diff options
Diffstat (limited to 'hw/i386/acpi-build.c')
-rw-r--r-- | hw/i386/acpi-build.c | 2642 |
1 files changed, 1320 insertions, 1322 deletions
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 1599caa7c5..53f804ac16 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -24,46 +24,61 @@ #include "qapi/error.h" #include "qapi/qmp/qnum.h" #include "acpi-build.h" -#include "qemu-common.h" +#include "acpi-common.h" #include "qemu/bitmap.h" #include "qemu/error-report.h" -#include "hw/pci/pci.h" -#include "qom/cpu.h" +#include "hw/pci/pci_bridge.h" +#include "hw/cxl/cxl.h" +#include "hw/core/cpu.h" #include "target/i386/cpu.h" -#include "hw/misc/pvpanic.h" #include "hw/timer/hpet.h" #include "hw/acpi/acpi-defs.h" #include "hw/acpi/acpi.h" #include "hw/acpi/cpu.h" #include "hw/nvram/fw_cfg.h" #include "hw/acpi/bios-linker-loader.h" -#include "hw/loader.h" -#include "hw/isa/isa.h" -#include "hw/block/fdc.h" +#include "hw/acpi/acpi_aml_interface.h" +#include "hw/input/i8042.h" #include "hw/acpi/memory_hotplug.h" #include "sysemu/tpm.h" #include "hw/acpi/tpm.h" #include "hw/acpi/vmgenid.h" +#include "hw/acpi/erst.h" +#include "hw/acpi/piix4.h" #include "sysemu/tpm_backend.h" -#include "hw/timer/mc146818rtc_regs.h" +#include "hw/rtc/mc146818rtc_regs.h" +#include "migration/vmstate.h" #include "hw/mem/memory-device.h" +#include "hw/mem/nvdimm.h" #include "sysemu/numa.h" +#include "sysemu/reset.h" +#include "hw/hyperv/vmbus-bridge.h" /* Supported chipsets: */ -#include "hw/acpi/piix4.h" +#include "hw/southbridge/ich9.h" #include "hw/acpi/pcihp.h" -#include "hw/i386/ich9.h" +#include "hw/i386/fw_cfg.h" +#include "hw/i386/pc.h" #include "hw/pci/pci_bus.h" +#include "hw/pci-host/i440fx.h" #include "hw/pci-host/q35.h" #include "hw/i386/x86-iommu.h" #include "hw/acpi/aml-build.h" +#include "hw/acpi/utils.h" +#include "hw/acpi/pci.h" +#include "hw/acpi/cxl.h" +#include "hw/acpi/acpi_generic_initiator.h" #include "qom/qom-qobject.h" #include "hw/i386/amd_iommu.h" #include "hw/i386/intel_iommu.h" +#include "hw/virtio/virtio-iommu.h" -#include "hw/acpi/ipmi.h" +#include "hw/acpi/hmat.h" +#include "hw/acpi/viot.h" + +#include CONFIG_DEVICES /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and * -M pc-i440fx-2.0. Even if the actual amount of AML generated grows @@ -83,18 +98,13 @@ #define ACPI_BUILD_DPRINTF(fmt, ...) #endif -/* Default IOAPIC ID */ -#define ACPI_BUILD_IOAPIC_ID 0x0 - -typedef struct AcpiMcfgInfo { - uint64_t mcfg_base; - uint32_t mcfg_size; -} AcpiMcfgInfo; - typedef struct AcpiPmInfo { bool s3_disabled; bool s4_disabled; bool pcihp_bridge_en; + bool smi_on_cpuhp; + bool smi_on_cpu_unplug; + bool pcihp_root_en; uint8_t s4_val; AcpiFadtData fadt; uint16_t cpu_hp_io_base; @@ -103,24 +113,37 @@ typedef struct AcpiPmInfo { } AcpiPmInfo; typedef struct AcpiMiscInfo { - bool is_piix4; bool has_hpet; +#ifdef CONFIG_TPM TPMVersion tpm_version; - const unsigned char *dsdt_code; - unsigned dsdt_size; - uint16_t pvpanic_port; - uint16_t applesmc_io_base; +#endif } AcpiMiscInfo; -typedef struct AcpiBuildPciBusHotplugState { - GArray *device_table; - GArray *notify_table; - struct AcpiBuildPciBusHotplugState *parent; - bool pcihp_bridge_en; -} AcpiBuildPciBusHotplugState; +typedef struct FwCfgTPMConfig { + uint32_t tpmppi_address; + uint8_t tpm_version; + uint8_t tpmppi_version; +} QEMU_PACKED FwCfgTPMConfig; -static void init_common_fadt_data(Object *o, AcpiFadtData *data) +static bool acpi_get_mcfg(AcpiMcfgInfo *mcfg); + +const struct AcpiGenericAddress x86_nvdimm_acpi_dsmio = { + .space_id = AML_AS_SYSTEM_IO, + .address = NVDIMM_ACPI_IO_BASE, + .bit_width = NVDIMM_ACPI_IO_LEN << 3 +}; + +static void init_common_fadt_data(MachineState *ms, Object *o, + AcpiFadtData *data) { + X86MachineState *x86ms = X86_MACHINE(ms); + /* + * "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. + */ + bool smm_enabled = object_property_get_bool(o, "smm-compat", NULL) ? + true : x86_machine_is_smm_enabled(x86ms); uint32_t io = object_property_get_uint(o, ACPI_PM_PROP_PM_IO_BASE, NULL); AmlAddressSpace as = AML_AS_SYSTEM_IO; AcpiFadtData fadt = { @@ -135,17 +158,22 @@ static void init_common_fadt_data(Object *o, AcpiFadtData *data) * CPUs for more than 8 CPUs, "Clustered Logical" mode has to be * used */ - ((max_cpus > 8) ? (1 << ACPI_FADT_F_FORCE_APIC_CLUSTER_MODEL) : 0), + ((ms->smp.max_cpus > 8) ? + (1 << ACPI_FADT_F_FORCE_APIC_CLUSTER_MODEL) : 0), .int_model = 1 /* Multiple APIC */, .rtc_century = RTC_CENTURY, .plvl2_lat = 0xfff /* C2 state not supported */, .plvl3_lat = 0xfff /* C3 state not supported */, - .smi_cmd = ACPI_PORT_SMI_CMD, + .smi_cmd = smm_enabled ? ACPI_PORT_SMI_CMD : 0, .sci_int = object_property_get_uint(o, ACPI_PM_PROP_SCI_INT, NULL), .acpi_enable_cmd = - object_property_get_uint(o, ACPI_PM_PROP_ACPI_ENABLE_CMD, NULL), + smm_enabled ? + object_property_get_uint(o, ACPI_PM_PROP_ACPI_ENABLE_CMD, NULL) : + 0, .acpi_disable_cmd = - object_property_get_uint(o, ACPI_PM_PROP_ACPI_DISABLE_CMD, NULL), + smm_enabled ? + object_property_get_uint(o, ACPI_PM_PROP_ACPI_DISABLE_CMD, NULL) : + 0, .pm1a_evt = { .space_id = as, .bit_width = 4 * 8, .address = io }, .pm1a_cnt = { .space_id = as, .bit_width = 2 * 8, .address = io + 0x04 }, @@ -155,42 +183,53 @@ static void init_common_fadt_data(Object *o, AcpiFadtData *data) .address = object_property_get_uint(o, ACPI_PM_PROP_GPE0_BLK, NULL) }, }; + + /* + * ACPI v2, Table 5-10 - Fixed ACPI Description Table Boot Architecture + * Flags, bit offset 1 - 8042. + */ + fadt.iapc_boot_arch = iapc_boot_arch_8042(); + *data = fadt; } -static void acpi_get_pm_info(AcpiPmInfo *pm) +static void acpi_get_pm_info(MachineState *machine, AcpiPmInfo *pm) { - Object *piix = piix4_pm_find(); - Object *lpc = ich9_lpc_find(); + Object *piix = object_resolve_type_unambiguous(TYPE_PIIX4_PM, NULL); + Object *lpc = object_resolve_type_unambiguous(TYPE_ICH9_LPC_DEVICE, NULL); Object *obj = piix ? piix : lpc; QObject *o; pm->cpu_hp_io_base = 0; pm->pcihp_io_base = 0; pm->pcihp_io_len = 0; + pm->smi_on_cpuhp = false; + pm->smi_on_cpu_unplug = false; - init_common_fadt_data(obj, &pm->fadt); + assert(obj); + init_common_fadt_data(machine, obj, &pm->fadt); if (piix) { /* w2k requires FADT(rev1) or it won't boot, keep PC compatible */ pm->fadt.rev = 1; pm->cpu_hp_io_base = PIIX4_CPU_HOTPLUG_IO_BASE; - pm->pcihp_io_base = - object_property_get_uint(obj, ACPI_PCIHP_IO_BASE_PROP, NULL); - pm->pcihp_io_len = - object_property_get_uint(obj, ACPI_PCIHP_IO_LEN_PROP, NULL); } if (lpc) { + uint64_t smi_features = object_property_get_uint(lpc, + ICH9_LPC_SMI_NEGOTIATED_FEAT_PROP, NULL); struct AcpiGenericAddress r = { .space_id = AML_AS_SYSTEM_IO, .bit_width = 8, .address = ICH9_RST_CNT_IOPORT }; pm->fadt.reset_reg = r; pm->fadt.reset_val = 0xf; pm->fadt.flags |= 1 << ACPI_FADT_F_RESET_REG_SUP; pm->cpu_hp_io_base = ICH9_CPU_HOTPLUG_IO_BASE; + pm->smi_on_cpuhp = + !!(smi_features & BIT_ULL(ICH9_LPC_SMI_F_CPU_HOTPLUG_BIT)); + pm->smi_on_cpu_unplug = + !!(smi_features & BIT_ULL(ICH9_LPC_SMI_F_CPU_HOT_UNPLUG_BIT)); } - assert(obj); - - /* The above need not be conditional on machine type because the reset port - * happens to be the same on PIIX (pc) and ICH9 (q35). */ - QEMU_BUILD_BUG_ON(ICH9_RST_CNT_IOPORT != RCR_IOPORT); + pm->pcihp_io_base = + object_property_get_uint(obj, ACPI_PCIHP_IO_BASE_PROP, NULL); + pm->pcihp_io_len = + object_property_get_uint(obj, ACPI_PCIHP_IO_LEN_PROP, NULL); /* Fill in optional s3/s4 related properties */ o = object_property_get_qobject(obj, ACPI_PM_PROP_S3_DISABLED, NULL); @@ -216,44 +255,32 @@ static void acpi_get_pm_info(AcpiPmInfo *pm) qobject_unref(o); pm->pcihp_bridge_en = - object_property_get_bool(obj, "acpi-pci-hotplug-with-bridge-support", + object_property_get_bool(obj, ACPI_PM_PROP_ACPI_PCIHP_BRIDGE, + NULL); + pm->pcihp_root_en = + object_property_get_bool(obj, ACPI_PM_PROP_ACPI_PCI_ROOTHP, NULL); } static void acpi_get_misc_info(AcpiMiscInfo *info) { - Object *piix = piix4_pm_find(); - Object *lpc = ich9_lpc_find(); - assert(!!piix != !!lpc); - - if (piix) { - info->is_piix4 = true; - } - if (lpc) { - info->is_piix4 = false; - } - info->has_hpet = hpet_find(); +#ifdef CONFIG_TPM info->tpm_version = tpm_get_version(tpm_find()); - info->pvpanic_port = pvpanic_port(); - info->applesmc_io_base = applesmc_port(); +#endif } /* * Because of the PXB hosts we cannot simply query TYPE_PCI_HOST_BRIDGE. * On i386 arch we only have two pci hosts, so we can look only for them. */ -static Object *acpi_get_i386_pci_host(void) +Object *acpi_get_i386_pci_host(void) { PCIHostState *host; - host = OBJECT_CHECK(PCIHostState, - object_resolve_path("/machine/i440fx", NULL), - TYPE_PCI_HOST_BRIDGE); + host = PCI_HOST_BRIDGE(object_resolve_path("/machine/i440fx", NULL)); if (!host) { - host = OBJECT_CHECK(PCIHostState, - object_resolve_path("/machine/q35", NULL), - TYPE_PCI_HOST_BRIDGE); + host = PCI_HOST_BRIDGE(object_resolve_path("/machine/q35", NULL)); } return OBJECT(host); @@ -264,7 +291,10 @@ static void acpi_get_pci_holes(Range *hole, Range *hole64) Object *pci_host; pci_host = acpi_get_i386_pci_host(); - g_assert(pci_host); + + if (!pci_host) { + return; + } range_set_bounds1(hole, object_property_get_uint(pci_host, @@ -290,131 +320,144 @@ static void acpi_align_size(GArray *blob, unsigned align) g_array_set_size(blob, ROUND_UP(acpi_data_len(blob), align)); } -/* FACS */ +/* + * ACPI spec 1.0b, + * 5.2.6 Firmware ACPI Control Structure + */ static void -build_facs(GArray *table_data, BIOSLinker *linker) +build_facs(GArray *table_data) { - AcpiFacsDescriptorRev1 *facs = acpi_data_push(table_data, sizeof *facs); - memcpy(&facs->signature, "FACS", 4); - facs->length = cpu_to_le32(sizeof(*facs)); + const char *sig = "FACS"; + const uint8_t reserved[40] = {}; + + g_array_append_vals(table_data, sig, 4); /* Signature */ + build_append_int_noprefix(table_data, 64, 4); /* Length */ + build_append_int_noprefix(table_data, 0, 4); /* Hardware Signature */ + build_append_int_noprefix(table_data, 0, 4); /* Firmware Waking Vector */ + build_append_int_noprefix(table_data, 0, 4); /* Global Lock */ + build_append_int_noprefix(table_data, 0, 4); /* Flags */ + g_array_append_vals(table_data, reserved, 40); /* Reserved */ } -void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, - const CPUArchIdList *apic_ids, GArray *entry) +Aml *aml_pci_device_dsm(void) { - uint32_t apic_id = apic_ids->cpus[uid].arch_id; + Aml *method; - /* ACPI spec says that LAPIC entry for non present - * CPU may be omitted from MADT or it must be marked - * as disabled. However omitting non present CPU from - * MADT breaks hotplug on linux. So possible CPUs - * should be put in MADT but kept disabled. - */ - if (apic_id < 255) { - AcpiMadtProcessorApic *apic = acpi_data_push(entry, sizeof *apic); - - apic->type = ACPI_APIC_PROCESSOR; - apic->length = sizeof(*apic); - apic->processor_id = uid; - apic->local_apic_id = apic_id; - if (apic_ids->cpus[uid].cpu != NULL) { - apic->flags = cpu_to_le32(1); - } else { - apic->flags = cpu_to_le32(0); - } - } else { - AcpiMadtProcessorX2Apic *apic = acpi_data_push(entry, sizeof *apic); - - apic->type = ACPI_APIC_LOCAL_X2APIC; - apic->length = sizeof(*apic); - apic->uid = cpu_to_le32(uid); - apic->x2apic_id = cpu_to_le32(apic_id); - if (apic_ids->cpus[uid].cpu != NULL) { - apic->flags = cpu_to_le32(1); - } else { - apic->flags = cpu_to_le32(0); - } + method = aml_method("_DSM", 4, AML_SERIALIZED); + { + Aml *params = aml_local(0); + Aml *pkg = aml_package(2); + aml_append(pkg, aml_int(0)); + aml_append(pkg, aml_int(0)); + aml_append(method, aml_store(pkg, params)); + aml_append(method, + aml_store(aml_name("BSEL"), aml_index(params, aml_int(0)))); + aml_append(method, + aml_store(aml_name("ASUN"), aml_index(params, aml_int(1)))); + aml_append(method, + aml_return(aml_call5("PDSM", aml_arg(0), aml_arg(1), + aml_arg(2), aml_arg(3), params)) + ); } + return method; } -static void -build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms) +static void build_append_pci_dsm_func0_common(Aml *ctx, Aml *retvar) { - MachineClass *mc = MACHINE_GET_CLASS(pcms); - const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(MACHINE(pcms)); - int madt_start = table_data->len; - AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(pcms->acpi_dev); - AcpiDeviceIf *adev = ACPI_DEVICE_IF(pcms->acpi_dev); - bool x2apic_mode = false; - - AcpiMultipleApicTable *madt; - AcpiMadtIoApic *io_apic; - AcpiMadtIntsrcovr *intsrcovr; - int i; + Aml *UUID, *ifctx1; + uint8_t byte_list[1] = { 0 }; /* nothing supported yet */ - madt = acpi_data_push(table_data, sizeof *madt); - madt->local_apic_address = cpu_to_le32(APIC_DEFAULT_ADDRESS); - madt->flags = cpu_to_le32(1); + aml_append(ctx, aml_store(aml_buffer(1, byte_list), retvar)); + /* + * PCI Firmware Specification 3.1 + * 4.6. _DSM Definitions for PCI + */ + UUID = aml_touuid("E5C937D0-3553-4D7A-9117-EA4D19C3434D"); + ifctx1 = aml_if(aml_lnot(aml_equal(aml_arg(0), UUID))); + { + /* call is for unsupported UUID, bail out */ + aml_append(ifctx1, aml_return(retvar)); + } + aml_append(ctx, ifctx1); - for (i = 0; i < apic_ids->len; i++) { - adevc->madt_cpu(adev, i, apic_ids, table_data); - if (apic_ids->cpus[i].arch_id > 254) { - x2apic_mode = true; - } + ifctx1 = aml_if(aml_lless(aml_arg(1), aml_int(2))); + { + /* call is for unsupported REV, bail out */ + aml_append(ifctx1, aml_return(retvar)); } + aml_append(ctx, ifctx1); +} - io_apic = acpi_data_push(table_data, sizeof *io_apic); - io_apic->type = ACPI_APIC_IO; - io_apic->length = sizeof(*io_apic); - io_apic->io_apic_id = ACPI_BUILD_IOAPIC_ID; - io_apic->address = cpu_to_le32(IO_APIC_DEFAULT_ADDRESS); - io_apic->interrupt = cpu_to_le32(0); - - if (pcms->apic_xrupt_override) { - intsrcovr = acpi_data_push(table_data, sizeof *intsrcovr); - intsrcovr->type = ACPI_APIC_XRUPT_OVERRIDE; - intsrcovr->length = sizeof(*intsrcovr); - intsrcovr->source = 0; - intsrcovr->gsi = cpu_to_le32(2); - intsrcovr->flags = cpu_to_le16(0); /* conforms to bus specifications */ - } - for (i = 1; i < 16; i++) { -#define ACPI_BUILD_PCI_IRQS ((1<<5) | (1<<9) | (1<<10) | (1<<11)) - if (!