Received-SPF: pass (google.com: domain of linux-kernel+bounces-70890-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: Yang Weijiang <weijiang.yang@intel.com>
To: seanjc@google.com,
	pbonzini@redhat.com,
	dave.hansen@intel.com,
	x86@kernel.org,
	kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: peterz@infradead.org,
	chao.gao@intel.com,
	rick.p.edgecombe@intel.com,
	mlevitsk@redhat.com,
	john.allen@amd.com,
	weijiang.yang@intel.com
Subject: [PATCH v10 25/27] KVM: nVMX: Introduce new VMX_BASIC bit for event error_code delivery to L1
Date: Sun, 18 Feb 2024 23:47:31 -0800
Message-ID: <20240219074733.122080-26-weijiang.yang@intel.com>
In-Reply-To: <20240219074733.122080-1-weijiang.yang@intel.com>
References: <20240219074733.122080-1-weijiang.yang@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Per SDM description(Vol.3D, Appendix A.1):
"If bit 56 is read as 1, software can use VM entry to deliver a hardware
exception with or without an error code, regardless of vector"

Modify has_error_code check before inject events to nested guest. Only
enforce the check when guest is in real mode, the exception is not hard
exception and the platform doesn't enumerate bit56 in VMX_BASIC, in all
other case ignore the check to make the logic consistent with SDM.

Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Chao Gao <chao.gao@intel.com>
---
 arch/x86/kvm/vmx/nested.c | 27 ++++++++++++++++++---------
 arch/x86/kvm/vmx/nested.h |  5 +++++
 2 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 4be0078ca713..0439208523b8 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1230,9 +1230,9 @@ static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
 {
 	const u64 feature_and_reserved =
 		/* feature (except bit 48; see below) */
-		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
+		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) | BIT_ULL(56) |
 		/* reserved */
-		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
+		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 57);
 	u64 vmx_basic = vmcs_config.nested.basic;
 
 	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
@@ -2865,7 +2865,6 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
 		u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
 		u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
 		bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
-		bool should_have_error_code;
 		bool urg = nested_cpu_has2(vmcs12,
 					   SECONDARY_EXEC_UNRESTRICTED_GUEST);
 		bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;
@@ -2882,12 +2881,20 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
 		    CC(intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
 			return -EINVAL;
 
-		/* VM-entry interruption-info field: deliver error code */
-		should_have_error_code =
-			intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
-			x86_exception_has_error_code(vector);
-		if (CC(has_error_code != should_have_error_code))
-			return -EINVAL;
+		/*
+		 * Cannot deliver error code in real mode or if the interrupt
+		 * type is not hardware exception. For other cases, do the
+		 * consistency check only if the vCPU doesn't enumerate
+		 * VMX_BASIC_NO_HW_ERROR_CODE_CC.
+		 */
+		if (!prot_mode || intr_type != INTR_TYPE_HARD_EXCEPTION) {
+			if (CC(has_error_code))
+				return -EINVAL;
+		} else if (!nested_cpu_has_no_hw_errcode_cc(vcpu)) {
+			if (CC(has_error_code !=
+			       x86_exception_has_error_code(vector)))
+				return -EINVAL;
+		}
 
 		/* VM-entry exception error code */
 		if (CC(has_error_code &&
@@ -7011,6 +7018,8 @@ static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs)
 
 	if (cpu_has_vmx_basic_inout())
 		msrs->basic |= VMX_BASIC_INOUT;
+	if (cpu_has_vmx_basic_no_hw_errcode())
+		msrs->basic |= VMX_BASIC_NO_HW_ERROR_CODE_CC;
 }
 
 static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs)
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index cce4e2aa30fb..747061c2aeb9 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -285,6 +285,11 @@ static inline bool nested_cr4_valid(struct kvm_vcpu *vcpu, unsigned long val)
 	       __kvm_is_valid_cr4(vcpu, val);
 }
 
+static inline bool nested_cpu_has_no_hw_errcode_cc(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.basic & VMX_BASIC_NO_HW_ERROR_CODE_CC;
+}
+
 /* No difference in the restrictions on guest and host CR4 in VMX operation. */
 #define nested_guest_cr4_valid	nested_cr4_valid
 #define nested_host_cr4_valid	nested_cr4_valid
-- 
2.43.0