diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2020-09-17 20:40:59 +0100 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2020-09-17 20:40:59 +0100 |
commit | a6a0c8394c5b0ce4cee2a1597d235d9b2b9af3c2 (patch) | |
tree | c8ea53fc15098d0e08ac06ce2ee22b190e4e6f02 /hw | |
parent | 3af984709398d61ecdcd32fb61295e6332d94392 (diff) | |
parent | 63bcfe7be09787ad6425afcaab5501b53bc26095 (diff) | |
download | qemu-a6a0c8394c5b0ce4cee2a1597d235d9b2b9af3c2.zip qemu-a6a0c8394c5b0ce4cee2a1597d235d9b2b9af3c2.tar.gz qemu-a6a0c8394c5b0ce4cee2a1597d235d9b2b9af3c2.tar.bz2 |
Merge remote-tracking branch 'remotes/kraxel/tags/microvm-20200917-pull-request' into staging
microvm: add acpi support
# gpg: Signature made Thu 17 Sep 2020 14:53:06 BST
# gpg: using RSA key 4CB6D8EED3E87138
# gpg: Good signature from "Gerd Hoffmann (work) <kraxel@redhat.com>" [full]
# gpg: aka "Gerd Hoffmann <gerd@kraxel.org>" [full]
# gpg: aka "Gerd Hoffmann (private) <kraxel@gmail.com>" [full]
# Primary key fingerprint: A032 8CFF B93A 17A7 9901 FE7D 4CB6 D8EE D3E8 7138
* remotes/kraxel/tags/microvm-20200917-pull-request: (21 commits)
microvm: enable ramfb
tests/acpi: update expected data files for microvm
tests/acpi: add microvm test
tests/acpi: allow override blkdev
tests/acpi: allow microvm test data updates.
microvm: wire up hotplug
x86: move cpu hotplug from pc to x86
x86: move acpi_dev from pc/microvm
x86: constify x86_machine_is_*_enabled
microvm/acpi: disable virtio-mmio cmdline hack
microvm/acpi: use seabios with acpi=on
microvm/acpi: use GSI 16-23 for virtio
microvm/acpi: add acpi_dsdt_add_virtio() for x86
microvm/acpi: add minimal acpi support
microvm: make virtio irq base runtime configurable
acpi: move acpi_dsdt_add_power_button() to ged
acpi: ged: add x86 device variant.
acpi: ged: add control regs
seabios: add bios-microvm.bin binary
seabios: add microvm config, update build rules
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'hw')
-rw-r--r-- | hw/acpi/generic_event_device.c | 52 | ||||
-rw-r--r-- | hw/arm/virt-acpi-build.c | 8 | ||||
-rw-r--r-- | hw/i386/Kconfig | 1 | ||||
-rw-r--r-- | hw/i386/acpi-build.c | 2 | ||||
-rw-r--r-- | hw/i386/acpi-microvm.c | 240 | ||||
-rw-r--r-- | hw/i386/acpi-microvm.h | 8 | ||||
-rw-r--r-- | hw/i386/generic_event_device_x86.c | 36 | ||||
-rw-r--r-- | hw/i386/meson.build | 3 | ||||
-rw-r--r-- | hw/i386/microvm.c | 108 | ||||
-rw-r--r-- | hw/i386/pc.c | 297 | ||||
-rw-r--r-- | hw/i386/pc_piix.c | 2 | ||||
-rw-r--r-- | hw/i386/pc_q35.c | 2 | ||||
-rw-r--r-- | hw/i386/x86.c | 275 |
13 files changed, 731 insertions, 303 deletions
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index b8abdef..6df400e 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -20,6 +20,7 @@ #include "hw/qdev-properties.h" #include "migration/vmstate.h" #include "qemu/error-report.h" +#include "sysemu/runstate.h" static const uint32_t ged_supported_events[] = { ACPI_GED_MEM_HOTPLUG_EVT, @@ -141,6 +142,14 @@ void build_ged_aml(Aml *table, const char *name, HotplugHandler *hotplug_dev, aml_append(table, dev); } +void acpi_dsdt_add_power_button(Aml *scope) +{ + Aml *dev = aml_device(ACPI_POWER_BUTTON_DEVICE); + aml_append(dev, aml_name_decl("_HID", aml_string("PNP0C0C"))); + aml_append(dev, aml_name_decl("_UID", aml_int(0))); + aml_append(scope, dev); +} + /* Memory read by the GED _EVT AML dynamic method */ static uint64_t ged_evt_read(void *opaque, hwaddr addr, unsigned size) { @@ -176,6 +185,45 @@ static const MemoryRegionOps ged_evt_ops = { }, }; +static uint64_t ged_regs_read(void *opaque, hwaddr addr, unsigned size) +{ + return 0; +} + +static void ged_regs_write(void *opaque, hwaddr addr, uint64_t data, + unsigned int size) +{ + bool slp_en; + int slp_typ; + + switch (addr) { + case ACPI_GED_REG_SLEEP_CTL: + slp_typ = (data >> 2) & 0x07; + slp_en = (data >> 5) & 0x01; + if (slp_en && slp_typ == 5) { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } + return; + case ACPI_GED_REG_SLEEP_STS: + return; + case ACPI_GED_REG_RESET: + if (data == ACPI_GED_RESET_VALUE) { + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } + return; + } +} + +static const MemoryRegionOps ged_regs_ops = { + .read = ged_regs_read, + .write = ged_regs_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 1, + }, +}; + static void acpi_ged_device_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { @@ -332,6 +380,10 @@ static void acpi_ged_initfn(Object *obj) sysbus_init_mmio(sbd, &s->container_memhp); acpi_memory_hotplug_init(&s->container_memhp, OBJECT(dev), &s->memhp_state, 0); + + memory_region_init_io(&ged_st->regs, obj, &ged_regs_ops, ged_st, + TYPE_ACPI_GED "-regs", ACPI_GED_REG_COUNT); + sysbus_init_mmio(sbd, &ged_st->regs); } static void acpi_ged_class_init(ObjectClass *class, void *data) diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 9efd7a3..6bff5e3 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -357,14 +357,6 @@ static void acpi_dsdt_add_gpio(Aml *scope, const MemMapEntry *gpio_memmap, aml_append(scope, dev); } -static void acpi_dsdt_add_power_button(Aml *scope) -{ - Aml *dev = aml_device(ACPI_POWER_BUTTON_DEVICE); - aml_append(dev, aml_name_decl("_HID", aml_string("PNP0C0C"))); - aml_append(dev, aml_name_decl("_UID", aml_int(0))); - aml_append(scope, dev); -} - static void acpi_dsdt_add_tpm(Aml *scope, VirtMachineState *vms) { PlatformBusDevice *pbus = PLATFORM_BUS_DEVICE(vms->platform_bus_dev); diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index 03e347b..d0bd8b5 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -103,6 +103,7 @@ config MICROVM select I8259 select MC146818RTC select VIRTIO_MMIO + select ACPI_HW_REDUCED config X86_IOMMU bool diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 7a5a8b3..0e0535d 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -2431,7 +2431,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) acpi_add_table(table_offsets, tables_blob); acpi_build_madt(tables_blob, tables->linker, x86ms, - ACPI_DEVICE_IF(pcms->acpi_dev), true); + ACPI_DEVICE_IF(x86ms->acpi_dev), true); vmgenid_dev = find_vmgenid_dev(); if (vmgenid_dev) { diff --git a/hw/i386/acpi-microvm.c b/hw/i386/acpi-microvm.c new file mode 100644 index 0000000..df39c5d --- /dev/null +++ b/hw/i386/acpi-microvm.c @@ -0,0 +1,240 @@ +/* Support for generating ACPI tables and passing them to Guests + * + * Copyright (C) 2008-2010 Kevin O'Connor <kevin@koconnor.net> + * Copyright (C) 2006 Fabrice Bellard + * Copyright (C) 2013 Red Hat Inc + * + * Author: Michael S. Tsirkin <mst@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program 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 General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/cutils.h" +#include "qapi/error.h" + +#include "exec/memory.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/aml-build.h" +#include "hw/acpi/bios-linker-loader.h" +#include "hw/acpi/generic_event_device.h" +#include "hw/acpi/utils.h" +#include "hw/boards.h" +#include "hw/i386/fw_cfg.h" +#include "hw/i386/microvm.h" +#include "hw/virtio/virtio-mmio.h" + +#include "acpi-common.h" +#include "acpi-microvm.h" + +static void acpi_dsdt_add_virtio(Aml *scope, + MicrovmMachineState *mms) +{ + gchar *separator; + long int index; + BusState *bus; + BusChild *kid; + + bus = sysbus_get_default(); + QTAILQ_FOREACH(kid, &bus->children, sibling) { + DeviceState *dev = kid->child; + Object *obj = object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MMIO); + + if (obj) { + VirtIOMMIOProxy *mmio = VIRTIO_MMIO(obj); + VirtioBusState *mmio_virtio_bus = &mmio->bus; + BusState *mmio_bus = &mmio_virtio_bus->parent_obj; + + if (QTAILQ_EMPTY(&mmio_bus->children)) { + continue; + } + separator = g_strrstr(mmio_bus->name, "."); + if (!separator) { + continue; + } + if (qemu_strtol(separator + 1, NULL, 10, &index) != 0) { + continue; + } + + uint32_t irq = mms->virtio_irq_base + index; + hwaddr base = VIRTIO_MMIO_BASE + index * 512; + hwaddr size = 512; + + Aml *dev = aml_device("VR%02u", (unsigned)index); + aml_append(dev, aml_name_decl("_HID", aml_string("LNRO0005"))); + aml_append(dev, aml_name_decl("_UID", aml_int(index))); + aml_append(dev, aml_name_decl("_CCA", aml_int(1))); + + Aml *crs = aml_resource_template(); + aml_append(crs, aml_memory32_fixed(base, size, AML_READ_WRITE)); + aml_append(crs, + aml_interrupt(AML_CONSUMER, AML_LEVEL, AML_ACTIVE_HIGH, + AML_EXCLUSIVE, &irq, 