From ace9429bb58fd418f0c81d4c2835699bddf6bde6 Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Thu, 11 Apr 2024 10:27:49 +0200 Subject: Adding upstream version 6.6.15. Signed-off-by: Daniel Baumann --- arch/x86/kvm/svm/avic.c | 1221 +++++++++ arch/x86/kvm/svm/hyperv.c | 18 + arch/x86/kvm/svm/hyperv.h | 45 + arch/x86/kvm/svm/nested.c | 1818 +++++++++++++ arch/x86/kvm/svm/pmu.c | 250 ++ arch/x86/kvm/svm/sev.c | 3140 +++++++++++++++++++++++ arch/x86/kvm/svm/svm.c | 5381 +++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/svm/svm.h | 725 ++++++ arch/x86/kvm/svm/svm_onhyperv.c | 41 + arch/x86/kvm/svm/svm_onhyperv.h | 116 + arch/x86/kvm/svm/svm_ops.h | 64 + arch/x86/kvm/svm/vmenter.S | 390 +++ 12 files changed, 13209 insertions(+) create mode 100644 arch/x86/kvm/svm/avic.c create mode 100644 arch/x86/kvm/svm/hyperv.c create mode 100644 arch/x86/kvm/svm/hyperv.h create mode 100644 arch/x86/kvm/svm/nested.c create mode 100644 arch/x86/kvm/svm/pmu.c create mode 100644 arch/x86/kvm/svm/sev.c create mode 100644 arch/x86/kvm/svm/svm.c create mode 100644 arch/x86/kvm/svm/svm.h create mode 100644 arch/x86/kvm/svm/svm_onhyperv.c create mode 100644 arch/x86/kvm/svm/svm_onhyperv.h create mode 100644 arch/x86/kvm/svm/svm_ops.h create mode 100644 arch/x86/kvm/svm/vmenter.S (limited to 'arch/x86/kvm/svm') diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c new file mode 100644 index 0000000000..4b74ea91f4 --- /dev/null +++ b/arch/x86/kvm/svm/avic.c @@ -0,0 +1,1221 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Yaniv Kamay + * Avi Kivity + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include + +#include + +#include "trace.h" +#include "lapic.h" +#include "x86.h" +#include "irq.h" +#include "svm.h" + +/* + * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID, + * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry + * if an interrupt can't be delivered, e.g. because the vCPU isn't running. + * + * For the vCPU ID, use however many bits are currently allowed for the max + * guest physical APIC ID (limited by the size of the physical ID table), and + * use whatever bits remain to assign arbitrary AVIC IDs to VMs. Note, the + * size of the GATag is defined by hardware (32 bits), but is an opaque value + * as far as hardware is concerned. + */ +#define AVIC_VCPU_ID_MASK AVIC_PHYSICAL_MAX_INDEX_MASK + +#define AVIC_VM_ID_SHIFT HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK) +#define AVIC_VM_ID_MASK (GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT) + +#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK) +#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) + +#define __AVIC_GATAG(vm_id, vcpu_id) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \ + ((vcpu_id) & AVIC_VCPU_ID_MASK)) +#define AVIC_GATAG(vm_id, vcpu_id) \ +({ \ + u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id); \ + \ + WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id)); \ + WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id)); \ + ga_tag; \ +}) + +static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u); + +static bool force_avic; +module_param_unsafe(force_avic, bool, 0444); + +/* Note: + * This hash table is used to map VM_ID to a struct kvm_svm, + * when handling AMD IOMMU GALOG notification to schedule in + * a particular vCPU. + */ +#define SVM_VM_DATA_HASH_BITS 8 +static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); +static u32 next_vm_id = 0; +static bool next_vm_id_wrapped = 0; +static DEFINE_SPINLOCK(svm_vm_data_hash_lock); +bool x2avic_enabled; + +/* + * This is a wrapper of struct amd_iommu_ir_data. + */ +struct amd_svm_iommu_ir { + struct list_head node; /* Used by SVM for per-vcpu ir_list */ + void *data; /* Storing pointer to struct amd_ir_data */ +}; + +static void avic_activate_vmcb(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); + vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + + /* + * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR + * accesses, while interrupt injection to a running vCPU can be + * achieved using AVIC doorbell. KVM disables the APIC access page + * (deletes the memslot) if any vCPU has x2APIC enabled, thus enabling + * AVIC in hybrid mode activates only the doorbell mechanism. + */ + if (x2avic_enabled && apic_x2apic_mode(svm->vcpu.arch.apic)) { + vmcb->control.int_ctl |= X2APIC_MODE_MASK; + vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID; + /* Disabling MSR intercept for x2APIC registers */ + svm_set_x2apic_msr_interception(svm, false); + } else { + /* + * Flush the TLB, the guest may have inserted a non-APIC + * mapping into the TLB while AVIC was disabled. + */ + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, &svm->vcpu); + + /* For xAVIC and hybrid-xAVIC modes */ + vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; + /* Enabling MSR intercept for x2APIC registers */ + svm_set_x2apic_msr_interception(svm, true); + } +} + +static void avic_deactivate_vmcb(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); + vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + + /* + * If running nested and the guest uses its own MSR bitmap, there + * is no need to update L0's msr bitmap + */ + if (is_guest_mode(&svm->vcpu) && + vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)) + return; + + /* Enabling MSR intercept for x2APIC registers */ + svm_set_x2apic_msr_interception(svm, true); +} + +/* Note: + * This function is called from IOMMU driver to notify + * SVM to schedule in a particular vCPU of a particular VM. + */ +int avic_ga_log_notifier(u32 ga_tag) +{ + unsigned long flags; + struct kvm_svm *kvm_svm; + struct kvm_vcpu *vcpu = NULL; + u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag); + u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag); + + pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id); + trace_kvm_avic_ga_log(vm_id, vcpu_id); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) { + if (kvm_svm->avic_vm_id != vm_id) + continue; + vcpu = kvm_get_vcpu_by_id(&kvm_svm->kvm, vcpu_id); + break; + } + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + + /* Note: + * At this point, the IOMMU should have already set the pending + * bit in the vAPIC backing page. So, we just need to schedule + * in the vcpu. + */ + if (vcpu) + kvm_vcpu_wake_up(vcpu); + + return 0; +} + +void avic_vm_destroy(struct kvm *kvm) +{ + unsigned long flags; + struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + + if (!enable_apicv) + return; + + if (kvm_svm->avic_logical_id_table_page) + __free_page(kvm_svm->avic_logical_id_table_page); + if (kvm_svm->avic_physical_id_table_page) + __free_page(kvm_svm->avic_physical_id_table_page); + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + hash_del(&kvm_svm->hnode); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); +} + +int avic_vm_init(struct kvm *kvm) +{ + unsigned long flags; + int err = -ENOMEM; + struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + struct kvm_svm *k2; + struct page *p_page; + struct page *l_page; + u32 vm_id; + + if (!enable_apicv) + return 0; + + /* Allocating physical APIC ID table (4KB) */ + p_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!p_page) + goto free_avic; + + kvm_svm->avic_physical_id_table_page = p_page; + + /* Allocating logical APIC ID table (4KB) */ + l_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!l_page) + goto free_avic; + + kvm_svm->avic_logical_id_table_page = l_page; + + spin_lock_irqsave(&svm_vm_data_hash_lock, flags); + again: + vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK; + if (vm_id == 0) { /* id is 1-based, zero is not okay */ + next_vm_id_wrapped = 1; + goto again; + } + /* Is it still in use? Only possible if wrapped at least once */ + if (next_vm_id_wrapped) { + hash_for_each_possible(svm_vm_data_hash, k2, hnode, vm_id) { + if (k2->avic_vm_id == vm_id) + goto again; + } + } + kvm_svm->avic_vm_id = vm_id; + hash_add(svm_vm_data_hash, &kvm_svm->hnode, kvm_svm->avic_vm_id); + spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags); + + return 0; + +free_avic: + avic_vm_destroy(kvm); + return err; +} + +void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) +{ + struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm); + phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page)); + phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page)); + phys_addr_t ppa = __sme_set(page_to_phys(kvm_svm->avic_physical_id_table_page)); + + vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; + vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; + vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; + vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK; + + if (kvm_apicv_activated(svm->vcpu.kvm)) + avic_activate_vmcb(svm); + else + avic_deactivate_vmcb(svm); +} + +static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, + unsigned int index) +{ + u64 *avic_physical_id_table; + struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); + + if ((!x2avic_enabled && index > AVIC_MAX_PHYSICAL_ID) || + (index > X2AVIC_MAX_PHYSICAL_ID)) + return NULL; + + avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page); + + return &avic_physical_id_table[index]; +} + +static int avic_init_backing_page(struct kvm_vcpu *vcpu) +{ + u64 *entry, new_entry; + int id = vcpu->vcpu_id; + struct vcpu_svm *svm = to_svm(vcpu); + + if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) || + (id > X2AVIC_MAX_PHYSICAL_ID)) + return -EINVAL; + + if (!vcpu->arch.apic->regs) + return -EINVAL; + + if (kvm_apicv_activated(vcpu->kvm)) { + int ret; + + /* + * Note, AVIC hardware walks the nested page table to check + * permissions, but does not use the SPA address specified in + * the leaf SPTE since it uses address in the AVIC_BACKING_PAGE + * pointer field of the VMCB. + */ + ret = kvm_alloc_apic_access_page(vcpu->kvm); + if (ret) + return ret; + } + + svm->avic_backing_page = virt_to_page(vcpu->arch.apic->regs); + + /* Setting AVIC backing page address in the phy APIC ID table */ + entry = avic_get_physical_id_entry(vcpu, id); + if (!entry) + return -EINVAL; + + new_entry = __sme_set((page_to_phys(svm->avic_backing_page) & + AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) | + AVIC_PHYSICAL_ID_ENTRY_VALID_MASK); + WRITE_ONCE(*entry, new_entry); + + svm->avic_physical_id_cache = entry; + + return 0; +} + +void avic_ring_doorbell(struct kvm_vcpu *vcpu) +{ + /* + * Note, the vCPU could get migrated to a different pCPU at any point, + * which could result in signalling the wrong/previous pCPU. But if + * that happens the vCPU is guaranteed to do a VMRUN (after being + * migrated) and thus will process pending interrupts, i.e. a doorbell + * is not needed (and the spurious one is harmless). + */ + int cpu = READ_ONCE(vcpu->cpu); + + if (cpu != get_cpu()) { + wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); + trace_kvm_avic_doorbell(vcpu->vcpu_id, kvm_cpu_get_apicid(cpu)); + } + put_cpu(); +} + + +static void avic_kick_vcpu(struct kvm_vcpu *vcpu, u32 icrl) +{ + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); +} + +static void avic_kick_vcpu_by_physical_id(struct kvm *kvm, u32 physical_id, + u32 icrl) +{ + /* + * KVM inhibits AVIC if any vCPU ID diverges from the vCPUs APIC ID, + * i.e. APIC ID == vCPU ID. + */ + struct kvm_vcpu *target_vcpu = kvm_get_vcpu_by_id(kvm, physical_id); + + /* Once again, nothing to do if the target vCPU doesn't exist. */ + if (unlikely(!target_vcpu)) + return; + + avic_kick_vcpu(target_vcpu, icrl); +} + +static void avic_kick_vcpu_by_logical_id(struct kvm *kvm, u32 *avic_logical_id_table, + u32 logid_index, u32 icrl) +{ + u32 physical_id; + + if (avic_logical_id_table) { + u32 logid_entry = avic_logical_id_table[logid_index]; + + /* Nothing to do if the logical destination is invalid. */ + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) + return; + + physical_id = logid_entry & + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + } else { + /* + * For x2APIC, the logical APIC ID is a read-only value that is + * derived from the x2APIC ID, thus the x2APIC ID can be found + * by reversing the calculation (stored in logid_index). Note, + * bits 31:20 of the x2APIC ID aren't propagated to the logical + * ID, but KVM limits the x2APIC ID limited to KVM_MAX_VCPU_IDS. + */ + physical_id = logid_index; + } + + avic_kick_vcpu_by_physical_id(kvm, physical_id, icrl); +} + +/* + * A fast-path version of avic_kick_target_vcpus(), which attempts to match + * destination APIC ID to vCPU without looping through all vCPUs. + */ +static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source, + u32 icrl, u32 icrh, u32 index) +{ + int dest_mode = icrl & APIC_DEST_MASK; + int shorthand = icrl & APIC_SHORT_MASK; + struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + u32 dest; + + if (shorthand != APIC_DEST_NOSHORT) + return -EINVAL; + + if (apic_x2apic_mode(source)) + dest = icrh; + else + dest = GET_XAPIC_DEST_FIELD(icrh); + + if (dest_mode == APIC_DEST_PHYSICAL) { + /* broadcast destination, use slow path */ + if (apic_x2apic_mode(source) && dest == X2APIC_BROADCAST) + return -EINVAL; + if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST) + return -EINVAL; + + if (WARN_ON_ONCE(dest != index)) + return -EINVAL; + + avic_kick_vcpu_by_physical_id(kvm, dest, icrl); + } else { + u32 *avic_logical_id_table; + unsigned long bitmap, i; + u32 cluster; + + if (apic_x2apic_mode(source)) { + /* 16 bit dest mask, 16 bit cluster id */ + bitmap = dest & 0xFFFF; + cluster = (dest >> 16) << 4; + } else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) { + /* 8 bit dest mask*/ + bitmap = dest; + cluster = 0; + } else { + /* 4 bit desk mask, 4 bit cluster id */ + bitmap = dest & 0xF; + cluster = (dest >> 4) << 2; + } + + /* Nothing to do if there are no destinations in the cluster. */ + if (unlikely(!bitmap)) + return 0; + + if (apic_x2apic_mode(source)) + avic_logical_id_table = NULL; + else + avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page); + + /* + * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical + * IDs, thus each bit in the destination is guaranteed to map + * to at most one vCPU. + */ + for_each_set_bit(i, &bitmap, 16) + avic_kick_vcpu_by_logical_id(kvm, avic_logical_id_table, + cluster + i, icrl); + } + + return 0; +} + +static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, + u32 icrl, u32 icrh, u32 index) +{ + u32 dest = apic_x2apic_mode(source) ? icrh : GET_XAPIC_DEST_FIELD(icrh); + unsigned long i; + struct kvm_vcpu *vcpu; + + if (!avic_kick_target_vcpus_fast(kvm, source, icrl, icrh, index)) + return; + + trace_kvm_avic_kick_vcpu_slowpath(icrh, icrl, index); + + /* + * Wake any target vCPUs that are blocking, i.e. waiting for a wake + * event. There's no need to signal doorbells, as hardware has handled + * vCPUs that were in guest at the time of the IPI, and vCPUs that have + * since entered the guest will have processed pending IRQs at VMRUN. + */ + kvm_for_each_vcpu(i, vcpu, kvm) { + if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, + dest, icrl & APIC_DEST_MASK)) + avic_kick_vcpu(vcpu, icrl); + } +} + +int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 icrh = svm->vmcb->control.exit_info_1 >> 32; + u32 icrl = svm->vmcb->control.exit_info_1; + u32 id = svm->vmcb->control.exit_info_2 >> 32; + u32 index = svm->vmcb->control.exit_info_2 & 0x1FF; + struct kvm_lapic *apic = vcpu->arch.apic; + + trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index); + + switch (id) { + case AVIC_IPI_FAILURE_INVALID_TARGET: + case AVIC_IPI_FAILURE_INVALID_INT_TYPE: + /* + * Emulate IPIs that are not handled by AVIC hardware, which + * only virtualizes Fixed, Edge-Triggered INTRs, and falls over + * if _any_ targets are invalid, e.g. if the logical mode mask + * is a superset of running vCPUs. + * + * The exit is a trap, e.g. ICR holds the correct value and RIP + * has been advanced, KVM is responsible only for emulating the + * IPI. Sadly, hardware may sometimes leave the BUSY flag set, + * in which case KVM needs to emulate the ICR write as well in + * order to clear the BUSY flag. + */ + if (icrl & APIC_ICR_BUSY) + kvm_apic_write_nodecode(vcpu, APIC_ICR); + else + kvm_apic_send_ipi(apic, icrl, icrh); + break; + case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: + /* + * At this point, we expect that the AVIC HW has already + * set the appropriate IRR bits on the valid target + * vcpus. So, we just need to kick the appropriate vcpu. + */ + avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh, index); + break; + case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: + WARN_ONCE(1, "Invalid backing page\n"); + break; + case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR: + /* Invalid IPI with vector < 16 */ + break; + default: + vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n"); + } + + return 1; +} + +unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu) +{ + if (is_guest_mode(vcpu)) + return APICV_INHIBIT_REASON_NESTED; + return 0; +} + +static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) +{ + struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); + u32 *logical_apic_id_table; + u32 cluster, index; + + ldr = GET_APIC_LOGICAL_ID(ldr); + + if (flat) { + cluster = 0; + } else { + cluster = (ldr >> 4); + if (cluster >= 0xf) + return NULL; + ldr &= 0xf; + } + if (!ldr || !is_power_of_2(ldr)) + return NULL; + + index = __ffs(ldr); + if (WARN_ON_ONCE(index > 7)) + return NULL; + index += (cluster << 2); + + logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page); + + return &logical_apic_id_table[index]; +} + +static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) +{ + bool flat; + u32 *entry, new_entry; + + flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT; + entry = avic_get_logical_id_entry(vcpu, ldr, flat); + if (!entry) + return; + + new_entry = READ_ONCE(*entry); + new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); + new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; + WRITE_ONCE(*entry, new_entry); +} + +static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool flat = svm->dfr_reg == APIC_DFR_FLAT; + u32 *entry; + + /* Note: x2AVIC does not use logical APIC ID table */ + if (apic_x2apic_mode(vcpu->arch.apic)) + return; + + entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat); + if (entry) + clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); +} + +static void avic_handle_ldr_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); + u32 id = kvm_xapic_id(vcpu->arch.apic); + + /* AVIC does not support LDR update for x2APIC */ + if (apic_x2apic_mode(vcpu->arch.apic)) + return; + + if (ldr == svm->ldr_reg) + return; + + avic_invalidate_logical_id_entry(vcpu); + + svm->ldr_reg = ldr; + avic_ldr_write(vcpu, id, ldr); +} + +static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 dfr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR); + + if (svm->dfr_reg == dfr) + return; + + avic_invalidate_logical_id_entry(vcpu); + svm->dfr_reg = dfr; +} + +static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu) +{ + u32 offset = to_svm(vcpu)->vmcb->control.exit_info_1 & + AVIC_UNACCEL_ACCESS_OFFSET_MASK; + + switch (offset) { + case APIC_LDR: + avic_handle_ldr_update(vcpu); + break; + case APIC_DFR: + avic_handle_dfr_update(vcpu); + break; + case APIC_RRR: + /* Ignore writes to Read Remote Data, it's read-only. */ + return 1; + default: + break; + } + + kvm_apic_write_nodecode(vcpu, offset); + return 1; +} + +static bool is_avic_unaccelerated_access_trap(u32 offset) +{ + bool ret = false; + + switch (offset) { + case APIC_ID: + case APIC_EOI: + case APIC_RRR: + case APIC_LDR: + case APIC_DFR: + case APIC_SPIV: + case APIC_ESR: + case APIC_ICR: + case APIC_LVTT: + case APIC_LVTTHMR: + case APIC_LVTPC: + case APIC_LVT0: + case APIC_LVT1: + case APIC_LVTERR: + case APIC_TMICT: + case APIC_TDCR: + ret = true; + break; + default: + break; + } + return ret; +} + +int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int ret = 0; + u32 offset = svm->vmcb->control.exit_info_1 & + AVIC_UNACCEL_ACCESS_OFFSET_MASK; + u32 vector = svm->vmcb->control.exit_info_2 & + AVIC_UNACCEL_ACCESS_VECTOR_MASK; + bool write = (svm->vmcb->control.exit_info_1 >> 32) & + AVIC_UNACCEL_ACCESS_WRITE_MASK; + bool trap = is_avic_unaccelerated_access_trap(offset); + + trace_kvm_avic_unaccelerated_access(vcpu->vcpu_id, offset, + trap, write, vector); + if (trap) { + /* Handling Trap */ + WARN_ONCE(!write, "svm: Handling trap read.\n"); + ret = avic_unaccel_trap_write(vcpu); + } else { + /* Handling Fault */ + ret = kvm_emulate_instruction(vcpu, 0); + } + + return ret; +} + +int avic_init_vcpu(struct vcpu_svm *svm) +{ + int ret; + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm)) + return 0; + + ret = avic_init_backing_page(vcpu); + if (ret) + return ret; + + INIT_LIST_HEAD(&svm->ir_list); + spin_lock_init(&svm->ir_list_lock); + svm->dfr_reg = APIC_DFR_FLAT; + + return ret; +} + +void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) +{ + avic_handle_dfr_update(vcpu); + avic_handle_ldr_update(vcpu); +} + +static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + struct vcpu_svm *svm = to_svm(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + /* + * Here, we go through the per-vcpu ir_list to update all existing + * interrupt remapping table entry targeting this vcpu. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + + if (list_empty(&svm->ir_list)) + goto out; + + list_for_each_entry(ir, &svm->ir_list, node) { + if (activate) + ret = amd_iommu_activate_guest_mode(ir->data); + else + ret = amd_iommu_deactivate_guest_mode(ir->data); + if (ret) + break; + } +out: + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + return ret; +} + +static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) +{ + unsigned long flags; + struct amd_svm_iommu_ir *cur; + + spin_lock_irqsave(&svm->ir_list_lock, flags); + list_for_each_entry(cur, &svm->ir_list, node) { + if (cur->data != pi->ir_data) + continue; + list_del(&cur->node); + kfree(cur); + break; + } + spin_unlock_irqrestore(&svm->ir_list_lock, flags); +} + +static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) +{ + int ret = 0; + unsigned long flags; + struct amd_svm_iommu_ir *ir; + u64 entry; + + /** + * In some cases, the existing irte is updated and re-set, + * so we need to check here if it's already been * added + * to the ir_list. + */ + if (pi->ir_data && (pi->prev_ga_tag != 0)) { + struct kvm *kvm = svm->vcpu.kvm; + u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag); + struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); + struct vcpu_svm *prev_svm; + + if (!prev_vcpu) { + ret = -EINVAL; + goto out; + } + + prev_svm = to_svm(prev_vcpu); + svm_ir_list_del(prev_svm, pi); + } + + /** + * Allocating new amd_iommu_pi_data, which will get + * add to the per-vcpu ir_list. + */ + ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT); + if (!ir) { + ret = -ENOMEM; + goto out; + } + ir->data = pi->ir_data; + + spin_lock_irqsave(&svm->ir_list_lock, flags); + + /* + * Update the target pCPU for IOMMU doorbells if the vCPU is running. + * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM + * will update the pCPU info when the vCPU awkened and/or scheduled in. + * See also avic_vcpu_load(). + */ + entry = READ_ONCE(*(svm->avic_physical_id_cache)); + if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) + amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK, + true, pi->ir_data); + + list_add(&ir->node, &svm->ir_list); + spin_unlock_irqrestore(&svm->ir_list_lock, flags); +out: + return ret; +} + +/* + * Note: + * The HW cannot support posting multicast/broadcast + * interrupts to a vCPU. So, we still use legacy interrupt + * remapping for these kind of interrupts. + * + * For lowest-priority interrupts, we only support + * those with single CPU as the destination, e.g. user + * configures the interrupts via /proc/irq or uses + * irqbalance to make the interrupts single-CPU. + */ +static int +get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, + struct vcpu_data *vcpu_info, struct vcpu_svm **svm) +{ + struct kvm_lapic_irq irq; + struct kvm_vcpu *vcpu = NULL; + + kvm_set_msi_irq(kvm, e, &irq); + + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || + !kvm_irq_is_postable(&irq)) { + pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n", + __func__, irq.vector); + return -1; + } + + pr_debug("SVM: %s: use GA mode for irq %u\n", __func__, + irq.vector); + *svm = to_svm(vcpu); + vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page)); + vcpu_info->vector = irq.vector; + + return 0; +} + +/* + * avic_pi_update_irte - set IRTE for Posted-Interrupts + * + * @kvm: kvm + * @host_irq: host irq of the interrupt + * @guest_irq: gsi of the interrupt + * @set: set or unset PI + * returns 0 on success, < 0 on failure + */ +int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + struct kvm_kernel_irq_routing_entry *e; + struct kvm_irq_routing_table *irq_rt; + int idx, ret = 0; + + if (!kvm_arch_has_assigned_device(kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n", + __func__, host_irq, guest_irq, set); + + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + + if (guest_irq >= irq_rt->nr_rt_entries || + hlist_empty(&irq_rt->map[guest_irq])) { + pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", + guest_irq, irq_rt->nr_rt_entries); + goto out; + } + + hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { + struct vcpu_data vcpu_info; + struct vcpu_svm *svm = NULL; + + if (e->type != KVM_IRQ_ROUTING_MSI) + continue; + + /** + * Here, we setup with legacy mode in the following cases: + * 1. When cannot target interrupt to a specific vcpu. + * 2. Unsetting posted interrupt. + * 3. APIC virtualization is disabled for the vcpu. + * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) + */ + if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && + kvm_vcpu_apicv_active(&svm->vcpu)) { + struct amd_iommu_pi_data pi; + + /* Try to enable guest_mode in IRTE */ + pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & + AVIC_HPA_MASK); + pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id, + svm->vcpu.vcpu_id); + pi.is_guest_mode = true; + pi.vcpu_data = &vcpu_info; + ret = irq_set_vcpu_affinity(host_irq, &pi); + + /** + * Here, we successfully setting up vcpu affinity in + * IOMMU guest mode. Now, we need to store the posted + * interrupt information in a per-vcpu ir_list so that + * we can reference to them directly when we update vcpu + * scheduling information in IOMMU irte. + */ + if (!ret && pi.is_guest_mode) + svm_ir_list_add(svm, &pi); + } else { + /* Use legacy mode in IRTE */ + struct amd_iommu_pi_data pi; + + /** + * Here, pi is used to: + * - Tell IOMMU to use legacy mode for this interrupt. + * - Retrieve ga_tag of prior interrupt remapping data. + */ + pi.prev_ga_tag = 0; + pi.is_guest_mode = false; + ret = irq_set_vcpu_affinity(host_irq, &pi); + + /** + * Check if the posted interrupt was previously + * setup with the guest_mode by checking if the ga_tag + * was cached. If so, we need to clean up the per-vcpu + * ir_list. + */ + if (!ret && pi.prev_ga_tag) { + int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag); + struct kvm_vcpu *vcpu; + + vcpu = kvm_get_vcpu_by_id(kvm, id); + if (vcpu) + svm_ir_list_del(to_svm(vcpu), &pi); + } + } + + if (!ret && svm) { + trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id, + e->gsi, vcpu_info.vector, + vcpu_info.pi_desc_addr, set); + } + + if (ret < 0) { + pr_err("%s: failed to update PI IRTE\n", __func__); + goto out; + } + } + + ret = 0; +out: + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + +static inline int +avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) +{ + int ret = 0; + struct amd_svm_iommu_ir *ir; + struct vcpu_svm *svm = to_svm(vcpu); + + lockdep_assert_held(&svm->ir_list_lock); + + if (!kvm_arch_has_assigned_device(vcpu->kvm)) + return 0; + + /* + * Here, we go through the per-vcpu ir_list to update all existing + * interrupt remapping table entry targeting this vcpu. + */ + if (list_empty(&svm->ir_list)) + return 0; + + list_for_each_entry(ir, &svm->ir_list, node) { + ret = amd_iommu_update_ga(cpu, r, ir->data); + if (ret) + return ret; + } + return 0; +} + +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + u64 entry; + int h_physical_id = kvm_cpu_get_apicid(cpu); + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long flags; + + lockdep_assert_preemption_disabled(); + + if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) + return; + + /* + * No need to update anything if the vCPU is blocking, i.e. if the vCPU + * is being scheduled in after being preempted. The CPU entries in the + * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'. + * If the vCPU was migrated, its new CPU value will be stuffed when the + * vCPU unblocks. + */ + if (kvm_vcpu_is_blocking(vcpu)) + return; + + /* + * Grab the per-vCPU interrupt remapping lock even if the VM doesn't + * _currently_ have assigned devices, as that can change. Holding + * ir_list_lock ensures that either svm_ir_list_add() will consume + * up-to-date entry information, or that this task will wait until + * svm_ir_list_add() completes to set the new target pCPU. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + + entry = READ_ONCE(*(svm->avic_physical_id_cache)); + WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); + + entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; + entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK); + entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; + + WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true); + + spin_unlock_irqrestore(&svm->ir_list_lock, flags); +} + +void avic_vcpu_put(struct kvm_vcpu *vcpu) +{ + u64 entry; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long flags; + + lockdep_assert_preemption_disabled(); + + /* + * Note, reading the Physical ID entry outside of ir_list_lock is safe + * as only the pCPU that has loaded (or is loading) the vCPU is allowed + * to modify the entry, and preemption is disabled. I.e. the vCPU + * can't be scheduled out and thus avic_vcpu_{put,load}() can't run + * recursively. + */ + entry = READ_ONCE(*(svm->avic_physical_id_cache)); + + /* Nothing to do if IsRunning == '0' due to vCPU blocking. */ + if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) + return; + + /* + * Take and hold the per-vCPU interrupt remapping lock while updating + * the Physical ID entry even though the lock doesn't protect against + * multiple writers (see above). Holding ir_list_lock ensures that + * either svm_ir_list_add() will consume up-to-date entry information, + * or that this task will wait until svm_ir_list_add() completes to + * mark the vCPU as not running. + */ + spin_lock_irqsave(&svm->ir_list_lock, flags); + + avic_update_iommu_vcpu_affinity(vcpu, -1, 0); + + entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; + WRITE_ONCE(*(svm->avic_physical_id_cache), entry); + + spin_unlock_irqrestore(&svm->ir_list_lock, flags); + +} + +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb01.ptr; + + if (!lapic_in_kernel(vcpu) || !enable_apicv) + return; + + if (kvm_vcpu_apicv_active(vcpu)) { + /** + * During AVIC temporary deactivation, guest could update + * APIC ID, DFR and LDR registers, which would not be trapped + * by avic_unaccelerated_access_interception(). In this case, + * we need to check and update the AVIC logical APIC ID table + * accordingly before re-activating. + */ + avic_apicv_post_state_restore(vcpu); + avic_activate_vmcb(svm); + } else { + avic_deactivate_vmcb(svm); + } + vmcb_mark_dirty(vmcb, VMCB_AVIC); +} + +void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + bool activated = kvm_vcpu_apicv_active(vcpu); + + if (!enable_apicv) + return; + + avic_refresh_virtual_apic_mode(vcpu); + + if (activated) + avic_vcpu_load(vcpu, vcpu->cpu); + else + avic_vcpu_put(vcpu); + + avic_set_pi_irte_mode(vcpu, activated); +} + +void avic_vcpu_blocking(struct kvm_vcpu *vcpu) +{ + if (!kvm_vcpu_apicv_active(vcpu)) + return; + + /* + * Unload the AVIC when the vCPU is about to block, _before_ + * the vCPU actually blocks. + * + * Any IRQs that arrive before IsRunning=0 will not cause an + * incomplete IPI vmexit on the source, therefore vIRR will also + * be checked by kvm_vcpu_check_block() before blocking. The + * memory barrier implicit in set_current_state orders writing + * IsRunning=0 before reading the vIRR. The processor needs a + * matching memory barrier on interrupt delivery between writing + * IRR and reading IsRunning; the lack of this barrier might be + * the cause of errata #1235). + */ + avic_vcpu_put(vcpu); +} + +void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) +{ + if (!kvm_vcpu_apicv_active(vcpu)) + return; + + avic_vcpu_load(vcpu, vcpu->cpu); +} + +/* + * Note: + * - The module param avic enable both xAPIC and x2APIC mode. + * - Hypervisor can support both xAVIC and x2AVIC in the same guest. + * - The mode can be switched at run-time. + */ +bool avic_hardware_setup(void) +{ + if (!npt_enabled) + return false; + + /* AVIC is a prerequisite for x2AVIC. */ + if (!boot_cpu_has(X86_FEATURE_AVIC) && !force_avic) { + if (boot_cpu_has(X86_FEATURE_X2AVIC)) { + pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); + pr_warn(FW_BUG "Try enable AVIC using force_avic option"); + } + return false; + } + + if (boot_cpu_has(X86_FEATURE_AVIC)) { + pr_info("AVIC enabled\n"); + } else if (force_avic) { + /* + * Some older systems does not advertise AVIC support. + * See Revision Guide for specific AMD processor for more detail. + */ + pr_warn("AVIC is not supported in CPUID but force enabled"); + pr_warn("Your system might crash and burn"); + } + + /* AVIC is a prerequisite for x2AVIC. */ + x2avic_enabled = boot_cpu_has(X86_FEATURE_X2AVIC); + if (x2avic_enabled) + pr_info("x2AVIC enabled\n"); + + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + + return true; +} diff --git a/arch/x86/kvm/svm/hyperv.c b/arch/x86/kvm/svm/hyperv.c new file mode 100644 index 0000000000..088f6429b2 --- /dev/null +++ b/arch/x86/kvm/svm/hyperv.c @@ -0,0 +1,18 @@ +// 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); + + svm->vmcb->control.exit_code = HV_SVM_EXITCODE_ENL; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH; + svm->vmcb->control.exit_info_2 = 0; + nested_svm_vmexit(svm); +} diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h new file mode 100644 index 0000000000..02f4784b5d --- /dev/null +++ b/arch/x86/kvm/svm/hyperv.h @@ -0,0 +1,45 @@ +/* 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 + +#include "../hyperv.h" +#include "svm.h" + +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; +} + +void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); + +#endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c new file mode 100644 index 0000000000..60891b9ce2 --- /dev/null +++ b/arch/x86/kvm/svm/nested.c @@ -0,0 +1,1818 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Yaniv Kamay + * Avi Kivity + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +#include +#include + +#include "kvm_emulate.h" +#include "trace.h" +#include "mmu.h" +#include "x86.h" +#include "smm.h" +#include "cpuid.h" +#include "lapic.h" +#include "svm.h" +#include "hyperv.h" + +#define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK + +static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, + struct x86_exception *fault) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + + if (vmcb->control.exit_code != SVM_EXIT_NPF) { + /* + * TODO: track the cause of the nested page fault, and + * correctly fill in the high bits of exit_info_1. + */ + vmcb->control.exit_code = SVM_EXIT_NPF; + vmcb->control.exit_code_hi = 0; + vmcb->control.exit_info_1 = (1ULL << 32); + vmcb->control.exit_info_2 = fault->address; + } + + vmcb->control.exit_info_1 &= ~0xffffffffULL; + vmcb->control.exit_info_1 |= fault->error_code; + + nested_svm_vmexit(svm); +} + +static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr3 = svm->nested.ctl.nested_cr3; + u64 pdpte; + int ret; + + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); + if (ret) + return 0; + return pdpte; +} + +static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return svm->nested.ctl.nested_cr3; +} + +static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + WARN_ON(mmu_is_nested(vcpu)); + + vcpu->arch.mmu = &vcpu->arch.guest_mmu; + + /* + * The NPT format depends on L1's CR4 and EFER, which is in vmcb01. Note, + * when called via KVM_SET_NESTED_STATE, that state may _not_ match current + * vCPU state. CR0.WP is explicitly ignored, while CR0.PG is required. + */ + kvm_init_shadow_npt_mmu(vcpu, X86_CR0_PG, svm->vmcb01.ptr->save.cr4, + svm->vmcb01.ptr->save.efer, + svm->nested.ctl.nested_cr3); + vcpu->arch.mmu->get_guest_pgd = nested_svm_get_tdp_cr3; + vcpu->arch.mmu->get_pdptr = nested_svm_get_tdp_pdptr; + vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit; + vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; +} + +static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) +{ + vcpu->arch.mmu = &vcpu->arch.root_mmu; + vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; +} + +static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm) +{ + if (!guest_can_use(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) + return true; + + if (!nested_npt_enabled(svm)) + return true; + + if (!(svm->nested.ctl.virt_ext & VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK)) + return true; + + return false; +} + +void recalc_intercepts(struct vcpu_svm *svm) +{ + struct vmcb_control_area *c, *h; + struct vmcb_ctrl_area_cached *g; + unsigned int i; + + vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + + if (!is_guest_mode(&svm->vcpu)) + return; + + c = &svm->vmcb->control; + h = &svm->vmcb01.ptr->control; + g = &svm->nested.ctl; + + for (i = 0; i < MAX_INTERCEPT; i++) + c->intercepts[i] = h->intercepts[i]; + + if (g->int_ctl & V_INTR_MASKING_MASK) { + /* + * If L2 is active and V_INTR_MASKING is enabled in vmcb12, + * disable intercept of CR8 writes as L2's CR8 does not affect + * any interrupt KVM may want to inject. + * + * Similarly, disable intercept of virtual interrupts (used to + * detect interrupt windows) if the saved RFLAGS.IF is '0', as + * the effective RFLAGS.IF for L1 interrupts will never be set + * while L2 is running (L2's RFLAGS.IF doesn't affect L1 IRQs). + */ + vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); + if (!(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF)) + vmcb_clr_intercept(c, INTERCEPT_VINTR); + } + + /* + * We want to see VMMCALLs from a nested guest only when Hyper-V L2 TLB + * flush feature is enabled. + */ + if (!nested_svm_l2_tlb_flush_enabled(&svm->vcpu)) + vmcb_clr_intercept(c, INTERCEPT_VMMCALL); + + for (i = 0; i < MAX_INTERCEPT; i++) + c->intercepts[i] |= g->intercepts[i]; + + /* If SMI is not intercepted, ignore guest SMI intercept as well */ + if (!intercept_smi) + vmcb_clr_intercept(c, INTERCEPT_SMI); + + if (nested_vmcb_needs_vls_intercept(svm)) { + /* + * If the virtual VMLOAD/VMSAVE is not enabled for the L2, + * we must intercept these instructions to correctly + * emulate them in case L1 doesn't intercept them. + */ + vmcb_set_intercept(c, INTERCEPT_VMLOAD); + vmcb_set_intercept(c, INTERCEPT_VMSAVE); + } else { + WARN_ON(!(c->virt_ext & VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK)); + } +} + +/* + * Merge L0's (KVM) and L1's (Nested VMCB) MSR permission bitmaps. The function + * is optimized in that it only merges the parts where KVM MSR permission bitmap + * may contain zero bits. + */ +static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) +{ + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + int i; + + /* + * MSR bitmap update can be skipped when: + * - MSR bitmap for L1 hasn't changed. + * - Nested hypervisor (L1) is attempting to launch the same L2 as + * before. + * - Nested hypervisor (L1) is using Hyper-V emulation interface and + * tells KVM (L0) there were no changes in MSR bitmap for L2. + */ + if (!svm->nested.force_msr_bitmap_recalc && + kvm_hv_hypercall_enabled(&svm->vcpu) && + hve->hv_enlightenments_control.msr_bitmap && + (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) + goto set_msrpm_base_pa; + + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + return true; + + for (i = 0; i < MSRPM_OFFSETS; i++) { + u32 value, p; + u64 offset; + + if (msrpm_offsets[i] == 0xffffffff) + break; + + p = msrpm_offsets[i]; + + /* x2apic msrs are intercepted always for the nested guest */ + if (is_x2apic_msrpm_offset(p)) + continue; + + offset = svm->nested.ctl.msrpm_base_pa + (p * 4); + + if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) + return false; + + svm->nested.msrpm[p] = svm->msrpm[p] | value; + } + + svm->nested.force_msr_bitmap_recalc = false; + +set_msrpm_base_pa: + svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); + + return true; +} + +/* + * Bits 11:0 of bitmap address are ignored by hardware + */ +static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size) +{ + u64 addr = PAGE_ALIGN(pa); + + return kvm_vcpu_is_legal_gpa(vcpu, addr) && + kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1); +} + +static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, + struct vmcb_ctrl_area_cached *control) +{ + if (CC(!vmcb12_is_intercept(control, INTERCEPT_VMRUN))) + return false; + + if (CC(control->asid == 0)) + return false; + + if (CC((control->nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && !npt_enabled)) + return false; + + if (CC(!nested_svm_check_bitmap_pa(vcpu, control->msrpm_base_pa, + MSRPM_SIZE))) + return false; + if (CC(!nested_svm_check_bitmap_pa(vcpu, control->iopm_base_pa, + IOPM_SIZE))) + return false; + + if (CC((control->int_ctl & V_NMI_ENABLE_MASK) && + !vmcb12_is_intercept(control, INTERCEPT_NMI))) { + return false; + } + + return true; +} + +/* Common checks that apply to both L1 and L2 state. */ +static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, + struct vmcb_save_area_cached *save) +{ + if (CC(!