Resguardo inicial

linux-7.2.3/arch/x86/kvm/svm/hyperv.c

@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD SVM specific code for Hyper-V on KVM.
+ *
+ * Copyright 2022 Red Hat, Inc. and/or its affiliates.
+ */
+#include "hyperv.h"
+
+void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/*
+	 * The exit code used by Hyper-V for software-defined exits is reserved
+	 * by AMD specifically for such use cases.
+	 */
+	BUILD_BUG_ON(HV_SVM_EXITCODE_ENL != SVM_EXIT_SW);
+
+	svm->vmcb->control.exit_code = HV_SVM_EXITCODE_ENL;
+	svm->vmcb->control.exit_info_1 = HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH;
+	svm->vmcb->control.exit_info_2 = 0;
+	nested_svm_vmexit(svm);
+}

linux-7.2.3/arch/x86/kvm/svm/hyperv.h

@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common Hyper-V on KVM and KVM on Hyper-V definitions (SVM).
+ */
+
+#ifndef __ARCH_X86_KVM_SVM_HYPERV_H__
+#define __ARCH_X86_KVM_SVM_HYPERV_H__
+
+#include <asm/mshyperv.h>
+
+#include "../hyperv.h"
+#include "svm.h"
+
+#ifdef CONFIG_KVM_HYPERV
+static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
+	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+	if (!hv_vcpu)
+		return;
+
+	hv_vcpu->nested.pa_page_gpa = hve->partition_assist_page;
+	hv_vcpu->nested.vm_id = hve->hv_vm_id;
+	hv_vcpu->nested.vp_id = hve->hv_vp_id;
+}
+
+static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
+	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+	if (!hv_vcpu)
+		return false;
+
+	if (!hve->hv_enlightenments_control.nested_flush_hypercall)
+		return false;
+
+	return hv_vcpu->vp_assist_page.nested_control.features.directhypercall;
+}
+
+static inline bool nested_svm_is_l2_tlb_flush_hcall(struct kvm_vcpu *vcpu)
+{
+	return guest_hv_cpuid_has_l2_tlb_flush(vcpu) &&
+	       nested_svm_l2_tlb_flush_enabled(vcpu) &&
+	       kvm_hv_is_tlb_flush_hcall(vcpu);
+}
+
+void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
+#else /* CONFIG_KVM_HYPERV */
+static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {}
+static inline bool nested_svm_is_l2_tlb_flush_hcall(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {}
+#endif /* CONFIG_KVM_HYPERV */
+
+#endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */

linux-7.2.3/arch/x86/kvm/svm/pmu.c

@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KVM PMU support for AMD
+ *
+ * Copyright 2015, Red Hat, Inc. and/or its affiliates.
+ *
+ * Author:
+ *   Wei Huang <wei@redhat.com>
+ *
+ * Implementation is based on pmu_intel.c file
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <linux/perf_event.h>
+#include "x86.h"
+#include "cpuid.h"
+#include "lapic.h"
+#include "pmu.h"
+#include "svm.h"
+
+enum pmu_type {
+	PMU_TYPE_COUNTER = 0,
+	PMU_TYPE_EVNTSEL,
+};
+
+static struct kvm_pmc *amd_pmu_get_pmc(struct kvm_pmu *pmu, int pmc_idx)
+{
+	unsigned int num_counters = pmu->nr_arch_gp_counters;
+
+	if (pmc_idx >= num_counters)
+		return NULL;
+
+	return &pmu->gp_counters[array_index_nospec(pmc_idx, num_counters)];
+}
+
+static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
+					     enum pmu_type type)
+{
+	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+	unsigned int idx;
+
+	if (!pmu->version)
+		return NULL;
+
+	switch (msr) {
+	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
+		if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		/*
+		 * Each PMU counter has a pair of CTL and CTR MSRs. CTLn
+		 * MSRs (accessed via EVNTSEL) are even, CTRn MSRs are odd.
+		 */
+		idx = (unsigned int)((msr - MSR_F15H_PERF_CTL0) / 2);
+		if (!(msr & 0x1) != (type == PMU_TYPE_EVNTSEL))
+			return NULL;
+		break;
+	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
+		if (type != PMU_TYPE_EVNTSEL)
+			return NULL;
+		idx = msr - MSR_K7_EVNTSEL0;
+		break;
+	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
+		if (type != PMU_TYPE_COUNTER)
+			return NULL;
+		idx = msr - MSR_K7_PERFCTR0;
+		break;
+	default:
+		return NULL;
+	}
+
+	return amd_pmu_get_pmc(pmu, idx);
+}
+
+static int amd_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	if (idx >= pmu->nr_arch_gp_counters)
+		return -EINVAL;
+
+	return 0;
+}
+
+/* idx is the ECX register of RDPMC instruction */
+static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
+	unsigned int idx, u64 *mask)
+{
+	return amd_pmu_get_pmc(vcpu_to_pmu(vcpu), idx);
+}
+
+static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
+	pmc = pmc ? pmc : get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
+
+	return pmc;
+}
+
+static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	switch (msr) {
+	case MSR_K7_EVNTSEL0 ... MSR_K7_PERFCTR3:
+		return pmu->version > 0;
+	case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5:
+		return guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE);
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_CTL:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR:
+	case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET:
+		return pmu->version > 1;
+	default:
+		if (msr > MSR_F15H_PERF_CTR5 &&
+		    msr < MSR_F15H_PERF_CTL0 + 2 * pmu->nr_arch_gp_counters)
+			return pmu->version > 1;
+		break;
+	}
+
+	return amd_msr_idx_to_pmc(vcpu, msr);
+}
+
+static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+	u32 msr = msr_info->index;
+
+	/* MSR_PERFCTRn */
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
+	if (pmc) {
+		msr_info->data = pmc_read_counter(pmc);
+		return 0;
+	}
+	/* MSR_EVNTSELn */
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
+	if (pmc) {
+		msr_info->data = pmc->eventsel;
+		return 0;
+	}
+
+	return 1;
+}
+
+static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct kvm_pmc *pmc;
+	u32 msr = msr_info->index;
+	u64 data = msr_info->data;
+
+	/* MSR_PERFCTRn */
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
+	if (pmc) {
+		pmc_write_counter(pmc, data);
+		return 0;
+	}
+	/* MSR_EVNTSELn */
+	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL);
+	if (pmc) {
+		data &= ~pmu->reserved_bits;
+		if (data != pmc->eventsel) {
+			pmc->eventsel = data;
+			pmc->eventsel_hw = (data & ~AMD64_EVENTSEL_HOSTONLY) |
+					   AMD64_EVENTSEL_GUESTONLY;
+
+			if (data & AMD64_EVENTSEL_HOST_GUEST_MASK)
+				__set_bit(pmc->idx, pmu->pmc_has_mode_specific_enables);
+			else
+				__clear_bit(pmc->idx, pmu->pmc_has_mode_specific_enables);
+
+			kvm_pmu_request_counter_reprogram(pmc);
+		}
+		return 0;
+	}
+
+	return 1;
+}
+
+static void amd_pmu_refresh(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	union cpuid_0x80000022_ebx ebx;
+
+	pmu->version = 1;
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFMON_V2)) {
+		pmu->version = 2;
+		/*
+		 * Note, PERFMON_V2 is also in 0x80000022.0x0, i.e. the guest
