xref: /openbmc/qemu/docs/devel/multi-process.rst (revision 4921d0a7)
1Multi-process QEMU
2===================
3
4.. note::
5
6  This is the design document for multi-process QEMU. It does not
7  necessarily reflect the status of the current implementation, which
8  may lack features or be considerably different from what is described
9  in this document. This document is still useful as a description of
10  the goals and general direction of this feature.
11
12  Please refer to the following wiki for latest details:
13  https://wiki.qemu.org/Features/MultiProcessQEMU
14
15QEMU is often used as the hypervisor for virtual machines running in the
16Oracle cloud. Since one of the advantages of cloud computing is the
17ability to run many VMs from different tenants in the same cloud
18infrastructure, a guest that compromised its hypervisor could
19potentially use the hypervisor's access privileges to access data it is
20not authorized for.
21
22QEMU can be susceptible to security attacks because it is a large,
23monolithic program that provides many features to the VMs it services.
24Many of these features can be configured out of QEMU, but even a reduced
25configuration QEMU has a large amount of code a guest can potentially
26attack. Separating QEMU reduces the attack surface by aiding to
27limit each component in the system to only access the resources that
28it needs to perform its job.
29
30QEMU services
31-------------
32
33QEMU can be broadly described as providing three main services. One is a
34VM control point, where VMs can be created, migrated, re-configured, and
35destroyed. A second is to emulate the CPU instructions within the VM,
36often accelerated by HW virtualization features such as Intel's VT
37extensions. Finally, it provides IO services to the VM by emulating HW
38IO devices, such as disk and network devices.
39
40A multi-process QEMU
41~~~~~~~~~~~~~~~~~~~~
42
43A multi-process QEMU involves separating QEMU services into separate
44host processes. Each of these processes can be given only the privileges
45it needs to provide its service, e.g., a disk service could be given
46access only to the disk images it provides, and not be allowed to
47access other files, or any network devices. An attacker who compromised
48this service would not be able to use this exploit to access files or
49devices beyond what the disk service was given access to.
50
51A QEMU control process would remain, but in multi-process mode, will
52have no direct interfaces to the VM. During VM execution, it would still
53provide the user interface to hot-plug devices or live migrate the VM.
54
55A first step in creating a multi-process QEMU is to separate IO services
56from the main QEMU program, which would continue to provide CPU
57emulation. i.e., the control process would also be the CPU emulation
58process. In a later phase, CPU emulation could be separated from the
59control process.
60
61Separating IO services
62----------------------
63
64Separating IO services into individual host processes is a good place to
65begin for a couple of reasons. One is the sheer number of IO devices QEMU
66can emulate provides a large surface of interfaces which could potentially
67be exploited, and, indeed, have been a source of exploits in the past.
68Another is the modular nature of QEMU device emulation code provides
69interface points where the QEMU functions that perform device emulation
70can be separated from the QEMU functions that manage the emulation of
71guest CPU instructions. The devices emulated in the separate process are
72referred to as remote devices.
73
74QEMU device emulation
75~~~~~~~~~~~~~~~~~~~~~
76
77QEMU uses an object oriented SW architecture for device emulation code.
78Configured objects are all compiled into the QEMU binary, then objects
79are instantiated by name when used by the guest VM. For example, the
80code to emulate a device named "foo" is always present in QEMU, but its
81instantiation code is only run when the device is included in the target
82VM. (e.g., via the QEMU command line as *-device foo*)
83
84The object model is hierarchical, so device emulation code names its
85parent object (such as "pci-device" for a PCI device) and QEMU will
86instantiate a parent object before calling the device's instantiation
87code.
88
89Current separation models
90~~~~~~~~~~~~~~~~~~~~~~~~~
91
92In order to separate the device emulation code from the CPU emulation
93code, the device object code must run in a different process. There are
94a couple of existing QEMU features that can run emulation code
95separately from the main QEMU process. These are examined below.
96
97vhost user model
98^^^^^^^^^^^^^^^^
99
100Virtio guest device drivers can be connected to vhost user applications
101in order to perform their IO operations. This model uses special virtio
102device drivers in the guest and vhost user device objects in QEMU, but
103once the QEMU vhost user code has configured the vhost user application,
104mission-mode IO is performed by the application. The vhost user
105application is a daemon process that can be contacted via a known UNIX
106domain socket.
107
108vhost socket
109''''''''''''
110
111As mentioned above, one of the tasks of the vhost device object within
112QEMU is to contact the vhost application and send it configuration
113information about this device instance. As part of the configuration
114process, the application can also be sent other file descriptors over
115the socket, which then can be used by the vhost user application in
116various ways, some of which are described below.