(save->efer & EFER_SVME))) + return false; + + if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || + CC(save->cr0 & ~0xffffffffULL)) + return false; + + if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) + return false; + + /* + * These checks are also performed by KVM_SET_SREGS, + * except that EFER.LMA is not checked by SVM against + * CR0.PG && EFER.LME. + */ + if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) { + if (CC(!(save->cr4 & X86_CR4_PAE)) || + CC(!(save->cr0 & X86_CR0_PE)) || + CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3))) + return false; + } + + /* Note, SVM doesn't have any additional restrictions on CR4. */ + if (CC(!__kvm_is_valid_cr4(vcpu, save->cr4))) + return false; + + if (CC(!kvm_valid_efer(vcpu, save->efer))) + return false; + + return true; +} + +static bool nested_vmcb_check_save(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_save_area_cached *save = &svm->nested.save; + + return __nested_vmcb_check_save(vcpu, save); +} + +static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_ctrl_area_cached *ctl = &svm->nested.ctl; + + return __nested_vmcb_check_controls(vcpu, ctl); +} + +static +void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu, + struct vmcb_ctrl_area_cached *to, + struct vmcb_control_area *from) +{ + unsigned int i; + + for (i = 0; i < MAX_INTERCEPT; i++) + to->intercepts[i] = from->intercepts[i]; + + to->iopm_base_pa = from->iopm_base_pa; + to->msrpm_base_pa = from->msrpm_base_pa; + to->tsc_offset = from->tsc_offset; + to->tlb_ctl = from->tlb_ctl; + to->int_ctl = from->int_ctl; + to->int_vector = from->int_vector; + to->int_state = from->int_state; + to->exit_code = from->exit_code; + to->exit_code_hi = from->exit_code_hi; + to->exit_info_1 = from->exit_info_1; + to->exit_info_2 = from->exit_info_2; + to->exit_int_info = from->exit_int_info; + to->exit_int_info_err = from->exit_int_info_err; + to->nested_ctl = from->nested_ctl; + to->event_inj = from->event_inj; + to->event_inj_err = from->event_inj_err; + to->next_rip = from->next_rip; + to->nested_cr3 = from->nested_cr3; + to->virt_ext = from->virt_ext; + to->pause_filter_count = from->pause_filter_count; + to->pause_filter_thresh = from->pause_filter_thresh; + + /* Copy asid here because nested_vmcb_check_controls will check it. */ + to->asid = from->asid; + to->msrpm_base_pa &= ~0x0fffULL; + to->iopm_base_pa &= ~0x0fffULL; + + /* Hyper-V extensions (Enlightened VMCB) */ + if (kvm_hv_hypercall_enabled(vcpu)) { + to->clean = from->clean; + memcpy(&to->hv_enlightenments, &from->hv_enlightenments, + sizeof(to->hv_enlightenments)); + } +} + +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control) +{ + __nested_copy_vmcb_control_to_cache(&svm->vcpu, &svm->nested.ctl, control); +} + +static void __nested_copy_vmcb_save_to_cache(struct vmcb_save_area_cached *to, + struct vmcb_save_area *from) +{ + /* + * Copy only fields that are validated, as we need them + * to avoid TOC/TOU races. + */ + to->efer = from->efer; + to->cr0 = from->cr0; + to->cr3 = from->cr3; + to->cr4 = from->cr4; + + to->dr6 = from->dr6; + to->dr7 = from->dr7; +} + +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save) +{ + __nested_copy_vmcb_save_to_cache(&svm->nested.save, save); +} + +/* + * Synchronize fields that are written by the processor, so that + * they can be copied back into the vmcb12. + */ +void nested_sync_control_from_vmcb02(struct vcpu_svm *svm) +{ + u32 mask; + svm->nested.ctl.event_inj = svm->vmcb->control.event_inj; + svm->nested.ctl.event_inj_err = svm->vmcb->control.event_inj_err; + + /* Only a few fields of int_ctl are written by the processor. */ + mask = V_IRQ_MASK | V_TPR_MASK; + /* + * Don't sync vmcb02 V_IRQ back to vmcb12 if KVM (L0) is intercepting + * virtual interrupts in order to request an interrupt window, as KVM + * has usurped vmcb02's int_ctl. If an interrupt window opens before + * the next VM-Exit, svm_clear_vintr() will restore vmcb12's int_ctl. + * If no window opens, V_IRQ will be correctly preserved in vmcb12's + * int_ctl (because it was never recognized while L2 was running). + */ + if (svm_is_intercept(svm, INTERCEPT_VINTR) && + !test_bit(INTERCEPT_VINTR, (unsigned long *)svm->nested.ctl.intercepts)) + mask &= ~V_IRQ_MASK; + + 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; +} + +/* + * Transfer any event that L0 or L1 wanted to inject into L2 to + * EXIT_INT_INFO. + */ +static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, + struct vmcb *vmcb12) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + u32 exit_int_info = 0; + unsigned int nr; + + if (vcpu->arch.exception.injected) { + nr = vcpu->arch.exception.vector; + exit_int_info = nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT; + + if (vcpu->arch.exception.has_error_code) { + exit_int_info |= SVM_EVTINJ_VALID_ERR; + vmcb12->control.exit_int_info_err = + vcpu->arch.exception.error_code; + } + + } else if (vcpu->arch.nmi_injected) { + exit_int_info = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; + + } else if (vcpu->arch.interrupt.injected) { + nr = vcpu->arch.interrupt.nr; + exit_int_info = nr | SVM_EVTINJ_VALID; + + if (vcpu->arch.interrupt.soft) + exit_int_info |= SVM_EVTINJ_TYPE_SOFT; + else + exit_int_info |= SVM_EVTINJ_TYPE_INTR; + } + + vmcb12->control.exit_int_info = exit_int_info; +} + +static void nested_svm_transition_tlb_flush(struct kvm_vcpu *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) && npt_enabled) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + + /* + * TODO: optimize unconditional TLB flush/MMU sync. A partial list of + * things to fix before this can be conditional: + * + * - Flush TLBs for both L1 and L2 remote TLB flush + * - Honor L1's request to flush an ASID on nested VMRUN + * - Sync nested NPT MMU on VMRUN that flushes L2's ASID[*] + * - Don't crush a pending TLB flush in vmcb02 on nested VMRUN + * - Flush L1's ASID on KVM_REQ_TLB_FLUSH_GUEST + * + * [*] Unlike nested EPT, SVM's ASID management can invalidate nested + * NPT guest-physical mappings on VMRUN. + */ + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); +} + +/* + * Load guest's/host's cr3 on nested vmentry or vmexit. @nested_npt is true + * if we are emulating VM-Entry into a guest with NPT enabled. + */ +static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, + bool nested_npt, bool reload_pdptrs) +{ + if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) + return -EINVAL; + + if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && + CC(!load_pdptrs(vcpu, cr3))) + return -EINVAL; + + vcpu->arch.cr3 = cr3; + + /* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */ + kvm_init_mmu(vcpu); + + if (!nested_npt) + kvm_mmu_new_pgd(vcpu, cr3); + + return 0; +} + +void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm) +{ + if (!svm->nested.vmcb02.ptr) + return; + + /* FIXME: merge g_pat from vmcb01 and vmcb12. */ + svm->nested.vmcb02.ptr->save.g_pat = svm->vmcb01.ptr->save.g_pat; +} + +static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12) +{ + bool new_vmcb12 = false; + struct vmcb *vmcb01 = svm->vmcb01.ptr; + struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; + struct kvm_vcpu *vcpu = &svm->vcpu; + + nested_vmcb02_compute_g_pat(svm); + + /* Load the nested guest state */ + if (svm->nested.vmcb12_gpa != svm->nested.last_vmcb12_gpa) { + new_vmcb12 = true; + svm->nested.last_vmcb12_gpa = svm->nested.vmcb12_gpa; + svm->nested.force_msr_bitmap_recalc = true; + } + + if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_SEG))) { + vmcb02->save.es = vmcb12->save.es; + vmcb02->save.cs = vmcb12->save.cs; + vmcb02->save.ss = vmcb12->save.ss; + vmcb02->save.ds = vmcb12->save.ds; + vmcb02->save.cpl = vmcb12->save.cpl; + vmcb_mark_dirty(vmcb02, VMCB_SEG); + } + + if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DT))) { + vmcb02->save.gdtr = vmcb12->save.gdtr; + vmcb02->save.idtr = vmcb12->save.idtr; + vmcb_mark_dirty(vmcb02, VMCB_DT); + } + + kvm_set_rflags(vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); + + svm_set_efer(vcpu, svm->nested.save.efer); + + svm_set_cr0(vcpu, svm->nested.save.cr0); + svm_set_cr4(vcpu, svm->nested.save.cr4); + + svm->vcpu.arch.cr2 = vmcb12->save.cr2; + + kvm_rax_write(vcpu, vmcb12->save.rax); + kvm_rsp_write(vcpu, vmcb12->save.rsp); + kvm_rip_write(vcpu, vmcb12->save.rip); + + /* In case we don't even reach vcpu_run, the fields are not updated */ + vmcb02->save.rax = vmcb12->save.rax; + vmcb02->save.rsp = vmcb12->save.rsp; + vmcb02->save.rip = vmcb12->save.rip; + + /* These bits will be set properly on the first execution when new_vmc12 is true */ + if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) { + vmcb02->save.dr7 = svm->nested.save.dr7 | DR7_FIXED_1; + svm->vcpu.arch.dr6 = svm->nested.save.dr6 | DR6_ACTIVE_LOW; + vmcb_mark_dirty(vmcb02, VMCB_DR); + } + + if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { + /* + * Reserved bits of DEBUGCTL are ignored. Be consistent with + * svm_set_msr's definition of reserved bits. + */ + svm_copy_lbrs(vmcb02, vmcb12); + vmcb02->save.dbgctl &= ~DEBUGCTL_RESERVED_BITS; + svm_update_lbrv(&svm->vcpu); + + } else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) { + svm_copy_lbrs(vmcb02, vmcb01); + } +} + +static inline bool is_evtinj_soft(u32 evtinj) +{ + u32 type = evtinj & SVM_EVTINJ_TYPE_MASK; + u8 vector = evtinj & SVM_EVTINJ_VEC_MASK; + + if (!(evtinj & SVM_EVTINJ_VALID)) + return false; + + if (type == SVM_EVTINJ_TYPE_SOFT) + return true; + + return type == SVM_EVTINJ_TYPE_EXEPT && kvm_exception_is_soft(vector); +} + +static bool is_evtinj_nmi(u32 evtinj) +{ + u32 type = evtinj & SVM_EVTINJ_TYPE_MASK; + + if (!(evtinj & SVM_EVTINJ_VALID)) + return false; + + return type == SVM_EVTINJ_TYPE_NMI; +} + +static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, + unsigned long vmcb12_rip, + unsigned long vmcb12_csbase) +{ + u32 int_ctl_vmcb01_bits = V_INTR_MASKING_MASK; + u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK; + + struct kvm_vcpu *vcpu = &svm->vcpu; + struct vmcb *vmcb01 = svm->vmcb01.ptr; + struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; + u32 pause_count12; + u32 pause_thresh12; + + /* + * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, + * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. + */ + + if (guest_can_use(vcpu, X86_FEATURE_VGIF) && + (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK)) + int_ctl_vmcb12_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); + 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; + vmcb02->control.msrpm_base_pa = vmcb01->control.msrpm_base_pa; + + /* Done at vmrun: asid. */ + + /* Also overwritten later if necessary. */ + vmcb02->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; + + /* nested_cr3. */ + if (nested_npt_enabled(svm)) + nested_svm_init_mmu_context(vcpu); + + vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset( + vcpu->arch.l1_tsc_offset, + svm->nested.ctl.tsc_offset, + svm->tsc_ratio_msr); + + vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; + + if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) + nested_svm_update_tsc_ratio_msr(vcpu); + + vmcb02->control.int_ctl = + (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | + (vmcb01->control.int_ctl & int_ctl_vmcb01_bits); + + vmcb02->control.int_vector = svm->nested.ctl.int_vector; + vmcb02->control.int_state = svm->nested.ctl.int_state; + vmcb02->control.event_inj = svm->nested.ctl.event_inj; + vmcb02->control.event_inj_err = svm->nested.ctl.event_inj_err; + + /* + * next_rip is consumed on VMRUN as the return address pushed on the + * stack for injected soft exceptions/interrupts. If nrips is exposed + * to L1, take it verbatim from vmcb12. If nrips is supported in + * hardware but not exposed to L1, stuff the actual L2 RIP to emulate + * what a nrips=0 CPU would do (L1 is responsible for advancing RIP + * prior to injecting the event). + */ + if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + vmcb02->control.next_rip = svm->nested.ctl.next_rip; + else if (boot_cpu_has(X86_FEATURE_NRIPS)) + vmcb02->control.next_rip = vmcb12_rip; + + svm->nmi_l1_to_l2 = is_evtinj_nmi(vmcb02->control.event_inj); + if (is_evtinj_soft(vmcb02->control.event_inj)) { + svm->soft_int_injected = true; + svm->soft_int_csbase = vmcb12_csbase; + svm->soft_int_old_rip = vmcb12_rip; + if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + svm->soft_int_next_rip = svm->nested.ctl.next_rip; + else + svm->soft_int_next_rip = vmcb12_rip; + } + + vmcb02->control.virt_ext = vmcb01->control.virt_ext & + LBR_CTL_ENABLE_MASK; + if (guest_can_use(vcpu, X86_FEATURE_LBRV)) + vmcb02->control.virt_ext |= + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK); + + if (!nested_vmcb_needs_vls_intercept(svm)) + vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + + if (guest_can_use(vcpu, X86_FEATURE_PAUSEFILTER)) + pause_count12 = svm->nested.ctl.pause_filter_count; + else + pause_count12 = 0; + if (guest_can_use(vcpu, X86_FEATURE_PFTHRESHOLD)) + pause_thresh12 = svm->nested.ctl.pause_filter_thresh; + else + pause_thresh12 = 0; + if (kvm_pause_in_guest(svm->vcpu.kvm)) { + /* use guest values since host doesn't intercept PAUSE */ + vmcb02->control.pause_filter_count = pause_count12; + vmcb02->control.pause_filter_thresh = pause_thresh12; + + } else { + /* start from host values otherwise */ + vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count; + vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh; + + /* ... but ensure filtering is disabled if so requested. */ + if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) { + if (!pause_count12) + vmcb02->control.pause_filter_count = 0; + if (!pause_thresh12) + vmcb02->control.pause_filter_thresh = 0; + } + } + + nested_svm_transition_tlb_flush(vcpu); + + /* Enter Guest-Mode */ + enter_guest_mode(vcpu); + + /* + * Merge guest and host intercepts - must be called with vcpu in + * guest-mode to take effect. + */ + recalc_intercepts(svm); +} + +static void nested_svm_copy_common_state(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +{ + /* + * Some VMCB state is shared between L1 and L2 and thus has to be + * moved at the time of nested vmrun and vmexit. + * + * VMLOAD/VMSAVE state would also belong in this category, but KVM + * always performs VMLOAD and VMSAVE from the VMCB01. + */ + to_vmcb->save.spec_ctrl = from_vmcb->save.spec_ctrl; +} + +int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, + struct vmcb *vmcb12, bool from_vmrun) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + trace_kvm_nested_vmenter(svm->vmcb->save.rip, + vmcb12_gpa, + vmcb12->save.rip, + vmcb12->control.int_ctl, + vmcb12->control.event_inj, + vmcb12->control.nested_ctl, + vmcb12->control.nested_cr3, + vmcb12->save.cr3, + KVM_ISA_SVM); + + trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff, + vmcb12->control.intercepts[INTERCEPT_CR] >> 16, + vmcb12->control.intercepts[INTERCEPT_EXCEPTION], + vmcb12->control.intercepts[INTERCEPT_WORD3], + vmcb12->control.intercepts[INTERCEPT_WORD4], + vmcb12->control.intercepts[INTERCEPT_WORD5]); + + + svm->nested.vmcb12_gpa = vmcb12_gpa; + + WARN_ON(svm->vmcb == svm->nested.vmcb02.ptr); + + nested_svm_copy_common_state(svm->vmcb01.ptr, svm->nested.vmcb02.ptr); + + svm_switch_vmcb(svm, &svm->nested.vmcb02); + nested_vmcb02_prepare_control(svm, vmcb12->save.rip, vmcb12->save.cs.base); + nested_vmcb02_prepare_save(svm, vmcb12); + + ret = nested_svm_load_cr3(&svm->vcpu, svm->nested.save.cr3, + nested_npt_enabled(svm), from_vmrun); + if (ret) + return ret; + + if (!from_vmrun) + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + + svm_set_gif(svm, true); + + if (kvm_vcpu_apicv_active(vcpu)) + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + + nested_svm_hv_update_vm_vp_ids(vcpu); + + return 0; +} + +int nested_svm_vmrun(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + struct vmcb *vmcb12; + struct kvm_host_map map; + u64 vmcb12_gpa; + struct vmcb *vmcb01 = svm->vmcb01.ptr; + + if (!svm->nested.hsave_msr) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + if (is_smm(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + /* This fails when VP assist page is enabled but the supplied GPA is bogus */ + ret = kvm_hv_verify_vp_assist(vcpu); + if (ret) { + kvm_inject_gp(vcpu, 0); + return ret; + } + + vmcb12_gpa = svm->vmcb->save.rax; + ret = kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map); + if (ret == -EINVAL) { + kvm_inject_gp(vcpu, 0); + return 1; + } else if (ret) { + return kvm_skip_emulated_instruction(vcpu); + } + + ret = kvm_skip_emulated_instruction(vcpu); + + vmcb12 = map.hva; + + if (WARN_ON_ONCE(!svm->nested.initialized)) + return -EINVAL; + + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); + + if (!nested_vmcb_check_save(vcpu) || + !nested_vmcb_check_controls(vcpu)) { + vmcb12->control.exit_code = SVM_EXIT_ERR; + vmcb12->control.exit_code_hi = 0; + vmcb12->control.exit_info_1 = 0; + vmcb12->control.exit_info_2 = 0; + goto out; + } + + /* + * Since vmcb01 is not in use, we can use it to store some of the L1 + * state. + */ + vmcb01->save.efer = vcpu->arch.efer; + vmcb01->save.cr0 = kvm_read_cr0(vcpu); + vmcb01->save.cr4 = vcpu->arch.cr4; + vmcb01->save.rflags = kvm_get_rflags(vcpu); + vmcb01->save.rip = kvm_rip_read(vcpu); + + if (!npt_enabled) + vmcb01->save.cr3 = kvm_read_cr3(vcpu); + + svm->nested.nested_run_pending = 1; + + if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true)) + goto out_exit_err; + + if (nested_svm_vmrun_msrpm(svm)) + goto out; + +out_exit_err: + svm->nested.nested_run_pending = 0; + svm->nmi_l1_to_l2 = false; + svm->soft_int_injected = false; + + svm->vmcb->control.exit_code = SVM_EXIT_ERR; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + + nested_svm_vmexit(svm); + +out: + kvm_vcpu_unmap(vcpu, &map, true); + + return ret; +} + +/* Copy state save area fields which are handled by VMRUN */ +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save) +{ + to_save->es = from_save->es; + to_save->cs = from_save->cs; + to_save->ss = from_save->ss; + to_save->ds = from_save->ds; + to_save->gdtr = from_save->gdtr; + to_save->idtr = from_save->idtr; + to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED; + to_save->efer = from_save->efer; + to_save->cr0 = from_save->cr0; + to_save->cr3 = from_save->cr3; + to_save->cr4 = from_save->cr4; + to_save->rax = from_save->rax; + to_save->rsp = from_save->rsp; + to_save->rip = from_save->rip; + to_save->cpl = 0; +} + +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb) +{ + to_vmcb->save.fs = from_vmcb->save.fs; + to_vmcb->save.gs = from_vmcb->save.gs; + to_vmcb->save.tr = from_vmcb->save.tr; + to_vmcb->save.ldtr = from_vmcb->save.ldtr; + to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base; + to_vmcb->save.star = from_vmcb->save.star; + to_vmcb->save.lstar = from_vmcb->save.lstar; + to_vmcb->save.cstar = from_vmcb->save.cstar; + to_vmcb->save.sfmask = from_vmcb->save.sfmask; + to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs; + to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp; + to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; +} + +int nested_svm_vmexit(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct vmcb *vmcb01 = svm->vmcb01.ptr; + struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; + struct vmcb *vmcb12; + struct kvm_host_map map; + int rc; + + rc = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa), &map); + if (rc) { + if (rc == -EINVAL) + kvm_inject_gp(vcpu, 0); + return 1; + } + + vmcb12 = map.hva; + + /* Exit Guest-Mode */ + leave_guest_mode(vcpu); + svm->nested.vmcb12_gpa = 0; + WARN_ON_ONCE(svm->nested.nested_run_pending); + + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + + /* in case we halted in L2 */ + svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE; + + /* Give the current vmcb to the guest */ + + vmcb12->save.es = vmcb02->save.es; + vmcb12->save.cs = vmcb02->save.cs; + vmcb12->save.ss = vmcb02->save.ss; + vmcb12->save.ds = vmcb02->save.ds; + vmcb12->save.gdtr = vmcb02->save.gdtr; + vmcb12->save.idtr = vmcb02->save.idtr; + vmcb12->save.efer = svm->vcpu.arch.efer; + vmcb12->save.cr0 = kvm_read_cr0(vcpu); + vmcb12->save.cr3 = kvm_read_cr3(vcpu); + vmcb12->save.cr2 = vmcb02->save.cr2; + vmcb12->save.cr4 = svm->vcpu.arch.cr4; + vmcb12->save.rflags = kvm_get_rflags(vcpu); + vmcb12->save.rip = kvm_rip_read(vcpu); + vmcb12->save.rsp = kvm_rsp_read(vcpu); + vmcb12->save.rax = kvm_rax_read(vcpu); + vmcb12->save.dr7 = vmcb02->save.dr7; + vmcb12->save.dr6 = svm->vcpu.arch.dr6; + vmcb12->save.cpl = vmcb02->save.cpl; + + vmcb12->control.int_state = vmcb02->control.int_state; + vmcb12->control.exit_code = vmcb02->control.exit_code; + vmcb12->control.exit_code_hi = vmcb02->control.exit_code_hi; + vmcb12->control.exit_info_1 = vmcb02->control.exit_info_1; + vmcb12->control.exit_info_2 = vmcb02->control.exit_info_2; + + if (vmcb12->control.exit_code != SVM_EXIT_ERR) + nested_save_pending_event_to_vmcb12(svm, vmcb12); + + if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + vmcb12->control.next_rip = vmcb02->control.next_rip; + + vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; + vmcb12->control.event_inj = svm->nested.ctl.event_inj; + vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; + + if (!kvm_pause_in_guest(vcpu->kvm)) { + vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count; + vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); + + } + + nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); + + svm_switch_vmcb(svm, &svm->vmcb01); + + /* + * Rules for synchronizing int_ctl bits from vmcb02 to vmcb01: + * + * V_IRQ, V_IRQ_VECTOR, V_INTR_PRIO_MASK, V_IGN_TPR: If L1 doesn't + * intercept interrupts, then KVM will use vmcb02's V_IRQ (and related + * flags) to detect interrupt windows for L1 IRQs (even if L1 uses + * virtual interrupt masking). Raise KVM_REQ_EVENT to ensure that + * KVM re-requests an interrupt window if necessary, which implicitly + * copies this bits from vmcb02 to vmcb01. + * + * V_TPR: If L1 doesn't use virtual interrupt masking, then L1's vTPR + * is stored in vmcb02, but its value doesn't need to be copied from/to + * vmcb01 because it is copied from/to the virtual APIC's TPR register + * on each VM entry/exit. + * + * V_GIF: If nested vGIF is not used, KVM uses vmcb02's V_GIF for L1's + * V_GIF. However, GIF is architecturally clear on each VM exit, thus + * there is no need to copy V_GIF from vmcb02 to vmcb01. + */ + if (!nested_exit_on_intr(svm)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + + if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { + svm_copy_lbrs(vmcb12, vmcb02); + svm_update_lbrv(vcpu); + } else if (unlikely(vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK)) { + svm_copy_lbrs(vmcb01, vmcb02); + 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. + */ + svm_set_gif(svm, false); + vmcb01->control.exit_int_info = 0; + + svm->vcpu.arch.tsc_offset = svm->vcpu.arch.l1_tsc_offset; + if (vmcb01->control.tsc_offset != svm->vcpu.arch.tsc_offset) { + vmcb01->control.tsc_offset = svm->vcpu.arch.tsc_offset; + vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); + } + + if (kvm_caps.has_tsc_control && + vcpu->arch.tsc_scaling_ratio != vcpu->arch.l1_tsc_scaling_ratio) { + vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; + svm_write_tsc_multiplier(vcpu); + } + + svm->nested.ctl.nested_cr3 = 0; + + /* + * Restore processor state that had been saved in vmcb01 + */ + kvm_set_rflags(vcpu, vmcb01->save.rflags); + svm_set_efer(vcpu, vmcb01->save.efer); + svm_set_cr0(vcpu, vmcb01->save.cr0 | X86_CR0_PE); + svm_set_cr4(vcpu, vmcb01->save.cr4); + kvm_rax_write(vcpu, vmcb01->save.rax); + kvm_rsp_write(vcpu, vmcb01->save.rsp); + kvm_rip_write(vcpu, vmcb01->save.rip); + + svm->vcpu.arch.dr7 = DR7_FIXED_1; + kvm_update_dr7(&svm->vcpu); + + trace_kvm_nested_vmexit_inject(vmcb12->control.exit_code, + vmcb12->control.exit_info_1, + vmcb12->control.exit_info_2, + vmcb12->control.exit_int_info, + vmcb12->control.exit_int_info_err, + KVM_ISA_SVM); + + kvm_vcpu_unmap(vcpu, &map, true); + + nested_svm_transition_tlb_flush(vcpu); + + nested_svm_uninit_mmu_context(vcpu); + + rc = nested_svm_load_cr3(vcpu, vmcb01->save.cr3, false, true); + if (rc) + return 1; + + /* + * Drop what we picked up for L2 via svm_complete_interrupts() so it + * doesn't end up in L1. + */ + svm->vcpu.arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + + /* + * If we are here following the completion of a VMRUN that + * is being single-stepped, queue the pending #DB intercept + * right now so that it an be accounted for before we execute + * L1's next instruction. + */ + if (unlikely(vmcb01->save.rflags & X86_EFLAGS_TF)) + kvm_queue_exception(&(svm->vcpu), DB_VECTOR); + + /* + * Un-inhibit the AVIC right away, so that other vCPUs can start + * to benefit from it right away. + */ + if (kvm_apicv_activated(vcpu->kvm)) + __kvm_vcpu_update_apicv(vcpu); + + return 0; +} + +static void nested_svm_triple_fault(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN)) + return; + + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); + nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN); +} + +int svm_allocate_nested(struct vcpu_svm *svm) +{ + struct page *vmcb02_page; + + if (svm->nested.initialized) + return 0; + + vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!vmcb02_page) + return -ENOMEM; + svm->nested.vmcb02.ptr = page_address(vmcb02_page); + svm->nested.vmcb02.pa = __sme_set(page_to_pfn(vmcb02_page) << PAGE_SHIFT); + + svm->nested.msrpm = svm_vcpu_alloc_msrpm(); + if (!svm->nested.msrpm) + goto err_free_vmcb02; + svm_vcpu_init_msrpm(&svm->vcpu, svm->nested.msrpm); + + svm->nested.initialized = true; + return 0; + +err_free_vmcb02: + __free_page(vmcb02_page); + return -ENOMEM; +} + +void svm_free_nested(struct vcpu_svm *svm) +{ + if (!svm->nested.initialized) + return; + + if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr)) + svm_switch_vmcb(svm, &svm->vmcb01); + + svm_vcpu_free_msrpm(svm->nested.msrpm); + svm->nested.msrpm = NULL; + + __free_page(virt_to_page(svm->nested.vmcb02.ptr)); + svm->nested.vmcb02.ptr = NULL; + + /* + * When last_vmcb12_gpa matches the current vmcb12 gpa, + * some vmcb12 fields are not loaded if they are marked clean + * in the vmcb12, since in this case they are up to date already. + * + * When the vmcb02 is freed, this optimization becomes invalid. + */ + svm->nested.last_vmcb12_gpa = INVALID_GPA; + + svm->nested.initialized = false; +} + +void svm_leave_nested(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_guest_mode(vcpu)) { + svm->nested.nested_run_pending = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + + leave_guest_mode(vcpu); + + svm_switch_vmcb(svm, &svm->vmcb01); + + nested_svm_uninit_mmu_context(vcpu); + vmcb_mark_all_dirty(svm->vmcb); + + if (kvm_apicv_activated(vcpu->kvm)) + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); +} + +static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) +{ + u32 offset, msr, value; + int write, mask; + + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + return NESTED_EXIT_HOST; + + msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + offset = svm_msrpm_offset(msr); + write = svm->vmcb->control.exit_info_1 & 1; + mask = 1 << ((2 * (msr & 0xf)) + write); + + if (offset == MSR_INVALID) + return NESTED_EXIT_DONE; + + /* Offset is in 32 bit units but need in 8 bit units */ + offset *= 4; + + if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.ctl.msrpm_base_pa + offset, &value, 4)) + return NESTED_EXIT_DONE; + + return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; +} + +static int nested_svm_intercept_ioio(struct vcpu_svm *svm) +{ + unsigned port, size, iopm_len; + u16 val, mask; + u8 start_bit; + u64 gpa; + + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) + return NESTED_EXIT_HOST; + + port = svm->vmcb->control.exit_info_1 >> 16; + size = (svm->vmcb->control.exit_info_1 & SVM_IOIO_SIZE_MASK) >> + SVM_IOIO_SIZE_SHIFT; + gpa = svm->nested.ctl.iopm_base_pa + (port / 8); + start_bit = port % 8; + iopm_len = (start_bit + size > 8) ? 2 : 1; + mask = (0xf >> (4 - size)) << start_bit; + val = 0; + + if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len)) + return NESTED_EXIT_DONE; + + return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; +} + +static int nested_svm_intercept(struct vcpu_svm *svm) +{ + u32 exit_code = svm->vmcb->control.exit_code; + int vmexit = NESTED_EXIT_HOST; + + switch (exit_code) { + case SVM_EXIT_MSR: + vmexit = nested_svm_exit_handled_msr(svm); + break; + case SVM_EXIT_IOIO: + vmexit = nested_svm_intercept_ioio(svm); + break; + case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) + vmexit = NESTED_EXIT_DONE; + break; + } + case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) + vmexit = NESTED_EXIT_DONE; + break; + } + case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { + /* + * Host-intercepted exceptions have been checked already in + * nested_svm_exit_special. There is nothing to do here, + * the vmexit is injected by svm_check_nested_events. + */ + vmexit = NESTED_EXIT_DONE; + break; + } + case SVM_EXIT_ERR: { + vmexit = NESTED_EXIT_DONE; + break; + } + default: { + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) + vmexit = NESTED_EXIT_DONE; + } + } + + return vmexit; +} + +int nested_svm_exit_handled(struct vcpu_svm *svm) +{ + int vmexit; + + vmexit = nested_svm_intercept(svm); + + if (vmexit == NESTED_EXIT_DONE) + nested_svm_vmexit(svm); + + return vmexit; +} + +int nested_svm_check_permissions(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.efer & EFER_SVME) || !is_paging(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + if (to_svm(vcpu)->vmcb->save.cpl) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + return 0; +} + +static bool nested_svm_is_exception_vmexit(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(vector)); +} + +static void nested_svm_inject_exception_vmexit(struct kvm_vcpu *vcpu) +{ + struct kvm_queued_exception *ex = &vcpu->arch.exception_vmexit; + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + + vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + ex->vector; + vmcb->control.exit_code_hi = 0; + + if (ex->has_error_code) + vmcb->control.exit_info_1 = ex->error_code; + + /* + * EXITINFO2 is undefined for all exception intercepts other + * than #PF. + */ + if (ex->vector == PF_VECTOR) { + if (ex->has_payload) + vmcb->control.exit_info_2 = ex->payload; + else + vmcb->control.exit_info_2 = vcpu->arch.cr2; + } else if (ex->vector == DB_VECTOR) { + /* See kvm_check_and_inject_events(). */ + kvm_deliver_exception_payload(vcpu, ex); + + if (vcpu->arch.dr7 & DR7_GD) { + vcpu->arch.dr7 &= ~DR7_GD; + kvm_update_dr7(vcpu); + } + } else { + WARN_ON(ex->has_payload); + } + + nested_svm_vmexit(svm); +} + +static inline bool nested_exit_on_init(struct vcpu_svm *svm) +{ + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); +} + +static int svm_check_nested_events(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + struct vcpu_svm *svm = to_svm(vcpu); + /* + * Only a pending nested run blocks a pending exception. If there is a + * previously injected event, the pending exception occurred while said + * event was being delivered and thus needs to be handled. + */ + bool block_nested_exceptions = svm->nested.nested_run_pending; + /* + * New events (not exceptions) are only recognized at instruction + * boundaries. If an event needs reinjection, then KVM is handling a + * VM-Exit that occurred _during_ instruction execution; new events are + * blocked until the instruction completes. + */ + bool block_nested_events = block_nested_exceptions || + kvm_event_needs_reinjection(vcpu); + + if (lapic_in_kernel(vcpu) && + test_bit(KVM_APIC_INIT, &apic->pending_events)) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_init(svm)) + return 0; + nested_svm_simple_vmexit(svm, SVM_EXIT_INIT); + return 0; + } + + if (vcpu->arch.exception_vmexit.pending) { + if (block_nested_exceptions) + return -EBUSY; + nested_svm_inject_exception_vmexit(vcpu); + return 0; + } + + if (vcpu->arch.exception.pending) { + if (block_nested_exceptions) + return -EBUSY; + return 0; + } + +#ifdef CONFIG_KVM_SMM + if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_smi(svm)) + return 0; + nested_svm_simple_vmexit(svm, SVM_EXIT_SMI); + return 0; + } +#endif + + if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_nmi(svm)) + return 0; + nested_svm_simple_vmexit(svm, SVM_EXIT_NMI); + return 0; + } + + if (kvm_cpu_has_interrupt(vcpu) && !svm_interrupt_blocked(vcpu)) { + if (block_nested_events) + return -EBUSY; + if (!nested_exit_on_intr(svm)) + return 0; + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); + nested_svm_simple_vmexit(svm, SVM_EXIT_INTR); + return 0; + } + + return 0; +} + +int nested_svm_exit_special(struct vcpu_svm *svm) +{ + u32 exit_code = svm->vmcb->control.exit_code; + struct kvm_vcpu *vcpu = &svm->vcpu; + + switch (exit_code) { + case SVM_EXIT_INTR: + case SVM_EXIT_NMI: + case SVM_EXIT_NPF: + return NESTED_EXIT_HOST; + case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { + u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); + + if (svm->vmcb01.ptr->control.intercepts[INTERCEPT_EXCEPTION] & + excp_bits) + return NESTED_EXIT_HOST; + else if (exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR && + svm->vcpu.arch.apf.host_apf_flags) + /* Trap async PF even if not shadowing */ + return NESTED_EXIT_HOST; + break; + } + case SVM_EXIT_VMMCALL: + /* Hyper-V L2 TLB flush hypercall is handled by L0 */ + if (guest_hv_cpuid_has_l2_tlb_flush(vcpu) && + nested_svm_l2_tlb_flush_enabled(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu)) + return NESTED_EXIT_HOST; + break; + default: + break; + } + + return NESTED_EXIT_CONTINUE; +} + +void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->arch.tsc_scaling_ratio = + kvm_calc_nested_tsc_multiplier(vcpu->arch.l1_tsc_scaling_ratio, + svm->tsc_ratio_msr); + svm_write_tsc_multiplier(vcpu); +} + +/* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */ +static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst, + struct vmcb_ctrl_area_cached *from) +{ + unsigned int i; + + memset(dst, 0, sizeof(struct vmcb_control_area)); + + for (i = 0; i < MAX_INTERCEPT; i++) + dst->intercepts[i] = from->intercepts[i]; + + dst->iopm_base_pa = from->iopm_base_pa; + dst->msrpm_base_pa = from->msrpm_base_pa; + dst->tsc_offset = from->tsc_offset; + dst->asid = from->asid; + dst->tlb_ctl = from->tlb_ctl; + dst->int_ctl = from->int_ctl; + dst->int_vector = from->int_vector; + dst->int_state = from->int_state; + dst->exit_code = from->exit_code; + dst->exit_code_hi = from->exit_code_hi; + dst->exit_info_1 = from->exit_info_1; + dst->exit_info_2 = from->exit_info_2; + dst->exit_int_info = from->exit_int_info; + dst->exit_int_info_err = from->exit_int_info_err; + dst->nested_ctl = from->nested_ctl; + dst->event_inj = from->event_inj; + dst->event_inj_err = from->event_inj_err; + dst->next_rip = from->next_rip; + dst->nested_cr3 = from->nested_cr3; + dst->virt_ext = from->virt_ext; + dst->pause_filter_count = from->pause_filter_count; + dst->pause_filter_thresh = from->pause_filter_thresh; + /* 'clean' and 'hv_enlightenments' are not changed by KVM */ +} + +static int svm_get_nested_state(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + u32 user_data_size) +{ + struct vcpu_svm *svm; + struct vmcb_control_area *ctl; + unsigned long r; + struct kvm_nested_state kvm_state = { + .flags = 0, + .format = KVM_STATE_NESTED_FORMAT_SVM, + .size = sizeof(kvm_state), + }; + struct vmcb __user *user_vmcb = (struct vmcb __user *) + &user_kvm_nested_state->data.svm[0]; + + if (!vcpu) + return kvm_state.size + KVM_STATE_NESTED_SVM_VMCB_SIZE; + + svm = to_svm(vcpu); + + if (user_data_size < kvm_state.size) + goto out; + + /* First fill in the header and copy it out. */ + if (is_guest_mode(vcpu)) { + kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb12_gpa; + kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE; + kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE; + + if (svm->nested.nested_run_pending) + kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + } + + if (gif_set(svm)) + kvm_state.flags |= KVM_STATE_NESTED_GIF_SET; + + if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state))) + return -EFAULT; + + if (!is_guest_mode(vcpu)) + goto out; + + /* + * Copy over the full size of the VMCB rather than just the size + * of the structs. + */ + if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE)) + return -EFAULT; + + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return -ENOMEM; + + nested_copy_vmcb_cache_to_control(ctl, &svm->nested.ctl); + r = copy_to_user(&user_vmcb->control, ctl, + sizeof(user_vmcb->control)); + kfree(ctl); + if (r) + return -EFAULT; + + if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save, + sizeof(user_vmcb->save))) + return -EFAULT; +out: + return kvm_state.size; +} + +static int svm_set_nested_state(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb __user *user_vmcb = (struct vmcb __user *) + &user_kvm_nested_state->data.svm[0]; + struct vmcb_control_area *ctl; + struct vmcb_save_area *save; + struct vmcb_save_area_cached save_cached; + struct vmcb_ctrl_area_cached ctl_cached; + unsigned long cr0; + int ret; + + BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) > + KVM_STATE_NESTED_SVM_VMCB_SIZE); + + if (kvm_state->format != KVM_STATE_NESTED_FORMAT_SVM) + return -EINVAL; + + if (kvm_state->flags & ~(KVM_STATE_NESTED_GUEST_MODE | + KVM_STATE_NESTED_RUN_PENDING | + KVM_STATE_NESTED_GIF_SET)) + return -EINVAL; + + /* + * If in guest mode, vcpu->arch.efer actually refers to the L2 guest's + * EFER.SVME, but EFER.SVME still has to be 1 for VMRUN to succeed. + */ + if (!(vcpu->arch.efer & EFER_SVME)) { + /* GIF=1 and no guest mode are required if SVME=0. */ + if (kvm_state->flags != KVM_STATE_NESTED_GIF_SET) + return -EINVAL; + } + + /* SMM temporarily disables SVM, so we cannot be in guest mode. */ + if (is_smm(vcpu) && (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) + return -EINVAL; + + if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) { + svm_leave_nested(vcpu); + svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); + return 0; + } + + if (!page_address_valid(vcpu, kvm_state->hdr.svm.vmcb_pa)) + return -EINVAL; + if (kvm_state->size < sizeof(*kvm_state) + KVM_STATE_NESTED_SVM_VMCB_SIZE) + return -EINVAL; + + ret = -ENOMEM; + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL_ACCOUNT); + save = kzalloc(sizeof(*save), GFP_KERNEL_ACCOUNT); + if (!ctl || !save) + goto out_free; + + ret = -EFAULT; + if (copy_from_user(ctl, &user_vmcb->control, sizeof(*ctl))) + goto out_free; + if (copy_from_user(save, &user_vmcb->save, sizeof(*save))) + goto out_free; + + ret = -EINVAL; + __nested_copy_vmcb_control_to_cache(vcpu, &ctl_cached, ctl); + if (!__nested_vmcb_check_controls(vcpu, &ctl_cached)) + goto out_free; + + /* + * Processor state contains L2 state. Check that it is + * valid for guest mode (see nested_vmcb_check_save). + */ + cr0 = kvm_read_cr0(vcpu); + if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW)) + goto out_free; + + /* + * Validate host state saved from before VMRUN (see + * nested_svm_check_permissions). + */ + __nested_copy_vmcb_save_to_cache(&save_cached, save); + if (!(save->cr0 & X86_CR0_PG) || + !(save->cr0 & X86_CR0_PE) || + (save->rflags & X86_EFLAGS_VM) || + !