diff options
Diffstat (limited to 'hw')
39 files changed, 1280 insertions, 1168 deletions
diff --git a/hw/9pfs/xen-9p-backend.c b/hw/9pfs/xen-9p-backend.c index 4aa9c8c736..a3ac53f989 100644 --- a/hw/9pfs/xen-9p-backend.c +++ b/hw/9pfs/xen-9p-backend.c @@ -513,7 +513,7 @@ static void xen_9pfs_alloc(struct XenLegacyDevice *xendev) xenstore_write_be_int(xendev, "max-ring-page-order", MAX_RING_ORDER); } -struct XenDevOps xen_9pfs_ops = { +static struct XenDevOps xen_9pfs_ops = { .size = sizeof(Xen9pfsDev), .flags = DEVOPS_FLAG_NEED_GNTDEV, .alloc = xen_9pfs_alloc, @@ -522,3 +522,9 @@ struct XenDevOps xen_9pfs_ops = { .disconnect = xen_9pfs_disconnect, .free = xen_9pfs_free, }; + +static void xen_9pfs_register_backend(void) +{ + xen_be_register("9pfs", &xen_9pfs_ops); +} +xen_backend_init(xen_9pfs_register_backend); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index 98c264ed21..8b97683a45 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -15,6 +15,7 @@ config ARM_VIRT select ACPI select ARM_SMMUV3 select GPIO_KEY + select DEVICE_TREE select FW_CFG_DMA select PCI_EXPRESS select PCI_EXPRESS_GENERIC_BRIDGE @@ -265,6 +266,7 @@ config SBSA_REF default y depends on TCG && AARCH64 imply PCI_DEVICES + select DEVICE_TREE select AHCI select ARM_SMMUV3 select GPIO_KEY @@ -347,6 +349,7 @@ config VEXPRESS bool default y depends on TCG && ARM + select DEVICE_TREE select A9MPCORE select A15MPCORE select ARM_MPTIMER @@ -492,6 +495,7 @@ config XLNX_ZYNQMP_ARM select CPU_CLUSTER select DDC select DPCD + select DEVICE_TREE select SDHCI select SSI select SSI_M25P80 @@ -509,6 +513,7 @@ config XLNX_VERSAL depends on TCG && AARCH64 select ARM_GIC select CPU_CLUSTER + select DEVICE_TREE select PL011 select CADENCE select VIRTIO_MMIO diff --git a/hw/arm/meson.build b/hw/arm/meson.build index 6808135c1f..aefde0c69a 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -1,5 +1,5 @@ arm_ss = ss.source_set() -arm_ss.add(files('boot.c'), fdt) +arm_ss.add(files('boot.c')) arm_ss.add(when: 'CONFIG_ARM_VIRT', if_true: files('virt.c')) arm_ss.add(when: 'CONFIG_ACPI', if_true: files('virt-acpi-build.c')) arm_ss.add(when: 'CONFIG_DIGIC', if_true: files('digic_boards.c')) diff --git a/hw/core/Kconfig b/hw/core/Kconfig index 9397503656..24411f5930 100644 --- a/hw/core/Kconfig +++ b/hw/core/Kconfig @@ -4,8 +4,14 @@ config EMPTY_SLOT config PTIMER bool +config DEVICE_TREE + bool + # fail the build if libfdt not found + depends on FDT + config FITLOADER bool + depends on DEVICE_TREE config GENERIC_LOADER bool @@ -14,13 +20,14 @@ config GENERIC_LOADER config GUEST_LOADER bool default y - depends on TCG + depends on TCG && DEVICE_TREE config OR_IRQ bool config PLATFORM_BUS bool + depends on DEVICE_TREE config REGISTER bool diff --git a/hw/core/meson.build b/hw/core/meson.build index f20d4143f7..a3d9bab9f4 100644 --- a/hw/core/meson.build +++ b/hw/core/meson.build @@ -16,7 +16,7 @@ common_ss.add(files('cpu-common.c')) common_ss.add(files('machine-smp.c')) system_ss.add(when: 'CONFIG_FITLOADER', if_true: files('loader-fit.c')) system_ss.add(when: 'CONFIG_GENERIC_LOADER', if_true: files('generic-loader.c')) -system_ss.add(when: ['CONFIG_GUEST_LOADER', fdt], if_true: files('guest-loader.c')) +system_ss.add(when: 'CONFIG_GUEST_LOADER', if_true: files('guest-loader.c')) system_ss.add(when: 'CONFIG_OR_IRQ', if_true: files('or-irq.c')) system_ss.add(when: 'CONFIG_PLATFORM_BUS', if_true: files('platform-bus.c')) system_ss.add(when: 'CONFIG_PTIMER', if_true: files('ptimer.c')) diff --git a/hw/display/xenfb.c b/hw/display/xenfb.c index b2130a0d70..27536bfce0 100644 --- a/hw/display/xenfb.c +++ b/hw/display/xenfb.c @@ -972,7 +972,7 @@ static void fb_event(struct XenLegacyDevice *xendev) /* -------------------------------------------------------------------- */ -struct XenDevOps xen_kbdmouse_ops = { +static struct XenDevOps xen_kbdmouse_ops = { .size = sizeof(struct XenInput), .init = input_init, .initialise = input_initialise, @@ -995,3 +995,9 @@ static const GraphicHwOps xenfb_ops = { .gfx_update = xenfb_update, .ui_info = xenfb_ui_info, }; + +static void xen_vkbd_register_backend(void) +{ + xen_be_register("vkbd", &xen_kbdmouse_ops); +} +xen_backend_init(xen_vkbd_register_backend); diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index 40b1e44580..f4a33b6c08 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -115,7 +115,8 @@ config Q35 config MICROVM bool default y - depends on I386 + depends on I386 && FDT + select DEVICE_TREE select SERIAL_ISA # for serial_hds_isa_init() select ISA_BUS select APIC diff --git a/hw/i386/fw_cfg.c b/hw/i386/fw_cfg.c index d802d2787f..6e0d9945d0 100644 --- a/hw/i386/fw_cfg.c +++ b/hw/i386/fw_cfg.c @@ -203,6 +203,7 @@ void fw_cfg_build_feature_control(MachineState *ms, FWCfgState *fw_cfg) fw_cfg_add_file(fw_cfg, "etc/msr_feature_control", val, sizeof(*val)); } +#ifdef CONFIG_ACPI void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg) { /* @@ -229,3 +230,4 @@ void fw_cfg_add_acpi_dsdt(Aml *scope, FWCfgState *fw_cfg) aml_append(dev, aml_name_decl("_CRS", crs)); aml_append(scope, dev); } +#endif diff --git a/hw/i386/meson.build b/hw/i386/meson.build index d8b70ef3e9..03aad10df7 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -1,18 +1,20 @@ i386_ss = ss.source_set() i386_ss.add(files( 'fw_cfg.c', - 'vapic.c', 'e820_memory_layout.c', + 'monitor.c', 'multiboot.c', 'x86.c', + 'x86-cpu.c', )) +i386_ss.add(when: 'CONFIG_APIC', if_true: files('vapic.c')) i386_ss.add(when: 'CONFIG_X86_IOMMU', if_true: files('x86-iommu.c'), if_false: files('x86-iommu-stub.c')) i386_ss.add(when: 'CONFIG_AMD_IOMMU', if_true: files('amd_iommu.c'), if_false: files('amd_iommu-stub.c')) i386_ss.add(when: 'CONFIG_I440FX', if_true: files('pc_piix.c')) -i386_ss.add(when: 'CONFIG_MICROVM', if_true: files('microvm.c', 'acpi-microvm.c', 'microvm-dt.c')) +i386_ss.add(when: 'CONFIG_MICROVM', if_true: files('x86-common.c', 'microvm.c', 'acpi-microvm.c', 'microvm-dt.c')) i386_ss.add(when: 'CONFIG_Q35', if_true: files('pc_q35.c')) i386_ss.add(when: 'CONFIG_VMMOUSE', if_true: files('vmmouse.c')) i386_ss.add(when: 'CONFIG_VMPORT', if_true: files('vmport.c')) @@ -22,6 +24,7 @@ i386_ss.add(when: 'CONFIG_SGX', if_true: files('sgx-epc.c','sgx.c'), i386_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-common.c')) i386_ss.add(when: 'CONFIG_PC', if_true: files( + 'x86-common.c', 'pc.c', 'pc_sysfw.c', 'acpi-build.c', diff --git a/hw/i386/monitor.c b/hw/i386/monitor.c new file mode 100644 index 0000000000..1ebd3564bf --- /dev/null +++ b/hw/i386/monitor.c @@ -0,0 +1,46 @@ +/* + * QEMU monitor + * + * Copyright (c) 2003-2004 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "monitor/monitor.h" +#include "qapi/qmp/qdict.h" +#include "qapi/error.h" +#include "qapi/qapi-commands-misc-target.h" +#include "hw/i386/x86.h" +#include "hw/rtc/mc146818rtc.h" + +#include CONFIG_DEVICES + +void qmp_rtc_reset_reinjection(Error **errp) +{ + X86MachineState *x86ms = X86_MACHINE(qdev_get_machine()); + +#ifdef CONFIG_MC146818RTC + if (x86ms->rtc) { + rtc_reset_reinjection(MC146818_RTC(x86ms->rtc)); + } +#else + assert(!x86ms->rtc); +#endif +} diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 505ea750f4..bfb46e9b54 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -1250,7 +1250,6 @@ void pc_basic_device_init(struct PCMachineState *pcms, pci_create_simple(pcms->pcibus, -1, "xen-platform"); } xen_bus_init(); - xen_be_init(); } #endif @@ -1827,9 +1826,6 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) assert(!mc->get_hotplug_handler); mc->get_hotplug_handler = pc_get_hotplug_handler; mc->hotplug_allowed = pc_hotplug_allowed; - mc->cpu_index_to_instance_props = x86_cpu_index_to_props; - mc->get_default_cpu_node_id = x86_get_default_cpu_node_id; - mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids; mc->auto_enable_numa_with_memhp = true; mc->auto_enable_numa_with_memdev = true; mc->has_hotpluggable_cpus = true; diff --git a/hw/i386/x86-common.c b/hw/i386/x86-common.c new file mode 100644 index 0000000000..67b03c913a --- /dev/null +++ b/hw/i386/x86-common.c @@ -0,0 +1,1007 @@ +/* + * Copyright (c) 2003-2004 Fabrice Bellard + * Copyright (c) 2019, 2024 Red Hat, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qemu/cutils.h" +#include "qemu/units.h" +#include "qemu/datadir.h" +#include "qapi/error.h" +#include "sysemu/numa.h" +#include "sysemu/sysemu.h" +#include "sysemu/xen.h" +#include "trace.h" + +#include "hw/i386/x86.h" +#include "target/i386/cpu.h" +#include "hw/rtc/mc146818rtc.h" +#include "target/i386/sev.h" + +#include "hw/acpi/cpu_hotplug.h" +#include "hw/irq.h" +#include "hw/loader.h" +#include "multiboot.h" +#include "elf.h" +#include "standard-headers/asm-x86/bootparam.h" +#include CONFIG_DEVICES +#include "kvm/kvm_i386.h" + +#ifdef CONFIG_XEN_EMU +#include "hw/xen/xen.h" +#include "hw/i386/kvm/xen_evtchn.h" +#endif + +/* Physical Address of PVH entry point read from kernel ELF NOTE */ +static size_t pvh_start_addr; + +static void x86_cpu_new(X86MachineState *x86ms, int64_t apic_id, Error **errp) +{ + Object *cpu = object_new(MACHINE(x86ms)->cpu_type); + + if (!object_property_set_uint(cpu, "apic-id", apic_id, errp)) { + goto out; + } + qdev_realize(DEVICE(cpu), NULL, errp); + +out: + object_unref(cpu); +} + +void x86_cpus_init(X86MachineState *x86ms, int default_cpu_version) +{ + int i; + const CPUArchIdList *possible_cpus; + MachineState *ms = MACHINE(x86ms); + MachineClass *mc = MACHINE_GET_CLASS(x86ms); + + x86_cpu_set_default_version(default_cpu_version); + + /* + * Calculates the limit to CPU APIC ID values + * + * Limit for the APIC ID value, so that all + * CPU APIC IDs are < x86ms->apic_id_limit. + * + * This is used for FW_CFG_MAX_CPUS. See comments on fw_cfg_arch_create(). + */ + x86ms->apic_id_limit = x86_cpu_apic_id_from_index(x86ms, + ms->smp.max_cpus - 1) + 1; + + /* + * Can we support APIC ID 255 or higher? With KVM, that requires + * both in-kernel lapic and X2APIC userspace API. + * + * kvm_enabled() must go first to ensure that kvm_* references are + * not emitted for the linker to consume (kvm_enabled() is + * a literal `0` in configurations where kvm_* aren't defined) + */ + if (kvm_enabled() && x86ms->apic_id_limit > 255 && + kvm_irqchip_in_kernel() && !kvm_enable_x2apic()) { + error_report("current -smp configuration requires kernel " + "irqchip and X2APIC API support."); + exit(EXIT_FAILURE); + } + + if (kvm_enabled()) { + kvm_set_max_apic_id(x86ms->apic_id_limit); + } + + if (!kvm_irqchip_in_kernel()) { + apic_set_max_apic_id(x86ms->apic_id_limit); + } + + possible_cpus = mc->possible_cpu_arch_ids(ms); + for (i = 0; i < ms->smp.cpus; i++) { + x86_cpu_new(x86ms, possible_cpus->cpus[i].arch_id, &error_fatal); + } +} + +void x86_rtc_set_cpus_count(ISADevice *s, uint16_t cpus_count) +{ + MC146818RtcState *rtc = MC146818_RTC(s); + + if (cpus_count > 0xff) { + /* + * If the number of CPUs can't be represented in 8 bits, the + * BIOS must use "FW_CFG_NB_CPUS". Set