diff options
Diffstat (limited to 'arch/x86/kvm/svm')
| -rw-r--r-- | arch/x86/kvm/svm/avic.c | 516 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/hyperv.h | 35 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/nested.c | 1181 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/pmu.c | 70 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/sev.c | 1743 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/svm.c | 2596 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/svm.h | 414 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/svm_onhyperv.c | 40 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/svm_onhyperv.h | 103 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/svm_ops.h | 6 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/vmenter.S | 51 |
11 files changed, 4377 insertions, 2378 deletions
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 78bdcfac4e40..d1bc5820ea46 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,26 +27,6 @@ #include "irq.h" #include "svm.h" -/* enable / disable AVIC */ -int avic; -#ifdef CONFIG_X86_LOCAL_APIC -module_param(avic, int, S_IRUGO); -#endif - -#define SVM_AVIC_DOORBELL 0xc001011b - -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - -/* - * 0xff is broadcast, so the max index allowed for physical APIC ID - * table is 0xfe. APIC IDs above 0xff are reserved. - */ -#define AVIC_MAX_PHYSICAL_ID_COUNT 255 - -#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 -#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 -#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF - /* AVIC GATAG is encoded using VM and VCPU IDs */ #define AVIC_VCPU_ID_BITS 8 #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) @@ -79,12 +59,6 @@ struct amd_svm_iommu_ir { void *data; /* Storing pointer to struct amd_ir_data */ }; -enum avic_ipi_failure_cause { - AVIC_IPI_FAILURE_INVALID_INT_TYPE, - AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, - AVIC_IPI_FAILURE_INVALID_TARGET, - AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, -}; /* Note: * This function is called from IOMMU driver to notify @@ -126,7 +100,7 @@ void avic_vm_destroy(struct kvm *kvm) unsigned long flags; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); - if (!avic) + if (!enable_apicv) return; if (kvm_svm->avic_logical_id_table_page) @@ -149,7 +123,7 @@ int avic_vm_init(struct kvm *kvm) struct page *l_page; u32 vm_id; - if (!avic) + if (!enable_apicv) return 0; /* Allocating physical APIC ID table (4KB) */ @@ -191,9 +165,8 @@ free_avic: return err; } -void avic_init_vmcb(struct vcpu_svm *svm) +void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) { - struct vmcb *vmcb = svm->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)); @@ -203,6 +176,8 @@ void avic_init_vmcb(struct vcpu_svm *svm) vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT; + vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK; + if (kvm_apicv_activated(svm->vcpu.kvm)) vmcb->control.int_ctl |= AVIC_ENABLE_MASK; else @@ -223,7 +198,7 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, return &avic_physical_id_table[index]; } -/** +/* * Note: * AVIC hardware walks the nested page table to check permissions, * but does not use the SPA address specified in the leaf page @@ -231,31 +206,26 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, * field of the VMCB. Therefore, we set up the * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. */ -static int avic_update_access_page(struct kvm *kvm, bool activate) +static int avic_alloc_access_page(struct kvm *kvm) { void __user *ret; int r = 0; mutex_lock(&kvm->slots_lock); - /* - * During kvm_destroy_vm(), kvm_pit_set_reinject() could trigger - * APICv mode change, which update APIC_ACCESS_PAGE_PRIVATE_MEMSLOT - * memory region. So, we need to ensure that kvm->mm == current->mm. - */ - if ((kvm->arch.apic_access_page_done == activate) || - (kvm->mm != current->mm)) + + if (kvm->arch.apic_access_memslot_enabled) goto out; ret = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, APIC_DEFAULT_PHYS_BASE, - activate ? PAGE_SIZE : 0); + PAGE_SIZE); if (IS_ERR(ret)) { r = PTR_ERR(ret); goto out; } - kvm->arch.apic_access_page_done = activate; + kvm->arch.apic_access_memslot_enabled = true; out: mutex_unlock(&kvm->slots_lock); return r; @@ -270,18 +240,18 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (id >= AVIC_MAX_PHYSICAL_ID_COUNT) return -EINVAL; - if (!svm->vcpu.arch.apic->regs) + if (!vcpu->arch.apic->regs) return -EINVAL; if (kvm_apicv_activated(vcpu->kvm)) { int ret; - ret = avic_update_access_page(vcpu->kvm, true); + ret = avic_alloc_access_page(vcpu->kvm); if (ret) return ret; } - svm->avic_backing_page = virt_to_page(svm->vcpu.arch.apic->regs); + 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); @@ -298,48 +268,172 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) 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)); + put_cpu(); +} + +/* + * 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) +{ + u32 l1_physical_id, dest; + struct kvm_vcpu *target_vcpu; + int dest_mode = icrl & APIC_DEST_MASK; + int shorthand = icrl & APIC_SHORT_MASK; + struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + + if (shorthand != APIC_DEST_NOSHORT) + return -EINVAL; + + if (apic_x2apic_mode(source)) + dest = icrh; + else + dest = GET_APIC_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; + + l1_physical_id = dest; + + if (WARN_ON_ONCE(l1_physical_id != index)) + return -EINVAL; + + } else { + u32 bitmap, cluster; + int logid_index; + + if (apic_x2apic_mode(source)) { + /* 16 bit dest mask, 16 bit cluster id */ + bitmap = dest & 0xFFFF0000; + 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; + } + + if (unlikely(!bitmap)) + /* guest bug: nobody to send the logical interrupt to */ + return 0; + + if (!is_power_of_2(bitmap)) + /* multiple logical destinations, use slow path */ + return -EINVAL; + + logid_index = cluster + __ffs(bitmap); + + if (apic_x2apic_mode(source)) { + l1_physical_id = logid_index; + } else { + u32 *avic_logical_id_table = + page_address(kvm_svm->avic_logical_id_table_page); + + u32 logid_entry = avic_logical_id_table[logid_index]; + + if (WARN_ON_ONCE(index != logid_index)) + return -EINVAL; + + /* guest bug: non existing/reserved logical destination */ + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) + return 0; + + l1_physical_id = logid_entry & + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + } + } + + target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id); + if (unlikely(!target_vcpu)) + /* guest bug: non existing vCPU is a target of this IPI*/ + return 0; + + target_vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(target_vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + return 0; +} + static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, - u32 icrl, u32 icrh) + u32 icrl, u32 icrh, u32 index) { + unsigned long i; struct kvm_vcpu *vcpu; - int i; - kvm_for_each_vcpu(i, vcpu, kvm) { - bool m = kvm_apic_match_dest(vcpu, source, - icrl & APIC_SHORT_MASK, - GET_APIC_DEST_FIELD(icrh), - icrl & APIC_DEST_MASK); + if (!avic_kick_target_vcpus_fast(kvm, source, icrl, icrh, index)) + return; - if (m && !avic_vcpu_is_running(vcpu)) - kvm_vcpu_wake_up(vcpu); + 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, + GET_APIC_DEST_FIELD(icrh), + icrl & APIC_DEST_MASK)) { + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + } } } -int avic_incomplete_ipi_interception(struct vcpu_svm *svm) +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 & 0xFF; - struct kvm_lapic *apic = svm->vcpu.arch.apic; + u32 index = svm->vmcb->control.exit_info_2 & 0x1FF; + struct kvm_lapic *apic = vcpu->arch.apic; - trace_kvm_avic_incomplete_ipi(svm->vcpu.vcpu_id, icrh, icrl, id, index); + trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index); switch (id) { case AVIC_IPI_FAILURE_INVALID_INT_TYPE: /* - * AVIC hardware handles the generation of - * IPIs when the specified Message Type is Fixed - * (also known as fixed delivery mode) and - * the Trigger Mode is edge-triggered. The hardware - * also supports self and broadcast delivery modes - * specified via the Destination Shorthand(DSH) - * field of the ICRL. Logical and physical APIC ID - * formats are supported. All other IPI types cause - * a #VMEXIT, which needs to emulated. + * Emulate IPIs that are not handled by AVIC hardware, which + * only virtualizes Fixed, Edge-Triggered INTRs. 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. */ - kvm_lapic_reg_write(apic, APIC_ICR2, icrh); - kvm_lapic_reg_write(apic, APIC_ICR, icrl); + 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: /* @@ -347,11 +441,9 @@ int avic_incomplete_ipi_interception(struct vcpu_svm *svm) * set the appropriate IRR bits on the valid target * vcpus. So, we just need to kick the appropriate vcpu. */ - avic_kick_target_vcpus(svm->vcpu.kvm, apic, icrl, icrh); + avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh, index); break; case AVIC_IPI_FAILURE_INVALID_TARGET: - WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", - index, svm->vcpu.vcpu_id, icrh, icrl); break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); @@ -363,6 +455,13 @@ int avic_incomplete_ipi_interception(struct vcpu_svm *svm) 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); @@ -442,35 +541,6 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) return ret; } -static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu) -{ - u64 *old, *new; - struct vcpu_svm *svm = to_svm(vcpu); - u32 id = kvm_xapic_id(vcpu->arch.apic); - - if (vcpu->vcpu_id == id) - return 0; - - old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id); - new = avic_get_physical_id_entry(vcpu, id); - if (!new || !old) - return 1; - - /* We need to move physical_id_entry to new offset */ - *new = *old; - *old = 0ULL; - to_svm(vcpu)->avic_physical_id_cache = new; - - /* - * Also update the guest physical APIC ID in the logical - * APIC ID table entry if already setup the LDR. - */ - if (svm->ldr_reg) - avic_handle_ldr_update(vcpu); - - return 0; -} - static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -483,30 +553,24 @@ static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) svm->dfr_reg = dfr; } -static int avic_unaccel_trap_write(struct vcpu_svm *svm) +static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu) { - struct kvm_lapic *apic = svm->vcpu.arch.apic; - u32 offset = svm->vmcb->control.exit_info_1 & + u32 offset = to_svm(vcpu)->vmcb->control.exit_info_1 & AVIC_UNACCEL_ACCESS_OFFSET_MASK; switch (offset) { - case APIC_ID: - if (avic_handle_apic_id_update(&svm->vcpu)) - return 0; - break; case APIC_LDR: - if (avic_handle_ldr_update(&svm->vcpu)) + if (avic_handle_ldr_update(vcpu)) return 0; break; case APIC_DFR: - avic_handle_dfr_update(&svm->vcpu); + avic_handle_dfr_update(vcpu); break; default: break; } - kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); - + kvm_apic_write_nodecode(vcpu, offset); return 1; } @@ -539,8 +603,9 @@ static bool is_avic_unaccelerated_access_trap(u32 offset) return ret; } -int avic_unaccelerated_access_interception(struct vcpu_svm *svm) +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; @@ -550,15 +615,15 @@ int avic_unaccelerated_access_interception(struct vcpu_svm *svm) AVIC_UNACCEL_ACCESS_WRITE_MASK; bool trap = is_avic_unaccelerated_access_trap(offset); - trace_kvm_avic_unaccelerated_access(svm->vcpu.vcpu_id, 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(svm); + ret = avic_unaccel_trap_write(vcpu); } else { /* Handling Fault */ - ret = kvm_emulate_instruction(&svm->vcpu, 0); + ret = kvm_emulate_instruction(vcpu, 0); } return ret; @@ -569,10 +634,10 @@ int avic_init_vcpu(struct vcpu_svm *svm) int ret; struct kvm_vcpu *vcpu = &svm->vcpu; - if (!avic || !irqchip_in_kernel(vcpu->kvm)) + if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm)) return 0; - ret = avic_init_backing_page(&svm->vcpu); + ret = avic_init_backing_page(vcpu); if (ret) return ret; @@ -583,39 +648,13 @@ int avic_init_vcpu(struct vcpu_svm *svm) return ret; } -void avic_post_state_restore(struct kvm_vcpu *vcpu) +void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) { - if (avic_handle_apic_id_update(vcpu) != 0) - return; avic_handle_dfr_update(vcpu); avic_handle_ldr_update(vcpu); } -void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate) -{ - if (!avic || !lapic_in_kernel(vcpu)) - return; - - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - kvm_request_apicv_update(vcpu->kvm, activate, - APICV_INHIBIT_REASON_IRQWIN); - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); -} - -void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) -{ - return; -} - -void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ -} - -void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) -{ -} - -static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) +static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) { int ret = 0; unsigned long flags; @@ -647,63 +686,6 @@ out: return ret; } -void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; - bool activated = kvm_vcpu_apicv_active(vcpu); - - if (!avic) - return; - - if (activated) { - /** - * 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_post_state_restore(vcpu); - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - } else { - vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; - } - vmcb_mark_dirty(vmcb, VMCB_AVIC); - - svm_set_pi_irte_mode(vcpu, activated); -} - -void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) -{ - return; -} - -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) -{ - if (!vcpu->arch.apicv_active) - return -1; - - kvm_lapic_set_irr(vec, vcpu->arch.apic); - smp_mb__after_atomic(); - - if (avic_vcpu_is_running(vcpu)) { - int cpuid = vcpu->cpu; - - if (cpuid != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid)); - put_cpu(); - } else - kvm_vcpu_wake_up(vcpu); - - return 0; -} - -bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) -{ - return false; -} - static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) { unsigned long flags; @@ -727,7 +709,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) struct amd_svm_iommu_ir *ir; /** - * In some cases, the existing irte is updaed and re-set, + * 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. */ @@ -764,7 +746,7 @@ out: return ret; } -/** +/* * Note: * The HW cannot support posting multicast/broadcast * interrupts to a vCPU. So, we still use legacy interrupt @@ -801,7 +783,7 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, } /* - * svm_update_pi_irte - set IRTE for Posted-Interrupts + * avic_pi_update_irte - set IRTE for Posted-Interrupts * * @kvm: kvm * @host_irq: host irq of the interrupt @@ -809,12 +791,12 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, * @set: set or unset PI * returns 0 on success, < 0 on failure */ -int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set) +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 = -EINVAL; + int idx, ret = 0; if (!kvm_arch_has_assigned_device(kvm) || !irq_remapping_cap(IRQ_POSTING_CAP)) @@ -825,7 +807,13 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, idx = srcu_read_lock(&kvm->irq_srcu); irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - WARN_ON(guest_irq >= irq_rt->nr_rt_entries); + + 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; @@ -838,7 +826,7 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * 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 virtialization is disabled for the vcpu. + * 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 && @@ -910,22 +898,23 @@ out: return ret; } -bool svm_check_apicv_inhibit_reasons(ulong bit) +bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) { ulong supported = 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_X2APIC); + BIT(APICV_INHIBIT_REASON_X2APIC) | + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | + BIT(APICV_INHIBIT_REASON_SEV) | + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); - return supported & BIT(bit); + return supported & BIT(reason); } -void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate) -{ - avic_update_access_page(kvm, activate); -} static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) @@ -960,18 +949,22 @@ out: void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; - /* ID = 0xff (broadcast), ID > 0xff (reserved) */ int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); - if (!kvm_vcpu_apicv_active(vcpu)) + lockdep_assert_preemption_disabled(); + + if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) return; /* - * Since the host physical APIC id is 8 bits, - * we can support host APIC ID upto 255. + * 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 (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) + if (kvm_vcpu_is_blocking(vcpu)) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); @@ -979,14 +972,10 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) 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; - if (svm->avic_is_running) - entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_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, - svm->avic_is_running); + avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true); } void avic_vcpu_put(struct kvm_vcpu *vcpu) @@ -994,39 +983,78 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) u64 entry; struct vcpu_svm *svm = to_svm(vcpu); - if (!kvm_vcpu_apicv_active(vcpu)) - return; + lockdep_assert_preemption_disabled(); entry = READ_ONCE(*(svm->avic_physical_id_cache)); - if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) - avic_update_iommu_vcpu_affinity(vcpu, -1, 0); + + /* Nothing to do if IsRunning == '0' due to vCPU blocking. */ + if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) + return; + + avic_update_iommu_vcpu_affinity(vcpu, -1, 0); entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK; WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } -/** - * This function is called during VCPU halt/unhalt. - */ -static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) + +void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb01.ptr; + bool activated = kvm_vcpu_apicv_active(vcpu); + + if (!enable_apicv) + return; + + if (activated) { + /** + * 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); + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + } else { + vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + } + vmcb_mark_dirty(vmcb, VMCB_AVIC); - svm->avic_is_running = is_run; - if (is_run) + if (activated) avic_vcpu_load(vcpu, vcpu->cpu); else avic_vcpu_put(vcpu); + + avic_set_pi_irte_mode(vcpu, activated); } -void svm_vcpu_blocking(struct kvm_vcpu *vcpu) +void avic_vcpu_blocking(struct kvm_vcpu *vcpu) { - avic_set_running(vcpu, false); + 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 svm_vcpu_unblocking(struct kvm_vcpu *vcpu) +void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) { - if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) - kvm_vcpu_update_apicv(vcpu); - avic_set_running(vcpu, true); + if (!kvm_vcpu_apicv_active(vcpu)) + return; + + avic_vcpu_load(vcpu, vcpu->cpu); } diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h new file mode 100644 index 000000000000..7d6d97968fb9 --- /dev/null +++ b/arch/x86/kvm/svm/hyperv.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Common Hyper-V on KVM and KVM on Hyper-V definitions (SVM). + */ + +#ifndef __ARCH_X86_KVM_SVM_HYPERV_H__ +#define __ARCH_X86_KVM_SVM_HYPERV_H__ + +#include <asm/mshyperv.h> + +#include "../hyperv.h" + +/* + * Hyper-V uses the software reserved 32 bytes in VMCB + * control area to expose SVM enlightenments to guests. + */ +struct hv_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB + */ +#define VMCB_HV_NESTED_ENLIGHTENMENTS VMCB_SW + +#endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index fb204eaa8bb3..ba7cd26f438f 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -28,44 +28,53 @@ #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 (svm->vmcb->control.exit_code != SVM_EXIT_NPF) { + 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. */ - svm->vmcb->control.exit_code = SVM_EXIT_NPF; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = (1ULL << 32); - svm->vmcb->control.exit_info_2 = fault->address; + 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; } - svm->vmcb->control.exit_info_1 &= ~0xffffffffULL; - svm->vmcb->control.exit_info_1 |= fault->error_code; + vmcb->control.exit_info_1 &= ~0xffffffffULL; + vmcb->control.exit_info_1 |= fault->error_code; nested_svm_vmexit(svm); } -static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_exception *fault) +static bool nested_svm_handle_page_fault_workaround(struct kvm_vcpu *vcpu, + struct x86_exception *fault) { - struct vcpu_svm *svm = to_svm(vcpu); - WARN_ON(!is_guest_mode(vcpu)); - - if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && - !svm->nested.nested_run_pending) { - svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; - svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = fault->error_code; - svm->vmcb->control.exit_info_2 = fault->address; - nested_svm_vmexit(svm); - } else { - kvm_inject_page_fault(vcpu, fault); - } + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; + + WARN_ON(!is_guest_mode(vcpu)); + + if (vmcb12_is_intercept(&svm->nested.ctl, + INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) && + !WARN_ON_ONCE(svm->nested.nested_run_pending)) { + vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR; + vmcb->control.exit_code_hi = 0; + vmcb->control.exit_info_1 = fault->error_code; + vmcb->control.exit_info_2 = fault->address; + nested_svm_vmexit(svm); + return true; + } + + return false; } static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) @@ -92,17 +101,22 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *hsave = svm->nested.hsave; WARN_ON(mmu_is_nested(vcpu)); vcpu->arch.mmu = &vcpu->arch.guest_mmu; - kvm_init_shadow_npt_mmu(vcpu, X86_CR0_PG, hsave->save.cr4, hsave->save.efer, + + /* + * 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; - reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; } @@ -112,9 +126,24 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; } +static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm) +{ + if (!svm->v_vmload_vmsave_enabled) + 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, *g; + struct vmcb_control_area *c, *h; + struct vmcb_ctrl_area_cached *g; unsigned int i; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -123,7 +152,7 @@ void recalc_intercepts(struct vcpu_svm *svm) return; c = &svm->vmcb->control; - h = &svm->nested.hsave->control; + h = &svm->vmcb01.ptr->control; g = &svm->nested.ctl; for (i = 0; i < MAX_INTERCEPT; i++) @@ -147,49 +176,50 @@ void recalc_intercepts(struct vcpu_svm *svm) for (i = 0; i < MAX_INTERCEPT; i++) c->intercepts[i] |= g->intercepts[i]; -} - -static void copy_vmcb_control_area(struct vmcb_control_area *dst, - struct vmcb_control_area *from) -{ - unsigned int i; - for (i = 0; i < MAX_INTERCEPT; i++) - dst->intercepts[i] = from->intercepts[i]; + /* If SMI is not intercepted, ignore guest SMI intercept as well */ + if (!intercept_smi) + vmcb_clr_intercept(c, INTERCEPT_SMI); - dst->iopm_base_pa = from->iopm_base_pa; - dst->msrpm_base_pa = from->msrpm_base_pa; - dst->tsc_offset = from->tsc_offset; - /* asid not copied, it is handled manually for svm->vmcb. */ - 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->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; + 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_enlightenments *hve = + (struct hv_enlightenments *)svm->nested.ctl.reserved_sw; + int i; + /* - * This function merges the msr permission bitmaps of kvm and the - * nested vmcb. It is optimized in that it only merges the parts where - * the kvm msr permission bitmap may contain zero bits + * 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. */ - int i; + if (!svm->nested.force_msr_bitmap_recalc && + kvm_hv_hypercall_enabled(&svm->vcpu) && + hve->hv_enlightenments_control.msr_bitmap && + (svm->nested.ctl.clean & BIT(VMCB_HV_NESTED_ENLIGHTENMENTS))) + goto set_msrpm_base_pa; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; for (i = 0; i < MSRPM_OFFSETS; i++) { @@ -208,95 +238,190 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) 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; } -static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) +/* + * 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) { - struct vcpu_svm *svm = to_svm(vcpu); + u64 addr = PAGE_ALIGN(pa); - if (WARN_ON(!is_guest_mode(vcpu))) - return true; + return kvm_vcpu_is_legal_gpa(vcpu, addr) && + kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1); +} - 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; +static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl) +{ + /* Nested FLUSHBYASID is not supported yet. */ + switch(tlb_ctl) { + case TLB_CONTROL_DO_NOTHING: + case TLB_CONTROL_FLUSH_ALL_ASID: + return true; + default: + return false; } - - return true; } -static bool nested_vmcb_check_controls(struct vmcb_control_area *control) +static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, + struct vmcb_ctrl_area_cached *control) { - if ((vmcb_is_intercept(control, INTERCEPT_VMRUN)) == 0) + 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 (control->asid == 0) + 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 ((control->nested_ctl & SVM_NESTED_CTL_NP_ENABLE) && - !npt_enabled) + if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) return false; return true; } -static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12) +/* 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) { - struct kvm_vcpu *vcpu = &svm->vcpu; - bool vmcb12_lma; - - /* - * FIXME: these should be done after copying the fields, - * to avoid TOC/TOU races. For these save area checks - * the possible damage is limited since kvm_set_cr0 and - * kvm_set_cr4 handle failure; EFER_SVME is an exception - * so it is force-set later in nested_prepare_vmcb_save. - */ - if ((vmcb12->save.efer & EFER_SVME) == 0) + if (CC(!