__nested_vmcb_check_save(vcpu, &save_cached)) + goto out_free; + + + /* + * All checks done, we can enter guest mode. Userspace provides + * vmcb12.control, which will be combined with L1 and stored into + * vmcb02, and the L1 save state which we store in vmcb01. + * L2 registers if needed are moved from the current VMCB to VMCB02. + */ + + if (is_guest_mode(vcpu)) + svm_leave_nested(vcpu); + else + svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; + + svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); + + svm->nested.nested_run_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + + svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; + + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save); + nested_copy_vmcb_control_to_cache(svm, ctl); + + svm_switch_vmcb(svm, &svm->nested.vmcb02); + nested_vmcb02_prepare_control(svm, svm->vmcb->save.rip, svm->vmcb->save.cs.base); + + /* + * While the nested guest CR3 is already checked and set by + * KVM_SET_SREGS, it was set when nested state was yet loaded, + * thus MMU might not be initialized correctly. + * Set it again to fix this. + */ + + ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, + nested_npt_enabled(svm), false); + if (WARN_ON_ONCE(ret)) + goto out_free; + + svm->nested.force_msr_bitmap_recalc = true; + + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + ret = 0; +out_free: + kfree(save); + kfree(ctl); + + return ret; +} + +static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (WARN_ON(!is_guest_mode(vcpu))) + return true; + + if (!vcpu->arch.pdptrs_from_userspace && + !nested_npt_enabled(svm) && is_pae_paging(vcpu)) + /* + * Reload the guest's PDPTRs since after a migration + * the guest CR3 might be restored prior to setting the nested + * state which can lead to a load of wrong PDPTRs. + */ + if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3))) + return false; + + if (!nested_svm_vmrun_msrpm(svm)) { + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; + } + + if (kvm_hv_verify_vp_assist(vcpu)) + return false; + + return true; +} + +struct kvm_x86_nested_ops svm_nested_ops = { + .leave_nested = svm_leave_nested, + .is_exception_vmexit = nested_svm_is_exception_vmexit, + .check_events = svm_check_nested_events, + .triple_fault = nested_svm_triple_fault, + .get_nested_state_pages = svm_get_nested_state_pages, + .get_state = svm_get_nested_state, + .set_state = svm_set_nested_state, + .hv_inject_synthetic_vmexit_post_tlb_flush = svm_hv_inject_synthetic_vmexit_post_tlb_flush, +}; diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c new file mode 100644 index 0000000000..3fd47de14b --- /dev/null +++ b/arch/x86/kvm/svm/pmu.c @@ -0,0 +1,250 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM PMU support for AMD + * + * Copyright 2015, Red Hat, Inc. and/or its affiliates. + * + * Author: + * Wei Huang + * + * Implementation is based on pmu_intel.c file + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#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_pmc_idx_to_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 (!vcpu->kvm->arch.enable_pmu) + return NULL; + + switch (msr) { + case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: + if (!guest_cpuid_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_pmc_idx_to_pmc(pmu, idx); +} + +static bool amd_hw_event_available(struct kvm_pmc *pmc) +{ + return true; +} + +static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + idx &= ~(3u << 30); + + return idx < pmu->nr_arch_gp_counters; +} + +/* 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_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30)); +} + +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_cpuid_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: + 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); + pmc_update_sample_period(pmc); + 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; + 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_cpuid_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_cpuid_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_mask = ~((1ull << pmu->nr_arch_gp_counters) - 1); + pmu->global_status_mask = pmu->global_ctrl_mask; + } + + pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; + pmu->reserved_bits = 0xfffffff000280000ull; + 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; + bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters); +} + +static void amd_pmu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > AMD64_NUM_COUNTERS_CORE); + BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > INTEL_PMC_MAX_GENERIC); + + for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC ; 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; + } +} + +struct kvm_pmu_ops amd_pmu_ops __initdata = { + .hw_event_available = amd_hw_event_available, + .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, + .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, + .msr_idx_to_pmc = amd_msr_idx_to_pmc, + .is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx, + .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, + .EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT, + .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC, + .MIN_NR_GP_COUNTERS = AMD64_NUM_COUNTERS, +}; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c new file mode 100644 index 0000000000..4900c07804 --- /dev/null +++ b/arch/x86/kvm/svm/sev.c @@ -0,0 +1,3140 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM-SEV support + * + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include "mmu.h" +#include "x86.h" +#include "svm.h" +#include "svm_ops.h" +#include "cpuid.h" +#include "trace.h" + +#ifndef CONFIG_KVM_AMD_SEV +/* + * When this config is not defined, SEV feature is not supported and APIs in + * this file are not used but this file still gets compiled into the KVM AMD + * module. + * + * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum + * misc_res_type {} defined in linux/misc_cgroup.h. + * + * Below macros allow compilation to succeed. + */ +#define MISC_CG_RES_SEV MISC_CG_RES_TYPES +#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES +#endif + +#ifdef CONFIG_KVM_AMD_SEV +/* enable/disable SEV support */ +static bool sev_enabled = true; +module_param_named(sev, sev_enabled, bool, 0444); + +/* enable/disable SEV-ES support */ +static bool sev_es_enabled = true; +module_param_named(sev_es, sev_es_enabled, bool, 0444); + +/* enable/disable SEV-ES DebugSwap support */ +static bool sev_es_debug_swap_enabled = true; +module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444); +#else +#define sev_enabled false +#define sev_es_enabled false +#define sev_es_debug_swap_enabled false +#endif /* CONFIG_KVM_AMD_SEV */ + +static u8 sev_enc_bit; +static DECLARE_RWSEM(sev_deactivate_lock); +static DEFINE_MUTEX(sev_bitmap_lock); +unsigned int max_sev_asid; +static unsigned int min_sev_asid; +static unsigned long sev_me_mask; +static unsigned int nr_asids; +static unsigned long *sev_asid_bitmap; +static unsigned long *sev_reclaim_asid_bitmap; + +struct enc_region { + struct list_head list; + unsigned long npages; + struct page **pages; + unsigned long uaddr; + unsigned long size; +}; + +/* Called with the sev_bitmap_lock held, or on shutdown */ +static int sev_flush_asids(int min_asid, int max_asid) +{ + int ret, asid, error = 0; + + /* Check if there are any ASIDs to reclaim before performing a flush */ + asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); + if (asid > max_asid) + return -EBUSY; + + /* + * DEACTIVATE will clear the WBINVD indicator causing DF_FLUSH to fail, + * so it must be guarded. + */ + down_write(&sev_deactivate_lock); + + wbinvd_on_all_cpus(); + ret = sev_guest_df_flush(&error); + + up_write(&sev_deactivate_lock); + + if (ret) + pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error); + + return ret; +} + +static inline bool is_mirroring_enc_context(struct kvm *kvm) +{ + return !!to_kvm_svm(kvm)->sev_info.enc_context_owner; +} + +/* Must be called with the sev_bitmap_lock held */ +static bool __sev_recycle_asids(int min_asid, int max_asid) +{ + if (sev_flush_asids(min_asid, max_asid)) + return false; + + /* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */ + bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap, + nr_asids); + bitmap_zero(sev_reclaim_asid_bitmap, nr_asids); + + return true; +} + +static int sev_misc_cg_try_charge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + return misc_cg_try_charge(type, sev->misc_cg, 1); +} + +static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) +{ + enum misc_res_type type = sev->es_active ? MISC_CG_RES_SEV_ES : MISC_CG_RES_SEV; + misc_cg_uncharge(type, sev->misc_cg, 1); +} + +static int sev_asid_new(struct kvm_sev_info *sev) +{ + int asid, min_asid, max_asid, ret; + bool retry = true; + + WARN_ON(sev->misc_cg); + sev->misc_cg = get_current_misc_cg(); + ret = sev_misc_cg_try_charge(sev); + if (ret) { + put_misc_cg(sev->misc_cg); + sev->misc_cg = NULL; + return ret; + } + + mutex_lock(&sev_bitmap_lock); + + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + */ + min_asid = sev->es_active ? 1 : min_sev_asid; + max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; +again: + asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); + if (asid > max_asid) { + if (retry && __sev_recycle_asids(min_asid, max_asid)) { + retry = false; + goto again; + } + mutex_unlock(&sev_bitmap_lock); + ret = -EBUSY; + goto e_uncharge; + } + + __set_bit(asid, sev_asid_bitmap); + + mutex_unlock(&sev_bitmap_lock); + + return asid; +e_uncharge: + sev_misc_cg_uncharge(sev); + put_misc_cg(sev->misc_cg); + sev->misc_cg = NULL; + return ret; +} + +static int sev_get_asid(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return sev->asid; +} + +static void sev_asid_free(struct kvm_sev_info *sev) +{ + struct svm_cpu_data *sd; + int cpu; + + mutex_lock(&sev_bitmap_lock); + + __set_bit(sev->asid, sev_reclaim_asid_bitmap); + + for_each_possible_cpu(cpu) { + sd = per_cpu_ptr(&svm_data, cpu); + sd->sev_vmcbs[sev->asid] = NULL; + } + + mutex_unlock(&sev_bitmap_lock); + + sev_misc_cg_uncharge(sev); + put_misc_cg(sev->misc_cg); + sev->misc_cg = NULL; +} + +static void sev_decommission(unsigned int handle) +{ + struct sev_data_decommission decommission; + + if (!handle) + return; + + decommission.handle = handle; + sev_guest_decommission(&decommission, NULL); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ + struct sev_data_deactivate deactivate; + + if (!handle) + return; + + deactivate.handle = handle; + + /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ + down_read(&sev_deactivate_lock); + sev_guest_deactivate(&deactivate, NULL); + up_read(&sev_deactivate_lock); + + sev_decommission(handle); +} + +static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + int asid, ret; + + if (kvm->created_vcpus) + return -EINVAL; + + ret = -EBUSY; + if (unlikely(sev->active)) + return ret; + + sev->active = true; + sev->es_active = argp->id == KVM_SEV_ES_INIT; + asid = sev_asid_new(sev); + if (asid < 0) + goto e_no_asid; + sev->asid = asid; + + ret = sev_platform_init(&argp->error); + if (ret) + goto e_free; + + INIT_LIST_HEAD(&sev->regions_list); + INIT_LIST_HEAD(&sev->mirror_vms); + + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV); + + return 0; + +e_free: + sev_asid_free(sev); + sev->asid = 0; +e_no_asid: + sev->es_active = false; + sev->active = false; + return ret; +} + +static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) +{ + struct sev_data_activate activate; + int asid = sev_get_asid(kvm); + int ret; + + /* activate ASID on the given handle */ + activate.handle = handle; + activate.asid = asid; + ret = sev_guest_activate(&activate, error); + + return ret; +} + +static int __sev_issue_cmd(int fd, int id, void *data, int *error) +{ + struct fd f; + int ret; + + f = fdget(fd); + if (!f.file) + return -EBADF; + + ret = sev_issue_cmd_external_user(f.file, id, data, error); + + fdput(f); + return ret; +} + +static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *error) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return __sev_issue_cmd(sev->fd, id, data, error); +} + +static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_start start; + struct kvm_sev_launch_start params; + void *dh_blob, *session_blob; + int *error = &argp->error; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + memset(&start, 0, sizeof(start)); + + dh_blob = NULL; + if (params.dh_uaddr) { + dh_blob = psp_copy_user_blob(params.dh_uaddr, params.dh_len); + if (IS_ERR(dh_blob)) + return PTR_ERR(dh_blob); + + start.dh_cert_address = __sme_set(__pa(dh_blob)); + start.dh_cert_len = params.dh_len; + } + + session_blob = NULL; + if (params.session_uaddr) { + session_blob = psp_copy_user_blob(params.session_uaddr, params.session_len); + if (IS_ERR(session_blob)) { + ret = PTR_ERR(session_blob); + goto e_free_dh; + } + + start.session_address = __sme_set(__pa(session_blob)); + start.session_len = params.session_len; + } + + start.handle = params.handle; + start.policy = params.policy; + + /* create memory encryption context */ + ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_LAUNCH_START, &start, error); + if (ret) + goto e_free_session; + + /* Bind ASID to this guest */ + ret = sev_bind_asid(kvm, start.handle, error); + if (ret) { + sev_decommission(start.handle); + goto e_free_session; + } + + /* return handle to userspace */ + params.handle = start.handle; + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { + sev_unbind_asid(kvm, start.handle); + ret = -EFAULT; + goto e_free_session; + } + + sev->handle = start.handle; + sev->fd = argp->sev_fd; + +e_free_session: + kfree(session_blob); +e_free_dh: + kfree(dh_blob); + return ret; +} + +static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, + unsigned long ulen, unsigned long *n, + int write) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + unsigned long npages, size; + int npinned; + unsigned long locked, lock_limit; + struct page **pages; + unsigned long first, last; + int ret; + + lockdep_assert_held(&kvm->lock); + + if (ulen == 0 || uaddr + ulen < uaddr) + return ERR_PTR(-EINVAL); + + /* Calculate number of pages. */ + first = (uaddr & PAGE_MASK) >> PAGE_SHIFT; + last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT; + npages = (last - first + 1); + + locked = sev->pages_locked + npages; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { + pr_err("SEV: %lu locked pages exceed the lock limit of %lu.\n", locked, lock_limit); + return ERR_PTR(-ENOMEM); + } + + if (WARN_ON_ONCE(npages > INT_MAX)) + return ERR_PTR(-EINVAL); + + /* Avoid using vmalloc for smaller buffers. */ + size = npages * sizeof(struct page *); + if (size > PAGE_SIZE) + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); + else + pages = kmalloc(size, GFP_KERNEL_ACCOUNT); + + if (!pages) + return ERR_PTR(-ENOMEM); + + /* Pin the user virtual address. */ + npinned = pin_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); + if (npinned != npages) { + pr_err("SEV: Failure locking %lu pages.\n", npages); + ret = -ENOMEM; + goto err; + } + + *n = npages; + sev->pages_locked = locked; + + return pages; + +err: + if (npinned > 0) + unpin_user_pages(pages, npinned); + + kvfree(pages); + return ERR_PTR(ret); +} + +static void sev_unpin_memory(struct kvm *kvm, struct page **pages, + unsigned long npages) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + unpin_user_pages(pages, npages); + kvfree(pages); + sev->pages_locked -= npages; +} + +static void sev_clflush_pages(struct page *pages[], unsigned long npages) +{ + uint8_t *page_virtual; + unsigned long i; + + if (this_cpu_has(X86_FEATURE_SME_COHERENT) || npages == 0 || + pages == NULL) + return; + + for (i = 0; i < npages; i++) { + page_virtual = kmap_local_page(pages[i]); + clflush_cache_range(page_virtual, PAGE_SIZE); + kunmap_local(page_virtual); + cond_resched(); + } +} + +static unsigned long get_num_contig_pages(unsigned long idx, + struct page **inpages, unsigned long npages) +{ + unsigned long paddr, next_paddr; + unsigned long i = idx + 1, pages = 1; + + /* find the number of contiguous pages starting from idx */ + paddr = __sme_page_pa(inpages[idx]); + while (i < npages) { + next_paddr = __sme_page_pa(inpages[i++]); + if ((paddr + PAGE_SIZE) == next_paddr) { + pages++; + paddr = next_paddr; + continue; + } + break; + } + + return pages; +} + +static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i; + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_launch_update_data params; + struct sev_data_launch_update_data data; + struct page **inpages; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + vaddr = params.uaddr; + size = params.len; + vaddr_end = vaddr + size; + + /* Lock the user memory. */ + inpages = sev_pin_memory(kvm, vaddr, size, &npages, 1); + if (IS_ERR(inpages)) + return PTR_ERR(inpages); + + /* + * Flush (on non-coherent CPUs) before LAUNCH_UPDATE encrypts pages in + * place; the cache may contain the data that was written unencrypted. + */ + sev_clflush_pages(inpages, npages); + + data.reserved = 0; + data.handle = sev->handle; + + for (i = 0; vaddr < vaddr_end; vaddr = next_vaddr, i += pages) { + int offset, len; + + /* + * If the user buffer is not page-aligned, calculate the offset + * within the page. + */ + offset = vaddr & (PAGE_SIZE - 1); + + /* Calculate the number of pages that can be encrypted in one go. */ + pages = get_num_contig_pages(i, inpages, npages); + + len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size); + + data.len = len; + data.address = __sme_page_pa(inpages[i]) + offset; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, &data, &argp->error); + if (ret) + goto e_unpin; + + size -= len; + next_vaddr = vaddr + len; + } + +e_unpin: + /* content of memory is updated, mark pages dirty */ + for (i = 0; i < npages; i++) { + set_page_dirty_lock(inpages[i]); + mark_page_accessed(inpages[i]); + } + /* unlock the user pages */ + sev_unpin_memory(kvm, inpages, npages); + return ret; +} + +static int sev_es_sync_vmsa(struct vcpu_svm *svm) +{ + struct sev_es_save_area *save = svm->sev_es.vmsa; + + /* Check some debug related fields before encrypting the VMSA */ + if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1)) + return -EINVAL; + + /* + * SEV-ES will use a VMSA that is pointed to by the VMCB, not + * the traditional VMSA that is part of the VMCB. Copy the + * traditional VMSA as it has been built so far (in prep + * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state. + */ + memcpy(save, &svm->vmcb->save, sizeof(svm->vmcb->save)); + + /* Sync registgers */ + save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX]; + save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX]; + save->rcx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + save->rdx = svm->vcpu.arch.regs[VCPU_REGS_RDX]; + save->rsp = svm->vcpu.arch.regs[VCPU_REGS_RSP]; + save->rbp = svm->vcpu.arch.regs[VCPU_REGS_RBP]; + save->rsi = svm->vcpu.arch.regs[VCPU_REGS_RSI]; + save->rdi = svm->vcpu.arch.regs[VCPU_REGS_RDI]; +#ifdef CONFIG_X86_64 + save->r8 = svm->vcpu.arch.regs[VCPU_REGS_R8]; + save->r9 = svm->vcpu.arch.regs[VCPU_REGS_R9]; + save->r10 = svm->vcpu.arch.regs[VCPU_REGS_R10]; + save->r11 = svm->vcpu.arch.regs[VCPU_REGS_R11]; + save->r12 = svm->vcpu.arch.regs[VCPU_REGS_R12]; + save->r13 = svm->vcpu.arch.regs[VCPU_REGS_R13]; + save->r14 = svm->vcpu.arch.regs[VCPU_REGS_R14]; + save->r15 = svm->vcpu.arch.regs[VCPU_REGS_R15]; +#endif + save->rip = svm->vcpu.arch.regs[VCPU_REGS_RIP]; + + /* Sync some non-GPR registers before encrypting */ + save->xcr0 = svm->vcpu.arch.xcr0; + save->pkru = svm->vcpu.arch.pkru; + save->xss = svm->vcpu.arch.ia32_xss; + save->dr6 = svm->vcpu.arch.dr6; + + if (sev_es_debug_swap_enabled) + save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP; + + pr_debug("Virtual Machine Save Area (VMSA):\n"); + print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false); + + return 0; +} + +static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, + int *error) +{ + struct sev_data_launch_update_vmsa vmsa; + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + if (vcpu->guest_debug) { + pr_warn_once("KVM_SET_GUEST_DEBUG for SEV-ES guest is not supported"); + return -EINVAL; + } + + /* Perform some pre-encryption checks against the VMSA */ + ret = sev_es_sync_vmsa(svm); + if (ret) + return ret; + + /* + * The LAUNCH_UPDATE_VMSA command will perform in-place encryption of + * the VMSA memory content (i.e it will write the same memory region + * with the guest's key), so invalidate it first. + */ + clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE); + + vmsa.reserved = 0; + vmsa.handle = to_kvm_svm(kvm)->sev_info.handle; + vmsa.address = __sme_pa(svm->sev_es.vmsa); + vmsa.len = PAGE_SIZE; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error); + if (ret) + return ret; + + vcpu->arch.guest_state_protected = true; + return 0; +} + +static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + int ret; + + if (!sev_es_guest(kvm)) + return -ENOTTY; + + kvm_for_each_vcpu(i, vcpu, kvm) { + ret = mutex_lock_killable(&vcpu->mutex); + if (ret) + return ret; + + ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error); + + mutex_unlock(&vcpu->mutex); + if (ret) + return ret; + } + + return 0; +} + +static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + void __user *measure = (void __user *)(uintptr_t)argp->data; + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_measure data; + struct kvm_sev_launch_measure params; + void __user *p = NULL; + void *blob = NULL; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, measure, sizeof(params))) + return -EFAULT; + + memset(&data, 0, sizeof(data)); + + /* User wants to query the blob length */ + if (!params.len) + goto cmd; + + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { + if (params.len > SEV_FW_BLOB_MAX_SIZE) + return -EINVAL; + + blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT); + if (!blob) + return -ENOMEM; + + data.address = __psp_pa(blob); + data.len = params.len; + } + +cmd: + data.handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_MEASURE, &data, &argp->error); + + /* + * If we query the session length, FW responded with expected data. + */ + if (!params.len) + goto done; + + if (ret) + goto e_free_blob; + + if (blob) { + if (copy_to_user(p, blob, params.len)) + ret = -EFAULT; + } + +done: + params.len = data.len; + if (copy_to_user(measure, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free_blob: + kfree(blob); + return ret; +} + +static int sev_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_finish data; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data.handle = sev->handle; + return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, &data, &argp->error); +} + +static int sev_guest_status(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_guest_status params; + struct sev_data_guest_status data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + memset(&data, 0, sizeof(data)); + + data.handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, &data, &argp->error); + if (ret) + return ret; + + params.policy = data.policy; + params.state = data.state; + params.handle = data.handle; + + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) + ret = -EFAULT; + + return ret; +} + +static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, + unsigned long dst, int size, + int *error, bool enc) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_dbg data; + + data.reserved = 0; + data.handle = sev->handle; + data.dst_addr = dst; + data.src_addr = src; + data.len = size; + + return sev_issue_cmd(kvm, + enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT, + &data, error); +} + +static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, + unsigned long dst_paddr, int sz, int *err) +{ + int offset; + + /* + * Its safe to read more than we are asked, caller should ensure that + * destination has enough space. + */ + offset = src_paddr & 15; + src_paddr = round_down(src_paddr, 16); + sz = round_up(sz + offset, 16); + + return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false); +} + +static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, + void __user *dst_uaddr, + unsigned long dst_paddr, + int size, int *err) +{ + struct page *tpage = NULL; + int ret, offset; + + /* if inputs are not 16-byte then use intermediate buffer */ + if (!IS_ALIGNED(dst_paddr, 16) || + !IS_ALIGNED(paddr, 16) || + !IS_ALIGNED(size, 16)) { + tpage = (void *)alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!tpage) + return -ENOMEM; + + dst_paddr = __sme_page_pa(tpage); + } + + ret = __sev_dbg_decrypt(kvm, paddr, dst_paddr, size, err); + if (ret) + goto e_free; + + if (tpage) { + offset = paddr & 15; + if (copy_to_user(dst_uaddr, page_address(tpage) + offset, size)) + ret = -EFAULT; + } + +e_free: + if (tpage) + __free_page(tpage); + + return ret; +} + +static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, + void __user *vaddr, + unsigned long dst_paddr, + void __user *dst_vaddr, + int size, int *error) +{ + struct page *src_tpage = NULL; + struct page *dst_tpage = NULL; + int ret, len = size; + + /* If source buffer is not aligned then use an intermediate buffer */ + if (!IS_ALIGNED((unsigned long)vaddr, 16)) { + src_tpage = alloc_page(GFP_KERNEL_ACCOUNT); + if (!src_tpage) + return -ENOMEM; + + if (copy_from_user(page_address(src_tpage), vaddr, size)) { + __free_page(src_tpage); + return -EFAULT; + } + + paddr = __sme_page_pa(src_tpage); + } + + /* + * If destination buffer or length is not aligned then do read-modify-write: + * - decrypt destination in an intermediate buffer + * - copy the source buffer in an intermediate buffer + * - use the intermediate buffer as source buffer + */ + if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + int dst_offset; + + dst_tpage = alloc_page(GFP_KERNEL_ACCOUNT); + if (!dst_tpage) { + ret = -ENOMEM; + goto e_free; + } + + ret = __sev_dbg_decrypt(kvm, dst_paddr, + __sme_page_pa(dst_tpage), size, error); + if (ret) + goto e_free; + + /* + * If source is kernel buffer then use memcpy() otherwise + * copy_from_user(). + */ + dst_offset = dst_paddr & 15; + + if (src_tpage) + memcpy(page_address(dst_tpage) + dst_offset, + page_address(src_tpage), size); + else { + if (copy_from_user(page_address(dst_tpage) + dst_offset, + vaddr, size)) { + ret = -EFAULT; + goto e_free; + } + } + + paddr = __sme_page_pa(dst_tpage); + dst_paddr = round_down(dst_paddr, 16); + len = round_up(size, 16); + } + + ret = __sev_issue_dbg_cmd(kvm, paddr, dst_paddr, len, error, true); + +e_free: + if (src_tpage) + __free_page(src_tpage); + if (dst_tpage) + __free_page(dst_tpage); + return ret; +} + +static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) +{ + unsigned long vaddr, vaddr_end, next_vaddr; + unsigned long dst_vaddr; + struct page **src_p, **dst_p; + struct kvm_sev_dbg debug; + unsigned long n; + unsigned int size; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug))) + return -EFAULT; + + if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr) + return -EINVAL; + if (!debug.dst_uaddr) + return -EINVAL; + + vaddr = debug.src_uaddr; + size = debug.len; + vaddr_end = vaddr + size; + dst_vaddr = debug.dst_uaddr; + + for (; vaddr < vaddr_end; vaddr = next_vaddr) { + int len, s_off, d_off; + + /* lock userspace source and destination page */ + src_p = sev_pin_memory(kvm, vaddr & PAGE_MASK, PAGE_SIZE, &n, 0); + if (IS_ERR(src_p)) + return PTR_ERR(src_p); + + dst_p = sev_pin_memory(kvm, dst_vaddr & PAGE_MASK, PAGE_SIZE, &n, 1); + if (IS_ERR(dst_p)) { + sev_unpin_memory(kvm, src_p, n); + return PTR_ERR(dst_p); + } + + /* + * Flush (on non-coherent CPUs) before DBG_{DE,EN}CRYPT read or modify + * the pages; flush the destination too so that future accesses do not + * see stale data. + */ + sev_clflush_pages(src_p, 1); + sev_clflush_pages(dst_p, 1); + + /* + * Since user buffer may not be page aligned, calculate the + * offset within the page. + */ + s_off = vaddr & ~PAGE_MASK; + d_off = dst_vaddr & ~PAGE_MASK; + len = min_t(size_t, (PAGE_SIZE - s_off), size); + + if (dec) + ret = __sev_dbg_decrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + (void __user *)dst_vaddr, + __sme_page_pa(dst_p[0]) + d_off, + len, &argp->error); + else + ret = __sev_dbg_encrypt_user(kvm, + __sme_page_pa(src_p[0]) + s_off, + (void __user *)vaddr, + __sme_page_pa(dst_p[0]) + d_off, + (void __user *)dst_vaddr, + len, &argp->error); + + sev_unpin_memory(kvm, src_p, n); + sev_unpin_memory(kvm, dst_p, n); + + if (ret) + goto err; + + next_vaddr = vaddr + len; + dst_vaddr = dst_vaddr + len; + size -= len; + } +err: + return ret; +} + +static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_launch_secret data; + struct kvm_sev_launch_secret params; + struct page **pages; + void *blob, *hdr; + unsigned long n, i; + int ret, offset; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + pages = sev_pin_memory(kvm, params.guest_uaddr, params.guest_len, &n, 1); + if (IS_ERR(pages)) + return PTR_ERR(pages); + + /* + * Flush (on non-coherent CPUs) before LAUNCH_SECRET encrypts pages in + * place; the cache may contain the data that was written unencrypted. + */ + sev_clflush_pages(pages, n); + + /* + * The secret must be copied into contiguous memory region, lets verify + * that userspace memory pages are contiguous before we issue command. + */ + if (get_num_contig_pages(0, pages, n) != n) { + ret = -EINVAL; + goto e_unpin_memory; + } + + memset(&data, 0, sizeof(data)); + + offset = params.guest_uaddr & (PAGE_SIZE - 1); + data.guest_address = __sme_page_pa(pages[0]) + offset; + data.guest_len = params.guest_len; + + blob = psp_copy_user_blob(params.trans_uaddr, params.trans_len); + if (IS_ERR(blob)) { + ret = PTR_ERR(blob); + goto e_unpin_memory; + } + + data.trans_address = __psp_pa(blob); + data.trans_len = params.trans_len; + + hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); + if (IS_ERR(hdr)) { + ret = PTR_ERR(hdr); + goto e_free_blob; + } + data.hdr_address = __psp_pa(hdr); + data.hdr_len = params.hdr_len; + + data.handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_SECRET, &data, &argp->error); + + kfree(hdr); + +e_free_blob: + kfree(blob); +e_unpin_memory: + /* content of memory is updated, mark pages dirty */ + for (i = 0; i < n; i++) { + set_page_dirty_lock(pages[i]); + mark_page_accessed(pages[i]); + } + sev_unpin_memory(kvm, pages, n); + return ret; +} + +static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + void __user *report = (void __user *)(uintptr_t)argp->data; + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_attestation_report data; + struct kvm_sev_attestation_report params; + void __user *p; + void *blob = NULL; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) + return -EFAULT; + + memset(&data, 0, sizeof(data)); + + /* User wants to query the blob length */ + if (!params.len) + goto cmd; + + p = (void __user *)(uintptr_t)params.uaddr; + if (p) { + if (params.len > SEV_FW_BLOB_MAX_SIZE) + return -EINVAL; + + blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT); + if (!blob) + return -ENOMEM; + + data.address = __psp_pa(blob); + data.len = params.len; + memcpy(data.mnonce, params.mnonce, sizeof(params.mnonce)); + } +cmd: + data.handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_ATTESTATION_REPORT, &data, &argp->error); + /* + * If we query the session length, FW responded with expected data. + */ + if (!params.len) + goto done; + + if (ret) + goto e_free_blob; + + if (blob) { + if (copy_to_user(p, blob, params.len)) + ret = -EFAULT; + } + +done: + params.len = data.len; + if (copy_to_user(report, ¶ms, sizeof(params))) + ret = -EFAULT; +e_free_blob: + kfree(blob); + return ret; +} + +/* Userspace wants to query session length. */ +static int +__sev_send_start_query_session_length(struct kvm *kvm, struct kvm_sev_cmd *argp, + struct kvm_sev_send_start *params) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_send_start data; + int ret; + + memset(&data, 0, sizeof(data)); + data.handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); + + params->session_len = data.session_len; + if (copy_to_user((void __user *)(uintptr_t)argp->data, params, + sizeof(struct kvm_sev_send_start))) + ret = -EFAULT; + + return ret; +} + +static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_send_start data; + struct kvm_sev_send_start params; + void *amd_certs, *session_data; + void *pdh_cert, *plat_certs; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + sizeof(struct kvm_sev_send_start))) + return -EFAULT; + + /* if session_len is zero, userspace wants to query the session length */ + if (!params.session_len) + return __sev_send_start_query_session_length(kvm, argp, + ¶ms); + + /* some sanity checks */ + if (!params.pdh_cert_uaddr || !params.pdh_cert_len || + !params.session_uaddr || params.session_len > SEV_FW_BLOB_MAX_SIZE) + return -EINVAL; + + /* allocate the memory to hold the session data blob */ + session_data = kzalloc(params.session_len, GFP_KERNEL_ACCOUNT); + if (!session_data) + return -ENOMEM; + + /* copy the certificate blobs from userspace */ + pdh_cert = psp_copy_user_blob(params.pdh_cert_uaddr, + params.pdh_cert_len); + if (IS_ERR(pdh_cert)) { + ret = PTR_ERR(pdh_cert); + goto e_free_session; + } + + plat_certs = psp_copy_user_blob(params.plat_certs_uaddr, + params.plat_certs_len); + if (IS_ERR(plat_certs)) { + ret = PTR_ERR(plat_certs); + goto e_free_pdh; + } + + amd_certs = psp_copy_user_blob(params.amd_certs_uaddr, + params.amd_certs_len); + if (IS_ERR(amd_certs)) { + ret = PTR_ERR(amd_certs); + goto e_free_plat_cert; + } + + /* populate the FW SEND_START field with system physical address */ + memset(&data, 0, sizeof(data)); + data.pdh_cert_address = __psp_pa(pdh_cert); + data.pdh_cert_len = params.pdh_cert_len; + data.plat_certs_address = __psp_pa(plat_certs); + data.plat_certs_len = params.plat_certs_len; + data.amd_certs_address = __psp_pa(amd_certs); + data.amd_certs_len = params.amd_certs_len; + data.session_address = __psp_pa(session_data); + data.session_len = params.session_len; + data.handle = sev->handle; + + ret = sev_issue_cmd(kvm, SEV_CMD_SEND_START, &data, &argp->error); + + if (!ret && copy_to_user((void __user *)(uintptr_t)params.session_uaddr, + session_data, params.session_len)) { + ret = -EFAULT; + goto e_free_amd_cert; + } + + params.policy = data.policy; + params.session_len = data.session_len; + if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, + sizeof(struct kvm_sev_send_start))) + ret = -EFAULT; + +e_free_amd_cert: + kfree(amd_certs); +e_free_plat_cert: + kfree(plat_certs); +e_free_pdh: + kfree(pdh_cert); +e_free_session: + kfree(session_data); + return ret; +} + +/* Userspace wants to query either header or trans length. */ +static int +__sev_send_update_data_query_lengths(struct kvm *kvm, struct kvm_sev_cmd *argp, + struct kvm_sev_send_update_data *params) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_send_update_data data; + int ret; + + memset(&data, 0, sizeof(data)); + data.handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error); + + params->hdr_len = data.hdr_len; + params->trans_len = data.trans_len; + + if (copy_to_user((void __user *)(uintptr_t)argp->data, params, + sizeof(struct kvm_sev_send_update_data))) + ret = -EFAULT; + + return ret; +} + +static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_send_update_data data; + struct kvm_sev_send_update_data params; + void *hdr, *trans_data; + struct page **guest_page; + unsigned long n; + int ret, offset; + + if (!sev_guest(kvm)) + return -ENOTTY; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + sizeof(struct kvm_sev_send_update_data))) + return -EFAULT; + + /* userspace wants to query either header or trans length */ + if (!params.trans_len || !params.hdr_len) + return __sev_send_update_data_query_lengths(kvm, argp, ¶ms); + + if (!params.trans_uaddr || !params.guest_uaddr || + !params.guest_len || !params.hdr_uaddr) + return -EINVAL; + + /* Check if we are crossing the page boundary */ + offset = params.guest_uaddr & (PAGE_SIZE - 1); + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) + return -EINVAL; + + /* Pin guest memory */ + guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, + PAGE_SIZE, &n, 0); + if (IS_ERR(guest_page)) + return PTR_ERR(guest_page); + + /* allocate memory for header and transport buffer */ + ret = -ENOMEM; + hdr = kzalloc(params.hdr_len, GFP_KERNEL_ACCOUNT); + if (!hdr) + goto e_unpin; + + trans_data = kzalloc(params.trans_len, GFP_KERNEL_ACCOUNT); + if (!trans_data) + goto e_free_hdr; + + memset(&data, 0, sizeof(data)); + data.hdr_address = __psp_pa(hdr); + data.hdr_len = params.hdr_len; + data.trans_address = __psp_pa(trans_data); + data.trans_len = params.trans_len; + + /* The SEND_UPDATE_DATA command requires C-bit to be always set. */ + data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; + data.guest_address |= sev_me_mask; + data.guest_len = params.guest_len; + data.handle = sev->handle; + + ret = sev_issue_cmd(kvm, SEV_CMD_SEND_UPDATE_DATA, &data, &argp->error); + + if (ret) + goto e_free_trans_data; + + /* copy transport buffer to user space */ + if (copy_to_user((void __user *)(uintptr_t)params.trans_uaddr, + trans_data, params.trans_len)) { + ret = -EFAULT; + goto e_free_trans_data; + } + + /* Copy packet header to userspace. */ + if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr, + params.hdr_len)) + ret = -EFAULT; + +e_free_trans_data: + kfree(trans_data); +e_free_hdr: + kfree(hdr); +e_unpin: + sev_unpin_memory(kvm, guest_page, n); + + return ret; +} + +static int sev_send_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_send_finish data; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data.handle = sev->handle; + return sev_issue_cmd(kvm, SEV_CMD_SEND_FINISH, &data, &argp->error); +} + +static int sev_send_cancel(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_send_cancel data; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data.handle = sev->handle; + return sev_issue_cmd(kvm, SEV_CMD_SEND_CANCEL, &data, &argp->error); +} + +static int sev_receive_start(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_receive_start start; + struct kvm_sev_receive_start params; + int *error = &argp->error; + void *session_data; + void *pdh_data; + int ret; + + if (!sev_guest(kvm)) + return -ENOTTY; + + /* Get parameter from the userspace */ + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + sizeof(struct kvm_sev_receive_start))) + return -EFAULT; + + /* some sanity checks */ + if (!params.pdh_uaddr || !params.pdh_len || + !params.session_uaddr || !params.session_len) + return -EINVAL; + + pdh_data = psp_copy_user_blob(params.pdh_uaddr, params.pdh_len); + if (IS_ERR(pdh_data)) + return PTR_ERR(pdh_data); + + session_data = psp_copy_user_blob(params.session_uaddr, + params.session_len); + if (IS_ERR(session_data)) { + ret = PTR_ERR(session_data); + goto e_free_pdh; + } + + memset(&start, 0, sizeof(start)); + start.handle = params.handle; + start.policy = params.policy; + start.pdh_cert_address = __psp_pa(pdh_data); + start.pdh_cert_len = params.pdh_len; + start.session_address = __psp_pa(session_data); + start.session_len = params.session_len; + + /* create memory encryption context */ + ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_RECEIVE_START, &start, + error); + if (ret) + goto e_free_session; + + /* Bind ASID to this guest */ + ret = sev_bind_asid(kvm, start.handle, error); + if (ret) { + sev_decommission(start.handle); + goto e_free_session; + } + + params.handle = start.handle; + if (copy_to_user((void __user *)(uintptr_t)argp->data, + ¶ms, sizeof(struct kvm_sev_receive_start))) { + ret = -EFAULT; + sev_unbind_asid(kvm, start.handle); + goto e_free_session; + } + + sev->handle = start.handle; + sev->fd = argp->sev_fd; + +e_free_session: + kfree(session_data); +e_free_pdh: + kfree(pdh_data); + + return ret; +} + +static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_receive_update_data params; + struct sev_data_receive_update_data data; + void *hdr = NULL, *trans = NULL; + struct page **guest_page; + unsigned long n; + int ret, offset; + + if (!sev_guest(kvm)) + return -EINVAL; + + if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, + sizeof(struct kvm_sev_receive_update_data))) + return -EFAULT; + + if (!params.hdr_uaddr || !params.hdr_len || + !params.guest_uaddr || !params.guest_len || + !params.trans_uaddr || !params.trans_len) + return -EINVAL; + + /* Check if we are crossing the page boundary */ + offset = params.guest_uaddr & (PAGE_SIZE - 1); + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) + return -EINVAL; + + hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); + if (IS_ERR(hdr)) + return PTR_ERR(hdr); + + trans = psp_copy_user_blob(params.trans_uaddr, params.trans_len); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto e_free_hdr; + } + + memset(&data, 0, sizeof(data)); + data.hdr_address = __psp_pa(hdr); + data.hdr_len = params.hdr_len; + data.trans_address = __psp_pa(trans); + data.trans_len = params.trans_len; + + /* Pin guest memory */ + guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK, + PAGE_SIZE, &n, 1); + if (IS_ERR(guest_page)) { + ret = PTR_ERR(guest_page); + goto e_free_trans; + } + + /* + * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP + * encrypts the written data with the guest's key, and the cache may + * contain dirty, unencrypted data. + */ + sev_clflush_pages(guest_page, n); + + /* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */ + data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset; + data.guest_address |= sev_me_mask; + data.guest_len = params.guest_len; + data.handle = sev->handle; + + ret = sev_issue_cmd(kvm, SEV_CMD_RECEIVE_UPDATE_DATA, &data, + &argp->error); + + sev_unpin_memory(kvm, guest_page, n); + +e_free_trans: + kfree(trans); +e_free_hdr: + kfree(hdr); + + return ret; +} + +static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_data_receive_finish data; + + if (!sev_guest(kvm)) + return -ENOTTY; + + data.handle = sev->handle; + return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); +} + +static bool is_cmd_allowed_from_mirror(u32 cmd_id) +{ + /* + * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES + * active mirror VMs. Also allow the debugging and status commands. + */ + if (cmd_id == KVM_SEV_LAUNCH_UPDATE_VMSA || + cmd_id == KVM_SEV_GUEST_STATUS || cmd_id == KVM_SEV_DBG_DECRYPT || + cmd_id == KVM_SEV_DBG_ENCRYPT) + return true; + + return false; +} + +static int sev_lock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + int r = -EBUSY; + + if (dst_kvm == src_kvm) + return -EINVAL; + + /* + * Bail if these VMs are already involved in a migration to avoid + * deadlock between two VMs trying to migrate to/from each other. + */ + if (atomic_cmpxchg_acquire(&dst_sev->migration_in_progress, 0, 1)) + return -EBUSY; + + if (atomic_cmpxchg_acquire(&src_sev->migration_in_progress, 0, 1)) + goto release_dst; + + r = -EINTR; + if (mutex_lock_killable(&dst_kvm->lock)) + goto release_src; + if (mutex_lock_killable_nested(&src_kvm->lock, SINGLE_DEPTH_NESTING)) + goto unlock_dst; + return 0; + +unlock_dst: + mutex_unlock(&dst_kvm->lock); +release_src: + atomic_set_release(&src_sev->migration_in_progress, 0); +release_dst: + atomic_set_release(&dst_sev->migration_in_progress, 0); + return r; +} + +static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src_sev = &to_kvm_svm(src_kvm)->sev_info; + + mutex_unlock(&dst_kvm->lock); + mutex_unlock(&src_kvm->lock); + atomic_set_release(&dst_sev->migration_in_progress, 0); + atomic_set_release(&src_sev->migration_in_progress, 0); +} + +/* vCPU mutex subclasses. */ +enum sev_migration_role { + SEV_MIGRATION_SOURCE = 0, + SEV_MIGRATION_TARGET, + SEV_NR_MIGRATION_ROLES, +}; + +static int sev_lock_vcpus_for_migration(struct kvm *kvm, + enum sev_migration_role role) +{ + struct kvm_vcpu *vcpu; + unsigned long i, j; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mutex_lock_killable_nested(&vcpu->mutex, role)) + goto out_unlock; + +#ifdef CONFIG_PROVE_LOCKING + if (!i) + /* + * Reset the role to one that avoids colliding with + * the role used for the first vcpu mutex. + */ + role = SEV_NR_MIGRATION_ROLES; + else + mutex_release(&vcpu->mutex.dep_map, _THIS_IP_); +#endif + } + + return 0; + +out_unlock: + + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + +#ifdef CONFIG_PROVE_LOCKING + if (j) + mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_); +#endif + + mutex_unlock(&vcpu->mutex); + } + return -EINTR; +} + +static void sev_unlock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + unsigned long i; + bool first = true; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, + SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_); + + mutex_unlock(&vcpu->mutex); + } +} + +static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) +{ + struct kvm_sev_info *dst = &to_kvm_svm(dst_kvm)->sev_info; + struct kvm_sev_info *src = &to_kvm_svm(src_kvm)->sev_info; + struct kvm_vcpu *dst_vcpu, *src_vcpu; + struct vcpu_svm *dst_svm, *src_svm; + struct kvm_sev_info *mirror; + unsigned long i; + + dst->active = true; + dst->asid = src->asid; + dst->handle = src->handle; + dst->pages_locked = src->pages_locked; + dst->enc_context_owner = src->enc_context_owner; + dst->es_active = src->es_active; + + src->asid = 0; + src->active = false; + src->handle = 0; + src->pages_locked = 0; + src->enc_context_owner = NULL; + src->es_active = false; + + list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); + + /* + * If this VM has mirrors, "transfer" each mirror's refcount of the + * source to the destination (this KVM). The caller holds a reference + * to the source, so there's no danger of use-after-free. + */ + list_cut_before(&dst->mirror_vms, &src->mirror_vms, &src->mirror_vms); + list_for_each_entry(mirror, &dst->mirror_vms, mirror_entry) { + kvm_get_kvm(dst_kvm); + kvm_put_kvm(src_kvm); + mirror->enc_context_owner = dst_kvm; + } + + /* + * If this VM is a mirror, remove the old mirror from the owners list + * and add the new mirror to the list. + */ + if (is_mirroring_enc_context(dst_kvm)) { + struct kvm_sev_info *owner_sev_info = + &to_kvm_svm(dst->enc_context_owner)->sev_info; + + list_del(&src->mirror_entry); + list_add_tail(&dst->mirror_entry, &owner_sev_info->mirror_vms); + } + + kvm_for_each_vcpu(i, dst_vcpu, dst_kvm) { + dst_svm = to_svm(dst_vcpu); + + sev_init_vmcb(dst_svm); + + if (!dst->es_active) + continue; + + /* + * Note, the source is not required to have the same number of + * vCPUs as the destination when migrating a vanilla SEV VM. + */ + src_vcpu = kvm_get_vcpu(src_kvm, i); + src_svm = to_svm(src_vcpu); + + /* + * Transfer VMSA and GHCB state to the destination. Nullify and + * clear source fields as appropriate, the state now belongs to + * the destination. + */ + memcpy(&dst_svm->sev_es, &src_svm->sev_es, sizeof(src_svm->sev_es)); + dst_svm->vmcb->control.ghcb_gpa = src_svm->vmcb->control.ghcb_gpa; + dst_svm->vmcb->control.vmsa_pa = src_svm->vmcb->control.vmsa_pa; + dst_vcpu->arch.guest_state_protected = true; + + memset(&src_svm->sev_es, 0, sizeof(src_svm->sev_es)); + src_svm->vmcb->control.ghcb_gpa = INVALID_PAGE; + src_svm->vmcb->control.vmsa_pa = INVALID_PAGE; + src_vcpu->arch.guest_state_protected = false; + } +} + +static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src) +{ + struct kvm_vcpu *src_vcpu; + unsigned long i; + + if (!sev_es_guest(src)) + return 0; + + if (atomic_read(&src->online_vcpus) != atomic_read(&dst->online_vcpus)) + return -EINVAL; + + kvm_for_each_vcpu(i, src_vcpu, src) { + if (!src_vcpu->arch.guest_state_protected) + return -EINVAL; + } + + return 0; +} + +int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *src_sev, *cg_cleanup_sev; + struct fd f = fdget(source_fd); + struct kvm *source_kvm; + bool charged = false; + int ret; + + if (!f.file) + return -EBADF; + + if (!file_is_kvm(f.file)) { + ret = -EBADF; + goto out_fput; + } + + source_kvm = f.file->private_data; + ret = sev_lock_two_vms(kvm, source_kvm); + if (ret) + goto out_fput; + + if (sev_guest(kvm) || !sev_guest(source_kvm)) { + ret = -EINVAL; + goto out_unlock; + } + + src_sev = &to_kvm_svm(source_kvm)->sev_info; + + dst_sev->misc_cg = get_current_misc_cg(); + cg_cleanup_sev = dst_sev; + if (dst_sev->misc_cg != src_sev->misc_cg) { + ret = sev_misc_cg_try_charge(dst_sev); + if (ret) + goto out_dst_cgroup; + charged = true; + } + + ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE); + if (ret) + goto out_dst_cgroup; + ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET); + if (ret) + goto out_dst_vcpu; + + ret = sev_check_source_vcpus(kvm, source_kvm); + if (ret) + goto out_source_vcpu; + + sev_migrate_from(kvm, source_kvm); + kvm_vm_dead(source_kvm); + cg_cleanup_sev = src_sev; + ret = 0; + +out_source_vcpu: + sev_unlock_vcpus_for_migration(source_kvm); +out_dst_vcpu: + sev_unlock_vcpus_for_migration(kvm); +out_dst_cgroup: + /* Operates on the source on success, on the destination on failure. */ + if (charged) + sev_misc_cg_uncharge(cg_cleanup_sev); + put_misc_cg(cg_cleanup_sev->misc_cg); + cg_cleanup_sev->misc_cg = NULL; +out_unlock: + sev_unlock_two_vms(kvm, source_kvm); +out_fput: + fdput(f); + return ret; +} + +int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) +{ + struct kvm_sev_cmd sev_cmd; + int r; + + if (!sev_enabled) + return -ENOTTY; + + if (!argp) + return 0; + + if (copy_from_user(&sev_cmd, argp, sizeof(struct kvm_sev_cmd))) + return -EFAULT; + + mutex_lock(&kvm->lock); + + /* Only the enc_context_owner handles some memory enc operations. */ + if (is_mirroring_enc_context(kvm) && + !is_cmd_allowed_from_mirror(sev_cmd.id)) { + r = -EINVAL; + goto out; + } + + switch (sev_cmd.id) { + case KVM_SEV_ES_INIT: + if (!sev_es_enabled) { + r = -ENOTTY; + goto out; + } + fallthrough; + case KVM_SEV_INIT: + r = sev_guest_init(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_START: + r = sev_launch_start(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_UPDATE_DATA: + r = sev_launch_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_UPDATE_VMSA: + r = sev_launch_update_vmsa(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_MEASURE: + r = sev_launch_measure(kvm, &sev_cmd); + break; + case KVM_SEV_LAUNCH_FINISH: + r = sev_launch_finish(kvm, &sev_cmd); + break; + case KVM_SEV_GUEST_STATUS: + r = sev_guest_status(kvm, &sev_cmd); + break; + case KVM_SEV_DBG_DECRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, true); + break; + case KVM_SEV_DBG_ENCRYPT: + r = sev_dbg_crypt(kvm, &sev_cmd, false); + break; + case KVM_SEV_LAUNCH_SECRET: + r = sev_launch_secret(kvm, &sev_cmd); + break; + case KVM_SEV_GET_ATTESTATION_REPORT: + r = sev_get_attestation_report(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_START: + r = sev_send_start(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_UPDATE_DATA: + r = sev_send_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_FINISH: + r = sev_send_finish(kvm, &sev_cmd); + break; + case KVM_SEV_SEND_CANCEL: + r = sev_send_cancel(kvm, &sev_cmd); + break; + case KVM_SEV_RECEIVE_START: + r = sev_receive_start(kvm, &sev_cmd); + break; + case KVM_SEV_RECEIVE_UPDATE_DATA: + r = sev_receive_update_data(kvm, &sev_cmd); + break; + case KVM_SEV_RECEIVE_FINISH: + r = sev_receive_finish(kvm, &sev_cmd); + break; + default: + r = -EINVAL; + goto out; + } + + if (copy_to_user(argp, &sev_cmd, sizeof(struct kvm_sev_cmd))) + r = -EFAULT; + +out: + mutex_unlock(&kvm->lock); + return r; +} + +int sev_mem_enc_register_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct enc_region *region; + int ret = 0; + + if (!sev_guest(kvm)) + return -ENOTTY; + + /* If kvm is mirroring encryption context it isn't responsible for it */ + if (is_mirroring_enc_context(kvm)) + return -EINVAL; + + if (range->addr > ULONG_MAX || range->size > ULONG_MAX) + return -EINVAL; + + region = kzalloc(sizeof(*region), GFP_KERNEL_ACCOUNT); + if (!region) + return -ENOMEM; + + mutex_lock(&kvm->lock); + region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); + if (IS_ERR(region->pages)) { + ret = PTR_ERR(region->pages); + mutex_unlock(&kvm->lock); + goto e_free; + } + + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + + /* + * The guest may change the memory encryption attribute from C=0 -> C=1 + * or vice versa for this memory range. Lets make sure caches are + * flushed to ensure that guest data gets written into memory with + * correct C-bit. + */ + sev_clflush_pages(region->pages, region->npages); + + return ret; + +e_free: + kfree(region); + return ret; +} + +static struct enc_region * +find_enc_region(struct kvm *kvm, struct kvm_enc_region *range) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct list_head *head = &sev->regions_list; + struct enc_region *i; + + list_for_each_entry(i, head, list) { + if (i->uaddr == range->addr && + i->size == range->size) + return i; + } + + return NULL; +} + +static void __unregister_enc_region_locked(struct kvm *kvm, + struct enc_region *region) +{ + sev_unpin_memory(kvm, region->pages, region->npages); + list_del(®ion->list); + kfree(region); +} + +int sev_mem_enc_unregister_region(struct kvm *kvm, + struct kvm_enc_region *range) +{ + struct enc_region *region; + int ret; + + /* If kvm is mirroring encryption context it isn't responsible for it */ + if (is_mirroring_enc_context(kvm)) + return -EINVAL; + + mutex_lock(&kvm->lock); + + if (!sev_guest(kvm)) { + ret = -ENOTTY; + goto failed; + } + + region = find_enc_region(kvm, range); + if (!region) { + ret = -EINVAL; + goto failed; + } + + /* + * Ensure that all guest tagged cache entries are flushed before + * releasing the pages back to the system for use. CLFLUSH will + * not do this, so issue a WBINVD. + */ + wbinvd_on_all_cpus(); + + __unregister_enc_region_locked(kvm, region); + + mutex_unlock(&kvm->lock); + return 0; + +failed: + mutex_unlock(&kvm->lock); + return ret; +} + +int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) +{ + struct fd f = fdget(source_fd); + struct kvm *source_kvm; + struct kvm_sev_info *source_sev, *mirror_sev; + int ret; + + if (!f.file) + return -EBADF; + + if (!file_is_kvm(f.file)) { + ret = -EBADF; + goto e_source_fput; + } + + source_kvm = f.file->private_data; + ret = sev_lock_two_vms(kvm, source_kvm); + if (ret) + goto e_source_fput; + + /* + * Mirrors of mirrors should work, but let's not get silly. Also + * disallow out-of-band SEV/SEV-ES init if the target is already an + * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being + * created after SEV/SEV-ES initialization, e.g. to init intercepts. + */ + if (sev_guest(kvm) || !sev_guest(source_kvm) || + is_mirroring_enc_context(source_kvm) || kvm->created_vcpus) { + ret = -EINVAL; + goto e_unlock; + } + + /* + * The mirror kvm holds an enc_context_owner ref so its asid can't + * disappear until we're done with it + */ + source_sev = &to_kvm_svm(source_kvm)->sev_info; + kvm_get_kvm(source_kvm); + mirror_sev = &to_kvm_svm(kvm)->sev_info; + list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms); + + /* Set enc_context_owner and copy its encryption context over */ + mirror_sev->enc_context_owner = source_kvm; + mirror_sev->active = true; + mirror_sev->asid = source_sev->asid; + mirror_sev->fd = source_sev->fd; + mirror_sev->es_active = source_sev->es_active; + mirror_sev->handle = source_sev->handle; + INIT_LIST_HEAD(&mirror_sev->regions_list); + INIT_LIST_HEAD(&mirror_sev->mirror_vms); + ret = 0; + + /* + * Do not copy ap_jump_table. Since the mirror does not share the same + * KVM contexts as the original, and they may have different + * memory-views. + */ + +e_unlock: + sev_unlock_two_vms(kvm, source_kvm); +e_source_fput: + fdput(f); + return ret; +} + +void sev_vm_destroy(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct list_head *head = &sev->regions_list; + struct list_head *pos, *q; + + if (!sev_guest(kvm)) + return; + + WARN_ON(!list_empty(&sev->mirror_vms)); + + /* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */ + if (is_mirroring_enc_context(kvm)) { + struct kvm *owner_kvm = sev->enc_context_owner; + + mutex_lock(&owner_kvm->lock); + list_del(&sev->mirror_entry); + mutex_unlock(&owner_kvm->lock); + kvm_put_kvm(owner_kvm); + return; + } + + /* + * Ensure that all guest tagged cache entries are flushed before + * releasing the pages back to the system for use. CLFLUSH will + * not do this, so issue a WBINVD. + */ + wbinvd_on_all_cpus(); + + /* + * if userspace was terminated before unregistering the memory regions + * then lets unpin all the registered memory. + */ + if (!list_empty(head)) { + list_for_each_safe(pos, q, head) { + __unregister_enc_region_locked(kvm, + list_entry(pos, struct enc_region, list)); + cond_resched(); + } + } + + sev_unbind_asid(kvm, sev->handle); + sev_asid_free(sev); +} + +void __init sev_set_cpu_caps(void) +{ + if (!sev_enabled) + kvm_cpu_cap_clear(X86_FEATURE_SEV); + if (!sev_es_enabled) + kvm_cpu_cap_clear(X86_FEATURE_SEV_ES); +} + +void __init sev_hardware_setup(void) +{ +#ifdef CONFIG_KVM_AMD_SEV + unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count; + bool sev_es_supported = false; + bool sev_supported = false; + + if (!sev_enabled || !npt_enabled || !nrips) + goto out; + + /* + * SEV must obviously be supported in hardware. Sanity check that the + * CPU supports decode assists, which is mandatory for SEV guests to + * support instruction emulation. + */ + if (!boot_cpu_has(X86_FEATURE_SEV) || + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS))) + goto out; + + /* Retrieve SEV CPUID information */ + cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); + + /* Set encryption bit location for SEV-ES guests */ + sev_enc_bit = ebx & 0x3f; + + /* Maximum number of encrypted guests supported simultaneously */ + max_sev_asid = ecx; + if (!max_sev_asid) + goto out; + + /* Minimum ASID value that should be used for SEV guest */ + min_sev_asid = edx; + sev_me_mask = 1UL << (ebx & 0x3f); + + /* + * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap, + * even though it's never used, so that the bitmap is indexed by the + * actual ASID. + */ + nr_asids = max_sev_asid + 1; + sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL); + if (!sev_asid_bitmap) + goto out; + + sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL); + if (!sev_reclaim_asid_bitmap) { + bitmap_free(sev_asid_bitmap); + sev_asid_bitmap = NULL; + goto out; + } + + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + sev_supported = true; + + /* SEV-ES support requested? */ + if (!sev_es_enabled) + goto out; + + /* + * SEV-ES requires MMIO caching as KVM doesn't have access to the guest + * instruction stream, i.e. can't emulate in response to a #NPF and + * instead relies on #NPF(RSVD) being reflected into the guest as #VC + * (the guest can then do a #VMGEXIT to request MMIO emulation). + */ + if (!enable_mmio_caching) + goto out; + + /* Does the CPU support SEV-ES? */ + if (!boot_cpu_has(X86_FEATURE_SEV_ES)) + goto out; + + /* Has the system been allocated ASIDs for SEV-ES? */ + if (min_sev_asid == 1) + goto out; + + sev_es_asid_count = min_sev_asid - 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)); + sev_es_supported = true; + +out: + if (boot_cpu_has(X86_FEATURE_SEV)) + pr_info("SEV %s (ASIDs %u - %u)\n", + sev_supported ? "enabled" : "disabled", + min_sev_asid, max_sev_asid); + if (boot_cpu_has(X86_FEATURE_SEV_ES)) + pr_info("SEV-ES %s (ASIDs %u - %u)\n", + sev_es_supported ? "enabled" : "disabled", + min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); + + sev_enabled = sev_supported; + sev_es_enabled = sev_es_supported; + if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) || + !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP)) + sev_es_debug_swap_enabled = false; +#endif +} + +void sev_hardware_unsetup(void) +{ + if (!sev_enabled) + return; + + /* No need to take sev_bitmap_lock, all VMs have been destroyed. */ + sev_flush_asids(1, max_sev_asid); + + bitmap_free(sev_asid_bitmap); + bitmap_free(sev_reclaim_asid_bitmap); + + misc_cg_set_capacity(MISC_CG_RES_SEV, 0); + misc_cg_set_capacity(MISC_CG_RES_SEV_ES, 0); +} + +int sev_cpu_init(struct svm_cpu_data *sd) +{ + if (!sev_enabled) + return 0; + + sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL); + if (!sd->sev_vmcbs) + return -ENOMEM; + + return 0; +} + +/* + * Pages used by hardware to hold guest encrypted state must be flushed before + * returning them to the system. + */ +static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) +{ + int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + + /* + * Note! The address must be a kernel address, as regular page walk + * checks are performed by VM_PAGE_FLUSH, i.e. operating on a user + * address is non-deterministic and unsafe. This function deliberately + * takes a pointer to deter passing in a user address. + */ + unsigned long addr = (unsigned long)va; + + /* + * If CPU enforced cache coherency for encrypted mappings of the + * same physical page is supported, use CLFLUSHOPT instead. NOTE: cache + * flush is still needed in order to work properly with DMA devices. + */ + if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) { + clflush_cache_range(va, PAGE_SIZE); + return; + } + + /* + * VM Page Flush takes a host virtual address and a guest ASID. Fall + * back to WBINVD if this faults so as not to make any problems worse + * by leaving stale encrypted data in the cache. + */ + if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid))) + goto do_wbinvd; + + return; + +do_wbinvd: + wbinvd_on_all_cpus(); +} + +void sev_guest_memory_reclaimed(struct kvm *kvm) +{ + if (!sev_guest(kvm)) + return; + + wbinvd_on_all_cpus(); +} + +void sev_free_vcpu(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm; + + if (!sev_es_guest(vcpu->kvm)) + return; + + svm = to_svm(vcpu); + + if (vcpu->arch.guest_state_protected) + sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa); + + __free_page(virt_to_page(svm->sev_es.vmsa)); + + if (svm->sev_es.ghcb_sa_free) + kvfree(svm->sev_es.ghcb_sa); +} + +static void dump_ghcb(struct vcpu_svm *svm) +{ + struct ghcb *ghcb = svm->sev_es.ghcb; + unsigned int nbits; + + /* Re-use the dump_invalid_vmcb module parameter */ + if (!dump_invalid_vmcb) { + pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n"); + return; + } + + nbits = sizeof(ghcb->save.valid_bitmap) * 8; + + pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa); + pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code", + ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb)); + pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1", + ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb)); + pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2", + ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb)); + pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch", + ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb)); + pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap); +} + +static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct ghcb *ghcb = svm->sev_es.ghcb; + + /* + * The GHCB protocol so far allows for the following data + * to be returned: + * GPRs RAX, RBX, RCX, RDX + * + * Copy their values, even if they may not have been written during the + * VM-Exit. It's the guest's responsibility to not consume random data. + */ + ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); + ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); + ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); + ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); +} + +static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; + struct ghcb *ghcb = svm->sev_es.ghcb; + u64 exit_code; + + /* + * The GHCB protocol so far allows for the following data + * to be supplied: + * GPRs RAX, RBX, RCX, RDX + * XCR0 + * CPL + * + * VMMCALL allows the guest to provide extra registers. KVM also + * expects RSI for hypercalls, so include that, too. + * + * Copy their values to the appropriate location if supplied. + */ + memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); + + BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap)); + memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap)); + + vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm, ghcb); + vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm, ghcb); + + svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm, ghcb); + + if (kvm_ghcb_xcr0_is_valid(svm)) { + vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb); + kvm_update_cpuid_runtime(vcpu); + } + + /* Copy the GHCB exit information into the VMCB fields */ + exit_code = ghcb_get_sw_exit_code(ghcb); + control->exit_code = lower_32_bits(exit_code); + control->exit_code_hi = upper_32_bits(exit_code); + control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb); + control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb); + svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm, ghcb); + + /* Clear the valid entries fields */ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); +} + +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + +static int sev_es_validate_vmgexit(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; + u64 exit_code; + u64 reason; + + /* + * Retrieve the exit code now even though it may not be marked valid + * as it could help with debugging. + */ + exit_code = kvm_ghcb_get_sw_exit_code(control); + + /* Only GHCB Usage code 0 is supported */ + if (svm->sev_es.ghcb->ghcb_usage) { + reason = GHCB_ERR_INVALID_USAGE; + goto vmgexit_err; + } + + reason = GHCB_ERR_MISSING_INPUT; + + if (!kvm_ghcb_sw_exit_code_is_valid(svm) || + !kvm_ghcb_sw_exit_info_1_is_valid(svm) || + !kvm_ghcb_sw_exit_info_2_is_valid(svm)) + goto vmgexit_err; + + switch (exit_code) { + case SVM_EXIT_READ_DR7: + break; + case SVM_EXIT_WRITE_DR7: + if (!kvm_ghcb_rax_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_EXIT_RDTSC: + break; + case SVM_EXIT_RDPMC: + if (!kvm_ghcb_rcx_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_EXIT_CPUID: + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) + goto vmgexit_err; + if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd) + if (!kvm_ghcb_xcr0_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_EXIT_INVD: + break; + case SVM_EXIT_IOIO: + if (control->exit_info_1 & SVM_IOIO_STR_MASK) { + if (!kvm_ghcb_sw_scratch_is_valid(svm)) + goto vmgexit_err; + } else { + if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK)) + if (!kvm_ghcb_rax_is_valid(svm)) + goto vmgexit_err; + } + break; + case SVM_EXIT_MSR: + if (!kvm_ghcb_rcx_is_valid(svm)) + goto vmgexit_err; + if (control->exit_info_1) { + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) + goto vmgexit_err; + } + break; + case SVM_EXIT_VMMCALL: + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_cpl_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_EXIT_RDTSCP: + break; + case SVM_EXIT_WBINVD: + break; + case SVM_EXIT_MONITOR: + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm) || + !kvm_ghcb_rdx_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_EXIT_MWAIT: + if (!kvm_ghcb_rax_is_valid(svm) || + !kvm_ghcb_rcx_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_VMGEXIT_MMIO_READ: + case SVM_VMGEXIT_MMIO_WRITE: + if (!kvm_ghcb_sw_scratch_is_valid(svm)) + goto vmgexit_err; + break; + case SVM_VMGEXIT_NMI_COMPLETE: + case SVM_VMGEXIT_AP_HLT_LOOP: + case SVM_VMGEXIT_AP_JUMP_TABLE: + case SVM_VMGEXIT_UNSUPPORTED_EVENT: + break; + default: + reason = GHCB_ERR_INVALID_EVENT; + goto vmgexit_err; + } + + return 0; + +vmgexit_err: + if (reason == GHCB_ERR_INVALID_USAGE) { + vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", + svm->sev_es.ghcb->ghcb_usage); + } else if (reason == GHCB_ERR_INVALID_EVENT) { + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n", + exit_code); + } else { + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n", + exit_code); + dump_ghcb(svm); + } + + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, reason); + + /* Resume the guest to "return" the error code. */ + return 1; +} + +void sev_es_unmap_ghcb(struct vcpu_svm *svm) +{ + if (!svm->sev_es.ghcb) + return; + + if (svm->sev_es.ghcb_sa_free) { + /* + * The scratch area lives outside the GHCB, so there is a + * buffer that, depending on the operation performed, may + * need to be synced, then freed. + */ + if (svm->sev_es.ghcb_sa_sync) { + kvm_write_guest(svm->vcpu.kvm, + svm->sev_es.sw_scratch, + svm->sev_es.ghcb_sa, + svm->sev_es.ghcb_sa_len); + svm->sev_es.ghcb_sa_sync = false; + } + + kvfree(svm->sev_es.ghcb_sa); + svm->sev_es.ghcb_sa = NULL; + svm->sev_es.ghcb_sa_free = false; + } + + trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb); + + sev_es_sync_to_ghcb(svm); + + kvm_vcpu_unmap(&svm->vcpu, &svm->sev_es.ghcb_map, true); + svm->sev_es.ghcb = NULL; +} + +void pre_sev_run(struct vcpu_svm *svm, int cpu) +{ + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); + int asid = sev_get_asid(svm->vcpu.kvm); + + /* Assign the asid allocated with this SEV guest */ + svm->asid = asid; + + /* + * Flush guest TLB: + * + * 1) when different VMCB for the same ASID is to be run on the same host CPU. + * 2) or this VMCB was executed on different host CPU in previous VMRUNs. + */ + if (sd->sev_vmcbs[asid] == svm->vmcb && + svm->vcpu.arch.last_vmentry_cpu == cpu) + return; + + sd->sev_vmcbs[asid] = svm->vmcb; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; + vmcb_mark_dirty(svm->vmcb, VMCB_ASID); +} + +#define GHCB_SCRATCH_AREA_LIMIT (16ULL * PAGE_SIZE) +static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + u64 ghcb_scratch_beg, ghcb_scratch_end; + u64 scratch_gpa_beg, scratch_gpa_end; + void *scratch_va; + + scratch_gpa_beg = svm->sev_es.sw_scratch; + if (!scratch_gpa_beg) { + pr_err("vmgexit: scratch gpa not provided\n"); + goto e_scratch; + } + + scratch_gpa_end = scratch_gpa_beg + len; + if (scratch_gpa_end < scratch_gpa_beg) { + pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n", + len, scratch_gpa_beg); + goto e_scratch; + } + + if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { + /* Scratch area begins within GHCB */ + ghcb_scratch_beg = control->ghcb_gpa + + offsetof(struct ghcb, shared_buffer); + ghcb_scratch_end = control->ghcb_gpa + + offsetof(struct ghcb, reserved_0xff0); + + /* + * If the scratch area begins within the GHCB, it must be + * completely contained in the GHCB shared buffer area. + */ + if (scratch_gpa_beg < ghcb_scratch_beg || + scratch_gpa_end > ghcb_scratch_end) { + pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n", + scratch_gpa_beg, scratch_gpa_end); + goto e_scratch; + } + + scratch_va = (void *)svm->sev_es.ghcb; + scratch_va += (scratch_gpa_beg - control->ghcb_gpa); + } else { + /* + * The guest memory must be read into a kernel buffer, so + * limit the size + */ + if (len > GHCB_SCRATCH_AREA_LIMIT) { + pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", + len, GHCB_SCRATCH_AREA_LIMIT); + goto e_scratch; + } + scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT); + if (!scratch_va) + return -ENOMEM; + + if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) { + /* Unable to copy scratch area from guest */ + pr_err("vmgexit: kvm_read_guest for scratch area failed\n"); + + kvfree(scratch_va); + return -EFAULT; + } + + /* + * The scratch area is outside the GHCB. The operation will + * dictate whether the buffer needs to be synced before running + * the vCPU next time (i.e. a read was requested so the data + * must be written back to the guest memory). + */ + svm->sev_es.ghcb_sa_sync = sync; + svm->sev_es.ghcb_sa_free = true; + } + + svm->sev_es.ghcb_sa = scratch_va; + svm->sev_es.ghcb_sa_len = len; + + return 0; + +e_scratch: + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + + return 1; +} + +static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, + unsigned int pos) +{ + svm->vmcb->control.ghcb_gpa &= ~(mask << pos); + svm->vmcb->control.ghcb_gpa |= (value & mask) << pos; +} + +static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos) +{ + return (svm->vmcb->control.ghcb_gpa >> pos) & mask; +} + +static void set_ghcb_msr(struct vcpu_svm *svm, u64 value) +{ + svm->vmcb->control.ghcb_gpa = value; +} + +static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control = &svm->vmcb->control; + struct kvm_vcpu *vcpu = &svm->vcpu; + u64 ghcb_info; + int ret = 1; + + ghcb_info = control->ghcb_gpa & GHCB_MSR_INFO_MASK; + + trace_kvm_vmgexit_msr_protocol_enter(svm->vcpu.vcpu_id, + control->ghcb_gpa); + + switch (ghcb_info) { + case GHCB_MSR_SEV_INFO_REQ: + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + GHCB_VERSION_MIN, + sev_enc_bit)); + break; + case GHCB_MSR_CPUID_REQ: { + u64 cpuid_fn, cpuid_reg, cpuid_value; + + cpuid_fn = get_ghcb_msr_bits(svm, + GHCB_MSR_CPUID_FUNC_MASK, + GHCB_MSR_CPUID_FUNC_POS); + + /* Initialize the registers needed by the CPUID intercept */ + vcpu->arch.regs[VCPU_REGS_RAX] = cpuid_fn; + vcpu->arch.regs[VCPU_REGS_RCX] = 0; + + ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID); + if (!ret) { + /* Error, keep GHCB MSR value as-is */ + break; + } + + cpuid_reg = get_ghcb_msr_bits(svm, + GHCB_MSR_CPUID_REG_MASK, + GHCB_MSR_CPUID_REG_POS); + if (cpuid_reg == 0) + cpuid_value = vcpu->arch.regs[VCPU_REGS_RAX]; + else if (cpuid_reg == 1) + cpuid_value = vcpu->arch.regs[VCPU_REGS_RBX]; + else if (cpuid_reg == 2) + cpuid_value = vcpu->arch.regs[VCPU_REGS_RCX]; + else + cpuid_value = vcpu->arch.regs[VCPU_REGS_RDX]; + + set_ghcb_msr_bits(svm, cpuid_value, + GHCB_MSR_CPUID_VALUE_MASK, + GHCB_MSR_CPUID_VALUE_POS); + + set_ghcb_msr_bits(svm, GHCB_MSR_CPUID_RESP, + GHCB_MSR_INFO_MASK, + GHCB_MSR_INFO_POS); + break; + } + case GHCB_MSR_TERM_REQ: { + u64 reason_set, reason_code; + + reason_set = get_ghcb_msr_bits(svm, + GHCB_MSR_TERM_REASON_SET_MASK, + GHCB_MSR_TERM_REASON_SET_POS); + reason_code = get_ghcb_msr_bits(svm, + GHCB_MSR_TERM_REASON_MASK, + GHCB_MSR_TERM_REASON_POS); + pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", + reason_set, reason_code); + + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM; + vcpu->run->system_event.ndata = 1; + vcpu->run->system_event.data[0] = control->ghcb_gpa; + + return 0; + } + default: + /* Error, keep GHCB MSR value as-is */ + break; + } + + trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, + control->ghcb_gpa, ret); + + return ret; +} + +int sev_handle_vmgexit(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_control_area *control = &svm->vmcb->control; + u64 ghcb_gpa, exit_code; + int ret; + + /* Validate the GHCB */ + ghcb_gpa = control->ghcb_gpa; + if (ghcb_gpa & GHCB_MSR_INFO_MASK) + return sev_handle_vmgexit_msr_protocol(svm); + + if (!ghcb_gpa) { + vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n"); + + /* Without a GHCB, just return right back to the guest */ + return 1; + } + + if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { + /* Unable to map GHCB from guest */ + vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", + ghcb_gpa); + + /* Without a GHCB, just return right back to the guest */ + return 1; + } + + svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; + + trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb); + + sev_es_sync_from_ghcb(svm); + ret = sev_es_validate_vmgexit(svm); + if (ret) + return ret; + + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 0); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 0); + + exit_code = kvm_ghcb_get_sw_exit_code(control); + switch (exit_code) { + case SVM_VMGEXIT_MMIO_READ: + ret = setup_vmgexit_scratch(svm, true, control->exit_info_2); + if (ret) + break; + + ret = kvm_sev_es_mmio_read(vcpu, + control->exit_info_1, + control->exit_info_2, + svm->sev_es.ghcb_sa); + break; + case SVM_VMGEXIT_MMIO_WRITE: + ret = setup_vmgexit_scratch(svm, false, control->exit_info_2); + if (ret) + break; + + ret = kvm_sev_es_mmio_write(vcpu, + control->exit_info_1, + control->exit_info_2, + svm->sev_es.ghcb_sa); + break; + case SVM_VMGEXIT_NMI_COMPLETE: + ++vcpu->stat.nmi_window_exits; + svm->nmi_masked = false; + kvm_make_request(KVM_REQ_EVENT, vcpu); + ret = 1; + break; + case SVM_VMGEXIT_AP_HLT_LOOP: + ret = kvm_emulate_ap_reset_hold(vcpu); + break; + case SVM_VMGEXIT_AP_JUMP_TABLE: { + struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info; + + switch (control->exit_info_1) { + case 0: + /* Set AP jump table address */ + sev->ap_jump_table = control->exit_info_2; + break; + case 1: + /* Get AP jump table address */ + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, sev->ap_jump_table); + break; + default: + pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", + control->exit_info_1); + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT); + } + + ret = 1; + break; + } + case SVM_VMGEXIT_UNSUPPORTED_EVENT: + vcpu_unimpl(vcpu, + "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", + control->exit_info_1, control->exit_info_2); + ret = -EINVAL; + break; + default: + ret = svm_invoke_exit_handler(vcpu, exit_code); + } + + return ret; +} + +int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) +{ + int count; + int bytes; + int r; + + if (svm->vmcb->control.exit_info_2 > INT_MAX) + return -EINVAL; + + count = svm->vmcb->control.exit_info_2; + if (unlikely(check_mul_overflow(count, size, &bytes))) + return -EINVAL; + + r = setup_vmgexit_scratch(svm, in, bytes); + if (r) + return r; + + return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, + count, in); +} + +static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); + } +} + +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) +{ + struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_cpuid_entry2 *best; + + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + best = kvm_find_cpuid_entry(vcpu, 0x8000001F); + if (best) + vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_vcpu_after_set_cpuid(svm); +} + +static void sev_es_init_vmcb(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + struct kvm_vcpu *vcpu = &svm->vcpu; + + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; + svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; + + /* + * An SEV-ES guest requires a VMSA area that is a separate from the + * VMCB page. Do not include the encryption mask on the VMSA physical + * address since hardware will access it using the guest key. Note, + * the VMSA will be NULL if this vCPU is the destination for intrahost + * migration, and will be copied later. + */ + if (svm->sev_es.vmsa) + svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa); + + /* Can't intercept CR register access, HV can't modify CR registers */ + svm_clr_intercept(svm, INTERCEPT_CR0_READ); + svm_clr_intercept(svm, INTERCEPT_CR4_READ); + svm_clr_intercept(svm, INTERCEPT_CR8_READ); + svm_clr_intercept(svm, INTERCEPT_CR0_WRITE); + svm_clr_intercept(svm, INTERCEPT_CR4_WRITE); + svm_clr_intercept(svm, INTERCEPT_CR8_WRITE); + + svm_clr_intercept(svm, INTERCEPT_SELECTIVE_CR0); + + /* Track EFER/CR register changes */ + svm_set_intercept(svm, TRAP_EFER_WRITE); + svm_set_intercept(svm, TRAP_CR0_WRITE); + svm_set_intercept(svm, TRAP_CR4_WRITE); + svm_set_intercept(svm, TRAP_CR8_WRITE); + + vmcb->control.intercepts[INTERCEPT_DR] = 0; + if (!sev_es_debug_swap_enabled) { + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); + recalc_intercepts(svm); + } else { + /* + * Disable #DB intercept iff DebugSwap is enabled. KVM doesn't + * allow debugging SEV-ES guests, and enables DebugSwap iff + * NO_NESTED_DATA_BP is supported, so there's no reason to + * intercept #DB when DebugSwap is enabled. For simplicity + * with respect to guest debug, intercept #DB for other VMs + * even if NO_NESTED_DATA_BP is supported, i.e. even if the + * guest can't DoS the CPU with infinite #DB vectoring. + */ + clr_exception_intercept(svm, DB_VECTOR); + } + + /* Can't intercept XSETBV, HV can't modify XCR0 directly */ + svm_clr_intercept(svm, INTERCEPT_XSETBV); + + /* Clear intercepts on selected MSRs */ + set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); +} + +void sev_init_vmcb(struct vcpu_svm *svm) +{ + svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; + clr_exception_intercept(svm, UD_VECTOR); + + /* + * Don't intercept #GP for SEV guests, e.g. for the VMware backdoor, as + * KVM can't decrypt guest memory to decode the faulting instruction. + */ + clr_exception_intercept(svm, GP_VECTOR); + + if (sev_es_guest(svm->vcpu.kvm)) + sev_es_init_vmcb(svm); +} + +void sev_es_vcpu_reset(struct vcpu_svm *svm) +{ + /* + * Set the GHCB MSR value as per the GHCB specification when emulating + * vCPU RESET for an SEV-ES guest. + */ + set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX, + GHCB_VERSION_MIN, + sev_enc_bit)); +} + +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) +{ + /* + * All host state for SEV-ES guests is categorized into three swap types + * based on how it is handled by hardware during a world switch: + * + * A: VMRUN: Host state saved in host save area + * VMEXIT: Host state loaded from host save area + * + * B: VMRUN: Host state _NOT_ saved in host save area + * VMEXIT: Host state loaded from host save area + * + * C: VMRUN: Host state _NOT_ saved in host save area + * VMEXIT: Host state initialized to default(reset) values + * + * Manually save type-B state, i.e. state that is loaded by VMEXIT but + * isn't saved by VMRUN, that isn't already saved by VMSAVE (performed + * by common SVM code). + */ + hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); + hostsa->pkru = read_pkru(); + hostsa->xss = host_xss; + + /* + * If DebugSwap is enabled, debug registers are loaded but NOT saved by + * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both + * saves and loads debug registers (Type-A). + */ + if (sev_es_debug_swap_enabled) { + hostsa->dr0 = native_get_debugreg(0); + hostsa->dr1 = native_get_debugreg(1); + hostsa->dr2 = native_get_debugreg(2); + hostsa->dr3 = native_get_debugreg(3); + hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0); + hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1); + hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2); + hostsa->dr3_addr_mask = amd_get_dr_addr_mask(3); + } +} + +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* First SIPI: Use the values as initially set by the VMM */ + if (!svm->sev_es.received_first_sipi) { + svm->sev_es.received_first_sipi = true; + return; + } + + /* + * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where + * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a + * non-zero value. + */ + if (!svm->sev_es.ghcb) + return; + + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c new file mode 100644 index 0000000000..77f1eeefcd --- /dev/null +++ b/arch/x86/kvm/svm/svm.c @@ -0,0 +1,5381 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include + +#include "irq.h" +#include "mmu.h" +#include "kvm_cache_regs.h" +#include "x86.h" +#include "smm.h" +#include "cpuid.h" +#include "pmu.