(ACPI_BUILD_PCI_IRQS & (1 << i))) { - /* No need for a INT source override structure. */ - continue; - } - intsrcovr = acpi_data_push(table_data, sizeof *intsrcovr); - intsrcovr->type = ACPI_APIC_XRUPT_OVERRIDE; - intsrcovr->length = sizeof(*intsrcovr); - intsrcovr->source = i; - intsrcovr->gsi = cpu_to_le32(i); - intsrcovr->flags = cpu_to_le16(0xd); /* active high, level triggered */ - } - - if (x2apic_mode) { - AcpiMadtLocalX2ApicNmi *local_nmi; - - local_nmi = acpi_data_push(table_data, sizeof *local_nmi); - local_nmi->type = ACPI_APIC_LOCAL_X2APIC_NMI; - local_nmi->length = sizeof(*local_nmi); - local_nmi->uid = 0xFFFFFFFF; /* all processors */ - local_nmi->flags = cpu_to_le16(0); - local_nmi->lint = 1; /* ACPI_LINT1 */ - } else { - AcpiMadtLocalNmi *local_nmi; +static Aml *aml_pci_edsm(void) +{ + Aml *method, *ifctx; + Aml *zero = aml_int(0); + Aml *func = aml_arg(2); + Aml *ret = aml_local(0); + Aml *aidx = aml_local(1); + Aml *params = aml_arg(4); + + method = aml_method("EDSM", 5, AML_SERIALIZED); - local_nmi = acpi_data_push(table_data, sizeof *local_nmi); - local_nmi->type = ACPI_APIC_LOCAL_NMI; - local_nmi->length = sizeof(*local_nmi); - local_nmi->processor_id = 0xff; /* all processors */ - local_nmi->flags = cpu_to_le16(0); - local_nmi->lint = 1; /* ACPI_LINT1 */ + /* get supported functions */ + ifctx = aml_if(aml_equal(func, zero)); + { + /* 1: have supported functions */ + /* 7: support for function 7 */ + const uint8_t caps = 1 | BIT(7); + build_append_pci_dsm_func0_common(ifctx, ret); + aml_append(ifctx, aml_store(aml_int(caps), aml_index(ret, zero))); + aml_append(ifctx, aml_return(ret)); } + aml_append(method, ifctx); + + /* handle specific functions requests */ + /* + * PCI Firmware Specification 3.1 + * 4.6.7. _DSM for Naming a PCI or PCI Express Device Under + * Operating Systems + */ + ifctx = aml_if(aml_equal(func, aml_int(7))); + { + Aml *pkg = aml_package(2); + aml_append(pkg, zero); + /* optional, if not impl. should return null string */ + aml_append(pkg, aml_string("%s", "")); + aml_append(ifctx, aml_store(pkg, ret)); + + /* + * IASL is fine when initializing Package with computational data, + * however it makes guest unhappy /it fails to process such AML/. + * So use runtime assignment to set acpi-index after initializer + * to make OSPM happy. + */ + aml_append(ifctx, + aml_store(aml_derefof(aml_index(params, aml_int(0))), aidx)); + aml_append(ifctx, aml_store(aidx, aml_index(ret, zero))); + aml_append(ifctx, aml_return(ret)); + } + aml_append(method, ifctx); + + return method; +} + +static Aml *aml_pci_static_endpoint_dsm(PCIDevice *pdev) +{ + Aml *method; - build_header(linker, table_data, - (void *)(table_data->data + madt_start), "APIC", - table_data->len - madt_start, 1, NULL, NULL); + g_assert(pdev->acpi_index != 0); + method = aml_method("_DSM", 4, AML_SERIALIZED); + { + Aml *params = aml_local(0); + Aml *pkg = aml_package(1); + aml_append(pkg, aml_int(pdev->acpi_index)); + aml_append(method, aml_store(pkg, params)); + aml_append(method, + aml_return(aml_call5("EDSM", aml_arg(0), aml_arg(1), + aml_arg(2), aml_arg(3), params)) + ); + } + return method; } static void build_append_pcihp_notify_entry(Aml *method, int slot) @@ -427,151 +470,259 @@ static void build_append_pcihp_notify_entry(Aml *method, int slot) aml_append(method, if_ctx); } -static void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus, - bool pcihp_bridge_en) +static bool is_devfn_ignored_generic(const int devfn, const PCIBus *bus) { - Aml *dev, *notify_method = NULL, *method; - QObject *bsel; - PCIBus *sec; - int i; - - bsel = object_property_get_qobject(OBJECT(bus), ACPI_PCIHP_PROP_BSEL, NULL); - if (bsel) { - uint64_t bsel_val = qnum_get_uint(qobject_to(QNum, bsel)); + const PCIDevice *pdev = bus->devices[devfn]; - aml_append(parent_scope, aml_name_decl("BSEL", aml_int(bsel_val))); - notify_method = aml_method("DVNT", 2, AML_NOTSERIALIZED); + if (PCI_FUNC(devfn)) { + if (IS_PCI_BRIDGE(pdev)) { + /* + * Ignore only hotplugged PCI bridges on !0 functions, but + * allow describing cold plugged bridges on all functions + */ + if (DEVICE(pdev)->hotplugged) { + return true; + } + } } + return false; +} - for (i = 0; i < ARRAY_SIZE(bus->devices); i += PCI_FUNC_MAX) { - DeviceClass *dc; - PCIDeviceClass *pc; - PCIDevice *pdev = bus->devices[i]; - int slot = PCI_SLOT(i); - bool hotplug_enabled_dev; - bool bridge_in_acpi; - - if (!pdev) { - if (bsel) { /* add hotplug slots for non present devices */ - dev = aml_device("S%.02X", PCI_DEVFN(slot, 0)); - aml_append(dev, aml_name_decl("_SUN", aml_int(slot))); - aml_append(dev, aml_name_decl("_ADR", aml_int(slot << 16))); - method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); - aml_append(method, - aml_call2("PCEJ", aml_name("BSEL"), aml_name("_SUN")) - ); - aml_append(dev, method); - aml_append(parent_scope, dev); - - build_append_pcihp_notify_entry(notify_method, slot); - } - continue; +static bool is_devfn_ignored_hotplug(const int devfn, const PCIBus *bus) +{ + PCIDevice *pdev = bus->devices[devfn]; + if (pdev) { + return is_devfn_ignored_generic(devfn, bus) || + !DEVICE_GET_CLASS(pdev)->hotpluggable || + /* Cold plugged bridges aren't themselves hot-pluggable */ + (IS_PCI_BRIDGE(pdev) && !DEVICE(pdev)->hotplugged); + } else { /* non populated slots */ + /* + * hotplug is supported only for non-multifunction device + * so generate device description only for function 0 + */ + if (PCI_FUNC(devfn) || + (pci_bus_is_express(bus) && PCI_SLOT(devfn) > 0)) { + return true; } + } + return false; +} - pc = PCI_DEVICE_GET_CLASS(pdev); - dc = DEVICE_GET_CLASS(pdev); +void build_append_pcihp_slots(Aml *parent_scope, PCIBus *bus) +{ + int devfn; + Aml *dev, *notify_method = NULL, *method; + QObject *bsel = object_property_get_qobject(OBJECT(bus), + ACPI_PCIHP_PROP_BSEL, NULL); + uint64_t bsel_val = qnum_get_uint(qobject_to(QNum, bsel)); + qobject_unref(bsel); - /* When hotplug for bridges is enabled, bridges are - * described in ACPI separately (see build_pci_bus_end). - * In this case they aren't themselves hot-pluggable. - * Hotplugged bridges *are* hot-pluggable. - */ - bridge_in_acpi = pc->is_bridge && pcihp_bridge_en && - !DEVICE(pdev)->hotplugged; + aml_append(parent_scope, aml_name_decl("BSEL", aml_int(bsel_val))); + notify_method = aml_method("DVNT", 2, AML_NOTSERIALIZED); - hotplug_enabled_dev = bsel && dc->hotpluggable && !bridge_in_acpi; + for (devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) { + int slot = PCI_SLOT(devfn); + int adr = slot << 16 | PCI_FUNC(devfn); - if (pc->class_id == PCI_CLASS_BRIDGE_ISA) { + if (is_devfn_ignored_hotplug(devfn, bus)) { continue; } - /* start to compose PCI slot descriptor */ - dev = aml_device("S%.02X", PCI_DEVFN(slot, 0)); - aml_append(dev, aml_name_decl("_ADR", aml_int(slot << 16))); + if (bus->devices[devfn]) { + dev = aml_scope("S%.02X", devfn); + } else { + dev = aml_device("S%.02X", devfn); + aml_append(dev, aml_name_decl("_ADR", aml_int(adr))); + } - if (pc->class_id == PCI_CLASS_DISPLAY_VGA) { - /* add VGA specific AML methods */ - int s3d; + /* + * Can't declare _SUN here for every device as it changes 'slot' + * enumeration order in linux kernel, so use another variable for it + */ + aml_append(dev, aml_name_decl("ASUN", aml_int(slot))); + aml_append(dev, aml_pci_device_dsm()); - if (object_dynamic_cast(OBJECT(pdev), "qxl-vga")) { - s3d = 3; - } else { - s3d = 0; - } + aml_append(dev, aml_name_decl("_SUN", aml_int(slot))); + /* add _EJ0 to make slot hotpluggable */ + method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); + aml_append(method, + aml_call2("PCEJ", aml_name("BSEL"), aml_name("_SUN")) + ); + aml_append(dev, method); - method = aml_method("_S1D", 0, AML_NOTSERIALIZED); - aml_append(method, aml_return(aml_int(0))); - aml_append(dev, method); + build_append_pcihp_notify_entry(notify_method, slot); - method = aml_method("_S2D", 0, AML_NOTSERIALIZED); - aml_append(method, aml_return(aml_int(0))); - aml_append(dev, method); + /* device descriptor has been composed, add it into parent context */ + aml_append(parent_scope, dev); + } + aml_append(parent_scope, notify_method); +} - method = aml_method("_S3D", 0, AML_NOTSERIALIZED); - aml_append(method, aml_return(aml_int(s3d))); - aml_append(dev, method); - } else if (hotplug_enabled_dev) { - /* add _SUN/_EJ0 to make slot hotpluggable */ - aml_append(dev, aml_name_decl("_SUN", aml_int(slot))); +void build_append_pci_bus_devices(Aml *parent_scope, PCIBus *bus) +{ + int devfn; + Aml *dev; - method = aml_method("_EJ0", 1, AML_NOTSERIALIZED); - aml_append(method, - aml_call2("PCEJ", aml_name("BSEL"), aml_name("_SUN")) - ); - aml_append(dev, method); + for (devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) { + /* ACPI spec: 1.0b: Table 6-2 _ADR Object Bus Types, PCI type */ + int adr = PCI_SLOT(devfn) << 16 | PCI_FUNC(devfn); + PCIDevice *pdev = bus->devices[devfn]; - if (bsel) { - build_append_pcihp_notify_entry(notify_method, slot); - } - } else if (bridge_in_acpi) { - /* - * device is coldplugged bridge, - * add child device descriptions into its scope - */ - PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(pdev)); + if (!pdev || is_devfn_ignored_generic(devfn, bus)) { + continue; + } + + /* start to compose PCI device descriptor */ + dev = aml_device("S%.02X", devfn); + aml_append(dev, aml_name_decl("_ADR", aml_int(adr))); - build_append_pci_bus_devices(dev, sec_bus, pcihp_bridge_en); + call_dev_aml_func(DEVICE(bus->devices[devfn]), dev); + /* add _DSM if device has acpi-index set */ + if (pdev->acpi_index && + !object_property_get_bool(OBJECT(pdev), "hotpluggable", + &error_abort)) { + aml_append(dev, aml_pci_static_endpoint_dsm(pdev)); } - /* slot descriptor has been composed, add it into parent context */ + + /* device descriptor has been composed, add it into parent context */ aml_append(parent_scope, dev); } +} - if (bsel) { - aml_append(parent_scope, notify_method); +static bool build_append_notfication_callback(Aml *parent_scope, + const PCIBus *bus) +{ + Aml *method; + PCIBus *sec; + QObject *bsel; + int nr_notifiers = 0; + GQueue *pcnt_bus_list = g_queue_new(); + + QLIST_FOREACH(sec, &bus->child, sibling) { + Aml *br_scope = aml_scope("S%.02X", sec->parent_dev->devfn); + if (pci_bus_is_root(sec)) { + continue; + } + nr_notifiers = nr_notifiers + + build_append_notfication_callback(br_scope, sec); + /* + * add new child scope to parent + * and keep track of bus that have PCNT, + * bus list is used later to call children PCNTs from this level PCNT + */ + if (nr_notifiers) { + g_queue_push_tail(pcnt_bus_list, sec); + aml_append(parent_scope, br_scope); + } } - /* Append PCNT method to notify about events on local and child buses. - * Add unconditionally for root since DSDT expects it. + /* + * Append PCNT method to notify about events on local and child buses. + * ps: hostbridge might not have hotplug (bsel) enabled but might have + * child bridges that do have bsel. */ method = aml_method("PCNT", 0, AML_NOTSERIALIZED); /* If bus supports hotplug select it and notify about local events */ + bsel = object_property_get_qobject(OBJECT(bus), ACPI_PCIHP_PROP_BSEL, NULL); if (bsel) { uint64_t bsel_val = qnum_get_uint(qobject_to(QNum, bsel)); aml_append(method, aml_store(aml_int(bsel_val), aml_name("BNUM"))); - aml_append(method, - aml_call2("DVNT", aml_name("PCIU"), aml_int(1) /* Device Check */) - ); - aml_append(method, - aml_call2("DVNT", aml_name("PCID"), aml_int(3)/* Eject Request */) - ); + aml_append(method, aml_call2("DVNT", aml_name("PCIU"), + aml_int(1))); /* Device Check */ + aml_append(method, aml_call2("DVNT", aml_name("PCID"), + aml_int(3))); /* Eject Request */ + nr_notifiers++; } /* Notify about child bus events in any case */ - if (pcihp_bridge_en) { - QLIST_FOREACH(sec, &bus->child, sibling) { - int32_t devfn = sec->parent_dev->devfn; + while ((sec = g_queue_pop_head(pcnt_bus_list))) { + aml_append(method, aml_name("^S%.02X.PCNT", sec->parent_dev->devfn)); + } - if (pci_bus_is_root(sec) || pci_bus_is_express(sec)) { - continue; - } + aml_append(parent_scope, method); + qobject_unref(bsel); + g_queue_free(pcnt_bus_list); + return !!nr_notifiers; +} + +static Aml *aml_pci_pdsm(void) +{ + Aml *method, *ifctx, *ifctx1; + Aml *ret = aml_local(0); + Aml *caps = aml_local(1); + Aml *acpi_index = aml_local(2); + Aml *zero = aml_int(0); + Aml *one = aml_int(1); + Aml *func = aml_arg(2); + Aml *params = aml_arg(4); + Aml *bnum = aml_derefof(aml_index(params, aml_int(0))); + Aml *sunum = aml_derefof(aml_index(params, aml_int(1))); + + method = aml_method("PDSM", 5, AML_SERIALIZED); + + /* get supported functions */ + ifctx = aml_if(aml_equal(func, zero)); + { + build_append_pci_dsm_func0_common(ifctx, ret); - aml_append(method, aml_name("^S%.02X.PCNT", devfn)); + aml_append(ifctx, aml_store(zero, caps)); + aml_append(ifctx, + aml_store(aml_call2("AIDX", bnum, sunum), acpi_index)); + /* + * advertise function 7 if device has acpi-index + * acpi_index values: + * 0: not present (default value) + * FFFFFFFF: not supported (old QEMU without PIDX reg) + * other: device's acpi-index + */ + ifctx1 = aml_if(aml_lnot( + aml_or(aml_equal(acpi_index, zero), + aml_equal(acpi_index, aml_int(0xFFFFFFFF)), NULL) + )); + { + /* have supported functions */ + aml_append(ifctx1, aml_or(caps, one, caps)); + /* support for function 7 */ + aml_append(ifctx1, + aml_or(caps, aml_shiftleft(one, aml_int(7)), caps)); } + aml_append(ifctx, ifctx1); + + aml_append(ifctx, aml_store(caps, aml_index(ret, zero))); + aml_append(ifctx, aml_return(ret)); } - aml_append(parent_scope, method); - qobject_unref(bsel); + aml_append(method, ifctx); + + /* handle specific functions requests */ + /* + * PCI Firmware Specification 3.1 + * 4.6.7. _DSM for Naming a PCI or PCI Express Device Under + * Operating Systems + */ + ifctx = aml_if(aml_equal(func, aml_int(7))); + { + Aml *pkg = aml_package(2); + + aml_append(pkg, zero); + /* + * optional, if not impl. should return null string + */ + aml_append(pkg, aml_string("%s", "")); + aml_append(ifctx, aml_store(pkg, ret)); + + aml_append(ifctx, aml_store(aml_call2("AIDX", bnum, sunum), acpi_index)); + /* + * update acpi-index to actual value + */ + aml_append(ifctx, aml_store(acpi_index, aml_index(ret, zero))); + aml_append(ifctx, aml_return(ret)); + } + + aml_append(method, ifctx); + return method; } /** @@ -613,7 +764,7 @@ static Aml *initialize_route(Aml *route, const char *link_name, * * Returns an array of 128 routes, one for each device, * based on device location. - * The main goal is to equaly distribute the interrupts + * The main goal is to equally distribute the interrupts * over the 4 existing ACPI links (works only for i440fx). * The hash function is (slot + pin) & 3 -> "LNK[D|A|B|C]". * @@ -692,285 +843,6 @@ static Aml *build_prt(bool is_pci0_prt) return method; } -typedef struct CrsRangeEntry { - uint64_t base; - uint64_t limit; -} CrsRangeEntry; - -static void crs_range_insert(GPtrArray *ranges, uint64_t base, uint64_t limit) -{ - CrsRangeEntry *entry; - - entry = g_malloc(sizeof(*entry)); - entry->base = base; - entry->limit = limit; - - g_ptr_array_add(ranges, entry); -} - -static void crs_range_free(gpointer data) -{ - CrsRangeEntry *entry = (CrsRangeEntry *)data; - g_free(entry); -} - -typedef struct CrsRangeSet { - GPtrArray *io_ranges; - GPtrArray *mem_ranges; - GPtrArray *mem_64bit_ranges; - } CrsRangeSet; - -static void crs_range_set_init(CrsRangeSet *range_set) -{ - range_set->io_ranges = g_ptr_array_new_with_free_func(crs_range_free); - range_set->mem_ranges = g_ptr_array_new_with_free_func(crs_range_free); - range_set->mem_64bit_ranges = - g_ptr_array_new_with_free_func(crs_range_free); -} - -static void crs_range_set_free(CrsRangeSet *range_set) -{ - g_ptr_array_free(range_set->io_ranges, true); - g_ptr_array_free(range_set->mem_ranges, true); - g_ptr_array_free(range_set->mem_64bit_ranges, true); -} - -static gint crs_range_compare(gconstpointer a, gconstpointer b) -{ - CrsRangeEntry *entry_a = *(CrsRangeEntry **)a; - CrsRangeEntry *entry_b = *(CrsRangeEntry **)b; - - return (int64_t)entry_a->base - (int64_t)entry_b->base; -} - -/* - * crs_replace_with_free_ranges - given the 'used' ranges within [start - end] - * interval, computes the 'free' ranges from the same interval. - * Example: If the input array is { [a1 - a2],[b1 - b2] }, the function - * will return { [base - a1], [a2 - b1], [b2 - limit] }. - */ -static void crs_replace_with_free_ranges(GPtrArray *ranges, - uint64_t start, uint64_t end) -{ - GPtrArray *free_ranges = g_ptr_array_new(); - uint64_t free_base = start; - int i; - - g_ptr_array_sort(ranges, crs_range_compare); - for (i = 0; i < ranges->len; i++) { - CrsRangeEntry *used = g_ptr_array_index(ranges, i); - - if (free_base < used->base) { - crs_range_insert(free_ranges, free_base, used->base - 1); - } - - free_base = used->limit + 1; - } - - if (free_base < end) { - crs_range_insert(free_ranges, free_base, end); - } - - g_ptr_array_set_size(ranges, 0); - for (i = 0; i < free_ranges->len; i++) { - g_ptr_array_add(ranges, g_ptr_array_index(free_ranges, i)); - } - - g_ptr_array_free(free_ranges, true); -} - -/* - * crs_range_merge - merges adjacent ranges in the given array. - * Array elements are deleted and replaced with the merged ranges. - */ -static void crs_range_merge(GPtrArray *range) -{ - GPtrArray *tmp = g_ptr_array_new_with_free_func(crs_range_free); - CrsRangeEntry *entry; - uint64_t range_base, range_limit; - int i; - - if (!range->len) { - return; - } - - g_ptr_array_sort(range, crs_range_compare); - - entry = g_ptr_array_index(range, 0); - range_base = entry->base; - range_limit = entry->limit; - for (i = 1; i < range->len; i++) { - entry = g_ptr_array_index(range, i); - if (entry->base - 1 == range_limit) { - range_limit = entry->limit; - } else { - crs_range_insert(tmp, range_base, range_limit); - range_base = entry->base; - range_limit = entry->limit; - } - } - crs_range_insert(tmp, range_base, range_limit); - - g_ptr_array_set_size(range, 0); - for (i = 0; i < tmp->len; i++) { - entry = g_ptr_array_index(tmp, i); - crs_range_insert(range, entry->base, entry->limit); - } - g_ptr_array_free(tmp, true); -} - -static Aml *build_crs(PCIHostState *host, CrsRangeSet *range_set) -{ - Aml *crs = aml_resource_template(); - CrsRangeSet temp_range_set; - CrsRangeEntry *entry; - uint8_t max_bus = pci_bus_num(host->bus); - uint8_t type; - int devfn; - int i; - - crs_range_set_init(&temp_range_set); - for (devfn = 0; devfn < ARRAY_SIZE(host->bus->devices); devfn++) { - uint64_t range_base, range_limit; - PCIDevice *dev = host->bus->devices[devfn]; - - if (!dev) { - continue; - } - - for (i = 0; i < PCI_NUM_REGIONS; i++) { - PCIIORegion *r = &dev->io_regions[i]; - - range_base = r->addr; - range_limit = r->addr + r->size - 1; - - /* - * Work-around for old bioses - * that do not support multiple root buses - */ - if (!range_base || range_base > range_limit) { - continue; - } - - if (r->type & PCI_BASE_ADDRESS_SPACE_IO) { - crs_range_insert(temp_range_set.io_ranges, - range_base, range_limit); - } else { /* "memory" */ - crs_range_insert(temp_range_set.mem_ranges, - range_base, range_limit); - } - } - - type = dev->config[PCI_HEADER_TYPE] & ~PCI_HEADER_TYPE_MULTI_FUNCTION; - if (type == PCI_HEADER_TYPE_BRIDGE) { - uint8_t subordinate = dev->config[PCI_SUBORDINATE_BUS]; - if (subordinate > max_bus) { - max_bus = subordinate; - } - - range_base = pci_bridge_get_base(dev, PCI_BASE_ADDRESS_SPACE_IO); - range_limit = pci_bridge_get_limit(dev, PCI_BASE_ADDRESS_SPACE_IO); - - /* - * Work-around for old bioses - * that do not support multiple root buses - */ - if (range_base && range_base <= range_limit) { - crs_range_insert(temp_range_set.io_ranges, - range_base, range_limit); - } - - range_base = - pci_bridge_get_base(dev, PCI_BASE_ADDRESS_SPACE_MEMORY); - range_limit = - pci_bridge_get_limit(dev, PCI_BASE_ADDRESS_SPACE_MEMORY); - - /* - * Work-around for old bioses - * that do not support multiple root buses - */ - if (range_base && range_base <= range_limit) { - uint64_t length = range_limit - range_base + 1; - if (range_limit <= UINT32_MAX && length <= UINT32_MAX) { - crs_range_insert(temp_range_set.mem_ranges, - range_base, range_limit); - } else { - crs_range_insert(temp_range_set.mem_64bit_ranges, - range_base, range_limit); - } - } - - range_base = - pci_bridge_get_base(dev, PCI_BASE_ADDRESS_MEM_PREFETCH); - range_limit = - pci_bridge_get_limit(dev, PCI_BASE_ADDRESS_MEM_PREFETCH); - - /* - * Work-around for old bioses - * that do not support multiple root buses - */ - if (range_base && range_base <= range_limit) { - uint64_t length = range_limit - range_base + 1; - if (range_limit <= UINT32_MAX && length <= UINT32_MAX) { - crs_range_insert(temp_range_set.mem_ranges, - range_base, range_limit); - } else { - crs_range_insert(temp_range_set.mem_64bit_ranges, - range_base, range_limit); - } - } - } - } - - crs_range_merge(temp_range_set.io_ranges); - for (i = 0; i < temp_range_set.io_ranges->len; i++) { - entry = g_ptr_array_index(temp_range_set.io_ranges, i); - aml_append(crs, - aml_word_io(AML_MIN_FIXED, AML_MAX_FIXED, - AML_POS_DECODE, AML_ENTIRE_RANGE, - 0, entry->base, entry->limit, 0, - entry->limit - entry->base + 1)); - crs_range_insert(range_set->io_ranges, entry->base, entry->limit); - } - - crs_range_merge(temp_range_set.mem_ranges); - for (i = 0; i < temp_range_set.mem_ranges->len; i++) { - entry = g_ptr_array_index(temp_range_set.mem_ranges, i); - aml_append(crs, - aml_dword_memory(AML_POS_DECODE, AML_MIN_FIXED, - AML_MAX_FIXED, AML_NON_CACHEABLE, - AML_READ_WRITE, - 0, entry->base, entry->limit, 0, - entry->limit - entry->base + 1)); - crs_range_insert(range_set->mem_ranges, entry->base, entry->limit); - } - - crs_range_merge(temp_range_set.mem_64bit_ranges); - for (i = 0; i < temp_range_set.mem_64bit_ranges->len; i++) { - entry = g_ptr_array_index(temp_range_set.mem_64bit_ranges, i); - aml_append(crs, - aml_qword_memory(AML_POS_DECODE, AML_MIN_FIXED, - AML_MAX_FIXED, AML_NON_CACHEABLE, - AML_READ_WRITE, - 0, entry->base, entry->limit, 0, - entry->limit - entry->base + 1)); - crs_range_insert(range_set->mem_64bit_ranges, - entry->base, entry->limit); - } - - crs_range_set_free(&temp_range_set); - - aml_append(crs, - aml_word_bus_number(AML_MIN_FIXED, AML_MAX_FIXED, AML_POS_DECODE, - 0, - pci_bus_num(host->bus), - max_bus, - 0, - max_bus - pci_bus_num(host->bus) + 1)); - - return crs; -} - static void build_hpet_aml(Aml *table) { Aml *crs; @@ -1023,253 +895,41 @@ static void build_hpet_aml(Aml *table) aml_append(table, scope); } -static Aml *build_fdinfo_aml(int idx, FloppyDriveType type) -{ - Aml *dev, *fdi; - uint8_t maxc, maxh, maxs; - - isa_fdc_get_drive_max_chs(type, &maxc, &maxh, &maxs); - - dev = aml_device("FLP%c", 'A' + idx); - - aml_append(dev, aml_name_decl("_ADR", aml_int(idx))); - - fdi = aml_package(16); - aml_append(fdi, aml_int(idx)); /* Drive Number */ - aml_append(fdi, - aml_int(cmos_get_fd_drive_type(type))); /* Device Type */ - /* - * the values below are the limits of the drive, and are thus independent - * of the inserted media - */ - aml_append(fdi, aml_int(maxc)); /* Maximum Cylinder Number */ - aml_append(fdi, aml_int(maxs)); /* Maximum Sector Number */ - aml_append(fdi, aml_int(maxh)); /* Maximum Head Number */ - /* - * SeaBIOS returns the below values for int 0x13 func 0x08 regardless of - * the drive type, so shall we - */ - aml_append(fdi, aml_int(0xAF)); /* disk_specify_1 */ - aml_append(fdi, aml_int(0x02)); /* disk_specify_2 */ - aml_append(fdi, aml_int(0x25)); /* disk_motor_wait */ - aml_append(fdi, aml_int(0x02)); /* disk_sector_siz */ - aml_append(fdi, aml_int(0x12)); /* disk_eot */ - aml_append(fdi, aml_int(0x1B)); /* disk_rw_gap */ - aml_append(fdi, aml_int(0xFF)); /* disk_dtl */ - aml_append(fdi, aml_int(0x6C)); /* disk_formt_gap */ - aml_append(fdi, aml_int(0xF6)); /* disk_fill */ - aml_append(fdi, aml_int(0x0F)); /* disk_head_sttl */ - aml_append(fdi, aml_int(0x08)); /* disk_motor_strt */ - - aml_append(dev, aml_name_decl("_FDI", fdi)); - return dev; -} - -static Aml *build_fdc_device_aml(ISADevice *fdc) +static Aml *build_vmbus_device_aml(VMBusBridge *vmbus_bridge) { - int i; Aml *dev; - Aml *crs; - -#define ACPI_FDE_MAX_FD 4 - uint32_t fde_buf[5] = { - 0, 0, 0, 0, /* presence of floppy drives #0 - #3 */ - cpu_to_le32(2) /* tape presence (2 == never present) */ - }; - - dev = aml_device("FDC0"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0700"))); - - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, 0x03F2, 0x03F2, 0x00, 0x04)); - aml_append(crs, aml_io(AML_DECODE16, 0x03F7, 0x03F7, 0x00, 0x01)); - aml_append(crs, aml_irq_no_flags(6)); - aml_append(crs, - aml_dma(AML_COMPATIBILITY, AML_NOTBUSMASTER, AML_TRANSFER8, 2)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - for (i = 0; i < MIN(MAX_FD, ACPI_FDE_MAX_FD); i++) { - FloppyDriveType type = isa_fdc_get_drive_type(fdc, i); - - if (type < FLOPPY_DRIVE_TYPE_NONE) { - fde_buf[i] = cpu_to_le32(1); /* drive present */ - aml_append(dev, build_fdinfo_aml(i, type)); - } - } - aml_append(dev, aml_name_decl("_FDE", - aml_buffer(sizeof(fde_buf), (uint8_t *)fde_buf))); - - return dev; -} - -static Aml *build_rtc_device_aml(void) -{ - Aml *dev; - Aml *crs; - - dev = aml_device("RTC"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0B00"))); - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, 0x0070, 0x0070, 0x10, 0x02)); - aml_append(crs, aml_irq_no_flags(8)); - aml_append(crs, aml_io(AML_DECODE16, 0x0072, 0x0072, 0x02, 0x06)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - return dev; -} - -static Aml *build_kbd_device_aml(void) -{ - Aml *dev; - Aml *crs; Aml *method; - - dev = aml_device("KBD"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0303"))); - - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - aml_append(method, aml_return(aml_int(0x0f))); - aml_append(dev, method); - - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, 0x0060, 0x0060, 0x01, 0x01)); - aml_append(crs, aml_io(AML_DECODE16, 0x0064, 0x0064, 0x01, 0x01)); - aml_append(crs, aml_irq_no_flags(1)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - return dev; -} - -static Aml *build_mouse_device_aml(void) -{ - Aml *dev; Aml *crs; - Aml *method; - dev = aml_device("MOU"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0F13"))); + dev = aml_device("VMBS"); + aml_append(dev, aml_name_decl("STA", aml_int(0xF))); + aml_append(dev, aml_name_decl("_HID", aml_string("VMBus"))); + aml_append(dev, aml_name_decl("_UID", aml_int(0x0))); + aml_append(dev, aml_name_decl("_DDN", aml_string("VMBUS"))); - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - aml_append(method, aml_return(aml_int(0x0f))); + method = aml_method("_DIS", 