Add kvmtool
diff --git a/kvmtool/.gitignore b/kvmtool/.gitignore
new file mode 100644
index 0000000..e935ee5
--- /dev/null
+++ b/kvmtool/.gitignore
@@ -0,0 +1,16 @@
+/lkvm
+/lkvm-static
+/vm
+*.o
+*.d
+*.swp
+/cscope.*
+tags
+tests/boot/boot_test.iso
+tests/boot/rootfs/
+guest/init
+guest/pre_init
+guest/init_stage2
+KVMTOOLS-VERSION-FILE
+/x86/bios/bios.bin
+/x86/bios/bios.bin.elf
diff --git a/kvmtool/COPYING b/kvmtool/COPYING
new file mode 100644
index 0000000..10828e0
--- /dev/null
+++ b/kvmtool/COPYING
@@ -0,0 +1,341 @@
+
+ GNU GENERAL PUBLIC LICENSE
+ Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+ 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The licenses for most software are designed to take away your
+freedom to share and change it. By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users. This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it. (Some other Free Software Foundation software is covered by
+the GNU Library General Public License instead.) You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+ To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have. You must make sure that they, too, receive or can get the
+source code. And you must show them these terms so they know their
+rights.
+
+ We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+ Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software. If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+ Finally, any free program is threatened constantly by software
+patents. We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary. To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ GNU GENERAL PUBLIC LICENSE
+ TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+ 0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License. The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language. (Hereinafter, translation is included without limitation in
+the term "modification".) Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope. The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+ 1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+ 2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+ a) You must cause the modified files to carry prominent notices
+ stating that you changed the files and the date of any change.
+
+ b) You must cause any work that you distribute or publish, that in
+ whole or in part contains or is derived from the Program or any
+ part thereof, to be licensed as a whole at no charge to all third
+ parties under the terms of this License.
+
+ c) If the modified program normally reads commands interactively
+ when run, you must cause it, when started running for such
+ interactive use in the most ordinary way, to print or display an
+ announcement including an appropriate copyright notice and a
+ notice that there is no warranty (or else, saying that you provide
+ a warranty) and that users may redistribute the program under
+ these conditions, and telling the user how to view a copy of this
+ License. (Exception: if the Program itself is interactive but
+ does not normally print such an announcement, your work based on
+ the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole. If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works. But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+ 3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+ a) Accompany it with the complete corresponding machine-readable
+ source code, which must be distributed under the terms of Sections
+ 1 and 2 above on a medium customarily used for software interchange; or,
+
+ b) Accompany it with a written offer, valid for at least three
+ years, to give any third party, for a charge no more than your
+ cost of physically performing source distribution, a complete
+ machine-readable copy of the corresponding source code, to be
+ distributed under the terms of Sections 1 and 2 above on a medium
+ customarily used for software interchange; or,
+
+ c) Accompany it with the information you received as to the offer
+ to distribute corresponding source code. (This alternative is
+ allowed only for noncommercial distribution and only if you
+ received the program in object code or executable form with such
+ an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it. For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable. However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+ 4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License. Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+ 5. You are not required to accept this License, since you have not
+signed it. However, nothing else grants you permission to modify or
+distribute the Program or its derivative works. These actions are
+prohibited by law if you do not accept this License. Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+ 6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions. You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+ 7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all. For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices. Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+ 8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded. In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+ 9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number. If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation. If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+ 10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission. For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this. Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+ NO WARRANTY
+
+ 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+ 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+ Gnomovision version 69, Copyright (C) year name of author
+ Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary. Here is a sample; alter the names:
+
+ Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+ `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+ <signature of Ty Coon>, 1 April 1989
+ Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs. If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library. If this is what you want to do, use the GNU Library General
+Public License instead of this License.
diff --git a/kvmtool/CREDITS-Git b/kvmtool/CREDITS-Git
new file mode 100644
index 0000000..c2ddcb3
--- /dev/null
+++ b/kvmtool/CREDITS-Git
@@ -0,0 +1,30 @@
+Most of the infrastructure that 'perf' uses here has been reused
+from the Git project, as of version:
+
+ 66996ec: Sync with 1.6.2.4
+
+Here is an (incomplete!) list of main contributors to those files
+in util/* and elsewhere:
+
+ Alex Riesen
+ Christian Couder
+ Dmitry Potapov
+ Jeff King
+ Johannes Schindelin
+ Johannes Sixt
+ Junio C Hamano
+ Linus Torvalds
+ Matthias Kestenholz
+ Michal Ostrowski
+ Miklos Vajna
+ Petr Baudis
+ Pierre Habouzit
+ René Scharfe
+ Samuel Tardieu
+ Shawn O. Pearce
+ Steffen Prohaska
+ Steve Haslam
+
+Thanks guys!
+
+The full history of the files can be found in the upstream Git commits.
diff --git a/kvmtool/Documentation/kernel-debugging.txt b/kvmtool/Documentation/kernel-debugging.txt
new file mode 100644
index 0000000..98b9438
--- /dev/null
+++ b/kvmtool/Documentation/kernel-debugging.txt
@@ -0,0 +1,15 @@
+This document explains how to debug a guests' kernel using KGDB.
+
+1. Run the guest:
+ 'lkvm run -k [vmlinuz] -p "kgdboc=ttyS1 kgdbwait" --tty 1'
+
+And see which PTY got assigned to ttyS1 (you'll see:
+' Info: Assigned terminal 1 to pty /dev/pts/X').
+
+2. Run GDB on the host:
+ 'gdb [vmlinuz]'
+
+3. Connect to the guest (from within GDB):
+ 'target remote /dev/pty/X'
+
+4. Start debugging! (enter 'continue' to continue boot).
diff --git a/kvmtool/Documentation/kvmtool.1 b/kvmtool/Documentation/kvmtool.1
new file mode 100644
index 0000000..2b8c274
--- /dev/null
+++ b/kvmtool/Documentation/kvmtool.1
@@ -0,0 +1,226 @@
+.\" Manpage for kvmtool
+.\" Copyright (C) 2015 by Andre Przywara <andre.przywara@arm.com>
+.TH kvmtool 1 "11 Nov 2015" "0.1" "kvmtool man page"
+.SH NAME
+kvmtool \- running KVM guests
+.SH SYNOPSIS
+lkvm COMMAND [ARGS]
+.SH DESCRIPTION
+kvmtool is a userland tool for creating and controlling KVM guests.
+.SH "KVMTOOL COMMANDS"
+.sp
+.PP
+.B run -k <kernel\-image> [\-c <cores>] [\-m <MiB>] [\-p <command line>]
+.br
+.B [\-i <initrd>] [\-d <image file>] [\-\-console serial|virtio|hv]
+.br
+.B [\-\-dev <node>] [\-\-debug] [\-\-debug\-single\-step] [\-\-debug\-ioport]
+.RS 4
+Run a guest.
+.sp
+.B \-k, \-\-kernel <image file>
+.RS 4
+The virtual machine kernel.
+.RE
+.sp
+.B \-c, \-\-cpus <n>
+.RS 4
+The number of virtual CPUs to run.
+.RE
+.sp
+.B \-m, \-\-mem <n>
+.RS 4
+Virtual machine memory size in MiB.
+.RE
+.sp
+.B \-p, \-\-params <parameters>
+.RS 4
+Additional kernel command line arguments.
+.RE
+.sp
+.B \-i, \-\-initrd <image file>
+.RS 4
+Initial RAM disk image.
+.RE
+.sp
+.B \-d, \-\-disk <image file|directory>
+.RS 4
+A disk image file or a rootfs directory.
+.RE
+.sp
+.B \-\-console serial|virtio|hv
+.RS 4
+Console to use.
+.RE
+.sp
+.B \-\-dev <device node>
+.RS 4
+KVM device file (instead of the default /dev/kvm).
+.RE
+.sp
+.B \-\-debug
+.RS 4
+Enable debug messages.
+.RE
+.sp
+.B \-\-debug-single-step
+.RS 4
+Enable single stepping.
+.RE
+.sp
+.B \-\-debug-ioport
+.RS 4
+Enable ioport debugging.
+.RE
+.RE
+.PP
+.B setup <name>
+.RS 4
+Setup a new virtual machine. This creates a new rootfs in the .lkvm
+folder of your home directory.
+.RE
+.PP
+.B pause \-\-all|\-\-name <name>
+.RS 4
+Pause a virtual machine.
+.sp
+.B \-a, \-\-all
+.RS 4
+Pause all running instances.
+.RE
+.sp
+.B \-n, \-\-name <name>
+.RS 4
+Pause that specified instance. For a list of running instances, see \fI lkvm list\fR.
+.RE
+.RE
+.PP
+.B resume --all|--name <name>
+.RS 4
+Resume a previously paused virtual machine.
+.sp
+.B \-a, \-\-all
+.RS 4
+Resume all running instances.
+.RE
+.sp
+.B \-n, \-\-name <name>
+.RS 4
+Resume that specified instance. For a list of running instances, see \fI lkvm list\fR.
+.RE
+.RE
+.PP
+.B list [\-i] [\-r]
+.RS 4
+Print a list of running instances on the host. This is restricted to instances
+started by the current user, as it looks in the .lkvm folder in your home
+directory to find the socket files.
+.sp
+.B \-i, \-\-run
+.RS 4
+List all running instances.
+.RE
+.sp
+.B \-r, \-\-rootfs
+.RS 4
+List rootfs instances.
+.RE
+.RE
+.PP
+.B debug --all|--name <guest name> [--dump] [--nmi <n>] [--sysrq <rq>]
+.RS 4
+Print debug information from a running VM instance.
+.sp
+.B \-a, \-\-all
+.RS 4
+Debug all running instances.
+.RE
+.PP
+.B \-n, \-\-name <guest name>
+.RS 4
+Debug the specified instance.
+.RE
+.sp
+.B \-d, \-\-dump
+.RS 4
+Generate a debug dump from guest.
+.RE
+.PP
+.B \-m, \-\-nmi <VCPU nr>
+.RS 4
+Generate an NMI on the specified virtual CPU.
+.RE
+.PP
+.B \-s, \-\-sysrq <sysrq>
+.RS 4
+Inject a Linux sysrq into the guest.
+.RE
+.RE
+.PP
+.B balloon \-\-name <guest name> \-\-inflate|\-\-deflate <amount in MB>
+.RS 4
+This command inflates or deflates the virtio balloon located in the
+specified instance.
+\-\-inflate increases the size of the balloon, thus \fIdecreasing\fR the
+amount of virtual RAM available for the guest. \-\-deflate returns previously
+inflated memory back to the guest.
+.sp
+.B \-n, \-\-name <guest name>
+.RS 4
+Ballon the specified instance. For a list of all instances, see \fI"lkvm list"\fR.
+.RE
+.PP
+.B \-i, \-\-inflate <n>
+.RS 4
+Inflates the ballon by the specified number of Megabytes. This decreases the
+amount of usable memory in the guest.
+.RE
+.PP
+.B \-d, \-\-deflate <n>
+.RS 4
+Deflates the ballon by the specified number of Megabytes. This increases the
+amount of usable memory in the guest.
+.RE
+.RE
+.PP
+.B stop --all|--name <name>
+.RS 4
+Stop a running instance.
+.sp
+.B \-a, \-\-all
+.RS 4
+Stop all running instances.
+.RE
+.sp
+.B \-n, \-\-name <name>
+.RS 4
+Stop the specified instance. For a list of running instances, see \fI lkvm list\fR.
+.RE
+.RE
+.PP
+.B stat \-\-all|\-\-name <name> [\-m]
+.RS 4
+Print statistics about a running instance.
+.sp
+.B \-m, \-\-memory
+.RS 4
+Display memory statistics.
+.RE
+.RE
+.PP
+.B sandbox (\fIlkvm run arguments\fR) \-\- [sandboxed command]
+.RS 4
+Run a command in a sandboxed guest. Kvmtool will inject a special init
+binary which will do an initial setup of the guest Linux and then
+lauch a shell script with the specified command. Upon this command ending,
+the guest will be shutdown.
+.RE
+.SH EXAMPLES
+.RS 4
+\fB$\fR lkvm run -k bzImage
+.RE
+.SH SEE ALSO
+qemu(1), kvm(4)
+.SH BUGS
+.SH AUTHOR
+Andre Przywara <andre.przywara@arm.com>
diff --git a/kvmtool/Documentation/virtio-console.txt b/kvmtool/Documentation/virtio-console.txt
new file mode 100644
index 0000000..4a58d56
--- /dev/null
+++ b/kvmtool/Documentation/virtio-console.txt
@@ -0,0 +1,41 @@
+General
+--------
+
+virtio-console as the name implies is a console over virtio transport. Here is
+a simple head to head comparison of the virtio-console vs regular 8250 console:
+
+8250 serial console:
+
+ - Requires CONFIG_SERIAL_8250=y and CONFIG_SERIAL_8250_CONSOLE=y kernel configs,
+which are enabled almost everywhere.
+ - Doesn't require guest-side changes.
+ - Compatible with older guests.
+
+virtio-console:
+
+ - Requires CONFIG_VIRTIO_CONSOLE=y (along with all other virtio dependencies),
+which got enabled only in recent kernels (but not all of them).
+ - Much faster.
+ - Consumes less processing resources.
+ - Requires guest-side changes.
+
+Enabling virtio-console
+------------------------
+
+First, make sure guest kernel is built with CONFIG_VIRTIO_CONSOLE=y. Once this
+is done, the following has to be done inside guest image:
+
+ - Add the following line to /etc/inittab:
+ 'hvc0:2345:respawn:/sbin/agetty -L 9600 hvc0'
+ - Add 'hvc0' to /etc/securetty (so you could actually log on)
+ - Start the guest with '--console virtio'
+
+Common errors
+--------------
+
+Q: I don't see anything on the screen!
+A: Make sure CONFIG_VIRTIO_CONSOLE=y is enabled in the *guest* kernel, also
+make sure you've updated /etc/inittab
+
+Q: It won't accept my username/password, but I enter them correctly!
+A: You didn't add 'hvc0' to /etc/securetty
diff --git a/kvmtool/INSTALL b/kvmtool/INSTALL
new file mode 100644
index 0000000..ca8e022
--- /dev/null
+++ b/kvmtool/INSTALL
@@ -0,0 +1,99 @@
+ Installation instructions for kvmtool
+---------------------------------------
+
+==========================================================================
+For the impatient:
+Just typing "make" should do the trick most of the times.
+You will get a binary called "lkvm" which is self-contained.
+No extra libraries or files need to be installed.
+==========================================================================
+
+"make install" will copy the compiled file into $HOME/bin, this can be
+changed by providing "prefix=" on the make command-line. DESTDIR will be
+honoured.
+
+Prerequisites
+--------------
+For compilation you will need a recent GNU tool chain (binutils, gcc, make),
+also the standard C library.
+
+For deb based systems:
+ $ sudo apt-get install build-essential
+ On x86-64 systems you have to add the 32-bit compat headers:
+ $ sudo apt-get install libc6-dev-i386
+For Fedora based systems:
+ # yum install glibc-static
+For OpenSUSE based systems:
+ # zypper install glibc-devel-static
+
+Architectures which require device tree (PowerPC, ARM, ARM64) also require
+libfdt.
+ deb: $ sudo apt-get install libfdt-dev
+ Fedora: # yum install libfdt-devel
+ OpenSUSE: # zypper install libfdt1-devel
+Also see "Cross compiling" below.
+
+Optional libraries
+-------------------
+By running "make" some checks are invoked that determine the availability
+of certain optional libraries. Those are:
+- libbfd: enable symbol look-up support in debug mode
+- gtk3: enable support for displaying the guest framebuffer in a GTK+-3 window
+- vncserver: enable support for exporting the guest framebuffer in a VNC session
+- SDL: enable support for displaying the guest framebuffer in a SDL window
+- zlib: enable support for compressed QCOW images
+- aio: enable support for asynchronous I/O
+(Note that a guest framebuffer is currently only supported on x86.)
+So for the full glory you would need:
+(on a .deb based system):
+$ sudo apt-get install binutils-dev libgtk-3-dev libvncserver-dev libsdl2-dev \
+ zlib1g-dev libaio-dev
+(on RPM based systems):
+# $TOOL install binutils-devel gtk3-devel libvncserver-devel SDL-devel \
+ zlib-devel libaio-devel
+$TOOL is "yum" for Fedora and "zypper" for OpenSUSE.
+
+Cross compiling
+----------------
+The Makefile will honour the CROSS_COMPILE environment variable when calling
+the compiler and the linker binary. To trigger cross compilation, also set ARCH
+to the Linux name of the architecture. Architectures supported:
+- i386
+- x86_64
+- powerpc
+- arm
+- arm64
+- mips
+If ARCH is not provided, the target architecture will be automatically
+determined by running "uname -m" on your host, resulting in a native build.
+
+To cross-compile to ARM for instance, install a cross-compiler, put the
+required libraries in the cross-compiler's SYSROOT and type:
+$ make CROSS_COMPILE=arm-linux-gnueabihf- ARCH=arm
+
+Missing libraries when cross-compiling
+---------------------------------------
+The cross-compiler will look for target libraries in its SYSROOT directory,
+so you need to put the header and library files (.so) there.
+While most cross compiler packages come with the target's glibc already
+installed, optional libraries (or libfdt) maybe not.
+On multiarch system you should be able to install those be appending
+the architecture name after the package (example for ARM64):
+$ sudo apt-get install libfdt-dev:arm64
+
+PowerPC and ARM/ARM64 require libfdt to be installed. If you cannot use
+precompiled mulitarch packages, you could either copy the required header and
+library files from an installed target system into the SYSROOT (you will need
+/usr/include/*fdt*.h and /usr/lib64/libfdt-v.v.v.so and its symlinks), or you
+can cross-compile the libfdt library yourself:
+
+$ git clone git://git.kernel.org/pub/scm/utils/dtc/dtc.git
+$ cd dtc
+$ export CC=${CROSS_COMPILE}gcc
+$ TRIPLET=$($CC -dumpmachine)
+$ SYSROOT=$($CC -print-sysroot)
+$ make libfdt
+$ sudo make DESTDIR=$SYSROOT PREFIX=/usr LIBDIR=/usr/lib/$TRIPLET install-lib install-includes
+
+This assumes a multiarch-enabled system, if there is no per-arch directory for
+libraries, replace the LIBDIR paths above with LIBDIR=/usr/lib or /usr/lib64.
diff --git a/kvmtool/Makefile b/kvmtool/Makefile
new file mode 100644
index 0000000..35bb118
--- /dev/null
+++ b/kvmtool/Makefile
@@ -0,0 +1,563 @@
+#
+# Define WERROR=0 to disable -Werror.
+#
+
+ifeq ($(strip $(V)),)
+ ifeq ($(findstring s,$(filter-out --%,$(MAKEFLAGS))),)
+ E = @echo
+ else
+ E = @\#
+ endif
+ Q = @
+else
+ E = @\#
+ Q =
+endif
+export E Q
+
+include config/utilities.mak
+include config/feature-tests.mak
+
+CC := $(CROSS_COMPILE)gcc
+CFLAGS :=
+LD := $(CROSS_COMPILE)ld
+LDFLAGS :=
+OBJCOPY := $(CROSS_COMPILE)objcopy
+
+FIND := find
+CSCOPE := cscope
+TAGS := ctags
+INSTALL := install
+
+prefix = $(HOME)
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+
+DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
+bindir_SQ = $(subst ','\'',$(bindir))
+
+PROGRAM := lkvm
+PROGRAM_ALIAS := vm
+
+OBJS += builtin-balloon.o
+OBJS += builtin-debug.o
+OBJS += builtin-help.o
+OBJS += builtin-list.o
+OBJS += builtin-stat.o
+OBJS += builtin-pause.o
+OBJS += builtin-resume.o
+OBJS += builtin-run.o
+OBJS += builtin-setup.o
+OBJS += builtin-stop.o
+OBJS += builtin-version.o
+OBJS += devices.o
+OBJS += disk/core.o
+OBJS += framebuffer.o
+OBJS += guest_compat.o
+OBJS += hw/rtc.o
+OBJS += hw/serial.o
+OBJS += ioport.o
+OBJS += irq.o
+OBJS += kvm-cpu.o
+OBJS += kvm.o
+OBJS += main.o
+OBJS += mmio.o
+OBJS += pci.o
+OBJS += term.o
+OBJS += vfio/core.o
+OBJS += vfio/pci.o
+OBJS += virtio/blk.o
+OBJS += virtio/scsi.o
+OBJS += virtio/console.o
+OBJS += virtio/core.o
+OBJS += virtio/net.o
+OBJS += virtio/rng.o
+OBJS += virtio/balloon.o
+OBJS += virtio/pci.o
+OBJS += disk/blk.o
+OBJS += disk/qcow.o
+OBJS += disk/raw.o
+OBJS += ioeventfd.o
+OBJS += net/uip/core.o
+OBJS += net/uip/arp.o
+OBJS += net/uip/icmp.o
+OBJS += net/uip/ipv4.o
+OBJS += net/uip/tcp.o
+OBJS += net/uip/udp.o
+OBJS += net/uip/buf.o
+OBJS += net/uip/csum.o
+OBJS += net/uip/dhcp.o
+OBJS += kvm-cmd.o
+OBJS += util/init.o
+OBJS += util/iovec.o
+OBJS += util/rbtree.o
+OBJS += util/threadpool.o
+OBJS += util/parse-options.o
+OBJS += util/rbtree-interval.o
+OBJS += util/strbuf.o
+OBJS += util/read-write.o
+OBJS += util/util.o
+OBJS += virtio/9p.o
+OBJS += virtio/9p-pdu.o
+OBJS += kvm-ipc.o
+OBJS += builtin-sandbox.o
+OBJS += virtio/mmio.o
+
+# Translate uname -m into ARCH string
+ARCH ?= $(shell uname -m | sed -e s/i.86/i386/ -e s/ppc.*/powerpc/ \
+ -e s/armv.*/arm/ -e s/aarch64.*/arm64/ -e s/mips64/mips/)
+
+ifeq ($(ARCH),i386)
+ ARCH := x86
+ DEFINES += -DCONFIG_X86_32
+endif
+ifeq ($(ARCH),x86_64)
+ ARCH := x86
+ DEFINES += -DCONFIG_X86_64
+ ARCH_PRE_INIT = x86/init.S
+endif
+
+### Arch-specific stuff
+
+#x86
+ifeq ($(ARCH),x86)
+ DEFINES += -DCONFIG_X86
+ OBJS += hw/i8042.o
+ OBJS += x86/boot.o
+ OBJS += x86/cpuid.o
+ OBJS += x86/interrupt.o
+ OBJS += x86/ioport.o
+ OBJS += x86/irq.o
+ OBJS += x86/kvm.o
+ OBJS += x86/kvm-cpu.o
+ OBJS += x86/mptable.o
+# Exclude BIOS object files from header dependencies.
+ OTHEROBJS += x86/bios.o
+ OTHEROBJS += x86/bios/bios-rom.o
+ ARCH_INCLUDE := x86/include
+ ARCH_HAS_FRAMEBUFFER := y
+endif
+# POWER/ppc: Actually only support ppc64 currently.
+ifeq ($(ARCH), powerpc)
+ DEFINES += -DCONFIG_PPC
+ OBJS += powerpc/boot.o
+ OBJS += powerpc/ioport.o
+ OBJS += powerpc/kvm.o
+ OBJS += powerpc/cpu_info.o
+ OBJS += powerpc/kvm-cpu.o
+ OBJS += powerpc/spapr_hcall.o
+ OBJS += powerpc/spapr_rtas.o
+ OBJS += powerpc/spapr_hvcons.o
+ OBJS += powerpc/spapr_pci.o
+ OBJS += powerpc/xics.o
+ ARCH_INCLUDE := powerpc/include
+
+ ARCH_WANT_LIBFDT := y
+endif
+
+# ARM
+OBJS_ARM_COMMON := arm/fdt.o arm/gic.o arm/gicv2m.o arm/ioport.o \
+ arm/kvm.o arm/kvm-cpu.o arm/pci.o arm/timer.o \
+ arm/pmu.o
+HDRS_ARM_COMMON := arm/include
+ifeq ($(ARCH), arm)
+ DEFINES += -DCONFIG_ARM
+ OBJS += $(OBJS_ARM_COMMON)
+ OBJS += arm/aarch32/arm-cpu.o
+ OBJS += arm/aarch32/kvm-cpu.o
+ ARCH_INCLUDE := $(HDRS_ARM_COMMON)
+ ARCH_INCLUDE += -Iarm/aarch32/include
+ CFLAGS += -march=armv7-a
+
+ ARCH_WANT_LIBFDT := y
+ ARCH_HAS_FLASH_MEM := y
+endif
+
+# ARM64
+ifeq ($(ARCH), arm64)
+ DEFINES += -DCONFIG_ARM64
+ OBJS += $(OBJS_ARM_COMMON)
+ OBJS += arm/aarch64/arm-cpu.o
+ OBJS += arm/aarch64/kvm-cpu.o
+ OBJS += arm/aarch64/kvm.o
+ ARCH_INCLUDE := $(HDRS_ARM_COMMON)
+ ARCH_INCLUDE += -Iarm/aarch64/include
+
+ ARCH_WANT_LIBFDT := y
+ ARCH_HAS_FLASH_MEM := y
+endif
+
+ifeq ($(ARCH),mips)
+ DEFINES += -DCONFIG_MIPS
+ ARCH_INCLUDE := mips/include
+ OBJS += mips/kvm.o
+ OBJS += mips/kvm-cpu.o
+endif
+###
+
+ifeq (,$(ARCH_INCLUDE))
+ $(error This architecture ($(ARCH)) is not supported in kvmtool)
+endif
+
+###
+
+# Detect optional features.
+# On a given system, some libs may link statically, some may not; so, check
+# both and only build those that link!
+
+ifeq ($(call try-build,$(SOURCE_STRLCPY),$(CFLAGS),$(LDFLAGS)),y)
+ CFLAGS_DYNOPT += -DHAVE_STRLCPY
+ CFLAGS_STATOPT += -DHAVE_STRLCPY
+endif
+
+ifeq ($(call try-build,$(SOURCE_BFD),$(CFLAGS),$(LDFLAGS) -lbfd -static),y)
+ CFLAGS_STATOPT += -DCONFIG_HAS_BFD
+ OBJS_STATOPT += symbol.o
+ LIBS_STATOPT += -lbfd
+else
+ ifeq ($(call try-build,$(SOURCE_BFD),$(CFLAGS),$(LDFLAGS) -lbfd),y)
+ CFLAGS_DYNOPT += -DCONFIG_HAS_BFD
+ OBJS_DYNOPT += symbol.o
+ LIBS_DYNOPT += -lbfd
+ else
+ NOTFOUND += bfd
+ endif
+endif
+
+ifeq (y,$(ARCH_HAS_FRAMEBUFFER))
+ OBJS += hw/vesa.o
+
+ CFLAGS_GTK3 := $(shell pkg-config --cflags gtk+-3.0 2>/dev/null)
+ LDFLAGS_GTK3 := $(shell pkg-config --libs gtk+-3.0 2>/dev/null)
+ ifeq ($(call try-build,$(SOURCE_GTK3),$(CFLAGS) $(CFLAGS_GTK3),$(LDFLAGS) $(LDFLAGS_GTK3)),y)
+ OBJS_DYNOPT += ui/gtk3.o
+ CFLAGS_DYNOPT += -DCONFIG_HAS_GTK3 $(CFLAGS_GTK3)
+ LIBS_DYNOPT += $(LDFLAGS_GTK3)
+ else
+ NOTFOUND += GTK3
+ endif
+
+ ifeq ($(call try-build,$(SOURCE_VNCSERVER),$(CFLAGS),$(LDFLAGS) -lvncserver),y)
+ OBJS_DYNOPT += ui/vnc.o
+ CFLAGS_DYNOPT += -DCONFIG_HAS_VNCSERVER
+ LIBS_DYNOPT += -lvncserver
+ else
+ NOTFOUND += vncserver
+ endif
+ ifeq ($(call try-build,$(SOURCE_VNCSERVER),$(CFLAGS),$(LDFLAGS) -lvncserver -static),y)
+ OBJS_STATOPT += ui/vnc.o
+ CFLAGS_STATOPT += -DCONFIG_HAS_VNCSERVER
+ LIBS_STATOPT += -lvncserver
+ endif
+
+ ifeq ($(call try-build,$(SOURCE_SDL),$(CFLAGS),$(LDFLAGS) -lSDL),y)
+ OBJS_DYNOPT += ui/sdl.o
+ CFLAGS_DYNOPT += -DCONFIG_HAS_SDL
+ LIBS_DYNOPT += -lSDL
+ else
+ NOTFOUND += SDL
+ endif
+ ifeq ($(call try-build,$(SOURCE_SDL),$(CFLAGS),$(LDFLAGS) -lSDL -static), y)
+ OBJS_STATOPT += ui/sdl.o
+ CFLAGS_STATOPT += -DCONFIG_HAS_SDL
+ LIBS_STATOPT += -lSDL
+ endif
+endif
+
+ifeq (y,$(ARCH_HAS_FLASH_MEM))
+ OBJS += hw/cfi_flash.o
+endif
+
+ifeq ($(call try-build,$(SOURCE_ZLIB),$(CFLAGS),$(LDFLAGS) -lz),y)
+ CFLAGS_DYNOPT += -DCONFIG_HAS_ZLIB
+ LIBS_DYNOPT += -lz
+else
+ ifeq ($(call try-build,$(SOURCE_ZLIB),$(CFLAGS),$(LDFLAGS) -lz -static),y)
+ CFLAGS_STATOPT += -DCONFIG_HAS_ZLIB
+ LIBS_STATOPT += -lz
+ else
+ NOTFOUND += zlib
+ endif
+endif
+
+ifeq ($(call try-build,$(SOURCE_AIO),$(CFLAGS),$(LDFLAGS) -laio),y)
+ CFLAGS_DYNOPT += -DCONFIG_HAS_AIO
+ LIBS_DYNOPT += -laio
+ OBJS_DYNOPT += disk/aio.o
+else
+ ifeq ($(call try-build,$(SOURCE_AIO),$(CFLAGS),$(LDFLAGS) -laio -static),y)
+ CFLAGS_STATOPT += -DCONFIG_HAS_AIO
+ LIBS_STATOPT += -laio
+ OBJS_STATOPT += disk/aio.o
+ else
+ NOTFOUND += aio
+ endif
+endif
+
+ifeq ($(LTO),1)
+ FLAGS_LTO := -flto
+ ifeq ($(call try-build,$(SOURCE_HELLO),$(CFLAGS),$(LDFLAGS) $(FLAGS_LTO)),y)
+ CFLAGS += $(FLAGS_LTO)
+ endif
+endif
+
+ifeq ($(call try-build,$(SOURCE_STATIC),$(CFLAGS),$(LDFLAGS) -static),y)
+ CFLAGS += -DCONFIG_GUEST_INIT
+ GUEST_INIT := guest/init
+ GUEST_OBJS = guest/guest_init.o
+ ifeq ($(ARCH_PRE_INIT),)
+ GUEST_INIT_FLAGS += -static $(PIE_FLAGS)
+ else
+ CFLAGS += -DCONFIG_GUEST_PRE_INIT
+ GUEST_INIT_FLAGS += -DCONFIG_GUEST_PRE_INIT
+ GUEST_PRE_INIT := guest/pre_init
+ GUEST_OBJS += guest/guest_pre_init.o
+ endif
+else
+$(warning No static libc found. Skipping guest init)
+ NOTFOUND += static-libc
+endif
+
+ifeq (y,$(ARCH_WANT_LIBFDT))
+ ifneq ($(call try-build,$(SOURCE_LIBFDT),$(CFLAGS),-lfdt),y)
+ $(error No libfdt found. Please install libfdt-dev package)
+ else
+ CFLAGS_DYNOPT += -DCONFIG_HAS_LIBFDT
+ CFLAGS_STATOPT += -DCONFIG_HAS_LIBFDT
+ LIBS_DYNOPT += -lfdt
+ LIBS_STATOPT += -lfdt
+ endif
+endif
+
+ifeq ($(call try-build,$(SOURCE_HELLO),$(CFLAGS),-no-pie),y)
+ PIE_FLAGS += -no-pie
+endif
+
+ifneq ($(NOTFOUND),)
+ $(warning Skipping optional libraries: $(NOTFOUND))
+endif
+
+###
+
+LIBS += -lrt
+LIBS += -lpthread
+LIBS += -lutil
+
+
+comma = ,
+
+# The dependency file for the current target
+depfile = $(subst $(comma),_,$(dir $@).$(notdir $@).d)
+
+DEPS := $(foreach obj,$(OBJS),\
+ $(subst $(comma),_,$(dir $(obj)).$(notdir $(obj)).d))
+
+DEFINES += -D_FILE_OFFSET_BITS=64
+DEFINES += -D_GNU_SOURCE
+DEFINES += -DKVMTOOLS_VERSION='"$(KVMTOOLS_VERSION)"'
+DEFINES += -DBUILD_ARCH='"$(ARCH)"'
+
+KVM_INCLUDE := include
+CFLAGS += $(CPPFLAGS) $(DEFINES) -I$(KVM_INCLUDE) -I$(ARCH_INCLUDE) -O2 -fno-strict-aliasing -g
+
+WARNINGS += -Wall
+WARNINGS += -Wformat=2
+WARNINGS += -Winit-self
+WARNINGS += -Wmissing-declarations
+WARNINGS += -Wmissing-prototypes
+WARNINGS += -Wnested-externs
+WARNINGS += -Wno-system-headers
+WARNINGS += -Wold-style-definition
+WARNINGS += -Wredundant-decls
+WARNINGS += -Wsign-compare
+WARNINGS += -Wstrict-prototypes
+WARNINGS += -Wundef
+WARNINGS += -Wvolatile-register-var
+WARNINGS += -Wwrite-strings
+WARNINGS += -Wno-format-nonliteral
+
+CFLAGS += $(WARNINGS)
+
+ifneq ($(WERROR),0)
+ CFLAGS += -Werror
+endif
+
+all: $(PROGRAM) $(PROGRAM_ALIAS)
+
+# CFLAGS used when building objects
+# This is intentionally not assigned using :=
+c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CFLAGS)
+
+# When building -static all objects are built with appropriate flags, which
+# may differ between static & dynamic .o. The objects are separated into
+# .o and .static.o. See the %.o: %.c rules below.
+#
+# $(OTHEROBJS) are things that do not get substituted like this.
+#
+STATIC_OBJS = $(patsubst %.o,%.static.o,$(OBJS) $(OBJS_STATOPT))
+
+STATIC_DEPS := $(foreach obj,$(STATIC_OBJS),\
+ $(subst $(comma),_,$(dir $(obj)).$(notdir $(obj)).d))
+
+$(PROGRAM)-static: $(STATIC_OBJS) $(OTHEROBJS) $(GUEST_OBJS)
+ $(E) " LINK " $@
+ $(Q) $(CC) -static $(CFLAGS) $(STATIC_OBJS) $(OTHEROBJS) $(GUEST_OBJS) $(LDFLAGS) $(LIBS) $(LIBS_STATOPT) -o $@
+
+$(PROGRAM): $(OBJS) $(OBJS_DYNOPT) $(OTHEROBJS) $(GUEST_OBJS)
+ $(E) " LINK " $@
+ $(Q) $(CC) $(CFLAGS) $(OBJS) $(OBJS_DYNOPT) $(OTHEROBJS) $(GUEST_OBJS) $(LDFLAGS) $(LIBS) $(LIBS_DYNOPT) -o $@
+
+$(PROGRAM_ALIAS): $(PROGRAM)
+ $(E) " LN " $@
+ $(Q) ln -f $(PROGRAM) $@
+
+ifneq ($(ARCH_PRE_INIT),)
+$(GUEST_PRE_INIT): $(ARCH_PRE_INIT)
+ $(E) " COMPILE " $@
+ $(Q) $(CC) -s $(PIE_FLAGS) -nostdlib $< -o $@
+
+guest/guest_pre_init.c: $(GUEST_PRE_INIT)
+ $(E) " CONVERT " $@
+ $(Q) $(call binary-to-C,$<,pre_init_binary,$@)
+endif
+
+$(GUEST_INIT): guest/init.c
+ $(E) " COMPILE " $@
+ $(Q) $(CC) $(GUEST_INIT_FLAGS) $< -o $@
+
+guest/guest_init.c: $(GUEST_INIT)
+ $(E) " CONVERT " $@
+ $(Q) $(call binary-to-C,$<,init_binary,$@)
+
+%.s: %.c
+ $(Q) $(CC) -o $@ -S $(CFLAGS) -fverbose-asm $<
+
+$(OBJS):
+
+util/rbtree.static.o util/rbtree.o: util/rbtree.c
+ifeq ($(C),1)
+ $(E) " CHECK " $@
+ $(Q) $(CHECK) -c $(CFLAGS) $< -o $@
+endif
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(c_flags) $< -o $@
+
+%.static.o: %.c
+ifeq ($(C),1)
+ $(E) " CHECK " $@
+ $(Q) $(CHECK) -c $(CFLAGS) $(CFLAGS_STATOPT) $< -o $@
+endif
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(c_flags) $(CFLAGS_STATOPT) $< -o $@
+
+%.o: %.c
+ifeq ($(C),1)
+ $(E) " CHECK " $@
+ $(Q) $(CHECK) -c $(CFLAGS) $(CFLAGS_DYNOPT) $< -o $@
+endif
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(c_flags) $(CFLAGS_DYNOPT) $< -o $@
+
+
+#
+# BIOS assembly weirdness
+#
+BIOS_CFLAGS += -m32
+BIOS_CFLAGS += -march=i386
+BIOS_CFLAGS += -mregparm=3
+
+BIOS_CFLAGS += -fno-stack-protector
+BIOS_CFLAGS += -fno-pic
+
+x86/bios.o: x86/bios/bios.bin x86/bios/bios-rom.h
+
+x86/bios/bios.bin.elf: x86/bios/entry.S x86/bios/e820.c x86/bios/int10.c x86/bios/int15.c x86/bios/rom.ld.S
+ $(E) " CC x86/bios/memcpy.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c x86/bios/memcpy.c -o x86/bios/memcpy.o
+ $(E) " CC x86/bios/e820.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c x86/bios/e820.c -o x86/bios/e820.o
+ $(E) " CC x86/bios/int10.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c x86/bios/int10.c -o x86/bios/int10.o
+ $(E) " CC x86/bios/int15.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c x86/bios/int15.c -o x86/bios/int15.o
+ $(E) " CC x86/bios/entry.o"
+ $(Q) $(CC) $(CFLAGS) $(BIOS_CFLAGS) -c x86/bios/entry.S -o x86/bios/entry.o
+ $(E) " LD " $@
+ $(Q) $(LD) -T x86/bios/rom.ld.S -o x86/bios/bios.bin.elf x86/bios/memcpy.o x86/bios/entry.o x86/bios/e820.o x86/bios/int10.o x86/bios/int15.o
+
+x86/bios/bios.bin: x86/bios/bios.bin.elf
+ $(E) " OBJCOPY " $@
+ $(Q) $(OBJCOPY) -O binary -j .text x86/bios/bios.bin.elf x86/bios/bios.bin
+
+x86/bios/bios-rom.o: x86/bios/bios-rom.S x86/bios/bios.bin x86/bios/bios-rom.h
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(CFLAGS) x86/bios/bios-rom.S -o x86/bios/bios-rom.o
+
+x86/bios/bios-rom.h: x86/bios/bios.bin.elf
+ $(E) " NM " $@
+ $(Q) cd x86/bios && sh gen-offsets.sh > bios-rom.h && cd ..