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "trace.h" + +#include "svm.h" +#include "svm_ops.h" + +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" + +MODULE_AUTHOR("Qumranet"); +MODULE_LICENSE("GPL"); + +#ifdef MODULE +static const struct x86_cpu_id svm_cpu_id[] = { + X86_MATCH_FEATURE(X86_FEATURE_SVM, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); +#endif + +#define SEG_TYPE_LDT 2 +#define SEG_TYPE_BUSY_TSS16 3 + +static bool erratum_383_found __read_mostly; + +u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; + +/* + * Set osvw_len to higher value when updated Revision Guides + * are published and we know what the new status bits are + */ +static uint64_t osvw_len = 4, osvw_status; + +static DEFINE_PER_CPU(u64, current_tsc_ratio); + +#define X2APIC_MSR(x) (APIC_BASE_MSR + (x >> 4)) + +static const struct svm_direct_access_msrs { + u32 index; /* Index of the MSR */ + bool always; /* True if intercept is initially cleared */ +} direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = { + { .index = MSR_STAR, .always = true }, + { .index = MSR_IA32_SYSENTER_CS, .always = true }, + { .index = MSR_IA32_SYSENTER_EIP, .always = false }, + { .index = MSR_IA32_SYSENTER_ESP, .always = false }, +#ifdef CONFIG_X86_64 + { .index = MSR_GS_BASE, .always = true }, + { .index = MSR_FS_BASE, .always = true }, + { .index = MSR_KERNEL_GS_BASE, .always = true }, + { .index = MSR_LSTAR, .always = true }, + { .index = MSR_CSTAR, .always = true }, + { .index = MSR_SYSCALL_MASK, .always = true }, +#endif + { .index = MSR_IA32_SPEC_CTRL, .always = false }, + { .index = MSR_IA32_PRED_CMD, .always = false }, + { .index = MSR_IA32_FLUSH_CMD, .always = false }, + { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, + { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, + { .index = MSR_IA32_LASTINTFROMIP, .always = false }, + { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_EFER, .always = false }, + { .index = MSR_IA32_CR_PAT, .always = false }, + { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, + { .index = MSR_TSC_AUX, .always = false }, + { .index = X2APIC_MSR(APIC_ID), .always = false }, + { .index = X2APIC_MSR(APIC_LVR), .always = false }, + { .index = X2APIC_MSR(APIC_TASKPRI), .always = false }, + { .index = X2APIC_MSR(APIC_ARBPRI), .always = false }, + { .index = X2APIC_MSR(APIC_PROCPRI), .always = false }, + { .index = X2APIC_MSR(APIC_EOI), .always = false }, + { .index = X2APIC_MSR(APIC_RRR), .always = false }, + { .index = X2APIC_MSR(APIC_LDR), .always = false }, + { .index = X2APIC_MSR(APIC_DFR), .always = false }, + { .index = X2APIC_MSR(APIC_SPIV), .always = false }, + { .index = X2APIC_MSR(APIC_ISR), .always = false }, + { .index = X2APIC_MSR(APIC_TMR), .always = false }, + { .index = X2APIC_MSR(APIC_IRR), .always = false }, + { .index = X2APIC_MSR(APIC_ESR), .always = false }, + { .index = X2APIC_MSR(APIC_ICR), .always = false }, + { .index = X2APIC_MSR(APIC_ICR2), .always = false }, + + /* + * Note: + * AMD does not virtualize APIC TSC-deadline timer mode, but it is + * emulated by KVM. When setting APIC LVTT (0x832) register bit 18, + * the AVIC hardware would generate GP fault. Therefore, always + * intercept the MSR 0x832, and do not setup direct_access_msr. + */ + { .index = X2APIC_MSR(APIC_LVTTHMR), .always = false }, + { .index = X2APIC_MSR(APIC_LVTPC), .always = false }, + { .index = X2APIC_MSR(APIC_LVT0), .always = false }, + { .index = X2APIC_MSR(APIC_LVT1), .always = false }, + { .index = X2APIC_MSR(APIC_LVTERR), .always = false }, + { .index = X2APIC_MSR(APIC_TMICT), .always = false }, + { .index = X2APIC_MSR(APIC_TMCCT), .always = false }, + { .index = X2APIC_MSR(APIC_TDCR), .always = false }, + { .index = MSR_INVALID, .always = false }, +}; + +/* + * These 2 parameters are used to config the controls for Pause-Loop Exiting: + * pause_filter_count: On processors that support Pause filtering(indicated + * by CPUID Fn8000_000A_EDX), the VMCB provides a 16 bit pause filter + * count value. On VMRUN this value is loaded into an internal counter. + * Each time a pause instruction is executed, this counter is decremented + * until it reaches zero at which time a #VMEXIT is generated if pause + * intercept is enabled. Refer to AMD APM Vol 2 Section 15.14.4 Pause + * Intercept Filtering for more details. + * This also indicate if ple logic enabled. + * + * pause_filter_thresh: In addition, some processor families support advanced + * pause filtering (indicated by CPUID Fn8000_000A_EDX) upper bound on + * the amount of time a guest is allowed to execute in a pause loop. + * In this mode, a 16-bit pause filter threshold field is added in the + * VMCB. The threshold value is a cycle count that is used to reset the + * pause counter. As with simple pause filtering, VMRUN loads the pause + * count value from VMCB into an internal counter. Then, on each pause + * instruction the hardware checks the elapsed number of cycles since + * the most recent pause instruction against the pause filter threshold. + * If the elapsed cycle count is greater than the pause filter threshold, + * then the internal pause count is reloaded from the VMCB and execution + * continues. If the elapsed cycle count is less than the pause filter + * threshold, then the internal pause count is decremented. If the count + * value is less than zero and PAUSE intercept is enabled, a #VMEXIT is + * triggered. If advanced pause filtering is supported and pause filter + * threshold field is set to zero, the filter will operate in the simpler, + * count only mode. + */ + +static unsigned short pause_filter_thresh = KVM_DEFAULT_PLE_GAP; +module_param(pause_filter_thresh, ushort, 0444); + +static unsigned short pause_filter_count = KVM_SVM_DEFAULT_PLE_WINDOW; +module_param(pause_filter_count, ushort, 0444); + +/* Default doubles per-vcpu window every exit. */ +static unsigned short pause_filter_count_grow = KVM_DEFAULT_PLE_WINDOW_GROW; +module_param(pause_filter_count_grow, ushort, 0444); + +/* Default resets per-vcpu window every exit to pause_filter_count. */ +static unsigned short pause_filter_count_shrink = KVM_DEFAULT_PLE_WINDOW_SHRINK; +module_param(pause_filter_count_shrink, ushort, 0444); + +/* Default is to compute the maximum so we can never overflow. */ +static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX; +module_param(pause_filter_count_max, ushort, 0444); + +/* + * Use nested page tables by default. Note, NPT may get forced off by + * svm_hardware_setup() if it's unsupported by hardware or the host kernel. + */ +bool npt_enabled = true; +module_param_named(npt, npt_enabled, bool, 0444); + +/* allow nested virtualization in KVM/SVM */ +static int nested = true; +module_param(nested, int, S_IRUGO); + +/* enable/disable Next RIP Save */ +int nrips = true; +module_param(nrips, int, 0444); + +/* enable/disable Virtual VMLOAD VMSAVE */ +static int vls = true; +module_param(vls, int, 0444); + +/* enable/disable Virtual GIF */ +int vgif = true; +module_param(vgif, int, 0444); + +/* enable/disable LBR virtualization */ +static int lbrv = true; +module_param(lbrv, int, 0444); + +static int tsc_scaling = true; +module_param(tsc_scaling, int, 0444); + +/* + * enable / disable AVIC. Because the defaults differ for APICv + * support between VMX and SVM we cannot use module_param_named. + */ +static bool avic; +module_param(avic, bool, 0444); + +bool __read_mostly dump_invalid_vmcb; +module_param(dump_invalid_vmcb, bool, 0644); + + +bool intercept_smi = true; +module_param(intercept_smi, bool, 0444); + +bool vnmi = true; +module_param(vnmi, bool, 0444); + +static bool svm_gp_erratum_intercept = true; + +static u8 rsm_ins_bytes[] = "\x0f\xaa"; + +static unsigned long iopm_base; + +DEFINE_PER_CPU(struct svm_cpu_data, svm_data); + +/* + * Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via + * the VMCB, and the SYSCALL/SYSENTER MSRs are handled by VMLOAD/VMSAVE. + * + * RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to + * defer the restoration of TSC_AUX until the CPU returns to userspace. + */ +static int tsc_aux_uret_slot __read_mostly = -1; + +static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; + +#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges) +#define MSRS_RANGE_SIZE 2048 +#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) + +u32 svm_msrpm_offset(u32 msr) +{ + u32 offset; + int i; + + for (i = 0; i < NUM_MSR_MAPS; i++) { + if (msr < msrpm_ranges[i] || + msr >= msrpm_ranges[i] + MSRS_IN_RANGE) + continue; + + offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */ + offset += (i * MSRS_RANGE_SIZE); /* add range offset */ + + /* Now we have the u8 offset - but need the u32 offset */ + return offset / 4; + } + + /* MSR not in any range */ + return MSR_INVALID; +} + +static void svm_flush_tlb_current(struct kvm_vcpu *vcpu); + +static int get_npt_level(void) +{ +#ifdef CONFIG_X86_64 + return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; +#else + return PT32E_ROOT_LEVEL; +#endif +} + +int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 old_efer = vcpu->arch.efer; + vcpu->arch.efer = efer; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } + + if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) { + if (!(efer & EFER_SVME)) { + svm_leave_nested(vcpu); + svm_set_gif(svm, true); + /* #GP intercept is still needed for vmware backdoor */ + if (!enable_vmware_backdoor) + clr_exception_intercept(svm, GP_VECTOR); + + /* + * Free the nested guest state, unless we are in SMM. + * In this case we will return to the nested guest + * as soon as we leave SMM. + */ + if (!is_smm(vcpu)) + svm_free_nested(svm); + + } else { + int ret = svm_allocate_nested(svm); + + if (ret) { + vcpu->arch.efer = old_efer; + return ret; + } + + /* + * Never intercept #GP for SEV guests, KVM can't + * decrypt guest memory to workaround the erratum. + */ + if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm)) + set_exception_intercept(svm, GP_VECTOR); + } + } + + svm->vmcb->save.efer = efer | EFER_SVME; + vmcb_mark_dirty(svm->vmcb, VMCB_CR); + return 0; +} + +static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 ret = 0; + + if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) + ret = KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS; + return ret; +} + +static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (mask == 0) + svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; + else + svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK; + +} +static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); + +static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, + bool commit_side_effects) +{ + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long old_rflags; + + /* + * SEV-ES does not expose the next RIP. The RIP update is controlled by + * the type of exit and the #VC handler in the guest. + */ + if (sev_es_guest(vcpu->kvm)) + goto done; + + if (nrips && svm->vmcb->control.next_rip != 0) { + WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS)); + svm->next_rip = svm->vmcb->control.next_rip; + } + + if (!svm->next_rip) { + /* + * FIXME: Drop this when kvm_emulate_instruction() does the + * right thing and treats "can't emulate" as outright failure + * for EMULTYPE_SKIP. + */ + if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0)) + return 0; + + if (unlikely(!commit_side_effects)) + old_rflags = svm->vmcb->save.rflags; + + if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) + return 0; + + if (unlikely(!commit_side_effects)) + svm->vmcb->save.rflags = old_rflags; + } else { + kvm_rip_write(vcpu, svm->next_rip); + } + +done: + if (likely(commit_side_effects)) + svm_set_interrupt_shadow(vcpu, 0); + + return 1; +} + +static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + return __svm_skip_emulated_instruction(vcpu, true); +} + +static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) +{ + unsigned long rip, old_rip = kvm_rip_read(vcpu); + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * Due to architectural shortcomings, the CPU doesn't always provide + * NextRIP, e.g. if KVM intercepted an exception that occurred while + * the CPU was vectoring an INTO/INT3 in the guest. Temporarily skip + * the instruction even if NextRIP is supported to acquire the next + * RIP so that it can be shoved into the NextRIP field, otherwise + * hardware will fail to advance guest RIP during event injection. + * Drop the exception/interrupt if emulation fails and effectively + * retry the instruction, it's the least awful option. If NRIPS is + * in use, the skip must not commit any side effects such as clearing + * the interrupt shadow or RFLAGS.RF. + */ + if (!__svm_skip_emulated_instruction(vcpu, !nrips)) + return -EIO; + + rip = kvm_rip_read(vcpu); + + /* + * Save the injection information, even when using next_rip, as the + * VMCB's next_rip will be lost (cleared on VM-Exit) if the injection + * doesn't complete due to a VM-Exit occurring while the CPU is + * vectoring the event. Decoding the instruction isn't guaranteed to + * work as there may be no backing instruction, e.g. if the event is + * being injected by L1 for L2, or if the guest is patching INT3 into + * a different instruction. + */ + svm->soft_int_injected = true; + svm->soft_int_csbase = svm->vmcb->save.cs.base; + svm->soft_int_old_rip = old_rip; + svm->soft_int_next_rip = rip; + + if (nrips) + kvm_rip_write(vcpu, old_rip); + + if (static_cpu_has(X86_FEATURE_NRIPS)) + svm->vmcb->control.next_rip = rip; + + return 0; +} + +static void svm_inject_exception(struct kvm_vcpu *vcpu) +{ + struct kvm_queued_exception *ex = &vcpu->arch.exception; + struct vcpu_svm *svm = to_svm(vcpu); + + kvm_deliver_exception_payload(vcpu, ex); + + if (kvm_exception_is_soft(ex->vector) && + svm_update_soft_interrupt_rip(vcpu)) + return; + + svm->vmcb->control.event_inj = ex->vector + | SVM_EVTINJ_VALID + | (ex->has_error_code ? SVM_EVTINJ_VALID_ERR : 0) + | SVM_EVTINJ_TYPE_EXEPT; + svm->vmcb->control.event_inj_err = ex->error_code; +} + +static void svm_init_erratum_383(void) +{ + u32 low, high; + int err; + u64 val; + + if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH)) + return; + + /* Use _safe variants to not break nested virtualization */ + val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err); + if (err) + return; + + val |= (1ULL << 47); + + low = lower_32_bits(val); + high = upper_32_bits(val); + + native_write_msr_safe(MSR_AMD64_DC_CFG, low, high); + + erratum_383_found = true; +} + +static void svm_init_osvw(struct kvm_vcpu *vcpu) +{ + /* + * Guests should see errata 400 and 415 as fixed (assuming that + * HLT and IO instructions are intercepted). + */ + vcpu->arch.osvw.length = (osvw_len >= 3) ? (osvw_len) : 3; + vcpu->arch.osvw.status = osvw_status & ~(6ULL); + + /* + * By increasing VCPU's osvw.length to 3 we are telling the guest that + * all osvw.status bits inside that length, including bit 0 (which is + * reserved for erratum 298), are valid. However, if host processor's + * osvw_len is 0 then osvw_status[0] carries no information. We need to + * be conservative here and therefore we tell the guest that erratum 298 + * is present (because we really don't know). + */ + if (osvw_len == 0 && boot_cpu_data.x86 == 0x10) + vcpu->arch.osvw.status |= 1; +} + +static bool __kvm_is_svm_supported(void) +{ + int cpu = smp_processor_id(); + struct cpuinfo_x86 *c = &cpu_data(cpu); + + u64 vm_cr; + + if (c->x86_vendor != X86_VENDOR_AMD && + c->x86_vendor != X86_VENDOR_HYGON) { + pr_err("CPU %d isn't AMD or Hygon\n", cpu); + return false; + } + + if (!cpu_has(c, X86_FEATURE_SVM)) { + pr_err("SVM not supported by CPU %d\n", cpu); + return false; + } + + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { + pr_info("KVM is unsupported when running as an SEV guest\n"); + return false; + } + + rdmsrl(MSR_VM_CR, vm_cr); + if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) { + pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu); + return false; + } + + return true; +} + +static bool kvm_is_svm_supported(void) +{ + bool supported; + + migrate_disable(); + supported = __kvm_is_svm_supported(); + migrate_enable(); + + return supported; +} + +static int svm_check_processor_compat(void) +{ + if (!__kvm_is_svm_supported()) + return -EIO; + + return 0; +} + +static void __svm_write_tsc_multiplier(u64 multiplier) +{ + if (multiplier == __this_cpu_read(current_tsc_ratio)) + return; + + wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); + __this_cpu_write(current_tsc_ratio, multiplier); +} + +static inline void kvm_cpu_svm_disable(void) +{ + uint64_t efer; + + wrmsrl(MSR_VM_HSAVE_PA, 0); + rdmsrl(MSR_EFER, efer); + if (efer & EFER_SVME) { + /* + * Force GIF=1 prior to disabling SVM, e.g. to ensure INIT and + * NMI aren't blocked. + */ + stgi(); + wrmsrl(MSR_EFER, efer & ~EFER_SVME); + } +} + +static void svm_emergency_disable(void) +{ + kvm_rebooting = true; + + kvm_cpu_svm_disable(); +} + +static void svm_hardware_disable(void) +{ + /* Make sure we clean up behind us */ + if (tsc_scaling) + __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); + + kvm_cpu_svm_disable(); + + amd_pmu_disable_virt(); +} + +static int svm_hardware_enable(void) +{ + + struct svm_cpu_data *sd; + uint64_t efer; + int me = raw_smp_processor_id(); + + rdmsrl(MSR_EFER, efer); + if (efer & EFER_SVME) + return -EBUSY; + + sd = per_cpu_ptr(&svm_data, me); + sd->asid_generation = 1; + sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; + sd->next_asid = sd->max_asid + 1; + sd->min_asid = max_sev_asid + 1; + + wrmsrl(MSR_EFER, efer | EFER_SVME); + + wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa); + + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + /* + * Set the default value, even if we don't use TSC scaling + * to avoid having stale value in the msr + */ + __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); + } + + + /* + * Get OSVW bits. + * + * Note that it is possible to have a system with mixed processor + * revisions and therefore different OSVW bits. If bits are not the same + * on different processors then choose the worst case (i.e. if erratum + * is present on one processor and not on another then assume that the + * erratum is present everywhere). + */ + if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) { + uint64_t len, status = 0; + int err; + + len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err); + if (!err) + status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS, + &err); + + if (err) + osvw_status = osvw_len = 0; + else { + if (len < osvw_len) + osvw_len = len; + osvw_status |= status; + osvw_status &= (1ULL << osvw_len) - 1; + } + } else + osvw_status = osvw_len = 0; + + svm_init_erratum_383(); + + amd_pmu_enable_virt(); + + /* + * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type + * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests. + * Since Linux does not change the value of TSC_AUX once set, prime the + * TSC_AUX field now to avoid a RDMSR on every vCPU run. + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { + struct sev_es_save_area *hostsa; + u32 __maybe_unused msr_hi; + + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); + + rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi); + } + + return 0; +} + +static void svm_cpu_uninit(int cpu) +{ + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); + + if (!sd->save_area) + return; + + kfree(sd->sev_vmcbs); + __free_page(sd->save_area); + sd->save_area_pa = 0; + sd->save_area = NULL; +} + +static int svm_cpu_init(int cpu) +{ + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); + int ret = -ENOMEM; + + memset(sd, 0, sizeof(struct svm_cpu_data)); + sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!sd->save_area) + return ret; + + ret = sev_cpu_init(sd); + if (ret) + goto free_save_area; + + sd->save_area_pa = __sme_page_pa(sd->save_area); + return 0; + +free_save_area: + __free_page(sd->save_area); + sd->save_area = NULL; + return ret; + +} + +static void set_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ); + vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE); + + recalc_intercepts(svm); +} + +static void clr_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb->control.intercepts[INTERCEPT_DR] = 0; + + recalc_intercepts(svm); +} + +static int direct_access_msr_slot(u32 msr) +{ + u32 i; + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) + if (direct_access_msrs[i].index == msr) + return i; + + return -ENOENT; +} + +static void set_shadow_msr_intercept(struct kvm_vcpu *vcpu, u32 msr, int read, + int write) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int slot = direct_access_msr_slot(msr); + + if (slot == -ENOENT) + return; + + /* Set the shadow bitmaps to the desired intercept states */ + if (read) + set_bit(slot, svm->shadow_msr_intercept.read); + else + clear_bit(slot, svm->shadow_msr_intercept.read); + + if (write) + set_bit(slot, svm->shadow_msr_intercept.write); + else + clear_bit(slot, svm->shadow_msr_intercept.write); +} + +static bool valid_msr_intercept(u32 index) +{ + return direct_access_msr_slot(index) != -ENOENT; +} + +static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +{ + u8 bit_write; + unsigned long tmp; + u32 offset; + u32 *msrpm; + + /* + * For non-nested case: + * If the L01 MSR bitmap does not intercept the MSR, then we need to + * save it. + * + * For nested case: + * If the L02 MSR bitmap does not intercept the MSR, then we need to + * save it. + */ + msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm: + to_svm(vcpu)->msrpm; + + offset = svm_msrpm_offset(msr); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + return test_bit(bit_write, &tmp); +} + +static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm, + u32 msr, int read, int write) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u8 bit_read, bit_write; + unsigned long tmp; + u32 offset; + + /* + * If this warning triggers extend the direct_access_msrs list at the + * beginning of the file + */ + WARN_ON(!valid_msr_intercept(msr)); + + /* Enforce non allowed MSRs to trap */ + if (read && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) + read = 0; + + if (write && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) + write = 0; + + offset = svm_msrpm_offset(msr); + bit_read = 2 * (msr & 0x0f); + bit_write = 2 * (msr & 0x0f) + 1; + tmp = msrpm[offset]; + + BUG_ON(offset == MSR_INVALID); + + read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp); + write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp); + + msrpm[offset] = tmp; + + svm_hv_vmcb_dirty_nested_enlightenments(vcpu); + svm->nested.force_msr_bitmap_recalc = true; +} + +void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, + int read, int write) +{ + set_shadow_msr_intercept(vcpu, msr, read, write); + set_msr_interception_bitmap(vcpu, msrpm, msr, read, write); +} + +u32 *svm_vcpu_alloc_msrpm(void) +{ + unsigned int order = get_order(MSRPM_SIZE); + struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, order); + u32 *msrpm; + + if (!pages) + return NULL; + + msrpm = page_address(pages); + memset(msrpm, 0xff, PAGE_SIZE * (1 << order)); + + return msrpm; +} + +void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm) +{ + int i; + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + if (!direct_access_msrs[i].always) + continue; + set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1); + } +} + +void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) +{ + int i; + + if (intercept == svm->x2avic_msrs_intercepted) + return; + + if (!x2avic_enabled) + return; + + for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { + int index = direct_access_msrs[i].index; + + if ((index < APIC_BASE_MSR) || + (index > APIC_BASE_MSR + 0xff)) + continue; + set_msr_interception(&svm->vcpu, svm->msrpm, index, + !intercept, !intercept); + } + + svm->x2avic_msrs_intercepted = intercept; +} + +void svm_vcpu_free_msrpm(u32 *msrpm) +{ + __free_pages(virt_to_page(msrpm), get_order(MSRPM_SIZE)); +} + +static void svm_msr_filter_changed(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 i; + + /* + * Set intercept permissions for all direct access MSRs again. They + * will automatically get filtered through the MSR filter, so we are + * back in sync after this. + */ + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + u32 msr = direct_access_msrs[i].index; + u32 read = test_bit(i, svm->shadow_msr_intercept.read); + u32 write = test_bit(i, svm->shadow_msr_intercept.write); + + set_msr_interception_bitmap(vcpu, svm->msrpm, msr, read, write); + } +} + +static void add_msr_offset(u32 offset) +{ + int i; + + for (i = 0; i < MSRPM_OFFSETS; ++i) { + + /* Offset already in list? */ + if (msrpm_offsets[i] == offset) + return; + + /* Slot used by another offset? */ + if (msrpm_offsets[i] != MSR_INVALID) + continue; + + /* Add offset to list */ + msrpm_offsets[i] = offset; + + return; + } + + /* + * If this BUG triggers the msrpm_offsets table has an overflow. Just + * increase MSRPM_OFFSETS in this case. + */ + BUG(); +} + +static void init_msrpm_offsets(void) +{ + int i; + + memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets)); + + for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) { + u32 offset; + + offset = svm_msrpm_offset(direct_access_msrs[i].index); + BUG_ON(offset == MSR_INVALID); + + add_msr_offset(offset); + } +} + +void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) +{ + to_vmcb->save.dbgctl = from_vmcb->save.dbgctl; + to_vmcb->save.br_from = from_vmcb->save.br_from; + to_vmcb->save.br_to = from_vmcb->save.br_to; + to_vmcb->save.last_excp_from = from_vmcb->save.last_excp_from; + to_vmcb->save.last_excp_to = from_vmcb->save.last_excp_to; + + vmcb_mark_dirty(to_vmcb, VMCB_LBR); +} + +static void svm_enable_lbrv(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ + if (is_guest_mode(vcpu)) + svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); +} + +static void svm_disable_lbrv(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0); + + /* + * Move the LBR msrs back to the vmcb01 to avoid copying them + * on nested guest entries. + */ + if (is_guest_mode(vcpu)) + svm_copy_lbrs(svm->vmcb01.ptr, svm->vmcb); +} + +static struct vmcb *svm_get_lbr_vmcb(struct vcpu_svm *svm) +{ + /* + * If LBR virtualization is disabled, the LBR MSRs are always kept in + * vmcb01. If LBR virtualization is enabled and L1 is running VMs of + * its own, the MSRs are moved between vmcb01 and vmcb02 as needed. + */ + return svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK ? svm->vmcb : + svm->vmcb01.ptr; +} + +void svm_update_lbrv(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK; + bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) || + (is_guest_mode(vcpu) && guest_can_use(vcpu, X86_FEATURE_LBRV) && + (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)); + + if (enable_lbrv == current_enable_lbrv) + return; + + if (enable_lbrv) + svm_enable_lbrv(vcpu); + else + svm_disable_lbrv(vcpu); +} + +void disable_nmi_singlestep(struct vcpu_svm *svm) +{ + svm->nmi_singlestep = false; + + if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) { + /* Clear our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_RF; + } +} + +static void grow_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_control_area *control = &svm->vmcb->control; + int old = control->pause_filter_count; + + if (kvm_pause_in_guest(vcpu->kvm)) + return; + + control->pause_filter_count = __grow_ple_window(old, + pause_filter_count, + pause_filter_count_grow, + pause_filter_count_max); + + if (control->pause_filter_count != old) { + vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + trace_kvm_ple_window_update(vcpu->vcpu_id, + control->pause_filter_count, old); + } +} + +static void shrink_ple_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_control_area *control = &svm->vmcb->control; + int old = control->pause_filter_count; + + if (kvm_pause_in_guest(vcpu->kvm)) + return; + + control->pause_filter_count = + __shrink_ple_window(old, + pause_filter_count, + pause_filter_count_shrink, + pause_filter_count); + if (control->pause_filter_count != old) { + vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + trace_kvm_ple_window_update(vcpu->vcpu_id, + control->pause_filter_count, old); + } +} + +static void svm_hardware_unsetup(void) +{ + int cpu; + + sev_hardware_unsetup(); + + for_each_possible_cpu(cpu) + svm_cpu_uninit(cpu); + + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), + get_order(IOPM_SIZE)); + iopm_base = 0; +} + +static void init_seg(struct vmcb_seg *seg) +{ + seg->selector = 0; + seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK | + SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ + seg->limit = 0xffff; + seg->base = 0; +} + +static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) +{ + seg->selector = 0; + seg->attrib = SVM_SELECTOR_P_MASK | type; + seg->limit = 0xffff; + seg->base = 0; +} + +static u64 svm_get_l2_tsc_offset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return svm->nested.ctl.tsc_offset; +} + +static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return svm->tsc_ratio_msr; +} + +static void svm_write_tsc_offset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb01.ptr->control.tsc_offset = vcpu->arch.l1_tsc_offset; + svm->vmcb->control.tsc_offset = vcpu->arch.tsc_offset; + vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); +} + +void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + if (to_svm(vcpu)->guest_state_loaded) + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); + preempt_enable(); +} + +/* Evaluate instruction intercepts that depend on guest CPUID features. */ +static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, + struct vcpu_svm *svm) +{ + /* + * Intercept INVPCID if shadow paging is enabled to sync/free shadow + * roots, or if INVPCID is disabled in the guest to inject #UD. + */ + if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) { + if (!npt_enabled || + !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID)) + svm_set_intercept(svm, INTERCEPT_INVPCID); + else + svm_clr_intercept(svm, INTERCEPT_INVPCID); + } + + if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) { + if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + svm_clr_intercept(svm, INTERCEPT_RDTSCP); + else + svm_set_intercept(svm, INTERCEPT_RDTSCP); + } +} + +static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (guest_cpuid_is_intel(vcpu)) { + /* + * We must intercept SYSENTER_EIP and SYSENTER_ESP + * accesses because the processor only stores 32 bits. + * For the same reason we cannot use virtual VMLOAD/VMSAVE. + */ + svm_set_intercept(svm, INTERCEPT_VMLOAD); + svm_set_intercept(svm, INTERCEPT_VMSAVE); + svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0); + } else { + /* + * If hardware supports Virtual VMLOAD VMSAVE then enable it + * in VMCB and clear intercepts to avoid #VMEXIT. + */ + if (vls) { + svm_clr_intercept(svm, INTERCEPT_VMLOAD); + svm_clr_intercept(svm, INTERCEPT_VMSAVE); + svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; + } + /* No need to intercept these MSRs */ + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 1, 1); + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 1, 1); + } +} + +static void init_vmcb(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb01.ptr; + struct vmcb_control_area *control = &vmcb->control; + struct vmcb_save_area *save = &vmcb->save; + + svm_set_intercept(svm, INTERCEPT_CR0_READ); + svm_set_intercept(svm, INTERCEPT_CR3_READ); + svm_set_intercept(svm, INTERCEPT_CR4_READ); + svm_set_intercept(svm, INTERCEPT_CR0_WRITE); + svm_set_intercept(svm, INTERCEPT_CR3_WRITE); + svm_set_intercept(svm, INTERCEPT_CR4_WRITE); + if (!kvm_vcpu_apicv_active(vcpu)) + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); + + set_dr_intercepts(svm); + + set_exception_intercept(svm, PF_VECTOR); + set_exception_intercept(svm, UD_VECTOR); + set_exception_intercept(svm, MC_VECTOR); + set_exception_intercept(svm, AC_VECTOR); + set_exception_intercept(svm, DB_VECTOR); + /* + * Guest access to VMware backdoor ports could legitimately + * trigger #GP because of TSS I/O permission bitmap. + * We intercept those #GP and allow access to them anyway + * as VMware does. + */ + if (enable_vmware_backdoor) + set_exception_intercept(svm, GP_VECTOR); + + svm_set_intercept(svm, INTERCEPT_INTR); + svm_set_intercept(svm, INTERCEPT_NMI); + + if (intercept_smi) + svm_set_intercept(svm, INTERCEPT_SMI); + + svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0); + svm_set_intercept(svm, INTERCEPT_RDPMC); + svm_set_intercept(svm, INTERCEPT_CPUID); + svm_set_intercept(svm, INTERCEPT_INVD); + svm_set_intercept(svm, INTERCEPT_INVLPG); + svm_set_intercept(svm, INTERCEPT_INVLPGA); + svm_set_intercept(svm, INTERCEPT_IOIO_PROT); + svm_set_intercept(svm, INTERCEPT_MSR_PROT); + svm_set_intercept(svm, INTERCEPT_TASK_SWITCH); + svm_set_intercept(svm, INTERCEPT_SHUTDOWN); + svm_set_intercept(svm, INTERCEPT_VMRUN); + svm_set_intercept(svm, INTERCEPT_VMMCALL); + svm_set_intercept(svm, INTERCEPT_VMLOAD); + svm_set_intercept(svm, INTERCEPT_VMSAVE); + svm_set_intercept(svm, INTERCEPT_STGI); + svm_set_intercept(svm, INTERCEPT_CLGI); + svm_set_intercept(svm, INTERCEPT_SKINIT); + svm_set_intercept(svm, INTERCEPT_WBINVD); + svm_set_intercept(svm, INTERCEPT_XSETBV); + svm_set_intercept(svm, INTERCEPT_RDPRU); + svm_set_intercept(svm, INTERCEPT_RSM); + + if (!kvm_mwait_in_guest(vcpu->kvm)) { + svm_set_intercept(svm, INTERCEPT_MONITOR); + svm_set_intercept(svm, INTERCEPT_MWAIT); + } + + if (!kvm_hlt_in_guest(vcpu->kvm)) + svm_set_intercept(svm, INTERCEPT_HLT); + + control->iopm_base_pa = __sme_set(iopm_base); + control->msrpm_base_pa = __sme_set(__pa(svm->msrpm)); + control->int_ctl = V_INTR_MASKING_MASK; + + init_seg(&save->es); + init_seg(&save->ss); + init_seg(&save->ds); + init_seg(&save->fs); + init_seg(&save->gs); + + save->cs.selector = 0xf000; + save->cs.base = 0xffff0000; + /* Executable/Readable Code Segment */ + save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK | + SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK; + save->cs.limit = 0xffff; + + save->gdtr.base = 0; + save->gdtr.limit = 0xffff; + save->idtr.base = 0; + save->idtr.limit = 0xffff; + + init_sys_seg(&save->ldtr, SEG_TYPE_LDT); + init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); + + if (npt_enabled) { + /* Setup VMCB for Nested Paging */ + control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE; + svm_clr_intercept(svm, INTERCEPT_INVLPG); + clr_exception_intercept(svm, PF_VECTOR); + svm_clr_intercept(svm, INTERCEPT_CR3_READ); + svm_clr_intercept(svm, INTERCEPT_CR3_WRITE); + save->g_pat = vcpu->arch.pat; + save->cr3 = 0; + } + svm->current_vmcb->asid_generation = 0; + svm->asid = 0; + + svm->nested.vmcb12_gpa = INVALID_GPA; + svm->nested.last_vmcb12_gpa = INVALID_GPA; + + if (!kvm_pause_in_guest(vcpu->kvm)) { + control->pause_filter_count = pause_filter_count; + if (pause_filter_thresh) + control->pause_filter_thresh = pause_filter_thresh; + svm_set_intercept(svm, INTERCEPT_PAUSE); + } else { + svm_clr_intercept(svm, INTERCEPT_PAUSE); + } + + svm_recalc_instruction_intercepts(vcpu, svm); + + /* + * If the host supports V_SPEC_CTRL then disable the interception + * of MSR_IA32_SPEC_CTRL. + */ + if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + + if (kvm_vcpu_apicv_active(vcpu)) + avic_init_vmcb(svm, vmcb); + + if (vnmi) + svm->vmcb->control.int_ctl |= V_NMI_ENABLE_MASK; + + if (vgif) { + svm_clr_intercept(svm, INTERCEPT_STGI); + svm_clr_intercept(svm, INTERCEPT_CLGI); + svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK; + } + + if (sev_guest(vcpu->kvm)) + sev_init_vmcb(svm); + + svm_hv_init_vmcb(vmcb); + init_vmcb_after_set_cpuid(vcpu); + + vmcb_mark_all_dirty(vmcb); + + enable_gif(svm); +} + +static void __svm_vcpu_reset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm_vcpu_init_msrpm(vcpu, svm->msrpm); + + svm_init_osvw(vcpu); + vcpu->arch.microcode_version = 0x01000065; + svm->tsc_ratio_msr = kvm_caps.default_tsc_scaling_ratio; + + svm->nmi_masked = false; + svm->awaiting_iret_completion = false; + + if (sev_es_guest(vcpu->kvm)) + sev_es_vcpu_reset(svm); +} + +static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->spec_ctrl = 0; + svm->virt_spec_ctrl = 0; + + init_vmcb(vcpu); + + if (!init_event) + __svm_vcpu_reset(vcpu); +} + +void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb) +{ + svm->current_vmcb = target_vmcb; + svm->vmcb = target_vmcb->ptr; +} + +static int svm_vcpu_create(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm; + struct page *vmcb01_page; + struct page *vmsa_page = NULL; + int err; + + BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0); + svm = to_svm(vcpu); + + err = -ENOMEM; + vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!vmcb01_page) + goto out; + + if (sev_es_guest(vcpu->kvm)) { + /* + * SEV-ES guests require a separate VMSA page used to contain + * the encrypted register state of the guest. + */ + vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!vmsa_page) + goto error_free_vmcb_page; + + /* + * SEV-ES guests maintain an encrypted version of their FPU + * state which is restored and saved on VMRUN and VMEXIT. + * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't + * do xsave/xrstor on it. + */ + fpstate_set_confidential(&vcpu->arch.guest_fpu); + } + + err = avic_init_vcpu(svm); + if (err) + goto error_free_vmsa_page; + + svm->msrpm = svm_vcpu_alloc_msrpm(); + if (!svm->msrpm) { + err = -ENOMEM; + goto error_free_vmsa_page; + } + + svm->x2avic_msrs_intercepted = true; + + svm->vmcb01.ptr = page_address(vmcb01_page); + svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT); + svm_switch_vmcb(svm, &svm->vmcb01); + + if (vmsa_page) + svm->sev_es.vmsa = page_address(vmsa_page); + + svm->guest_state_loaded = false; + + return 0; + +error_free_vmsa_page: + if (vmsa_page) + __free_page(vmsa_page); +error_free_vmcb_page: + __free_page(vmcb01_page); +out: + return err; +} + +static void svm_clear_current_vmcb(struct vmcb *vmcb) +{ + int i; + + for_each_online_cpu(i) + cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL); +} + +static void svm_vcpu_free(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So, ensure that no logical CPU has this + * vmcb page recorded as its current vmcb. + */ + svm_clear_current_vmcb(svm->vmcb); + + svm_leave_nested(vcpu); + svm_free_nested(svm); + + sev_free_vcpu(vcpu); + + __free_page(pfn_to_page(__sme_clr(svm->vmcb01.pa) >> PAGE_SHIFT)); + __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); +} + +static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); + + if (sev_es_guest(vcpu->kvm)) + sev_es_unmap_ghcb(svm); + + if (svm->guest_state_loaded) + return; + + /* + * Save additional host state that will be restored on VMEXIT (sev-es) + * or subsequent vmload of host save area. + */ + vmsave(sd->save_area_pa); + if (sev_es_guest(vcpu->kvm)) { + struct sev_es_save_area *hostsa; + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); + + sev_es_prepare_switch_to_guest(hostsa); + } + + if (tsc_scaling) + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); + + /* + * TSC_AUX is always virtualized for SEV-ES guests when the feature is + * available. The user return MSR support is not required in this case + * because TSC_AUX is restored on #VMEXIT from the host save area + * (which has been initialized in svm_hardware_enable()). + */ + if (likely(tsc_aux_uret_slot >= 0) && + (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) + kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); + + svm->guest_state_loaded = true; +} + +static void svm_prepare_host_switch(struct kvm_vcpu *vcpu) +{ + to_svm(vcpu)->guest_state_loaded = false; +} + +static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); + + if (sd->current_vmcb != svm->vmcb) { + sd->current_vmcb = svm->vmcb; + + if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT)) + indirect_branch_prediction_barrier(); + } + if (kvm_vcpu_apicv_active(vcpu)) + avic_vcpu_load(vcpu, cpu); +} + +static void svm_vcpu_put(struct kvm_vcpu *vcpu) +{ + if (kvm_vcpu_apicv_active(vcpu)) + avic_vcpu_put(vcpu); + + svm_prepare_host_switch(vcpu); + + ++vcpu->stat.host_state_reload; +} + +static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long rflags = svm->vmcb->save.rflags; + + if (svm->nmi_singlestep) { + /* Hide our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + rflags &= ~X86_EFLAGS_RF; + } + return rflags; +} + +static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (to_svm(vcpu)->nmi_singlestep) + rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); + + /* + * Any change of EFLAGS.VM is accompanied by a reload of SS + * (caused by either a task switch or an inter-privilege IRET), + * so we do not need to update the CPL here. + */ + to_svm(vcpu)->vmcb->save.rflags = rflags; +} + +static bool svm_get_if_flag(struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = to_svm(vcpu)->vmcb; + + return sev_es_guest(vcpu->kvm) + ? vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK + : kvm_get_rflags(vcpu) & X86_EFLAGS_IF; +} + +static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) +{ + kvm_register_mark_available(vcpu, reg); + + switch (reg) { + case VCPU_EXREG_PDPTR: + /* + * When !npt_enabled, mmu->pdptrs[] is already available since + * it is always updated per SDM when moving to CRs. + */ + if (npt_enabled) + load_pdptrs(vcpu, kvm_read_cr3(vcpu)); + break; + default: + KVM_BUG_ON(1, vcpu->kvm); + } +} + +static void svm_set_vintr(struct vcpu_svm *svm) +{ + struct vmcb_control_area *control; + + /* + * The following fields are ignored when AVIC is enabled + */ + WARN_ON(kvm_vcpu_apicv_activated(&svm->vcpu)); + + svm_set_intercept(svm, INTERCEPT_VINTR); + + /* + * Recalculating intercepts may have cleared the VINTR intercept. If + * V_INTR_MASKING is enabled in vmcb12, then the effective RFLAGS.IF + * for L1 physical interrupts is L1's RFLAGS.IF at the time of VMRUN. + * Requesting an interrupt window if save.RFLAGS.IF=0 is pointless as + * interrupts will never be unblocked while L2 is running. + */ + if (!svm_is_intercept(svm, INTERCEPT_VINTR)) + return; + + /* + * This is just a dummy VINTR to actually cause a vmexit to happen. + * Actual injection of virtual interrupts happens through EVENTINJ. + */ + control = &svm->vmcb->control; + control->int_vector = 0x0; + control->int_ctl &= ~V_INTR_PRIO_MASK; + control->int_ctl |= V_IRQ_MASK | + ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); + vmcb_mark_dirty(svm->vmcb, VMCB_INTR); +} + +static void svm_clear_vintr(struct vcpu_svm *svm) +{ + svm_clr_intercept(svm, INTERCEPT_VINTR); + + /* Drop int_ctl fields related to VINTR injection. */ + svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK; + if (is_guest_mode(&svm->vcpu)) { + svm->vmcb01.ptr->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK; + + WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) != + (svm->nested.ctl.int_ctl & V_TPR_MASK)); + + svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & + V_IRQ_INJECTION_BITS_MASK; + + svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; + } + + vmcb_mark_dirty(svm->vmcb, VMCB_INTR); +} + +static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) +{ + struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; + struct vmcb_save_area *save01 = &to_svm(vcpu)->vmcb01.ptr->save; + + switch (seg) { + case VCPU_SREG_CS: return &save->cs; + case VCPU_SREG_DS: return &save->ds; + case VCPU_SREG_ES: return &save->es; + case VCPU_SREG_FS: return &save01->fs; + case VCPU_SREG_GS: return &save01->gs; + case VCPU_SREG_SS: return &save->ss; + case VCPU_SREG_TR: return &save01->tr; + case VCPU_SREG_LDTR: return &save01->ldtr; + } + BUG(); + return NULL; +} + +static u64 svm_get_segment_base(struct kvm_vcpu *vcpu, int seg) +{ + struct vmcb_seg *s = svm_seg(vcpu, seg); + + return s->base; +} + +static void svm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct vmcb_seg *s = svm_seg(vcpu, seg); + + var->base = s->base; + var->limit = s->limit; + var->selector = s->selector; + var->type = s->attrib & SVM_SELECTOR_TYPE_MASK; + var->s = (s->attrib >> SVM_SELECTOR_S_SHIFT) & 1; + var->dpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; + var->present = (s->attrib >> SVM_SELECTOR_P_SHIFT) & 1; + var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1; + var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1; + var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; + + /* + * AMD CPUs circa 2014 track the G bit for all segments except CS. + * However, the SVM spec states that the G bit is not observed by the + * CPU, and some VMware virtual CPUs drop the G bit for all segments. + * So let's synthesize a legal G bit for all segments, this helps + * running KVM nested. It also helps cross-vendor migration, because + * Intel's vmentry has a check on the 'G' bit. + */ + var->g = s->limit > 0xfffff; + + /* + * AMD's VMCB does not have an explicit unusable field, so emulate it + * for cross vendor migration purposes by "not present" + */ + var->unusable = !var->present; + + switch (seg) { + case VCPU_SREG_TR: + /* + * Work around a bug where the busy flag in the tr selector + * isn't exposed + */ + var->type |= 0x2; + break; + case VCPU_SREG_DS: + case VCPU_SREG_ES: + case VCPU_SREG_FS: + case VCPU_SREG_GS: + /* + * The accessed bit must always be set in the segment + * descriptor cache, although it can be cleared in the + * descriptor, the cached bit always remains at 1. Since + * Intel has a check on this, set it here to support + * cross-vendor migration. + */ + if (!var->unusable) + var->type |= 0x1; + break; + case VCPU_SREG_SS: + /* + * On AMD CPUs sometimes the DB bit in the segment + * descriptor is left as 1, although the whole segment has + * been made unusable. Clear it here to pass an Intel VMX + * entry check when cross vendor migrating. + */ + if (var->unusable) + var->db = 0; + /* This is symmetric with svm_set_segment() */ + var->dpl = to_svm(vcpu)->vmcb->save.cpl; + break; + } +} + +static int svm_get_cpl(struct kvm_vcpu *vcpu) +{ + struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; + + return save->cpl; +} + +static void svm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) +{ + struct kvm_segment cs; + + svm_get_segment(vcpu, &cs, VCPU_SREG_CS); + *db = cs.db; + *l = cs.l; +} + +static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + dt->size = svm->vmcb->save.idtr.limit; + dt->address = svm->vmcb->save.idtr.base; +} + +static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.idtr.limit = dt->size; + svm->vmcb->save.idtr.base = dt->address ; + vmcb_mark_dirty(svm->vmcb, VMCB_DT); +} + +static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + dt->size = svm->vmcb->save.gdtr.limit; + dt->address = svm->vmcb->save.gdtr.base; +} + +static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.gdtr.limit = dt->size; + svm->vmcb->save.gdtr.base = dt->address ; + vmcb_mark_dirty(svm->vmcb, VMCB_DT); +} + +static void sev_post_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * For guests that don't set guest_state_protected, the cr3 update is + * handled via kvm_mmu_load() while entering the guest. For guests + * that do (SEV-ES/SEV-SNP), the cr3 update needs to be written to + * VMCB save area now, since the save area will become the initial + * contents of the VMSA, and future VMCB save area updates won't be + * seen. + */ + if (sev_es_guest(vcpu->kvm)) { + svm->vmcb->save.cr3 = cr3; + vmcb_mark_dirty(svm->vmcb, VMCB_CR); + } +} + +static bool svm_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + return true; +} + +void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 hcr0 = cr0; + bool old_paging = is_paging(vcpu); + +#ifdef CONFIG_X86_64 + if (vcpu->arch.efer & EFER_LME) { + if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { + vcpu->arch.efer |= EFER_LMA; + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer |= EFER_LMA | EFER_LME; + } + + if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) { + vcpu->arch.efer &= ~EFER_LMA; + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); + } + } +#endif + vcpu->arch.cr0 = cr0; + + if (!npt_enabled) { + hcr0 |= X86_CR0_PG | X86_CR0_WP; + if (old_paging != is_paging(vcpu)) + svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); + } + + /* + * re-enable caching here because the QEMU bios + * does not do it - this results in some delay at + * reboot + */ + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + hcr0 &= ~(X86_CR0_CD | X86_CR0_NW); + + svm->vmcb->save.cr0 = hcr0; + vmcb_mark_dirty(svm->vmcb, VMCB_CR); + + /* + * SEV-ES guests must always keep the CR intercepts cleared. CR + * tracking is done using the CR write traps. + */ + if (sev_es_guest(vcpu->kvm)) + return; + + if (hcr0 == cr0) { + /* Selective CR0 write remains on. */ + svm_clr_intercept(svm, INTERCEPT_CR0_READ); + svm_clr_intercept(svm, INTERCEPT_CR0_WRITE); + } else { + svm_set_intercept(svm, INTERCEPT_CR0_READ); + svm_set_intercept(svm, INTERCEPT_CR0_WRITE); + } +} + +static bool svm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + return true; +} + +void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE; + unsigned long old_cr4 = vcpu->arch.cr4; + + if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) + svm_flush_tlb_current(vcpu); + + vcpu->arch.cr4 = cr4; + if (!npt_enabled) { + cr4 |= X86_CR4_PAE; + + if (!is_paging(vcpu)) + cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); + } + cr4 |= host_cr4_mce; + to_svm(vcpu)->vmcb->save.cr4 = cr4; + vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); + + if ((cr4 ^ old_cr4) & (X86_CR4_OSXSAVE | X86_CR4_PKE)) + kvm_update_cpuid_runtime(vcpu); +} + +static void svm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_seg *s = svm_seg(vcpu, seg); + + s->base = var->base; + s->limit = var->limit; + s->selector = var->selector; + s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); + s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; + s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; + s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT; + s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; + s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; + s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; + s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; + + /* + * This is always accurate, except if SYSRET returned to a segment + * with SS.DPL != 3. Intel does not have this quirk, and always + * forces SS.DPL to 3 on sysret, so we ignore that case; fixing it + * would entail passing the CPL to userspace and back. + */ + if (seg == VCPU_SREG_SS) + /* This is symmetric with svm_get_segment() */ + svm->vmcb->save.cpl = (var->dpl & 3); + + vmcb_mark_dirty(svm->vmcb, VMCB_SEG); +} + +static void svm_update_exception_bitmap(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + clr_exception_intercept(svm, BP_VECTOR); + + if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + set_exception_intercept(svm, BP_VECTOR); + } +} + +static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) +{ + if (sd->next_asid > sd->max_asid) { + ++sd->asid_generation; + sd->next_asid = sd->min_asid; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; + vmcb_mark_dirty(svm->vmcb, VMCB_ASID); + } + + svm->current_vmcb->asid_generation = sd->asid_generation; + svm->asid = sd->next_asid++; +} + +static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value) +{ + struct vmcb *vmcb = svm->vmcb; + + if (svm->vcpu.arch.guest_state_protected) + return; + + if (unlikely(value != vmcb->save.dr6)) { + vmcb->save.dr6 = value; + vmcb_mark_dirty(vmcb, VMCB_DR); + } +} + +static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (WARN_ON_ONCE(sev_es_guest(vcpu->kvm))) + return; + + get_debugreg(vcpu->arch.db[0], 0); + get_debugreg(vcpu->arch.db[1], 1); + get_debugreg(vcpu->arch.db[2], 2); + get_debugreg(vcpu->arch.db[3], 3); + /* + * We cannot reset svm->vmcb->save.dr6 to DR6_ACTIVE_LOW here, + * because db_interception might need it. We can do it before vmentry. + */ + vcpu->arch.dr6 = svm->vmcb->save.dr6; + vcpu->arch.dr7 = svm->vmcb->save.dr7; + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; + set_dr_intercepts(svm); +} + +static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (vcpu->arch.guest_state_protected) + return; + + svm->vmcb->save.dr7 = value; + vmcb_mark_dirty(svm->vmcb, VMCB_DR); +} + +static int pf_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + u64 fault_address = svm->vmcb->control.exit_info_2; + u64 error_code = svm->vmcb->control.exit_info_1; + + return kvm_handle_page_fault(vcpu, error_code, fault_address, + static_cpu_has(X86_FEATURE_DECODEASSISTS) ? + svm->vmcb->control.insn_bytes : NULL, + svm->vmcb->control.insn_len); +} + +static int npf_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + u64 fault_address = svm->vmcb->control.exit_info_2; + u64 error_code = svm->vmcb->control.exit_info_1; + + trace_kvm_page_fault(vcpu, fault_address, error_code); + return kvm_mmu_page_fault(vcpu, fault_address, error_code, + static_cpu_has(X86_FEATURE_DECODEASSISTS) ? + svm->vmcb->control.insn_bytes : NULL, + svm->vmcb->control.insn_len); +} + +static int db_interception(struct kvm_vcpu *vcpu) +{ + struct kvm_run *kvm_run = vcpu->run; + struct vcpu_svm *svm = to_svm(vcpu); + + if (!(vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && + !svm->nmi_singlestep) { + u32 payload = svm->vmcb->save.dr6 ^ DR6_ACTIVE_LOW; + kvm_queue_exception_p(vcpu, DB_VECTOR, payload); + return 1; + } + + if (svm->nmi_singlestep) { + disable_nmi_singlestep(svm); + /* Make sure we check for pending NMIs upon entry */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { + kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6; + kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7; + kvm_run->debug.arch.pc = + svm->vmcb->save.cs.base + svm->vmcb->save.rip; + kvm_run->debug.arch.exception = DB_VECTOR; + return 0; + } + + return 1; +} + +static int bp_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_run *kvm_run = vcpu->run; + + kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; + kvm_run->debug.arch.exception = BP_VECTOR; + return 0; +} + +static int ud_interception(struct kvm_vcpu *vcpu) +{ + return handle_ud(vcpu); +} + +static int ac_interception(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception_e(vcpu, AC_VECTOR, 0); + return 1; +} + +static bool is_erratum_383(void) +{ + int err, i; + u64 value; + + if (!erratum_383_found) + return false; + + value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err); + if (err) + return false; + + /* Bit 62 may or may not be set for this mce */ + value &= ~(1ULL << 62); + + if (value != 0xb600000000010015ULL) + return false; + + /* Clear MCi_STATUS registers */ + for (i = 0; i < 6; ++i) + native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0); + + value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err); + if (!err) { + u32 low, high; + + value &= ~(1ULL << 2); + low = lower_32_bits(value); + high = upper_32_bits(value); + + native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high); + } + + /* Flush tlb to evict multi-match entries */ + __flush_tlb_all(); + + return true; +} + +static void svm_handle_mce(struct kvm_vcpu *vcpu) +{ + if (is_erratum_383()) { + /* + * Erratum 383 triggered. Guest state is corrupt so kill the + * guest. + */ + pr_err("Guest triggered AMD Erratum 383\n"); + + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + + return; + } + + /* + * On an #MC intercept the MCE handler is not called automatically in + * the host. So do it by hand here. + */ + kvm_machine_check(); +} + +static int mc_interception(struct kvm_vcpu *vcpu) +{ + return 1; +} + +static int shutdown_interception(struct kvm_vcpu *vcpu) +{ + struct kvm_run *kvm_run = vcpu->run; + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * The VM save area has already been encrypted so it + * cannot be reinitialized - just terminate. + */ + if (sev_es_guest(vcpu->kvm)) + return -EINVAL; + + /* + * VMCB is undefined after a SHUTDOWN intercept. INIT the vCPU to put + * the VMCB in a known good state. Unfortuately, KVM doesn't have + * KVM_MP_STATE_SHUTDOWN and can't add it without potentially breaking + * userspace. At a platform view, INIT is acceptable behavior as + * there exist bare metal platforms that automatically INIT the CPU + * in response to shutdown. + */ + clear_page(svm->vmcb); + kvm_vcpu_reset(vcpu, true); + + kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + return 0; +} + +static int io_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ + int size, in, string; + unsigned port; + + ++vcpu->stat.io_exits; + string = (io_info & SVM_IOIO_STR_MASK) != 0; + in = (io_info & SVM_IOIO_TYPE_MASK) != 0; + port = io_info >> 16; + size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; + + if (string) { + if (sev_es_guest(vcpu->kvm)) + return sev_es_string_io(svm, size, port, in); + else + return kvm_emulate_instruction(vcpu, 0); + } + + svm->next_rip = svm->vmcb->control.exit_info_2; + + return kvm_fast_pio(vcpu, size, port, in); +} + +static int nmi_interception(struct kvm_vcpu *vcpu) +{ + return 1; +} + +static int smi_interception(struct kvm_vcpu *vcpu) +{ + return 1; +} + +static int intr_interception(struct kvm_vcpu *vcpu) +{ + ++vcpu->stat.irq_exits; + return 1; +} + +static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb12; + struct kvm_host_map map; + int ret; + + if (nested_svm_check_permissions(vcpu)) + return 1; + + ret = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map); + if (ret) { + if (ret == -EINVAL) + kvm_inject_gp(vcpu, 0); + return 1; + } + + vmcb12 = map.hva; + + ret = kvm_skip_emulated_instruction(vcpu); + + if (vmload) { + svm_copy_vmloadsave_state(svm->vmcb, vmcb12); + svm->sysenter_eip_hi = 0; + svm->sysenter_esp_hi = 0; + } else { + svm_copy_vmloadsave_state(vmcb12, svm->vmcb); + } + + kvm_vcpu_unmap(vcpu, &map, true); + + return ret; +} + +static int vmload_interception(struct kvm_vcpu *vcpu) +{ + return vmload_vmsave_interception(vcpu, true); +} + +static int vmsave_interception(struct kvm_vcpu *vcpu) +{ + return vmload_vmsave_interception(vcpu, false); +} + +static int vmrun_interception(struct kvm_vcpu *vcpu) +{ + if (nested_svm_check_permissions(vcpu)) + return 1; + + return nested_svm_vmrun(vcpu); +} + +enum { + NONE_SVM_INSTR, + SVM_INSTR_VMRUN, + SVM_INSTR_VMLOAD, + SVM_INSTR_VMSAVE, +}; + +/* Return NONE_SVM_INSTR if not SVM instrs, otherwise return decode result */ +static int svm_instr_opcode(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + + if (ctxt->b != 0x1 || ctxt->opcode_len != 2) + return NONE_SVM_INSTR; + + switch (ctxt->modrm) { + case 0xd8: /* VMRUN */ + return SVM_INSTR_VMRUN; + case 0xda: /* VMLOAD */ + return SVM_INSTR_VMLOAD; + case 0xdb: /* VMSAVE */ + return SVM_INSTR_VMSAVE; + default: + break; + } + + return NONE_SVM_INSTR; +} + +static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode) +{ + const int guest_mode_exit_codes[] = { + [SVM_INSTR_VMRUN] = SVM_EXIT_VMRUN, + [SVM_INSTR_VMLOAD] = SVM_EXIT_VMLOAD, + [SVM_INSTR_VMSAVE] = SVM_EXIT_VMSAVE, + }; + int (*const svm_instr_handlers[])(struct kvm_vcpu *vcpu) = { + [SVM_INSTR_VMRUN] = vmrun_interception, + [SVM_INSTR_VMLOAD] = vmload_interception, + [SVM_INSTR_VMSAVE] = vmsave_interception, + }; + struct vcpu_svm *svm = to_svm(vcpu); + int ret; + + if (is_guest_mode(vcpu)) { + /* Returns '1' or -errno on failure, '0' on success. */ + ret = nested_svm_simple_vmexit(svm, guest_mode_exit_codes[opcode]); + if (ret) + return ret; + return 1; + } + return svm_instr_handlers[opcode](vcpu); +} + +/* + * #GP handling code. Note that #GP can be triggered under the following two + * cases: + * 1) SVM VM-related instructions (VMRUN/VMSAVE/VMLOAD) that trigger #GP on + * some AMD CPUs when EAX of these instructions are in the reserved memory + * regions (e.g. SMM memory on host). + * 2) VMware backdoor + */ +static int gp_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 error_code = svm->vmcb->control.exit_info_1; + int opcode; + + /* Both #GP cases have zero error_code */ + if (error_code) + goto reinject; + + /* Decode the instruction for usage later */ + if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) + goto reinject; + + opcode = svm_instr_opcode(vcpu); + + if (opcode == NONE_SVM_INSTR) { + if (!enable_vmware_backdoor) + goto reinject; + + /* + * VMware backdoor emulation on #GP interception only handles + * IN{S}, OUT{S}, and RDPMC. + */ + if (!is_guest_mode(vcpu)) + return kvm_emulate_instruction(vcpu, + EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE); + } else { + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + + return emulate_svm_instr(vcpu, opcode); + } + +reinject: + kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); + return 1; +} + +void svm_set_gif(struct vcpu_svm *svm, bool value) +{ + if (value) { + /* + * If VGIF is enabled, the STGI intercept is only added to + * detect the opening of the SMI/NMI window; remove it now. + * Likewise, clear the VINTR intercept, we will set it + * again while processing KVM_REQ_EVENT if needed. + */ + if (vgif) + svm_clr_intercept(svm, INTERCEPT_STGI); + if (svm_is_intercept(svm, INTERCEPT_VINTR)) + svm_clear_vintr(svm); + + enable_gif(svm); + if (svm->vcpu.arch.smi_pending || + svm->vcpu.arch.nmi_pending || + kvm_cpu_has_injectable_intr(&svm->vcpu) || + kvm_apic_has_pending_init_or_sipi(&svm->vcpu)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + } else { + disable_gif(svm); + + /* + * After a CLGI no interrupts should come. But if vGIF is + * in use, we still rely on the VINTR intercept (rather than + * STGI) to detect an open interrupt window. + */ + if (!vgif) + svm_clear_vintr(svm); + } +} + +static int stgi_interception(struct kvm_vcpu *vcpu) +{ + int ret; + + if (nested_svm_check_permissions(vcpu)) + return 1; + + ret = kvm_skip_emulated_instruction(vcpu); + svm_set_gif(to_svm(vcpu), true); + return ret; +} + +static int clgi_interception(struct kvm_vcpu *vcpu) +{ + int ret; + + if (nested_svm_check_permissions(vcpu)) + return 1; + + ret = kvm_skip_emulated_instruction(vcpu); + svm_set_gif(to_svm(vcpu), false); + return ret; +} + +static int invlpga_interception(struct kvm_vcpu *vcpu) +{ + gva_t gva = kvm_rax_read(vcpu); + u32 asid = kvm_rcx_read(vcpu); + + /* FIXME: Handle an address size prefix. */ + if (!is_long_mode(vcpu)) + gva = (u32)gva; + + trace_kvm_invlpga(to_svm(vcpu)->vmcb->save.rip, asid, gva); + + /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ + kvm_mmu_invlpg(vcpu, gva); + + return kvm_skip_emulated_instruction(vcpu); +} + +static int skinit_interception(struct kvm_vcpu *vcpu) +{ + trace_kvm_skinit(to_svm(vcpu)->vmcb->save.rip, kvm_rax_read(vcpu)); + + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + +static int task_switch_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u16 tss_selector; + int reason; + int int_type = svm->vmcb->control.exit_int_info & + SVM_EXITINTINFO_TYPE_MASK; + int int_vec = svm->vmcb->control.exit_int_info & SVM_EVTINJ_VEC_MASK; + uint32_t type = + svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK; + uint32_t idt_v = + svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID; + bool has_error_code = false; + u32 error_code = 0; + + tss_selector = (u16)svm->vmcb->control.exit_info_1; + + if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_REASON_IRET)) + reason = TASK_SWITCH_IRET; + else if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_REASON_JMP)) + reason = TASK_SWITCH_JMP; + else if (idt_v) + reason = TASK_SWITCH_GATE; + else + reason = TASK_SWITCH_CALL; + + if (reason == TASK_SWITCH_GATE) { + switch (type) { + case SVM_EXITINTINFO_TYPE_NMI: + vcpu->arch.nmi_injected = false; + break; + case SVM_EXITINTINFO_TYPE_EXEPT: + if (svm->vmcb->control.exit_info_2 & + (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) { + has_error_code = true; + error_code = + (u32)svm->vmcb->control.exit_info_2; + } + kvm_clear_exception_queue(vcpu); + break; + case SVM_EXITINTINFO_TYPE_INTR: + case SVM_EXITINTINFO_TYPE_SOFT: + kvm_clear_interrupt_queue(vcpu); + break; + default: + break; + } + } + + if (reason != TASK_SWITCH_GATE || + int_type == SVM_EXITINTINFO_TYPE_SOFT || + (int_type == SVM_EXITINTINFO_TYPE_EXEPT && + (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) { + if (!svm_skip_emulated_instruction(vcpu)) + return 0; + } + + if (int_type != SVM_EXITINTINFO_TYPE_SOFT) + int_vec = -1; + + return kvm_task_switch(vcpu, tss_selector, int_vec, reason, + has_error_code, error_code); +} + +static void svm_clr_iret_intercept(struct vcpu_svm *svm) +{ + if (!sev_es_guest(svm->vcpu.kvm)) + svm_clr_intercept(svm, INTERCEPT_IRET); +} + +static void svm_set_iret_intercept(struct vcpu_svm *svm) +{ + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_IRET); +} + +static int iret_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + WARN_ON_ONCE(sev_es_guest(vcpu->kvm)); + + ++vcpu->stat.nmi_window_exits; + svm->awaiting_iret_completion = true; + + svm_clr_iret_intercept(svm); + svm->nmi_iret_rip = kvm_rip_read(vcpu); + + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 1; +} + +static int invlpg_interception(struct kvm_vcpu *vcpu) +{ + if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) + return kvm_emulate_instruction(vcpu, 0); + + kvm_mmu_invlpg(vcpu, to_svm(vcpu)->vmcb->control.exit_info_1); + return kvm_skip_emulated_instruction(vcpu); +} + +static int emulate_on_interception(struct kvm_vcpu *vcpu) +{ + return kvm_emulate_instruction(vcpu, 0); +} + +static int rsm_interception(struct kvm_vcpu *vcpu) +{ + return kvm_emulate_instruction_from_buffer(vcpu, rsm_ins_bytes, 2); +} + +static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu, + unsigned long val) +{ + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long cr0 = vcpu->arch.cr0; + bool ret = false; + + if (!is_guest_mode(vcpu) || + (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) + return false; + + cr0 &= ~SVM_CR0_SELECTIVE_MASK; + val &= ~SVM_CR0_SELECTIVE_MASK; + + if (cr0 ^ val) { + svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; + ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE); + } + + return ret; +} + +#define CR_VALID (1ULL << 63) + +static int cr_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int reg, cr; + unsigned long val; + int err; + + if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) + return emulate_on_interception(vcpu); + + if (unlikely((svm->vmcb->control.exit_info_1 & CR_VALID) == 0)) + return emulate_on_interception(vcpu); + + reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; + if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE) + cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0; + else + cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; + + err = 0; + if (cr >= 16) { /* mov to cr */ + cr -= 16; + val = kvm_register_read(vcpu, reg); + trace_kvm_cr_write(cr, val); + switch (cr) { + case 0: + if (!check_selective_cr0_intercepted(vcpu, val)) + err = kvm_set_cr0(vcpu, val); + else + return 1; + + break; + case 3: + err = kvm_set_cr3(vcpu, val); + break; + case 4: + err = kvm_set_cr4(vcpu, val); + break; + case 8: + err = kvm_set_cr8(vcpu, val); + break; + default: + WARN(1, "unhandled write to CR%d", cr); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + } else { /* mov from cr */ + switch (cr) { + case 0: + val = kvm_read_cr0(vcpu); + break; + case 2: + val = vcpu->arch.cr2; + break; + case 3: + val = kvm_read_cr3(vcpu); + break; + case 4: + val = kvm_read_cr4(vcpu); + break; + case 8: + val = kvm_get_cr8(vcpu); + break; + default: + WARN(1, "unhandled read from CR%d", cr); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + kvm_register_write(vcpu, reg, val); + trace_kvm_cr_read(cr, val); + } + return kvm_complete_insn_gp(vcpu, err); +} + +static int cr_trap(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long old_value, new_value; + unsigned int cr; + int ret = 0; + + new_value = (unsigned long)svm->vmcb->control.exit_info_1; + + cr = svm->vmcb->control.exit_code - SVM_EXIT_CR0_WRITE_TRAP; + switch (cr) { + case 0: + old_value = kvm_read_cr0(vcpu); + svm_set_cr0(vcpu, new_value); + + kvm_post_set_cr0(vcpu, old_value, new_value); + break; + case 4: + old_value = kvm_read_cr4(vcpu); + svm_set_cr4(vcpu, new_value); + + kvm_post_set_cr4(vcpu, old_value, new_value); + break; + case 8: + ret = kvm_set_cr8(vcpu, new_value); + break; + default: + WARN(1, "unhandled CR%d write trap", cr); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + return kvm_complete_insn_gp(vcpu, ret); +} + +static int dr_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int reg, dr; + unsigned long val; + int err = 0; + + /* + * SEV-ES intercepts DR7 only to disable guest debugging and the guest issues a VMGEXIT + * for DR7 write only. KVM cannot change DR7 (always swapped as type 'A') so return early. + */ + if (sev_es_guest(vcpu->kvm)) + return 1; + + if (vcpu->guest_debug == 0) { + /* + * No more DR vmexits; force a reload of the debug registers + * and reenter on this instruction. The next vmexit will + * retrieve the full state of the debug registers. + */ + clr_dr_intercepts(svm); + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; + return 1; + } + + if (!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) + return emulate_on_interception(vcpu); + + reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; + dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0; + if (dr >= 16) { /* mov to DRn */ + dr -= 16; + val = kvm_register_read(vcpu, reg); + err = kvm_set_dr(vcpu, dr, val); + } else { + kvm_get_dr(vcpu, dr, &val); + kvm_register_write(vcpu, reg, val); + } + + return kvm_complete_insn_gp(vcpu, err); +} + +static int cr8_write_interception(struct kvm_vcpu *vcpu) +{ + int r; + + u8 cr8_prev = kvm_get_cr8(vcpu); + /* instruction emulation calls kvm_set_cr8() */ + r = cr_interception(vcpu); + if (lapic_in_kernel(vcpu)) + return r; + if (cr8_prev <= kvm_get_cr8(vcpu)) + return r; + vcpu->run->exit_reason = KVM_EXIT_SET_TPR; + return 0; +} + +static int efer_trap(struct kvm_vcpu *vcpu) +{ + struct msr_data msr_info; + int ret; + + /* + * Clear the EFER_SVME bit from EFER. The SVM code always sets this + * bit in svm_set_efer(), but __kvm_valid_efer() checks it against + * whether the guest has X86_FEATURE_SVM - this avoids a failure if + * the guest doesn't have X86_FEATURE_SVM. + */ + msr_info.host_initiated = false; + msr_info.index = MSR_EFER; + msr_info.data = to_svm(vcpu)->vmcb->control.exit_info_1 & ~EFER_SVME; + ret = kvm_set_msr_common(vcpu, &msr_info); + + return kvm_complete_insn_gp(vcpu, ret); +} + +static int svm_get_msr_feature(struct kvm_msr_entry *msr) +{ + msr->data = 0; + + switch (msr->index) { + case MSR_AMD64_DE_CFG: + if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) + msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; + break; + default: + return KVM_MSR_RET_INVALID; + } + + return 0; +} + +static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + switch (msr_info->index) { + case MSR_AMD64_TSC_RATIO: + if (!msr_info->host_initiated && + !guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) + return 1; + msr_info->data = svm->tsc_ratio_msr; + break; + case MSR_STAR: + msr_info->data = svm->vmcb01.ptr->save.star; + break; +#ifdef CONFIG_X86_64 + case MSR_LSTAR: + msr_info->data = svm->vmcb01.ptr->save.lstar; + break; + case MSR_CSTAR: + msr_info->data = svm->vmcb01.ptr->save.cstar; + break; + case MSR_KERNEL_GS_BASE: + msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base; + break; + case MSR_SYSCALL_MASK: + msr_info->data = svm->vmcb01.ptr->save.sfmask; + break; +#endif + case MSR_IA32_SYSENTER_CS: + msr_info->data = svm->vmcb01.ptr->save.sysenter_cs; + break; + case MSR_IA32_SYSENTER_EIP: + msr_info->data = (u32)svm->vmcb01.ptr->save.sysenter_eip; + if (guest_cpuid_is_intel(vcpu)) + msr_info->data |= (u64)svm->sysenter_eip_hi << 32; + break; + case MSR_IA32_SYSENTER_ESP: + msr_info->data = svm->vmcb01.ptr->save.sysenter_esp; + if (guest_cpuid_is_intel(vcpu)) + msr_info->data |= (u64)svm->sysenter_esp_hi << 32; + break; + case MSR_TSC_AUX: + msr_info->data = svm->tsc_aux; + break; + case MSR_IA32_DEBUGCTLMSR: + msr_info->data = svm_get_lbr_vmcb(svm)->save.dbgctl; + break; + case MSR_IA32_LASTBRANCHFROMIP: + msr_info->data = svm_get_lbr_vmcb(svm)->save.br_from; + break; + case MSR_IA32_LASTBRANCHTOIP: + msr_info->data = svm_get_lbr_vmcb(svm)->save.br_to; + break; + case MSR_IA32_LASTINTFROMIP: + msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_from; + break; + case MSR_IA32_LASTINTTOIP: + msr_info->data = svm_get_lbr_vmcb(svm)->save.last_excp_to; + break; + case MSR_VM_HSAVE_PA: + msr_info->data = svm->nested.hsave_msr; + break; + case MSR_VM_CR: + msr_info->data = svm->nested.vm_cr_msr; + break; + case MSR_IA32_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_has_spec_ctrl_msr(vcpu)) + return 1; + + if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + msr_info->data = svm->vmcb->save.spec_ctrl; + else + msr_info->data = svm->spec_ctrl; + break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + msr_info->data = svm->virt_spec_ctrl; + break; + case MSR_F15H_IC_CFG: { + + int family, model; + + family = guest_cpuid_family(vcpu); + model = guest_cpuid_model(vcpu); + + if (family < 0 || model < 0) + return kvm_get_msr_common(vcpu, msr_info); + + msr_info->data = 0; + + if (family == 0x15 && + (model >= 0x2 && model < 0x20)) + msr_info->data = 0x1E; + } + break; + case MSR_AMD64_DE_CFG: + msr_info->data = svm->msr_decfg; + break; + default: + return kvm_get_msr_common(vcpu, msr_info); + } + return 0; +} + +static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) +{ + struct vcpu_svm *svm = to_svm(vcpu); + if (!err || !sev_es_guest(vcpu->kvm) || WARN_ON_ONCE(!svm->sev_es.ghcb)) + return kvm_complete_insn_gp(vcpu, err); + + ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 1); + ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, + X86_TRAP_GP | + SVM_EVTINJ_TYPE_EXEPT | + SVM_EVTINJ_VALID); + return 1; +} + +static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int svm_dis, chg_mask; + + if (data & ~SVM_VM_CR_VALID_MASK) + return 1; + + chg_mask = SVM_VM_CR_VALID_MASK; + + if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK) + chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK); + + svm->nested.vm_cr_msr &= ~chg_mask; + svm->nested.vm_cr_msr |= (data & chg_mask); + + svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK; + + /* check for svm_disable while efer.svme is set */ + if (svm_dis && (vcpu->arch.efer & EFER_SVME)) + return 1; + + return 0; +} + +static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int ret = 0; + + u32 ecx = msr->index; + u64 data = msr->data; + switch (ecx) { + case MSR_AMD64_TSC_RATIO: + + if (!guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) { + + if (!msr->host_initiated) + return 1; + /* + * In case TSC scaling is not enabled, always + * leave this MSR at the default value. + * + * Due to bug in qemu 6.2.0, it would try to set + * this msr to 0 if tsc scaling is not enabled. + * Ignore this value as well. + */ + if (data != 0 && data != svm->tsc_ratio_msr) + return 1; + break; + } + + if (data & SVM_TSC_RATIO_RSVD) + return 1; + + svm->tsc_ratio_msr = data; + + if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + is_guest_mode(vcpu)) + nested_svm_update_tsc_ratio_msr(vcpu); + + break; + case MSR_IA32_CR_PAT: + ret = kvm_set_msr_common(vcpu, msr); + if (ret) + break; + + svm->vmcb01.ptr->save.g_pat = data; + if (is_guest_mode(vcpu)) + nested_vmcb02_compute_g_pat(svm); + vmcb_mark_dirty(svm->vmcb, VMCB_NPT); + break; + case MSR_IA32_SPEC_CTRL: + if (!msr->host_initiated && + !guest_has_spec_ctrl_msr(vcpu)) + return 1; + + if (kvm_spec_ctrl_test_value(data)) + return 1; + + if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + svm->vmcb->save.spec_ctrl = data; + else + svm->spec_ctrl = data; + if (!data) + break; + + /* + * For non-nested: + * When it's written (to non-zero) for the first time, pass + * it through. + * + * For nested: + * The handling of the MSR bitmap for L2 guests is done in + * nested_svm_vmrun_msrpm. + * We update the L1 MSR bit as well since it will end up + * touching the MSR anyway now. + */ + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); + break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + if (data & ~SPEC_CTRL_SSBD) + return 1; + + svm->virt_spec_ctrl = data; + break; + case MSR_STAR: + svm->vmcb01.ptr->save.star = data; + break; +#ifdef CONFIG_X86_64 + case MSR_LSTAR: + svm->vmcb01.ptr->save.lstar = data; + break; + case MSR_CSTAR: + svm->vmcb01.ptr->save.cstar = data; + break; + case MSR_KERNEL_GS_BASE: + svm->vmcb01.ptr->save.kernel_gs_base = data; + break; + case MSR_SYSCALL_MASK: + svm->vmcb01.ptr->save.sfmask = data; + break; +#endif + case MSR_IA32_SYSENTER_CS: + svm->vmcb01.ptr->save.sysenter_cs = data; + break; + case MSR_IA32_SYSENTER_EIP: + svm->vmcb01.ptr->save.sysenter_eip = (u32)data; + /* + * We only intercept the MSR_IA32_SYSENTER_{EIP|ESP} msrs + * when we spoof an Intel vendor ID (for cross vendor migration). + * In this case we use this intercept to track the high + * 32 bit part of these msrs to support Intel's + * implementation of SYSENTER/SYSEXIT. + */ + svm->sysenter_eip_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0; + break; + case MSR_IA32_SYSENTER_ESP: + svm->vmcb01.ptr->save.sysenter_esp = (u32)data; + svm->sysenter_esp_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0; + break; + case MSR_TSC_AUX: + /* + * TSC_AUX is always virtualized for SEV-ES guests when the + * feature is available. The user return MSR support is not + * required in this case because TSC_AUX is restored on #VMEXIT + * from the host save area (which has been initialized in + * svm_hardware_enable()). + */ + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm)) + break; + + /* + * TSC_AUX is usually changed only during boot and never read + * directly. Intercept TSC_AUX instead of exposing it to the + * guest via direct_access_msrs, and switch it via user return. + */ + preempt_disable(); + ret = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); + preempt_enable(); + if (ret) + break; + + svm->tsc_aux = data; + break; + case MSR_IA32_DEBUGCTLMSR: + if (!lbrv) { + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); + break; + } + if (data & DEBUGCTL_RESERVED_BITS) + return 1; + + svm_get_lbr_vmcb(svm)->save.dbgctl = data; + svm_update_lbrv(vcpu); + break; + case MSR_VM_HSAVE_PA: + /* + * Old kernels did not validate the value written to + * MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid + * value to allow live migrating buggy or malicious guests + * originating from those kernels. + */ + if (!msr->host_initiated && !page_address_valid(vcpu, data)) + return 1; + + svm->nested.hsave_msr = data & PAGE_MASK; + break; + case MSR_VM_CR: + return svm_set_vm_cr(vcpu, data); + case MSR_VM_IGNNE: + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); + break; + case MSR_AMD64_DE_CFG: { + struct kvm_msr_entry msr_entry; + + msr_entry.index = msr->index; + if (svm_get_msr_feature(&msr_entry)) + return 1; + + /* Check the supported bits */ + if (data & ~msr_entry.data) + return 1; + + /* Don't allow the guest to change a bit, #GP */ + if (!msr->host_initiated && (data ^ msr_entry.data)) + return 1; + + svm->msr_decfg = data; + break; + } + default: + return kvm_set_msr_common(vcpu, msr); + } + return ret; +} + +static int msr_interception(struct kvm_vcpu *vcpu) +{ + if (to_svm(vcpu)->vmcb->control.exit_info_1) + return kvm_emulate_wrmsr(vcpu); + else + return kvm_emulate_rdmsr(vcpu); +} + +static int interrupt_window_interception(struct kvm_vcpu *vcpu) +{ + kvm_make_request(KVM_REQ_EVENT, vcpu); + svm_clear_vintr(to_svm(vcpu)); + + /* + * If not running nested, for AVIC, the only reason to end up here is ExtINTs. + * In this case AVIC was temporarily disabled for + * requesting the IRQ window and we have to re-enable it. + * + * If running nested, still remove the VM wide AVIC inhibit to + * support case in which the interrupt window was requested when the + * vCPU was not running nested. + + * All vCPUs which run still run nested, will remain to have their + * AVIC still inhibited due to per-cpu AVIC inhibition. + */ + kvm_clear_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN); + + ++vcpu->stat.irq_window_exits; + return 1; +} + +static int pause_interception(struct kvm_vcpu *vcpu) +{ + bool in_kernel; + /* + * CPL is not made available for an SEV-ES guest, therefore + * vcpu->arch.preempted_in_kernel can never be true. Just + * set in_kernel to false as well. + */ + in_kernel = !sev_es_guest(vcpu->kvm) && svm_get_cpl(vcpu) == 0; + + grow_ple_window(vcpu); + + kvm_vcpu_on_spin(vcpu, in_kernel); + return kvm_skip_emulated_instruction(vcpu); +} + +static int invpcid_interception(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long type; + gva_t gva; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + /* + * For an INVPCID intercept: + * EXITINFO1 provides the linear address of the memory operand. + * EXITINFO2 provides the contents of the register operand. + */ + type = svm->vmcb->control.exit_info_2; + gva = svm->vmcb->control.exit_info_1; + + return kvm_handle_invpcid(vcpu, type, gva); +} + +static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { + [SVM_EXIT_READ_CR0] = cr_interception, + [SVM_EXIT_READ_CR3] = cr_interception, + [SVM_EXIT_READ_CR4] = cr_interception, + [SVM_EXIT_READ_CR8] = cr_interception, + [SVM_EXIT_CR0_SEL_WRITE] = cr_interception, + [SVM_EXIT_WRITE_CR0] = cr_interception, + [SVM_EXIT_WRITE_CR3] = cr_interception, + [SVM_EXIT_WRITE_CR4] = cr_interception, + [SVM_EXIT_WRITE_CR8] = cr8_write_interception, + [SVM_EXIT_READ_DR0] = dr_interception, + [SVM_EXIT_READ_DR1] = dr_interception, + [SVM_EXIT_READ_DR2] = dr_interception, + [SVM_EXIT_READ_DR3] = dr_interception, + [SVM_EXIT_READ_DR4] = dr_interception, + [SVM_EXIT_READ_DR5] = dr_interception, + [SVM_EXIT_READ_DR6] = dr_interception, + [SVM_EXIT_READ_DR7] = dr_interception, + [SVM_EXIT_WRITE_DR0] = dr_interception, + [SVM_EXIT_WRITE_DR1] = dr_interception, + [SVM_EXIT_WRITE_DR2] = dr_interception, + [SVM_EXIT_WRITE_DR3] = dr_interception, + [SVM_EXIT_WRITE_DR4] = dr_interception, + [SVM_EXIT_WRITE_DR5] = dr_interception, + [SVM_EXIT_WRITE_DR6] = dr_interception, + [SVM_EXIT_WRITE_DR7] = dr_interception, + [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, + [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, + [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, + [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, + [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception, + [SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception, + [SVM_EXIT_INTR] = intr_interception, + [SVM_EXIT_NMI] = nmi_interception, + [SVM_EXIT_SMI] = smi_interception, + [SVM_EXIT_VINTR] = interrupt_window_interception, + [SVM_EXIT_RDPMC] = kvm_emulate_rdpmc, + [SVM_EXIT_CPUID] = kvm_emulate_cpuid, + [SVM_EXIT_IRET] = iret_interception, + [SVM_EXIT_INVD] = kvm_emulate_invd, + [SVM_EXIT_PAUSE] = pause_interception, + [SVM_EXIT_HLT] = kvm_emulate_halt, + [SVM_EXIT_INVLPG] = invlpg_interception, + [SVM_EXIT_INVLPGA] = invlpga_interception, + [SVM_EXIT_IOIO] = io_interception, + [SVM_EXIT_MSR] = msr_interception, + [SVM_EXIT_TASK_SWITCH] = task_switch_interception, + [SVM_EXIT_SHUTDOWN] = shutdown_interception, + [SVM_EXIT_VMRUN] = vmrun_interception, + [SVM_EXIT_VMMCALL] = kvm_emulate_hypercall, + [SVM_EXIT_VMLOAD] = vmload_interception, + [SVM_EXIT_VMSAVE] = vmsave_interception, + [SVM_EXIT_STGI] = stgi_interception, + [SVM_EXIT_CLGI] = clgi_interception, + [SVM_EXIT_SKINIT] = skinit_interception, + [SVM_EXIT_RDTSCP] = kvm_handle_invalid_op, + [SVM_EXIT_WBINVD] = kvm_emulate_wbinvd, + [SVM_EXIT_MONITOR] = kvm_emulate_monitor, + [SVM_EXIT_MWAIT] = kvm_emulate_mwait, + [SVM_EXIT_XSETBV] = kvm_emulate_xsetbv, + [SVM_EXIT_RDPRU] = kvm_handle_invalid_op, + [SVM_EXIT_EFER_WRITE_TRAP] = efer_trap, + [SVM_EXIT_CR0_WRITE_TRAP] = cr_trap, + [SVM_EXIT_CR4_WRITE_TRAP] = cr_trap, + [SVM_EXIT_CR8_WRITE_TRAP] = cr_trap, + [SVM_EXIT_INVPCID] = invpcid_interception, + [SVM_EXIT_NPF] = npf_interception, + [SVM_EXIT_RSM] = rsm_interception, + [SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception, + [SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception, + [SVM_EXIT_VMGEXIT] = sev_handle_vmgexit, +}; + +static void dump_vmcb(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_control_area *control = &svm->vmcb->control; + struct vmcb_save_area *save = &svm->vmcb->save; + struct vmcb_save_area *save01 = &svm->vmcb01.ptr->save; + + if (!dump_invalid_vmcb) { + pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n"); + return; + } + + pr_err("VMCB %p, last attempted VMRUN on CPU %d\n", + svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu); + pr_err("VMCB Control Area:\n"); + pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff); + pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16); + pr_err("%-20s%04x\n", "dr_read:", control->intercepts[INTERCEPT_DR] & 0xffff); + pr_err("%-20s%04x\n", "dr_write:", control->intercepts[INTERCEPT_DR] >> 16); + pr_err("%-20s%08x\n", "exceptions:", control->intercepts[INTERCEPT_EXCEPTION]); + pr_err("%-20s%08x %08x\n", "intercepts:", + control->intercepts[INTERCEPT_WORD3], + control->intercepts[INTERCEPT_WORD4]); + pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count); + pr_err("%-20s%d\n", "pause filter threshold:", + control->pause_filter_thresh); + pr_err("%-20s%016llx\n", "iopm_base_pa:", control->iopm_base_pa); + pr_err("%-20s%016llx\n", "msrpm_base_pa:", control->msrpm_base_pa); + pr_err("%-20s%016llx\n", "tsc_offset:", control->tsc_offset); + pr_err("%-20s%d\n", "asid:", control->asid); + pr_err("%-20s%d\n", "tlb_ctl:", control->tlb_ctl); + pr_err("%-20s%08x\n", "int_ctl:", control->int_ctl); + pr_err("%-20s%08x\n", "int_vector:", control->int_vector); + pr_err("%-20s%08x\n", "int_state:", control->int_state); + pr_err("%-20s%08x\n", "exit_code:", control->exit_code); + pr_err("%-20s%016llx\n", "exit_info1:", control->exit_info_1); + pr_err("%-20s%016llx\n", "exit_info2:", control->exit_info_2); + pr_err("%-20s%08x\n", "exit_int_info:", control->exit_int_info); + pr_err("%-20s%08x\n", "exit_int_info_err:", control->exit_int_info_err); + pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl); + pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3); + pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar); + pr_err("%-20s%016llx\n", "ghcb:", control->ghcb_gpa); + pr_err("%-20s%08x\n", "event_inj:", control->event_inj); + pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err); + pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext); + pr_err("%-20s%016llx\n", "next_rip:", control->next_rip); + pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page); + pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id); + pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id); + pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa); + pr_err("VMCB State Save Area:\n"); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "es:", + save->es.selector, save->es.attrib, + save->es.limit, save->es.