build: Add support for building firecracker hypervisor

Support building with `make HYPERVISOR=firecracker`.

Notes:

- Firecracker is currently only supported on x86_64, hence the
  architecture check.

- The template file `cli/config/configuration-fc.toml.in` is based
  on `cli/config/configuration.toml.in`.

Fixes #1105.

Signed-off-by: James O. D. Hunt <james.o.hunt@intel.com>

.gitignore

@@ -1,6 +1,7 @@
 *.o
 *.patch
 *.swp
+/cli/config/configuration-fc.toml
 /cli/config/configuration-qemu.toml
 /cli/config-generated.go
 /cli/coverage.html

Makefile

@@ -80,6 +80,7 @@ endif
 PREFIXDEPS    := $(PREFIX)
 BINDIR        := $(EXEC_PREFIX)/bin
 QEMUBINDIR    := $(PREFIXDEPS)/bin
+FCBINDIR      := $(PREFIXDEPS)/bin
 SYSCONFDIR    := /etc
 LOCALSTATEDIR := /var
 
@@ -117,15 +118,19 @@ FIRMWAREPATH :=
 # Name of default configuration file the runtime will use.
 CONFIG_FILE = configuration.toml
 
+HYPERVISOR_FC = firecracker
 HYPERVISOR_QEMU = qemu
 
 # Determines which hypervisor is specified in $(CONFIG_FILE).
 DEFAULT_HYPERVISOR = $(HYPERVISOR_QEMU)
 
 # List of hypervisors this build system can generate configuration for.
-HYPERVISORS := $(HYPERVISOR_QEMU)
+HYPERVISORS := $(HYPERVISOR_FC) $(HYPERVISOR_QEMU)
+
 QEMUPATH := $(QEMUBINDIR)/$(QEMUCMD)
 
+FCPATH = $(FCBINDIR)/$(FCCMD)
+
 SHIMCMD := $(BIN_PREFIX)-shim
 SHIMPATH := $(PKGLIBEXECDIR)/$(SHIMCMD)
 
@@ -150,9 +155,6 @@ DEFMEMSZ := 2048
 DEFMEMSLOTS := 10
 #Default number of bridges
 DEFBRIDGES := 1
-#Default network model
-DEFNETWORKMODEL := macvtap
-
 DEFDISABLEGUESTSECCOMP := true
 
 #Default entropy source
@@ -210,6 +212,29 @@ ifneq (,$(QEMUCMD))
     KERNELPATH_QEMU = $(KERNELDIR)/$(KERNELNAME_QEMU)
 endif
 
+ifneq (,$(FCCMD))
+    KNOWN_HYPERVISORS += $(HYPERVISOR_FC)
+
+    CONFIG_FILE_FC = configuration-fc.toml
+    CONFIG_FC = $(CLI_DIR)/config/$(CONFIG_FILE_FC)
+    CONFIG_FC_IN = $(CONFIG_FC).in
+
+    CONFIG_PATH_FC = $(abspath $(CONFDIR)/$(CONFIG_FILE_FC))
+    CONFIG_PATHS += $(CONFIG_PATH_FC)
+
+    SYSCONFIG_FC = $(abspath $(SYSCONFDIR)/$(CONFIG_FILE_FC))
+    SYSCONFIG_PATHS += $(SYSCONFIG_FC)
+
+    CONFIGS += $(CONFIG_FC)
+
+    # firecracker-specific options (all should be suffixed by "_FC")
+    DEFBLOCKSTORAGEDRIVER_FC := virtio-mmio
+    DEFNETWORKMODEL_FC := tcfilter
+    KERNELTYPE_FC = uncompressed
+    KERNEL_NAME_FC = $(call MAKE_KERNEL_NAME,$(KERNELTYPE_FC))
+    KERNELPATH_FC = $(KERNELDIR)/$(KERNEL_NAME_FC)
+endif
+
 ifeq (,$(KNOWN_HYPERVISORS))
     $(error "ERROR: No hypervisors known for architecture $(ARCH) (looked for: $(HYPERVISORS))")
 endif
@@ -226,6 +251,9 @@ ifeq ($(DEFAULT_HYPERVISOR),$(HYPERVISOR_QEMU))
     DEFAULT_HYPERVISOR_CONFIG_PATH = $(CONFIG_PATH_QEMU)
 endif
 
