[PATCH v6 63/64] KVM: arm64: nv: Fast-track 'InHost' exception returns

[Marc Zyngier <maz@kernel.org>]

A significant part of the ARMv8.3-NV extension is to trap ERET
instructions so that the hypervisor gets a chance to switch
from a vEL2 L1 guest to an EL1 L2 guest.

But this also has the unfortunate consequence of trapping ERET
in unsuspecting circumstances, such as staying at vEL2 (interrupt
handling while being in the guest hypervisor), or returning to host
userspace in the case of a VHE guest.

Although we already make some effort to handle these ERET quicker
by not doing the put/load dance, it is still way too far down the
line for it to be efficient enough.

For these cases, it would ideal to ERET directly, no question asked.
Of course, we can't do that. But the next best thing is to do it as
early as possible, in fixup_guest_exit(), much as we would handle
FPSIMD exceptions.

Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/emulate-nested.c | 29 +++------------------
 arch/arm64/kvm/hyp/vhe/switch.c | 46 +++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 1f6cf8fe9fe3..3f3b1296b4ac 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -76,8 +76,7 @@ static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr)
 
 void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 {
-	u64 spsr, elr, mode;
-	bool direct_eret;
+	u64 spsr, elr;
 
 	/*
 	 * Forward this trap to the virtual EL2 if the virtual
@@ -86,33 +85,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	if (forward_nv_traps(vcpu))
 		return;
 
-	/*
-	 * Going through the whole put/load motions is a waste of time
-	 * if this is a VHE guest hypervisor returning to its own
-	 * userspace, or the hypervisor performing a local exception
-	 * return. No need to save/restore registers, no need to
-	 * switch S2 MMU. Just do the canonical ERET.
-	 */
-	spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
-	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
-
-	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
-
-	direct_eret  = (mode == PSR_MODE_EL0t &&
-			vcpu_el2_e2h_is_set(vcpu) &&
-			vcpu_el2_tge_is_set(vcpu));
-	direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t);
-
-	if (direct_eret) {
-		*vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2);
-		*vcpu_cpsr(vcpu) = spsr;
-		trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr);
-		return;
-	}
-
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);
 
+	spsr = __vcpu_sys_reg(vcpu, SPSR_EL2);
+	spsr = kvm_check_illegal_exception_return(vcpu, spsr);
 	elr = __vcpu_sys_reg(vcpu, ELR_EL2);
 
 	trace_kvm_nested_eret(vcpu, elr, spsr);
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 65120c9027d6..f469bf51b4be 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -161,6 +161,51 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
 	__deactivate_traps_common(vcpu);
 }
 
+static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
+	u64 spsr, mode;
+
+	/*
+	 * Going through the whole put/load motions is a waste of time
+	 * if this is a VHE guest hypervisor returning to its own
+	 * userspace, or the hypervisor performing a local exception
+	 * return. No need to save/restore registers, no need to
+	 * switch S2 MMU. Just do the canonical ERET.
+	 *
+	 * Unless the trap has to be forwarded further down the line,
+	 * of course...
+	 */
+	if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV)
+		return false;
+
+	spsr = read_sysreg_el1(SYS_SPSR);
+	spsr = __fixup_spsr_el2_read(ctxt, spsr);
+	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	switch (mode) {
+	case PSR_MODE_EL0t:
+		if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
+			return false;
+		break;
+	case PSR_MODE_EL2t:
+		mode = PSR_MODE_EL1t;
+		break;
+	case PSR_MODE_EL2h:
+		mode = PSR_MODE_EL1h;
+		break;
+	default:
+		return false;
+	}
+
+	spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+
+	write_sysreg_el2(spsr, SYS_SPSR);
+	write_sysreg_el2(read_sysreg_el1(SYS_ELR), SYS_ELR);
+
+	return true;
+}
+
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
@@ -170,6 +215,7 @@ static const exit_handler_fn hyp_exit_handlers[] = {
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+	[ESR_ELx_EC_ERET]		= kvm_hyp_handle_eret,
 };
 
 static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
-- 
2.30.2