+		 * CPUID entry is guaranteed to be non-NULL.
+		 */
+		BUILD_BUG_ON(x86_feature_cpuid(X86_FEATURE_PERFMON_V2).function != 0x80000022 ||
+			     x86_feature_cpuid(X86_FEATURE_PERFMON_V2).index);
+		ebx.full = kvm_find_cpuid_entry_index(vcpu, 0x80000022, 0)->ebx;
+		pmu->nr_arch_gp_counters = ebx.split.num_core_pmc;
+	} else if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE)) {
+		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS_CORE;
+	} else {
+		pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS;
+	}
+
+	pmu->nr_arch_gp_counters = min_t(unsigned int, pmu->nr_arch_gp_counters,
+					 kvm_pmu_cap.num_counters_gp);
+
+	if (pmu->version > 1) {
+		pmu->global_ctrl_rsvd = ~(BIT_ULL(pmu->nr_arch_gp_counters) - 1);
+		pmu->global_status_rsvd = pmu->global_ctrl_rsvd;
+	}
+
+	pmu->counter_bitmask[KVM_PMC_GP] = BIT_ULL(48) - 1;
+
+	pmu->reserved_bits = 0xfffffff000280000ull;
+	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SVM) && kvm_vcpu_has_mediated_pmu(vcpu))
+		pmu->reserved_bits &= ~AMD64_EVENTSEL_HOST_GUEST_MASK;
+
+	pmu->raw_event_mask = AMD64_RAW_EVENT_MASK;
+	/* not applicable to AMD; but clean them to prevent any fall out */
+	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
+	pmu->nr_arch_fixed_counters = 0;
+}
+
+static void amd_pmu_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	int i;
+
+	BUILD_BUG_ON(KVM_MAX_NR_AMD_GP_COUNTERS > AMD64_NUM_COUNTERS_CORE);
+
+	for (i = 0; i < KVM_MAX_NR_AMD_GP_COUNTERS; i++) {
+		pmu->gp_counters[i].type = KVM_PMC_GP;
+		pmu->gp_counters[i].vcpu = vcpu;
+		pmu->gp_counters[i].idx = i;
+		pmu->gp_counters[i].current_config = 0;
+	}
+}
+
+static bool amd_pmu_is_mediated_pmu_supported(struct x86_pmu_capability *host_pmu)
+{
+	return host_pmu->version >= 2;
+}
+
+static void amd_mediated_pmu_load(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	u64 global_status;
+
+	rdmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, global_status);
+	/* Clear host global_status MSR if non-zero. */
+	if (global_status)
+		wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, global_status);
+
+	wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET, pmu->global_status);
+	wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, pmu->global_ctrl);
+}
+
+static void amd_mediated_pmu_put(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
+	rdmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, pmu->global_status);
+
+	/* Clear global status bits if non-zero */
+	if (pmu->global_status)
+		wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, pmu->global_status);
+}
+
+static bool amd_pmc_is_disabled_in_current_mode(struct kvm_pmc *pmc)
+{
+	struct kvm_vcpu *vcpu = pmc->vcpu;
+	u64 host_guest_bits;
+
+	if (!kvm_vcpu_has_mediated_pmu(vcpu))
+		return false;
+
+	/* Common code is supposed to check the common enable bit */
+	if (WARN_ON_ONCE(!(pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE)))
+		return false;
+
+	/* If both bits are cleared, the counter is always enabled */
+	host_guest_bits = pmc->eventsel & AMD64_EVENTSEL_HOST_GUEST_MASK;
+	if (!host_guest_bits)
+		return false;
+
+	/* If EFER.SVME=0 and either bit is set, the counter is disabled */
+	if (!(vcpu->arch.efer & EFER_SVME))
+		return true;
+
+	/*
+	 * If EFER.SVME=1, the counter is disabled iff only one of the bits is
+	 * set AND the set bit doesn't match the vCPU mode.
+	 */
+	if (host_guest_bits == AMD64_EVENTSEL_HOST_GUEST_MASK)
+		return false;
+
+	return !!(host_guest_bits & AMD64_EVENTSEL_GUESTONLY) != is_guest_mode(vcpu);
+}
+
+struct kvm_pmu_ops amd_pmu_ops __initdata = {
+	.rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc,
+	.msr_idx_to_pmc = amd_msr_idx_to_pmc,
+	.check_rdpmc_early = amd_check_rdpmc_early,
+	.is_valid_msr = amd_is_valid_msr,
+	.get_msr = amd_pmu_get_msr,
+	.set_msr = amd_pmu_set_msr,
+	.refresh = amd_pmu_refresh,
+	.init = amd_pmu_init,
+	.pmc_is_disabled_in_current_mode = amd_pmc_is_disabled_in_current_mode,
+
+	.is_mediated_pmu_supported = amd_pmu_is_mediated_pmu_supported,
+	.mediated_load = amd_mediated_pmu_load,
+	.mediated_put = amd_mediated_pmu_put,
+
+	.EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT,
+	.MAX_NR_GP_COUNTERS = KVM_MAX_NR_AMD_GP_COUNTERS,
+	.MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS,
+
+	.PERF_GLOBAL_CTRL = MSR_AMD64_PERF_CNTR_GLOBAL_CTL,
+	.GP_EVENTSEL_BASE = MSR_F15H_PERF_CTL0,
+	.GP_COUNTER_BASE = MSR_F15H_PERF_CTR0,
+	.FIXED_COUNTER_BASE = 0,
+	.MSR_STRIDE = 2,
+};

