Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
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>
Subject: [PATCH v11 096/113] KVM: TDX: Implement callbacks for MSR operations for TDX
Date:   Thu, 12 Jan 2023 08:32:44 -0800
Message-Id: <3140c1573c4da61ffa15ce9e0b95fea3ed19537d.1673539699.git.isaku.yamahata@intel.com>
In-Reply-To: <cover.1673539699.git.isaku.yamahata@intel.com>
References: <cover.1673539699.git.isaku.yamahata@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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

Implements set_msr/get_msr/has_emulated_msr methods for TDX to handle
hypercall from guest TD for paravirtualized rdmsr and wrmsr.  The TDX
module virtualizes MSRs.  For some MSRs, it injects #VE to the guest TD
upon RDMSR or WRMSR.  The exact list of such MSRs are defined in the spec.

Upon #VE, the guest TD may execute hypercalls,
TDG.VP.VMCALL<INSTRUCTION.RDMSR> and TDG.VP.VMCALL<INSTRUCTION.WRMSR>,
which are defined in GHCI (Guest-Host Communication Interface) so that the
host VMM (e.g. KVM) can virtualize the MSRs.

There are three classes of MSRs virtualization.
- non-configurable: TDX module directly virtualizes it. VMM can't configure.
  the value set by KVM_SET_MSR_INDEX_LIST is ignored.
- configurable: TDX module directly virtualizes it. VMM can configure at the
  VM creation time.  The value set by KVM_SET_MSR_INDEX_LIST is used.
- #VE case
  Guest TD would issue TDG.VP.VMCALL<INSTRUCTION.{WRMSR,RDMSR> and
  VMM handles the MSR hypercall. The value set by KVM_SET_MSR_INDEX_LIST is
  used.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
Changes v10 -> v11
- added .msr_filter_changed()
---
 arch/x86/kvm/vmx/main.c    | 44 ++++++++++++++++++++---
 arch/x86/kvm/vmx/tdx.c     | 74 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/x86_ops.h |  6 ++++
 arch/x86/kvm/x86.c         |  1 -
 arch/x86/kvm/x86.h         |  2 ++
 5 files changed, 122 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index f9339d8f95eb..cb79d64a2058 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -183,6 +183,42 @@ static void vt_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 	vmx_handle_exit_irqoff(vcpu);
 }
 
+static int vt_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	if (unlikely(is_td_vcpu(vcpu)))
+		return tdx_set_msr(vcpu, msr_info);
+
+	return vmx_set_msr(vcpu, msr_info);
+}
+
+/*
+ * The kvm parameter can be NULL (module initialization, or invocation before
+ * VM creation). Be sure to check the kvm parameter before using it.
+ */
+static bool vt_has_emulated_msr(struct kvm *kvm, u32 index)
+{
+	if (kvm && is_td(kvm))
+		return tdx_has_emulated_msr(index, true);
+
+	return vmx_has_emulated_msr(kvm, index);
+}
+
+static int vt_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	if (unlikely(is_td_vcpu(vcpu)))
+		return tdx_get_msr(vcpu, msr_info);
+
+	return vmx_get_msr(vcpu, msr_info);
+}
+
+static void vt_msr_filter_changed(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu))
+		return;
+
+	vmx_msr_filter_changed(vcpu);
+}
+
 static void vt_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 {
 	struct pi_desc *pi = vcpu_to_pi_desc(vcpu);
@@ -428,7 +464,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.hardware_enable = vmx_hardware_enable,
 	.hardware_disable = vt_hardware_disable,
-	.has_emulated_msr = vmx_has_emulated_msr,
+	.has_emulated_msr = vt_has_emulated_msr,
 
 	.is_vm_type_supported = vt_is_vm_type_supported,
 	.vm_size = sizeof(struct kvm_vmx),
@@ -448,8 +484,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
 	.get_msr_feature = vmx_get_msr_feature,
-	.get_msr = vmx_get_msr,
-	.set_msr = vmx_set_msr,
+	.get_msr = vt_get_msr,
+	.set_msr = vt_set_msr,
 	.get_segment_base = vmx_get_segment_base,
 	.get_segment = vmx_get_segment,
 	.set_segment = vmx_set_segment,
@@ -560,7 +596,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
 	.migrate_timers = vmx_migrate_timers,
 
-	.msr_filter_changed = vmx_msr_filter_changed,
+	.msr_filter_changed = vt_msr_filter_changed,
 	.complete_emulated_msr = kvm_complete_insn_gp,
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 8fab8e641070..5d8894899055 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1629,6 +1629,80 @@ void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 	*error_code = 0;
 }
 