RTC field to 0 just + * to make old BIOSes fail more predictably. + */ + mc146818rtc_set_cmos_data(rtc, 0x5f, 0); + } else { + mc146818rtc_set_cmos_data(rtc, 0x5f, cpus_count - 1); + } +} + +static int x86_apic_cmp(const void *a, const void *b) +{ + CPUArchId *apic_a = (CPUArchId *)a; + CPUArchId *apic_b = (CPUArchId *)b; + + return apic_a->arch_id - apic_b->arch_id; +} + +/* + * returns pointer to CPUArchId descriptor that matches CPU's apic_id + * in ms->possible_cpus->cpus, if ms->possible_cpus->cpus has no + * entry corresponding to CPU's apic_id returns NULL. + */ +static CPUArchId *x86_find_cpu_slot(MachineState *ms, uint32_t id, int *idx) +{ + CPUArchId apic_id, *found_cpu; + + apic_id.arch_id = id; + found_cpu = bsearch(&apic_id, ms->possible_cpus->cpus, + ms->possible_cpus->len, sizeof(*ms->possible_cpus->cpus), + x86_apic_cmp); + if (found_cpu && idx) { + *idx = found_cpu - ms->possible_cpus->cpus; + } + return found_cpu; +} + +void x86_cpu_plug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + CPUArchId *found_cpu; + Error *local_err = NULL; + X86CPU *cpu = X86_CPU(dev); + X86MachineState *x86ms = X86_MACHINE(hotplug_dev); + + if (x86ms->acpi_dev) { + hotplug_handler_plug(x86ms->acpi_dev, dev, &local_err); + if (local_err) { + goto out; + } + } + + /* increment the number of CPUs */ + x86ms->boot_cpus++; + if (x86ms->rtc) { + x86_rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); + } + if (x86ms->fw_cfg) { + fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus); + } + + found_cpu = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, NULL); + found_cpu->cpu = CPU(dev); +out: + error_propagate(errp, local_err); +} + +void x86_cpu_unplug_request_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + int idx = -1; + X86CPU *cpu = X86_CPU(dev); + X86MachineState *x86ms = X86_MACHINE(hotplug_dev); + + if (!x86ms->acpi_dev) { + error_setg(errp, "CPU hot unplug not supported without ACPI"); + return; + } + + x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, &idx); + assert(idx != -1); + if (idx == 0) { + error_setg(errp, "Boot CPU is unpluggable"); + return; + } + + hotplug_handler_unplug_request(x86ms->acpi_dev, dev, + errp); +} + +void x86_cpu_unplug_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + CPUArchId *found_cpu; + Error *local_err = NULL; + X86CPU *cpu = X86_CPU(dev); + X86MachineState *x86ms = X86_MACHINE(hotplug_dev); + + hotplug_handler_unplug(x86ms->acpi_dev, dev, &local_err); + if (local_err) { + goto out; + } + + found_cpu = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, NULL); + found_cpu->cpu = NULL; + qdev_unrealize(dev); + + /* decrement the number of CPUs */ + x86ms->boot_cpus--; + /* Update the number of CPUs in CMOS */ + x86_rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); + fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus); + out: + error_propagate(errp, local_err); +} + +void x86_cpu_pre_plug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + int idx; + CPUState *cs; + CPUArchId *cpu_slot; + X86CPUTopoIDs topo_ids; + X86CPU *cpu = X86_CPU(dev); + CPUX86State *env = &cpu->env; + MachineState *ms = MACHINE(hotplug_dev); + X86MachineState *x86ms = X86_MACHINE(hotplug_dev); + unsigned int smp_cores = ms->smp.cores; + unsigned int smp_threads = ms->smp.threads; + X86CPUTopoInfo topo_info; + + if (!object_dynamic_cast(OBJECT(cpu), ms->cpu_type)) { + error_setg(errp, "Invalid CPU type, expected cpu type: '%s'", + ms->cpu_type); + return; + } + + if (x86ms->acpi_dev) { + Error *local_err = NULL; + + hotplug_handler_pre_plug(HOTPLUG_HANDLER(x86ms->acpi_dev), dev, + &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + } + + init_topo_info(&topo_info, x86ms); + + env->nr_dies = ms->smp.dies; + + /* + * If APIC ID is not set, + * set it based on socket/die/core/thread properties. + */ + if (cpu->apic_id == UNASSIGNED_APIC_ID) { + int max_socket = (ms->smp.max_cpus - 1) / + smp_threads / smp_cores / ms->smp.dies; + + /* + * die-id was optional in QEMU 4.0 and older, so keep it optional + * if there's only one die per socket. + */ + if (cpu->die_id < 0 && ms->smp.dies == 1) { + cpu->die_id = 0; + } + + if (cpu->socket_id < 0) { + error_setg(errp, "CPU socket-id is not set"); + return; + } else if (cpu->socket_id > max_socket) { + error_setg(errp, "Invalid CPU socket-id: %u must be in range 0:%u", + cpu->socket_id, max_socket); + return; + } + if (cpu->die_id < 0) { + error_setg(errp, "CPU die-id is not set"); + return; + } else if (cpu->die_id > ms->smp.dies - 1) { + error_setg(errp, "Invalid CPU die-id: %u must be in range 0:%u", + cpu->die_id, ms->smp.dies - 1); + return; + } + if (cpu->core_id < 0) { + error_setg(errp, "CPU core-id is not set"); + return; + } else if (cpu->core_id > (smp_cores - 1)) { + error_setg(errp, "Invalid CPU core-id: %u must be in range 0:%u", + cpu->core_id, smp_cores - 1); + return; + } + if (cpu->thread_id < 0) { + error_setg(errp, "CPU thread-id is not set"); + return; + } else if (cpu->thread_id > (smp_threads - 1)) { + error_setg(errp, "Invalid CPU thread-id: %u must be in range 0:%u", + cpu->thread_id, smp_threads - 1); + return; + } + + topo_ids.pkg_id = cpu->socket_id; + topo_ids.die_id = cpu->die_id; + topo_ids.core_id = cpu->core_id; + topo_ids.smt_id = cpu->thread_id; + cpu->apic_id = x86_apicid_from_topo_ids(&topo_info, &topo_ids); + } + + cpu_slot = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, &idx); + if (!cpu_slot) { + x86_topo_ids_from_apicid(cpu->apic_id, &topo_info, &topo_ids); + error_setg(errp, + "Invalid CPU [socket: %u, die: %u, core: %u, thread: %u] with" + " APIC ID %" PRIu32 ", valid index range 0:%d", + topo_ids.pkg_id, topo_ids.die_id, topo_ids.core_id, topo_ids.smt_id, + cpu->apic_id, ms->possible_cpus->len - 1); + return; + } + + if (cpu_slot->cpu) { + error_setg(errp, "CPU[%d] with APIC ID %" PRIu32 " exists", + idx, cpu->apic_id); + return; + } + + /* if 'address' properties socket-id/core-id/thread-id are not set, set them + * so that machine_query_hotpluggable_cpus would show correct values + */ + /* TODO: move socket_id/core_id/thread_id checks into x86_cpu_realizefn() + * once -smp refactoring is complete and there will be CPU private + * CPUState::nr_cores and CPUState::nr_threads fields instead of globals */ + x86_topo_ids_from_apicid(cpu->apic_id, &topo_info, &topo_ids); + if (cpu->socket_id != -1 && cpu->socket_id != topo_ids.pkg_id) { + error_setg(errp, "property socket-id: %u doesn't match set apic-id:" + " 0x%x (socket-id: %u)", cpu->socket_id, cpu->apic_id, + topo_ids.pkg_id); + return; + } + cpu->socket_id = topo_ids.pkg_id; + + if (cpu->die_id != -1 && cpu->die_id != topo_ids.die_id) { + error_setg(errp, "property die-id: %u doesn't match set apic-id:" + " 0x%x (die-id: %u)", cpu->die_id, cpu->apic_id, topo_ids.die_id); + return; + } + cpu->die_id = topo_ids.die_id; + + if (cpu->core_id != -1 && cpu->core_id != topo_ids.core_id) { + error_setg(errp, "property core-id: %u doesn't match set apic-id:" + " 0x%x (core-id: %u)", cpu->core_id, cpu->apic_id, + topo_ids.core_id); + return; + } + cpu->core_id = topo_ids.core_id; + + if (cpu->thread_id != -1 && cpu->thread_id != topo_ids.smt_id) { + error_setg(errp, "property thread-id: %u doesn't match set apic-id:" + " 0x%x (thread-id: %u)", cpu->thread_id, cpu->apic_id, + topo_ids.smt_id); + return; + } + cpu->thread_id = topo_ids.smt_id; + + /* + * kvm_enabled() must go first to ensure that kvm_* references are + * not emitted for the linker to consume (kvm_enabled() is + * a literal `0` in configurations where kvm_* aren't defined) + */ + if (kvm_enabled() && hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX) && + !kvm_hv_vpindex_settable()) { + error_setg(errp, "kernel doesn't allow setting HyperV VP_INDEX"); + return; + } + + cs = CPU(cpu); + cs->cpu_index = idx; + + numa_cpu_pre_plug(cpu_slot, dev, errp); +} + +static long get_file_size(FILE *f) +{ + long where, size; + + /* XXX: on Unix systems, using fstat() probably makes more sense */ + + where = ftell(f); + fseek(f, 0, SEEK_END); + size = ftell(f); + fseek(f, where, SEEK_SET); + + return size; +} + +void gsi_handler(void *opaque, int n, int level) +{ + GSIState *s = opaque; + + trace_x86_gsi_interrupt(n, level); + switch (n) { + case 0 ... ISA_NUM_IRQS - 1: + if (s->i8259_irq[n]) { + /* Under KVM, Kernel will forward to both PIC and IOAPIC */ + qemu_set_irq(s->i8259_irq[n], level); + } + /* fall through */ + case ISA_NUM_IRQS ... IOAPIC_NUM_PINS - 1: +#ifdef CONFIG_XEN_EMU + /* + * Xen delivers the GSI to the Legacy PIC (not that Legacy PIC + * routing actually works properly under Xen). And then to + * *either* the PIRQ handling or the I/OAPIC depending on + * whether the former wants it. + */ + if (xen_mode == XEN_EMULATE && xen_evtchn_set_gsi(n, level)) { + break; + } +#endif + qemu_set_irq(s->ioapic_irq[n], level); + break; + case IO_APIC_SECONDARY_IRQBASE + ... IO_APIC_SECONDARY_IRQBASE + IOAPIC_NUM_PINS - 1: + qemu_set_irq(s->ioapic2_irq[n - IO_APIC_SECONDARY_IRQBASE], level); + break; + } +} + +void ioapic_init_gsi(GSIState *gsi_state, Object *parent) +{ + DeviceState *dev; + SysBusDevice *d; + unsigned int i; + + assert(parent); + if (kvm_ioapic_in_kernel()) { + dev = qdev_new(TYPE_KVM_IOAPIC); + } else { + dev = qdev_new(TYPE_IOAPIC); + } + object_property_add_child(parent, "ioapic", OBJECT(dev)); + d = SYS_BUS_DEVICE(dev); + sysbus_realize_and_unref(d, &error_fatal); + sysbus_mmio_map(d, 0, IO_APIC_DEFAULT_ADDRESS); + + for (i = 0; i < IOAPIC_NUM_PINS; i++) { + gsi_state->ioapic_irq[i] = qdev_get_gpio_in(dev, i); + } +} + +DeviceState *ioapic_init_secondary(GSIState *gsi_state) +{ + DeviceState *dev; + SysBusDevice *d; + unsigned int i; + + dev = qdev_new(TYPE_IOAPIC); + d = SYS_BUS_DEVICE(dev); + sysbus_realize_and_unref(d, &error_fatal); + sysbus_mmio_map(d, 0, IO_APIC_SECONDARY_ADDRESS); + + for (i = 0; i < IOAPIC_NUM_PINS; i++) { + gsi_state->ioapic2_irq[i] = qdev_get_gpio_in(dev, i); + } + return dev; +} + +/* + * The entry point into the kernel for PVH boot is different from + * the native entry point. The PVH entry is defined by the x86/HVM + * direct boot ABI and is available in an ELFNOTE in the kernel binary. + * + * This function is passed to load_elf() when it is called from + * load_elfboot() which then additionally checks for an ELF Note of + * type XEN_ELFNOTE_PHYS32_ENTRY and passes it to this function to + * parse the PVH entry address from the ELF Note. + * + * Due to trickery in elf_opts.h, load_elf() is actually available as + * load_elf32() or load_elf64() and this routine needs to be able + * to deal with being called as 32 or 64 bit. + * + * The address of the PVH entry point is saved to the 'pvh_start_addr' + * global variable. (although the entry point is 32-bit, the kernel + * binary can be either 32-bit or 64-bit). + */ +static uint64_t read_pvh_start_addr(void *arg1, void *arg2, bool is64) +{ + size_t *elf_note_data_addr; + + /* Check if ELF Note