+
+check: all
+ $(MAKE) -C tests
+ ./$(PROGRAM) run tests/pit/tick.bin
+ ./$(PROGRAM) run -d tests/boot/boot_test.iso -p "init=init"
+.PHONY: check
+
+install: all
+ $(E) " INSTALL"
+ $(Q) $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
+ $(Q) $(INSTALL) $(PROGRAM) '$(DESTDIR_SQ)$(bindir_SQ)'
+.PHONY: install
+
+clean:
+ $(E) " CLEAN"
+ $(Q) rm -f x86/bios/*.bin
+ $(Q) rm -f x86/bios/*.elf
+ $(Q) rm -f x86/bios/*.o
+ $(Q) rm -f x86/bios/bios-rom.h
+ $(Q) rm -f tests/boot/boot_test.iso
+ $(Q) rm -rf tests/boot/rootfs/
+ $(Q) rm -f $(DEPS) $(STATIC_DEPS) $(OBJS) $(OTHEROBJS) $(OBJS_DYNOPT) $(STATIC_OBJS) $(PROGRAM) $(PROGRAM_ALIAS) $(PROGRAM)-static $(GUEST_INIT) $(GUEST_PRE_INIT) $(GUEST_OBJS)
+ $(Q) rm -f guest/guest_init.c guest/guest_pre_init.c
+ $(Q) rm -f cscope.*
+ $(Q) rm -f tags
+ $(Q) rm -f TAGS
+ $(Q) rm -f KVMTOOLS-VERSION-FILE
+.PHONY: clean
+
+KVM_DEV ?= /dev/kvm
+
+$(KVM_DEV):
+ $(E) " MKNOD " $@
+ $(Q) mknod $@ char 10 232
+
+devices: $(KVM_DEV)
+.PHONY: devices
+
+TAGS:
+ $(E) " GEN" $@
+ $(Q) $(RM) -f TAGS
+ $(Q) $(FIND) . -name '*.[hcS]' -print | xargs etags -a
+.PHONY: TAGS
+
+tags:
+ $(E) " GEN" $@
+ $(Q) $(RM) -f tags
+ $(Q) $(FIND) . -name '*.[hcS]' -print | xargs ctags -a
+.PHONY: tags
+
+cscope:
+ $(E) " GEN" $@
+ $(Q) $(FIND) . -name '*.[hcS]' -print > cscope.files
+ $(Q) $(CSCOPE) -bkqu
+.PHONY: cscope
+
+#
+# Escape redundant work on cleaning up
+ifneq ($(MAKECMDGOALS),clean)
+-include $(DEPS)
+
+KVMTOOLS-VERSION-FILE:
+ @$(SHELL_PATH) util/KVMTOOLS-VERSION-GEN $(OUTPUT)
+-include $(OUTPUT)KVMTOOLS-VERSION-FILE
+endif
diff --git a/kvmtool/README b/kvmtool/README
new file mode 100644
index 0000000..d3c2d3a
--- /dev/null
+++ b/kvmtool/README
@@ -0,0 +1,119 @@
+Native Linux KVM tool
+=====================
+
+kvmtool is a lightweight tool for hosting KVM guests. As a pure virtualization
+tool it only supports guests using the same architecture, though it supports
+running 32-bit guests on those 64-bit architectures that allow this.
+
+From the original announcement email:
+-------------------------------------------------------
+The goal of this tool is to provide a clean, from-scratch, lightweight
+KVM host tool implementation that can boot Linux guest images (just a
+hobby, won't be big and professional like QEMU) with no BIOS
+dependencies and with only the minimal amount of legacy device
+emulation.
+
+It's great as a learning tool if you want to get your feet wet in
+virtualization land: it's only 5 KLOC of clean C code that can already
+boot a guest Linux image.
+
+Right now it can boot a Linux image and provide you output via a serial
+console, over the host terminal, i.e. you can use it to boot a guest
+Linux image in a terminal or over ssh and log into the guest without
+much guest or host side setup work needed.
+--------------------------
+
+This is the stand-alone version which does not live inside a Linux
+kernel tree.
+1. To check it out, clone the main git repository:
+
+ git clone git://git.kernel.org/pub/scm/linux/kernel/git/will/kvmtool.git
+
+2. Compile the tool (for more elaborate instructions see INSTALL):
+
+ cd kvmtool && make
+
+3. Download a raw userspace image:
+
+ wget http://wiki.qemu.org/download/linux-0.2.img.bz2 && bunzip2
+linux-0.2.img.bz2
+
+4. The guest kernel has to be built with the following configuration:
+
+ - For the default console output:
+ CONFIG_SERIAL_8250=y
+ CONFIG_SERIAL_8250_CONSOLE=y
+
+ - For running 32bit images on 64bit hosts:
+ CONFIG_IA32_EMULATION=y
+
+ - Proper FS options according to image FS (e.g. CONFIG_EXT2_FS, CONFIG_EXT4_FS).
+
+ - For all virtio devices listed below:
+ CONFIG_VIRTIO=y
+ CONFIG_VIRTIO_RING=y
+ CONFIG_VIRTIO_PCI=y
+
+ - For virtio-blk devices (--disk, -d):
+ CONFIG_VIRTIO_BLK=y
+
+ - For virtio-net devices ([--network, -n] virtio):
+ CONFIG_VIRTIO_NET=y
+
+ - For virtio-9p devices (--virtio-9p):
+ CONFIG_NET_9P=y
+ CONFIG_NET_9P_VIRTIO=y
+ CONFIG_9P_FS=y
+
+ - For virtio-balloon device (--balloon):
+ CONFIG_VIRTIO_BALLOON=y
+
+ - For virtio-console device (--console virtio):
+ CONFIG_VIRTIO_CONSOLE=y
+
+ - For virtio-rng device (--rng):
+ CONFIG_HW_RANDOM_VIRTIO=y
+
+ - For vesa device (--sdl or --vnc):
+ CONFIG_FB_VESA=y
+
+
+5. And finally, launch the hypervisor:
+
+ ./lkvm run --disk linux-0.2.img \
+ --kernel ../../arch/x86/boot/bzImage \
+or
+
+ sudo ./lkvm run --disk linux-0.2.img \
+ --kernel ../../arch/x86/boot/bzImage \
+ --network virtio
+
+The tool has been written by Pekka Enberg, Cyrill Gorcunov, Asias He,
+Sasha Levin and Prasad Joshi. Special thanks to Avi Kivity for his help
+on KVM internals and Ingo Molnar for all-around support and encouragement!
+
+See the following thread for original discussion for motivation of this
+project:
+
+http://thread.gmane.org/gmane.linux.kernel/962051/focus=962620
+
+Another detailed example can be found in the lwn.net article:
+
+http://lwn.net/Articles/658511/
+
+Contributing
+------------
+
+Please send patches for kvmtool to kvm@vger.kernel.org, in the usual git
+patch format, including "kvmtool" in the mail subject. "kvmtool" can be
+added automatically by issuing the command
+
+ git config format.subjectprefix "PATCH kvmtool"
+
+in the git repository.
+
+Maintainers
+-----------
+
+kvmtool is maintained by Will Deacon <will@kernel.org> and Julien Thierry
+<julien.thierry.kdev@gmail.com>.
diff --git a/kvmtool/arm/aarch32/arm-cpu.c b/kvmtool/arm/aarch32/arm-cpu.c
new file mode 100644
index 0000000..16bba55
--- /dev/null
+++ b/kvmtool/arm/aarch32/arm-cpu.c
@@ -0,0 +1,50 @@
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+
+#include "arm-common/gic.h"
+#include "arm-common/timer.h"
+
+#include <linux/byteorder.h>
+#include <linux/types.h>
+
+static void generate_fdt_nodes(void *fdt, struct kvm *kvm)
+{
+ int timer_interrupts[4] = {13, 14, 11, 10};
+
+ gic__generate_fdt_nodes(fdt, kvm->cfg.arch.irqchip);
+ timer__generate_fdt_nodes(fdt, kvm, timer_interrupts);
+}
+
+static int arm_cpu__vcpu_init(struct kvm_cpu *vcpu)
+{
+ vcpu->generate_fdt_nodes = generate_fdt_nodes;
+ return 0;
+}
+
+static struct kvm_arm_target target_generic_v7 = {
+ .id = UINT_MAX,
+ .compatible = "arm,arm-v7",
+ .init = arm_cpu__vcpu_init,
+};
+
+static struct kvm_arm_target target_cortex_a15 = {
+ .id = KVM_ARM_TARGET_CORTEX_A15,
+ .compatible = "arm,cortex-a15",
+ .init = arm_cpu__vcpu_init,
+};
+
+static struct kvm_arm_target target_cortex_a7 = {
+ .id = KVM_ARM_TARGET_CORTEX_A7,
+ .compatible = "arm,cortex-a7",
+ .init = arm_cpu__vcpu_init,
+};
+
+static int arm_cpu__core_init(struct kvm *kvm)
+{
+ kvm_cpu__set_kvm_arm_generic_target(&target_generic_v7);
+
+ return (kvm_cpu__register_kvm_arm_target(&target_cortex_a15) ||
+ kvm_cpu__register_kvm_arm_target(&target_cortex_a7));
+}
+core_init(arm_cpu__core_init);
diff --git a/kvmtool/arm/aarch32/include/asm/kvm.h b/kvmtool/arm/aarch32/include/asm/kvm.h
new file mode 100644
index 0000000..a4217c1
--- /dev/null
+++ b/kvmtool/arm/aarch32/include/asm/kvm.h
@@ -0,0 +1,311 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#ifndef __ARM_KVM_H__
+#define __ARM_KVM_H__
+
+#include <linux/types.h>
+#include <linux/psci.h>
+#include <asm/ptrace.h>
+
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
+
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
+#define KVM_REG_SIZE(id) \
+ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+/* Valid for svc_regs, abt_regs, und_regs, irq_regs in struct kvm_regs */
+#define KVM_ARM_SVC_sp svc_regs[0]
+#define KVM_ARM_SVC_lr svc_regs[1]
+#define KVM_ARM_SVC_spsr svc_regs[2]
+#define KVM_ARM_ABT_sp abt_regs[0]
+#define KVM_ARM_ABT_lr abt_regs[1]
+#define KVM_ARM_ABT_spsr abt_regs[2]
+#define KVM_ARM_UND_sp und_regs[0]
+#define KVM_ARM_UND_lr und_regs[1]
+#define KVM_ARM_UND_spsr und_regs[2]
+#define KVM_ARM_IRQ_sp irq_regs[0]
+#define KVM_ARM_IRQ_lr irq_regs[1]
+#define KVM_ARM_IRQ_spsr irq_regs[2]
+
+/* Valid only for fiq_regs in struct kvm_regs */
+#define KVM_ARM_FIQ_r8 fiq_regs[0]
+#define KVM_ARM_FIQ_r9 fiq_regs[1]
+#define KVM_ARM_FIQ_r10 fiq_regs[2]
+#define KVM_ARM_FIQ_fp fiq_regs[3]
+#define KVM_ARM_FIQ_ip fiq_regs[4]
+#define KVM_ARM_FIQ_sp fiq_regs[5]
+#define KVM_ARM_FIQ_lr fiq_regs[6]
+#define KVM_ARM_FIQ_spsr fiq_regs[7]
+
+struct kvm_regs {
+ struct pt_regs usr_regs; /* R0_usr - R14_usr, PC, CPSR */
+ unsigned long svc_regs[3]; /* SP_svc, LR_svc, SPSR_svc */
+ unsigned long abt_regs[3]; /* SP_abt, LR_abt, SPSR_abt */
+ unsigned long und_regs[3]; /* SP_und, LR_und, SPSR_und */
+ unsigned long irq_regs[3]; /* SP_irq, LR_irq, SPSR_irq */
+ unsigned long fiq_regs[8]; /* R8_fiq - R14_fiq, SPSR_fiq */
+};
+
+/* Supported Processor Types */
+#define KVM_ARM_TARGET_CORTEX_A15 0
+#define KVM_ARM_TARGET_CORTEX_A7 1
+#define KVM_ARM_NUM_TARGETS 2
+
+/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
+#define KVM_ARM_DEVICE_TYPE_SHIFT 0
+#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_ID_SHIFT 16
+#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+
+/* Supported device IDs */
+#define KVM_ARM_DEVICE_VGIC_V2 0
+
+/* Supported VGIC address types */
+#define KVM_VGIC_V2_ADDR_TYPE_DIST 0
+#define KVM_VGIC_V2_ADDR_TYPE_CPU 1
+
+#define KVM_VGIC_V2_DIST_SIZE 0x1000
+#define KVM_VGIC_V2_CPU_SIZE 0x2000
+
+/* Supported VGICv3 address types */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
+#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
+
+#define KVM_VGIC_V3_DIST_SIZE SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
+
+#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */
+
+struct kvm_vcpu_init {
+ __u32 target;
+ __u32 features[7];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
+
+struct kvm_guest_debug_arch {
+};
+
+struct kvm_debug_exit_arch {
+};
+
+struct kvm_sync_regs {
+ /* Used with KVM_CAP_ARM_USER_IRQ */
+ __u64 device_irq_level;
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+ struct {
+ __u8 serror_pending;
+ __u8 serror_has_esr;
+ /* Align it to 8 bytes */
+ __u8 pad[6];
+ __u64 serror_esr;
+ } exception;
+ __u32 reserved[12];
+};
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000
+#define KVM_REG_ARM_COPROC_SHIFT 16
+#define KVM_REG_ARM_32_OPC2_MASK 0x0000000000000007
+#define KVM_REG_ARM_32_OPC2_SHIFT 0
+#define KVM_REG_ARM_OPC1_MASK 0x0000000000000078
+#define KVM_REG_ARM_OPC1_SHIFT 3
+#define KVM_REG_ARM_CRM_MASK 0x0000000000000780
+#define KVM_REG_ARM_CRM_SHIFT 7
+#define KVM_REG_ARM_32_CRN_MASK 0x0000000000007800
+#define KVM_REG_ARM_32_CRN_SHIFT 11
+/*
+ * For KVM currently all guest registers are nonsecure, but we reserve a bit
+ * in the encoding to distinguish secure from nonsecure for AArch32 system
+ * registers that are banked by security. This is 1 for the secure banked
+ * register, and 0 for the nonsecure banked register or if the register is
+ * not banked by security.
+ */
+#define KVM_REG_ARM_SECURE_MASK 0x0000000010000000
+#define KVM_REG_ARM_SECURE_SHIFT 28
+
+#define ARM_CP15_REG_SHIFT_MASK(x,n) \
+ (((x) << KVM_REG_ARM_ ## n ## _SHIFT) & KVM_REG_ARM_ ## n ## _MASK)
+
+#define __ARM_CP15_REG(op1,crn,crm,op2) \
+ (KVM_REG_ARM | (15 << KVM_REG_ARM_COPROC_SHIFT) | \
+ ARM_CP15_REG_SHIFT_MASK(op1, OPC1) | \
+ ARM_CP15_REG_SHIFT_MASK(crn, 32_CRN) | \
+ ARM_CP15_REG_SHIFT_MASK(crm, CRM) | \
+ ARM_CP15_REG_SHIFT_MASK(op2, 32_OPC2))
+
+#define ARM_CP15_REG32(...) (__ARM_CP15_REG(__VA_ARGS__) | KVM_REG_SIZE_U32)
+
+#define __ARM_CP15_REG64(op1,crm) \
+ (__ARM_CP15_REG(op1, 0, crm, 0) | KVM_REG_SIZE_U64)
+#define ARM_CP15_REG64(...) __ARM_CP15_REG64(__VA_ARGS__)
+
+/* PL1 Physical Timer Registers */
+#define KVM_REG_ARM_PTIMER_CTL ARM_CP15_REG32(0, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CNT ARM_CP15_REG64(0, 14)
+#define KVM_REG_ARM_PTIMER_CVAL ARM_CP15_REG64(2, 14)
+
+/* Virtual Timer Registers */
+#define KVM_REG_ARM_TIMER_CTL ARM_CP15_REG32(0, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT ARM_CP15_REG64(1, 14)
+#define KVM_REG_ARM_TIMER_CVAL ARM_CP15_REG64(3, 14)
+
+/* Normal registers are mapped as coprocessor 16. */
+#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_CORE_REG(name) (offsetof(struct kvm_regs, name) / 4)
+
+/* Some registers need more space to represent values. */
+#define KVM_REG_ARM_DEMUX (0x0011 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_DEMUX_ID_MASK 0x000000000000FF00
+#define KVM_REG_ARM_DEMUX_ID_SHIFT 8
+#define KVM_REG_ARM_DEMUX_ID_CCSIDR (0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT)
+#define KVM_REG_ARM_DEMUX_VAL_MASK 0x00000000000000FF
+#define KVM_REG_ARM_DEMUX_VAL_SHIFT 0
+
+/* VFP registers: we could overload CP10 like ARM does, but that's ugly. */
+#define KVM_REG_ARM_VFP (0x0012 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_VFP_MASK 0x000000000000FFFF
+#define KVM_REG_ARM_VFP_BASE_REG 0x0
+#define KVM_REG_ARM_VFP_FPSID 0x1000
+#define KVM_REG_ARM_VFP_FPSCR 0x1001
+#define KVM_REG_ARM_VFP_MVFR1 0x1006
+#define KVM_REG_ARM_VFP_MVFR0 0x1007
+#define KVM_REG_ARM_VFP_FPEXC 0x1008
+#define KVM_REG_ARM_VFP_FPINST 0x1009
+#define KVM_REG_ARM_VFP_FPINST2 0x100A
+
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
+ /* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
+ /* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
+
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2
+#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32
+#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+ (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
+#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0
+#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL 4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
+#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
+#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
+ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
+#define VGIC_LEVEL_INFO_LINE_LEVEL 0
+
+/* Device Control API on vcpu fd */
+#define KVM_ARM_VCPU_PMU_V3_CTRL 0
+#define KVM_ARM_VCPU_PMU_V3_IRQ 0
+#define KVM_ARM_VCPU_PMU_V3_INIT 1
+#define KVM_ARM_VCPU_TIMER_CTRL 1
+#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
+#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
+
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
+#define KVM_DEV_ARM_ITS_CTRL_RESET 4
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_TYPE_SHIFT 24
+#define KVM_ARM_IRQ_TYPE_MASK 0xff
+#define KVM_ARM_IRQ_VCPU_SHIFT 16
+#define KVM_ARM_IRQ_VCPU_MASK 0xff
+#define KVM_ARM_IRQ_NUM_SHIFT 0
+#define KVM_ARM_IRQ_NUM_MASK 0xffff
+
+/* irq_type field */
+#define KVM_ARM_IRQ_TYPE_CPU 0
+#define KVM_ARM_IRQ_TYPE_SPI 1
+#define KVM_ARM_IRQ_TYPE_PPI 2
+
+/* out-of-kernel GIC cpu interrupt injection irq_number field */
+#define KVM_ARM_IRQ_CPU_IRQ 0
+#define KVM_ARM_IRQ_CPU_FIQ 1
+
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
+#define KVM_ARM_IRQ_GIC_MAX 127
+#endif
+
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS 1
+
+/* PSCI interface */
+#define KVM_PSCI_FN_BASE 0x95c1ba5e
+#define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n))
+
+#define KVM_PSCI_FN_CPU_SUSPEND KVM_PSCI_FN(0)
+#define KVM_PSCI_FN_CPU_OFF KVM_PSCI_FN(1)
+#define KVM_PSCI_FN_CPU_ON KVM_PSCI_FN(2)
+#define KVM_PSCI_FN_MIGRATE KVM_PSCI_FN(3)
+
+#define KVM_PSCI_RET_SUCCESS PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED
+
+#endif /* __ARM_KVM_H__ */
diff --git a/kvmtool/arm/aarch32/include/kvm/barrier.h b/kvmtool/arm/aarch32/include/kvm/barrier.h
new file mode 100644
index 0000000..94913a9
--- /dev/null
+++ b/kvmtool/arm/aarch32/include/kvm/barrier.h
@@ -0,0 +1,10 @@
+#ifndef KVM__KVM_BARRIER_H
+#define KVM__KVM_BARRIER_H
+
+#define dmb() asm volatile ("dmb" : : : "memory")
+
+#define mb() dmb()
+#define rmb() dmb()
+#define wmb() dmb()
+
+#endif /* KVM__KVM_BARRIER_H */
diff --git a/kvmtool/arm/aarch32/include/kvm/fdt-arch.h b/kvmtool/arm/aarch32/include/kvm/fdt-arch.h
new file mode 100644
index 0000000..e448bf1
--- /dev/null
+++ b/kvmtool/arm/aarch32/include/kvm/fdt-arch.h
@@ -0,0 +1,6 @@
+#ifndef KVM__KVM_FDT_H
+#define KVM__KVM_FDT_H
+
+#include "arm-common/fdt-arch.h"
+
+#endif /* KVM__KVM_FDT_H */
diff --git a/kvmtool/arm/aarch32/include/kvm/kvm-arch.h b/kvmtool/arm/aarch32/include/kvm/kvm-arch.h
new file mode 100644
index 0000000..a772bb1
--- /dev/null
+++ b/kvmtool/arm/aarch32/include/kvm/kvm-arch.h
@@ -0,0 +1,10 @@
+#ifndef KVM__KVM_ARCH_H
+#define KVM__KVM_ARCH_H
+
+#define kvm__arch_get_kern_offset(...) 0x8000
+
+#define ARM_MAX_MEMORY(...) ARM_LOMAP_MAX_MEMORY
+
+#include "arm-common/kvm-arch.h"
+
+#endif /* KVM__KVM_ARCH_H */
diff --git a/kvmtool/arm/aarch32/include/kvm/kvm-config-arch.h b/kvmtool/arm/aarch32/include/kvm/kvm-config-arch.h
new file mode 100644
index 0000000..acf0d23
--- /dev/null
+++ b/kvmtool/arm/aarch32/include/kvm/kvm-config-arch.h
@@ -0,0 +1,8 @@
+#ifndef KVM__KVM_CONFIG_ARCH_H
+#define KVM__KVM_CONFIG_ARCH_H
+
+#define ARM_OPT_ARCH_RUN(...)
+
+#include "arm-common/kvm-config-arch.h"
+
+#endif /* KVM__KVM_CONFIG_ARCH_H */
diff --git a/kvmtool/arm/aarch32/include/kvm/kvm-cpu-arch.h b/kvmtool/arm/aarch32/include/kvm/kvm-cpu-arch.h
new file mode 100644
index 0000000..780e0e2
--- /dev/null
+++ b/kvmtool/arm/aarch32/include/kvm/kvm-cpu-arch.h
@@ -0,0 +1,23 @@
+#ifndef KVM__KVM_CPU_ARCH_H
+#define KVM__KVM_CPU_ARCH_H
+
+#include "kvm/kvm.h"
+
+#include "arm-common/kvm-cpu-arch.h"
+
+#define ARM_VCPU_FEATURE_FLAGS(kvm, cpuid) { \
+ [0] = (!!(cpuid) << KVM_ARM_VCPU_POWER_OFF), \
+}
+
+#define ARM_MPIDR_HWID_BITMASK 0xFFFFFF
+#define ARM_CPU_ID 0, 0, 0
+#define ARM_CPU_ID_MPIDR 5
+
+static inline void kvm_cpu__select_features(struct kvm *kvm,
+ struct kvm_vcpu_init *init) { }
+static inline int kvm_cpu__configure_features(struct kvm_cpu *vcpu)
+{
+ return 0;
+}
+
+#endif /* KVM__KVM_CPU_ARCH_H */
diff --git a/kvmtool/arm/aarch32/kvm-cpu.c b/kvmtool/arm/aarch32/kvm-cpu.c
new file mode 100644
index 0000000..95fb1da
--- /dev/null
+++ b/kvmtool/arm/aarch32/kvm-cpu.c
@@ -0,0 +1,132 @@
+#include "kvm/kvm-cpu.h"
+#include "kvm/kvm.h"
+#include "kvm/virtio.h"
+
+#include <asm/ptrace.h>
+
+#define ARM_CORE_REG(x) (KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | \
+ KVM_REG_ARM_CORE_REG(x))
+
+unsigned long kvm_cpu__get_vcpu_mpidr(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ u32 mpidr;
+
+ reg.id = ARM_CP15_REG32(ARM_CPU_ID, ARM_CPU_ID_MPIDR);
+ reg.addr = (u64)(unsigned long)&mpidr;
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (get_mpidr vcpu%ld", vcpu->cpu_id);
+
+ return mpidr;
+}
+
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_one_reg reg;
+ u32 data;
+
+ /* Who said future-proofing was a good idea? */
+ reg.addr = (u64)(unsigned long)&data;
+
+ /* cpsr = IRQs/FIQs masked */
+ data = PSR_I_BIT | PSR_F_BIT | SVC_MODE;
+ reg.id = ARM_CORE_REG(usr_regs.ARM_cpsr);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (cpsr)");
+
+ /* Secondary cores are stopped awaiting PSCI wakeup */
+ if (vcpu->cpu_id != 0)
+ return;
+
+ /* r0 = 0 */
+ data = 0;
+ reg.id = ARM_CORE_REG(usr_regs.ARM_r0);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (r0)");
+
+ /* r1 = machine type (-1) */
+ data = -1;
+ reg.id = ARM_CORE_REG(usr_regs.ARM_r1);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (r1)");
+
+ /* r2 = physical address of the device tree blob */
+ data = kvm->arch.dtb_guest_start;
+ reg.id = ARM_CORE_REG(usr_regs.ARM_r2);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (r2)");
+
+ /* pc = start of kernel image */
+ data = kvm->arch.kern_guest_start;
+ reg.id = ARM_CORE_REG(usr_regs.ARM_pc);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (pc)");
+}
+
+int kvm_cpu__get_endianness(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ u32 data;
+
+ reg.id = ARM_CORE_REG(usr_regs.ARM_cpsr);
+ reg.addr = (u64)(unsigned long)&data;
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (cpsr)");
+
+ return (data & PSR_E_BIT) ? VIRTIO_ENDIAN_BE : VIRTIO_ENDIAN_LE;
+}
+
+void kvm_cpu__show_code(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ u32 data;
+ int debug_fd = kvm_cpu__get_debug_fd();
+
+ reg.addr = (u64)(unsigned long)&data;
+
+ dprintf(debug_fd, "\n*pc:\n");
+ reg.id = ARM_CORE_REG(usr_regs.ARM_pc);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (show_code @ PC)");
+
+ kvm__dump_mem(vcpu->kvm, data, 32, debug_fd);
+
+ dprintf(debug_fd, "\n*lr (svc):\n");
+ reg.id = ARM_CORE_REG(svc_regs[1]);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (show_code @ LR_svc)");
+ data &= ~0x1;
+
+ kvm__dump_mem(vcpu->kvm, data, 32, debug_fd);
+}
+
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ u32 data;
+ int debug_fd = kvm_cpu__get_debug_fd();
+
+ reg.addr = (u64)(unsigned long)&data;
+ dprintf(debug_fd, "\n Registers:\n");
+
+ reg.id = ARM_CORE_REG(usr_regs.ARM_pc);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (pc)");
+ dprintf(debug_fd, " PC: 0x%x\n", data);
+
+ reg.id = ARM_CORE_REG(usr_regs.ARM_cpsr);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (cpsr)");
+ dprintf(debug_fd, " CPSR: 0x%x\n", data);
+
+ reg.id = ARM_CORE_REG(svc_regs[0]);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (SP_svc)");
+ dprintf(debug_fd, " SP_svc: 0x%x\n", data);
+
+ reg.id = ARM_CORE_REG(svc_regs[1]);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (LR_svc)");
+ dprintf(debug_fd, " LR_svc: 0x%x\n", data);
+}
diff --git a/kvmtool/arm/aarch64/arm-cpu.c b/kvmtool/arm/aarch64/arm-cpu.c
new file mode 100644
index 0000000..d7572b7
--- /dev/null
+++ b/kvmtool/arm/aarch64/arm-cpu.c
@@ -0,0 +1,72 @@
+#include "kvm/fdt.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+
+#include "arm-common/gic.h"
+#include "arm-common/timer.h"
+#include "arm-common/pmu.h"
+
+#include <linux/byteorder.h>
+#include <linux/types.h>
+
+static void generate_fdt_nodes(void *fdt, struct kvm *kvm)
+{
+ int timer_interrupts[4] = {13, 14, 11, 10};
+
+ gic__generate_fdt_nodes(fdt, kvm->cfg.arch.irqchip);
+ timer__generate_fdt_nodes(fdt, kvm, timer_interrupts);
+ pmu__generate_fdt_nodes(fdt, kvm);
+}
+
+static int arm_cpu__vcpu_init(struct kvm_cpu *vcpu)
+{
+ vcpu->generate_fdt_nodes = generate_fdt_nodes;
+ return 0;
+}
+
+static struct kvm_arm_target target_generic_v8 = {
+ .id = UINT_MAX,
+ .compatible = "arm,arm-v8",
+ .init = arm_cpu__vcpu_init,
+};
+
+static struct kvm_arm_target target_aem_v8 = {
+ .id = KVM_ARM_TARGET_AEM_V8,
+ .compatible = "arm,arm-v8",
+ .init = arm_cpu__vcpu_init,
+};
+
+static struct kvm_arm_target target_foundation_v8 = {
+ .id = KVM_ARM_TARGET_FOUNDATION_V8,
+ .compatible = "arm,arm-v8",
+ .init = arm_cpu__vcpu_init,
+};
+
+static struct kvm_arm_target target_cortex_a57 = {
+ .id = KVM_ARM_TARGET_CORTEX_A57,
+ .compatible = "arm,cortex-a57",
+ .init = arm_cpu__vcpu_init,
+};
+
+/*
+ * We really don't need to register a target for every
+ * new CPU. The target for Potenza CPU is only registered
+ * to enable compatibility with older host kernels.
+ */
+static struct kvm_arm_target target_potenza = {
+ .id = KVM_ARM_TARGET_XGENE_POTENZA,
+ .compatible = "arm,arm-v8",
+ .init = arm_cpu__vcpu_init,
+};
+
+static int arm_cpu__core_init(struct kvm *kvm)
+{
+ kvm_cpu__set_kvm_arm_generic_target(&target_generic_v8);
+
+ return (kvm_cpu__register_kvm_arm_target(&target_aem_v8) ||
+ kvm_cpu__register_kvm_arm_target(&target_foundation_v8) ||
+ kvm_cpu__register_kvm_arm_target(&target_cortex_a57) ||
+ kvm_cpu__register_kvm_arm_target(&target_potenza));
+}
+core_init(arm_cpu__core_init);
diff --git a/kvmtool/arm/aarch64/include/asm/image.h b/kvmtool/arm/aarch64/include/asm/image.h
new file mode 100644
index 0000000..c2b1321
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/asm/image.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_IMAGE_H
+#define __ASM_IMAGE_H
+
+#define ARM64_IMAGE_MAGIC "ARM\x64"
+
+#define ARM64_IMAGE_FLAG_BE_SHIFT 0
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT (ARM64_IMAGE_FLAG_BE_SHIFT + 1)
+#define ARM64_IMAGE_FLAG_PHYS_BASE_SHIFT \
+ (ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT + 2)
+#define ARM64_IMAGE_FLAG_BE_MASK 0x1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_MASK 0x3
+#define ARM64_IMAGE_FLAG_PHYS_BASE_MASK 0x1
+
+#define ARM64_IMAGE_FLAG_LE 0
+#define ARM64_IMAGE_FLAG_BE 1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_4K 1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_16K 2
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_64K 3
+#define ARM64_IMAGE_FLAG_PHYS_BASE 1
+
+#ifndef __ASSEMBLY__
+
+#define arm64_image_flag_field(flags, field) \
+ (((flags) >> field##_SHIFT) & field##_MASK)
+
+/*
+ * struct arm64_image_header - arm64 kernel image header
+ * See Documentation/arm64/booting.rst for details
+ *
+ * @code0: Executable code, or
+ * @mz_header alternatively used for part of MZ header
+ * @code1: Executable code
+ * @text_offset: Image load offset
+ * @image_size: Effective Image size
+ * @flags: kernel flags
+ * @reserved: reserved
+ * @magic: Magic number
+ * @reserved5: reserved, or
+ * @pe_header: alternatively used for PE COFF offset
+ */
+
+struct arm64_image_header {
+ __le32 code0;
+ __le32 code1;
+ __le64 text_offset;
+ __le64 image_size;
+ __le64 flags;
+ __le64 res2;
+ __le64 res3;
+ __le64 res4;
+ __le32 magic;
+ __le32 res5;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_IMAGE_H */
diff --git a/kvmtool/arm/aarch64/include/asm/kvm.h b/kvmtool/arm/aarch64/include/asm/kvm.h
new file mode 100644
index 0000000..9a50771
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/asm/kvm.h
@@ -0,0 +1,372 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012,2013 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * Derived from arch/arm/include/uapi/asm/kvm.h:
+ * Copyright (C) 2012 - Virtual Open Systems and Columbia University
+ * Author: Christoffer Dall <c.dall@virtualopensystems.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KVM_H__
+#define __ARM_KVM_H__
+
+#define KVM_SPSR_EL1 0
+#define KVM_SPSR_SVC KVM_SPSR_EL1
+#define KVM_SPSR_ABT 1
+#define KVM_SPSR_UND 2
+#define KVM_SPSR_IRQ 3
+#define KVM_SPSR_FIQ 4
+#define KVM_NR_SPSR 5
+
+#ifndef __ASSEMBLY__
+#include <linux/psci.h>
+#include <linux/types.h>
+#include <asm/ptrace.h>
+#include <asm/sve_context.h>
+
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
+#define __KVM_HAVE_VCPU_EVENTS
+
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
+#define KVM_REG_SIZE(id) \
+ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+struct kvm_regs {
+ struct user_pt_regs regs; /* sp = sp_el0 */
+
+ __u64 sp_el1;
+ __u64 elr_el1;
+
+ __u64 spsr[KVM_NR_SPSR];
+
+ struct user_fpsimd_state fp_regs;
+};
+
+/*
+ * Supported CPU Targets - Adding a new target type is not recommended,
+ * unless there are some special registers not supported by the
+ * genericv8 syreg table.
+ */
+#define KVM_ARM_TARGET_AEM_V8 0
+#define KVM_ARM_TARGET_FOUNDATION_V8 1
+#define KVM_ARM_TARGET_CORTEX_A57 2
+#define KVM_ARM_TARGET_XGENE_POTENZA 3
+#define KVM_ARM_TARGET_CORTEX_A53 4
+/* Generic ARM v8 target */
+#define KVM_ARM_TARGET_GENERIC_V8 5
+
+#define KVM_ARM_NUM_TARGETS 6
+
+/* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
+#define KVM_ARM_DEVICE_TYPE_SHIFT 0
+#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_ID_SHIFT 16
+#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+
+/* Supported device IDs */
+#define KVM_ARM_DEVICE_VGIC_V2 0
+
+/* Supported VGIC address types */
+#define KVM_VGIC_V2_ADDR_TYPE_DIST 0
+#define KVM_VGIC_V2_ADDR_TYPE_CPU 1
+
+#define KVM_VGIC_V2_DIST_SIZE 0x1000
+#define KVM_VGIC_V2_CPU_SIZE 0x2000
+
+/* Supported VGICv3 address types */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
+#define KVM_VGIC_ITS_ADDR_TYPE 4
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5
+
+#define KVM_VGIC_V3_DIST_SIZE SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
+
+#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
+#define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */
+#define KVM_ARM_VCPU_PSCI_0_2 2 /* CPU uses PSCI v0.2 */
+#define KVM_ARM_VCPU_PMU_V3 3 /* Support guest PMUv3 */
+#define KVM_ARM_VCPU_SVE 4 /* enable SVE for this CPU */
+#define KVM_ARM_VCPU_PTRAUTH_ADDRESS 5 /* VCPU uses address authentication */
+#define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */
+
+struct kvm_vcpu_init {
+ __u32 target;
+ __u32 features[7];
+};
+
+struct kvm_sregs {
+};
+
+struct kvm_fpu {
+};
+
+/*
+ * See v8 ARM ARM D7.3: Debug Registers
+ *
+ * The architectural limit is 16 debug registers of each type although
+ * in practice there are usually less (see ID_AA64DFR0_EL1).
+ *
+ * Although the control registers are architecturally defined as 32
+ * bits wide we use a 64 bit structure here to keep parity with
+ * KVM_GET/SET_ONE_REG behaviour which treats all system registers as
+ * 64 bit values. It also allows for the possibility of the
+ * architecture expanding the control registers without having to
+ * change the userspace ABI.
