From:   isaku.yamahata@intel.com
To:     kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
        Paolo Bonzini <pbonzini@redhat.com>, erdemaktas@google.com,
        Sean Christopherson <seanjc@google.com>,
        Sagi Shahar <sagis@google.com>,
        David Matlack <dmatlack@google.com>,
        Kai Huang <kai.huang@intel.com>,
        Zhi Wang <zhi.wang.linux@gmail.com>
Subject: [PATCH v13 092/113] KVM: TDX: Handle TDX PV HLT hypercall
Date:   Sun, 12 Mar 2023 10:56:56 -0700
Message-Id: <31a159667678eba69e279eca96061574f1d35354.1678643052.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1678643051.git.isaku.yamahata@intel.com>
References: <cover.1678643051.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Isaku Yamahata <isaku.yamahata@intel.com>

Wire up TDX PV HLT hypercall to the KVM backend function.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/kvm/vmx/tdx.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 arch/x86/kvm/vmx/tdx.h |  3 +++
 2 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 62cd3e899560..a28399d1fd6e 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -627,7 +627,32 @@ void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu)
 {
-	return pi_has_pending_interrupt(vcpu);
+	bool ret = pi_has_pending_interrupt(vcpu);
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	if (ret || vcpu->arch.mp_state != KVM_MP_STATE_HALTED)
+		return true;
+
+	if (tdx->interrupt_disabled_hlt)
+		return false;
+
+	/*
+	 * This is for the case where the virtual interrupt is recognized,
+	 * i.e. set in vmcs.RVI, between the STI and "HLT".  KVM doesn't have
+	 * access to RVI and the interrupt is no longer in the PID (because it
+	 * was "recognized".  It doesn't get delivered in the guest because the
+	 * TDCALL completes before interrupts are enabled.
+	 *
+	 * TDX modules sets RVI while in an STI interrupt shadow.
+	 * - TDExit(typically TDG.VP.VMCALL<HLT>) from the guest to TDX module.
+	 *   The interrupt shadow at this point is gone.
+	 * - It knows that there is an interrupt that can be delivered
+	 *   (RVI > PPR && EFLAGS.IF=1, the other conditions of 29.2.2 don't
+	 *    matter)
+	 * - It forwards the TDExit nevertheless, to a clueless hypervisor that
+	 *   has no way to glean either RVI or PPR.
+	 */
+	return !!xchg(&tdx->buggy_hlt_workaround, 0);
 }
 
 void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
@@ -978,6 +1003,17 @@ static int tdx_emulate_cpuid(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int tdx_emulate_hlt(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	/* See tdx_protected_apic_has_interrupt() to avoid heavy seamcall */
+	tdx->interrupt_disabled_hlt = tdvmcall_a0_read(vcpu);
+
+	tdvmcall_set_return_code(vcpu, TDG_VP_VMCALL_SUCCESS);
+	return kvm_emulate_halt_noskip(vcpu);
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	if (tdvmcall_exit_type(vcpu))
@@ -986,6 +1022,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 	switch (tdvmcall_leaf(vcpu)) {
 	case EXIT_REASON_CPUID:
 		return tdx_emulate_cpuid(vcpu);
+	case EXIT_REASON_HLT:
+		return tdx_emulate_hlt(vcpu);
 	default:
 		break;
 	}
@@ -1319,6 +1357,8 @@ void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
 	struct kvm_vcpu *vcpu = apic->vcpu;
 	struct vcpu_tdx *tdx = to_tdx(vcpu);
 
+	/* See comment in tdx_protected_apic_has_interrupt(). */
+	tdx->buggy_hlt_workaround = 1;
 	/* TDX supports only posted interrupt.  No lapic emulation. */
 	__vmx_deliver_posted_interrupt(vcpu, &tdx->pi_desc, vector);
 }
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index fa44a1a9295f..71818c500186 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -93,6 +93,9 @@ struct vcpu_tdx {
 	bool host_state_need_restore;
 	u64 msr_host_kernel_gs_base;
 
+	bool interrupt_disabled_hlt;
+	unsigned int buggy_hlt_workaround;
+
 	/*
 	 * Dummy to make pmu_intel not corrupt memory.
 	 * TODO: Support PMU for TDX.  Future work.
-- 
2.25.1