header passed in is valid */ + if (arg1 == NULL) { + return 0; + } + + if (is64) { + struct elf64_note *nhdr64 = (struct elf64_note *)arg1; + uint64_t nhdr_size64 = sizeof(struct elf64_note); + uint64_t phdr_align = *(uint64_t *)arg2; + uint64_t nhdr_namesz = nhdr64->n_namesz; + + elf_note_data_addr = + ((void *)nhdr64) + nhdr_size64 + + QEMU_ALIGN_UP(nhdr_namesz, phdr_align); + + pvh_start_addr = *elf_note_data_addr; + } else { + struct elf32_note *nhdr32 = (struct elf32_note *)arg1; + uint32_t nhdr_size32 = sizeof(struct elf32_note); + uint32_t phdr_align = *(uint32_t *)arg2; + uint32_t nhdr_namesz = nhdr32->n_namesz; + + elf_note_data_addr = + ((void *)nhdr32) + nhdr_size32 + + QEMU_ALIGN_UP(nhdr_namesz, phdr_align); + + pvh_start_addr = *(uint32_t *)elf_note_data_addr; + } + + return pvh_start_addr; +} + +static bool load_elfboot(const char *kernel_filename, + int kernel_file_size, + uint8_t *header, + size_t pvh_xen_start_addr, + FWCfgState *fw_cfg) +{ + uint32_t flags = 0; + uint32_t mh_load_addr = 0; + uint32_t elf_kernel_size = 0; + uint64_t elf_entry; + uint64_t elf_low, elf_high; + int kernel_size; + + if (ldl_p(header) != 0x464c457f) { + return false; /* no elfboot */ + } + + bool elf_is64 = header[EI_CLASS] == ELFCLASS64; + flags = elf_is64 ? + ((Elf64_Ehdr *)header)->e_flags : ((Elf32_Ehdr *)header)->e_flags; + + if (flags & 0x00010004) { /* LOAD_ELF_HEADER_HAS_ADDR */ + error_report("elfboot unsupported flags = %x", flags); + exit(1); + } + + uint64_t elf_note_type = XEN_ELFNOTE_PHYS32_ENTRY; + kernel_size = load_elf(kernel_filename, read_pvh_start_addr, + NULL, &elf_note_type, &elf_entry, + &elf_low, &elf_high, NULL, 0, I386_ELF_MACHINE, + 0, 0); + + if (kernel_size < 0) { + error_report("Error while loading elf kernel"); + exit(1); + } + mh_load_addr = elf_low; + elf_kernel_size = elf_high - elf_low; + + if (pvh_start_addr == 0) { + error_report("Error loading uncompressed kernel without PVH ELF Note"); + exit(1); + } + fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ENTRY, pvh_start_addr); + fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, mh_load_addr); + fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, elf_kernel_size); + + return true; +} + +void x86_load_linux(X86MachineState *x86ms, + FWCfgState *fw_cfg, + int acpi_data_size, + bool pvh_enabled) +{ + bool linuxboot_dma_enabled = X86_MACHINE_GET_CLASS(x86ms)->fwcfg_dma_enabled; + uint16_t protocol; + int setup_size, kernel_size, cmdline_size; + int dtb_size, setup_data_offset; + uint32_t initrd_max; + uint8_t header[8192], *setup, *kernel; + hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0; + FILE *f; + char *vmode; + MachineState *machine = MACHINE(x86ms); + struct setup_data *setup_data; + const char *kernel_filename = machine->kernel_filename; + const char *initrd_filename = machine->initrd_filename; + const char *dtb_filename = machine->dtb; + const char *kernel_cmdline = machine->kernel_cmdline; + SevKernelLoaderContext sev_load_ctx = {}; + + /* Align to 16 bytes as a paranoia measure */ + cmdline_size = (strlen(kernel_cmdline) + 16) & ~15; + + /* load the kernel header */ + f = fopen(kernel_filename, "rb"); + if (!f) { + fprintf(stderr, "qemu: could not open kernel file '%s': %s\n", + kernel_filename, strerror(errno)); + exit(1); + } + + kernel_size = get_file_size(f); + if (!kernel_size || + fread(header, 1, MIN(ARRAY_SIZE(header), kernel_size), f) != + MIN(ARRAY_SIZE(header), kernel_size)) { + fprintf(stderr, "qemu: could not load kernel '%s': %s\n", + kernel_filename, strerror(errno)); + exit(1); + } + + /* kernel protocol version */ + if (ldl_p(header + 0x202) == 0x53726448) { + protocol = lduw_p(header + 0x206); + } else { + /* + * This could be a multiboot kernel. If it is, let's stop treating it + * like a Linux kernel. + * Note: some multiboot images could be in the ELF format (the same of + * PVH), so we try multiboot first since we check the multiboot magic + * header before to load it. + */ + if (load_multiboot(x86ms, fw_cfg, f, kernel_filename, initrd_filename, + kernel_cmdline, kernel_size, header)) { + return; + } + /* + * Check if the file is an uncompressed kernel file (ELF) and load it, + * saving the PVH entry point used by the x86/HVM direct boot ABI. + * If load_elfboot() is successful, populate the fw_cfg info. + */ + if (pvh_enabled && + load_elfboot(kernel_filename, kernel_size, + header, pvh_start_addr, fw_cfg)) { + fclose(f); + + fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, + strlen(kernel_cmdline) + 1); + fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline); + + fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, sizeof(header)); + fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, + header, sizeof(header)); + + /* load initrd */ + if (initrd_filename) { + GMappedFile *mapped_file; + gsize initrd_size; + gchar *initrd_data; + GError *gerr = NULL; + + mapped_file = g_mapped_file_new(initrd_filename, false, &gerr); + if (!mapped_file) { + fprintf(stderr, "qemu: error reading initrd %s: %s\n", + initrd_filename, gerr->message); + exit(1); + } + x86ms->initrd_mapped_file = mapped_file; + + initrd_data = g_mapped_file_get_contents(mapped_file); + initrd_size = g_mapped_file_get_length(mapped_file); + initrd_max = x86ms->below_4g_mem_size - acpi_data_size - 1; + if (initrd_size >= initrd_max) { + fprintf(stderr, "qemu: initrd is too large, cannot support." + "(max: %"PRIu32", need %"PRId64")\n", + initrd_max, (uint64_t)initrd_size); + exit(1); + } + + initrd_addr = (initrd_max - initrd_size) & ~4095; + + fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr); + fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size); + fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, + initrd_size); + } + + option_rom[nb_option_roms].bootindex = 0; + option_rom[nb_option_roms].name = "pvh.bin"; + nb_option_roms++; + + return; + } + protocol = 0; + } + + if (protocol < 0x200 || !(header[0x211] & 0x01)) { + /* Low kernel */ + real_addr = 0x90000; + cmdline_addr = 0x9a000 - cmdline_size; + prot_addr = 0x10000; + } else if (protocol < 0x202) { + /* High but ancient kernel */ + real_addr = 0x90000; + cmdline_addr = 0x9a000 - cmdline_size; + prot_addr = 0x100000; + } else { + /* High and recent kernel */ + real_addr = 0x10000; + cmdline_addr = 0x20000; + prot_addr = 0x100000; + } + + /* highest address for loading the initrd */ + if (protocol >= 0x20c && + lduw_p(header + 0x236) & XLF_CAN_BE_LOADED_ABOVE_4G) { + /* + * Linux has supported initrd up to 4 GB for a very long time (2007, + * long before XLF_CAN_BE_LOADED_ABOVE_4G which was added in 2013), + * though it only sets initrd_max to 2 GB to "work around bootloader + * bugs". Luckily, QEMU firmware(which does something like bootloader) + * has supported this. + * + * It's believed that if XLF_CAN_BE_LOADED_ABOVE_4G is set, initrd can + * be loaded into any address. + * + * In addition, initrd_max is uint32_t simply because QEMU doesn't + * support the 64-bit boot protocol (specifically the ext_ramdisk_image + * field). + * + * Therefore here just limit initrd_max to UINT32_MAX simply as well. + */ + initrd_max = UINT32_MAX; + } else if (protocol >= 0x203) { + initrd_max = ldl_p(header + 0x22c); + } else { + initrd_max = 0x37ffffff; + } + + if (initrd_max >= x86ms->below_4g_mem_size - acpi_data_size) { + initrd_max = x86ms->below_4g_mem_size - acpi_data_size - 1; + } + + fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr); + fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(kernel_cmdline) + 1); + fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline); + sev_load_ctx.cmdline_data = (char *)kernel_cmdline; + sev_load_ctx.cmdline_size = strlen(kernel_cmdline) + 1; + + if (protocol >= 0x202) { + stl_p(header + 0x228, cmdline_addr); + } else { + stw_p(header + 0x20, 0xA33F); + stw_p(header + 0x22, cmdline_addr - real_addr); + } + + /* handle vga= parameter */ + vmode = strstr(kernel_cmdline, "vga="); + if (vmode) { + unsigned int video_mode; + const char *end; + int ret; + /* skip "vga=" */ + vmode += 4; + if (!strncmp(vmode, "normal", 6)) { + video_mode = 0xffff; + } else if (!strncmp(vmode, "ext", 3)) { + video_mode = 0xfffe; + } else if (!strncmp(vmode, "ask", 3)) { + video_mode = 0xfffd; + } else { + ret = qemu_strtoui(vmode, &end, 0, &video_mode); + if (ret != 0 || (*end && *end != ' ')) { + fprintf(stderr, "qemu: invalid 'vga=' kernel parameter.\n"); + exit(1); + } + } + stw_p(header + 0x1fa, video_mode); + } + + /* loader type */ + /* + * High nybble = B reserved for QEMU; low nybble is revision number. + * If this code is substantially changed, you may want to consider + * incrementing the revision. + */ + if (protocol >= 0x200) { + header[0x210] = 0xB0; + } + /* heap */ + if (protocol >= 0x201) { + header[0x211] |= 0x80; /* CAN_USE_HEAP */ + stw_p(header + 0x224, cmdline_addr - real_addr - 0x200); + } + + /* load initrd */ + if (initrd_filename) { + GMappedFile *mapped_file; + gsize initrd_size; + gchar *initrd_data; + GError *gerr = NULL; + + if (protocol < 0x200) { + fprintf(stderr, "qemu: linux kernel too old to load a ram disk\n"); + exit(1); + } + + mapped_file = g_mapped_file_new(initrd_filename, false, &gerr); + if (!mapped_file) { + fprintf(stderr, "qemu: error reading initrd %s: %s\n", + initrd_filename, gerr->message); + exit(1); + } + x86ms->initrd_mapped_file = mapped_file; + + initrd_data = g_mapped_file_get_contents(mapped_file); + initrd_size = g_mapped_file_get_length(mapped_file); + if (initrd_size >= initrd_max) { + fprintf(stderr, "qemu: initrd is too large, cannot support." + "(max: %"PRIu32", need %"PRId64")\n", + initrd_max, (uint64_t)initrd_size); + exit(1); + } + + initrd_addr = (initrd_max - initrd_size) & ~4095; + + fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr); + fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size); + fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, initrd_size); + sev_load_ctx.initrd_data = initrd_data; + sev_load_ctx.initrd_size = initrd_size; + + stl_p(header + 0x218, initrd_addr); + stl_p(header + 0x21c, initrd_size); + } + + /* load kernel and setup */ + setup_size = header[0x1f1]; + if (setup_size == 0) { + setup_size = 4; + } + setup_size = (setup_size + 1) * 512; + if (setup_size > kernel_size) { + fprintf(stderr, "qemu: invalid kernel header\n"); + exit(1); + } + kernel_size -= setup_size; + + setup = g_malloc(setup_size); + kernel = g_malloc(kernel_size); + fseek(f, 0, SEEK_SET); + if (fread(setup, 1, setup_size, f) != setup_size) { + fprintf(stderr, "fread() failed\n"); + exit(1); + } + if (fread(kernel, 1, kernel_size, f) != kernel_size) { + fprintf(stderr, "fread() failed\n"); + exit(1); + } + fclose(f); + + /* append dtb to kernel */ + if (dtb_filename) { + if (protocol < 0x209) { + fprintf(stderr, "qemu: Linux kernel too old to load a dtb\n"); + exit(1); + } + + dtb_size = get_image_size(dtb_filename); + if (dtb_size <= 0) { + fprintf(stderr, "qemu: error reading dtb %s: %s\n", + dtb_filename, strerror(errno)); + exit(1); + } + + setup_data_offset = QEMU_ALIGN_UP(kernel_size, 16); + kernel_size = setup_data_offset + sizeof(struct setup_data) + dtb_size; + kernel = g_realloc(kernel, kernel_size); + + stq_p(header + 0x250, prot_addr + setup_data_offset); + + setup_data = (struct setup_data *)(kernel + setup_data_offset); + setup_data->next = 0; + setup_data->type = cpu_to_le32(SETUP_DTB); + setup_data->len = cpu_to_le32(dtb_size); + + load_image_size(dtb_filename, setup_data->data, dtb_size); + } + + /* + * If we're starting an encrypted VM, it will be OVMF based, which uses the + * efi stub for booting and doesn't require any values to be placed in the + * kernel header. We therefore don't update the header so the hash of the + * kernel on the other side of the fw_cfg interface matches the hash of the + * file the user passed in. + */ + if (!sev_enabled()) { + memcpy(setup, header, MIN(sizeof(header), setup_size)); + } + + fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, prot_addr); + fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, kernel_size); + fw_cfg_add_bytes(fw_cfg, FW_CFG_KERNEL_DATA, kernel, kernel_size); + sev_load_ctx.kernel_data = (char *)kernel; + sev_load_ctx.kernel_size = kernel_size; + + fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_ADDR, real_addr); + fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, setup_size); + fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, setup, setup_size); + sev_load_ctx.setup_data = (char *)setup; + sev_load_ctx.setup_size = setup_size; + + if (sev_enabled()) { + sev_add_kernel_loader_hashes(&sev_load_ctx, &error_fatal); + } + + option_rom[nb_option_roms].bootindex = 0; + option_rom[nb_option_roms].name = "linuxboot.bin"; + if (linuxboot_dma_enabled && fw_cfg_dma_enabled(fw_cfg)) { + option_rom[nb_option_roms].name = "linuxboot_dma.bin"; + } + nb_option_roms++; +} + +void x86_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *isa_memory, + MemoryRegion *bios, bool read_only) +{ + uint64_t bios_size = memory_region_size(bios); + uint64_t isa_bios_size = MIN(bios_size, 128 * KiB); + + memory_region_init_alias(isa_bios, NULL, "isa-bios", bios, + bios_size - isa_bios_size, isa_bios_size); + memory_region_add_subregion_overlap(isa_memory, 1 * MiB - isa_bios_size, + isa_bios, 1); + memory_region_set_readonly(isa_bios, read_only); +} + +void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware, + MemoryRegion *rom_memory, bool isapc_ram_fw) +{ + const char *bios_name; + char *filename; + int bios_size; + ssize_t ret; + + /* BIOS load */ + bios_name = MACHINE(x86ms)->firmware ?: default_firmware; + filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); + if (filename) { + bios_size = get_image_size(filename); + } else { + bios_size = -1; + } + if (bios_size <= 0 || + (bios_size % 65536) != 0) { + goto bios_error; + } + memory_region_init_ram(&x86ms->bios, NULL, "pc.bios", bios_size, + &error_fatal); + if (sev_enabled()) { + /* + * The concept of a "reset" simply doesn't exist for + * confidential computing guests, we have to destroy and + * re-launch them instead. So there is no need to register + * the firmware as rom to properly re-initialize on reset. + * Just go for a straight file load instead. + */ + void *ptr = memory_region_get_ram_ptr(&x86ms->bios); + load_image_size(filename, ptr, bios_size); + x86_firmware_configure(ptr, bios_size); + } else { + memory_region_set_readonly(&x86ms->bios, !isapc_ram_fw); + ret = rom_add_file_fixed(bios_name, (uint32_t)(-bios_size), -1); + if (ret != 0) { + goto bios_error; + } + } + g_free(filename); + + /* map the last 128KB of the BIOS in ISA space */ + x86_isa_bios_init(&x86ms->isa_bios, rom_memory, &x86ms->bios, + !isapc_ram_fw); + + /* map all the bios at the top of memory */ + memory_region_add_subregion(rom_memory, + (uint32_t)(-bios_size), + &x86ms->bios); + return; + +bios_error: + fprintf(stderr, "qemu: could not load PC BIOS '%s'\n", bios_name); + exit(1); +} diff --git a/hw/i386/x86-cpu.c b/hw/i386/x86-cpu.c new file mode 100644 index 0000000000..ab2920522d --- /dev/null +++ b/hw/i386/x86-cpu.c @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2003-2004 Fabrice Bellard + * Copyright (c) 2019, 2024 Red Hat, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include "qemu/osdep.h" +#include "sysemu/whpx.h" +#include "sysemu/cpu-timers.h" +#include "trace.h" + +#include "hw/i386/x86.h" +#include "target/i386/cpu.h" +#include "hw/intc/i8259.h" +#include "hw/irq.h" +#include "sysemu/kvm.h" + +/* TSC handling */ +uint64_t cpu_get_tsc(CPUX86State *env) +{ + return cpus_get_elapsed_ticks(); +} + +/* IRQ handling */ +static void pic_irq_request(void *opaque, int irq, int level) +{ + CPUState *cs = first_cpu; + X86CPU *cpu = X86_CPU(cs); + + trace_x86_pic_interrupt(irq, level); + if (cpu_is_apic_enabled(cpu->apic_state) && !kvm_irqchip_in_kernel() && + !whpx_apic_in_platform()) { + CPU_FOREACH(cs) { + cpu = X86_CPU(cs); + if (apic_accept_pic_intr(cpu->apic_state)) { + apic_deliver_pic_intr(cpu->apic_state, level); + } + } + } else { + if (level) { + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } else { + cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); + } + } +} + +qemu_irq x86_allocate_cpu_irq(void) +{ + return qemu_allocate_irq(pic_irq_request, NULL, 0); +} + +int cpu_get_pic_interrupt(CPUX86State *env) +{ + X86CPU *cpu = env_archcpu(env); + int intno; + + if (!kvm_irqchip_in_kernel() && !whpx_apic_in_platform()) { + intno = apic_get_interrupt(cpu->apic_state); + if (intno >= 0) { + return intno; + } + /* read the irq from the PIC */ + if (!apic_accept_pic_intr(cpu->apic_state)) { + return -1; + } + } + + intno = pic_read_irq(isa_pic); + return intno; +} + +DeviceState *cpu_get_current_apic(void) +{ + if (current_cpu) { + X86CPU *cpu = X86_CPU(current_cpu); + return cpu->apic_state; + } else { + return NULL; + } +} diff --git a/hw/i386/x86.c b/hw/i386/x86.c index c61f4ebfa6..0b5cc59956 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -22,52 +22,25 @@ */ #include "qemu/osdep.h" #include "qemu/error-report.h" -#include "qemu/option.h" -#include "qemu/cutils.h" #include "qemu/units.h" -#include "qemu/datadir.h" #include "qapi/error.h" #include "qapi/qapi-visit-common.h" -#include "qapi/clone-visitor.h" #include "qapi/qapi-visit-machine.h" #include "qapi/visitor.h" #include "sysemu/qtest.h" -#include "sysemu/whpx.h" #include "sysemu/numa.h" -#include "sysemu/replay.h" -#include "sysemu/sysemu.h" -#include "sysemu/cpu-timers.h" -#include "sysemu/xen.h" #include "trace.h" +#include "hw/acpi/aml-build.h" #include "hw/i386/x86.h" -#include "target/i386/cpu.h" #include "hw/i386/topology.h" -#include "hw/i386/fw_cfg.h" -#include "hw/intc/i8259.h" -#include "hw/rtc/mc146818rtc.h" -#include "target/i386/sev.h" -#include "hw/acpi/cpu_hotplug.h" -#include "hw/irq.h" #include "hw/nmi.h" -#include "hw/loader.h" -#include "multiboot.h" -#include "elf.h" -#include "standard-headers/asm-x86/bootparam.h" -#include CONFIG_DEVICES #include "kvm/kvm_i386.h" -#ifdef CONFIG_XEN_EMU -#include "hw/xen/xen.h" -#include "hw/i386/kvm/xen_evtchn.h" -#endif -/* Physical Address of PVH entry point read from kernel ELF NOTE */ -static size_t pvh_start_addr; - -static void init_topo_info(X86CPUTopoInfo *topo_info, - const X86MachineState *x86ms) +void init_topo_info(X86CPUTopoInfo *topo_info, + const X86MachineState *x86ms) { MachineState *ms = MACHINE(x86ms); @@ -94,356 +67,7 @@ uint32_t x86_cpu_apic_id_from_index(X86MachineState *x86ms, return x86_apicid_from_cpu_idx(&topo_info, cpu_index); } - -void x86_cpu_new(X86MachineState *x86ms, int64_t apic_id, Error **errp) -{ - Object *cpu = object_new(MACHINE(x86ms)->cpu_type); - - if (!object_property_set_uint(cpu, "apic-id", apic_id, errp)) { - goto out; - } - qdev_realize(DEVICE(cpu), NULL, errp); - -out: - object_unref(cpu); -} - -void x86_cpus_init(X86MachineState *x86ms, int default_cpu_version) -{ - int i; - const CPUArchIdList *possible_cpus; - MachineState *ms = MACHINE(x86ms); - MachineClass *mc = MACHINE_GET_CLASS(x86ms); - - x86_cpu_set_default_version(default_cpu_version); - - /* - * Calculates the limit to CPU APIC ID values - * - * Limit for the APIC ID value, so that all - * CPU APIC IDs are < x86ms->apic_id_limit. - * - * This is used for FW_CFG_MAX_CPUS. See comments on fw_cfg_arch_create(). - */ - x86ms->apic_id_limit = x86_cpu_apic_id_from_index(x86ms, - ms->smp.max_cpus - 1) + 1; - - /* - * Can we support APIC ID 255 or higher? With KVM, that requires - * both in-kernel lapic and X2APIC userspace API. - * - * kvm_enabled() must go first to ensure that kvm_* references are - * not emitted for the linker to consume (kvm_enabled() is - * a literal `0` in configurations where kvm_* aren't defined) - */ - if (kvm_enabled() && x86ms->apic_id_limit > 255 && - kvm_irqchip_in_kernel() && !kvm_enable_x2apic()) { - error_report("current -smp configuration requires kernel " - "irqchip and X2APIC API support."); - exit(EXIT_FAILURE); - } - - if (kvm_enabled()) { - kvm_set_max_apic_id(x86ms->apic_id_limit); - } - - if (!kvm_irqchip_in_kernel()) { - apic_set_max_apic_id(x86ms->apic_id_limit); - } - - possible_cpus = mc->possible_cpu_arch_ids(ms); - for (i = 0; i < ms->smp.cpus; i++) { - x86_cpu_new(x86ms, possible_cpus->cpus[i].arch_id, &error_fatal); - } -} - -void x86_rtc_set_cpus_count(ISADevice *s, uint16_t cpus_count) -{ - MC146818RtcState *rtc = MC146818_RTC(s); - - if (cpus_count > 0xff) { - /* - * If the number of CPUs can't be represented in 8 bits, the - * BIOS must use "FW_CFG_NB_CPUS". Set RTC field to 0 just - * to make old BIOSes fail more predictably. - */ - mc146818rtc_set_cmos_data(rtc, 0x5f, 0); - } else { - mc146818rtc_set_cmos_data(rtc, 0x5f, cpus_count - 1); - } -} - -static int x86_apic_cmp(const void *a, const void *b) -{ - CPUArchId *apic_a = (CPUArchId *)a; - CPUArchId *apic_b = (CPUArchId *)b; - - return apic_a->arch_id - apic_b->arch_id; -} - -/* - * returns pointer to CPUArchId descriptor that matches CPU's apic_id - * in ms->possible_cpus->cpus, if ms->possible_cpus->cpus has no - * entry corresponding to CPU's apic_id returns NULL. - */ -CPUArchId *x86_find_cpu_slot(MachineState *ms, uint32_t id, int *idx) -{ - CPUArchId apic_id, *found_cpu; - - apic_id.arch_id = id; - found_cpu = bsearch(&apic_id, ms->possible_cpus->cpus, - ms->possible_cpus->len, sizeof(*ms->possible_cpus->cpus), - x86_apic_cmp); - if (found_cpu && idx) { - *idx = found_cpu - ms->possible_cpus->cpus; - } - return found_cpu; -} - -void x86_cpu_plug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) -{ - CPUArchId *found_cpu; - Error *local_err = NULL; - X86CPU *cpu = X86_CPU(dev); - X86MachineState *x86ms = X86_MACHINE(hotplug_dev); - - if (x86ms->acpi_dev) { - hotplug_handler_plug(x86ms->acpi_dev, dev, &local_err); - if (local_err) { - goto out; - } - } - - /* increment the number of CPUs */ - x86ms->boot_cpus++; - if (x86ms->rtc) { - x86_rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); - } - if (x86ms->fw_cfg) { - fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus); - } - - found_cpu = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, NULL); - found_cpu->cpu = CPU(dev); -out: - error_propagate(errp, local_err); -} - -void x86_cpu_unplug_request_cb(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) -{ - int idx = -1; - X86CPU *cpu = X86_CPU(dev); - X86MachineState *x86ms = X86_MACHINE(hotplug_dev); - - if (!x86ms->acpi_dev) { - error_setg(errp, "CPU hot unplug not supported without ACPI"); - return; - } - - x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, &idx); - assert(idx != -1); - if (idx == 0) { - error_setg(errp, "Boot CPU is unpluggable"); - return; - } - - hotplug_handler_unplug_request(x86ms->acpi_dev, dev, - errp); -} - -void x86_cpu_unplug_cb(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) -{ - CPUArchId *found_cpu; - Error *local_err = NULL; - X86CPU *cpu = X86_CPU(dev); - X86MachineState *x86ms = X86_MACHINE(hotplug_dev); - - hotplug_handler_unplug(x86ms->acpi_dev, dev, &local_err); - if (local_err) { - goto out; - } - - found_cpu = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, NULL); - found_cpu->cpu = NULL; - qdev_unrealize(dev); - - /* decrement the number of CPUs */ - x86ms->boot_cpus--; - /* Update the number of CPUs in CMOS */ - x86_rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); - fw_cfg_modify_i16(x86ms->fw_cfg, FW_CFG_NB_CPUS, x86ms->boot_cpus); - out: - error_propagate(errp, local_err); -} - -void x86_cpu_pre_plug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) -{ - int idx; - CPUState *cs; - CPUArchId *cpu_slot; - X86CPUTopoIDs topo_ids; - X86CPU *cpu = X86_CPU(dev); - CPUX86State *env = &cpu->env; - MachineState *ms = MACHINE(hotplug_dev); - X86MachineState *x86ms = X86_MACHINE(hotplug_dev); - unsigned int smp_cores = ms->smp.cores; - unsigned int smp_threads = ms->smp.threads; - X86CPUTopoInfo topo_info; - - if (!object_dynamic_cast(OBJECT(cpu), ms->cpu_type)) { - error_setg(errp, "Invalid CPU type, expected cpu type: '%s'", - ms->cpu_type); - return; - } - - if (x86ms->acpi_dev) { - Error *local_err = NULL; - - hotplug_handler_pre_plug(HOTPLUG_HANDLER(x86ms->acpi_dev), dev, - &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } - } - - init_topo_info(&topo_info, x86ms); - - env->nr_dies = ms->smp.dies; - - /* - * If APIC ID is not set, - * set it based on socket/die/core/thread properties. - */ - if (cpu->apic_id == UNASSIGNED_APIC_ID) { - int max_socket = (ms->smp.max_cpus - 1) / - smp_threads / smp_cores / ms->smp.dies; - - /* - * die-id was optional in QEMU 4.0 and older, so keep it optional - * if there's only one die per socket. - */ - if (cpu->die_id < 0 && ms->smp.dies == 1) { - cpu->die_id = 0; - } - - if (cpu->socket_id < 0) { - error_setg(errp, "CPU socket-id is not set"); - return; - } else if (cpu->socket_id > max_socket) { - error_setg(errp, "Invalid CPU socket-id: %u must be in range 0:%u", - cpu->socket_id, max_socket); - return; - } - if (cpu->die_id < 0) { - error_setg(errp, "CPU die-id is not set"); - return; - } else if (cpu->die_id > ms->smp.dies - 1) { - error_setg(errp, "Invalid CPU die-id: %u must be in range 0:%u", - cpu->die_id, ms->smp.dies - 1); - return; - } - if (cpu->core_id < 0) { - error_setg(errp, "CPU core-id is not set"); - return; - } else if (cpu->core_id > (smp_cores - 1)) { - error_setg(errp, "Invalid CPU core-id: %u must be in range 0:%u", - cpu->core_id, smp_cores - 1); - return; - } - if (cpu->thread_id < 0) { - error_setg(errp, "CPU thread-id is not set"); - return; - } else if (cpu->thread_id > (smp_threads - 1)) { - error_setg(errp, "Invalid CPU thread-id: %u must be in range 0:%u", - cpu->thread_id, smp_threads - 1); - return; - } - - topo_ids.pkg_id = cpu->socket_id; - topo_ids.die_id = cpu->die_id; - topo_ids.core_id = cpu->core_id; - topo_ids.smt_id = cpu->thread_id; - cpu->apic_id = x86_apicid_from_topo_ids(&topo_info, &topo_ids); - } - - cpu_slot = x86_find_cpu_slot(MACHINE(x86ms), cpu->apic_id, &idx); - if (!cpu_slot) { - x86_topo_ids_from_apicid(cpu->apic_id, &topo_info, &topo_ids); - error_setg(errp, - "Invalid CPU [socket: %u, die: %u, core: %u, thread: %u] with" - " APIC ID %" PRIu32 ", valid index range 0:%d", - topo_ids.pkg_id, topo_ids.die_id, topo_ids.core_id, topo_ids.smt_id, - cpu->apic_id, ms->possible_cpus->len - 1); - return; - } - - if (cpu_slot->cpu) { - error_setg(errp, "CPU[%d] with APIC ID %" PRIu32 " exists", - idx, cpu->apic_id); - return; - } - - /* if 'address' properties socket-id/core-id/thread-id are not set, set them - * so that machine_query_hotpluggable_cpus would show correct values - */ - /* TODO: move socket_id/core_id/thread_id checks into x86_cpu_realizefn() - * once -smp refactoring is complete and there will be CPU private - * CPUState::nr_cores and CPUState::nr_threads fields instead of globals */ - x86_topo_ids_from_apicid(cpu->apic_id, &topo_info, &topo_ids); - if (cpu->socket_id != -1 && cpu->socket_id != topo_ids.pkg_id) { - error_setg(errp, "property socket-id: %u doesn't match set apic-id:" - " 0x%x (socket-id: %u)", cpu->socket_id, cpu->apic_id, - topo_ids.pkg_id); - return; - } - cpu->socket_id = topo_ids.pkg_id; - - if (cpu->die_id != -1 && cpu->die_id != topo_ids.die_id) { - error_setg(errp, "property die-id: %u doesn't match set apic-id:" - " 0x%x (die-id: %u)", cpu->die_id, cpu->apic_id, topo_ids.die_id); - return; - } - cpu->die_id = topo_ids.die_id; - - if (cpu->core_id != -1 && cpu->core_id != topo_ids.core_id) { - error_setg(errp, "property core-id: %u doesn't match set apic-id:" - " 0x%x (core-id: %u)", cpu->core_id, cpu->apic_id, - topo_ids.core_id); - return; - } - cpu->core_id = topo_ids.core_id; - - if (cpu->thread_id != -1 && cpu->thread_id != topo_ids.smt_id) { - error_setg(errp, "property thread-id: %u doesn't match set apic-id:" - " 0x%x (thread-id: %u)", cpu->thread_id, cpu->apic_id, - topo_ids.smt_id); - return; - } - cpu->thread_id = topo_ids.smt_id; - - /* - * kvm_enabled() must go first to ensure that kvm_* references are - * not emitted for the linker to consume (kvm_enabled() is - * a literal `0` in configurations where kvm_* aren't defined) - */ - if (kvm_enabled() && hyperv_feat_enabled(cpu, HYPERV_FEAT_VPINDEX) && - !kvm_hv_vpindex_settable()) { - error_setg(errp, "kernel doesn't allow setting HyperV VP_INDEX"); - return; - } - - cs = CPU(cpu); - cs->cpu_index = idx; - - numa_cpu_pre_plug(cpu_slot, dev, errp); -} - -CpuInstanceProperties +static CpuInstanceProperties x86_cpu_index_to_props(MachineState *ms, unsigned cpu_index) { MachineClass *mc = MACHINE_GET_CLASS(ms); @@ -453,7 +77,7 @@ x86_cpu_index_to_props(MachineState *ms, unsigned cpu_index) return possible_cpus->cpus[cpu_index].props; } -int64_t x86_get_default_cpu_node_id(const MachineState *ms, int idx) +static int64_t x86_get_default_cpu_node_id(const MachineState *ms, int idx) { X86CPUTopoIDs topo_ids; X86MachineState *x86ms = X86_MACHINE(ms); @@ -467,7 +91,7 @@ int64_t x86_get_default_cpu_node_id(const MachineState *ms, int idx) return topo_ids.pkg_id % ms->numa_state->num_nodes; } -const CPUArchIdList *x86_possible_cpu_arch_ids(MachineState *ms) +static const CPUArchIdList *x86_possible_cpu_arch_ids(MachineState *ms) { X86MachineState *x86ms = X86_MACHINE(ms); unsigned int max_cpus = ms->smp.max_cpus; @@ -528,676 +152,6 @@ static void x86_nmi(NMIState *n, int cpu_index, Error **errp) } } -static long get_file_size(FILE *f) -{ - long where, size; - - /* XXX: on Unix systems, using fstat() probably makes more sense */ - - where = ftell(f); - fseek(f, 0, SEEK_END); - size = ftell(f); - fseek(f, where, SEEK_SET); - - return size; -} - -/* TSC handling */ -uint64_t cpu_get_tsc(CPUX86State *env) -{ - return cpus_get_elapsed_ticks(); -} - -/* IRQ handling */ -static void pic_irq_request(void *opaque, int irq, int level) -{ - CPUState *cs = first_cpu; - X86CPU *cpu = X86_CPU(cs); - - trace_x86_pic_interrupt(irq, level); - if (cpu_is_apic_enabled(cpu->apic_state) && !kvm_irqchip_in_kernel() && - !whpx_apic_in_platform()) { - CPU_FOREACH(cs) { - cpu = X86_CPU(cs); - if (apic_accept_pic_intr(cpu->apic_state)) { - apic_deliver_pic_intr(cpu->apic_state, level); - } - } - } else { - if (level) { - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - } - } -} - -qemu_irq x86_allocate_cpu_irq(void) -{ - return qemu_allocate_irq(pic_irq_request, NULL, 0); -} - -int cpu_get_pic_interrupt(CPUX86State *env) -{ - X86CPU *cpu = env_archcpu(env); - int intno; - - if (!kvm_irqchip_in_kernel() && !whpx_apic_in_platform()) { - intno = apic_get_interrupt(cpu->apic_state); - if (intno >= 0) { - return intno; - } - /* read the irq from the PIC */ - if (!apic_accept_pic_intr(cpu->apic_state)) { - return -1; - } - } - - intno = pic_read_irq(isa_pic); - return intno; -} - -DeviceState *cpu_get_current_apic(void) -{ - if (current_cpu) { - X86CPU *cpu = X86_CPU(current_cpu); - return cpu->apic_state; - } else { - return NULL; - } -} - -void gsi_handler(void *opaque, int n, int level) -{ - GSIState *s = opaque; - - trace_x86_gsi_interrupt(n, level); - switch (n) { - case 0 ... ISA_NUM_IRQS - 1: - if (s->i8259_irq[n]) { - /* Under KVM, Kernel will forward to both PIC and IOAPIC */ - qemu_set_irq(s->i8259_irq[n], level); - } - /* fall through */ - case ISA_NUM_IRQS ... IOAPIC_NUM_PINS - 1: -#ifdef CONFIG_XEN_EMU - /* - * Xen delivers the GSI to the Legacy PIC (not that Legacy PIC - * routing actually works properly under Xen). And then to - * *either* the PIRQ handling or the I/OAPIC depending on - * whether the former wants it. - */ - if (xen_mode == XEN_EMULATE && xen_evtchn_set_gsi(n, level)) { - break; - } -#endif - qemu_set_irq(s->ioapic_irq[n], level); - break; - case IO_APIC_SECONDARY_IRQBASE - ... IO_APIC_SECONDARY_IRQBASE + IOAPIC_NUM_PINS - 1: - qemu_set_irq(s->ioapic2_irq[n - IO_APIC_SECONDARY_IRQBASE], level); - break; - } -} - -void ioapic_init_gsi(GSIState *gsi_state, Object *parent) -{ - DeviceState *dev; - SysBusDevice *d; - unsigned int i; - - assert(parent); - if (kvm_ioapic_in_kernel()) { - dev = qdev_new(TYPE_KVM_IOAPIC); - } else { - dev = qdev_new(TYPE_IOAPIC); - } - object_property_add_child(parent, "ioapic", OBJECT(dev)); - d = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(d, &error_fatal); - sysbus_mmio_map(d, 0, IO_APIC_DEFAULT_ADDRESS); - - for (i = 0; i < IOAPIC_NUM_PINS; i++) { - gsi_state->ioapic_irq[i] = qdev_get_gpio_in(dev, i); - } -} - -DeviceState *ioapic_init_secondary(GSIState *gsi_state) -{ - DeviceState *dev; - SysBusDevice *d; - unsigned int i; - - dev = qdev_new(TYPE_IOAPIC); - d = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(d, &error_fatal); - sysbus_mmio_map(d, 0, IO_APIC_SECONDARY_ADDRESS); - - for (i = 0; i < IOAPIC_NUM_PINS; i++) { - gsi_state->ioapic2_irq[i] = qdev_get_gpio_in(dev, i); - } - return dev; -} - -/* - * The entry point into the kernel for PVH boot is