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "cs:", + save->cs.selector, save->cs.attrib, + save->cs.limit, save->cs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ss:", + save->ss.selector, save->ss.attrib, + save->ss.limit, save->ss.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ds:", + save->ds.selector, save->ds.attrib, + save->ds.limit, save->ds.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "fs:", + save01->fs.selector, save01->fs.attrib, + save01->fs.limit, save01->fs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "gs:", + save01->gs.selector, save01->gs.attrib, + save01->gs.limit, save01->gs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "gdtr:", + save->gdtr.selector, save->gdtr.attrib, + save->gdtr.limit, save->gdtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ldtr:", + save01->ldtr.selector, save01->ldtr.attrib, + save01->ldtr.limit, save01->ldtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "idtr:", + save->idtr.selector, save->idtr.attrib, + save->idtr.limit, save->idtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "tr:", + save01->tr.selector, save01->tr.attrib, + save01->tr.limit, save01->tr.base); + pr_err("vmpl: %d cpl: %d efer: %016llx\n", + save->vmpl, save->cpl, save->efer); + pr_err("%-15s %016llx %-13s %016llx\n", + "cr0:", save->cr0, "cr2:", save->cr2); + pr_err("%-15s %016llx %-13s %016llx\n", + "cr3:", save->cr3, "cr4:", save->cr4); + pr_err("%-15s %016llx %-13s %016llx\n", + "dr6:", save->dr6, "dr7:", save->dr7); + pr_err("%-15s %016llx %-13s %016llx\n", + "rip:", save->rip, "rflags:", save->rflags); + pr_err("%-15s %016llx %-13s %016llx\n", + "rsp:", save->rsp, "rax:", save->rax); + pr_err("%-15s %016llx %-13s %016llx\n", + "star:", save01->star, "lstar:", save01->lstar); + pr_err("%-15s %016llx %-13s %016llx\n", + "cstar:", save01->cstar, "sfmask:", save01->sfmask); + pr_err("%-15s %016llx %-13s %016llx\n", + "kernel_gs_base:", save01->kernel_gs_base, + "sysenter_cs:", save01->sysenter_cs); + pr_err("%-15s %016llx %-13s %016llx\n", + "sysenter_esp:", save01->sysenter_esp, + "sysenter_eip:", save01->sysenter_eip); + pr_err("%-15s %016llx %-13s %016llx\n", + "gpat:", save->g_pat, "dbgctl:", save->dbgctl); + pr_err("%-15s %016llx %-13s %016llx\n", + "br_from:", save->br_from, "br_to:", save->br_to); + pr_err("%-15s %016llx %-13s %016llx\n", + "excp_from:", save->last_excp_from, + "excp_to:", save->last_excp_to); +} + +static bool svm_check_exit_valid(u64 exit_code) +{ + return (exit_code < ARRAY_SIZE(svm_exit_handlers) && + svm_exit_handlers[exit_code]); +} + +static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code) +{ + vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%llx\n", exit_code); + dump_vmcb(vcpu); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; + vcpu->run->internal.ndata = 2; + vcpu->run->internal.data[0] = exit_code; + vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + return 0; +} + +int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) +{ + if (!svm_check_exit_valid(exit_code)) + return svm_handle_invalid_exit(vcpu, exit_code); + +#ifdef CONFIG_RETPOLINE + if (exit_code == SVM_EXIT_MSR) + return msr_interception(vcpu); + else if (exit_code == SVM_EXIT_VINTR) + return interrupt_window_interception(vcpu); + else if (exit_code == SVM_EXIT_INTR) + return intr_interception(vcpu); + else if (exit_code == SVM_EXIT_HLT) + return kvm_emulate_halt(vcpu); + else if (exit_code == SVM_EXIT_NPF) + return npf_interception(vcpu); +#endif + return svm_exit_handlers[exit_code](vcpu); +} + +static void svm_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, + u32 *intr_info, u32 *error_code) +{ + struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + + *reason = control->exit_code; + *info1 = control->exit_info_1; + *info2 = control->exit_info_2; + *intr_info = control->exit_int_info; + if ((*intr_info & SVM_EXITINTINFO_VALID) && + (*intr_info & SVM_EXITINTINFO_VALID_ERR)) + *error_code = control->exit_int_info_err; + else + *error_code = 0; +} + +static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_run *kvm_run = vcpu->run; + u32 exit_code = svm->vmcb->control.exit_code; + + /* SEV-ES guests must use the CR write traps to track CR registers. */ + if (!sev_es_guest(vcpu->kvm)) { + if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE)) + vcpu->arch.cr0 = svm->vmcb->save.cr0; + if (npt_enabled) + vcpu->arch.cr3 = svm->vmcb->save.cr3; + } + + if (is_guest_mode(vcpu)) { + int vmexit; + + trace_kvm_nested_vmexit(vcpu, KVM_ISA_SVM); + + vmexit = nested_svm_exit_special(svm); + + if (vmexit == NESTED_EXIT_CONTINUE) + vmexit = nested_svm_exit_handled(svm); + + if (vmexit == NESTED_EXIT_DONE) + return 1; + } + + if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { + kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; + kvm_run->fail_entry.hardware_entry_failure_reason + = svm->vmcb->control.exit_code; + kvm_run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu; + dump_vmcb(vcpu); + return 0; + } + + if (exit_fastpath != EXIT_FASTPATH_NONE) + return 1; + + return svm_invoke_exit_handler(vcpu, exit_code); +} + +static void pre_svm_run(struct kvm_vcpu *vcpu) +{ + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * If the previous vmrun of the vmcb occurred on a different physical + * cpu, then mark the vmcb dirty and assign a new asid. Hardware's + * vmcb clean bits are per logical CPU, as are KVM's asid assignments. + */ + if (unlikely(svm->current_vmcb->cpu != vcpu->cpu)) { + svm->current_vmcb->asid_generation = 0; + vmcb_mark_all_dirty(svm->vmcb); + svm->current_vmcb->cpu = vcpu->cpu; + } + + if (sev_guest(vcpu->kvm)) + return pre_sev_run(svm, vcpu->cpu); + + /* FIXME: handle wraparound of asid_generation */ + if (svm->current_vmcb->asid_generation != sd->asid_generation) + new_asid(svm, sd); +} + +static void svm_inject_nmi(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; + + if (svm->nmi_l1_to_l2) + return; + + svm->nmi_masked = true; + svm_set_iret_intercept(svm); + ++vcpu->stat.nmi_injections; +} + +static bool svm_is_vnmi_pending(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!is_vnmi_enabled(svm)) + return false; + + return !!(svm->vmcb->control.int_ctl & V_NMI_PENDING_MASK); +} + +static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!is_vnmi_enabled(svm)) + return false; + + if (svm->vmcb->control.int_ctl & V_NMI_PENDING_MASK) + return false; + + svm->vmcb->control.int_ctl |= V_NMI_PENDING_MASK; + vmcb_mark_dirty(svm->vmcb, VMCB_INTR); + + /* + * Because the pending NMI is serviced by hardware, KVM can't know when + * the NMI is "injected", but for all intents and purposes, passing the + * NMI off to hardware counts as injection. + */ + ++vcpu->stat.nmi_injections; + + return true; +} + +static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u32 type; + + if (vcpu->arch.interrupt.soft) { + if (svm_update_soft_interrupt_rip(vcpu)) + return; + + type = SVM_EVTINJ_TYPE_SOFT; + } else { + type = SVM_EVTINJ_TYPE_INTR; + } + + trace_kvm_inj_virq(vcpu->arch.interrupt.nr, + vcpu->arch.interrupt.soft, reinjected); + ++vcpu->stat.irq_injections; + + svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | + SVM_EVTINJ_VALID | type; +} + +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vector) +{ + /* + * apic->apicv_active must be read after vcpu->mode. + * Pairs with smp_store_release in vcpu_enter_guest. + */ + bool in_guest_mode = (smp_load_acquire(&vcpu->mode) == IN_GUEST_MODE); + + /* Note, this is called iff the local APIC is in-kernel. */ + if (!READ_ONCE(vcpu->arch.apic->apicv_active)) { + /* Process the interrupt via kvm_check_and_inject_events(). */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + return; + } + + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); + if (in_guest_mode) { + /* + * Signal the doorbell to tell hardware to inject the IRQ. If + * the vCPU exits the guest before the doorbell chimes, hardware + * will automatically process AVIC interrupts at the next VMRUN. + */ + avic_ring_doorbell(vcpu); + } else { + /* + * Wake the vCPU if it was blocking. KVM will then detect the + * pending IRQ when checking if the vCPU has a wake event. + */ + kvm_vcpu_wake_up(vcpu); + } +} + +static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + kvm_lapic_set_irr(vector, apic); + + /* + * Pairs with the smp_mb_*() after setting vcpu->guest_mode in + * vcpu_enter_guest() to ensure the write to the vIRR is ordered before + * the read of guest_mode. This guarantees that either VMRUN will see + * and process the new vIRR entry, or that svm_complete_interrupt_delivery + * will signal the doorbell if the CPU has already entered the guest. + */ + smp_mb__after_atomic(); + svm_complete_interrupt_delivery(apic->vcpu, delivery_mode, trig_mode, vector); +} + +static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * SEV-ES guests must always keep the CR intercepts cleared. CR + * tracking is done using the CR write traps. + */ + if (sev_es_guest(vcpu->kvm)) + return; + + if (nested_svm_virtualize_tpr(vcpu)) + return; + + svm_clr_intercept(svm, INTERCEPT_CR8_WRITE); + + if (irr == -1) + return; + + if (tpr >= irr) + svm_set_intercept(svm, INTERCEPT_CR8_WRITE); +} + +static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_vnmi_enabled(svm)) + return svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK; + else + return svm->nmi_masked; +} + +static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_vnmi_enabled(svm)) { + if (masked) + svm->vmcb->control.int_ctl |= V_NMI_BLOCKING_MASK; + else + svm->vmcb->control.int_ctl &= ~V_NMI_BLOCKING_MASK; + + } else { + svm->nmi_masked = masked; + if (masked) + svm_set_iret_intercept(svm); + else + svm_clr_iret_intercept(svm); + } +} + +bool svm_nmi_blocked(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + + if (!gif_set(svm)) + return true; + + if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) + return false; + + if (svm_get_nmi_mask(vcpu)) + return true; + + return vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK; +} + +static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) + return -EBUSY; + + if (svm_nmi_blocked(vcpu)) + return 0; + + /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) + return -EBUSY; + return 1; +} + +bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + + if (!gif_set(svm)) + return true; + + if (is_guest_mode(vcpu)) { + /* As long as interrupts are being delivered... */ + if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) + ? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF) + : !(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) + return true; + + /* ... vmexits aren't blocked by the interrupt shadow */ + if (nested_exit_on_intr(svm)) + return false; + } else { + if (!svm_get_if_flag(vcpu)) + return true; + } + + return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK); +} + +static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (svm->nested.nested_run_pending) + return -EBUSY; + + if (svm_interrupt_blocked(vcpu)) + return 0; + + /* + * An IRQ must not be injected into L2 if it's supposed to VM-Exit, + * e.g. if the IRQ arrived asynchronously after checking nested events. + */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm)) + return -EBUSY; + + return 1; +} + +static void svm_enable_irq_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes + * 1, because that's a separate STGI/VMRUN intercept. The next time we + * get that intercept, this function will be called again though and + * we'll get the vintr intercept. However, if the vGIF feature is + * enabled, the STGI interception will not occur. Enable the irq + * window under the assumption that the hardware will set the GIF. + */ + if (vgif || gif_set(svm)) { + /* + * IRQ window is not needed when AVIC is enabled, + * unless we have pending ExtINT since it cannot be injected + * via AVIC. In such case, KVM needs to temporarily disable AVIC, + * and fallback to injecting IRQ via V_IRQ. + * + * If running nested, AVIC is already locally inhibited + * on this vCPU, therefore there is no need to request + * the VM wide AVIC inhibition. + */ + if (!is_guest_mode(vcpu)) + kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN); + + svm_set_vintr(svm); + } +} + +static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * KVM should never request an NMI window when vNMI is enabled, as KVM + * allows at most one to-be-injected NMI and one pending NMI, i.e. if + * two NMIs arrive simultaneously, KVM will inject one and set + * V_NMI_PENDING for the other. WARN, but continue with the standard + * single-step approach to try and salvage the pending NMI. + */ + WARN_ON_ONCE(is_vnmi_enabled(svm)); + + if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) + return; /* IRET will cause a vm exit */ + + /* + * SEV-ES guests are responsible for signaling when a vCPU is ready to + * receive a new NMI, as SEV-ES guests can't be single-stepped, i.e. + * KVM can't intercept and single-step IRET to detect when NMIs are + * unblocked (architecturally speaking). See SVM_VMGEXIT_NMI_COMPLETE. + * + * Note, GIF is guaranteed to be '1' for SEV-ES guests as hardware + * ignores SEV-ES guest writes to EFER.SVME *and* CLGI/STGI are not + * supported NAEs in the GHCB protocol. + */ + if (sev_es_guest(vcpu->kvm)) + return; + + if (!gif_set(svm)) { + if (vgif) + svm_set_intercept(svm, INTERCEPT_STGI); + return; /* STGI will cause a vm exit */ + } + + /* + * Something prevents NMI from been injected. Single step over possible + * problem (IRET or exception injection or interrupt shadow) + */ + svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu); + svm->nmi_singlestep = true; + svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); +} + +static void svm_flush_tlb_asid(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * Unlike VMX, SVM doesn't provide a way to flush only NPT TLB entries. + * A TLB flush for the current ASID flushes both "host" and "guest" TLB + * entries, and thus is a superset of Hyper-V's fine grained flushing. + */ + kvm_hv_vcpu_purge_flush_tlb(vcpu); + + /* + * Flush only the current ASID even if the TLB flush was invoked via + * kvm_flush_remote_tlbs(). Although flushing remote TLBs requires all + * ASIDs to be flushed, KVM uses a single ASID for L1 and L2, and + * unconditionally does a TLB flush on both nested VM-Enter and nested + * VM-Exit (via kvm_mmu_reset_context()). + */ + if (static_cpu_has(X86_FEATURE_FLUSHBYASID)) + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; + else + svm->current_vmcb->asid_generation--; +} + +static void svm_flush_tlb_current(struct kvm_vcpu *vcpu) +{ + hpa_t root_tdp = vcpu->arch.mmu->root.hpa; + + /* + * When running on Hyper-V with EnlightenedNptTlb enabled, explicitly + * flush the NPT mappings via hypercall as flushing the ASID only + * affects virtual to physical mappings, it does not invalidate guest + * physical to host physical mappings. + */ + if (svm_hv_is_enlightened_tlb_enabled(vcpu) && VALID_PAGE(root_tdp)) + hyperv_flush_guest_mapping(root_tdp); + + svm_flush_tlb_asid(vcpu); +} + +static void svm_flush_tlb_all(struct kvm_vcpu *vcpu) +{ + /* + * When running on Hyper-V with EnlightenedNptTlb enabled, remote TLB + * flushes should be routed to hv_flush_remote_tlbs() without requesting + * a "regular" remote flush. Reaching this point means either there's + * a KVM bug or a prior hv_flush_remote_tlbs() call failed, both of + * which might be fatal to the guest. Yell, but try to recover. + */ + if (WARN_ON_ONCE(svm_hv_is_enlightened_tlb_enabled(vcpu))) + hv_flush_remote_tlbs(vcpu->kvm); + + svm_flush_tlb_asid(vcpu); +} + +static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + invlpga(gva, svm->vmcb->control.asid); +} + +static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (nested_svm_virtualize_tpr(vcpu)) + return; + + if (!svm_is_intercept(svm, INTERCEPT_CR8_WRITE)) { + int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK; + kvm_set_cr8(vcpu, cr8); + } +} + +static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr8; + + if (nested_svm_virtualize_tpr(vcpu) || + kvm_vcpu_apicv_active(vcpu)) + return; + + cr8 = kvm_get_cr8(vcpu); + svm->vmcb->control.int_ctl &= ~V_TPR_MASK; + svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; +} + +static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector, + int type) +{ + bool is_exception = (type == SVM_EXITINTINFO_TYPE_EXEPT); + bool is_soft = (type == SVM_EXITINTINFO_TYPE_SOFT); + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * If NRIPS is enabled, KVM must snapshot the pre-VMRUN next_rip that's + * associated with the original soft exception/interrupt. next_rip is + * cleared on all exits that can occur while vectoring an event, so KVM + * needs to manually set next_rip for re-injection. Unlike the !nrips + * case below, this needs to be done if and only if KVM is re-injecting + * the same event, i.e. if the event is a soft exception/interrupt, + * otherwise next_rip is unused on VMRUN. + */ + if (nrips && (is_soft || (is_exception && kvm_exception_is_soft(vector))) && + kvm_is_linear_rip(vcpu, svm->soft_int_old_rip + svm->soft_int_csbase)) + svm->vmcb->control.next_rip = svm->soft_int_next_rip; + /* + * If NRIPS isn't enabled, KVM must manually advance RIP prior to + * injecting the soft exception/interrupt. That advancement needs to + * be unwound if vectoring didn't complete. Note, the new event may + * not be the injected event, e.g. if KVM injected an INTn, the INTn + * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will + * be the reported vectored event, but RIP still needs to be unwound. + */ + else if (!nrips && (is_soft || is_exception) && + kvm_is_linear_rip(vcpu, svm->soft_int_next_rip + svm->soft_int_csbase)) + kvm_rip_write(vcpu, svm->soft_int_old_rip); +} + +static void svm_complete_interrupts(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u8 vector; + int type; + u32 exitintinfo = svm->vmcb->control.exit_int_info; + bool nmi_l1_to_l2 = svm->nmi_l1_to_l2; + bool soft_int_injected = svm->soft_int_injected; + + svm->nmi_l1_to_l2 = false; + svm->soft_int_injected = false; + + /* + * If we've made progress since setting awaiting_iret_completion, we've + * executed an IRET and can allow NMI injection. + */ + if (svm->awaiting_iret_completion && + kvm_rip_read(vcpu) != svm->nmi_iret_rip) { + svm->awaiting_iret_completion = false; + svm->nmi_masked = false; + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + + if (!(exitintinfo & SVM_EXITINTINFO_VALID)) + return; + + kvm_make_request(KVM_REQ_EVENT, vcpu); + + vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK; + type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK; + + if (soft_int_injected) + svm_complete_soft_interrupt(vcpu, vector, type); + + switch (type) { + case SVM_EXITINTINFO_TYPE_NMI: + vcpu->arch.nmi_injected = true; + svm->nmi_l1_to_l2 = nmi_l1_to_l2; + break; + case SVM_EXITINTINFO_TYPE_EXEPT: + /* + * Never re-inject a #VC exception. + */ + if (vector == X86_TRAP_VC) + break; + + if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { + u32 err = svm->vmcb->control.exit_int_info_err; + kvm_requeue_exception_e(vcpu, vector, err); + + } else + kvm_requeue_exception(vcpu, vector); + break; + case SVM_EXITINTINFO_TYPE_INTR: + kvm_queue_interrupt(vcpu, vector, false); + break; + case SVM_EXITINTINFO_TYPE_SOFT: + kvm_queue_interrupt(vcpu, vector, true); + break; + default: + break; + } + +} + +static void svm_cancel_injection(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_control_area *control = &svm->vmcb->control; + + control->exit_int_info = control->event_inj; + control->exit_int_info_err = control->event_inj_err; + control->event_inj = 0; + svm_complete_interrupts(vcpu); +} + +static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) +{ + return 1; +} + +static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +{ + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && + to_svm(vcpu)->vmcb->control.exit_info_1) + return handle_fastpath_set_msr_irqoff(vcpu); + + return EXIT_FASTPATH_NONE; +} + +static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + guest_state_enter_irqoff(); + + amd_clear_divider(); + + if (sev_es_guest(vcpu->kvm)) + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + else + __svm_vcpu_run(svm, spec_ctrl_intercepted); + + guest_state_exit_irqoff(); +} + +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); + + trace_kvm_entry(vcpu); + + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + + /* + * Disable singlestep if we're injecting an interrupt/exception. + * We don't want our modified rflags to be pushed on the stack where + * we might not be able to easily reset them if we disabled NMI + * singlestep later. + */ + if (svm->nmi_singlestep && svm->vmcb->control.event_inj) { + /* + * Event injection happens before external interrupts cause a + * vmexit and interrupts are disabled here, so smp_send_reschedule + * is enough to force an immediate vmexit. + */ + disable_nmi_singlestep(svm); + smp_send_reschedule(vcpu->cpu); + } + + pre_svm_run(vcpu); + + sync_lapic_to_cr8(vcpu); + + if (unlikely(svm->asid != svm->vmcb->control.asid)) { + svm->vmcb->control.asid = svm->asid; + vmcb_mark_dirty(svm->vmcb, VMCB_ASID); + } + svm->vmcb->save.cr2 = vcpu->arch.cr2; + + svm_hv_update_vp_id(svm->vmcb, vcpu); + + /* + * Run with all-zero DR6 unless needed, so that we can get the exact cause + * of a #DB. + */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + svm_set_dr6(svm, vcpu->arch.dr6); + else + svm_set_dr6(svm, DR6_ACTIVE_LOW); + + clgi(); + kvm_load_guest_xsave_state(vcpu); + + kvm_wait_lapic_expire(vcpu); + + /* + * If this vCPU has touched SPEC_CTRL, restore the guest's value if + * it's non-zero. Since vmentry is serialising on affected CPUs, there + * is no need to worry about the conditional branch over the wrmsr + * being speculatively taken. + */ + if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + x86_spec_ctrl_set_guest(svm->virt_spec_ctrl); + + svm_vcpu_enter_exit(vcpu, spec_ctrl_intercepted); + + if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + x86_spec_ctrl_restore_host(svm->virt_spec_ctrl); + + if (!sev_es_guest(vcpu->kvm)) { + vcpu->arch.cr2 = svm->vmcb->save.cr2; + vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; + vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; + vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; + } + vcpu->arch.regs_dirty = 0; + + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) + kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); + + kvm_load_host_xsave_state(vcpu); + stgi(); + + /* Any pending NMI will happen here */ + + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) + kvm_after_interrupt(vcpu); + + sync_cr8_to_lapic(vcpu); + + svm->next_rip = 0; + if (is_guest_mode(vcpu)) { + nested_sync_control_from_vmcb02(svm); + + /* Track VMRUNs that have made past consistency checking */ + if (svm->nested.nested_run_pending && + svm->vmcb->control.exit_code != SVM_EXIT_ERR) + ++vcpu->stat.nested_run; + + svm->nested.nested_run_pending = 0; + } + + svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; + vmcb_mark_all_clean(svm->vmcb); + + /* if exit due to PF check for async PF */ + if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) + vcpu->arch.apf.host_apf_flags = + kvm_read_and_reset_apf_flags(); + + vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET; + + /* + * We need to handle MC intercepts here before the vcpu has a chance to + * change the physical cpu + */ + if (unlikely(svm->vmcb->control.exit_code == + SVM_EXIT_EXCP_BASE + MC_VECTOR)) + svm_handle_mce(vcpu); + + trace_kvm_exit(vcpu, KVM_ISA_SVM); + + svm_complete_interrupts(vcpu); + + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + + return svm_exit_handlers_fastpath(vcpu); +} + +static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, + int root_level) +{ + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long cr3; + + if (npt_enabled) { + svm->vmcb->control.nested_cr3 = __sme_set(root_hpa); + vmcb_mark_dirty(svm->vmcb, VMCB_NPT); + + hv_track_root_tdp(vcpu, root_hpa); + + cr3 = vcpu->arch.cr3; + } else if (root_level >= PT64_ROOT_4LEVEL) { + cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu); + } else { + /* PCID in the guest should be impossible with a 32-bit MMU. */ + WARN_ON_ONCE(kvm_get_active_pcid(vcpu)); + cr3 = root_hpa; + } + + svm->vmcb->save.cr3 = cr3; + vmcb_mark_dirty(svm->vmcb, VMCB_CR); +} + +static void +svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) +{ + /* + * Patch in the VMMCALL instruction: + */ + hypercall[0] = 0x0f; + hypercall[1] = 0x01; + hypercall[2] = 0xd9; +} + +/* + * 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 svm_has_emulated_msr(struct kvm *kvm, u32 index) +{ + switch (index) { + case MSR_IA32_MCG_EXT_CTL: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: + return false; + case MSR_IA32_SMBASE: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + return false; + /* SEV-ES guests do not support SMM, so report false */ + if (kvm && sev_es_guest(kvm)) + return false; + break; + default: + break; + } + + return true; +} + +static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * SVM doesn't provide a way to disable just XSAVES in the guest, KVM + * can only disable all variants of by disallowing CR4.OSXSAVE from + * being set. As a result, if the host has XSAVE and XSAVES, and the + * guest has XSAVE enabled, the guest can execute XSAVES without + * faulting. Treat XSAVES as enabled in this case regardless of + * whether it's advertised to the guest so that KVM context switches + * XSS on VM-Enter/VM-Exit. Failure to do so would effectively give + * the guest read/write access to the host's XSS. + */ + if (boot_cpu_has(X86_FEATURE_XSAVE) && + boot_cpu_has(X86_FEATURE_XSAVES) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) + kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES); + + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_TSCRATEMSR); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LBRV); + + /* + * Intercept VMLOAD if the vCPU mode is Intel in order to emulate that + * VMLOAD drops bits 63:32 of SYSENTER (ignoring the fact that exposing + * SVM on Intel is bonkers and extremely unlikely to work). + */ + if (!guest_cpuid_is_intel(vcpu)) + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); + + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VGIF); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VNMI); + + svm_recalc_instruction_intercepts(vcpu, svm); + + if (boot_cpu_has(X86_FEATURE_IBPB)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, + !!guest_has_pred_cmd_msr(vcpu)); + + if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, + !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + + if (sev_guest(vcpu->kvm)) + sev_vcpu_after_set_cpuid(svm); + + init_vmcb_after_set_cpuid(vcpu); +} + +static bool svm_has_wbinvd_exit(void) +{ + return true; +} + +#define PRE_EX(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_PRE_EXCEPT, } +#define POST_EX(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_POST_EXCEPT, } +#define POST_MEM(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_POST_MEMACCESS, } + +static const struct __x86_intercept { + u32 exit_code; + enum x86_intercept_stage stage; +} x86_intercept_map[] = { + [x86_intercept_cr_read] = POST_EX(SVM_EXIT_READ_CR0), + [x86_intercept_cr_write] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_clts] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_lmsw] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_smsw] = POST_EX(SVM_EXIT_READ_CR0), + [x86_intercept_dr_read] = POST_EX(SVM_EXIT_READ_DR0), + [x86_intercept_dr_write] = POST_EX(SVM_EXIT_WRITE_DR0), + [x86_intercept_sldt] = POST_EX(SVM_EXIT_LDTR_READ), + [x86_intercept_str] = POST_EX(SVM_EXIT_TR_READ), + [x86_intercept_lldt] = POST_EX(SVM_EXIT_LDTR_WRITE), + [x86_intercept_ltr] = POST_EX(SVM_EXIT_TR_WRITE), + [x86_intercept_sgdt] = POST_EX(SVM_EXIT_GDTR_READ), + [x86_intercept_sidt] = POST_EX(SVM_EXIT_IDTR_READ), + [x86_intercept_lgdt] = POST_EX(SVM_EXIT_GDTR_WRITE), + [x86_intercept_lidt] = POST_EX(SVM_EXIT_IDTR_WRITE), + [x86_intercept_vmrun] = POST_EX(SVM_EXIT_VMRUN), + [x86_intercept_vmmcall] = POST_EX(SVM_EXIT_VMMCALL), + [x86_intercept_vmload] = POST_EX(SVM_EXIT_VMLOAD), + [x86_intercept_vmsave] = POST_EX(SVM_EXIT_VMSAVE), + [x86_intercept_stgi] = POST_EX(SVM_EXIT_STGI), + [x86_intercept_clgi] = POST_EX(SVM_EXIT_CLGI), + [x86_intercept_skinit] = POST_EX(SVM_EXIT_SKINIT), + [x86_intercept_invlpga] = POST_EX(SVM_EXIT_INVLPGA), + [x86_intercept_rdtscp] = POST_EX(SVM_EXIT_RDTSCP), + [x86_intercept_monitor] = POST_MEM(SVM_EXIT_MONITOR), + [x86_intercept_mwait] = POST_EX(SVM_EXIT_MWAIT), + [x86_intercept_invlpg] = POST_EX(SVM_EXIT_INVLPG), + [x86_intercept_invd] = POST_EX(SVM_EXIT_INVD), + [x86_intercept_wbinvd] = POST_EX(SVM_EXIT_WBINVD), + [x86_intercept_wrmsr] = POST_EX(SVM_EXIT_MSR), + [x86_intercept_rdtsc] = POST_EX(SVM_EXIT_RDTSC), + [x86_intercept_rdmsr] = POST_EX(SVM_EXIT_MSR), + [x86_intercept_rdpmc] = POST_EX(SVM_EXIT_RDPMC), + [x86_intercept_cpuid] = PRE_EX(SVM_EXIT_CPUID), + [x86_intercept_rsm] = PRE_EX(SVM_EXIT_RSM), + [x86_intercept_pause] = PRE_EX(SVM_EXIT_PAUSE), + [x86_intercept_pushf] = PRE_EX(SVM_EXIT_PUSHF), + [x86_intercept_popf] = PRE_EX(SVM_EXIT_POPF), + [x86_intercept_intn] = PRE_EX(SVM_EXIT_SWINT), + [x86_intercept_iret] = PRE_EX(SVM_EXIT_IRET), + [x86_intercept_icebp] = PRE_EX(SVM_EXIT_ICEBP), + [x86_intercept_hlt] = POST_EX(SVM_EXIT_HLT), + [x86_intercept_in] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_ins] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_out] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_outs] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_xsetbv] = PRE_EX(SVM_EXIT_XSETBV), +}; + +#undef PRE_EX +#undef POST_EX +#undef POST_MEM + +static int svm_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int vmexit, ret = X86EMUL_CONTINUE; + struct __x86_intercept icpt_info; + struct vmcb *vmcb = svm->vmcb; + + if (info->intercept >= ARRAY_SIZE(x86_intercept_map)) + goto out; + + icpt_info = x86_intercept_map[info->intercept]; + + if (stage != icpt_info.stage) + goto out; + + switch (icpt_info.exit_code) { + case SVM_EXIT_READ_CR0: + if (info->intercept == x86_intercept_cr_read) + icpt_info.exit_code += info->modrm_reg; + break; + case SVM_EXIT_WRITE_CR0: { + unsigned long cr0, val; + + if (info->intercept == x86_intercept_cr_write) + icpt_info.exit_code += info->modrm_reg; + + if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0 || + info->intercept == x86_intercept_clts) + break; + + if (!(vmcb12_is_intercept(&svm->nested.ctl, + INTERCEPT_SELECTIVE_CR0))) + break; + + cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK; + val = info->src_val & ~SVM_CR0_SELECTIVE_MASK; + + if (info->intercept == x86_intercept_lmsw) { + cr0 &= 0xfUL; + val &= 0xfUL; + /* lmsw can't clear PE - catch this here */ + if (cr0 & X86_CR0_PE) + val |= X86_CR0_PE; + } + + if (cr0 ^ val) + icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE; + + break; + } + case SVM_EXIT_READ_DR0: + case SVM_EXIT_WRITE_DR0: + icpt_info.exit_code += info->modrm_reg; + break; + case SVM_EXIT_MSR: + if (info->intercept == x86_intercept_wrmsr) + vmcb->control.exit_info_1 = 1; + else + vmcb->control.exit_info_1 = 0; + break; + case SVM_EXIT_PAUSE: + /* + * We get this for NOP only, but pause + * is rep not, check this here + */ + if (info->rep_prefix != REPE_PREFIX) + goto out; + break; + case SVM_EXIT_IOIO: { + u64 exit_info; + u32 bytes; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + exit_info = ((info->src_val & 0xffff) << 16) | + SVM_IOIO_TYPE_MASK; + bytes = info->dst_bytes; + } else { + exit_info = (info->dst_val & 0xffff) << 16; + bytes = info->src_bytes; + } + + if (info->intercept == x86_intercept_outs || + info->intercept == x86_intercept_ins) + exit_info |= SVM_IOIO_STR_MASK; + + if (info->rep_prefix) + exit_info |= SVM_IOIO_REP_MASK; + + bytes = min(bytes, 4u); + + exit_info |= bytes << SVM_IOIO_SIZE_SHIFT; + + exit_info |= (u32)info->ad_bytes << (SVM_IOIO_ASIZE_SHIFT - 1); + + vmcb->control.exit_info_1 = exit_info; + vmcb->control.exit_info_2 = info->next_rip; + + break; + } + default: + break; + } + + /* TODO: Advertise NRIPS to guest hypervisor unconditionally */ + if (static_cpu_has(X86_FEATURE_NRIPS)) + vmcb->control.next_rip = info->next_rip; + vmcb->control.exit_code = icpt_info.exit_code; + vmexit = nested_svm_exit_handled(svm); + + ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED + : X86EMUL_CONTINUE; + +out: + return ret; +} + +static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu) +{ + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_INTR) + vcpu->arch.at_instruction_boundary = true; +} + +static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu) +{ + if (!kvm_pause_in_guest(vcpu->kvm)) + shrink_ple_window(vcpu); +} + +static void svm_setup_mce(struct kvm_vcpu *vcpu) +{ + /* [63:9] are reserved. */ + vcpu->arch.mcg_cap &= 0x1ff; +} + +#ifdef CONFIG_KVM_SMM +bool svm_smi_blocked(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* Per APM Vol.2 15.22.2 "Response to SMI" */ + if (!gif_set(svm)) + return true; + + return is_smm(vcpu); +} + +static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) +{ + struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) + return -EBUSY; + + if (svm_smi_blocked(vcpu)) + return 0; + + /* An SMI must not be injected into L2 if it's supposed to VM-Exit. */ + if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm)) + return -EBUSY; + + return 1; +} + +static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_host_map map_save; + int ret; + + if (!is_guest_mode(vcpu)) + return 0; + + /* + * 32-bit SMRAM format doesn't preserve EFER and SVM state. Userspace is + * responsible for ensuring nested SVM and SMIs are mutually exclusive. + */ + + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 1; + + smram->smram64.svm_guest_flag = 1; + smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa; + + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; + svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; + svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; + + ret = nested_svm_simple_vmexit(svm, SVM_EXIT_SW); + if (ret) + return ret; + + /* + * KVM uses VMCB01 to store L1 host state while L2 runs but + * VMCB01 is going to be used during SMM and thus the state will + * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save + * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the + * format of the area is identical to guest save area offsetted + * by 0x400 (matches the offset of 'struct vmcb_save_area' + * within 'struct vmcb'). Note: HSAVE area may also be used by + * L1 hypervisor to save additional host context (e.g. KVM does + * that, see svm_prepare_switch_to_guest()) which must be + * preserved. + */ + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save)) + return 1; + + BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); + + svm_copy_vmrun_state(map_save.hva + 0x400, + &svm->vmcb01.ptr->save); + + kvm_vcpu_unmap(vcpu, &map_save, true); + return 0; +} + +static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_host_map map, map_save; + struct vmcb *vmcb12; + int ret; + + const struct kvm_smram_state_64 *smram64 = &smram->smram64; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 0; + + /* Non-zero if SMI arrived while vCPU was in guest mode. */ + if (!smram64->svm_guest_flag) + return 0; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; + + if (!(smram64->efer & EFER_SVME)) + return 1; + + if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram64->svm_guest_vmcb_gpa), &map)) + return 1; + + ret = 1; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save)) + goto unmap_map; + + if (svm_allocate_nested(svm)) + goto unmap_save; + + /* + * Restore L1 host state from L1 HSAVE area as VMCB01 was + * used during SMM (see svm_enter_smm()) + */ + + svm_copy_vmrun_state(&svm->vmcb01.ptr->save, map_save.hva + 0x400); + + /* + * Enter the nested guest now + */ + + vmcb_mark_all_dirty(svm->vmcb01.ptr); + + vmcb12 = map.hva; + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); + ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false); + + if (ret) + goto unmap_save; + + svm->nested.nested_run_pending = 1; + +unmap_save: + kvm_vcpu_unmap(vcpu, &map_save, true); +unmap_map: + kvm_vcpu_unmap(vcpu, &map, true); + return ret; +} + +static void svm_enable_smi_window(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!gif_set(svm)) { + if (vgif) + svm_set_intercept(svm, INTERCEPT_STGI); + /* STGI will cause a vm exit */ + } else { + /* We must be in SMM; RSM will cause a vmexit anyway. */ + } +} +#endif + +static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) +{ + bool smep, smap, is_user; + u64 error_code; + + /* Emulation is always possible when KVM has access to all guest state. */ + if (!sev_guest(vcpu->kvm)) + return true; + + /* #UD and #GP should never be intercepted for SEV guests. */ + WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | + EMULTYPE_TRAP_UD_FORCED | + EMULTYPE_VMWARE_GP)); + + /* + * Emulation is impossible for SEV-ES guests as KVM doesn't have access + * to guest register state. + */ + if (sev_es_guest(vcpu->kvm)) + return false; + + /* + * Emulation is possible if the instruction is already decoded, e.g. + * when completing I/O after returning from userspace. + */ + if (emul_type & EMULTYPE_NO_DECODE) + return true; + + /* + * Emulation is possible for SEV guests if and only if a prefilled + * buffer containing the bytes of the intercepted instruction is + * available. SEV guest memory is encrypted with a guest specific key + * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and + * decode garbage. + * + * If KVM is NOT trying to simply skip an instruction, inject #UD if + * KVM reached this point without an instruction buffer. In practice, + * this path should never be hit by a well-behaved guest, e.g. KVM + * doesn't intercept #UD or #GP for SEV guests, but this path is still + * theoretically reachable, e.g. via unaccelerated fault-like AVIC + * access, and needs to be handled by KVM to avoid putting the guest + * into an infinite loop. Injecting #UD is somewhat arbitrary, but + * its the least awful option given lack of insight into the guest. + * + * If KVM is trying to skip an instruction, simply resume the guest. + * If a #NPF occurs while the guest is vectoring an INT3/INTO, then KVM + * will attempt to re-inject the INT3/INTO and skip the instruction. + * In that scenario, retrying the INT3/INTO and hoping the guest will + * make forward progress is the only option that has a chance of + * success (and in practice it will work the vast majority of the time). + */ + if (unlikely(!insn)) { + if (!