(save->efer & EFER_SVME))) return false; - if (((vmcb12->save.cr0 & X86_CR0_CD) == 0) && (vmcb12->save.cr0 & X86_CR0_NW)) + if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) || + CC(save->cr0 & ~0xffffffffULL)) return false; - if (!kvm_dr6_valid(vmcb12->save.dr6) || !kvm_dr7_valid(vmcb12->save.dr7)) + if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7))) return false; - vmcb12_lma = (vmcb12->save.efer & EFER_LME) && (vmcb12->save.cr0 & X86_CR0_PG); - - if (vmcb12_lma) { - if (!(vmcb12->save.cr4 & X86_CR4_PAE) || - !(vmcb12->save.cr0 & X86_CR0_PE) || - kvm_vcpu_is_illegal_gpa(vcpu, vmcb12->save.cr3)) + /* + * 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; } - if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.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 void load_nested_vmcb_control(struct vcpu_svm *svm, - struct vmcb_control_area *control) +static bool nested_vmcb_check_save(struct kvm_vcpu *vcpu) { - copy_vmcb_control_area(&svm->nested.ctl, control); + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb_save_area_cached *save = &svm->nested.save; - /* Copy it here because nested_svm_check_controls will check it. */ - svm->nested.ctl.asid = control->asid; - svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL; - svm->nested.ctl.iopm_base_pa &= ~0x0fffULL; + 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->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->reserved_sw, from->reserved_sw, + sizeof(struct 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 nested_vmcb. + * they can be copied back into the vmcb12. */ -void sync_nested_vmcb_control(struct vcpu_svm *svm) +void nested_sync_control_from_vmcb02(struct vcpu_svm *svm) { u32 mask; svm->nested.ctl.event_inj = svm->vmcb->control.event_inj; @@ -316,6 +441,10 @@ void sync_nested_vmcb_control(struct vcpu_svm *svm) */ mask &= ~V_IRQ_MASK; } + + if (nested_vgif_enabled(svm)) + mask |= V_GIF_MASK; + svm->nested.ctl.int_ctl &= ~mask; svm->nested.ctl.int_ctl |= svm->vmcb->control.int_ctl & mask; } @@ -324,8 +453,8 @@ void sync_nested_vmcb_control(struct vcpu_svm *svm) * Transfer any event that L0 or L1 wanted to inject into L2 to * EXIT_INT_INFO. */ -static void nested_vmcb_save_pending_event(struct vcpu_svm *svm, - struct vmcb *vmcb12) +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; @@ -357,9 +486,23 @@ static void nested_vmcb_save_pending_event(struct vcpu_svm *svm, vmcb12->control.exit_int_info = exit_int_info; } -static inline bool nested_npt_enabled(struct vcpu_svm *svm) +static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) { - return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE; + /* + * 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); } /* @@ -367,104 +510,218 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) * 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 nested_npt, bool reload_pdptrs) { - if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) + if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) return -EINVAL; - if (!nested_npt && is_pae_paging(vcpu) && - (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) { - if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) - return -EINVAL; - } - - /* - * TODO: optimize unconditional TLB flush/MMU sync here and in - * kvm_init_shadow_npt_mmu(). - */ - if (!nested_npt) - kvm_mmu_new_pgd(vcpu, cr3, false, false); + if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && + CC(!load_pdptrs(vcpu, cr3))) + return -EINVAL; vcpu->arch.cr3 = cr3; - kvm_register_mark_available(vcpu, VCPU_EXREG_CR3); - kvm_init_mmu(vcpu, false); + /* 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; } -static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12) +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; + + nested_vmcb02_compute_g_pat(svm); + /* Load the nested guest state */ - svm->vmcb->save.es = vmcb12->save.es; - svm->vmcb->save.cs = vmcb12->save.cs; - svm->vmcb->save.ss = vmcb12->save.ss; - svm->vmcb->save.ds = vmcb12->save.ds; - svm->vmcb->save.gdtr = vmcb12->save.gdtr; - svm->vmcb->save.idtr = vmcb12->save.idtr; + 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(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - /* - * Force-set EFER_SVME even though it is checked earlier on the - * VMCB12, because the guest can flip the bit between the check - * and now. Clearing EFER_SVME would call svm_free_nested. - */ - svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_efer(&svm->vcpu, svm->nested.save.efer); + + svm_set_cr0(&svm->vcpu, svm->nested.save.cr0); + svm_set_cr4(&svm->vcpu, svm->nested.save.cr4); + + svm->vcpu.arch.cr2 = vmcb12->save.cr2; - svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); - svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); - svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2; kvm_rax_write(&svm->vcpu, vmcb12->save.rax); kvm_rsp_write(&svm->vcpu, vmcb12->save.rsp); kvm_rip_write(&svm->vcpu, vmcb12->save.rip); /* In case we don't even reach vcpu_run, the fields are not updated */ - svm->vmcb->save.rax = vmcb12->save.rax; - svm->vmcb->save.rsp = vmcb12->save.rsp; - svm->vmcb->save.rip = vmcb12->save.rip; - svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1; - svm->vcpu.arch.dr6 = vmcb12->save.dr6 | DR6_ACTIVE_LOW; - svm->vmcb->save.cpl = vmcb12->save.cpl; + 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(svm->lbrv_enabled && (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 void nested_prepare_vmcb_control(struct vcpu_svm *svm) +static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) { - const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK; + 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 (svm->vgif_enabled && (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); + + /* 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(&svm->vcpu); + 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); - svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = - svm->vcpu.arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; + vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; - svm->vmcb->control.int_ctl = - (svm->nested.ctl.int_ctl & ~mask) | - (svm->nested.hsave->control.int_ctl & mask); + if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { + WARN_ON(!svm->tsc_scaling_enabled); + nested_svm_update_tsc_ratio_msr(vcpu); + } - svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; - svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; - svm->vmcb->control.int_state = svm->nested.ctl.int_state; - svm->vmcb->control.event_inj = svm->nested.ctl.event_inj; - svm->vmcb->control.event_inj_err = svm->nested.ctl.event_inj_err; + 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; + + vmcb02->control.virt_ext = vmcb01->control.virt_ext & + LBR_CTL_ENABLE_MASK; + if (svm->lbrv_enabled) + 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; + + pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0; + pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 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; + } + } - svm->vmcb->control.pause_filter_count = svm->nested.ctl.pause_filter_count; - svm->vmcb->control.pause_filter_thresh = svm->nested.ctl.pause_filter_thresh; + nested_svm_transition_tlb_flush(vcpu); /* Enter Guest-Mode */ - enter_guest_mode(&svm->vcpu); + enter_guest_mode(vcpu); /* - * Merge guest and host intercepts - must be called with vcpu in - * guest-mode to take affect here + * Merge guest and host intercepts - must be called with vcpu in + * guest-mode to take effect. */ recalc_intercepts(svm); +} - vmcb_mark_all_dirty(svm->vmcb); +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 vcpu_svm *svm, u64 vmcb12_gpa, - struct vmcb *vmcb12) +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_vmrun(svm->vmcb->save.rip, vmcb12_gpa, @@ -482,56 +739,71 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa, svm->nested.vmcb12_gpa = vmcb12_gpa; - nested_prepare_vmcb_control(svm); - nested_prepare_vmcb_save(svm, vmcb12); - ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3, - nested_npt_enabled(svm)); + 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); + 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 (!npt_enabled) - svm->vcpu.arch.mmu->inject_page_fault = svm_inject_page_fault_nested; + 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); + return 0; } -int nested_svm_vmrun(struct vcpu_svm *svm) +int nested_svm_vmrun(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); int ret; struct vmcb *vmcb12; - struct vmcb *hsave = svm->nested.hsave; - struct vmcb *vmcb = svm->vmcb; struct kvm_host_map map; u64 vmcb12_gpa; + struct vmcb *vmcb01 = svm->vmcb01.ptr; - if (is_smm(&svm->vcpu)) { - kvm_queue_exception(&svm->vcpu, UD_VECTOR); + if (!svm->nested.hsave_msr) { + kvm_inject_gp(vcpu, 0); + return 1; + } + + if (is_smm(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); return 1; } vmcb12_gpa = svm->vmcb->save.rax; - ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb12_gpa), &map); + ret = kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map); if (ret == -EINVAL) { - kvm_inject_gp(&svm->vcpu, 0); + kvm_inject_gp(vcpu, 0); return 1; } else if (ret) { - return kvm_skip_emulated_instruction(&svm->vcpu); + return kvm_skip_emulated_instruction(vcpu); } - ret = kvm_skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(vcpu); vmcb12 = map.hva; if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - load_nested_vmcb_control(svm, &vmcb12->control); + nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); + nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - if (!nested_vmcb_check_save(svm, vmcb12) || - !nested_vmcb_check_controls(&svm->nested.ctl)) { + 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; @@ -539,38 +811,22 @@ int nested_svm_vmrun(struct vcpu_svm *svm) goto out; } - - /* Clear internal status */ - kvm_clear_exception_queue(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->vcpu); - /* - * Save the old vmcb, so we don't need to pick what we save, but can - * restore everything when a VMEXIT occurs + * Since vmcb01 is not in use, we can use it to store some of the L1 + * state. */ - hsave->save.es = vmcb->save.es; - hsave->save.cs = vmcb->save.cs; - hsave->save.ss = vmcb->save.ss; - hsave->save.ds = vmcb->save.ds; - hsave->save.gdtr = vmcb->save.gdtr; - hsave->save.idtr = vmcb->save.idtr; - hsave->save.efer = svm->vcpu.arch.efer; - hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); - hsave->save.cr4 = svm->vcpu.arch.cr4; - hsave->save.rflags = kvm_get_rflags(&svm->vcpu); - hsave->save.rip = kvm_rip_read(&svm->vcpu); - hsave->save.rsp = vmcb->save.rsp; - hsave->save.rax = vmcb->save.rax; - if (npt_enabled) - hsave->save.cr3 = vmcb->save.cr3; - else - hsave->save.cr3 = kvm_read_cr3(&svm->vcpu); + 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); - copy_vmcb_control_area(&hsave->control, &vmcb->control); + if (!npt_enabled) + vmcb01->save.cr3 = kvm_read_cr3(vcpu); svm->nested.nested_run_pending = 1; - if (enter_svm_guest_mode(svm, vmcb12_gpa, vmcb12)) + if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true)) goto out_exit_err; if (nested_svm_vmrun_msrpm(svm)) @@ -587,12 +843,33 @@ out_exit_err: nested_svm_vmexit(svm); out: - kvm_vcpu_unmap(&svm->vcpu, &map, true); + kvm_vcpu_unmap(vcpu, &map, true); return ret; } -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +/* 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; @@ -610,105 +887,122 @@ void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) int nested_svm_vmexit(struct vcpu_svm *svm) { - int rc; + struct kvm_vcpu *vcpu = &svm->vcpu; + struct vmcb *vmcb01 = svm->vmcb01.ptr; + struct vmcb *vmcb02 = svm->nested.vmcb02.ptr; struct vmcb *vmcb12; - struct vmcb *hsave = svm->nested.hsave; - struct vmcb *vmcb = svm->vmcb; struct kvm_host_map map; + int rc; - rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa), &map); + rc = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa), &map); if (rc) { if (rc == -EINVAL) - kvm_inject_gp(&svm->vcpu, 0); + kvm_inject_gp(vcpu, 0); return 1; } vmcb12 = map.hva; /* Exit Guest-Mode */ - leave_guest_mode(&svm->vcpu); + 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, &svm->vcpu); + 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 = vmcb->save.es; - vmcb12->save.cs = vmcb->save.cs; - vmcb12->save.ss = vmcb->save.ss; - vmcb12->save.ds = vmcb->save.ds; - vmcb12->save.gdtr = vmcb->save.gdtr; - vmcb12->save.idtr = vmcb->save.idtr; + 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(&svm->vcpu); - vmcb12->save.cr3 = kvm_read_cr3(&svm->vcpu); - vmcb12->save.cr2 = vmcb->save.cr2; + 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(&svm->vcpu); - vmcb12->save.rip = kvm_rip_read(&svm->vcpu); - vmcb12->save.rsp = kvm_rsp_read(&svm->vcpu); - vmcb12->save.rax = kvm_rax_read(&svm->vcpu); - vmcb12->save.dr7 = vmcb->save.dr7; + 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 = vmcb->save.cpl; + vmcb12->save.cpl = vmcb02->save.cpl; - vmcb12->control.int_state = vmcb->control.int_state; - vmcb12->control.exit_code = vmcb->control.exit_code; - vmcb12->control.exit_code_hi = vmcb->control.exit_code_hi; - vmcb12->control.exit_info_1 = vmcb->control.exit_info_1; - vmcb12->control.exit_info_2 = vmcb->control.exit_info_2; + 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_vmcb_save_pending_event(svm, vmcb12); + nested_save_pending_event_to_vmcb12(svm, vmcb12); if (svm->nrips_enabled) - vmcb12->control.next_rip = vmcb->control.next_rip; + vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; vmcb12->control.tlb_ctl = svm->nested.ctl.tlb_ctl; vmcb12->control.event_inj = svm->nested.ctl.event_inj; vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; - vmcb12->control.pause_filter_count = - svm->vmcb->control.pause_filter_count; - vmcb12->control.pause_filter_thresh = - svm->vmcb->control.pause_filter_thresh; + if (!kvm_pause_in_guest(vcpu->kvm)) { + vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count; + vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); - /* Restore the original control entries */ - copy_vmcb_control_area(&vmcb->control, &hsave->control); + } + + nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); + + svm_switch_vmcb(svm, &svm->vmcb01); + + if (unlikely(svm->lbrv_enabled && (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); + } - /* On vmexit the GIF is set to false */ + /* + * 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->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = - svm->vcpu.arch.l1_tsc_offset; + 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 (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { + WARN_ON(!svm->tsc_scaling_enabled); + vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); + } svm->nested.ctl.nested_cr3 = 0; - /* Restore selected save entries */ - svm->vmcb->save.es = hsave->save.es; - svm->vmcb->save.cs = hsave->save.cs; - svm->vmcb->save.ss = hsave->save.ss; - svm->vmcb->save.ds = hsave->save.ds; - svm->vmcb->save.gdtr = hsave->save.gdtr; - svm->vmcb->save.idtr = hsave->save.idtr; - kvm_set_rflags(&svm->vcpu, hsave->save.rflags); - kvm_set_rflags(&svm->vcpu, hsave->save.rflags | X86_EFLAGS_FIXED); - svm_set_efer(&svm->vcpu, hsave->save.efer); - svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); - svm_set_cr4(&svm->vcpu, hsave->save.cr4); - kvm_rax_write(&svm->vcpu, hsave->save.rax); - kvm_rsp_write(&svm->vcpu, hsave->save.rsp); - kvm_rip_write(&svm->vcpu, hsave->save.rip); - svm->vmcb->save.dr7 = DR7_FIXED_1; - svm->vmcb->save.cpl = 0; - svm->vmcb->control.exit_int_info = 0; - - vmcb_mark_all_dirty(svm->vmcb); + /* + * 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, @@ -717,50 +1011,71 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->control.exit_int_info_err, KVM_ISA_SVM); - kvm_vcpu_unmap(&svm->vcpu, &map, true); + kvm_vcpu_unmap(vcpu, &map, true); - nested_svm_uninit_mmu_context(&svm->vcpu); + nested_svm_transition_tlb_flush(vcpu); - rc = nested_svm_load_cr3(&svm->vcpu, hsave->save.cr3, false); + nested_svm_uninit_mmu_context(vcpu); + + rc = nested_svm_load_cr3(vcpu, vmcb01->save.cr3, false, true); if (rc) return 1; - if (npt_enabled) - svm->vmcb->save.cr3 = hsave->save.cr3; - /* * 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(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->vcpu); + 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) +{ + nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN); +} + int svm_allocate_nested(struct vcpu_svm *svm) { - struct page *hsave_page; + struct page *vmcb02_page; if (svm->nested.initialized) return 0; - hsave_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (!hsave_page) + vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!vmcb02_page) return -ENOMEM; - svm->nested.hsave = page_address(hsave_page); + 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_hsave; + goto err_free_vmcb02; svm_vcpu_init_msrpm(&svm->vcpu, svm->nested.msrpm); svm->nested.initialized = true; return 0; -err_free_hsave: - __free_page(hsave_page); +err_free_vmcb02: + __free_page(vmcb02_page); return -ENOMEM; } @@ -772,8 +1087,17 @@ void svm_free_nested(struct vcpu_svm *svm) svm_vcpu_free_msrpm(svm->nested.msrpm); svm->nested.msrpm = NULL; - __free_page(virt_to_page(svm->nested.hsave)); - svm->nested.hsave = 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; } @@ -781,20 +1105,23 @@ void svm_free_nested(struct vcpu_svm *svm) /* * Forcibly leave nested mode in order to be able to reset the VCPU later on. */ -void svm_leave_nested(struct vcpu_svm *svm) +void svm_leave_nested(struct kvm_vcpu *vcpu) { - if (is_guest_mode(&svm->vcpu)) { - struct vmcb *hsave = svm->nested.hsave; - struct vmcb *vmcb = svm->vmcb; + struct vcpu_svm *svm = to_svm(vcpu); + if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; - leave_guest_mode(&svm->vcpu); - copy_vmcb_control_area(&vmcb->control, &hsave->control); - nested_svm_uninit_mmu_context(&svm->vcpu); + 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); } - kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu); + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); } static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) @@ -802,7 +1129,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) u32 offset, msr, value; int write, mask; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return NESTED_EXIT_HOST; msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; @@ -829,7 +1156,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) u8 start_bit; u64 gpa; - if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT))) return NESTED_EXIT_HOST; port = svm->vmcb->control.exit_info_1 >> 16; @@ -860,12 +1187,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) vmexit = nested_svm_intercept_ioio(svm); break; case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; break; } @@ -883,7 +1210,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) break; } default: { - if (vmcb_is_intercept(&svm->nested.ctl, exit_code)) + if (vmcb12_is_intercept(&svm->nested.ctl, exit_code)) vmexit = NESTED_EXIT_DONE; } } @@ -903,16 +1230,15 @@ int nested_svm_exit_handled(struct vcpu_svm *svm) return vmexit; } -int nested_svm_check_permissions(struct vcpu_svm *svm) +int nested_svm_check_permissions(struct kvm_vcpu *vcpu) { - if (!(svm->vcpu.arch.efer & EFER_SVME) || - !is_paging(&svm->vcpu)) { - kvm_queue_exception(&svm->vcpu, UD_VECTOR); + if (!(vcpu->arch.efer & EFER_SVME) || !is_paging(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - if (svm->vmcb->save.cpl) { - kvm_inject_gp(&svm->vcpu, 0); + if (to_svm(vcpu)->vmcb->save.cpl) { + kvm_inject_gp(vcpu, 0); return 1; } @@ -929,12 +1255,13 @@ static bool nested_exit_on_exception(struct vcpu_svm *svm) static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) { unsigned int nr = svm->vcpu.arch.exception.nr; + struct vmcb *vmcb = svm->vmcb; - svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; - svm->vmcb->control.exit_code_hi = 0; + vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; + vmcb->control.exit_code_hi = 0; if (svm->vcpu.arch.exception.has_error_code) - svm->vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code; + vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code; /* * EXITINFO2 is undefined for all exception intercepts other @@ -942,11 +1269,11 @@ static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) */ if (nr == PF_VECTOR) { if (svm->vcpu.arch.exception.nested_apf) - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; + vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token; else if (svm->vcpu.arch.exception.has_payload) - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; + vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload; else - svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; } else if (nr == DB_VECTOR) { /* See inject_pending_event. */ kvm_deliver_exception_payload(&svm->vcpu); @@ -960,50 +1287,11 @@ static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm) nested_svm_vmexit(svm); } -static void nested_svm_smi(struct vcpu_svm *svm) -{ - svm->vmcb->control.exit_code = SVM_EXIT_SMI; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); -} - -static void nested_svm_nmi(struct vcpu_svm *svm) -{ - svm->vmcb->control.exit_code = SVM_EXIT_NMI; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); -} - -static void nested_svm_intr(struct vcpu_svm *svm) -{ - trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); - - svm->vmcb->control.exit_code = SVM_EXIT_INTR; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); -} - static inline bool nested_exit_on_init(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); -} - -static void nested_svm_init(struct vcpu_svm *svm) -{ - svm->vmcb->control.exit_code = SVM_EXIT_INIT; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - - nested_svm_vmexit(svm); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INIT); } - static int svm_check_nested_events(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1017,12 +1305,18 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; if (!nested_exit_on_init(svm)) return 0; - nested_svm_init(svm); + nested_svm_simple_vmexit(svm, SVM_EXIT_INIT); return 0; } if (vcpu->arch.exception.pending) { - if (block_nested_events) + /* + * Only a pending nested run can block a pending exception. + * Otherwise an injected NMI/interrupt should either be + * lost or delivered to the nested hypervisor in the EXITINTINFO + * vmcb field, while delivering the pending exception. + */ + if (svm->nested.nested_run_pending) return -EBUSY; if (!nested_exit_on_exception(svm)) return 0; @@ -1035,7 +1329,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; if (!nested_exit_on_smi(svm)) return 0; - nested_svm_smi(svm); + nested_svm_simple_vmexit(svm, SVM_EXIT_SMI); return 0; } @@ -1044,7 +1338,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; if (!nested_exit_on_nmi(svm)) return 0; - nested_svm_nmi(svm); + nested_svm_simple_vmexit(svm, SVM_EXIT_NMI); return 0; } @@ -1053,7 +1347,8 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return -EBUSY; if (!nested_exit_on_intr(svm)) return 0; - nested_svm_intr(svm); + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); + nested_svm_simple_vmexit(svm, SVM_EXIT_INTR); return 0; } @@ -1072,8 +1367,8 @@ int nested_svm_exit_special(struct vcpu_svm *svm) case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); - if (get_host_vmcb(svm)->control.intercepts[INTERCEPT_EXCEPTION] & - excp_bits) + 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) @@ -1088,11 +1383,58 @@ int nested_svm_exit_special(struct vcpu_svm *svm) 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->arch.tsc_scaling_ratio); +} + +/* 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->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 'reserved_sw' 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, @@ -1134,13 +1476,21 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu, */ if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE)) return -EFAULT; - if (copy_to_user(&user_vmcb->control, &svm->nested.ctl, - sizeof(user_vmcb->control))) + + 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->nested.hsave->save, + + if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save, sizeof(user_vmcb->save))) return -EFAULT; - out: return kvm_state.size; } @@ -1150,13 +1500,14 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, struct kvm_nested_state *kvm_state) { struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *hsave = svm->nested.hsave; 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; - u32 cr0; BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) > KVM_STATE_NESTED_SVM_VMCB_SIZE); @@ -1184,7 +1535,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); return 0; } @@ -1195,8 +1546,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; ret = -ENOMEM; - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); - save = kzalloc(sizeof(*save), GFP_KERNEL); + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL_ACCOUNT); + save = kzalloc(sizeof(*save), GFP_KERNEL_ACCOUNT); if (!ctl || !save) goto out_free; @@ -1207,12 +1558,13 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, goto out_free; ret = -EINVAL; - if (!nested_vmcb_check_controls(ctl)) + __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_checks). + * valid for guest mode (see nested_vmcb_check_save). */ cr0 = kvm_read_cr0(vcpu); if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW)) @@ -1221,29 +1573,53 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, /* * Validate host state saved from before VMRUN (see * nested_svm_check_permissions). - * TODO: validate reserved bits for all saved state. */ - if (!