diff options
| author | Peter Maydell <peter.maydell@linaro.org> | 2021-02-10 15:42:19 +0000 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2021-02-10 15:42:20 +0000 |
| commit | 83339e21d05c824ebc9131d644f25c23d0e41ecf (patch) | |
| tree | 3254c62fa674de5d3d3ae02743122ecccb000fe3 | |
| parent | 7b2c4cdd794e499883281c18770b2d16adebfaac (diff) | |
| parent | eb847c42296497978942f738cd41dc29a35a49b2 (diff) | |
Merge remote-tracking branch 'remotes/stefanha-gitlab/tags/block-pull-request' into staging
Pull request
v4:
* Add PCI_EXPRESS Kconfig dependency to fix s390x in "multi-process: setup PCI
host bridge for remote device" [Philippe and Thomas]
# gpg: Signature made Wed 10 Feb 2021 09:26:14 GMT
# gpg: using RSA key 8695A8BFD3F97CDAAC35775A9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>" [full]
# gpg: aka "Stefan Hajnoczi <stefanha@gmail.com>" [full]
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35 775A 9CA4 ABB3 81AB 73C8
* remotes/stefanha-gitlab/tags/block-pull-request: (27 commits)
docs: fix Parallels Image "dirty bitmap" section
multi-process: perform device reset in the remote process
multi-process: Retrieve PCI info from remote process
multi-process: create IOHUB object to handle irq
multi-process: Synchronize remote memory
multi-process: PCI BAR read/write handling for proxy & remote endpoints
multi-process: Forward PCI config space acceses to the remote process
multi-process: add proxy communication functions
multi-process: introduce proxy object
multi-process: setup memory manager for remote device
multi-process: Associate fd of a PCIDevice with its object
multi-process: Initialize message handler in remote device
multi-process: define MPQemuMsg format and transmission functions
io: add qio_channel_readv_full_all_eof & qio_channel_readv_full_all helpers
io: add qio_channel_writev_full_all helper
multi-process: setup a machine object for remote device process
multi-process: setup PCI host bridge for remote device
multi-process: Add config option for multi-process QEMU
memory: alloc RAM from file at offset
multi-process: add configure and usage information
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
53 files changed, 3296 insertions, 70 deletions
diff --git a/.github/lockdown.yml b/.github/lockdown.yml index 9acc393f1c..07fc2f31ee 100644 --- a/.github/lockdown.yml +++ b/.github/lockdown.yml @@ -10,8 +10,8 @@ issues: comment: | Thank you for your interest in the QEMU project. - This repository is a read-only mirror of the project's master - repostories hosted on https://git.qemu.org/git/qemu.git. + This repository is a read-only mirror of the project's repostories hosted + at https://gitlab.com/qemu-project/qemu.git. The project does not process issues filed on GitHub. The project issues are tracked on Launchpad: @@ -24,8 +24,8 @@ pulls: comment: | Thank you for your interest in the QEMU project. - This repository is a read-only mirror of the project's master - repostories hosted on https://git.qemu.org/git/qemu.git. + This repository is a read-only mirror of the project's repostories hosted + on https://gitlab.com/qemu-project/qemu.git. The project does not process merge requests filed on GitHub. QEMU welcomes contributions of code (either fixing bugs or adding new diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index 7c0db64710..28a83afb91 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -18,7 +18,6 @@ include: image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest before_script: - JOBS=$(expr $(nproc) + 1) - - sed -i s,git.qemu.org/git,gitlab.com/qemu-project, .gitmodules script: - mkdir build - cd build diff --git a/.gitmodules b/.gitmodules index 2bdeeacef8..08b1b48a09 100644 --- a/.gitmodules +++ b/.gitmodules @@ -1,66 +1,66 @@ [submodule "roms/seabios"] path = roms/seabios - url = https://git.qemu.org/git/seabios.git/ + url = https://gitlab.com/qemu-project/seabios.git/ [submodule "roms/SLOF"] path = roms/SLOF - url = https://git.qemu.org/git/SLOF.git + url = https://gitlab.com/qemu-project/SLOF.git [submodule "roms/ipxe"] path = roms/ipxe - url = https://git.qemu.org/git/ipxe.git + url = https://gitlab.com/qemu-project/ipxe.git [submodule "roms/openbios"] path = roms/openbios - url = https://git.qemu.org/git/openbios.git + url = https://gitlab.com/qemu-project/openbios.git [submodule "roms/qemu-palcode"] path = roms/qemu-palcode - url = https://git.qemu.org/git/qemu-palcode.git + url = https://gitlab.com/qemu-project/qemu-palcode.git [submodule "roms/sgabios"] path = roms/sgabios - url = https://git.qemu.org/git/sgabios.git + url = https://gitlab.com/qemu-project/sgabios.git [submodule "dtc"] path = dtc - url = https://git.qemu.org/git/dtc.git + url = https://gitlab.com/qemu-project/dtc.git [submodule "roms/u-boot"] path = roms/u-boot - url = https://git.qemu.org/git/u-boot.git + url = https://gitlab.com/qemu-project/u-boot.git [submodule "roms/skiboot"] path = roms/skiboot - url = https://git.qemu.org/git/skiboot.git + url = https://gitlab.com/qemu-project/skiboot.git [submodule "roms/QemuMacDrivers"] path = roms/QemuMacDrivers - url = https://git.qemu.org/git/QemuMacDrivers.git + url = https://gitlab.com/qemu-project/QemuMacDrivers.git [submodule "ui/keycodemapdb"] path = ui/keycodemapdb - url = https://git.qemu.org/git/keycodemapdb.git + url = https://gitlab.com/qemu-project/keycodemapdb.git [submodule "capstone"] path = capstone - url = https://git.qemu.org/git/capstone.git + url = https://gitlab.com/qemu-project/capstone.git [submodule "roms/seabios-hppa"] path = roms/seabios-hppa - url = https://git.qemu.org/git/seabios-hppa.git + url = https://gitlab.com/qemu-project/seabios-hppa.git [submodule "roms/u-boot-sam460ex"] path = roms/u-boot-sam460ex - url = https://git.qemu.org/git/u-boot-sam460ex.git + url = https://gitlab.com/qemu-project/u-boot-sam460ex.git [submodule "tests/fp/berkeley-testfloat-3"] path = tests/fp/berkeley-testfloat-3 - url = https://git.qemu.org/git/berkeley-testfloat-3.git + url = https://gitlab.com/qemu-project/berkeley-testfloat-3.git [submodule "tests/fp/berkeley-softfloat-3"] path = tests/fp/berkeley-softfloat-3 - url = https://git.qemu.org/git/berkeley-softfloat-3.git + url = https://gitlab.com/qemu-project/berkeley-softfloat-3.git [submodule "roms/edk2"] path = roms/edk2 - url = https://git.qemu.org/git/edk2.git + url = https://gitlab.com/qemu-project/edk2.git [submodule "slirp"] path = slirp - url = https://git.qemu.org/git/libslirp.git + url = https://gitlab.com/qemu-project/libslirp.git [submodule "roms/opensbi"] path = roms/opensbi - url = https://git.qemu.org/git/opensbi.git + url = https://gitlab.com/qemu-project/opensbi.git [submodule "roms/qboot"] path = roms/qboot - url = https://git.qemu.org/git/qboot.git + url = https://gitlab.com/qemu-project/qboot.git [submodule "meson"] path = meson - url = https://git.qemu.org/git/meson.git + url = https://gitlab.com/qemu-project/meson.git [submodule "roms/vbootrom"] path = roms/vbootrom - url = https://git.qemu.org/git/vbootrom.git + url = https://gitlab.com/qemu-project/vbootrom.git diff --git a/Kconfig.host b/Kconfig.host index a9a55a9c31..24255ef441 100644 --- a/Kconfig.host +++ b/Kconfig.host @@ -37,3 +37,7 @@ config VIRTFS config PVRDMA bool + +config MULTIPROCESS_ALLOWED + bool + imply MULTIPROCESS diff --git a/MAINTAINERS b/MAINTAINERS index 06635ba81a..e6f1eca30f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3200,6 +3200,30 @@ S: Maintained F: hw/semihosting/ F: include/hw/semihosting/ +Multi-process QEMU +M: Elena Ufimtseva <elena.ufimtseva@oracle.com> +M: Jagannathan Raman <jag.raman@oracle.com> +M: John G Johnson <john.g.johnson@oracle.com> +S: Maintained +F: docs/devel/multi-process.rst +F: docs/system/multi-process.rst +F: hw/pci-host/remote.c +F: include/hw/pci-host/remote.h +F: hw/remote/machine.c +F: include/hw/remote/machine.h +F: hw/remote/mpqemu-link.c +F: include/hw/remote/mpqemu-link.h +F: hw/remote/message.c +F: hw/remote/remote-obj.c +F: include/hw/remote/memory.h +F: hw/remote/memory.c +F: hw/remote/proxy.c +F: include/hw/remote/proxy.h +F: hw/remote/proxy-memory-listener.c +F: include/hw/remote/proxy-memory-listener.h +F: hw/remote/iohub.c +F: include/hw/remote/iohub.h + Build and test automation ------------------------- Build and test automation diff --git a/README.rst b/README.rst index 58b9f2dc15..ce39d89077 100644 --- a/README.rst +++ b/README.rst @@ -60,7 +60,7 @@ The QEMU source code is maintained under the GIT version control system. .. code-block:: shell - git clone https://git.qemu.org/git/qemu.git + git clone https://gitlab.com/qemu-project/qemu.git When submitting patches, one common approach is to use 'git format-patch' and/or 'git send-email' to format & send the mail to the @@ -78,7 +78,7 @@ The QEMU website is also maintained under source control. .. code-block:: shell - git clone https://git.qemu.org/git/qemu-web.git + git clone https://gitlab.com/qemu-project/qemu-web.git * `<https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/>`_ diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c index e5626d4330..69b0ae30bb 100644 --- a/backends/hostmem-memfd.c +++ b/backends/hostmem-memfd.c @@ -55,7 +55,7 @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) name = host_memory_backend_get_name(backend); memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), name, backend->size, - backend->share, fd, errp); + backend->share, fd, 0, errp); g_free(name); } @@ -463,6 +463,7 @@ skip_meson=no gettext="auto" fuse="auto" fuse_lseek="auto" +multiprocess="no" malloc_trim="auto" @@ -797,6 +798,7 @@ Linux) linux="yes" linux_user="yes" vhost_user=${default_feature:-yes} + multiprocess=${default_feature:-yes} ;; esac @@ -1556,6 +1558,10 @@ for opt do ;; --disable-fuse-lseek) fuse_lseek="disabled" ;; + --enable-multiprocess) multiprocess="yes" + ;; + --disable-multiprocess) multiprocess="no" + ;; *) echo "ERROR: unknown option $opt" echo "Try '$0 --help' for more information" @@ -1908,6 +1914,7 @@ disabled with --disable-FEATURE, default is enabled if available libdaxctl libdaxctl support fuse FUSE block device export fuse-lseek SEEK_HOLE/SEEK_DATA support for FUSE exports + multiprocess Multiprocess QEMU support NOTE: The object files are built at the place where configure is launched EOF @@ -6082,6 +6089,9 @@ fi if test "$have_mlockall" = "yes" ; then echo "HAVE_MLOCKALL=y" >> $config_host_mak fi +if test "$multiprocess" = "yes" ; then + echo "CONFIG_MULTIPROCESS_ALLOWED=y" >> $config_host_mak +fi if test "$fuzzing" = "yes" ; then # If LIB_FUZZING_ENGINE is set, assume we are running on OSS-Fuzz, and the # needed CFLAGS have already been provided diff --git a/docs/devel/index.rst b/docs/devel/index.rst index 98a7016a9b..22854e334d 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -37,3 +37,4 @@ Contents: clocks qom block-coroutine-wrapper + multi-process diff --git a/docs/devel/multi-process.rst b/docs/devel/multi-process.rst new file mode 100644 index 0000000000..69699329d6 --- /dev/null +++ b/docs/devel/multi-process.rst @@ -0,0 +1,966 @@ +This is the design document for multi-process QEMU. It does not +necessarily reflect the status of the current implementation, which +may lack features or be considerably different from what is described +in this document. This document is still useful as a description of +the goals and general direction of this feature. + +Please refer to the following wiki for latest details: +https://wiki.qemu.org/Features/MultiProcessQEMU + +Multi-process QEMU +=================== + +QEMU is often used as the hypervisor for virtual machines running in the +Oracle cloud. Since one of the advantages of cloud computing is the +ability to run many VMs from different tenants in the same cloud +infrastructure, a guest that compromised its hypervisor could +potentially use the hypervisor's access privileges to access data it is +not authorized for. + +QEMU can be susceptible to security attacks because it is a large, +monolithic program that provides many features to the VMs it services. +Many of these features can be configured out of QEMU, but even a reduced +configuration QEMU has a large amount of code a guest can potentially +attack. Separating QEMU reduces the attack surface by aiding to +limit each component in the system to only access the resources that +it needs to perform its job. + +QEMU services +------------- + +QEMU can be broadly described as providing three main services. One is a +VM control point, where VMs can be created, migrated, re-configured, and +destroyed. A second is to emulate the CPU instructions within the VM, +often accelerated by HW virtualization features such as Intel's VT +extensions. Finally, it provides IO services to the VM by emulating HW +IO devices, such as disk and network devices. + +A multi-process QEMU +~~~~~~~~~~~~~~~~~~~~ + +A multi-process QEMU involves separating QEMU services into separate +host processes. Each of these processes can be given only the privileges +it needs to provide its service, e.g., a disk service could be given +access only to the disk images it provides, and not be allowed to +access other files, or any network devices. An attacker who compromised +this service would not be able to use this exploit to access files or +devices beyond what the disk service was given access to. + +A QEMU control process would remain, but in multi-process mode, will +have no direct interfaces to the VM. During VM execution, it would still +provide the user interface to hot-plug devices or live migrate the VM. + +A first step in creating a multi-process QEMU is to separate IO services +from the main QEMU program, which would continue to provide CPU +emulation. i.e., the control process would also be the CPU emulation +process. In a later phase, CPU emulation could be separated from the +control process. + +Separating IO services +---------------------- + +Separating IO services into individual host processes is a good place to +begin for a couple of reasons. One is the sheer number of IO devices QEMU +can emulate provides a large surface of interfaces which could potentially +be exploited, and, indeed, have been a source of exploits in the past. +Another is the modular nature of QEMU device emulation code provides +interface points where the QEMU functions that perform device emulation +can be separated from the QEMU functions that manage the emulation of +guest CPU instructions. The devices emulated in the separate process are +referred to as remote devices. + +QEMU device emulation +~~~~~~~~~~~~~~~~~~~~~ + +QEMU uses an object oriented SW architecture for device emulation code. +Configured objects are all compiled into the QEMU binary, then objects +are instantiated by name when used by the guest VM. For example, the +code to emulate a device named "foo" is always present in QEMU, but its +instantiation code is only run when the device is included in the target +VM. (e.g., via the QEMU command line as *-device foo*) + +The object model is hierarchical, so device emulation code names its +parent object (such as "pci-device" for a PCI device) and QEMU will +instantiate a parent object before calling the device's instantiation +code. + +Current separation models +~~~~~~~~~~~~~~~~~~~~~~~~~ + +In order to separate the device emulation code from the CPU emulation +code, the