ wa_epilogue:
 
 el1_trap:
 	get_vcpu_ptr	x1, x0
-
-	mrs		x0, esr_el2
-	lsr		x0, x0, #ESR_ELx_EC_SHIFT
-	/*
-	 * x0: ESR_EC
-	 * x1: vcpu pointer
-	 */
-
-	/*
-	 * 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.
-	 */
-alternative_if_not ARM64_HAS_NO_FPSIMD
-	cmp	x0, #ESR_ELx_EC_FP_ASIMD
-	b.eq	__fpsimd_guest_restore
-alternative_else_nop_endif
-
 	mov	x0, #ARM_EXCEPTION_TRAP
 	b	__guest_exit
 
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index c50cedc447f1..d496ef579859 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -22,21 +22,25 @@
 
 #include <kvm/arm_psci.h>
 
+#include <asm/cpufeature.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_host.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>
 
-static bool __hyp_text __fpsimd_enabled_nvhe(void)
+/* Check whether the FP regs were dirtied while in the host-side run loop: */
+static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu)
 {
-	return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP);
-}
+	if (vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE)
+		vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED |
+				      KVM_ARM64_FP_HOST);
 
-static bool fpsimd_enabled_vhe(void)
-{
-	return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN);
+	return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED);
 }
 
 /* Save the 32-bit only FPSIMD system register state */
@@ -93,7 +97,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
 
 	val = read_sysreg(cpacr_el1);
 	val |= CPACR_EL1_TTA;
-	val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN);
+	val &= ~CPACR_EL1_ZEN;
+	if (!update_fp_enabled(vcpu))
+		val &= ~CPACR_EL1_FPEN;
+
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(kvm_get_hyp_vector(), vbar_el1);
@@ -106,7 +113,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
 	__activate_traps_common(vcpu);
 
 	val = CPTR_EL2_DEFAULT;
-	val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ;
+	val |= CPTR_EL2_TTA | CPTR_EL2_TZ;
+	if (!update_fp_enabled(vcpu))
+		val |= CPTR_EL2_TFP;
+
 	write_sysreg(val, cptr_el2);
 }
 
@@ -319,6 +329,50 @@ static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 	}
 }
 
+static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu)
+{
+	struct user_fpsimd_state *host_fpsimd = vcpu->arch.host_fpsimd_state;
+
+	if (has_vhe())
+		write_sysreg(read_sysreg(cpacr_el1) | CPACR_EL1_FPEN,
+			     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 (system_supports_sve() &&
+		    (vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE)) {
+			struct thread_struct *thread = container_of(
+				host_fpsimd,
+				struct thread_struct, uw.fpsimd_state);
+
+			sve_save_state(sve_pffr(thread), &host_fpsimd->fpsr);
+		} else {
+			__fpsimd_save_state(host_fpsimd);
+		}
+
+		vcpu->arch.flags &= ~KVM_ARM64_FP_HOST;
+	}
+
+	__fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs);
+
+	/* Skip restoring fpexc32 for AArch64 guests */
+	if (!(read_sysreg(hcr_el2) & HCR_RW))
+		write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2],
+			     fpexc32_el2);
+
+	vcpu->arch.flags |= KVM_ARM64_FP_ENABLED;
+
+	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
@@ -335,11 +389,23 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	 * same PC once the SError has been injected, and replay the
 	 * trapping instruction.
 	 */
-	if (*exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu))
+	if (*exit_code != ARM_EXCEPTION_TRAP)
+		goto exit;
+
+	/*
+	 * 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.
+	 */
+	if (system_supports_fpsimd() &&
+	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_FP_ASIMD)
+		return __hyp_switch_fpsimd(vcpu);
+
+	if (!__populate_fault_info(vcpu))
 		return true;
 
-	if (static_branch_unlikely(&vgic_v2_cpuif_trap) &&
-	    *exit_code == ARM_EXCEPTION_TRAP) {
+	if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
 		bool valid;
 
 		valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
@@ -351,12 +417,8 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
 