+ */
+#define KVM_ARM_MAX_DBG_REGS 16
+struct kvm_guest_debug_arch {
+ __u64 dbg_bcr[KVM_ARM_MAX_DBG_REGS];
+ __u64 dbg_bvr[KVM_ARM_MAX_DBG_REGS];
+ __u64 dbg_wcr[KVM_ARM_MAX_DBG_REGS];
+ __u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS];
+};
+
+struct kvm_debug_exit_arch {
+ __u32 hsr;
+ __u64 far; /* used for watchpoints */
+};
+
+/*
+ * Architecture specific defines for kvm_guest_debug->control
+ */
+
+#define KVM_GUESTDBG_USE_SW_BP (1 << 16)
+#define KVM_GUESTDBG_USE_HW (1 << 17)
+
+struct kvm_sync_regs {
+ /* Used with KVM_CAP_ARM_USER_IRQ */
+ __u64 device_irq_level;
+};
+
+struct kvm_arch_memory_slot {
+};
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+ struct {
+ __u8 serror_pending;
+ __u8 serror_has_esr;
+ /* Align it to 8 bytes */
+ __u8 pad[6];
+ __u64 serror_esr;
+ } exception;
+ __u32 reserved[12];
+};
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000
+#define KVM_REG_ARM_COPROC_SHIFT 16
+
+/* Normal registers are mapped as coprocessor 16. */
+#define KVM_REG_ARM_CORE (0x0010 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_CORE_REG(name) (offsetof(struct kvm_regs, name) / sizeof(__u32))
+
+/* Some registers need more space to represent values. */
+#define KVM_REG_ARM_DEMUX (0x0011 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_DEMUX_ID_MASK 0x000000000000FF00
+#define KVM_REG_ARM_DEMUX_ID_SHIFT 8
+#define KVM_REG_ARM_DEMUX_ID_CCSIDR (0x00 << KVM_REG_ARM_DEMUX_ID_SHIFT)
+#define KVM_REG_ARM_DEMUX_VAL_MASK 0x00000000000000FF
+#define KVM_REG_ARM_DEMUX_VAL_SHIFT 0
+
+/* AArch64 system registers */
+#define KVM_REG_ARM64_SYSREG (0x0013 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM64_SYSREG_OP0_MASK 0x000000000000c000
+#define KVM_REG_ARM64_SYSREG_OP0_SHIFT 14
+#define KVM_REG_ARM64_SYSREG_OP1_MASK 0x0000000000003800
+#define KVM_REG_ARM64_SYSREG_OP1_SHIFT 11
+#define KVM_REG_ARM64_SYSREG_CRN_MASK 0x0000000000000780
+#define KVM_REG_ARM64_SYSREG_CRN_SHIFT 7
+#define KVM_REG_ARM64_SYSREG_CRM_MASK 0x0000000000000078
+#define KVM_REG_ARM64_SYSREG_CRM_SHIFT 3
+#define KVM_REG_ARM64_SYSREG_OP2_MASK 0x0000000000000007
+#define KVM_REG_ARM64_SYSREG_OP2_SHIFT 0
+
+#define ARM64_SYS_REG_SHIFT_MASK(x,n) \
+ (((x) << KVM_REG_ARM64_SYSREG_ ## n ## _SHIFT) & \
+ KVM_REG_ARM64_SYSREG_ ## n ## _MASK)
+
+#define __ARM64_SYS_REG(op0,op1,crn,crm,op2) \
+ (KVM_REG_ARM64 | KVM_REG_ARM64_SYSREG | \
+ ARM64_SYS_REG_SHIFT_MASK(op0, OP0) | \
+ ARM64_SYS_REG_SHIFT_MASK(op1, OP1) | \
+ ARM64_SYS_REG_SHIFT_MASK(crn, CRN) | \
+ ARM64_SYS_REG_SHIFT_MASK(crm, CRM) | \
+ ARM64_SYS_REG_SHIFT_MASK(op2, OP2))
+
+#define ARM64_SYS_REG(...) (__ARM64_SYS_REG(__VA_ARGS__) | KVM_REG_SIZE_U64)
+
+/* Physical Timer EL0 Registers */
+#define KVM_REG_ARM_PTIMER_CTL ARM64_SYS_REG(3, 3, 14, 2, 1)
+#define KVM_REG_ARM_PTIMER_CVAL ARM64_SYS_REG(3, 3, 14, 2, 2)
+#define KVM_REG_ARM_PTIMER_CNT ARM64_SYS_REG(3, 3, 14, 0, 1)
+
+/* EL0 Virtual Timer Registers */
+#define KVM_REG_ARM_TIMER_CTL ARM64_SYS_REG(3, 3, 14, 3, 1)
+#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
+#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
+
+/* SVE registers */
+#define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT)
+
+/* Z- and P-regs occupy blocks at the following offsets within this range: */
+#define KVM_REG_ARM64_SVE_ZREG_BASE 0
+#define KVM_REG_ARM64_SVE_PREG_BASE 0x400
+#define KVM_REG_ARM64_SVE_FFR_BASE 0x600
+
+#define KVM_ARM64_SVE_NUM_ZREGS __SVE_NUM_ZREGS
+#define KVM_ARM64_SVE_NUM_PREGS __SVE_NUM_PREGS
+
+#define KVM_ARM64_SVE_MAX_SLICES 32
+
+#define KVM_REG_ARM64_SVE_ZREG(n, i) \
+ (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_ZREG_BASE | \
+ KVM_REG_SIZE_U2048 | \
+ (((n) & (KVM_ARM64_SVE_NUM_ZREGS - 1)) << 5) | \
+ ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_REG_ARM64_SVE_PREG(n, i) \
+ (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_PREG_BASE | \
+ KVM_REG_SIZE_U256 | \
+ (((n) & (KVM_ARM64_SVE_NUM_PREGS - 1)) << 5) | \
+ ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_REG_ARM64_SVE_FFR(i) \
+ (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_FFR_BASE | \
+ KVM_REG_SIZE_U256 | \
+ ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+/*
+ * Register values for KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() and
+ * KVM_REG_ARM64_SVE_FFR() are represented in memory in an endianness-
+ * invariant layout which differs from the layout used for the FPSIMD
+ * V-registers on big-endian systems: see sigcontext.h for more explanation.
+ */
+
+#define KVM_ARM64_SVE_VQ_MIN __SVE_VQ_MIN
+#define KVM_ARM64_SVE_VQ_MAX __SVE_VQ_MAX
+
+/* Vector lengths pseudo-register: */
+#define KVM_REG_ARM64_SVE_VLS (KVM_REG_ARM64 | KVM_REG_ARM64_SVE | \
+ KVM_REG_SIZE_U512 | 0xffff)
+#define KVM_ARM64_SVE_VLS_WORDS \
+ ((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1)
+
+/* Device Control API: ARM VGIC */
+#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
+#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
+#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2
+#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32
+#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+ (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
+#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0
+#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3
+#define KVM_DEV_ARM_VGIC_GRP_CTRL 4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
+#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
+#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
+ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
+#define VGIC_LEVEL_INFO_LINE_LEVEL 0
+
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
+#define KVM_DEV_ARM_ITS_CTRL_RESET 4
+
+/* Device Control API on vcpu fd */
+#define KVM_ARM_VCPU_PMU_V3_CTRL 0
+#define KVM_ARM_VCPU_PMU_V3_IRQ 0
+#define KVM_ARM_VCPU_PMU_V3_INIT 1
+#define KVM_ARM_VCPU_TIMER_CTRL 1
+#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
+#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_TYPE_SHIFT 24
+#define KVM_ARM_IRQ_TYPE_MASK 0xff
+#define KVM_ARM_IRQ_VCPU_SHIFT 16
+#define KVM_ARM_IRQ_VCPU_MASK 0xff
+#define KVM_ARM_IRQ_NUM_SHIFT 0
+#define KVM_ARM_IRQ_NUM_MASK 0xffff
+
+/* irq_type field */
+#define KVM_ARM_IRQ_TYPE_CPU 0
+#define KVM_ARM_IRQ_TYPE_SPI 1
+#define KVM_ARM_IRQ_TYPE_PPI 2
+
+/* out-of-kernel GIC cpu interrupt injection irq_number field */
+#define KVM_ARM_IRQ_CPU_IRQ 0
+#define KVM_ARM_IRQ_CPU_FIQ 1
+
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
+#define KVM_ARM_IRQ_GIC_MAX 127
+#endif
+
+/* One single KVM irqchip, ie. the VGIC */
+#define KVM_NR_IRQCHIPS 1
+
+/* PSCI interface */
+#define KVM_PSCI_FN_BASE 0x95c1ba5e
+#define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n))
+
+#define KVM_PSCI_FN_CPU_SUSPEND KVM_PSCI_FN(0)
+#define KVM_PSCI_FN_CPU_OFF KVM_PSCI_FN(1)
+#define KVM_PSCI_FN_CPU_ON KVM_PSCI_FN(2)
+#define KVM_PSCI_FN_MIGRATE KVM_PSCI_FN(3)
+
+#define KVM_PSCI_RET_SUCCESS PSCI_RET_SUCCESS
+#define KVM_PSCI_RET_NI PSCI_RET_NOT_SUPPORTED
+#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS
+#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED
+
+#endif
+
+#endif /* __ARM_KVM_H__ */
diff --git a/kvmtool/arm/aarch64/include/asm/sve_context.h b/kvmtool/arm/aarch64/include/asm/sve_context.h
new file mode 100644
index 0000000..754ab75
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/asm/sve_context.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (C) 2017-2018 ARM Limited */
+
+/*
+ * For use by other UAPI headers only.
+ * Do not make direct use of header or its definitions.
+ */
+
+#ifndef _UAPI__ASM_SVE_CONTEXT_H
+#define _UAPI__ASM_SVE_CONTEXT_H
+
+#include <linux/types.h>
+
+#define __SVE_VQ_BYTES 16 /* number of bytes per quadword */
+
+#define __SVE_VQ_MIN 1
+#define __SVE_VQ_MAX 512
+
+#define __SVE_VL_MIN (__SVE_VQ_MIN * __SVE_VQ_BYTES)
+#define __SVE_VL_MAX (__SVE_VQ_MAX * __SVE_VQ_BYTES)
+
+#define __SVE_NUM_ZREGS 32
+#define __SVE_NUM_PREGS 16
+
+#define __sve_vl_valid(vl) \
+ ((vl) % __SVE_VQ_BYTES == 0 && \
+ (vl) >= __SVE_VL_MIN && \
+ (vl) <= __SVE_VL_MAX)
+
+#define __sve_vq_from_vl(vl) ((vl) / __SVE_VQ_BYTES)
+#define __sve_vl_from_vq(vq) ((vq) * __SVE_VQ_BYTES)
+
+#define __SVE_ZREG_SIZE(vq) ((__u32)(vq) * __SVE_VQ_BYTES)
+#define __SVE_PREG_SIZE(vq) ((__u32)(vq) * (__SVE_VQ_BYTES / 8))
+#define __SVE_FFR_SIZE(vq) __SVE_PREG_SIZE(vq)
+
+#define __SVE_ZREGS_OFFSET 0
+#define __SVE_ZREG_OFFSET(vq, n) \
+ (__SVE_ZREGS_OFFSET + __SVE_ZREG_SIZE(vq) * (n))
+#define __SVE_ZREGS_SIZE(vq) \
+ (__SVE_ZREG_OFFSET(vq, __SVE_NUM_ZREGS) - __SVE_ZREGS_OFFSET)
+
+#define __SVE_PREGS_OFFSET(vq) \
+ (__SVE_ZREGS_OFFSET + __SVE_ZREGS_SIZE(vq))
+#define __SVE_PREG_OFFSET(vq, n) \
+ (__SVE_PREGS_OFFSET(vq) + __SVE_PREG_SIZE(vq) * (n))
+#define __SVE_PREGS_SIZE(vq) \
+ (__SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - __SVE_PREGS_OFFSET(vq))
+
+#define __SVE_FFR_OFFSET(vq) \
+ (__SVE_PREGS_OFFSET(vq) + __SVE_PREGS_SIZE(vq))
+
+#endif /* ! _UAPI__ASM_SVE_CONTEXT_H */
diff --git a/kvmtool/arm/aarch64/include/kvm/barrier.h b/kvmtool/arm/aarch64/include/kvm/barrier.h
new file mode 100644
index 0000000..97ab252
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/kvm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef KVM__KVM_BARRIER_H
+#define KVM__KVM_BARRIER_H
+
+#define mb() asm volatile ("dmb ish" : : : "memory")
+#define rmb() asm volatile ("dmb ishld" : : : "memory")
+#define wmb() asm volatile ("dmb ishst" : : : "memory")
+
+#endif /* KVM__KVM_BARRIER_H */
diff --git a/kvmtool/arm/aarch64/include/kvm/fdt-arch.h b/kvmtool/arm/aarch64/include/kvm/fdt-arch.h
new file mode 100644
index 0000000..e448bf1
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/kvm/fdt-arch.h
@@ -0,0 +1,6 @@
+#ifndef KVM__KVM_FDT_H
+#define KVM__KVM_FDT_H
+
+#include "arm-common/fdt-arch.h"
+
+#endif /* KVM__KVM_FDT_H */
diff --git a/kvmtool/arm/aarch64/include/kvm/kvm-arch.h b/kvmtool/arm/aarch64/include/kvm/kvm-arch.h
new file mode 100644
index 0000000..55ef8ed
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/kvm/kvm-arch.h
@@ -0,0 +1,13 @@
+#ifndef KVM__KVM_ARCH_H
+#define KVM__KVM_ARCH_H
+
+struct kvm;
+unsigned long long kvm__arch_get_kern_offset(struct kvm *kvm, int fd);
+
+#define ARM_MAX_MEMORY(kvm) ((kvm)->cfg.arch.aarch32_guest ? \
+ ARM_LOMAP_MAX_MEMORY : \
+ ARM_HIMAP_MAX_MEMORY)
+
+#include "arm-common/kvm-arch.h"
+
+#endif /* KVM__KVM_ARCH_H */
diff --git a/kvmtool/arm/aarch64/include/kvm/kvm-config-arch.h b/kvmtool/arm/aarch64/include/kvm/kvm-config-arch.h
new file mode 100644
index 0000000..04be43d
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/kvm/kvm-config-arch.h
@@ -0,0 +1,15 @@
+#ifndef KVM__KVM_CONFIG_ARCH_H
+#define KVM__KVM_CONFIG_ARCH_H
+
+#define ARM_OPT_ARCH_RUN(cfg) \
+ OPT_BOOLEAN('\0', "aarch32", &(cfg)->aarch32_guest, \
+ "Run AArch32 guest"), \
+ OPT_BOOLEAN('\0', "pmu", &(cfg)->has_pmuv3, \
+ "Create PMUv3 device"), \
+ OPT_U64('\0', "kaslr-seed", &(cfg)->kaslr_seed, \
+ "Specify random seed for Kernel Address Space " \
+ "Layout Randomization (KASLR)"),
+
+#include "arm-common/kvm-config-arch.h"
+
+#endif /* KVM__KVM_CONFIG_ARCH_H */
diff --git a/kvmtool/arm/aarch64/include/kvm/kvm-cpu-arch.h b/kvmtool/arm/aarch64/include/kvm/kvm-cpu-arch.h
new file mode 100644
index 0000000..8dfb82e
--- /dev/null
+++ b/kvmtool/arm/aarch64/include/kvm/kvm-cpu-arch.h
@@ -0,0 +1,23 @@
+#ifndef KVM__KVM_CPU_ARCH_H
+#define KVM__KVM_CPU_ARCH_H
+
+#include "kvm/kvm.h"
+
+#include "arm-common/kvm-cpu-arch.h"
+
+#define ARM_VCPU_FEATURE_FLAGS(kvm, cpuid) { \
+ [0] = ((!!(cpuid) << KVM_ARM_VCPU_POWER_OFF) | \
+ (!!(kvm)->cfg.arch.aarch32_guest << KVM_ARM_VCPU_EL1_32BIT) | \
+ (!!(kvm)->cfg.arch.has_pmuv3 << KVM_ARM_VCPU_PMU_V3)) \
+}
+
+#define ARM_MPIDR_HWID_BITMASK 0xFF00FFFFFFUL
+#define ARM_CPU_ID 3, 0, 0, 0
+#define ARM_CPU_ID_MPIDR 5
+#define ARM_CPU_CTRL 3, 0, 1, 0
+#define ARM_CPU_CTRL_SCTLR_EL1 0
+
+void kvm_cpu__select_features(struct kvm *kvm, struct kvm_vcpu_init *init);
+int kvm_cpu__configure_features(struct kvm_cpu *vcpu);
+
+#endif /* KVM__KVM_CPU_ARCH_H */
diff --git a/kvmtool/arm/aarch64/kvm-cpu.c b/kvmtool/arm/aarch64/kvm-cpu.c
new file mode 100644
index 0000000..9f3e858
--- /dev/null
+++ b/kvmtool/arm/aarch64/kvm-cpu.c
@@ -0,0 +1,256 @@
+#include "kvm/kvm-cpu.h"
+#include "kvm/kvm.h"
+#include "kvm/virtio.h"
+
+#include <asm/ptrace.h>
+
+#define COMPAT_PSR_F_BIT 0x00000040
+#define COMPAT_PSR_I_BIT 0x00000080
+#define COMPAT_PSR_E_BIT 0x00000200
+#define COMPAT_PSR_MODE_SVC 0x00000013
+
+#define SCTLR_EL1_E0E_MASK (1 << 24)
+#define SCTLR_EL1_EE_MASK (1 << 25)
+
+static __u64 __core_reg_id(__u64 offset)
+{
+ __u64 id = KVM_REG_ARM64 | KVM_REG_ARM_CORE | offset;
+
+ if (offset < KVM_REG_ARM_CORE_REG(fp_regs))
+ id |= KVM_REG_SIZE_U64;
+ else if (offset < KVM_REG_ARM_CORE_REG(fp_regs.fpsr))
+ id |= KVM_REG_SIZE_U128;
+ else
+ id |= KVM_REG_SIZE_U32;
+
+ return id;
+}
+
+#define ARM64_CORE_REG(x) __core_reg_id(KVM_REG_ARM_CORE_REG(x))
+
+unsigned long kvm_cpu__get_vcpu_mpidr(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ u64 mpidr;
+
+ reg.id = ARM64_SYS_REG(ARM_CPU_ID, ARM_CPU_ID_MPIDR);
+ reg.addr = (u64)&mpidr;
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (get_mpidr vcpu%ld", vcpu->cpu_id);
+
+ return mpidr;
+}
+
+static void reset_vcpu_aarch32(struct kvm_cpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_one_reg reg;
+ u64 data;
+
+ reg.addr = (u64)&data;
+
+ /* pstate = all interrupts masked */
+ data = COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT | COMPAT_PSR_MODE_SVC;
+ reg.id = ARM64_CORE_REG(regs.pstate);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (spsr[EL1])");
+
+ /* Secondary cores are stopped awaiting PSCI wakeup */
+ if (vcpu->cpu_id != 0)
+ return;
+
+ /* r0 = 0 */
+ data = 0;
+ reg.id = ARM64_CORE_REG(regs.regs[0]);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (r0)");
+
+ /* r1 = machine type (-1) */
+ data = -1;
+ reg.id = ARM64_CORE_REG(regs.regs[1]);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (r1)");
+
+ /* r2 = physical address of the device tree blob */
+ data = kvm->arch.dtb_guest_start;
+ reg.id = ARM64_CORE_REG(regs.regs[2]);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (r2)");
+
+ /* pc = start of kernel image */
+ data = kvm->arch.kern_guest_start;
+ reg.id = ARM64_CORE_REG(regs.pc);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (pc)");
+}
+
+static void reset_vcpu_aarch64(struct kvm_cpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_one_reg reg;
+ u64 data;
+
+ reg.addr = (u64)&data;
+
+ /* pstate = all interrupts masked */
+ data = PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL1h;
+ reg.id = ARM64_CORE_REG(regs.pstate);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (spsr[EL1])");
+
+ /* x1...x3 = 0 */
+ data = 0;
+ reg.id = ARM64_CORE_REG(regs.regs[1]);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (x1)");
+
+ reg.id = ARM64_CORE_REG(regs.regs[2]);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (x2)");
+
+ reg.id = ARM64_CORE_REG(regs.regs[3]);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (x3)");
+
+ /* Secondary cores are stopped awaiting PSCI wakeup */
+ if (vcpu->cpu_id == 0) {
+ /* x0 = physical address of the device tree blob */
+ data = kvm->arch.dtb_guest_start;
+ reg.id = ARM64_CORE_REG(regs.regs[0]);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (x0)");
+
+ /* pc = start of kernel image */
+ data = kvm->arch.kern_guest_start;
+ reg.id = ARM64_CORE_REG(regs.pc);
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die_perror("KVM_SET_ONE_REG failed (pc)");
+ }
+}
+
+void kvm_cpu__select_features(struct kvm *kvm, struct kvm_vcpu_init *init)
+{
+ /* Enable pointer authentication if available */
+ if (kvm__supports_extension(kvm, KVM_CAP_ARM_PTRAUTH_ADDRESS) &&
+ kvm__supports_extension(kvm, KVM_CAP_ARM_PTRAUTH_GENERIC)) {
+ init->features[0] |= 1UL << KVM_ARM_VCPU_PTRAUTH_ADDRESS;
+ init->features[0] |= 1UL << KVM_ARM_VCPU_PTRAUTH_GENERIC;
+ }
+
+ /* Enable SVE if available */
+ if (kvm__supports_extension(kvm, KVM_CAP_ARM_SVE))
+ init->features[0] |= 1UL << KVM_ARM_VCPU_SVE;
+}
+
+int kvm_cpu__configure_features(struct kvm_cpu *vcpu)
+{
+ if (kvm__supports_extension(vcpu->kvm, KVM_CAP_ARM_SVE)) {
+ int feature = KVM_ARM_VCPU_SVE;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_ARM_VCPU_FINALIZE, &feature)) {
+ pr_err("KVM_ARM_VCPU_FINALIZE: %s", strerror(errno));
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu)
+{
+ if (vcpu->kvm->cfg.arch.aarch32_guest)
+ return reset_vcpu_aarch32(vcpu);
+ else
+ return reset_vcpu_aarch64(vcpu);
+}
+
+int kvm_cpu__get_endianness(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ u64 psr;
+ u64 sctlr;
+
+ /*
+ * Quoting the definition given by Peter Maydell:
+ *
+ * "Endianness of the CPU which does the virtio reset at the
+ * point when it does that reset"
+ *
+ * We first check for an AArch32 guest: its endianness can
+ * change when using SETEND, which affects the CPSR.E bit.
+ *
+ * If we're AArch64, use SCTLR_EL1.E0E if access comes from
+ * EL0, and SCTLR_EL1.EE if access comes from EL1.
+ */
+ reg.id = ARM64_CORE_REG(regs.pstate);
+ reg.addr = (u64)&psr;
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (spsr[EL1])");
+
+ if (psr & PSR_MODE32_BIT)
+ return (psr & COMPAT_PSR_E_BIT) ? VIRTIO_ENDIAN_BE : VIRTIO_ENDIAN_LE;
+
+ reg.id = ARM64_SYS_REG(ARM_CPU_CTRL, ARM_CPU_CTRL_SCTLR_EL1);
+ reg.addr = (u64)&sctlr;
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (SCTLR_EL1)");
+
+ if ((psr & PSR_MODE_MASK) == PSR_MODE_EL0t)
+ sctlr &= SCTLR_EL1_E0E_MASK;
+ else
+ sctlr &= SCTLR_EL1_EE_MASK;
+ return sctlr ? VIRTIO_ENDIAN_BE : VIRTIO_ENDIAN_LE;
+}
+
+void kvm_cpu__show_code(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ unsigned long data;
+ int debug_fd = kvm_cpu__get_debug_fd();
+
+ reg.addr = (u64)&data;
+
+ dprintf(debug_fd, "\n*pc:\n");
+ reg.id = ARM64_CORE_REG(regs.pc);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (show_code @ PC)");
+
+ kvm__dump_mem(vcpu->kvm, data, 32, debug_fd);
+
+ dprintf(debug_fd, "\n*lr:\n");
+ reg.id = ARM64_CORE_REG(regs.regs[30]);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (show_code @ LR)");
+
+ kvm__dump_mem(vcpu->kvm, data, 32, debug_fd);
+}
+
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu)
+{
+ struct kvm_one_reg reg;
+ unsigned long data;
+ int debug_fd = kvm_cpu__get_debug_fd();
+
+ reg.addr = (u64)&data;
+ dprintf(debug_fd, "\n Registers:\n");
+
+ reg.id = ARM64_CORE_REG(regs.pc);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (pc)");
+ dprintf(debug_fd, " PC: 0x%lx\n", data);
+
+ reg.id = ARM64_CORE_REG(regs.pstate);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (pstate)");
+ dprintf(debug_fd, " PSTATE: 0x%lx\n", data);
+
+ reg.id = ARM64_CORE_REG(sp_el1);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (sp_el1)");
+ dprintf(debug_fd, " SP_EL1: 0x%lx\n", data);
+
+ reg.id = ARM64_CORE_REG(regs.regs[30]);
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®) < 0)
+ die("KVM_GET_ONE_REG failed (lr)");
+ dprintf(debug_fd, " LR: 0x%lx\n", data);
+}
diff --git a/kvmtool/arm/aarch64/kvm.c b/kvmtool/arm/aarch64/kvm.c
new file mode 100644
index 0000000..49e1dd3
--- /dev/null
+++ b/kvmtool/arm/aarch64/kvm.c
@@ -0,0 +1,48 @@
+#include "kvm/kvm.h"
+
+#include <asm/image.h>
+
+#include <linux/byteorder.h>
+
+/*
+ * Return the TEXT_OFFSET value that the guest kernel expects. Note
+ * that pre-3.17 kernels expose this value using the native endianness
+ * instead of Little-Endian. BE kernels of this vintage may fail to
+ * boot. See Documentation/arm64/booting.rst in your local kernel tree.
+ */
+unsigned long long kvm__arch_get_kern_offset(struct kvm *kvm, int fd)
+{
+ struct arm64_image_header header;
+ off_t cur_offset;
+ ssize_t size;
+ const char *warn_str;
+
+ /* the 32bit kernel offset is a well known value */
+ if (kvm->cfg.arch.aarch32_guest)
+ return 0x8000;
+
+ cur_offset = lseek(fd, 0, SEEK_CUR);
+ if (cur_offset == (off_t)-1 ||
+ lseek(fd, 0, SEEK_SET) == (off_t)-1) {
+ warn_str = "Failed to seek in kernel image file";
+ goto fail;
+ }
+
+ size = xread(fd, &header, sizeof(header));
+ if (size < 0 || (size_t)size < sizeof(header))
+ die("Failed to read kernel image header");
+
+ lseek(fd, cur_offset, SEEK_SET);
+
+ if (memcmp(&header.magic, ARM64_IMAGE_MAGIC, sizeof(header.magic)))
+ pr_warning("Kernel image magic not matching");
+
+ if (le64_to_cpu(header.image_size))
+ return le64_to_cpu(header.text_offset);
+
+ warn_str = "Image size is 0";
+fail:
+ pr_warning("%s, assuming TEXT_OFFSET to be 0x80000", warn_str);
+ return 0x80000;
+}
+
diff --git a/kvmtool/arm/fdt.c b/kvmtool/arm/fdt.c
new file mode 100644
index 0000000..02091e9
--- /dev/null
+++ b/kvmtool/arm/fdt.c
@@ -0,0 +1,230 @@
+#include "kvm/devices.h"
+#include "kvm/fdt.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/virtio-mmio.h"
+
+#include "arm-common/gic.h"
+#include "arm-common/pci.h"
+
+#include <stdbool.h>
+
+#include <linux/byteorder.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+#include <linux/psci.h>
+
+static void dump_fdt(const char *dtb_file, void *fdt)
+{
+ int count, fd;
+
+ fd = open(dtb_file, O_CREAT | O_TRUNC | O_RDWR, 0666);
+ if (fd < 0)
+ die("Failed to write dtb to %s", dtb_file);
+
+ count = write(fd, fdt, FDT_MAX_SIZE);
+ if (count < 0)
+ die_perror("Failed to dump dtb");
+
+ pr_debug("Wrote %d bytes to dtb %s", count, dtb_file);
+ close(fd);
+}
+
+#define CPU_NAME_MAX_LEN 15
+static void generate_cpu_nodes(void *fdt, struct kvm *kvm)
+{
+ int cpu;
+
+ _FDT(fdt_begin_node(fdt, "cpus"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x1));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x0));
+
+ for (cpu = 0; cpu < kvm->nrcpus; ++cpu) {
+ char cpu_name[CPU_NAME_MAX_LEN];
+ struct kvm_cpu *vcpu = kvm->cpus[cpu];
+ unsigned long mpidr = kvm_cpu__get_vcpu_mpidr(vcpu);
+
+ mpidr &= ARM_MPIDR_HWID_BITMASK;
+ snprintf(cpu_name, CPU_NAME_MAX_LEN, "cpu@%lx", mpidr);
+
+ _FDT(fdt_begin_node(fdt, cpu_name));
+ _FDT(fdt_property_string(fdt, "device_type", "cpu"));
+ _FDT(fdt_property_string(fdt, "compatible", vcpu->cpu_compatible));
+
+ if (kvm->nrcpus > 1)
+ _FDT(fdt_property_string(fdt, "enable-method", "psci"));
+
+ _FDT(fdt_property_cell(fdt, "reg", mpidr));
+ _FDT(fdt_end_node(fdt));
+ }
+
+ _FDT(fdt_end_node(fdt));
+}
+
+static void generate_irq_prop(void *fdt, u8 irq, enum irq_type irq_type)
+{
+ u32 irq_prop[] = {
+ cpu_to_fdt32(GIC_FDT_IRQ_TYPE_SPI),
+ cpu_to_fdt32(irq - GIC_SPI_IRQ_BASE),
+ cpu_to_fdt32(irq_type)
+ };
+
+ _FDT(fdt_property(fdt, "interrupts", irq_prop, sizeof(irq_prop)));
+}
+
+struct psci_fns {
+ u32 cpu_suspend;
+ u32 cpu_off;
+ u32 cpu_on;
+ u32 migrate;
+};
+
+static struct psci_fns psci_0_1_fns = {
+ .cpu_suspend = KVM_PSCI_FN_CPU_SUSPEND,
+ .cpu_off = KVM_PSCI_FN_CPU_OFF,
+ .cpu_on = KVM_PSCI_FN_CPU_ON,
+ .migrate = KVM_PSCI_FN_MIGRATE,
+};
+
+static struct psci_fns psci_0_2_aarch32_fns = {
+ .cpu_suspend = PSCI_0_2_FN_CPU_SUSPEND,
+ .cpu_off = PSCI_0_2_FN_CPU_OFF,
+ .cpu_on = PSCI_0_2_FN_CPU_ON,
+ .migrate = PSCI_0_2_FN_MIGRATE,
+};
+
+static struct psci_fns psci_0_2_aarch64_fns = {
+ .cpu_suspend = PSCI_0_2_FN64_CPU_SUSPEND,
+ .cpu_off = PSCI_0_2_FN_CPU_OFF,
+ .cpu_on = PSCI_0_2_FN64_CPU_ON,
+ .migrate = PSCI_0_2_FN64_MIGRATE,
+};
+
+static int setup_fdt(struct kvm *kvm)
+{
+ struct device_header *dev_hdr;
+ u8 staging_fdt[FDT_MAX_SIZE];
+ u64 mem_reg_prop[] = {
+ cpu_to_fdt64(kvm->arch.memory_guest_start),
+ cpu_to_fdt64(kvm->ram_size),
+ };
+ struct psci_fns *fns;
+ void *fdt = staging_fdt;
+ void *fdt_dest = guest_flat_to_host(kvm,
+ kvm->arch.dtb_guest_start);
+ void (*generate_mmio_fdt_nodes)(void *, struct device_header *,
+ void (*)(void *, u8, enum irq_type));
+ void (*generate_cpu_peripheral_fdt_nodes)(void *, struct kvm *)
+ = kvm->cpus[0]->generate_fdt_nodes;
+
+ /* Create new tree without a reserve map */
+ _FDT(fdt_create(fdt, FDT_MAX_SIZE));
+ _FDT(fdt_finish_reservemap(fdt));
+
+ /* Header */
+ _FDT(fdt_begin_node(fdt, ""));
+ _FDT(fdt_property_cell(fdt, "interrupt-parent", PHANDLE_GIC));
+ _FDT(fdt_property_string(fdt, "compatible", "linux,dummy-virt"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x2));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x2));
+
+ /* /chosen */
+ _FDT(fdt_begin_node(fdt, "chosen"));
+
+ /* Pass on our amended command line to a Linux kernel only. */
+ if (kvm->cfg.firmware_filename) {
+ if (kvm->cfg.kernel_cmdline)
+ _FDT(fdt_property_string(fdt, "bootargs",
+ kvm->cfg.kernel_cmdline));
+ } else
+ _FDT(fdt_property_string(fdt, "bootargs",
+ kvm->cfg.real_cmdline));
+
+ _FDT(fdt_property_u64(fdt, "kaslr-seed", kvm->cfg.arch.kaslr_seed));
+ _FDT(fdt_property_string(fdt, "stdout-path", "serial0"));
+
+ /* Initrd */
+ if (kvm->arch.initrd_size != 0) {
+ u64 ird_st_prop = cpu_to_fdt64(kvm->arch.initrd_guest_start);
+ u64 ird_end_prop = cpu_to_fdt64(kvm->arch.initrd_guest_start +
+ kvm->arch.initrd_size);
+
+ _FDT(fdt_property(fdt, "linux,initrd-start",
+ &ird_st_prop, sizeof(ird_st_prop)));
+ _FDT(fdt_property(fdt, "linux,initrd-end",
+ &ird_end_prop, sizeof(ird_end_prop)));
+ }
+ _FDT(fdt_end_node(fdt));
+
+ /* Memory */
+ _FDT(fdt_begin_node(fdt, "memory"));
+ _FDT(fdt_property_string(fdt, "device_type", "memory"));
+ _FDT(fdt_property(fdt, "reg", mem_reg_prop, sizeof(mem_reg_prop)));
+ _FDT(fdt_end_node(fdt));
+
+ /* CPU and peripherals (interrupt controller, timers, etc) */
+ generate_cpu_nodes(fdt, kvm);
+ if (generate_cpu_peripheral_fdt_nodes)
+ generate_cpu_peripheral_fdt_nodes(fdt, kvm);
+
+ /* Virtio MMIO devices */
+ dev_hdr = device__first_dev(DEVICE_BUS_MMIO);
+ while (dev_hdr) {
+ generate_mmio_fdt_nodes = dev_hdr->data;
+ generate_mmio_fdt_nodes(fdt, dev_hdr, generate_irq_prop);
+ dev_hdr = device__next_dev(dev_hdr);
+ }
+
+ /* IOPORT devices (!) */
+ dev_hdr = device__first_dev(DEVICE_BUS_IOPORT);
+ while (dev_hdr) {
+ generate_mmio_fdt_nodes = dev_hdr->data;
+ generate_mmio_fdt_nodes(fdt, dev_hdr, generate_irq_prop);
+ dev_hdr = device__next_dev(dev_hdr);
+ }
+
+ /* PCI host controller */
+ pci__generate_fdt_nodes(fdt);
+
+ /* PSCI firmware */
+ _FDT(fdt_begin_node(fdt, "psci"));
+ if (kvm__supports_extension(kvm, KVM_CAP_ARM_PSCI_0_2)) {
+ const char compatible[] = "arm,psci-0.2\0arm,psci";
+ _FDT(fdt_property(fdt, "compatible",
+ compatible, sizeof(compatible)));
+ if (kvm->cfg.arch.aarch32_guest)
+ fns = &psci_0_2_aarch32_fns;
+ else
+ fns = &psci_0_2_aarch64_fns;
+ } else {
+ _FDT(fdt_property_string(fdt, "compatible", "arm,psci"));
+ fns = &psci_0_1_fns;
+ }
+ _FDT(fdt_property_string(fdt, "method", "hvc"));
+ _FDT(fdt_property_cell(fdt, "cpu_suspend", fns->cpu_suspend));
+ _FDT(fdt_property_cell(fdt, "cpu_off", fns->cpu_off));
+ _FDT(fdt_property_cell(fdt, "cpu_on", fns->cpu_on));
+ _FDT(fdt_property_cell(fdt, "migrate", fns->migrate));
+ _FDT(fdt_end_node(fdt));
+
+ if (fdt_stdout_path) {
+ _FDT(fdt_begin_node(fdt, "aliases"));
+ _FDT(fdt_property_string(fdt, "serial0", fdt_stdout_path));
+ _FDT(fdt_end_node(fdt));
+
+ free(fdt_stdout_path);
+ fdt_stdout_path = NULL;
+ }
+
+ /* Finalise. */
+ _FDT(fdt_end_node(fdt));
+ _FDT(fdt_finish(fdt));
+
+ _FDT(fdt_open_into(fdt, fdt_dest, FDT_MAX_SIZE));
+ _FDT(fdt_pack(fdt_dest));
+
+ if (kvm->cfg.arch.dump_dtb_filename)
+ dump_fdt(kvm->cfg.arch.dump_dtb_filename, fdt_dest);
+ return 0;
+}
+late_init(setup_fdt);
diff --git a/kvmtool/arm/gic.c b/kvmtool/arm/gic.c
new file mode 100644
index 0000000..26be4b4
--- /dev/null
+++ b/kvmtool/arm/gic.c
@@ -0,0 +1,464 @@
+#include "kvm/fdt.h"
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/virtio.h"
+
+#include "arm-common/gic.h"
+
+#include <linux/byteorder.h>
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+
+#define IRQCHIP_GIC 0
+
+static int gic_fd = -1;
+static u64 gic_redists_base;
+static u64 gic_redists_size;
+static u64 gic_msi_base;
+static u64 gic_msi_size = 0;
+static bool vgic_is_init = false;
+
+struct kvm_irqfd_line {
+ unsigned int gsi;
+ int trigger_fd;
+ int resample_fd;
+ struct list_head list;
+};
+
+static LIST_HEAD(irqfd_lines);
+
+int irqchip_parser(const struct option *opt, const char *arg, int unset)
+{
+ enum irqchip_type *type = opt->value;
+
+ if (!strcmp(arg, "gicv2")) {
+ *type = IRQCHIP_GICV2;
+ } else if (!strcmp(arg, "gicv2m")) {
+ *type = IRQCHIP_GICV2M;
+ } else if (!strcmp(arg, "gicv3")) {
+ *type = IRQCHIP_GICV3;
+ } else if (!strcmp(arg, "gicv3-its")) {
+ *type = IRQCHIP_GICV3_ITS;
+ } else {
+ pr_err("irqchip: unknown type \"%s\"\n", arg);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int irq__setup_irqfd_lines(struct kvm *kvm)
+{
+ int ret;
+ struct kvm_irqfd_line *line, *tmp;
+
+ list_for_each_entry_safe(line, tmp, &irqfd_lines, list) {
+ ret = irq__common_add_irqfd(kvm, line->gsi, line->trigger_fd,
+ line->resample_fd);
+ if (ret < 0) {
+ pr_err("Failed to register IRQFD");
+ return ret;
+ }
+
+ list_del(&line->list);
+ free(line);
+ }
+
+ return 0;
+}
+
+static int irq__routing_init(struct kvm *kvm)
+{
+ int r;
+ int irqlines = ALIGN(irq__get_nr_allocated_lines(), 32);
+
+ /*
+ * This describes the default routing that the kernel uses without
+ * any routing explicitly set up via KVM_SET_GSI_ROUTING. So we
+ * don't need to commit these setting right now. The first actual
+ * user (MSI routing) will engage these mappings then.