device object code must run in a different process. There are +a couple of existing QEMU features that can run emulation code +separately from the main QEMU process. These are examined below. + +vhost user model +^^^^^^^^^^^^^^^^ + +Virtio guest device drivers can be connected to vhost user applications +in order to perform their IO operations. This model uses special virtio +device drivers in the guest and vhost user device objects in QEMU, but +once the QEMU vhost user code has configured the vhost user application, +mission-mode IO is performed by the application. The vhost user +application is a daemon process that can be contacted via a known UNIX +domain socket. + +vhost socket +'''''''''''' + +As mentioned above, one of the tasks of the vhost device object within +QEMU is to contact the vhost application and send it configuration +information about this device instance. As part of the configuration +process, the application can also be sent other file descriptors over +the socket, which then can be used by the vhost user application in +various ways, some of which are described below. + +vhost MMIO store acceleration +''''''''''''''''''''''''''''' + +VMs are often run using HW virtualization features via the KVM kernel +driver. This driver allows QEMU to accelerate the emulation of guest CPU +instructions by running the guest in a virtual HW mode. When the guest +executes instructions that cannot be executed by virtual HW mode, +execution returns to the KVM driver so it can inform QEMU to emulate the +instructions in SW. + +One of the events that can cause a return to QEMU is when a guest device +driver accesses an IO location. QEMU then dispatches the memory +operation to the corresponding QEMU device object. In the case of a +vhost user device, the memory operation would need to be sent over a +socket to the vhost application. This path is accelerated by the QEMU +virtio code by setting up an eventfd file descriptor that the vhost +application can directly receive MMIO store notifications from the KVM +driver, instead of needing them to be sent to the QEMU process first. + +vhost interrupt acceleration +'''''''''''''''''''''''''''' + +Another optimization used by the vhost application is the ability to +directly inject interrupts into the VM via the KVM driver, again, +bypassing the need to send the interrupt back to the QEMU process first. +The QEMU virtio setup code configures the KVM driver with an eventfd +that triggers the device interrupt in the guest when the eventfd is +written. This irqfd file descriptor is then passed to the vhost user +application program. + +vhost access to guest memory +'''''''''''''''''''''''''''' + +The vhost application is also allowed to directly access guest memory, +instead of needing to send the data as messages to QEMU. This is also +done with file descriptors sent to the vhost user application by QEMU. +These descriptors can be passed to ``mmap()`` by the vhost application +to map the guest address space into the vhost application. + +IOMMUs introduce another level of complexity, since the address given to +the guest virtio device to DMA to or from is not a guest physical +address. This case is handled by having vhost code within QEMU register +as a listener for IOMMU mapping changes. The vhost application maintains +a cache of IOMMMU translations: sending translation requests back to +QEMU on cache misses, and in turn receiving flush requests from QEMU +when mappings are purged. + +applicability to device separation +'''''''''''''''''''''''''''''''''' + +Much of the vhost model can be re-used by separated device emulation. In +particular, the ideas of using a socket between QEMU and the device +emulation application, using a file descriptor to inject interrupts into +the VM via KVM, and allowing the application to ``mmap()`` the guest +should be re used. + +There are, however, some notable differences between how a vhost +application works and the needs of separated device emulation. The most +basic is that vhost uses custom virtio device drivers which always +trigger IO with MMIO stores. A separated device emulation model must +work with existing IO device models and guest device drivers. MMIO loads +break vhost store acceleration since they are synchronous - guest +progress cannot continue until the load has been emulated. By contrast, +stores are asynchronous, the guest can continue after the store event +has been sent to the vhost application. + +Another difference is that in the vhost user model, a single daemon can +support multiple QEMU instances. This is contrary to the security regime +desired, in which the emulation application should only be allowed to +access the files or devices the VM it's running on behalf of can access. +#### qemu-io model + +Qemu-io is a test harness used to test changes to the QEMU block backend +object code. (e.g., the code that implements disk images for disk driver +emulation) Qemu-io is not a device emulation application per se, but it +does compile the QEMU block objects into a separate binary from the main +QEMU one. This could be useful for disk device emulation, since its +emulation applications will need to include the QEMU block objects. + +New separation model based on proxy objects +------------------------------------------- + +A different model based on proxy objects in the QEMU program +communicating with remote emulation programs could provide separation +while minimizing the changes needed to the device emulation code. The +rest of this section is a discussion of how a proxy object model would +work. + +Remote emulation processes +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The remote emulation process will run the QEMU object hierarchy without +modification. The device emulation objects will be also be based on the +QEMU code, because for anything but the simplest device, it would not be +a tractable to re-implement both the object model and the many device +backends that QEMU has. + +The processes will communicate with the QEMU process over UNIX domain +sockets. The processes can be executed either as standalone processes, +or be executed by QEMU. In both cases, the host backends the emulation +processes will provide are specified on its command line, as they would +be for QEMU. For example: + +:: + + disk-proc -blockdev driver=file,node-name=file0,filename=disk-file0 \ + -blockdev driver=qcow2,node-name=drive0,file=file0 + +would indicate process *disk-proc* uses a qcow2 emulated disk named +*file0* as its backend. + +Emulation processes may emulate more than one guest controller. A common +configuration might be to put all controllers of the same device class +(e.g., disk, network, etc.) in a single process, so that all backends of +the same type can be managed by a single QMP monitor. + +communication with QEMU +^^^^^^^^^^^^^^^^^^^^^^^ + +The first argument to the remote emulation process will be a Unix domain +socket that connects with the Proxy object. This is a required argument. + +:: + + disk-proc <socket number> <backend list> + +remote process QMP monitor +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Remote emulation processes can be monitored via QMP, similar to QEMU +itself. The QMP monitor socket is specified the same as for a QEMU +process: + +:: + + disk-proc -qmp unix:/tmp/disk-mon,server + +can be monitored over the UNIX socket path */tmp/disk-mon*. + +QEMU command line +~~~~~~~~~~~~~~~~~ + +Each remote device emulated in a remote process on the host is +represented as a *-device* of type *pci-proxy-dev*. A socket +sub-option to this option specifies the Unix socket that connects +to the remote process. An *id* sub-option is required, and it should +be the same id as used in the remote process. + +:: + + qemu-system-x86_64 ... -device pci-proxy-dev,id=lsi0,socket=3 + +can be used to add a device emulated in a remote process + + +QEMU management of remote processes +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +QEMU is not aware of the type of type of the remote PCI device. It is +a pass through device as far as QEMU is concerned. + +communication with emulation process +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +primary channel +''''''''''''''' + +The primary channel (referred to as com in the code) is used to bootstrap +the remote process. It is also used to pass on device-agnostic commands +like reset. + +per-device channels +''''''''''''''''''' + +Each remote device communicates with QEMU using a dedicated communication +channel. The proxy object sets up this channel using the primary +channel during its initialization. + +QEMU device proxy objects +~~~~~~~~~~~~~~~~~~~~~~~~~ + +QEMU has an object model based on sub-classes inherited from the +"object" super-class. The sub-classes that are of interest here are the +"device" and "bus" sub-classes whose child sub-classes make up the +device tree of a QEMU emulated system. + +The proxy object model will use device proxy objects to replace the +device emulation code within the QEMU process. These objects will live +in the same place in the object and bus hierarchies as the objects they +replace. i.e., the proxy object for an LSI SCSI controller will be a +sub-class of the "pci-device" class, and will have the same PCI bus +parent and the same SCSI bus child objects as the LSI controller object +it replaces. + +It is worth noting that the same proxy object is used to mediate with +all types of remote PCI devices. + +object initialization +^^^^^^^^^^^^^^^^^^^^^ + +The Proxy device objects are initialized in the exact same manner in +which any other QEMU device would be initialized. + +In addition, the Proxy objects perform the following two tasks: +- Parses the "socket" sub option and connects to the remote process +using this channel +- Uses the "id" sub-option to connect to the emulated device on the +separate process + +class\_init +''''''''''' + +The ``class_init()`` method of a proxy object will, in general behave +similarly to the object it replaces, including setting any static +properties and methods needed by the proxy. + +instance\_init / realize +'''''''''''''''''''''''' + +The ``instance_init()`` and ``realize()`` functions would only need to +perform tasks related to being a proxy, such are registering its own +MMIO handlers, or creating a child bus that other proxy devices can be +attached to later. + +Other tasks will be device-specific. For example, PCI device objects +will initialize the PCI config space in order to make a valid PCI device +tree within the QEMU process. + +address space registration +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Most devices are driven by guest device driver accesses to IO addresses +or ports. The QEMU device emulation code uses QEMU's memory region +function calls (such as ``memory_region_init_io()``) to add callback +functions that QEMU will invoke when the guest accesses the device's +areas of the IO address space. When a guest driver does access the +device, the VM will exit HW virtualization mode and return to QEMU, +which will then lookup and execute the corresponding callback function. + +A proxy object would need to mirror the memory region calls the actual +device emulator would perform in its initialization code, but with its +own callbacks. When invoked by QEMU as a result of a guest IO operation, +they will forward the operation to the device emulation process. + +PCI config space +^^^^^^^^^^^^^^^^ + +PCI devices also have a configuration space that can be accessed by the +guest driver. Guest accesses to this space is not handled by the device +emulation object, but by its PCI parent object. Much of this space is +read-only, but certain registers (especially BAR and MSI-related ones) +need to be propagated to the emulation process. + +PCI parent proxy +'''''''''''''''' + +One way to propagate guest PCI config accesses is to create a +"pci-device-proxy" class that can serve as the parent of a PCI device +proxy object. This class's parent would be "pci-device" and it would +override the PCI parent's ``config_read()`` and ``config_write()`` +methods with ones that forward these operations to the emulation +program. + +interrupt receipt +^^^^^^^^^^^^^^^^^ + +A proxy for a device that generates interrupts will need to create a +socket to receive interrupt indications from the emulation process. An +incoming interrupt indication would then be sent up to its bus parent to +be injected into the guest. For example, a PCI device object may use +``pci_set_irq()``. + +live migration +^^^^^^^^^^^^^^ + +The proxy will register to save and restore any *vmstate* it needs over +a live migration event. The device proxy does not need to manage the +remote device's *vmstate*; that will be handled by the remote process +proxy (see below). + +QEMU remote device operation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Generic device operations, such as DMA, will be performed by the remote +process proxy by sending messages to the remote process. + +DMA operations +^^^^^^^^^^^^^^ + +DMA operations would be handled much like vhost applications do. One of +the initial messages sent to the emulation process is a guest memory +table. Each entry in this table consists of a file descriptor and size +that the emulation process can ``mmap()`` to directly access guest +memory, similar to ``vhost_user_set_mem_table()``. Note guest memory +must be backed by file descriptors, such as when QEMU is given the +*-mem-path* command line option. + +IOMMU operations +^^^^^^^^^^^^^^^^ + +When the emulated system includes an IOMMU, the remote process proxy in +QEMU will need to create a socket for IOMMU requests from the emulation +process. It will handle those requests with an +``address_space_get_iotlb_entry()`` call. In order to handle IOMMU +unmaps, the remote process proxy will also register as a listener on the +device's DMA address space. When an IOMMU memory region is created +within the DMA address space, an IOMMU notifier for unmaps will be added +to the memory region that will forward unmaps to the emulation process +over the IOMMU socket. + +device hot-plug via QMP +^^^^^^^^^^^^^^^^^^^^^^^ + +An QMP "device\_add" command can add a device emulated by a remote +process. It will also have "rid" option to the command, just as the +*-device* command line option does. The remote process may either be one +started at QEMU startup, or be one added by the "add-process" QMP +command described above. In either case, the remote process proxy will +forward the new device's JSON description to the corresponding emulation +process. + +live migration +^^^^^^^^^^^^^^ + +The remote process proxy will also register for live migration +notifications with ``vmstate_register()``. When called to save state, +the proxy will send the remote process a secondary socket file +descriptor to save the remote process's device *vmstate* over. The +incoming byte stream length and data will be saved as the proxy's +*vmstate*. When the proxy is resumed on its new host, this *vmstate* +will be extracted, and a secondary socket file descriptor will be sent +to the new remote process through which it receives the *vmstate* in +order to restore the devices there. + +device emulation in remote process +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The parts of QEMU that the emulation program will need include the +object model; the memory emulation objects; the device emulation objects +of the targeted device, and any dependent devices; and, the device's +backends. It will also need code to setup the machine environment, +handle requests from the QEMU process, and route machine-level requests +(such as interrupts or IOMMU mappings) back to the QEMU process. + +initialization +^^^^^^^^^^^^^^ + +The process initialization sequence will follow the same sequence +followed by QEMU. It will first initialize the backend objects, then +device emulation objects. The JSON descriptions sent by the QEMU process +will drive which objects need to be created. + +- address spaces + +Before the device objects are created, the initial address spaces and +memory regions must be configured with ``memory_map_init()``. This +creates a RAM memory region object (*system\_memory*) and an IO memory +region object (*system\_io*). + +- RAM + +RAM memory region creation will follow how ``pc_memory_init()`` creates +them, but must use ``memory_region_init_ram_from_fd()`` instead of +``memory_region_allocate_system_memory()``. The file descriptors needed +will be supplied by the guest memory table from above. Those RAM regions +would then be added to the *system\_memory* memory region with +``memory_region_add_subregion()``. + +- PCI + +IO initialization will be driven by the JSON descriptions sent from the +QEMU process. For a PCI device, a PCI bus will need to be created with +``pci_root_bus_new()``, and a PCI memory region will need to be created +and added to the *system\_memory* memory region with +``memory_region_add_subregion_overlap()``. The overlap version is +required for architectures where PCI memory overlaps with RAM memory. + +MMIO handling +^^^^^^^^^^^^^ + +The device emulation objects will use ``memory_region_init_io()`` to +install their MMIO handlers, and ``pci_register_bar()`` to associate +those handlers with a PCI BAR, as they do within QEMU currently. + +In order to use ``address_space_rw()`` in the emulation process to +handle MMIO requests from QEMU, the PCI physical addresses must be the +same in the QEMU process and the device emulation process. In order to +accomplish that, guest BAR programming must also be forwarded from QEMU +to the emulation process. + +interrupt injection +^^^^^^^^^^^^^^^^^^^ + +When device emulation wants to inject an interrupt into the VM, the +request climbs the device's bus object hierarchy until the point where a +bus object knows how to signal the interrupt to the guest. The details +depend on the type of interrupt being raised. + +- PCI pin interrupts + +On x86 systems, there is an emulated IOAPIC object attached to the root +PCI bus object, and the root PCI object forwards interrupt requests to +it. The IOAPIC object, in turn, calls the KVM driver to inject the +corresponding interrupt into the VM. The simplest way to handle this in +an emulation process would be to setup the root PCI bus driver (via +``pci_bus_irqs()``) to send a interrupt request back to the QEMU +process, and have the device proxy object reflect it up the PCI tree +there. + +- PCI MSI/X interrupts + +PCI MSI/X interrupts are implemented in HW as DMA writes to a +CPU-specific PCI address. In QEMU on x86, a KVM APIC object receives +these DMA writes, then calls into the KVM driver to inject the interrupt +into the VM. A simple emulation process implementation would be to send +the MSI DMA address from QEMU as a message at initialization, then +install an address space handler at that address which forwards the MSI +message back to QEMU. + +DMA operations +^^^^^^^^^^^^^^ + +When a emulation object wants to DMA into or out of guest memory, it +first must use dma\_memory\_map() to convert the DMA address to a local +virtual address. The emulation process memory region objects setup above +will be used to translate the DMA address to a local virtual address the +device emulation code can access. + +IOMMU +^^^^^ + +When an IOMMU is in use in QEMU, DMA translation uses IOMMU memory +regions to translate the DMA address to a guest physical address before +that physical address can be translated to a local virtual address. The +emulation process will need similar functionality. + +- IOTLB cache + +The emulation process will maintain a cache of recent IOMMU translations +(the IOTLB). When the translate() callback of an IOMMU memory region is +invoked, the IOTLB cache will be searched for an entry that will map the +DMA address to a guest PA. On a cache miss, a message will be sent back +to QEMU requesting the corresponding translation entry, which be both be +used to return a guest address and be added to the cache. + +- IOTLB purge + +The IOMMU emulation will also need to act on unmap requests from QEMU. +These happen when the guest IOMMU driver purges an entry from the +guest's translation table. + +live migration +^^^^^^^^^^^^^^ + +When a remote process receives a live migration indication from QEMU, it +will set up a channel using the received file descriptor with +``qio_channel_socket_new_fd()``. This channel will be used to create a +*QEMUfile* that can be passed to ``qemu_save_device_state()`` to send +the process's device state back to QEMU. This method will be reversed on +restore - the channel will be passed to ``qemu_loadvm_state()`` to +restore the device state. + +Accelerating device emulation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The messages that are required to be sent between QEMU and the emulation +process can add considerable latency to IO operations. The optimizations +described below attempt to ameliorate this effect by allowing the +emulation process to communicate directly with the kernel KVM driver. +The KVM file descriptors created would be passed to the emulation process +via initialization messages, much like the guest memory table is done. +#### MMIO acceleration + +Vhost user applications can receive guest virtio driver stores directly +from KVM. The issue with the eventfd mechanism used by vhost user is +that it does not pass any data with the event indication, so it cannot +handle guest loads or guest stores that carry store data. This concept +could, however, be expanded to cover more cases. + +The expanded idea would require a new type of KVM device: +*KVM\_DEV\_TYPE\_USER*. This device has two file descriptors: a master +descriptor that QEMU can use for configuration, and a slave descriptor +that the emulation process can use to receive MMIO notifications. QEMU +would create both descriptors using the KVM driver, and pass the slave +descriptor to the emulation process via an initialization message. + +data structures +^^^^^^^^^^^^^^^ + +- guest physical range + +The guest physical range structure describes the address range that a +device will respond to. It includes the base and length of the range, as +well as which bus the range resides on (e.g., on an x86machine, it can +specify whether the range refers to memory or IO addresses). + +A device can have multiple physical address ranges it responds to (e.g., +a PCI device can have multiple BARs), so the structure will also include +an enumerated identifier to specify which of the device's ranges is +being referred to. + ++--------+----------------------------+ +| Name | Description | ++========+============================+ +| addr | range base address | ++--------+----------------------------+ +| len | range length | ++--------+----------------------------+ +| bus | addr type (memory or IO) | ++--------+----------------------------+ +| id | range ID (e.g., PCI BAR) | ++--------+----------------------------+ + +- MMIO request structure + +This structure describes an MMIO operation. It includes which guest +physical range the MMIO was within, the offset within that range, the +MMIO type (e.g., load or store), and its length and data. It also +includes a sequence number that can be used to reply to the MMIO, and +the CPU that issued the MMIO. + ++----------+------------------------+ +| Name | Description | ++==========+========================+ +| rid | range MMIO is within | ++----------+------------------------+ +| offset | offset withing *rid* | ++----------+------------------------+ +| type | e.g., load or store | ++----------+------------------------+ +| len | MMIO length | ++----------+------------------------+ +| data | store data | ++----------+------------------------+ +| seq | sequence ID | ++----------+------------------------+ + +- MMIO request queues + +MMIO request queues are FIFO arrays of MMIO request structures. There +are two queues: pending queue is for MMIOs that haven't been read by the +emulation program, and the sent queue is for MMIOs that haven't been +acknowledged. The main use of the second queue is to validate MMIO +replies from the emulation program. + +- scoreboard + +Each CPU in the VM is emulated in QEMU by a separate thread, so multiple +MMIOs may be waiting to be consumed by an emulation program and multiple +threads may be waiting for MMIO replies. The scoreboard would contain a +wait queue and sequence number for the per-CPU threads, allowing them to +be individually woken when the MMIO reply is received from the emulation +program. It also tracks the number of posted MMIO stores to the device +that haven't been replied to, in order to satisfy the PCI constraint +that a load to a device will not complete until all previous stores to +that device have been completed. + +- device shadow memory + +Some MMIO loads do not have device side-effects. These MMIOs can be +completed without sending a MMIO request to the emulation program if the +emulation program shares a shadow image of the device's memory image +with the KVM driver. + +The emulation program will ask the KVM driver to allocate memory for the +shadow image, and will then use ``mmap()`` to directly access it. The +emulation program can control KVM access to the shadow image by sending +KVM an access map telling it which areas of the image have no +side-effects (and can be completed immediately), and which require a +MMIO request to the emulation program. The access map can also inform +the KVM drive which size accesses are allowed to the image. + +master descriptor +^^^^^^^^^^^^^^^^^ + +The master descriptor is used by QEMU to configure the new KVM device. +The descriptor would be returned by the KVM driver when QEMU issues a +*KVM\_CREATE\_DEVICE* ``ioctl()`` with a *KVM\_DEV\_TYPE\_USER* type. + +KVM\_DEV\_TYPE\_USER device ops + + +The *KVM\_DEV\_TYPE\_USER* operations vector will be registered by a +``kvm_register_device_ops()`` call when the KVM system in initialized by +``kvm_init()``. These device ops are called by the KVM driver when QEMU +executes certain ``ioctl()`` operations on its KVM file descriptor. They +include: + +- create + +This routine is called when QEMU issues a *KVM\_CREATE\_DEVICE* +``ioctl()`` on its per-VM file descriptor. It will allocate and +initialize a KVM user device specific data structure, and assign the +*kvm\_device* private field to it. + +- ioctl + +This routine is invoked when QEMU issues an ``ioctl()`` on the master +descriptor. The ``ioctl()`` commands supported are defined by the KVM +device type. *KVM\_DEV\_TYPE\_USER* ones will need several commands: + +*KVM\_DEV\_USER\_SLAVE\_FD* creates the slave file descriptor that will +be passed to the device emulation program. Only one slave can be created +by each master descriptor. The file operations performed by this +descriptor are described below. + +The *KVM\_DEV\_USER\_PA\_RANGE* command configures a guest physical +address range that the slave descriptor will receive MMIO notifications +for. The range is specified by a guest physical range structure +argument. For buses that assign addresses to devices dynamically, this +command can be executed while the guest is running, such as the case +when a guest changes a device's PCI BAR registers. + +*KVM\_DEV\_USER\_PA\_RANGE* will use ``kvm_io_bus_register_dev()`` to +register *kvm\_io\_device\_ops* callbacks to be invoked when the guest +performs a MMIO operation within the range. When a range is changed, +``kvm_io_bus_unregister_dev()`` is used to remove the previous +instantiation. + +*KVM\_DEV\_USER\_TIMEOUT* will configure a timeout value that specifies +how long KVM will wait for the emulation process to respond to a MMIO +indication. + +- destroy + +This routine is called when the VM instance is destroyed. It will need +to destroy the slave descriptor; and free any memory allocated by the +driver, as well as the *kvm\_device* structure itself. + +slave descriptor +^^^^^^^^^^^^^^^^ + +The slave descriptor will have its own file operations vector, which +responds to system calls on the descriptor performed by the device +emulation program. + +- read + +A read returns any pending MMIO requests from the KVM driver as MMIO +request structures. Multiple structures can be returned if there are +multiple MMIO operations pending. The MMIO requests are moved from the +pending queue to the sent queue, and if there are threads waiting for +space in the pending to add new MMIO operations, they will be woken +here. + +- write + +A write also consists of a set of MMIO requests. They are compared to +the MMIO requests in the sent queue. Matches are removed from the sent +queue, and any threads waiting for the reply are woken. If a store is +removed, then the number of posted stores in the per-CPU scoreboard is +decremented. When the number is zero, and a non side-effect load was +waiting for posted stores to complete, the load is continued. + +- ioctl + +There are several ioctl()s that can be performed on the slave +descriptor. + +A *KVM\_DEV\_USER\_SHADOW\_SIZE* ``ioctl()`` causes the KVM driver to +allocate memory for the shadow image. This memory can later be +``mmap()``\ ed by the emulation process to share the emulation's view of +device memory with the KVM driver. + +A *KVM\_DEV\_USER\_SHADOW\_CTRL* ``ioctl()`` controls access to the +shadow image. It will send the KVM driver a shadow control map, which +specifies which areas of the image can complete guest loads without +sending the load request to the emulation program. It will also specify +the size of load operations that are allowed. + +- poll + +An emulation program will use the ``poll()`` call with a *POLLIN* flag +to determine if there are MMIO requests waiting to be read. It will +return if the pending MMIO request queue is not empty. + +- mmap + +This call allows the emulation program to directly access the shadow +image allocated by the KVM driver. As device emulation updates device +memory, changes with no side-effects will be reflected in the shadow, +and the KVM driver can satisfy guest loads from the shadow image without +needing to wait for the emulation program. + +kvm\_io\_device ops +^^^^^^^^^^^^^^^^^^^ + +Each KVM per-CPU thread can handle MMIO operation on behalf of the guest +VM. KVM will use the MMIO's guest physical address to search for a +matching *kvm\_io\_device* to see if the MMIO can be handled by the KVM +driver instead of exiting back to QEMU. If a match is found, the +corresponding callback will be invoked. + +- read + +This callback