117
118vhost MMIO store acceleration
119'''''''''''''''''''''''''''''
120
121VMs are often run using HW virtualization features via the KVM kernel
122driver. This driver allows QEMU to accelerate the emulation of guest CPU
123instructions by running the guest in a virtual HW mode. When the guest
124executes instructions that cannot be executed by virtual HW mode,
125execution returns to the KVM driver so it can inform QEMU to emulate the
126instructions in SW.
127
128One of the events that can cause a return to QEMU is when a guest device
129driver accesses an IO location. QEMU then dispatches the memory
130operation to the corresponding QEMU device object. In the case of a
131vhost user device, the memory operation would need to be sent over a
132socket to the vhost application. This path is accelerated by the QEMU
133virtio code by setting up an eventfd file descriptor that the vhost
134application can directly receive MMIO store notifications from the KVM
135driver, instead of needing them to be sent to the QEMU process first.
136
137vhost interrupt acceleration
138''''''''''''''''''''''''''''
139
140Another optimization used by the vhost application is the ability to
141directly inject interrupts into the VM via the KVM driver, again,
142bypassing the need to send the interrupt back to the QEMU process first.
143The QEMU virtio setup code configures the KVM driver with an eventfd
144that triggers the device interrupt in the guest when the eventfd is
145written. This irqfd file descriptor is then passed to the vhost user
146application program.
147
148vhost access to guest memory
149''''''''''''''''''''''''''''
150
151The vhost application is also allowed to directly access guest memory,
152instead of needing to send the data as messages to QEMU. This is also
153done with file descriptors sent to the vhost user application by QEMU.
154These descriptors can be passed to ``mmap()`` by the vhost application
155to map the guest address space into the vhost application.
156
157IOMMUs introduce another level of complexity, since the address given to
158the guest virtio device to DMA to or from is not a guest physical
159address. This case is handled by having vhost code within QEMU register
160as a listener for IOMMU mapping changes. The vhost application maintains
161a cache of IOMMMU translations: sending translation requests back to
162QEMU on cache misses, and in turn receiving flush requests from QEMU
163when mappings are purged.
164
165applicability to device separation
166''''''''''''''''''''''''''''''''''
167
168Much of the vhost model can be re-used by separated device emulation. In
169particular, the ideas of using a socket between QEMU and the device
170emulation application, using a file descriptor to inject interrupts into
171the VM via KVM, and allowing the application to ``mmap()`` the guest
172should be re used.
173
174There are, however, some notable differences between how a vhost
175application works and the needs of separated device emulation. The most
176basic is that vhost uses custom virtio device drivers which always
177trigger IO with MMIO stores. A separated device emulation model must
178work with existing IO device models and guest device drivers. MMIO loads
179break vhost store acceleration since they are synchronous - guest
180progress cannot continue until the load has been emulated. By contrast,
181stores are asynchronous, the guest can continue after the store event
182has been sent to the vhost application.
183
184Another difference is that in the vhost user model, a single daemon can
185support multiple QEMU instances. This is contrary to the security regime
186desired, in which the emulation application should only be allowed to
187access the files or devices the VM it's running on behalf of can access.
188#### qemu-io model
189
190``qemu-io`` is a test harness used to test changes to the QEMU block backend
191object code (e.g., the code that implements disk images for disk driver
192emulation). ``qemu-io`` is not a device emulation application per se, but it
193does compile the QEMU block objects into a separate binary from the main
194QEMU one. This could be useful for disk device emulation, since its
195emulation applications will need to include the QEMU block objects.
196
197New separation model based on proxy objects
198-------------------------------------------
199
200A different model based on proxy objects in the QEMU program
201communicating with remote emulation programs could provide separation
202while minimizing the changes needed to the device emulation code. The
203rest of this section is a discussion of how a proxy object model would
204work.
205
206Remote emulation processes
207~~~~~~~~~~~~~~~~~~~~~~~~~~
208
209The remote emulation process will run the QEMU object hierarchy without
210modification. The device emulation objects will be also be based on the
211QEMU code, because for anything but the simplest device, it would not be
212a tractable to re-implement both the object model and the many device
213backends that QEMU has.
214
215The processes will communicate with the QEMU process over UNIX domain
216sockets. The processes can be executed either as standalone processes,
217or be executed by QEMU. In both cases, the host backends the emulation
218processes will provide are specified on its command line, as they would
219be for QEMU. For example:
220
221::
222
223    disk-proc -blockdev driver=file,node-name=file0,filename=disk-file0  \
224    -blockdev driver=qcow2,node-name=drive0,file=file0
225
226would indicate process *disk-proc* uses a qcow2 emulated disk named
227*file0* as its backend.