+ifeq ($(DEFAULT_HYPERVISOR),$(HYPERVISOR_FC))
+    DEFAULT_HYPERVISOR_CONFIG_PATH = $(CONFIG_PATH_FC)
+endif
 
 CONFDIR := $(DEFAULTSDIR)/$(PROJECT_DIR)
 SYSCONFDIR := $(SYSCONFDIR)/$(PROJECT_DIR)
@@ -245,6 +273,8 @@ USER_VARS += BINDIR
 USER_VARS += CONFIG_PATH
 USER_VARS += DESTDIR
 USER_VARS += DEFAULT_HYPERVISOR
+USER_VARS += FCCMD
+USER_VARS += FCPATH
 USER_VARS += SYSCONFIG
 USER_VARS += IMAGENAME
 USER_VARS += IMAGEPATH
@@ -253,6 +283,7 @@ USER_VARS += INITRDPATH
 USER_VARS += MACHINETYPE
 USER_VARS += KERNELDIR
 USER_VARS += KERNELTYPE
+USER_VARS += KERNELTYPE_FC
 USER_VARS += FIRMWAREPATH
 USER_VARS += MACHINEACCELERATORS
 USER_VARS += KERNELPARAMS
@@ -279,9 +310,11 @@ USER_VARS += DEFMAXVCPUS
 USER_VARS += DEFMEMSZ
 USER_VARS += DEFMEMSLOTS
 USER_VARS += DEFBRIDGES
+USER_VARS += DEFNETWORKMODEL_FC
 USER_VARS += DEFNETWORKMODEL_QEMU
 USER_VARS += DEFDISABLEGUESTSECCOMP
 USER_VARS += DEFDISABLEBLOCK
+USER_VARS += DEFBLOCKSTORAGEDRIVER_FC
 USER_VARS += DEFBLOCKSTORAGEDRIVER_QEMU
 USER_VARS += DEFENABLEIOTHREADS
 USER_VARS += DEFENABLEMEMPREALLOC
@@ -437,9 +470,12 @@ $(GENERATED_FILES): %: %.in Makefile VERSION
 		-e "s|@COMMIT@|$(COMMIT)|g" \
 		-e "s|@VERSION@|$(VERSION)|g" \
 		-e "s|@CONFIG_QEMU_IN@|$(CONFIG_QEMU_IN)|g" \
+		-e "s|@CONFIG_FC_IN@|$(CONFIG_FC_IN)|g" \
 		-e "s|@CONFIG_PATH@|$(CONFIG_PATH)|g" \
+		-e "s|@FCPATH@|$(FCPATH)|g" \
 		-e "s|@SYSCONFIG@|$(SYSCONFIG)|g" \
 		-e "s|@IMAGEPATH@|$(IMAGEPATH)|g" \
+		-e "s|@KERNELPATH_FC@|$(KERNELPATH_FC)|g" \
 		-e "s|@KERNELPATH_QEMU@|$(KERNELPATH_QEMU)|g" \
 		-e "s|@INITRDPATH@|$(INITRDPATH)|g" \
 		-e "s|@FIRMWAREPATH@|$(FIRMWAREPATH)|g" \
@@ -463,9 +499,11 @@ $(GENERATED_FILES): %: %.in Makefile VERSION
 		-e "s|@DEFMEMSZ@|$(DEFMEMSZ)|g" \
 		-e "s|@DEFMEMSLOTS@|$(DEFMEMSLOTS)|g" \
 		-e "s|@DEFBRIDGES@|$(DEFBRIDGES)|g" \
+		-e "s|@DEFNETWORKMODEL_FC@|$(DEFNETWORKMODEL_FC)|g" \
 		-e "s|@DEFNETWORKMODEL_QEMU@|$(DEFNETWORKMODEL_QEMU)|g" \
 		-e "s|@DEFDISABLEGUESTSECCOMP@|$(DEFDISABLEGUESTSECCOMP)|g" \
 		-e "s|@DEFDISABLEBLOCK@|$(DEFDISABLEBLOCK)|g" \
+		-e "s|@DEFBLOCKSTORAGEDRIVER_FC@|$(DEFBLOCKSTORAGEDRIVER_FC)|g" \
 		-e "s|@DEFBLOCKSTORAGEDRIVER_QEMU@|$(DEFBLOCKSTORAGEDRIVER_QEMU)|g" \
 		-e "s|@DEFENABLEIOTHREADS@|$(DEFENABLEIOTHREADS)|g" \
 		-e "s|@DEFENABLEMEMPREALLOC@|$(DEFENABLEMEMPREALLOC)|g" \
@@ -609,6 +647,9 @@ endif
 	@printf "\tdefault alternate config path (SYSCONFIG) : %s\n" $(abspath $(SYSCONFIG))
 ifneq (,$(findstring $(HYPERVISOR_QEMU),$(KNOWN_HYPERVISORS)))
 	@printf "\t$(HYPERVISOR_QEMU) hypervisor path (QEMUPATH) : %s\n" $(abspath $(QEMUPATH))
+endif
+ifneq (,$(findstring $(HYPERVISOR_FC),$(KNOWN_HYPERVISORS)))
+	@printf "\t$(HYPERVISOR_FC) hypervisor path (FCPATH) : %s\n" $(abspath $(FCPATH))
 endif
 	@printf "\tassets path (PKGDATADIR) : %s\n" $(abspath $(PKGDATADIR))
 	@printf "\tproxy+shim path (PKGLIBEXECDIR) : %s\n" $(abspath $(PKGLIBEXECDIR))

