On Mon, Jul 01, 2019 at 04:47:05PM +0200, Sergio Lopez wrote: > Microvm is a machine type inspired by both NEMU and Firecracker, and > constructed after the machine model implemented by the latter. > > It's main purpose is providing users a KVM-only machine type with fast > boot times, minimal attack surface (measured as the number of IO ports > and MMIO regions exposed to the Guest) and small footprint (specially > when combined with the ongoing QEMU modularization effort). > > Normally, other than the device support provided by KVM itself, > microvm only supports virtio-mmio devices. Microvm also includes a > legacy mode, which adds an ISA bus with a 16550A serial port, useful > for being able to see the early boot kernel messages. > > Microvm only supports booting PVH-enabled Linux ELF images. Booting > other PVH-enabled kernels may be possible, but due to the lack of ACPI > and firmware, we're relying on the command line for specifying the > location of the virtio-mmio transports. If there's an interest on > using this machine type with other kernels, we'll try to find some > kind of middle ground solution. > > Signed-off-by: Sergio Lopez <s...@redhat.com> > --- > default-configs/i386-softmmu.mak | 1 + > hw/i386/Kconfig | 4 + > hw/i386/Makefile.objs | 1 + > hw/i386/microvm.c | 500 +++++++++++++++++++++++++++++++ > include/hw/i386/microvm.h | 77 +++++ > 5 files changed, 583 insertions(+) > create mode 100644 hw/i386/microvm.c > create mode 100644 include/hw/i386/microvm.h > > diff --git a/default-configs/i386-softmmu.mak > b/default-configs/i386-softmmu.mak > index cd5ea391e8..338f07420f 100644 > --- a/default-configs/i386-softmmu.mak > +++ b/default-configs/i386-softmmu.mak > @@ -26,3 +26,4 @@ CONFIG_ISAPC=y > CONFIG_I440FX=y > CONFIG_Q35=y > CONFIG_ACPI_PCI=y > +CONFIG_MICROVM=y > diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig > index 9817888216..94c565d8db 100644 > --- a/hw/i386/Kconfig > +++ b/hw/i386/Kconfig > @@ -87,6 +87,10 @@ config Q35 > select VMMOUSE > select FW_CFG_DMA > > +config MICROVM > + bool > + select VIRTIO_MMIO > + > config VTD > bool > > diff --git a/hw/i386/Makefile.objs b/hw/i386/Makefile.objs > index c5f20bbd72..7bffca413e 100644 > --- a/hw/i386/Makefile.objs > +++ b/hw/i386/Makefile.objs > @@ -4,6 +4,7 @@ obj-y += pvh.o > obj-y += pc.o > obj-$(CONFIG_I440FX) += pc_piix.o > obj-$(CONFIG_Q35) += pc_q35.o > +obj-$(CONFIG_MICROVM) += mptable.o microvm.o > obj-y += fw_cfg.o pc_sysfw.o > obj-y += x86-iommu.o > obj-$(CONFIG_VTD) += intel_iommu.o > diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c > new file mode 100644 > index 0000000000..8b5efe9e45 > --- /dev/null > +++ b/hw/i386/microvm.c > @@ -0,0 +1,500 @@ > +/* > + * Copyright (c) 2018 Intel Corporation > + * Copyright (c) 2019 Red Hat, Inc. > + * > + * 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. > + * > + * This program is distributed in the hope 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/error-report.h" > +#include "qemu/cutils.h" > +#include "qapi/error.h" > +#include "qapi/visitor.h" > +#include "sysemu/sysemu.h" > +#include "sysemu/cpus.h" > +#include "sysemu/numa.h" > + > +#include "hw/loader.h" > +#include "hw/nmi.h" > +#include "hw/kvm/clock.h" > +#include "hw/i386/microvm.h" > +#include "hw/i386/pc.h" > +#include "target/i386/cpu.h" > +#include "hw/timer/i8254.h" > +#include "hw/char/serial.h" > +#include "hw/i386/topology.h" > +#include "hw/virtio/virtio-mmio.h" > +#include "hw/i386/mptable.h" > + > +#include "cpu.h" > +#include "elf.h" > +#include "pvh.h" > +#include "kvm_i386.h" > +#include "hw/xen/start_info.h" > + > +static void microvm_gsi_handler(void *opaque, int n, int level) > +{ > + qemu_irq *ioapic_irq = opaque; > + > + qemu_set_irq(ioapic_irq[n], level); > +} > + > +static void microvm_legacy_init(MicrovmMachineState *mms) > +{ > + ISABus *isa_bus; > + GSIState *gsi_state; > + qemu_irq *i8259; > + int i; > + > + assert(kvm_irqchip_in_kernel()); > + gsi_state = g_malloc0(sizeof(*gsi_state)); > + mms->gsi = qemu_allocate_irqs(gsi_handler, gsi_state, GSI_NUM_PINS); > + > + isa_bus = isa_bus_new(NULL, get_system_memory(), get_system_io(), > + &error_abort); > + isa_bus_irqs(isa_bus, mms->gsi); > + > + assert(kvm_pic_in_kernel()); > + i8259 = kvm_i8259_init(isa_bus); > + > + for (i = 0; i < ISA_NUM_IRQS; i++) { > + gsi_state->i8259_irq[i] = i8259[i]; > + } > + > + kvm_pit_init(isa_bus, 0x40); > + > + for (i = 0; i < VIRTIO_NUM_TRANSPORTS; i++) { > + int nirq = VIRTIO_IRQ_BASE + i; > + ISADevice *isadev = isa_create(isa_bus, TYPE_ISA_SERIAL); > + qemu_irq mmio_irq; > + > + isa_init_irq(isadev, &mmio_irq, nirq); > + sysbus_create_simple("virtio-mmio", > + VIRTIO_MMIO_BASE + i * 512, > + mms->gsi[VIRTIO_IRQ_BASE + i]); > + } > + > + g_free(i8259); > + > + serial_hds_isa_init(isa_bus, 0, 1); > +} > + > +static void microvm_ioapic_init(MicrovmMachineState *mms) > +{ > + qemu_irq *ioapic_irq; > + DeviceState *ioapic_dev; > + SysBusDevice *d; > + int i; > + > + assert(kvm_irqchip_in_kernel()); > + ioapic_irq = g_new0(qemu_irq, IOAPIC_NUM_PINS); > + kvm_pc_setup_irq_routing(true); > + > + assert(kvm_ioapic_in_kernel()); > + ioapic_dev = qdev_create(NULL, "kvm-ioapic"); > + > + object_property_add_child(qdev_get_machine(), > + "ioapic", OBJECT(ioapic_dev), NULL); > + > + qdev_init_nofail(ioapic_dev); > + d = SYS_BUS_DEVICE(ioapic_dev); > + sysbus_mmio_map(d, 0, IO_APIC_DEFAULT_ADDRESS); > + > + for (i = 0; i < IOAPIC_NUM_PINS; i++) { > + ioapic_irq[i] = qdev_get_gpio_in(ioapic_dev, i); > + } > + > + mms->gsi = qemu_allocate_irqs(microvm_gsi_handler, > + ioapic_irq, IOAPIC_NUM_PINS); > + > + for (i = 0; i < VIRTIO_NUM_TRANSPORTS; i++) { > + sysbus_create_simple("virtio-mmio", > + VIRTIO_MMIO_BASE + i * 512, > + mms->gsi[VIRTIO_IRQ_BASE + i]); > + } > +} > + > +static void microvm_memory_init(MicrovmMachineState *mms) > +{ > + MachineState *machine = MACHINE(mms); > + MemoryRegion *ram, *ram_below_4g, *ram_above_4g; > + MemoryRegion *system_memory = get_system_memory(); > + > + if (machine->ram_size > MICROVM_MAX_BELOW_4G) { > + mms->above_4g_mem_size = machine->ram_size - MICROVM_MAX_BELOW_4G; > + mms->below_4g_mem_size = MICROVM_MAX_BELOW_4G; > + } else { > + mms->above_4g_mem_size = 0; > + mms->below_4g_mem_size = machine->ram_size; > + } > + > + ram = g_malloc(sizeof(*ram)); > + memory_region_allocate_system_memory(ram, NULL, "microvm.ram", > + machine->ram_size); > + > + ram_below_4g = g_malloc(sizeof(*ram_below_4g)); > + memory_region_init_alias(ram_below_4g, NULL, "ram-below-4g", ram, > + 0, mms->below_4g_mem_size); > + memory_region_add_subregion(system_memory, 0, ram_below_4g); > + > + e820_add_entry(0, mms->below_4g_mem_size, E820_RAM); > + > + if (mms->above_4g_mem_size > 0) { > + ram_above_4g = g_malloc(sizeof(*ram_above_4g)); > + memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram, > + mms->below_4g_mem_size, > + mms->above_4g_mem_size); > + memory_region_add_subregion(system_memory, 0x100000000ULL, > + ram_above_4g); > + e820_add_entry(0x100000000ULL, mms->above_4g_mem_size, E820_RAM); > + } > +} > + > +static void microvm_cpus_init(const char *typename, Error **errp) > +{ > + int i; > + > + for (i = 0; i < smp_cpus; i++) { > + Object *cpu = NULL; > + Error *local_err = NULL; > + > + cpu = object_new(typename); > + > + object_property_set_uint(cpu, i, "apic-id", &local_err); > + object_property_set_bool(cpu, true, "realized", &local_err); > + > + object_unref(cpu); > + error_propagate(errp, local_err); > + } > +} > + > +static void microvm_machine_state_init(MachineState *machine) > +{ > + MicrovmMachineState *mms = MICROVM_MACHINE(machine); > + Error *local_err = NULL; > + > + if (machine->kernel_filename == NULL) { > + error_report("missing kernel image file name, required by microvm"); > + exit(1); > + }
Could it be useful to support initrd as well? I'm thinking a possibility to a microvm to use only the initrd without a block device. In this case, Linux expects the initrd address and size in the first element of the modlist in the 'struct hvm_start_info'. See pc-bios/optionrom/pvh_main.c Cheers, Stefano