is invoked when the guest performs a load to the device. +Loads with side-effects must be handled synchronously, with the KVM +driver putting the QEMU thread to sleep waiting for the emulation +process reply before re-starting the guest. Loads that do not have +side-effects may be optimized by satisfying them from the shadow image, +if there are no outstanding stores to the device by this CPU. PCI memory +ordering demands that a load cannot complete before all older stores to +the same device have been completed. + +- write + +Stores can be handled asynchronously unless the pending MMIO request +queue is full. In this case, the QEMU thread must sleep waiting for +space in the queue. Stores will increment the number of posted stores in +the per-CPU scoreboard, in order to implement the PCI ordering +constraint above. + +interrupt acceleration +^^^^^^^^^^^^^^^^^^^^^^ + +This performance optimization would work much like a vhost user +application does, where the QEMU process sets up *eventfds* that cause +the device's corresponding interrupt to be triggered by the KVM driver. +These irq file descriptors are sent to the emulation process at +initialization, and are used when the emulation code raises a device +interrupt. + +intx acceleration +''''''''''''''''' + +Traditional PCI pin interrupts are level based, so, in addition to an +irq file descriptor, a re-sampling file descriptor needs to be sent to +the emulation program. This second file descriptor allows multiple +devices sharing an irq to be notified when the interrupt has been +acknowledged by the guest, so they can re-trigger the interrupt if their +device has not de-asserted its interrupt. + +intx irq descriptor + + +The irq descriptors are created by the proxy object +``using event_notifier_init()`` to create the irq and re-sampling +*eventds*, and ``kvm_vm_ioctl(KVM_IRQFD)`` to bind them to an interrupt. +The interrupt route can be found with +``pci_device_route_intx_to_irq()``. + +intx routing changes + + +Intx routing can be changed when the guest programs the APIC the device +pin is connected to. The proxy object in QEMU will use +``pci_device_set_intx_routing_notifier()`` to be informed of any guest +changes to the route. This handler will broadly follow the VFIO +interrupt logic to change the route: de-assigning the existing irq +descriptor from its route, then assigning it the new route. (see +``vfio_intx_update()``) + +MSI/X acceleration +'''''''''''''''''' + +MSI/X interrupts are sent as DMA transactions to the host. The interrupt +data contains a vector that is programmed by the guest, A device may have +multiple MSI interrupts associated with it, so multiple irq descriptors +may need to be sent to the emulation program. + +MSI/X irq descriptor + + +This case will also follow the VFIO example. For each MSI/X interrupt, +an *eventfd* is created, a virtual interrupt is allocated by +``kvm_irqchip_add_msi_route()``, and the virtual interrupt is bound to +the eventfd with ``kvm_irqchip_add_irqfd_notifier()``. + +MSI/X config space changes + + +The guest may dynamically update several MSI-related tables in the +device's PCI config space. These include per-MSI interrupt enables and +vector data. Additionally, MSIX tables exist in device memory space, not +config space. Much like the BAR case above, the proxy object must look +at guest config space programming to keep the MSI interrupt state +consistent between QEMU and the emulation program. + +-------------- + +Disaggregated CPU emulation +--------------------------- + +After IO services have been disaggregated, a second phase would be to +separate a process to handle CPU instruction emulation from the main +QEMU control function. There are no object separation points for this +code, so the first task would be to create one. + +Host access controls +-------------------- + +Separating QEMU relies on the host OS's access restriction mechanisms to +enforce that the differing processes can only access the objects they +are entitled to. There are a couple types of mechanisms usually provided +by general purpose OSs. + +Discretionary access control +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Discretionary access control allows each user to control who can access +their files. In Linux, this type of control is usually too coarse for +QEMU separation, since it only provides three separate access controls: +one for the same user ID, the second for users IDs with the same group +ID, and the third for all other user IDs. Each device instance would +need a separate user ID to provide access control, which is likely to be +unwieldy for dynamically created VMs. + +Mandatory access control +~~~~~~~~~~~~~~~~~~~~~~~~ + +Mandatory access control allows the OS to add an additional set of +controls on top of discretionary access for the OS to control. It also +adds other attributes to processes and files such as types, roles, and +categories, and can establish rules for how processes and files can +interact. + +Type enforcement +^^^^^^^^^^^^^^^^ + +Type enforcement assigns a *type* attribute to processes and files, and +allows rules to be written on what operations a process with a given +type can perform on a file with a given type. QEMU separation could take +advantage of type enforcement by running the emulation processes with +different types, both from the main QEMU process, and from the emulation +processes of different classes of devices. + +For example, guest disk images and disk emulation processes could have +types separate from the main QEMU process and non-disk emulation +processes, and the type rules could prevent processes other than disk +emulation ones from accessing guest disk images. Similarly, network +emulation processes can have a type separate from the main QEMU process +and non-network emulation process, and only that type can access the +host tun/tap device used to provide guest networking. + +Category enforcement +^^^^^^^^^^^^^^^^^^^^ + +Category enforcement assigns a set of numbers within a given range to +the process or file. The process is granted access to the file if the +process's set is a superset of the file's set. This enforcement can be +used to separate multiple instances of devices in the same class. + +For example, if there are multiple disk devices provides to a guest, +each device emulation process could be provisioned with a separate +category. The different device emulation processes would not be able to +access each other's backing disk images. + +Alternatively, categories could be used in lieu of the type enforcement +scheme described above. In this scenario, different categories would be +used to prevent device emulation processes in different classes from +accessing resources assigned to other classes. diff --git a/docs/interop/parallels.txt b/docs/interop/parallels.txt index e9271eba5d..f15bf35bd1 100644 --- a/docs/interop/parallels.txt +++ b/docs/interop/parallels.txt @@ -208,7 +208,7 @@ of its data area are: 28 - 31: l1_size The number of entries in the L1 table of the bitmap. - variable: l1 (64 * l1_size bytes) + variable: l1_table (8 * l1_size bytes) L1 offset table (in bytes) A dirty bitmap is stored using a one-level structure for the mapping to host diff --git a/docs/system/index.rst b/docs/system/index.rst index d40f72c92b..625b494372 100644 --- a/docs/system/index.rst +++ b/docs/system/index.rst @@ -34,6 +34,7 @@ Contents: pr-manager targets security + multi-process deprecated removed-features build-platforms diff --git a/docs/system/multi-process.rst b/docs/system/multi-process.rst new file mode 100644 index 0000000000..46bb0cafc2 --- /dev/null +++ b/docs/system/multi-process.rst @@ -0,0 +1,64 @@ +Multi-process QEMU +================== + +This document describes how to configure and use multi-process qemu. +For the design document refer to docs/devel/qemu-multiprocess. + +1) Configuration +---------------- + +multi-process is enabled by default for targets that enable KVM + + +2) Usage +-------- + +Multi-process QEMU requires an orchestrator to launch. + +Following is a description of command-line used to launch mpqemu. + +* Orchestrator: + + - The Orchestrator creates a unix socketpair + + - It launches the remote process and passes one of the + sockets to it via command-line. + + - It then launches QEMU and specifies the other socket as an option + to the Proxy device object + +* Remote Process: + + - QEMU can enter remote process mode by using the "remote" machine + option. + + - The orchestrator creates a "remote-object" with details about + the device and the file descriptor for the device + + - The remaining options are no different from how one launches QEMU with + devices. + + - Example command-line for the remote process is as follows: + + /usr/bin/qemu-system-x86_64 \ + -machine x-remote \ + -device lsi53c895a,id=lsi0 \ + -drive id=drive_image2,file=/build/ol7-nvme-test-1.qcow2 \ + -device scsi-hd,id=drive2,drive=drive_image2,bus=lsi0.0,scsi-id=0 \ + -object x-remote-object,id=robj1,devid=lsi1,fd=4, + +* QEMU: + + - Since parts of the RAM are shared between QEMU & remote process, a + memory-backend-memfd is required to facilitate this, as follows: + + -object memory-backend-memfd,id=mem,size=2G + + - A "x-pci-proxy-dev" device is created for each of the PCI devices emulated + in the remote process. A "socket" sub-option specifies the other end of + unix channel created by orchestrator. The "id" sub-option must be specified + and should be the same as the "id" specified for the remote PCI device + + - Example commandline for QEMU is as follows: + + -device x-pci-proxy-dev,id=lsi0,socket=3 diff --git a/hw/Kconfig b/hw/Kconfig index d4cec9e476..8ea26479c4 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -27,6 +27,7 @@ source pci-host/Kconfig source pcmcia/Kconfig source pci/Kconfig source rdma/Kconfig +source remote/Kconfig source rtc/Kconfig source scsi/Kconfig source sd/Kconfig diff --git a/hw/meson.build b/hw/meson.build index 010de7219c..e615d72d4d 100644 --- a/hw/meson.build +++ b/hw/meson.build @@ -56,6 +56,7 @@ subdir('moxie') subdir('nios2') subdir('openrisc') subdir('ppc') +subdir('remote') subdir('riscv') subdir('rx') subdir('s390x') diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index 0505b52c98..603e992a7f 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -495,7 +495,8 @@ static void process_msg_shmem(IVShmemState *s, int fd, Error **errp) /* mmap the region and map into the BAR2 */ memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s), - "ivshmem.bar2", size, true, fd, &local_err); + "ivshmem.bar2", size, true, fd, 0, + &local_err); if (local_err) { error_propagate(errp, local_err); return; diff --git a/hw/pci-host/Kconfig b/hw/pci-host/Kconfig index eb03f0489d..8b8c763c28 100644 --- a/hw/pci-host/Kconfig +++ b/hw/pci-host/Kconfig @@ -65,3 +65,6 @@ config PCI_POWERNV select PCI_EXPRESS select MSI_NONBROKEN select PCIE_PORT + +config REMOTE_PCIHOST + bool diff --git a/hw/pci-host/meson.build b/hw/pci-host/meson.build index da9d1a9964..1847c69905 100644 --- a/hw/pci-host/meson.build +++ b/hw/pci-host/meson.build @@ -9,6 +9,7 @@ pci_ss.add(when: 'CONFIG_PCI_EXPRESS_XILINX', if_true: files('xilinx-pcie.c')) pci_ss.add(when: 'CONFIG_PCI_I440FX', if_true: files('i440fx.c')) pci_ss.add(when: 'CONFIG_PCI_SABRE', if_true: files('sabre.c')) pci_ss.add(when: 'CONFIG_XEN_IGD_PASSTHROUGH', if_true: files('xen_igd_pt.c')) +pci_ss.add(when: 'CONFIG_REMOTE_PCIHOST', if_true: files('remote.c')) # PPC devices pci_ss.add(when: 'CONFIG_PREP_PCI', if_true: files('prep.c')) diff --git a/hw/pci-host/remote.c b/hw/pci-host/remote.c new file mode 100644 index 0000000000..eee45444ef --- /dev/null +++ b/hw/pci-host/remote.c @@ -0,0 +1,75 @@ +/* + * Remote PCI host device + * + * Unlike PCI host devices that model physical hardware, the purpose + * of this PCI host is to host multi-process QEMU devices. + * + * Multi-process QEMU extends the PCI host of a QEMU machine into a + * remote process. Any PCI device attached to the remote process is + * visible in the QEMU guest. This allows existing QEMU device models + * to be reused in the remote process. + * + * This PCI host is purely a container for PCI devices. It's fake in the + * sense that the guest never sees this PCI host and has no way of + * accessing it. Its job is just to provide the environment that QEMU + * PCI device models need when running in a remote process. + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/pci/pci.h" +#include "hw/pci/pci_host.h" +#include "hw/pci/pcie_host.h" +#include "hw/qdev-properties.h" +#include "hw/pci-host/remote.h" +#include "exec/memory.h" + +static const char *remote_pcihost_root_bus_path(PCIHostState *host_bridge, + PCIBus *rootbus) +{ + return "0000:00"; +} + +static void remote_pcihost_realize(DeviceState *dev, Error **errp) +{ + PCIHostState *pci = PCI_HOST_BRIDGE(dev); + RemotePCIHost *s = REMOTE_PCIHOST(dev); + + pci->bus = pci_root_bus_new(DEVICE(s), "remote-pci", + s->mr_pci_mem, s->mr_sys_io, + 0, TYPE_PCIE_BUS); +} + +static void remote_pcihost_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass); + + hc->root_bus_path = remote_pcihost_root_bus_path; + dc->realize = remote_pcihost_realize; + + dc->user_creatable = false; + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); + dc->fw_name = "pci"; +} + +static const TypeInfo remote_pcihost_info = { + .name = TYPE_REMOTE_PCIHOST, + .parent = TYPE_PCIE_HOST_BRIDGE, + .instance_size = sizeof(RemotePCIHost), + .class_init = remote_pcihost_class_init, +}; + +static void remote_pcihost_register(void) +{ + type_register_static(&remote_pcihost_info); +} + +type_init(remote_pcihost_register) diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig new file mode 100644 index 0000000000..08c16e235f --- /dev/null +++ b/hw/remote/Kconfig @@ -0,0 +1,4 @@ +config MULTIPROCESS + bool + depends on PCI && PCI_EXPRESS && KVM + select REMOTE_PCIHOST diff --git a/hw/remote/iohub.c b/hw/remote/iohub.c new file mode 100644 index 0000000000..e4ff131a6b --- /dev/null +++ b/hw/remote/iohub.c @@ -0,0 +1,119 @@ +/* + * Remote IO Hub + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/pci/pci.h" +#include "hw/pci/pci_ids.h" +#include "hw/pci/pci_bus.h" +#include "qemu/thread.h" +#include "hw/boards.h" +#include "hw/remote/machine.h" +#include "hw/remote/iohub.h" +#include "qemu/main-loop.h" + +void remote_iohub_init(RemoteIOHubState *iohub) +{ + int pirq; + + memset(&iohub->irqfds, 0, sizeof(iohub->irqfds)); + memset(&iohub->resamplefds, 0, sizeof(iohub->resamplefds)); + + for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) { + qemu_mutex_init(&iohub->irq_level_lock[pirq]); + iohub->irq_level[pirq] = 0; + event_notifier_init_fd(&iohub->irqfds[pirq], -1); + event_notifier_init_fd(&iohub->resamplefds[pirq], -1); + } +} + +void remote_iohub_finalize(RemoteIOHubState *iohub) +{ + int pirq; + + for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) { + qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]), + NULL, NULL, NULL); + event_notifier_cleanup(&iohub->irqfds[pirq]); + event_notifier_cleanup(&iohub->resamplefds[pirq]); + qemu_mutex_destroy(&iohub->irq_level_lock[pirq]); + } +} + +int remote_iohub_map_irq(PCIDevice *pci_dev, int intx) +{ + return pci_dev->devfn; +} + +void remote_iohub_set_irq(void *opaque, int pirq, int level) +{ + RemoteIOHubState *iohub = opaque; + + assert(pirq >= 0); + assert(pirq < PCI_DEVFN_MAX); + + QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]); + + if (level) { + if (++iohub->irq_level[pirq] == 1) { + event_notifier_set(&iohub->irqfds[pirq]); + } + } else if (iohub->irq_level[pirq] > 0) { + iohub->irq_level[pirq]--; + } +} + +static void intr_resample_handler(void *opaque) +{ + ResampleToken *token = opaque; + RemoteIOHubState *iohub = token->iohub; + int pirq, s; + + pirq = token->pirq; + + s = event_notifier_test_and_clear(&iohub->resamplefds[pirq]); + + assert(s >= 0); + + QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]); + + if (iohub->irq_level[pirq]) { + event_notifier_set(&iohub->irqfds[pirq]); + } +} + +void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg) +{ + RemoteMachineState *machine = REMOTE_MACHINE(current_machine); + RemoteIOHubState *iohub = &machine->iohub; + int pirq, intx; + + intx = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1; + + pirq = remote_iohub_map_irq(pci_dev, intx); + + if (event_notifier_get_fd(&iohub->irqfds[pirq]) != -1) { + qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]), + NULL, NULL, NULL); + event_notifier_cleanup(&iohub->irqfds[pirq]); + event_notifier_cleanup(&iohub->resamplefds[pirq]); + memset(&iohub->token[pirq], 0, sizeof(ResampleToken)); + } + + event_notifier_init_fd(&iohub->irqfds[pirq], msg->fds[0]); + event_notifier_init_fd(&iohub->resamplefds[pirq], msg->fds[1]); + + iohub->token[pirq].iohub = iohub; + iohub->token[pirq].pirq = pirq; + + qemu_set_fd_handler(msg->fds[1], intr_resample_handler, NULL, + &iohub->token[pirq]); +} diff --git a/hw/remote/machine.c b/hw/remote/machine.c new file mode 100644 index 0000000000..c0ab4f528a --- /dev/null +++ b/hw/remote/machine.c @@ -0,0 +1,80 @@ +/* + * Machine for remote device + * + * This machine type is used by the remote device process in multi-process + * QEMU. QEMU device models depend on parent busses, interrupt controllers, + * memory regions, etc. The remote machine type offers this environment so + * that QEMU device models can be used as remote devices. + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/machine.