arch/amd64-options.mk

@@ -1,4 +1,4 @@
-# Copyright (c) 2018 Intel Corporation
+# Copyright (c) 2018-2019 Intel Corporation
 #
 # SPDX-License-Identifier: Apache-2.0
 #
@@ -10,3 +10,6 @@ KERNELPARAMS :=
 MACHINEACCELERATORS :=
 
 QEMUCMD := qemu-lite-system-x86_64
+
+# Firecracker binary name
+FCCMD := firecracker

cli/config/configuration-fc.toml.in

@@ -0,0 +1,291 @@
+# Copyright (c) 2017-2019 Intel Corporation
+#
+# SPDX-License-Identifier: Apache-2.0
+#
+
+# XXX: WARNING: this file is auto-generated.
+# XXX:
+# XXX: Source file: "@CONFIG_FC_IN@"
+# XXX: Project:
+# XXX:   Name: @PROJECT_NAME@
+# XXX:   Type: @PROJECT_TYPE@
+
+[hypervisor.firecracker]
+path = "@FCPATH@"
+kernel = "@KERNELPATH_FC@"
+image = "@IMAGEPATH@"
+
+# Optional space-separated list of options to pass to the guest kernel.
+# For example, use `kernel_params = "vsyscall=emulate"` if you are having
+# trouble running pre-2.15 glibc.
+#
+# WARNING: - any parameter specified here will take priority over the default
+# parameter value of the same name used to start the virtual machine.
+# Do not set values here unless you understand the impact of doing so as you
+# may stop the virtual machine from booting.
+# To see the list of default parameters, enable hypervisor debug, create a
+# container and look for 'default-kernel-parameters' log entries.
+kernel_params = "@KERNELPARAMS@"
+
+# Default number of vCPUs per SB/VM:
+# unspecified or 0                --> will be set to @DEFVCPUS@
+# < 0                             --> will be set to the actual number of physical cores
+# > 0 <= number of physical cores --> will be set to the specified number
+# > number of physical cores      --> will be set to the actual number of physical cores
+default_vcpus = 1
+
+# Default maximum number of vCPUs per SB/VM:
+# unspecified or == 0             --> will be set to the actual number of physical cores or to the maximum number
+#                                     of vCPUs supported by KVM if that number is exceeded
+# > 0 <= number of physical cores --> will be set to the specified number
+# > number of physical cores      --> will be set to the actual number of physical cores or to the maximum number
+#                                     of vCPUs supported by KVM if that number is exceeded
+# WARNING: Depending of the architecture, the maximum number of vCPUs supported by KVM is used when
+# the actual number of physical cores is greater than it.
+# WARNING: Be aware that this value impacts the virtual machine's memory footprint and CPU
+# the hotplug functionality. For example, `default_maxvcpus = 240` specifies that until 240 vCPUs
+# can be added to a SB/VM, but the memory footprint will be big. Another example, with
+# `default_maxvcpus = 8` the memory footprint will be small, but 8 will be the maximum number of
+# vCPUs supported by the SB/VM. In general, we recommend that you do not edit this variable,
+# unless you know what are you doing.
+default_maxvcpus = @DEFMAXVCPUS@
+
+# Bridges can be used to hot plug devices.
+# Limitations:
+# * Currently only pci bridges are supported
+# * Until 30 devices per bridge can be hot plugged.
+# * Until 5 PCI bridges can be cold plugged per VM.
+#   This limitation could be a bug in the kernel
+# Default number of bridges per SB/VM:
+# unspecified or 0   --> will be set to @DEFBRIDGES@
+# > 1 <= 5           --> will be set to the specified number
+# > 5                --> will be set to 5
+default_bridges = @DEFBRIDGES@
+
+# Default memory size in MiB for SB/VM.
+# If unspecified then it will be set @DEFMEMSZ@ MiB.
+default_memory = @DEFMEMSZ@
+#
+# Default memory slots per SB/VM.
+# If unspecified then it will be set @DEFMEMSLOTS@.
+# This is will determine the times that memory will be hotadded to sandbox/VM.
+#memory_slots = @DEFMEMSLOTS@
+
+# The size in MiB will be plused to max memory of hypervisor.
+# It is the memory address space for the NVDIMM devie.
+# If set block storage driver (block_device_driver) to "nvdimm",
+# should set memory_offset to the size of block device.
+# Default 0
+#memory_offset = 0
+
+# Disable block device from being used for a container's rootfs.