228
229Emulation processes may emulate more than one guest controller. A common
230configuration might be to put all controllers of the same device class
231(e.g., disk, network, etc.) in a single process, so that all backends of
232the same type can be managed by a single QMP monitor.
233
234communication with QEMU
235^^^^^^^^^^^^^^^^^^^^^^^
236
237The first argument to the remote emulation process will be a Unix domain
238socket that connects with the Proxy object. This is a required argument.
239
240::
241
242    disk-proc <socket number> <backend list>
243
244remote process QMP monitor
245^^^^^^^^^^^^^^^^^^^^^^^^^^
246
247Remote emulation processes can be monitored via QMP, similar to QEMU
248itself. The QMP monitor socket is specified the same as for a QEMU
249process:
250
251::
252
253    disk-proc -qmp unix:/tmp/disk-mon,server
254
255can be monitored over the UNIX socket path */tmp/disk-mon*.
256
257QEMU command line
258~~~~~~~~~~~~~~~~~
259
260Each remote device emulated in a remote process on the host is
261represented as a *-device* of type *pci-proxy-dev*. A socket
262sub-option to this option specifies the Unix socket that connects
263to the remote process. An *id* sub-option is required, and it should
264be the same id as used in the remote process.
265
266::
267
268    qemu-system-x86_64 ... -device pci-proxy-dev,id=lsi0,socket=3
269
270can be used to add a device emulated in a remote process
271
272
273QEMU management of remote processes
274~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
275
276QEMU is not aware of the type of type of the remote PCI device. It is
277a pass through device as far as QEMU is concerned.
278
279communication with emulation process
280^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
281
282primary channel
283'''''''''''''''
284
285The primary channel (referred to as com in the code) is used to bootstrap
286the remote process. It is also used to pass on device-agnostic commands
287like reset.
288
289per-device channels
290'''''''''''''''''''
291
292Each remote device communicates with QEMU using a dedicated communication
293channel. The proxy object sets up this channel using the primary
294channel during its initialization.
295
296QEMU device proxy objects
297~~~~~~~~~~~~~~~~~~~~~~~~~
298
299QEMU has an object model based on sub-classes inherited from the
300"object" super-class. The sub-classes that are of interest here are the
301"device" and "bus" sub-classes whose child sub-classes make up the
302device tree of a QEMU emulated system.
303
304The proxy object model will use device proxy objects to replace the
305device emulation code within the QEMU process. These objects will live
306in the same place in the object and bus hierarchies as the objects they
307replace. i.e., the proxy object for an LSI SCSI controller will be a
308sub-class of the "pci-device" class, and will have the same PCI bus
309parent and the same SCSI bus child objects as the LSI controller object
310it replaces.
311
312It is worth noting that the same proxy object is used to mediate with
313all types of remote PCI devices.
314
315object initialization
316^^^^^^^^^^^^^^^^^^^^^
317
318The Proxy device objects are initialized in the exact same manner in
319which any other QEMU device would be initialized.
320
321In addition, the Proxy objects perform the following two tasks:
322- Parses the "socket" sub option and connects to the remote process
323using this channel
324- Uses the "id" sub-option to connect to the emulated device on the
325separate process
326
327class\_init
328'''''''''''
329
330The ``class_init()`` method of a proxy object will, in general behave
331similarly to the object it replaces, including setting any static
332properties and methods needed by the proxy.
333
334instance\_init / realize
335''''''''''''''''''''''''
336
337The ``instance_init()`` and ``realize()`` functions would only need to
338perform tasks related to being a proxy, such are registering its own
339MMIO handlers, or creating a child bus that other proxy devices can be
340attached to later.
341
342Other tasks will be device-specific. For example, PCI device objects
343will initialize the PCI config space in order to make a valid PCI device
344tree within the QEMU process.
345
346address space registration
347^^^^^^^^^^^^^^^^^^^^^^^^^^
348
349Most devices are driven by guest device driver accesses to IO addresses
350or ports. The QEMU device emulation code uses QEMU's memory region
351function calls (such as ``memory_region_init_io()``) to add callback
352functions that QEMU will invoke when the guest accesses the device's
353areas of the IO address space. When a guest driver does access the
354device, the VM will exit HW virtualization mode and return to QEMU,
355which will then lookup and execute the corresponding callback function.
356
357A proxy object would need to mirror the memory region calls the actual
358device emulator would perform in its initialization code, but with its
359own callbacks. When invoked by QEMU as a result of a guest IO operation,
360they will forward the operation to the device emulation process.
361
362PCI config space
363^^^^^^^^^^^^^^^^
364
365PCI devices also have a configuration space that can be accessed by the
366guest driver. Guest accesses to this space is not handled by the device
367emulation object, but by its PCI parent object. Much of this space is
368read-only, but certain registers (especially BAR and MSI-related ones)
369need to be propagated to the emulation process.