1)); + aml_append(dev, aml_name_decl("_CRS", crs)); + aml_append(scope, dev); + } + } +} + +static void +build_dsdt_microvm(GArray *table_data, BIOSLinker *linker, + MicrovmMachineState *mms) +{ + X86MachineState *x86ms = X86_MACHINE(mms); + Aml *dsdt, *sb_scope, *scope, *pkg; + bool ambiguous; + Object *isabus; + + isabus = object_resolve_path_type("", TYPE_ISA_BUS, &ambiguous); + assert(isabus); + assert(!ambiguous); + + dsdt = init_aml_allocator(); + + /* Reserve space for header */ + acpi_data_push(dsdt->buf, sizeof(AcpiTableHeader)); + + sb_scope = aml_scope("_SB"); + fw_cfg_add_acpi_dsdt(sb_scope, x86ms->fw_cfg); + isa_build_aml(ISA_BUS(isabus), sb_scope); + build_ged_aml(sb_scope, GED_DEVICE, x86ms->acpi_dev, + GED_MMIO_IRQ, AML_SYSTEM_MEMORY, GED_MMIO_BASE); + acpi_dsdt_add_power_button(sb_scope); + acpi_dsdt_add_virtio(sb_scope, mms); + aml_append(dsdt, sb_scope); + + /* ACPI 5.0: Table 7-209 System State Package */ + scope = aml_scope("\\"); + pkg = aml_package(4); + aml_append(pkg, aml_int(ACPI_GED_SLP_TYP_S5)); + aml_append(pkg, aml_int(0)); /* ignored */ + aml_append(pkg, aml_int(0)); /* reserved */ + aml_append(pkg, aml_int(0)); /* reserved */ + aml_append(scope, aml_name_decl("_S5", pkg)); + 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, 2, NULL, NULL); + free_aml_allocator(); +} + +static void acpi_build_microvm(AcpiBuildTables *tables, + MicrovmMachineState *mms) +{ + MachineState *machine = MACHINE(mms); + X86MachineState *x86ms = X86_MACHINE(mms); + GArray *table_offsets; + GArray *tables_blob = tables->table_data; + unsigned dsdt, xsdt; + AcpiFadtData pmfadt = { + /* ACPI 5.0: 4.1 Hardware-Reduced ACPI */ + .rev = 5, + .flags = ((1 << ACPI_FADT_F_HW_REDUCED_ACPI) | + (1 << ACPI_FADT_F_RESET_REG_SUP)), + + /* ACPI 5.0: 4.8.3.7 Sleep Control and Status Registers */ + .sleep_ctl = { + .space_id = AML_AS_SYSTEM_MEMORY, + .bit_width = 8, + .address = GED_MMIO_BASE_REGS + ACPI_GED_REG_SLEEP_CTL, + }, + .sleep_sts = { + .space_id = AML_AS_SYSTEM_MEMORY, + .bit_width = 8, + .address = GED_MMIO_BASE_REGS + ACPI_GED_REG_SLEEP_STS, + }, + + /* ACPI 5.0: 4.8.3.6 Reset Register */ + .reset_reg = { + .space_id = AML_AS_SYSTEM_MEMORY, + .bit_width = 8, + .address = GED_MMIO_BASE_REGS + ACPI_GED_REG_RESET, + }, + .reset_val = ACPI_GED_RESET_VALUE, + }; + + table_offsets = g_array_new(false, true /* clear */, + sizeof(uint32_t)); + bios_linker_loader_alloc(tables->linker, + ACPI_BUILD_TABLE_FILE, tables_blob, + 64 /* Ensure FACS is aligned */, + false /* high memory */); + + dsdt = tables_blob->len; + build_dsdt_microvm(tables_blob, tables->linker, mms); + + pmfadt.dsdt_tbl_offset = &dsdt; + pmfadt.xdsdt_tbl_offset = &dsdt; + acpi_add_table(table_offsets, tables_blob); + build_fadt(tables_blob, tables->linker, &pmfadt, NULL, NULL); + + acpi_add_table(table_offsets, tables_blob); + acpi_build_madt(tables_blob, tables->linker, X86_MACHINE(machine), + ACPI_DEVICE_IF(x86ms->acpi_dev), false); + + xsdt = tables_blob->len; + build_xsdt(tables_blob, tables->linker, table_offsets, NULL, NULL); + + /* RSDP is in FSEG memory, so allocate it separately */ + { + AcpiRsdpData rsdp_data = { + /* ACPI 2.0: 5.2.4.3 RSDP Structure */ + .revision = 2, /* xsdt needs v2 */ + .oem_id = ACPI_BUILD_APPNAME6, + .xsdt_tbl_offset = &xsdt, + .rsdt_tbl_offset = NULL, + }; + build_rsdp(tables->rsdp, tables->linker, &rsdp_data); + } + + /* Cleanup memory that's no longer used. */ + g_array_free(table_offsets, true); +} + +static void acpi_build_no_update(void *build_opaque) +{ + /* nothing, microvm tables don't change at runtime */ +} + +void acpi_setup_microvm(MicrovmMachineState *mms) +{ + X86MachineState *x86ms = X86_MACHINE(mms); + AcpiBuildTables tables; + + assert(x86ms->fw_cfg); + + if (!x86_machine_is_acpi_enabled(x86ms)) { + return; + } + + acpi_build_tables_init(&tables); + acpi_build_microvm(&tables, mms); + + /* Now expose it all to Guest */ + acpi_add_rom_blob(acpi_build_no_update, NULL, + tables.table_data, + ACPI_BUILD_TABLE_FILE, + ACPI_BUILD_TABLE_MAX_SIZE); + acpi_add_rom_blob(acpi_build_no_update, NULL, + tables.linker->cmd_blob, + "etc/table-loader", 