+ */
+ for (next_gsi = 0; next_gsi < irqlines; next_gsi++) {
+ r = irq__allocate_routing_entry();
+ if (r)
+ return r;
+
+ irq_routing->entries[irq_routing->nr++] =
+ (struct kvm_irq_routing_entry) {
+ .gsi = next_gsi,
+ .type = KVM_IRQ_ROUTING_IRQCHIP,
+ .u.irqchip.irqchip = IRQCHIP_GIC,
+ .u.irqchip.pin = next_gsi,
+ };
+ }
+
+ return 0;
+}
+
+static int gic__create_its_frame(struct kvm *kvm, u64 its_frame_addr)
+{
+ struct kvm_create_device its_device = {
+ .type = KVM_DEV_TYPE_ARM_VGIC_ITS,
+ .flags = 0,
+ };
+ struct kvm_device_attr its_attr = {
+ .group = KVM_DEV_ARM_VGIC_GRP_ADDR,
+ .attr = KVM_VGIC_ITS_ADDR_TYPE,
+ .addr = (u64)(unsigned long)&its_frame_addr,
+ };
+ struct kvm_device_attr its_init_attr = {
+ .group = KVM_DEV_ARM_VGIC_GRP_CTRL,
+ .attr = KVM_DEV_ARM_VGIC_CTRL_INIT,
+ };
+ int err;
+
+ err = ioctl(kvm->vm_fd, KVM_CREATE_DEVICE, &its_device);
+ if (err) {
+ fprintf(stderr,
+ "GICv3 ITS requested, but kernel does not support it.\n");
+ fprintf(stderr, "Try --irqchip=gicv3 instead\n");
+ return err;
+ }
+
+ err = ioctl(its_device.fd, KVM_HAS_DEVICE_ATTR, &its_attr);
+ if (err) {
+ close(its_device.fd);
+ its_device.fd = -1;
+ return err;
+ }
+
+ err = ioctl(its_device.fd, KVM_SET_DEVICE_ATTR, &its_attr);
+ if (err)
+ return err;
+
+ return ioctl(its_device.fd, KVM_SET_DEVICE_ATTR, &its_init_attr);
+}
+
+static int gic__create_msi_frame(struct kvm *kvm, enum irqchip_type type,
+ u64 msi_frame_addr)
+{
+ switch (type) {
+ case IRQCHIP_GICV2M:
+ return gic__create_gicv2m_frame(kvm, msi_frame_addr);
+ case IRQCHIP_GICV3_ITS:
+ return gic__create_its_frame(kvm, msi_frame_addr);
+ default: /* No MSI frame needed */
+ return 0;
+ }
+}
+
+static int gic__create_device(struct kvm *kvm, enum irqchip_type type)
+{
+ int err;
+ u64 cpu_if_addr = ARM_GIC_CPUI_BASE;
+ u64 dist_addr = ARM_GIC_DIST_BASE;
+ struct kvm_create_device gic_device = {
+ .flags = 0,
+ };
+ struct kvm_device_attr cpu_if_attr = {
+ .group = KVM_DEV_ARM_VGIC_GRP_ADDR,
+ .attr = KVM_VGIC_V2_ADDR_TYPE_CPU,
+ .addr = (u64)(unsigned long)&cpu_if_addr,
+ };
+ struct kvm_device_attr dist_attr = {
+ .group = KVM_DEV_ARM_VGIC_GRP_ADDR,
+ .addr = (u64)(unsigned long)&dist_addr,
+ };
+ struct kvm_device_attr redist_attr = {
+ .group = KVM_DEV_ARM_VGIC_GRP_ADDR,
+ .attr = KVM_VGIC_V3_ADDR_TYPE_REDIST,
+ .addr = (u64)(unsigned long)&gic_redists_base,
+ };
+
+ switch (type) {
+ case IRQCHIP_GICV2M:
+ case IRQCHIP_GICV2:
+ gic_device.type = KVM_DEV_TYPE_ARM_VGIC_V2;
+ dist_attr.attr = KVM_VGIC_V2_ADDR_TYPE_DIST;
+ break;
+ case IRQCHIP_GICV3:
+ case IRQCHIP_GICV3_ITS:
+ gic_device.type = KVM_DEV_TYPE_ARM_VGIC_V3;
+ dist_attr.attr = KVM_VGIC_V3_ADDR_TYPE_DIST;
+ break;
+ case IRQCHIP_AUTO:
+ return -ENODEV;
+ }
+
+ err = ioctl(kvm->vm_fd, KVM_CREATE_DEVICE, &gic_device);
+ if (err)
+ return err;
+
+ gic_fd = gic_device.fd;
+
+ switch (type) {
+ case IRQCHIP_GICV2M:
+ case IRQCHIP_GICV2:
+ err = ioctl(gic_fd, KVM_SET_DEVICE_ATTR, &cpu_if_attr);
+ break;
+ case IRQCHIP_GICV3_ITS:
+ case IRQCHIP_GICV3:
+ err = ioctl(gic_fd, KVM_SET_DEVICE_ATTR, &redist_attr);
+ break;
+ case IRQCHIP_AUTO:
+ return -ENODEV;
+ }
+ if (err)
+ goto out_err;
+
+ err = ioctl(gic_fd, KVM_SET_DEVICE_ATTR, &dist_attr);
+ if (err)
+ goto out_err;
+
+ err = gic__create_msi_frame(kvm, type, gic_msi_base);
+ if (err)
+ goto out_err;
+
+ return 0;
+
+out_err:
+ close(gic_fd);
+ gic_fd = -1;
+ return err;
+}
+
+static int gic__create_irqchip(struct kvm *kvm)
+{
+ int err;
+ struct kvm_arm_device_addr gic_addr[] = {
+ [0] = {
+ .id = KVM_VGIC_V2_ADDR_TYPE_DIST |
+ (KVM_ARM_DEVICE_VGIC_V2 << KVM_ARM_DEVICE_ID_SHIFT),
+ .addr = ARM_GIC_DIST_BASE,
+ },
+ [1] = {
+ .id = KVM_VGIC_V2_ADDR_TYPE_CPU |
+ (KVM_ARM_DEVICE_VGIC_V2 << KVM_ARM_DEVICE_ID_SHIFT),
+ .addr = ARM_GIC_CPUI_BASE,
+ }
+ };
+
+ err = ioctl(kvm->vm_fd, KVM_CREATE_IRQCHIP);
+ if (err)
+ return err;
+
+ err = ioctl(kvm->vm_fd, KVM_ARM_SET_DEVICE_ADDR, &gic_addr[0]);
+ if (err)
+ return err;
+
+ err = ioctl(kvm->vm_fd, KVM_ARM_SET_DEVICE_ADDR, &gic_addr[1]);
+ return err;
+}
+
+int gic__create(struct kvm *kvm, enum irqchip_type type)
+{
+ enum irqchip_type try;
+ int err;
+
+ switch (type) {
+ case IRQCHIP_AUTO:
+ for (try = IRQCHIP_GICV3_ITS; try >= IRQCHIP_GICV2; try--) {
+ err = gic__create(kvm, try);
+ if (!err)
+ break;
+ }
+ if (err)
+ return err;
+
+ kvm->cfg.arch.irqchip = try;
+ return 0;
+ case IRQCHIP_GICV2M:
+ gic_msi_size = KVM_VGIC_V2M_SIZE;
+ gic_msi_base = ARM_GIC_CPUI_BASE - gic_msi_size;
+ break;
+ case IRQCHIP_GICV2:
+ break;
+ case IRQCHIP_GICV3_ITS:
+ /* The 64K page with the doorbell is included. */
+ gic_msi_size = KVM_VGIC_V3_ITS_SIZE;
+ /* fall through */
+ case IRQCHIP_GICV3:
+ gic_redists_size = kvm->cfg.nrcpus * ARM_GIC_REDIST_SIZE;
+ gic_redists_base = ARM_GIC_DIST_BASE - gic_redists_size;
+ gic_msi_base = gic_redists_base - gic_msi_size;
+ break;
+ default:
+ return -ENODEV;
+ }
+
+ /* Try the new way first, and fallback on legacy method otherwise */
+ err = gic__create_device(kvm, type);
+ if (err && type == IRQCHIP_GICV2)
+ err = gic__create_irqchip(kvm);
+
+ return err;
+}
+
+/*
+ * Sets the number of used interrupts and finalizes the GIC init explicitly.
+ */
+static int gic__init_gic(struct kvm *kvm)
+{
+ int ret;
+
+ int lines = irq__get_nr_allocated_lines();
+ u32 nr_irqs = ALIGN(lines, 32) + GIC_SPI_IRQ_BASE;
+ struct kvm_device_attr nr_irqs_attr = {
+ .group = KVM_DEV_ARM_VGIC_GRP_NR_IRQS,
+ .addr = (u64)(unsigned long)&nr_irqs,
+ };
+ struct kvm_device_attr vgic_init_attr = {
+ .group = KVM_DEV_ARM_VGIC_GRP_CTRL,
+ .attr = KVM_DEV_ARM_VGIC_CTRL_INIT,
+ };
+
+ /*
+ * If we didn't use the KVM_CREATE_DEVICE method, KVM will
+ * give us some default number of interrupts. The GIC initialization
+ * will be done automatically in this case.
+ */
+ if (gic_fd < 0)
+ return 0;
+
+ if (!ioctl(gic_fd, KVM_HAS_DEVICE_ATTR, &nr_irqs_attr)) {
+ ret = ioctl(gic_fd, KVM_SET_DEVICE_ATTR, &nr_irqs_attr);
+ if (ret)
+ return ret;
+ }
+
+ irq__routing_init(kvm);
+
+ if (!ioctl(gic_fd, KVM_HAS_DEVICE_ATTR, &vgic_init_attr)) {
+ ret = ioctl(gic_fd, KVM_SET_DEVICE_ATTR, &vgic_init_attr);
+ if (ret)
+ return ret;
+ }
+
+ kvm->msix_needs_devid = kvm__supports_vm_extension(kvm,
+ KVM_CAP_MSI_DEVID);
+
+ vgic_is_init = true;
+
+ return irq__setup_irqfd_lines(kvm);
+}
+late_init(gic__init_gic)
+
+void gic__generate_fdt_nodes(void *fdt, enum irqchip_type type)
+{
+ const char *compatible, *msi_compatible = NULL;
+ u64 msi_prop[2];
+ u64 reg_prop[] = {
+ cpu_to_fdt64(ARM_GIC_DIST_BASE), cpu_to_fdt64(ARM_GIC_DIST_SIZE),
+ 0, 0, /* to be filled */
+ };
+
+ switch (type) {
+ case IRQCHIP_GICV2M:
+ msi_compatible = "arm,gic-v2m-frame";
+ /* fall-through */
+ case IRQCHIP_GICV2:
+ compatible = "arm,cortex-a15-gic";
+ reg_prop[2] = cpu_to_fdt64(ARM_GIC_CPUI_BASE);
+ reg_prop[3] = cpu_to_fdt64(ARM_GIC_CPUI_SIZE);
+ break;
+ case IRQCHIP_GICV3_ITS:
+ msi_compatible = "arm,gic-v3-its";
+ /* fall-through */
+ case IRQCHIP_GICV3:
+ compatible = "arm,gic-v3";
+ reg_prop[2] = cpu_to_fdt64(gic_redists_base);
+ reg_prop[3] = cpu_to_fdt64(gic_redists_size);
+ break;
+ default:
+ return;
+ }
+
+ _FDT(fdt_begin_node(fdt, "intc"));
+ _FDT(fdt_property_string(fdt, "compatible", compatible));
+ _FDT(fdt_property_cell(fdt, "#interrupt-cells", GIC_FDT_IRQ_NUM_CELLS));
+ _FDT(fdt_property(fdt, "interrupt-controller", NULL, 0));
+ _FDT(fdt_property(fdt, "reg", reg_prop, sizeof(reg_prop)));
+ _FDT(fdt_property_cell(fdt, "phandle", PHANDLE_GIC));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 2));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 2));
+
+ if (msi_compatible) {
+ _FDT(fdt_property(fdt, "ranges", NULL, 0));
+
+ _FDT(fdt_begin_node(fdt, "msic"));
+ _FDT(fdt_property_string(fdt, "compatible", msi_compatible));
+ _FDT(fdt_property(fdt, "msi-controller", NULL, 0));
+ _FDT(fdt_property_cell(fdt, "phandle", PHANDLE_MSI));
+ msi_prop[0] = cpu_to_fdt64(gic_msi_base);
+ msi_prop[1] = cpu_to_fdt64(gic_msi_size);
+ _FDT(fdt_property(fdt, "reg", msi_prop, sizeof(msi_prop)));
+ _FDT(fdt_end_node(fdt));
+ }
+
+ _FDT(fdt_end_node(fdt));
+}
+
+#define KVM_IRQCHIP_IRQ(x) (KVM_ARM_IRQ_TYPE_SPI << KVM_ARM_IRQ_TYPE_SHIFT) |\
+ ((x) & KVM_ARM_IRQ_NUM_MASK)
+
+void kvm__irq_line(struct kvm *kvm, int irq, int level)
+{
+ struct kvm_irq_level irq_level = {
+ .irq = KVM_IRQCHIP_IRQ(irq),
+ .level = !!level,
+ };
+
+ if (irq < GIC_SPI_IRQ_BASE || irq > GIC_MAX_IRQ)
+ pr_warning("Ignoring invalid GIC IRQ %d", irq);
+ else if (ioctl(kvm->vm_fd, KVM_IRQ_LINE, &irq_level) < 0)
+ pr_warning("Could not KVM_IRQ_LINE for irq %d", irq);
+}
+
+void kvm__irq_trigger(struct kvm *kvm, int irq)
+{
+ kvm__irq_line(kvm, irq, VIRTIO_IRQ_HIGH);
+ kvm__irq_line(kvm, irq, VIRTIO_IRQ_LOW);
+}
+
+int gic__add_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd,
+ int resample_fd)
+{
+ struct kvm_irqfd_line *line;
+
+ if (vgic_is_init)
+ return irq__common_add_irqfd(kvm, gsi, trigger_fd, resample_fd);
+
+ /* Postpone the routing setup until we have a distributor */
+ line = malloc(sizeof(*line));
+ if (!line)
+ return -ENOMEM;
+
+ *line = (struct kvm_irqfd_line) {
+ .gsi = gsi,
+ .trigger_fd = trigger_fd,
+ .resample_fd = resample_fd,
+ };
+ list_add(&line->list, &irqfd_lines);
+
+ return 0;
+}
+
+void gic__del_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd)
+{
+ struct kvm_irqfd_line *line;
+
+ if (vgic_is_init) {
+ irq__common_del_irqfd(kvm, gsi, trigger_fd);
+ return;
+ }
+
+ list_for_each_entry(line, &irqfd_lines, list) {
+ if (line->gsi != gsi)
+ continue;
+
+ list_del(&line->list);
+ free(line);
+ break;
+ }
+}
diff --git a/kvmtool/arm/gicv2m.c b/kvmtool/arm/gicv2m.c
new file mode 100644
index 0000000..d7e6398
--- /dev/null
+++ b/kvmtool/arm/gicv2m.c
@@ -0,0 +1,153 @@
+#include <errno.h>
+#include <stdlib.h>
+
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#include "arm-common/gic.h"
+
+#define GICV2M_MSI_TYPER 0x008
+#define GICV2M_MSI_SETSPI 0x040
+#define GICV2M_MSI_IIDR 0xfcc
+
+#define GICV2M_SPI_MASK 0x3ff
+#define GICV2M_MSI_TYPER_VAL(start, nr) \
+ (((start) & GICV2M_SPI_MASK) << 16 | ((nr) & GICV2M_SPI_MASK))
+
+struct gicv2m_chip {
+ int first_spi;
+ int num_spis;
+ int *spis;
+ u64 base;
+ u64 size;
+};
+
+static struct gicv2m_chip v2m;
+
+/*
+ * MSI routing is setup lazily, when the guest writes the MSI tables. The guest
+ * writes which SPI is associated to an MSI vector into the message data field.
+ * The IRQ code notifies us of any change to MSI routing via this callback.
+ * Store the MSI->SPI translation for later.
+ *
+ * Data is the GIC interrupt ID, that includes SGIs and PPIs. SGIs at 0-15, PPIs
+ * are 16-31 and SPIs are 32-1019. What we're saving for later is the MSI's GSI
+ * number, a logical ID used by KVM for routing. The GSI of an SPI is implicitly
+ * defined by KVM to be its pin number (SPI index), and the GSI of an MSI is
+ * allocated by kvmtool.
+ */
+static int gicv2m_update_routing(struct kvm *kvm,
+ struct kvm_irq_routing_entry *entry)
+{
+ int spi;
+
+ if (entry->type != KVM_IRQ_ROUTING_MSI)
+ return -EINVAL;
+
+ if (!entry->u.msi.address_hi && !entry->u.msi.address_lo)
+ return 0;
+
+ spi = entry->u.msi.data & GICV2M_SPI_MASK;
+ if (spi < v2m.first_spi || spi >= v2m.first_spi + v2m.num_spis) {
+ pr_err("invalid SPI number %d", spi);
+ return -EINVAL;
+ }
+
+ v2m.spis[spi - v2m.first_spi] = entry->gsi;
+
+ return 0;
+}
+
+/*
+ * Find SPI bound to the given MSI and return the associated GSI.
+ */
+static int gicv2m_translate_gsi(struct kvm *kvm, u32 gsi)
+{
+ int i;
+
+ for (i = 0; i < v2m.num_spis; i++) {
+ if (v2m.spis[i] == (int)gsi)
+ return i + v2m.first_spi - KVM_IRQ_OFFSET;
+ }
+
+ /* Not an MSI */
+ return gsi;
+}
+
+static bool gicv2m_can_signal_msi(struct kvm *kvm)
+{
+ return true;
+}
+
+/*
+ * Instead of setting up MSI routes, virtual devices can also trigger them
+ * manually (like a direct write to MSI_SETSPI). In this case, trigger the SPI
+ * directly.
+ */
+static int gicv2m_signal_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+ int spi = msi->data & GICV2M_SPI_MASK;
+
+ if (spi < v2m.first_spi || spi >= v2m.first_spi + v2m.num_spis) {
+ pr_err("invalid SPI number %d", spi);
+ return -EINVAL;
+ }
+
+ kvm__irq_trigger(kvm, spi);
+ return 0;
+}
+
+static struct msi_routing_ops gicv2m_routing = {
+ .update_route = gicv2m_update_routing,
+ .translate_gsi = gicv2m_translate_gsi,
+ .can_signal_msi = gicv2m_can_signal_msi,
+ .signal_msi = gicv2m_signal_msi,
+};
+
+static void gicv2m_mmio_callback(struct kvm_cpu *vcpu, u64 addr, u8 *data,
+ u32 len, u8 is_write, void *ptr)
+{
+ if (is_write)
+ return;
+
+ addr -= v2m.base;
+
+ switch (addr) {
+ case GICV2M_MSI_TYPER:
+ *(u32 *)data = GICV2M_MSI_TYPER_VAL(v2m.first_spi,
+ v2m.num_spis);
+ break;
+ case GICV2M_MSI_IIDR:
+ *(u32 *)data = 0x0;
+ break;
+ }
+}
+
+int gic__create_gicv2m_frame(struct kvm *kvm, u64 base)
+{
+ int i;
+ int irq = irq__alloc_line();
+
+ v2m = (struct gicv2m_chip) {
+ .first_spi = irq, /* Includes GIC_SPI_IRQ_BASE */
+ .num_spis = 64, /* arbitrary */
+ .base = base,
+ .size = KVM_VGIC_V2M_SIZE,
+ };
+
+ v2m.spis = calloc(v2m.num_spis, sizeof(int));
+ if (!v2m.spis)
+ return -ENOMEM;
+
+ v2m.spis[0] = -1;
+ for (i = 1; i < v2m.num_spis; i++) {
+ irq__alloc_line();
+ v2m.spis[i] = -1;
+ }
+
+ msi_routing_ops = &gicv2m_routing;
+
+ return kvm__register_mmio(kvm, base, KVM_VGIC_V2M_SIZE, false,
+ gicv2m_mmio_callback, kvm);
+}
diff --git a/kvmtool/arm/include/arm-common/fdt-arch.h b/kvmtool/arm/include/arm-common/fdt-arch.h
new file mode 100644
index 0000000..60c2d40
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/fdt-arch.h
@@ -0,0 +1,6 @@
+#ifndef ARM__FDT_H
+#define ARM__FDT_H
+
+enum phandles {PHANDLE_RESERVED = 0, PHANDLE_GIC, PHANDLE_MSI, PHANDLES_MAX};
+
+#endif /* ARM__FDT_H */
diff --git a/kvmtool/arm/include/arm-common/gic.h b/kvmtool/arm/include/arm-common/gic.h
new file mode 100644
index 0000000..ec9cf31
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/gic.h
@@ -0,0 +1,47 @@
+#ifndef ARM_COMMON__GIC_H
+#define ARM_COMMON__GIC_H
+
+#define GIC_SGI_IRQ_BASE 0
+#define GIC_PPI_IRQ_BASE 16
+#define GIC_SPI_IRQ_BASE 32
+
+#define GIC_FDT_IRQ_NUM_CELLS 3
+
+#define GIC_FDT_IRQ_TYPE_SPI 0
+#define GIC_FDT_IRQ_TYPE_PPI 1
+
+#define GIC_FDT_IRQ_PPI_CPU_SHIFT 8
+#define GIC_FDT_IRQ_PPI_CPU_MASK (0xff << GIC_FDT_IRQ_PPI_CPU_SHIFT)
+
+#define GIC_CPUI_CTLR_EN (1 << 0)
+#define GIC_CPUI_PMR_MIN_PRIO 0xff
+
+#define GIC_CPUI_OFF_PMR 4
+
+#define GIC_MAX_CPUS 8
+#define GIC_MAX_IRQ 255
+
+#define KVM_VGIC_V2M_SIZE 0x1000
+
+enum irqchip_type {
+ IRQCHIP_AUTO,
+ IRQCHIP_GICV2,
+ IRQCHIP_GICV2M,
+ IRQCHIP_GICV3,
+ IRQCHIP_GICV3_ITS,
+};
+
+struct kvm;
+
+int gic__alloc_irqnum(void);
+int gic__create(struct kvm *kvm, enum irqchip_type type);
+int gic__create_gicv2m_frame(struct kvm *kvm, u64 msi_frame_addr);
+void gic__generate_fdt_nodes(void *fdt, enum irqchip_type type);
+
+int gic__add_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd,
+ int resample_fd);
+void gic__del_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd);
+#define irq__add_irqfd gic__add_irqfd
+#define irq__del_irqfd gic__del_irqfd
+
+#endif /* ARM_COMMON__GIC_H */
diff --git a/kvmtool/arm/include/arm-common/kvm-arch.h b/kvmtool/arm/include/arm-common/kvm-arch.h
new file mode 100644
index 0000000..d84e50c
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/kvm-arch.h
@@ -0,0 +1,81 @@
+#ifndef ARM_COMMON__KVM_ARCH_H
+#define ARM_COMMON__KVM_ARCH_H
+
+#include <stdbool.h>
+#include <linux/const.h>
+#include <linux/types.h>
+
+#include "arm-common/gic.h"
+
+#define ARM_IOPORT_AREA _AC(0x0000000000000000, UL)
+#define ARM_FLASH_AREA _AC(0x0000000002000000, UL)
+#define ARM_MMIO_AREA _AC(0x0000000003000000, UL)
+#define ARM_AXI_AREA _AC(0x0000000040000000, UL)
+#define ARM_MEMORY_AREA _AC(0x0000000080000000, UL)
+
+#define ARM_LOMAP_MAX_MEMORY ((1ULL << 32) - ARM_MEMORY_AREA)
+#define ARM_HIMAP_MAX_MEMORY ((1ULL << 40) - ARM_MEMORY_AREA)
+
+#define ARM_GIC_DIST_BASE (ARM_AXI_AREA - ARM_GIC_DIST_SIZE)
+#define ARM_GIC_CPUI_BASE (ARM_GIC_DIST_BASE - ARM_GIC_CPUI_SIZE)
+#define ARM_GIC_SIZE (ARM_GIC_DIST_SIZE + ARM_GIC_CPUI_SIZE)
+#define ARM_GIC_DIST_SIZE 0x10000
+#define ARM_GIC_CPUI_SIZE 0x20000
+
+#define KVM_FLASH_MMIO_BASE ARM_FLASH_AREA
+#define KVM_FLASH_MAX_SIZE (ARM_MMIO_AREA - ARM_FLASH_AREA)
+
+#define ARM_IOPORT_SIZE (1U << 16)
+#define ARM_VIRTIO_MMIO_SIZE (ARM_AXI_AREA - (ARM_MMIO_AREA + ARM_GIC_SIZE))
+#define ARM_PCI_CFG_SIZE (1ULL << 24)
+#define ARM_PCI_MMIO_SIZE (ARM_MEMORY_AREA - \
+ (ARM_AXI_AREA + ARM_PCI_CFG_SIZE))
+
+#define KVM_IOPORT_AREA ARM_IOPORT_AREA
+#define KVM_PCI_CFG_AREA ARM_AXI_AREA
+#define KVM_PCI_MMIO_AREA (KVM_PCI_CFG_AREA + ARM_PCI_CFG_SIZE)
+#define KVM_VIRTIO_MMIO_AREA ARM_MMIO_AREA
+
+#define KVM_IOEVENTFD_HAS_PIO 0
+
+/*
+ * On a GICv3 there must be one redistributor per vCPU.
+ * The value here is the size for one, we multiply this at runtime with
+ * the number of requested vCPUs to get the actual size.
+ */
+#define ARM_GIC_REDIST_SIZE 0x20000
+
+#define KVM_IRQ_OFFSET GIC_SPI_IRQ_BASE
+
+#define KVM_VM_TYPE 0
+
+#define VIRTIO_DEFAULT_TRANS(kvm) \
+ ((kvm)->cfg.arch.virtio_trans_pci ? VIRTIO_PCI : VIRTIO_MMIO)
+
+#define VIRTIO_RING_ENDIAN (VIRTIO_ENDIAN_LE | VIRTIO_ENDIAN_BE)
+
+static inline bool arm_addr_in_ioport_region(u64 phys_addr)
+{
+ u64 limit = KVM_IOPORT_AREA + ARM_IOPORT_SIZE;
+ return phys_addr >= KVM_IOPORT_AREA && phys_addr < limit;
+}
+
+struct kvm_arch {
+ /*
+ * We may have to align the guest memory for virtio, so keep the
+ * original pointers here for munmap.
+ */
+ void *ram_alloc_start;
+ u64 ram_alloc_size;
+
+ /*
+ * Guest addresses for memory layout.
+ */
+ u64 memory_guest_start;
+ u64 kern_guest_start;
+ u64 initrd_guest_start;
+ u64 initrd_size;
+ u64 dtb_guest_start;
+};
+
+#endif /* ARM_COMMON__KVM_ARCH_H */
diff --git a/kvmtool/arm/include/arm-common/kvm-config-arch.h b/kvmtool/arm/include/arm-common/kvm-config-arch.h
new file mode 100644
index 0000000..5734c46
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/kvm-config-arch.h
@@ -0,0 +1,38 @@
+#ifndef ARM_COMMON__KVM_CONFIG_ARCH_H
+#define ARM_COMMON__KVM_CONFIG_ARCH_H
+
+#include "kvm/parse-options.h"
+
+struct kvm_config_arch {
+ const char *dump_dtb_filename;
+ unsigned int force_cntfrq;
+ bool virtio_trans_pci;
+ bool aarch32_guest;
+ bool has_pmuv3;
+ u64 kaslr_seed;
+ enum irqchip_type irqchip;
+ u64 fw_addr;
+};
+
+int irqchip_parser(const struct option *opt, const char *arg, int unset);
+
+#define OPT_ARCH_RUN(pfx, cfg) \
+ pfx, \
+ ARM_OPT_ARCH_RUN(cfg) \
+ OPT_STRING('\0', "dump-dtb", &(cfg)->dump_dtb_filename, \
+ ".dtb file", "Dump generated .dtb to specified file"), \
+ OPT_UINTEGER('\0', "override-bad-firmware-cntfrq", &(cfg)->force_cntfrq,\
+ "Specify Generic Timer frequency in guest DT to " \
+ "work around buggy secure firmware *Firmware should be " \
+ "updated to program CNTFRQ correctly*"), \
+ OPT_BOOLEAN('\0', "force-pci", &(cfg)->virtio_trans_pci, \
+ "Force virtio devices to use PCI as their default " \
+ "transport"), \
+ OPT_CALLBACK('\0', "irqchip", &(cfg)->irqchip, \
+ "[gicv2|gicv2m|gicv3|gicv3-its]", \
+ "Type of interrupt controller to emulate in the guest", \
+ irqchip_parser, NULL), \
+ OPT_U64('\0', "firmware-address", &(cfg)->fw_addr, \
+ "Address where firmware should be loaded"),
+
+#endif /* ARM_COMMON__KVM_CONFIG_ARCH_H */
diff --git a/kvmtool/arm/include/arm-common/kvm-cpu-arch.h b/kvmtool/arm/include/arm-common/kvm-cpu-arch.h
new file mode 100644
index 0000000..923d2c4
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/kvm-cpu-arch.h
@@ -0,0 +1,62 @@
+#ifndef ARM_COMMON__KVM_CPU_ARCH_H
+#define ARM_COMMON__KVM_CPU_ARCH_H
+
+#include <linux/kvm.h>
+#include <pthread.h>
+#include <stdbool.h>
+
+struct kvm;
+
+struct kvm_cpu {
+ pthread_t thread;
+
+ unsigned long cpu_id;
+ unsigned long cpu_type;
+ const char *cpu_compatible;
+
+ struct kvm *kvm;
+ int vcpu_fd;
+ struct kvm_run *kvm_run;
+ struct kvm_cpu_task *task;
+
+ u8 is_running;
+ u8 paused;
+ u8 needs_nmi;
+
+ struct kvm_coalesced_mmio_ring *ring;
+
+ void (*generate_fdt_nodes)(void *fdt, struct kvm* kvm);
+};
+
+struct kvm_arm_target {
+ u32 id;
+ const char *compatible;
+ int (*init)(struct kvm_cpu *vcpu);
+};
+
+void kvm_cpu__set_kvm_arm_generic_target(struct kvm_arm_target *target);
+
+int kvm_cpu__register_kvm_arm_target(struct kvm_arm_target *target);
+
+static inline bool kvm_cpu__emulate_io(struct kvm_cpu *vcpu, u16 port, void *data,
+ int direction, int size, u32 count)
+{
+ return false;
+}
+
+static inline bool kvm_cpu__emulate_mmio(struct kvm_cpu *vcpu, u64 phys_addr,
+ u8 *data, u32 len, u8 is_write)
+{
+ if (arm_addr_in_ioport_region(phys_addr)) {
+ int direction = is_write ? KVM_EXIT_IO_OUT : KVM_EXIT_IO_IN;
+ u16 port = (phys_addr - KVM_IOPORT_AREA) & USHRT_MAX;
+
+ return kvm__emulate_io(vcpu, port, data, direction, len, 1);
+ }
+
+ return kvm__emulate_mmio(vcpu, phys_addr, data, len, is_write);
+}
+
+unsigned long kvm_cpu__get_vcpu_mpidr(struct kvm_cpu *vcpu);
+
+#endif /* ARM_COMMON__KVM_CPU_ARCH_H */
diff --git a/kvmtool/arm/include/arm-common/pci.h b/kvmtool/arm/include/arm-common/pci.h
new file mode 100644
index 0000000..9008a0e
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/pci.h
@@ -0,0 +1,6 @@
+#ifndef ARM_COMMON__PCI_H
+#define ARM_COMMON__PCI_H
+
+void pci__generate_fdt_nodes(void *fdt);
+
+#endif /* ARM_COMMON__PCI_H */
diff --git a/kvmtool/arm/include/arm-common/pmu.h b/kvmtool/arm/include/arm-common/pmu.h
new file mode 100644
index 0000000..7a170a5
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/pmu.h
@@ -0,0 +1,4 @@
+
+#define KVM_ARM_PMUv3_PPI 23
+
+void pmu__generate_fdt_nodes(void *fdt, struct kvm *kvm);
diff --git a/kvmtool/arm/include/arm-common/timer.h b/kvmtool/arm/include/arm-common/timer.h
new file mode 100644
index 0000000..928e9ea
--- /dev/null
+++ b/kvmtool/arm/include/arm-common/timer.h
@@ -0,0 +1,6 @@
+#ifndef ARM_COMMON__TIMER_H
+#define ARM_COMMON__TIMER_H
+
+void timer__generate_fdt_nodes(void *fdt, struct kvm *kvm, int *irqs);
+
+#endif /* ARM_COMMON__TIMER_H */
diff --git a/kvmtool/arm/ioport.c b/kvmtool/arm/ioport.c
new file mode 100644
index 0000000..2f0feb9
--- /dev/null
+++ b/kvmtool/arm/ioport.c
@@ -0,0 +1,12 @@
+#include "kvm/ioport.h"
+#include "kvm/irq.h"
+
+int ioport__setup_arch(struct kvm *kvm)
+{
+ return 0;
+}
+
+void ioport__map_irq(u8 *irq)
+{
+ *irq = irq__alloc_line();
+}
diff --git a/kvmtool/arm/kvm-cpu.c b/kvmtool/arm/kvm-cpu.c
new file mode 100644
index 0000000..2acecae
--- /dev/null
+++ b/kvmtool/arm/kvm-cpu.c
@@ -0,0 +1,153 @@
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+static int debug_fd;
+
+void kvm_cpu__set_debug_fd(int fd)
+{
+ debug_fd = fd;
+}
+
+int kvm_cpu__get_debug_fd(void)
+{
+ return debug_fd;
+}
+
+static struct kvm_arm_target *kvm_arm_generic_target;
+static struct kvm_arm_target *kvm_arm_targets[KVM_ARM_NUM_TARGETS];
+
+void kvm_cpu__set_kvm_arm_generic_target(struct kvm_arm_target *target)
+{
+ kvm_arm_generic_target = target;
+}
+
+int kvm_cpu__register_kvm_arm_target(struct kvm_arm_target *target)
+{
+ unsigned int i = 0;
+
+ for (i = 0; i < ARRAY_SIZE(kvm_arm_targets); ++i) {
+ if (!kvm_arm_targets[i]) {
+ kvm_arm_targets[i] = target;
+ return 0;
+ }
+ }
+
+ return -ENOSPC;
+}
+
+struct kvm_cpu *kvm_cpu__arch_init(struct kvm *kvm, unsigned long cpu_id)
+{
+ struct kvm_arm_target *target;
+ struct kvm_cpu *vcpu;
+ int coalesced_offset, mmap_size, err = -1;
+ unsigned int i;
+ struct kvm_vcpu_init preferred_init;
+ struct kvm_vcpu_init vcpu_init = {
+ .features = ARM_VCPU_FEATURE_FLAGS(kvm, cpu_id)
+ };
+
+ if (kvm->cfg.arch.aarch32_guest &&
+ !kvm__supports_extension(kvm, KVM_CAP_ARM_EL1_32BIT))
+ die("32bit guests are not supported\n");
+
+ vcpu = calloc(1, sizeof(struct kvm_cpu));
+ if (!vcpu)
+ return NULL;
+
+ vcpu->vcpu_fd = ioctl(kvm->vm_fd, KVM_CREATE_VCPU, cpu_id);
+ if (vcpu->vcpu_fd < 0)
+ die_perror("KVM_CREATE_VCPU ioctl");
+
+ mmap_size = ioctl(kvm->sys_fd, KVM_GET_VCPU_MMAP_SIZE, 0);
+ if (mmap_size < 0)
+ die_perror("KVM_GET_VCPU_MMAP_SIZE ioctl");
+
+ vcpu->kvm_run = mmap(NULL, mmap_size, PROT_RW, MAP_SHARED,
+ vcpu->vcpu_fd, 0);
+ if (vcpu->kvm_run == MAP_FAILED)
+ die("unable to mmap vcpu fd");
+
+ /* Set KVM_ARM_VCPU_PSCI_0_2 if available */
+ if (kvm__supports_extension(kvm, KVM_CAP_ARM_PSCI_0_2)) {
+ vcpu_init.features[0] |= (1UL << KVM_ARM_VCPU_PSCI_0_2);
+ }
+
+ kvm_cpu__select_features(kvm, &vcpu_init);
+
+ /*
+ * If the preferred target ioctl is successful then
+ * use preferred target else try each and every target type
+ */
+ err = ioctl(kvm->vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init);
+ if (!err) {
+ /* Match preferred target CPU type. */
+ target = NULL;
+ for (i = 0; i < ARRAY_SIZE(kvm_arm_targets); ++i) {
+ if (!kvm_arm_targets[i])
+ continue;
+ if (kvm_arm_targets[i]->id == preferred_init.target) {
+ target = kvm_arm_targets[i];
+ break;
+ }
+ }
+ if (!target) {
+ target = kvm_arm_generic_target;
+ vcpu_init.target = preferred_init.target;
+ } else {
+ vcpu_init.target = target->id;
+ }
+ err = ioctl(vcpu->vcpu_fd, KVM_ARM_VCPU_INIT, &vcpu_init);
+ } else {
+ /* Find an appropriate target CPU type. */
+ for (i = 0; i < ARRAY_SIZE(kvm_arm_targets); ++i) {
+ if (!kvm_arm_targets[i])
+ continue;
+ target = kvm_arm_targets[i];
+ vcpu_init.target = target->id;
+ err = ioctl(vcpu->vcpu_fd, KVM_ARM_VCPU_INIT, &vcpu_init);
+ if (!err)
+ break;
+ }
+ if (err)
+ die("Unable to find matching target");
+ }
+
+ if (err || target->init(vcpu))
+ die("Unable to initialise vcpu");
+
+ coalesced_offset = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION,
+ KVM_CAP_COALESCED_MMIO);
+ if (coalesced_offset)
+ vcpu->ring = (void *)vcpu->kvm_run +
+ (coalesced_offset * PAGE_SIZE);
+
+ /* Populate the vcpu structure. */
+ vcpu->kvm = kvm;
+ vcpu->cpu_id = cpu_id;
+ vcpu->cpu_type = vcpu_init.target;
+ vcpu->cpu_compatible = target->compatible;
+ vcpu->is_running = true;
+
+ if (kvm_cpu__configure_features(vcpu))
+ die("Unable to configure requested vcpu features");
+
+ return vcpu;
+}
+
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu)
+{
+}
+
+void kvm_cpu__delete(struct kvm_cpu *vcpu)
+{
+ free(vcpu);
+}
+
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu)
+{
+ return false;
+}
+
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu)
+{
+}
diff --git a/kvmtool/arm/kvm.c b/kvmtool/arm/kvm.c
new file mode 100644
index 0000000..5aea18f
--- /dev/null
+++ b/kvmtool/arm/kvm.c
@@ -0,0 +1,239 @@
+#include "kvm/kvm.h"
+#include "kvm/term.h"
+#include "kvm/util.h"
+#include "kvm/8250-serial.h"
+#include "kvm/virtio-console.h"
+#include "kvm/fdt.h"
+
+#include "arm-common/gic.h"
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+
+struct kvm_ext kvm_req_ext[] = {
+ { DEFINE_KVM_EXT(KVM_CAP_IRQCHIP) },
+ { DEFINE_KVM_EXT(KVM_CAP_ONE_REG) },
+ { DEFINE_KVM_EXT(KVM_CAP_ARM_PSCI) },
+ { 0, 0 },
+};
+
+bool kvm__arch_cpu_supports_vm(void)
+{
+ /* The KVM capability check is enough. */
+ return true;
+}
+
+void kvm__init_ram(struct kvm *kvm)
+{
+ int err;
+ u64 phys_start, phys_size;
+ void *host_mem;
+
+ phys_start = ARM_MEMORY_AREA;
+ phys_size = kvm->ram_size;
+ host_mem = kvm->ram_start;
+
+ err = kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+ if (err)
+ die("Failed to register %lld bytes of memory at physical "
+ "address 0x%llx [err %d]", phys_size, phys_start, err);
+
+ kvm->arch.memory_guest_start = phys_start;
+}
+
+void kvm__arch_delete_ram(struct kvm *kvm)
+{
+ munmap(kvm->arch.ram_alloc_start, kvm->arch.ram_alloc_size);
+}
+
+void kvm__arch_read_term(struct kvm *kvm)
+{
+ serial8250__update_consoles(kvm);
+ virtio_console__inject_interrupt(kvm);
+}
+
+void kvm__arch_set_cmdline(char *cmdline, bool video)
+{
+}
+
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size)
+{
+ /*
+ * Allocate guest memory. We must align our buffer to 64K to
+ * correlate with the maximum guest page size for virtio-mmio.