+# In case of a storage driver like devicemapper where a container's 
+# root file system is backed by a block device, the block device is passed
+# directly to the hypervisor for performance reasons. 
+# This flag prevents the block device from being passed to the hypervisor, 
+# 9pfs is used instead to pass the rootfs.
+disable_block_device_use = @DEFDISABLEBLOCK@
+
+# Block storage driver to be used for the hypervisor in case the container
+# rootfs is backed by a block device. This is virtio-scsi, virtio-blk
+# or nvdimm.
+block_device_driver = "@DEFBLOCKSTORAGEDRIVER_FC@"
+
+# Specifies cache-related options will be set to block devices or not.
+# Default false
+#block_device_cache_set = true
+
+# Specifies cache-related options for block devices.
+# Denotes whether use of O_DIRECT (bypass the host page cache) is enabled.
+# Default false
+#block_device_cache_direct = true
+
+# Specifies cache-related options for block devices.
+# Denotes whether flush requests for the device are ignored.
+# Default false
+#block_device_cache_noflush = true
+
+# Enable pre allocation of VM RAM, default false
+# Enabling this will result in lower container density
+# as all of the memory will be allocated and locked
+# This is useful when you want to reserve all the memory
+# upfront or in the cases where you want memory latencies
+# to be very predictable
+# Default false
+#enable_mem_prealloc = true
+
+# Enable huge pages for VM RAM, default false
+# Enabling this will result in the VM memory
+# being allocated using huge pages.
+# This is useful when you want to use vhost-user network
+# stacks within the container. This will automatically 
+# result in memory pre allocation
+#enable_hugepages = true
+
+# Enable swap of vm memory. Default false.
+# The behaviour is undefined if mem_prealloc is also set to true
+#enable_swap = true
+
+# This option changes the default hypervisor and kernel parameters
+# to enable debug output where available. This extra output is added
+# to the proxy logs, but only when proxy debug is also enabled.
+# 
+# Default false
+#enable_debug = true
+
+# Disable the customizations done in the runtime when it detects
+# that it is running on top a VMM. This will result in the runtime
+# behaving as it would when running on bare metal.
+# 
+#disable_nesting_checks = true
+
+# This is the msize used for 9p shares. It is the number of bytes 
+# used for 9p packet payload.
+#msize_9p = @DEFMSIZE9P@
+
+# If true and vsocks are supported, use vsocks to communicate directly
+# with the agent (no proxy is started).
+# Default true
+use_vsock = true
+
+# VFIO devices are hotplugged on a bridge by default. 
+# Enable hotplugging on root bus. This may be required for devices with
+# a large PCI bar, as this is a current limitation with hotplugging on 
+# a bridge. This value is valid for "pc" machine type.
+# Default false
+#hotplug_vfio_on_root_bus = true
+
+# If host doesn't support vhost_net, set to true. Thus we won't create vhost fds for nics.
+# Default false
+#disable_vhost_net = true
+#
+# Default entropy source.
+# The path to a host source of entropy (including a real hardware RNG)
+# /dev/urandom and /dev/random are two main options.
+# Be aware that /dev/random is a blocking source of entropy.  If the host
+# runs out of entropy, the VMs boot time will increase leading to get startup
+# timeouts.
+# The source of entropy /dev/urandom is non-blocking and provides a
+# generally acceptable source of entropy. It should work well for pretty much
+# all practical purposes.
+#entropy_source= "@DEFENTROPYSOURCE@"
+
+# Path to OCI hook binaries in the *guest rootfs*.
+# This does not affect host-side hooks which must instead be added to
+# the OCI spec passed to the runtime.
+#
+# You can create a rootfs with hooks by customizing the osbuilder scripts:
+# https://github.com/kata-containers/osbuilder
+#
+# Hooks must be stored in a subdirectory of guest_hook_path according to their
+# hook type, i.e. "guest_hook_path/{prestart,postart,poststop}".
+# The agent will scan these directories for executable files and add them, in