different from - * the native entry point. The PVH entry is defined by the x86/HVM - * direct boot ABI and is available in an ELFNOTE in the kernel binary. - * - * This function is passed to load_elf() when it is called from - * load_elfboot() which then additionally checks for an ELF Note of - * type XEN_ELFNOTE_PHYS32_ENTRY and passes it to this function to - * parse the PVH entry address from the ELF Note. - * - * Due to trickery in elf_opts.h, load_elf() is actually available as - * load_elf32() or load_elf64() and this routine needs to be able - * to deal with being called as 32 or 64 bit. - * - * The address of the PVH entry point is saved to the 'pvh_start_addr' - * global variable. (although the entry point is 32-bit, the kernel - * binary can be either 32-bit or 64-bit). - */ -static uint64_t read_pvh_start_addr(void *arg1, void *arg2, bool is64) -{ - size_t *elf_note_data_addr; - - /* Check if ELF Note header passed in is valid */ - if (arg1 == NULL) { - return 0; - } - - if (is64) { - struct elf64_note *nhdr64 = (struct elf64_note *)arg1; - uint64_t nhdr_size64 = sizeof(struct elf64_note); - uint64_t phdr_align = *(uint64_t *)arg2; - uint64_t nhdr_namesz = nhdr64->n_namesz; - - elf_note_data_addr = - ((void *)nhdr64) + nhdr_size64 + - QEMU_ALIGN_UP(nhdr_namesz, phdr_align); - - pvh_start_addr = *elf_note_data_addr; - } else { - struct elf32_note *nhdr32 = (struct elf32_note *)arg1; - uint32_t nhdr_size32 = sizeof(struct elf32_note); - uint32_t phdr_align = *(uint32_t *)arg2; - uint32_t nhdr_namesz = nhdr32->n_namesz; - - elf_note_data_addr = - ((void *)nhdr32) + nhdr_size32 + - QEMU_ALIGN_UP(nhdr_namesz, phdr_align); - - pvh_start_addr = *(uint32_t *)elf_note_data_addr; - } - - return pvh_start_addr; -} - -static bool load_elfboot(const char *kernel_filename, - int kernel_file_size, - uint8_t *header, - size_t pvh_xen_start_addr, - FWCfgState *fw_cfg) -{ - uint32_t flags = 0; - uint32_t mh_load_addr = 0; - uint32_t elf_kernel_size = 0; - uint64_t elf_entry; - uint64_t elf_low, elf_high; - int kernel_size; - - if (ldl_p(header) != 0x464c457f) { - return false; /* no elfboot */ - } - - bool elf_is64 = header[EI_CLASS] == ELFCLASS64; - flags = elf_is64 ? - ((Elf64_Ehdr *)header)->e_flags : ((Elf32_Ehdr *)header)->e_flags; - - if (flags & 0x00010004) { /* LOAD_ELF_HEADER_HAS_ADDR */ - error_report("elfboot unsupported flags = %x", flags); - exit(1); - } - - uint64_t elf_note_type = XEN_ELFNOTE_PHYS32_ENTRY; - kernel_size = load_elf(kernel_filename, read_pvh_start_addr, - NULL, &elf_note_type, &elf_entry, - &elf_low, &elf_high, NULL, 0, I386_ELF_MACHINE, - 0, 0); - - if (kernel_size < 0) { - error_report("Error while loading elf kernel"); - exit(1); - } - mh_load_addr = elf_low; - elf_kernel_size = elf_high - elf_low; - - if (pvh_start_addr == 0) { - error_report("Error loading uncompressed kernel without PVH ELF Note"); - exit(1); - } - fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ENTRY, pvh_start_addr); - fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, mh_load_addr); - fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, elf_kernel_size); - - return true; -} - -void x86_load_linux(X86MachineState *x86ms, - FWCfgState *fw_cfg, - int acpi_data_size, - bool pvh_enabled) -{ - bool linuxboot_dma_enabled = X86_MACHINE_GET_CLASS(x86ms)->fwcfg_dma_enabled; - uint16_t protocol; - int setup_size, kernel_size, cmdline_size; - int dtb_size, setup_data_offset; - uint32_t initrd_max; - uint8_t header[8192], *setup, *kernel; - hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0; - FILE *f; - char *vmode; - MachineState *machine = MACHINE(x86ms); - struct setup_data *setup_data; - const char *kernel_filename = machine->kernel_filename; - const char *initrd_filename = machine->initrd_filename; - const char *dtb_filename = machine->dtb; - const char *kernel_cmdline = machine->kernel_cmdline; - SevKernelLoaderContext sev_load_ctx = {}; - - /* Align to 16 bytes as a paranoia measure */ - cmdline_size = (strlen(kernel_cmdline) + 16) & ~15; - - /* load the kernel header */ - f = fopen(kernel_filename, "rb"); - if (!f) { - fprintf(stderr, "qemu: could not open kernel file '%s': %s\n", - kernel_filename, strerror(errno)); - exit(1); - } - - kernel_size = get_file_size(f); - if (!kernel_size || - fread(header, 1, MIN(ARRAY_SIZE(header), kernel_size), f) != - MIN(ARRAY_SIZE(header), kernel_size)) { - fprintf(stderr, "qemu: could not load kernel '%s': %s\n", - kernel_filename, strerror(errno)); - exit(1); - } - - /* kernel protocol version */ - if (ldl_p(header + 0x202) == 0x53726448) { - protocol = lduw_p(header + 0x206); - } else { - /* - * This could be a multiboot kernel. If it is, let's stop treating it - * like a Linux kernel. - * Note: some multiboot images could be in the ELF format (the same of - * PVH), so we try multiboot first since we check the multiboot magic - * header before to load it. - */ - if (load_multiboot(x86ms, fw_cfg, f, kernel_filename, initrd_filename, - kernel_cmdline, kernel_size, header)) { - return; - } - /* - * Check if the file is an uncompressed kernel file (ELF) and load it, - * saving the PVH entry point used by the x86/HVM direct boot ABI. - * If load_elfboot() is successful, populate the fw_cfg info. - */ - if (pvh_enabled && - load_elfboot(kernel_filename, kernel_size, - header, pvh_start_addr, fw_cfg)) { - fclose(f); - - fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, - strlen(kernel_cmdline) + 1); - fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline); - - fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, sizeof(header)); - fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, - header, sizeof(header)); - - /* load initrd */ - if (initrd_filename) { - GMappedFile *mapped_file; - gsize initrd_size; - gchar *initrd_data; - GError *gerr = NULL; - - mapped_file = g_mapped_file_new(initrd_filename, false, &gerr); - if (!mapped_file) { - fprintf(stderr, "qemu: error reading initrd %s: %s\n", - initrd_filename, gerr->message); - exit(1); - } - x86ms->initrd_mapped_file = mapped_file; - - initrd_data = g_mapped_file_get_contents(mapped_file); - initrd_size = g_mapped_file_get_length(mapped_file); - initrd_max = x86ms->below_4g_mem_size - acpi_data_size - 1; - if (initrd_size >= initrd_max) { - fprintf(stderr, "qemu: initrd is too large, cannot support." - "(max: %"PRIu32", need %"PRId64")\n", - initrd_max, (uint64_t)initrd_size); - exit(1); - } - - initrd_addr = (initrd_max - initrd_size) & ~4095; - - fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr); - fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size); - fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, - initrd_size); - } - - option_rom[nb_option_roms].bootindex = 0; - option_rom[nb_option_roms].name = "pvh.bin"; - nb_option_roms++; - - return; - } - protocol = 0; - } - - if (protocol < 0x200 || !(header[0x211] & 0x01)) { - /* Low kernel */ - real_addr = 0x90000; - cmdline_addr = 0x9a000 - cmdline_size; - prot_addr = 0x10000; - } else if (protocol < 0x202) { - /* High but ancient kernel */ - real_addr = 0x90000; - cmdline_addr = 0x9a000 - cmdline_size; - prot_addr = 0x100000; - } else { - /* High and recent kernel */ - real_addr = 0x10000; - cmdline_addr = 0x20000; - prot_addr = 0x100000; - } - - /* highest address for loading the initrd */ - if (protocol >= 0x20c && - lduw_p(header + 0x236) & XLF_CAN_BE_LOADED_ABOVE_4G) { - /* - * Linux has supported initrd up to 4 GB for a very long time (2007, - * long before XLF_CAN_BE_LOADED_ABOVE_4G which was added in 2013), - * though it only sets initrd_max to 2 GB to "work around bootloader - * bugs". Luckily, QEMU firmware(which does something like bootloader) - * has supported this. - * - * It's believed that if XLF_CAN_BE_LOADED_ABOVE_4G is set, initrd can - * be loaded into any address. - * - * In addition, initrd_max is uint32_t simply because QEMU doesn't - * support the 64-bit boot protocol (specifically the ext_ramdisk_image - * field). - * - * Therefore here just limit initrd_max to UINT32_MAX simply as well. - */ - initrd_max = UINT32_MAX; - } else if (protocol >= 0x203) { - initrd_max = ldl_p(header + 0x22c); - } else { - initrd_max = 0x37ffffff; - } - - if (initrd_max >= x86ms->below_4g_mem_size - acpi_data_size) { - initrd_max = x86ms->below_4g_mem_size - acpi_data_size - 1; - } - - fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr); - fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(kernel_cmdline) + 1); - fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline); - sev_load_ctx.cmdline_data = (char *)kernel_cmdline; - sev_load_ctx.cmdline_size = strlen(kernel_cmdline) + 1; - - if (protocol >= 0x202) { - stl_p(header + 0x228, cmdline_addr); - } else { - stw_p(header + 0x20, 0xA33F); - stw_p(header + 0x22, cmdline_addr - real_addr); - } - - /* handle vga= parameter */ - vmode = strstr(kernel_cmdline, "vga="); - if (vmode) { - unsigned int video_mode; - const char *end; - int ret; - /* skip "vga=" */ - vmode += 4; - if (!strncmp(vmode, "normal", 6)) { - video_mode = 0xffff; - } else if (!strncmp(vmode, "ext", 3)) { - video_mode = 0xfffe; - } else if (!strncmp(vmode, "ask", 3)) { - video_mode = 0xfffd; - } else { - ret = qemu_strtoui(vmode, &end, 0, &video_mode); - if (ret != 0 || (*end && *end != ' ')) { - fprintf(stderr, "qemu: invalid 'vga=' kernel parameter.