1 \input texinfo @c -*- texinfo -*-
3 @settitle QEMU CPU Emulator Reference Documentation
6 @center @titlefont{QEMU CPU Emulator Reference Documentation}
14 QEMU is a FAST! processor emulator. By using dynamic translation it
15 achieves a reasonnable speed while being easy to port on new host
18 QEMU has two operating modes:
20 @item User mode emulation. In this mode, QEMU can launch Linux processes
21 compiled for one CPU on another CPU. Linux system calls are converted
22 because of endianness and 32/64 bit mismatches. The Wine Windows API
23 emulator (@url{http://www.winehq.org}) and the DOSEMU DOS emulator
24 (@url{www.dosemu.org}) are the main targets for QEMU.
26 @item Full system emulation. In this mode, QEMU emulates a full
27 system, including a processor and various peripherials. Currently, it
28 is only used to launch an x86 Linux kernel on an x86 Linux system. It
29 enables easier testing and debugging of system code. It can also be
30 used to provide virtual hosting of several virtual PCs on a single
35 As QEMU requires no host kernel patches to run, it is very safe and
38 QEMU generic features:
42 @item User space only or full system emulation.
44 @item Using dynamic translation to native code for reasonnable speed.
46 @item Working on x86 and PowerPC hosts. Being tested on ARM, Sparc32, Alpha and S390.
48 @item Self-modifying code support.
50 @item Precise exception support.
52 @item The virtual CPU is a library (@code{libqemu}) which can be used
57 QEMU user mode emulation features:
59 @item Generic Linux system call converter, including most ioctls.
61 @item clone() emulation using native CPU clone() to use Linux scheduler for threads.
63 @item Accurate signal handling by remapping host signals to target signals.
67 QEMU full system emulation features:
69 @item Using mmap() system calls to simulate the MMU
72 @section x86 emulation
74 QEMU x86 target features:
78 @item The virtual x86 CPU supports 16 bit and 32 bit addressing with segmentation.
79 LDT/GDT and IDT are emulated. VM86 mode is also supported to run DOSEMU.
81 @item Support of host page sizes bigger than 4KB in user mode emulation.
83 @item QEMU can emulate itself on x86.
85 @item An extensive Linux x86 CPU test program is included @file{tests/test-i386}.
86 It can be used to test other x86 virtual CPUs.
90 Current QEMU limitations:
94 @item No SSE/MMX support (yet).
96 @item No x86-64 support.
98 @item IPC syscalls are missing.
100 @item The x86 segment limits and access rights are not tested at every
103 @item On non x86 host CPUs, @code{double}s are used instead of the non standard
104 10 byte @code{long double}s of x86 for floating point emulation to get
105 maximum performances.
107 @item Full system emulation only works if no data are mapped above the virtual address
110 @item Some priviledged instructions or behaviors are missing. Only the ones
111 needed for proper Linux kernel operation are emulated.
113 @item No memory separation between the kernel and the user processes is done.
114 It will be implemented very soon.
118 @section ARM emulation
122 @item ARM emulation can currently launch small programs while using the
123 generic dynamic code generation architecture of QEMU.
125 @item No FPU support (yet).
127 @item No automatic regression testing (yet).
131 @chapter QEMU User space emulation invocation
135 If you need to compile QEMU, please read the @file{README} which gives
136 the related information.
138 In order to launch a Linux process, QEMU needs the process executable
139 itself and all the target (x86) dynamic libraries used by it.
143 @item On x86, you can just try to launch any process by using the native
150 @code{-L /} tells that the x86 dynamic linker must be searched with a
153 @item Since QEMU is also a linux process, you can launch qemu with qemu:
156 qemu -L / qemu -L / /bin/ls
159 @item On non x86 CPUs, you need first to download at least an x86 glibc
160 (@file{qemu-XXX-i386-glibc21.tar.gz} on the QEMU web page). Ensure that
161 @code{LD_LIBRARY_PATH} is not set:
164 unset LD_LIBRARY_PATH
167 Then you can launch the precompiled @file{ls} x86 executable:
170 qemu /usr/local/qemu-i386/bin/ls-i386
172 You can look at @file{/usr/local/qemu-i386/bin/qemu-conf.sh} so that
173 QEMU is automatically launched by the Linux kernel when you try to
174 launch x86 executables. It requires the @code{binfmt_misc} module in the
177 @item The x86 version of QEMU is also included. You can try weird things such as:
179 qemu /usr/local/qemu-i386/bin/qemu-i386 /usr/local/qemu-i386/bin/ls-i386
188 @item Ensure that you have a working QEMU with the x86 glibc
189 distribution (see previous section). In order to verify it, you must be
193 qemu /usr/local/qemu-i386/bin/ls-i386
196 @item Download the binary x86 Wine install
197 (@file{qemu-XXX-i386-wine.tar.gz} on the QEMU web page).