0, AML_NOTSERIALIZED); + aml_append(method, aml_store(aml_and(aml_name("STA"), aml_int(0xD), NULL), + aml_name("STA"))); aml_append(dev, method); - crs = aml_resource_template(); - aml_append(crs, aml_irq_no_flags(12)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - return dev; -} - -static Aml *build_lpt_device_aml(void) -{ - Aml *dev; - Aml *crs; - Aml *method; - Aml *if_ctx; - Aml *else_ctx; - Aml *zero = aml_int(0); - Aml *is_present = aml_local(0); - - dev = aml_device("LPT"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0400"))); - - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - aml_append(method, aml_store(aml_name("LPEN"), is_present)); - if_ctx = aml_if(aml_equal(is_present, zero)); - { - aml_append(if_ctx, aml_return(aml_int(0x00))); - } - aml_append(method, if_ctx); - else_ctx = aml_else(); - { - aml_append(else_ctx, aml_return(aml_int(0x0f))); - } - aml_append(method, else_ctx); + method = aml_method("_PS0", 0, AML_NOTSERIALIZED); + aml_append(method, aml_store(aml_or(aml_name("STA"), aml_int(0xF), NULL), + aml_name("STA"))); aml_append(dev, method); - crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, 0x0378, 0x0378, 0x08, 0x08)); - aml_append(crs, aml_irq_no_flags(7)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - return dev; -} - -static Aml *build_com_device_aml(uint8_t uid) -{ - Aml *dev; - Aml *crs; - Aml *method; - Aml *if_ctx; - Aml *else_ctx; - Aml *zero = aml_int(0); - Aml *is_present = aml_local(0); - const char *enabled_field = "CAEN"; - uint8_t irq = 4; - uint16_t io_port = 0x03F8; - - assert(uid == 1 || uid == 2); - if (uid == 2) { - enabled_field = "CBEN"; - irq = 3; - io_port = 0x02F8; - } - - dev = aml_device("COM%d", uid); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0501"))); - aml_append(dev, aml_name_decl("_UID", aml_int(uid))); - method = aml_method("_STA", 0, AML_NOTSERIALIZED); - aml_append(method, aml_store(aml_name("%s", enabled_field), is_present)); - if_ctx = aml_if(aml_equal(is_present, zero)); - { - aml_append(if_ctx, aml_return(aml_int(0x00))); - } - aml_append(method, if_ctx); - else_ctx = aml_else(); - { - aml_append(else_ctx, aml_return(aml_int(0x0f))); - } - aml_append(method, else_ctx); + aml_append(method, aml_return(aml_name("STA"))); aml_append(dev, method); + aml_append(dev, aml_name_decl("_PS3", aml_int(0x0))); + crs = aml_resource_template(); - aml_append(crs, aml_io(AML_DECODE16, io_port, io_port, 0x00, 0x08)); - aml_append(crs, aml_irq_no_flags(irq)); + aml_append(crs, aml_irq_no_flags(vmbus_bridge->irq)); aml_append(dev, aml_name_decl("_CRS", crs)); return dev; } -static void build_isa_devices_aml(Aml *table) -{ - ISADevice *fdc = pc_find_fdc0(); - bool ambiguous; - - Aml *scope = aml_scope("_SB.PCI0.ISA"); - Object *obj = object_resolve_path_type("", TYPE_ISA_BUS, &ambiguous); - - aml_append(scope, build_rtc_device_aml()); - aml_append(scope, build_kbd_device_aml()); - aml_append(scope, build_mouse_device_aml()); - if (fdc) { - aml_append(scope, build_fdc_device_aml(fdc)); - } - aml_append(scope, build_lpt_device_aml()); - aml_append(scope, build_com_device_aml(1)); - aml_append(scope, build_com_device_aml(2)); - - if (ambiguous) { - error_report("Multiple ISA busses, unable to define IPMI ACPI data"); - } else if (!obj) { - error_report("No ISA bus, unable to define IPMI ACPI data"); - } else { - build_acpi_ipmi_devices(scope, BUS(obj)); - } - - aml_append(table, scope); -} - static void build_dbg_aml(Aml *table) { Aml *field; @@ -1419,7 +1079,6 @@ static void build_piix4_pci0_int(Aml *table) { Aml *dev; Aml *crs; - Aml *field; Aml *method; uint32_t irqs; Aml *sb_scope = aml_scope("_SB"); @@ -1428,13 +1087,6 @@ static void build_piix4_pci0_int(Aml *table) aml_append(pci0_scope, build_prt(true)); aml_append(sb_scope, pci0_scope); - field = aml_field("PCI0.ISA.P40C", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); - aml_append(field, aml_named_field("PRQ0", 8)); - aml_append(field, aml_named_field("PRQ1", 8)); - aml_append(field, aml_named_field("PRQ2", 8)); - aml_append(field, aml_named_field("PRQ3", 8)); - aml_append(sb_scope, field); - aml_append(sb_scope, build_irq_status_method()); aml_append(sb_scope, build_iqcr_method(true)); @@ -1538,7 +1190,6 @@ static Aml *build_q35_routing_table(const char *str) static void build_q35_pci0_int(Aml *table) { - Aml *field; Aml *method; Aml *sb_scope = aml_scope("_SB"); Aml *pci0_scope = aml_scope("PCI0"); @@ -1575,18 +1226,6 @@ static void build_q35_pci0_int(Aml *table) aml_append(pci0_scope, method); aml_append(sb_scope, pci0_scope); - field = aml_field("PCI0.ISA.PIRQ", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); - aml_append(field, aml_named_field("PRQA", 8)); - aml_append(field, aml_named_field("PRQB", 8)); - aml_append(field, aml_named_field("PRQC", 8)); - aml_append(field, aml_named_field("PRQD", 8)); - aml_append(field, aml_reserved_field(0x20)); - aml_append(field, aml_named_field("PRQE", 8)); - aml_append(field, aml_named_field("PRQF", 8)); - aml_append(field, aml_named_field("PRQG", 8)); - aml_append(field, aml_named_field("PRQH", 8)); - aml_append(sb_scope, field); - aml_append(sb_scope, build_irq_status_method()); aml_append(sb_scope, build_iqcr_method(false)); @@ -1611,90 +1250,47 @@ static void build_q35_pci0_int(Aml *table) aml_append(table, sb_scope); } -static void build_q35_isa_bridge(Aml *table) +static Aml *build_q35_dram_controller(const AcpiMcfgInfo *mcfg) { Aml *dev; - Aml *scope; - Aml *field; - - scope = aml_scope("_SB.PCI0"); - dev = aml_device("ISA"); - aml_append(dev, aml_name_decl("_ADR", aml_int(0x001F0000))); - - /* ICH9 PCI to ISA irq remapping */ - aml_append(dev, aml_operation_region("PIRQ", AML_PCI_CONFIG, - aml_int(0x60), 0x0C)); - - aml_append(dev, aml_operation_region("LPCD", AML_PCI_CONFIG, - aml_int(0x80), 0x02)); - field = aml_field("LPCD", AML_ANY_ACC, AML_NOLOCK, AML_PRESERVE); - aml_append(field, aml_named_field("COMA", 3)); - aml_append(field, aml_reserved_field(1)); - aml_append(field, aml_named_field("COMB", 3)); - aml_append(field, aml_reserved_field(1)); - aml_append(field, aml_named_field("LPTD", 2)); - aml_append(dev, field); - - aml_append(dev, aml_operation_region("LPCE", AML_PCI_CONFIG, - aml_int(0x82), 0x02)); - /* enable bits */ - field = aml_field("LPCE", AML_ANY_ACC, AML_NOLOCK, AML_PRESERVE); - aml_append(field, aml_named_field("CAEN", 1)); - aml_append(field, aml_named_field("CBEN", 1)); - aml_append(field, aml_named_field("LPEN", 1)); - aml_append(dev, field); - - aml_append(scope, dev); - aml_append(table, scope); -} - -static void build_piix4_pm(Aml *table) -{ - Aml *dev; - Aml *scope; - - scope = aml_scope("_SB.PCI0"); - dev = aml_device("PX13"); - aml_append(dev, aml_name_decl("_ADR", aml_int(0x00010003))); - - aml_append(dev, aml_operation_region("P13C", AML_PCI_CONFIG, - aml_int(0x00), 0xff)); - aml_append(scope, dev); - aml_append(table, scope); -} - -static void build_piix4_isa_bridge(Aml *table) -{ - Aml *dev; - Aml *scope; - Aml *field; - - scope = aml_scope("_SB.PCI0"); - dev = aml_device("ISA"); - aml_append(dev, aml_name_decl("_ADR", aml_int(0x00010000))); - - /* PIIX PCI to ISA irq remapping */ - aml_append(dev, aml_operation_region("P40C", AML_PCI_CONFIG, - aml_int(0x60), 0x04)); - /* enable bits */ - field = aml_field("^PX13.P13C", AML_ANY_ACC, AML_NOLOCK, AML_PRESERVE); - /* Offset(0x5f),, 7, */ - aml_append(field, aml_reserved_field(0x2f8)); - aml_append(field, aml_reserved_field(7)); - aml_append(field, aml_named_field("LPEN", 1)); - /* Offset(0x67),, 3, */ - aml_append(field, aml_reserved_field(0x38)); - aml_append(field, aml_reserved_field(3)); - aml_append(field, aml_named_field("CAEN", 1)); - aml_append(field, aml_reserved_field(3)); - aml_append(field, aml_named_field("CBEN", 1)); - aml_append(dev, field); + Aml *resource_template; + + /* DRAM controller */ + dev = aml_device("DRAC"); + aml_append(dev, aml_name_decl("_HID", aml_string("PNP0C01"))); + + resource_template = aml_resource_template(); + if (mcfg->base + mcfg->size - 1 >= (1ULL << 32)) { + aml_append(resource_template, + aml_qword_memory(AML_POS_DECODE, + AML_MIN_FIXED, + AML_MAX_FIXED, + AML_NON_CACHEABLE, + AML_READ_WRITE, + 0x0000000000000000, + mcfg->base, + mcfg->base + mcfg->size - 1, + 0x0000000000000000, + mcfg->size)); + } else { + aml_append(resource_template, + aml_dword_memory(AML_POS_DECODE, + AML_MIN_FIXED, + AML_MAX_FIXED, + AML_NON_CACHEABLE, + AML_READ_WRITE, + 0x0000000000000000, + mcfg->base, + mcfg->base + mcfg->size - 1, + 0x0000000000000000, + mcfg->size)); + } + aml_append(dev, aml_name_decl("_CRS", resource_template)); - aml_append(scope, dev); - aml_append(table, scope); + return dev; } -static void build_piix4_pci_hotplug(Aml *table) +static void build_x86_acpi_pci_hotplug(Aml *table, uint64_t pcihp_addr) { Aml *scope; Aml *field; @@ -1703,22 +1299,25 @@ static void build_piix4_pci_hotplug(Aml *table) scope = aml_scope("_SB.PCI0"); aml_append(scope, - aml_operation_region("PCST", AML_SYSTEM_IO, aml_int(0xae00), 0x08)); + aml_operation_region("PCST", AML_SYSTEM_IO, aml_int(pcihp_addr), 0x08)); field = aml_field("PCST", AML_DWORD_ACC, AML_NOLOCK, AML_WRITE_AS_ZEROS); aml_append(field, aml_named_field("PCIU", 32)); aml_append(field, aml_named_field("PCID", 32)); aml_append(scope, field); aml_append(scope, - aml_operation_region("SEJ", AML_SYSTEM_IO, aml_int(0xae08), 0x04)); + aml_operation_region("SEJ", AML_SYSTEM_IO, + aml_int(pcihp_addr + ACPI_PCIHP_SEJ_BASE), 0x04)); field = aml_field("SEJ", AML_DWORD_ACC, AML_NOLOCK, AML_WRITE_AS_ZEROS); aml_append(field, aml_named_field("B0EJ", 32)); aml_append(scope, field); aml_append(scope, - aml_operation_region("BNMR", AML_SYSTEM_IO, aml_int(0xae10), 0x04)); + aml_operation_region("BNMR", AML_SYSTEM_IO, + aml_int(pcihp_addr + ACPI_PCIHP_BNMR_BASE), 0x08)); field = aml_field("BNMR", AML_DWORD_ACC, AML_NOLOCK, AML_WRITE_AS_ZEROS); aml_append(field, aml_named_field("BNUM", 32)); + aml_append(field, aml_named_field("PIDX", 32)); aml_append(scope, field); aml_append(scope, aml_mutex("BLCK", 0)); @@ -1732,10 +1331,22 @@ static void build_piix4_pci_hotplug(Aml *table) aml_append(method, aml_return(aml_int(0))); aml_append(scope, method); + method = aml_method("AIDX", 2, AML_NOTSERIALIZED); + aml_append(method, aml_acquire(aml_name("BLCK"), 0xFFFF)); + aml_append(method, aml_store(aml_arg(0), aml_name("BNUM"))); + aml_append(method, + aml_store(aml_shiftleft(aml_int(1), aml_arg(1)), aml_name("PIDX"))); + aml_append(method, aml_store(aml_name("PIDX"), aml_local(0))); + aml_append(method, aml_release(aml_name("BLCK"))); + aml_append(method, aml_return(aml_local(0))); + aml_append(scope, method); + + aml_append(scope, aml_pci_pdsm()); + aml_append(table, scope); } -static Aml *build_q35_osc_method(void) +static Aml *build_q35_osc_method(bool enable_native_pcie_hotplug) { Aml *if_ctx; Aml *if_ctx2; @@ -1757,8 +1368,10 @@ static Aml *build_q35_osc_method(void) /* * Always allow native PME, AER (no dependencies) * Allow SHPC (PCI bridges can have SHPC controller) + * Disable PCIe Native Hot-plug if ACPI PCI Hot-plug is enabled. */ - aml_append(if_ctx, aml_and(a_ctrl, aml_int(0x1F), a_ctrl)); + aml_append(if_ctx, aml_and(a_ctrl, + aml_int(0x1E | (enable_native_pcie_hotplug ? 0x1 : 0x0)), a_ctrl)); if_ctx2 = aml_if(aml_lnot(aml_equal(aml_arg(1), aml_int(1)))); /* Unknown revision */ @@ -1783,84 +1396,130 @@ static Aml *build_q35_osc_method(void) return method; } +static void build_acpi0017(Aml *table) +{ + Aml *dev, *scope, *method; + + scope = aml_scope("_SB"); + dev = aml_device("CXLM"); + aml_append(dev, aml_name_decl("_HID", aml_string("ACPI0017"))); + + method = aml_method("_STA", 0, AML_NOTSERIALIZED); + aml_append(method, aml_return(aml_int(0x0B))); + aml_append(dev, method); + build_cxl_dsm_method(dev); + + aml_append(scope, dev); + aml_append(table, scope); +} + static void build_dsdt(GArray *table_data, BIOSLinker *linker, AcpiPmInfo *pm, AcpiMiscInfo *misc, Range *pci_hole, Range *pci_hole64, MachineState *machine) { + Object *i440fx = object_resolve_type_unambiguous(TYPE_I440FX_PCI_HOST_BRIDGE, + NULL); + Object *q35 = object_resolve_type_unambiguous(TYPE_Q35_HOST_DEVICE, NULL); CrsRangeEntry *entry; Aml *dsdt, *sb_scope, *scope, *dev, *method, *field, *pkg, *crs; CrsRangeSet crs_range_set; PCMachineState *pcms = PC_MACHINE(machine); PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(machine); + X86MachineState *x86ms = X86_MACHINE(machine); + AcpiMcfgInfo mcfg; + bool mcfg_valid = !!acpi_get_mcfg(&mcfg); uint32_t nr_mem = machine->ram_slots; int root_bus_limit = 0xFF; PCIBus *bus = NULL; +#ifdef CONFIG_TPM + TPMIf *tpm = tpm_find(); +#endif + bool cxl_present = false; int i; + VMBusBridge *vmbus_bridge = vmbus_bridge_find(); + AcpiTable table = { .sig = "DSDT", .rev = 1, .oem_id = x86ms->oem_id, + .oem_table_id = x86ms->oem_table_id }; - dsdt = init_aml_allocator(); + assert(!!i440fx != !!q35); - /* Reserve space for header */ - acpi_data_push(dsdt->buf, sizeof(AcpiTableHeader)); + acpi_table_begin(&table, table_data); + dsdt = init_aml_allocator(); build_dbg_aml(dsdt); - if (misc->is_piix4) { + if (i440fx) { sb_scope = aml_scope("_SB"); dev = aml_device("PCI0"); aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A03"))); - aml_append(dev, aml_name_decl("_ADR", aml_int(0))); - aml_append(dev, aml_name_decl("_UID", aml_int(1))); + aml_append(dev, aml_name_decl("_UID", aml_int(pcmc->pci_root_uid))); + aml_append(dev, aml_pci_edsm()); aml_append(sb_scope, dev); aml_append(dsdt, sb_scope); - build_hpet_aml(dsdt); - build_piix4_pm(dsdt); - build_piix4_isa_bridge(dsdt); - build_isa_devices_aml(dsdt); - build_piix4_pci_hotplug(dsdt); + if (pm->pcihp_bridge_en || pm->pcihp_root_en) { + build_x86_acpi_pci_hotplug(dsdt, pm->pcihp_io_base); + } build_piix4_pci0_int(dsdt); - } else { + } else if (q35) { sb_scope = aml_scope("_SB"); dev = aml_device("PCI0"); aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A08"))); aml_append(dev, aml_name_decl("_CID", aml_eisaid("PNP0A03"))); - aml_append(dev, aml_name_decl("_ADR", aml_int(0))); - aml_append(dev, aml_name_decl("_UID", aml_int(1))); - aml_append(dev, build_q35_osc_method()); + aml_append(dev, aml_name_decl("_UID", aml_int(pcmc->pci_root_uid))); + aml_append(dev, build_q35_osc_method(!pm->pcihp_bridge_en)); + aml_append(dev, aml_pci_edsm()); aml_append(sb_scope, dev); + if (mcfg_valid) { + aml_append(sb_scope, build_q35_dram_controller(&mcfg)); + } + + if (pm->smi_on_cpuhp) { + /* reserve SMI block resources, IO ports 0xB2, 0xB3 */ + dev = aml_device("PCI0.SMI0"); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A06"))); + aml_append(dev, aml_name_decl("_UID", aml_string("SMI resources"))); + crs = aml_resource_template(); + aml_append(crs, + aml_io( + AML_DECODE16, + pm->fadt.smi_cmd, + pm->fadt.smi_cmd, + 1, + 2) + ); + aml_append(dev, aml_name_decl("_CRS", crs)); + aml_append(dev, aml_operation_region("SMIR", AML_SYSTEM_IO, + aml_int(pm->fadt.smi_cmd), 2)); + field = aml_field("SMIR", AML_BYTE_ACC, AML_NOLOCK, + AML_WRITE_AS_ZEROS); + aml_append(field, aml_named_field("SMIC", 8)); + aml_append(field, aml_reserved_field(8)); + aml_append(dev, field); + aml_append(sb_scope, dev); + } + aml_append(dsdt, sb_scope); - build_hpet_aml(dsdt); - build_q35_isa_bridge(dsdt); - build_isa_devices_aml(dsdt); + if (pm->pcihp_bridge_en) { + build_x86_acpi_pci_hotplug(dsdt, pm->pcihp_io_base); + } build_q35_pci0_int(dsdt); } - if (pcmc->legacy_cpu_hotplug) { - build_legacy_cpu_hotplug_aml(dsdt, machine, pm->cpu_hp_io_base); - } else { - CPUHotplugFeatures opts = { - .apci_1_compatible = true, .has_legacy_cphp = true - }; - build_cpus_aml(dsdt, machine, opts, pm->cpu_hp_io_base, - "\\_SB.PCI0", "\\_GPE._E02"); + if (misc->has_hpet) { + build_hpet_aml(dsdt); + } + + if (vmbus_bridge) { + sb_scope = aml_scope("_SB"); + aml_append(sb_scope, build_vmbus_device_aml(vmbus_bridge)); + aml_append(dsdt, sb_scope); } - build_memory_hotplug_aml(dsdt, nr_mem, "\\_SB.PCI0", "\\_GPE._E03"); scope = aml_scope("_GPE"); { aml_append(scope, aml_name_decl("_HID", aml_string("ACPI0006"))); - - if (misc->is_piix4) { - method = aml_method("_E01", 0, AML_NOTSERIALIZED); - aml_append(method, - aml_acquire(aml_name("\\_SB.PCI0.BLCK"), 0xFFFF)); - aml_append(method, aml_call0("\\_SB.PCI0.PCNT")); - aml_append(method, aml_release(aml_name("\\_SB.PCI0.BLCK"))); - aml_append(scope, method); - } - - if (pcms->acpi_nvdimm_state.is_enabled) { + if (machine->nvdimms_state->is_enabled) { method = aml_method("_E04", 0, AML_NOTSERIALIZED); aml_append(method, aml_notify(aml_name("\\_SB.NVDR"), aml_int(0x80))); @@ -1869,8 +1528,26 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } aml_append(dsdt, scope); + if (pcmc->legacy_cpu_hotplug) { + build_legacy_cpu_hotplug_aml(dsdt, machine, pm->cpu_hp_io_base); + } else { + CPUHotplugFeatures opts = { + .acpi_1_compatible = true, .has_legacy_cphp = true, + .smi_path = pm->smi_on_cpuhp ? "\\_SB.PCI0.SMI0.SMIC" : NULL, + .fw_unplugs_cpu = pm->smi_on_cpu_unplug, + }; + build_cpus_aml(dsdt, machine, opts, pc_madt_cpu_entry, + pm->cpu_hp_io_base, "\\_SB.PCI0", "\\_GPE._E02"); + } + + if (pcms->memhp_io_base && nr_mem) { + build_memory_hotplug_aml(dsdt, nr_mem, "\\_SB.PCI0", + "\\_GPE._E03", AML_SYSTEM_IO, + pcms->memhp_io_base); + } + crs_range_set_init(&crs_range_set); - bus = PC_MACHINE(machine)->bus; + bus = PC_MACHINE(machine)->pcibus; if (bus) { QLIST_FOREACH(bus, &bus->child, sibling) { uint8_t bus_num = pci_bus_num(bus); @@ -1886,12 +1563,30 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } scope = aml_scope("\\_SB"); - dev = aml_device("PC%.02X", bus_num); + + if (pci_bus_is_cxl(bus)) { + dev = aml_device("CL%.02X", bus_num); + } else { + dev = aml_device("PC%.02X", bus_num); + } aml_append(dev, aml_name_decl("_UID", aml_int(bus_num))); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A03"))); aml_append(dev, aml_name_decl("_BBN", aml_int(bus_num))); - if (pci_bus_is_express(bus)) { - aml_append(dev, build_q35_osc_method()); + if (pci_bus_is_cxl(bus)) { + struct Aml *aml_pkg = aml_package(2); + + aml_append(dev, aml_name_decl("_HID", aml_string("ACPI0016"))); + aml_append(aml_pkg, aml_eisaid("PNP0A08")); + aml_append(aml_pkg, aml_eisaid("PNP0A03")); + aml_append(dev, aml_name_decl("_CID", aml_pkg)); + build_cxl_osc_method(dev); + } else if (pci_bus_is_express(bus)) { + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A08"))); + aml_append(dev, aml_name_decl("_CID", aml_eisaid("PNP0A03"))); + + /* Expander bridges do not have ACPI PCI Hot-plug enabled */ + aml_append(dev, build_q35_osc_method(true)); + } else { + aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0A03"))); } if (numa_node != NUMA_NODE_UNASSIGNED) { @@ -1899,13 +1594,39 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } aml_append(dev, build_prt(false)); - crs = build_crs(PCI_HOST_BRIDGE(BUS(bus)->parent), &crs_range_set); + crs = build_crs(PCI_HOST_BRIDGE(BUS(bus)->parent), &crs_range_set, + 0, 0, 0, 0); aml_append(dev, aml_name_decl("_CRS", crs)); aml_append(scope, dev); aml_append(dsdt, scope); + + /* Handle the ranges for the PXB expanders */ + if (pci_bus_is_cxl(bus)) { + MemoryRegion *mr = &pcms->cxl_devices_state.host_mr; + uint64_t base = mr->addr; + + cxl_present = true; + crs_range_insert(crs_range_set.mem_ranges, base, + base + memory_region_size(mr) - 1); + } } } + if (cxl_present) { + build_acpi0017(dsdt); + } + + /* + * At this point crs_range_set has all the ranges used by pci + * busses *other* than PCI0. These ranges will be excluded from + * the PCI0._CRS. Add mmconfig to the set so it will be excluded + * too. + */ + if (mcfg_valid) { + crs_range_insert(crs_range_set.mem_ranges, + mcfg.base, mcfg.base + mcfg.size - 1); + } + scope = aml_scope("\\_SB.PCI0"); /* build PCI0._CRS */ crs = aml_resource_template(); @@ -1962,10 +1683,12 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } } - if (TPM_IS_TIS(tpm_find())) { +#ifdef CONFIG_TPM + if (TPM_IS_TIS_ISA(tpm_find())) { aml_append(crs, aml_memory32_fixed(TPM_TIS_ADDR_BASE, TPM_TIS_ADDR_SIZE, AML_READ_WRITE)); } +#endif aml_append(scope, aml_name_decl("_CRS", crs)); /* reserve GPE0 block resources */ @@ -1989,7 +1712,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, crs_range_set_free(&crs_range_set); /* reserve PCIHP resources */ - if (pm->pcihp_io_len) { + if (pm->pcihp_io_len && (pm->pcihp_bridge_en || pm->pcihp_root_en)) { dev = aml_device("PHPR"); aml_append(dev, aml_name_decl("_HID", aml_string("PNP0A06"))); aml_append(dev, @@ -2037,278 +1760,237 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, /* create fw_cfg node, unconditionally */ { - /* when using port i/o, the 8-bit data register *always* overlaps - * with half of the 16-bit control register. Hence, the total size - * of the i/o region used is FW_CFG_CTL_SIZE; when using DMA, the - * DMA control register is located at FW_CFG_DMA_IO_BASE + 4 */ - uint8_t io_size = object_property_get_bool(OBJECT(pcms->fw_cfg), - "dma_enabled", NULL) ? - ROUND_UP(FW_CFG_CTL_SIZE, 4) + sizeof(dma_addr_t) : - FW_CFG_CTL_SIZE; - scope = aml_scope("\\_SB.PCI0"); - dev = aml_device("FWCF"); - - aml_append(dev, aml_name_decl("_HID", aml_string("QEMU0002"))); - - /* device present, functioning, decoding, not shown in UI */ - aml_append(dev, aml_name_decl("_STA", aml_int(0xB))); - - crs = aml_resource_template(); - aml_append(crs, - aml_io(AML_DECODE16, FW_CFG_IO_BASE, FW_CFG_IO_BASE, 0x01, io_size) - ); - aml_append(dev, aml_name_decl("_CRS", crs)); - - aml_append(scope, dev); - aml_append(dsdt, scope); - } - - if (misc->applesmc_io_base) { - scope = aml_scope("\\_SB.PCI0.ISA"); - dev = aml_device("SMC"); - - aml_append(dev, aml_name_decl("_HID", aml_eisaid("APP0001"))); - /* device present, functioning, decoding, not shown in UI */ - aml_append(dev, aml_name_decl("_STA", aml_int(0xB))); - - crs = aml_resource_template(); - aml_append(crs, - aml_io(AML_DECODE16, misc->applesmc_io_base, misc->applesmc_io_base, - 0x01, APPLESMC_MAX_DATA_LENGTH) - ); - aml_append(crs, aml_irq_no_flags(6)); - aml_append(dev, aml_name_decl("_CRS", crs)); - - aml_append(scope, dev); - aml_append(dsdt, scope); - } - - if (misc->pvpanic_port) { - scope = aml_scope("\\_SB.PCI0.ISA"); - - dev = aml_device("PEVT"); - aml_append(dev, aml_name_decl("_HID", aml_string("QEMU0001"))); - - crs = aml_resource_template(); - aml_append(crs, - aml_io(AML_DECODE16, misc->pvpanic_port, misc->pvpanic_port, 1, 1) - ); - aml_append(dev, aml_name_decl("_CRS", crs)); - - aml_append(dev, aml_operation_region("PEOR", AML_SYSTEM_IO, - aml_int(misc->pvpanic_port), 1)); - field = aml_field("PEOR", AML_BYTE_ACC, AML_NOLOCK, AML_PRESERVE); - aml_append(field, aml_named_field("PEPT", 8)); - aml_append(dev, field); - - /* device present, functioning, decoding, shown in UI */ - aml_append(dev, aml_name_decl("_STA", aml_int(0xF))); - - method = aml_method("RDPT", 0, AML_NOTSERIALIZED); - aml_append(method, aml_store(aml_name("PEPT"), aml_local(0))); - aml_append(method, aml_return(aml_local(0))); - aml_append(dev, method); - - method = aml_method("WRPT", 1, AML_NOTSERIALIZED); - aml_append(method, aml_store(aml_arg(0), aml_name("PEPT"))); - aml_append(dev, method); - - aml_append(scope, dev); + fw_cfg_add_acpi_dsdt(scope, x86ms->fw_cfg); aml_append(dsdt, scope); } sb_scope = aml_scope("\\_SB"); { - Object *pci_host; - PCIBus *bus = NULL; + Object *pci_host = acpi_get_i386_pci_host(); - pci_host = acpi_get_i386_pci_host(); if (pci_host) { - bus = PCI_HOST_BRIDGE(pci_host)->bus; - } - - if (bus) { - Aml *scope = aml_scope("PCI0"); + PCIBus *pbus = PCI_HOST_BRIDGE(pci_host)->bus; + Aml *ascope = aml_scope("PCI0"); /* Scan all PCI buses. Generate tables to support hotplug. */ - build_append_pci_bus_devices(scope, bus, pm->pcihp_bridge_en); - - if (TPM_IS_TIS(tpm_find())) { - dev = aml_device("ISA.TPM"); - aml_append(dev, aml_name_decl("_HID", aml_eisaid("PNP0C31"))); - aml_append(dev, aml_name_decl("_STA", aml_int(0xF))); - crs = aml_resource_template(); - aml_append(crs, aml_memory32_fixed(TPM_TIS_ADDR_BASE, - TPM_TIS_ADDR_SIZE, AML_READ_WRITE)); - /* - FIXME: TPM_TIS_IRQ=5 conflicts with PNP0C0F irqs, - Rewrite to take IRQ from TPM device model and - fix default IRQ value there to use some unused IRQ - */ - /* aml_append(crs, aml_irq_no_flags(TPM_TIS_IRQ)); */ - aml_append(dev, aml_name_decl("_CRS", crs)); - aml_append(scope, dev); + build_append_pci_bus_devices(ascope, pbus); + if (object_property_find(OBJECT(pbus), ACPI_PCIHP_PROP_BSEL)) { + build_append_pcihp_slots(ascope, pbus); } - - aml_append(sb_scope, scope); + aml_append(sb_scope, ascope); } } - if (TPM_IS_CRB(tpm_find())) { +#ifdef CONFIG_TPM + if (TPM_IS_CRB(tpm)) { dev = aml_device("TPM"); aml_append(dev, aml_name_decl("_HID", aml_string("MSFT0101"))); + aml_append(dev, aml_name_decl("_STR", + aml_string("TPM 2.0 Device"))); crs = aml_resource_template(); aml_append(crs, aml_memory32_fixed(TPM_CRB_ADDR_BASE, TPM_CRB_ADDR_SIZE, AML_READ_WRITE)); aml_append(dev, aml_name_decl("_CRS", crs)); + aml_append(dev, aml_name_decl("_STA", aml_int(0xf))); + aml_append(dev, aml_name_decl("_UID", aml_int(1))); + + tpm_build_ppi_acpi(tpm, dev); + + aml_append(sb_scope, dev); + } +#endif + + if (pcms->sgx_epc.size != 0) { + uint64_t epc_base = pcms->sgx_epc.base; + uint64_t epc_size = pcms->sgx_epc.size; + + dev = aml_device("EPC"); + aml_append(dev, aml_name_decl("_HID", aml_eisaid("INT0E0C"))); + aml_append(dev, aml_name_decl("_STR", + aml_unicode("Enclave Page Cache 1.0"))); + crs = aml_resource_template(); + aml_append(crs, + aml_qword_memory(AML_POS_DECODE, AML_MIN_FIXED, + AML_MAX_FIXED, AML_NON_CACHEABLE, + AML_READ_WRITE, 0, epc_base, + epc_base + epc_size - 1, 0, epc_size)); + aml_append(dev, aml_name_decl("_CRS", crs)); + method = aml_method("_STA", 0, AML_NOTSERIALIZED); aml_append(method, aml_return(aml_int(0x0f))); aml_append(dev, method); aml_append(sb_scope, dev); } - aml_append(dsdt, sb_scope); + if (pm->pcihp_bridge_en || pm->pcihp_root_en) { + bool has_pcnt; + + Object *pci_host = acpi_get_i386_pci_host(); + PCIBus *b = PCI_HOST_BRIDGE(pci_host)->bus; + + scope = aml_scope("\\_SB.PCI0"); + has_pcnt = build_append_notfication_callback(scope, b); + if (has_pcnt) { + aml_append(dsdt, scope); + } + + scope = aml_scope("_GPE"); + { + method = aml_method("_E01", 0, AML_NOTSERIALIZED); + if (has_pcnt) { + aml_append(method, + aml_acquire(aml_name("\\_SB.PCI0.BLCK"), 0xFFFF)); + aml_append(method, aml_call0("\\_SB.PCI0.PCNT")); + aml_append(method, aml_release(aml_name("\\_SB.PCI0.BLCK"))); + } + aml_append(scope, method); + } + aml_append(dsdt, scope); + } + /* copy AML table into ACPI tables blob and patch header there */ g_array_append_vals(table_data, dsdt->buf->data, dsdt->buf->len); - build_header(linker, table_data, - (void *)(table_data->data + table_data->len - dsdt->buf->len), - "DSDT", dsdt->buf->len, 1, NULL, NULL); + acpi_table_end(linker, &table); free_aml_allocator(); } +/* + * IA-PC HPET (High Precision Event Timers) Specification (Revision: 1.0a) + * 3.2.4The ACPI 2.0 HPET Description Table (HPET) + */ static void -build_hpet(GArray *table_data, BIOSLinker *linker) +build_hpet(GArray *table_data, BIOSLinker *linker, const char *oem_id, + const char *oem_table_id) { - Acpi20Hpet *hpet; + AcpiTable table = { .sig = "HPET", .rev = 1, + .oem_id = oem_id, .oem_table_id = oem_table_id }; - hpet = acpi_data_push(table_data, sizeof(*hpet)); + acpi_table_begin(&table, table_data); /* Note timer_block_id value must be kept in sync with value advertised by * emulated hpet */ - hpet->timer_block_id = cpu_to_le32(0x8086a201); - hpet->addr.address = cpu_to_le64(HPET_BASE); - build_header(linker, table_data, - (void *)hpet, "HPET", sizeof(*hpet), 1, NULL, NULL); + /* Event Timer Block ID */ + build_append_int_noprefix(table_data, 0x8086a201, 4); + /* BASE_ADDRESS */ + build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 0, 0, 0, HPET_BASE); + /* HPET Number */ + build_append_int_noprefix(table_data, 0, 1); + /* Main Counter Minimum Clock_tick in Periodic Mode */ + build_append_int_noprefix(table_data, 0, 2); + /* Page Protection And OEM Attribute */ + build_append_int_noprefix(table_data, 0, 1); + acpi_table_end(linker, &table); } +#ifdef CONFIG_TPM +/* + * TCPA Description Table + * + * Following Level 00, Rev 00.37 of specs: + * http://www.trustedcomputinggroup.org/resources/tcg_acpi_specification + * 7.1.2 ACPI Table Layout + */ static void -build_tpm_tcpa(GArray *table_data, BIOSLinker *linker, GArray *tcpalog) +build_tpm_tcpa(GArray *table_data, BIOSLinker *linker, GArray *tcpalog, + const char *oem_id, const char *oem_table_id) { - Acpi20Tcpa *tcpa = acpi_data_push(table_data, sizeof *tcpa); - unsigned log_addr_size = sizeof(tcpa->log_area_start_address); - unsigned log_addr_offset = - (char *)&tcpa->log_area_start_address - table_data->data; - - tcpa->platform_class = cpu_to_le16(TPM_TCPA_ACPI_CLASS_CLIENT); - tcpa->log_area_minimum_length = cpu_to_le32(TPM_LOG_AREA_MINIMUM_SIZE); - acpi_data_push(tcpalog, le32_to_cpu(tcpa->log_area_minimum_length)); + unsigned log_addr_offset; + AcpiTable table = { .sig = "TCPA", .rev = 2, + .oem_id = oem_id, .oem_table_id = oem_table_id }; + + acpi_table_begin(&table, table_data); + /* Platform Class */ + build_append_int_noprefix(table_data, TPM_TCPA_ACPI_CLASS_CLIENT, 2); + /* Log Area Minimum Length (LAML) */ + build_append_int_noprefix(table_data, TPM_LOG_AREA_MINIMUM_SIZE, 4); + /* Log Area Start Address (LASA) */ + log_addr_offset = table_data->len; + build_append_int_noprefix(table_data, 0, 8); + /* allocate/reserve space for TPM log area */ + acpi_data_push(tcpalog, TPM_LOG_AREA_MINIMUM_SIZE); bios_linker_loader_alloc(linker, ACPI_BUILD_TPMLOG_FILE, tcpalog, 1, false /* high memory */); - - /* log area start address to be filled by Guest linker */ - bios_linker_loader_add_pointer(linker, - ACPI_BUILD_TABLE_FILE, log_addr_offset, log_addr_size, - ACPI_BUILD_TPMLOG_FILE, 0); - - build_header(linker, table_data, - (void *)tcpa, "TCPA", sizeof(*tcpa), 2, NULL, NULL); -} - -static void -build_tpm2(GArray *table_data, BIOSLinker *linker, GArray *tcpalog) -{ - Acpi20TPM2 *tpm2_ptr = acpi_data_push(table_data, sizeof *tpm2_ptr); - unsigned log_addr_size = sizeof(tpm2_ptr->log_area_start_address); - unsigned log_addr_offset = - (char *)&tpm2_ptr->log_area_start_address - table_data->data; - - tpm2_ptr->platform_class = cpu_to_le16(TPM2_ACPI_CLASS_CLIENT); - if (TPM_IS_TIS(tpm_find())) { - tpm2_ptr->control_area_address = cpu_to_le64(0); - tpm2_ptr->start_method = cpu_to_le32(TPM2_START_METHOD_MMIO); - } else if (TPM_IS_CRB(tpm_find())) { - tpm2_ptr->control_area_address = cpu_to_le64(TPM_CRB_ADDR_CTRL); - tpm2_ptr->start_method = cpu_to_le32(TPM2_START_METHOD_CRB); - } else { - g_warn_if_reached(); - } - - tpm2_ptr->log_area_minimum_length = - cpu_to_le32(TPM_LOG_AREA_MINIMUM_SIZE); - /* log area start address to be filled by Guest linker */ bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, - log_addr_offset, log_addr_size, - ACPI_BUILD_TPMLOG_FILE, 0); - build_header(linker, table_data, - (void *)tpm2_ptr, "TPM2", sizeof(*tpm2_ptr), 4, NULL, NULL); + log_addr_offset, 8, ACPI_BUILD_TPMLOG_FILE, 0); + + acpi_table_end(linker, &table); } +#endif #define HOLE_640K_START (640 * KiB) #define HOLE_640K_END (1 * MiB) +/* + * ACPI spec, Revision 3.0 + * 5.2.15 System Resource Affinity Table (SRAT) + */ static void build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) { - AcpiSystemResourceAffinityTable *srat; - AcpiSratMemoryAffinity *numamem; - int i; - int srat_start, numa_start, slots; + int numa_mem_start, slots; uint64_t mem_len, mem_base, next_base; MachineClass *mc = MACHINE_GET_CLASS(machine); + X86MachineState *x86ms = X86_MACHINE(machine); const CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(machine); - PCMachineState *pcms = PC_MACHINE(machine); - ram_addr_t hotplugabble_address_space_size = - object_property_get_int(OBJECT(pcms), PC_MACHINE_DEVMEM_REGION_SIZE, - NULL); - - srat_start = table_data->len; + int nb_numa_nodes = machine->numa_state->num_nodes; + NodeInfo *numa_info = machine->numa_state->nodes; + AcpiTable table = { .sig = "SRAT", .rev = 1, .oem_id = x86ms->oem_id, + .oem_table_id = x86ms->oem_table_id }; - srat = acpi_data_push(table_data, sizeof *srat); - srat->reserved1 = cpu_to_le32(1); + acpi_table_begin(&table, table_data); + build_append_int_noprefix(table_data, 1, 4); /* Reserved */ + build_append_int_noprefix(table_data, 0, 8); /* Reserved */ for (i = 0; i < apic_ids->len; i++) { int node_id = apic_ids->cpus[i].props.node_id; uint32_t apic_id = apic_ids->cpus[i].arch_id; if (apic_id < 255) { - AcpiSratProcessorAffinity *core; - - core = acpi_data_push(table_data, sizeof *core); - core->type = ACPI_SRAT_PROCESSOR_APIC; - core->length = sizeof(*core); - core->local_apic_id = apic_id; - core->proximity_lo = node_id; - memset(core->proximity_hi, 0, 3); - core->local_sapic_eid = 0; - core->flags = cpu_to_le32(1); + /* 5.2.15.1 Processor Local APIC/SAPIC Affinity Structure */ + build_append_int_noprefix(table_data, 0, 1); /* Type */ + build_append_int_noprefix(table_data, 16, 1); /* Length */ + /* Proximity Domain [7:0] */ + build_append_int_noprefix(table_data, node_id, 1); + build_append_int_noprefix(table_data, apic_id, 1); /* APIC ID */ + /* Flags, Table 5-36 */ + build_append_int_noprefix(table_data, 1, 4); + build_append_int_noprefix(table_data, 0, 1); /* Local SAPIC EID */ + /* Proximity Domain [31:8] */ + build_append_int_noprefix(table_data, 0, 3); + build_append_int_noprefix(table_data, 0, 4); /* Reserved */ } else { - AcpiSratProcessorX2ApicAffinity *core; - - core = acpi_data_push(table_data, sizeof *core); - core->type = ACPI_SRAT_PROCESSOR_x2APIC; - core->length = sizeof(*core); - core->x2apic_id = cpu_to_le32(apic_id); - core->proximity_domain = cpu_to_le32(node_id); - core->flags = cpu_to_le32(1); + /* + * ACPI spec, Revision 4.0 + * 5.2.16.3 Processor Local x2APIC Affinity Structure + */ + build_append_int_noprefix(table_data, 2, 1); /* Type */ + build_append_int_noprefix(table_data, 24, 1); /* Length */ + build_append_int_noprefix(table_data, 0, 2); /* Reserved */ + /* Proximity Domain */ + build_append_int_noprefix(table_data, node_id, 4); + build_append_int_noprefix(table_data, apic_id, 4); /* X2APIC ID */ + /* Flags, Table 5-39 */ + build_append_int_noprefix(table_data, 1 /* Enabled */, 4); + build_append_int_noprefix(table_data, 0, 4); /* Clock Domain */ + build_append_int_noprefix(table_data, 0, 4); /* Reserved */ } } - /* the memory map is a bit tricky, it contains at least one hole * from 640k-1M and possibly another one from 3.5G-4G. */ next_base = 0; - numa_start = table_data->len; + numa_mem_start = table_data->len; - for (i = 1; i < pcms->numa_nodes + 1; ++i) { + for (i = 1; i < nb_numa_nodes + 1; ++i) { mem_base = next_base; - mem_len = pcms->node_mem[i - 1]; + mem_len = numa_info[i - 1].node_mem; next_base = mem_base + mem_len; /* Cut out the 640K hole */ @@ -2316,8 +1998,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) next_base > HOLE_640K_START) { mem_len -= next_base - HOLE_640K_START; if (mem_len > 0) { - numamem = acpi_data_push(table_data, sizeof *numamem); - build_srat_memory(numamem, mem_base, mem_len, i - 1, + build_srat_memory(table_data, mem_base, mem_len, i - 1, MEM_AFFINITY_ENABLED); } @@ -2331,31 +2012,43 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) } /* Cut out the ACPI_PCI hole */ - if (mem_base <= pcms->below_4g_mem_size && - next_base > pcms->below_4g_mem_size) { - mem_len -= next_base - pcms->below_4g_mem_size; + if (mem_base <= x86ms->below_4g_mem_size && + next_base > x86ms->below_4g_mem_size) { + mem_len -= next_base - x86ms->below_4g_mem_size; if (mem_len > 0) { - numamem = acpi_data_push(table_data, sizeof *numamem); - build_srat_memory(numamem, mem_base, mem_len, i - 1, + build_srat_memory(table_data, mem_base, mem_len, i - 1, MEM_AFFINITY_ENABLED); } - mem_base = 1ULL << 32; - mem_len = next_base - pcms->below_4g_mem_size; + mem_base = x86ms->above_4g_mem_start; + mem_len = next_base - x86ms->below_4g_mem_size; next_base = mem_base + mem_len; } if (mem_len > 0) { - numamem = acpi_data_push(table_data, sizeof *numamem); - build_srat_memory(numamem, mem_base, mem_len, i - 1, + build_srat_memory(table_data, mem_base, mem_len, i - 1, MEM_AFFINITY_ENABLED); } } - slots = (table_data->len - numa_start) / sizeof *numamem; - for (; slots < pcms->numa_nodes + 2; slots++) { - numamem = acpi_data_push(table_data, sizeof *numamem); - build_srat_memory(numamem, 0, 0, 0, MEM_AFFINITY_NOFLAGS); + + if (machine->nvdimms_state->is_enabled) { + nvdimm_build_srat(table_data); + } + + sgx_epc_build_srat(table_data); + + /* + * TODO: this part is not in ACPI spec and current linux kernel boots fine + * without these entries. But I recall there were issues the last time I + * tried to remove it with some ancient guest OS, however I can't remember + * what that was so keep this around for now + */ + slots = (table_data->len - numa_mem_start) / 40 /* mem affinity len */; + for (; slots < nb_numa_nodes + 2; slots++) { + build_srat_memory(table_data, 0, 0, 0, MEM_AFFINITY_NOFLAGS); } + build_srat_generic_pci_initiator(table_data); + /* * Entry is required for Windows to enable memory hotplug in OS * and for Linux to enable SWIOTLB when booted with less than @@ -2364,124 +2057,327 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) * Memory devices may override proximity set by this entry, * providing _PXM method if necessary. */ - if (hotplugabble_address_space_size) { - numamem = acpi_data_push(table_data, sizeof *numamem); - build_srat_memory(numamem, machine->device_memory->base, - hotplugabble_address_space_size, pcms->numa_nodes - 1, + if (machine->device_memory) { + build_srat_memory(table_data, machine->device_memory->base, + memory_region_size(&machine->device_memory->mr), + nb_numa_nodes - 1, MEM_AFFINITY_HOTPLUGGABLE | MEM_AFFINITY_ENABLED); } - build_header(linker, table_data, - (void *)(table_data->data + srat_start), - "SRAT", - table_data->len - srat_start, 1, NULL, NULL); + acpi_table_end(linker, &table); } +/* + * Insert DMAR scope for PCI bridges and endpoint devices + */ static void -build_mcfg_q35(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info) +insert_scope(PCIBus *bus, PCIDevice *dev, void *opaque) { - AcpiTableMcfg *mcfg; - const char *sig; - int len = sizeof(*mcfg) + 1 * sizeof(mcfg->allocation[0]); - - mcfg = acpi_data_push(table_data, len); - mcfg->allocation[0].address = cpu_to_le64(info->mcfg_base); - /* Only a single allocation so no need to play with segments */ - mcfg->allocation[0].pci_segment = cpu_to_le16(0); - mcfg->allocation[0].start_bus_number = 0; - mcfg->allocation[0].end_bus_number = PCIE_MMCFG_BUS(info->mcfg_size - 1); - - /* MCFG is used for ECAM which can be enabled or disabled by guest. - * To avoid table size changes (which create migration issues), - * always create the table even if there are no allocations, - * but set the signature to a reserved value in this case. - * ACPI spec requires OSPMs to ignore such tables. - */ - if (info->mcfg_base == PCIE_BASE_ADDR_UNMAPPED) { - /* Reserved signature: ignored by OSPM */ - sig = "QEMU"; + const size_t device_scope_size = 6 /* device scope structure */ + + 2 /* 1 path entry */; + GArray *scope_blob = opaque; + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { + /* Dmar Scope Type: 0x02 for PCI Bridge */ + build_append_int_noprefix(scope_blob, 0x02, 1); } else { - sig = "MCFG"; + /* Dmar Scope Type: 0x01 for PCI Endpoint Device */ + build_append_int_noprefix(scope_blob, 0x01, 1); } - build_header(linker, table_data, (void *)mcfg, sig, len, 1, NULL, NULL); + + /* length */ + build_append_int_noprefix(scope_blob, device_scope_size, 1); + /* reserved */ + build_append_int_noprefix(scope_blob, 0, 2); + /* enumeration_id */ + build_append_int_noprefix(scope_blob, 0, 1); + /* bus */ + build_append_int_noprefix(scope_blob, pci_bus_num(bus), 1); + /* device */ + build_append_int_noprefix(scope_blob, PCI_SLOT(dev->devfn), 1); + /* function */ + build_append_int_noprefix(scope_blob, PCI_FUNC(dev->devfn), 1); +} + +/* For a given PCI host bridge, walk and insert DMAR scope */ +static int +dmar_host_bridges(Object *obj, void *opaque) +{ + GArray *scope_blob = opaque; + + if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) { + PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; + + if (bus && !pci_bus_bypass_iommu(bus)) { + pci_for_each_device_under_bus(bus, insert_scope, scope_blob); + } + } + + return 0; } /* - * VT-d spec 8.1 DMA Remapping Reporting Structure - * (version Oct. 2014 or later) + * Intel ® Virtualization Technology for Directed I/O + * Architecture Specification. Revision 3.3 + * 8.1 DMA Remapping Reporting Structure */ static void -build_dmar_q35(GArray *table_data, BIOSLinker *linker) +build_dmar_q35(GArray *table_data, BIOSLinker *linker, const char *oem_id, + const char *oem_table_id) { - int dmar_start = table_data->len; - - AcpiTableDmar *dmar; - AcpiDmarHardwareUnit *drhd; - AcpiDmarRootPortATS *atsr; uint8_t dmar_flags = 0; + uint8_t rsvd10[10] = {}; + /* Root complex IOAPIC uses one path only */ + const size_t ioapic_scope_size = 6 /* device scope structure */ + + 2 /* 1 path entry */; X86IOMMUState *iommu = x86_iommu_get_default(); - AcpiDmarDeviceScope *scope = NULL; - /* Root complex IOAPIC use one path[0] only */ - size_t ioapic_scope_size = sizeof(*scope) + sizeof(scope->path[0]); IntelIOMMUState *intel_iommu = INTEL_IOMMU_DEVICE(iommu); + GArray *scope_blob = g_array_new(false, true, 1); + + AcpiTable table = { .sig = "DMAR", .rev = 1, .oem_id = oem_id, + .oem_table_id = oem_table_id }; + + /* + * A PCI bus walk, for each PCI host bridge. + * Insert scope for each PCI bridge and endpoint device which + * is attached to a bus with iommu enabled. + */ + object_child_foreach_recursive(object_get_root(), + dmar_host_bridges, scope_blob); assert(iommu); - if (iommu->intr_supported) { + if (x86_iommu_ir_supported(iommu)) { dmar_flags |= 0x1; /* Flags: 0x1: INT_REMAP */ } - dmar = acpi_data_push(table_data, sizeof(*dmar)); - dmar->host_address_width = intel_iommu->aw_bits - 1; - dmar->flags = dmar_flags; + acpi_table_begin(&table, table_data); + /* Host Address Width */ + build_append_int_noprefix(table_data, intel_iommu->aw_bits - 1, 1); + build_append_int_noprefix(table_data, dmar_flags, 1); /* Flags */ + g_array_append_vals(table_data, rsvd10, sizeof(rsvd10)); /* Reserved */ - /* DMAR Remapping Hardware Unit Definition structure */ - drhd = acpi_data_push(table_data, sizeof(*drhd) + ioapic_scope_size); - drhd->type = cpu_to_le16(ACPI_DMAR_TYPE_HARDWARE_UNIT); - drhd->length = cpu_to_le16(sizeof(*drhd) + ioapic_scope_size); - drhd->flags = ACPI_DMAR_INCLUDE_PCI_ALL; - drhd->pci_segment = cpu_to_le16(0); - drhd->address = cpu_to_le64(Q35_HOST_BRIDGE_IOMMU_ADDR); + /* 8.3 DMAR Remapping Hardware Unit Definition structure */ + build_append_int_noprefix(table_data, 0, 2); /* Type */ + /* Length */ + build_append_int_noprefix(table_data, + 16 + ioapic_scope_size + scope_blob->len, 2); + /* Flags */ + build_append_int_noprefix(table_data, 0 /* Don't include all pci device */ , + 1); + build_append_int_noprefix(table_data, 0 , 1); /* Reserved */ + build_append_int_noprefix(table_data, 0 , 2); /* Segment Number */ + /* Register Base Address */ + build_append_int_noprefix(table_data, Q35_HOST_BRIDGE_IOMMU_ADDR , 8); /* Scope definition for the root-complex IOAPIC. See VT-d spec * 8.3.1 (version Oct. 2014 or later). */ - scope = &drhd->scope[0]; - scope->entry_type = 0x03; /* Type: 0x03 for IOAPIC */ - scope->length = ioapic_scope_size; - scope->enumeration_id = ACPI_BUILD_IOAPIC_ID; - scope->bus = Q35_PSEUDO_BUS_PLATFORM; - scope->path[0].device = PCI_SLOT(Q35_PSEUDO_DEVFN_IOAPIC); - scope->path[0].function = PCI_FUNC(Q35_PSEUDO_DEVFN_IOAPIC); + build_append_int_noprefix(table_data, 0x03 /* IOAPIC */, 1); /* Type */ + build_append_int_noprefix(table_data, ioapic_scope_size, 1); /* Length */ + build_append_int_noprefix(table_data, 0, 2); /* Reserved */ + /* Enumeration ID */ + build_append_int_noprefix(table_data, ACPI_BUILD_IOAPIC_ID, 1); + /* Start Bus Number */ + build_append_int_noprefix(table_data, Q35_PSEUDO_BUS_PLATFORM, 1); + /* Path, {Device, Function} pair */ + build_append_int_noprefix(table_data, PCI_SLOT(Q35_PSEUDO_DEVFN_IOAPIC), 1); + build_append_int_noprefix(table_data, PCI_FUNC(Q35_PSEUDO_DEVFN_IOAPIC), 1); + + /* Add scope found above */ + g_array_append_vals(table_data, scope_blob->data, scope_blob->len); + g_array_free(scope_blob, true); if (iommu->dt_supported) { - atsr = acpi_data_push(table_data, sizeof(*atsr)); - atsr->type = cpu_to_le16(ACPI_DMAR_TYPE_ATSR); - atsr->length = cpu_to_le16(sizeof(*atsr)); - atsr->flags = ACPI_DMAR_ATSR_ALL_PORTS; - atsr->pci_segment = cpu_to_le16(0); + /* 8.5 Root Port ATS Capability Reporting Structure */ + build_append_int_noprefix(table_data, 2, 2); /* Type */ + build_append_int_noprefix(table_data, 8, 2); /* Length */ + build_append_int_noprefix(table_data, 1 /* ALL_PORTS */, 1); /* Flags */ + build_append_int_noprefix(table_data, 0, 1); /* Reserved */ + build_append_int_noprefix(table_data, 0, 2); /* Segment Number */ } - build_header(linker, table_data, (void *)(table_data->data + dmar_start), - "DMAR", table_data->len - dmar_start, 1, NULL, NULL); + acpi_table_end(linker, &table); +} + +/* + * Windows ACPI Emulated Devices Table + * (Version 1.0 - April 6, 2009) + * Spec: http://download.microsoft.com/download/7/E/7/7E7662CF-CBEA-470B-A97E-CE7CE0D98DC2/WAET.docx + * + * Helpful to speedup Windows guests and ignored by others. + */ +static void +build_waet(GArray *table_data, BIOSLinker *linker, const char *oem_id, + const char *oem_table_id) +{ + AcpiTable table = { .sig = "WAET", .rev = 1, .oem_id = oem_id, + .oem_table_id = oem_table_id }; + + acpi_table_begin(&table, table_data); + /* + * Set "ACPI PM timer good" flag. + * + * Tells Windows guests that our ACPI PM timer is reliable in the + * sense that guest can read it only once to obtain a reliable value. + * Which avoids costly VMExits caused by guest re-reading it unnecessarily. + */ + build_append_int_noprefix(table_data, 1 << 1 /* ACPI PM timer good */, 4); + acpi_table_end(linker, &table); } + /* * IVRS table as specified in AMD IOMMU Specification v2.62, Section 5.2 * accessible here http://support.amd.com/TechDocs/48882_IOMMU.pdf */ +#define IOAPIC_SB_DEVID (uint64_t)PCI_BUILD_BDF(0, PCI_DEVFN(0x14, 0)) + +/* + * Insert IVHD entry for device and recurse, insert alias, or insert range as + * necessary for the PCI topology. + */ +static void +insert_ivhd(PCIBus *bus, PCIDevice *dev, void *opaque) +{ + GArray *table_data = opaque; + uint32_t entry; + + /* "Select" IVHD entry, type 0x2 */ + entry = PCI_BUILD_BDF(pci_bus_num(bus), dev->devfn) << 8 | 0x2; + build_append_int_noprefix(table_data, entry, 4); + + if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { + PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(dev)); + uint8_t sec = pci_bus_num(sec_bus); + uint8_t sub = dev->config[PCI_SUBORDINATE_BUS]; + + if (pci_bus_is_express(sec_bus)) { + /* + * Walk the bus if there are subordinates, otherwise use a range + * to cover an entire leaf bus. We could potentially also use a + * range for traversed buses, but we'd need to take care not to + * create both Select and Range entries covering the same device. + * This is easier and potentially more compact. + * + * An example bare metal system seems to use Select entries for + * root ports without a slot (ie. built-ins) and Range entries + * when there is a slot. The same system also only hard-codes + * the alias range for an onboard PCIe-to-PCI bridge, apparently + * making no effort to support nested bridges. We attempt to + * be more thorough here. + */ + if (sec == sub) { /* leaf bus */ + /* "Start of Range" IVHD entry, type 0x3 */ + entry = PCI_BUILD_BDF(sec, PCI_DEVFN(0, 0)) << 8 | 0x3; + build_append_int_noprefix(table_data, entry, 4); + /* "End of Range" IVHD entry, type 0x4 */ + entry = PCI_BUILD_BDF(sub, PCI_DEVFN(31, 7)) << 8 | 0x4; + build_append_int_noprefix(table_data, entry, 4); + } else { + pci_for_each_device(sec_bus, sec, insert_ivhd, table_data); + } + } else { + /* + * If the secondary bus is conventional, then we need to create an + * Alias range for everything downstream. The range covers the + * first devfn on the secondary bus to the last devfn on the + * subordinate bus. The alias target depends on legacy versus + * express bridges, just as in pci_device_iommu_address_space(). + * DeviceIDa vs DeviceIDb as per the AMD IOMMU spec. + */ + uint16_t dev_id_a, dev_id_b; + + dev_id_a = PCI_BUILD_BDF(sec, PCI_DEVFN(0, 0)); + + if (pci_is_express(dev) && + pcie_cap_get_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE) { + dev_id_b = dev_id_a; + } else { + dev_id_b = PCI_BUILD_BDF(pci_bus_num(bus), dev->devfn); + } + + /* "Alias Start of Range" IVHD entry, type 0x43, 8 bytes */ + build_append_int_noprefix(table_data, dev_id_a << 8 | 0x43, 4); + build_append_int_noprefix(table_data, dev_id_b << 8 | 0x0, 4); + + /* "End of Range" IVHD entry, type 0x4 */ + entry = PCI_BUILD_BDF(sub, PCI_DEVFN(31, 7)) << 8 | 0x4; + build_append_int_noprefix(table_data, entry, 4); + } + } +} + +/* For all PCI host bridges, walk and insert IVHD entries */ +static int +ivrs_host_bridges(Object *obj, void *opaque) +{ + GArray *ivhd_blob = opaque; + + if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) { + PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; + + if (bus && !pci_bus_bypass_iommu(bus)) { + pci_for_each_device_under_bus(bus, insert_ivhd, ivhd_blob); + } + } + + return 0; +} + static void -build_amd_iommu(GArray *table_data, BIOSLinker *linker) +build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id, + const char *oem_table_id) { - int iommu_start = table_data->len; AMDVIState *s = AMD_IOMMU_DEVICE(x86_iommu_get_default()); + GArray *ivhd_blob = g_array_new(false, true, 1); + AcpiTable table = { .sig = "IVRS", .rev = 1, .oem_id = oem_id, + .oem_table_id = oem_table_id }; + uint64_t feature_report; - /* IVRS header */ - acpi_data_push(table_data, sizeof(AcpiTableHeader)); + acpi_table_begin(&table, table_data); /* IVinfo - IO virtualization information common to all * IOMMU units in a system */ - build_append_int_noprefix(table_data, 40UL << 8/* PASize */, 4); + build_append_int_noprefix(table_data, + (1UL << 0) | /* EFRSup */ + (40UL << 8), /* PASize */ + 4); /* reserved */ build_append_int_noprefix(table_data, 0, 8); + /* + * A PCI bus walk, for each PCI host bridge, is necessary to create a + * complete set of IVHD entries. Do this into a separate blob so that we + * can calculate the total IVRS table length here and then append the new + * blob further below. Fall back to an entry covering all devices, which + * is sufficient when no aliases are present. + */ + object_child_foreach_recursive(object_get_root(), + ivrs_host_bridges, ivhd_blob); + + if (!ivhd_blob->len) { + /* + * Type 1 device entry reporting all devices + * These are 4-byte device entries currently reporting the range of + * Refer to Spec - Table 95:IVHD Device Entry Type Codes(4-byte) + */ + build_append_int_noprefix(ivhd_blob, 0x0000001, 4); + } + + /* + * When interrupt remapping is supported, we add a special IVHD device + * for type IO-APIC + * Refer to spec - Table 95: IVHD device entry type codes + * + * Linux IOMMU driver checks for the special IVHD device (type IO-APIC). + * See Linux kernel commit 'c2ff5cf5294bcbd7fa50f7d860e90a66db7e5059' + */ + if (x86_iommu_ir_supported(x86_iommu_get_default())) { + build_append_int_noprefix(ivhd_blob, + (0x1ull << 56) | /* type IOAPIC */ + (IOAPIC_SB_DEVID << 40) | /* IOAPIC devid */ + 0x48, /* special device */ + 8); + } + /* IVHD definition - type 10h */ build_append_int_noprefix(table_data, 0x10, 1); /* virtualization flags */ @@ -2491,12 +2387,15 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker) (1UL << 6) | /* PrefSup */ (1UL << 7), /* PPRSup */ 1); + /* IVHD length */ - build_append_int_noprefix(table_data, 28, 2); + build_append_int_noprefix(table_data, ivhd_blob->len + 24, 2); /* DeviceID */ - build_append_int_noprefix(table_data, s->devid, 2); + build_append_int_noprefix(table_data, + object_property_get_int(OBJECT(&s->pci), "addr", + &error_abort), 2); /* Capability offset */ - build_append_int_noprefix(table_data, s->capab_offset, 2); + build_append_int_noprefix(table_data, s->pci.capab_offset, 2); /* IOMMU base address */ build_append_int_noprefix(table_data, s->mmio.addr, 8); /* PCI Segment Group */ @@ -2504,46 +2403,54 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker) /* IOMMU info */ build_append_int_noprefix(table_data, 0, 2); /* IOMMU Feature Reporting */ + feature_report = (48UL << 30) | /* HATS */ + (48UL << 28) | /* GATS */ + (1UL << 2) | /* GTSup */ + (1UL << 6); /* GASup */ + if (s->xtsup) { + feature_report |= (1UL << 0); /* XTSup */ + } + build_append_int_noprefix(table_data, feature_report, 4); + + /* IVHD entries as found above */ + g_array_append_vals(table_data, ivhd_blob->data, ivhd_blob->len); + + /* IVHD definition - type 11h */ + build_append_int_noprefix(table_data, 0x11, 1); + /* virtualization flags */ build_append_int_noprefix(table_data, - (48UL << 30) | /* HATS */ - (48UL << 28) | /* GATS */ - (1UL << 2), /* GTSup */ - 4); - /* - * Type 1 device entry reporting all devices - * These are 4-byte device entries currently reporting the range of - * Refer to Spec - Table 95:IVHD Device Entry Type Codes(4-byte) - */ - build_append_int_noprefix(table_data, 0x0000001, 4); + (1UL << 0) | /* HtTunEn */ + (1UL << 4), /* iotblSup */ + 1); - build_header(linker, table_data, (void *)(table_data->data + iommu_start), - "IVRS", table_data->len - iommu_start, 1, NULL, NULL); -} + /* IVHD length */ + 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", + &error_abort), 2); + /* Capability offset */ + build_append_int_noprefix(table_data, s->pci.capab_offset, 2); + /* IOMMU base address */ + build_append_int_noprefix(table_data, s->mmio.addr, 8); + /* PCI Segment Group */ + build_append_int_noprefix(table_data, 0, 2); + /* IOMMU info */ + build_append_int_noprefix(table_data, 0, 2); + /* IOMMU Attributes */ + build_append_int_noprefix(table_data, 0, 4); + /* EFR Register Image */ + build_append_int_noprefix(table_data, + amdvi_extended_feature_register(s), + 8); + /* EFR Register Image 2 */ + build_append_int_noprefix(table_data, 0, 8); -static GArray * -build_rsdp(GArray *rsdp_table, BIOSLinker *linker, unsigned rsdt_tbl_offset) -{ - AcpiRsdpDescriptor *rsdp = acpi_data_push(rsdp_table, sizeof *rsdp); - unsigned rsdt_pa_size = sizeof(rsdp->rsdt_physical_address); - unsigned rsdt_pa_offset = - (char *)&rsdp->rsdt_physical_address - rsdp_table->data; - - bios_linker_loader_alloc(linker, ACPI_BUILD_RSDP_FILE, rsdp_table, 16, - true /* fseg memory */); - - memcpy(&rsdp->signature, "RSD PTR ", 8); - memcpy(rsdp->oem_id, ACPI_BUILD_APPNAME6, 6); - /* Address to be filled by Guest linker */ - bios_linker_loader_add_pointer(linker, - ACPI_BUILD_RSDP_FILE, rsdt_pa_offset, rsdt_pa_size, - ACPI_BUILD_TABLE_FILE, rsdt_tbl_offset); - - /* Checksum to be filled by Guest linker */ - bios_linker_loader_add_checksum(linker, ACPI_BUILD_RSDP_FILE, - (char *)rsdp - rsdp_table->data, sizeof *rsdp, - (char *)&rsdp->checksum - rsdp_table->data); - - return rsdp_table; + /* IVHD entries as found above */ + g_array_append_vals(table_data, ivhd_blob->data, ivhd_blob->len); + + g_array_free(ivhd_blob, TRUE); + acpi_table_end(linker, &table); } typedef @@ -2563,18 +2470,23 @@ static bool acpi_get_mcfg(AcpiMcfgInfo *mcfg) QObject *o; pci_host = acpi_get_i386_pci_host(); - g_assert(pci_host); + if (!pci_host) { + return false; + } o = object_property_get_qobject(pci_host, PCIE_HOST_MCFG_BASE, NULL); if (!o) { return false; } - mcfg->mcfg_base = qnum_get_uint(qobject_to(QNum, o)); + mcfg->base = qnum_get_uint(qobject_to(QNum, o)); qobject_unref(o); + if (mcfg->base == PCIE_BASE_ADDR_UNMAPPED) { + return false; + } o = object_property_get_qobject(pci_host, PCIE_HOST_MCFG_SIZE, NULL); assert(o); - mcfg->mcfg_size = qnum_get_uint(qobject_to(QNum, o)); + mcfg->size = qnum_get_uint(qobject_to(QNum, o)); qobject_unref(o); return true; } @@ -2584,23 +2496,39 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) { PCMachineState *pcms = PC_MACHINE(machine); PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms); + X86MachineState *x86ms = X86_MACHINE(machine); + DeviceState *iommu = pcms->iommu; GArray *table_offsets; unsigned facs, dsdt, rsdt, fadt; AcpiPmInfo pm; AcpiMiscInfo misc; AcpiMcfgInfo mcfg; - Range pci_hole, pci_hole64; + Range pci_hole = {}, pci_hole64 = {}; uint8_t *u; size_t aml_len = 0; GArray *tables_blob = tables->table_data; AcpiSlicOem slic_oem = { .id = NULL, .table_id = NULL }; Object *vmgenid_dev; + char *oem_id; + char *oem_table_id; - acpi_get_pm_info(&pm); + acpi_get_pm_info(machine, &pm); acpi_get_misc_info(&misc); acpi_get_pci_holes(&pci_hole, &pci_hole64); acpi_get_slic_oem(&slic_oem); + if (slic_oem.id) { + oem_id = slic_oem.id; + } else { + oem_id = x86ms->oem_id; + } + + if (slic_oem.table_id) { + oem_table_id = slic_oem.table_id; + } else { + oem_table_id = x86ms->oem_table_id; + } + table_offsets = g_array_new(false, true /* clear */, sizeof(uint32_t)); ACPI_BUILD_DPRINTF("init ACPI tables\n"); @@ -2616,7 +2544,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) * requirements. */ facs = tables_blob->len; - build_facs(tables_blob, tables->linker); + build_facs(tables_blob); /* DSDT is pointed to by FADT */ dsdt = tables_blob->len; @@ -2634,60 +2562,97 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) pm.fadt.facs_tbl_offset = &facs; pm.fadt.dsdt_tbl_offset = &dsdt; pm.fadt.xdsdt_tbl_offset = &dsdt; - build_fadt(tables_blob, tables->linker, &pm.fadt, - slic_oem.id, slic_oem.table_id); + build_fadt(tables_blob, tables->linker, &pm.fadt, oem_id, oem_table_id); aml_len += tables_blob->len - fadt; acpi_add_table(table_offsets, tables_blob); - build_madt(tables_blob, tables->linker, pcms); + acpi_build_madt(tables_blob, tables->linker, x86ms, + x86ms->oem_id, x86ms->oem_table_id); + +#ifdef CONFIG_ACPI_ERST + { + Object *erst_dev; + erst_dev = find_erst_dev(); + if (erst_dev) { + acpi_add_table(table_offsets, tables_blob); + build_erst(tables_blob, tables->linker, erst_dev, + x86ms->oem_id, x86ms->oem_table_id); + } + } +#endif vmgenid_dev = find_vmgenid_dev(); if (vmgenid_dev) { acpi_add_table(table_offsets, tables_blob); vmgenid_build_acpi(VMGENID(vmgenid_dev), tables_blob, - tables->vmgenid, tables->linker); + tables->vmgenid, tables->linker, x86ms->oem_id); } if (misc.has_hpet) { acpi_add_table(table_offsets, tables_blob); - build_hpet(tables_blob, tables->linker); + build_hpet(tables_blob, tables->linker, x86ms->oem_id, + x86ms->oem_table_id); } +#ifdef CONFIG_TPM if (misc.tpm_version != TPM_VERSION_UNSPEC) { - acpi_add_table(table_offsets, tables_blob); - build_tpm_tcpa(tables_blob, tables->linker, tables->tcpalog); - - if (misc.tpm_version == TPM_VERSION_2_0) { + if (misc.tpm_version == TPM_VERSION_1_2) { acpi_add_table(table_offsets, tables_blob); - build_tpm2(tables_blob, tables->linker, tables->tcpalog); + build_tpm_tcpa(tables_blob, tables->linker, tables->tcpalog, + x86ms->oem_id, x86ms->oem_table_id); + } else { /* TPM_VERSION_2_0 */ + acpi_add_table(table_offsets, tables_blob); + build_tpm2(tables_blob, tables->linker, tables->tcpalog, + x86ms->oem_id, x86ms->oem_table_id); } } - if (pcms->numa_nodes) { +#endif + if (machine->numa_state->num_nodes) { acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, machine); - if (have_numa_distance) { + if (machine->numa_state->have_numa_distance) { + acpi_add_table(table_offsets, tables_blob); + build_slit(tables_blob, tables->linker, machine, x86ms->oem_id, + x86ms->oem_table_id); + } + if (machine->numa_state->hmat_enabled) { acpi_add_table(table_offsets, tables_blob); - build_slit(tables_blob, tables->linker); + build_hmat(tables_blob, tables->linker, machine->numa_state, + x86ms->oem_id, x86ms->oem_table_id); } } if (acpi_get_mcfg(&mcfg)) { acpi_add_table(table_offsets, tables_blob); - build_mcfg_q35(tables_blob, tables->linker, &mcfg); + build_mcfg(tables_blob, tables->linker, &mcfg, x86ms->oem_id, + x86ms->oem_table_id); } - if (x86_iommu_get_default()) { - IommuType IOMMUType = x86_iommu_get_type(); - if (IOMMUType == TYPE_AMD) { - acpi_add_table(table_offsets, tables_blob); - build_amd_iommu(tables_blob, tables->linker); - } else if (IOMMUType == TYPE_INTEL) { - acpi_add_table(table_offsets, tables_blob); - build_dmar_q35(tables_blob, tables->linker); - } + if (object_dynamic_cast(OBJECT(iommu), TYPE_AMD_IOMMU_DEVICE)) { + acpi_add_table(table_offsets, tables_blob); + build_amd_iommu(tables_blob, tables->linker, x86ms->oem_id, + x86ms->oem_table_id); + } else if (object_dynamic_cast(OBJECT(iommu), TYPE_INTEL_IOMMU_DEVICE)) { + acpi_add_table(table_offsets, tables_blob); + build_dmar_q35(tables_blob, tables->linker, x86ms->oem_id, + x86ms->oem_table_id); + } else if (object_dynamic_cast(OBJECT(iommu), TYPE_VIRTIO_IOMMU_PCI)) { + PCIDevice *pdev = PCI_DEVICE(iommu); + + acpi_add_table(table_offsets, tables_blob); + build_viot(machine, tables_blob, tables->linker, pci_get_bdf(pdev), + x86ms->oem_id, x86ms->oem_table_id); } - if (pcms->acpi_nvdimm_state.is_enabled) { + if (machine->nvdimms_state->is_enabled) { nvdimm_build_acpi(table_offsets, tables_blob, tables->linker, - &pcms->acpi_nvdimm_state, machine->ram_slots); + machine->nvdimms_state, machine->ram_slots, + x86ms->oem_id, x86ms->oem_table_id); + } + if (pcms->cxl_devices_state.is_enabled) { + cxl_build_cedt(table_offsets, tables_blob, tables->linker, + x86ms->oem_id, x86ms->oem_table_id, &pcms->cxl_devices_state); } + acpi_add_table(table_offsets, tables_blob); + build_waet(tables_blob, tables->linker, x86ms->oem_id, x86ms->oem_table_id); + /* Add tables supplied by user (if any) */ for (u = acpi_table_first(); u; u = acpi_table_next(u)) { unsigned len = acpi_table_len(u); @@ -2699,10 +2664,28 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) /* RSDT is pointed to by RSDP */ rsdt = tables_blob->len; build_rsdt(tables_blob, tables->linker, table_offsets, - slic_oem.id, slic_oem.table_id); + oem_id, oem_table_id); /* RSDP is in FSEG memory, so allocate it separately */ - build_rsdp(tables->rsdp, tables->linker, rsdt); + { + AcpiRsdpData rsdp_data = { + .revision = 0, + .oem_id = x86ms->oem_id, + .xsdt_tbl_offset = NULL, + .rsdt_tbl_offset = &rsdt, + }; + build_rsdp(tables->rsdp, tables->linker, &rsdp_data); + if (!pcmc->rsdp_in_ram) { + /* We used to allocate some extra space for RSDP revision 2 but + * only used the RSDP revision 0 space. The extra bytes were + * zeroed out and not used. + * Here we continue wasting those extra 16 bytes to make sure we + * don't break migration for machine types 2.2 and older due to + * RSDP blob size mismatch. + */ + build_append_int_noprefix(tables->rsdp, 0, 16); + } + } /* We'll expose it all to Guest so we want to reduce * chance of size changes. @@ -2727,28 +2710,30 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) */ int legacy_aml_len = pcmc->legacy_acpi_table_size + - ACPI_BUILD_LEGACY_CPU_AML_SIZE * pcms->apic_id_limit; + ACPI_BUILD_LEGACY_CPU_AML_SIZE * x86ms->apic_id_limit; int legacy_table_size = ROUND_UP(tables_blob->len - aml_len + legacy_aml_len, ACPI_BUILD_ALIGN_SIZE); - if (tables_blob->len > legacy_table_size) { + if ((tables_blob->len > legacy_table_size) && + !pcmc->resizable_acpi_blob) { /* Should happen only with PCI bridges and -M pc-i440fx-2.0. */ warn_report("ACPI table size %u exceeds %d bytes," " migration may not work", tables_blob->len, legacy_table_size); error_printf("Try removing CPUs, NUMA nodes, memory slots" - " or PCI bridges."); + " or PCI bridges.\n"); } g_array_set_size(tables_blob, legacy_table_size); } else { /* Make sure we have a buffer in case we need to resize the tables. */ - if (tables_blob->len > ACPI_BUILD_TABLE_SIZE / 2) { + if ((tables_blob->len > ACPI_BUILD_TABLE_SIZE / 2) && + !pcmc->resizable_acpi_blob) { /* As of QEMU 2.1, this fires with 160 VCPUs and 255 memory slots. */ warn_report("ACPI table size %u exceeds %d bytes," " migration may not work", tables_blob->len, ACPI_BUILD_TABLE_SIZE / 2); error_printf("Try removing CPUs, NUMA nodes, memory slots" - " or PCI bridges."); + " or PCI bridges.\n"); } acpi_align_size(tables_blob, ACPI_BUILD_TABLE_SIZE); } @@ -2757,6 +2742,8 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) /* Cleanup memory that's no longer used. */ g_array_free(table_offsets, true); + g_free(slic_oem.id); + g_free(slic_oem.table_id); } static void acpi_ram_update(MemoryRegion *mr, GArray *data) @@ -2803,19 +2790,11 @@ static void acpi_build_reset(void *build_opaque) build_state->patched = 0; } -static MemoryRegion *acpi_add_rom_blob(AcpiBuildState *build_state, - GArray *blob, const char *name, - uint64_t max_size) -{ - return rom_add_blob(name, blob->data, acpi_data_len(blob), max_size, -1, - name, acpi_build_update, build_state, NULL, true); -} - static const VMStateDescription vmstate_acpi_build = { .name = "acpi_build", .version_id = 1, .minimum_version_id = 1, - .fields = (VMStateField[]) { + .fields = (const VMStateField[]) { VMSTATE_UINT8(patched, AcpiBuildState), VMSTATE_END_OF_LIST() }, @@ -2825,11 +2804,16 @@ void acpi_setup(void) { PCMachineState *pcms = PC_MACHINE(qdev_get_machine()); PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms); + X86MachineState *x86ms = X86_MACHINE(pcms); AcpiBuildTables tables; AcpiBuildState *build_state; Object *vmgenid_dev; +#ifdef CONFIG_TPM + TPMIf *tpm; + static FwCfgTPMConfig tpm_config; +#endif - if (!pcms->fw_cfg) { + if (!x86ms->fw_cfg) { ACPI_BUILD_DPRINTF("No fw cfg. Bailing out.\n"); return; } @@ -2839,7 +2823,7 @@ void acpi_setup(void) return; } - if (!acpi_enabled) { + if (!x86_machine_is_acpi_enabled(X86_MACHINE(pcms))) { ACPI_BUILD_DPRINTF("ACPI disabled. Bailing out.\n"); return; } @@ -2850,21 +2834,34 @@ void acpi_setup(void) acpi_build(&tables, MACHINE(pcms)); /* Now expose it all to Guest */ - build_state->table_mr = acpi_add_rom_blob(build_state, tables.table_data, - ACPI_BUILD_TABLE_FILE, - ACPI_BUILD_TABLE_MAX_SIZE); + build_state->table_mr = acpi_add_rom_blob(acpi_build_update, + build_state, tables.table_data, + ACPI_BUILD_TABLE_FILE); assert(build_state->table_mr != NULL); build_state->linker_mr = - acpi_add_rom_blob(build_state, tables.linker->cmd_blob, - "etc/table-loader", 0); + acpi_add_rom_blob(acpi_build_update, build_state, + tables.linker->cmd_blob, ACPI_BUILD_LOADER_FILE); - fw_cfg_add_file(pcms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, +#ifdef CONFIG_TPM + fw_cfg_add_file(x86ms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, acpi_data_len(tables.tcpalog)); + tpm = tpm_find(); + if (tpm && object_property_get_bool(OBJECT(tpm), "ppi", &error_abort)) { + tpm_config = (FwCfgTPMConfig) { + .tpmppi_address = cpu_to_le32(TPM_PPI_ADDR_BASE), + .tpm_version = tpm_get_version(tpm), + .tpmppi_version = TPM_PPI_VERSION_1_30 + }; + fw_cfg_add_file(x86ms->fw_cfg, "etc/tpm/config", + &tpm_config, sizeof tpm_config); + } +#endif + vmgenid_dev = find_vmgenid_dev(); if (vmgenid_dev) { - vmgenid_add_fw_cfg(VMGENID(vmgenid_dev), pcms->fw_cfg, + vmgenid_add_fw_cfg(VMGENID(vmgenid_dev), x86ms->fw_cfg, tables.vmgenid); } @@ -2877,14 +2874,15 @@ void acpi_setup(void) uint32_t rsdp_size = acpi_data_len(tables.rsdp); build_state->rsdp = g_memdup(tables.rsdp->data, rsdp_size); - fw_cfg_add_file_callback(pcms->fw_cfg, ACPI_BUILD_RSDP_FILE, + fw_cfg_add_file_callback(x86ms->fw_cfg, ACPI_BUILD_RSDP_FILE, acpi_build_update, NULL, build_state, build_state->rsdp, rsdp_size, true); build_state->rsdp_mr = NULL; } else { build_state->rsdp = NULL; - build_state->rsdp_mr = acpi_add_rom_blob(build_state, tables.rsdp, - ACPI_BUILD_RSDP_FILE, 0); + build_state->rsdp_mr = acpi_add_rom_blob(acpi_build_update, + build_state, tables.rsdp, + ACPI_BUILD_RSDP_FILE); } qemu_register_reset(acpi_build_reset, build_state); |