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "qapi/error.h" +#include "hw/pci/pci_host.h" +#include "hw/remote/iohub.h" + +static void remote_machine_init(MachineState *machine) +{ + MemoryRegion *system_memory, *system_io, *pci_memory; + RemoteMachineState *s = REMOTE_MACHINE(machine); + RemotePCIHost *rem_host; + PCIHostState *pci_host; + + system_memory = get_system_memory(); + system_io = get_system_io(); + + pci_memory = g_new(MemoryRegion, 1); + memory_region_init(pci_memory, NULL, "pci", UINT64_MAX); + + rem_host = REMOTE_PCIHOST(qdev_new(TYPE_REMOTE_PCIHOST)); + + rem_host->mr_pci_mem = pci_memory; + rem_host->mr_sys_mem = system_memory; + rem_host->mr_sys_io = system_io; + + s->host = rem_host; + + object_property_add_child(OBJECT(s), "remote-pcihost", OBJECT(rem_host)); + memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1); + + qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal); + + pci_host = PCI_HOST_BRIDGE(rem_host); + + remote_iohub_init(&s->iohub); + + pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq, + &s->iohub, REMOTE_IOHUB_NB_PIRQS); +} + +static void remote_machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->init = remote_machine_init; + mc->desc = "Experimental remote machine"; +} + +static const TypeInfo remote_machine = { + .name = TYPE_REMOTE_MACHINE, + .parent = TYPE_MACHINE, + .instance_size = sizeof(RemoteMachineState), + .class_init = remote_machine_class_init, +}; + +static void remote_machine_register_types(void) +{ + type_register_static(&remote_machine); +} + +type_init(remote_machine_register_types); diff --git a/hw/remote/memory.c b/hw/remote/memory.c new file mode 100644 index 0000000000..32085b1e05 --- /dev/null +++ b/hw/remote/memory.c @@ -0,0 +1,65 @@ +/* + * Memory manager for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/memory.h" +#include "exec/address-spaces.h" +#include "exec/ram_addr.h" +#include "qapi/error.h" + +static void remote_sysmem_reset(void) +{ + MemoryRegion *sysmem, *subregion, *next; + + sysmem = get_system_memory(); + + QTAILQ_FOREACH_SAFE(subregion, &sysmem->subregions, subregions_link, next) { + if (subregion->ram) { + memory_region_del_subregion(sysmem, subregion); + object_unparent(OBJECT(subregion)); + } + } +} + +void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + SyncSysmemMsg *sysmem_info = &msg->data.sync_sysmem; + MemoryRegion *sysmem, *subregion; + static unsigned int suffix; + int region; + + sysmem = get_system_memory(); + + remote_sysmem_reset(); + + for (region = 0; region < msg->num_fds; region++) { + g_autofree char *name; + subregion = g_new(MemoryRegion, 1); + name = g_strdup_printf("remote-mem-%u", suffix++); + memory_region_init_ram_from_fd(subregion, NULL, + name, sysmem_info->sizes[region], + true, msg->fds[region], + sysmem_info->offsets[region], + errp); + + if (*errp) { + g_free(subregion); + remote_sysmem_reset(); + return; + } + + memory_region_add_subregion(sysmem, sysmem_info->gpas[region], + subregion); + + } +} diff --git a/hw/remote/meson.build b/hw/remote/meson.build new file mode 100644 index 0000000000..e6a5574242 --- /dev/null +++ b/hw/remote/meson.build @@ -0,0 +1,13 @@ +remote_ss = ss.source_set() + +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c')) + +specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) +specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c')) + +softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) diff --git a/hw/remote/message.c b/hw/remote/message.c new file mode 100644 index 0000000000..11d729845c --- /dev/null +++ b/hw/remote/message.c @@ -0,0 +1,230 @@ +/* + * Copyright © 2020, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL-v2, version 2 or later. + * + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/machine.h" +#include "io/channel.h" +#include "hw/remote/mpqemu-link.h" +#include "qapi/error.h" +#include "sysemu/runstate.h" +#include "hw/pci/pci.h" +#include "exec/memattrs.h" +#include "hw/remote/memory.h" +#include "hw/remote/iohub.h" +#include "sysemu/reset.h" + +static void process_config_write(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp); +static void process_config_read(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp); +static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); +static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); +static void process_device_reset_msg(QIOChannel *ioc, PCIDevice *dev, + Error **errp); + +void coroutine_fn mpqemu_remote_msg_loop_co(void *data) +{ + g_autofree RemoteCommDev *com = (RemoteCommDev *)data; + PCIDevice *pci_dev = NULL; + Error *local_err = NULL; + + assert(com->ioc); + + pci_dev = com->dev; + for (; !local_err;) { + MPQemuMsg msg = {0}; + + if (!mpqemu_msg_recv(&msg, com->ioc, &local_err)) { + break; + } + + if (!mpqemu_msg_valid(&msg)) { + error_setg(&local_err, "Received invalid message from proxy" + "in remote process pid="FMT_pid"", + getpid()); + break; + } + + switch (msg.cmd) { + case MPQEMU_CMD_PCI_CFGWRITE: + process_config_write(com->ioc, pci_dev, &msg, &local_err); + break; + case MPQEMU_CMD_PCI_CFGREAD: + process_config_read(com->ioc, pci_dev, &msg, &local_err); + break; + case MPQEMU_CMD_BAR_WRITE: + process_bar_write(com->ioc, &msg, &local_err); + break; + case MPQEMU_CMD_BAR_READ: + process_bar_read(com->ioc, &msg, &local_err); + break; + case MPQEMU_CMD_SYNC_SYSMEM: + remote_sysmem_reconfig(&msg, &local_err); + break; + case MPQEMU_CMD_SET_IRQFD: + process_set_irqfd_msg(pci_dev, &msg); + break; + case MPQEMU_CMD_DEVICE_RESET: + process_device_reset_msg(com->ioc, pci_dev, &local_err); + break; + default: + error_setg(&local_err, + "Unknown command (%d) received for device %s" + " (pid="FMT_pid")", + msg.cmd, DEVICE(pci_dev)->id, getpid()); + } + } + + if (local_err) { + error_report_err(local_err); + qemu_system_shutdown_request(SHUTDOWN_CAUSE_HOST_ERROR); + } else { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } +} + +static void process_config_write(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data; + MPQemuMsg ret = { 0 }; + + if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) { + error_setg(errp, "Bad address for PCI config write, pid "FMT_pid".", + getpid()); + ret.data.u64 = UINT64_MAX; + } else { + pci_default_write_config(dev, conf->addr, conf->val, conf->len); + } + + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_config_read(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data; + MPQemuMsg ret = { 0 }; + + if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) { + error_setg(errp, "Bad address for PCI config read, pid "FMT_pid".", + getpid()); + ret.data.u64 = UINT64_MAX; + } else { + ret.data.u64 = pci_default_read_config(dev, conf->addr, conf->len); + } + + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + BarAccessMsg *bar_access = &msg->data.bar_access; + AddressSpace *as = + bar_access->memory ? &address_space_memory : &address_space_io; + MPQemuMsg ret = { 0 }; + MemTxResult res; + uint64_t val; + + if (!is_power_of_2(bar_access->size) || + (bar_access->size > sizeof(uint64_t))) { + ret.data.u64 = UINT64_MAX; + goto fail; + } + + val = cpu_to_le64(bar_access->val); + + res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED, + (void *)&val, bar_access->size, true); + + if (res != MEMTX_OK) { + error_setg(errp, "Bad address %"PRIx64" for mem write, pid "FMT_pid".", + bar_access->addr, getpid()); + ret.data.u64 = -1; + } + +fail: + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + BarAccessMsg *bar_access = &msg->data.bar_access; + MPQemuMsg ret = { 0 }; + AddressSpace *as; + MemTxResult res; + uint64_t val = 0; + + as = bar_access->memory ? &address_space_memory : &address_space_io; + + if (!is_power_of_2(bar_access->size) || + (bar_access->size > sizeof(uint64_t))) { + val = UINT64_MAX; + goto fail; + } + + res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED, + (void *)&val, bar_access->size, false); + + if (res != MEMTX_OK) { + error_setg(errp, "Bad address %"PRIx64" for mem read, pid "FMT_pid".", + bar_access->addr, getpid()); + val = UINT64_MAX; + } + +fail: + ret.cmd = MPQEMU_CMD_RET; + ret.data.u64 = le64_to_cpu(val); + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_device_reset_msg(QIOChannel *ioc, PCIDevice *dev, + Error **errp) +{ + DeviceClass *dc = DEVICE_GET_CLASS(dev); + DeviceState *s = DEVICE(dev); + MPQemuMsg ret = { 0 }; + + if (dc->reset) { + dc->reset(s); + } + + ret.cmd = MPQEMU_CMD_RET; + + mpqemu_msg_send(&ret, ioc, errp); +} diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c new file mode 100644 index 0000000000..9ce31526e8 --- /dev/null +++ b/hw/remote/mpqemu-link.c @@ -0,0 +1,267 @@ +/* + * Communication channel between QEMU and remote device process + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "qemu/module.h" +#include "hw/remote/mpqemu-link.h" +#include "qapi/error.h" +#include "qemu/iov.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "io/channel.h" +#include "sysemu/iothread.h" +#include "trace.h" + +/* + * Send message over the ioc QIOChannel. + * This function is safe to call from: + * - main loop in co-routine context. Will block the main loop if not in + * co-routine context; + * - vCPU thread with no co-routine context and if the channel is not part + * of the main loop handling; + * - IOThread within co-routine context, outside of co-routine context + * will block IOThread; + * Returns true if no errors were encountered, false otherwise. + */ +bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp) +{ + ERRP_GUARD(); + bool iolock = qemu_mutex_iothread_locked(); + bool iothread = qemu_in_iothread(); + struct iovec send[2] = {}; + int *fds = NULL; + size_t nfds = 0; + bool ret = false; + + send[0].iov_base = msg; + send[0].iov_len = MPQEMU_MSG_HDR_SIZE; + + send[1].iov_base = (void *)&msg->data; + send[1].iov_len = msg->size; + + if (msg->num_fds) { + nfds = msg->num_fds; + fds = msg->fds; + } + + /* + * Dont use in IOThread out of co-routine context as + * it will block IOThread. + */ + assert(qemu_in_coroutine() || !iothread); + + /* + * Skip unlocking/locking iothread lock when the IOThread is running + * in co-routine context. Co-routine context is asserted above + * for IOThread case. + * Also skip lock handling while in a co-routine in the main context. + */ + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_unlock_iothread(); + } + + if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send), + fds, nfds, errp)) { + ret = true; + } else { + trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds); + } + + if (iolock && !iothread && !qemu_in_coroutine()) { + /* See above comment why skip locking here. */ + qemu_mutex_lock_iothread(); + } + + return ret; +} + +/* + * Read message from the ioc QIOChannel. + * This function is safe to call from: + * - From main loop in co-routine context. Will block the main loop if not in + * co-routine context; + * - From vCPU thread with no co-routine context and if the channel is not part + * of the main loop handling; + * - From IOThread within co-routine context, outside of co-routine context + * will block IOThread; + */ +static ssize_t mpqemu_read(QIOChannel *ioc, void *buf, size_t len, int **fds, + size_t *nfds, Error **errp) +{ + ERRP_GUARD(); + struct iovec iov = { .iov_base = buf, .iov_len = len }; + bool iolock = qemu_mutex_iothread_locked(); + bool iothread = qemu_in_iothread(); + int ret = -1; + + /* + * Dont use in IOThread out of co-routine context as + * it will block IOThread. + */ + assert(qemu_in_coroutine() || !iothread); + + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_unlock_iothread(); + } + + ret = qio_channel_readv_full_all_eof(ioc, &iov, 1, fds, nfds, errp); + + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_lock_iothread(); + } + + return (ret <= 0) ? ret : iov.iov_len; +} + +bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp) +{ + ERRP_GUARD(); + g_autofree int *fds = NULL; + size_t nfds = 0; + ssize_t len; + bool ret = false; + + len = mpqemu_read(ioc, msg, MPQEMU_MSG_HDR_SIZE, &fds, &nfds, errp); + if (len <= 0) { + goto fail; + } else if (len != MPQEMU_MSG_HDR_SIZE) { + error_setg(errp, "Message header corrupted"); + goto fail; + } + + if (msg->size > sizeof(msg->data)) { + error_setg(errp, "Invalid size for message"); + goto fail; + } + + if (!msg->size) { + goto copy_fds; + } + + len = mpqemu_read(ioc, &msg->data, msg->size, NULL, NULL, errp); + if (len <= 0) { + goto fail; + } + if (len != msg->size) { + error_setg(errp, "Unable to read full message"); + goto fail; + } + +copy_fds: + msg->num_fds = nfds; + if (nfds > G_N_ELEMENTS(msg->fds)) { + error_setg(errp, + "Overflow error: received %zu fds, more than max of %d fds", + nfds, REMOTE_MAX_FDS); + goto fail; + } + if (nfds) { + memcpy(msg->fds, fds, nfds * sizeof(int)); + } + + ret = true; + +fail: + if (*errp) { + trace_mpqemu_recv_io_error(msg->cmd, msg->size, nfds); + } + while (*errp && nfds) { + close(fds[nfds - 1]); + nfds--; + } + + return ret; +} + +/* + * Send msg and wait for a reply with command code RET_MSG. + * Returns the message received of size u64 or UINT64_MAX + * on error. + * Called from VCPU thread in non-coroutine context. + * Used by the Proxy object to communicate to remote processes. + */ +uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, + Error **errp) +{ + ERRP_GUARD(); + MPQemuMsg msg_reply = {0}; + uint64_t ret = UINT64_MAX; + + assert(!qemu_in_coroutine()); + + QEMU_LOCK_GUARD(&pdev->io_mutex); + if (!mpqemu_msg_send(msg, pdev->ioc, errp)) { + return ret; + } + + if (!mpqemu_msg_recv(&msg_reply, pdev->ioc, errp)) { + return ret; + } + + if (!mpqemu_msg_valid(&msg_reply) || msg_reply.cmd != MPQEMU_CMD_RET) { + error_setg(errp, "ERROR: Invalid reply received for command %d", + msg->cmd); + return ret; + } + + return msg_reply.data.u64; +} + +bool mpqemu_msg_valid(MPQemuMsg *msg) +{ + if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) { + return false; + } + + /* Verify FDs. */ + if (msg->num_fds >= REMOTE_MAX_FDS) { + return false; + } + + if (msg->num_fds > 0) { + for (int i = 0; i < msg->num_fds; i++) { + if (fcntl(msg->fds[i], F_GETFL) == -1) { + return false; + } + } + } + + /* Verify message specific fields. */ + switch (msg->cmd) { + case MPQEMU_CMD_SYNC_SYSMEM: + if (msg->num_fds == 0 || msg->size != sizeof(SyncSysmemMsg)) { + return false; + } + break; + case MPQEMU_CMD_PCI_CFGWRITE: + case MPQEMU_CMD_PCI_CFGREAD: + if (msg->size != sizeof(PciConfDataMsg)) { + return false; + } + break; + case MPQEMU_CMD_BAR_WRITE: + case MPQEMU_CMD_BAR_READ: + if ((msg->size != sizeof(BarAccessMsg)) || (msg->num_fds != 0)) { + return false; + } + break; + case MPQEMU_CMD_SET_IRQFD: + if (msg->size || (msg->num_fds != 2)) { + return false; + } + break; + default: + break; + } + + return true; +} diff --git a/hw/remote/proxy-memory-listener.c b/hw/remote/proxy-memory-listener.c new file mode 100644 index 0000000000..af1fa6f5aa --- /dev/null +++ b/hw/remote/proxy-memory-listener.c @@ -0,0 +1,227 @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "qemu/compiler.h" +#include "qemu/int128.h" +#include "qemu/range.h" +#include "exec/memory.h" +#include "exec/cpu-common.h" +#include "cpu.h" +#include "exec/ram_addr.