diff options
Diffstat (limited to 'hw/i386')
-rw-r--r-- | hw/i386/Kconfig | 6 | ||||
-rw-r--r-- | hw/i386/acpi-build.c | 18 | ||||
-rw-r--r-- | hw/i386/acpi-build.h | 2 | ||||
-rw-r--r-- | hw/i386/amd_iommu.c | 121 | ||||
-rw-r--r-- | hw/i386/amd_iommu.h | 5 | ||||
-rw-r--r-- | hw/i386/intel_iommu.c | 35 | ||||
-rw-r--r-- | hw/i386/kvm/apic.c | 5 | ||||
-rw-r--r-- | hw/i386/kvm/xen-stubs.c | 13 | ||||
-rw-r--r-- | hw/i386/kvm/xen_evtchn.c | 2 | ||||
-rw-r--r-- | hw/i386/meson.build | 1 | ||||
-rw-r--r-- | hw/i386/monitor.c | 2 | ||||
-rw-r--r-- | hw/i386/pc.c | 71 | ||||
-rw-r--r-- | hw/i386/pc_piix.c | 31 | ||||
-rw-r--r-- | hw/i386/pc_q35.c | 26 | ||||
-rw-r--r-- | hw/i386/pc_sysfw.c | 7 | ||||
-rw-r--r-- | hw/i386/sgx-stub.c | 6 | ||||
-rw-r--r-- | hw/i386/sgx.c | 34 | ||||
-rw-r--r-- | hw/i386/tdvf-hob.c | 130 | ||||
-rw-r--r-- | hw/i386/tdvf-hob.h | 26 | ||||
-rw-r--r-- | hw/i386/tdvf.c | 189 | ||||
-rw-r--r-- | hw/i386/x86-common.c | 6 | ||||
-rw-r--r-- | hw/i386/x86.c | 1 |
22 files changed, 546 insertions, 191 deletions
diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index d34ce07..eb65bda 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -10,6 +10,11 @@ config SGX bool depends on KVM +config TDX + bool + select X86_FW_OVMF + depends on KVM + config PC bool imply APPLESMC @@ -26,6 +31,7 @@ config PC imply QXL imply SEV imply SGX + imply TDX imply TEST_DEVICES imply TPM_CRB imply TPM_TIS_ISA diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 3fffa4a..61851cc 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -139,7 +139,7 @@ static void init_common_fadt_data(MachineState *ms, Object *o, /* * "ICH9-LPC" or "PIIX4_PM" has "smm-compat" property to keep the old * behavior for compatibility irrelevant to smm_enabled, which doesn't - * comforms to ACPI spec. + * conform to the ACPI spec. */ bool smm_enabled = object_property_get_bool(o, "smm-compat", NULL) ? true : x86_machine_is_smm_enabled(x86ms); @@ -589,8 +589,8 @@ void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus) } } -static bool build_append_notfication_callback(Aml *parent_scope, - const PCIBus *bus) +static bool build_append_notification_callback(Aml *parent_scope, + const PCIBus *bus) { Aml *method; PCIBus *sec; @@ -604,7 +604,7 @@ static bool build_append_notfication_callback(Aml *parent_scope, continue; } nr_notifiers = nr_notifiers + - build_append_notfication_callback(br_scope, sec); + build_append_notification_callback(br_scope, sec); /* * add new child scope to parent * and keep track of bus that have PCNT, @@ -1773,7 +1773,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, PCIBus *b = PCI_HOST_BRIDGE(pci_host)->bus; scope = aml_scope("\\_SB.PCI0"); - has_pcnt = build_append_notfication_callback(scope, b); + has_pcnt = build_append_notification_callback(scope, b); if (has_pcnt) { aml_append(dsdt, scope); } @@ -2333,10 +2333,10 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id, build_append_int_noprefix(table_data, ivhd_blob->len + 24, 2); /* DeviceID */ build_append_int_noprefix(table_data, - object_property_get_int(OBJECT(&s->pci), "addr", + object_property_get_int(OBJECT(s->pci), "addr", &error_abort), 2); /* Capability offset */ - build_append_int_noprefix(table_data, s->pci.capab_offset, 2); + build_append_int_noprefix(table_data, s->pci->capab_offset, 2); /* IOMMU base address */ build_append_int_noprefix(table_data, s->mr_mmio.addr, 8); /* PCI Segment Group */ @@ -2368,10 +2368,10 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id, build_append_int_noprefix(table_data, ivhd_blob->len + 40, 2); /* DeviceID */ build_append_int_noprefix(table_data, - object_property_get_int(OBJECT(&s->pci), "addr", + object_property_get_int(OBJECT(s->pci), "addr", &error_abort), 2); /* Capability offset */ - build_append_int_noprefix(table_data, s->pci.capab_offset, 2); + build_append_int_noprefix(table_data, s->pci->capab_offset, 2); /* IOMMU base address */ build_append_int_noprefix(table_data, s->mr_mmio.addr, 8); /* PCI Segment Group */ diff --git a/hw/i386/acpi-build.h b/hw/i386/acpi-build.h index 0dce155..275ec05 100644 --- a/hw/i386/acpi-build.h +++ b/hw/i386/acpi-build.h @@ -5,7 +5,7 @@ extern const struct AcpiGenericAddress x86_nvdimm_acpi_dsmio; -/* PCI Hot-plug registers bases. See docs/spec/acpi_pci_hotplug.txt */ +/* PCI Hot-plug registers' base. See docs/specs/acpi_pci_hotplug.rst */ #define ACPI_PCIHP_SEJ_BASE 0x8 #define ACPI_PCIHP_BNMR_BASE 0x10 diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 2cf7e24..963aa24 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -167,11 +167,11 @@ static void amdvi_generate_msi_interrupt(AMDVIState *s) { MSIMessage msg = {}; MemTxAttrs attrs = { - .requester_id = pci_requester_id(&s->pci.dev) + .requester_id = pci_requester_id(&s->pci->dev) }; - if (msi_enabled(&s->pci.dev)) { - msg = msi_get_message(&s->pci.dev, 0); + if (msi_enabled(&s->pci->dev)) { + msg = msi_get_message(&s->pci->dev, 0); address_space_stl_le(&address_space_memory, msg.address, msg.data, attrs, NULL); } @@ -239,7 +239,7 @@ static void amdvi_page_fault(AMDVIState *s, uint16_t devid, info |= AMDVI_EVENT_IOPF_I | AMDVI_EVENT_IOPF; amdvi_encode_event(evt, devid, addr, info); amdvi_log_event(s, evt); - pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS, + pci_word_test_and_set_mask(s->pci->dev.config + PCI_STATUS, PCI_STATUS_SIG_TARGET_ABORT); } /* @@ -256,7 +256,7 @@ static void amdvi_log_devtab_error(AMDVIState *s, uint16_t devid, amdvi_encode_event(evt, devid, devtab, info); amdvi_log_event(s, evt); - pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS, + pci_word_test_and_set_mask(s->pci->dev.config + PCI_STATUS, PCI_STATUS_SIG_TARGET_ABORT); } /* log an event trying to access command buffer @@ -269,7 +269,7 @@ static void amdvi_log_command_error(AMDVIState *s, hwaddr addr) amdvi_encode_event(evt, 0, addr, info); amdvi_log_event(s, evt); - pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS, + pci_word_test_and_set_mask(s->pci->dev.config + PCI_STATUS, PCI_STATUS_SIG_TARGET_ABORT); } /* log an illegal command event @@ -310,7 +310,7 @@ static void amdvi_log_pagetab_error(AMDVIState *s, uint16_t devid, info |= AMDVI_EVENT_PAGE_TAB_HW_ERROR; amdvi_encode_event(evt, devid, addr, info); amdvi_log_event(s, evt); - pci_word_test_and_set_mask(s->pci.dev.config + PCI_STATUS, + pci_word_test_and_set_mask(s->pci->dev.config + PCI_STATUS, PCI_STATUS_SIG_TARGET_ABORT); } @@ -1426,7 +1426,6 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn) AMDVIState *s = opaque; AMDVIAddressSpace **iommu_as, *amdvi_dev_as; int bus_num = pci_bus_num(bus); - X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s); iommu_as = s->address_spaces[bus_num]; @@ -1486,15 +1485,8 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn) AMDVI_INT_ADDR_FIRST, &amdvi_dev_as->iommu_ir, 1); - if (!x86_iommu->pt_supported) { - memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, false); - memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu), - true); - } else { - memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu), - false); - memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, true); - } + memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, false); + memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu), true); } return &iommu_as[devfn]->as; } @@ -1607,26 +1599,92 @@ static void amdvi_sysbus_reset(DeviceState *dev) { AMDVIState *s = AMD_IOMMU_DEVICE(dev); - msi_reset(&s->pci.dev); + msi_reset(&s->pci->dev); amdvi_init(s); } +static const VMStateDescription vmstate_amdvi_sysbus_migratable = { + .name = "amd-iommu", + .version_id = 1, + .minimum_version_id = 1, + .priority = MIG_PRI_IOMMU, + .fields = (VMStateField[]) { + /* Updated in amdvi_handle_control_write() */ + VMSTATE_BOOL(enabled, AMDVIState), + VMSTATE_BOOL(ga_enabled, AMDVIState), + VMSTATE_BOOL(ats_enabled, AMDVIState), + VMSTATE_BOOL(cmdbuf_enabled, AMDVIState), + VMSTATE_BOOL(completion_wait_intr, AMDVIState), + VMSTATE_BOOL(evtlog_enabled, AMDVIState), + VMSTATE_BOOL(evtlog_intr, AMDVIState), + /* Updated in amdvi_handle_devtab_write() */ + VMSTATE_UINT64(devtab, AMDVIState), + VMSTATE_UINT64(devtab_len, AMDVIState), + /* Updated in amdvi_handle_cmdbase_write() */ + VMSTATE_UINT64(cmdbuf, AMDVIState), + VMSTATE_UINT64(cmdbuf_len, AMDVIState), + /* Updated in amdvi_handle_cmdhead_write() */ + VMSTATE_UINT32(cmdbuf_head, AMDVIState), + /* Updated in amdvi_handle_cmdtail_write() */ + VMSTATE_UINT32(cmdbuf_tail, AMDVIState), + /* Updated in amdvi_handle_evtbase_write() */ + VMSTATE_UINT64(evtlog, AMDVIState), + VMSTATE_UINT32(evtlog_len, AMDVIState), + /* Updated in amdvi_handle_evthead_write() */ + VMSTATE_UINT32(evtlog_head, AMDVIState), + /* Updated in amdvi_handle_evttail_write() */ + VMSTATE_UINT32(evtlog_tail, AMDVIState), + /* Updated in amdvi_handle_pprbase_write() */ + VMSTATE_UINT64(ppr_log, AMDVIState), + VMSTATE_UINT32(pprlog_len, AMDVIState), + /* Updated in amdvi_handle_pprhead_write() */ + VMSTATE_UINT32(pprlog_head, AMDVIState), + /* Updated in amdvi_handle_tailhead_write() */ + VMSTATE_UINT32(pprlog_tail, AMDVIState), + /* MMIO registers */ + VMSTATE_UINT8_ARRAY(mmior, AMDVIState, AMDVI_MMIO_SIZE), + VMSTATE_UINT8_ARRAY(romask, AMDVIState, AMDVI_MMIO_SIZE), + VMSTATE_UINT8_ARRAY(w1cmask, AMDVIState, AMDVI_MMIO_SIZE), + VMSTATE_END_OF_LIST() + } +}; + static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) { + DeviceClass *dc = (DeviceClass *) object_get_class(OBJECT(dev)); AMDVIState *s = AMD_IOMMU_DEVICE(dev); MachineState *ms = MACHINE(qdev_get_machine()); PCMachineState *pcms = PC_MACHINE(ms); X86MachineState *x86ms = X86_MACHINE(ms); PCIBus *bus = pcms->pcibus; - s->iotlb = g_hash_table_new_full(amdvi_uint64_hash, - amdvi_uint64_equal, g_free, g_free); + if (s->pci_id) { + PCIDevice *pdev = NULL; + int ret = pci_qdev_find_device(s->pci_id, &pdev); - /* This device should take care of IOMMU PCI properties */ - if (!qdev_realize(DEVICE(&s->pci), &bus->qbus, errp)) { - return; + if (ret) { + error_report("Cannot find PCI device '%s'", s->pci_id); + return; + } + + if (!object_dynamic_cast(OBJECT(pdev), TYPE_AMD_IOMMU_PCI)) { + error_report("Device '%s' must be an AMDVI-PCI device type", s->pci_id); + return; + } + + s->pci = AMD_IOMMU_PCI(pdev); + dc->vmsd = &vmstate_amdvi_sysbus_migratable; + } else { + s->pci = AMD_IOMMU_PCI(object_new(TYPE_AMD_IOMMU_PCI)); + /* This device should take care of IOMMU PCI properties */ + if (!qdev_realize(DEVICE(s->pci), &bus->qbus, errp)) { + return; + } } + s->iotlb = g_hash_table_new_full(amdvi_uint64_hash, + amdvi_uint64_equal, g_free, g_free); + /* Pseudo address space under root PCI bus. */ x86ms->ioapic_as = amdvi_host_dma_iommu(bus, s, AMDVI_IOAPIC_SB_DEVID); @@ -1657,12 +1715,21 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) exit(EXIT_FAILURE); } + if (s->xtsup) { + if (kvm_irqchip_is_split() && !kvm_enable_x2apic()) { + error_report("AMD IOMMU xtsup=on requires x2APIC support on " + "the KVM side"); + exit(EXIT_FAILURE); + } + } + pci_setup_iommu(bus, &amdvi_iommu_ops, s); amdvi_init(s); } static const Property amdvi_properties[] = { DEFINE_PROP_BOOL("xtsup", AMDVIState, xtsup, false), + DEFINE_PROP_STRING("pci-id", AMDVIState, pci_id), }; static const VMStateDescription vmstate_amdvi_sysbus = { @@ -1670,13 +1737,6 @@ static const VMStateDescription vmstate_amdvi_sysbus = { .unmigratable = 1 }; -static void amdvi_sysbus_instance_init(Object *klass) -{ - AMDVIState *s = AMD_IOMMU_DEVICE(klass); - - object_initialize(&s->pci, sizeof(s->pci), TYPE_AMD_IOMMU_PCI); -} - static void amdvi_sysbus_class_init(ObjectClass *klass, const void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -1696,7 +1756,6 @@ static const TypeInfo amdvi_sysbus = { .name = TYPE_AMD_IOMMU_DEVICE, .parent = TYPE_X86_IOMMU_DEVICE, .instance_size = sizeof(AMDVIState), - .instance_init = amdvi_sysbus_instance_init, .class_init = amdvi_sysbus_class_init }; diff --git a/hw/i386/amd_iommu.h b/hw/i386/amd_iommu.h index 2812513..5672bde 100644 --- a/hw/i386/amd_iommu.h +++ b/hw/i386/amd_iommu.h @@ -315,7 +315,8 @@ struct AMDVIPCIState { struct AMDVIState { X86IOMMUState iommu; /* IOMMU bus device */ - AMDVIPCIState pci; /* IOMMU PCI device */ + AMDVIPCIState *pci; /* IOMMU PCI device */ + char *pci_id; /* ID of AMDVI-PCI device, if user created */ uint32_t version; @@ -328,7 +329,7 @@ struct AMDVIState { bool excl_enabled; hwaddr devtab; /* base address device table */ - size_t devtab_len; /* device table length */ + uint64_t devtab_len; /* device table length */ hwaddr cmdbuf; /* command buffer base address */ uint64_t cmdbuf_len; /* command buffer length */ diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 5f8ed12..69d72ad 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -1728,8 +1728,6 @@ static bool vtd_as_pt_enabled(VTDAddressSpace *as) static bool vtd_switch_address_space(VTDAddressSpace *as) { bool use_iommu, pt; - /* Whether we need to take the BQL on our own */ - bool take_bql = !bql_locked(); assert(as); @@ -1746,9 +1744,7 @@ static bool vtd_switch_address_space(VTDAddressSpace *as) * from vtd_pt_enable_fast_path(). However the memory APIs need * it. We'd better make sure we have had it already, or, take it. */ - if (take_bql) { - bql_lock(); - } + BQL_LOCK_GUARD(); /* Turn off first then on the other */ if (use_iommu) { @@ -1801,10 +1797,6 @@ static bool vtd_switch_address_space(VTDAddressSpace *as) memory_region_set_enabled(&as->iommu_ir_fault, false); } - if (take_bql) { - bql_unlock(); - } - return use_iommu; } @@ -4213,9 +4205,30 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, VTDAddressSpace *vtd_dev_as; char name[128]; + vtd_iommu_lock(s); vtd_dev_as = g_hash_table_lookup(s->vtd_address_spaces, &key); + vtd_iommu_unlock(s); + if (!vtd_dev_as) { - struct vtd_as_key *new_key = g_malloc(sizeof(*new_key)); + struct vtd_as_key *new_key; + /* Slow path */ + + /* + * memory_region_add_subregion_overlap requires the bql, + * make sure we own it. + */ + BQL_LOCK_GUARD(); + vtd_iommu_lock(s); + + /* Check again as we released the lock for a moment */ + vtd_dev_as = g_hash_table_lookup(s->vtd_address_spaces, &key); + if (vtd_dev_as) { + vtd_iommu_unlock(s); + return vtd_dev_as; + } + + /* Still nothing, allocate a new address space */ + new_key = g_malloc(sizeof(*new_key)); new_key->bus = bus; new_key->devfn = devfn; @@ -4306,6 +4319,8 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, vtd_switch_address_space(vtd_dev_as); g_hash_table_insert(s->vtd_address_spaces, new_key, vtd_dev_as); + + vtd_iommu_unlock(s); } return vtd_dev_as; } diff --git a/hw/i386/kvm/apic.c b/hw/i386/kvm/apic.c index 39035db..1be9bfe 100644 --- a/hw/i386/kvm/apic.c +++ b/hw/i386/kvm/apic.c @@ -17,6 +17,7 @@ #include "system/hw_accel.h" #include "system/kvm.h" #include "kvm/kvm_i386.h" +#include "kvm/tdx.h" static inline void kvm_apic_set_reg(struct kvm_lapic_state *kapic, int reg_id, uint32_t val) @@ -141,6 +142,10 @@ static void kvm_apic_put(CPUState *cs, run_on_cpu_data data) struct kvm_lapic_state kapic; int ret; + if (is_tdx_vm()) { + return; + } + kvm_put_apicbase(s->cpu, s->apicbase); kvm_put_apic_state(s, &kapic); diff --git a/hw/i386/kvm/xen-stubs.c b/hw/i386/kvm/xen-stubs.c index d03131e..ce73119 100644 --- a/hw/i386/kvm/xen-stubs.c +++ b/hw/i386/kvm/xen-stubs.c @@ -12,7 +12,6 @@ #include "qemu/osdep.h" #include "qapi/error.h" -#include "qapi/qapi-commands-misc-target.h" #include "xen_evtchn.h" #include "xen_primary_console.h" @@ -38,15 +37,3 @@ void xen_primary_console_create(void) void xen_primary_console_set_be_port(uint16_t port) { } -#ifdef TARGET_I386 -EvtchnInfoList *qmp_xen_event_list(Error **errp) -{ - error_setg(errp, "Xen event channel emulation not enabled"); - return NULL; -} - -void qmp_xen_event_inject(uint32_t port, Error **errp) -{ - error_setg(errp, "Xen event channel emulation not enabled"); -} -#endif diff --git a/hw/i386/kvm/xen_evtchn.c b/hw/i386/kvm/xen_evtchn.c index b519054..dd566c4 100644 --- a/hw/i386/kvm/xen_evtchn.c +++ b/hw/i386/kvm/xen_evtchn.c @@ -19,7 +19,7 @@ #include "monitor/monitor.h" #include "monitor/hmp.h" #include "qapi/error.h" -#include "qapi/qapi-commands-misc-target.h" +#include "qapi/qapi-commands-misc-i386.h" #include "qobject/qdict.h" #include "qom/object.h" #include "exec/target_page.h" diff --git a/hw/i386/meson.build b/hw/i386/meson.build index 10bdfde..7896f34 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -32,6 +32,7 @@ i386_ss.add(when: 'CONFIG_PC', if_true: files( 'port92.c')) i386_ss.add(when: 'CONFIG_X86_FW_OVMF', if_true: files('pc_sysfw_ovmf.c'), if_false: files('pc_sysfw_ovmf-stubs.c')) +i386_ss.add(when: 'CONFIG_TDX', if_true: files('tdvf.c', 'tdvf-hob.c')) subdir('kvm') subdir('xen') diff --git a/hw/i386/monitor.c b/hw/i386/monitor.c index 1921e4d..79df965 100644 --- a/hw/i386/monitor.c +++ b/hw/i386/monitor.c @@ -26,7 +26,7 @@ #include "monitor/monitor.h" #include "qobject/qdict.h" #include "qapi/error.h" -#include "qapi/qapi-commands-misc-target.h" +#include "qapi/qapi-commands-misc-i386.h" #include "hw/i386/x86.h" #include "hw/rtc/mc146818rtc.h" diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 7065615..b211633 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -44,6 +44,7 @@ #include "system/xen.h" #include "system/reset.h" #include "kvm/kvm_i386.h" +#include "kvm/tdx.h" #include "hw/xen/xen.h" #include "qobject/qlist.h" #include "qemu/error-report.h" @@ -259,28 +260,6 @@ GlobalProperty pc_compat_2_6[] = { }; const size_t pc_compat_2_6_len = G_N_ELEMENTS(pc_compat_2_6); -GlobalProperty pc_compat_2_5[] = {}; -const size_t pc_compat_2_5_len = G_N_ELEMENTS(pc_compat_2_5); - -GlobalProperty pc_compat_2_4[] = { - PC_CPU_MODEL_IDS("2.4.0") - { "Haswell-" TYPE_X86_CPU, "abm", "off" }, - { "Haswell-noTSX-" TYPE_X86_CPU, "abm", "off" }, - { "Broadwell-" TYPE_X86_CPU, "abm", "off" }, - { "Broadwell-noTSX-" TYPE_X86_CPU, "abm", "off" }, - { "host" "-" TYPE_X86_CPU, "host-cache-info", "on" }, - { TYPE_X86_CPU, "check", "off" }, - { "qemu64" "-" TYPE_X86_CPU, "sse4a", "on" }, - { "qemu64" "-" TYPE_X86_CPU, "abm", "on" }, - { "qemu64" "-" TYPE_X86_CPU, "popcnt", "on" }, - { "qemu32" "-" TYPE_X86_CPU, "popcnt", "on" }, - { "Opteron_G2" "-" TYPE_X86_CPU, "rdtscp", "on" }, - { "Opteron_G3" "-" TYPE_X86_CPU, "rdtscp", "on" }, - { "Opteron_G4" "-" TYPE_X86_CPU, "rdtscp", "on" }, - { "Opteron_G5" "-" TYPE_X86_CPU, "rdtscp", "on", } -}; -const size_t pc_compat_2_4_len = G_N_ELEMENTS(pc_compat_2_4); - /* * @PC_FW_DATA: * Size of the chunk of memory at the top of RAM for the BIOS ACPI tables @@ -976,21 +955,23 @@ void pc_memory_init(PCMachineState *pcms, /* Initialize PC system firmware */ pc_system_firmware_init(pcms, rom_memory); - option_rom_mr = g_malloc(sizeof(*option_rom_mr)); - if (machine_require_guest_memfd(machine)) { - memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom", - PC_ROM_SIZE, &error_fatal); - } else { - memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE, - &error_fatal); - if (pcmc->pci_enabled) { - memory_region_set_readonly(option_rom_mr, true); + if (!is_tdx_vm()) { + option_rom_mr = g_malloc(sizeof(*option_rom_mr)); + if (machine_require_guest_memfd(machine)) { + memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom", + PC_ROM_SIZE, &error_fatal); + } else { + memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE, + &error_fatal); + if (pcmc->pci_enabled) { + memory_region_set_readonly(option_rom_mr, true); + } } + memory_region_add_subregion_overlap(rom_memory, + PC_ROM_MIN_VGA, + option_rom_mr, + 1); } - memory_region_add_subregion_overlap(rom_memory, - PC_ROM_MIN_VGA, - option_rom_mr, - 1); fw_cfg = fw_cfg_arch_create(machine, x86ms->boot_cpus, x86ms->apic_id_limit); @@ -999,14 +980,13 @@ void pc_memory_init(PCMachineState *pcms, if (machine->device_memory) { uint64_t *val = g_malloc(sizeof(*val)); - uint64_t res_mem_end = machine->device_memory->base; - - if (!pcmc->broken_reserved_end) { - res_mem_end += memory_region_size(&machine->device_memory->mr); - } + uint64_t res_mem_end; if (pcms->cxl_devices_state.is_enabled) { res_mem_end = cxl_resv_end; + } else { + res_mem_end = machine->device_memory->base + + memory_region_size(&machine->device_memory->mr); } *val = cpu_to_le64(ROUND_UP(res_mem_end, 1 * GiB)); fw_cfg_add_file(fw_cfg, "etc/reserved-memory-end", val, sizeof(*val)); @@ -1044,9 +1024,7 @@ uint64_t pc_pci_hole64_start(void) hole64_start = pc_get_cxl_range_end(pcms); } else if (pcmc->has_reserved_memory && (ms->ram_size < ms->maxram_size)) { pc_get_device_memory_range(pcms, &hole64_start, &size); - if (!pcmc->broken_reserved_end) { - hole64_start += size; - } + hole64_start += size; } else { hole64_start = pc_above_4g_end(pcms); } @@ -1058,7 +1036,6 @@ DeviceState *pc_vga_init(ISABus *isa_bus, PCIBus *pci_bus) { DeviceState *dev = NULL; - rom_set_order_override(FW_CFG_ORDER_OVERRIDE_VGA); if (pci_bus) { PCIDevice *pcidev = pci_vga_init(pci_bus); dev = pcidev ? &pcidev->qdev : NULL; @@ -1066,7 +1043,7 @@ DeviceState *pc_vga_init(ISABus *isa_bus, PCIBus *pci_bus) ISADevice *isadev = isa_vga_init(isa_bus); dev = isadev ? DEVICE(isadev) : NULL; } - rom_reset_order_override(); + return dev; } @@ -1256,8 +1233,6 @@ void pc_nic_init(PCMachineClass *pcmc, ISABus *isa_bus, PCIBus *pci_bus) bool default_is_ne2k = g_str_equal(mc->default_nic, TYPE_ISA_NE2000); NICInfo *nd; - rom_set_order_override(FW_CFG_ORDER_OVERRIDE_NIC); - while ((nd = qemu_find_nic_info(TYPE_ISA_NE2000, default_is_ne2k, NULL))) { pc_init_ne2k_isa(isa_bus, nd, &error_fatal); } @@ -1266,8 +1241,6 @@ void pc_nic_init(PCMachineClass *pcmc, ISABus *isa_bus, PCIBus *pci_bus) if (pci_bus) { pci_init_nic_devices(pci_bus, mc->default_nic); } - - rom_reset_order_override(); } void pc_i8259_create(ISABus *isa_bus, qemu_irq *i8259_irqs) diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 0dce512..ea7572e 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -285,6 +285,8 @@ static void pc_init1(MachineState *machine, const char *pci_type) pcms->idebus[0] = qdev_get_child_bus(dev, "ide.0"); pcms->idebus[1] = qdev_get_child_bus(dev, "ide.1"); } else { + uint32_t irq; + isa_bus = isa_bus_new(NULL, system_memory, system_io, &error_abort); isa_bus_register_input_irqs(isa_bus, x86ms->gsi); @@ -292,6 +294,9 @@ static void pc_init1(MachineState *machine, const char *pci_type) x86ms->rtc = isa_new(TYPE_MC146818_RTC); qdev_prop_set_int32(DEVICE(x86ms->rtc), "base_year", 2000); isa_realize_and_unref(x86ms->rtc, isa_bus, &error_fatal); + irq = object_property_get_uint(OBJECT(x86ms->rtc), "irq", + &error_fatal); + isa_connect_gpio_out(ISA_DEVICE(x86ms->rtc), 0, irq); i8257_dma_init(OBJECT(machine), isa_bus, 0); pcms->hpet_enabled = false; @@ -778,32 +783,6 @@ static void pc_i440fx_machine_2_6_options(MachineClass *m) DEFINE_I440FX_MACHINE(2, 6); -static void pc_i440fx_machine_2_5_options(MachineClass *m) -{ - X86MachineClass *x86mc = X86_MACHINE_CLASS(m); - - pc_i440fx_machine_2_6_options(m); - x86mc->save_tsc_khz = false; - m->legacy_fw_cfg_order = 1; - compat_props_add(m->compat_props, hw_compat_2_5, hw_compat_2_5_len); - compat_props_add(m->compat_props, pc_compat_2_5, pc_compat_2_5_len); -} - -DEFINE_I440FX_MACHINE(2, 5); - -static void pc_i440fx_machine_2_4_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - - pc_i440fx_machine_2_5_options(m); - m->hw_version = "2.4.0"; - pcmc->broken_reserved_end = true; - compat_props_add(m->compat_props, hw_compat_2_4, hw_compat_2_4_len); - compat_props_add(m->compat_props, pc_compat_2_4, pc_compat_2_4_len); -} - -DEFINE_I440FX_MACHINE(2, 4); - #ifdef CONFIG_ISAPC static void isapc_machine_options(MachineClass *m) { diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index c538b3d..33211b1 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -672,29 +672,3 @@ static void pc_q35_machine_2_6_options(MachineClass *m) } DEFINE_Q35_MACHINE(2, 6); - -static void pc_q35_machine_2_5_options(MachineClass *m) -{ - X86MachineClass *x86mc = X86_MACHINE_CLASS(m); - - pc_q35_machine_2_6_options(m); - x86mc->save_tsc_khz = false; - m->legacy_fw_cfg_order = 1; - compat_props_add(m->compat_props, hw_compat_2_5, hw_compat_2_5_len); - compat_props_add(m->compat_props, pc_compat_2_5, pc_compat_2_5_len); -} - -DEFINE_Q35_MACHINE(2, 5); - -static void pc_q35_machine_2_4_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - - pc_q35_machine_2_5_options(m); - m->hw_version = "2.4.0"; - pcmc->broken_reserved_end = true; - compat_props_add(m->compat_props, hw_compat_2_4, hw_compat_2_4_len); - compat_props_add(m->compat_props, pc_compat_2_4, pc_compat_2_4_len); -} - -DEFINE_Q35_MACHINE(2, 4); diff --git a/hw/i386/pc_sysfw.c b/hw/i386/pc_sysfw.c index 1eeb58a..821396c 100644 --- a/hw/i386/pc_sysfw.c +++ b/hw/i386/pc_sysfw.c @@ -37,6 +37,7 @@ #include "hw/block/flash.h" #include "system/kvm.h" #include "target/i386/sev.h" +#include "kvm/tdx.h" #define FLASH_SECTOR_SIZE 4096 @@ -280,5 +281,11 @@ void x86_firmware_configure(hwaddr gpa, void *ptr, int size) } sev_encrypt_flash(gpa, ptr, size, &error_fatal); + } else if (is_tdx_vm()) { + ret = tdx_parse_tdvf(ptr, size); + if (ret) { + error_report("failed to parse TDVF for TDX VM"); + exit(1); + } } } diff --git a/hw/i386/sgx-stub.c b/hw/i386/sgx-stub.c index 38ff75e..d295e54 100644 --- a/hw/i386/sgx-stub.c +++ b/hw/i386/sgx-stub.c @@ -3,20 +3,20 @@ #include "monitor/hmp-target.h" #include "hw/i386/pc.h" #include "hw/i386/sgx-epc.h" +#include "qapi/qapi-commands-misc-i386.h" #include "qapi/error.h" -#include "qapi/qapi-commands-misc-target.h" void sgx_epc_build_srat(GArray *table_data) { } -SGXInfo *qmp_query_sgx(Error **errp) +SgxInfo *qmp_query_sgx(Error **errp) { error_setg(errp, "SGX support is not compiled in"); return NULL; } -SGXInfo *qmp_query_sgx_capabilities(Error **errp) +SgxInfo *qmp_query_sgx_capabilities(Error **errp) { error_setg(errp, "SGX support is not compiled in"); return NULL; diff --git a/hw/i386/sgx.c b/hw/i386/sgx.c index 5685c4f..e280154 100644 --- a/hw/i386/sgx.c +++ b/hw/i386/sgx.c @@ -19,7 +19,7 @@ #include "monitor/hmp-target.h" #include "qapi/error.h" #include "qemu/error-report.h" -#include "qapi/qapi-commands-misc-target.h" +#include "qapi/qapi-commands-misc-i386.h" #include "system/address-spaces.h" #include "system/hw_accel.h" #include "system/reset.h" @@ -84,10 +84,10 @@ static uint64_t sgx_calc_section_metric(uint64_t low, uint64_t high) ((high & MAKE_64BIT_MASK(0, 20)) << 32); } -static SGXEPCSectionList *sgx_calc_host_epc_sections(void) +static SgxEpcSectionList *sgx_calc_host_epc_sections(void) { - SGXEPCSectionList *head = NULL, **tail = &head; - SGXEPCSection *section; + SgxEpcSectionList *head = NULL, **tail = &head; + SgxEpcSection *section; uint32_t i, type; uint32_t eax, ebx, ecx, edx; uint32_t j = 0; @@ -104,7 +104,7 @@ static SGXEPCSectionList *sgx_calc_host_epc_sections(void) break; } - section = g_new0(SGXEPCSection, 1); + section = g_new0(SgxEpcSection, 1); section->node = j++; section->size = sgx_calc_section_metric(ecx, edx); QAPI_LIST_APPEND(tail, section); @@ -153,9 +153,9 @@ static void sgx_epc_reset(void *opaque) } } -SGXInfo *qmp_query_sgx_capabilities(Error **errp) +SgxInfo *qmp_query_sgx_capabilities(Error **errp) { - SGXInfo *info = NULL; + SgxInfo *info = NULL; uint32_t eax, ebx, ecx, edx; Error *local_err = NULL; @@ -166,7 +166,7 @@ SGXInfo *qmp_query_sgx_capabilities(Error **errp) return NULL; } - info = g_new0(SGXInfo, 1); + info = g_new0(SgxInfo, 1); host_cpuid(0x7, 0, &eax, &ebx, &ecx, &edx); info->sgx = ebx & (1U << 2) ? true : false; @@ -183,17 +183,17 @@ SGXInfo *qmp_query_sgx_capabilities(Error **errp) return info; } -static SGXEPCSectionList *sgx_get_epc_sections_list(void) +static SgxEpcSectionList *sgx_get_epc_sections_list(void) { GSList *device_list = sgx_epc_get_device_list(); - SGXEPCSectionList *head = NULL, **tail = &head; - SGXEPCSection *section; + SgxEpcSectionList *head = NULL, **tail = &head; + SgxEpcSection *section; for (; device_list; device_list = device_list->next) { DeviceState *dev = device_list->data; Object *obj = OBJECT(dev); - section = g_new0(SGXEPCSection, 1); + section = g_new0(SgxEpcSection, 1); section->node = object_property_get_uint(obj, SGX_EPC_NUMA_NODE_PROP, &error_abort); section->size = object_property_get_uint(obj, SGX_EPC_SIZE_PROP, @@ -205,9 +205,9 @@ static SGXEPCSectionList *sgx_get_epc_sections_list(void) return head; } -SGXInfo *qmp_query_sgx(Error **errp) +SgxInfo *qmp_query_sgx(Error **errp) { - SGXInfo *info = NULL; + SgxInfo *info = NULL; X86MachineState *x86ms; PCMachineState *pcms = (PCMachineState *)object_dynamic_cast(qdev_get_machine(), @@ -223,7 +223,7 @@ SGXInfo *qmp_query_sgx(Error **errp) return NULL; } - info = g_new0(SGXInfo, 1); + info = g_new0(SgxInfo, 1); info->sgx = true; info->sgx1 = true; @@ -237,8 +237,8 @@ SGXInfo *qmp_query_sgx(Error **errp) void hmp_info_sgx(Monitor *mon, const QDict *qdict) { Error *err = NULL; - SGXEPCSectionList *section_list, *section; - g_autoptr(SGXInfo) info = qmp_query_sgx(&err); + SgxEpcSectionList *section_list, *section; + g_autoptr(SgxInfo) info = qmp_query_sgx(&err); uint64_t size = 0; if (err) { diff --git a/hw/i386/tdvf-hob.c b/hw/i386/tdvf-hob.c new file mode 100644 index 0000000..782b3d1 --- /dev/null +++ b/hw/i386/tdvf-hob.c @@ -0,0 +1,130 @@ +/* + * Copyright (c) 2025 Intel Corporation + * Author: Isaku Yamahata <isaku.yamahata at gmail.com> + * <isaku.yamahata at intel.com> + * Xiaoyao Li <xiaoyao.li@intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "standard-headers/uefi/uefi.h" +#include "hw/pci/pcie_host.h" +#include "tdvf-hob.h" + +typedef struct TdvfHob { + hwaddr hob_addr; + void *ptr; + int size; + + /* working area */ + void *current; + void *end; +} TdvfHob; + +static uint64_t tdvf_current_guest_addr(const TdvfHob *hob) +{ + return hob->hob_addr + (hob->current - hob->ptr); +} + +static void tdvf_align(TdvfHob *hob, size_t align) +{ + hob->current = QEMU_ALIGN_PTR_UP(hob->current, align); +} + +static