199 @item Configure Wine on your account. Look at the provided script
200 @file{/usr/local/qemu-i386/bin/wine-conf.sh}. Your previous
201 @code{$@{HOME@}/.wine} directory is saved to @code{$@{HOME@}/.wine.org}.
203 @item Then you can try the example @file{putty.exe}:
206 qemu /usr/local/qemu-i386/wine/bin/wine /usr/local/qemu-i386/wine/c/Program\ Files/putty.exe
211 @section Command line options
214 usage: qemu [-h] [-d] [-L path] [-s size] program [arguments...]
221 Set the x86 elf interpreter prefix (default=/usr/local/qemu-i386)
223 Set the x86 stack size in bytes (default=524288)
230 Activate log (logfile=/tmp/qemu.log)
232 Act as if the host page size was 'pagesize' bytes
235 @chapter QEMU System emulator invocation
239 This section explains how to launch a Linux kernel inside QEMU.
243 Download the archive @file{vl-test-xxx.tar.gz} containing a Linux kernel
244 and an initrd (initial Ram Disk). The archive also contains a
245 precompiled version of @file{vl}, the QEMU System emulator.
247 @item Optional: If you want network support (for example to launch X11 examples), you
248 must copy the script @file{vl-ifup} in @file{/etc} and configure
249 properly @code{sudo} so that the command @code{ifconfig} contained in
250 @file{vl-ifup} can be executed as root. You must verify that your host
251 kernel supports the TUN/TAP network interfaces: the device
252 @file{/dev/net/tun} must be present.
254 When network is enabled, there is a virtual network connection between
255 the host kernel and the emulated kernel. The emulated kernel is seen
256 from the host kernel at IP address 172.20.0.2 and the host kernel is
257 seen from the emulated kernel at IP address 172.20.0.1.
259 @item Launch @code{vl.sh}. You should have the following output:
263 connected to host network interface: tun0
264 Uncompressing Linux... Ok, booting the kernel.
265 Linux version 2.4.20 (bellard@voyager) (gcc version 2.95.2 20000220 (Debian GNU/Linux)) #42 Wed Jun 25 14:16:12 CEST 2003
266 BIOS-provided physical RAM map:
267 BIOS-88: 0000000000000000 - 000000000009f000 (usable)
268 BIOS-88: 0000000000100000 - 0000000002000000 (usable)
269 32MB LOWMEM available.
270 On node 0 totalpages: 8192
274 Kernel command line: root=/dev/ram ramdisk_size=6144
276 Detected 501.785 MHz processor.
277 Calibrating delay loop... 973.20 BogoMIPS
278 Memory: 24776k/32768k available (725k kernel code, 7604k reserved, 151k data, 48k init, 0k highmem)
279 Dentry cache hash table entries: 4096 (order: 3, 32768 bytes)
280 Inode cache hash table entries: 2048 (order: 2, 16384 bytes)
281 Mount-cache hash table entries: 512 (order: 0, 4096 bytes)
282 Buffer-cache hash table entries: 1024 (order: 0, 4096 bytes)
283 Page-cache hash table entries: 8192 (order: 3, 32768 bytes)
284 CPU: Intel Pentium Pro stepping 03
285 Checking 'hlt' instruction... OK.
286 POSIX conformance testing by UNIFIX
287 Linux NET4.0 for Linux 2.4
288 Based upon Swansea University Computer Society NET3.039
289 Initializing RT netlink socket
292 pty: 256 Unix98 ptys configured
293 Serial driver version 5.05c (2001-07-08) with no serial options enabled
294 ttyS00 at 0x03f8 (irq = 4) is a 16450
295 ne.c:v1.10 9/23/94 Donald Becker (becker@scyld.com)
296 Last modified Nov 1, 2000 by Paul Gortmaker
297 NE*000 ethercard probe at 0x300: 52 54 00 12 34 56
298 eth0: NE2000 found at 0x300, using IRQ 9.
