Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   Santosh Shukla <santosh.shukla@amd.com>
To:     <kvm@vger.kernel.org>, <seanjc@google.com>
CC:     <pbonzini@redhat.com>, <jmattson@google.com>, <joro@8bytes.org>,
        <linux-kernel@vger.kernel.org>, <mail@maciej.szmigiero.name>,
        <mlevitsk@redhat.com>, <thomas.lendacky@amd.com>,
        <vkuznets@redhat.com>
Subject: [PATCHv3 10/10] KVM: nSVM: implement support for nested VNMI
Date:   Mon, 27 Feb 2023 09:24:00 +0530
Message-ID: <20230227035400.1498-11-santosh.shukla@amd.com>
In-Reply-To: <20230227035400.1498-1-santosh.shukla@amd.com>
References: <20230227035400.1498-1-santosh.shukla@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 27 Feb 2023 03:57:23.1946
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 2f73c24a-64dd-45b3-b459-08db1876bb6c
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: DM6NAM11FT114.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: IA0PR12MB7724
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Allows L1 to use vNMI to accelerate its injection of NMI
to L2 by passing through vNMI int_ctl bits from vmcb12
to/from vmcb02.

In case of L1 and L2 both using VNMI- Copy VNMI bits from vmcb12 to
vmcb02 during entry and vice-versa during exit.
And in case of L1 uses VNMI and L2 doesn't- Copy VNMI bits from vmcb01 to
vmcb02 during entry and vice-versa during exit.

Tested with the KVM-unit-test and Nested Guest scenario.

Co-developed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Santosh Shukla <santosh.shukla@amd.com>
---
v3:
- Fix identiation and style issue.
- Fix SOB
- Removed `svm->nmi_masked` var use for nested svm case.
- Reworded the commit description.
https://lore.kernel.org/all/Y9m15P8xQ2dxvIzd@google.com/

 arch/x86/kvm/svm/nested.c | 33 +++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c    |  5 +++++
 arch/x86/kvm/svm/svm.h    |  6 ++++++
 3 files changed, 44 insertions(+)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 74e9e9e76d77..b018fe2fdf88 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -281,6 +281,11 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 	if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl)))
 		return false;
 
+	if (CC((control->int_ctl & V_NMI_ENABLE_MASK) &&
+	       !vmcb12_is_intercept(control, INTERCEPT_NMI))) {
+		return false;
+	}
+
 	return true;
 }
 
@@ -436,6 +441,9 @@ void nested_sync_control_from_vmcb02(struct vcpu_svm *svm)
 	if (nested_vgif_enabled(svm))
 		mask |= V_GIF_MASK;
 
+	if (nested_vnmi_enabled(svm))
+		mask |= V_NMI_BLOCKING_MASK | V_NMI_PENDING_MASK;
+
 	svm->nested.ctl.int_ctl        &= ~mask;
 	svm->nested.ctl.int_ctl        |= svm->vmcb->control.int_ctl & mask;
 }
@@ -655,6 +663,17 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	else
 		int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK);
 
+	if (vnmi) {
+		if (vmcb01->control.int_ctl & V_NMI_PENDING_MASK) {
+			svm->vcpu.arch.nmi_pending++;
+			kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
+		}
+		if (nested_vnmi_enabled(svm))
+			int_ctl_vmcb12_bits |= (V_NMI_PENDING_MASK |
+						V_NMI_ENABLE_MASK |
+						V_NMI_BLOCKING_MASK);
+	}
+
 	/* Copied from vmcb01.  msrpm_base can be overwritten later.  */
 	vmcb02->control.nested_ctl = vmcb01->control.nested_ctl;
 	vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa;
@@ -1058,6 +1077,20 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		svm_update_lbrv(vcpu);
 	}
 
+	if (vnmi) {
+		if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK)
+			vmcb01->control.int_ctl |= V_NMI_BLOCKING_MASK;
+		else
+			vmcb01->control.int_ctl &= ~V_NMI_BLOCKING_MASK;
+
+		if (vcpu->arch.nmi_pending) {
+			vcpu->arch.nmi_pending--;
+			vmcb01->control.int_ctl |= V_NMI_PENDING_MASK;
+		} else
+			vmcb01->control.int_ctl &= ~V_NMI_PENDING_MASK;
+
+	}
+
 	/*
 	 * On vmexit the  GIF is set to false and
 	 * no event can be injected in L1.
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 84d9d2566629..08b7856e2da2 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4226,6 +4226,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF);
 
+	svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_AMD_VNMI);
+
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
 	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
@@ -4981,6 +4983,9 @@ static __init void svm_set_cpu_caps(void)
 		if (vgif)
 			kvm_cpu_cap_set(X86_FEATURE_VGIF);
 
+		if (vnmi)
+			kvm_cpu_cap_set(X86_FEATURE_AMD_VNMI);
+
 		/* Nested VM can receive #VMEXIT instead of triggering #GP */
 		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
 	}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index fb48c347bbe0..e229eadbf1ce 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -266,6 +266,7 @@ struct vcpu_svm {
 	bool pause_filter_enabled         : 1;
 	bool pause_threshold_enabled      : 1;
 	bool vgif_enabled                 : 1;
+	bool vnmi_enabled                 : 1;
 
 	u32 ldr_reg;
 	u32 dfr_reg;
@@ -540,6 +541,11 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm)
 	return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE;
 }
 
+static inline bool nested_vnmi_enabled(struct vcpu_svm *svm)
+{
+	return svm->vnmi_enabled && (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK);
+}
+
 static inline bool is_x2apic_msrpm_offset(u32 offset)
 {
 	/* 4 msrs per u8, and 4 u8 in u32 */
-- 
2.25.1