370
371PCI parent proxy
372''''''''''''''''
373
374One way to propagate guest PCI config accesses is to create a
375"pci-device-proxy" class that can serve as the parent of a PCI device
376proxy object. This class's parent would be "pci-device" and it would
377override the PCI parent's ``config_read()`` and ``config_write()``
378methods with ones that forward these operations to the emulation
379program.
380
381interrupt receipt
382^^^^^^^^^^^^^^^^^
383
384A proxy for a device that generates interrupts will need to create a
385socket to receive interrupt indications from the emulation process. An
386incoming interrupt indication would then be sent up to its bus parent to
387be injected into the guest. For example, a PCI device object may use
388``pci_set_irq()``.
389
390live migration
391^^^^^^^^^^^^^^
392
393The proxy will register to save and restore any *vmstate* it needs over
394a live migration event. The device proxy does not need to manage the
395remote device's *vmstate*; that will be handled by the remote process
396proxy (see below).
397
398QEMU remote device operation
399~~~~~~~~~~~~~~~~~~~~~~~~~~~~
400
401Generic device operations, such as DMA, will be performed by the remote
402process proxy by sending messages to the remote process.
403
404DMA operations
405^^^^^^^^^^^^^^
406
407DMA operations would be handled much like vhost applications do. One of
408the initial messages sent to the emulation process is a guest memory
409table. Each entry in this table consists of a file descriptor and size
410that the emulation process can ``mmap()`` to directly access guest
411memory, similar to ``vhost_user_set_mem_table()``. Note guest memory
412must be backed by shared file-backed memory, for example, using
413*-object memory-backend-file,share=on* and setting that memory backend
414as RAM for the machine.
415
416IOMMU operations
417^^^^^^^^^^^^^^^^
418
419When the emulated system includes an IOMMU, the remote process proxy in
420QEMU will need to create a socket for IOMMU requests from the emulation
421process. It will handle those requests with an
422``address_space_get_iotlb_entry()`` call. In order to handle IOMMU
423unmaps, the remote process proxy will also register as a listener on the
424device's DMA address space. When an IOMMU memory region is created
425within the DMA address space, an IOMMU notifier for unmaps will be added
426to the memory region that will forward unmaps to the emulation process
427over the IOMMU socket.
428
429device hot-plug via QMP
430^^^^^^^^^^^^^^^^^^^^^^^
431
432An QMP "device\_add" command can add a device emulated by a remote
433process. It will also have "rid" option to the command, just as the
434*-device* command line option does. The remote process may either be one
435started at QEMU startup, or be one added by the "add-process" QMP
436command described above. In either case, the remote process proxy will
437forward the new device's JSON description to the corresponding emulation
438process.
439
440live migration
441^^^^^^^^^^^^^^
442
443The remote process proxy will also register for live migration
444notifications with ``vmstate_register()``. When called to save state,
445the proxy will send the remote process a secondary socket file
446descriptor to save the remote process's device *vmstate* over. The
447incoming byte stream length and data will be saved as the proxy's
448*vmstate*. When the proxy is resumed on its new host, this *vmstate*
449will be extracted, and a secondary socket file descriptor will be sent
450to the new remote process through which it receives the *vmstate* in
451order to restore the devices there.
452
453device emulation in remote process
454~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
455
456The parts of QEMU that the emulation program will need include the
457object model; the memory emulation objects; the device emulation objects
458of the targeted device, and any dependent devices; and, the device's
459backends. It will also need code to setup the machine environment,
460handle requests from the QEMU process, and route machine-level requests
461(such as interrupts or IOMMU mappings) back to the QEMU process.
462
463initialization
464^^^^^^^^^^^^^^
465
466The process initialization sequence will follow the same sequence
467followed by QEMU. It will first initialize the backend objects, then
468device emulation objects. The JSON descriptions sent by the QEMU process
469will drive which objects need to be created.
470
471-  address spaces
472
473Before the device objects are created, the initial address spaces and
474memory regions must be configured with ``memory_map_init()``. This
475creates a RAM memory region object (*system\_memory*) and an IO memory
476region object (*system\_io*).
477
478-  RAM
479
480RAM memory region creation will follow how ``pc_memory_init()`` creates
481them, but must use ``memory_region_init_ram_from_fd()`` instead of
482``memory_region_allocate_system_memory()``. The file descriptors needed
483will be supplied by the guest memory table from above. Those RAM regions
484would then be added to the *system\_memory* memory region with
485``memory_region_add_subregion()``.