299 RAMDISK driver initialized: 16 RAM disks of 6144K size 1024 blocksize
300 NET4: Linux TCP/IP 1.0 for NET4.0
301 IP Protocols: ICMP, UDP, TCP, IGMP
302 IP: routing cache hash table of 512 buckets, 4Kbytes
303 TCP: Hash tables configured (established 2048 bind 2048)
304 NET4: Unix domain sockets 1.0/SMP for Linux NET4.0.
305 RAMDISK: ext2 filesystem found at block 0
306 RAMDISK: Loading 6144 blocks [1 disk] into ram disk... done.
307 Freeing initrd memory: 6144k freed
308 VFS: Mounted root (ext2 filesystem).
309 Freeing unused kernel memory: 48k freed
310 sh: can't access tty; job control turned off
315 Then you can play with the kernel inside the virtual serial console. You
316 can launch @code{ls} for example. Type @key{Ctrl-a h} to have an help
317 about the keys you can type inside the virtual serial console. In
318 particular @key{Ctrl-a b} is the Magic SysRq key.
321 If the network is enabled, launch the script @file{/etc/linuxrc} in the
322 emulator (don't forget the leading dot):
327 Then enable X11 connections on your PC from the emulated Linux:
332 You can now launch @file{xterm} or @file{xlogo} and verify that you have
333 a real Virtual Linux system !
337 NOTE: the example initrd is a modified version of the one made by Kevin
338 Lawton for the plex86 Project (@url{www.plex86.org}).
340 @section Kernel Compilation
342 You can use any Linux kernel within QEMU provided it is mapped at
343 address 0x90000000 (the default is 0xc0000000). You must modify only two
344 lines in the kernel source:
346 In asm/page.h, replace
348 #define __PAGE_OFFSET (0xc0000000)
352 #define __PAGE_OFFSET (0x90000000)
355 And in arch/i386/vmlinux.lds, replace
357 . = 0xc0000000 + 0x100000;
361 . = 0x90000000 + 0x100000;
364 The file config-2.4.20 gives the configuration of the example kernel.
371 As you would do to make a real kernel. Then you can use with QEMU
372 exactly the same kernel as you would boot on your PC (in
373 @file{arch/i386/boot/bzImage}).
375 @section PC Emulation
377 QEMU emulates the following PC peripherials:
381 PIC (interrupt controler)
387 Serial port (port=0x3f8, irq=4)
389 NE2000 network adapter (port=0x300, irq=9)
391 Dumb VGA (to print the @code{uncompressing Linux kernel} message)
394 @chapter QEMU Internals
396 @section QEMU compared to other emulators
398 Like bochs [3], QEMU emulates an x86 CPU. But QEMU is much faster than
399 bochs as it uses dynamic compilation and because it uses the host MMU to
400 simulate the x86 MMU. The downside is that currently the emulation is
401 not as accurate as bochs (for example, you cannot currently run Windows
404 Like Valgrind [2], QEMU does user space emulation and dynamic
405 translation. Valgrind is mainly a memory debugger while QEMU has no
406 support for it (QEMU could be used to detect out of bound memory
407 accesses as Valgrind, but it has no support to track uninitialised data
408 as Valgrind does). Valgrind dynamic translator generates better code
409 than QEMU (in particular it does register allocation) but it is closely
410 tied to an x86 host and target and has no support for precise exception
411 and system emulation.
413 EM86 [4] is the closest project to user space QEMU (and QEMU still uses
414 some of its code, in particular the ELF file loader). EM86 was limited
415 to an alpha host and used a proprietary and slow interpreter (the
416 interpreter part of the FX!32 Digital Win32 code translator [5]).
418 TWIN [6] is a Windows API emulator like Wine. It is less accurate than
419 Wine but includes a protected mode x86 interpreter to launch x86 Windows
420 executables. Such an approach as greater potential because most of the
421 Windows API is executed natively but it is far more difficult to develop
422 because all the data structures and function parameters exchanged
423 between the API and the x86 code must be converted.
425 User mode Linux [7] was the only solution before QEMU to launch a Linux
426 kernel as a process while not needing any host kernel patches. However,
427 user mode Linux requires heavy kernel patches while QEMU accepts
428 unpatched Linux kernels. It would be interesting to compare the
429 performance of the two approaches.
431 The new Plex86 [8] PC virtualizer is done in the same spirit as the QEMU
432 system emulator. It requires a patched Linux kernel to work (you cannot
433 launch the same kernel on your PC), but the patches are really small. As
434 it is a PC virtualizer (no emulation is done except for some priveledged
435 instructions), it has the potential of being faster than QEMU. The
436 downside is that a complicated (and potentially unsafe) kernel patch is
439 @section Portable dynamic translation
441 QEMU is a dynamic translator. When it first encounters a piece of code,
442 it converts it to the host instruction set. Usually dynamic translators
443 are very complicated and highly CPU dependent. QEMU uses some tricks
444 which make it relatively easily portable and simple while achieving good
447 The basic idea is to split every x86 instruction into fewer simpler
448 instructions. Each simple instruction is implemented by a piece of C
449 code (see @file{op-i386.c}). Then a compile time tool (@file{dyngen})
450 takes the corresponding object file (@file{op-i386.o}) to generate a
451 dynamic code generator which concatenates the simple instructions to
452 build a function (see @file{op-i386.h:dyngen_code()}).