linux-7.2.3/arch/x86/kvm/svm/svm_onhyperv.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KVM L1 hypervisor optimizations on Hyper-V for SVM.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kvm_host.h>
+
+#include <asm/mshyperv.h>
+
+#include "svm.h"
+#include "svm_ops.h"
+
+#include "hyperv.h"
+#include "kvm_onhyperv.h"
+#include "svm_onhyperv.h"
+
+static int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
+{
+	struct hv_vmcb_enlightenments *hve;
+	hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu);
+
+	if (partition_assist_page == INVALID_PAGE)
+		return -ENOMEM;
+
+	hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
+
+	hve->partition_assist_page = partition_assist_page;
+	hve->hv_vm_id = (unsigned long)vcpu->kvm;
+	if (!hve->hv_enlightenments_control.nested_flush_hypercall) {
+		hve->hv_enlightenments_control.nested_flush_hypercall = 1;
+		vmcb_mark_dirty(to_svm(vcpu)->vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS);
+	}
+
+	return 0;
+}
+
+__init void svm_hv_hardware_setup(void)
+{
+	if (npt_enabled &&
+	    ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) {
+		pr_info(KBUILD_MODNAME ": Hyper-V enlightened NPT TLB flush enabled\n");
+		svm_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs;
+		svm_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range;
+	}
+
+	if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) {
+		int cpu;
+
+		pr_info(KBUILD_MODNAME ": Hyper-V Direct TLB Flush enabled\n");
+		for_each_online_cpu(cpu) {
+			struct hv_vp_assist_page *vp_ap =
+				hv_get_vp_assist_page(cpu);
+
+			if (!vp_ap)
+				continue;
+
+			vp_ap->nested_control.features.directhypercall = 1;
+		}
+		svm_x86_ops.enable_l2_tlb_flush =
+				svm_hv_enable_l2_tlb_flush;
+	}
+}