486
487-  PCI
488
489IO initialization will be driven by the JSON descriptions sent from the
490QEMU process. For a PCI device, a PCI bus will need to be created with
491``pci_root_bus_new()``, and a PCI memory region will need to be created
492and added to the *system\_memory* memory region with
493``memory_region_add_subregion_overlap()``. The overlap version is
494required for architectures where PCI memory overlaps with RAM memory.
495
496MMIO handling
497^^^^^^^^^^^^^
498
499The device emulation objects will use ``memory_region_init_io()`` to
500install their MMIO handlers, and ``pci_register_bar()`` to associate
501those handlers with a PCI BAR, as they do within QEMU currently.
502
503In order to use ``address_space_rw()`` in the emulation process to
504handle MMIO requests from QEMU, the PCI physical addresses must be the
505same in the QEMU process and the device emulation process. In order to
506accomplish that, guest BAR programming must also be forwarded from QEMU
507to the emulation process.
508
509interrupt injection
510^^^^^^^^^^^^^^^^^^^
511
512When device emulation wants to inject an interrupt into the VM, the
513request climbs the device's bus object hierarchy until the point where a
514bus object knows how to signal the interrupt to the guest. The details
515depend on the type of interrupt being raised.
516
517-  PCI pin interrupts
518
519On x86 systems, there is an emulated IOAPIC object attached to the root
520PCI bus object, and the root PCI object forwards interrupt requests to
521it. The IOAPIC object, in turn, calls the KVM driver to inject the
522corresponding interrupt into the VM. The simplest way to handle this in
523an emulation process would be to setup the root PCI bus driver (via
524``pci_bus_irqs()``) to send a interrupt request back to the QEMU
525process, and have the device proxy object reflect it up the PCI tree
526there.
527
528-  PCI MSI/X interrupts
529
530PCI MSI/X interrupts are implemented in HW as DMA writes to a
531CPU-specific PCI address. In QEMU on x86, a KVM APIC object receives
532these DMA writes, then calls into the KVM driver to inject the interrupt
533into the VM. A simple emulation process implementation would be to send
534the MSI DMA address from QEMU as a message at initialization, then
535install an address space handler at that address which forwards the MSI
536message back to QEMU.
537
538DMA operations
539^^^^^^^^^^^^^^
540
541When a emulation object wants to DMA into or out of guest memory, it
542first must use dma\_memory\_map() to convert the DMA address to a local
543virtual address. The emulation process memory region objects setup above
544will be used to translate the DMA address to a local virtual address the
545device emulation code can access.
546
547IOMMU
548^^^^^
549
550When an IOMMU is in use in QEMU, DMA translation uses IOMMU memory
551regions to translate the DMA address to a guest physical address before
552that physical address can be translated to a local virtual address. The
553emulation process will need similar functionality.
554
555-  IOTLB cache
556
557The emulation process will maintain a cache of recent IOMMU translations
558(the IOTLB). When the translate() callback of an IOMMU memory region is
559invoked, the IOTLB cache will be searched for an entry that will map the
560DMA address to a guest PA. On a cache miss, a message will be sent back
561to QEMU requesting the corresponding translation entry, which be both be
562used to return a guest address and be added to the cache.
563
564-  IOTLB purge
565
566The IOMMU emulation will also need to act on unmap requests from QEMU.
567These happen when the guest IOMMU driver purges an entry from the
568guest's translation table.
569
570live migration
571^^^^^^^^^^^^^^
572
573When a remote process receives a live migration indication from QEMU, it
574will set up a channel using the received file descriptor with
575``qio_channel_socket_new_fd()``. This channel will be used to create a
576*QEMUfile* that can be passed to ``qemu_save_device_state()`` to send
577the process's device state back to QEMU. This method will be reversed on
578restore - the channel will be passed to ``qemu_loadvm_state()`` to
579restore the device state.
580
581Accelerating device emulation
582~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
583
584The messages that are required to be sent between QEMU and the emulation
585process can add considerable latency to IO operations. The optimizations
586described below attempt to ameliorate this effect by allowing the
587emulation process to communicate directly with the kernel KVM driver.
588The KVM file descriptors created would be passed to the emulation process
589via initialization messages, much like the guest memory table is done.
590#### MMIO acceleration
591
592Vhost user applications can receive guest virtio driver stores directly
593from KVM. The issue with the eventfd mechanism used by vhost user is
594that it does not pass any data with the event indication, so it cannot
595handle guest loads or guest stores that carry store data. This concept
596could, however, be expanded to cover more cases.
597
598The expanded idea would require a new type of KVM device:
599*KVM\_DEV\_TYPE\_USER*. This device has two file descriptors: a master
600descriptor that QEMU can use for configuration, and a slave descriptor
601that the emulation process can use to receive MMIO notifications. QEMU
602would create both descriptors using the KVM driver, and pass the slave
603descriptor to the emulation process via an initialization message.
