diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 65eead8362e0..c79747d5f4dd 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1112,7 +1112,8 @@ struct kvm_vcpu_arch {
 #define IN_NESTED_ERET		__vcpu_single_flag(sflags, BIT(7))
 /* SError pending for nested guest */
 #define NESTED_SERROR_PENDING	__vcpu_single_flag(sflags, BIT(8))
-
+/* KVM is currently emulating an L2 to L1 exception */
+#define IN_NESTED_EXCEPTION	__vcpu_single_flag(sflags, BIT(9))
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
 #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) +	\
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index dba7ced74ca5..15c691a6266d 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2862,6 +2862,8 @@ static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2,
 
 	preempt_disable();
 
+	vcpu_set_flag(vcpu, IN_NESTED_EXCEPTION);
+
 	/*
 	 * We may have an exception or PC update in the EL0/EL1 context.
 	 * Commit it before entering EL2.
@@ -2884,6 +2886,8 @@ static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2,
 	__kvm_adjust_pc(vcpu);
 
 	kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	vcpu_clear_flag(vcpu, IN_NESTED_EXCEPTION);
+
 	preempt_enable();
 
 	if (kvm_vcpu_has_pmu(vcpu))
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 15e17aca1dec..3f6b1e29cd6b 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -28,6 +28,20 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
 	if (!system_supports_fpsimd())
 		return;
 
+	/*
+	 * Avoid needless save/restore of the guest's common
+	 * FPSIMD/SVE/SME regs during transitions between L1/L2.
+	 *
+	 * These transitions only happens in a non-preemptible context
+	 * where the host regs have already been saved and unbound. The
+	 * live registers are either free or owned by the guest.
+	 */
+	if (vcpu_get_flag(vcpu, IN_NESTED_ERET) ||
+	    vcpu_get_flag(vcpu, IN_NESTED_EXCEPTION)) {
+		WARN_ON_ONCE(host_owns_fp_regs());
+		return;
+	}
+
 	/*
 	 * Ensure that any host FPSIMD/SVE/SME state is saved and unbound such
 	 * that the host kernel is responsible for restoring this state upon
@@ -102,6 +116,18 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
 
+	/*
+	 * See comment in kvm_arch_vcpu_load_fp(). Note that we also rely on
+	 * the guest's max VL to have been set by fpsimd_lazy_switch_to_host()
+	 * so that any intervening kernel-mode SIMD (NEON or otherwise)
+	 * operation sees the full guest state that needs saving.
+	 */
+	if (vcpu_get_flag(vcpu, IN_NESTED_ERET) ||
+	    vcpu_get_flag(vcpu, IN_NESTED_EXCEPTION)) {
+		WARN_ON_ONCE(host_owns_fp_regs());
+		return;
+	}
+
 	local_irq_save(flags);
 
 	if (guest_owns_fp_regs()) {