linux-7.2.3/arch/x86/kvm/svm/svm_onhyperv.h

@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * KVM L1 hypervisor optimizations on Hyper-V for SVM.
+ */
+
+#ifndef __ARCH_X86_KVM_SVM_ONHYPERV_H__
+#define __ARCH_X86_KVM_SVM_ONHYPERV_H__
+
+#include <asm/mshyperv.h>
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+#include "kvm_onhyperv.h"
+#include "svm/hyperv.h"
+
+__init void svm_hv_hardware_setup(void);
+
+static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu)
+{
+	struct hv_vmcb_enlightenments *hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
+
+	return ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB &&
+	       !!hve->hv_enlightenments_control.enlightened_npt_tlb;
+}
+
+static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
+{
+	struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
+
+	BUILD_BUG_ON(sizeof(vmcb->control.hv_enlightenments) !=
+		     sizeof(vmcb->control.reserved_sw));
+
+	if (npt_enabled &&
+	    ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB)
+		hve->hv_enlightenments_control.enlightened_npt_tlb = 1;
+
+	if (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)
+		hve->hv_enlightenments_control.msr_bitmap = 1;
+}
+
+static inline void svm_hv_vmcb_dirty_nested_enlightenments(
+		struct kvm_vcpu *vcpu)
+{
+	struct vmcb *vmcb = to_svm(vcpu)->vmcb;
+	struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
+
+	if (hve->hv_enlightenments_control.msr_bitmap)
+		vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS);
+}
+
+static inline void svm_hv_update_vp_id(struct vmcb *vmcb, struct kvm_vcpu *vcpu)
+{
+	struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
+	u32 vp_index = kvm_hv_get_vpindex(vcpu);
+
+	if (hve->hv_vp_id != vp_index) {
+		hve->hv_vp_id = vp_index;
+		vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS);
+	}
+}
+#else
+
+static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
+static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
+{
+}
+
+static inline __init void svm_hv_hardware_setup(void)
+{
+}
+
+static inline void svm_hv_vmcb_dirty_nested_enlightenments(
+		struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void svm_hv_update_vp_id(struct vmcb *vmcb,
+		struct kvm_vcpu *vcpu)
+{
+}
+#endif /* CONFIG_HYPERV */
+
+#endif /* __ARCH_X86_KVM_SVM_ONHYPERV_H__ */