+# lexicographical order, to the lifecycle of the guest container.
+# Hooks are executed in the runtime namespace of the guest. See the official documentation:
+# https://github.com/opencontainers/runtime-spec/blob/v1.0.1/config.md#posix-platform-hooks
+# Warnings will be logged if any error is encountered will scanning for hooks,
+# but it will not abort container execution.
+#guest_hook_path = "/usr/share/oci/hooks"
+
+[factory]
+# VM templating support. Once enabled, new VMs are created from template
+# using vm cloning. They will share the same initial kernel, initramfs and
+# agent memory by mapping it readonly. It helps speeding up new container
+# creation and saves a lot of memory if there are many kata containers running
+# on the same host.
+#
+# When disabled, new VMs are created from scratch.
+#
+# Note: Requires "initrd=" to be set ("image=" is not supported).
+#
+# Default false
+#enable_template = true
+
+[proxy.@PROJECT_TYPE@]
+
+[shim.@PROJECT_TYPE@]
+path = "@SHIMPATH@"
+
+# If enabled, shim messages will be sent to the system log
+# (default: disabled)
+#enable_debug = true
+
+# If enabled, the shim will create opentracing.io traces and spans.
+# (See https://www.jaegertracing.io/docs/getting-started).
+#
+# Note: By default, the shim runs in a separate network namespace. Therefore,
+# to allow it to send trace details to the Jaeger agent running on the host,
+# it is necessary to set 'disable_new_netns=true' so that it runs in the host
+# network namespace.
+#
+# (default: disabled)
+#enable_tracing = true
+
+[agent.@PROJECT_TYPE@]
+# There is no field for this section. The goal is only to be able to
+# specify which type of agent the user wants to use.
+
+[netmon]
+# If enabled, the network monitoring process gets started when the
+# sandbox is created. This allows for the detection of some additional
+# network being added to the existing network namespace, after the
+# sandbox has been created.
+# (default: disabled)
+#enable_netmon = true
+
+# Specify the path to the netmon binary.
+path = "@NETMONPATH@"
+
+# If enabled, netmon messages will be sent to the system log
+# (default: disabled)
+#enable_debug = true
+
+[runtime]
+# If enabled, the runtime will log additional debug messages to the
+# system log
+# (default: disabled)
+#enable_debug = true
+#
+# Internetworking model
+# Determines how the VM should be connected to the
+# the container network interface
+# Options:
+#
+#   - bridged
+#     Uses a linux bridge to interconnect the container interface to
+#     the VM. Works for most cases except macvlan and ipvlan.
+#
+#   - macvtap
+#     Used when the Container network interface can be bridged using
+#     macvtap.
+#
+#   - none
+#     Used when customize network. Only creates a tap device. No veth pair.
+#
+#   - tcfilter
+#     Uses tc filter rules to redirect traffic from the network interface
+#     provided by plugin to a tap interface connected to the VM.
+#
+internetworking_model="@DEFNETWORKMODEL_FC@"
+
+# disable guest seccomp
+# Determines whether container seccomp profiles are passed to the virtual
+# machine and applied by the kata agent. If set to true, seccomp is not applied
+# within the guest
+# (default: true)
+disable_guest_seccomp=@DEFDISABLEGUESTSECCOMP@
+
+# If enabled, the runtime will create opentracing.io traces and spans.
+# (See https://www.jaegertracing.io/docs/getting-started).
+# (default: disabled)
+#enable_tracing = true
+
+# If enabled, the runtime will not create a network namespace for shim and hypervisor processes.
+# This option may have some potential impacts to your host. It should only be used when you know what you're doing.
+# `disable_new_netns` conflicts with `enable_netmon`
+# `disable_new_netns` conflicts with `internetworking_model=bridged` and `internetworking_model=macvtap`. It works only
+# with `internetworking_model=none`. The tap device will be in the host network namespace and can connect to a bridge
+# (like OVS) directly.
+# If you are using docker, `disable_new_netns` only works with `docker run --net=none`
+# (default: false)
+#disable_new_netns = true