604
605data structures
606^^^^^^^^^^^^^^^
607
608-  guest physical range
609
610The guest physical range structure describes the address range that a
611device will respond to. It includes the base and length of the range, as
612well as which bus the range resides on (e.g., on an x86machine, it can
613specify whether the range refers to memory or IO addresses).
614
615A device can have multiple physical address ranges it responds to (e.g.,
616a PCI device can have multiple BARs), so the structure will also include
617an enumerated identifier to specify which of the device's ranges is
618being referred to.
619
620+--------+----------------------------+
621| Name   | Description                |
622+========+============================+
623| addr   | range base address         |
624+--------+----------------------------+
625| len    | range length               |
626+--------+----------------------------+
627| bus    | addr type (memory or IO)   |
628+--------+----------------------------+
629| id     | range ID (e.g., PCI BAR)   |
630+--------+----------------------------+
631
632-  MMIO request structure
633
634This structure describes an MMIO operation. It includes which guest
635physical range the MMIO was within, the offset within that range, the
636MMIO type (e.g., load or store), and its length and data. It also
637includes a sequence number that can be used to reply to the MMIO, and
638the CPU that issued the MMIO.
639
640+----------+------------------------+
641| Name     | Description            |
642+==========+========================+
643| rid      | range MMIO is within   |
644+----------+------------------------+
645| offset   | offset within *rid*    |
646+----------+------------------------+
647| type     | e.g., load or store    |
648+----------+------------------------+
649| len      | MMIO length            |
650+----------+------------------------+
651| data     | store data             |
652+----------+------------------------+
653| seq      | sequence ID            |
654+----------+------------------------+
655
656-  MMIO request queues
657
658MMIO request queues are FIFO arrays of MMIO request structures. There
659are two queues: pending queue is for MMIOs that haven't been read by the
660emulation program, and the sent queue is for MMIOs that haven't been
661acknowledged. The main use of the second queue is to validate MMIO
662replies from the emulation program.
663
664-  scoreboard
665
666Each CPU in the VM is emulated in QEMU by a separate thread, so multiple
667MMIOs may be waiting to be consumed by an emulation program and multiple
668threads may be waiting for MMIO replies. The scoreboard would contain a
669wait queue and sequence number for the per-CPU threads, allowing them to
670be individually woken when the MMIO reply is received from the emulation
671program. It also tracks the number of posted MMIO stores to the device
672that haven't been replied to, in order to satisfy the PCI constraint
673that a load to a device will not complete until all previous stores to
674that device have been completed.
675
676-  device shadow memory
677
678Some MMIO loads do not have device side-effects. These MMIOs can be
679completed without sending a MMIO request to the emulation program if the
680emulation program shares a shadow image of the device's memory image
681with the KVM driver.
682
683The emulation program will ask the KVM driver to allocate memory for the
684shadow image, and will then use ``mmap()`` to directly access it. The
685emulation program can control KVM access to the shadow image by sending
686KVM an access map telling it which areas of the image have no
687side-effects (and can be completed immediately), and which require a
688MMIO request to the emulation program. The access map can also inform
689the KVM drive which size accesses are allowed to the image.
690
691master descriptor
692^^^^^^^^^^^^^^^^^
693
694The master descriptor is used by QEMU to configure the new KVM device.
695The descriptor would be returned by the KVM driver when QEMU issues a
696*KVM\_CREATE\_DEVICE* ``ioctl()`` with a *KVM\_DEV\_TYPE\_USER* type.
697
698KVM\_DEV\_TYPE\_USER device ops
699
700
701The *KVM\_DEV\_TYPE\_USER* operations vector will be registered by a
702``kvm_register_device_ops()`` call when the KVM system in initialized by
703``kvm_init()``. These device ops are called by the KVM driver when QEMU
704executes certain ``ioctl()`` operations on its KVM file descriptor. They
705include:
706
707-  create
708
709This routine is called when QEMU issues a *KVM\_CREATE\_DEVICE*
710``ioctl()`` on its per-VM file descriptor. It will allocate and
711initialize a KVM user device specific data structure, and assign the
712*kvm\_device* private field to it.
713
714-  ioctl
715
716This routine is invoked when QEMU issues an ``ioctl()`` on the master
717descriptor. The ``ioctl()`` commands supported are defined by the KVM
718device type. *KVM\_DEV\_TYPE\_USER* ones will need several commands:
719
720*KVM\_DEV\_USER\_SLAVE\_FD* creates the slave file descriptor that will
721be passed to the device emulation program. Only one slave can be created
722by each master descriptor. The file operations performed by this
723descriptor are described below.