454 In essence, the process is similar to [1], but more work is done at
457 A key idea to get optimal performances is that constant parameters can
458 be passed to the simple operations. For that purpose, dummy ELF
459 relocations are generated with gcc for each constant parameter. Then,
460 the tool (@file{dyngen}) can locate the relocations and generate the
461 appriopriate C code to resolve them when building the dynamic code.
463 That way, QEMU is no more difficult to port than a dynamic linker.
465 To go even faster, GCC static register variables are used to keep the
466 state of the virtual CPU.
468 @section Register allocation
470 Since QEMU uses fixed simple instructions, no efficient register
471 allocation can be done. However, because RISC CPUs have a lot of
472 register, most of the virtual CPU state can be put in registers without
473 doing complicated register allocation.
475 @section Condition code optimisations
477 Good CPU condition codes emulation (@code{EFLAGS} register on x86) is a
478 critical point to get good performances. QEMU uses lazy condition code
479 evaluation: instead of computing the condition codes after each x86
480 instruction, it just stores one operand (called @code{CC_SRC}), the
481 result (called @code{CC_DST}) and the type of operation (called
484 @code{CC_OP} is almost never explicitely set in the generated code
485 because it is known at translation time.
487 In order to increase performances, a backward pass is performed on the
488 generated simple instructions (see
489 @code{translate-i386.c:optimize_flags()}). When it can be proved that
490 the condition codes are not needed by the next instructions, no
491 condition codes are computed at all.
493 @section CPU state optimisations
495 The x86 CPU has many internal states which change the way it evaluates
496 instructions. In order to achieve a good speed, the translation phase
497 considers that some state information of the virtual x86 CPU cannot
498 change in it. For example, if the SS, DS and ES segments have a zero
499 base, then the translator does not even generate an addition for the
502 [The FPU stack pointer register is not handled that way yet].
504 @section Translation cache
506 A 2MByte cache holds the most recently used translations. For
507 simplicity, it is completely flushed when it is full. A translation unit
508 contains just a single basic block (a block of x86 instructions
509 terminated by a jump or by a virtual CPU state change which the
510 translator cannot deduce statically).
512 @section Direct block chaining
514 After each translated basic block is executed, QEMU uses the simulated
515 Program Counter (PC) and other cpu state informations (such as the CS
516 segment base value) to find the next basic block.
518 In order to accelerate the most common cases where the new simulated PC
519 is known, QEMU can patch a basic block so that it jumps directly to the
522 The most portable code uses an indirect jump. An indirect jump makes it
523 easier to make the jump target modification atomic. On some
524 architectures (such as PowerPC), the @code{JUMP} opcode is directly
525 patched so that the block chaining has no overhead.
527 @section Self-modifying code and translated code invalidation
529 Self-modifying code is a special challenge in x86 emulation because no
530 instruction cache invalidation is signaled by the application when code
533 When translated code is generated for a basic block, the corresponding
534 host page is write protected if it is not already read-only (with the
535 system call @code{mprotect()}). Then, if a write access is done to the
536 page, Linux raises a SEGV signal. QEMU then invalidates all the
537 translated code in the page and enables write accesses to the page.
539 Correct translated code invalidation is done efficiently by maintaining
540 a linked list of every translated block contained in a given page. Other
541 linked lists are also maintained to undo direct block chaining.
543 Althought the overhead of doing @code{mprotect()} calls is important,
544 most MSDOS programs can be emulated at reasonnable speed with QEMU and
547 Note that QEMU also invalidates pages of translated code when it detects
548 that memory mappings are modified with @code{mmap()} or @code{munmap()}.
550 @section Exception support
552 longjmp() is used when an exception such as division by zero is
555 The host SIGSEGV and SIGBUS signal handlers are used to get invalid
556 memory accesses. The exact CPU state can be retrieved because all the
557 x86 registers are stored in fixed host registers. The simulated program
558 counter is found by retranslating the corresponding basic block and by
559 looking where the host program counter was at the exception point.
561 The virtual CPU cannot retrieve the exact @code{EFLAGS} register because
562 in some cases it is not computed because of condition code
563 optimisations. It is not a big concern because the emulated code can
564 still be restarted in any cases.
