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:   Vitaly Kuznetsov <vkuznets@redhat.com>
To:     kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
        Sean Christopherson <seanjc@google.com>
Cc:     Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Michael Kelley <mikelley@microsoft.com>,
        Siddharth Chandrasekaran <sidcha@amazon.de>,
        Yuan Yao <yuan.yao@linux.intel.com>,
        Maxim Levitsky <mlevitsk@redhat.com>,
        linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v11 26/46] KVM: nVMX: hyper-v: Enable L2 TLB flush
Date:   Tue,  4 Oct 2022 14:39:36 +0200
Message-Id: <20221004123956.188909-27-vkuznets@redhat.com>
In-Reply-To: <20221004123956.188909-1-vkuznets@redhat.com>
References: <20221004123956.188909-1-vkuznets@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain
Content-Transfer-Encoding: 8bit
Precedence: bulk

Enable L2 TLB flush feature on nVMX when:
- Enlightened VMCS is in use.
- The feature flag is enabled in eVMCS.
- The feature flag is enabled in partition assist page.

Perform synthetic vmexit to L1 after processing TLB flush call upon
request (HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH).

Note: nested_evmcs_l2_tlb_flush_enabled() uses cached VP assist page copy
which gets updated from nested_vmx_handle_enlightened_vmptrld(). This is
also guaranteed to happen post migration with eVMCS backed L2 running.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/include/asm/hyperv-tlfs.h |  9 +++++++++
 arch/x86/kvm/vmx/hyperv.c          | 17 +++++++++++++++++
 arch/x86/kvm/vmx/hyperv.h          |  1 +
 arch/x86/kvm/vmx/nested.c          | 20 ++++++++++++++++++++
 4 files changed, 47 insertions(+)

diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 6639979302ab..b25c6792d409 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -600,6 +600,15 @@ struct hv_enlightened_vmcs {
 
 #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL			0xFFFF
 
+/*
+ * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by
+ * pairing it with architecturally impossible exit reasons.  Bit 28 is set only
+ * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit
+ * is pending.  I.e. it will never be set by hardware for non-SMI exits (there
+ * are only three), nor will it ever be set unless the VMM is an STM.
+ */
+#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH		0x10000031
+
 /*
  * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose
  * SVM enlightenments to guests.
diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c
index bceca1a99804..04a0bba58c7d 100644
--- a/arch/x86/kvm/vmx/hyperv.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -5,6 +5,7 @@
 
 #include "../cpuid.h"
 #include "hyperv.h"
+#include "nested.h"
 #include "vmcs.h"
 #include "vmx.h"
 #include "trace.h"
@@ -500,6 +501,22 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+	if (!hv_vcpu || !evmcs)
+		return false;
+
+	if (!evmcs->hv_enlightenments_control.nested_flush_hypercall)
+		return false;
+
+	return hv_vcpu->vp_assist_page.nested_control.features.directhypercall;
+}
+
 void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu)
 {
+	nested_vmx_vmexit(vcpu, HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH, 0, 0);
 }
diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h
index 8bf366730d33..571e7929d14e 100644
--- a/arch/x86/kvm/vmx/hyperv.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -243,6 +243,7 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 			uint16_t *vmcs_version);
 void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
 int nested_evmcs_check_controls(struct vmcs12 *vmcs12);
+bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu);
 void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
 
 #endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b7a1290b1ada..96da5931ac80 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1131,6 +1131,15 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	/*
+	 * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
+	 * L2's VP_ID upon request from the guest. Make sure we check for
+	 * pending entries in the right FIFO upon L1/L2 transition as these
+	 * requests are put by other vCPUs asynchronously.
+	 */
+	if (to_hv_vcpu(vcpu) && enable_ept)
+		kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+
 	/*
 	 * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
 	 * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
@@ -3266,6 +3275,12 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 
 static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy
+	 * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory
+	 * to make nested_evmcs_l2_tlb_flush_enabled() work correctly post
+	 * migration.
+	 */
 	if (!nested_get_evmcs_page(vcpu)) {
 		pr_debug_ratelimited("%s: enlightened vmptrld failed\n",
 				     __func__);
@@ -6142,6 +6157,11 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
 		 * Handle L2's bus locks in L0 directly.
 		 */
 		return true;
+	case EXIT_REASON_VMCALL:
+		/* Hyper-V L2 TLB flush hypercall is handled by L0 */
+		return guest_hv_cpuid_has_l2_tlb_flush(vcpu) &&
+			nested_evmcs_l2_tlb_flush_enabled(vcpu) &&
+			kvm_hv_is_tlb_flush_hcall(vcpu);
 	default:
 		break;
 	}
-- 
2.37.3