0); + acpi_add_rom_blob(acpi_build_no_update, NULL, + tables.rsdp, + ACPI_BUILD_RSDP_FILE, 0); + + acpi_build_tables_cleanup(&tables, false); +} diff --git a/hw/i386/acpi-microvm.h b/hw/i386/acpi-microvm.h new file mode 100644 index 0000000..dfe8536 --- /dev/null +++ b/hw/i386/acpi-microvm.h @@ -0,0 +1,8 @@ +#ifndef HW_I386_ACPI_MICROVM_H +#define HW_I386_ACPI_MICROVM_H + +#include "hw/i386/microvm.h" + +void acpi_setup_microvm(MicrovmMachineState *mms); + +#endif diff --git a/hw/i386/generic_event_device_x86.c b/hw/i386/generic_event_device_x86.c new file mode 100644 index 0000000..e26fb02 --- /dev/null +++ b/hw/i386/generic_event_device_x86.c @@ -0,0 +1,36 @@ +/* + * x86 variant of the generic event device for hw reduced acpi + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + */ + +#include "qemu/osdep.h" +#include "hw/acpi/generic_event_device.h" +#include "hw/i386/pc.h" + +static void acpi_ged_x86_class_init(ObjectClass *class, void *data) +{ + AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_CLASS(class); + + adevc->madt_cpu = pc_madt_cpu_entry; +} + +static const TypeInfo acpi_ged_x86_info = { + .name = TYPE_ACPI_GED_X86, + .parent = TYPE_ACPI_GED, + .class_init = acpi_ged_x86_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_HOTPLUG_HANDLER }, + { TYPE_ACPI_DEVICE_IF }, + { } + } +}; + +static void acpi_ged_x86_register_types(void) +{ + type_register_static(&acpi_ged_x86_info); +} + +type_init(acpi_ged_x86_register_types) diff --git a/hw/i386/meson.build b/hw/i386/meson.build index 63918fb..e5d109f 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -11,13 +11,14 @@ 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')) i386_ss.add(when: 'CONFIG_I440FX', if_true: files('pc_piix.c')) -i386_ss.add(when: 'CONFIG_MICROVM', if_true: files('microvm.c')) +i386_ss.add(when: 'CONFIG_MICROVM', if_true: files('microvm.c', 'acpi-microvm.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')) i386_ss.add(when: 'CONFIG_VTD', if_true: files('intel_iommu.c')) i386_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-common.c')) +i386_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device_x86.c')) i386_ss.add(when: 'CONFIG_PC', if_true: files( 'pc.c', 'pc_sysfw.c', diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c index 81d0888..60d3272 100644 --- a/hw/i386/microvm.c +++ b/hw/i386/microvm.c @@ -26,6 +26,8 @@ #include "sysemu/cpus.h" #include "sysemu/numa.h" #include "sysemu/reset.h" +#include "sysemu/runstate.h" +#include "acpi-microvm.h" #include "hw/loader.h" #include "hw/irq.h" @@ -37,17 +39,21 @@ #include "hw/timer/i8254.h" #include "hw/rtc/mc146818rtc.h" #include "hw/char/serial.h" +#include "hw/display/ramfb.h" #include "hw/i386/topology.h" #include "hw/i386/e820_memory_layout.h" #include "hw/i386/fw_cfg.h" #include "hw/virtio/virtio-mmio.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/generic_event_device.h" #include "cpu.h" #include "elf.h" #include "kvm_i386.h" #include "hw/xen/start_info.h" -#define MICROVM_BIOS_FILENAME "bios-microvm.bin" +#define MICROVM_QBOOT_FILENAME "qboot.rom" +#define MICROVM_BIOS_FILENAME "bios-microvm.bin" static void microvm_set_rtc(MicrovmMachineState *mms, ISADevice *s) { @@ -121,13 +127,25 @@ static void microvm_devices_init(MicrovmMachineState *mms) kvmclock_create(); + mms->virtio_irq_base = x86_machine_is_acpi_enabled(x86ms) ? 16 : 5; for (i = 0; i < VIRTIO_NUM_TRANSPORTS; i++) { sysbus_create_simple("virtio-mmio", VIRTIO_MMIO_BASE + i * 512, - x86ms->gsi[VIRTIO_IRQ_BASE + i]); + x86ms->gsi[mms->virtio_irq_base + i]); } /* Optional and legacy devices */ + if (x86_machine_is_acpi_enabled(x86ms)) { + DeviceState *dev = qdev_new(TYPE_ACPI_GED_X86); + qdev_prop_set_uint32(dev, "ged-event", ACPI_GED_PWR_DOWN_EVT); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, GED_MMIO_BASE); + /* sysbus_mmio_map(SYS_BUS_DEVICE(dev), 1, GED_MMIO_BASE_MEMHP); */ + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 2, GED_MMIO_BASE_REGS); + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, + x86ms->gsi[GED_MMIO_IRQ]); + sysbus_realize(SYS_BUS_DEVICE(dev), &error_fatal); + x86ms->acpi_dev = HOTPLUG_HANDLER(dev); + } if (mms->pic == ON_OFF_AUTO_ON || mms->pic == ON_OFF_AUTO_AUTO) { qemu_irq *i8259; @@ -158,7 +176,9 @@ static void microvm_devices_init(MicrovmMachineState *mms) } if (bios_name == NULL) { - bios_name = MICROVM_BIOS_FILENAME; + bios_name = x86_machine_is_acpi_enabled(x86ms) + ? MICROVM_BIOS_FILENAME + : MICROVM_QBOOT_FILENAME; } x86_bios_rom_init(get_system_memory(), true); } @@ -227,7 +247,7 @@ static void microvm_memory_init(MicrovmMachineState *mms) x86ms->ioapic_as = &address_space_memory; } -static gchar *microvm_get_mmio_cmdline(gchar *name) +static gchar *microvm_get_mmio_cmdline(gchar *name, uint32_t virtio_irq_base) { gchar *cmdline; gchar *separator; @@ -247,7 +267,7 @@ static gchar *microvm_get_mmio_cmdline(gchar *name) ret = g_snprintf(cmdline, VIRTIO_CMDLINE_MAXLEN, " virtio_mmio.device=512@0x%lx:%ld", VIRTIO_MMIO_BASE + index * 512, - VIRTIO_IRQ_BASE + index); + virtio_irq_base + index); if (ret < 0 || ret >= VIRTIO_CMDLINE_MAXLEN) { g_free(cmdline); return NULL; @@ -259,6 +279,7 @@ static gchar *microvm_get_mmio_cmdline(gchar *name) static void microvm_fix_kernel_cmdline(MachineState *machine) { X86MachineState *x86ms = X86_MACHINE(machine); + MicrovmMachineState *mms = MICROVM_MACHINE(machine); BusState *bus; BusChild *kid; char *cmdline; @@ -282,7 +303,8 @@ static void microvm_fix_kernel_cmdline(MachineState *machine) BusState *mmio_bus = &mmio_virtio_bus->parent_obj; if (!QTAILQ_EMPTY(&mmio_bus->children)) { - gchar *mmio_cmdline = microvm_get_mmio_cmdline(mmio_bus->name); + gchar *mmio_cmdline = microvm_get_mmio_cmdline + (mmio_bus->name, mms->virtio_irq_base); if (mmio_cmdline) { char *newcmd = g_strjoin(NULL, cmdline, mmio_cmdline, NULL); g_free(mmio_cmdline); @@ -299,6 +321,39 @@ static void microvm_fix_kernel_cmdline(MachineState *machine) g_free(cmdline); } +static void microvm_device_pre_plug_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + x86_cpu_pre_plug(hotplug_dev, dev, errp); +} + +static void microvm_device_plug_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + x86_cpu_plug(hotplug_dev, dev, errp); +} + +static void microvm_device_unplug_request_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + error_setg(errp, "unplug not supported by microvm"); +} + +static void microvm_device_unplug_cb(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + error_setg(errp, "unplug not supported by microvm"); +} + +static HotplugHandler *microvm_get_hotplug_handler(MachineState *machine, + DeviceState *dev) +{ + if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { + return HOTPLUG_HANDLER(machine); + } + return NULL; +} + static void microvm_machine_state_init(MachineState *machine) { MicrovmMachineState *mms = MICROVM_MACHINE(machine); @@ -322,7 +377,8 @@ static void microvm_machine_reset(MachineState *machine) CPUState *cs; X86CPU *cpu; - if (machine->kernel_filename != NULL && + if (!x86_machine_is_acpi_enabled(X86_MACHINE(machine)) && + machine->kernel_filename != NULL && mms->auto_kernel_cmdline && !mms->kernel_cmdline_fixed) { microvm_fix_kernel_cmdline(machine); mms->kernel_cmdline_fixed = true; @@ -435,6 +491,28 @@ static void microvm_machine_set_auto_kernel_cmdline(Object *obj, bool value, mms->auto_kernel_cmdline = value; } +static void microvm_machine_done(Notifier *notifier, void *data) +{ + MicrovmMachineState *mms = container_of(notifier, MicrovmMachineState, + machine_done); + + acpi_setup_microvm(mms); +} + +static void microvm_powerdown_req(Notifier *notifier, void *data) +{ + MicrovmMachineState *mms = container_of(notifier, MicrovmMachineState, + powerdown_req); + X86MachineState *x86ms = X86_MACHINE(mms); + + if (x86ms->acpi_dev) { + Object *obj = OBJECT(x86ms->acpi_dev); + AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(obj); + adevc->send_event(ACPI_DEVICE_IF(x86ms->acpi_dev), + ACPI_POWER_DOWN_STATUS); + } +} + static void microvm_machine_initfn(Object *obj) { MicrovmMachineState *mms = MICROVM_MACHINE(obj); @@ -449,11 +527,17 @@ static void microvm_machine_initfn(Object *obj) /* State */ mms->kernel_cmdline_fixed = false; + + mms->machine_done.notify = microvm_machine_done; + qemu_add_machine_init_done_notifier(&mms->machine_done); + mms->powerdown_req.notify = microvm_powerdown_req; + qemu_register_powerdown_notifier(&mms->powerdown_req); } static void microvm_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); + HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc); mc->init = microvm_machine_state_init; @@ -475,6 +559,13 @@ static void microvm_class_init(ObjectClass *oc, void *data) /* Machine class handlers */ mc->reset = microvm_machine_reset; + /* hotplug (for cpu coldplug) */ + mc->get_hotplug_handler = microvm_get_hotplug_handler; + hc->pre_plug = microvm_device_pre_plug_cb; + hc->plug = microvm_device_plug_cb; + hc->unplug_request = microvm_device_unplug_request_cb; + hc->unplug = microvm_device_unplug_cb; + object_class_property_add(oc, MICROVM_MACHINE_PIC, "OnOffAuto", microvm_machine_get_pic, microvm_machine_set_pic, @@ -514,6 +605,8 @@ static void microvm_class_init(ObjectClass *oc, void *data) object_class_property_set_description(oc, MICROVM_MACHINE_AUTO_KERNEL_CMDLINE, "Set off to disable adding virtio-mmio devices to the kernel cmdline"); + + machine_class_allow_dynamic_sysbus_dev(mc, TYPE_RAMFB_DEVICE); } static const TypeInfo microvm_machine_info = { @@ -524,6 +617,7 @@ static const TypeInfo microvm_machine_info = { .class_size = sizeof(MicrovmMachineClass), .class_init = microvm_class_init, .interfaces = (InterfaceInfo[]) { + { TYPE_HOTPLUG_HANDLER }, { } }, }; diff --git a/hw/i386/pc.c b/hw/i386/pc.c index d11daac..b553693 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -803,19 +803,6 @@ void pc_hot_add_cpu(MachineState *ms, const int64_t id, Error **errp) } } -static void rtc_set_cpus_count(ISADevice *rtc, uint16_t cpus_count) -{ - 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. - */ - rtc_set_memory(rtc, 0x5f, 0); - } else { - rtc_set_memory(rtc, 0x5f, cpus_count - 1); - } -} - static void pc_machine_done(Notifier *notifier, void *data) { @@ -825,7 +812,7 @@ void pc_machine_done(Notifier *notifier, void *data) PCIBus *bus = pcms->bus; /* set the number of CPUs */ - rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); + x86_rtc_set_cpus_count(x86ms->rtc, x86ms->boot_cpus); if (bus) { int extra_hosts = 0; @@ -1274,6 +1261,7 @@ static void pc_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { const PCMachineState *pcms = PC_MACHINE(hotplug_dev); + const X86MachineState *x86ms = X86_MACHINE(hotplug_dev); const PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms); const MachineState *ms = MACHINE(hotplug_dev); const bool is_nvdimm = object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM); @@ -1285,7 +1273,7 @@ static void pc_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, * but pcms->acpi_dev is still created. Check !acpi_enabled in * addition to cover this case. */ - if (!pcms->acpi_dev || !x86_machine_is_acpi_enabled(X86_MACHINE(pcms))) { + if (!x86ms->acpi_dev || !x86_machine_is_acpi_enabled(x86ms)) { error_setg(errp, "memory hotplug is not enabled: missing acpi device or acpi disabled"); return; @@ -1296,7 +1284,7 @@ static void pc_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, return; } - hotplug_handler_pre_plug(pcms->acpi_dev, dev, &local_err); + hotplug_handler_pre_plug(x86ms->acpi_dev, dev, &local_err); if (local_err) { error_propagate(errp, local_err); return; @@ -1311,6 +1299,7 @@ static void pc_memory_plug(HotplugHandler *hotplug_dev, { Error *local_err = NULL; PCMachineState *pcms = PC_MACHINE(hotplug_dev); + X86MachineState *x86ms = X86_MACHINE(hotplug_dev); MachineState *ms = MACHINE(hotplug_dev); bool is_nvdimm = object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM); @@ -1323,7 +1312,7 @@ static void pc_memory_plug(HotplugHandler *hotplug_dev, nvdimm_plug(ms->nvdimms_state); } - hotplug_handler_plug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &error_abort); + hotplug_handler_plug(x86ms->acpi_dev, dev, &error_abort); out: error_propagate(errp, local_err); } @@ -1331,14 +1320,14 @@ out: static void pc_memory_unplug_request(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { - PCMachineState *pcms = PC_MACHINE(hotplug_dev); + X86MachineState *x86ms = X86_MACHINE(hotplug_dev); /* * When -no-acpi is used with Q35 machine type, no ACPI is built, * but pcms->acpi_dev is