+ * If using THP, then our minimal alignment becomes 2M.
+ * 2M trumps 64K, so let's go with that.
+ */
+ kvm->ram_size = min(ram_size, (u64)ARM_MAX_MEMORY(kvm));
+ kvm->arch.ram_alloc_size = kvm->ram_size + SZ_2M;
+ kvm->arch.ram_alloc_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path,
+ kvm->arch.ram_alloc_size);
+
+ if (kvm->arch.ram_alloc_start == MAP_FAILED)
+ die("Failed to map %lld bytes for guest memory (%d)",
+ kvm->arch.ram_alloc_size, errno);
+
+ kvm->ram_start = (void *)ALIGN((unsigned long)kvm->arch.ram_alloc_start,
+ SZ_2M);
+
+ madvise(kvm->arch.ram_alloc_start, kvm->arch.ram_alloc_size,
+ MADV_MERGEABLE);
+
+ madvise(kvm->arch.ram_alloc_start, kvm->arch.ram_alloc_size,
+ MADV_HUGEPAGE);
+
+ /* Create the virtual GIC. */
+ if (gic__create(kvm, kvm->cfg.arch.irqchip))
+ die("Failed to create virtual GIC");
+}
+
+#define FDT_ALIGN SZ_2M
+#define INITRD_ALIGN 4
+bool kvm__arch_load_kernel_image(struct kvm *kvm, int fd_kernel, int fd_initrd,
+ const char *kernel_cmdline)
+{
+ void *pos, *kernel_end, *limit;
+ unsigned long guest_addr;
+ ssize_t file_size;
+
+ /*
+ * Linux requires the initrd and dtb to be mapped inside lowmem,
+ * so we can't just place them at the top of memory.
+ */
+ limit = kvm->ram_start + min(kvm->ram_size, (u64)SZ_256M) - 1;
+
+ pos = kvm->ram_start + kvm__arch_get_kern_offset(kvm, fd_kernel);
+ kvm->arch.kern_guest_start = host_to_guest_flat(kvm, pos);
+ file_size = read_file(fd_kernel, pos, limit - pos);
+ if (file_size < 0) {
+ if (errno == ENOMEM)
+ die("kernel image too big to contain in guest memory.");
+
+ die_perror("kernel read");
+ }
+ kernel_end = pos + file_size;
+ pr_debug("Loaded kernel to 0x%llx (%zd bytes)",
+ kvm->arch.kern_guest_start, file_size);
+
+ /*
+ * Now load backwards from the end of memory so the kernel
+ * decompressor has plenty of space to work with. First up is
+ * the device tree blob...
+ */
+ pos = limit;
+ pos -= (FDT_MAX_SIZE + FDT_ALIGN);
+ guest_addr = ALIGN(host_to_guest_flat(kvm, pos), FDT_ALIGN);
+ pos = guest_flat_to_host(kvm, guest_addr);
+ if (pos < kernel_end)
+ die("fdt overlaps with kernel image.");
+
+ kvm->arch.dtb_guest_start = guest_addr;
+ pr_debug("Placing fdt at 0x%llx - 0x%llx",
+ kvm->arch.dtb_guest_start,
+ host_to_guest_flat(kvm, limit));
+ limit = pos;
+
+ /* ... and finally the initrd, if we have one. */
+ if (fd_initrd != -1) {
+ struct stat sb;
+ unsigned long initrd_start;
+
+ if (fstat(fd_initrd, &sb))
+ die_perror("fstat");
+
+ pos -= (sb.st_size + INITRD_ALIGN);
+ guest_addr = ALIGN(host_to_guest_flat(kvm, pos), INITRD_ALIGN);
+ pos = guest_flat_to_host(kvm, guest_addr);
+ if (pos < kernel_end)
+ die("initrd overlaps with kernel image.");
+
+ initrd_start = guest_addr;
+ file_size = read_file(fd_initrd, pos, limit - pos);
+ if (file_size == -1) {
+ if (errno == ENOMEM)
+ die("initrd too big to contain in guest memory.");
+
+ die_perror("initrd read");
+ }
+
+ kvm->arch.initrd_guest_start = initrd_start;
+ kvm->arch.initrd_size = file_size;
+ pr_debug("Loaded initrd to 0x%llx (%llu bytes)",
+ kvm->arch.initrd_guest_start,
+ kvm->arch.initrd_size);
+ } else {
+ kvm->arch.initrd_size = 0;
+ }
+
+ return true;
+}
+
+static bool validate_fw_addr(struct kvm *kvm, u64 fw_addr)
+{
+ u64 ram_phys;
+
+ ram_phys = host_to_guest_flat(kvm, kvm->ram_start);
+
+ if (fw_addr < ram_phys || fw_addr >= ram_phys + kvm->ram_size) {
+ pr_err("Provide --firmware-address an address in RAM: "
+ "0x%016llx - 0x%016llx",
+ ram_phys, ram_phys + kvm->ram_size);
+
+ return false;
+ }
+
+ return true;
+}
+
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename)
+{
+ u64 fw_addr = kvm->cfg.arch.fw_addr;
+ void *host_pos;
+ void *limit;
+ ssize_t fw_sz;
+ int fd;
+
+ limit = kvm->ram_start + kvm->ram_size;
+
+ /* For default firmware address, lets load it at the begining of RAM */
+ if (fw_addr == 0)
+ fw_addr = ARM_MEMORY_AREA;
+
+ if (!validate_fw_addr(kvm, fw_addr))
+ die("Bad firmware destination: 0x%016llx", fw_addr);
+
+ fd = open(firmware_filename, O_RDONLY);
+ if (fd < 0)
+ return false;
+
+ host_pos = guest_flat_to_host(kvm, fw_addr);
+ if (!host_pos || host_pos < kvm->ram_start)
+ return false;
+
+ fw_sz = read_file(fd, host_pos, limit - host_pos);
+ if (fw_sz < 0)
+ die("failed to load firmware");
+ close(fd);
+
+ /* Kernel isn't loaded by kvm, point start address to firmware */
+ kvm->arch.kern_guest_start = fw_addr;
+
+ /* Load dtb just after the firmware image*/
+ host_pos += fw_sz;
+ if (host_pos + FDT_MAX_SIZE > limit)
+ die("not enough space to load fdt");
+
+ kvm->arch.dtb_guest_start = ALIGN(host_to_guest_flat(kvm, host_pos),
+ FDT_ALIGN);
+ pr_info("Placing fdt at 0x%llx - 0x%llx",
+ kvm->arch.dtb_guest_start,
+ kvm->arch.dtb_guest_start + FDT_MAX_SIZE);
+
+ return true;
+}
+
+int kvm__arch_setup_firmware(struct kvm *kvm)
+{
+ return 0;
+}
diff --git a/kvmtool/arm/pci.c b/kvmtool/arm/pci.c
new file mode 100644
index 0000000..ed325fa
--- /dev/null
+++ b/kvmtool/arm/pci.c
@@ -0,0 +1,125 @@
+#include "kvm/devices.h"
+#include "kvm/fdt.h"
+#include "kvm/kvm.h"
+#include "kvm/of_pci.h"
+#include "kvm/pci.h"
+#include "kvm/util.h"
+
+#include "arm-common/pci.h"
+
+/*
+ * An entry in the interrupt-map table looks like:
+ * <pci unit address> <pci interrupt pin> <gic phandle> <gic interrupt>
+ */
+
+struct of_gic_irq {
+ u32 type, num, flags;
+} __attribute__((packed));
+
+struct of_interrupt_map_entry {
+ struct of_pci_irq_mask pci_irq_mask;
+ u32 gic_phandle;
+ u32 gic_addr_hi;
+ u32 gic_addr_lo;
+ struct of_gic_irq gic_irq;
+} __attribute__((packed));
+
+void pci__generate_fdt_nodes(void *fdt)
+{
+ struct device_header *dev_hdr;
+ struct of_interrupt_map_entry irq_map[OF_PCI_IRQ_MAP_MAX];
+ unsigned nentries = 0;
+ /* Bus range */
+ u32 bus_range[] = { cpu_to_fdt32(0), cpu_to_fdt32(0), };
+ /* Configuration Space */
+ u64 cfg_reg_prop[] = { cpu_to_fdt64(KVM_PCI_CFG_AREA),
+ cpu_to_fdt64(ARM_PCI_CFG_SIZE), };
+ /* Describe the memory ranges */
+ struct of_pci_ranges_entry ranges[] = {
+ {
+ .pci_addr = {
+ .hi = cpu_to_fdt32(of_pci_b_ss(OF_PCI_SS_IO)),
+ .mid = 0,
+ .lo = 0,
+ },
+ .cpu_addr = cpu_to_fdt64(KVM_IOPORT_AREA),
+ .length = cpu_to_fdt64(ARM_IOPORT_SIZE),
+ },
+ {
+ .pci_addr = {
+ .hi = cpu_to_fdt32(of_pci_b_ss(OF_PCI_SS_M32)),
+ .mid = cpu_to_fdt32(KVM_PCI_MMIO_AREA >> 32),
+ .lo = cpu_to_fdt32(KVM_PCI_MMIO_AREA),
+ },
+ .cpu_addr = cpu_to_fdt64(KVM_PCI_MMIO_AREA),
+ .length = cpu_to_fdt64(ARM_PCI_MMIO_SIZE),
+ },
+ };
+
+ /* Boilerplate PCI properties */
+ _FDT(fdt_begin_node(fdt, "pci"));
+ _FDT(fdt_property_string(fdt, "device_type", "pci"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x3));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x2));
+ _FDT(fdt_property_cell(fdt, "#interrupt-cells", 0x1));
+ _FDT(fdt_property_string(fdt, "compatible", "pci-host-cam-generic"));
+ _FDT(fdt_property(fdt, "dma-coherent", NULL, 0));
+
+ _FDT(fdt_property(fdt, "bus-range", bus_range, sizeof(bus_range)));
+ _FDT(fdt_property(fdt, "reg", &cfg_reg_prop, sizeof(cfg_reg_prop)));
+ _FDT(fdt_property(fdt, "ranges", ranges, sizeof(ranges)));
+ _FDT(fdt_property_cell(fdt, "msi-parent", PHANDLE_MSI));
+
+ /* Generate the interrupt map ... */
+ dev_hdr = device__first_dev(DEVICE_BUS_PCI);
+ while (dev_hdr && nentries < ARRAY_SIZE(irq_map)) {
+ struct of_interrupt_map_entry *entry = &irq_map[nentries];
+ struct pci_device_header *pci_hdr = dev_hdr->data;
+ u8 dev_num = dev_hdr->dev_num;
+ u8 pin = pci_hdr->irq_pin;
+ u8 irq = pci_hdr->irq_line;
+ u32 irq_flags = pci_hdr->irq_type;
+
+ *entry = (struct of_interrupt_map_entry) {
+ .pci_irq_mask = {
+ .pci_addr = {
+ .hi = cpu_to_fdt32(of_pci_b_ddddd(dev_num)),
+ .mid = 0,
+ .lo = 0,
+ },
+ .pci_pin = cpu_to_fdt32(pin),
+ },
+ .gic_phandle = cpu_to_fdt32(PHANDLE_GIC),
+ .gic_addr_hi = 0,
+ .gic_addr_lo = 0,
+ .gic_irq = {
+ .type = cpu_to_fdt32(GIC_FDT_IRQ_TYPE_SPI),
+ .num = cpu_to_fdt32(irq - GIC_SPI_IRQ_BASE),
+ .flags = cpu_to_fdt32(irq_flags),
+ },
+ };
+
+ nentries++;
+ dev_hdr = device__next_dev(dev_hdr);
+ }
+
+ _FDT(fdt_property(fdt, "interrupt-map", irq_map,
+ sizeof(struct of_interrupt_map_entry) * nentries));
+
+ /* ... and the corresponding mask. */
+ if (nentries) {
+ struct of_pci_irq_mask irq_mask = {
+ .pci_addr = {
+ .hi = cpu_to_fdt32(of_pci_b_ddddd(-1)),
+ .mid = 0,
+ .lo = 0,
+ },
+ .pci_pin = cpu_to_fdt32(7),
+ };
+
+ _FDT(fdt_property(fdt, "interrupt-map-mask", &irq_mask,
+ sizeof(irq_mask)));
+ }
+
+ _FDT(fdt_end_node(fdt));
+}
diff --git a/kvmtool/arm/pmu.c b/kvmtool/arm/pmu.c
new file mode 100644
index 0000000..ffd152e
--- /dev/null
+++ b/kvmtool/arm/pmu.c
@@ -0,0 +1,81 @@
+#include "kvm/fdt.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+
+#include "arm-common/gic.h"
+#include "arm-common/pmu.h"
+
+#ifdef CONFIG_ARM64
+static int set_pmu_attr(struct kvm *kvm, int vcpu_idx,
+ struct kvm_device_attr *attr)
+{
+ int ret, fd;
+
+ fd = kvm->cpus[vcpu_idx]->vcpu_fd;
+
+ ret = ioctl(fd, KVM_HAS_DEVICE_ATTR, attr);
+ if (!ret) {
+ ret = ioctl(fd, KVM_SET_DEVICE_ATTR, attr);
+ if (ret)
+ perror("PMU KVM_SET_DEVICE_ATTR failed");
+ } else {
+ pr_err("Unsupported PMU on vcpu%d\n", vcpu_idx);
+ }
+
+ return ret;
+}
+
+void pmu__generate_fdt_nodes(void *fdt, struct kvm *kvm)
+{
+ const char compatible[] = "arm,armv8-pmuv3";
+ int irq = KVM_ARM_PMUv3_PPI;
+ int i, ret;
+
+ u32 cpu_mask = (((1 << kvm->nrcpus) - 1) << GIC_FDT_IRQ_PPI_CPU_SHIFT) \
+ & GIC_FDT_IRQ_PPI_CPU_MASK;
+ u32 irq_prop[] = {
+ cpu_to_fdt32(GIC_FDT_IRQ_TYPE_PPI),
+ cpu_to_fdt32(irq - 16),
+ cpu_to_fdt32(cpu_mask | IRQ_TYPE_LEVEL_HIGH),
+ };
+
+ if (!kvm->cfg.arch.has_pmuv3)
+ return;
+
+ if (!kvm__supports_extension(kvm, KVM_CAP_ARM_PMU_V3)) {
+ pr_info("PMU unsupported\n");
+ return;
+ }
+
+ for (i = 0; i < kvm->nrcpus; i++) {
+ struct kvm_device_attr pmu_attr;
+
+ pmu_attr = (struct kvm_device_attr){
+ .group = KVM_ARM_VCPU_PMU_V3_CTRL,
+ .addr = (u64)(unsigned long)&irq,
+ .attr = KVM_ARM_VCPU_PMU_V3_IRQ,
+ };
+
+ ret = set_pmu_attr(kvm, i, &pmu_attr);
+ if (ret)
+ return;
+
+ pmu_attr = (struct kvm_device_attr){
+ .group = KVM_ARM_VCPU_PMU_V3_CTRL,
+ .attr = KVM_ARM_VCPU_PMU_V3_INIT,
+ };
+
+ ret = set_pmu_attr(kvm, i, &pmu_attr);
+ if (ret)
+ return;
+ }
+
+ _FDT(fdt_begin_node(fdt, "pmu"));
+ _FDT(fdt_property(fdt, "compatible", compatible, sizeof(compatible)));
+ _FDT(fdt_property(fdt, "interrupts", irq_prop, sizeof(irq_prop)));
+ _FDT(fdt_end_node(fdt));
+}
+#else
+void pmu__generate_fdt_nodes(void *fdt, struct kvm *kvm) { }
+#endif
diff --git a/kvmtool/arm/timer.c b/kvmtool/arm/timer.c
new file mode 100644
index 0000000..71bfe8d
--- /dev/null
+++ b/kvmtool/arm/timer.c
@@ -0,0 +1,41 @@
+#include "kvm/fdt.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+
+#include "arm-common/gic.h"
+#include "arm-common/timer.h"
+
+void timer__generate_fdt_nodes(void *fdt, struct kvm *kvm, int *irqs)
+{
+ const char compatible[] = "arm,armv8-timer\0arm,armv7-timer";
+
+ u32 cpu_mask = (((1 << kvm->nrcpus) - 1) << GIC_FDT_IRQ_PPI_CPU_SHIFT) \
+ & GIC_FDT_IRQ_PPI_CPU_MASK;
+ u32 irq_prop[] = {
+ cpu_to_fdt32(GIC_FDT_IRQ_TYPE_PPI),
+ cpu_to_fdt32(irqs[0]),
+ cpu_to_fdt32(cpu_mask | IRQ_TYPE_LEVEL_LOW),
+
+ cpu_to_fdt32(GIC_FDT_IRQ_TYPE_PPI),
+ cpu_to_fdt32(irqs[1]),
+ cpu_to_fdt32(cpu_mask | IRQ_TYPE_LEVEL_LOW),
+
+ cpu_to_fdt32(GIC_FDT_IRQ_TYPE_PPI),
+ cpu_to_fdt32(irqs[2]),
+ cpu_to_fdt32(cpu_mask | IRQ_TYPE_LEVEL_LOW),
+
+ cpu_to_fdt32(GIC_FDT_IRQ_TYPE_PPI),
+ cpu_to_fdt32(irqs[3]),
+ cpu_to_fdt32(cpu_mask | IRQ_TYPE_LEVEL_LOW),
+ };
+
+ _FDT(fdt_begin_node(fdt, "timer"));
+ _FDT(fdt_property(fdt, "compatible", compatible, sizeof(compatible)));
+ _FDT(fdt_property(fdt, "interrupts", irq_prop, sizeof(irq_prop)));
+ _FDT(fdt_property(fdt, "always-on", NULL, 0));
+ if (kvm->cfg.arch.force_cntfrq > 0)
+ _FDT(fdt_property_cell(fdt, "clock-frequency", kvm->cfg.arch.force_cntfrq));
+ _FDT(fdt_end_node(fdt));
+}
+
diff --git a/kvmtool/builtin-balloon.c b/kvmtool/builtin-balloon.c
new file mode 100644
index 0000000..d158ace
--- /dev/null
+++ b/kvmtool/builtin-balloon.c
@@ -0,0 +1,80 @@
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-balloon.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm.h>
+#include <kvm/kvm-ipc.h>
+
+static const char *instance_name;
+static u64 inflate;
+static u64 deflate;
+
+static const char * const balloon_usage[] = {
+ "lkvm balloon [-n name] [-p pid] [-i amount] [-d amount]",
+ NULL
+};
+
+static const struct option balloon_options[] = {
+ OPT_GROUP("Instance options:"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_GROUP("Balloon options:"),
+ OPT_U64('i', "inflate", &inflate, "Amount to inflate (in MB)"),
+ OPT_U64('d', "deflate", &deflate, "Amount to deflate (in MB)"),
+ OPT_END(),
+};
+
+void kvm_balloon_help(void)
+{
+ usage_with_options(balloon_usage, balloon_options);
+}
+
+static void parse_balloon_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, balloon_options, balloon_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_balloon_help();
+ }
+}
+
+int kvm_cmd_balloon(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+ int amount;
+
+ parse_balloon_options(argc, argv);
+
+ if (inflate == 0 && deflate == 0)
+ kvm_balloon_help();
+
+ if (instance_name == NULL)
+ kvm_balloon_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ if (inflate)
+ amount = inflate;
+ else if (deflate)
+ amount = -deflate;
+ else
+ kvm_balloon_help();
+
+ r = kvm_ipc__send_msg(instance, KVM_IPC_BALLOON,
+ sizeof(amount), (u8 *)&amount);
+
+ close(instance);
+
+ if (r < 0)
+ return -1;
+
+ return 0;
+}
diff --git a/kvmtool/builtin-debug.c b/kvmtool/builtin-debug.c
new file mode 100644
index 0000000..4ae51d2
--- /dev/null
+++ b/kvmtool/builtin-debug.c
@@ -0,0 +1,110 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-debug.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+#include <kvm/read-write.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+#define BUFFER_SIZE 100
+
+static bool all;
+static int nmi = -1;
+static bool dump;
+static const char *instance_name;
+static const char *sysrq;
+
+static const char * const debug_usage[] = {
+ "lkvm debug [--all] [-n name] [-d] [-m vcpu]",
+ NULL
+};
+
+static const struct option debug_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('d', "dump", &dump, "Generate a debug dump from guest"),
+ OPT_INTEGER('m', "nmi", &nmi, "Generate NMI on VCPU"),
+ OPT_STRING('s', "sysrq", &sysrq, "sysrq", "Inject a sysrq"),
+ OPT_GROUP("Instance options:"),
+ OPT_BOOLEAN('a', "all", &all, "Debug all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_debug_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, debug_options, debug_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_debug_help();
+ }
+}
+
+void kvm_debug_help(void)
+{
+ usage_with_options(debug_usage, debug_options);
+}
+
+static int do_debug(const char *name, int sock)
+{
+ char buff[BUFFER_SIZE];
+ struct debug_cmd_params cmd = {.dbg_type = 0};
+ int r;
+
+ if (dump)
+ cmd.dbg_type |= KVM_DEBUG_CMD_TYPE_DUMP;
+
+ if (nmi != -1) {
+ cmd.dbg_type |= KVM_DEBUG_CMD_TYPE_NMI;
+ cmd.cpu = nmi;
+ }
+
+ if (sysrq) {
+ cmd.dbg_type |= KVM_DEBUG_CMD_TYPE_SYSRQ;
+ cmd.sysrq = sysrq[0];
+ }
+
+ r = kvm_ipc__send_msg(sock, KVM_IPC_DEBUG, sizeof(cmd), (u8 *)&cmd);
+ if (r < 0)
+ return r;
+
+ if (!dump)
+ return 0;
+
+ do {
+ r = xread(sock, buff, BUFFER_SIZE);
+ if (r < 0)
+ return 0;
+ printf("%.*s", r, buff);
+ } while (r > 0);
+
+ return 0;
+}
+
+int kvm_cmd_debug(int argc, const char **argv, const char *prefix)
+{
+ parse_debug_options(argc, argv);
+ int instance;
+ int r;
+
+ if (all)
+ return kvm__enumerate_instances(do_debug);
+
+ if (instance_name == NULL)
+ kvm_debug_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_debug(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
diff --git a/kvmtool/builtin-help.c b/kvmtool/builtin-help.c
new file mode 100644
index 0000000..5970fb7
--- /dev/null
+++ b/kvmtool/builtin-help.c
@@ -0,0 +1,63 @@
+#include <stdio.h>
+#include <string.h>
+
+/* user defined headers */
+#include <common-cmds.h>
+
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-help.h>
+#include <kvm/kvm.h>
+
+
+const char kvm_usage_string[] =
+ "lkvm COMMAND [ARGS]";
+
+const char kvm_more_info_string[] =
+ "See 'lkvm help COMMAND' for more information on a specific command.";
+
+
+static void list_common_cmds_help(void)
+{
+ unsigned int i, longest = 0;
+
+ for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
+ if (longest < strlen(common_cmds[i].name))
+ longest = strlen(common_cmds[i].name);
+ }
+
+ puts(" The most commonly used lkvm commands are:");
+ for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
+ printf(" %-*s ", longest, common_cmds[i].name);
+ puts(common_cmds[i].help);
+ }
+}
+
+static void kvm_help(void)
+{
+ printf("\n To start a simple non-privileged shell run '%s run'\n\n"
+ "usage: %s\n\n", KVM_BINARY_NAME, kvm_usage_string);
+ list_common_cmds_help();
+ printf("\n %s\n\n", kvm_more_info_string);
+}
+
+
+static void help_cmd(const char *cmd)
+{
+ struct cmd_struct *p;
+ p = kvm_get_command(kvm_commands, cmd);
+ if (!p)
+ kvm_help();
+ else if (p->help)
+ p->help();
+}
+
+int kvm_cmd_help(int argc, const char **argv, const char *prefix)
+{
+ if (!argv || !*argv) {
+ kvm_help();
+ return 0;
+ }
+ help_cmd(argv[0]);
+ return 0;
+}
diff --git a/kvmtool/builtin-list.c b/kvmtool/builtin-list.c
new file mode 100644
index 0000000..c35be93
--- /dev/null
+++ b/kvmtool/builtin-list.c
@@ -0,0 +1,155 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-list.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <dirent.h>
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+#include <fcntl.h>
+
+static bool run;
+static bool rootfs;
+
+static const char * const list_usage[] = {
+ "lkvm list",
+ NULL
+};
+
+static const struct option list_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('i', "run", &run, "List running instances"),
+ OPT_BOOLEAN('r', "rootfs", &rootfs, "List rootfs instances"),
+ OPT_END()
+};
+
+#define KVM_INSTANCE_RUNNING "running"
+#define KVM_INSTANCE_PAUSED "paused"
+#define KVM_INSTANCE_SHUTOFF "shut off"
+
+void kvm_list_help(void)
+{
+ usage_with_options(list_usage, list_options);
+}
+
+static pid_t get_pid(int sock)
+{
+ pid_t pid;
+ int r;
+
+ r = kvm_ipc__send(sock, KVM_IPC_PID);
+ if (r < 0)
+ return r;
+
+ r = read(sock, &pid, sizeof(pid));
+ if (r < 0)
+ return r;
+
+ return pid;
+}
+
+int get_vmstate(int sock)
+{
+ int vmstate;
+ int r;
+
+ r = kvm_ipc__send(sock, KVM_IPC_VMSTATE);
+ if (r < 0)
+ return r;
+
+ r = read(sock, &vmstate, sizeof(vmstate));
+ if (r < 0)
+ return r;
+
+ return vmstate;
+
+}
+
+static int print_guest(const char *name, int sock)
+{
+ pid_t pid;
+ int vmstate;
+
+ pid = get_pid(sock);
+ vmstate = get_vmstate(sock);
+
+ if ((int)pid < 0 || vmstate < 0)
+ return -1;
+
+ if (vmstate == KVM_VMSTATE_PAUSED)
+ printf("%5d %-20s %s\n", pid, name, KVM_INSTANCE_PAUSED);
+ else
+ printf("%5d %-20s %s\n", pid, name, KVM_INSTANCE_RUNNING);
+
+ return 0;
+}
+
+static int kvm_list_running_instances(void)
+{
+ return kvm__enumerate_instances(print_guest);
+}
+
+static int kvm_list_rootfs(void)
+{
+ DIR *dir;
+ struct dirent *dirent;
+
+ dir = opendir(kvm__get_dir());
+ if (dir == NULL)
+ return -1;
+
+ while ((dirent = readdir(dir))) {
+ if (dirent->d_type == DT_DIR &&
+ strcmp(dirent->d_name, ".") &&
+ strcmp(dirent->d_name, ".."))
+ printf("%5s %-20s %s\n", "", dirent->d_name, KVM_INSTANCE_SHUTOFF);
+ }
+
+ return 0;
+}
+
+static void parse_setup_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, list_options, list_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_list_help();
+ }
+}
+
+int kvm_cmd_list(int argc, const char **argv, const char *prefix)
+{
+ int status, r;
+
+ parse_setup_options(argc, argv);
+
+ if (!run && !rootfs)
+ run = rootfs = true;
+
+ printf("%6s %-20s %s\n", "PID", "NAME", "STATE");
+ printf("------------------------------------\n");
+
+ status = 0;
+
+ if (run) {
+ r = kvm_list_running_instances();
+ if (r < 0)
+ perror("Error listing instances");
+
+ status |= r;
+ }
+
+ if (rootfs) {
+ r = kvm_list_rootfs();
+ if (r < 0)
+ perror("Error listing rootfs");
+
+ status |= r;
+ }
+
+ return status;
+}
diff --git a/kvmtool/builtin-pause.c b/kvmtool/builtin-pause.c
new file mode 100644
index 0000000..c08595a
--- /dev/null
+++ b/kvmtool/builtin-pause.c
@@ -0,0 +1,88 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-pause.h>
+#include <kvm/builtin-list.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+static bool all;
+static const char *instance_name;
+
+static const char * const pause_usage[] = {
+ "lkvm pause [--all] [-n name]",
+ NULL
+};
+
+static const struct option pause_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('a', "all", &all, "Pause all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_pause_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, pause_options, pause_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_pause_help();
+ }
+}
+
+void kvm_pause_help(void)
+{
+ usage_with_options(pause_usage, pause_options);
+}
+
+static int do_pause(const char *name, int sock)
+{
+ int r;
+ int vmstate;
+
+ vmstate = get_vmstate(sock);
+ if (vmstate < 0)
+ return vmstate;
+ if (vmstate == KVM_VMSTATE_PAUSED) {
+ printf("Guest %s is already paused.\n", name);
+ return 0;
+ }
+
+ r = kvm_ipc__send(sock, KVM_IPC_PAUSE);
+ if (r)
+ return r;
+
+ printf("Guest %s paused\n", name);
+
+ return 0;
+}
+
+int kvm_cmd_pause(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+
+ parse_pause_options(argc, argv);
+
+ if (all)
+ return kvm__enumerate_instances(do_pause);
+
+ if (instance_name == NULL)
+ kvm_pause_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_pause(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
diff --git a/kvmtool/builtin-resume.c b/kvmtool/builtin-resume.c
new file mode 100644
index 0000000..0e954b4
--- /dev/null
+++ b/kvmtool/builtin-resume.c
@@ -0,0 +1,88 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-resume.h>
+#include <kvm/builtin-list.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+static bool all;
+static const char *instance_name;
+
+static const char * const resume_usage[] = {
+ "lkvm resume [--all] [-n name]",
+ NULL
+};
+
+static const struct option resume_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('a', "all", &all, "Resume all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_resume_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, resume_options, resume_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_resume_help();
+ }
+}
+
+void kvm_resume_help(void)
+{
+ usage_with_options(resume_usage, resume_options);
+}
+
+static int do_resume(const char *name, int sock)
+{
+ int r;
+ int vmstate;
+
+ vmstate = get_vmstate(sock);
+ if (vmstate < 0)
+ return vmstate;
+ if (vmstate == KVM_VMSTATE_RUNNING) {
+ printf("Guest %s is still running.\n", name);
+ return 0;
+ }
+
+ r = kvm_ipc__send(sock, KVM_IPC_RESUME);
+ if (r)
+ return r;
+
+ printf("Guest %s resumed\n", name);
+
+ return 0;
+}
+
+int kvm_cmd_resume(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+
+ parse_resume_options(argc, argv);
+
+ if (all)
+ return kvm__enumerate_instances(do_resume);
+
+ if (instance_name == NULL)
+ kvm_resume_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_resume(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
diff --git a/kvmtool/builtin-run.c b/kvmtool/builtin-run.c
new file mode 100644
index 0000000..c23e7a2
--- /dev/null
+++ b/kvmtool/builtin-run.c
@@ -0,0 +1,704 @@
+#include "kvm/builtin-run.h"
+
+#include "kvm/builtin-setup.h"
+#include "kvm/virtio-balloon.h"
+#include "kvm/virtio-console.h"
+#include "kvm/parse-options.h"
+#include "kvm/8250-serial.h"
+#include "kvm/framebuffer.h"
+#include "kvm/disk-image.h"
+#include "kvm/threadpool.h"
+#include "kvm/virtio-scsi.h"
+#include "kvm/virtio-blk.h"
+#include "kvm/virtio-net.h"
+#include "kvm/virtio-rng.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/virtio-9p.h"
+#include "kvm/barrier.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/ioport.h"
+#include "kvm/symbol.h"
+#include "kvm/i8042.h"
+#include "kvm/mutex.h"
+#include "kvm/term.h"
+#include "kvm/util.h"
+#include "kvm/strbuf.h"
+#include "kvm/vesa.h"
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/rtc.h"
+#include "kvm/sdl.h"
+#include "kvm/vnc.h"
+#include "kvm/guest_compat.h"
+#include "kvm/kvm-ipc.h"
+#include "kvm/builtin-debug.h"
+
+#include <linux/types.h>
+#include <linux/err.h>
+
+#include <sys/utsname.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <termios.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <stdio.h>
+
+#define MB_SHIFT (20)
+#define KB_SHIFT (10)
+#define GB_SHIFT (30)
+
+__thread struct kvm_cpu *current_kvm_cpu;
+
+static int kvm_run_wrapper;
+
+bool do_debug_print = false;
+
+static const char * const run_usage[] = {
+ "lkvm run [<options>] [<kernel image>]",
+ NULL
+};
+
+enum {
+ KVM_RUN_DEFAULT,
+ KVM_RUN_SANDBOX,
+};
+
+static int img_name_parser(const struct option *opt, const char *arg, int unset)
+{
+ char path[PATH_MAX];
+ struct stat st;
+
+ snprintf(path, PATH_MAX, "%s%s", kvm__get_dir(), arg);
+
+ if ((stat(arg, &st) == 0 && S_ISDIR(st.st_mode)) ||
+ (stat(path, &st) == 0 && S_ISDIR(st.st_mode)))
+ return virtio_9p_img_name_parser(opt, arg, unset);
+ return disk_img_name_parser(opt, arg, unset);
+}
+
+void kvm_run_set_wrapper_sandbox(void)
+{
+ kvm_run_wrapper = KVM_RUN_SANDBOX;
+}
+
+#ifndef OPT_ARCH_RUN
+#define OPT_ARCH_RUN(...)