(emul_type & EMULTYPE_SKIP)) + kvm_queue_exception(vcpu, UD_VECTOR); + return false; + } + + /* + * Emulate for SEV guests if the insn buffer is not empty. The buffer + * will be empty if the DecodeAssist microcode cannot fetch bytes for + * the faulting instruction because the code fetch itself faulted, e.g. + * the guest attempted to fetch from emulated MMIO or a guest page + * table used to translate CS:RIP resides in emulated MMIO. + */ + if (likely(insn_len)) + return true; + + /* + * Detect and workaround Errata 1096 Fam_17h_00_0Fh. + * + * Errata: + * When CPU raises #NPF on guest data access and vCPU CR4.SMAP=1, it is + * possible that CPU microcode implementing DecodeAssist will fail to + * read guest memory at CS:RIP and vmcb.GuestIntrBytes will incorrectly + * be '0'. This happens because microcode reads CS:RIP using a _data_ + * loap uop with CPL=0 privileges. If the load hits a SMAP #PF, ucode + * gives up and does not fill the instruction bytes buffer. + * + * As above, KVM reaches this point iff the VM is an SEV guest, the CPU + * supports DecodeAssist, a #NPF was raised, KVM's page fault handler + * triggered emulation (e.g. for MMIO), and the CPU returned 0 in the + * GuestIntrBytes field of the VMCB. + * + * This does _not_ mean that the erratum has been encountered, as the + * DecodeAssist will also fail if the load for CS:RIP hits a legitimate + * #PF, e.g. if the guest attempt to execute from emulated MMIO and + * encountered a reserved/not-present #PF. + * + * To hit the erratum, the following conditions must be true: + * 1. CR4.SMAP=1 (obviously). + * 2. CR4.SMEP=0 || CPL=3. If SMEP=1 and CPL<3, the erratum cannot + * have been hit as the guest would have encountered a SMEP + * violation #PF, not a #NPF. + * 3. The #NPF is not due to a code fetch, in which case failure to + * retrieve the instruction bytes is legitimate (see abvoe). + * + * In addition, don't apply the erratum workaround if the #NPF occurred + * while translating guest page tables (see below). + */ + error_code = to_svm(vcpu)->vmcb->control.exit_info_1; + if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) + goto resume_guest; + + smep = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMEP); + smap = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMAP); + is_user = svm_get_cpl(vcpu) == 3; + if (smap && (!smep || is_user)) { + pr_err_ratelimited("SEV Guest triggered AMD Erratum 1096\n"); + + /* + * If the fault occurred in userspace, arbitrarily inject #GP + * to avoid killing the guest and to hopefully avoid confusing + * the guest kernel too much, e.g. injecting #PF would not be + * coherent with respect to the guest's page tables. Request + * triple fault if the fault occurred in the kernel as there's + * no fault that KVM can inject without confusing the guest. + * In practice, the triple fault is moot as no sane SEV kernel + * will execute from user memory while also running with SMAP=1. + */ + if (is_user) + kvm_inject_gp(vcpu, 0); + else + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + } + +resume_guest: + /* + * If the erratum was not hit, simply resume the guest and let it fault + * again. While awful, e.g. the vCPU may get stuck in an infinite loop + * if the fault is at CPL=0, it's the lesser of all evils. Exiting to + * userspace will kill the guest, and letting the emulator read garbage + * will yield random behavior and potentially corrupt the guest. + * + * Simply resuming the guest is technically not a violation of the SEV + * architecture. AMD's APM states that all code fetches and page table + * accesses for SEV guest are encrypted, regardless of the C-Bit. The + * APM also states that encrypted accesses to MMIO are "ignored", but + * doesn't explicitly define "ignored", i.e. doing nothing and letting + * the guest spin is technically "ignoring" the access. + */ + return false; +} + +static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return !gif_set(svm); +} + +static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + if (!sev_es_guest(vcpu->kvm)) + return kvm_vcpu_deliver_sipi_vector(vcpu, vector); + + sev_vcpu_deliver_sipi_vector(vcpu, vector); +} + +static void svm_vm_destroy(struct kvm *kvm) +{ + avic_vm_destroy(kvm); + sev_vm_destroy(kvm); +} + +static int svm_vm_init(struct kvm *kvm) +{ + if (!pause_filter_count || !pause_filter_thresh) + kvm->arch.pause_in_guest = true; + + if (enable_apicv) { + int ret = avic_vm_init(kvm); + if (ret) + return ret; + } + + return 0; +} + +static struct kvm_x86_ops svm_x86_ops __initdata = { + .name = KBUILD_MODNAME, + + .check_processor_compatibility = svm_check_processor_compat, + + .hardware_unsetup = svm_hardware_unsetup, + .hardware_enable = svm_hardware_enable, + .hardware_disable = svm_hardware_disable, + .has_emulated_msr = svm_has_emulated_msr, + + .vcpu_create = svm_vcpu_create, + .vcpu_free = svm_vcpu_free, + .vcpu_reset = svm_vcpu_reset, + + .vm_size = sizeof(struct kvm_svm), + .vm_init = svm_vm_init, + .vm_destroy = svm_vm_destroy, + + .prepare_switch_to_guest = svm_prepare_switch_to_guest, + .vcpu_load = svm_vcpu_load, + .vcpu_put = svm_vcpu_put, + .vcpu_blocking = avic_vcpu_blocking, + .vcpu_unblocking = avic_vcpu_unblocking, + + .update_exception_bitmap = svm_update_exception_bitmap, + .get_msr_feature = svm_get_msr_feature, + .get_msr = svm_get_msr, + .set_msr = svm_set_msr, + .get_segment_base = svm_get_segment_base, + .get_segment = svm_get_segment, + .set_segment = svm_set_segment, + .get_cpl = svm_get_cpl, + .get_cs_db_l_bits = svm_get_cs_db_l_bits, + .is_valid_cr0 = svm_is_valid_cr0, + .set_cr0 = svm_set_cr0, + .post_set_cr3 = sev_post_set_cr3, + .is_valid_cr4 = svm_is_valid_cr4, + .set_cr4 = svm_set_cr4, + .set_efer = svm_set_efer, + .get_idt = svm_get_idt, + .set_idt = svm_set_idt, + .get_gdt = svm_get_gdt, + .set_gdt = svm_set_gdt, + .set_dr7 = svm_set_dr7, + .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, + .cache_reg = svm_cache_reg, + .get_rflags = svm_get_rflags, + .set_rflags = svm_set_rflags, + .get_if_flag = svm_get_if_flag, + + .flush_tlb_all = svm_flush_tlb_all, + .flush_tlb_current = svm_flush_tlb_current, + .flush_tlb_gva = svm_flush_tlb_gva, + .flush_tlb_guest = svm_flush_tlb_asid, + + .vcpu_pre_run = svm_vcpu_pre_run, + .vcpu_run = svm_vcpu_run, + .handle_exit = svm_handle_exit, + .skip_emulated_instruction = svm_skip_emulated_instruction, + .update_emulated_instruction = NULL, + .set_interrupt_shadow = svm_set_interrupt_shadow, + .get_interrupt_shadow = svm_get_interrupt_shadow, + .patch_hypercall = svm_patch_hypercall, + .inject_irq = svm_inject_irq, + .inject_nmi = svm_inject_nmi, + .is_vnmi_pending = svm_is_vnmi_pending, + .set_vnmi_pending = svm_set_vnmi_pending, + .inject_exception = svm_inject_exception, + .cancel_injection = svm_cancel_injection, + .interrupt_allowed = svm_interrupt_allowed, + .nmi_allowed = svm_nmi_allowed, + .get_nmi_mask = svm_get_nmi_mask, + .set_nmi_mask = svm_set_nmi_mask, + .enable_nmi_window = svm_enable_nmi_window, + .enable_irq_window = svm_enable_irq_window, + .update_cr8_intercept = svm_update_cr8_intercept, + .set_virtual_apic_mode = avic_refresh_virtual_apic_mode, + .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, + .apicv_post_state_restore = avic_apicv_post_state_restore, + .required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS, + + .get_exit_info = svm_get_exit_info, + + .vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid, + + .has_wbinvd_exit = svm_has_wbinvd_exit, + + .get_l2_tsc_offset = svm_get_l2_tsc_offset, + .get_l2_tsc_multiplier = svm_get_l2_tsc_multiplier, + .write_tsc_offset = svm_write_tsc_offset, + .write_tsc_multiplier = svm_write_tsc_multiplier, + + .load_mmu_pgd = svm_load_mmu_pgd, + + .check_intercept = svm_check_intercept, + .handle_exit_irqoff = svm_handle_exit_irqoff, + + .request_immediate_exit = __kvm_request_immediate_exit, + + .sched_in = svm_sched_in, + + .nested_ops = &svm_nested_ops, + + .deliver_interrupt = svm_deliver_interrupt, + .pi_update_irte = avic_pi_update_irte, + .setup_mce = svm_setup_mce, + +#ifdef CONFIG_KVM_SMM + .smi_allowed = svm_smi_allowed, + .enter_smm = svm_enter_smm, + .leave_smm = svm_leave_smm, + .enable_smi_window = svm_enable_smi_window, +#endif + + .mem_enc_ioctl = sev_mem_enc_ioctl, + .mem_enc_register_region = sev_mem_enc_register_region, + .mem_enc_unregister_region = sev_mem_enc_unregister_region, + .guest_memory_reclaimed = sev_guest_memory_reclaimed, + + .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, + .vm_move_enc_context_from = sev_vm_move_enc_context_from, + + .can_emulate_instruction = svm_can_emulate_instruction, + + .apic_init_signal_blocked = svm_apic_init_signal_blocked, + + .msr_filter_changed = svm_msr_filter_changed, + .complete_emulated_msr = svm_complete_emulated_msr, + + .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, + .vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons, +}; + +/* + * The default MMIO mask is a single bit (excluding the present bit), + * which could conflict with the memory encryption bit. Check for + * memory encryption support and override the default MMIO mask if + * memory encryption is enabled. + */ +static __init void svm_adjust_mmio_mask(void) +{ + unsigned int enc_bit, mask_bit; + u64 msr, mask; + + /* If there is no memory encryption support, use existing mask */ + if (cpuid_eax(0x80000000) < 0x8000001f) + return; + + /* If memory encryption is not enabled, use existing mask */ + rdmsrl(MSR_AMD64_SYSCFG, msr); + if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) + return; + + enc_bit = cpuid_ebx(0x8000001f) & 0x3f; + mask_bit = boot_cpu_data.x86_phys_bits; + + /* Increment the mask bit if it is the same as the encryption bit */ + if (enc_bit == mask_bit) + mask_bit++; + + /* + * If the mask bit location is below 52, then some bits above the + * physical addressing limit will always be reserved, so use the + * rsvd_bits() function to generate the mask. This mask, along with + * the present bit, will be used to generate a page fault with + * PFER.RSV = 1. + * + * If the mask bit location is 52 (or above), then clear the mask. + */ + mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0; + + kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK); +} + +static __init void svm_set_cpu_caps(void) +{ + kvm_set_cpu_caps(); + + kvm_caps.supported_perf_cap = 0; + kvm_caps.supported_xss = 0; + + /* CPUID 0x80000001 and 0x8000000A (SVM features) */ + if (nested) { + kvm_cpu_cap_set(X86_FEATURE_SVM); + kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); + + if (nrips) + kvm_cpu_cap_set(X86_FEATURE_NRIPS); + + if (npt_enabled) + kvm_cpu_cap_set(X86_FEATURE_NPT); + + if (tsc_scaling) + kvm_cpu_cap_set(X86_FEATURE_TSCRATEMSR); + + if (vls) + kvm_cpu_cap_set(X86_FEATURE_V_VMSAVE_VMLOAD); + if (lbrv) + kvm_cpu_cap_set(X86_FEATURE_LBRV); + + if (boot_cpu_has(X86_FEATURE_PAUSEFILTER)) + kvm_cpu_cap_set(X86_FEATURE_PAUSEFILTER); + + if (boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) + kvm_cpu_cap_set(X86_FEATURE_PFTHRESHOLD); + + if (vgif) + kvm_cpu_cap_set(X86_FEATURE_VGIF); + + if (vnmi) + kvm_cpu_cap_set(X86_FEATURE_VNMI); + + /* Nested VM can receive #VMEXIT instead of triggering #GP */ + kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK); + } + + /* CPUID 0x80000008 */ + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) || + boot_cpu_has(X86_FEATURE_AMD_SSBD)) + kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); + + if (enable_pmu) { + /* + * Enumerate support for PERFCTR_CORE if and only if KVM has + * access to enough counters to virtualize "core" support, + * otherwise limit vPMU support to the legacy number of counters. + */ + if (kvm_pmu_cap.num_counters_gp < AMD64_NUM_COUNTERS_CORE) + kvm_pmu_cap.num_counters_gp = min(AMD64_NUM_COUNTERS, + kvm_pmu_cap.num_counters_gp); + else + kvm_cpu_cap_check_and_set(X86_FEATURE_PERFCTR_CORE); + + if (kvm_pmu_cap.version != 2 || + !kvm_cpu_cap_has(X86_FEATURE_PERFCTR_CORE)) + kvm_cpu_cap_clear(X86_FEATURE_PERFMON_V2); + } + + /* CPUID 0x8000001F (SME/SEV features) */ + sev_set_cpu_caps(); +} + +static __init int svm_hardware_setup(void) +{ + int cpu; + struct page *iopm_pages; + void *iopm_va; + int r; + unsigned int order = get_order(IOPM_SIZE); + + /* + * NX is required for shadow paging and for NPT if the NX huge pages + * mitigation is enabled. + */ + if (!boot_cpu_has(X86_FEATURE_NX)) { + pr_err_ratelimited("NX (Execute Disable) not supported\n"); + return -EOPNOTSUPP; + } + kvm_enable_efer_bits(EFER_NX); + + iopm_pages = alloc_pages(GFP_KERNEL, order); + + if (!iopm_pages) + return -ENOMEM; + + iopm_va = page_address(iopm_pages); + memset(iopm_va, 0xff, PAGE_SIZE * (1 << order)); + iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; + + init_msrpm_offsets(); + + kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | + XFEATURE_MASK_BNDCSR); + + if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) + kvm_enable_efer_bits(EFER_FFXSR); + + if (tsc_scaling) { + if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { + tsc_scaling = false; + } else { + pr_info("TSC scaling supported\n"); + kvm_caps.has_tsc_control = true; + } + } + kvm_caps.max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX; + kvm_caps.tsc_scaling_ratio_frac_bits = 32; + + tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); + + if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) + kvm_enable_efer_bits(EFER_AUTOIBRS); + + /* Check for pause filtering support */ + if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) { + pause_filter_count = 0; + pause_filter_thresh = 0; + } else if (!boot_cpu_has(X86_FEATURE_PFTHRESHOLD)) { + pause_filter_thresh = 0; + } + + if (nested) { + pr_info("Nested Virtualization enabled\n"); + kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); + } + + /* + * KVM's MMU doesn't support using 2-level paging for itself, and thus + * NPT isn't supported if the host is using 2-level paging since host + * CR4 is unchanged on VMRUN. + */ + if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE)) + npt_enabled = false; + + if (!boot_cpu_has(X86_FEATURE_NPT)) + npt_enabled = false; + + /* Force VM NPT level equal to the host's paging level */ + kvm_configure_mmu(npt_enabled, get_npt_level(), + get_npt_level(), PG_LEVEL_1G); + pr_info("Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); + + /* Setup shadow_me_value and shadow_me_mask */ + kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); + + svm_adjust_mmio_mask(); + + nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + + /* + * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which + * may be modified by svm_adjust_mmio_mask()), as well as nrips. + */ + sev_hardware_setup(); + + svm_hv_hardware_setup(); + + for_each_possible_cpu(cpu) { + r = svm_cpu_init(cpu); + if (r) + goto err; + } + + enable_apicv = avic = avic && avic_hardware_setup(); + + if (!enable_apicv) { + svm_x86_ops.vcpu_blocking = NULL; + svm_x86_ops.vcpu_unblocking = NULL; + svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL; + } else if (!x2avic_enabled) { + svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true; + } + + if (vls) { + if (!npt_enabled || + !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) || + !IS_ENABLED(CONFIG_X86_64)) { + vls = false; + } else { + pr_info("Virtual VMLOAD VMSAVE supported\n"); + } + } + + if (boot_cpu_has(X86_FEATURE_SVME_ADDR_CHK)) + svm_gp_erratum_intercept = false; + + if (vgif) { + if (!boot_cpu_has(X86_FEATURE_VGIF)) + vgif = false; + else + pr_info("Virtual GIF supported\n"); + } + + vnmi = vgif && vnmi && boot_cpu_has(X86_FEATURE_VNMI); + if (vnmi) + pr_info("Virtual NMI enabled\n"); + + if (!vnmi) { + svm_x86_ops.is_vnmi_pending = NULL; + svm_x86_ops.set_vnmi_pending = NULL; + } + + + if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } + + if (!enable_pmu) + pr_info("PMU virtualization is disabled\n"); + + svm_set_cpu_caps(); + + /* + * It seems that on AMD processors PTE's accessed bit is + * being set by the CPU hardware before the NPF vmexit. + * This is not expected behaviour and our tests fail because + * of it. + * A workaround here is to disable support for + * GUEST_MAXPHYADDR < HOST_MAXPHYADDR if NPT is enabled. + * In this case userspace can know if there is support using + * KVM_CAP_SMALLER_MAXPHYADDR extension and decide how to handle + * it + * If future AMD CPU models change the behaviour described above, + * this variable can be changed accordingly + */ + allow_smaller_maxphyaddr = !npt_enabled; + + return 0; + +err: + svm_hardware_unsetup(); + return r; +} + + +static struct kvm_x86_init_ops svm_init_ops __initdata = { + .hardware_setup = svm_hardware_setup, + + .runtime_ops = &svm_x86_ops, + .pmu_ops = &amd_pmu_ops, +}; + +static void __svm_exit(void) +{ + kvm_x86_vendor_exit(); + + cpu_emergency_unregister_virt_callback(svm_emergency_disable); +} + +static int __init svm_init(void) +{ + int r; + + __unused_size_checks(); + + if (!kvm_is_svm_supported()) + return -EOPNOTSUPP; + + r = kvm_x86_vendor_init(&svm_init_ops); + if (r) + return r; + + cpu_emergency_register_virt_callback(svm_emergency_disable); + + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), + THIS_MODULE); + if (r) + goto err_kvm_init; + + return 0; + +err_kvm_init: + __svm_exit(); + return r; +} + +static void __exit svm_exit(void) +{ + kvm_exit(); + __svm_exit(); +} + +module_init(svm_init) +module_exit(svm_exit) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h new file mode 100644 index 0000000000..be67ab7fdd --- /dev/null +++ b/arch/x86/kvm/svm/svm.h @@ -0,0 +1,725 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * AMD SVM support + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Yaniv Kamay + * Avi Kivity + */ + +#ifndef __SVM_SVM_H +#define __SVM_SVM_H + +#include +#include +#include + +#include +#include + +#include "cpuid.h" +#include "kvm_cache_regs.h" + +#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) + +#define IOPM_SIZE PAGE_SIZE * 3 +#define MSRPM_SIZE PAGE_SIZE * 2 + +#define MAX_DIRECT_ACCESS_MSRS 46 +#define MSRPM_OFFSETS 32 +extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; +extern bool npt_enabled; +extern int nrips; +extern int vgif; +extern bool intercept_smi; +extern bool x2avic_enabled; +extern bool vnmi; + +/* + * Clean bits in VMCB. + * VMCB_ALL_CLEAN_MASK might also need to + * be updated if this enum is modified. + */ +enum { + VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, + pause filter count */ + VMCB_PERM_MAP, /* IOPM Base and MSRPM Base */ + VMCB_ASID, /* ASID */ + VMCB_INTR, /* int_ctl, int_vector */ + VMCB_NPT, /* npt_en, nCR3, gPAT */ + VMCB_CR, /* CR0, CR3, CR4, EFER */ + VMCB_DR, /* DR6, DR7 */ + VMCB_DT, /* GDT, IDT */ + VMCB_SEG, /* CS, DS, SS, ES, CPL */ + VMCB_CR2, /* CR2 only */ + VMCB_LBR, /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */ + VMCB_AVIC, /* AVIC APIC_BAR, AVIC APIC_BACKING_PAGE, + * AVIC PHYSICAL_TABLE pointer, + * AVIC LOGICAL_TABLE pointer + */ + VMCB_SW = 31, /* Reserved for hypervisor/software use */ +}; + +#define VMCB_ALL_CLEAN_MASK ( \ + (1U << VMCB_INTERCEPTS) | (1U << VMCB_PERM_MAP) | \ + (1U << VMCB_ASID) | (1U << VMCB_INTR) | \ + (1U << VMCB_NPT) | (1U << VMCB_CR) | (1U << VMCB_DR) | \ + (1U << VMCB_DT) | (1U << VMCB_SEG) | (1U << VMCB_CR2) | \ + (1U << VMCB_LBR) | (1U << VMCB_AVIC) | \ + (1U << VMCB_SW)) + +/* TPR and CR2 are always written before VMRUN */ +#define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2)) + +struct kvm_sev_info { + bool active; /* SEV enabled guest */ + bool es_active; /* SEV-ES enabled guest */ + unsigned int asid; /* ASID used for this guest */ + unsigned int handle; /* SEV firmware handle */ + int fd; /* SEV device fd */ + unsigned long pages_locked; /* Number of pages locked */ + struct list_head regions_list; /* List of registered regions */ + u64 ap_jump_table; /* SEV-ES AP Jump Table address */ + struct kvm *enc_context_owner; /* Owner of copied encryption context */ + struct list_head mirror_vms; /* List of VMs mirroring */ + struct list_head mirror_entry; /* Use as a list entry of mirrors */ + struct misc_cg *misc_cg; /* For misc cgroup accounting */ + atomic_t migration_in_progress; +}; + +struct kvm_svm { + struct kvm kvm; + + /* Struct members for AVIC */ + u32 avic_vm_id; + struct page *avic_logical_id_table_page; + struct page *avic_physical_id_table_page; + struct hlist_node hnode; + + struct kvm_sev_info sev_info; +}; + +struct kvm_vcpu; + +struct kvm_vmcb_info { + struct vmcb *ptr; + unsigned long pa; + int cpu; + uint64_t asid_generation; +}; + +struct vmcb_save_area_cached { + u64 efer; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; +}; + +struct vmcb_ctrl_area_cached { + u32 intercepts[MAX_INTERCEPT]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u32 exit_code; + u32 exit_code_hi; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 nested_ctl; + u32 event_inj; + u32 event_inj_err; + u64 next_rip; + u64 nested_cr3; + u64 virt_ext; + u32 clean; + union { + struct hv_vmcb_enlightenments hv_enlightenments; + u8 reserved_sw[32]; + }; +}; + +struct svm_nested_state { + struct kvm_vmcb_info vmcb02; + u64 hsave_msr; + u64 vm_cr_msr; + u64 vmcb12_gpa; + u64 last_vmcb12_gpa; + + /* These are the merged vectors */ + u32 *msrpm; + + /* A VMRUN has started but has not yet been performed, so + * we cannot inject a nested vmexit yet. */ + bool nested_run_pending; + + /* cache for control fields of the guest */ + struct vmcb_ctrl_area_cached ctl; + + /* + * Note: this struct is not kept up-to-date while L2 runs; it is only + * valid within nested_svm_vmrun. + */ + struct vmcb_save_area_cached save; + + bool initialized; + + /* + * Indicates whether MSR bitmap for L2 needs to be rebuilt due to + * changes in MSR bitmap for L1 or switching to a different L2. Note, + * this flag can only be used reliably in conjunction with a paravirt L1 + * which informs L0 whether any changes to MSR bitmap for L2 were done + * on its side. + */ + bool force_msr_bitmap_recalc; +}; + +struct vcpu_sev_es_state { + /* SEV-ES support */ + struct sev_es_save_area *vmsa; + struct ghcb *ghcb; + u8 valid_bitmap[16]; + struct kvm_host_map ghcb_map; + bool received_first_sipi; + + /* SEV-ES scratch area support */ + u64 sw_scratch; + void *ghcb_sa; + u32 ghcb_sa_len; + bool ghcb_sa_sync; + bool ghcb_sa_free; +}; + +struct vcpu_svm { + struct kvm_vcpu vcpu; + /* vmcb always points at current_vmcb->ptr, it's purely a shorthand. */ + struct vmcb *vmcb; + struct kvm_vmcb_info vmcb01; + struct kvm_vmcb_info *current_vmcb; + u32 asid; + u32 sysenter_esp_hi; + u32 sysenter_eip_hi; + uint64_t tsc_aux; + + u64 msr_decfg; + + u64 next_rip; + + u64 spec_ctrl; + + u64 tsc_ratio_msr; + /* + * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be + * translated into the appropriate L2_CFG bits on the host to + * perform speculative control. + */ + u64 virt_spec_ctrl; + + u32 *msrpm; + + ulong nmi_iret_rip; + + struct svm_nested_state nested; + + /* NMI mask value, used when vNMI is not enabled */ + bool nmi_masked; + + /* + * True when NMIs are still masked but guest IRET was just intercepted + * and KVM is waiting for RIP to change, which will signal that the + * intercepted IRET was retired and thus NMI can be unmasked. + */ + bool awaiting_iret_completion; + + /* + * Set when KVM is awaiting IRET completion and needs to inject NMIs as + * soon as the IRET completes (e.g. NMI is pending injection). KVM + * temporarily steals RFLAGS.TF to single-step the guest in this case + * in order to regain control as soon as the NMI-blocking condition + * goes away. + */ + bool nmi_singlestep; + u64 nmi_singlestep_guest_rflags; + + bool nmi_l1_to_l2; + + unsigned long soft_int_csbase; + unsigned long soft_int_old_rip; + unsigned long soft_int_next_rip; + bool soft_int_injected; + + u32 ldr_reg; + u32 dfr_reg; + struct page *avic_backing_page; + u64 *avic_physical_id_cache; + + /* + * Per-vcpu list of struct amd_svm_iommu_ir: + * This is used mainly to store interrupt remapping information used + * when update the vcpu affinity. This avoids the need to scan for + * IRTE and try to match ga_tag in the IOMMU driver. + */ + struct list_head ir_list; + spinlock_t ir_list_lock; + + /* Save desired MSR intercept (read: pass-through) state */ + struct { + DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS); + DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS); + } shadow_msr_intercept; + + struct vcpu_sev_es_state sev_es; + + bool guest_state_loaded; + + bool x2avic_msrs_intercepted; + + /* Guest GIF value, used when vGIF is not enabled */ + bool guest_gif; +}; + +struct svm_cpu_data { + u64 asid_generation; + u32 max_asid; + u32 next_asid; + u32 min_asid; + + struct page *save_area; + unsigned long save_area_pa; + + struct vmcb *current_vmcb; + + /* index = sev_asid, value = vmcb pointer */ + struct vmcb **sev_vmcbs; +}; + +DECLARE_PER_CPU(struct svm_cpu_data, svm_data); + +void recalc_intercepts(struct vcpu_svm *svm); + +static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) +{ + return container_of(kvm, struct kvm_svm, kvm); +} + +static __always_inline bool sev_guest(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_AMD_SEV + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return sev->active; +#else + return false; +#endif +} + +static __always_inline bool sev_es_guest(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_AMD_SEV + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + return sev->es_active && !WARN_ON_ONCE(!sev->active); +#else + return false; +#endif +} + +static inline void vmcb_mark_all_dirty(struct vmcb *vmcb) +{ + vmcb->control.clean = 0; +} + +static inline void vmcb_mark_all_clean(struct vmcb *vmcb) +{ + vmcb->control.clean = VMCB_ALL_CLEAN_MASK + & ~VMCB_ALWAYS_DIRTY_MASK; +} + +static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit) +{ + vmcb->control.clean &= ~(1 << bit); +} + +static inline bool vmcb_is_dirty(struct vmcb *vmcb, int bit) +{ + return !test_bit(bit, (unsigned long *)&vmcb->control.clean); +} + +static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) +{ + return container_of(vcpu, struct vcpu_svm, vcpu); +} + +/* + * Only the PDPTRs are loaded on demand into the shadow MMU. All other + * fields are synchronized on VM-Exit, because accessing the VMCB is cheap. + * + * CR3 might be out of date in the VMCB but it is not marked dirty; instead, + * KVM_REQ_LOAD_MMU_PGD is always requested when the cached vcpu->arch.cr3 + * is changed. svm_load_mmu_pgd() then syncs the new CR3 value into the VMCB. + */ +#define SVM_REGS_LAZY_LOAD_SET (1 << VCPU_EXREG_PDPTR) + +static inline void vmcb_set_intercept(struct vmcb_control_area *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + __set_bit(bit, (unsigned long *)&control->intercepts); +} + +static inline void vmcb_clr_intercept(struct vmcb_control_area *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + __clear_bit(bit, (unsigned long *)&control->intercepts); +} + +static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + return test_bit(bit, (unsigned long *)&control->intercepts); +} + +static inline bool vmcb12_is_intercept(struct vmcb_ctrl_area_cached *control, u32 bit) +{ + WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT); + return test_bit(bit, (unsigned long *)&control->intercepts); +} + +static inline void set_exception_intercept(struct vcpu_svm *svm, u32 bit) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + WARN_ON_ONCE(bit >= 32); + vmcb_set_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit); + + recalc_intercepts(svm); +} + +static inline void clr_exception_intercept(struct vcpu_svm *svm, u32 bit) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + WARN_ON_ONCE(bit >= 32); + vmcb_clr_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit); + + recalc_intercepts(svm); +} + +static inline void svm_set_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb_set_intercept(&vmcb->control, bit); + + recalc_intercepts(svm); +} + +static inline void svm_clr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb_clr_intercept(&vmcb->control, bit); + + recalc_intercepts(svm); +} + +static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit) +{ + return vmcb_is_intercept(&svm->vmcb->control, bit); +} + +static inline bool nested_vgif_enabled(struct vcpu_svm *svm) +{ + return guest_can_use(&svm->vcpu, X86_FEATURE_VGIF) && + (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK); +} + +static inline struct vmcb *get_vgif_vmcb(struct vcpu_svm *svm) +{ + if (!vgif) + return NULL; + + if (is_guest_mode(&svm->vcpu) && !nested_vgif_enabled(svm)) + return svm->nested.vmcb02.ptr; + else + return svm->vmcb01.ptr; +} + +static inline void enable_gif(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_vgif_vmcb(svm); + + if (vmcb) + vmcb->control.int_ctl |= V_GIF_MASK; + else + svm->guest_gif = true; +} + +static inline void disable_gif(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_vgif_vmcb(svm); + + if (vmcb) + vmcb->control.int_ctl &= ~V_GIF_MASK; + else + svm->guest_gif = false; +} + +static inline bool gif_set(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_vgif_vmcb(svm); + + if (vmcb) + return !!(vmcb->control.int_ctl & V_GIF_MASK); + else + return svm->guest_gif; +} + +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 guest_can_use(&svm->vcpu, X86_FEATURE_VNMI) && + (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 */ + u32 msr = offset * 16; + + return (msr >= APIC_BASE_MSR) && + (msr < (APIC_BASE_MSR + 0x100)); +} + +static inline struct vmcb *get_vnmi_vmcb_l1(struct vcpu_svm *svm) +{ + if (!vnmi) + return NULL; + + if (is_guest_mode(&svm->vcpu)) + return NULL; + else + return svm->vmcb01.ptr; +} + +static inline bool is_vnmi_enabled(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_vnmi_vmcb_l1(svm); + + if (vmcb) + return !!(vmcb->control.int_ctl & V_NMI_ENABLE_MASK); + else + return false; +} + +/* svm.c */ +#define MSR_INVALID 0xffffffffU + +#define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) + +extern bool dump_invalid_vmcb; + +u32 svm_msrpm_offset(u32 msr); +u32 *svm_vcpu_alloc_msrpm(void); +void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); +void svm_vcpu_free_msrpm(u32 *msrpm); +void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +void svm_update_lbrv(struct kvm_vcpu *vcpu); + +int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); +void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +void disable_nmi_singlestep(struct vcpu_svm *svm); +bool svm_smi_blocked(struct kvm_vcpu *vcpu); +bool svm_nmi_blocked(struct kvm_vcpu *vcpu); +bool svm_interrupt_blocked(struct kvm_vcpu *vcpu); +void svm_set_gif(struct vcpu_svm *svm, bool value); +int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code); +void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, + int read, int write); +void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool disable); +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vec); + +/* nested.c */ + +#define NESTED_EXIT_HOST 0 /* Exit handled on host level */ +#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ +#define NESTED_EXIT_CONTINUE 2 /* Further checks needed */ + +static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return is_guest_mode(vcpu) && (svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK); +} + +static inline bool nested_exit_on_smi(struct vcpu_svm *svm) +{ + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); +} + +static inline bool nested_exit_on_intr(struct vcpu_svm *svm) +{ + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); +} + +static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) +{ + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); +} + +int enter_svm_guest_mode(struct kvm_vcpu *vcpu, + u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); +void svm_leave_nested(struct kvm_vcpu *vcpu); +void svm_free_nested(struct vcpu_svm *svm); +int svm_allocate_nested(struct vcpu_svm *svm); +int nested_svm_vmrun(struct kvm_vcpu *vcpu); +void svm_copy_vmrun_state(struct vmcb_save_area *to_save, + struct vmcb_save_area *from_save); +void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +int nested_svm_vmexit(struct vcpu_svm *svm); + +static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code) +{ + svm->vmcb->control.exit_code = exit_code; + svm->vmcb->control.exit_info_1 = 0; + svm->vmcb->control.exit_info_2 = 0; + return nested_svm_vmexit(svm); +} + +int nested_svm_exit_handled(struct vcpu_svm *svm); +int nested_svm_check_permissions(struct kvm_vcpu *vcpu); +int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, + bool has_error_code, u32 error_code); +int nested_svm_exit_special(struct vcpu_svm *svm); +void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); +void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu); +void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, + struct vmcb_control_area *control); +void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm, + struct vmcb_save_area *save); +void nested_sync_control_from_vmcb02(struct vcpu_svm *svm); +void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm); +void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); + +extern struct kvm_x86_nested_ops svm_nested_ops; + +/* avic.c */ +#define AVIC_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE) | \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_NESTED) | \ + BIT(APICV_INHIBIT_REASON_IRQWIN) | \ + BIT(APICV_INHIBIT_REASON_PIT_REINJ) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_SEV) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) \ +) + +bool avic_hardware_setup(void); +int avic_ga_log_notifier(u32 ga_tag); +void avic_vm_destroy(struct kvm *kvm); +int avic_vm_init(struct kvm *kvm); +void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb); +int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu); +int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu); +int avic_init_vcpu(struct vcpu_svm *svm); +void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); +void avic_vcpu_put(struct kvm_vcpu *vcpu); +void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); +void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); +int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set); +void avic_vcpu_blocking(struct kvm_vcpu *vcpu); +void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); +void avic_ring_doorbell(struct kvm_vcpu *vcpu); +unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu); +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu); + + +/* sev.c */ + +#define GHCB_VERSION_MAX 1ULL +#define GHCB_VERSION_MIN 1ULL + + +extern unsigned int max_sev_asid; + +void sev_vm_destroy(struct kvm *kvm); +int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp); +int sev_mem_enc_register_region(struct kvm *kvm, + struct kvm_enc_region *range); +int sev_mem_enc_unregister_region(struct kvm *kvm, + struct kvm_enc_region *range); +int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd); +int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd); +void sev_guest_memory_reclaimed(struct kvm *kvm); + +void pre_sev_run(struct vcpu_svm *svm, int cpu); +void __init sev_set_cpu_caps(void); +void __init sev_hardware_setup(void); +void sev_hardware_unsetup(void); +int sev_cpu_init(struct svm_cpu_data *sd); +void sev_init_vmcb(struct vcpu_svm *svm); +void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm); +void sev_free_vcpu(struct kvm_vcpu *vcpu); +int sev_handle_vmgexit(struct kvm_vcpu *vcpu); +int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in); +void sev_es_vcpu_reset(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); +void sev_es_unmap_ghcb(struct vcpu_svm *svm); + +/* vmenter.S */ + +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); + +#define DEFINE_KVM_GHCB_ACCESSORS(field) \ + static __always_inline bool kvm_ghcb_##field##_is_valid(const struct vcpu_svm *svm) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&svm->sev_es.valid_bitmap); \ + } \ + \ + static __always_inline u64 kvm_ghcb_get_##field##_if_valid(struct vcpu_svm *svm, struct ghcb *ghcb) \ + { \ + return kvm_ghcb_##field##_is_valid(svm) ? ghcb->save.field : 0; \ + } \ + +DEFINE_KVM_GHCB_ACCESSORS(cpl) +DEFINE_KVM_GHCB_ACCESSORS(rax) +DEFINE_KVM_GHCB_ACCESSORS(rcx) +DEFINE_KVM_GHCB_ACCESSORS(rdx) +DEFINE_KVM_GHCB_ACCESSORS(rbx) +DEFINE_KVM_GHCB_ACCESSORS(rsi) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_code) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_KVM_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_KVM_GHCB_ACCESSORS(sw_scratch) +DEFINE_KVM_GHCB_ACCESSORS(xcr0) + +#endif diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c new file mode 100644 index 0000000000..7af8422d33 --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM L1 hypervisor optimizations on Hyper-V for SVM. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include + +#include + +#include "svm.h" +#include "svm_ops.h" + +#include "hyperv.h" +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" + +int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) +{ + struct hv_vmcb_enlightenments *hve; + struct hv_partition_assist_pg **p_hv_pa_pg = + &to_kvm_hv(vcpu->kvm)->hv_pa_pg; + + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); + + if (!*p_hv_pa_pg) + return -ENOMEM; + + hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments; + + hve->partition_assist_page = __pa(*p_hv_pa_pg); + 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; +} + diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h new file mode 100644 index 0000000000..f85bc617ff --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -0,0 +1,116 @@ +/* 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 + +#if IS_ENABLED(CONFIG_HYPERV) + +#include "kvm_onhyperv.h" +#include "svm/hyperv.h" + +static struct kvm_x86_ops svm_x86_ops; + +int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu); + +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 __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; + } +} + +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__ */ diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h new file mode 100644 index 0000000000..36c8af87a7 --- /dev/null +++ b/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 + +#include "x86.h" + +#define svm_asm(insn, clobber...) \ +do { \ + asm_volatile_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_volatile_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_volatile_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 */ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S new file mode 100644 index 0000000000..ef2ebabb05 --- /dev/null +++ b/arch/x86/kvm/svm/vmenter.S @@ -0,0 +1,390 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include +#include +#include +#include "kvm-asm-offsets.h" + +#define WORD_SIZE (BITS_PER_LONG / 8) + +/* Intentionally omit RAX as it's context switched by hardware */ +#define VCPU_RCX (SVM_vcpu_arch_regs + __VCPU_REGS_RCX * WORD_SIZE) +#define VCPU_RDX (SVM_vcpu_arch_regs + __VCPU_REGS_RDX * WORD_SIZE) +#define VCPU_RBX (SVM_vcpu_arch_regs + __VCPU_REGS_RBX * WORD_SIZE) +/* Intentionally omit RSP as it's context switched by hardware */ +#define VCPU_RBP (SVM_vcpu_arch_regs + __VCPU_REGS_RBP * WORD_SIZE) +#define VCPU_RSI (SVM_vcpu_arch_regs + __VCPU_REGS_RSI * WORD_SIZE) +#define VCPU_RDI (SVM_vcpu_arch_regs + __VCPU_REGS_RDI * WORD_SIZE) + +#ifdef CONFIG_X86_64 +#define VCPU_R8 (SVM_vcpu_arch_regs + __VCPU_REGS_R8 * WORD_SIZE) +#define VCPU_R9 (SVM_vcpu_arch_regs + __VCPU_REGS_R9 * WORD_SIZE) +#define VCPU_R10 (SVM_vcpu_arch_regs + __VCPU_REGS_R10 * WORD_SIZE) +#define VCPU_R11 (SVM_vcpu_arch_regs + __VCPU_REGS_R11 * WORD_SIZE) +#define VCPU_R12 (SVM_vcpu_arch_regs + __VCPU_REGS_R12 * WORD_SIZE) +#define VCPU_R13 (SVM_vcpu_arch_regs + __VCPU_REGS_R13 * WORD_SIZE) +#define VCPU_R14 (SVM_vcpu_arch_regs + __VCPU_REGS_R14 * WORD_SIZE) +#define VCPU_R15 (SVM_vcpu_arch_regs + __VCPU_REGS_R15 * WORD_SIZE) +#endif + +#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 +801: +.endm +.macro RESTORE_GUEST_SPEC_CTRL_BODY +800: + /* + * SPEC_CTRL handling: if the guest's SPEC_CTRL value differs from the + * host's, write the MSR. This is kept out-of-line so that the common + * case does not have to jump. + * + * IMPORTANT: To avoid RSB underflow attacks and any other nastiness, + * there must not be any returns or indirect branches between this code + * and vmentry. + */ + movl SVM_spec_ctrl(%_ASM_DI), %eax + cmp PER_CPU_VAR(x86_spec_ctrl_current), %eax + je 801b + mov $MSR_IA32_SPEC_CTRL, %ecx + xor %edx, %edx + wrmsr + jmp 801b +.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 +901: +.endm +.macro RESTORE_HOST_SPEC_CTRL_BODY +900: + /* Same for after vmexit. */ + mov $MSR_IA32_SPEC_CTRL, %ecx + + /* + * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, + * if it was not intercepted during guest execution. + */ + cmpb $0, (%_ASM_SP) + jnz 998f + rdmsr + movl %eax, SVM_spec_ctrl(%_ASM_DI) +998: + + /* Now restore the host value of the MSR if different from the guest's. */ + movl PER_CPU_VAR(x86_spec_ctrl_current), %eax + cmp SVM_spec_ctrl(%_ASM_DI), %eax + je 901b + xor %edx, %edx + wrmsr + jmp 901b +.endm + + +/** + * __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode + * @svm: struct vcpu_svm * + * @spec_ctrl_intercepted: bool + */ +SYM_FUNC_START(__svm_vcpu_run) + push %_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. */ + RESTORE_GUEST_SPEC_CTRL + + /* + * 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. */ + mov VCPU_RCX(%_ASM_DI), %_ASM_CX + mov VCPU_RDX(%_ASM_DI), %_ASM_DX + mov VCPU_RBX(%_ASM_DI), %_ASM_BX + mov VCPU_RBP(%_ASM_DI), %_ASM_BP + mov VCPU_RSI(%_ASM_DI), %_ASM_SI +#ifdef CONFIG_X86_64 + mov VCPU_R8 (%_ASM_DI), %r8 + mov VCPU_R9 (%_ASM_DI), %r9 + mov VCPU_R10(%_ASM_DI), %r10 + mov VCPU_R11(%_ASM_DI), %r11 + mov VCPU_R12(%_ASM_DI), %r12 + mov VCPU_R13(%_ASM_DI), %r13 + mov VCPU_R14(%_ASM_DI), %r14 + mov VCPU_R15(%_ASM_DI), %r15 +#endif + mov VCPU_RDI(%_ASM_DI), %_ASM_DI + + /* Enter guest mode */ + sti + +3: vmrun %_ASM_AX +4: + cli + + /* Pop @svm to RAX while it's the only available register. */ + pop %_ASM_AX + + /* Save all guest registers. */ + mov %_ASM_CX, VCPU_RCX(%_ASM_AX) + mov %_ASM_DX, VCPU_RDX(%_ASM_AX) + mov %_ASM_BX, VCPU_RBX(%_ASM_AX) + mov %_ASM_BP, VCPU_RBP(%_ASM_AX) + mov %_ASM_SI, VCPU_RSI(%_ASM_AX) + mov %_ASM_DI, VCPU_RDI(%_ASM_AX) +#ifdef CONFIG_X86_64 + mov %r8, VCPU_R8 (%_ASM_AX) + mov %r9, VCPU_R9 (%_ASM_AX) + mov %r10, VCPU_R10(%_ASM_AX) + mov %r11, VCPU_R11(%_ASM_AX) + mov %r12, VCPU_R12(%_ASM_AX) + mov %r13, VCPU_R13(%_ASM_AX) + mov %r14, VCPU_R14(%_ASM_AX) + mov %r15, VCPU_R15(%_ASM_AX) +#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: + +#ifdef CONFIG_RETPOLINE + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE +#endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_HOST_SPEC_CTRL + + /* + * 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. + */ + xor %ecx, %ecx + xor %edx, %edx + xor %ebx, %ebx + xor %ebp, %ebp + xor %esi, %esi + xor %edi, %edi +#ifdef CONFIG_X86_64 + xor %r8d, %r8d + xor %r9d, %r9d + xor %r10d, %r10d + xor %r11d, %r11d + xor %r12d, %r12d + xor %r13d, %r13d + xor %r14d, %r14d + xor %r15d, %r15d +#endif + + /* "Pop" @spec_ctrl_intercepted. */ + 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 + + RESTORE_GUEST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY + +10: cmpb $0, kvm_rebooting + jne 2b + ud2 +30: cmpb $0, kvm_rebooting + jne 4b + ud2 +50: cmpb $0, kvm_rebooting + jne 6b + ud2 +70: cmpb $0, kvm_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) + +/** + * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode + * @svm: struct vcpu_svm * + * @spec_ctrl_intercepted: bool + */ +SYM_FUNC_START(__svm_sev_es_vcpu_run) + push %_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 + + /* 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. */ + RESTORE_GUEST_SPEC_CTRL + + /* Get svm->current_vmcb->pa into RAX. */ + mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX + mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX + + /* Enter guest mode */ + sti + +1: vmrun %_ASM_AX + +2: cli + + /* Pop @svm to RDI, guest registers have been saved already. */ + pop %_ASM_DI + +#ifdef CONFIG_RETPOLINE + /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ + FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE +#endif + + /* Clobbers RAX, RCX, RDX. */ + RESTORE_HOST_SPEC_CTRL + + /* + * 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 + + /* "Pop" @spec_ctrl_intercepted. */ + 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 + + RESTORE_GUEST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY + +3: cmpb $0, kvm_rebooting + jne 2b + ud2 + + _ASM_EXTABLE(1b, 3b) + +SYM_FUNC_END(__svm_sev_es_vcpu_run) -- cgit v1.2.3