724
725The *KVM\_DEV\_USER\_PA\_RANGE* command configures a guest physical
726address range that the slave descriptor will receive MMIO notifications
727for. The range is specified by a guest physical range structure
728argument. For buses that assign addresses to devices dynamically, this
729command can be executed while the guest is running, such as the case
730when a guest changes a device's PCI BAR registers.
731
732*KVM\_DEV\_USER\_PA\_RANGE* will use ``kvm_io_bus_register_dev()`` to
733register *kvm\_io\_device\_ops* callbacks to be invoked when the guest
734performs a MMIO operation within the range. When a range is changed,
735``kvm_io_bus_unregister_dev()`` is used to remove the previous
736instantiation.
737
738*KVM\_DEV\_USER\_TIMEOUT* will configure a timeout value that specifies
739how long KVM will wait for the emulation process to respond to a MMIO
740indication.
741
742-  destroy
743
744This routine is called when the VM instance is destroyed. It will need
745to destroy the slave descriptor; and free any memory allocated by the
746driver, as well as the *kvm\_device* structure itself.
747
748slave descriptor
749^^^^^^^^^^^^^^^^
750
751The slave descriptor will have its own file operations vector, which
752responds to system calls on the descriptor performed by the device
753emulation program.
754
755-  read
756
757A read returns any pending MMIO requests from the KVM driver as MMIO
758request structures. Multiple structures can be returned if there are
759multiple MMIO operations pending. The MMIO requests are moved from the
760pending queue to the sent queue, and if there are threads waiting for
761space in the pending to add new MMIO operations, they will be woken
762here.
763
764-  write
765
766A write also consists of a set of MMIO requests. They are compared to
767the MMIO requests in the sent queue. Matches are removed from the sent
768queue, and any threads waiting for the reply are woken. If a store is
769removed, then the number of posted stores in the per-CPU scoreboard is
770decremented. When the number is zero, and a non side-effect load was
771waiting for posted stores to complete, the load is continued.
772
773-  ioctl
774
775There are several ioctl()s that can be performed on the slave
776descriptor.
777
778A *KVM\_DEV\_USER\_SHADOW\_SIZE* ``ioctl()`` causes the KVM driver to
779allocate memory for the shadow image. This memory can later be
780``mmap()``\ ed by the emulation process to share the emulation's view of
781device memory with the KVM driver.
782
783A *KVM\_DEV\_USER\_SHADOW\_CTRL* ``ioctl()`` controls access to the
784shadow image. It will send the KVM driver a shadow control map, which
785specifies which areas of the image can complete guest loads without
786sending the load request to the emulation program. It will also specify
787the size of load operations that are allowed.
788
789-  poll
790
791An emulation program will use the ``poll()`` call with a *POLLIN* flag
792to determine if there are MMIO requests waiting to be read. It will
793return if the pending MMIO request queue is not empty.
794
795-  mmap
796
797This call allows the emulation program to directly access the shadow
798image allocated by the KVM driver. As device emulation updates device
799memory, changes with no side-effects will be reflected in the shadow,
800and the KVM driver can satisfy guest loads from the shadow image without
801needing to wait for the emulation program.
802
803kvm\_io\_device ops
804^^^^^^^^^^^^^^^^^^^
805
806Each KVM per-CPU thread can handle MMIO operation on behalf of the guest
807VM. KVM will use the MMIO's guest physical address to search for a
808matching *kvm\_io\_device* to see if the MMIO can be handled by the KVM
809driver instead of exiting back to QEMU. If a match is found, the
810corresponding callback will be invoked.
811
812-  read
813
814This callback is invoked when the guest performs a load to the device.
815Loads with side-effects must be handled synchronously, with the KVM
816driver putting the QEMU thread to sleep waiting for the emulation
817process reply before re-starting the guest. Loads that do not have
818side-effects may be optimized by satisfying them from the shadow image,
819if there are no outstanding stores to the device by this CPU. PCI memory
820ordering demands that a load cannot complete before all older stores to
821the same device have been completed.
822
823-  write
824
825Stores can be handled asynchronously unless the pending MMIO request
826queue is full. In this case, the QEMU thread must sleep waiting for
827space in the queue. Stores will increment the number of posted stores in
828the per-CPU scoreboard, in order to implement the PCI ordering
829constraint above.
830
831interrupt acceleration
832^^^^^^^^^^^^^^^^^^^^^^
833
834This performance optimization would work much like a vhost user
835application does, where the QEMU process sets up *eventfds* that cause
836the device's corresponding interrupt to be triggered by the KVM driver.
837These irq file descriptors are sent to the emulation process at
838initialization, and are used when the emulation code raises a device
839interrupt.