+#endif
+
+#define BUILD_OPTIONS(name, cfg, kvm) \
+ struct option name[] = { \
+ OPT_GROUP("Basic options:"), \
+ OPT_STRING('\0', "name", &(cfg)->guest_name, "guest name", \
+ "A name for the guest"), \
+ OPT_INTEGER('c', "cpus", &(cfg)->nrcpus, "Number of CPUs"), \
+ OPT_U64('m', "mem", &(cfg)->ram_size, "Virtual machine memory" \
+ " size in MiB."), \
+ OPT_CALLBACK('d', "disk", kvm, "image or rootfs_dir", "Disk " \
+ " image or rootfs directory", img_name_parser, \
+ kvm), \
+ OPT_BOOLEAN('\0', "balloon", &(cfg)->balloon, "Enable virtio" \
+ " balloon"), \
+ OPT_BOOLEAN('\0', "vnc", &(cfg)->vnc, "Enable VNC framebuffer"),\
+ OPT_BOOLEAN('\0', "gtk", &(cfg)->gtk, "Enable GTK framebuffer"),\
+ OPT_BOOLEAN('\0', "sdl", &(cfg)->sdl, "Enable SDL framebuffer"),\
+ OPT_BOOLEAN('\0', "rng", &(cfg)->virtio_rng, "Enable virtio" \
+ " Random Number Generator"), \
+ OPT_CALLBACK('\0', "9p", NULL, "dir_to_share,tag_name", \
+ "Enable virtio 9p to share files between host and" \
+ " guest", virtio_9p_rootdir_parser, kvm), \
+ OPT_STRING('\0', "console", &(cfg)->console, "serial, virtio or"\
+ " hv", "Console to use"), \
+ OPT_STRING('\0', "dev", &(cfg)->dev, "device_file", \
+ "KVM device file"), \
+ OPT_CALLBACK('\0', "tty", NULL, "tty id", \
+ "Remap guest TTY into a pty on the host", \
+ tty_parser, NULL), \
+ OPT_STRING('\0', "sandbox", &(cfg)->sandbox, "script", \
+ "Run this script when booting into custom" \
+ " rootfs"), \
+ OPT_STRING('\0', "hugetlbfs", &(cfg)->hugetlbfs_path, "path", \
+ "Hugetlbfs path"), \
+ \
+ OPT_GROUP("Kernel options:"), \
+ OPT_STRING('k', "kernel", &(cfg)->kernel_filename, "kernel", \
+ "Kernel to boot in virtual machine"), \
+ OPT_STRING('i', "initrd", &(cfg)->initrd_filename, "initrd", \
+ "Initial RAM disk image"), \
+ OPT_STRING('p', "params", &(cfg)->kernel_cmdline, "params", \
+ "Kernel command line arguments"), \
+ OPT_STRING('f', "firmware", &(cfg)->firmware_filename, "firmware",\
+ "Firmware image to boot in virtual machine"), \
+ OPT_STRING('F', "flash", &(cfg)->flash_filename, "flash",\
+ "Flash image to present to virtual machine"), \
+ \
+ OPT_GROUP("Networking options:"), \
+ OPT_CALLBACK_DEFAULT('n', "network", NULL, "network params", \
+ "Create a new guest NIC", \
+ netdev_parser, NULL, kvm), \
+ OPT_BOOLEAN('\0', "no-dhcp", &(cfg)->no_dhcp, "Disable kernel" \
+ " DHCP in rootfs mode"), \
+ \
+ OPT_GROUP("VFIO options:"), \
+ OPT_CALLBACK('\0', "vfio-pci", NULL, "[domain:]bus:dev.fn", \
+ "Assign a PCI device to the virtual machine", \
+ vfio_device_parser, kvm), \
+ \
+ OPT_GROUP("Debug options:"), \
+ OPT_BOOLEAN('\0', "debug", &do_debug_print, \
+ "Enable debug messages"), \
+ OPT_BOOLEAN('\0', "debug-single-step", &(cfg)->single_step, \
+ "Enable single stepping"), \
+ OPT_BOOLEAN('\0', "debug-ioport", &(cfg)->ioport_debug, \
+ "Enable ioport debugging"), \
+ OPT_BOOLEAN('\0', "debug-mmio", &(cfg)->mmio_debug, \
+ "Enable MMIO debugging"), \
+ OPT_INTEGER('\0', "debug-iodelay", &(cfg)->debug_iodelay, \
+ "Delay IO by millisecond"), \
+ \
+ OPT_ARCH(RUN, cfg) \
+ OPT_END() \
+ };
+
+static void *kvm_cpu_thread(void *arg)
+{
+ char name[16];
+
+ current_kvm_cpu = arg;
+
+ sprintf(name, "kvm-vcpu-%lu", current_kvm_cpu->cpu_id);
+ kvm__set_thread_name(name);
+
+ if (kvm_cpu__start(current_kvm_cpu))
+ goto panic_kvm;
+
+ return (void *) (intptr_t) 0;
+
+panic_kvm:
+ fprintf(stderr, "KVM exit reason: %u (\"%s\")\n",
+ current_kvm_cpu->kvm_run->exit_reason,
+ kvm_exit_reasons[current_kvm_cpu->kvm_run->exit_reason]);
+ if (current_kvm_cpu->kvm_run->exit_reason == KVM_EXIT_UNKNOWN)
+ fprintf(stderr, "KVM exit code: 0x%llu\n",
+ (unsigned long long)current_kvm_cpu->kvm_run->hw.hardware_exit_reason);
+
+ kvm_cpu__set_debug_fd(STDOUT_FILENO);
+ kvm_cpu__show_registers(current_kvm_cpu);
+ kvm_cpu__show_code(current_kvm_cpu);
+ kvm_cpu__show_page_tables(current_kvm_cpu);
+
+ return (void *) (intptr_t) 1;
+}
+
+static char kernel[PATH_MAX];
+
+static const char *host_kernels[] = {
+ "/boot/vmlinuz",
+ "/boot/bzImage",
+ NULL
+};
+
+static const char *default_kernels[] = {
+ "./bzImage",
+ "arch/" BUILD_ARCH "/boot/bzImage",
+ "../../arch/" BUILD_ARCH "/boot/bzImage",
+ NULL
+};
+
+static const char *default_vmlinux[] = {
+ "vmlinux",
+ "../../../vmlinux",
+ "../../vmlinux",
+ NULL
+};
+
+static void kernel_usage_with_options(void)
+{
+ const char **k;
+ struct utsname uts;
+
+ fprintf(stderr, "Fatal: could not find default kernel image in:\n");
+ k = &default_kernels[0];
+ while (*k) {
+ fprintf(stderr, "\t%s\n", *k);
+ k++;
+ }
+
+ if (uname(&uts) < 0)
+ return;
+
+ k = &host_kernels[0];
+ while (*k) {
+ if (snprintf(kernel, PATH_MAX, "%s-%s", *k, uts.release) < 0)
+ return;
+ fprintf(stderr, "\t%s\n", kernel);
+ k++;
+ }
+ fprintf(stderr, "\nPlease see '%s run --help' for more options.\n\n",
+ KVM_BINARY_NAME);
+}
+
+static u64 host_ram_size(void)
+{
+ long page_size;
+ long nr_pages;
+
+ nr_pages = sysconf(_SC_PHYS_PAGES);
+ if (nr_pages < 0) {
+ pr_warning("sysconf(_SC_PHYS_PAGES) failed");
+ return 0;
+ }
+
+ page_size = sysconf(_SC_PAGE_SIZE);
+ if (page_size < 0) {
+ pr_warning("sysconf(_SC_PAGE_SIZE) failed");
+ return 0;
+ }
+
+ return (nr_pages * page_size) >> MB_SHIFT;
+}
+
+/*
+ * If user didn't specify how much memory it wants to allocate for the guest,
+ * avoid filling the whole host RAM.
+ */
+#define RAM_SIZE_RATIO 0.8
+
+static u64 get_ram_size(int nr_cpus)
+{
+ u64 available;
+ u64 ram_size;
+
+ ram_size = 64 * (nr_cpus + 3);
+
+ available = host_ram_size() * RAM_SIZE_RATIO;
+ if (!available)
+ available = MIN_RAM_SIZE_MB;
+
+ if (ram_size > available)
+ ram_size = available;
+
+ return ram_size;
+}
+
+static const char *find_kernel(void)
+{
+ const char **k;
+ struct stat st;
+ struct utsname uts;
+
+ k = &default_kernels[0];
+ while (*k) {
+ if (stat(*k, &st) < 0 || !S_ISREG(st.st_mode)) {
+ k++;
+ continue;
+ }
+ strlcpy(kernel, *k, PATH_MAX);
+ return kernel;
+ }
+
+ if (uname(&uts) < 0)
+ return NULL;
+
+ k = &host_kernels[0];
+ while (*k) {
+ if (snprintf(kernel, PATH_MAX, "%s-%s", *k, uts.release) < 0)
+ return NULL;
+
+ if (stat(kernel, &st) < 0 || !S_ISREG(st.st_mode)) {
+ k++;
+ continue;
+ }
+ return kernel;
+
+ }
+ return NULL;
+}
+
+static const char *find_vmlinux(void)
+{
+ const char **vmlinux;
+
+ vmlinux = &default_vmlinux[0];
+ while (*vmlinux) {
+ struct stat st;
+
+ if (stat(*vmlinux, &st) < 0 || !S_ISREG(st.st_mode)) {
+ vmlinux++;
+ continue;
+ }
+ return *vmlinux;
+ }
+ return NULL;
+}
+
+void kvm_run_help(void)
+{
+ struct kvm *kvm = NULL;
+
+ BUILD_OPTIONS(options, &kvm->cfg, kvm);
+ usage_with_options(run_usage, options);
+}
+
+static int kvm_run_set_sandbox(struct kvm *kvm)
+{
+ const char *guestfs_name = kvm->cfg.custom_rootfs_name;
+ char path[PATH_MAX], script[PATH_MAX], *tmp;
+
+ snprintf(path, PATH_MAX, "%s%s/virt/sandbox.sh", kvm__get_dir(), guestfs_name);
+
+ remove(path);
+
+ if (kvm->cfg.sandbox == NULL)
+ return 0;
+
+ tmp = realpath(kvm->cfg.sandbox, NULL);
+ if (tmp == NULL)
+ return -ENOMEM;
+
+ snprintf(script, PATH_MAX, "/host/%s", tmp);
+ free(tmp);
+
+ return symlink(script, path);
+}
+
+static void kvm_write_sandbox_cmd_exactly(int fd, const char *arg)
+{
+ const char *single_quote;
+
+ if (!*arg) { /* zero length string */
+ if (write(fd, "''", 2) <= 0)
+ die("Failed writing sandbox script");
+ return;
+ }
+
+ while (*arg) {
+ single_quote = strchrnul(arg, '\'');
+
+ /* write non-single-quote string as #('string') */
+ if (arg != single_quote) {
+ if (write(fd, "'", 1) <= 0 ||
+ write(fd, arg, single_quote - arg) <= 0 ||
+ write(fd, "'", 1) <= 0)
+ die("Failed writing sandbox script");
+ }
+
+ /* write single quote as #("'") */
+ if (*single_quote) {
+ if (write(fd, "\"'\"", 3) <= 0)
+ die("Failed writing sandbox script");
+ } else
+ break;
+
+ arg = single_quote + 1;
+ }
+}
+
+static void resolve_program(const char *src, char *dst, size_t len)
+{
+ struct stat st;
+ int err;
+
+ err = stat(src, &st);
+
+ if (!err && S_ISREG(st.st_mode)) {
+ char resolved_path[PATH_MAX];
+
+ if (!realpath(src, resolved_path))
+ die("Unable to resolve program %s: %s\n", src, strerror(errno));
+
+ if (snprintf(dst, len, "/host%s", resolved_path) >= (int)len)
+ die("Pathname too long: %s -> %s\n", src, resolved_path);
+
+ } else
+ strlcpy(dst, src, len);
+}
+
+static void kvm_run_write_sandbox_cmd(struct kvm *kvm, const char **argv, int argc)
+{
+ const char script_hdr[] = "#! /bin/bash\n\n";
+ char program[PATH_MAX];
+ int fd;
+
+ remove(kvm->cfg.sandbox);
+
+ fd = open(kvm->cfg.sandbox, O_RDWR | O_CREAT, 0777);
+ if (fd < 0)
+ die("Failed creating sandbox script");
+
+ if (write(fd, script_hdr, sizeof(script_hdr) - 1) <= 0)
+ die("Failed writing sandbox script");
+
+ resolve_program(argv[0], program, PATH_MAX);
+ kvm_write_sandbox_cmd_exactly(fd, program);
+
+ argv++;
+ argc--;
+
+ while (argc) {
+ if (write(fd, " ", 1) <= 0)
+ die("Failed writing sandbox script");
+
+ kvm_write_sandbox_cmd_exactly(fd, argv[0]);
+ argv++;
+ argc--;
+ }
+ if (write(fd, "\n", 1) <= 0)
+ die("Failed writing sandbox script");
+
+ close(fd);
+}
+
+static struct kvm *kvm_cmd_run_init(int argc, const char **argv)
+{
+ static char real_cmdline[2048], default_name[20];
+ unsigned int nr_online_cpus;
+ struct kvm *kvm = kvm__new();
+ bool video;
+
+ if (IS_ERR(kvm))
+ return kvm;
+
+ nr_online_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+ kvm->cfg.custom_rootfs_name = "default";
+
+ while (argc != 0) {
+ BUILD_OPTIONS(options, &kvm->cfg, kvm);
+ argc = parse_options(argc, argv, options, run_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION |
+ PARSE_OPT_KEEP_DASHDASH);
+ if (argc != 0) {
+ /* Cusrom options, should have been handled elsewhere */
+ if (strcmp(argv[0], "--") == 0) {
+ if (kvm_run_wrapper == KVM_RUN_SANDBOX) {
+ kvm->cfg.sandbox = DEFAULT_SANDBOX_FILENAME;
+ kvm_run_write_sandbox_cmd(kvm, argv+1, argc-1);
+ break;
+ }
+ }
+
+ if ((kvm_run_wrapper == KVM_RUN_DEFAULT && kvm->cfg.kernel_filename) ||
+ (kvm_run_wrapper == KVM_RUN_SANDBOX && kvm->cfg.sandbox)) {
+ fprintf(stderr, "Cannot handle parameter: "
+ "%s\n", argv[0]);
+ usage_with_options(run_usage, options);
+ free(kvm);
+ return ERR_PTR(-EINVAL);
+ }
+ if (kvm_run_wrapper == KVM_RUN_SANDBOX) {
+ /*
+ * first unhandled parameter is treated as
+ * sandbox command
+ */
+ kvm->cfg.sandbox = DEFAULT_SANDBOX_FILENAME;
+ kvm_run_write_sandbox_cmd(kvm, argv, argc);
+ } else {
+ /*
+ * first unhandled parameter is treated as a kernel
+ * image
+ */
+ kvm->cfg.kernel_filename = argv[0];
+ }
+ argv++;
+ argc--;
+ }
+
+ }
+
+ kvm->nr_disks = kvm->cfg.image_count;
+
+ if (!kvm->cfg.kernel_filename && !kvm->cfg.firmware_filename) {
+ kvm->cfg.kernel_filename = find_kernel();
+
+ if (!kvm->cfg.kernel_filename) {
+ kernel_usage_with_options();
+ return ERR_PTR(-EINVAL);
+ }
+ }
+
+ kvm->cfg.vmlinux_filename = find_vmlinux();
+ kvm->vmlinux = kvm->cfg.vmlinux_filename;
+
+ if (kvm->cfg.nrcpus == 0)
+ kvm->cfg.nrcpus = nr_online_cpus;
+
+ if (!kvm->cfg.ram_size)
+ kvm->cfg.ram_size = get_ram_size(kvm->cfg.nrcpus);
+
+ if (kvm->cfg.ram_size > host_ram_size())
+ pr_warning("Guest memory size %lluMB exceeds host physical RAM size %lluMB",
+ (unsigned long long)kvm->cfg.ram_size,
+ (unsigned long long)host_ram_size());
+
+ kvm->cfg.ram_size <<= MB_SHIFT;
+
+ if (!kvm->cfg.dev)
+ kvm->cfg.dev = DEFAULT_KVM_DEV;
+
+ if (!kvm->cfg.console)
+ kvm->cfg.console = DEFAULT_CONSOLE;
+
+ video = kvm->cfg.vnc || kvm->cfg.sdl || kvm->cfg.gtk;
+ if (video) {
+ if ((kvm->cfg.vnc && (kvm->cfg.sdl || kvm->cfg.gtk)) ||
+ (kvm->cfg.sdl && kvm->cfg.gtk))
+ die("Only one of --vnc, --sdl or --gtk can be specified");
+ }
+
+ if (!strncmp(kvm->cfg.console, "virtio", 6))
+ kvm->cfg.active_console = CONSOLE_VIRTIO;
+ else if (!strncmp(kvm->cfg.console, "serial", 6))
+ kvm->cfg.active_console = CONSOLE_8250;
+ else if (!strncmp(kvm->cfg.console, "hv", 2))
+ kvm->cfg.active_console = CONSOLE_HV;
+ else
+ pr_warning("No console!");
+
+ if (!kvm->cfg.host_ip)
+ kvm->cfg.host_ip = DEFAULT_HOST_ADDR;
+
+ if (!kvm->cfg.guest_ip)
+ kvm->cfg.guest_ip = DEFAULT_GUEST_ADDR;
+
+ if (!kvm->cfg.guest_mac)
+ kvm->cfg.guest_mac = DEFAULT_GUEST_MAC;
+
+ if (!kvm->cfg.host_mac)
+ kvm->cfg.host_mac = DEFAULT_HOST_MAC;
+
+ if (!kvm->cfg.script)
+ kvm->cfg.script = DEFAULT_SCRIPT;
+
+ if (!kvm->cfg.network)
+ kvm->cfg.network = DEFAULT_NETWORK;
+
+ memset(real_cmdline, 0, sizeof(real_cmdline));
+ kvm__arch_set_cmdline(real_cmdline, video);
+
+ if (video) {
+ strcat(real_cmdline, " console=tty0");
+ } else {
+ switch (kvm->cfg.active_console) {
+ case CONSOLE_HV:
+ /* Fallthrough */
+ case CONSOLE_VIRTIO:
+ strcat(real_cmdline, " console=hvc0");
+ break;
+ case CONSOLE_8250:
+ strcat(real_cmdline, " console=ttyS0");
+ break;
+ }
+ }
+
+ if (!kvm->cfg.guest_name) {
+ if (kvm->cfg.custom_rootfs) {
+ kvm->cfg.guest_name = kvm->cfg.custom_rootfs_name;
+ } else {
+ sprintf(default_name, "guest-%u", getpid());
+ kvm->cfg.guest_name = default_name;
+ }
+ }
+
+ if (!kvm->cfg.using_rootfs && !kvm->cfg.disk_image[0].filename && !kvm->cfg.initrd_filename) {
+ char tmp[PATH_MAX];
+
+ kvm_setup_create_new(kvm->cfg.custom_rootfs_name);
+ kvm_setup_resolv(kvm->cfg.custom_rootfs_name);
+
+ snprintf(tmp, PATH_MAX, "%s%s", kvm__get_dir(), "default");
+ if (virtio_9p__register(kvm, tmp, "/dev/root") < 0)
+ die("Unable to initialize virtio 9p");
+ if (virtio_9p__register(kvm, "/", "hostfs") < 0)
+ die("Unable to initialize virtio 9p");
+ kvm->cfg.using_rootfs = kvm->cfg.custom_rootfs = 1;
+ }
+
+ if (kvm->cfg.using_rootfs) {
+ strcat(real_cmdline, " rw rootflags=trans=virtio,version=9p2000.L,cache=loose rootfstype=9p");
+ if (kvm->cfg.custom_rootfs) {
+ kvm_run_set_sandbox(kvm);
+
+#ifdef CONFIG_GUEST_PRE_INIT
+ strcat(real_cmdline, " init=/virt/pre_init");
+#else
+ strcat(real_cmdline, " init=/virt/init");
+#endif
+
+ if (!kvm->cfg.no_dhcp)
+ strcat(real_cmdline, " ip=dhcp");
+ if (kvm_setup_guest_init(kvm->cfg.custom_rootfs_name))
+ die("Failed to setup init for guest.");
+ }
+ } else if (!kvm->cfg.kernel_cmdline || !strstr(kvm->cfg.kernel_cmdline, "root=")) {
+ strlcat(real_cmdline, " root=/dev/vda rw ", sizeof(real_cmdline));
+ }
+
+ if (kvm->cfg.kernel_cmdline) {
+ strcat(real_cmdline, " ");
+ strlcat(real_cmdline, kvm->cfg.kernel_cmdline, sizeof(real_cmdline));
+ }
+
+ kvm->cfg.real_cmdline = real_cmdline;
+
+ if (kvm->cfg.kernel_filename) {
+ printf(" # %s run -k %s -m %Lu -c %d --name %s\n", KVM_BINARY_NAME,
+ kvm->cfg.kernel_filename,
+ (unsigned long long)kvm->cfg.ram_size / 1024 / 1024,
+ kvm->cfg.nrcpus, kvm->cfg.guest_name);
+ } else if (kvm->cfg.firmware_filename) {
+ printf(" # %s run --firmware %s -m %Lu -c %d --name %s\n", KVM_BINARY_NAME,
+ kvm->cfg.firmware_filename,
+ (unsigned long long)kvm->cfg.ram_size / 1024 / 1024,
+ kvm->cfg.nrcpus, kvm->cfg.guest_name);
+ }
+
+ if (init_list__init(kvm) < 0)
+ die ("Initialisation failed");
+
+ return kvm;
+}
+
+static int kvm_cmd_run_work(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; i < kvm->nrcpus; i++) {
+ if (pthread_create(&kvm->cpus[i]->thread, NULL, kvm_cpu_thread, kvm->cpus[i]) != 0)
+ die("unable to create KVM VCPU thread");
+ }
+
+ /* Only VCPU #0 is going to exit by itself when shutting down */
+ if (pthread_join(kvm->cpus[0]->thread, NULL) != 0)
+ die("unable to join with vcpu 0");
+
+ return kvm_cpu__exit(kvm);
+}
+
+static void kvm_cmd_run_exit(struct kvm *kvm, int guest_ret)
+{
+ compat__print_all_messages();
+
+ init_list__exit(kvm);
+
+ if (guest_ret == 0)
+ printf("\n # KVM session ended normally.\n");
+}
+
+int kvm_cmd_run(int argc, const char **argv, const char *prefix)
+{
+ int ret = -EFAULT;
+ struct kvm *kvm;
+
+ kvm = kvm_cmd_run_init(argc, argv);
+ if (IS_ERR(kvm))
+ return PTR_ERR(kvm);
+
+ ret = kvm_cmd_run_work(kvm);
+ kvm_cmd_run_exit(kvm, ret);
+
+ return ret;
+}
diff --git a/kvmtool/builtin-sandbox.c b/kvmtool/builtin-sandbox.c
new file mode 100644
index 0000000..433f536
--- /dev/null
+++ b/kvmtool/builtin-sandbox.c
@@ -0,0 +1,9 @@
+#include "kvm/builtin-sandbox.h"
+#include "kvm/builtin-run.h"
+
+int kvm_cmd_sandbox(int argc, const char **argv, const char *prefix)
+{
+ kvm_run_set_wrapper_sandbox();
+
+ return kvm_cmd_run(argc, argv, prefix);
+}
diff --git a/kvmtool/builtin-setup.c b/kvmtool/builtin-setup.c
new file mode 100644
index 0000000..b24d2a1
--- /dev/null
+++ b/kvmtool/builtin-setup.c
@@ -0,0 +1,285 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-setup.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/read-write.h>
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <limits.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+static const char *instance_name;
+
+static const char * const setup_usage[] = {
+ "lkvm setup [name]",
+ NULL
+};
+
+static const struct option setup_options[] = {
+ OPT_END()
+};
+
+static void parse_setup_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, setup_options, setup_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0 && instance_name)
+ kvm_setup_help();
+ else
+ instance_name = argv[0];
+ argv++;
+ argc--;
+ }
+}
+
+void kvm_setup_help(void)
+{
+ printf("\n%s setup creates a new rootfs under %s.\n"
+ "This can be used later by the '-d' parameter of '%s run'.\n",
+ KVM_BINARY_NAME, kvm__get_dir(), KVM_BINARY_NAME);
+ usage_with_options(setup_usage, setup_options);
+}
+
+static int copy_file(const char *from, const char *to)
+{
+ int in_fd, out_fd;
+ void *src, *dst;
+ struct stat st;
+ int err = -1;
+
+ in_fd = open(from, O_RDONLY);
+ if (in_fd < 0)
+ return err;
+
+ if (fstat(in_fd, &st) < 0)
+ goto error_close_in;
+
+ out_fd = open(to, O_RDWR | O_CREAT | O_TRUNC, st.st_mode & (S_IRWXU|S_IRWXG|S_IRWXO));
+ if (out_fd < 0)
+ goto error_close_in;
+
+ src = mmap(NULL, st.st_size, PROT_READ, MAP_SHARED, in_fd, 0);
+ if (src == MAP_FAILED)
+ goto error_close_out;
+
+ if (ftruncate(out_fd, st.st_size) < 0)
+ goto error_munmap_src;
+
+ dst = mmap(NULL, st.st_size, PROT_READ|PROT_WRITE, MAP_SHARED, out_fd, 0);
+ if (dst == MAP_FAILED)
+ goto error_munmap_src;
+
+ memcpy(dst, src, st.st_size);
+
+ if (fsync(out_fd) < 0)
+ goto error_munmap_dst;
+
+ err = 0;
+
+error_munmap_dst:
+ munmap(dst, st.st_size);
+error_munmap_src:
+ munmap(src, st.st_size);
+error_close_out:
+ close(out_fd);
+error_close_in:
+ close(in_fd);
+
+ return err;
+}
+
+static const char *guestfs_dirs[] = {
+ "/dev",
+ "/etc",
+ "/home",
+ "/host",
+ "/proc",
+ "/root",
+ "/sys",
+ "/tmp",
+ "/var",
+ "/var/lib",
+ "/virt",
+ "/virt/home",
+};
+
+static const char *guestfs_symlinks[] = {
+ "/bin",
+ "/lib",
+ "/lib64",
+ "/sbin",
+ "/usr",
+ "/etc/ld.so.conf",
+};
+
+#ifdef CONFIG_GUEST_INIT
+static int extract_file(const char *guestfs_name, const char *filename,
+ const void *data, size_t size)
+{
+ char path[PATH_MAX];
+ int fd, ret;
+
+ snprintf(path, PATH_MAX, "%s%s/%s", kvm__get_dir(),
+ guestfs_name, filename);
+
+ fd = open(path, O_EXCL | O_CREAT | O_WRONLY, 0755);
+ if (fd < 0) {
+ if (errno == EEXIST)
+ return 0;
+ die("Fail to setup %s", path);
+ }
+
+ ret = xwrite(fd, data, size);
+ if (ret < 0)
+ die("Fail to setup %s", path);
+ close(fd);
+
+ return 0;
+}
+
+extern unsigned char init_binary[];
+extern unsigned long init_binary_size;
+extern unsigned char pre_init_binary[];
+extern unsigned long pre_init_binary_size;
+
+int kvm_setup_guest_init(const char *guestfs_name)
+{
+ int err;
+
+#ifdef CONFIG_GUEST_PRE_INIT
+ err = extract_file(guestfs_name, "virt/pre_init",
+ pre_init_binary, pre_init_binary_size);
+ if (err)
+ return err;
+#endif
+ err = extract_file(guestfs_name, "virt/init",
+ init_binary, init_binary_size);
+ return err;
+}
+#else
+int kvm_setup_guest_init(const char *guestfs_name)
+{
+ die("Guest init image not compiled in");
+ return 0;
+}
+#endif
+
+static int copy_passwd(const char *guestfs_name)
+{
+ char path[PATH_MAX];
+ FILE *file;
+ int ret;
+
+ snprintf(path, PATH_MAX, "%s%s/etc/passwd", kvm__get_dir(), guestfs_name);
+
+ file = fopen(path, "w");
+ if (!file)
+ return -1;
+
+ ret = fprintf(file, "root:x:0:0:root:/root:/bin/sh\n");
+ if (ret > 0)
+ ret = 0;
+
+ fclose(file);
+
+ return ret;
+}
+
+static int make_guestfs_symlink(const char *guestfs_name, const char *path)
+{
+ char target[PATH_MAX];
+ char name[PATH_MAX];
+
+ snprintf(name, PATH_MAX, "%s%s%s", kvm__get_dir(), guestfs_name, path);
+
+ snprintf(target, PATH_MAX, "/host%s", path);
+
+ return symlink(target, name);
+}
+
+static int make_dir(const char *dir)
+{
+ char name[PATH_MAX];
+
+ snprintf(name, PATH_MAX, "%s%s", kvm__get_dir(), dir);
+
+ return mkdir(name, 0777);
+}
+
+static void make_guestfs_dir(const char *guestfs_name, const char *dir)
+{
+ char name[PATH_MAX];
+
+ snprintf(name, PATH_MAX, "%s%s", guestfs_name, dir);
+
+ make_dir(name);
+}
+
+void kvm_setup_resolv(const char *guestfs_name)
+{
+ char path[PATH_MAX];
+
+ snprintf(path, PATH_MAX, "%s%s/etc/resolv.conf", kvm__get_dir(), guestfs_name);
+
+ copy_file("/etc/resolv.conf", path);
+}
+
+static int do_setup(const char *guestfs_name)
+{
+ unsigned int i;
+ int ret;
+
+ ret = make_dir(guestfs_name);
+ if (ret < 0)
+ return ret;
+
+ for (i = 0; i < ARRAY_SIZE(guestfs_dirs); i++)
+ make_guestfs_dir(guestfs_name, guestfs_dirs[i]);
+
+ for (i = 0; i < ARRAY_SIZE(guestfs_symlinks); i++) {
+ make_guestfs_symlink(guestfs_name, guestfs_symlinks[i]);
+ }
+
+ ret = kvm_setup_guest_init(guestfs_name);
+ if (ret < 0)
+ return ret;
+
+ return copy_passwd(guestfs_name);
+}
+
+int kvm_setup_create_new(const char *guestfs_name)
+{
+ return do_setup(guestfs_name);
+}
+
+int kvm_cmd_setup(int argc, const char **argv, const char *prefix)
+{
+ int r;
+
+ parse_setup_options(argc, argv);
+
+ if (instance_name == NULL)
+ kvm_setup_help();
+
+ r = do_setup(instance_name);
+ if (r == 0)
+ printf("A new rootfs '%s' has been created in '%s%s'.\n\n"
+ "You can now start it by running the following command:\n\n"
+ " %s run -d %s\n",
+ instance_name, kvm__get_dir(), instance_name,
+ KVM_BINARY_NAME,instance_name);
+ else
+ printf("Unable to create rootfs in %s%s: %s\n",
+ kvm__get_dir(), instance_name, strerror(errno));
+
+ return r;
+}
diff --git a/kvmtool/builtin-stat.c b/kvmtool/builtin-stat.c
new file mode 100644
index 0000000..5d6407e
--- /dev/null
+++ b/kvmtool/builtin-stat.c
@@ -0,0 +1,127 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-stat.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <sys/select.h>
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+#include <linux/virtio_balloon.h>
+
+static bool mem;
+static bool all;
+static const char *instance_name;
+
+static const char * const stat_usage[] = {
+ "lkvm stat [command] [--all] [-n name]",
+ NULL
+};
+
+static const struct option stat_options[] = {
+ OPT_GROUP("Commands options:"),
+ OPT_BOOLEAN('m', "memory", &mem, "Display memory statistics"),
+ OPT_GROUP("Instance options:"),
+ OPT_BOOLEAN('a', "all", &all, "All instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_stat_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, stat_options, stat_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_stat_help();
+ }
+}
+
+void kvm_stat_help(void)
+{
+ usage_with_options(stat_usage, stat_options);
+}
+
+static int do_memstat(const char *name, int sock)
+{
+ struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
+ fd_set fdset;
+ struct timeval t = { .tv_sec = 1 };
+ int r;
+ u8 i;
+
+ FD_ZERO(&fdset);
+ FD_SET(sock, &fdset);
+ r = kvm_ipc__send(sock, KVM_IPC_STAT);
+ if (r < 0)
+ return r;
+
+ r = select(1, &fdset, NULL, NULL, &t);
+ if (r < 0) {
+ pr_err("Could not retrieve mem stats from %s", name);
+ return r;
+ }
+ r = read(sock, &stats, sizeof(stats));
+ if (r < 0)
+ return r;
+
+ printf("\n\n\t*** Guest memory statistics ***\n\n");
+ for (i = 0; i < VIRTIO_BALLOON_S_NR; i++) {
+ switch (stats[i].tag) {
+ case VIRTIO_BALLOON_S_SWAP_IN:
+ printf("The amount of memory that has been swapped in (in bytes):");
+ break;
+ case VIRTIO_BALLOON_S_SWAP_OUT:
+ printf("The amount of memory that has been swapped out to disk (in bytes):");
+ break;
+ case VIRTIO_BALLOON_S_MAJFLT:
+ printf("The number of major page faults that have occurred:");
+ break;
+ case VIRTIO_BALLOON_S_MINFLT:
+ printf("The number of minor page faults that have occurred:");
+ break;
+ case VIRTIO_BALLOON_S_MEMFREE:
+ printf("The amount of memory not being used for any purpose (in bytes):");
+ break;
+ case VIRTIO_BALLOON_S_MEMTOT:
+ printf("The total amount of memory available (in bytes):");
+ break;
+ }
+ printf("%llu\n", (unsigned long long)stats[i].val);
+ }
+ printf("\n");
+
+ return 0;
+}
+
+int kvm_cmd_stat(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r = 0;
+
+ parse_stat_options(argc, argv);
+
+ if (!mem)
+ usage_with_options(stat_usage, stat_options);
+
+ if (mem && all)
+ return kvm__enumerate_instances(do_memstat);
+
+ if (instance_name == NULL)
+ kvm_stat_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ if (mem)
+ r = do_memstat(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
diff --git a/kvmtool/builtin-stop.c b/kvmtool/builtin-stop.c
new file mode 100644
index 0000000..6067630
--- /dev/null
+++ b/kvmtool/builtin-stop.c
@@ -0,0 +1,70 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-stop.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+static bool all;
+static const char *instance_name;
+
+static const char * const stop_usage[] = {
+ "lkvm stop [--all] [-n name]",
+ NULL
+};
+
+static const struct option stop_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('a', "all", &all, "Stop all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_stop_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, stop_options, stop_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_stop_help();
+ }
+}
+
+void kvm_stop_help(void)
+{
+ usage_with_options(stop_usage, stop_options);
+}
+
+static int do_stop(const char *name, int sock)
+{
+ return kvm_ipc__send(sock, KVM_IPC_STOP);
+}
+
+int kvm_cmd_stop(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+
+ parse_stop_options(argc, argv);
+
+ if (all)
+ return kvm__enumerate_instances(do_stop);
+
+ if (instance_name == NULL)
+ kvm_stop_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_stop(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
diff --git a/kvmtool/builtin-version.c b/kvmtool/builtin-version.c
new file mode 100644
index 0000000..b8bb859
--- /dev/null
+++ b/kvmtool/builtin-version.c
@@ -0,0 +1,15 @@
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-version.h>
+#include <kvm/kvm.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+int kvm_cmd_version(int argc, const char **argv, const char *prefix)
+{
+ printf("kvm tool %s\n", KVMTOOLS_VERSION);
+
+ return 0;
+}
diff --git a/kvmtool/code16gcc.h b/kvmtool/code16gcc.h
new file mode 100644
index 0000000..d93e480
--- /dev/null
+++ b/kvmtool/code16gcc.h
@@ -0,0 +1,15 @@
+/*
+ * code16gcc.h
+ *
+ * This file is -include'd when compiling 16-bit C code.
+ * Note: this asm() needs to be emitted before gcc emits any code.
+ * Depending on gcc version, this requires -fno-unit-at-a-time or
+ * -fno-toplevel-reorder.
+ *
+ * Hopefully gcc will eventually have a real -m16 option so we can
+ * drop this hack long term.