linux-7.2.3/arch/x86/kvm/svm/svm_ops.h

@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_SVM_OPS_H
+#define __KVM_X86_SVM_OPS_H
+
+#include <linux/compiler_types.h>
+
+#include "x86.h"
+
+#define svm_asm(insn, clobber...)				\
+do {								\
+	asm goto("1: " __stringify(insn) "\n\t"	\
+			  _ASM_EXTABLE(1b, %l[fault])		\
+			  ::: clobber : fault);			\
+	return;							\
+fault:								\
+	kvm_spurious_fault();					\
+} while (0)
+
+#define svm_asm1(insn, op1, clobber...)				\
+do {								\
+	asm goto("1: "  __stringify(insn) " %0\n\t"	\
+			  _ASM_EXTABLE(1b, %l[fault])		\
+			  :: op1 : clobber : fault);		\
+	return;							\
+fault:								\
+	kvm_spurious_fault();					\
+} while (0)
+
+#define svm_asm2(insn, op1, op2, clobber...)				\
+do {									\
+	asm goto("1: "  __stringify(insn) " %1, %0\n\t"	\
+			  _ASM_EXTABLE(1b, %l[fault])			\
+			  :: op1, op2 : clobber : fault);		\
+	return;								\
+fault:									\
+	kvm_spurious_fault();						\
+} while (0)
+
+static inline void clgi(void)
+{
+	svm_asm(clgi);
+}
+
+static inline void stgi(void)
+{
+	svm_asm(stgi);
+}
+
+static inline void invlpga(unsigned long addr, u32 asid)
+{
+	svm_asm2(invlpga, "c"(asid), "a"(addr));
+}
+
+/*
+ * Despite being a physical address, the portion of rAX that is consumed by
+ * VMSAVE, VMLOAD, etc... is still controlled by the effective address size,
+ * hence 'unsigned long' instead of 'hpa_t'.
+ */
+static __always_inline void vmsave(unsigned long pa)
+{
+	svm_asm1(vmsave, "a" (pa), "memory");
+}
+
+#endif /* __KVM_X86_SVM_OPS_H */