(save->cr0 & X86_CR0_PG)) - goto out_free; - if (!(save->efer & EFER_SVME)) + __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. L1 control fields - * come from the nested save state. Guest state is already - * in the registers, the save area of the nested state instead - * contains saved L1 state. + * 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); - copy_vmcb_control_area(&hsave->control, &svm->vmcb->control); - hsave->save = *save; - svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - load_nested_vmcb_control(svm, ctl); - nested_prepare_vmcb_control(svm); + + 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); + + /* + * 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; @@ -1254,8 +1630,39 @@ out_free: 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; + } + + return true; +} + struct kvm_x86_nested_ops svm_nested_ops = { + .leave_nested = svm_leave_nested, .check_events = svm_check_nested_events, + .handle_page_fault_workaround = nested_svm_handle_page_fault_workaround, + .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, diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index fdf587f19c5f..136039fc6d01 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -16,6 +16,7 @@ #include "cpuid.h" #include "lapic.h" #include "pmu.h" +#include "svm.h" enum pmu_type { PMU_TYPE_COUNTER = 0, @@ -44,6 +45,22 @@ static struct kvm_event_hw_type_mapping amd_event_mapping[] = { [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, }; +/* duplicated from amd_f17h_perfmon_event_map. */ +static struct kvm_event_hw_type_mapping amd_f17h_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x60, 0xff, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x64, 0x09, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0x87, 0x02, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0x87, 0x01, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +/* amd_pmc_perf_hw_id depends on these being the same size */ +static_assert(ARRAY_SIZE(amd_event_mapping) == + ARRAY_SIZE(amd_f17h_event_mapping)); + static unsigned int get_msr_base(struct kvm_pmu *pmu, enum pmu_type type) { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); @@ -100,6 +117,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, { struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + if (!vcpu->kvm->arch.enable_pmu) + return NULL; + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: @@ -134,27 +154,31 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, return &pmu->gp_counters[msr_to_index(msr)]; } -static unsigned amd_find_arch_event(struct kvm_pmu *pmu, - u8 event_select, - u8 unit_mask) +static unsigned int amd_pmc_perf_hw_id(struct kvm_pmc *pmc) { + struct kvm_event_hw_type_mapping *event_mapping; + u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; + u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; int i; + /* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ + if (WARN_ON(pmc_is_fixed(pmc))) + return PERF_COUNT_HW_MAX; + + if (guest_cpuid_family(pmc->vcpu) >= 0x17) + event_mapping = amd_f17h_event_mapping; + else + event_mapping = amd_event_mapping; + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) - if (amd_event_mapping[i].eventsel == event_select - && amd_event_mapping[i].unit_mask == unit_mask) + if (event_mapping[i].eventsel == event_select + && event_mapping[i].unit_mask == unit_mask) break; if (i == ARRAY_SIZE(amd_event_mapping)) return PERF_COUNT_HW_MAX; - return amd_event_mapping[i].event_type; -} - -/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ -static unsigned amd_find_fixed_event(int idx) -{ - return PERF_COUNT_HW_MAX; + return event_mapping[i].event_type; } /* check if a PMC is enabled by comparing it against global_ctrl bits. Because @@ -181,14 +205,13 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER); } -/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ -static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +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); + return idx < pmu->nr_arch_gp_counters; } /* idx is the ECX register of RDPMC instruction */ @@ -256,17 +279,16 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc->counter += data - pmc_read_counter(pmc); + pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); if (pmc) { - if (data == pmc->eventsel) - return 0; - if (!(data & pmu->reserved_bits)) { + data &= ~pmu->reserved_bits; + if (data != pmc->eventsel) reprogram_gp_counter(pmc, data); - return 0; - } + return 0; } return 1; @@ -282,7 +304,8 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; - pmu->reserved_bits = 0xffffffff00200000ull; + pmu->reserved_bits = 0xfffffff000280000ull; + pmu->raw_event_mask = AMD64_RAW_EVENT_MASK; pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; @@ -319,9 +342,8 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) } } -struct kvm_pmu_ops amd_pmu_ops = { - .find_arch_event = amd_find_arch_event, - .find_fixed_event = amd_find_fixed_event, +struct kvm_pmu_ops amd_pmu_ops __initdata = { + .pmc_perf_hw_id = amd_pmc_perf_hw_id, .pmc_is_enabled = amd_pmc_is_enabled, .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 874ea309279f..51fd985cf21d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -14,11 +14,13 @@ #include <linux/psp-sev.h> #include <linux/pagemap.h> #include <linux/swap.h> +#include <linux/misc_cgroup.h> #include <linux/processor.h> #include <linux/trace_events.h> -#include <asm/fpu/internal.h> +#include <asm/pkru.h> #include <asm/trapnr.h> +#include <asm/fpu/xcr.h> #include "x86.h" #include "svm.h" @@ -26,14 +28,41 @@ #include "cpuid.h" #include "trace.h" -#define __ex(x) __kvm_handle_fault_on_reboot(x) +#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); +#else +#define sev_enabled false +#define sev_es_enabled false +#endif /* CONFIG_KVM_AMD_SEV */ static u8 sev_enc_bit; -static int sev_flush_asids(void); 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; @@ -45,9 +74,15 @@ struct enc_region { unsigned long size; }; -static int sev_flush_asids(void) +/* Called with the sev_bitmap_lock held, or on shutdown */ +static int sev_flush_asids(int min_asid, int max_asid) { - int ret, error = 0; + 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, @@ -66,56 +101,81 @@ static int sev_flush_asids(void) 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) { - int pos; - - /* Check if there are any ASIDs to reclaim before performing a flush */ - pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid); - if (pos >= max_asid) - return false; - - if (sev_flush_asids()) + 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, - max_sev_asid); - bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid); + 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 pos, min_asid, max_asid; + 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 ? 0 : 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: - pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid); - if (pos >= max_asid) { + 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); - return -EBUSY; + ret = -EBUSY; + goto e_uncharge; } - __set_bit(pos, sev_asid_bitmap); + __set_bit(asid, sev_asid_bitmap); mutex_unlock(&sev_bitmap_lock); - return pos + 1; + 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) @@ -125,55 +185,53 @@ static int sev_get_asid(struct kvm *kvm) return sev->asid; } -static void sev_asid_free(int asid) +static void sev_asid_free(struct kvm_sev_info *sev) { struct svm_cpu_data *sd; - int cpu, pos; + int cpu; mutex_lock(&sev_bitmap_lock); - pos = asid - 1; - __set_bit(pos, sev_reclaim_asid_bitmap); + __set_bit(sev->asid, sev_reclaim_asid_bitmap); for_each_possible_cpu(cpu) { sd = per_cpu(svm_data, cpu); - sd->sev_vmcbs[pos] = NULL; + 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_unbind_asid(struct kvm *kvm, unsigned int handle) +static void sev_decommission(unsigned int handle) { - struct sev_data_decommission *decommission; - struct sev_data_deactivate *data; + struct sev_data_decommission decommission; if (!handle) return; - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) + 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 */ - data->handle = handle; + deactivate.handle = handle; /* Guard DEACTIVATE against WBINVD/DF_FLUSH used in ASID recycling */ down_read(&sev_deactivate_lock); - sev_guest_deactivate(data, NULL); + sev_guest_deactivate(&deactivate, NULL); up_read(&sev_deactivate_lock); - kfree(data); - - decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); - if (!decommission) - return; - - /* decommission handle */ - decommission->handle = handle; - sev_guest_decommission(decommission, NULL); - - kfree(decommission); + sev_decommission(handle); } static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) @@ -181,54 +239,50 @@ 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) - return ret; + goto e_no_asid; + sev->asid = asid; ret = sev_platform_init(&argp->error); if (ret) goto e_free; - sev->active = true; - sev->asid = asid; 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(asid); + sev_asid_free(sev); + sev->asid = 0; +e_no_asid: + sev->es_active = false; + sev->active = false; return ret; } -static int sev_es_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) -{ - if (!sev_es) - return -ENOTTY; - - to_kvm_svm(kvm)->sev_info.es_active = true; - - return sev_guest_init(kvm, argp); -} - static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { - struct sev_data_activate *data; + struct sev_data_activate activate; int asid = sev_get_asid(kvm); int ret; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - /* activate ASID on the given handle */ - data->handle = handle; - data->asid = asid; - ret = sev_guest_activate(data, error); - kfree(data); + activate.handle = handle; + activate.asid = asid; + ret = sev_guest_activate(&activate, error); return ret; } @@ -258,7 +312,7 @@ static int sev_issue_cmd(struct kvm *kvm, int id, void *data, int *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 sev_data_launch_start start; struct kvm_sev_launch_start params; void *dh_blob, *session_blob; int *error = &argp->error; @@ -270,20 +324,16 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; - start = kzalloc(sizeof(*start), GFP_KERNEL_ACCOUNT); - if (!start) - return -ENOMEM; + 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)) { - ret = PTR_ERR(dh_blob); - goto e_free; - } + 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; + start.dh_cert_address = __sme_set(__pa(dh_blob)); + start.dh_cert_len = params.dh_len; } session_blob = NULL; @@ -294,40 +344,40 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) goto e_free_dh; } - start->session_address = __sme_set(__pa(session_blob)); - start->session_len = params.session_len; + start.session_address = __sme_set(__pa(session_blob)); + start.session_len = params.session_len; } - start->handle = params.handle; - start->policy = params.policy; + 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); + 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) + 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; + params.handle = start.handle; if (copy_to_user((void __user *)(uintptr_t)argp->data, ¶ms, sizeof(params))) { - sev_unbind_asid(kvm, start->handle); + sev_unbind_asid(kvm, start.handle); ret = -EFAULT; goto e_free_session; } - sev->handle = start->handle; + sev->handle = start.handle; sev->fd = argp->sev_fd; e_free_session: kfree(session_blob); e_free_dh: kfree(dh_blob); -e_free: - kfree(start); return ret; } @@ -417,6 +467,7 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages) page_virtual = kmap_atomic(pages[i]); clflush_cache_range(page_virtual, PAGE_SIZE); kunmap_atomic(page_virtual); + cond_resched(); } } @@ -446,7 +497,7 @@ 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 sev_data_launch_update_data data; struct page **inpages; int ret; @@ -456,20 +507,14 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - 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)) { - ret = PTR_ERR(inpages); - goto e_free; - } + if (IS_ERR(inpages)) + return PTR_ERR(inpages); /* * Flush (on non-coherent CPUs) before LAUNCH_UPDATE encrypts pages in @@ -477,6 +522,9 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) */ 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; @@ -491,10 +539,9 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) len = min_t(size_t, ((pages * PAGE_SIZE) - offset), size); - data->handle = sev->handle; - data->len = len; - data->address = __sme_page_pa(inpages[i]) + offset; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_DATA, data, &argp->error); + 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; @@ -510,19 +557,25 @@ e_unpin: } /* unlock the user pages */ sev_unpin_memory(kvm, inpages, npages); -e_free: - kfree(data); return ret; } static int sev_es_sync_vmsa(struct vcpu_svm *svm) { - struct vmcb_save_area *save = &svm->vmcb->save; + struct sev_es_save_area *save = svm->sev_es.vmsa; /* Check some debug related fields before encrypting the VMSA */ - if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1)) + 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]; @@ -548,68 +601,71 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm) 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; + + 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; + + /* Perform some pre-encryption checks against the VMSA */ + ret = sev_es_sync_vmsa(svm); + if (ret) + return ret; /* - * 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. + * 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. */ - memcpy(svm->vmsa, save, sizeof(*save)); + 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_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_launch_update_vmsa *vmsa; - int i, ret; + struct kvm_vcpu *vcpu; + unsigned long i; + int ret; if (!sev_es_guest(kvm)) return -ENOTTY; - vmsa = kzalloc(sizeof(*vmsa), GFP_KERNEL); - if (!vmsa) - return -ENOMEM; - - for (i = 0; i < kvm->created_vcpus; i++) { - struct vcpu_svm *svm = to_svm(kvm->vcpus[i]); - - /* Perform some pre-encryption checks against the VMSA */ - ret = sev_es_sync_vmsa(svm); + kvm_for_each_vcpu(i, vcpu, kvm) { + ret = mutex_lock_killable(&vcpu->mutex); if (ret) - goto e_free; + 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->vmsa, PAGE_SIZE); + ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error); - vmsa->handle = sev->handle; - vmsa->address = __sme_pa(svm->vmsa); - vmsa->len = PAGE_SIZE; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, vmsa, - &argp->error); + mutex_unlock(&vcpu->mutex); if (ret) - goto e_free; - - svm->vcpu.arch.guest_state_protected = true; + return ret; } -e_free: - kfree(vmsa); - 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 sev_data_launch_measure data; struct kvm_sev_launch_measure params; void __user *p = NULL; void *blob = NULL; @@ -621,9 +677,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, measure, sizeof(params))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; + memset(&data, 0, sizeof(data)); /* User wants to query the blob length */ if (!params.len) @@ -631,23 +685,20 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) p = (void __user *)(uintptr_t)params.uaddr; if (p) { - if (params.len > SEV_FW_BLOB_MAX_SIZE) { - ret = -EINVAL; - goto e_free; - } + if (params.len > SEV_FW_BLOB_MAX_SIZE) + return -EINVAL; - ret = -ENOMEM; - blob = kmalloc(params.len, GFP_KERNEL); + blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT); if (!blob) - goto e_free; + return -ENOMEM; - data->address = __psp_pa(blob); - data->len = params.len; + 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); + 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. @@ -664,63 +715,50 @@ cmd: } done: - params.len = data->len; + params.len = data.len; if (copy_to_user(measure, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); -e_free: - kfree(data); 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; - int ret; + struct sev_data_launch_finish data; if (!sev_guest(kvm)) return -ENOTTY; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - data->handle = sev->handle; - ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_FINISH, data, &argp->error); - - kfree(data); - return ret; + 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; + struct sev_data_guest_status data; int ret; if (!sev_guest(kvm)) return -ENOTTY; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; + memset(&data, 0, sizeof(data)); - data->handle = sev->handle; - ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, data, &argp->error); + data.handle = sev->handle; + ret = sev_issue_cmd(kvm, SEV_CMD_GUEST_STATUS, &data, &argp->error); if (ret) - goto e_free; + return ret; - params.policy = data->policy; - params.state = data->state; - params.handle = data->handle; + 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; -e_free: - kfree(data); + return ret; } @@ -729,23 +767,17 @@ static int __sev_issue_dbg_cmd(struct kvm *kvm, unsigned long src, int *error, bool enc) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - struct sev_data_dbg *data; - int ret; + struct sev_data_dbg data; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; - - data->handle = sev->handle; - data->dst_addr = dst; - data->src_addr = src; - data->len = size; + data.reserved = 0; + data.handle = sev->handle; + data.dst_addr = dst; + data.src_addr = src; + data.len = size; - ret = sev_issue_cmd(kvm, - enc ? SEV_CMD_DBG_ENCRYPT : SEV_CMD_DBG_DECRYPT, - data, error); - kfree(data); - return ret; + 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, @@ -765,7 +797,7 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, } static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user dst_uaddr, + void __user *dst_uaddr, unsigned long dst_paddr, int size, int *err) { @@ -776,7 +808,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (!IS_ALIGNED(dst_paddr, 16) || !IS_ALIGNED(paddr, 16) || !IS_ALIGNED(size, 16)) { - tpage = (void *)alloc_page(GFP_KERNEL); + tpage = (void *)alloc_page(GFP_KERNEL | __GFP_ZERO); if (!tpage) return -ENOMEM; @@ -789,8 +821,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (tpage) { offset = paddr & 15; - if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, - page_address(tpage) + offset, size)) + if (copy_to_user(dst_uaddr, page_address(tpage) + offset, size)) ret = -EFAULT; } @@ -802,9 +833,9 @@ e_free: } static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user vaddr, + void __user *vaddr, unsigned long dst_paddr, - unsigned long __user dst_vaddr, + void __user *dst_vaddr, int size, int *error) { struct page *src_tpage = NULL; @@ -812,13 +843,12 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, int ret, len = size; /* If source buffer is not aligned then use an intermediate buffer */ - if (!IS_ALIGNED(vaddr, 16)) { + if (!IS_ALIGNED((unsigned long)vaddr, 16)) { src_tpage = alloc_page(GFP_KERNEL); if (!src_tpage) return -ENOMEM; - if (copy_from_user(page_address(src_tpage), - (void __user *)(uintptr_t)vaddr, size)) { + if (copy_from_user(page_address(src_tpage), vaddr, size)) { __free_page(src_tpage); return -EFAULT; } @@ -832,7 +862,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, * - copy the source buffer in an intermediate buffer * - use the intermediate buffer as source buffer */ - if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { int dst_offset; dst_tpage = alloc_page(GFP_KERNEL); @@ -857,7 +887,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, page_address(src_tpage), size); else { if (copy_from_user(page_address(dst_tpage) + dst_offset, - (void __user *)(uintptr_t)vaddr, size)) { + vaddr, size)) { ret = -EFAULT; goto e_free; } @@ -937,15 +967,15 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (dec) ret = __sev_dbg_decrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, - dst_vaddr, + (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, - vaddr, + (void __user *)vaddr, __sme_page_pa(dst_p[0]) + d_off, - dst_vaddr, + (void __user *)dst_vaddr, len, &argp->error); sev_unpin_memory(kvm, src_p, n); @@ -965,7 +995,7 @@ err: 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 sev_data_launch_secret data; struct kvm_sev_launch_secret params; struct page **pages; void *blob, *hdr; @@ -997,41 +1027,36 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp) goto e_unpin_memory; } - ret = -ENOMEM; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - 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; + 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_free; + goto e_unpin_memory; } - data->trans_address = __psp_pa(blob); - data->trans_len = params.trans_len; + 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.