void *tdvf_get_area(TdvfHob *hob, uint64_t size) +{ + void *ret; + + if (hob->current + size > hob->end) { + error_report("TD_HOB overrun, size = 0x%" PRIx64, size); + exit(1); + } + + ret = hob->current; + hob->current += size; + tdvf_align(hob, 8); + return ret; +} + +static void tdvf_hob_add_memory_resources(TdxGuest *tdx, TdvfHob *hob) +{ + EFI_HOB_RESOURCE_DESCRIPTOR *region; + EFI_RESOURCE_ATTRIBUTE_TYPE attr; + EFI_RESOURCE_TYPE resource_type; + + TdxRamEntry *e; + int i; + + for (i = 0; i < tdx->nr_ram_entries; i++) { + e = &tdx->ram_entries[i]; + + if (e->type == TDX_RAM_UNACCEPTED) { + resource_type = EFI_RESOURCE_MEMORY_UNACCEPTED; + attr = EFI_RESOURCE_ATTRIBUTE_TDVF_UNACCEPTED; + } else if (e->type == TDX_RAM_ADDED) { + resource_type = EFI_RESOURCE_SYSTEM_MEMORY; + attr = EFI_RESOURCE_ATTRIBUTE_TDVF_PRIVATE; + } else { + error_report("unknown TDX_RAM_ENTRY type %d", e->type); + exit(1); + } + + region = tdvf_get_area(hob, sizeof(*region)); + *region = (EFI_HOB_RESOURCE_DESCRIPTOR) { + .Header = { + .HobType = EFI_HOB_TYPE_RESOURCE_DESCRIPTOR, + .HobLength = cpu_to_le16(sizeof(*region)), + .Reserved = cpu_to_le32(0), + }, + .Owner = EFI_HOB_OWNER_ZERO, + .ResourceType = cpu_to_le32(resource_type), + .ResourceAttribute = cpu_to_le32(attr), + .PhysicalStart = cpu_to_le64(e->address), + .ResourceLength = cpu_to_le64(e->length), + }; + } +} + +void tdvf_hob_create(TdxGuest *tdx, TdxFirmwareEntry *td_hob) +{ + TdvfHob hob = { + .hob_addr = td_hob->address, + .size = td_hob->size, + .ptr = td_hob->mem_ptr, + + .current = td_hob->mem_ptr, + .end = td_hob->mem_ptr + td_hob->size, + }; + + EFI_HOB_GENERIC_HEADER *last_hob; + EFI_HOB_HANDOFF_INFO_TABLE *hit; + + /* Note, Efi{Free}Memory{Bottom,Top} are ignored, leave 'em zeroed. */ + hit = tdvf_get_area(&hob, sizeof(*hit)); + *hit = (EFI_HOB_HANDOFF_INFO_TABLE) { + .Header = { + .HobType = EFI_HOB_TYPE_HANDOFF, + .HobLength = cpu_to_le16(sizeof(*hit)), + .Reserved = cpu_to_le32(0), + }, + .Version = cpu_to_le32(EFI_HOB_HANDOFF_TABLE_VERSION), + .BootMode = cpu_to_le32(0), + .EfiMemoryTop = cpu_to_le64(0), + .EfiMemoryBottom = cpu_to_le64(0), + .EfiFreeMemoryTop = cpu_to_le64(0), + .EfiFreeMemoryBottom = cpu_to_le64(0), + .EfiEndOfHobList = cpu_to_le64(0), /* initialized later */ + }; + + tdvf_hob_add_memory_resources(tdx, &hob); + + last_hob = tdvf_get_area(&hob, sizeof(*last_hob)); + *last_hob = (EFI_HOB_GENERIC_HEADER) { + .HobType = EFI_HOB_TYPE_END_OF_HOB_LIST, + .HobLength = cpu_to_le16(sizeof(*last_hob)), + .Reserved = cpu_to_le32(0), + }; + hit->EfiEndOfHobList = tdvf_current_guest_addr(&hob); +} diff --git a/hw/i386/tdvf-hob.h b/hw/i386/tdvf-hob.h new file mode 100644 index 0000000..4fc6a37 --- /dev/null +++ b/hw/i386/tdvf-hob.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef HW_I386_TD_HOB_H +#define HW_I386_TD_HOB_H + +#include "hw/i386/tdvf.h" +#include "target/i386/kvm/tdx.h" + +void tdvf_hob_create(TdxGuest *tdx, TdxFirmwareEntry *td_hob); + +#define EFI_RESOURCE_ATTRIBUTE_TDVF_PRIVATE \ + (EFI_RESOURCE_ATTRIBUTE_PRESENT | \ + EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \ + EFI_RESOURCE_ATTRIBUTE_TESTED) + +#define EFI_RESOURCE_ATTRIBUTE_TDVF_UNACCEPTED \ + (EFI_RESOURCE_ATTRIBUTE_PRESENT | \ + EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \ + EFI_RESOURCE_ATTRIBUTE_TESTED) + +#define EFI_RESOURCE_ATTRIBUTE_TDVF_MMIO \ + (EFI_RESOURCE_ATTRIBUTE_PRESENT | \ + EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \ + EFI_RESOURCE_ATTRIBUTE_UNCACHEABLE) + +#endif diff --git a/hw/i386/tdvf.c b/hw/i386/tdvf.c new file mode 100644 index 0000000..645d9d1 --- /dev/null +++ b/hw/i386/tdvf.c @@ -0,0 +1,189 @@ +/* + * Copyright (c) 2025 Intel Corporation + * Author: Isaku Yamahata <isaku.yamahata at gmail.com> + * <isaku.yamahata at intel.com> + * Xiaoyao Li <xiaoyao.li@intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" + +#include "hw/i386/pc.h" +#include "hw/i386/tdvf.h" +#include "system/kvm.h" + +#define TDX_METADATA_OFFSET_GUID "e47a6535-984a-4798-865e-4685a7bf8ec2" +#define TDX_METADATA_VERSION 1 +#define TDVF_SIGNATURE 0x46564454 /* TDVF as little endian */ +#define TDVF_ALIGNMENT 4096 + +/* + * the raw structs read from TDVF keeps the name convention in + * TDVF Design Guide spec. + */ +typedef struct { + uint32_t DataOffset; + uint32_t RawDataSize; + uint64_t MemoryAddress; + uint64_t MemoryDataSize; + uint32_t Type; + uint32_t Attributes; +} TdvfSectionEntry; + +typedef struct { + uint32_t Signature; + uint32_t Length; + uint32_t Version; + uint32_t NumberOfSectionEntries; + TdvfSectionEntry SectionEntries[]; +} TdvfMetadata; + +struct tdx_metadata_offset { + uint32_t offset; +}; + +static TdvfMetadata *tdvf_get_metadata(void *flash_ptr, int size) +{ + TdvfMetadata *metadata; + uint32_t offset = 0; + uint8_t *data; + + if ((uint32_t) size != size) { + return NULL; + } + + if (pc_system_ovmf_table_find(TDX_METADATA_OFFSET_GUID, &data, NULL)) { + offset = size - le32_to_cpu(((struct