566 @section Linux system call translation
568 QEMU includes a generic system call translator for Linux. It means that
569 the parameters of the system calls can be converted to fix the
570 endianness and 32/64 bit issues. The IOCTLs are converted with a generic
571 type description system (see @file{ioctls.h} and @file{thunk.c}).
573 QEMU supports host CPUs which have pages bigger than 4KB. It records all
574 the mappings the process does and try to emulated the @code{mmap()}
575 system calls in cases where the host @code{mmap()} call would fail
576 because of bad page alignment.
578 @section Linux signals
580 Normal and real-time signals are queued along with their information
581 (@code{siginfo_t}) as it is done in the Linux kernel. Then an interrupt
582 request is done to the virtual CPU. When it is interrupted, one queued
583 signal is handled by generating a stack frame in the virtual CPU as the
584 Linux kernel does. The @code{sigreturn()} system call is emulated to return
585 from the virtual signal handler.
587 Some signals (such as SIGALRM) directly come from the host. Other
588 signals are synthetized from the virtual CPU exceptions such as SIGFPE
589 when a division by zero is done (see @code{main.c:cpu_loop()}).
591 The blocked signal mask is still handled by the host Linux kernel so
592 that most signal system calls can be redirected directly to the host
593 Linux kernel. Only the @code{sigaction()} and @code{sigreturn()} system
594 calls need to be fully emulated (see @file{signal.c}).
596 @section clone() system call and threads
598 The Linux clone() system call is usually used to create a thread. QEMU
599 uses the host clone() system call so that real host threads are created
600 for each emulated thread. One virtual CPU instance is created for each
603 The virtual x86 CPU atomic operations are emulated with a global lock so
604 that their semantic is preserved.
606 Note that currently there are still some locking issues in QEMU. In
607 particular, the translated cache flush is not protected yet against
610 @section Self-virtualization
612 QEMU was conceived so that ultimately it can emulate itself. Althought
613 it is not very useful, it is an important test to show the power of the
616 Achieving self-virtualization is not easy because there may be address
617 space conflicts. QEMU solves this problem by being an executable ELF
618 shared object as the ld-linux.so ELF interpreter. That way, it can be
619 relocated at load time.
621 @section MMU emulation
623 For system emulation, QEMU uses the mmap() system call to emulate the
624 target CPU MMU. It works as long the emulated OS does not use an area
625 reserved by the host OS (such as the area above 0xc0000000 on x86
628 It is planned to add a slower but more precise MMU emulation
631 @section Bibliography
636 @url{http://citeseer.nj.nec.com/piumarta98optimizing.html}, Optimizing
637 direct threaded code by selective inlining (1998) by Ian Piumarta, Fabio
641 @url{http://developer.kde.org/~sewardj/}, Valgrind, an open-source
642 memory debugger for x86-GNU/Linux, by Julian Seward.
645 @url{http://bochs.sourceforge.net/}, the Bochs IA-32 Emulator Project,
646 by Kevin Lawton et al.
649 @url{http://www.cs.rose-hulman.edu/~donaldlf/em86/index.html}, the EM86
650 x86 emulator on Alpha-Linux.
653 @url{http://www.usenix.org/publications/library/proceedings/usenix-nt97/full_papers/chernoff/chernoff.pdf},
654 DIGITAL FX!32: Running 32-Bit x86 Applications on Alpha NT, by Anton
655 Chernoff and Ray Hookway.
658 @url{http://www.willows.com/}, Windows API library emulation from
662 @url{http://user-mode-linux.sourceforge.net/},
663 The User-mode Linux Kernel.
666 @url{http://www.plex86.org/},
667 The new Plex86 project.
671 @chapter Regression Tests
673 In the directory @file{tests/}, various interesting testing programs
674 are available. There are used for regression testing.
676 @section @file{hello-i386}
678 Very simple statically linked x86 program, just to test QEMU during a
679 port to a new host CPU.
681 @section @file{hello-arm}
683 Very simple statically linked ARM program, just to test QEMU during a
684 port to a new host CPU.
686 @section @file{test-i386}
688 This program executes most of the 16 bit and 32 bit x86 instructions and
689 generates a text output. It can be compared with the output obtained with
690 a real CPU or another emulator. The target @code{make test} runs this
691 program and a @code{diff} on the generated output.
693 The Linux system call @code{modify_ldt()} is used to create x86 selectors
694 to test some 16 bit addressing and 32 bit with segmentation cases.
696 The Linux system call @code{vm86()} is used to test vm86 emulation.
698 Various exceptions are raised to test most of the x86 user space
703 It is a simple benchmark. Care must be taken to interpret the results
704 because it mostly tests the ability of the virtual CPU to optimize the
705 @code{rol} x86 instruction and the condition code computations.