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); + 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_free: - kfree(data); e_unpin_memory: /* content of memory is updated, mark pages dirty */ for (i = 0; i < n; i++) { @@ -1046,7 +1071,7 @@ 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 sev_data_attestation_report data; struct kvm_sev_attestation_report params; void __user *p; void *blob = NULL; @@ -1058,9 +1083,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, (void __user *)(uintptr_t)argp->data, sizeof(params))) return -EFAULT; - data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT); - if (!data) - return -ENOMEM; + memset(&data, 0, sizeof(data)); /* User wants to query the blob length */ if (!params.len) @@ -1068,23 +1091,20 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) p = (void __user *)(uintptr_t)params.uaddr; if (p) { - if (params.len > SEV_FW_BLOB_MAX_SIZE) { - ret = -EINVAL; - goto e_free; - } + if (params.len > SEV_FW_BLOB_MAX_SIZE) + return -EINVAL; - ret = -ENOMEM; - blob = kmalloc(params.len, GFP_KERNEL); + blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT); if (!blob) - goto e_free; + return -ENOMEM; - data->address = __psp_pa(blob); - data->len = params.len; - memcpy(data->mnonce, params.mnonce, sizeof(params.mnonce)); + 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); + 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. */ @@ -1100,22 +1120,710 @@ cmd: } done: - params.len = data->len; + params.len = data.len; if (copy_to_user(report, ¶ms, sizeof(params))) ret = -EFAULT; e_free_blob: kfree(blob); -e_free: - kfree(data); return ret; } -int svm_mem_enc_op(struct kvm *kvm, void __user *argp) +/* 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 + 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 + 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; + bool first = true; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mutex_lock_killable_nested(&vcpu->mutex, role)) + goto out_unlock; + + if (first) { + /* + * Reset the role to one that avoids colliding with + * the role used for the first vcpu mutex. + */ + role = SEV_NR_MIGRATION_ROLES; + first = false; + } else { + mutex_release(&vcpu->mutex.dep_map, _THIS_IP_); + } + } + + return 0; + +out_unlock: + + first = true; + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + + if (first) + first = false; + else + mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_); + + + 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_sev_info *mirror; + + 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; + + src->asid = 0; + src->active = false; + src->handle = 0; + src->pages_locked = 0; + src->enc_context_owner = NULL; + + 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); + } +} + +static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) +{ + unsigned long i; + struct kvm_vcpu *dst_vcpu, *src_vcpu; + struct vcpu_svm *dst_svm, *src_svm; + + 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; + } + + kvm_for_each_vcpu(i, src_vcpu, src) { + src_svm = to_svm(src_vcpu); + dst_vcpu = kvm_get_vcpu(dst, i); + dst_svm = to_svm(dst_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; + } + to_kvm_svm(src)->sev_info.es_active = false; + to_kvm_svm(dst)->sev_info.es_active = true; + + 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 file *source_kvm_file; + struct kvm *source_kvm; + bool charged = false; + int ret; + + source_kvm_file = fget(source_fd); + if (!file_is_kvm(source_kvm_file)) { + ret = -EBADF; + goto out_fput; + } + + source_kvm = source_kvm_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; + + if (sev_es_guest(source_kvm)) { + ret = sev_es_migrate_from(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: + if (source_kvm_file) + fput(source_kvm_file); + return ret; +} + +int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; int r; - if (!svm_sev_enabled() || !sev) + if (!sev_enabled) return -ENOTTY; if (!argp) @@ -1126,13 +1834,23 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) 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_ES_INIT: - r = sev_es_guest_init(kvm, &sev_cmd); - break; case KVM_SEV_LAUNCH_START: r = sev_launch_start(kvm, &sev_cmd); break; @@ -1163,6 +1881,27 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) 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; @@ -1176,8 +1915,8 @@ out: return r; } -int svm_register_enc_region(struct kvm *kvm, - struct kvm_enc_region *range) +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; @@ -1186,6 +1925,10 @@ int svm_register_enc_region(struct kvm *kvm, 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; @@ -1246,12 +1989,16 @@ static void __unregister_enc_region_locked(struct kvm *kvm, kfree(region); } -int svm_unregister_enc_region(struct kvm *kvm, - struct kvm_enc_region *range) +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)) { @@ -1282,6 +2029,70 @@ failed: return ret; } +int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) +{ + struct file *source_kvm_file; + struct kvm *source_kvm; + struct kvm_sev_info *source_sev, *mirror_sev; + int ret; + + source_kvm_file = fget(source_fd); + if (!file_is_kvm(source_kvm_file)) { + ret = -EBADF; + goto e_source_fput; + } + + source_kvm = source_kvm_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: + if (source_kvm_file) + fput(source_kvm_file); + return ret; +} + void sev_vm_destroy(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -1291,7 +2102,18 @@ void sev_vm_destroy(struct kvm *kvm) if (!sev_guest(kvm)) return; - mutex_lock(&kvm->lock); + 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 @@ -1312,20 +2134,35 @@ void sev_vm_destroy(struct kvm *kvm) } } - mutex_unlock(&kvm->lock); - sev_unbind_asid(kvm, sev->handle); - sev_asid_free(sev->asid); + 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) { - unsigned int eax, ebx, ecx, edx; +#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; - /* Does the CPU support SEV? */ - if (!boot_cpu_has(X86_FEATURE_SEV)) + if (!sev_enabled || !npt_enabled) + 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 */ @@ -1336,27 +2173,39 @@ void __init sev_hardware_setup(void) /* Maximum number of encrypted guests supported simultaneously */ max_sev_asid = ecx; - - if (!svm_sev_enabled()) + 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 */ - sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL); + /* + * 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(max_sev_asid, GFP_KERNEL); - if (!sev_reclaim_asid_bitmap) + 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; + } - pr_info("SEV supported: %u ASIDs\n", max_sev_asid - min_sev_asid + 1); + sev_asid_count = max_sev_asid - min_sev_asid + 1; + if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)) + goto out; + + pr_info("SEV supported: %u ASIDs\n", sev_asid_count); sev_supported = true; /* SEV-ES support requested? */ - if (!sev_es) + if (!sev_es_enabled) goto out; /* Does the CPU support SEV-ES? */ @@ -1367,74 +2216,91 @@ void __init sev_hardware_setup(void) if (min_sev_asid == 1) goto out; - pr_info("SEV-ES supported: %u ASIDs\n", min_sev_asid - 1); + sev_es_asid_count = min_sev_asid - 1; + if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count)) + goto out; + + pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count); sev_es_supported = true; out: - sev = sev_supported; - sev_es = sev_es_supported; + sev_enabled = sev_supported; + sev_es_enabled = sev_es_supported; +#endif } -void sev_hardware_teardown(void) +void sev_hardware_unsetup(void) { - if (!svm_sev_enabled()) + 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); - sev_flush_asids(); + 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_guest_memory(struct vcpu_svm *svm, void *va, - unsigned long len) +static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { + int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + /* - * If hardware enforced cache coherency for encrypted mappings of the - * same physical page is supported, nothing to do. + * 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. */ - if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) - return; + unsigned long addr = (unsigned long)va; /* - * If the VM Page Flush MSR is supported, use it to flush the page - * (using the page virtual address and the guest ASID). + * 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_VM_PAGE_FLUSH)) { - struct kvm_sev_info *sev; - unsigned long va_start; - u64 start, stop; - - /* Align start and stop to page boundaries. */ - va_start = (unsigned long)va; - start = (u64)va_start & PAGE_MASK; - stop = PAGE_ALIGN((u64)va_start + len); - - if (start < stop) { - sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + if (boot_cpu_has(X86_FEATURE_SME_COHERENT)) { + clflush_cache_range(va, PAGE_SIZE); + return; + } - while (start < stop) { - wrmsrl(MSR_AMD64_VM_PAGE_FLUSH, - start | sev->asid); + /* + * 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; - start += PAGE_SIZE; - } + return; - return; - } +do_wbinvd: + wbinvd_on_all_cpus(); +} - WARN(1, "Address overflow, using WBINVD\n"); - } +void sev_guest_memory_reclaimed(struct kvm *kvm) +{ + if (!sev_guest(kvm)) + return; - /* - * Hardware should always have one of the above features, - * but if not, use WBINVD and issue a warning. - */ - WARN_ONCE(1, "Using WBINVD to flush guest memory\n"); wbinvd_on_all_cpus(); } @@ -1448,16 +2314,17 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); if (vcpu->arch.guest_state_protected) - sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE); - __free_page(virt_to_page(svm->vmsa)); + sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa); + + __free_page(virt_to_page(svm->sev_es.vmsa)); - if (svm->ghcb_sa_free) - kfree(svm->ghcb_sa); + 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->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ @@ -1483,7 +2350,7 @@ static void dump_ghcb(struct vcpu_svm *svm) static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; /* * The GHCB protocol so far allows for the following data @@ -1503,7 +2370,7 @@ 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->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 exit_code; /* @@ -1548,20 +2415,25 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu; struct ghcb *ghcb; - u64 exit_code = 0; + u64 exit_code; + u64 reason; - ghcb = svm->ghcb; - - /* Only GHCB Usage code 0 is supported */ - if (ghcb->ghcb_usage) - goto vmgexit_err; + ghcb = svm->sev_es.ghcb; /* - * Retrieve the exit code now even though is may not be marked valid + * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ exit_code = ghcb_get_sw_exit_code(ghcb); + /* Only GHCB Usage code 0 is supported */ + if (ghcb->ghcb_usage) { + reason = GHCB_ERR_INVALID_USAGE; + goto vmgexit_err; + } + + reason = GHCB_ERR_MISSING_INPUT; + if (!ghcb_sw_exit_code_is_valid(ghcb) || !ghcb_sw_exit_info_1_is_valid(ghcb) || !ghcb_sw_exit_info_2_is_valid(ghcb)) @@ -1640,6 +2512,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; default: + reason = GHCB_ERR_INVALID_EVENT; goto vmgexit_err; } @@ -1648,53 +2521,58 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) vmgexit_err: vcpu = &svm->vcpu; - if (ghcb->ghcb_usage) { + if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", 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 reason %#llx is not valid\n", + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n", exit_code); dump_ghcb(svm); } - 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; + /* Clear the valid entries fields */ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); + + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, reason); - return -EINVAL; + /* Resume the guest to "return" the error code. */ + return 1; } -static void pre_sev_es_run(struct vcpu_svm *svm) +void sev_es_unmap_ghcb(struct vcpu_svm *svm) { - if (!svm->ghcb) + if (!svm->sev_es.ghcb) return; - if (svm->ghcb_sa_free) { + 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->ghcb_sa_sync) { + if (svm->sev_es.ghcb_sa_sync) { kvm_write_guest(svm->vcpu.kvm, - ghcb_get_sw_scratch(svm->ghcb), - svm->ghcb_sa, svm->ghcb_sa_len); - svm->ghcb_sa_sync = false; + ghcb_get_sw_scratch(svm->sev_es.ghcb), + svm->sev_es.ghcb_sa, + svm->sev_es.ghcb_sa_len); + svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->ghcb_sa); - svm->ghcb_sa = NULL; - svm->ghcb_sa_free = 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->ghcb); + trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->sev_es.ghcb); sev_es_sync_to_ghcb(svm); - kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true); - svm->ghcb = NULL; + 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) @@ -1702,9 +2580,6 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); - /* Perform any SEV-ES pre-run actions */ - pre_sev_es_run(svm); - /* Assign the asid allocated with this SEV guest */ svm->asid = asid; @@ -1724,10 +2599,10 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) } #define GHCB_SCRATCH_AREA_LIMIT (16ULL * PAGE_SIZE) -static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) +static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) { struct vmcb_control_area *control = &svm->vmcb->control; - struct ghcb *ghcb = svm->ghcb; + struct ghcb *ghcb = svm->sev_es.ghcb; u64 ghcb_scratch_beg, ghcb_scratch_end; u64 scratch_gpa_beg, scratch_gpa_end; void *scratch_va; @@ -1735,14 +2610,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); - return false; + 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); - return false; + goto e_scratch; } if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { @@ -1760,10 +2635,10 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) 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); - return false; + goto e_scratch; } - scratch_va = (void *)svm->ghcb; + scratch_va = (void *)svm->sev_es.ghcb; scratch_va += (scratch_gpa_beg - control->ghcb_gpa); } else { /* @@ -1773,18 +2648,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) if (len > GHCB_SCRATCH_AREA_LIMIT) { pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", len, GHCB_SCRATCH_AREA_LIMIT); - return false; + goto e_scratch; } - scratch_va = kzalloc(len, GFP_KERNEL); + scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT); if (!scratch_va) - return false; + 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"); - kfree(scratch_va); - return false; + kvfree(scratch_va); + return -EFAULT; } /* @@ -1793,14 +2668,20 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) * the vCPU next time (i.e. a read was requested so the data * must be written back to the guest memory). */ - svm->ghcb_sa_sync = sync; - svm->ghcb_sa_free = true; + svm->sev_es.ghcb_sa_sync = sync; + svm->sev_es.ghcb_sa_free = true; } - svm->ghcb_sa = scratch_va; - svm->ghcb_sa_len = len; + svm->sev_es.ghcb_sa = scratch_va; + svm->sev_es.ghcb_sa_len = len; - return true; + return 0; + +e_scratch: + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + + return 1; } static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, @@ -1849,9 +2730,9 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) vcpu->arch.regs[VCPU_REGS_RAX] = cpuid_fn; vcpu->arch.regs[VCPU_REGS_RCX] = 0; - ret = svm_invoke_exit_handler(svm, SVM_EXIT_CPUID); + ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID); if (!ret) { - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ break; } @@ -1887,10 +2768,17 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) GHCB_MSR_TERM_REASON_POS); pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", reason_set, reason_code); - fallthrough; + + 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: - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ + break; } trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, @@ -1899,8 +2787,9 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) return ret; } -int sev_handle_vmgexit(struct vcpu_svm *svm) +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; struct ghcb *ghcb; @@ -1912,21 +2801,25 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) return sev_handle_vmgexit_msr_protocol(svm); if (!ghcb_gpa) { - vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB gpa is not set\n"); - return -EINVAL; + 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(&svm->vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) { + if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ - vcpu_unimpl(&svm->vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", + vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } - svm->ghcb = svm->ghcb_map.hva; - ghcb = svm->ghcb_map.hva; + svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; + ghcb = svm->sev_es.ghcb_map.hva; - trace_kvm_vmgexit_enter(svm->vcpu.vcpu_id, ghcb); + trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb); exit_code = ghcb_get_sw_exit_code(ghcb); @@ -1938,34 +2831,35 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); - ret = -EINVAL; switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: - if (!setup_vmgexit_scratch(svm, true, control->exit_info_2)) + ret = setup_vmgexit_scratch(svm, true, control->exit_info_2); + if (ret) break; - ret = kvm_sev_es_mmio_read(&svm->vcpu, + ret = kvm_sev_es_mmio_read(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_MMIO_WRITE: - if (!setup_vmgexit_scratch(svm, false, control->exit_info_2)) + ret = setup_vmgexit_scratch(svm, false, control->exit_info_2); + if (ret) break; - ret = kvm_sev_es_mmio_write(&svm->vcpu, + ret = kvm_sev_es_mmio_write(vcpu, control->exit_info_1, control->exit_info_2, - svm->ghcb_sa); + svm->sev_es.ghcb_sa); break; case SVM_VMGEXIT_NMI_COMPLETE: - ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); + ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET); break; case SVM_VMGEXIT_AP_HLT_LOOP: - ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + ret = kvm_emulate_ap_reset_hold(vcpu); break; case SVM_VMGEXIT_AP_JUMP_TABLE: { - struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; + struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info; switch (control->exit_info_1) { case 0: @@ -1979,23 +2873,21 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) 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(ghcb, 1); - ghcb_set_sw_exit_info_2(ghcb, - X86_TRAP_UD | - SVM_EVTINJ_TYPE_EXEPT | - SVM_EVTINJ_VALID); + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT); } ret = 1; break; } case SVM_VMGEXIT_UNSUPPORTED_EVENT: - vcpu_unimpl(&svm->vcpu, + 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(svm, exit_code); + ret = svm_invoke_exit_handler(vcpu, exit_code); } return ret; @@ -2003,11 +2895,23 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) { - if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2)) + int count; + int bytes; + int r; + + if (svm->vmcb->control.exit_info_2 > INT_MAX) return -EINVAL; - return kvm_sev_es_string_io(&svm->vcpu, size, port, - svm->ghcb_sa, svm->ghcb_sa_len, in); + 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); } void sev_es_init_vmcb(struct vcpu_svm *svm) @@ -2022,7 +2926,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) * VMCB page. Do not include the encryption mask on the VMSA physical * address since hardware will access it using the guest key. */ - svm->vmcb->control.vmsa_pa = __pa(svm->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); @@ -2053,36 +2957,40 @@ void sev_es_init_vmcb(struct vcpu_svm *svm) 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); + + if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && + (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) { + set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1); + if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP)) + svm_clr_intercept(svm, INTERCEPT_RDTSCP); + } } -void sev_es_create_vcpu(struct vcpu_svm *svm) +void sev_es_vcpu_reset(struct vcpu_svm *svm) { /* - * Set the GHCB MSR value as per the GHCB specification when creating - * a vCPU for an SEV-ES guest. + * 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_guest_switch(struct vcpu_svm *svm, unsigned int cpu) +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa) { - struct svm_cpu_data *sd = per_cpu(svm_data, cpu); - struct vmcb_save_area *hostsa; - /* * As an SEV-ES guest, hardware will restore the host state on VMEXIT, - * of which one step is to perform a VMLOAD. Since hardware does not - * perform a VMSAVE on VMRUN, the host savearea must be updated. + * of which one step is to perform a VMLOAD. KVM performs the + * corresponding VMSAVE in svm_prepare_guest_switch for both + * traditional and SEV-ES guests. */ - vmsave(__sme_page_pa(sd->save_area)); /* XCR0 is restored on VMEXIT, save the current host value */ - hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - /* PKRU is restored on VMEXIT, save the curent host value */ + /* PKRU is restored on VMEXIT, save the current host value */ hostsa->pkru = read_pkru(); /* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */ @@ -2094,8 +3002,8 @@ 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->received_first_sipi) { - svm->received_first_sipi = true; + if (!svm->sev_es.received_first_sipi) { + svm->sev_es.received_first_sipi = true; return; } @@ -2104,5 +3012,8 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a * non-zero value. */ - ghcb_set_sw_exit_info_2(svm->ghcb, 1); + 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 index 58a45bb139f8..87da90360bc7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -25,6 +25,7 @@ #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/rwsem.h> +#include <linux/cc_platform.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -36,6 +37,7 @@ #include <asm/spec-ctrl.h> #include <asm/cpu_device_id.h> #include <asm/traps.h> +#include <asm/fpu/api.h> #include <asm/virtext.h> #include "trace.h" @@ -43,7 +45,8 @@ #include "svm.h" #include "svm_ops.h" -#define __ex(x) __kvm_handle_fault_on_reboot(x) +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -56,26 +59,9 @@ static const struct x86_cpu_id svm_cpu_id[] = { MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); #endif -#define IOPM_ALLOC_ORDER 2 -#define MSRPM_ALLOC_ORDER 1 - #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 -#define SVM_FEATURE_LBRV (1 << 1) -#define SVM_FEATURE_SVML (1 << 2) -#define SVM_FEATURE_TSC_RATE (1 << 4) -#define SVM_FEATURE_VMCB_CLEAN (1 << 5) -#define SVM_FEATURE_FLUSH_ASID (1 << 6) -#define SVM_FEATURE_DECODE_ASSIST (1 << 7) -#define SVM_FEATURE_PAUSE_FILTER (1 << 10) - -#define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) - -#define TSC_RATIO_RSVD 0xffffff0000000000ULL -#define TSC_RATIO_MIN 0x0000000000000001ULL -#define TSC_RATIO_MAX 0x000000ffffffffffULL - static bool erratum_383_found __read_mostly; u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; @@ -87,7 +73,6 @@ u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; static uint64_t osvw_len = 4, osvw_status; static DEFINE_PER_CPU(u64, current_tsc_ratio); -#define TSC_RATIO_DEFAULT 0x0100000000ULL static const struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ @@ -95,6 +80,8 @@ static const struct svm_direct_access_msrs { } 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 }, @@ -112,6 +99,7 @@ static const struct svm_direct_access_msrs { { .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 = MSR_INVALID, .always = false }, }; @@ -183,20 +171,34 @@ static int vls = true; module_param(vls, int, 0444); /* enable/disable Virtual GIF */ -static int vgif = true; +int vgif = true; module_param(vgif, int, 0444); -/* enable/disable SEV support */ -int sev = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); -module_param(sev, 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); -/* enable/disable SEV-ES support */ -int sev_es = IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT); -module_param(sev_es, int, 0444); +static bool force_avic; +module_param_unsafe(force_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); + + static bool svm_gp_erratum_intercept = true; static u8 rsm_ins_bytes[] = "\x0f\xaa"; @@ -214,6 +216,15 @@ struct kvm_ldttss_desc { 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) @@ -241,12 +252,12 @@ u32 svm_msrpm_offset(u32 msr) return MSR_INVALID; } -#define MAX_INST_SIZE 15 +static void svm_flush_tlb_current(struct kvm_vcpu *vcpu); -static int get_max_npt_level(void) +static int get_npt_level(void) { #ifdef CONFIG_X86_64 - return PT64_ROOT_4LEVEL; + return pgtable_l5_enabled() ? PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL; #else return PT32E_ROOT_LEVEL; #endif @@ -268,7 +279,7 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) { if (!(efer & EFER_SVME)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, true); /* #GP intercept is still needed for vmware backdoor */ if (!enable_vmware_backdoor) @@ -279,7 +290,7 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) * In this case we will return to the nested guest * as soon as we leave SMM. */ - if (!is_smm(&svm->vcpu)) + if (!is_smm(vcpu)) svm_free_nested(svm); } else { @@ -290,7 +301,11 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return ret; } - if (svm_gp_erratum_intercept) + /* + * 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); } } @@ -327,7 +342,7 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) } -static int skip_emulated_instruction(struct kvm_vcpu *vcpu) +static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -363,10 +378,10 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) bool has_error_code = vcpu->arch.exception.has_error_code; u32 error_code = vcpu->arch.exception.error_code; - kvm_deliver_exception_payload(&svm->vcpu); + kvm_deliver_exception_payload(vcpu); if (nr == BP_VECTOR && !nrips) { - unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu); + unsigned long rip, old_rip = kvm_rip_read(vcpu); /* * For guest debugging where we have to reinject #BP if some @@ -375,8 +390,8 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) * raises a fault that is not intercepted. Still better than * failing in all cases. */ - (void)skip_emulated_instruction(&svm->vcpu); - rip = kvm_rip_read(&svm->vcpu); + (void)svm_skip_emulated_instruction(vcpu); + rip = kvm_rip_read(vcpu); svm->int3_rip = rip + svm->vmcb->save.cs.base; svm->int3_injected = rip - old_rip; } @@ -442,7 +457,7 @@ static int has_svm(void) return 0; } - if (sev_active()) { + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { pr_info("KVM is unsupported when running as an SEV guest\n"); return 0; } @@ -450,11 +465,24 @@ static int has_svm(void) return 1; } +void __svm_write_tsc_multiplier(u64 multiplier) +{ + preempt_disable(); + + if (multiplier == __this_cpu_read(current_tsc_ratio)) + goto out; + + wrmsrl(MSR_AMD64_TSC_RATIO, multiplier); + __this_cpu_write(current_tsc_ratio, multiplier); +out: + preempt_enable(); +} + static void svm_hardware_disable(void) { /* Make sure we clean up behind us */ - if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) - wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); + if (tsc_scaling) + __svm_write_tsc_multiplier(SVM_TSC_RATIO_DEFAULT); cpu_svm_disable(); @@ -496,8 +524,11 @@ static int svm_hardware_enable(void) wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area)); if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { - wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); - __this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT); + /* + * 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); } @@ -553,23 +584,19 @@ static void svm_cpu_uninit(int cpu) static int svm_cpu_init(int cpu) { struct svm_cpu_data *sd; + int ret = -ENOMEM; sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); if (!sd) - return -ENOMEM; + return ret; sd->cpu = cpu; - sd->save_area = alloc_page(GFP_KERNEL); + sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!sd->save_area) goto free_cpu_data; - clear_page(page_address(sd->save_area)); - - if (svm_sev_enabled()) { - sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1, - sizeof(void *), - GFP_KERNEL); - if (!sd->sev_vmcbs) - goto free_save_area; - } + + ret = sev_cpu_init(sd); + if (ret) + goto free_save_area; per_cpu(svm_data, cpu) = sd; @@ -579,7 +606,7 @@ free_save_area: __free_page(sd->save_area); free_cpu_data: kfree(sd); - return -ENOMEM; + return ret; } @@ -642,6 +669,7 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) 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; @@ -670,6 +698,9 @@ static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm, 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, @@ -681,14 +712,15 @@ void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, u32 *svm_vcpu_alloc_msrpm(void) { - struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER); + 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 << MSRPM_ALLOC_ORDER)); + memset(msrpm, 0xff, PAGE_SIZE * (1 << order)); return msrpm; } @@ -707,7 +739,7 @@ void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm) void svm_vcpu_free_msrpm(u32 *msrpm) { - __free_pages(virt_to_page(msrpm), MSRPM_ALLOC_ORDER); + __free_pages(virt_to_page(msrpm), get_order(MSRPM_SIZE)); } static void svm_msr_filter_changed(struct kvm_vcpu *vcpu) @@ -772,6 +804,17 @@ static void init_msrpm_offsets(void) } } +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); @@ -781,6 +824,10 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) 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) @@ -792,6 +839,67 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) 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 int svm_get_lbr_msr(struct vcpu_svm *svm, u32 index) +{ + /* + * If the LBR virtualization is disabled, the LBR msrs are always + * kept in the vmcb01 to avoid copying them on nested guest entries. + * + * If nested, and the LBR virtualization is enabled/disabled, the msrs + * are moved between the vmcb01 and vmcb02 as needed. + */ + struct vmcb *vmcb = + (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) ? + svm->vmcb : svm->vmcb01.ptr; + + switch (index) { + case MSR_IA32_DEBUGCTLMSR: + return vmcb->save.dbgctl; + case MSR_IA32_LASTBRANCHFROMIP: + return vmcb->save.br_from; + case MSR_IA32_LASTBRANCHTOIP: + return vmcb->save.br_to; + case MSR_IA32_LASTINTFROMIP: + return vmcb->save.last_excp_from; + case MSR_IA32_LASTINTTOIP: + return vmcb->save.last_excp_to; + default: + KVM_BUG(false, svm->vcpu.kvm, + "%s: Unknown MSR 0x%x", __func__, index); + return 0; + } +} + +void svm_update_lbrv(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + bool enable_lbrv = svm_get_lbr_msr(svm, MSR_IA32_DEBUGCTLMSR) & + DEBUGCTLMSR_LBR; + + bool current_enable_lbrv = !!