+ */
+
+#ifndef __ASSEMBLY__
+asm(".code16gcc");
+#endif
diff --git a/kvmtool/config/feature-tests.mak b/kvmtool/config/feature-tests.mak
new file mode 100644
index 0000000..03cdb42
--- /dev/null
+++ b/kvmtool/config/feature-tests.mak
@@ -0,0 +1,208 @@
+define SOURCE_HELLO
+#include <stdio.h>
+int main(void)
+{
+ return puts(\"hi\");
+}
+endef
+
+ifndef NO_DWARF
+define SOURCE_DWARF
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/version.h>
+#ifndef _ELFUTILS_PREREQ
+#error
+#endif
+
+int main(void)
+{
+ Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
+ return (long)dbg;
+}
+endef
+endif
+
+define SOURCE_LIBELF
+#include <libelf.h>
+
+int main(void)
+{
+ Elf *elf = elf_begin(0, ELF_C_READ, 0);
+ return (long)elf;
+}
+endef
+
+define SOURCE_GLIBC
+#include <gnu/libc-version.h>
+
+int main(void)
+{
+ const char *version = gnu_get_libc_version();
+ return (long)version;
+}
+endef
+
+define SOURCE_ELF_MMAP
+#include <libelf.h>
+int main(void)
+{
+ Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0);
+ return (long)elf;
+}
+endef
+
+ifndef NO_NEWT
+define SOURCE_NEWT
+#include <newt.h>
+
+int main(void)
+{
+ newtInit();
+ newtCls();
+ return newtFinished();
+}
+endef
+endif
+
+ifndef NO_LIBPERL
+define SOURCE_PERL_EMBED
+#include <EXTERN.h>
+#include <perl.h>
+
+int main(void)
+{
+perl_alloc();
+return 0;
+}
+endef
+endif
+
+ifndef NO_LIBPYTHON
+define SOURCE_PYTHON_VERSION
+#include <Python.h>
+#if PY_VERSION_HEX >= 0x03000000
+ #error
+#endif
+int main(void){}
+endef
+define SOURCE_PYTHON_EMBED
+#include <Python.h>
+int main(void)
+{
+ Py_Initialize();
+ return 0;
+}
+endef
+endif
+
+define SOURCE_BFD
+#include <bfd.h>
+
+int main(void)
+{
+ bfd_demangle(0, 0, 0);
+ return 0;
+}
+endef
+
+define SOURCE_CPLUS_DEMANGLE
+extern char *cplus_demangle(const char *, int);
+
+int main(void)
+{
+ cplus_demangle(0, 0);
+ return 0;
+}
+endef
+
+define SOURCE_STRLCPY
+#include <stdlib.h>
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+
+int main(void)
+{
+ strlcpy(NULL, NULL, 0);
+ return 0;
+}
+endef
+
+define SOURCE_VNCSERVER
+#include <rfb/rfb.h>
+
+int main(void)
+{
+ rfbIsActive((void *)0);
+ return 0;
+}
+endef
+
+define SOURCE_SDL
+#include <SDL/SDL.h>
+
+int main(void)
+{
+ SDL_Init(SDL_INIT_VIDEO);
+ return 0;
+}
+endef
+
+define SOURCE_ZLIB
+#include <zlib.h>
+
+int main(void)
+{
+ inflateInit2(NULL, 0);
+ return 0;
+}
+endef
+
+define SOURCE_AIO
+#include <libaio.h>
+
+int main(void)
+{
+ io_setup(0, NULL);
+ return 0;
+}
+endef
+
+define SOURCE_STATIC
+#include <stdlib.h>
+
+int main(void)
+{
+ return 0;
+}
+endef
+
+define SOURCE_GTK3
+#include <gtk/gtk.h>
+
+int main(void)
+{
+ gtk_main();
+
+ return 0;
+}
+endef
+
+define SOURCE_LIBFDT
+#include <libfdt.h>
+
+int main(void)
+{
+ fdt_check_header(NULL);
+ return 0;
+}
+endef
+
+define SOURCE_STRLCPY
+#include <string.h>
+
+int main(void)
+{
+ strlcpy(NULL, NULL, 0);
+ return 0;
+}
+endef
diff --git a/kvmtool/config/utilities.mak b/kvmtool/config/utilities.mak
new file mode 100644
index 0000000..612ed1f
--- /dev/null
+++ b/kvmtool/config/utilities.mak
@@ -0,0 +1,204 @@
+# This allows us to work with the newline character:
+define newline
+
+
+endef
+newline := $(newline)
+
+# nl-escape
+#
+# Usage: escape = $(call nl-escape[,escape])
+#
+# This is used as the common way to specify
+# what should replace a newline when escaping
+# newlines; the default is a bizarre string.
+#
+nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n)
+
+# escape-nl
+#
+# Usage: escaped-text = $(call escape-nl,text[,escape])
+#
+# GNU make's $(shell ...) function converts to a
+# single space each newline character in the output
+# produced during the expansion; this may not be
+# desirable.
+#
+# The only solution is to change each newline into
+# something that won't be converted, so that the
+# information can be recovered later with
+# $(call unescape-nl...)
+#
+escape-nl = $(subst $(newline),$(call nl-escape,$(2)),$(1))
+
+# unescape-nl
+#
+# Usage: text = $(call unescape-nl,escaped-text[,escape])
+#
+# See escape-nl.
+#
+unescape-nl = $(subst $(call nl-escape,$(2)),$(newline),$(1))
+
+# shell-escape-nl
+#
+# Usage: $(shell some-command | $(call shell-escape-nl[,escape]))
+#
+# Use this to escape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as a string constant
+# in an `awk' program that is delimited by shell
+# single-quotes, so be wary of the characters
+# that are chosen.
+#
+define shell-escape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "$(nl-escape)" $$0} END {printf t}'
+endef
+
+# shell-unescape-nl
+#
+# Usage: $(shell some-command | $(call shell-unescape-nl[,escape]))
+#
+# Use this to unescape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as an extended regular
+# expression constant in an `awk' program that is
+# delimited by shell single-quotes, so be wary
+# of the characters that are chosen.
+#
+# (The bash shell has a bug where `{gsub(...),...}' is
+# misinterpreted as a brace expansion; this can be
+# overcome by putting a space between `{' and `gsub').
+#
+define shell-unescape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "\n" $$0} END { gsub(/$(nl-escape)/,"\n",t); printf t }'
+endef
+
+# escape-for-shell-sq
+#
+# Usage: embeddable-text = $(call escape-for-shell-sq,text)
+#
+# This function produces text that is suitable for
+# embedding in a shell string that is delimited by
+# single-quotes.
+#
+escape-for-shell-sq = $(subst ','\'',$(1))
+
+# shell-sq
+#
+# Usage: single-quoted-and-escaped-text = $(call shell-sq,text)
+#
+shell-sq = '$(escape-for-shell-sq)'
+
+# shell-wordify
+#
+# Usage: wordified-text = $(call shell-wordify,text)
+#
+# For instance:
+#
+# |define text
+# |hello
+# |world
+# |endef
+# |
+# |target:
+# | echo $(call shell-wordify,$(text))
+#
+# At least GNU make gets confused by expanding a newline
+# within the context of a command line of a makefile rule
+# (this is in constrast to a `$(shell ...)' function call,
+# which can handle it just fine).
+#
+# This function avoids the problem by producing a string
+# that works as a shell word, regardless of whether or
+# not it contains a newline.
+#
+# If the text to be wordified contains a newline, then
+# an intrictate shell command substitution is constructed
+# to render the text as a single line; when the shell
+# processes the resulting escaped text, it transforms
+# it into the original unescaped text.
+#
+# If the text does not contain a newline, then this function
+# produces the same results as the `$(shell-sq)' function.
+#
+shell-wordify = $(if $(findstring $(newline),$(1)),$(_sw-esc-nl),$(shell-sq))
+define _sw-esc-nl
+"$$(echo $(call escape-nl,$(shell-sq),$(2)) | $(call shell-unescape-nl,$(2)))"
+endef
+
+# is-absolute
+#
+# Usage: bool-value = $(call is-absolute,path)
+#
+is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+
+# lookup
+#
+# Usage: absolute-executable-path-or-empty = $(call lookup,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+# trying too hard and getting things wrong).
+#
+lookup = $(call unescape-nl,$(shell sh -c $(_l-sh)))
+_l-sh = $(call shell-sq,command -v $(shell-sq) | $(call shell-escape-nl,))
+
+# is-executable
+#
+# Usage: bool-value = $(call is-executable,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+# trying too hard and getting things wrong).
+#
+is-executable = $(call _is-executable-helper,$(shell-sq))
+_is-executable-helper = $(shell sh -c $(_is-executable-sh))
+_is-executable-sh = $(call shell-sq,test -f $(1) -a -x $(1) && echo y)
+
+# get-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable,path)
+#
+# The goal is to get an absolute path for an executable;
+# the `command -v' is defined by POSIX, but it's not
+# necessarily very portable, so it's only used if
+# relative path resolution is requested, as determined
+# by the presence of a leading `/'.
+#
+get-executable = $(if $(1),$(if $(is-absolute),$(_ge-abspath),$(lookup)))
+_ge-abspath = $(if $(is-executable),$(1))
+
+# get-supplied-or-default-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
+#
+define get-executable-or-default
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
+endef
+_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2)))
+_gea_warn = $(warning The path '$(1)' is not executable.)
+_gea_err = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-cc
+# Usage: option = $(call try-cc, source-to-build, cc-options)
+try-cc = $(shell sh -c \
+ 'TMP="$(OUTPUT)$(TMPOUT).$$$$"; \
+ echo "$(1)" | \
+ $(CC) -x c -c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+ rm -f "$$TMP"')
+
+# try-build
+# Usage: option = $(call try-build, source-to-build, cc-options, link-options)
+try-build = $(shell sh -c \
+ 'TMP="$(OUTPUT)$(TMPOUT).$$$$"; \
+ echo "$(1)" | \
+ $(CC) -x c - $(2) $(3) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+ rm -f "$$TMP"')
+
+# binary-to-C
+# create a C source file describing the binary input file as an array
+# Usage: $(call binary-to-C,binary-file,C-symbol-name,C-output-file)
+binary-to-C = stat -c "unsigned long $(2)_size = %s;" $1 > $3; \
+ echo "unsigned char $(2)[] = {" >> $3; \
+ od -v -tx1 -An -w12 $1 | sed -e "s/ \(..\)/0x\1, /g" >> $3; \
+ echo "};" >> $3
diff --git a/kvmtool/devices.c b/kvmtool/devices.c
new file mode 100644
index 0000000..41cffdd
--- /dev/null
+++ b/kvmtool/devices.c
@@ -0,0 +1,93 @@
+#include "kvm/devices.h"
+#include "kvm/kvm.h"
+
+#include <linux/err.h>
+#include <linux/rbtree.h>
+
+struct device_bus {
+ struct rb_root root;
+ int dev_num;
+};
+
+static struct device_bus device_trees[DEVICE_BUS_MAX] = {
+ [0 ... (DEVICE_BUS_MAX - 1)] = { RB_ROOT, 0 },
+};
+
+int device__register(struct device_header *dev)
+{
+ struct device_bus *bus;
+ struct rb_node **node, *parent = NULL;
+
+ if (dev->bus_type >= DEVICE_BUS_MAX) {
+ pr_warning("Ignoring device registration on unknown bus %d\n",
+ dev->bus_type);
+ return -EINVAL;
+ }
+
+ bus = &device_trees[dev->bus_type];
+ dev->dev_num = bus->dev_num++;
+
+ node = &bus->root.rb_node;
+ while (*node) {
+ int num = rb_entry(*node, struct device_header, node)->dev_num;
+ int result = dev->dev_num - num;
+
+ parent = *node;
+ if (result < 0)
+ node = &((*node)->rb_left);
+ else if (result > 0)
+ node = &((*node)->rb_right);
+ else
+ return -EEXIST;
+ }
+
+ rb_link_node(&dev->node, parent, node);
+ rb_insert_color(&dev->node, &bus->root);
+ return 0;
+}
+
+void device__unregister(struct device_header *dev)
+{
+ struct device_bus *bus = &device_trees[dev->bus_type];
+ rb_erase(&dev->node, &bus->root);
+}
+
+struct device_header *device__find_dev(enum device_bus_type bus_type, u8 dev_num)
+{
+ struct rb_node *node;
+
+ if (bus_type >= DEVICE_BUS_MAX)
+ return ERR_PTR(-EINVAL);
+
+ node = device_trees[bus_type].root.rb_node;
+ while (node) {
+ struct device_header *dev = rb_entry(node, struct device_header,
+ node);
+ if (dev_num < dev->dev_num) {
+ node = node->rb_left;
+ } else if (dev_num > dev->dev_num) {
+ node = node->rb_right;
+ } else {
+ return dev;
+ }
+ }
+
+ return NULL;
+}
+
+struct device_header *device__first_dev(enum device_bus_type bus_type)
+{
+ struct rb_node *node;
+
+ if (bus_type >= DEVICE_BUS_MAX)
+ return NULL;
+
+ node = rb_first(&device_trees[bus_type].root);
+ return node ? rb_entry(node, struct device_header, node) : NULL;
+}
+
+struct device_header *device__next_dev(struct device_header *dev)
+{
+ struct rb_node *node = rb_next(&dev->node);
+ return node ? rb_entry(node, struct device_header, node) : NULL;
+}
diff --git a/kvmtool/disk/aio.c b/kvmtool/disk/aio.c
new file mode 100644
index 0000000..a7418c8
--- /dev/null
+++ b/kvmtool/disk/aio.c
@@ -0,0 +1,150 @@
+#include <libaio.h>
+#include <pthread.h>
+#include <sys/eventfd.h>
+
+#include "kvm/brlock.h"
+#include "kvm/disk-image.h"
+#include "kvm/kvm.h"
+#include "linux/list.h"
+
+#define AIO_MAX 256
+
+static int aio_submit(struct disk_image *disk, int nr, struct iocb **ios)
+{
+ int ret;
+
+ __sync_fetch_and_add(&disk->aio_inflight, nr);
+ /*
+ * A wmb() is needed here, to ensure disk_aio_thread() sees this
+ * increase after receiving the events. It is included in the
+ * __sync_fetch_and_add (as a full barrier).
+ */
+restart:
+ ret = io_submit(disk->ctx, nr, ios);
+ if (ret == -EAGAIN)
+ goto restart;
+ else if (ret <= 0)
+ /* disk_aio_thread() is never going to see those */
+ __sync_fetch_and_sub(&disk->aio_inflight, nr);
+
+ return ret;
+}
+
+ssize_t raw_image__read_async(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount,
+ void *param)
+{
+ struct iocb iocb;
+ u64 offset = sector << SECTOR_SHIFT;
+ struct iocb *ios[1] = { &iocb };
+
+ io_prep_preadv(&iocb, disk->fd, iov, iovcount, offset);
+ io_set_eventfd(&iocb, disk->evt);
+ iocb.data = param;
+
+ return aio_submit(disk, 1, ios);
+}
+
+ssize_t raw_image__write_async(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount,
+ void *param)
+{
+ struct iocb iocb;
+ u64 offset = sector << SECTOR_SHIFT;
+ struct iocb *ios[1] = { &iocb };
+
+ io_prep_pwritev(&iocb, disk->fd, iov, iovcount, offset);
+ io_set_eventfd(&iocb, disk->evt);
+ iocb.data = param;
+
+ return aio_submit(disk, 1, ios);
+}
+
+/*
+ * When this function returns there are no in-flight I/O. Caller ensures that
+ * io_submit() isn't called concurrently.
+ *
+ * Returns an inaccurate number of I/O that was in-flight when the function was
+ * called.
+ */
+int raw_image__wait(struct disk_image *disk)
+{
+ u64 inflight = disk->aio_inflight;
+
+ while (disk->aio_inflight) {
+ usleep(100);
+ barrier();
+ }
+
+ return inflight;
+}
+
+static int disk_aio_get_events(struct disk_image *disk)
+{
+ struct io_event event[AIO_MAX];
+ struct timespec notime = {0};
+ int nr, i;
+
+ do {
+ nr = io_getevents(disk->ctx, 1, ARRAY_SIZE(event), event, ¬ime);
+ for (i = 0; i < nr; i++)
+ disk->disk_req_cb(event[i].data, event[i].res);
+
+ /* Pairs with wmb() in aio_submit() */
+ rmb();
+ __sync_fetch_and_sub(&disk->aio_inflight, nr);
+
+ } while (nr > 0);
+
+ return 0;
+}
+
+static void *disk_aio_thread(void *param)
+{
+ struct disk_image *disk = param;
+ u64 dummy;
+
+ kvm__set_thread_name("disk-image-io");
+
+ while (read(disk->evt, &dummy, sizeof(dummy)) > 0) {
+ if (disk_aio_get_events(disk))
+ break;
+ }
+
+ return NULL;
+}
+
+int disk_aio_setup(struct disk_image *disk)
+{
+ int r;
+
+ /* No need to setup AIO if the disk ops won't make use of it */
+ if (!disk->ops->async)
+ return 0;
+
+ disk->evt = eventfd(0, 0);
+ if (disk->evt < 0)
+ return -errno;
+
+ io_setup(AIO_MAX, &disk->ctx);
+ r = pthread_create(&disk->thread, NULL, disk_aio_thread, disk);
+ if (r) {
+ r = -errno;
+ close(disk->evt);
+ return r;
+ }
+
+ disk->async = true;
+ return 0;
+}
+
+void disk_aio_destroy(struct disk_image *disk)
+{
+ if (!disk->async)
+ return;
+
+ pthread_cancel(disk->thread);
+ pthread_join(disk->thread, NULL);
+ close(disk->evt);
+ io_destroy(disk->ctx);
+}
diff --git a/kvmtool/disk/blk.c b/kvmtool/disk/blk.c
new file mode 100644
index 0000000..b4c9fba
--- /dev/null
+++ b/kvmtool/disk/blk.c
@@ -0,0 +1,72 @@
+#include "kvm/disk-image.h"
+
+#include <linux/err.h>
+#include <mntent.h>
+
+/*
+ * raw image and blk dev are similar, so reuse raw image ops.
+ */
+static struct disk_image_operations blk_dev_ops = {
+ .read = raw_image__read,
+ .write = raw_image__write,
+ .wait = raw_image__wait,
+ .async = true,
+};
+
+static bool is_mounted(struct stat *st)
+{
+ struct stat st_buf;
+ struct mntent *mnt;
+ FILE *f;
+
+ f = setmntent("/proc/mounts", "r");
+ if (!f)
+ return false;
+
+ while ((mnt = getmntent(f)) != NULL) {
+ if (stat(mnt->mnt_fsname, &st_buf) == 0 &&
+ S_ISBLK(st_buf.st_mode) && st->st_rdev == st_buf.st_rdev) {
+ fclose(f);
+ return true;
+ }
+ }
+
+ fclose(f);
+ return false;
+}
+
+struct disk_image *blkdev__probe(const char *filename, int flags, struct stat *st)
+{
+ int fd, r;
+ u64 size;
+
+ if (!S_ISBLK(st->st_mode))
+ return ERR_PTR(-EINVAL);
+
+ if (is_mounted(st)) {
+ pr_err("Block device %s is already mounted! Unmount before use.",
+ filename);
+ return ERR_PTR(-EINVAL);
+ }
+
+ /*
+ * Be careful! We are opening host block device!
+ * Open it readonly since we do not want to break user's data on disk.
+ */
+ fd = open(filename, flags);
+ if (fd < 0)
+ return ERR_PTR(fd);
+
+ if (ioctl(fd, BLKGETSIZE64, &size) < 0) {
+ r = -errno;
+ close(fd);
+ return ERR_PTR(r);
+ }
+
+ /*
+ * FIXME: This will not work on 32-bit host because we can not
+ * mmap large disk. There is not enough virtual address space
+ * in 32-bit host. However, this works on 64-bit host.
+ */
+ return disk_image__new(fd, size, &blk_dev_ops, DISK_IMAGE_REGULAR);
+}
diff --git a/kvmtool/disk/core.c b/kvmtool/disk/core.c
new file mode 100644
index 0000000..8d95c98
--- /dev/null
+++ b/kvmtool/disk/core.c
@@ -0,0 +1,345 @@
+#include "kvm/disk-image.h"
+#include "kvm/qcow.h"
+#include "kvm/virtio-blk.h"
+#include "kvm/kvm.h"
+
+#include <linux/err.h>
+#include <poll.h>
+
+int debug_iodelay;
+
+static int disk_image__close(struct disk_image *disk);
+
+int disk_img_name_parser(const struct option *opt, const char *arg, int unset)
+{
+ const char *cur;
+ char *sep;
+ struct kvm *kvm = opt->ptr;
+
+ if (kvm->cfg.image_count >= MAX_DISK_IMAGES)
+ die("Currently only 4 images are supported");
+
+ kvm->cfg.disk_image[kvm->cfg.image_count].filename = arg;
+ cur = arg;
+
+ if (strncmp(arg, "scsi:", 5) == 0) {
+ sep = strstr(arg, ":");
+ if (sep)
+ kvm->cfg.disk_image[kvm->cfg.image_count].wwpn = sep + 1;
+ sep = strstr(sep + 1, ":");
+ if (sep) {
+ *sep = 0;
+ kvm->cfg.disk_image[kvm->cfg.image_count].tpgt = sep + 1;
+ }
+ cur = sep + 1;
+ }
+
+ do {
+ sep = strstr(cur, ",");
+ if (sep) {
+ if (strncmp(sep + 1, "ro", 2) == 0)
+ kvm->cfg.disk_image[kvm->cfg.image_count].readonly = true;
+ else if (strncmp(sep + 1, "direct", 6) == 0)
+ kvm->cfg.disk_image[kvm->cfg.image_count].direct = true;
+ *sep = 0;
+ cur = sep + 1;
+ }
+ } while (sep);
+
+ kvm->cfg.image_count++;
+
+ return 0;
+}
+
+struct disk_image *disk_image__new(int fd, u64 size,
+ struct disk_image_operations *ops,
+ int use_mmap)
+{
+ struct disk_image *disk;
+ int r;
+
+ disk = malloc(sizeof *disk);
+ if (!disk)
+ return ERR_PTR(-ENOMEM);
+
+ *disk = (struct disk_image) {
+ .fd = fd,
+ .size = size,
+ .ops = ops,
+ };
+
+ if (use_mmap == DISK_IMAGE_MMAP) {
+ /*
+ * The write to disk image will be discarded
+ */
+ disk->priv = mmap(NULL, size, PROT_RW, MAP_PRIVATE | MAP_NORESERVE, fd, 0);
+ if (disk->priv == MAP_FAILED) {
+ r = -errno;
+ goto err_free_disk;
+ }
+ }
+
+ r = disk_aio_setup(disk);
+ if (r)
+ goto err_unmap_disk;
+
+ return disk;
+
+err_unmap_disk:
+ if (disk->priv)
+ munmap(disk->priv, size);
+err_free_disk:
+ free(disk);
+ return ERR_PTR(r);
+}
+
+static struct disk_image *disk_image__open(const char *filename, bool readonly, bool direct)
+{
+ struct disk_image *disk;
+ struct stat st;
+ int fd, flags;
+
+ if (readonly)
+ flags = O_RDONLY;
+ else
+ flags = O_RDWR;
+ if (direct)
+ flags |= O_DIRECT;
+
+ if (stat(filename, &st) < 0)
+ return ERR_PTR(-errno);
+
+ /* blk device ?*/
+ disk = blkdev__probe(filename, flags, &st);
+ if (!IS_ERR_OR_NULL(disk)) {
+ disk->readonly = readonly;
+ return disk;
+ }
+
+ fd = open(filename, flags);
+ if (fd < 0)
+ return ERR_PTR(fd);
+
+ /* qcow image ?*/
+ disk = qcow_probe(fd, true);
+ if (!IS_ERR_OR_NULL(disk)) {
+ pr_warning("Forcing read-only support for QCOW");
+ disk->readonly = true;
+ return disk;
+ }
+
+ /* raw image ?*/
+ disk = raw_image__probe(fd, &st, readonly);
+ if (!IS_ERR_OR_NULL(disk)) {
+ disk->readonly = readonly;
+ return disk;
+ }
+
+ if (close(fd) < 0)
+ pr_warning("close() failed");
+
+ return ERR_PTR(-ENOSYS);
+}
+
+static struct disk_image **disk_image__open_all(struct kvm *kvm)
+{
+ struct disk_image **disks;
+ const char *filename;
+ const char *wwpn;
+ const char *tpgt;
+ bool readonly;
+ bool direct;
+ void *err;
+ int i;
+ struct disk_image_params *params = (struct disk_image_params *)&kvm->cfg.disk_image;
+ int count = kvm->cfg.image_count;
+
+ if (!count)
+ return ERR_PTR(-EINVAL);
+ if (count > MAX_DISK_IMAGES)
+ return ERR_PTR(-ENOSPC);
+
+ disks = calloc(count, sizeof(*disks));
+ if (!disks)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < count; i++) {
+ filename = params[i].filename;
+ readonly = params[i].readonly;
+ direct = params[i].direct;
+ wwpn = params[i].wwpn;
+ tpgt = params[i].tpgt;
+
+ if (wwpn) {
+ disks[i] = malloc(sizeof(struct disk_image));
+ if (!disks[i])
+ return ERR_PTR(-ENOMEM);
+ disks[i]->wwpn = wwpn;
+ disks[i]->tpgt = tpgt;
+ continue;
+ }
+
+ if (!filename)
+ continue;
+
+ disks[i] = disk_image__open(filename, readonly, direct);
+ if (IS_ERR_OR_NULL(disks[i])) {
+ pr_err("Loading disk image '%s' failed", filename);
+ err = disks[i];
+ goto error;
+ }
+ disks[i]->debug_iodelay = kvm->cfg.debug_iodelay;
+ }
+
+ return disks;
+error:
+ for (i = 0; i < count; i++)
+ if (!IS_ERR_OR_NULL(disks[i]))
+ disk_image__close(disks[i]);
+
+ free(disks);
+ return err;
+}
+
+int disk_image__wait(struct disk_image *disk)
+{
+ if (disk->ops->wait)
+ return disk->ops->wait(disk);
+
+ return 0;
+}
+
+int disk_image__flush(struct disk_image *disk)
+{
+ if (disk->ops->flush)
+ return disk->ops->flush(disk);
+
+ return fsync(disk->fd);
+}
+
+static int disk_image__close(struct disk_image *disk)
+{
+ /* If there was no disk image then there's nothing to do: */
+ if (!disk)
+ return 0;
+
+ disk_aio_destroy(disk);
+
+ if (disk->ops->close)
+ return disk->ops->close(disk);
+
+ if (close(disk->fd) < 0)
+ pr_warning("close() failed");
+
+ free(disk);
+
+ return 0;
+}
+
+static int disk_image__close_all(struct disk_image **disks, int count)
+{
+ while (count)
+ disk_image__close(disks[--count]);
+
+ free(disks);
+
+ return 0;
+}
+
+/*
+ * Fill iov with disk data, starting from sector 'sector'.
+ * Return amount of bytes read.
+ */
+ssize_t disk_image__read(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t total = 0;
+
+ if (debug_iodelay)
+ msleep(debug_iodelay);
+
+ if (disk->ops->read) {
+ total = disk->ops->read(disk, sector, iov, iovcount, param);
+ if (total < 0) {
+ pr_info("disk_image__read error: total=%ld\n", (long)total);
+ return total;
+ }
+ }
+
+ if (!disk->async && disk->disk_req_cb)
+ disk->disk_req_cb(param, total);
+
+ return total;
+}
+
+/*
+ * Write iov to disk, starting from sector 'sector'.
+ * Return amount of bytes written.
+ */
+ssize_t disk_image__write(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t total = 0;
+
+ if (debug_iodelay)
+ msleep(debug_iodelay);
+
+ if (disk->ops->write) {
+ /*
+ * Try writev based operation first
+ */
+
+ total = disk->ops->write(disk, sector, iov, iovcount, param);
+ if (total < 0) {
+ pr_info("disk_image__write error: total=%ld\n", (long)total);
+ return total;
+ }
+ } else {
+ /* Do nothing */
+ }
+
+ if (!disk->async && disk->disk_req_cb)
+ disk->disk_req_cb(param, total);
+
+ return total;
+}
+
+ssize_t disk_image__get_serial(struct disk_image *disk, void *buffer, ssize_t *len)
+{
+ struct stat st;
+ int r;
+
+ r = fstat(disk->fd, &st);
+ if (r)
+ return r;
+
+ *len = snprintf(buffer, *len, "%llu%llu%llu",
+ (unsigned long long)st.st_dev,
+ (unsigned long long)st.st_rdev,
+ (unsigned long long)st.st_ino);
+ return *len;
+}
+
+void disk_image__set_callback(struct disk_image *disk,
+ void (*disk_req_cb)(void *param, long len))
+{
+ disk->disk_req_cb = disk_req_cb;
+}
+
+int disk_image__init(struct kvm *kvm)
+{
+ if (kvm->cfg.image_count) {
+ kvm->disks = disk_image__open_all(kvm);
+ if (IS_ERR(kvm->disks))
+ return PTR_ERR(kvm->disks);
+ }
+
+ return 0;
+}
+dev_base_init(disk_image__init);
+
+int disk_image__exit(struct kvm *kvm)
+{
+ return disk_image__close_all(kvm->disks, kvm->nr_disks);
+}
+dev_base_exit(disk_image__exit);
diff --git a/kvmtool/disk/qcow.c b/kvmtool/disk/qcow.c
new file mode 100644
index 0000000..dd6be62
--- /dev/null
+++ b/kvmtool/disk/qcow.c
@@ -0,0 +1,1526 @@
+#include "kvm/qcow.h"
+
+#include "kvm/disk-image.h"
+#include "kvm/read-write.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <errno.h>
+#ifdef CONFIG_HAS_ZLIB
+#include <zlib.h>
+#endif
+
+#include <linux/err.h>
+#include <linux/byteorder.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+static int update_cluster_refcount(struct qcow *q, u64 clust_idx, u16 append);
+static int qcow_write_refcount_table(struct qcow *q);
+static u64 qcow_alloc_clusters(struct qcow *q, u64 size, int update_ref);
+static void qcow_free_clusters(struct qcow *q, u64 clust_start, u64 size);
+
+static inline int qcow_pwrite_sync(int fd,
+ void *buf, size_t count, off_t offset)
+{
+ if (pwrite_in_full(fd, buf, count, offset) < 0)
+ return -1;
+
+ return fdatasync(fd);
+}
+
+static int l2_table_insert(struct rb_root *root, struct qcow_l2_table *new)
+{
+ struct rb_node **link = &(root->rb_node), *parent = NULL;
+ u64 offset = new->offset;
+
+ /* search the tree */
+ while (*link) {
+ struct qcow_l2_table *t;
+
+ t = rb_entry(*link, struct qcow_l2_table, node);
+ if (!t)
+ goto error;
+
+ parent = *link;
+
+ if (t->offset > offset)
+ link = &(*link)->rb_left;
+ else if (t->offset < offset)
+ link = &(*link)->rb_right;
+ else
+ goto out;
+ }
+
+ /* add new node */
+ rb_link_node(&new->node, parent, link);
+ rb_insert_color(&new->node, root);
+out:
+ return 0;
+error:
+ return -1;
+}
+
+static struct qcow_l2_table *l2_table_lookup(struct rb_root *root, u64 offset)
+{
+ struct rb_node *link = root->rb_node;
+
+ while (link) {
+ struct qcow_l2_table *t;
+
+ t = rb_entry(link, struct qcow_l2_table, node);
+ if (!t)
+ goto out;
+
+ if (t->offset > offset)
+ link = link->rb_left;
+ else if (t->offset < offset)
+ link = link->rb_right;
+ else
+ return t;
+ }
+out:
+ return NULL;
+}
+
+static void l1_table_free_cache(struct qcow_l1_table *l1t)
+{
+ struct rb_root *r = &l1t->root;
+ struct list_head *pos, *n;
+ struct qcow_l2_table *t;
+
+ list_for_each_safe(pos, n, &l1t->lru_list) {
+ /* Remove cache table from the list and RB tree */
+ list_del(pos);
+ t = list_entry(pos, struct qcow_l2_table, list);
+ rb_erase(&t->node, r);
+
+ /* Free the cached node */
+ free(t);
+ }
+}
+
+static int qcow_l2_cache_write(struct qcow *q, struct qcow_l2_table *c)
+{
+ struct qcow_header *header = q->header;
+ u64 size;
+
+ if (!c->dirty)
+ return 0;
+
+ size = 1 << header->l2_bits;
+
+ if (qcow_pwrite_sync(q->fd, c->table,
+ size * sizeof(u64), c->offset) < 0)
+ return -1;
+
+ c->dirty = 0;
+
+ return 0;
+}
+
+static int cache_table(struct qcow *q, struct qcow_l2_table *c)
+{
+ struct qcow_l1_table *l1t = &q->table;
+ struct rb_root *r = &l1t->root;
+ struct qcow_l2_table *lru;
+
+ if (l1t->nr_cached == MAX_CACHE_NODES) {
+ /*
+ * The node at the head of the list is least recently used
+ * node. Remove it from the list and replaced with a new node.