still created. Check !acpi_enabled in * addition to cover this case. */ - if (!pcms->acpi_dev || !x86_machine_is_acpi_enabled(X86_MACHINE(pcms))) { + if (!x86ms->acpi_dev || !x86_machine_is_acpi_enabled(x86ms)) { error_setg(errp, "memory hotplug is not enabled: missing acpi device or acpi disabled"); return; @@ -1349,7 +1338,7 @@ static void pc_memory_unplug_request(HotplugHandler *hotplug_dev, return; } - hotplug_handler_unplug_request(HOTPLUG_HANDLER(pcms->acpi_dev), dev, + hotplug_handler_unplug_request(x86ms->acpi_dev, dev, errp); } @@ -1357,9 +1346,10 @@ static void pc_memory_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { PCMachineState *pcms = PC_MACHINE(hotplug_dev); + X86MachineState *x86ms = X86_MACHINE(hotplug_dev); Error *local_err = NULL; - hotplug_handler_unplug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err); + hotplug_handler_unplug(x86ms->acpi_dev, dev, &local_err); if (local_err) { goto out; } @@ -1370,263 +1360,6 @@ static void pc_memory_unplug(HotplugHandler *hotplug_dev, error_propagate(errp, local_err); } -static int pc_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 *pc_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), - pc_apic_cmp); - if (found_cpu && idx) { - *idx = found_cpu - ms->possible_cpus->cpus; - } - return found_cpu; -} - -static void pc_cpu_plug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) -{ - CPUArchId *found_cpu; - Error *local_err = NULL; - X86CPU *cpu = X86_CPU(dev); - PCMachineState *pcms = PC_MACHINE(hotplug_dev); - X86MachineState *x86ms = X86_MACHINE(pcms); - - if (pcms->acpi_dev) { - hotplug_handler_plug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err); - if (local_err) { - goto out; - } - } - - /* increment the number of CPUs */ - x86ms->boot_cpus++; - if (x86ms->rtc) { - 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 = pc_find_cpu_slot(MACHINE(pcms), cpu->apic_id, NULL); - found_cpu->cpu = OBJECT(dev); -out: - error_propagate(errp, local_err); -} -static void pc_cpu_unplug_request_cb(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) -{ - int idx = -1; - X86CPU *cpu = X86_CPU(dev); - PCMachineState *pcms = PC_MACHINE(hotplug_dev); - - if (!pcms->acpi_dev) { - error_setg(errp, "CPU hot unplug not supported without ACPI"); - return; - } - - pc_find_cpu_slot(MACHINE(pcms), cpu->apic_id, &idx); - assert(idx != -1); - if (idx == 0) { - error_setg(errp, "Boot CPU is unpluggable"); - return; - } - - hotplug_handler_unplug_request(HOTPLUG_HANDLER(pcms->acpi_dev), dev, - errp); -} - -static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) -{ - CPUArchId *found_cpu; - Error *local_err = NULL; - X86CPU *cpu = X86_CPU(dev); - PCMachineState *pcms = PC_MACHINE(hotplug_dev); - X86MachineState *x86ms = X86_MACHINE(pcms); - - hotplug_handler_unplug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err); - if (local_err) { - goto out; - } - - found_cpu = pc_find_cpu_slot(MACHINE(pcms), 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 */ - 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); -} - -static void pc_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); - PCMachineState *pcms = PC_MACHINE(hotplug_dev); - X86MachineState *x86ms = X86_MACHINE(pcms); - 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; - } - - init_topo_info(&topo_info, x86ms); - - env->nr_dies = x86ms->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 / x86ms->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 && x86ms->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 > x86ms->smp_dies - 1) { - error_setg(errp, "Invalid CPU die-id: %u must be in range 0:%u", - cpu->die_id, x86ms->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 = pc_find_cpu_slot(MACHINE(pcms), cpu->apic_id, &idx); - if (!cpu_slot) { - MachineState *ms = MACHINE(pcms); - - 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; - - if (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 void pc_virtio_md_pci_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { @@ -1695,7 +1428,7 @@ static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { pc_memory_pre_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { - pc_cpu_pre_plug(hotplug_dev, dev, errp); + x86_cpu_pre_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { pc_virtio_md_pci_pre_plug(hotplug_dev, dev, errp); @@ -1708,7 +1441,7 @@ static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev, if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { pc_memory_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { - pc_cpu_plug(hotplug_dev, dev, errp); + x86_cpu_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { pc_virtio_md_pci_plug(hotplug_dev, dev, errp); @@ -1721,7 +1454,7 @@ static void pc_machine_device_unplug_request_cb(HotplugHandler *hotplug_dev, if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { pc_memory_unplug_request(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { - pc_cpu_unplug_request_cb(hotplug_dev, dev, errp); + x86_cpu_unplug_request_cb(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { pc_virtio_md_pci_unplug_request(hotplug_dev, dev, errp); @@ -1737,7 +1470,7 @@ static void pc_machine_device_unplug_cb(HotplugHandler *hotplug_dev, if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { pc_memory_unplug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { - pc_cpu_unplug_cb(hotplug_dev, dev, errp); + x86_cpu_unplug_cb(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { pc_virtio_md_pci_unplug(hotplug_dev, dev, errp); diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 33fa035..6f3e78b 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -293,7 +293,7 @@ static void pc_init1(MachineState *machine, object_property_add_link(OBJECT(machine), PC_MACHINE_ACPI_DEVICE_PROP, TYPE_HOTPLUG_HANDLER, - (Object **)&pcms->acpi_dev, + (Object **)&x86ms->acpi_dev, object_property_allow_set_link, OBJ_PROP_LINK_STRONG); object_property_set_link(OBJECT(machine), PC_MACHINE_ACPI_DEVICE_PROP, diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 0cb9c18..622d039 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -240,7 +240,7 @@ static void pc_q35_init(MachineState *machine) object_property_add_link(OBJECT(machine), PC_MACHINE_ACPI_DEVICE_PROP, TYPE_HOTPLUG_HANDLER, - (Object **)&pcms->acpi_dev, + (Object **)&x86ms->acpi_dev, object_property_allow_set_link, OBJ_PROP_LINK_STRONG); object_property_set_link(OBJECT(machine), PC_MACHINE_ACPI_DEVICE_PROP, diff --git a/hw/i386/x86.c b/hw/i386/x86.c index c1954db..c2ea989 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -41,6 +41,7 @@ #include "hw/i386/topology.h" #include "hw/i386/fw_cfg.h" #include "hw/intc/i8259.h" +#include "hw/rtc/mc146818rtc.h" #include "hw/acpi/cpu_hotplug.h" #include "hw/irq.h" @@ -137,6 +138,276 @@ void x86_cpus_init(X86MachineState *x86ms, int default_cpu_version) } } +void x86_rtc_set_cpus_count(ISADevice *rtc, uint16_t cpus_count) +{ + 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. + */ + rtc_set_memory(rtc, 0x5f, 0); + } else { + rtc_set_memory(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 = OBJECT(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; + } + + init_topo_info(&topo_info, x86ms); + + env->nr_dies = x86ms->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 / x86ms->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 && x86ms->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 > x86ms->smp_dies - 1) { + error_setg(errp, "Invalid CPU die-id: %u must be in range 0:%u", + cpu->die_id, x86ms->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) { + MachineState *ms = MACHINE(x86ms); + + 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; + + if (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 x86_cpu_index_to_props(MachineState *ms, unsigned cpu_index) { @@ -821,7 +1092,7 @@ void x86_bios_rom_init(MemoryRegion *rom_memory, bool isapc_ram_fw) bios); } -bool x86_machine_is_smm_enabled(X86MachineState *x86ms) +bool x86_machine_is_smm_enabled(const X86MachineState *x86ms) { bool smm_available = false; @@ -863,7 +1134,7 @@ static void x86_machine_set_smm(Object *obj, Visitor *v, const char *name, visit_type_OnOffAuto(v, name, &x86ms->smm, errp); } -bool x86_machine_is_acpi_enabled(X86MachineState *x86ms) +bool x86_machine_is_acpi_enabled(const X86MachineState *x86ms) { if (x86ms->acpi == ON_OFF_AUTO_OFF) { return false; |