840
841intx acceleration
842'''''''''''''''''
843
844Traditional PCI pin interrupts are level based, so, in addition to an
845irq file descriptor, a re-sampling file descriptor needs to be sent to
846the emulation program. This second file descriptor allows multiple
847devices sharing an irq to be notified when the interrupt has been
848acknowledged by the guest, so they can re-trigger the interrupt if their
849device has not de-asserted its interrupt.
850
851intx irq descriptor
852
853
854The irq descriptors are created by the proxy object
855``using event_notifier_init()`` to create the irq and re-sampling
856*eventds*, and ``kvm_vm_ioctl(KVM_IRQFD)`` to bind them to an interrupt.
857The interrupt route can be found with
858``pci_device_route_intx_to_irq()``.
859
860intx routing changes
861
862
863Intx routing can be changed when the guest programs the APIC the device
864pin is connected to. The proxy object in QEMU will use
865``pci_device_set_intx_routing_notifier()`` to be informed of any guest
866changes to the route. This handler will broadly follow the VFIO
867interrupt logic to change the route: de-assigning the existing irq
868descriptor from its route, then assigning it the new route. (see
869``vfio_intx_update()``)
870
871MSI/X acceleration
872''''''''''''''''''
873
874MSI/X interrupts are sent as DMA transactions to the host. The interrupt
875data contains a vector that is programmed by the guest, A device may have
876multiple MSI interrupts associated with it, so multiple irq descriptors
877may need to be sent to the emulation program.
878
879MSI/X irq descriptor
880
881
882This case will also follow the VFIO example. For each MSI/X interrupt,
883an *eventfd* is created, a virtual interrupt is allocated by
884``kvm_irqchip_add_msi_route()``, and the virtual interrupt is bound to
885the eventfd with ``kvm_irqchip_add_irqfd_notifier()``.
886
887MSI/X config space changes
888
889
890The guest may dynamically update several MSI-related tables in the
891device's PCI config space. These include per-MSI interrupt enables and
892vector data. Additionally, MSIX tables exist in device memory space, not
893config space. Much like the BAR case above, the proxy object must look
894at guest config space programming to keep the MSI interrupt state
895consistent between QEMU and the emulation program.
896
897--------------
898
899Disaggregated CPU emulation
900---------------------------
901
902After IO services have been disaggregated, a second phase would be to
903separate a process to handle CPU instruction emulation from the main
904QEMU control function. There are no object separation points for this
905code, so the first task would be to create one.
906
907Host access controls
908--------------------
909
910Separating QEMU relies on the host OS's access restriction mechanisms to
911enforce that the differing processes can only access the objects they
912are entitled to. There are a couple types of mechanisms usually provided
913by general purpose OSs.
914
915Discretionary access control
916~~~~~~~~~~~~~~~~~~~~~~~~~~~~
917
918Discretionary access control allows each user to control who can access
919their files. In Linux, this type of control is usually too coarse for
920QEMU separation, since it only provides three separate access controls:
921one for the same user ID, the second for users IDs with the same group
922ID, and the third for all other user IDs. Each device instance would
923need a separate user ID to provide access control, which is likely to be
924unwieldy for dynamically created VMs.
925
926Mandatory access control
927~~~~~~~~~~~~~~~~~~~~~~~~
928
929Mandatory access control allows the OS to add an additional set of
930controls on top of discretionary access for the OS to control. It also
931adds other attributes to processes and files such as types, roles, and
932categories, and can establish rules for how processes and files can
933interact.
934
935Type enforcement
936^^^^^^^^^^^^^^^^
937
938Type enforcement assigns a *type* attribute to processes and files, and
939allows rules to be written on what operations a process with a given
940type can perform on a file with a given type. QEMU separation could take
941advantage of type enforcement by running the emulation processes with
942different types, both from the main QEMU process, and from the emulation
943processes of different classes of devices.
944
945For example, guest disk images and disk emulation processes could have
946types separate from the main QEMU process and non-disk emulation
947processes, and the type rules could prevent processes other than disk
948emulation ones from accessing guest disk images. Similarly, network
949emulation processes can have a type separate from the main QEMU process
950and non-network emulation process, and only that type can access the
951host tun/tap device used to provide guest networking.
952
953Category enforcement
954^^^^^^^^^^^^^^^^^^^^
955
956Category enforcement assigns a set of numbers within a given range to
957the process or file. The process is granted access to the file if the
958process's set is a superset of the file's set. This enforcement can be
959used to separate multiple instances of devices in the same class.
960
961For example, if there are multiple disk devices provides to a guest,
962each device emulation process could be provisioned with a separate
963category. The different device emulation processes would not be able to
964access each other's backing disk images.
965
966Alternatively, categories could be used in lieu of the type enforcement
967scheme described above. In this scenario, different categories would be
968used to prevent device emulation processes in different classes from
969accessing resources assigned to other classes.
970