(svm->vmcb->control.virt_ext & + LBR_CTL_ENABLE_MASK); + + if (unlikely(is_guest_mode(vcpu) && svm->lbrv_enabled)) + if (unlikely(svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)) + enable_lbrv = true; + + 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) @@ -813,6 +921,9 @@ static void grow_ple_window(struct kvm_vcpu *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, @@ -831,6 +942,9 @@ static void shrink_ple_window(struct kvm_vcpu *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, @@ -843,222 +957,20 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu) } } -/* - * 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_K8_SYSCFG, msr); - if (!(msr & MSR_K8_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, PT_WRITABLE_MASK | PT_USER_MASK); -} - -static void svm_hardware_teardown(void) +static void svm_hardware_unsetup(void) { int cpu; - if (svm_sev_enabled()) - sev_hardware_teardown(); + sev_hardware_unsetup(); for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); + __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), + get_order(IOPM_SIZE)); iopm_base = 0; } -static __init void svm_set_cpu_caps(void) -{ - kvm_set_cpu_caps(); - - supported_xss = 0; - - /* CPUID 0x80000001 and 0x8000000A (SVM features) */ - if (nested) { - kvm_cpu_cap_set(X86_FEATURE_SVM); - - if (nrips) - kvm_cpu_cap_set(X86_FEATURE_NRIPS); - - if (npt_enabled) - kvm_cpu_cap_set(X86_FEATURE_NPT); - - /* 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); -} - -static __init int svm_hardware_setup(void) -{ - int cpu; - struct page *iopm_pages; - void *iopm_va; - int r; - - iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER); - - if (!iopm_pages) - return -ENOMEM; - - iopm_va = page_address(iopm_pages); - memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); - iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; - - init_msrpm_offsets(); - - supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); - - if (boot_cpu_has(X86_FEATURE_NX)) - kvm_enable_efer_bits(EFER_NX); - - if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) - kvm_enable_efer_bits(EFER_FFXSR); - - if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - kvm_has_tsc_control = true; - kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX; - kvm_tsc_scaling_ratio_frac_bits = 32; - } - - /* 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) { - printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); - kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); - } - - if (IS_ENABLED(CONFIG_KVM_AMD_SEV) && sev) { - sev_hardware_setup(); - } else { - sev = false; - sev_es = false; - } - - svm_adjust_mmio_mask(); - - for_each_possible_cpu(cpu) { - r = svm_cpu_init(cpu); - if (r) - goto err; - } - - /* - * 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; - - kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G); - pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); - - if (nrips) { - if (!boot_cpu_has(X86_FEATURE_NRIPS)) - nrips = false; - } - - if (avic) { - if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_AVIC) || - !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { - avic = false; - } else { - pr_info("AVIC enabled\n"); - - amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); - } - } - - 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"); - } - - 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_teardown(); - return r; -} - static void init_seg(struct vmcb_seg *seg) { seg->selector = 0; @@ -1076,29 +988,38 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static u64 svm_get_l2_tsc_offset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u64 g_tsc_offset = 0; - if (is_guest_mode(vcpu)) { - /* Write L1's TSC offset. */ - g_tsc_offset = svm->vmcb->control.tsc_offset - - svm->nested.hsave->control.tsc_offset; - svm->nested.hsave->control.tsc_offset = offset; - } + return svm->nested.ctl.tsc_offset; +} - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - svm->vmcb->control.tsc_offset - g_tsc_offset, - offset); +static u64 svm_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.tsc_offset = offset + g_tsc_offset; + return svm->tsc_ratio_msr; +} + +static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +{ + struct vcpu_svm *svm = to_svm(vcpu); + svm->vmcb01.ptr->control.tsc_offset = vcpu->arch.l1_tsc_offset; + svm->vmcb->control.tsc_offset = offset; vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS); - return svm->vmcb->control.tsc_offset; } -static void svm_check_invpcid(struct vcpu_svm *svm) +static void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 multiplier) +{ + __svm_write_tsc_multiplier(multiplier); +} + + +/* 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 @@ -1111,14 +1032,55 @@ static void svm_check_invpcid(struct vcpu_svm *svm) 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 void init_vmcb(struct vcpu_svm *svm) +static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu) { - struct vmcb_control_area *control = &svm->vmcb->control; - struct vmcb_save_area *save = &svm->vmcb->save; + struct vcpu_svm *svm = to_svm(vcpu); - svm->vcpu.arch.hflags = 0; + 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); + + svm->v_vmload_vmsave_enabled = false; + } 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); @@ -1126,7 +1088,7 @@ static void init_vmcb(struct vcpu_svm *svm) 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(&svm->vcpu)) + if (!kvm_vcpu_apicv_active(vcpu)) svm_set_intercept(svm, INTERCEPT_CR8_WRITE); set_dr_intercepts(svm); @@ -1140,14 +1102,18 @@ static void init_vmcb(struct vcpu_svm *svm) * 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. + * as VMware does. Don't intercept #GP for SEV guests as KVM can't + * decrypt guest memory to decode the faulting instruction. */ - if (enable_vmware_backdoor) + if (enable_vmware_backdoor && !sev_guest(vcpu->kvm)) set_exception_intercept(svm, GP_VECTOR); svm_set_intercept(svm, INTERCEPT_INTR); svm_set_intercept(svm, INTERCEPT_NMI); - svm_set_intercept(svm, INTERCEPT_SMI); + + 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); @@ -1170,12 +1136,12 @@ static void init_vmcb(struct vcpu_svm *svm) svm_set_intercept(svm, INTERCEPT_RDPRU); svm_set_intercept(svm, INTERCEPT_RSM); - if (!kvm_mwait_in_guest(svm->vcpu.kvm)) { + if (!kvm_mwait_in_guest(vcpu->kvm)) { svm_set_intercept(svm, INTERCEPT_MONITOR); svm_set_intercept(svm, INTERCEPT_MWAIT); } - if (!kvm_hlt_in_guest(svm->vcpu.kvm)) + if (!kvm_hlt_in_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_HLT); control->iopm_base_pa = __sme_set(iopm_base); @@ -1195,29 +1161,14 @@ static void init_vmcb(struct vcpu_svm *svm) 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); - svm_set_cr4(&svm->vcpu, 0); - svm_set_efer(&svm->vcpu, 0); - save->dr6 = 0xffff0ff0; - kvm_set_rflags(&svm->vcpu, X86_EFLAGS_FIXED); - save->rip = 0x0000fff0; - svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; - - /* - * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. - * It also updates the guest-visible cr0 value. - */ - svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); - kvm_mmu_reset_context(&svm->vcpu); - - save->cr4 = X86_CR4_PAE; - /* rdx = ?? */ - if (npt_enabled) { /* Setup VMCB for Nested Paging */ control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE; @@ -1225,17 +1176,16 @@ static void init_vmcb(struct vcpu_svm *svm) clr_exception_intercept(svm, PF_VECTOR); svm_clr_intercept(svm, INTERCEPT_CR3_READ); svm_clr_intercept(svm, INTERCEPT_CR3_WRITE); - save->g_pat = svm->vcpu.arch.pat; + save->g_pat = vcpu->arch.pat; save->cr3 = 0; - save->cr4 = 0; } - svm->asid_generation = 0; + svm->current_vmcb->asid_generation = 0; svm->asid = 0; - svm->nested.vmcb12_gpa = 0; - svm->vcpu.arch.hflags = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + svm->nested.last_vmcb12_gpa = INVALID_GPA; - if (!kvm_pause_in_guest(svm->vcpu.kvm)) { + 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; @@ -1244,20 +1194,17 @@ static void init_vmcb(struct vcpu_svm *svm) svm_clr_intercept(svm, INTERCEPT_PAUSE); } - svm_check_invpcid(svm); - - if (kvm_vcpu_apicv_active(&svm->vcpu)) - avic_init_vmcb(svm); + svm_recalc_instruction_intercepts(vcpu, svm); /* - * If hardware supports Virtual VMLOAD VMSAVE then enable it - * in VMCB and clear intercepts to avoid #VMEXIT. + * If the host supports V_SPEC_CTRL then disable the interception + * of MSR_IA32_SPEC_CTRL. */ - if (vls) { - svm_clr_intercept(svm, INTERCEPT_VMLOAD); - svm_clr_intercept(svm, INTERCEPT_VMSAVE); - svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - } + 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 (vgif) { svm_clr_intercept(svm, INTERCEPT_STGI); @@ -1265,50 +1212,61 @@ static void init_vmcb(struct vcpu_svm *svm) svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK; } - if (sev_guest(svm->vcpu.kvm)) { + if (sev_guest(vcpu->kvm)) { svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE; clr_exception_intercept(svm, UD_VECTOR); - if (sev_es_guest(svm->vcpu.kvm)) { + if (sev_es_guest(vcpu->kvm)) { /* Perform SEV-ES specific VMCB updates */ sev_es_init_vmcb(svm); } } - vmcb_mark_all_dirty(svm->vmcb); + 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_default_tsc_scaling_ratio; + + 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); - u32 dummy; - u32 eax = 1; svm->spec_ctrl = 0; svm->virt_spec_ctrl = 0; - if (!init_event) { - svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) - svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; - } - init_vmcb(svm); + init_vmcb(vcpu); - kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy, false); - kvm_rdx_write(vcpu, eax); + if (!init_event) + __svm_vcpu_reset(vcpu); +} - if (kvm_vcpu_apicv_active(vcpu) && !init_event) - avic_update_vapic_bar(svm, APIC_DEFAULT_PHYS_BASE); +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_create_vcpu(struct kvm_vcpu *vcpu) +static int svm_vcpu_create(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; - struct page *vmcb_page; + struct page *vmcb01_page; struct page *vmsa_page = NULL; int err; @@ -1316,11 +1274,11 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); err = -ENOMEM; - vmcb_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); - if (!vmcb_page) + vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + if (!vmcb01_page) goto out; - if (sev_es_guest(svm->vcpu.kvm)) { + if (sev_es_guest(vcpu->kvm)) { /* * SEV-ES guests require a separate VMSA page used to contain * the encrypted register state of the guest. @@ -1332,46 +1290,30 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu) /* * SEV-ES guests maintain an encrypted version of their FPU * state which is restored and saved on VMRUN and VMEXIT. - * Free the fpu structure to prevent KVM from attempting to - * access the FPU state. + * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't + * do xsave/xrstor on it. */ - kvm_free_guest_fpu(vcpu); + fpstate_set_confidential(&vcpu->arch.guest_fpu); } err = avic_init_vcpu(svm); if (err) goto error_free_vmsa_page; - /* We initialize this flag to true to make sure that the is_running - * bit would be set the first time the vcpu is loaded. - */ - if (irqchip_in_kernel(vcpu->kvm) && kvm_apicv_activated(vcpu->kvm)) - svm->avic_is_running = true; - svm->msrpm = svm_vcpu_alloc_msrpm(); if (!svm->msrpm) { err = -ENOMEM; goto error_free_vmsa_page; } - svm_vcpu_init_msrpm(vcpu, svm->msrpm); - - svm->vmcb = page_address(vmcb_page); - svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT); + 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->vmsa = page_address(vmsa_page); + svm->sev_es.vmsa = page_address(vmsa_page); - svm->asid_generation = 0; svm->guest_state_loaded = false; - init_vmcb(svm); - - svm_init_osvw(vcpu); - vcpu->arch.microcode_version = 0x01000065; - - if (sev_es_guest(svm->vcpu.kvm)) - /* Perform SEV-ES specific VMCB creation updates */ - sev_es_create_vcpu(svm); return 0; @@ -1379,7 +1321,7 @@ error_free_vmsa_page: if (vmsa_page) __free_page(vmsa_page); error_free_vmcb_page: - __free_page(vmcb_page); + __free_page(vmcb01_page); out: return err; } @@ -1392,7 +1334,7 @@ static void svm_clear_current_vmcb(struct vmcb *vmcb) cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL); } -static void svm_free_vcpu(struct kvm_vcpu *vcpu) +static void svm_vcpu_free(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1407,68 +1349,45 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) sev_free_vcpu(vcpu); - __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); - __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); + __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_guest_switch(struct kvm_vcpu *vcpu) +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(svm_data, vcpu->cpu); - unsigned int i; + + if (sev_es_guest(vcpu->kvm)) + sev_es_unmap_ghcb(svm); if (svm->guest_state_loaded) return; /* - * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save - * area (non-sev-es). Save ones that aren't so we can restore them - * individually later. - */ - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - - /* * Save additional host state that will be restored on VMEXIT (sev-es) * or subsequent vmload of host save area. */ - if (sev_es_guest(svm->vcpu.kvm)) { - sev_es_prepare_guest_switch(svm, vcpu->cpu); - } else { - vmsave(__sme_page_pa(sd->save_area)); - } + vmsave(__sme_page_pa(sd->save_area)); + if (sev_es_guest(vcpu->kvm)) { + struct sev_es_save_area *hostsa; + hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); - if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { - u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; - if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) { - __this_cpu_write(current_tsc_ratio, tsc_ratio); - wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); - } + sev_es_prepare_switch_to_guest(hostsa); } - /* This assumes that the kernel never uses MSR_TSC_AUX */ - if (static_cpu_has(X86_FEATURE_RDTSCP)) - wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + if (tsc_scaling) + __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); + + if (likely(tsc_aux_uret_slot >= 0)) + 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) { - struct vcpu_svm *svm = to_svm(vcpu); - unsigned int i; - - if (!svm->guest_state_loaded) - return; - - /* - * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save - * area (non-sev-es). Restore the ones that weren't. - */ - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - - svm->guest_state_loaded = false; + to_svm(vcpu)->guest_state_loaded = false; } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -1476,21 +1395,19 @@ 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(svm_data, cpu); - if (unlikely(cpu != vcpu->cpu)) { - svm->asid_generation = 0; - vmcb_mark_all_dirty(svm->vmcb); - } - if (sd->current_vmcb != svm->vmcb) { sd->current_vmcb = svm->vmcb; indirect_branch_prediction_barrier(); } - avic_vcpu_load(vcpu, cpu); + if (kvm_vcpu_apicv_active(vcpu)) + avic_vcpu_load(vcpu, cpu); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) { - avic_vcpu_put(vcpu); + if (kvm_vcpu_apicv_active(vcpu)) + avic_vcpu_put(vcpu); + svm_prepare_host_switch(vcpu); ++vcpu->stat.host_state_reload; @@ -1524,15 +1441,30 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) 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: - BUG_ON(!npt_enabled); - load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); + /* + * 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: - WARN_ON_ONCE(1); + KVM_BUG_ON(1, vcpu->kvm); } } @@ -1540,8 +1472,11 @@ 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_active(&svm->vcpu)); + /* + * The following fields are ignored when AVIC is enabled + */ + WARN_ON(kvm_vcpu_apicv_activated(&svm->vcpu)); + svm_set_intercept(svm, INTERCEPT_VINTR); /* @@ -1558,17 +1493,20 @@ static void svm_set_vintr(struct vcpu_svm *svm) static void svm_clear_vintr(struct vcpu_svm *svm) { - const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK; svm_clr_intercept(svm, INTERCEPT_VINTR); /* Drop int_ctl fields related to VINTR injection. */ - svm->vmcb->control.int_ctl &= mask; + svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK; if (is_guest_mode(&svm->vcpu)) { - svm->nested.hsave->control.int_ctl &= mask; + 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 & ~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); @@ -1577,16 +1515,17 @@ static void svm_clear_vintr(struct vcpu_svm *svm) 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 &save->fs; - case VCPU_SREG_GS: return &save->gs; + 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 &save->tr; - case VCPU_SREG_LDTR: return &save->ldtr; + case VCPU_SREG_TR: return &save01->tr; + case VCPU_SREG_LDTR: return &save01->ldtr; } BUG(); return NULL; @@ -1675,6 +1614,15 @@ static int svm_get_cpl(struct kvm_vcpu *vcpu) 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); @@ -1709,37 +1657,29 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) vmcb_mark_dirty(svm->vmcb, VMCB_DT); } -static void update_cr0_intercept(struct vcpu_svm *svm) +static void sev_post_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { - ulong gcr0; - u64 *hcr0; + 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. + * 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(svm->vcpu.kvm)) - return; - - gcr0 = svm->vcpu.arch.cr0; - hcr0 = &svm->vmcb->save.cr0; - *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) - | (gcr0 & SVM_CR0_SELECTIVE_MASK); - - vmcb_mark_dirty(svm->vmcb, VMCB_CR); - - if (gcr0 == *hcr0) { - 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); + if (sev_es_guest(vcpu->kvm)) { + svm->vmcb->save.cr3 = cr3; + vmcb_mark_dirty(svm->vmcb, VMCB_CR); } } 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 && !vcpu->arch.guest_state_protected) { @@ -1756,8 +1696,11 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) #endif vcpu->arch.cr0 = cr0; - if (!npt_enabled) - cr0 |= X86_CR0_PG | X86_CR0_WP; + 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 @@ -1765,10 +1708,26 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) * reboot */ if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); - svm->vmcb->save.cr0 = cr0; + hcr0 &= ~(X86_CR0_CD | X86_CR0_NW); + + svm->vmcb->save.cr0 = hcr0; vmcb_mark_dirty(svm->vmcb, VMCB_CR); - update_cr0_intercept(svm); + + /* + * 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) @@ -1782,11 +1741,15 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long old_cr4 = vcpu->arch.cr4; if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - svm_flush_tlb(vcpu); + svm_flush_tlb_current(vcpu); vcpu->arch.cr4 = cr4; - if (!npt_enabled) + 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); @@ -1847,7 +1810,7 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) vmcb_mark_dirty(svm->vmcb, VMCB_ASID); } - svm->asid_generation = sd->asid_generation; + svm->current_vmcb->asid_generation = sd->asid_generation; svm->asid = sd->next_asid++; } @@ -1896,39 +1859,43 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) vmcb_mark_dirty(svm->vmcb, VMCB_DR); } -static int pf_interception(struct vcpu_svm *svm) +static int pf_interception(struct kvm_vcpu *vcpu) { - u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); + 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(&svm->vcpu, error_code, fault_address, + 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 vcpu_svm *svm) +static int npf_interception(struct kvm_vcpu *vcpu) { - u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2); + 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(fault_address, error_code); - return kvm_mmu_page_fault(&svm->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 vcpu_svm *svm) +static int db_interception(struct kvm_vcpu *vcpu) { - struct kvm_run *kvm_run = svm->vcpu.run; - struct kvm_vcpu *vcpu = &svm->vcpu; + struct kvm_run *kvm_run = vcpu->run; + struct vcpu_svm *svm = to_svm(vcpu); - if (!