\n"); - exit(1); - } - } - stw_p(header + 0x1fa, video_mode); - } - - /* loader type */ - /* - * High nybble = B reserved for QEMU; low nybble is revision number. - * If this code is substantially changed, you may want to consider - * incrementing the revision. - */ - if (protocol >= 0x200) { - header[0x210] = 0xB0; - } - /* heap */ - if (protocol >= 0x201) { - header[0x211] |= 0x80; /* CAN_USE_HEAP */ - stw_p(header + 0x224, cmdline_addr - real_addr - 0x200); - } - - /* load initrd */ - if (initrd_filename) { - GMappedFile *mapped_file; - gsize initrd_size; - gchar *initrd_data; - GError *gerr = NULL; - - if (protocol < 0x200) { - fprintf(stderr, "qemu: linux kernel too old to load a ram disk\n"); - exit(1); - } - - mapped_file = g_mapped_file_new(initrd_filename, false, &gerr); - if (!mapped_file) { - fprintf(stderr, "qemu: error reading initrd %s: %s\n", - initrd_filename, gerr->message); - exit(1); - } - x86ms->initrd_mapped_file = mapped_file; - - initrd_data = g_mapped_file_get_contents(mapped_file); - initrd_size = g_mapped_file_get_length(mapped_file); - if (initrd_size >= initrd_max) { - fprintf(stderr, "qemu: initrd is too large, cannot support." - "(max: %"PRIu32", need %"PRId64")\n", - initrd_max, (uint64_t)initrd_size); - exit(1); - } - - initrd_addr = (initrd_max - initrd_size) & ~4095; - - fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr); - fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size); - fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, initrd_size); - sev_load_ctx.initrd_data = initrd_data; - sev_load_ctx.initrd_size = initrd_size; - - stl_p(header + 0x218, initrd_addr); - stl_p(header + 0x21c, initrd_size); - } - - /* load kernel and setup */ - setup_size = header[0x1f1]; - if (setup_size == 0) { - setup_size = 4; - } - setup_size = (setup_size + 1) * 512; - if (setup_size > kernel_size) { - fprintf(stderr, "qemu: invalid kernel header\n"); - exit(1); - } - kernel_size -= setup_size; - - setup = g_malloc(setup_size); - kernel = g_malloc(kernel_size); - fseek(f, 0, SEEK_SET); - if (fread(setup, 1, setup_size, f) != setup_size) { - fprintf(stderr, "fread() failed\n"); - exit(1); - } - if (fread(kernel, 1, kernel_size, f) != kernel_size) { - fprintf(stderr, "fread() failed\n"); - exit(1); - } - fclose(f); - - /* append dtb to kernel */ - if (dtb_filename) { - if (protocol < 0x209) { - fprintf(stderr, "qemu: Linux kernel too old to load a dtb\n"); - exit(1); - } - - dtb_size = get_image_size(dtb_filename); - if (dtb_size <= 0) { - fprintf(stderr, "qemu: error reading dtb %s: %s\n", - dtb_filename, strerror(errno)); - exit(1); - } - - setup_data_offset = QEMU_ALIGN_UP(kernel_size, 16); - kernel_size = setup_data_offset + sizeof(struct setup_data) + dtb_size; - kernel = g_realloc(kernel, kernel_size); - - stq_p(header + 0x250, prot_addr + setup_data_offset); - - setup_data = (struct setup_data *)(kernel + setup_data_offset); - setup_data->next = 0; - setup_data->type = cpu_to_le32(SETUP_DTB); - setup_data->len = cpu_to_le32(dtb_size); - - load_image_size(dtb_filename, setup_data->data, dtb_size); - } - - /* - * If we're starting an encrypted VM, it will be OVMF based, which uses the - * efi stub for booting and doesn't require any values to be placed in the - * kernel header. We therefore don't update the header so the hash of the - * kernel on the other side of the fw_cfg interface matches the hash of the - * file the user passed in. - */ - if (!sev_enabled()) { - memcpy(setup, header, MIN(sizeof(header), setup_size)); - } - - fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, prot_addr); - fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, kernel_size); - fw_cfg_add_bytes(fw_cfg, FW_CFG_KERNEL_DATA, kernel, kernel_size); - sev_load_ctx.kernel_data = (char *)kernel; - sev_load_ctx.kernel_size = kernel_size; - - fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_ADDR, real_addr); - fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, setup_size); - fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, setup, setup_size); - sev_load_ctx.setup_data = (char *)setup; - sev_load_ctx.setup_size = setup_size; - - if (sev_enabled()) { - sev_add_kernel_loader_hashes(&sev_load_ctx, &error_fatal); - } - - option_rom[nb_option_roms].bootindex = 0; - option_rom[nb_option_roms].name = "linuxboot.bin"; - if (linuxboot_dma_enabled && fw_cfg_dma_enabled(fw_cfg)) { - option_rom[nb_option_roms].name = "linuxboot_dma.bin"; - } - nb_option_roms++; -} - -void x86_isa_bios_init(MemoryRegion *isa_bios, MemoryRegion *isa_memory, - MemoryRegion *bios, bool read_only) -{ - uint64_t bios_size = memory_region_size(bios); - uint64_t isa_bios_size = MIN(bios_size, 128 * KiB); - - memory_region_init_alias(isa_bios, NULL, "isa-bios", bios, - bios_size - isa_bios_size, isa_bios_size); - memory_region_add_subregion_overlap(isa_memory, 1 * MiB - isa_bios_size, - isa_bios, 1); - memory_region_set_readonly(isa_bios, read_only); -} - -void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware, - MemoryRegion *rom_memory, bool isapc_ram_fw) -{ - const char *bios_name; - char *filename; - int bios_size; - ssize_t ret; - - /* BIOS load */ - bios_name = MACHINE(x86ms)->firmware ?: default_firmware; - filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name); - if (filename) { - bios_size = get_image_size(filename); - } else { - bios_size = -1; - } - if (bios_size <= 0 || - (bios_size % 65536) != 0) { - goto bios_error; - } - memory_region_init_ram(&x86ms->bios, NULL, "pc.bios", bios_size, - &error_fatal); - if (sev_enabled()) { - /* - * The concept of a "reset" simply doesn't exist for - * confidential computing guests, we have to destroy and - * re-launch them instead. So there is no need to register - * the firmware as rom to properly re-initialize on reset. - * Just go for a straight file load instead. - */ - void *ptr = memory_region_get_ram_ptr(&x86ms->bios); - load_image_size(filename, ptr, bios_size); - x86_firmware_configure(ptr, bios_size); - } else { - memory_region_set_readonly(&x86ms->bios, !isapc_ram_fw); - ret = rom_add_file_fixed(bios_name, (uint32_t)(-bios_size), -1); - if (ret != 0) { - goto bios_error; - } - } - g_free(filename); - - /* map the last 128KB of the BIOS in ISA space */ - x86_isa_bios_init(&x86ms->isa_bios, rom_memory, &x86ms->bios, - !isapc_ram_fw); - - /* map all the bios at the top of memory */ - memory_region_add_subregion(rom_memory, - (uint32_t)(-bios_size), - &x86ms->bios); - return; - -bios_error: - fprintf(stderr, "qemu: could not load PC BIOS '%s'\n", bios_name); - exit(1); -} - bool x86_machine_is_smm_enabled(const X86MachineState *x86ms) { bool smm_available = false; diff --git a/hw/intc/ioapic-stub.c b/hw/intc/ioapic-stub.c new file mode 100644 index 0000000000..4dcd86248d --- /dev/null +++ b/hw/intc/ioapic-stub.c @@ -0,0 +1,29 @@ +/* + * ioapic.c IOAPIC emulation logic + * + * Copyright (c) 2004-2005 Fabrice Bellard + * + * Split the ioapic logic from apic.c + * Xiantao Zhang <xiantao.zhang@intel.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/intc/ioapic.h" + +void ioapic_eoi_broadcast(int vector) +{ +} diff --git a/hw/intc/meson.build b/hw/intc/meson.build index f4b540e6a8..0d1b7d0a43 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -20,7 +20,7 @@ system_ss.add(when: 'CONFIG_GOLDFISH_PIC', if_true: files('goldfish_pic.c')) system_ss.add(when: 'CONFIG_HEATHROW_PIC', if_true: files('heathrow_pic.c')) system_ss.add(when: 'CONFIG_I8259', if_true: files('i8259_common.c', 'i8259.c')) system_ss.add(when: 'CONFIG_IMX', if_true: files('imx_avic.c', 'imx_gpcv2.c')) -system_ss.add(when: 'CONFIG_IOAPIC', if_true: files('ioapic_common.c')) +system_ss.add(when: 'CONFIG_IOAPIC', if_true: files('ioapic_common.c'), if_false: files('ioapic-stub.c')) system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_intc.c')) system_ss.add(when: 'CONFIG_OPENPIC', if_true: files('openpic.c')) system_ss.add(when: 'CONFIG_PL190', if_true: files('pl190.c')) diff --git a/hw/intc/s390_flic.c b/hw/intc/s390_flic.c index f4a848460b..7f93080087 100644 --- a/hw/intc/s390_flic.c +++ b/hw/intc/s390_flic.c @@ -405,6 +405,8 @@ static void qemu_s390_flic_class_init(ObjectClass *oc, void *data) static Property s390_flic_common_properties[] = { DEFINE_PROP_UINT32("adapter_routes_max_batch", S390FLICState, adapter_routes_max_batch, ADAPTER_ROUTES_MAX_GSI), + DEFINE_PROP_BOOL("migration-enabled", S390FLICState, + migration_enabled, true), DEFINE_PROP_END_OF_LIST(), }; @@ -457,7 +459,9 @@ type_init(qemu_s390_flic_register_types) static bool adapter_info_so_needed(void *opaque) { - return css_migration_enabled(); + S390FLICState *fs = S390_FLIC_COMMON(opaque); + + return fs->migration_enabled; } const VMStateDescription vmstate_adapter_info_so = { diff --git a/hw/loongarch/Kconfig b/hw/loongarch/Kconfig index ad77502445..90a0dba9d5 100644 --- a/hw/loongarch/Kconfig +++ b/hw/loongarch/Kconfig @@ -1,7 +1,8 @@ config LOONGARCH_VIRT bool default y - depends on LOONGARCH64 + depends on LOONGARCH64 && FDT + select DEVICE_TREE select PCI select PCI_EXPRESS_GENERIC_BRIDGE imply VIRTIO_VGA diff --git a/hw/loongarch/meson.build b/hw/loongarch/meson.build index d306d82c2e..bce7ebac97 100644 --- a/hw/loongarch/meson.build +++ b/hw/loongarch/meson.build @@ -3,7 +3,7 @@ loongarch_ss.add(files( 'fw_cfg.c', 'boot.c', )) -loongarch_ss.add(when: 'CONFIG_LOONGARCH_VIRT', if_true: [files('virt.c'), fdt]) +loongarch_ss.add(when: 'CONFIG_LOONGARCH_VIRT', if_true: files('virt.c')) loongarch_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-build.c')) hw_arch += {'loongarch': loongarch_ss} diff --git a/hw/mips/Kconfig b/hw/mips/Kconfig index 9bccb363eb..a7f26edebe 100644 --- a/hw/mips/Kconfig +++ b/hw/mips/Kconfig @@ -80,9 +80,10 @@ config MIPS_CPS config MIPS_BOSTON bool default y - depends on MIPS64 && !TARGET_BIG_ENDIAN + depends on MIPS64 && !TARGET_BIG_ENDIAN && FDT imply PCI_DEVICES imply TEST_DEVICES + select DEVICE_TREE select FITLOADER select MIPS_CPS select PCI_EXPRESS_XILINX diff --git a/hw/mips/meson.build b/hw/mips/meson.build index f06d88f343..ca37c42d90 100644 --- a/hw/mips/meson.build +++ b/hw/mips/meson.build @@ -9,7 +9,7 @@ if 'CONFIG_TCG' in config_all_accel mips_ss.add(when: 'CONFIG_JAZZ', if_true: files('jazz.c')) mips_ss.add(when: 'CONFIG_MIPSSIM', if_true: files('mipssim.c')) mips_ss.add(when: 'CONFIG_FULOONG', if_true: files('fuloong2e.c')) -mips_ss.add(when: 'CONFIG_MIPS_BOSTON', if_true: [files('boston.c'), fdt]) +mips_ss.add(when: 'CONFIG_MIPS_BOSTON', if_true: files('boston.c')) endif hw_arch += {'mips': mips_ss} diff --git a/hw/openrisc/Kconfig b/hw/openrisc/Kconfig index 9c9015e0a5..76b953c62c 100644 --- a/hw/openrisc/Kconfig +++ b/hw/openrisc/Kconfig @@ -2,6 +2,7 @@ config OR1K_SIM bool default y depends on OPENRISC + select DEVICE_TREE select SERIAL select OPENCORES_ETH select OMPIC @@ -14,6 +15,7 @@ config OR1K_VIRT imply PCI_DEVICES imply VIRTIO_VGA imply TEST_DEVICES + select DEVICE_TREE select PCI select PCI_EXPRESS_GENERIC_BRIDGE select GOLDFISH_RTC diff --git a/hw/openrisc/meson.build b/hw/openrisc/meson.build index 2dbc6365bb..82f1f0ef1c 100644 --- a/hw/openrisc/meson.build +++ b/hw/openrisc/meson.build @@ -1,7 +1,7 @@ openrisc_ss = ss.source_set() openrisc_ss.add(files('cputimer.c')) openrisc_ss.add(files('boot.c')) -openrisc_ss.add(when: 'CONFIG_OR1K_SIM', if_true: [files('openrisc_sim.c'), fdt]) -openrisc_ss.add(when: 'CONFIG_OR1K_VIRT', if_true: [files('virt.c'), fdt]) +openrisc_ss.add(when: 'CONFIG_OR1K_SIM', if_true: files('openrisc_sim.c')) +openrisc_ss.add(when: 'CONFIG_OR1K_VIRT', if_true: files('virt.c')) hw_arch += {'openrisc': openrisc_ss} diff --git a/hw/ppc/Kconfig b/hw/ppc/Kconfig index 78f83e78ce..347212f4db 100644 --- a/hw/ppc/Kconfig +++ b/hw/ppc/Kconfig @@ -1,7 +1,7 @@ config PSERIES bool default y - depends on PPC64 + depends on PPC64 && FDT imply USB_OHCI_PCI imply PCI_DEVICES imply TEST_DEVICES @@ -26,7 +26,7 @@ config SPAPR_RNG config POWERNV bool default y - depends on PPC64 + depends on PPC64 && FDT imply PCI_DEVICES imply TEST_DEVICES select ISA_IPMI_BT @@ -52,7 +52,7 @@ config PPC405 config PPC440 bool default y - depends on PPC + depends on PPC && FDT imply PCI_DEVICES imply TEST_DEVICES imply E1000_PCI @@ -71,7 +71,7 @@ config PPC4XX config SAM460EX bool default y - depends on PPC + depends on PPC && FDT select PFLASH_CFI01 select IDE_SII3112 select M41T80 @@ -168,19 +168,19 @@ config E500 config E500PLAT bool default y - depends on PPC + depends on PPC && FDT select E500 config MPC8544DS bool default y - depends on PPC + depends on PPC && FDT select