qemu-doc.texi

\input texinfo @c -*- texinfo -*-

@settitle QEMU x86 Emulator Reference Documentation
@titlepage
@sp 7
@center @titlefont{QEMU x86 Emulator Reference Documentation}
@sp 3
@end titlepage

@chapter Introduction

QEMU is an x86 processor emulator. Its purpose is to run x86 Linux
processes on non-x86 Linux architectures such as PowerPC or ARM. By
using dynamic translation it achieves a reasonnable speed while being
easy to port on new host CPUs. An obviously interesting x86 only process
is 'wine' (Windows emulation).

QEMU features:

@itemize 

@item User space only x86 emulator.

@item Currently ported on i386 and PowerPC.

@item Using dynamic translation for reasonnable speed.

@item The virtual x86 CPU supports 16 bit and 32 bit addressing with segmentation. 
User space LDT and GDT are emulated.

@item Generic Linux system call converter, including most ioctls.

@item clone() emulation using native CPU clone() to use Linux scheduler for threads.

@item Accurate signal handling by remapping host signals to virtual x86 signals.

@item The virtual x86 CPU is a library (@code{libqemu}) which can be used 
in other projects.

@item An extensive Linux x86 CPU test program is included @file{tests/test-i386}. 
It can be used to test other x86 virtual CPUs.

@end itemize

Current QEMU Limitations:

@itemize 

@item Not all x86 exceptions are precise (yet). [Very few programs need that].

@item Not self virtualizable (yet). [You cannot launch qemu with qemu on the same CPU].

@item No support for self modifying code (yet). [Very few programs need that, a notable exception is QEMU itself !].

@item No VM86 mode (yet), althought the virtual
CPU has support for most of it. [VM86 support is useful to launch old 16
bit DOS programs with dosemu or wine].

@item No SSE/MMX support (yet).

@item No x86-64 support.

@item Some Linux syscalls are missing.

@item The x86 segment limits and access rights are not tested at every 
memory access (and will never be to have good performances).

@item On non x86 host CPUs, @code{double}s are used instead of the non standard 
10 byte @code{long double}s of x86 for floating point emulation to get
maximum performances.

@end itemize

@chapter Invocation

In order to launch a Linux process, QEMU needs the process executable
itself and all the target (x86) dynamic libraries used by it. Currently,
QEMU is not distributed with the necessary packages so that you can test
it easily on non x86 CPUs.

However, the statically x86 binary 'tests/hello' can be used to do a
first test:

@example 
qemu tests/hello
@end example

@code{Hello world} should be printed on the terminal.

If you are testing it on a x86 CPU, then you can test it on any process:

@example 
qemu /bin/ls -l
@end example

@chapter QEMU Internals

@section QEMU compared to other emulators

Unlike bochs [3], QEMU emulates only a user space x86 CPU. It means that
you cannot launch an operating system with it. The benefit is that it is
simpler and faster due to the fact that some of the low level CPU state
can be ignored (in particular, no virtual memory needs to be emulated).

Like Valgrind [2], QEMU does user space emulation and dynamic
translation. Valgrind is mainly a memory debugger while QEMU has no
support for it (QEMU could be used to detect out of bound memory accesses
as Valgrind, but it has no support to track uninitialised data as
Valgrind does). Valgrind dynamic translator generates better code than
QEMU (in particular it does register allocation) but it is closely tied
to an x86 host.

EM86 [4] is the closest project to QEMU (and QEMU still uses some of its
code, in particular the ELF file loader). EM86 was limited to an alpha
host and used a proprietary and slow interpreter (the interpreter part
of the FX!32 Digital Win32 code translator [5]).

@section Portable dynamic translation

QEMU is a dynamic translator. When it first encounters a piece of code,
it converts it to the host instruction set. Usually dynamic translators
are very complicated and highly CPU dependant. QEMU uses some tricks
which make it relatively easily portable and simple while achieving good
performances.

The basic idea is to split every x86 instruction into fewer simpler
instructions. Each simple instruction is implemented by a piece of C
code (see @file{op-i386.c}). Then a compile time tool (@file{dyngen})
takes the corresponding object file (@file{op-i386.o}) to generate a
dynamic code generator which concatenates the simple instructions to
build a function (see @file{op-i386.h:dyngen_code()}).

In essence, the process is similar to [1], but more work is done at
compile time. 

A key idea to get optimal performances is that constant parameters can
be passed to the simple operations. For that purpose, dummy ELF
relocations are generated with gcc for each constant parameter. Then,
the tool (@file{dyngen}) can locate the relocations and generate the
appriopriate C code to resolve them when building the dynamic code.

That way, QEMU is no more difficult to port than a dynamic linker.

To go even faster, GCC static register variables are used to keep the
state of the virtual CPU.

@section Register allocation

Since QEMU uses fixed simple instructions, no efficient register
allocation can be done. However, because RISC CPUs have a lot of
register, most of the virtual CPU state can be put in registers without
doing complicated register allocation.