(svm->vcpu.guest_debug & + 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(&svm->vcpu, DB_VECTOR, payload); + kvm_queue_exception_p(vcpu, DB_VECTOR, payload); return 1; } @@ -1938,7 +1905,7 @@ static int db_interception(struct vcpu_svm *svm) kvm_make_request(KVM_REQ_EVENT, vcpu); } - if (svm->vcpu.guest_debug & + 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; @@ -1952,9 +1919,10 @@ static int db_interception(struct vcpu_svm *svm) return 1; } -static int bp_interception(struct vcpu_svm *svm) +static int bp_interception(struct kvm_vcpu *vcpu) { - struct kvm_run *kvm_run = svm->vcpu.run; + 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; @@ -1962,14 +1930,14 @@ static int bp_interception(struct vcpu_svm *svm) return 0; } -static int ud_interception(struct vcpu_svm *svm) +static int ud_interception(struct kvm_vcpu *vcpu) { - return handle_ud(&svm->vcpu); + return handle_ud(vcpu); } -static int ac_interception(struct vcpu_svm *svm) +static int ac_interception(struct kvm_vcpu *vcpu) { - kvm_queue_exception_e(&svm->vcpu, AC_VECTOR, 0); + kvm_queue_exception_e(vcpu, AC_VECTOR, 0); return 1; } @@ -2012,7 +1980,7 @@ static bool is_erratum_383(void) return true; } -static void svm_handle_mce(struct vcpu_svm *svm) +static void svm_handle_mce(struct kvm_vcpu *vcpu) { if (is_erratum_383()) { /* @@ -2021,7 +1989,7 @@ static void svm_handle_mce(struct vcpu_svm *svm) */ pr_err("KVM: Guest triggered AMD Erratum 383\n"); - kvm_make_request(KVM_REQ_TRIPLE_FAULT, &svm->vcpu); + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return; } @@ -2033,41 +2001,46 @@ static void svm_handle_mce(struct vcpu_svm *svm) kvm_machine_check(); } -static int mc_interception(struct vcpu_svm *svm) +static int mc_interception(struct kvm_vcpu *vcpu) { return 1; } -static int shutdown_interception(struct vcpu_svm *svm) +static int shutdown_interception(struct kvm_vcpu *vcpu) { - struct kvm_run *kvm_run = svm->vcpu.run; + 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(svm->vcpu.kvm)) + if (sev_es_guest(vcpu->kvm)) return -EINVAL; /* - * VMCB is undefined after a SHUTDOWN intercept - * so reinitialize it. + * 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); - init_vmcb(svm); + kvm_vcpu_reset(vcpu, true); kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; } -static int io_interception(struct vcpu_svm *svm) +static int io_interception(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->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; - ++svm->vcpu.stat.io_exits; + ++vcpu->stat.io_exits; string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; port = io_info >> 16; @@ -2082,93 +2055,75 @@ static int io_interception(struct vcpu_svm *svm) svm->next_rip = svm->vmcb->control.exit_info_2; - return kvm_fast_pio(&svm->vcpu, size, port, in); + return kvm_fast_pio(vcpu, size, port, in); } -static int nmi_interception(struct vcpu_svm *svm) +static int nmi_interception(struct kvm_vcpu *vcpu) { return 1; } -static int intr_interception(struct vcpu_svm *svm) +static int smi_interception(struct kvm_vcpu *vcpu) { - ++svm->vcpu.stat.irq_exits; return 1; } -static int nop_on_interception(struct vcpu_svm *svm) +static int intr_interception(struct kvm_vcpu *vcpu) { + ++vcpu->stat.irq_exits; return 1; } -static int halt_interception(struct vcpu_svm *svm) +static int vmload_vmsave_interception(struct kvm_vcpu *vcpu, bool vmload) { - return kvm_emulate_halt(&svm->vcpu); -} - -static int vmmcall_interception(struct vcpu_svm *svm) -{ - return kvm_emulate_hypercall(&svm->vcpu); -} - -static int vmload_interception(struct vcpu_svm *svm) -{ - struct vmcb *nested_vmcb; + struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb12; struct kvm_host_map map; int ret; - if (nested_svm_check_permissions(svm)) + if (nested_svm_check_permissions(vcpu)) return 1; - ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map); + ret = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map); if (ret) { if (ret == -EINVAL) - kvm_inject_gp(&svm->vcpu, 0); + kvm_inject_gp(vcpu, 0); return 1; } - nested_vmcb = map.hva; + vmcb12 = map.hva; - ret = kvm_skip_emulated_instruction(&svm->vcpu); + ret = kvm_skip_emulated_instruction(vcpu); - nested_svm_vmloadsave(nested_vmcb, svm->vmcb); - kvm_vcpu_unmap(&svm->vcpu, &map, true); + 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 vmsave_interception(struct vcpu_svm *svm) +static int vmload_interception(struct kvm_vcpu *vcpu) { - struct vmcb *nested_vmcb; - struct kvm_host_map map; - int ret; - - if (nested_svm_check_permissions(svm)) - return 1; - - ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->vmcb->save.rax), &map); - if (ret) { - if (ret == -EINVAL) - kvm_inject_gp(&svm->vcpu, 0); - return 1; - } - - nested_vmcb = map.hva; - - ret = kvm_skip_emulated_instruction(&svm->vcpu); - - nested_svm_vmloadsave(svm->vmcb, nested_vmcb); - kvm_vcpu_unmap(&svm->vcpu, &map, true); + return vmload_vmsave_interception(vcpu, true); +} - return ret; +static int vmsave_interception(struct kvm_vcpu *vcpu) +{ + return vmload_vmsave_interception(vcpu, false); } -static int vmrun_interception(struct vcpu_svm *svm) +static int vmrun_interception(struct kvm_vcpu *vcpu) { - if (nested_svm_check_permissions(svm)) + if (nested_svm_check_permissions(vcpu)) return 1; - return nested_svm_vmrun(svm); + return nested_svm_vmrun(vcpu); } enum { @@ -2207,7 +2162,7 @@ static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode) [SVM_INSTR_VMLOAD] = SVM_EXIT_VMLOAD, [SVM_INSTR_VMSAVE] = SVM_EXIT_VMSAVE, }; - int (*const svm_instr_handlers[])(struct vcpu_svm *svm) = { + int (*const svm_instr_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_INSTR_VMRUN] = vmrun_interception, [SVM_INSTR_VMLOAD] = vmload_interception, [SVM_INSTR_VMSAVE] = vmsave_interception, @@ -2216,17 +2171,13 @@ static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode) int ret; if (is_guest_mode(vcpu)) { - svm->vmcb->control.exit_code = guest_mode_exit_codes[opcode]; - svm->vmcb->control.exit_info_1 = 0; - svm->vmcb->control.exit_info_2 = 0; - /* Returns '1' or -errno on failure, '0' on success. */ - ret = nested_svm_vmexit(svm); + ret = nested_svm_simple_vmexit(svm, guest_mode_exit_codes[opcode]); if (ret) return ret; return 1; } - return svm_instr_handlers[opcode](svm); + return svm_instr_handlers[opcode](vcpu); } /* @@ -2237,9 +2188,9 @@ static int emulate_svm_instr(struct kvm_vcpu *vcpu, int opcode) * regions (e.g. SMM memory on host). * 2) VMware backdoor */ -static int gp_interception(struct vcpu_svm *svm) +static int gp_interception(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->vcpu; + struct vcpu_svm *svm = to_svm(vcpu); u32 error_code = svm->vmcb->control.exit_info_1; int opcode; @@ -2264,8 +2215,13 @@ static int gp_interception(struct vcpu_svm *svm) if (!is_guest_mode(vcpu)) return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE); - } else + } 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); @@ -2281,7 +2237,7 @@ void svm_set_gif(struct vcpu_svm *svm, bool value) * Likewise, clear the VINTR intercept, we will set it * again while processing KVM_REQ_EVENT if needed. */ - if (vgif_enabled(svm)) + if (vgif) svm_clr_intercept(svm, INTERCEPT_STGI); if (svm_is_intercept(svm, INTERCEPT_VINTR)) svm_clear_vintr(svm); @@ -2299,78 +2255,63 @@ void svm_set_gif(struct vcpu_svm *svm, bool value) * in use, we still rely on the VINTR intercept (rather than * STGI) to detect an open interrupt window. */ - if (!vgif_enabled(svm)) + if (!vgif) svm_clear_vintr(svm); } } -static int stgi_interception(struct vcpu_svm *svm) +static int stgi_interception(struct kvm_vcpu *vcpu) { int ret; - if (nested_svm_check_permissions(svm)) + if (nested_svm_check_permissions(vcpu)) return 1; - ret = kvm_skip_emulated_instruction(&svm->vcpu); - svm_set_gif(svm, true); + ret = kvm_skip_emulated_instruction(vcpu); + svm_set_gif(to_svm(vcpu), true); return ret; } -static int clgi_interception(struct vcpu_svm *svm) +static int clgi_interception(struct kvm_vcpu *vcpu) { int ret; - if (nested_svm_check_permissions(svm)) + if (nested_svm_check_permissions(vcpu)) return 1; - ret = kvm_skip_emulated_instruction(&svm->vcpu); - svm_set_gif(svm, false); + ret = kvm_skip_emulated_instruction(vcpu); + svm_set_gif(to_svm(vcpu), false); return ret; } -static int invlpga_interception(struct vcpu_svm *svm) +static int invlpga_interception(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->vcpu; - - trace_kvm_invlpga(svm->vmcb->save.rip, kvm_rcx_read(&svm->vcpu), - kvm_rax_read(&svm->vcpu)); + gva_t gva = kvm_rax_read(vcpu); + u32 asid = kvm_rcx_read(vcpu); - /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ - kvm_mmu_invlpg(vcpu, kvm_rax_read(&svm->vcpu)); - - return kvm_skip_emulated_instruction(&svm->vcpu); -} + /* FIXME: Handle an address size prefix. */ + if (!is_long_mode(vcpu)) + gva = (u32)gva; -static int skinit_interception(struct vcpu_svm *svm) -{ - trace_kvm_skinit(svm->vmcb->save.rip, kvm_rax_read(&svm->vcpu)); + trace_kvm_invlpga(to_svm(vcpu)->vmcb->save.rip, asid, gva); - kvm_queue_exception(&svm->vcpu, UD_VECTOR); - return 1; -} + /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ + kvm_mmu_invlpg(vcpu, gva); -static int wbinvd_interception(struct vcpu_svm *svm) -{ - return kvm_emulate_wbinvd(&svm->vcpu); + return kvm_skip_emulated_instruction(vcpu); } -static int xsetbv_interception(struct vcpu_svm *svm) +static int skinit_interception(struct kvm_vcpu *vcpu) { - u64 new_bv = kvm_read_edx_eax(&svm->vcpu); - u32 index = kvm_rcx_read(&svm->vcpu); + trace_kvm_skinit(to_svm(vcpu)->vmcb->save.rip, kvm_rax_read(vcpu)); - int err = kvm_set_xcr(&svm->vcpu, index, new_bv); - return kvm_complete_insn_gp(&svm->vcpu, err); -} - -static int rdpru_interception(struct vcpu_svm *svm) -{ - kvm_queue_exception(&svm->vcpu, UD_VECTOR); + kvm_queue_exception(vcpu, UD_VECTOR); return 1; } -static int task_switch_interception(struct vcpu_svm *svm) +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 & @@ -2399,7 +2340,7 @@ static int task_switch_interception(struct vcpu_svm *svm) if (reason == TASK_SWITCH_GATE) { switch (type) { case SVM_EXITINTINFO_TYPE_NMI: - svm->vcpu.arch.nmi_injected = false; + vcpu->arch.nmi_injected = false; break; case SVM_EXITINTINFO_TYPE_EXEPT: if (svm->vmcb->control.exit_info_2 & @@ -2408,10 +2349,10 @@ static int task_switch_interception(struct vcpu_svm *svm) error_code = (u32)svm->vmcb->control.exit_info_2; } - kvm_clear_exception_queue(&svm->vcpu); + kvm_clear_exception_queue(vcpu); break; case SVM_EXITINTINFO_TYPE_INTR: - kvm_clear_interrupt_queue(&svm->vcpu); + kvm_clear_interrupt_queue(vcpu); break; default: break; @@ -2422,78 +2363,59 @@ static int task_switch_interception(struct vcpu_svm *svm) int_type == SVM_EXITINTINFO_TYPE_SOFT || (int_type == SVM_EXITINTINFO_TYPE_EXEPT && (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) { - if (!skip_emulated_instruction(&svm->vcpu)) + if (!svm_skip_emulated_instruction(vcpu)) return 0; } if (int_type != SVM_EXITINTINFO_TYPE_SOFT) int_vec = -1; - return kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, + return kvm_task_switch(vcpu, tss_selector, int_vec, reason, has_error_code, error_code); } -static int cpuid_interception(struct vcpu_svm *svm) +static int iret_interception(struct kvm_vcpu *vcpu) { - return kvm_emulate_cpuid(&svm->vcpu); -} + struct vcpu_svm *svm = to_svm(vcpu); -static int iret_interception(struct vcpu_svm *svm) -{ - ++svm->vcpu.stat.nmi_window_exits; - svm->vcpu.arch.hflags |= HF_IRET_MASK; - if (!sev_es_guest(svm->vcpu.kvm)) { + ++vcpu->stat.nmi_window_exits; + vcpu->arch.hflags |= HF_IRET_MASK; + if (!sev_es_guest(vcpu->kvm)) { svm_clr_intercept(svm, INTERCEPT_IRET); - svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu); + svm->nmi_iret_rip = kvm_rip_read(vcpu); } - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } -static int invd_interception(struct vcpu_svm *svm) -{ - /* Treat an INVD instruction as a NOP and just skip it. */ - return kvm_skip_emulated_instruction(&svm->vcpu); -} - -static int invlpg_interception(struct vcpu_svm *svm) +static int invlpg_interception(struct kvm_vcpu *vcpu) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) - return kvm_emulate_instruction(&svm->vcpu, 0); - - kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); - return kvm_skip_emulated_instruction(&svm->vcpu); -} + return kvm_emulate_instruction(vcpu, 0); -static int emulate_on_interception(struct vcpu_svm *svm) -{ - return kvm_emulate_instruction(&svm->vcpu, 0); + kvm_mmu_invlpg(vcpu, to_svm(vcpu)->vmcb->control.exit_info_1); + return kvm_skip_emulated_instruction(vcpu); } -static int rsm_interception(struct vcpu_svm *svm) +static int emulate_on_interception(struct kvm_vcpu *vcpu) { - return kvm_emulate_instruction_from_buffer(&svm->vcpu, rsm_ins_bytes, 2); + return kvm_emulate_instruction(vcpu, 0); } -static int rdpmc_interception(struct vcpu_svm *svm) +static int rsm_interception(struct kvm_vcpu *vcpu) { - int err; - - if (!nrips) - return emulate_on_interception(svm); - - err = kvm_rdpmc(&svm->vcpu); - return kvm_complete_insn_gp(&svm->vcpu, err); + return kvm_emulate_instruction_from_buffer(vcpu, rsm_ins_bytes, 2); } -static bool check_selective_cr0_intercepted(struct vcpu_svm *svm, +static bool check_selective_cr0_intercepted(struct kvm_vcpu *vcpu, unsigned long val) { - unsigned long cr0 = svm->vcpu.arch.cr0; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long cr0 = vcpu->arch.cr0; bool ret = false; - if (!is_guest_mode(&svm->vcpu) || - (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) + if (!is_guest_mode(vcpu) || + (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0)))) return false; cr0 &= ~SVM_CR0_SELECTIVE_MASK; @@ -2509,17 +2431,18 @@ static bool check_selective_cr0_intercepted(struct vcpu_svm *svm, #define CR_VALID (1ULL << 63) -static int cr_interception(struct vcpu_svm *svm) +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(svm); + return emulate_on_interception(vcpu); if (unlikely((svm->vmcb->control.exit_info_1 & CR_VALID) == 0)) - return emulate_on_interception(svm); + 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) @@ -2530,61 +2453,61 @@ static int cr_interception(struct vcpu_svm *svm) err = 0; if (cr >= 16) { /* mov to cr */ cr -= 16; - val = kvm_register_read(&svm->vcpu, reg); + val = kvm_register_read(vcpu, reg); trace_kvm_cr_write(cr, val); switch (cr) { case 0: - if (!check_selective_cr0_intercepted(svm, val)) - err = kvm_set_cr0(&svm->vcpu, val); + if (!check_selective_cr0_intercepted(vcpu, val)) + err = kvm_set_cr0(vcpu, val); else return 1; break; case 3: - err = kvm_set_cr3(&svm->vcpu, val); + err = kvm_set_cr3(vcpu, val); break; case 4: - err = kvm_set_cr4(&svm->vcpu, val); + err = kvm_set_cr4(vcpu, val); break; case 8: - err = kvm_set_cr8(&svm->vcpu, val); + err = kvm_set_cr8(vcpu, val); break; default: WARN(1, "unhandled write to CR%d", cr); - kvm_queue_exception(&svm->vcpu, UD_VECTOR); + kvm_queue_exception(vcpu, UD_VECTOR); return 1; } } else { /* mov from cr */ switch (cr) { case 0: - val = kvm_read_cr0(&svm->vcpu); + val = kvm_read_cr0(vcpu); break; case 2: - val = svm->vcpu.arch.cr2; + val = vcpu->arch.cr2; break; case 3: - val = kvm_read_cr3(&svm->vcpu); + val = kvm_read_cr3(vcpu); break; case 4: - val = kvm_read_cr4(&svm->vcpu); + val = kvm_read_cr4(vcpu); break; case 8: - val = kvm_get_cr8(&svm->vcpu); + val = kvm_get_cr8(vcpu); break; default: WARN(1, "unhandled read from CR%d", cr); - kvm_queue_exception(&svm->vcpu, UD_VECTOR); + kvm_queue_exception(vcpu, UD_VECTOR); return 1; } - kvm_register_write(&svm->vcpu, reg, val); + kvm_register_write(vcpu, reg, val); trace_kvm_cr_read(cr, val); } - return kvm_complete_insn_gp(&svm->vcpu, err); + return kvm_complete_insn_gp(vcpu, err); } -static int cr_trap(struct vcpu_svm *svm) +static int cr_trap(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->vcpu; + struct vcpu_svm *svm = to_svm(vcpu); unsigned long old_value, new_value; unsigned int cr; int ret = 0; @@ -2606,7 +2529,7 @@ static int cr_trap(struct vcpu_svm *svm) kvm_post_set_cr4(vcpu, old_value, new_value); break; case 8: - ret = kvm_set_cr8(&svm->vcpu, new_value); + ret = kvm_set_cr8(vcpu, new_value); break; default: WARN(1, "unhandled CR%d write trap", cr); @@ -2617,57 +2540,57 @@ static int cr_trap(struct vcpu_svm *svm) return kvm_complete_insn_gp(vcpu, ret); } -static int dr_interception(struct vcpu_svm *svm) +static int dr_interception(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); int reg, dr; unsigned long val; int err = 0; - if (svm->vcpu.guest_debug == 0) { + 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); - svm->vcpu.arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; return 1; } if (!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) - return emulate_on_interception(svm); + 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(&svm->vcpu, reg); - err = kvm_set_dr(&svm->vcpu, dr, val); + val = kvm_register_read(vcpu, reg); + err = kvm_set_dr(vcpu, dr, val); } else { - kvm_get_dr(&svm->vcpu, dr, &val); - kvm_register_write(&svm->vcpu, reg, val); + kvm_get_dr(vcpu, dr, &val); + kvm_register_write(vcpu, reg, val); } - return kvm_complete_insn_gp(&svm->vcpu, err); + return kvm_complete_insn_gp(vcpu, err); } -static int cr8_write_interception(struct vcpu_svm *svm) +static int cr8_write_interception(struct kvm_vcpu *vcpu) { - struct kvm_run *kvm_run = svm->vcpu.run; int r; - u8 cr8_prev = kvm_get_cr8(&svm->vcpu); + u8 cr8_prev = kvm_get_cr8(vcpu); /* instruction emulation calls kvm_set_cr8() */ - r = cr_interception(svm); - if (lapic_in_kernel(&svm->vcpu)) + r = cr_interception(vcpu); + if (lapic_in_kernel(vcpu)) return r; - if (cr8_prev <= kvm_get_cr8(&svm->vcpu)) + if (cr8_prev <= kvm_get_cr8(vcpu)) return r; - kvm_run->exit_reason = KVM_EXIT_SET_TPR; + vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } -static int efer_trap(struct vcpu_svm *svm) +static int efer_trap(struct kvm_vcpu *vcpu) { struct msr_data msr_info; int ret; @@ -2680,10 +2603,10 @@ static int efer_trap(struct vcpu_svm *svm) */ msr_info.host_initiated = false; msr_info.index = MSR_EFER; - msr_info.data = svm->vmcb->control.exit_info_1 & ~EFER_SVME; - ret = kvm_set_msr_common(&svm->vcpu, &msr_info); + 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(&svm->vcpu, ret); + return kvm_complete_insn_gp(vcpu, ret); } static int svm_get_msr_feature(struct kvm_msr_entry *msr) @@ -2709,56 +2632,50 @@ 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 && !svm->tsc_scaling_enabled) + return 1; + msr_info->data = svm->tsc_ratio_msr; + break; case MSR_STAR: - msr_info->data = svm->vmcb->save.star; + msr_info->data = svm->vmcb01.ptr->save.star; break; #ifdef CONFIG_X86_64 case MSR_LSTAR: - msr_info->data = svm->vmcb->save.lstar; + msr_info->data = svm->vmcb01.ptr->save.lstar; break; case MSR_CSTAR: - msr_info->data = svm->vmcb->save.cstar; + msr_info->data = svm->vmcb01.ptr->save.cstar; break; case MSR_KERNEL_GS_BASE: - msr_info->data = svm->vmcb->save.kernel_gs_base; + msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base; break; case MSR_SYSCALL_MASK: - msr_info->data = svm->vmcb->save.sfmask; + msr_info->data = svm->vmcb01.ptr->save.sfmask; break; #endif case MSR_IA32_SYSENTER_CS: - msr_info->data = svm->vmcb->save.sysenter_cs; + msr_info->data = svm->vmcb01.ptr->save.sysenter_cs; break; case MSR_IA32_SYSENTER_EIP: - msr_info->data = svm->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->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: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) - return 1; msr_info->data = svm->tsc_aux; break; - /* - * Nobody will change the following 5 values in the VMCB so we can - * safely return them on rdmsr. They will always be 0 until LBRV is - * implemented. - */ case MSR_IA32_DEBUGCTLMSR: - msr_info->data = svm->vmcb->save.dbgctl; - break; case MSR_IA32_LASTBRANCHFROMIP: - msr_info->data = svm->vmcb->save.br_from; - break; case MSR_IA32_LASTBRANCHTOIP: - msr_info->data = svm->vmcb->save.br_to; - break; case MSR_IA32_LASTINTFROMIP: - msr_info->data = svm->vmcb->save.last_excp_from; - break; case MSR_IA32_LASTINTTOIP: - msr_info->data = svm->vmcb->save.last_excp_to; + msr_info->data = svm_get_lbr_msr(svm, msr_info->index); break; case MSR_VM_HSAVE_PA: msr_info->data = svm->nested.hsave_msr; @@ -2771,7 +2688,10 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_has_spec_ctrl_msr(vcpu)) return 1; - msr_info->data = svm->spec_ctrl; + 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 && @@ -2809,22 +2729,17 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) static int svm_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) { struct vcpu_svm *svm = to_svm(vcpu); - if (!sev_es_guest(svm->vcpu.kvm) || !err) - return kvm_complete_insn_gp(&svm->vcpu, err); + 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->ghcb, 1); - ghcb_set_sw_exit_info_2(svm->ghcb, + 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 rdmsr_interception(struct vcpu_svm *svm) -{ - return kvm_emulate_rdmsr(&svm->vcpu); -} - static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) { struct vcpu_svm *svm = to_svm(vcpu); @@ -2853,15 +2768,46 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct vcpu_svm *svm = to_svm(vcpu); + int r; u32 ecx = msr->index; u64 data = msr->data; switch (ecx) { + case MSR_AMD64_TSC_RATIO: + + if (!svm->tsc_scaling_enabled) { + + 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 (svm->tsc_scaling_enabled && is_guest_mode(vcpu)) + nested_svm_update_tsc_ratio_msr(vcpu); + + break; case MSR_IA32_CR_PAT: if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) return 1; vcpu->arch.pat = data; - svm->vmcb->save.g_pat = data; + 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: @@ -2872,7 +2818,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (kvm_spec_ctrl_test_value(data)) return 1; - svm->spec_ctrl = data; + if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + svm->vmcb->save.spec_ctrl = data; + else + svm->spec_ctrl = data; if (!data) break; @@ -2915,47 +2864,56 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->virt_spec_ctrl = data; break; case MSR_STAR: - svm->vmcb->save.star = data; + svm->vmcb01.ptr->save.star = data; break; #ifdef CONFIG_X86_64 case MSR_LSTAR: - svm->vmcb->save.lstar = data; + svm->vmcb01.ptr->save.lstar = data; break; case MSR_CSTAR: - svm->vmcb->save.cstar = data; + svm->vmcb01.ptr->save.cstar = data; break; case MSR_KERNEL_GS_BASE: - svm->vmcb->save.kernel_gs_base = data; + svm->vmcb01.ptr->save.kernel_gs_base = data; break; case MSR_SYSCALL_MASK: - svm->vmcb->save.sfmask = data; + svm->vmcb01.ptr->save.sfmask = data; break; #endif case MSR_IA32_SYSENTER_CS: - svm->vmcb->save.sysenter_cs = data; + svm->vmcb01.ptr->save.sysenter_cs = data; break; case MSR_IA32_SYSENTER_EIP: - svm->sysenter_eip = data; - svm->vmcb->save.sysenter_eip = data; + 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->sysenter_esp = data; - svm->vmcb->save.sysenter_esp = data; + 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: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) - return 1; - /* - * This is rare, so we update the MSR here instead of using - * direct_access_msrs. Doing that would require a rdmsr in - * svm_vcpu_put. + * 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(); + r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); + preempt_enable(); + if (r) + return 1; + svm->tsc_aux = data; - wrmsrl(MSR_TSC_AUX, svm->tsc_aux); break; case MSR_IA32_DEBUGCTLMSR: - if (!boot_cpu_has(X86_FEATURE_LBRV)) { + if (!lbrv) { vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", __func__, data); break; @@ -2963,15 +2921,25 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & DEBUGCTL_RESERVED_BITS) return 1; - svm->vmcb->save.dbgctl = data; - vmcb_mark_dirty(svm->vmcb, VMCB_LBR); - if (data & (1ULL<<0)) - svm_enable_lbrv(vcpu); + if (svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) + svm->vmcb->save.dbgctl = data; else - svm_disable_lbrv(vcpu); + svm->vmcb01.ptr->save.dbgctl = data; + + svm_update_lbrv(vcpu); + break; case MSR_VM_HSAVE_PA: - svm->nested.hsave_msr = data; + /* + * 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); @@ -2996,84 +2964,62 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->msr_decfg = data; break; } - case MSR_IA32_APICBASE: - if (kvm_vcpu_apicv_active(vcpu)) - avic_update_vapic_bar(to_svm(vcpu), data); - fallthrough; default: return kvm_set_msr_common(vcpu, msr); } return 0; } -static int wrmsr_interception(struct vcpu_svm *svm) +static int msr_interception(struct kvm_vcpu *vcpu) { - return kvm_emulate_wrmsr(&svm->vcpu); -} - -static int msr_interception(struct vcpu_svm *svm) -{ - if (svm->vmcb->control.exit_info_1) - return wrmsr_interception(svm); + if (to_svm(vcpu)->vmcb->control.exit_info_1) + return kvm_emulate_wrmsr(vcpu); else - return rdmsr_interception(svm); + return kvm_emulate_rdmsr(vcpu); } -static int interrupt_window_interception(struct vcpu_svm *svm) +static int interrupt_window_interception(struct kvm_vcpu *vcpu) { - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); - svm_clear_vintr(svm); + kvm_make_request(KVM_REQ_EVENT, vcpu); + svm_clear_vintr(to_svm(vcpu)); /* - * For AVIC, the only reason to end up here is ExtINTs. + * 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. */ - svm_toggle_avic_for_irq_window(&svm->vcpu, true); + kvm_clear_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN); - ++svm->vcpu.stat.irq_window_exits; + ++vcpu->stat.irq_window_exits; return 1; } -static int pause_interception(struct vcpu_svm *svm) +static int pause_interception(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->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(svm->vcpu.kvm) && svm_get_cpl(vcpu) == 0; + in_kernel = !sev_es_guest(vcpu->kvm) && svm_get_cpl(vcpu) == 0; - if (!kvm_pause_in_guest(vcpu->kvm)) - grow_ple_window(vcpu); + grow_ple_window(vcpu); kvm_vcpu_on_spin(vcpu, in_kernel); - return 1; -} - -static int nop_interception(struct vcpu_svm *svm) -{ - return kvm_skip_emulated_instruction(&(svm->vcpu)); + return kvm_skip_emulated_instruction(vcpu); } -static int monitor_interception(struct vcpu_svm *svm) +static int invpcid_interception(struct kvm_vcpu *vcpu) { - printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); - return nop_interception(svm); -} - -static int mwait_interception(struct vcpu_svm *svm) -{ - printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); - return nop_interception(svm); -} - -static int invpcid_interception(struct vcpu_svm *svm) -{ - struct kvm_vcpu *vcpu = &svm->vcpu; + struct vcpu_svm *svm = to_svm(vcpu); unsigned long type; gva_t gva; @@ -3090,15 +3036,10 @@ static int invpcid_interception(struct vcpu_svm *svm) type = svm->vmcb->control.exit_info_2; gva = svm->vmcb->control.exit_info_1; - if (type > 3) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return kvm_handle_invpcid(vcpu, type, gva); } -static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { +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, @@ -3133,15 +3074,14 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, - [SVM_EXIT_SMI] = nop_on_interception, - [SVM_EXIT_INIT] = nop_on_interception, + [SVM_EXIT_SMI] = smi_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, - [SVM_EXIT_RDPMC] = rdpmc_interception, - [SVM_EXIT_CPUID] = cpuid_interception, + [SVM_EXIT_RDPMC] = kvm_emulate_rdpmc, + [SVM_EXIT_CPUID] = kvm_emulate_cpuid, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = invd_interception, + [SVM_EXIT_INVD] = kvm_emulate_invd, [SVM_EXIT_PAUSE] = pause_interception, - [SVM_EXIT_HLT] = halt_interception, + [SVM_EXIT_HLT] = kvm_emulate_halt, [SVM_EXIT_INVLPG] = invlpg_interception, [SVM_EXIT_INVLPGA] = invlpga_interception, [SVM_EXIT_IOIO] = io_interception, @@ -3149,17 +3089,18 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_TASK_SWITCH] = task_switch_interception, [SVM_EXIT_SHUTDOWN] = shutdown_interception, [SVM_EXIT_VMRUN] = vmrun_interception, - [SVM_EXIT_VMMCALL] = vmmcall_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_WBINVD] = wbinvd_interception, - [SVM_EXIT_MONITOR] = monitor_interception, - [SVM_EXIT_MWAIT] = mwait_interception, - [SVM_EXIT_XSETBV] = xsetbv_interception, - [SVM_EXIT_RDPRU] = rdpru_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, @@ -3177,12 +3118,15 @@ 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); @@ -3239,30 +3183,30 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) save->ds.limit, save->ds.base); pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", "fs:", - save->fs.selector, save->fs.attrib, - save->fs.limit, save->fs.base); + 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:", - save->gs.selector, save->gs.attrib, - save->gs.limit, save->gs.base); + 