tdx_metadata_offset *)data)->offset); + + if (offset + sizeof(*metadata) > size) { + return NULL; + } + } else { + error_report("Cannot find TDX_METADATA_OFFSET_GUID"); + return NULL; + } + + metadata = flash_ptr + offset; + + /* Finally, verify the signature to determine if this is a TDVF image. */ + metadata->Signature = le32_to_cpu(metadata->Signature); + if (metadata->Signature != TDVF_SIGNATURE) { + error_report("Invalid TDVF signature in metadata!"); + return NULL; + } + + /* Sanity check that the TDVF doesn't overlap its own metadata. */ + metadata->Length = le32_to_cpu(metadata->Length); + if (offset + metadata->Length > size) { + return NULL; + } + + /* Only version 1 is supported/defined. */ + metadata->Version = le32_to_cpu(metadata->Version); + if (metadata->Version != TDX_METADATA_VERSION) { + return NULL; + } + + return metadata; +} + +static int tdvf_parse_and_check_section_entry(const TdvfSectionEntry *src, + TdxFirmwareEntry *entry) +{ + entry->data_offset = le32_to_cpu(src->DataOffset); + entry->data_len = le32_to_cpu(src->RawDataSize); + entry->address = le64_to_cpu(src->MemoryAddress); + entry->size = le64_to_cpu(src->MemoryDataSize); + entry->type = le32_to_cpu(src->Type); + entry->attributes = le32_to_cpu(src->Attributes); + + /* sanity check */ + if (entry->size < entry->data_len) { + error_report("Broken metadata RawDataSize 0x%x MemoryDataSize 0x%"PRIx64, + entry->data_len, entry->size); + return -1; + } + if (!QEMU_IS_ALIGNED(entry->address, TDVF_ALIGNMENT)) { + error_report("MemoryAddress 0x%"PRIx64" not page aligned", entry->address); + return -1; + } + if (!QEMU_IS_ALIGNED(entry->size, TDVF_ALIGNMENT)) { + error_report("MemoryDataSize 0x%"PRIx64" not page aligned", entry->size); + return -1; + } + + switch (entry->type) { + case TDVF_SECTION_TYPE_BFV: + case TDVF_SECTION_TYPE_CFV: + /* The sections that must be copied from firmware image to TD memory */ + if (entry->data_len == 0) { + error_report("%d section with RawDataSize == 0", entry->type); + return -1; + } + break; + case TDVF_SECTION_TYPE_TD_HOB: + case TDVF_SECTION_TYPE_TEMP_MEM: + /* The sections that no need to be copied from firmware image */ + if (entry->data_len != 0) { + error_report("%d section with RawDataSize 0x%x != 0", + entry->type, entry->data_len); + return -1; + } + break; + default: + error_report("TDVF contains unsupported section type %d", entry->type); + return -1; + } + + return 0; +} + +int tdvf_parse_metadata(TdxFirmware *fw, void *flash_ptr, int size) +{ + g_autofree TdvfSectionEntry *sections = NULL; + TdvfMetadata *metadata; + ssize_t entries_size; + int i; + + metadata = tdvf_get_metadata(flash_ptr, size); + if (!metadata) { + return -EINVAL; + } + + /* load and parse metadata entries */ + fw->nr_entries = le32_to_cpu(metadata->NumberOfSectionEntries); + if (fw->nr_entries < 2) { + error_report("Invalid number of fw entries (%u) in TDVF Metadata", + fw->nr_entries); + return -EINVAL; + } + + entries_size = fw->nr_entries * sizeof(TdvfSectionEntry); + if (metadata->Length != sizeof(*metadata) + entries_size) { + error_report("TDVF metadata len (0x%x) mismatch, expected (0x%x)", + metadata->Length, + (uint32_t)(sizeof(*metadata) + entries_size)); + return -EINVAL; + } + + fw->entries = g_new(TdxFirmwareEntry, fw->nr_entries); + sections = g_new(TdvfSectionEntry, fw->nr_entries); + + memcpy(sections, (void *)metadata + sizeof(*metadata), entries_size); + + for (i = 0; i < fw->nr_entries; i++) { + if (tdvf_parse_and_check_section_entry(§ions[i], &fw->entries[i])) { + goto err; + } + } + + fw->mem_ptr = flash_ptr; + return 0; + +err: + fw->entries = 0; + g_free(fw->entries); + return -EINVAL; +} diff --git a/hw/i386/x86-common.c b/hw/i386/x86-common.c index 1b0671c..b1b5f11 100644 --- a/hw/i386/x86-common.c +++ b/hw/i386/x86-common.c @@ -44,6 +44,7 @@ #include "standard-headers/asm-x86/bootparam.h" #include CONFIG_DEVICES #include "kvm/kvm_i386.h" +#include "kvm/tdx.h" #ifdef CONFIG_XEN_EMU #include "hw/xen/xen.h" @@ -1035,11 +1036,14 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware, if (machine_require_guest_memfd(MACHINE(x86ms))) { memory_region_init_ram_guest_memfd(&x86ms->bios, NULL, "pc.bios", bios_size, &error_fatal); + if (is_tdx_vm()) { + tdx_set_tdvf_region(&x86ms->bios); + } } else { memory_region_init_ram(&x86ms->bios, NULL, "pc.bios", bios_size, &error_fatal); } - if (sev_enabled()) { + if (sev_enabled() || is_tdx_vm()) { /* * The concept of a "reset" simply doesn't exist for * confidential computing guests, we have to destroy and diff --git a/hw/i386/x86.c b/hw/i386/x86.c index e2d0409..f80533d 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -382,7 +382,6 @@ static void x86_machine_class_init(ObjectClass *oc, const void *data) mc->get_default_cpu_node_id = x86_get_default_cpu_node_id; mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids; mc->kvm_type = x86_kvm_type; - x86mc->save_tsc_khz = true; x86mc->fwcfg_dma_enabled = true; nc->nmi_monitor_handler = x86_nmi; |