E500 config VIRTEX bool default y - depends on PPC + depends on PPC && FDT select PPC4XX select PFLASH_CFI01 select SERIAL @@ -193,6 +193,7 @@ config FW_CFG_PPC bool config FDT_PPC + select DEVICE_TREE bool config VOF diff --git a/hw/ppc/meson.build b/hw/ppc/meson.build index d096636ee7..3ebbf329bc 100644 --- a/hw/ppc/meson.build +++ b/hw/ppc/meson.build @@ -3,9 +3,7 @@ ppc_ss.add(files( 'ppc.c', 'ppc_booke.c', )) -ppc_ss.add(when: 'CONFIG_FDT_PPC', if_true: [files( - 'fdt.c', -), fdt]) +ppc_ss.add(when: 'CONFIG_FDT_PPC', if_true: files('fdt.c')) ppc_ss.add(when: 'CONFIG_FW_CFG_PPC', if_true: files('fw_cfg.c')) # IBM pSeries (sPAPR) diff --git a/hw/riscv/Kconfig b/hw/riscv/Kconfig index 5f5f9e31bb..a2030e3a6f 100644 --- a/hw/riscv/Kconfig +++ b/hw/riscv/Kconfig @@ -12,6 +12,7 @@ config MICROCHIP_PFSOC depends on RISCV64 select CADENCE_SDHCI select CPU_CLUSTER + select DEVICE_TREE select MCHP_PFSOC_DMC select MCHP_PFSOC_IOSCB select MCHP_PFSOC_MMUART @@ -37,6 +38,7 @@ config RISCV_VIRT imply VIRTIO_VGA imply TEST_DEVICES imply TPM_TIS_SYSBUS + select DEVICE_TREE select RISCV_NUMA select GOLDFISH_RTC select PCI @@ -82,6 +84,7 @@ config SIFIVE_U depends on RISCV32 || RISCV64 select CADENCE select CPU_CLUSTER + select DEVICE_TREE select RISCV_ACLINT select SIFIVE_GPIO select SIFIVE_PDMA @@ -99,6 +102,7 @@ config SPIKE bool default y depends on RISCV32 || RISCV64 + select DEVICE_TREE select RISCV_NUMA select HTIF select RISCV_ACLINT diff --git a/hw/riscv/meson.build b/hw/riscv/meson.build index 2f7ee81be3..f872674093 100644 --- a/hw/riscv/meson.build +++ b/hw/riscv/meson.build @@ -1,5 +1,5 @@ riscv_ss = ss.source_set() -riscv_ss.add(files('boot.c'), fdt) +riscv_ss.add(files('boot.c')) riscv_ss.add(when: 'CONFIG_RISCV_NUMA', if_true: files('numa.c')) riscv_ss.add(files('riscv_hart.c')) riscv_ss.add(when: 'CONFIG_OPENTITAN', if_true: files('opentitan.c')) diff --git a/hw/rtc/mc146818rtc.c b/hw/rtc/mc146818rtc.c index 3379f92748..8ccee9a385 100644 --- a/hw/rtc/mc146818rtc.c +++ b/hw/rtc/mc146818rtc.c @@ -104,16 +104,9 @@ static void rtc_coalesced_timer_update(MC146818RtcState *s) } } -static QLIST_HEAD(, MC146818RtcState) rtc_devices = - QLIST_HEAD_INITIALIZER(rtc_devices); - -void qmp_rtc_reset_reinjection(Error **errp) +void rtc_reset_reinjection(MC146818RtcState *rtc) { - MC146818RtcState *s; - - QLIST_FOREACH(s, &rtc_devices, link) { - s->irq_coalesced = 0; - } + rtc->irq_coalesced = 0; } static bool rtc_policy_slew_deliver_irq(MC146818RtcState *s) @@ -941,7 +934,6 @@ static void rtc_realizefn(DeviceState *dev, Error **errp) object_property_add_tm(OBJECT(s), "date", rtc_get_date); qdev_init_gpio_out(dev, &s->irq, 1); - QLIST_INSERT_HEAD(&rtc_devices, s, link); } MC146818RtcState *mc146818_rtc_init(ISABus *bus, int base_year, diff --git a/hw/rx/Kconfig b/hw/rx/Kconfig index b2fa2b7eec..aa9242d1ef 100644 --- a/hw/rx/Kconfig +++ b/hw/rx/Kconfig @@ -8,5 +8,6 @@ config RX62N_MCU config RX_GDBSIM bool default y - depends on RX + depends on RX && FDT + select DEVICE_TREE select RX62N_MCU diff --git a/hw/s390x/css.c b/hw/s390x/css.c index 295530963a..b2d5327dbf 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -23,6 +23,8 @@ #include "hw/s390x/s390-virtio-ccw.h" #include "hw/s390x/s390-ccw.h" +bool css_migration_enabled = true; + typedef struct CrwContainer { CRW crw; QTAILQ_ENTRY(CrwContainer) sibling; @@ -180,7 +182,7 @@ static const VMStateDescription vmstate_orb = { static bool vmstate_schdev_orb_needed(void *opaque) { - return css_migration_enabled(); + return css_migration_enabled; } static const VMStateDescription vmstate_schdev_orb = { @@ -388,7 +390,7 @@ static int subch_dev_post_load(void *opaque, int version_id) css_subch_assign(s->cssid, s->ssid, s->schid, s->devno, s); } - if (css_migration_enabled()) { + if (css_migration_enabled) { /* No compat voodoo to do ;) */ return 0; } @@ -412,7 +414,9 @@ static int subch_dev_post_load(void *opaque, int version_id) void css_register_vmstate(void) { - vmstate_register(NULL, 0, &vmstate_css, &channel_subsys); + if (css_migration_enabled) { + vmstate_register(NULL, 0, &vmstate_css, &channel_subsys); + } } IndAddr *get_indicator(hwaddr ind_addr, int len) diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 2afaf45ce6..3d0bc3e7f2 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -50,22 +50,6 @@ static Error *pv_mig_blocker; -S390CPU *s390_cpu_addr2state(uint16_t cpu_addr) -{ - static MachineState *ms; - - if (!ms) { - ms = MACHINE(qdev_get_machine()); - g_assert(ms->possible_cpus); - } - - /* CPU address corresponds to the core_id and the index */ - if (cpu_addr >= ms->possible_cpus->len) { - return NULL; - } - return S390_CPU(ms->possible_cpus->cpus[cpu_addr].cpu); -} - static S390CPU *s390x_new_cpu(const char *typename, uint32_t core_id, Error **errp) { @@ -299,11 +283,9 @@ static void ccw_init(MachineState *machine) s390_enable_css_support(s390_cpu_addr2state(0)); ret = css_create_css_image(VIRTUAL_CSSID, true); - assert(ret == 0); - if (css_migration_enabled()) { - css_register_vmstate(); - } + + css_register_vmstate(); /* Create VirtIO network adapters */ s390_create_virtio_net(BUS(css_bus), mc->default_nic); @@ -765,7 +747,6 @@ static void ccw_machine_class_init(ObjectClass *oc, void *data) s390mc->ri_allowed = true; s390mc->cpu_model_allowed = true; - s390mc->css_migration_enabled = true; s390mc->hpage_1m_allowed = true; s390mc->max_threads = 1; mc->init = ccw_init; @@ -835,11 +816,6 @@ static const TypeInfo ccw_machine_info = { }, }; -bool css_migration_enabled(void) -{ - return get_machine_class()->css_migration_enabled; -} - #define DEFINE_CCW_MACHINE(suffix, verstr, latest) \ static void ccw_machine_##suffix##_class_init(ObjectClass *oc, \ void *data) \ @@ -1195,15 +1171,15 @@ static void ccw_machine_2_9_instance_options(MachineState *machine) static void ccw_machine_2_9_class_options(MachineClass *mc) { - S390CcwMachineClass *s390mc = S390_CCW_MACHINE_CLASS(mc); static GlobalProperty compat[] = { { TYPE_S390_STATTRIB, "migration-enabled", "off", }, + { TYPE_S390_FLIC_COMMON, "migration-enabled", "off", }, }; ccw_machine_2_10_class_options(mc); compat_props_add(mc->compat_props, hw_compat_2_9, hw_compat_2_9_len); compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); - s390mc->css_migration_enabled = false; + css_migration_enabled = false; } DEFINE_CCW_MACHINE(2_9, "2.9", false); diff --git a/hw/sh4/meson.build b/hw/sh4/meson.build index 424d5674de..70e814c3a2 100644 --- a/hw/sh4/meson.build +++ b/hw/sh4/meson.build @@ -1,5 +1,5 @@ sh4_ss = ss.source_set() -sh4_ss.add(files( +sh4_ss.add(when: 'CONFIG_SH7750', if_true: files( 'sh7750.c', 'sh7750_regnames.c', )) diff --git a/hw/usb/xen-usb.c b/hw/usb/xen-usb.c index 09ec326aea..416623f956 100644 --- a/hw/usb/xen-usb.c +++ b/hw/usb/xen-usb.c @@ -1083,7 +1083,7 @@ static void usbback_event(struct XenLegacyDevice *xendev) qemu_bh_schedule(usbif->bh); } -struct XenDevOps xen_usb_ops = { +static struct XenDevOps xen_usb_ops = { .size = sizeof(struct usbback_info), .flags = DEVOPS_FLAG_NEED_GNTDEV, .init = usbback_init, @@ -1095,15 +1095,9 @@ struct XenDevOps xen_usb_ops = { .event = usbback_event, }; -#else /* USBIF_SHORT_NOT_OK */ - -static int usbback_not_supported(void) +static void xen_usb_register_backend(void) { - return -EINVAL; + xen_be_register("qusb", &xen_usb_ops); } - -struct XenDevOps xen_usb_ops = { - .backend_register = usbback_not_supported, -}; - +xen_backend_init(xen_usb_register_backend); #endif diff --git a/hw/xen/xen-bus.c b/hw/xen/xen-bus.c index fb82cc33e4..95b207ac8b 100644 --- a/hw/xen/xen-bus.c +++ b/hw/xen/xen-bus.c @@ -13,6 +13,7 @@ #include "hw/sysbus.h" #include "hw/xen/xen.h" #include "hw/xen/xen-backend.h" +#include "hw/xen/xen-legacy-backend.h" /* xen_be_init() */ #include "hw/xen/xen-bus.h" #include "hw/xen/xen-bus-helper.h" #include "monitor/monitor.h" @@ -329,6 +330,9 @@ static void xen_bus_realize(BusState *bus, Error **errp) goto fail; } + /* Initialize legacy backend core & drivers */ + xen_be_init(); + if (xs_node_scanf(xenbus->xsh, XBT_NULL, "", /* domain root node */ "domid", NULL, "%u", &domid) == 1) { xenbus->backend_id = domid; diff --git a/hw/xen/xen-hvm-common.c b/hw/xen/xen-hvm-common.c index 1627da7398..2d1b032121 100644 --- a/hw/xen/xen-hvm-common.c +++ b/hw/xen/xen-hvm-common.c @@ -872,8 +872,6 @@ void xen_register_ioreq(XenIOState *state, unsigned int max_cpus, xen_bus_init(); - xen_be_init(); - return; err: diff --git a/hw/xen/xen-legacy-backend.c b/hw/xen/xen-legacy-backend.c index 124dd5f3d6..6f0b300a42 100644 --- a/hw/xen/xen-legacy-backend.c +++ b/hw/xen/xen-legacy-backend.c @@ -622,27 +622,11 @@ void xen_be_init(void) qbus_set_bus_hotplug_handler(xen_sysbus); xen_set_dynamic_sysbus(); - - xen_be_register("vkbd", &xen_kbdmouse_ops); -#ifdef CONFIG_VIRTFS - xen_be_register("9pfs", &xen_9pfs_ops); -#endif -#ifdef CONFIG_USB_LIBUSB - xen_be_register("qusb", &xen_usb_ops); -#endif } int xen_be_register(const char *type, struct XenDevOps *ops) { char path[50]; - int rc; - - if (ops->backend_register) { - rc = ops->backend_register(); - if (rc) { - return rc; - } - } snprintf(path, sizeof(path), "device-model/%u/backends/%s", xen_domid, type); diff --git a/hw/xenpv/xen_machine_pv.c b/hw/xenpv/xen_machine_pv.c index 1130d1a147..b500ce0989 100644 --- a/hw/xenpv/xen_machine_pv.c +++ b/hw/xenpv/xen_machine_pv.c @@ -34,8 +34,7 @@ static void xen_init_pv(MachineState *machine) { setup_xen_backend_ops(); - /* Initialize backend core & drivers */ - xen_be_init(); + xen_bus_init(); switch (xen_mode) { case XEN_ATTACH: @@ -60,8 +59,6 @@ static void xen_init_pv(MachineState *machine) vga_interface_created = true; } - xen_bus_init(); - /* config cleanup hook */ atexit(xen_config_cleanup); } diff --git a/hw/xtensa/Kconfig b/hw/xtensa/Kconfig index 443b415c2b..fc5c785cfa 100644 --- a/hw/xtensa/Kconfig +++ b/hw/xtensa/Kconfig @@ -14,7 +14,8 @@ config XTENSA_VIRT config XTENSA_XTFPGA bool default y - depends on XTENSA + depends on XTENSA && FDT + select DEVICE_TREE select OPENCORES_ETH select PFLASH_CFI01 select SERIAL diff --git a/hw/xtensa/xtfpga.c b/hw/xtensa/xtfpga.c index f49e6591dc..955e8867a3 100644 --- a/hw/xtensa/xtfpga.c +++ b/hw/xtensa/xtfpga.c @@ -356,7 +356,6 @@ static void xtfpga_init(const XtfpgaBoardDesc *board, MachineState *machine) cur_tagptr = put_tag(cur_tagptr, BP_TAG_COMMAND_LINE, strlen(kernel_cmdline) + 1, kernel_cmdline); } -#ifdef CONFIG_FDT if (dtb_filename) { int fdt_size; void *fdt = load_device_tree(dtb_filename, &fdt_size); @@ -373,14 +372,6 @@ static void xtfpga_init(const XtfpgaBoardDesc *board, MachineState *machine) cur_lowmem = QEMU_ALIGN_UP(cur_lowmem + fdt_size, 4 * KiB); g_free(fdt); } -#else - if (dtb_filename) { - error_report("could not load DTB '%s': " - "FDT support is not configured in QEMU", - dtb_filename); - exit(EXIT_FAILURE); - } -#endif if (initrd_filename) { BpMemInfo initrd_location = { 0 }; int initrd_size = load_ramdisk(initrd_filename, cur_lowmem, |