linux-7.2.3/arch/x86/kvm/svm/vmenter.S

@@ -0,0 +1,284 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/bitsperlong.h>
+#include <asm/frame.h>
+#include <asm/nospec-branch.h>
+#include "kvm-asm-offsets.h"
+#include "vmenter.h"
+
+#define SVM_vmcb01_pa	(SVM_vmcb01 + KVM_VMCB_pa)
+
+.section .noinstr.text, "ax"
+
+.macro RESTORE_GUEST_SPEC_CTRL
+	/* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */
+	ALTERNATIVE_2 "", \
+		"jmp 800f", X86_FEATURE_MSR_SPEC_CTRL, \
+		"", X86_FEATURE_V_SPEC_CTRL
+.endm
+
+.macro RESTORE_HOST_SPEC_CTRL
+	/* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */
+	ALTERNATIVE_2 "", \
+		"jmp 900f", X86_FEATURE_MSR_SPEC_CTRL, \
+		"", X86_FEATURE_V_SPEC_CTRL
+.endm
+
+#define SVM_CLEAR_CPU_BUFFERS \
+	ALTERNATIVE "", __CLEAR_CPU_BUFFERS, X86_FEATURE_CLEAR_CPU_BUF_VM
+
+/**
+ * __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode
+ * @svm:	 struct vcpu_svm *
+ * @enter_flags: u32
+ */
+SYM_FUNC_START(__svm_vcpu_run)
+	push %_ASM_BP
+	mov  %_ASM_SP, %_ASM_BP
+#ifdef CONFIG_X86_64
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+#else
+	push %edi
+	push %esi
+#endif
+	push %_ASM_BX
+
+	/*
+	 * Save variables needed after vmexit on the stack, in inverse
+	 * order compared to when they are needed.
+	 */
+
+	/* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL.  */
+	push %_ASM_ARG2
+
+	/* Needed to restore access to percpu variables.  */
+	__ASM_SIZE(push) PER_CPU_VAR(svm_data + SD_save_area_pa)
+
+	/* Finally save @svm. */
+	push %_ASM_ARG1
+
+.ifnc _ASM_ARG1, _ASM_DI
+	/*
+	 * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX
+	 * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL.
+	 */
+	mov %_ASM_ARG1, %_ASM_DI
+.endif
+
+	/* Clobbers RAX, RCX, RDX (and ESI on 32-bit), consumes RDI (@svm). */
+	RESTORE_GUEST_SPEC_CTRL
+801:
+
+	/*
+	 * Use a single vmcb (vmcb01 because it's always valid) for
+	 * context switching guest state via VMLOAD/VMSAVE, that way
+	 * the state doesn't need to be copied between vmcb01 and
+	 * vmcb02 when switching vmcbs for nested virtualization.
+	 */
+	mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
+1:	vmload %_ASM_AX
+2:
+
+	/* Get svm->current_vmcb->pa into RAX. */
+	mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX
+	mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX
+
+	/*
+	 * Load guest registers. Intentionally omit %_ASM_AX and %_ASM_SP as
+	 * context switched by hardware
+	 */
+	LOAD_REGS %_ASM_DI, SVM_vcpu_arch_regs, \
+		  %_ASM_CX, %_ASM_DX, %_ASM_BX, %_ASM_BP, %_ASM_SI
+#ifdef CONFIG_X86_64
+	LOAD_REGS %_ASM_DI, SVM_vcpu_arch_regs, \
+		  %r8, %r9, %r10, %r11, %r12, %r13, %r14, %r15
+#endif
+	LOAD_REGS %_ASM_DI, SVM_vcpu_arch_regs, %_ASM_DI
+
+	/* Clobbers EFLAGS.ZF */
+	SVM_CLEAR_CPU_BUFFERS
+
+	/* Enter guest mode */
+3:	vmrun %_ASM_AX
+4:
+	/* Pop @svm to RAX while it's the only available register. */
+	pop %_ASM_AX
+
+	/*
+	 * Save all guest registers. Intentionally omit %_ASM_AX and %_ASM_SP as
+	 * context switched by hardware
+	 */
+	STORE_REGS %_ASM_AX, SVM_vcpu_arch_regs, \
+		   %_ASM_CX, %_ASM_DX, %_ASM_BX, %_ASM_BP, %_ASM_SI, %_ASM_DI
+#ifdef CONFIG_X86_64
+	STORE_REGS %_ASM_AX, SVM_vcpu_arch_regs, \
+		   %r8, %r9, %r10, %r11, %r12, %r13, %r14, %r15
+#endif
+
+	/* @svm can stay in RDI from now on.  */
+	mov %_ASM_AX, %_ASM_DI
+
+	mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
+5:	vmsave %_ASM_AX
+6:
+
+	/* Restores GSBASE among other things, allowing access to percpu data.  */
+	pop %_ASM_AX
+7:	vmload %_ASM_AX
+8:
+
+	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
+
+	/*
+	 * Clobbers RAX, RCX, RDX (and ESI, EDI on 32-bit), consumes RDI (@svm)
+	 * and RSP (pointer to @spec_ctrl_intercepted).
+	 */
+	RESTORE_HOST_SPEC_CTRL
+901:
+
+	/*
+	 * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
+	 * untrained as soon as we exit the VM and are back to the
+	 * kernel. This should be done before re-enabling interrupts
+	 * because interrupt handlers won't sanitize 'ret' if the return is
+	 * from the kernel.
+	 */
+	UNTRAIN_RET_VM
+
+	/*
+	 * Clear all general purpose registers except RSP and RAX to prevent
+	 * speculative use of the guest's values, even those that are reloaded
+	 * via the stack.  In theory, an L1 cache miss when restoring registers
+	 * could lead to speculative execution with the guest's values.
+	 * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially
+	 * free.  RSP and RAX are exempt as they are restored by hardware
+	 * during VM-Exit.
+	 */
+	CLEAR_REGS %ecx, %edx, %ebx, %ebp, %esi, %edi
+#ifdef CONFIG_X86_64
+	CLEAR_REGS %r8d, %r9d, %r10d, %r11d, %r12d, %r13d, %r14d, %r15d
+#endif
+
+	/* "Pop" @enter_flags.  */
+	pop %_ASM_BX
+
+	pop %_ASM_BX
+
+#ifdef CONFIG_X86_64
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+#else
+	pop %esi
+	pop %edi
+#endif
+	pop %_ASM_BP
+	RET
+
+800:
+	RESTORE_GUEST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), 801b
+	jmp 801b
+900:
+	RESTORE_HOST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), (%_ASM_SP), 901b
+	jmp 901b
+
+10:	cmpb $0, _ASM_RIP(virt_rebooting)
+	jne 2b
+	ud2
+30:	cmpb $0, _ASM_RIP(virt_rebooting)
+	jne 4b
+	ud2
+50:	cmpb $0, _ASM_RIP(virt_rebooting)
+	jne 6b
+	ud2
+70:	cmpb $0, _ASM_RIP(virt_rebooting)
+	jne 8b
+	ud2
+
+	_ASM_EXTABLE(1b, 10b)
+	_ASM_EXTABLE(3b, 30b)
+	_ASM_EXTABLE(5b, 50b)
+	_ASM_EXTABLE(7b, 70b)
+
+SYM_FUNC_END(__svm_vcpu_run)
+
+#ifdef CONFIG_KVM_AMD_SEV
+
+#define SEV_ES_GPRS_BASE 0x300
+
+/**
+ * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode
+ * @svm:	 struct vcpu_svm *
+ * @enter_flags: u32
+ */
+SYM_FUNC_START(__svm_sev_es_vcpu_run)
+	FRAME_BEGIN
+
+	/*
+	 * Save non-volatile (callee-saved) registers to the host save area.
+	 * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not
+	 * saved on VMRUN.
+	 */
+	STORE_REGS %rdx, SEV_ES_GPRS_BASE, %rbp, %r15, %r14, %r13, %r12, %rbx
+
+	/*
+	 * Save volatile registers that hold arguments that are needed after
+	 * #VMEXIT (RDI=@svm and RSI=@enter_flags).
+	 */
+	STORE_REGS %rdx, SEV_ES_GPRS_BASE, %rdi, %rsi
+
+	/* Clobbers RAX, RCX, and RDX (@hostsa), consumes RDI (@svm). */
+	RESTORE_GUEST_SPEC_CTRL
+801:
+
+	/* Get svm->current_vmcb->pa into RAX. */
+	mov SVM_current_vmcb(%rdi), %rax
+	mov KVM_VMCB_pa(%rax), %rax
+
+	/* Clobbers EFLAGS.ZF */
+	SVM_CLEAR_CPU_BUFFERS
+
+	/* Enter guest mode */
+1:	vmrun %rax
+2:
+	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
+
+	/* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@enter_flags). */
+	RESTORE_HOST_SPEC_CTRL
+901:
+
+	/*
+	 * Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
+	 * untrained as soon as we exit the VM and are back to the
+	 * kernel. This should be done before re-enabling interrupts
+	 * because interrupt handlers won't sanitize RET if the return is
+	 * from the kernel.
+	 */
+	UNTRAIN_RET_VM
+
+	FRAME_END
+	RET
+
+800:
+	RESTORE_GUEST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), 801b
+	jmp 801b
+900:
+	RESTORE_HOST_SPEC_CTRL_BODY SVM_spec_ctrl(%_ASM_DI), %esi, 901b
+	jmp 901b
+
+3:	cmpb $0, virt_rebooting(%rip)
+	jne 2b
+	ud2
+
+	_ASM_EXTABLE(1b, 3b)
+
+SYM_FUNC_END(__svm_sev_es_vcpu_run)
+#endif /* CONFIG_KVM_AMD_SEV */