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "hw/remote/mpqemu-link.h" +#include "hw/remote/proxy-memory-listener.h" + +/* + * TODO: get_fd_from_hostaddr(), proxy_mrs_can_merge() and + * proxy_memory_listener_commit() defined below perform tasks similar to the + * functions defined in vhost-user.c. These functions are good candidates + * for refactoring. + * + */ + +static void proxy_memory_listener_reset(MemoryListener *listener) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + int mrs; + + for (mrs = 0; mrs < proxy_listener->n_mr_sections; mrs++) { + memory_region_unref(proxy_listener->mr_sections[mrs].mr); + } + + g_free(proxy_listener->mr_sections); + proxy_listener->mr_sections = NULL; + proxy_listener->n_mr_sections = 0; +} + +static int get_fd_from_hostaddr(uint64_t host, ram_addr_t *offset) +{ + MemoryRegion *mr; + ram_addr_t off; + + /** + * Assumes that the host address is a valid address as it's + * coming from the MemoryListener system. In the case host + * address is not valid, the following call would return + * the default subregion of "system_memory" region, and + * not NULL. So it's not possible to check for NULL here. + */ + mr = memory_region_from_host((void *)(uintptr_t)host, &off); + + if (offset) { + *offset = off; + } + + return memory_region_get_fd(mr); +} + +static bool proxy_mrs_can_merge(uint64_t host, uint64_t prev_host, size_t size) +{ + if (((prev_host + size) != host)) { + return false; + } + + if (get_fd_from_hostaddr(host, NULL) != + get_fd_from_hostaddr(prev_host, NULL)) { + return false; + } + + return true; +} + +static bool try_merge(ProxyMemoryListener *proxy_listener, + MemoryRegionSection *section) +{ + uint64_t mrs_size, mrs_gpa, mrs_page; + MemoryRegionSection *prev_sec; + bool merged = false; + uintptr_t mrs_host; + RAMBlock *mrs_rb; + + if (!proxy_listener->n_mr_sections) { + return false; + } + + mrs_rb = section->mr->ram_block; + mrs_page = (uint64_t)qemu_ram_pagesize(mrs_rb); + mrs_size = int128_get64(section->size); + mrs_gpa = section->offset_within_address_space; + mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) + + section->offset_within_region; + + if (get_fd_from_hostaddr(mrs_host, NULL) < 0) { + return true; + } + + mrs_host = mrs_host & ~(mrs_page - 1); + mrs_gpa = mrs_gpa & ~(mrs_page - 1); + mrs_size = ROUND_UP(mrs_size, mrs_page); + + prev_sec = proxy_listener->mr_sections + + (proxy_listener->n_mr_sections - 1); + uint64_t prev_gpa_start = prev_sec->offset_within_address_space; + uint64_t prev_size = int128_get64(prev_sec->size); + uint64_t prev_gpa_end = range_get_last(prev_gpa_start, prev_size); + uint64_t prev_host_start = + (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr) + + prev_sec->offset_within_region; + uint64_t prev_host_end = range_get_last(prev_host_start, prev_size); + + if (mrs_gpa <= (prev_gpa_end + 1)) { + g_assert(mrs_gpa > prev_gpa_start); + + if ((section->mr == prev_sec->mr) && + proxy_mrs_can_merge(mrs_host, prev_host_start, + (mrs_gpa - prev_gpa_start))) { + uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size); + merged = true; + prev_sec->offset_within_address_space = + MIN(prev_gpa_start, mrs_gpa); + prev_sec->offset_within_region = + MIN(prev_host_start, mrs_host) - + (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr); + prev_sec->size = int128_make64(max_end - MIN(prev_host_start, + mrs_host)); + } + } + + return merged; +} + +static void proxy_memory_listener_region_addnop(MemoryListener *listener, + MemoryRegionSection *section) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + + if (!memory_region_is_ram(section->mr) || + memory_region_is_rom(section->mr)) { + return; + } + + if (try_merge(proxy_listener, section)) { + return; + } + + ++proxy_listener->n_mr_sections; + proxy_listener->mr_sections = g_renew(MemoryRegionSection, + proxy_listener->mr_sections, + proxy_listener->n_mr_sections); + proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1] = *section; + proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1].fv = NULL; + memory_region_ref(section->mr); +} + +static void proxy_memory_listener_commit(MemoryListener *listener) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + MPQemuMsg msg; + MemoryRegionSection *section; + ram_addr_t offset; + uintptr_t host_addr; + int region; + Error *local_err = NULL; + + memset(&msg, 0, sizeof(MPQemuMsg)); + + msg.cmd = MPQEMU_CMD_SYNC_SYSMEM; + msg.num_fds = proxy_listener->n_mr_sections; + msg.size = sizeof(SyncSysmemMsg); + if (msg.num_fds > REMOTE_MAX_FDS) { + error_report("Number of fds is more than %d", REMOTE_MAX_FDS); + return; + } + + for (region = 0; region < proxy_listener->n_mr_sections; region++) { + section = &proxy_listener->mr_sections[region]; + msg.data.sync_sysmem.gpas[region] = + section->offset_within_address_space; + msg.data.sync_sysmem.sizes[region] = int128_get64(section->size); + host_addr = (uintptr_t)memory_region_get_ram_ptr(section->mr) + + section->offset_within_region; + msg.fds[region] = get_fd_from_hostaddr(host_addr, &offset); + msg.data.sync_sysmem.offsets[region] = offset; + } + if (!mpqemu_msg_send(&msg, proxy_listener->ioc, &local_err)) { + error_report_err(local_err); + } +} + +void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener) +{ + memory_listener_unregister(&proxy_listener->listener); + + proxy_memory_listener_reset(&proxy_listener->listener); +} + +void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener, + QIOChannel *ioc) +{ + proxy_listener->n_mr_sections = 0; + proxy_listener->mr_sections = NULL; + + proxy_listener->ioc = ioc; + + proxy_listener->listener.begin = proxy_memory_listener_reset; + proxy_listener->listener.commit = proxy_memory_listener_commit; + proxy_listener->listener.region_add = proxy_memory_listener_region_addnop; + proxy_listener->listener.region_nop = proxy_memory_listener_region_addnop; + proxy_listener->listener.priority = 10; + + memory_listener_register(&proxy_listener->listener, + &address_space_memory); +} diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c new file mode 100644 index 0000000000..4fa4be079d --- /dev/null +++ b/hw/remote/proxy.c @@ -0,0 +1,379 @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/proxy.h" +#include "hw/pci/pci.h" +#include "qapi/error.h" +#include "io/channel-util.h" +#include "hw/qdev-properties.h" +#include "monitor/monitor.h" +#include "migration/blocker.h" +#include "qemu/sockets.h" +#include "hw/remote/mpqemu-link.h" +#include "qemu/error-report.h" +#include "hw/remote/proxy-memory-listener.h" +#include "qom/object.h" +#include "qemu/event_notifier.h" +#include "sysemu/kvm.h" +#include "util/event_notifier-posix.c" + +static void probe_pci_info(PCIDevice *dev, Error **errp); +static void proxy_device_reset(DeviceState *dev); + +static void proxy_intx_update(PCIDevice *pci_dev) +{ + PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev); + PCIINTxRoute route; + int pin = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1; + + if (dev->virq != -1) { + kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &dev->intr, dev->virq); + dev->virq = -1; + } + + route = pci_device_route_intx_to_irq(pci_dev, pin); + + dev->virq = route.irq; + + if (dev->virq != -1) { + kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &dev->intr, + &dev->resample, dev->virq); + } +} + +static void setup_irqfd(PCIProxyDev *dev) +{ + PCIDevice *pci_dev = PCI_DEVICE(dev); + MPQemuMsg msg; + Error *local_err = NULL; + + event_notifier_init(&dev->intr, 0); + event_notifier_init(&dev->resample, 0); + + memset(&msg, 0, sizeof(MPQemuMsg)); + msg.cmd = MPQEMU_CMD_SET_IRQFD; + msg.num_fds = 2; + msg.fds[0] = event_notifier_get_fd(&dev->intr); + msg.fds[1] = event_notifier_get_fd(&dev->resample); + msg.size = 0; + + if (!mpqemu_msg_send(&msg, dev->ioc, &local_err)) { + error_report_err(local_err); + } + + dev->virq = -1; + + proxy_intx_update(pci_dev); + + pci_device_set_intx_routing_notifier(pci_dev, proxy_intx_update); +} + +static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) +{ + ERRP_GUARD(); + PCIProxyDev *dev = PCI_PROXY_DEV(device); + uint8_t *pci_conf = device->config; + int fd; + + if (!dev->fd) { + error_setg(errp, "fd parameter not specified for %s", + DEVICE(device)->id); + return; + } + + fd = monitor_fd_param(monitor_cur(), dev->fd, errp); + if (fd == -1) { + error_prepend(errp, "proxy: unable to parse fd %s: ", dev->fd); + return; + } + + if (!fd_is_socket(fd)) { + error_setg(errp, "proxy: fd %d is not a socket", fd); + close(fd); + return; + } + + dev->ioc = qio_channel_new_fd(fd, errp); + + error_setg(&dev->migration_blocker, "%s does not support migration", + TYPE_PCI_PROXY_DEV); + migrate_add_blocker(dev->migration_blocker, errp); + + qemu_mutex_init(&dev->io_mutex); + qio_channel_set_blocking(dev->ioc, true, NULL); + + pci_conf[PCI_LATENCY_TIMER] = 0xff; + pci_conf[PCI_INTERRUPT_PIN] = 0x01; + + proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc); + + setup_irqfd(dev); + + probe_pci_info(PCI_DEVICE(dev), errp); +} + +static void pci_proxy_dev_exit(PCIDevice *pdev) +{ + PCIProxyDev *dev = PCI_PROXY_DEV(pdev); + + if (dev->ioc) { + qio_channel_close(dev->ioc, NULL); + } + + migrate_del_blocker(dev->migration_blocker); + + error_free(dev->migration_blocker); + + proxy_memory_listener_deconfigure(&dev->proxy_listener); + + event_notifier_cleanup(&dev->intr); + event_notifier_cleanup(&dev->resample); +} + +static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val, + int len, unsigned int op) +{ + MPQemuMsg msg = { 0 }; + uint64_t ret = -EINVAL; + Error *local_err = NULL; + + msg.cmd = op; + msg.data.pci_conf_data.addr = addr; + msg.data.pci_conf_data.val = (op == MPQEMU_CMD_PCI_CFGWRITE) ? *val : 0; + msg.data.pci_conf_data.len = len; + msg.size = sizeof(PciConfDataMsg); + + ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + + if (ret == UINT64_MAX) { + error_report("Failed to perform PCI config %s operation", + (op == MPQEMU_CMD_PCI_CFGREAD) ? "READ" : "WRITE"); + } + + if (op == MPQEMU_CMD_PCI_CFGREAD) { + *val = (uint32_t)ret; + } +} + +static uint32_t pci_proxy_read_config(PCIDevice *d, uint32_t addr, int len) +{ + uint32_t val; + + config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGREAD); + + return val; +} + +static void pci_proxy_write_config(PCIDevice *d, uint32_t addr, uint32_t val, + int len) +{ + /* + * Some of the functions access the copy of remote device's PCI config + * space which is cached in the proxy device. Therefore, maintain + * it updated. + */ + pci_default_write_config(d, addr, val, len); + + config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGWRITE); +} + +static Property proxy_properties[] = { + DEFINE_PROP_STRING("fd", PCIProxyDev, fd), + DEFINE_PROP_END_OF_LIST(), +}; + +static void pci_proxy_dev_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + + k->realize = pci_proxy_dev_realize; + k->exit = pci_proxy_dev_exit; + k->config_read = pci_proxy_read_config; + k->config_write = pci_proxy_write_config; + + dc->reset = proxy_device_reset; + + device_class_set_props(dc, proxy_properties); +} + +static const TypeInfo pci_proxy_dev_type_info = { + .name = TYPE_PCI_PROXY_DEV, + .parent = TYPE_PCI_DEVICE, + .instance_size = sizeof(PCIProxyDev), + .class_init = pci_proxy_dev_class_init, + .interfaces = (InterfaceInfo[]) { + { INTERFACE_CONVENTIONAL_PCI_DEVICE }, + { }, + }, +}; + +static void pci_proxy_dev_register_types(void) +{ + type_register_static(&pci_proxy_dev_type_info); +} + +type_init(pci_proxy_dev_register_types) + +static void send_bar_access_msg(PCIProxyDev *pdev, MemoryRegion *mr, + bool write, hwaddr addr, uint64_t *val, + unsigned size, bool memory) +{ + MPQemuMsg msg = { 0 }; + long ret = -EINVAL; + Error *local_err = NULL; + + msg.size = sizeof(BarAccessMsg); + msg.data.bar_access.addr = mr->addr + addr; + msg.data.bar_access.size = size; + msg.data.bar_access.memory = memory; + + if (write) { + msg.cmd = MPQEMU_CMD_BAR_WRITE; + msg.data.bar_access.val = *val; + } else { + msg.cmd = MPQEMU_CMD_BAR_READ; + } + + ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + + if (!write) { + *val = ret; + } +} + +static void proxy_bar_write(void *opaque, hwaddr addr, uint64_t val, + unsigned size) +{ + ProxyMemoryRegion *pmr = opaque; + + send_bar_access_msg(pmr->dev, &pmr->mr, true, addr, &val, size, + pmr->memory); +} + +static uint64_t proxy_bar_read(void *opaque, hwaddr addr, unsigned size) +{ + ProxyMemoryRegion *pmr = opaque; + uint64_t val; + + send_bar_access_msg(pmr->dev, &pmr->mr, false, addr, &val, size, + pmr->memory); + + return val; +} + +const MemoryRegionOps proxy_mr_ops = { + .read = proxy_bar_read, + .write = proxy_bar_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 1, + .max_access_size = 8, + }, +}; + +static void probe_pci_info(PCIDevice *dev, Error **errp) +{ + PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev); + uint32_t orig_val, new_val, base_class, val; + PCIProxyDev *pdev = PCI_PROXY_DEV(dev); + DeviceClass *dc = DEVICE_CLASS(pc); + uint8_t type; + int i, size; + + config_op_send(pdev, PCI_VENDOR_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->vendor_id = (uint16_t)val; + + config_op_send(pdev, PCI_DEVICE_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->device_id = (uint16_t)val; + + config_op_send(pdev, PCI_CLASS_DEVICE, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->class_id = (uint16_t)val; + + config_op_send(pdev, PCI_SUBSYSTEM_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->subsystem_id = (uint16_t)val; + + base_class = pc->class_id >> 4; + switch (base_class) { + case PCI_BASE_CLASS_BRIDGE: + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); + break; + case PCI_BASE_CLASS_STORAGE: + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + break; + case PCI_BASE_CLASS_NETWORK: + set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); + break; + case PCI_BASE_CLASS_INPUT: + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + break; + case PCI_BASE_CLASS_DISPLAY: + set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); + break; + case PCI_BASE_CLASS_PROCESSOR: + set_bit(DEVICE_CATEGORY_CPU, dc->categories); + break; + default: + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + break; + } + + for (i = 0; i < PCI_NUM_REGIONS; i++) { + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4, + MPQEMU_CMD_PCI_CFGREAD); + new_val = 0xffffffff; + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4, + MPQEMU_CMD_PCI_CFGWRITE); + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4, + MPQEMU_CMD_PCI_CFGREAD); + size = (~(new_val & 0xFFFFFFF0)) + 1; + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4, + MPQEMU_CMD_PCI_CFGWRITE); + type = (new_val & 0x1) ? + PCI_BASE_ADDRESS_SPACE_IO : PCI_BASE_ADDRESS_SPACE_MEMORY; + + if (size) { + g_autofree char *name; + pdev->region[i].dev = pdev; + pdev->region[i].present = true; + if (type == PCI_BASE_ADDRESS_SPACE_MEMORY) { + pdev->region[i].memory = true; + } + name = g_strdup_printf("bar-region-%d", i); + memory_region_init_io(&pdev->region[i].mr, OBJECT(pdev), + &proxy_mr_ops, &pdev->region[i], + name, size); + pci_register_bar(dev, i, type, &pdev->region[i].mr); + } + } +} + +static void proxy_device_reset(DeviceState *dev) +{ + PCIProxyDev *pdev = PCI_PROXY_DEV(dev); + MPQemuMsg msg = { 0 }; + Error *local_err = NULL; + + msg.cmd = MPQEMU_CMD_DEVICE_RESET; + msg.size = 0; + + mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + +} diff --git a/hw/remote/remote-obj.c b/hw/remote/remote-obj.c new file mode 100644 index 0000000000..4f21254219 --- /dev/null +++ b/hw/remote/remote-obj.c @@ -0,0 +1,203 @@ +/* + * Copyright © 2020, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL-v2, version 2 or later. + * + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "qemu/error-report.h" +#include "qemu/notify.h" +#include "qom/object_interfaces.h" +#include "hw/qdev-core.h" +#include "io/channel.h" +#include "hw/qdev-core.h" +#include "hw/remote/machine.h" +#include "io/channel-util.h" +#include "qapi/error.h" +#include "sysemu/sysemu.h" +#include "hw/pci/pci.h" +#include "qemu/sockets.h" +#include "monitor/monitor.h" + +#define TYPE_REMOTE_OBJECT "x-remote-object" +OBJECT_DECLARE_TYPE(RemoteObject, RemoteObjectClass, REMOTE_OBJECT) + +struct RemoteObjectClass { + ObjectClass parent_class; + + unsigned int nr_devs; + unsigned int max_devs; +}; + +struct RemoteObject { + /* private */ + Object parent; + + Notifier machine_done; + + int32_t fd; + char *devid; + + QIOChannel *ioc; + + DeviceState *dev; + DeviceListener listener; +}; + +static void remote_object_set_fd(Object *obj, const char *str, Error **errp) +{ + RemoteObject *o = REMOTE_OBJECT(obj); + int fd = -1; + + fd = monitor_fd_param(monitor_cur(), str, errp); + if (fd == -1) { + error_prepend(errp, "Could not parse remote object fd %s:", str); + return; + } + + if (!fd_is_socket(fd)) { + error_setg(errp, "File descriptor '%s' is not a socket", str); + close(fd); + return; + } + + o->fd = fd; +} + +static void remote_object_set_devid(Object *obj, const char *str, Error **errp) +{ + RemoteObject *o = REMOTE_OBJECT(obj); + + g_free(o->devid); + + o->devid = g_strdup(str); +} + +static void remote_object_unrealize_listener(DeviceListener *listener, + DeviceState *dev) +{ + RemoteObject *o = container_of(listener, RemoteObject, listener); + + if (o->dev == dev) { + object_unref(OBJECT(o)); + } +} + +static void remote_object_machine_done(Notifier *notifier, void *data) +{ + RemoteObject *o = container_of(notifier, RemoteObject, machine_done); + DeviceState *dev = NULL; + QIOChannel *ioc = NULL; + Coroutine *co = NULL; + RemoteCommDev *comdev = NULL; + Error *err = NULL; + + dev = qdev_find_recursive(sysbus_get_default(), o->devid); + if (!dev || !object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + error_report("%s is not a PCI device", o->devid); + return; + } + + ioc = qio_channel_new_fd(o->fd, &err); + if (!ioc) { + error_report_err(err); + return; + } + qio_channel_set_blocking(ioc, false, NULL); + + o->dev = dev; + + o->listener.unrealize = remote_object_unrealize_listener; + device_listener_register(&o->listener); + + /* co-routine should free this. */ + comdev = g_new0(RemoteCommDev, 1); + *comdev = (RemoteCommDev) { + .ioc = ioc, + .dev = PCI_DEVICE(dev), + }; + + co = qemu_coroutine_create(mpqemu_remote_msg_loop_co, comdev); + qemu_coroutine_enter(co); +} + +static void remote_object_init(Object *obj) +{ + RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj); + RemoteObject *o = REMOTE_OBJECT(obj); + + if (k->nr_devs >= k->max_devs) { + error_report("Reached maximum number of devices: %u", k->max_devs); + return; + } + + o->ioc = NULL; + o->fd = -1; + o->devid = NULL; + + k->nr_devs++; + + o->machine_done.notify = remote_object_machine_done; + qemu_add_machine_init_done_notifier(&o->machine_done); +} + +static void remote_object_finalize(Object *obj) +{ + RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj); + RemoteObject *o = REMOTE_OBJECT(obj); + + device_listener_unregister(&o->listener); + + if (o->ioc) { + qio_channel_shutdown(o->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + qio_channel_close(o->ioc, NULL); + } + + object_unref(OBJECT(o->ioc)); + + k->nr_devs--; + g_free(o->devid); +} + +static void remote_object_class_init(ObjectClass *klass, void *data) +{ + RemoteObjectClass *k = REMOTE_OBJECT_CLASS(klass); + + /* + * Limit number of supported devices to 1. This is done to avoid devices + * from one VM accessing the RAM of another VM. This is done until we + * start using separate address spaces for individual devices. + */ + k->max_devs = 1; + k->nr_devs = 0; + + object_class_property_add_str(klass, "fd", NULL, remote_object_set_fd); + object_class_property_add_str(klass, "devid", NULL, + remote_object_set_devid); +} + +static const TypeInfo remote_object_info = { + .name = TYPE_REMOTE_OBJECT, + .parent = TYPE_OBJECT, + .instance_size = sizeof(RemoteObject), + .instance_init = remote_object_init, + .instance_finalize = remote_object_finalize, + .class_size = sizeof(RemoteObjectClass), + .class_init = remote_object_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static void register_types(void) +{ + type_register_static(&remote_object_info); +} + +type_init(register_types); diff --git a/hw/remote/trace-events b/hw/remote/trace-events new file mode 100644 index 0000000000..0b23974f90 --- /dev/null +++ b/hw/remote/trace-events @@ -0,0 +1,4 @@ +# multi-process trace events + +mpqemu_send_io_error(int cmd, int size, int nfds) "send command %d size %d, %d file descriptors to remote process" +mpqemu_recv_io_error(int cmd, int size, int nfds) "failed to receive %d size %d, %d file descriptors to remote process" diff --git a/hw/remote/trace.h b/hw/remote/trace.h new file mode 100644 index 0000000000..5d5e3ac720 --- /dev/null +++ b/hw/remote/trace.h @@ -0,0 +1 @@ +#include "trace/trace-hw_remote.h" diff --git a/include/exec/memory.h b/include/exec/memory.h index ed292767cd..c6fb714e49 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -998,6 +998,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr, * @size: size of the region. * @share: %true if memory must be mmaped with the MAP_SHARED flag * @fd: the fd to mmap. + * @offset: offset within the file referenced by fd * @errp: pointer to Error*, to store an error if it happens. * * Note that this function does not do anything to cause the data in the @@ -1009,6 +1010,7 @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, uint64_t size, bool share, int fd, + ram_addr_t offset, Error **errp); #endif diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 40b16609ab..3cb9791df3 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -121,8 +121,8 @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, uint32_t ram_flags, const char *mem_path, bool readonly, Error **errp); RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, - uint32_t ram_flags, int fd, bool readonly, - Error **errp); + uint32_t ram_flags, int fd, off_t offset, + bool readonly, Error **errp); RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, MemoryRegion *mr, Error **errp); diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h new file mode 100644 index 0000000000..3dcf6aa51d --- /dev/null +++ b/include/hw/pci-host/remote.h @@ -0,0 +1,30 @@ +/* + * PCI Host for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_PCIHOST_H +#define REMOTE_PCIHOST_H + +#include "exec/memory.h" +#include "hw/pci/pcie_host.h" + +#define TYPE_REMOTE_PCIHOST "remote-pcihost" +OBJECT_DECLARE_SIMPLE_TYPE(RemotePCIHost, REMOTE_PCIHOST) + +struct RemotePCIHost { + /*< private >*/ + PCIExpressHost parent_obj; + /*< public >*/ + + MemoryRegion *mr_pci_mem; + MemoryRegion *mr_sys_io; + MemoryRegion *mr_sys_mem; +}; + +#endif diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h index 11f8ab7149..bd0c17dc78 100644 --- a/include/hw/pci/pci_ids.h +++ b/include/hw/pci/pci_ids.h @@ -192,6 +192,9 @@ #define PCI_DEVICE_ID_SUN_SIMBA 0x5000 #define PCI_DEVICE_ID_SUN_SABRE 0xa000 +#define PCI_VENDOR_ID_ORACLE 0x108e +#define PCI_DEVICE_ID_REMOTE_IOHUB 0xb000 + #define PCI_VENDOR_ID_CMD 0x1095 #define PCI_DEVICE_ID_CMD_646 0x0646 diff --git a/include/hw/remote/iohub.h b/include/hw/remote/iohub.h new file mode 100644 index 0000000000..0bf98e0d78 --- /dev/null +++ b/include/hw/remote/iohub.h @@ -0,0 +1,42 @@ +/* + * IO Hub for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_IOHUB_H +#define REMOTE_IOHUB_H + +#include "hw/pci/pci.h" +#include "qemu/event_notifier.h" +#include "qemu/thread-posix.h" +#include "hw/remote/mpqemu-link.h" + +#define REMOTE_IOHUB_NB_PIRQS PCI_DEVFN_MAX + +typedef struct ResampleToken { + void *iohub; + int pirq; +} ResampleToken; + +typedef struct RemoteIOHubState { + PCIDevice d; + EventNotifier irqfds[REMOTE_IOHUB_NB_PIRQS]; + EventNotifier resamplefds[REMOTE_IOHUB_NB_PIRQS]; + unsigned int irq_level[REMOTE_IOHUB_NB_PIRQS]; + ResampleToken token[REMOTE_IOHUB_NB_PIRQS]; + QemuMutex irq_level_lock[REMOTE_IOHUB_NB_PIRQS]; +} RemoteIOHubState; + +int remote_iohub_map_irq(PCIDevice *pci_dev, int intx); +void remote_iohub_set_irq(void *opaque, int pirq, int level); +void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg); + +void remote_iohub_init(RemoteIOHubState *iohub); +void remote_iohub_finalize(RemoteIOHubState *iohub); + +#endif diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h new file mode 100644 index 0000000000..2a2a33c4b2 --- /dev/null +++ b/include/hw/remote/machine.h @@ -0,0 +1,38 @@ +/* + * Remote machine configuration + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_MACHINE_H +#define REMOTE_MACHINE_H + +#include "qom/object.h" +#include "hw/boards.h" +#include "hw/pci-host/remote.h" +#include "io/channel.h" +#include "hw/remote/iohub.h" + +struct RemoteMachineState { + MachineState parent_obj; + + RemotePCIHost *host; + RemoteIOHubState iohub; +}; + +/* Used to pass to co-routine device and ioc. */ +typedef struct RemoteCommDev { + PCIDevice *dev; + QIOChannel *ioc; +} RemoteCommDev; + +#define TYPE_REMOTE_MACHINE "x-remote-machine" +OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE) + +void coroutine_fn mpqemu_remote_msg_loop_co(void *data); + +#endif diff --git a/include/hw/remote/memory.h b/include/hw/remote/memory.h new file mode 100644 index 0000000000..bc2e30945f --- /dev/null +++ b/include/hw/remote/memory.h @@ -0,0 +1,19 @@ +/* + * Memory manager for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_MEMORY_H +#define REMOTE_MEMORY_H + +#include "exec/hwaddr.h" +#include "hw/remote/mpqemu-link.h" + +void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp); + +#endif diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h new file mode 100644 index 0000000000..4ec0915885 --- /dev/null +++ b/include/hw/remote/mpqemu-link.h @@ -0,0 +1,99 @@ +/* + * Communication channel between QEMU and remote device process + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef MPQEMU_LINK_H +#define MPQEMU_LINK_H + +#include "qom/object.h" +#include "qemu/thread.h" +#include "io/channel.h" +#include "exec/hwaddr.h" +#include "io/channel-socket.h" +#include "hw/remote/proxy.h" + +#define REMOTE_MAX_FDS 8 + +#define MPQEMU_MSG_HDR_SIZE offsetof(MPQemuMsg, data.u64) + +/** + * MPQemuCmd: + * + * MPQemuCmd enum type to specify the command to be executed on the remote + * device. + * + * This uses a private protocol between QEMU and the remote process. vfio-user + * protocol would supersede this in the future. + * + */ +typedef enum { + MPQEMU_CMD_SYNC_SYSMEM, + MPQEMU_CMD_RET, + MPQEMU_CMD_PCI_CFGWRITE, + MPQEMU_CMD_PCI_CFGREAD, + MPQEMU_CMD_BAR_WRITE, + MPQEMU_CMD_BAR_READ, + MPQEMU_CMD_SET_IRQFD, + MPQEMU_CMD_DEVICE_RESET, + MPQEMU_CMD_MAX, +} MPQemuCmd; + +typedef struct { + hwaddr gpas[REMOTE_MAX_FDS]; + uint64_t sizes[REMOTE_MAX_FDS]; + off_t offsets[REMOTE_MAX_FDS]; +} SyncSysmemMsg; + +typedef struct { + uint32_t addr; + uint32_t val; + int len; +} PciConfDataMsg; + +typedef struct { + hwaddr addr; + uint64_t val; + unsigned size; + bool memory; +} BarAccessMsg; + +/** + * MPQemuMsg: + * @cmd: The remote command + * @size: Size of the data to be shared + * @data: Structured data + * @fds: File descriptors to be shared with remote device + * + * MPQemuMsg Format of the message sent to the remote device from QEMU. + * + */ + +typedef struct { + int cmd; + size_t size; + + union { + uint64_t u64; + PciConfDataMsg pci_conf_data; + SyncSysmemMsg sync_sysmem; + BarAccessMsg bar_access; + } data; + + int fds[REMOTE_MAX_FDS]; + int num_fds; +} MPQemuMsg; + +bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); +bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); + +uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, + Error **errp); +bool mpqemu_msg_valid(MPQemuMsg *msg); + +#endif diff --git a/include/hw/remote/proxy-memory-listener.h b/include/hw/remote/proxy-memory-listener.h new file mode 100644 index 0000000000..c4f3efb928 --- /dev/null +++ b/include/hw/remote/proxy-memory-listener.h @@ -0,0 +1,28 @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef PROXY_MEMORY_LISTENER_H +#define PROXY_MEMORY_LISTENER_H + +#include "exec/memory.h" +#include "io/channel.h" + +typedef struct ProxyMemoryListener { + MemoryListener listener; + + int n_mr_sections; + MemoryRegionSection *mr_sections; + + QIOChannel *ioc; +} ProxyMemoryListener; + +void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener, + QIOChannel *ioc); +void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener); + +#endif diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h new file mode 100644 index 0000000000..741def71f1 --- /dev/null +++ b/include/hw/remote/proxy.h @@ -0,0 +1,48 @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef PROXY_H +#define PROXY_H + +#include "hw/pci/pci.h" +#include "io/channel.h" +#include "hw/remote/proxy-memory-listener.h" +#include "qemu/event_notifier.h" + +#define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" +OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) + +typedef struct ProxyMemoryRegion { + PCIProxyDev *dev; + MemoryRegion mr; + bool memory; + bool present; + uint8_t type; +} ProxyMemoryRegion; + +struct PCIProxyDev { + PCIDevice parent_dev; + char *fd; + + /* + * Mutex used to protect the QIOChannel fd from + * the concurrent access by the VCPUs since proxy + * blocks while awaiting for the replies from the + * process remote. + */ + QemuMutex io_mutex; + QIOChannel *ioc; + Error *migration_blocker; + ProxyMemoryListener proxy_listener; + int virq; + EventNotifier intr; + EventNotifier resample; + ProxyMemoryRegion region[PCI_NUM_REGIONS]; +}; + +#endif /* PROXY_H */ diff --git a/include/io/channel.h b/include/io/channel.h index ab9ea77959..88988979f8 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -777,4 +777,82 @@ void qio_channel_set_aio_fd_handler(QIOChannel *ioc, IOHandler *io_write, void *opaque); +/** + * qio_channel_readv_full_all_eof: + * @ioc: the channel object + * @iov: the array of memory regions to read data to + * @niov: the length of the @iov array + * @fds: an array of file handles to read + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Performs same function as qio_channel_readv_all_eof. + * Additionally, attempts to read file descriptors shared + * over the channel. The function will wait for all + * requested data to be read, yielding from the current + * coroutine if required. data refers to both file + * descriptors and the iovs. + * + * Returns: 1 if all bytes were read, 0 if end-of-file + * occurs without data, or -1 on error + */ + +int qio_channel_readv_full_all_eof(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp); + +/** + * qio_channel_readv_full_all: + * @ioc: the channel object + * @iov: the array of memory regions to read data to + * @niov: the length of the @iov array + * @fds: an array of file handles to read + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Performs same function as qio_channel_readv_all_eof. + * Additionally, attempts to read file descriptors shared + * over the channel. The function will wait for all + * requested data to be read, yielding from the current + * coroutine if required. data refers to both file + * descriptors and the iovs. + * + * Returns: 0 if all bytes were read, or -1 on error + */ + +int qio_channel_readv_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp); + +/** + * qio_channel_writev_full_all: + * @ioc: the channel object + * @iov: the array of memory regions to write data from + * @niov: the length of the @iov array + * @fds: an array of file handles to send + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Behaves like qio_channel_writev_full but will attempt + * to send all data passed (file handles and memory regions). + * The function will wait for all requested data + * to be written, yielding from the current coroutine + * if required. + * + * Returns: 0 if all bytes were written, or -1 on error + */ + +int qio_channel_writev_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int *fds, size_t nfds, + Error **errp); + #endif /* QIO_CHANNEL_H */ diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h index 8b7a5c70f3..456ff87df1 100644 --- a/include/qemu/mmap-alloc.h +++ b/include/qemu/mmap-alloc.h @@ -17,6 +17,7 @@ size_t qemu_mempath_getpagesize(const char *mem_path); * @readonly: true for a read-only mapping, false for read/write. * @shared: map has RAM_SHARED flag. * @is_pmem: map has RAM_PMEM flag. + * @map_offset: map starts at offset of map_offset from the start of fd * * Return: * On success, return a pointer to the mapped area. @@ -27,7 +28,8 @@ void *qemu_ram_mmap(int fd, size_t align, bool readonly, bool shared, - bool is_pmem); + bool is_pmem, + off_t map_offset); void qemu_ram_munmap(int fd, void *ptr, size_t size); diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h index 0c5284dbbc..f177142f16 100644 --- a/include/sysemu/iothread.h +++ b/include/sysemu/iothread.h @@ -57,4 +57,10 @@ IOThread *iothread_create(const char *id, Error **errp); void iothread_stop(IOThread *iothread); void iothread_destroy(IOThread *iothread); +/* + * Returns true if executing withing IOThread context, + * false otherwise. + */ +bool qemu_in_iothread(void); + #endif /* IOTHREAD_H */ diff --git a/io/channel.c b/io/channel.c index 93d449dee2..4555021b62 100644 --- a/io/channel.c +++ b/io/channel.c @@ -92,19 +92,47 @@ int qio_channel_readv_all_eof(QIOChannel *ioc, size_t niov, Error **errp) { + return qio_channel_readv_full_all_eof(ioc, iov, niov, NULL, NULL, errp); +} + +int qio_channel_readv_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + Error **errp) +{ + return qio_channel_readv_full_all(ioc, iov, niov, NULL, NULL, errp); +} + +int qio_channel_readv_full_all_eof(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp) +{ int ret = -1; struct iovec *local_iov = g_new(struct iovec, niov); struct iovec *local_iov_head = local_iov; unsigned int nlocal_iov = niov; + int **local_fds = fds; + size_t *local_nfds = nfds; bool partial = false; + if (nfds) { + *nfds = 0; + } + + if (fds) { + *fds = NULL; + } + nlocal_iov = iov_copy(local_iov, nlocal_iov, iov, niov, 0, iov_size(iov, niov)); - while (nlocal_iov > 0) { + while ((nlocal_iov > 0) || local_fds) { ssize_t len; - len = qio_channel_readv(ioc, local_iov, nlocal_iov, errp); + len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds, + local_nfds, errp); if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { qio_channel_yield(ioc, G_IO_IN); @@ -112,20 +140,50 @@ int qio_channel_readv_all_eof(QIOChannel *ioc, qio_channel_wait(ioc, G_IO_IN); } continue; - } else if (len < 0) { - goto cleanup; - } else if (len == 0) { - if (partial) { - error_setg(errp, - "Unexpected end-of-file before all bytes were read"); - } else { + } + + if (len == 0) { + if (local_nfds && *local_nfds) { + /* + * Got some FDs, but no data yet. This isn't an EOF + * scenario (yet), so carry on to try to read data + * on next loop iteration + */ + goto next_iter; + } else if (!partial) { + /* No fds and no data - EOF before any data read */ ret = 0; + goto cleanup; + } else { + len = -1; + error_setg(errp, + "Unexpected end-of-file before all data were read"); + /* Fallthrough into len < 0 handling */ + } + } + + if (len < 0) { + /* Close any FDs we previously received */ + if (nfds && fds) { + size_t i; + for (i = 0; i < (*nfds); i++) { + close((*fds)[i]); + } + g_free(*fds); + *fds = NULL; + *nfds = 0; } goto cleanup; } + if (nlocal_iov) { + iov_discard_front(&local_iov, &nlocal_iov, len); + } + +next_iter: partial = true; - iov_discard_front(&local_iov, &nlocal_iov, len); + local_fds = NULL; + local_nfds = NULL; } ret = 1; @@ -135,20 +193,23 @@ int qio_channel_readv_all_eof(QIOChannel *ioc, return ret; } -int qio_channel_readv_all(QIOChannel *ioc, - const struct iovec *iov, - size_t niov, - Error **errp) +int qio_channel_readv_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp) { - int ret = qio_channel_readv_all_eof(ioc, iov, niov, errp); + int ret = qio_channel_readv_full_all_eof(ioc, iov, niov, fds, nfds, errp); if (ret == 0) { - ret = -1; - error_setg(errp, - "Unexpected end-of-file before all bytes were read"); - } else if (ret == 1) { - ret = 0; + error_prepend(errp, + "Unexpected end-of-file before all data were read."); + return -1; + } + if (ret == 1) { + return 0; } + return ret; } @@ -157,6 +218,15 @@ int qio_channel_writev_all(QIOChannel *ioc, size_t niov, Error **errp) { + return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, errp); +} + +int qio_channel_writev_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int *fds, size_t nfds, + Error **errp) +{ int ret = -1; struct iovec *local_iov = g_new(struct iovec, niov); struct iovec *local_iov_head = local_iov; @@ -168,7 +238,8 @@ int qio_channel_writev_all(QIOChannel *ioc, while (nlocal_iov > 0) { ssize_t len; - len = qio_channel_writev(ioc, local_iov, nlocal_iov, errp); + len = qio_channel_writev_full(ioc, local_iov, nlocal_iov, fds, nfds, + errp); if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { qio_channel_yield(ioc, G_IO_OUT); @@ -182,6 +253,9 @@ int qio_channel_writev_all(QIOChannel *ioc, } iov_discard_front(&local_iov, &nlocal_iov, len); + + fds = NULL; + nfds = 0; } ret = 0; diff --git a/iothread.c b/iothread.c index b9f2751382..7f086387be 100644 --- a/iothread.c +++ b/iothread.c @@ -369,3 +369,9 @@ IOThread *iothread_by_id(const char *id) { return IOTHREAD(object_resolve_path_type(id, TYPE_IOTHREAD, NULL)); } + +bool qemu_in_iothread(void) +{ + return qemu_get_current_aio_context() == qemu_get_aio_context() ? + false : true; +} diff --git a/meson.build b/meson.build index e3ef660670..a923f249d8 100644 --- a/meson.build +++ b/meson.build @@ -1226,7 +1226,8 @@ host_kconfig = \ ('CONFIG_VHOST_KERNEL' in config_host ? ['CONFIG_VHOST_KERNEL=y'] : []) + \ (have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \ ('CONFIG_LINUX' in config_host ? ['CONFIG_LINUX=y'] : []) + \ - ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + \ + ('CONFIG_MULTIPROCESS_ALLOWED' in config_host ? ['CONFIG_MULTIPROCESS_ALLOWED=y'] : []) ignored = [ 'TARGET_XML_FILES', 'TARGET_ABI_DIR', 'TARGET_ARCH' ] @@ -1817,6 +1818,7 @@ if have_system 'net', 'softmmu', 'ui', + 'hw/remote', ] endif if have_system or have_user @@ -2652,6 +2654,7 @@ summary_info += {'libpmem support': config_host.has_key('CONFIG_LIBPMEM')} summary_info += {'libdaxctl support': config_host.has_key('CONFIG_LIBDAXCTL')} summary_info += {'libudev': libudev.found()} summary_info += {'FUSE lseek': fuse_lseek.found()} +summary_info += {'Multiprocess QEMU': config_host.has_key('CONFIG_MULTIPROCESS_ALLOWED')} summary(summary_info, bool_yn: true, section: 'Dependencies') if not supported_cpus.contains(cpu) diff --git a/pc-bios/README b/pc-bios/README index 33f9754ad3..db7129ef64 100644 --- a/pc-bios/README +++ b/pc-bios/README @@ -20,7 +20,7 @@ legacy x86 software to communicate with an attached serial console as if a video card were attached. The master sources reside in a subversion repository at http://sgabios.googlecode.com/svn/trunk. A git mirror is - available at https://git.qemu.org/git/sgabios.git. + available at https://gitlab.com/qemu-project/sgabios.git. - The PXE roms come from the iPXE project. Built with BANNER_TIME 0. Sources available at http://ipxe.org. Vendor:Device ID -> ROM mapping: @@ -37,7 +37,7 @@ - The u-boot binary for e500 comes from the upstream denx u-boot project where it was compiled using the qemu-ppce500 target. - A git mirror is available at: https://git.qemu.org/git/u-boot.git + A git mirror is available at: https://gitlab.com/qemu-project/u-boot.git The hash used to compile the current version is: 2072e72 - Skiboot (https://github.com/open-power/skiboot/) is an OPAL diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 271f5ff42a..e5499b94b4 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -1377,7 +1377,7 @@ sub vcs_exists { warn("$P: No supported VCS found. Add --nogit to options?\n"); warn("Using a git repository produces better results.\n"); warn("Try latest git repository using:\n"); - warn("git clone https://git.qemu.org/git/qemu.git\n"); + warn("git clone https://gitlab.com/qemu-project/qemu.git\n"); $printed_novcs = 1; } return 0; diff --git a/softmmu/memory.c b/softmmu/memory.c index 23e8e33001..874a8fccde 100644 --- a/softmmu/memory.c +++ b/softmmu/memory.c @@ -1612,6 +1612,7 @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, uint64_t size, bool share, int fd, + ram_addr_t offset, Error **errp) { Error *err = NULL; @@ -1621,7 +1622,7 @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, mr->destructor = memory_region_destructor_ram; mr->ram_block = qemu_ram_alloc_from_fd(size, mr, share ? RAM_SHARED : 0, - fd, false, &err); + fd, offset, false, &err); if (err) { mr->size = int128_zero(); object_unparent(OBJECT(mr)); diff --git a/softmmu/physmem.c b/softmmu/physmem.c index 96efaef97a..19e0aa9836 100644 --- a/softmmu/physmem.c +++ b/softmmu/physmem.c @@ -1543,6 +1543,7 @@ static void *file_ram_alloc(RAMBlock *block, int fd, bool readonly, bool truncate, + off_t offset, Error **errp) { void *area; @@ -1593,7 +1594,8 @@ static void *file_ram_alloc(RAMBlock *block, } area = qemu_ram_mmap(fd, memory, block->mr->align, readonly, - block->flags & RAM_SHARED, block->flags & RAM_PMEM); + block->flags & RAM_SHARED, block->flags & RAM_PMEM, + offset); if (area == MAP_FAILED) { error_setg_errno(errp, errno, "unable to map backing store for guest RAM"); @@ -2024,8 +2026,8 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared) #ifdef CONFIG_POSIX RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, - uint32_t ram_flags, int fd, bool readonly, - Error **errp) + uint32_t ram_flags, int fd, off_t offset, + bool readonly, Error **errp) { RAMBlock *new_block; Error *local_err = NULL; @@ -2079,7 +2081,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, new_block->max_length = size; new_block->flags = ram_flags; new_block->host = file_ram_alloc(new_block, size, fd, readonly, - !file_size, errp); + !file_size, offset, errp); if (!new_block->host) { g_free(new_block); return NULL; @@ -2110,7 +2112,7 @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, return NULL; } - block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, readonly, errp); + block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, 0, readonly, errp); if (!block) { if (created) { unlink(mem_path); diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c index 890fda6a35..e6fa8b598b 100644 --- a/util/mmap-alloc.c +++ b/util/mmap-alloc.c @@ -87,7 +87,8 @@ void *qemu_ram_mmap(int fd, size_t align, bool readonly, bool shared, - bool is_pmem) + bool is_pmem, + off_t map_offset) { int prot; int flags; @@ -150,7 +151,8 @@ void *qemu_ram_mmap(int fd, prot = PROT_READ | (readonly ? 0 : PROT_WRITE); - ptr = mmap(guardptr + offset, size, prot, flags | map_sync_flags, fd, 0); + ptr = mmap(guardptr + offset, size, prot, + flags | map_sync_flags, fd, map_offset); if (ptr == MAP_FAILED && map_sync_flags) { if (errno == ENOTSUP) { @@ -174,7 +176,7 @@ void *qemu_ram_mmap(int fd, * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC, * we will remove these flags to handle compatibility. */ - ptr = mmap(guardptr + offset, size, prot, flags, fd, 0); + ptr = mmap(guardptr + offset, size, prot, flags, fd, map_offset); } if (ptr == MAP_FAILED) { diff --git a/util/oslib-posix.c b/util/oslib-posix.c index bf57d3b030..36820fec16 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -230,7 +230,7 @@ void *qemu_memalign(size_t alignment, size_t size) void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared) { size_t align = QEMU_VMALLOC_ALIGN; - void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false); + void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false, 0); if (ptr == MAP_FAILED) { return NULL; |