@section Condition code optimisations

Good CPU condition codes emulation (@code{EFLAGS} register on x86) is a
critical point to get good performances. QEMU uses lazy condition code
evaluation: instead of computing the condition codes after each x86
instruction, it store justs one operand (called @code{CC_CRC}), the
result (called @code{CC_DST}) and the type of operation (called
@code{CC_OP}).

@code{CC_OP} is almost never explicitely set in the generated code
because it is known at translation time.

In order to increase performances, a backward pass is performed on the
generated simple instructions (see
@code{translate-i386.c:optimize_flags()}). When it can be proved that
the condition codes are not needed by the next instructions, no
condition codes are computed at all.

@section Translation CPU state optimisations

The x86 CPU has many internal states which change the way it evaluates
instructions. In order to achieve a good speed, the translation phase
considers that some state information of the virtual x86 CPU cannot
change in it. For example, if the SS, DS and ES segments have a zero
base, then the translator does not even generate an addition for the
segment base.

[The FPU stack pointer register is not handled that way yet].

@section Translation cache

A 2MByte cache holds the most recently used translations. For
simplicity, it is completely flushed when it is full. A translation unit
contains just a single basic block (a block of x86 instructions
terminated by a jump or by a virtual CPU state change which the
translator cannot deduce statically).

[Currently, the translated code is not patched if it jumps to another
translated code].

@section Exception support

longjmp() is used when an exception such as division by zero is
encountered. The host SIGSEGV and SIGBUS signal handlers are used to get
invalid memory accesses. 

[Currently, the virtual CPU cannot retrieve the exact CPU state in some
exceptions, although it could except for the @code{EFLAGS} register].

@section Linux system call translation

QEMU includes a generic system call translator for Linux. It means that
the parameters of the system calls can be converted to fix the
endianness and 32/64 bit issues. The IOCTLs are converted with a generic
type description system (see @file{ioctls.h} and @file{thunk.c}).

@section Linux signals

Normal and real-time signals are queued along with their information
(@code{siginfo_t}) as it is done in the Linux kernel. Then an interrupt
request is done to the virtual CPU. When it is interrupted, one queued
signal is handled by generating a stack frame in the virtual CPU as the
Linux kernel does. The @code{sigreturn()} system call is emulated to return
from the virtual signal handler.

Some signals (such as SIGALRM) directly come from the host. Other
signals are synthetized from the virtual CPU exceptions such as SIGFPE
when a division by zero is done (see @code{main.c:cpu_loop()}).

The blocked signal mask is still handled by the host Linux kernel so
that most signal system calls can be redirected directly to the host
Linux kernel. Only the @code{sigaction()} and @code{sigreturn()} system
calls need to be fully emulated (see @file{signal.c}).

@section clone() system call and threads

The Linux clone() system call is usually used to create a thread. QEMU
uses the host clone() system call so that real host threads are created
for each emulated thread. One virtual CPU instance is created for each
thread.

The virtual x86 CPU atomic operations are emulated with a global lock so
that their semantic is preserved.

@section Bibliography

@table @asis

@item [1] 
@url{http://citeseer.nj.nec.com/piumarta98optimizing.html}, Optimizing
direct threaded code by selective inlining (1998) by Ian Piumarta, Fabio
Riccardi.

@item [2]
@url{http://developer.kde.org/~sewardj/}, Valgrind, an open-source
memory debugger for x86-GNU/Linux, by Julian Seward.

@item [3]
@url{http://bochs.sourceforge.net/}, the Bochs IA-32 Emulator Project,
by Kevin Lawton et al.

@item [4]
@url{http://www.cs.rose-hulman.edu/~donaldlf/em86/index.html}, the EM86
x86 emulator on Alpha-Linux.

@item [5]
@url{http://www.usenix.org/publications/library/proceedings/usenix-nt97/full_papers/chernoff/chernoff.pdf},
DIGITAL FX!32: Running 32-Bit x86 Applications on Alpha NT, by Anton
Chernoff and Ray Hookway.

@end table

@chapter Regression Tests

In the directory @file{tests/}, various interesting x86 testing programs
are available. There are used for regression testing.

@section @file{hello}

Very simple statically linked x86 program, just to test QEMU during a
port to a new host CPU.

@section @file{test-i386}

This program executes most of the 16 bit and 32 bit x86 instructions and
generates a text output. It can be compared with the output obtained with
a real CPU or another emulator. The target @code{make test} runs this
program and a @code{diff} on the generated output.

The Linux system call @code{modify_ldt()} is used to create x86 selectors
to test some 16 bit addressing and 32 bit with segmentation cases.

@section @file{testsig}

This program tests various signal cases, including SIGFPE, SIGSEGV and
SIGILL.

@section @file{testclone}

Tests the @code{clone()} system call (basic test).

@section @file{testthread}

Tests the glibc threads (more complicated than @code{clone()} because signals
are also used).

@section @file{sha1}

It is a simple benchmark. Care must be taken to interpret the results
because it mostly tests the ability of the virtual CPU to optimize the
@code{rol} x86 instruction and the condition code computations.