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:", - save->ldtr.selector, save->ldtr.attrib, - save->ldtr.limit, save->ldtr.base); + 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:", - save->tr.selector, save->tr.attrib, - save->tr.limit, save->tr.base); - pr_err("cpl: %d efer: %016llx\n", - save->cpl, save->efer); + 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", @@ -3274,15 +3218,15 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) pr_err("%-15s %016llx %-13s %016llx\n", "rsp:", save->rsp, "rax:", save->rax); pr_err("%-15s %016llx %-13s %016llx\n", - "star:", save->star, "lstar:", save->lstar); + "star:", save01->star, "lstar:", save01->lstar); pr_err("%-15s %016llx %-13s %016llx\n", - "cstar:", save->cstar, "sfmask:", save->sfmask); + "cstar:", save01->cstar, "sfmask:", save01->sfmask); pr_err("%-15s %016llx %-13s %016llx\n", - "kernel_gs_base:", save->kernel_gs_base, - "sysenter_cs:", save->sysenter_cs); + "kernel_gs_base:", save01->kernel_gs_base, + "sysenter_cs:", save01->sysenter_cs); pr_err("%-15s %016llx %-13s %016llx\n", - "sysenter_esp:", save->sysenter_esp, - "sysenter_eip:", save->sysenter_eip); + "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", @@ -3292,12 +3236,14 @@ static void dump_vmcb(struct kvm_vcpu *vcpu) "excp_to:", save->last_excp_to); } -static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code) +static bool svm_check_exit_valid(u64 exit_code) { - if (exit_code < ARRAY_SIZE(svm_exit_handlers) && - svm_exit_handlers[exit_code]) - return 0; + 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; @@ -3305,35 +3251,36 @@ static int svm_handle_invalid_exit(struct kvm_vcpu *vcpu, u64 exit_code) vcpu->run->internal.ndata = 2; vcpu->run->internal.data[0] = exit_code; vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; - - return -EINVAL; + return 0; } -int svm_invoke_exit_handler(struct vcpu_svm *svm, u64 exit_code) +int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) { - if (svm_handle_invalid_exit(&svm->vcpu, exit_code)) - return 0; + 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(svm); + return msr_interception(vcpu); else if (exit_code == SVM_EXIT_VINTR) - return interrupt_window_interception(svm); + return interrupt_window_interception(vcpu); else if (exit_code == SVM_EXIT_INTR) - return intr_interception(svm); + return intr_interception(vcpu); else if (exit_code == SVM_EXIT_HLT) - return halt_interception(svm); + return kvm_emulate_halt(vcpu); else if (exit_code == SVM_EXIT_NPF) - return npf_interception(svm); + return npf_interception(vcpu); #endif - return svm_exit_handlers[exit_code](svm); + return svm_exit_handlers[exit_code](vcpu); } -static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, +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; @@ -3344,13 +3291,13 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2, *error_code = 0; } -static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) +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; - trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + trace_kvm_exit(vcpu, KVM_ISA_SVM); /* SEV-ES guests must use the CR write traps to track CR registers. */ if (!sev_es_guest(vcpu->kvm)) { @@ -3363,7 +3310,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (is_guest_mode(vcpu)) { int vmexit; - trace_kvm_nested_vmexit(exit_code, vcpu, KVM_ISA_SVM); + trace_kvm_nested_vmexit(vcpu, KVM_ISA_SVM); vmexit = nested_svm_exit_special(svm); @@ -3395,7 +3342,7 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; - return svm_invoke_exit_handler(svm, exit_code); + return svm_invoke_exit_handler(vcpu, exit_code); } static void reload_tss(struct kvm_vcpu *vcpu) @@ -3406,15 +3353,27 @@ static void reload_tss(struct kvm_vcpu *vcpu) load_TR_desc(); } -static void pre_svm_run(struct vcpu_svm *svm) +static void pre_svm_run(struct kvm_vcpu *vcpu) { - struct svm_cpu_data *sd = per_cpu(svm_data, svm->vcpu.cpu); + struct svm_cpu_data *sd = per_cpu(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(svm->vcpu.kvm)) - return pre_sev_run(svm, svm->vcpu.cpu); + if (sev_guest(vcpu->kvm)) + return pre_sev_run(svm, vcpu->cpu); /* FIXME: handle wraparound of asid_generation */ - if (svm->asid_generation != sd->asid_generation) + if (svm->current_vmcb->asid_generation != sd->asid_generation) new_asid(svm, sd); } @@ -3424,12 +3383,12 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; vcpu->arch.hflags |= HF_NMI_MASK; - if (!sev_es_guest(svm->vcpu.kvm)) + if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); ++vcpu->stat.nmi_injections; } -static void svm_set_irq(struct kvm_vcpu *vcpu) +static void svm_inject_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3442,6 +3401,55 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vector) +{ + /* + * vcpu->arch.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); + + if (!READ_ONCE(vcpu->arch.apicv_active)) { + /* Process the interrupt via inject_pending_event */ + 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); @@ -3478,7 +3486,7 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) return false; ret = (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || - (svm->vcpu.arch.hflags & HF_NMI_MASK); + (vcpu->arch.hflags & HF_NMI_MASK); return ret; } @@ -3489,18 +3497,18 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) 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 !svm_nmi_blocked(vcpu); + return 1; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) { - struct vcpu_svm *svm = to_svm(vcpu); - - return !!(svm->vcpu.arch.hflags & HF_NMI_MASK); + return !!(vcpu->arch.hflags & HF_NMI_MASK); } static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) @@ -3508,12 +3516,12 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) struct vcpu_svm *svm = to_svm(vcpu); if (masked) { - svm->vcpu.arch.hflags |= HF_NMI_MASK; - if (!sev_es_guest(svm->vcpu.kvm)) + vcpu->arch.hflags |= HF_NMI_MASK; + if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); } else { - svm->vcpu.arch.hflags &= ~HF_NMI_MASK; - if (!sev_es_guest(svm->vcpu.kvm)) + vcpu->arch.hflags &= ~HF_NMI_MASK; + if (!sev_es_guest(vcpu->kvm)) svm_clr_intercept(svm, INTERCEPT_IRET); } } @@ -3526,17 +3534,10 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (!gif_set(svm)) return true; - if (sev_es_guest(svm->vcpu.kvm)) { - /* - * SEV-ES guests to not expose RFLAGS. Use the VMCB interrupt mask - * bit to determine the state of the IF flag. - */ - if (!(vmcb->control.int_state & SVM_GUEST_INTERRUPT_MASK)) - return true; - } else if (is_guest_mode(vcpu)) { + if (is_guest_mode(vcpu)) { /* As long as interrupts are being delivered... */ if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) - ? !(svm->nested.hsave->save.rflags & X86_EFLAGS_IF) + ? !(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF) : !(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) return true; @@ -3544,7 +3545,7 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) if (nested_exit_on_intr(svm)) return false; } else { - if (!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF)) + if (!svm_get_if_flag(vcpu)) return true; } @@ -3554,9 +3555,13 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) 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. @@ -3564,7 +3569,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm)) return -EBUSY; - return !svm_interrupt_blocked(vcpu); + return 1; } static void svm_enable_irq_window(struct kvm_vcpu *vcpu) @@ -3579,14 +3584,20 @@ static void svm_enable_irq_window(struct kvm_vcpu *vcpu) * enabled, the STGI interception will not occur. Enable the irq * window under the assumption that the hardware will set the GIF. */ - if (vgif_enabled(svm) || gif_set(svm)) { + 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, we need to temporarily disable AVIC, + * 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. */ - svm_toggle_avic_for_irq_window(vcpu, false); + if (!is_guest_mode(vcpu)) + kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_IRQWIN); + svm_set_vintr(svm); } } @@ -3595,12 +3606,11 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if ((svm->vcpu.arch.hflags & (HF_NMI_MASK | HF_IRET_MASK)) - == HF_NMI_MASK) + if ((vcpu->arch.hflags & (HF_NMI_MASK | HF_IRET_MASK)) == HF_NMI_MASK) return; /* IRET will cause a vm exit */ if (!gif_set(svm)) { - if (vgif_enabled(svm)) + if (vgif) svm_set_intercept(svm, INTERCEPT_STGI); return; /* STGI will cause a vm exit */ } @@ -3614,17 +3624,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); } -static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) -{ - return 0; -} - -static int svm_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) -{ - return 0; -} - -void svm_flush_tlb(struct kvm_vcpu *vcpu) +static void svm_flush_tlb_current(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3638,7 +3638,7 @@ void svm_flush_tlb(struct kvm_vcpu *vcpu) if (static_cpu_has(X86_FEATURE_FLUSHBYASID)) svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; else - svm->asid_generation--; + svm->current_vmcb->asid_generation--; } static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva) @@ -3675,8 +3675,9 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; } -static void svm_complete_interrupts(struct vcpu_svm *svm) +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; @@ -3688,28 +3689,28 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) * If we've made progress since setting HF_IRET_MASK, we've * executed an IRET and can allow NMI injection. */ - if ((svm->vcpu.arch.hflags & HF_IRET_MASK) && - (sev_es_guest(svm->vcpu.kvm) || - kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip)) { - svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + if ((vcpu->arch.hflags & HF_IRET_MASK) && + (sev_es_guest(vcpu->kvm) || + kvm_rip_read(vcpu) != svm->nmi_iret_rip)) { + vcpu->arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); + kvm_make_request(KVM_REQ_EVENT, vcpu); } - svm->vcpu.arch.nmi_injected = false; - kvm_clear_exception_queue(&svm->vcpu); - kvm_clear_interrupt_queue(&svm->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, &svm->vcpu); + kvm_make_request(KVM_REQ_EVENT, vcpu); vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK; type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK; switch (type) { case SVM_EXITINTINFO_TYPE_NMI: - svm->vcpu.arch.nmi_injected = true; + vcpu->arch.nmi_injected = true; break; case SVM_EXITINTINFO_TYPE_EXEPT: /* @@ -3725,21 +3726,20 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) */ if (kvm_exception_is_soft(vector)) { if (vector == BP_VECTOR && int3_injected && - kvm_is_linear_rip(&svm->vcpu, svm->int3_rip)) - kvm_rip_write(&svm->vcpu, - kvm_rip_read(&svm->vcpu) - - int3_injected); + kvm_is_linear_rip(vcpu, svm->int3_rip)) + kvm_rip_write(vcpu, + kvm_rip_read(vcpu) - int3_injected); break; } if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { u32 err = svm->vmcb->control.exit_int_info_err; - kvm_requeue_exception_e(&svm->vcpu, vector, err); + kvm_requeue_exception_e(vcpu, vector, err); } else - kvm_requeue_exception(&svm->vcpu, vector); + kvm_requeue_exception(vcpu, vector); break; case SVM_EXITINTINFO_TYPE_INTR: - kvm_queue_interrupt(&svm->vcpu, vector, false); + kvm_queue_interrupt(vcpu, vector, false); break; default: break; @@ -3754,7 +3754,12 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) control->exit_int_info = control->event_inj; control->exit_int_info_err = control->event_inj_err; control->event_inj = 0; - svm_complete_interrupts(svm); + 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) @@ -3766,57 +3771,32 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } -static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, - struct vcpu_svm *svm) +static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) { - /* - * VMENTER enables interrupts (host state), but the kernel state is - * interrupts disabled when this is invoked. Also tell RCU about - * it. This is the same logic as for exit_to_user_mode(). - * - * This ensures that e.g. latency analysis on the host observes - * guest mode as interrupt enabled. - * - * guest_enter_irqoff() informs context tracking about the - * transition to guest mode and if enabled adjusts RCU state - * accordingly. - */ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - instrumentation_end(); + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long vmcb_pa = svm->current_vmcb->pa; - guest_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); + guest_state_enter_irqoff(); - if (sev_es_guest(svm->vcpu.kvm)) { - __svm_sev_es_vcpu_run(svm->vmcb_pa); + if (sev_es_guest(vcpu->kvm)) { + __svm_sev_es_vcpu_run(vmcb_pa); } else { struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); - __svm_vcpu_run(svm->vmcb_pa, (unsigned long *)&svm->vcpu.arch.regs); + /* + * 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. + */ + vmload(svm->vmcb01.pa); + __svm_vcpu_run(vmcb_pa, (unsigned long *)&vcpu->arch.regs); + vmsave(svm->vmcb01.pa); vmload(__sme_page_pa(sd->save_area)); } - /* - * VMEXIT disables interrupts (host state), but tracing and lockdep - * have them in state 'on' as recorded before entering guest mode. - * Same as enter_from_user_mode(). - * - * guest_exit_irqoff() restores host context and reinstates RCU if - * enabled and required. - * - * This needs to be done before the below as native_read_msr() - * contains a tracepoint and x86_spec_ctrl_restore_host() calls - * into world and some more. - */ - lockdep_hardirqs_off(CALLER_ADDR0); - guest_exit_irqoff(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - instrumentation_end(); + guest_state_exit_irqoff(); } static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) @@ -3845,7 +3825,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) smp_send_reschedule(vcpu->cpu); } - pre_svm_run(svm); + pre_svm_run(vcpu); sync_lapic_to_cr8(vcpu); @@ -3855,11 +3835,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) } 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(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + 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); @@ -3875,9 +3857,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); + if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl); - svm_vcpu_enter_exit(vcpu, svm); + svm_vcpu_enter_exit(vcpu); /* * We do not use IBRS in the kernel. If this vCPU has used the @@ -3894,23 +3877,26 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL) && + unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - if (!sev_es_guest(svm->vcpu.kvm)) + if (!sev_es_guest(vcpu->kvm)) reload_tss(vcpu); - x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); + if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL)) + x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl); - if (!sev_es_guest(svm->vcpu.kvm)) { + 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(&svm->vcpu); + kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); kvm_load_host_xsave_state(vcpu); stgi(); @@ -3918,13 +3904,19 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) /* Any pending NMI will happen here */ if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) - kvm_after_interrupt(&svm->vcpu); + kvm_after_interrupt(vcpu); sync_cr8_to_lapic(vcpu); svm->next_rip = 0; - if (is_guest_mode(&svm->vcpu)) { - sync_nested_vmcb_control(svm); + 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; } @@ -3933,13 +3925,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) /* if exit due to PF check for async PF */ if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) - svm->vcpu.arch.apf.host_apf_flags = + vcpu->arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags(); - if (npt_enabled) { - vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); - vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); - } + vcpu->arch.regs_avail &= ~SVM_REGS_LAZY_LOAD_SET; /* * We need to handle MC intercepts here before the vcpu has a chance to @@ -3947,9 +3936,9 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) */ if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + MC_VECTOR)) - svm_handle_mce(svm); + svm_handle_mce(vcpu); - svm_complete_interrupts(svm); + svm_complete_interrupts(vcpu); if (is_guest_mode(vcpu)) return EXIT_FASTPATH_NONE; @@ -3957,21 +3946,25 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) return svm_exit_handlers_fastpath(vcpu); } -static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root, +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; - cr3 = __sme_set(root); if (npt_enabled) { - svm->vmcb->control.nested_cr3 = cr3; + svm->vmcb->control.nested_cr3 = __sme_set(root_hpa); vmcb_mark_dirty(svm->vmcb, VMCB_NPT); - /* Loading L2's CR3 is handled by enter_svm_guest_mode. */ - if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) - return; + hv_track_root_tdp(vcpu, root_hpa); + cr3 = vcpu->arch.cr3; + } else if (vcpu->arch.mmu->root_role.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; @@ -4005,11 +3998,6 @@ static int __init svm_check_processor_compat(void) return 0; } -static bool svm_cpu_has_accelerated_tpr(void) -{ - return false; -} - /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. @@ -4041,6 +4029,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_cpuid_entry2 *best; + struct kvm *kvm = vcpu->kvm; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -4048,10 +4037,22 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) /* Update nrips enabled cache */ svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && - guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS); + guest_cpuid_has(vcpu, X86_FEATURE_NRIPS); + + svm->tsc_scaling_enabled = tsc_scaling && guest_cpuid_has(vcpu, X86_FEATURE_TSCRATEMSR); + svm->lbrv_enabled = lbrv && guest_cpuid_has(vcpu, X86_FEATURE_LBRV); + + svm->v_vmload_vmsave_enabled = vls && guest_cpuid_has(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); + + svm->pause_filter_enabled = kvm_cpu_cap_has(X86_FEATURE_PAUSEFILTER) && + guest_cpuid_has(vcpu, X86_FEATURE_PAUSEFILTER); - /* Check again if INVPCID interception if required */ - svm_check_invpcid(svm); + svm->pause_threshold_enabled = kvm_cpu_cap_has(X86_FEATURE_PFTHRESHOLD) && + guest_cpuid_has(vcpu, X86_FEATURE_PFTHRESHOLD); + + svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF); + + svm_recalc_instruction_intercepts(vcpu, svm); /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { @@ -4060,24 +4061,15 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); } - if (!kvm_vcpu_apicv_active(vcpu)) - return; - - /* - * AVIC does not work with an x2APIC mode guest. If the X2APIC feature - * is exposed to the guest, disable AVIC. - */ - if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC)) - kvm_request_apicv_update(vcpu->kvm, false, - APICV_INHIBIT_REASON_X2APIC); - - /* - * Currently, AVIC does not work with nested virtualization. - * So, we disable AVIC when cpuid for SVM is set in the L1 guest. - */ - if (nested && guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - kvm_request_apicv_update(vcpu->kvm, false, - APICV_INHIBIT_REASON_NESTED); + if (kvm_vcpu_apicv_active(vcpu)) { + /* + * AVIC does not work with an x2APIC mode guest. If the X2APIC feature + * is exposed to the guest, disable AVIC. + */ + if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC)) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_X2APIC); + } + init_vmcb_after_set_cpuid(vcpu); } static bool svm_has_wbinvd_exit(void) @@ -4182,7 +4174,7 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu, info->intercept == x86_intercept_clts) break; - if (!(vmcb_is_intercept(&svm->nested.ctl, + if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))) break; @@ -4271,6 +4263,8 @@ out: 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) @@ -4302,65 +4296,123 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) 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 !svm_smi_blocked(vcpu); + return 1; } -static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_host_map map_save; int ret; - if (is_guest_mode(vcpu)) { - /* FED8h - SVM Guest */ - put_smstate(u64, smstate, 0x7ed8, 1); - /* FEE0h - SVM Guest VMCB Physical Address */ - put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); + if (!is_guest_mode(vcpu)) + return 0; - 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]; + /* FED8h - SVM Guest */ + put_smstate(u64, smstate, 0x7ed8, 1); + /* FEE0h - SVM Guest VMCB Physical Address */ + put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); - ret = nested_svm_vmexit(svm); - if (ret) - return ret; - } + 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) == -EINVAL) + 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_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); - struct kvm_host_map map; - int ret = 0; + struct kvm_host_map map, map_save; + u64 saved_efer, vmcb12_gpa; + struct vmcb *vmcb12; + int ret; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 0; - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { - u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); - u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); - u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + /* Non-zero if SMI arrived while vCPU was in guest mode. */ + if (!GET_SMSTATE(u64, smstate, 0x7ed8)) + return 0; - if (guest) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) - return 1; + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; - if (!(saved_efer & EFER_SVME)) - return 1; + saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); + if (!(saved_efer & EFER_SVME)) + return 1; - if (kvm_vcpu_map(&svm->vcpu, - gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) - return 1; + vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); + if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) + return 1; - if (svm_allocate_nested(svm)) - return 1; + ret = 1; + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL) + goto unmap_map; - ret = enter_svm_guest_mode(svm, vmcb12_gpa, map.hva); - kvm_vcpu_unmap(&svm->vcpu, &map, true); - } - } + 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, vmcb12_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; } @@ -4369,7 +4421,7 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (!gif_set(svm)) { - if (vgif_enabled(svm)) + if (vgif) svm_set_intercept(svm, INTERCEPT_STGI); /* STGI will cause a vm exit */ } else { @@ -4377,79 +4429,140 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } } -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) +static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; unsigned long cr4; + 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)); /* - * When the guest is an SEV-ES guest, emulation is not possible. + * 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. + * + * 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 (unlikely(!insn)) { + 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 raise #NPF on guest data access and vCPU CR4.SMAP=1, it is - * possible that CPU microcode implementing DecodeAssist will fail - * to read bytes of instruction which caused #NPF. In this case, - * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly - * return 0 instead of the correct guest instruction bytes. - * - * This happens because CPU microcode reading instruction bytes - * uses a special opcode which attempts to read data using CPL=0 - * priviledges. The microcode reads CS:RIP and if it hits a SMAP - * fault, it gives up and returns no instruction bytes. + * 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. * - * Detection: - * We reach here in case CPU supports DecodeAssist, raised #NPF and - * returned 0 in GuestIntrBytes field of the VMCB. - * First, errata can only be triggered in case vCPU CR4.SMAP=1. - * Second, if vCPU CR4.SMEP=1, errata could only be triggered - * in case vCPU CPL==3 (Because otherwise guest would have triggered - * a SMEP fault instead of #NPF). - * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL. - * As most guests enable SMAP if they have also enabled SMEP, use above - * logic in order to attempt minimize false-positive of detecting errata - * while still preserving all cases semantic correctness. + * 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. * - * Workaround: - * To determine what instruction the guest was executing, the hypervisor - * will have to decode the instruction at the instruction pointer. + * 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. * - * In non SEV guest, hypervisor will be able to read the guest - * memory to decode the instruction pointer when insn_len is zero - * so we return true to indicate that decoding is possible. + * 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). * - * But in the SEV guest, the guest memory is encrypted with the - * guest specific key and hypervisor will not be able to decode the - * instruction pointer so we will not able to workaround it. Lets - * print the error and request to kill the guest. + * In addition, don't apply the erratum workaround if the #NPF occurred + * while translating guest page tables (see below). */ - if (likely(!insn || insn_len)) - return true; - - /* - * If RIP is invalid, go ahead with emulation which will cause an - * internal error exit. - */ - if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT)) - return true; + error_code = to_svm(vcpu)->vmcb->control.exit_info_1; + if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) + goto resume_guest; cr4 = kvm_read_cr4(vcpu); smep = cr4 & X86_CR4_SMEP; smap = cr4 & X86_CR4_SMAP; is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { - if (!sev_guest(vcpu->kvm)) - return true; - pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n"); - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + + /* + * 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; } @@ -4487,36 +4600,36 @@ static int svm_vm_init(struct kvm *kvm) if (!pause_filter_count || !pause_filter_thresh) kvm->arch.pause_in_guest = true; - if (avic) { + if (enable_apicv) { int ret = avic_vm_init(kvm); if (ret) return ret; } - kvm_apicv_init(kvm, avic); return 0; } static struct kvm_x86_ops svm_x86_ops __initdata = { - .hardware_unsetup = svm_hardware_teardown, + .name = "kvm_amd", + + .hardware_unsetup = svm_hardware_unsetup, .