+static bool tdx_is_emulated_kvm_msr(u32 index, bool write)
+{
+	switch (index) {
+	case MSR_KVM_POLL_CONTROL:
+		return true;
+	default:
+		return false;
+	}
+}
+
+bool tdx_has_emulated_msr(u32 index, bool write)
+{
+	switch (index) {
+	case MSR_IA32_UCODE_REV:
+	case MSR_IA32_ARCH_CAPABILITIES:
+	case MSR_IA32_POWER_CTL:
+	case MSR_MTRRcap:
+	case 0x200 ... 0x26f:
+		/* IA32_MTRR_PHYS{BASE, MASK}, IA32_MTRR_FIX*_* */
+	case MSR_IA32_CR_PAT:
+	case MSR_MTRRdefType:
+	case MSR_IA32_TSC_DEADLINE:
+	case MSR_IA32_MISC_ENABLE:
+	case MSR_PLATFORM_INFO:
+	case MSR_MISC_FEATURES_ENABLES:
+	case MSR_IA32_MCG_CAP:
+	case MSR_IA32_MCG_STATUS:
+	case MSR_IA32_MCG_CTL:
+	case MSR_IA32_MCG_EXT_CTL:
+	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
+	case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1:
+		/* MSR_IA32_MCx_{CTL, STATUS, ADDR, MISC, CTL2} */
+		return true;
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
+		/*
+		 * x2APIC registers that are virtualized by the CPU can't be
+		 * emulated, KVM doesn't have access to the virtual APIC page.
+		 */
+		switch (index) {
+		case X2APIC_MSR(APIC_TASKPRI):
+		case X2APIC_MSR(APIC_PROCPRI):
+		case X2APIC_MSR(APIC_EOI):
+		case X2APIC_MSR(APIC_ISR) ... X2APIC_MSR(APIC_ISR + APIC_ISR_NR):
+		case X2APIC_MSR(APIC_TMR) ... X2APIC_MSR(APIC_TMR + APIC_ISR_NR):
+		case X2APIC_MSR(APIC_IRR) ... X2APIC_MSR(APIC_IRR + APIC_ISR_NR):
+			return false;
+		default:
+			return true;
+		}
+	case MSR_IA32_APICBASE:
+	case MSR_EFER:
+		return !write;
+	case 0x4b564d00 ... 0x4b564dff:
+		/* KVM custom MSRs */
+		return tdx_is_emulated_kvm_msr(index, write);
+	default:
+		return false;
+	}
+}
+
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+	if (tdx_has_emulated_msr(msr->index, false))
+		return kvm_get_msr_common(vcpu, msr);
+	return 1;
+}
+
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+	if (tdx_has_emulated_msr(msr->index, true))
+		return kvm_set_msr_common(vcpu, msr);
+	return 1;
+}
+
 int tdx_dev_ioctl(void __user *argp)
 {
 	struct kvm_tdx_capabilities __user *user_caps;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 38fd5c3eee2f..3b747fb5bc20 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -171,6 +171,9 @@ void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
 void tdx_inject_nmi(struct kvm_vcpu *vcpu);
 void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 		u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code);
+bool tdx_has_emulated_msr(u32 index, bool write);
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
 int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
@@ -210,6 +213,9 @@ static inline void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mo
 static inline void tdx_inject_nmi(struct kvm_vcpu *vcpu) {}
 static inline void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1,
 				     u64 *info2, u32 *intr_info, u32 *error_code) {}
+static inline bool tdx_has_emulated_msr(u32 index, bool write) { return false; }
+static inline int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
+static inline int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
 
 static inline int tdx_vm_ioctl(struct kvm *kvm, void __user *argp) { return -EOPNOTSUPP; }
 static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ad8735874f1b..fe5bd1ab0eec 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -87,7 +87,6 @@
 #include "trace.h"
 
 #define MAX_IO_MSRS 256
-#define KVM_MAX_MCE_BANKS 32
 
 struct kvm_caps kvm_caps __read_mostly = {
 	.supported_mce_cap = MCG_CTL_P | MCG_SER_P,
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 9de72586f406..028bf3eaa43b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -8,6 +8,8 @@
 #include "kvm_cache_regs.h"
 #include "kvm_emulate.h"
 
+#define KVM_MAX_MCE_BANKS 32
+
 struct kvm_caps {
 	/* control of guest tsc rate supported? */
 	bool has_tsc_control;
-- 
2.25.1