-			if (ret == 1) {
-				if (__skip_instr(vcpu))
-					return true;
-				else
-					*exit_code = ARM_EXCEPTION_TRAP;
-			}
+			if (ret ==  1 && __skip_instr(vcpu))
+				return true;
 
 			if (ret == -1) {
 				/* Promote an illegal access to an
@@ -369,23 +431,21 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
 				*exit_code = ARM_EXCEPTION_EL1_SERROR;
 			}
+
+			goto exit;
 		}
 	}
 
 	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
-	    *exit_code == ARM_EXCEPTION_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) {
-			if (__skip_instr(vcpu))
-				return true;
-			else
-				*exit_code = ARM_EXCEPTION_TRAP;
-		}
+		if (ret == 1 && __skip_instr(vcpu))
+			return true;
 	}
 
+exit:
 	/* Return to the host kernel and handle the exit */
 	return false;
 }
@@ -428,7 +488,6 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
-	bool fp_enabled;
 	u64 exit_code;
 
 	host_ctxt = vcpu->arch.host_cpu_context;
@@ -454,19 +513,14 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	__set_host_arch_workaround_state(vcpu);
 
-	fp_enabled = fpsimd_enabled_vhe();
-
 	sysreg_save_guest_state_vhe(guest_ctxt);
 
 	__deactivate_traps(vcpu);
 
 	sysreg_restore_host_state_vhe(host_ctxt);
 
-	if (fp_enabled) {
-		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
-		__fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs);
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
 		__fpsimd_save_fpexc32(vcpu);
-	}
 
 	__debug_switch_to_host(vcpu);
 
@@ -478,7 +532,6 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_cpu_context *guest_ctxt;
-	bool fp_enabled;
 	u64 exit_code;
 
 	vcpu = kern_hyp_va(vcpu);
@@ -514,8 +567,6 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 
 	__set_host_arch_workaround_state(vcpu);
 
-	fp_enabled = __fpsimd_enabled_nvhe();
-
 	__sysreg_save_state_nvhe(guest_ctxt);
 	__sysreg32_save_state(vcpu);
 	__timer_disable_traps(vcpu);
@@ -526,11 +577,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
 
 	__sysreg_restore_state_nvhe(host_ctxt);
 
-	if (fp_enabled) {
-		__fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs);
-		__fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs);
+	if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
 		__fpsimd_save_fpexc32(vcpu);
-	}
 
 	/*
 	 * This must come after restoring the host sysregs, since a non-VHE
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index b3894df6bf1a..35bc16832efe 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -196,7 +196,7 @@ void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu)
 	sysreg[DACR32_EL2] = read_sysreg(dacr32_el2);
 	sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2);
 
-	if (has_vhe() || vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
+	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
 		sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2);
 }
 
@@ -218,7 +218,7 @@ void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu)
 	write_sysreg(sysreg[DACR32_EL2], dacr32_el2);
 	write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2);
 
-	if (has_vhe() || vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)
+	if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)
 		write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2);
 }
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 6e3b969391fd..a4363735d3f8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -31,7 +31,6 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_host.h>
@@ -338,7 +337,7 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu,
 {
 	if (p->is_write) {
 		vcpu_write_sys_reg(vcpu, p->regval, r->reg);
-		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
 		p->regval = vcpu_read_sys_reg(vcpu, r->reg);
 	}
@@ -369,7 +368,7 @@ static void reg_to_dbg(struct kvm_vcpu *vcpu,
 	}
 
 	*dbg_reg = val;
-	vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+	vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 }
 
 static void dbg_to_reg(struct kvm_vcpu *vcpu,
@@ -1441,7 +1440,7 @@ static bool trap_debug32(struct kvm_vcpu *vcpu,
 {
 	if (p->is_write) {
 		vcpu_cp14(vcpu, r->reg) = p->regval;
-		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
 		p->regval = vcpu_cp14(vcpu, r->reg);
 	}
@@ -1473,7 +1472,7 @@ static bool trap_xvr(struct kvm_vcpu *vcpu,
 		val |= p->regval << 32;
 		*dbg_reg = val;
 
-		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
+		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
 		p->regval = *dbg_reg >> 32;
 	}