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, - .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, .has_emulated_msr = svm_has_emulated_msr, - .vcpu_create = svm_create_vcpu, - .vcpu_free = svm_free_vcpu, + .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_guest_switch = svm_prepare_guest_switch, + .prepare_switch_to_guest = svm_prepare_switch_to_guest, .vcpu_load = svm_vcpu_load, .vcpu_put = svm_vcpu_put, - .vcpu_blocking = svm_vcpu_blocking, - .vcpu_unblocking = svm_vcpu_unblocking, + .vcpu_blocking = avic_vcpu_blocking, + .vcpu_unblocking = avic_vcpu_unblocking, .update_exception_bitmap = svm_update_exception_bitmap, .get_msr_feature = svm_get_msr_feature, @@ -4526,8 +4639,9 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .get_segment = svm_get_segment, .set_segment = svm_set_segment, .get_cpl = svm_get_cpl, - .get_cs_db_l_bits = kvm_get_cs_db_l_bits, + .get_cs_db_l_bits = svm_get_cs_db_l_bits, .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, @@ -4540,21 +4654,23 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, + .get_if_flag = svm_get_if_flag, - .tlb_flush_all = svm_flush_tlb, - .tlb_flush_current = svm_flush_tlb, - .tlb_flush_gva = svm_flush_tlb_gva, - .tlb_flush_guest = svm_flush_tlb, + .flush_tlb_all = svm_flush_tlb_current, + .flush_tlb_current = svm_flush_tlb_current, + .flush_tlb_gva = svm_flush_tlb_gva, + .flush_tlb_guest = svm_flush_tlb_current, - .run = svm_vcpu_run, - .handle_exit = handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, + .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, - .set_irq = svm_set_irq, - .set_nmi = svm_inject_nmi, + .inject_irq = svm_inject_irq, + .inject_nmi = svm_inject_nmi, .queue_exception = svm_queue_exception, .cancel_injection = svm_cancel_injection, .interrupt_allowed = svm_interrupt_allowed, @@ -4564,27 +4680,21 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .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 = svm_set_virtual_apic_mode, - .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, - .check_apicv_inhibit_reasons = svm_check_apicv_inhibit_reasons, - .pre_update_apicv_exec_ctrl = svm_pre_update_apicv_exec_ctrl, - .load_eoi_exitmap = svm_load_eoi_exitmap, - .hwapic_irr_update = svm_hwapic_irr_update, - .hwapic_isr_update = svm_hwapic_isr_update, - .sync_pir_to_irr = kvm_lapic_find_highest_irr, - .apicv_post_state_restore = avic_post_state_restore, - - .set_tss_addr = svm_set_tss_addr, - .set_identity_map_addr = svm_set_identity_map_addr, - .get_mt_mask = svm_get_mt_mask, + .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, + .check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons, + .apicv_post_state_restore = avic_apicv_post_state_restore, + .get_mt_mask = svm_get_mt_mask, .get_exit_info = svm_get_exit_info, .vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid, .has_wbinvd_exit = svm_has_wbinvd_exit, - .write_l1_tsc_offset = svm_write_l1_tsc_offset, + .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, @@ -4595,22 +4705,24 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .sched_in = svm_sched_in, - .pmu_ops = &amd_pmu_ops, .nested_ops = &svm_nested_ops, - .deliver_posted_interrupt = svm_deliver_avic_intr, - .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt, - .update_pi_irte = svm_update_pi_irte, + .deliver_interrupt = svm_deliver_interrupt, + .pi_update_irte = avic_pi_update_irte, .setup_mce = svm_setup_mce, .smi_allowed = svm_smi_allowed, - .pre_enter_smm = svm_pre_enter_smm, - .pre_leave_smm = svm_pre_leave_smm, + .enter_smm = svm_enter_smm, + .leave_smm = svm_leave_smm, .enable_smi_window = svm_enable_smi_window, - .mem_enc_op = svm_mem_enc_op, - .mem_enc_reg_region = svm_register_enc_region, - .mem_enc_unreg_region = svm_unregister_enc_region, + .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, @@ -4620,8 +4732,269 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .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(); + + 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); + + /* 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); + + /* AMD PMU PERFCTR_CORE CPUID */ + if (enable_pmu && boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) + kvm_cpu_cap_set(X86_FEATURE_PERFCTR_CORE); + + /* 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(); + + 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_has_tsc_control = true; + } + } + kvm_max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX; + kvm_tsc_scaling_ratio_frac_bits = 32; + + tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); + + /* 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) { + printk(KERN_INFO "kvm: 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("kvm: 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); + + /* Note, SEV setup consumes npt_enabled. */ + sev_hardware_setup(); + + svm_hv_hardware_setup(); + + svm_adjust_mmio_mask(); + + for_each_possible_cpu(cpu) { + r = svm_cpu_init(cpu); + if (r) + goto err; + } + + if (nrips) { + if (!boot_cpu_has(X86_FEATURE_NRIPS)) + nrips = false; + } + + enable_apicv = avic = avic && npt_enabled && (boot_cpu_has(X86_FEATURE_AVIC) || force_avic); + + if (enable_apicv) { + if (!boot_cpu_has(X86_FEATURE_AVIC)) { + pr_warn("AVIC is not supported in CPUID but force enabled"); + pr_warn("Your system might crash and burn"); + } else + pr_info("AVIC enabled\n"); + + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + } else { + svm_x86_ops.vcpu_blocking = NULL; + svm_x86_ops.vcpu_unblocking = NULL; + svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL; + } + + 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"); + } + + 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 = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -4629,6 +5002,7 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { .check_processor_compatibility = svm_check_processor_compat, .runtime_ops = &svm_x86_ops, + .pmu_ops = &amd_pmu_ops, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 39e071fdab0c..1bddd336a27e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -20,19 +20,27 @@ #include <linux/bits.h> #include <asm/svm.h> +#include <asm/sev-common.h> + +#include "kvm_cache_regs.h" #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) -static const u32 host_save_user_msrs[] = { - MSR_TSC_AUX, -}; -#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) +#define IOPM_SIZE PAGE_SIZE * 3 +#define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 18 +#define MAX_DIRECT_ACCESS_MSRS 21 #define MSRPM_OFFSETS 16 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; +extern int vgif; +extern bool intercept_smi; +/* + * 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 */ @@ -50,9 +58,17 @@ enum { * AVIC PHYSICAL_TABLE pointer, * AVIC LOGICAL_TABLE pointer */ - VMCB_DIRTY_MAX, + 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)) @@ -65,6 +81,11 @@ struct kvm_sev_info { 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 { @@ -81,11 +102,55 @@ struct kvm_svm { 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 nested_cr3; + u64 virt_ext; + u32 clean; + u8 reserved_sw[32]; +}; + struct svm_nested_state { - struct vmcb *hsave; + 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; @@ -95,29 +160,59 @@ struct svm_nested_state { bool nested_run_pending; /* cache for control fields of the guest */ - struct vmcb_control_area ctl; + 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; + struct kvm_host_map ghcb_map; + bool received_first_sipi; + + /* SEV-ES scratch area support */ + 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; - unsigned long vmcb_pa; + struct kvm_vmcb_info vmcb01; + struct kvm_vmcb_info *current_vmcb; struct svm_cpu_data *svm_data; u32 asid; - uint64_t asid_generation; - uint64_t sysenter_esp; - uint64_t sysenter_eip; + u32 sysenter_esp_hi; + u32 sysenter_eip_hi; uint64_t tsc_aux; u64 msr_decfg; u64 next_rip; - u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; - 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 @@ -137,14 +232,19 @@ struct vcpu_svm { unsigned int3_injected; unsigned long int3_rip; - /* cached guest cpuid flags for faster access */ - bool nrips_enabled : 1; + /* optional nested SVM features that are enabled for this guest */ + bool nrips_enabled : 1; + bool tsc_scaling_enabled : 1; + bool v_vmload_vmsave_enabled : 1; + bool lbrv_enabled : 1; + bool pause_filter_enabled : 1; + bool pause_threshold_enabled : 1; + bool vgif_enabled : 1; u32 ldr_reg; u32 dfr_reg; struct page *avic_backing_page; u64 *avic_physical_id_cache; - bool avic_is_running; /* * Per-vcpu list of struct amd_svm_iommu_ir: @@ -161,17 +261,7 @@ struct vcpu_svm { DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS); } shadow_msr_intercept; - /* SEV-ES support */ - struct vmcb_save_area *vmsa; - struct ghcb *ghcb; - struct kvm_host_map ghcb_map; - bool received_first_sipi; - - /* SEV-ES scratch area support */ - void *ghcb_sa; - u64 ghcb_sa_len; - bool ghcb_sa_sync; - bool ghcb_sa_free; + struct vcpu_sev_es_state sev_es; bool guest_state_loaded; }; @@ -196,12 +286,12 @@ DECLARE_PER_CPU(struct svm_cpu_data *, svm_data); void recalc_intercepts(struct vcpu_svm *svm); -static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) +static __always_inline struct kvm_svm *to_kvm_svm(struct kvm *kvm) { return container_of(kvm, struct kvm_svm, kvm); } -static inline bool sev_guest(struct kvm *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; @@ -212,12 +302,12 @@ static inline bool sev_guest(struct kvm *kvm) #endif } -static inline bool sev_es_guest(struct kvm *kvm) +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_guest(kvm) && sev->es_active; + return sev->es_active && !WARN_ON_ONCE(!sev->active); #else return false; #endif @@ -230,7 +320,7 @@ static inline void vmcb_mark_all_dirty(struct vmcb *vmcb) static inline void vmcb_mark_all_clean(struct vmcb *vmcb) { - vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1) + vmcb->control.clean = VMCB_ALL_CLEAN_MASK & ~VMCB_ALWAYS_DIRTY_MASK; } @@ -239,19 +329,26 @@ static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit) vmcb->control.clean &= ~(1 << bit); } -static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) +static inline bool vmcb_is_dirty(struct vmcb *vmcb, int bit) { - return container_of(vcpu, struct vcpu_svm, vcpu); + return !test_bit(bit, (unsigned long *)&vmcb->control.clean); } -static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm) +static __always_inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) { - if (is_guest_mode(&svm->vcpu)) - return svm->nested.hsave; - else - return svm->vmcb; + 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); @@ -270,9 +367,15 @@ static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit) 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_dr_intercepts(struct vcpu_svm *svm) { - struct vmcb *vmcb = get_host_vmcb(svm); + struct vmcb *vmcb = svm->vmcb01.ptr; if (!sev_es_guest(svm->vcpu.kvm)) { vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ); @@ -299,7 +402,7 @@ static inline void set_dr_intercepts(struct vcpu_svm *svm) static inline void clr_dr_intercepts(struct vcpu_svm *svm) { - struct vmcb *vmcb = get_host_vmcb(svm); + struct vmcb *vmcb = svm->vmcb01.ptr; vmcb->control.intercepts[INTERCEPT_DR] = 0; @@ -314,7 +417,7 @@ static inline void clr_dr_intercepts(struct vcpu_svm *svm) static inline void set_exception_intercept(struct vcpu_svm *svm, u32 bit) { - struct vmcb *vmcb = get_host_vmcb(svm); + struct vmcb *vmcb = svm->vmcb01.ptr; WARN_ON_ONCE(bit >= 32); vmcb_set_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit); @@ -324,7 +427,7 @@ static inline void set_exception_intercept(struct vcpu_svm *svm, u32 bit) static inline void clr_exception_intercept(struct vcpu_svm *svm, u32 bit) { - struct vmcb *vmcb = get_host_vmcb(svm); + struct vmcb *vmcb = svm->vmcb01.ptr; WARN_ON_ONCE(bit >= 32); vmcb_clr_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit); @@ -334,7 +437,7 @@ static inline void clr_exception_intercept(struct vcpu_svm *svm, u32 bit) static inline void svm_set_intercept(struct vcpu_svm *svm, int bit) { - struct vmcb *vmcb = get_host_vmcb(svm); + struct vmcb *vmcb = svm->vmcb01.ptr; vmcb_set_intercept(&vmcb->control, bit); @@ -343,7 +446,7 @@ static inline void svm_set_intercept(struct vcpu_svm *svm, int bit) static inline void svm_clr_intercept(struct vcpu_svm *svm, int bit) { - struct vmcb *vmcb = get_host_vmcb(svm); + struct vmcb *vmcb = svm->vmcb01.ptr; vmcb_clr_intercept(&vmcb->control, bit); @@ -355,59 +458,84 @@ static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit) return vmcb_is_intercept(&svm->vmcb->control, bit); } -static inline bool vgif_enabled(struct vcpu_svm *svm) +static inline bool nested_vgif_enabled(struct vcpu_svm *svm) +{ + return svm->vgif_enabled && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK); +} + +static inline struct vmcb *get_vgif_vmcb(struct vcpu_svm *svm) { - return !!(svm->vmcb->control.int_ctl & V_GIF_ENABLE_MASK); + 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) { - if (vgif_enabled(svm)) - svm->vmcb->control.int_ctl |= V_GIF_MASK; + struct vmcb *vmcb = get_vgif_vmcb(svm); + + if (vmcb) + vmcb->control.int_ctl |= V_GIF_MASK; else svm->vcpu.arch.hflags |= HF_GIF_MASK; } static inline void disable_gif(struct vcpu_svm *svm) { - if (vgif_enabled(svm)) - svm->vmcb->control.int_ctl &= ~V_GIF_MASK; + struct vmcb *vmcb = get_vgif_vmcb(svm); + + if (vmcb) + vmcb->control.int_ctl &= ~V_GIF_MASK; else svm->vcpu.arch.hflags &= ~HF_GIF_MASK; } static inline bool gif_set(struct vcpu_svm *svm) { - if (vgif_enabled(svm)) - return !!(svm->vmcb->control.int_ctl & V_GIF_MASK); + struct vmcb *vmcb = get_vgif_vmcb(svm); + + if (vmcb) + return !!(vmcb->control.int_ctl & V_GIF_MASK); else return !!(svm->vcpu.arch.hflags & HF_GIF_MASK); } +static inline bool nested_npt_enabled(struct vcpu_svm *svm) +{ + return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE; +} + /* svm.c */ #define MSR_INVALID 0xffffffffU -extern int sev; -extern int sev_es; +#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 svm_flush_tlb(struct kvm_vcpu *vcpu); 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 vcpu_svm *svm, u64 exit_code); +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_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vec); /* nested.c */ @@ -424,153 +552,111 @@ static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu) static inline bool nested_exit_on_smi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SMI); } static inline bool nested_exit_on_intr(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INTR); } static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) { - return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); + return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI); } -int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, - struct vmcb *nested_vmcb); -void svm_leave_nested(struct vcpu_svm *svm); +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 vcpu_svm *svm); -void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb); +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 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 sync_nested_vmcb_control(struct vcpu_svm *svm); +void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu); +void __svm_write_tsc_multiplier(u64 multiplier); +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_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - -extern int avic; - -static inline void avic_update_vapic_bar(struct vcpu_svm *svm, u64 data) -{ - svm->vmcb->control.avic_vapic_bar = data & VMCB_AVIC_APIC_BAR_MASK; - vmcb_mark_dirty(svm->vmcb, VMCB_AVIC); -} - -static inline bool avic_vcpu_is_running(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 *entry = svm->avic_physical_id_cache; - - if (!entry) - return false; - - return (READ_ONCE(*entry) & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); -} - 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); -void svm_toggle_avic_for_irq_window(struct kvm_vcpu *vcpu, bool activate); -int avic_incomplete_ipi_interception(struct vcpu_svm *svm); -int avic_unaccelerated_access_interception(struct vcpu_svm *svm); +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_post_state_restore(struct kvm_vcpu *vcpu); -void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu); -void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); -bool svm_check_apicv_inhibit_reasons(ulong bit); -void svm_pre_update_apicv_exec_ctrl(struct kvm *kvm, bool activate); -void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); -void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); -void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec); -bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu); -int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, - uint32_t guest_irq, bool set); -void svm_vcpu_blocking(struct kvm_vcpu *vcpu); -void svm_vcpu_unblocking(struct kvm_vcpu *vcpu); +void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); +void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); +bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason); +void avic_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); +void avic_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); +bool avic_dy_apicv_has_pending_interrupt(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); /* sev.c */ -#define GHCB_VERSION_MAX 1ULL -#define GHCB_VERSION_MIN 1ULL - -#define GHCB_MSR_INFO_POS 0 -#define GHCB_MSR_INFO_MASK (BIT_ULL(12) - 1) - -#define GHCB_MSR_SEV_INFO_RESP 0x001 -#define GHCB_MSR_SEV_INFO_REQ 0x002 -#define GHCB_MSR_VER_MAX_POS 48 -#define GHCB_MSR_VER_MAX_MASK 0xffff -#define GHCB_MSR_VER_MIN_POS 32 -#define GHCB_MSR_VER_MIN_MASK 0xffff -#define GHCB_MSR_CBIT_POS 24 -#define GHCB_MSR_CBIT_MASK 0xff -#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ - ((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \ - (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \ - (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \ - GHCB_MSR_SEV_INFO_RESP) - -#define GHCB_MSR_CPUID_REQ 0x004 -#define GHCB_MSR_CPUID_RESP 0x005 -#define GHCB_MSR_CPUID_FUNC_POS 32 -#define GHCB_MSR_CPUID_FUNC_MASK 0xffffffff -#define GHCB_MSR_CPUID_VALUE_POS 32 -#define GHCB_MSR_CPUID_VALUE_MASK 0xffffffff -#define GHCB_MSR_CPUID_REG_POS 30 -#define GHCB_MSR_CPUID_REG_MASK 0x3 - -#define GHCB_MSR_TERM_REQ 0x100 -#define GHCB_MSR_TERM_REASON_SET_POS 12 -#define GHCB_MSR_TERM_REASON_SET_MASK 0xf -#define GHCB_MSR_TERM_REASON_POS 16 -#define GHCB_MSR_TERM_REASON_MASK 0xff +#define GHCB_VERSION_MAX 1ULL +#define GHCB_VERSION_MIN 1ULL -extern unsigned int max_sev_asid; -static inline bool svm_sev_enabled(void) -{ - return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0; -} +extern unsigned int max_sev_asid; void sev_vm_destroy(struct kvm *kvm); -int svm_mem_enc_op(struct kvm *kvm, void __user *argp); -int svm_register_enc_region(struct kvm *kvm, - struct kvm_enc_region *range); -int svm_unregister_enc_region(struct kvm *kvm, - struct kvm_enc_region *range); +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_teardown(void); +void sev_hardware_unsetup(void); +int sev_cpu_init(struct svm_cpu_data *sd); void sev_free_vcpu(struct kvm_vcpu *vcpu); -int sev_handle_vmgexit(struct vcpu_svm *svm); +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_init_vmcb(struct vcpu_svm *svm); -void sev_es_create_vcpu(struct vcpu_svm *svm); +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_guest_switch(struct vcpu_svm *svm, unsigned int cpu); +void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); +void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c new file mode 100644 index 000000000000..8cdc62c74a96 --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM L1 hypervisor optimizations on Hyper-V for SVM. + */ + +#include <linux/kvm_host.h> + +#include <asm/mshyperv.h> + +#include "svm.h" +#include "svm_ops.h" + +#include "hyperv.h" +#include "kvm_onhyperv.h" +#include "svm_onhyperv.h" + +int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +{ + struct hv_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 = (struct hv_enlightenments *)to_svm(vcpu)->vmcb->control.reserved_sw; + + 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, VMCB_HV_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 000000000000..e2fc59380465 --- /dev/null +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -0,0 +1,103 @@ +/* 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__ + +#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_direct_tlbflush(struct kvm_vcpu *vcpu); + +static inline void svm_hv_init_vmcb(struct vmcb *vmcb) +{ + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + if (npt_enabled && + ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) + hve->hv_enlightenments_control.enlightened_npt_tlb = 1; + + if (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP) + hve->hv_enlightenments_control.msr_bitmap = 1; +} + +static inline void svm_hv_hardware_setup(void) +{ + if (npt_enabled && + ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { + pr_info("kvm: Hyper-V enlightened NPT TLB flush enabled\n"); + svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; + svm_x86_ops.tlb_remote_flush_with_range = + hv_remote_flush_tlb_with_range; + } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { + int cpu; + + pr_info("kvm: 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_direct_tlbflush = + svm_hv_enable_direct_tlbflush; + } +} + +static inline void svm_hv_vmcb_dirty_nested_enlightenments( + struct kvm_vcpu *vcpu) +{ + struct vmcb *vmcb = to_svm(vcpu)->vmcb; + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + + if (hve->hv_enlightenments_control.msr_bitmap) + vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); +} + +static inline void svm_hv_update_vp_id(struct vmcb *vmcb, + struct kvm_vcpu *vcpu) +{ + struct hv_enlightenments *hve = + (struct hv_enlightenments *)vmcb->control.reserved_sw; + 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, VMCB_HV_NESTED_ENLIGHTENMENTS); + } +} +#else + +static inline void svm_hv_init_vmcb(struct vmcb *vmcb) +{ +} + +static inline 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 index 8170f2a5a16f..9430d6437c9f 100644 --- a/arch/x86/kvm/svm/svm_ops.h +++ b/arch/x86/kvm/svm/svm_ops.h @@ -4,7 +4,7 @@ #include <linux/compiler_types.h> -#include <asm/kvm_host.h> +#include "x86.h" #define svm_asm(insn, clobber...) \ do { \ @@ -56,12 +56,12 @@ static inline void invlpga(unsigned long addr, u32 asid) * VMSAVE, VMLOAD, etc... is still controlled by the effective address size, * hence 'unsigned long' instead of 'hpa_t'. */ -static inline void vmsave(unsigned long pa) +static __always_inline void vmsave(unsigned long pa) { svm_asm1(vmsave, "a" (pa), "memory"); } -static inline void vmload(unsigned long pa) +static __always_inline void vmload(unsigned long pa) { svm_asm1(vmload, "a" (pa), "memory"); } diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 6feb8c08f45a..dfaeb47fcf2a 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -79,28 +79,10 @@ SYM_FUNC_START(__svm_vcpu_run) /* Enter guest mode */ sti -1: vmload %_ASM_AX - jmp 3f -2: cmpb $0, kvm_rebooting - jne 3f - ud2 - _ASM_EXTABLE(1b, 2b) -3: vmrun %_ASM_AX - jmp 5f -4: cmpb $0, kvm_rebooting - jne 5f - ud2 - _ASM_EXTABLE(3b, 4b) +1: vmrun %_ASM_AX -5: vmsave %_ASM_AX - jmp 7f -6: cmpb $0, kvm_rebooting - jne 7f - ud2 - _ASM_EXTABLE(5b, 6b) -7: - cli +2: cli #ifdef CONFIG_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ @@ -166,7 +148,14 @@ SYM_FUNC_START(__svm_vcpu_run) pop %edi #endif pop %_ASM_BP - ret + RET + +3: cmpb $0, kvm_rebooting + jne 2b + ud2 + + _ASM_EXTABLE(1b, 3b) + SYM_FUNC_END(__svm_vcpu_run) /** @@ -186,18 +175,15 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) #endif push %_ASM_BX - /* Enter guest mode */ + /* Move @vmcb to RAX. */ mov %_ASM_ARG1, %_ASM_AX + + /* Enter guest mode */ sti 1: vmrun %_ASM_AX - jmp 3f -2: cmpb $0, kvm_rebooting - jne 3f - ud2 - _ASM_EXTABLE(1b, 2b) -3: cli +2: cli #ifdef CONFIG_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ @@ -216,5 +202,12 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) pop %edi #endif pop %_ASM_BP - ret + RET + +3: cmpb $0, kvm_rebooting + jne 2b + ud2 + + _ASM_EXTABLE(1b, 3b) + SYM_FUNC_END(__svm_sev_es_vcpu_run) |