Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.33 as permitted sender) client-ip=23.128.96.33;
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>, chen.bo@intel.com,
        hang.yuan@intel.com, tina.zhang@intel.com
Subject: [PATCH v16 101/116] KVM: TDX: Silently ignore INIT/SIPI
Date:   Mon, 16 Oct 2023 09:14:53 -0700
Message-Id: <0a94ce8abb98fb291f20da10b9b9389b081f2188.1697471314.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1697471314.git.isaku.yamahata@intel.com>
References: <cover.1697471314.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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

The TDX module API doesn't provide API for VMM to inject INIT IPI and SIPI.
Instead it defines the different protocols to boot application processors.
Ignore INIT and SIPI events for the TDX guest.

There are two options. 1) (silently) ignore INIT/SIPI request or 2) return
error to guest TDs somehow.  Given that TDX guest is paravirtualized to
boot AP, the option 1 is chosen for simplicity.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  2 ++
 arch/x86/kvm/lapic.c               | 19 +++++++++++-------
 arch/x86/kvm/svm/svm.c             |  1 +
 arch/x86/kvm/vmx/main.c            | 32 ++++++++++++++++++++++++++++--
 arch/x86/kvm/vmx/tdx.c             |  4 ++--
 6 files changed, 48 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 19e1f22b92b1..8b3c5f2179cf 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -146,6 +146,7 @@ KVM_X86_OP_OPTIONAL(migrate_timers)
 KVM_X86_OP(msr_filter_changed)
 KVM_X86_OP(complete_emulated_msr)
 KVM_X86_OP(vcpu_deliver_sipi_vector)
+KVM_X86_OP(vcpu_deliver_init)
 KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
 
 #undef KVM_X86_OP
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 641f769b30d1..529c7e610d47 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1814,6 +1814,7 @@ struct kvm_x86_ops {
 	int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
 
 	void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
+	void (*vcpu_deliver_init)(struct kvm_vcpu *vcpu);
 
 	/*
 	 * Returns vCPU specific APICv inhibit reasons
@@ -2050,6 +2051,7 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
+void kvm_vcpu_deliver_init(struct kvm_vcpu *vcpu);
 
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 		    int reason, bool has_error_code, u32 error_code);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e037923edb5e..13d5f5c45c79 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -3261,6 +3261,16 @@ int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
 	return 0;
 }
 
+void kvm_vcpu_deliver_init(struct kvm_vcpu *vcpu)
+{
+	kvm_vcpu_reset(vcpu, true);
+	if (kvm_vcpu_is_bsp(vcpu))
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	else
+		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_init);
+
 int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -3292,13 +3302,8 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
-		kvm_vcpu_reset(vcpu, true);
-		if (kvm_vcpu_is_bsp(apic->vcpu))
-			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-		else
-			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
-	}
+	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events))
+		static_call(kvm_x86_vcpu_deliver_init)(vcpu);
 	if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events)) {
 		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
 			/* evaluate pending_events before reading the vector */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 70c1f7999399..30d9cc11a4b5 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -5017,6 +5017,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.complete_emulated_msr = svm_complete_emulated_msr,
 
 	.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
+	.vcpu_deliver_init = kvm_vcpu_deliver_init,
 	.vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons,
 };
 
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index ad91efcc2413..dd050a6196ae 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -331,6 +331,14 @@ static void vt_enable_smi_window(struct kvm_vcpu *vcpu)
 }
 #endif
 
+static bool vt_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu))
+		return true;
+
+	return vmx_apic_init_signal_blocked(vcpu);
+}
+
 static void vt_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi = vcpu_to_pi_desc(vcpu);
@@ -359,6 +367,25 @@ static void vt_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
 	vmx_deliver_interrupt(apic, delivery_mode, trig_mode, vector);
 }
 
+static void vt_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
+{
+	if (is_td_vcpu(vcpu))
+		return;
+
+	kvm_vcpu_deliver_sipi_vector(vcpu, vector);
+}
+
+static void vt_vcpu_deliver_init(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu)) {
+		/* TDX doesn't support INIT.  Ignore INIT event */
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+		return;
+	}
+
+	kvm_vcpu_deliver_init(vcpu);
+}
+
 static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu)) {
@@ -722,13 +749,14 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 #endif
 
 	.can_emulate_instruction = vmx_can_emulate_instruction,
-	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
+	.apic_init_signal_blocked = vt_apic_init_signal_blocked,
 	.migrate_timers = vmx_migrate_timers,
 
 	.msr_filter_changed = vt_msr_filter_changed,
 	.complete_emulated_msr = kvm_complete_insn_gp,
 
-	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
+	.vcpu_deliver_sipi_vector = vt_vcpu_deliver_sipi_vector,
+	.vcpu_deliver_init = vt_vcpu_deliver_init,
 
 	.mem_enc_ioctl = vt_mem_enc_ioctl,
 	.vcpu_mem_enc_ioctl = vt_vcpu_mem_enc_ioctl,
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index f368f9c950ad..14ab1450dda4 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -757,8 +757,8 @@ void tdx_vcpu_free(struct kvm_vcpu *vcpu)
 void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 
-	/* Ignore INIT silently because TDX doesn't support INIT event. */
-	if (init_event)
+	/* vcpu_deliver_init method silently discards INIT event. */
+	if (KVM_BUG_ON(init_event, vcpu->kvm))
 		return;
 	if (KVM_BUG_ON(is_td_vcpu_created(to_tdx(vcpu)), vcpu->kvm))
 		return;
-- 
2.25.1