+ */
+ lru = list_first_entry(&l1t->lru_list, struct qcow_l2_table, list);
+
+ /* Remove the node from the cache */
+ rb_erase(&lru->node, r);
+ list_del_init(&lru->list);
+ l1t->nr_cached--;
+
+ /* Free the LRUed node */
+ free(lru);
+ }
+
+ /* Add new node in RB Tree: Helps in searching faster */
+ if (l2_table_insert(r, c) < 0)
+ goto error;
+
+ /* Add in LRU replacement list */
+ list_add_tail(&c->list, &l1t->lru_list);
+ l1t->nr_cached++;
+
+ return 0;
+error:
+ return -1;
+}
+
+static struct qcow_l2_table *l2_table_search(struct qcow *q, u64 offset)
+{
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+
+ l2t = l2_table_lookup(&l1t->root, offset);
+ if (!l2t)
+ return NULL;
+
+ /* Update the LRU state, by moving the searched node to list tail */
+ list_move_tail(&l2t->list, &l1t->lru_list);
+
+ return l2t;
+}
+
+/* Allocates a new node for caching L2 table */
+static struct qcow_l2_table *new_cache_table(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l2_table *c;
+ u64 l2t_sz;
+ u64 size;
+
+ l2t_sz = 1 << header->l2_bits;
+ size = sizeof(*c) + l2t_sz * sizeof(u64);
+ c = calloc(1, size);
+ if (!c)
+ goto out;
+
+ c->offset = offset;
+ RB_CLEAR_NODE(&c->node);
+ INIT_LIST_HEAD(&c->list);
+out:
+ return c;
+}
+
+static inline u64 get_l1_index(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+
+ return offset >> (header->l2_bits + header->cluster_bits);
+}
+
+static inline u64 get_l2_index(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+
+ return (offset >> (header->cluster_bits)) & ((1 << header->l2_bits)-1);
+}
+
+static inline u64 get_cluster_offset(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+
+ return offset & ((1 << header->cluster_bits)-1);
+}
+
+static struct qcow_l2_table *qcow_read_l2_table(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l2_table *l2t;
+ u64 size;
+
+ size = 1 << header->l2_bits;
+
+ /* search an entry for offset in cache */
+ l2t = l2_table_search(q, offset);
+ if (l2t)
+ return l2t;
+
+ /* allocate new node for caching l2 table */
+ l2t = new_cache_table(q, offset);
+ if (!l2t)
+ goto error;
+
+ /* table not cached: read from the disk */
+ if (pread_in_full(q->fd, l2t->table, size * sizeof(u64), offset) < 0)
+ goto error;
+
+ /* cache the table */
+ if (cache_table(q, l2t) < 0)
+ goto error;
+
+ return l2t;
+error:
+ free(l2t);
+ return NULL;
+}
+
+static int qcow_decompress_buffer(u8 *out_buf, int out_buf_size,
+ const u8 *buf, int buf_size)
+{
+#ifdef CONFIG_HAS_ZLIB
+ z_stream strm1, *strm = &strm1;
+ int ret, out_len;
+
+ memset(strm, 0, sizeof(*strm));
+
+ strm->next_in = (u8 *)buf;
+ strm->avail_in = buf_size;
+ strm->next_out = out_buf;
+ strm->avail_out = out_buf_size;
+
+ ret = inflateInit2(strm, -12);
+ if (ret != Z_OK)
+ return -1;
+
+ ret = inflate(strm, Z_FINISH);
+ out_len = strm->next_out - out_buf;
+ if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) ||
+ out_len != out_buf_size) {
+ inflateEnd(strm);
+ return -1;
+ }
+
+ inflateEnd(strm);
+ return 0;
+#else
+ return -1;
+#endif
+}
+
+static ssize_t qcow1_read_cluster(struct qcow *q, u64 offset,
+ void *dst, u32 dst_len)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+ u64 clust_offset;
+ u64 clust_start;
+ u64 l2t_offset;
+ size_t length;
+ u64 l2t_size;
+ u64 l1_idx;
+ u64 l2_idx;
+ int coffset;
+ int csize;
+
+ l1_idx = get_l1_index(q, offset);
+ if (l1_idx >= l1t->table_size)
+ return -1;
+
+ clust_offset = get_cluster_offset(q, offset);
+ if (clust_offset >= q->cluster_size)
+ return -1;
+
+ length = q->cluster_size - clust_offset;
+ if (length > dst_len)
+ length = dst_len;
+
+ mutex_lock(&q->mutex);
+
+ l2t_offset = be64_to_cpu(l1t->l1_table[l1_idx]);
+ if (!l2t_offset)
+ goto zero_cluster;
+
+ l2t_size = 1 << header->l2_bits;
+
+ /* read and cache level 2 table */
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto out_error;
+
+ l2_idx = get_l2_index(q, offset);
+ if (l2_idx >= l2t_size)
+ goto out_error;
+
+ clust_start = be64_to_cpu(l2t->table[l2_idx]);
+ if (clust_start & QCOW1_OFLAG_COMPRESSED) {
+ coffset = clust_start & q->cluster_offset_mask;
+ csize = clust_start >> (63 - q->header->cluster_bits);
+ csize &= (q->cluster_size - 1);
+
+ if (pread_in_full(q->fd, q->cluster_data, csize,
+ coffset) < 0)
+ goto out_error;
+
+ if (qcow_decompress_buffer(q->cluster_cache, q->cluster_size,
+ q->cluster_data, csize) < 0)
+ goto out_error;
+
+ memcpy(dst, q->cluster_cache + clust_offset, length);
+ mutex_unlock(&q->mutex);
+ } else {
+ if (!clust_start)
+ goto zero_cluster;
+
+ mutex_unlock(&q->mutex);
+
+ if (pread_in_full(q->fd, dst, length,
+ clust_start + clust_offset) < 0)
+ return -1;
+ }
+
+ return length;
+
+zero_cluster:
+ mutex_unlock(&q->mutex);
+ memset(dst, 0, length);
+ return length;
+
+out_error:
+ mutex_unlock(&q->mutex);
+ length = -1;
+ return -1;
+}
+
+static ssize_t qcow2_read_cluster(struct qcow *q, u64 offset,
+ void *dst, u32 dst_len)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+ u64 clust_offset;
+ u64 clust_start;
+ u64 l2t_offset;
+ size_t length;
+ u64 l2t_size;
+ u64 l1_idx;
+ u64 l2_idx;
+ int coffset;
+ int sector_offset;
+ int nb_csectors;
+ int csize;
+
+ l1_idx = get_l1_index(q, offset);
+ if (l1_idx >= l1t->table_size)
+ return -1;
+
+ clust_offset = get_cluster_offset(q, offset);
+ if (clust_offset >= q->cluster_size)
+ return -1;
+
+ length = q->cluster_size - clust_offset;
+ if (length > dst_len)
+ length = dst_len;
+
+ mutex_lock(&q->mutex);
+
+ l2t_offset = be64_to_cpu(l1t->l1_table[l1_idx]);
+
+ l2t_offset &= ~QCOW2_OFLAG_COPIED;
+ if (!l2t_offset)
+ goto zero_cluster;
+
+ l2t_size = 1 << header->l2_bits;
+
+ /* read and cache level 2 table */
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto out_error;
+
+ l2_idx = get_l2_index(q, offset);
+ if (l2_idx >= l2t_size)
+ goto out_error;
+
+ clust_start = be64_to_cpu(l2t->table[l2_idx]);
+ if (clust_start & QCOW2_OFLAG_COMPRESSED) {
+ coffset = clust_start & q->cluster_offset_mask;
+ nb_csectors = ((clust_start >> q->csize_shift)
+ & q->csize_mask) + 1;
+ sector_offset = coffset & (SECTOR_SIZE - 1);
+ csize = nb_csectors * SECTOR_SIZE - sector_offset;
+
+ if (pread_in_full(q->fd, q->cluster_data,
+ nb_csectors * SECTOR_SIZE,
+ coffset & ~(SECTOR_SIZE - 1)) < 0) {
+ goto out_error;
+ }
+
+ if (qcow_decompress_buffer(q->cluster_cache, q->cluster_size,
+ q->cluster_data + sector_offset,
+ csize) < 0) {
+ goto out_error;
+ }
+
+ memcpy(dst, q->cluster_cache + clust_offset, length);
+ mutex_unlock(&q->mutex);
+ } else {
+ clust_start &= QCOW2_OFFSET_MASK;
+ if (!clust_start)
+ goto zero_cluster;
+
+ mutex_unlock(&q->mutex);
+
+ if (pread_in_full(q->fd, dst, length,
+ clust_start + clust_offset) < 0)
+ return -1;
+ }
+
+ return length;
+
+zero_cluster:
+ mutex_unlock(&q->mutex);
+ memset(dst, 0, length);
+ return length;
+
+out_error:
+ mutex_unlock(&q->mutex);
+ length = -1;
+ return -1;
+}
+
+static ssize_t qcow_read_sector_single(struct disk_image *disk, u64 sector,
+ void *dst, u32 dst_len)
+{
+ struct qcow *q = disk->priv;
+ struct qcow_header *header = q->header;
+ u32 nr_read;
+ u64 offset;
+ char *buf;
+ u32 nr;
+
+ buf = dst;
+ nr_read = 0;
+
+ while (nr_read < dst_len) {
+ offset = sector << SECTOR_SHIFT;
+ if (offset >= header->size)
+ return -1;
+
+ if (q->version == QCOW1_VERSION)
+ nr = qcow1_read_cluster(q, offset, buf,
+ dst_len - nr_read);
+ else
+ nr = qcow2_read_cluster(q, offset, buf,
+ dst_len - nr_read);
+
+ if (nr <= 0)
+ return -1;
+
+ nr_read += nr;
+ buf += nr;
+ sector += (nr >> SECTOR_SHIFT);
+ }
+
+ return dst_len;
+}
+
+static ssize_t qcow_read_sector(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t nr, total = 0;
+
+ while (iovcount--) {
+ nr = qcow_read_sector_single(disk, sector, iov->iov_base, iov->iov_len);
+ if (nr != (ssize_t)iov->iov_len) {
+ pr_info("qcow_read_sector error: nr=%ld iov_len=%ld\n", (long)nr, (long)iov->iov_len);
+ return -1;
+ }
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ total += nr;
+ iov++;
+ }
+
+ return total;
+}
+
+static void refcount_table_free_cache(struct qcow_refcount_table *rft)
+{
+ struct rb_root *r = &rft->root;
+ struct list_head *pos, *n;
+ struct qcow_refcount_block *t;
+
+ list_for_each_safe(pos, n, &rft->lru_list) {
+ list_del(pos);
+ t = list_entry(pos, struct qcow_refcount_block, list);
+ rb_erase(&t->node, r);
+
+ free(t);
+ }
+}
+
+static int refcount_block_insert(struct rb_root *root, struct qcow_refcount_block *new)
+{
+ struct rb_node **link = &(root->rb_node), *parent = NULL;
+ u64 offset = new->offset;
+
+ /* search the tree */
+ while (*link) {
+ struct qcow_refcount_block *t;
+
+ t = rb_entry(*link, struct qcow_refcount_block, node);
+ if (!t)
+ goto error;
+
+ parent = *link;
+
+ if (t->offset > offset)
+ link = &(*link)->rb_left;
+ else if (t->offset < offset)
+ link = &(*link)->rb_right;
+ else
+ goto out;
+ }
+
+ /* add new node */
+ rb_link_node(&new->node, parent, link);
+ rb_insert_color(&new->node, root);
+out:
+ return 0;
+error:
+ return -1;
+}
+
+static int write_refcount_block(struct qcow *q, struct qcow_refcount_block *rfb)
+{
+ if (!rfb->dirty)
+ return 0;
+
+ if (qcow_pwrite_sync(q->fd, rfb->entries,
+ rfb->size * sizeof(u16), rfb->offset) < 0)
+ return -1;
+
+ rfb->dirty = 0;
+
+ return 0;
+}
+
+static int cache_refcount_block(struct qcow *q, struct qcow_refcount_block *c)
+{
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct rb_root *r = &rft->root;
+ struct qcow_refcount_block *lru;
+
+ if (rft->nr_cached == MAX_CACHE_NODES) {
+ lru = list_first_entry(&rft->lru_list, struct qcow_refcount_block, list);
+
+ rb_erase(&lru->node, r);
+ list_del_init(&lru->list);
+ rft->nr_cached--;
+
+ free(lru);
+ }
+
+ if (refcount_block_insert(r, c) < 0)
+ goto error;
+
+ list_add_tail(&c->list, &rft->lru_list);
+ rft->nr_cached++;
+
+ return 0;
+error:
+ return -1;
+}
+
+static struct qcow_refcount_block *new_refcount_block(struct qcow *q, u64 rfb_offset)
+{
+ struct qcow_refcount_block *rfb;
+
+ rfb = malloc(sizeof *rfb + q->cluster_size);
+ if (!rfb)
+ return NULL;
+
+ rfb->offset = rfb_offset;
+ rfb->size = q->cluster_size / sizeof(u16);
+ RB_CLEAR_NODE(&rfb->node);
+ INIT_LIST_HEAD(&rfb->list);
+
+ return rfb;
+}
+
+static struct qcow_refcount_block *refcount_block_lookup(struct rb_root *root, u64 offset)
+{
+ struct rb_node *link = root->rb_node;
+
+ while (link) {
+ struct qcow_refcount_block *t;
+
+ t = rb_entry(link, struct qcow_refcount_block, node);
+ if (!t)
+ goto out;
+
+ if (t->offset > offset)
+ link = link->rb_left;
+ else if (t->offset < offset)
+ link = link->rb_right;
+ else
+ return t;
+ }
+out:
+ return NULL;
+}
+
+static struct qcow_refcount_block *refcount_block_search(struct qcow *q, u64 offset)
+{
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct qcow_refcount_block *rfb;
+
+ rfb = refcount_block_lookup(&rft->root, offset);
+ if (!rfb)
+ return NULL;
+
+ /* Update the LRU state, by moving the searched node to list tail */
+ list_move_tail(&rfb->list, &rft->lru_list);
+
+ return rfb;
+}
+
+static struct qcow_refcount_block *qcow_grow_refcount_block(struct qcow *q,
+ u64 clust_idx)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct qcow_refcount_block *rfb;
+ u64 new_block_offset;
+ u64 rft_idx;
+
+ rft_idx = clust_idx >> (header->cluster_bits -
+ QCOW_REFCOUNT_BLOCK_SHIFT);
+
+ if (rft_idx >= rft->rf_size) {
+ pr_warning("Don't support grow refcount block table");
+ return NULL;
+ }
+
+ new_block_offset = qcow_alloc_clusters(q, q->cluster_size, 0);
+ if (new_block_offset == (u64)-1)
+ return NULL;
+
+ rfb = new_refcount_block(q, new_block_offset);
+ if (!rfb)
+ return NULL;
+
+ memset(rfb->entries, 0x00, q->cluster_size);
+ rfb->dirty = 1;
+
+ /* write refcount block */
+ if (write_refcount_block(q, rfb) < 0)
+ goto free_rfb;
+
+ if (cache_refcount_block(q, rfb) < 0)
+ goto free_rfb;
+
+ rft->rf_table[rft_idx] = cpu_to_be64(new_block_offset);
+ if (update_cluster_refcount(q, new_block_offset >>
+ header->cluster_bits, 1) < 0)
+ goto recover_rft;
+
+ if (qcow_write_refcount_table(q) < 0)
+ goto recover_rft;
+
+ return rfb;
+
+recover_rft:
+ rft->rf_table[rft_idx] = 0;
+free_rfb:
+ free(rfb);
+ return NULL;
+}
+
+static struct qcow_refcount_block *qcow_read_refcount_block(struct qcow *q, u64 clust_idx)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct qcow_refcount_block *rfb;
+ u64 rfb_offset;
+ u64 rft_idx;
+
+ rft_idx = clust_idx >> (header->cluster_bits - QCOW_REFCOUNT_BLOCK_SHIFT);
+ if (rft_idx >= rft->rf_size)
+ return ERR_PTR(-ENOSPC);
+
+ rfb_offset = be64_to_cpu(rft->rf_table[rft_idx]);
+ if (!rfb_offset)
+ return ERR_PTR(-ENOSPC);
+
+ rfb = refcount_block_search(q, rfb_offset);
+ if (rfb)
+ return rfb;
+
+ rfb = new_refcount_block(q, rfb_offset);
+ if (!rfb)
+ return NULL;
+
+ if (pread_in_full(q->fd, rfb->entries, rfb->size * sizeof(u16), rfb_offset) < 0)
+ goto error_free_rfb;
+
+ if (cache_refcount_block(q, rfb) < 0)
+ goto error_free_rfb;
+
+ return rfb;
+
+error_free_rfb:
+ free(rfb);
+
+ return NULL;
+}
+
+static u16 qcow_get_refcount(struct qcow *q, u64 clust_idx)
+{
+ struct qcow_refcount_block *rfb = NULL;
+ struct qcow_header *header = q->header;
+ u64 rfb_idx;
+
+ rfb = qcow_read_refcount_block(q, clust_idx);
+ if (PTR_ERR(rfb) == -ENOSPC)
+ return 0;
+ else if (IS_ERR_OR_NULL(rfb)) {
+ pr_warning("Error while reading refcount table");
+ return -1;
+ }
+
+ rfb_idx = clust_idx & (((1ULL <<
+ (header->cluster_bits - QCOW_REFCOUNT_BLOCK_SHIFT)) - 1));
+
+ if (rfb_idx >= rfb->size) {
+ pr_warning("L1: refcount block index out of bounds");
+ return -1;
+ }
+
+ return be16_to_cpu(rfb->entries[rfb_idx]);
+}
+
+static int update_cluster_refcount(struct qcow *q, u64 clust_idx, u16 append)
+{
+ struct qcow_refcount_block *rfb = NULL;
+ struct qcow_header *header = q->header;
+ u16 refcount;
+ u64 rfb_idx;
+
+ rfb = qcow_read_refcount_block(q, clust_idx);
+ if (PTR_ERR(rfb) == -ENOSPC) {
+ rfb = qcow_grow_refcount_block(q, clust_idx);
+ if (!rfb) {
+ pr_warning("error while growing refcount table");
+ return -1;
+ }
+ } else if (IS_ERR_OR_NULL(rfb)) {
+ pr_warning("error while reading refcount table");
+ return -1;
+ }
+
+ rfb_idx = clust_idx & (((1ULL <<
+ (header->cluster_bits - QCOW_REFCOUNT_BLOCK_SHIFT)) - 1));
+ if (rfb_idx >= rfb->size) {
+ pr_warning("refcount block index out of bounds");
+ return -1;
+ }
+
+ refcount = be16_to_cpu(rfb->entries[rfb_idx]) + append;
+ rfb->entries[rfb_idx] = cpu_to_be16(refcount);
+ rfb->dirty = 1;
+
+ /* write refcount block */
+ if (write_refcount_block(q, rfb) < 0) {
+ pr_warning("refcount block index out of bounds");
+ return -1;
+ }
+
+ /* update free_clust_idx since refcount becomes zero */
+ if (!refcount && clust_idx < q->free_clust_idx)
+ q->free_clust_idx = clust_idx;
+
+ return 0;
+}
+
+static void qcow_free_clusters(struct qcow *q, u64 clust_start, u64 size)
+{
+ struct qcow_header *header = q->header;
+ u64 start, end, offset;
+
+ start = clust_start & ~(q->cluster_size - 1);
+ end = (clust_start + size - 1) & ~(q->cluster_size - 1);
+ for (offset = start; offset <= end; offset += q->cluster_size)
+ update_cluster_refcount(q, offset >> header->cluster_bits, -1);
+}
+
+/*
+ * Allocate clusters according to the size. Find a postion that
+ * can satisfy the size. free_clust_idx is initialized to zero and
+ * Record last position.
+ */
+static u64 qcow_alloc_clusters(struct qcow *q, u64 size, int update_ref)
+{
+ struct qcow_header *header = q->header;
+ u16 clust_refcount;
+ u32 clust_idx = 0, i;
+ u64 clust_num;
+
+ clust_num = (size + (q->cluster_size - 1)) >> header->cluster_bits;
+
+again:
+ for (i = 0; i < clust_num; i++) {
+ clust_idx = q->free_clust_idx++;
+ clust_refcount = qcow_get_refcount(q, clust_idx);
+ if (clust_refcount == (u16)-1)
+ return -1;
+ else if (clust_refcount > 0)
+ goto again;
+ }
+
+ clust_idx++;
+
+ if (update_ref)
+ for (i = 0; i < clust_num; i++)
+ if (update_cluster_refcount(q,
+ clust_idx - clust_num + i, 1))
+ return -1;
+
+ return (clust_idx - clust_num) << header->cluster_bits;
+}
+
+static int qcow_write_l1_table(struct qcow *q)
+{
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_header *header = q->header;
+
+ if (qcow_pwrite_sync(q->fd, l1t->l1_table,
+ l1t->table_size * sizeof(u64),
+ header->l1_table_offset) < 0)
+ return -1;
+
+ return 0;
+}
+
+/*
+ * Get l2 table. If the table has been copied, read table directly.
+ * If the table exists, allocate a new cluster and copy the table
+ * to the new cluster.
+ */
+static int get_cluster_table(struct qcow *q, u64 offset,
+ struct qcow_l2_table **result_l2t, u64 *result_l2_index)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+ u64 l1t_idx;
+ u64 l2t_offset;
+ u64 l2t_idx;
+ u64 l2t_size;
+ u64 l2t_new_offset;
+
+ l2t_size = 1 << header->l2_bits;
+
+ l1t_idx = get_l1_index(q, offset);
+ if (l1t_idx >= l1t->table_size)
+ return -1;
+
+ l2t_idx = get_l2_index(q, offset);
+ if (l2t_idx >= l2t_size)
+ return -1;
+
+ l2t_offset = be64_to_cpu(l1t->l1_table[l1t_idx]);
+ if (l2t_offset & QCOW2_OFLAG_COPIED) {
+ l2t_offset &= ~QCOW2_OFLAG_COPIED;
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto error;
+ } else {
+ l2t_new_offset = qcow_alloc_clusters(q,
+ l2t_size*sizeof(u64), 1);
+
+ if (l2t_new_offset != (u64)-1)
+ goto error;
+
+ l2t = new_cache_table(q, l2t_new_offset);
+ if (!l2t)
+ goto free_cluster;
+
+ if (l2t_offset) {
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto free_cache;
+ } else
+ memset(l2t->table, 0x00, l2t_size * sizeof(u64));
+
+ /* write l2 table */
+ l2t->dirty = 1;
+ if (qcow_l2_cache_write(q, l2t) < 0)
+ goto free_cache;
+
+ /* cache l2 table */
+ if (cache_table(q, l2t))
+ goto free_cache;
+
+ /* update the l1 talble */
+ l1t->l1_table[l1t_idx] = cpu_to_be64(l2t_new_offset
+ | QCOW2_OFLAG_COPIED);
+ if (qcow_write_l1_table(q)) {
+ pr_warning("Update l1 table error");
+ goto free_cache;
+ }
+
+ /* free old cluster */
+ qcow_free_clusters(q, l2t_offset, q->cluster_size);
+ }
+
+ *result_l2t = l2t;
+ *result_l2_index = l2t_idx;
+
+ return 0;
+
+free_cache:
+ free(l2t);
+
+free_cluster:
+ qcow_free_clusters(q, l2t_new_offset, q->cluster_size);
+
+error:
+ return -1;
+}
+
+/*
+ * If the cluster has been copied, write data directly. If not,
+ * read the original data and write it to the new cluster with
+ * modification.
+ */
+static ssize_t qcow_write_cluster(struct qcow *q, u64 offset,
+ void *buf, u32 src_len)
+{
+ struct qcow_l2_table *l2t;
+ u64 clust_new_start;
+ u64 clust_start;
+ u64 clust_flags;
+ u64 clust_off;
+ u64 l2t_idx;
+ u64 len;
+
+ l2t = NULL;
+
+ clust_off = get_cluster_offset(q, offset);
+ if (clust_off >= q->cluster_size)
+ return -1;
+
+ len = q->cluster_size - clust_off;
+ if (len > src_len)
+ len = src_len;
+
+ mutex_lock(&q->mutex);
+
+ if (get_cluster_table(q, offset, &l2t, &l2t_idx)) {
+ pr_warning("Get l2 table error");
+ goto error;
+ }
+
+ clust_start = be64_to_cpu(l2t->table[l2t_idx]);
+ clust_flags = clust_start & QCOW2_OFLAGS_MASK;
+
+ clust_start &= QCOW2_OFFSET_MASK;
+ if (!(clust_flags & QCOW2_OFLAG_COPIED)) {
+ clust_new_start = qcow_alloc_clusters(q, q->cluster_size, 1);
+ if (clust_new_start != (u64)-1) {
+ pr_warning("Cluster alloc error");
+ goto error;
+ }
+
+ offset &= ~(q->cluster_size - 1);
+
+ /* if clust_start is not zero, read the original data*/
+ if (clust_start) {
+ mutex_unlock(&q->mutex);
+ if (qcow2_read_cluster(q, offset, q->copy_buff,
+ q->cluster_size) < 0) {
+ pr_warning("Read copy cluster error");
+ qcow_free_clusters(q, clust_new_start,
+ q->cluster_size);
+ return -1;
+ }
+ mutex_lock(&q->mutex);
+ } else
+ memset(q->copy_buff, 0x00, q->cluster_size);
+
+ memcpy(q->copy_buff + clust_off, buf, len);
+
+ /* Write actual data */
+ if (pwrite_in_full(q->fd, q->copy_buff, q->cluster_size,
+ clust_new_start) < 0)
+ goto free_cluster;
+
+ /* update l2 table*/
+ l2t->table[l2t_idx] = cpu_to_be64(clust_new_start
+ | QCOW2_OFLAG_COPIED);
+ l2t->dirty = 1;
+
+ if (qcow_l2_cache_write(q, l2t))
+ goto free_cluster;
+
+ /* free old cluster*/
+ if (clust_flags & QCOW2_OFLAG_COMPRESSED) {
+ int size;
+ size = ((clust_start >> q->csize_shift) &
+ q->csize_mask) + 1;
+ size *= 512;
+ clust_start &= q->cluster_offset_mask;
+ clust_start &= ~511;
+
+ qcow_free_clusters(q, clust_start, size);
+ } else if (clust_start)
+ qcow_free_clusters(q, clust_start, q->cluster_size);
+
+ } else {
+ /* Write actual data */
+ if (pwrite_in_full(q->fd, buf, len,
+ clust_start + clust_off) < 0)
+ goto error;
+ }
+ mutex_unlock(&q->mutex);
+ return len;
+
+free_cluster:
+ qcow_free_clusters(q, clust_new_start, q->cluster_size);
+
+error:
+ mutex_unlock(&q->mutex);
+ return -1;
+}
+
+static ssize_t qcow_write_sector_single(struct disk_image *disk, u64 sector, void *src, u32 src_len)
+{
+ struct qcow *q = disk->priv;
+ struct qcow_header *header = q->header;
+ u32 nr_written;
+ char *buf;
+ u64 offset;
+ ssize_t nr;
+
+ buf = src;
+ nr_written = 0;
+ offset = sector << SECTOR_SHIFT;
+
+ while (nr_written < src_len) {
+ if (offset >= header->size)
+ return -1;
+
+ nr = qcow_write_cluster(q, offset, buf, src_len - nr_written);
+ if (nr < 0)
+ return -1;
+
+ nr_written += nr;
+ buf += nr;
+ offset += nr;
+ }
+
+ return nr_written;
+}
+
+static ssize_t qcow_write_sector(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t nr, total = 0;
+
+ while (iovcount--) {
+ nr = qcow_write_sector_single(disk, sector, iov->iov_base, iov->iov_len);
+ if (nr != (ssize_t)iov->iov_len) {
+ pr_info("qcow_write_sector error: nr=%ld iov_len=%ld\n", (long)nr, (long)iov->iov_len);
+ return -1;
+ }
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ iov++;
+ total += nr;
+ }
+
+ return total;
+}
+
+static int qcow_disk_flush(struct disk_image *disk)
+{
+ struct qcow *q = disk->priv;
+ struct qcow_refcount_table *rft;
+ struct list_head *pos, *n;
+ struct qcow_l1_table *l1t;
+
+ l1t = &q->table;
+ rft = &q->refcount_table;
+
+ mutex_lock(&q->mutex);
+
+ list_for_each_safe(pos, n, &rft->lru_list) {
+ struct qcow_refcount_block *c = list_entry(pos, struct qcow_refcount_block, list);
+
+ if (write_refcount_block(q, c) < 0)
+ goto error_unlock;
+ }
+
+ list_for_each_safe(pos, n, &l1t->lru_list) {
+ struct qcow_l2_table *c = list_entry(pos, struct qcow_l2_table, list);
+
+ if (qcow_l2_cache_write(q, c) < 0)
+ goto error_unlock;
+ }
+
+ if (qcow_write_l1_table < 0)
+ goto error_unlock;
+
+ mutex_unlock(&q->mutex);
+
+ return fsync(disk->fd);
+
+error_unlock:
+ mutex_unlock(&q->mutex);
+ return -1;
+}
+
+static int qcow_disk_close(struct disk_image *disk)
+{
+ struct qcow *q;
+
+ if (!disk)
+ return 0;
+
+ q = disk->priv;
+
+ refcount_table_free_cache(&q->refcount_table);
+ l1_table_free_cache(&q->table);
+ free(q->copy_buff);
+ free(q->cluster_data);
+ free(q->cluster_cache);
+ free(q->refcount_table.rf_table);
+ free(q->table.l1_table);
+ free(q->header);
+ free(q);
+
+ return 0;
+}
+
+static struct disk_image_operations qcow_disk_readonly_ops = {
+ .read = qcow_read_sector,
+ .close = qcow_disk_close,
+};
+
+static struct disk_image_operations qcow_disk_ops = {
+ .read = qcow_read_sector,
+ .write = qcow_write_sector,
+ .flush = qcow_disk_flush,
+ .close = qcow_disk_close,
+};
+
+static int qcow_read_refcount_table(struct qcow *q)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+
+ rft->rf_size = (header->refcount_table_size * q->cluster_size)
+ / sizeof(u64);
+
+ rft->rf_table = calloc(rft->rf_size, sizeof(u64));
+ if (!rft->rf_table)
+ return -1;
+
+ rft->root = (struct rb_root) RB_ROOT;
+ INIT_LIST_HEAD(&rft->lru_list);
+
+ return pread_in_full(q->fd, rft->rf_table, sizeof(u64) * rft->rf_size, header->refcount_table_offset);
+}
+
+static int qcow_write_refcount_table(struct qcow *q)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+
+ return qcow_pwrite_sync(q->fd, rft->rf_table,
+ rft->rf_size * sizeof(u64), header->refcount_table_offset);
+}
+
+static int qcow_read_l1_table(struct qcow *q)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *table = &q->table;
+
+ table->table_size = header->l1_size;
+
+ table->l1_table = calloc(table->table_size, sizeof(u64));
+ if (!table->l1_table)
+ return -1;
+
+ return pread_in_full(q->fd, table->l1_table, sizeof(u64) * table->table_size, header->l1_table_offset);
+}
+
+static void *qcow2_read_header(int fd)
+{
+ struct qcow2_header_disk f_header;
+ struct qcow_header *header;
+
+ header = malloc(sizeof(struct qcow_header));
+ if (!header)
+ return NULL;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow2_header_disk), 0) < 0) {
+ free(header);
+ return NULL;
+ }
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+ be64_to_cpus(&f_header.backing_file_offset);
+ be32_to_cpus(&f_header.backing_file_size);
+ be32_to_cpus(&f_header.cluster_bits);
+ be64_to_cpus(&f_header.size);
+ be32_to_cpus(&f_header.crypt_method);
+ be32_to_cpus(&f_header.l1_size);
+ be64_to_cpus(&f_header.l1_table_offset);
+ be64_to_cpus(&f_header.refcount_table_offset);
+ be32_to_cpus(&f_header.refcount_table_clusters);
+ be32_to_cpus(&f_header.nb_snapshots);
+ be64_to_cpus(&f_header.snapshots_offset);
+
+ *header = (struct qcow_header) {
+ .size = f_header.size,
+ .l1_table_offset = f_header.l1_table_offset,
+ .l1_size = f_header.l1_size,
+ .cluster_bits = f_header.cluster_bits,
+ .l2_bits = f_header.cluster_bits - 3,
+ .refcount_table_offset = f_header.refcount_table_offset,
+ .refcount_table_size = f_header.refcount_table_clusters,
+ };
+
+ return header;
+}
+
+static struct disk_image *qcow2_probe(int fd, bool readonly)
+{
+ struct disk_image *disk_image;
+ struct qcow_l1_table *l1t;
+ struct qcow_header *h;
+ struct qcow *q;
+
+ q = calloc(1, sizeof(struct qcow));
+ if (!q)
+ return NULL;
+
+ mutex_init(&q->mutex);
+ q->fd = fd;
+
+ l1t = &q->table;
+
+ l1t->root = (struct rb_root) RB_ROOT;
+ INIT_LIST_HEAD(&l1t->lru_list);
+
+ h = q->header = qcow2_read_header(fd);
+ if (!h)
+ goto free_qcow;
+
+ q->version = QCOW2_VERSION;
+ q->csize_shift = (62 - (q->header->cluster_bits - 8));
+ q->csize_mask = (1 << (q->header->cluster_bits - 8)) - 1;
+ q->cluster_offset_mask = (1LL << q->csize_shift) - 1;
+ q->cluster_size = 1 << q->header->cluster_bits;
+
+ q->copy_buff = malloc(q->cluster_size);
+ if (!q->copy_buff) {
+ pr_warning("copy buff malloc error");
+ goto free_header;
+ }
+
+ q->cluster_data = malloc(q->cluster_size);
+ if (!q->cluster_data) {
+ pr_warning("cluster data malloc error");
+ goto free_copy_buff;
+ }
+
+ q->cluster_cache = malloc(q->cluster_size);
+ if (!q->cluster_cache) {
+ pr_warning("cluster cache malloc error");
+ goto free_cluster_data;
+ }
+
+ if (qcow_read_l1_table(q) < 0)
+ goto free_cluster_cache;
+
+ if (qcow_read_refcount_table(q) < 0)
+ goto free_l1_table;
+
+ /*
+ * Do not use mmap use read/write instead
+ */
+ if (readonly)
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_readonly_ops, DISK_IMAGE_REGULAR);
+ else
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_ops, DISK_IMAGE_REGULAR);
+
+ if (IS_ERR_OR_NULL(disk_image))
+ goto free_refcount_table;
+
+ disk_image->priv = q;
+
+ return disk_image;
+
+free_refcount_table:
+ if (q->refcount_table.rf_table)
+ free(q->refcount_table.rf_table);
+free_l1_table:
+ if (q->table.l1_table)
+ free(q->table.l1_table);
+free_cluster_cache:
+ if (q->cluster_cache)
+ free(q->cluster_cache);
+free_cluster_data:
+ if (q->cluster_data)
+ free(q->cluster_data);
+free_copy_buff:
+ if (q->copy_buff)
+ free(q->copy_buff);
+free_header:
+ if (q->header)
+ free(q->header);
+free_qcow:
+ free(q);
+
+ return NULL;
+}
+
+static bool qcow2_check_image(int fd)
+{
+ struct qcow2_header_disk f_header;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow2_header_disk), 0) < 0)
+ return false;
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+
+ if (f_header.magic != QCOW_MAGIC)
+ return false;
+
+ if (f_header.version != QCOW2_VERSION)
+ return false;
+
+ return true;
+}
+
+static void *qcow1_read_header(int fd)
+{
+ struct qcow1_header_disk f_header;
+ struct qcow_header *header;
+
+ header = malloc(sizeof(struct qcow_header));
+ if (!header)
+ return NULL;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow1_header_disk), 0) < 0) {
+ free(header);
+ return NULL;
+ }
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+ be64_to_cpus(&f_header.backing_file_offset);
+ be32_to_cpus(&f_header.backing_file_size);
+ be32_to_cpus(&f_header.mtime);
+ be64_to_cpus(&f_header.size);
+ be32_to_cpus(&f_header.crypt_method);
+ be64_to_cpus(&f_header.l1_table_offset);
+
+ *header = (struct qcow_header) {
+ .size = f_header.size,
+ .l1_table_offset = f_header.l1_table_offset,
+ .l1_size = f_header.size / ((1 << f_header.l2_bits) * (1 << f_header.cluster_bits)),
+ .cluster_bits = f_header.cluster_bits,
+ .l2_bits = f_header.l2_bits,
+ };
+
+ return header;
+}
+
+static struct disk_image *qcow1_probe(int fd, bool readonly)
+{
+ struct disk_image *disk_image;
+ struct qcow_l1_table *l1t;
+ struct qcow_header *h;
+ struct qcow *q;
+
+ q = calloc(1, sizeof(struct qcow));
+ if (!q)
+ return NULL;
+
+ mutex_init(&q->mutex);
+ q->fd = fd;
+
+ l1t = &q->table;
+
+ l1t->root = (struct rb_root)RB_ROOT;
+ INIT_LIST_HEAD(&l1t->lru_list);
+ INIT_LIST_HEAD(&q->refcount_table.lru_list);
+
+ h = q->header = qcow1_read_header(fd);
+ if (!h)
+ goto free_qcow;
+
+ q->version = QCOW1_VERSION;
+ q->cluster_size = 1 << q->header->cluster_bits;
+ q->cluster_offset_mask = (1LL << (63 - q->header->cluster_bits)) - 1;
+ q->free_clust_idx = 0;
+
+ q->cluster_data = malloc(q->cluster_size);
+ if (!q->cluster_data) {
+ pr_warning("cluster data malloc error");
+ goto free_header;
+ }
+
+ q->cluster_cache = malloc(q->cluster_size);
+ if (!q->cluster_cache) {
+ pr_warning("cluster cache malloc error");
+ goto free_cluster_data;
+ }
+
+ if (qcow_read_l1_table(q) < 0)
+ goto free_cluster_cache;
+
+ /*
+ * Do not use mmap use read/write instead
+ */
+ if (readonly)
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_readonly_ops, DISK_IMAGE_REGULAR);
+ else
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_ops, DISK_IMAGE_REGULAR);
+
+ if (!disk_image)
+ goto free_l1_table;
+
+ disk_image->priv = q;
+
+ return disk_image;
+
+free_l1_table:
+ if (q->table.l1_table)
+ free(q->table.l1_table);
+free_cluster_cache:
+ if (q->cluster_cache)
+ free(q->cluster_cache);
+free_cluster_data:
+ if (q->cluster_data)
+ free(q->cluster_data);
+free_header:
+ if (q->header)
+ free(q->header);
+free_qcow:
+ free(q);
+
+ return NULL;
+}
+
+static bool qcow1_check_image(int fd)
+{
+ struct qcow1_header_disk f_header;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow1_header_disk), 0) < 0)
+ return false;
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+
+ if (f_header.magic != QCOW_MAGIC)
+ return false;
+
+ if (f_header.version != QCOW1_VERSION)
+ return false;
+
+ return true;
+}
+
+struct disk_image *qcow_probe(int fd, bool readonly)
+{
+ if (qcow1_check_image(fd))
+ return qcow1_probe(fd, readonly);
+
+ if (qcow2_check_image(fd))
+ return qcow2_probe(fd, readonly);
+
+ return NULL;
+}
diff --git a/kvmtool/disk/raw.c b/kvmtool/disk/raw.c
new file mode 100644
index 0000000..54b4e74
--- /dev/null
+++ b/kvmtool/disk/raw.c
@@ -0,0 +1,107 @@
+#include "kvm/disk-image.h"
+
+#include <linux/err.h>
+
+ssize_t raw_image__read_sync(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param)
+{
+ return preadv_in_full(disk->fd, iov, iovcount, sector << SECTOR_SHIFT);
+}
+
+ssize_t raw_image__write_sync(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount,
+ void *param)
+{
+ return pwritev_in_full(disk->fd, iov, iovcount, sector << SECTOR_SHIFT);
+}
+
+ssize_t raw_image__read_mmap(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param)
+{
+ u64 offset = sector << SECTOR_SHIFT;
+ ssize_t total = 0;
+
+ while (iovcount--) {
+ memcpy(iov->iov_base, disk->priv + offset, iov->iov_len);
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ offset += iov->iov_len;
+ total += iov->iov_len;
+ iov++;
+ }
+
+ return total;
+}
+
+ssize_t raw_image__write_mmap(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param)
+{
+ u64 offset = sector << SECTOR_SHIFT;
+ ssize_t total = 0;
+
+ while (iovcount--) {
+ memcpy(disk->priv + offset, iov->iov_base, iov->iov_len);
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ offset += iov->iov_len;
+ total += iov->iov_len;
+ iov++;
+ }
+
+ return total;
+}
+
+int raw_image__close(struct disk_image *disk)
+{
+ int ret = 0;
+
+ if (disk->priv != MAP_FAILED)
+ ret = munmap(disk->priv, disk->size);
+
+ return ret;
+}
+
+/*
+ * multiple buffer based disk image operations
+ */
+static struct disk_image_operations raw_image_regular_ops = {
+ .read = raw_image__read,
+ .write = raw_image__write,
+ .wait = raw_image__wait,
+ .async = true,
+};
+
+struct disk_image_operations ro_ops = {
+ .read = raw_image__read_mmap,
+ .write = raw_image__write_mmap,
+ .close = raw_image__close,
+};
+
+struct disk_image_operations ro_ops_nowrite = {
+ .read = raw_image__read,
+ .wait = raw_image__wait,
+ .async = true,
+};
+
+struct disk_image *raw_image__probe(int fd, struct stat *st, bool readonly)
+{
+ if (readonly) {
+ /*
+ * Use mmap's MAP_PRIVATE to implement non-persistent write
+ * FIXME: This does not work on 32-bit host.
+ */
+ struct disk_image *disk;
+
+ disk = disk_image__new(fd, st->st_size, &ro_ops, DISK_IMAGE_MMAP);
+ if (IS_ERR_OR_NULL(disk)) {
+ disk = disk_image__new(fd, st->st_size, &ro_ops_nowrite, DISK_IMAGE_REGULAR);
+ }
+
+ return disk;
+ } else {
+ /*
+ * Use read/write instead of mmap
+ */
+ return disk_image__new(fd, st->st_size, &raw_image_regular_ops, DISK_IMAGE_REGULAR);
+ }
+}
diff --git a/kvmtool/framebuffer.c b/kvmtool/framebuffer.c
new file mode 100644
index 0000000..fb8f51d
--- /dev/null
+++ b/kvmtool/framebuffer.c
@@ -0,0 +1,80 @@
+#include "kvm/framebuffer.h"
+#include "kvm/kvm.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <errno.h>
+
+static LIST_HEAD(framebuffers);
+
+struct framebuffer *fb__register(struct framebuffer *fb)
+{
+ INIT_LIST_HEAD(&fb->node);
+ list_add(&fb->node, &framebuffers);
+
+ return fb;
+}
+
+int fb__attach(struct framebuffer *fb, struct fb_target_operations *ops)
+{
+ if (fb->nr_targets >= FB_MAX_TARGETS)
+ return -ENOSPC;
+
+ fb->targets[fb->nr_targets++] = ops;
+
+ return 0;
+}
+
+static int start_targets(struct framebuffer *fb)
+{
+ unsigned long i;
+
+ for (i = 0; i < fb->nr_targets; i++) {
+ struct fb_target_operations *ops = fb->targets[i];
+ int err = 0;
+
+ if (ops->start)
+ err = ops->start(fb);
+
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int fb__init(struct kvm *kvm)
+{
+ struct framebuffer *fb;
+
+ list_for_each_entry(fb, &framebuffers, node) {
+ int err;
+
+ err = start_targets(fb);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+firmware_init(fb__init);
+
+int fb__exit(struct kvm *kvm)
+{
+ struct framebuffer *fb;
+
+ list_for_each_entry(fb, &framebuffers, node) {
+ u32 i;
+
+ for (i = 0; i < fb->nr_targets; i++)
+ if (fb->targets[i]->stop)
+ fb->targets[i]->stop(fb);
+
+ munmap(fb->mem, fb->mem_size);
+ }
+
+ return 0;
+}
+firmware_exit(fb__exit);
diff --git a/kvmtool/guest/.gitignore b/kvmtool/guest/.gitignore
new file mode 100644
index 0000000..0ccdcbb
--- /dev/null
+++ b/kvmtool/guest/.gitignore
@@ -0,0 +1,2 @@
+guest_pre_init.c
+guest_init.c
diff --git a/kvmtool/guest/init.c b/kvmtool/guest/init.c
new file mode 100644
index 0000000..52f6567
--- /dev/null
+++ b/kvmtool/guest/init.c
@@ -0,0 +1,81 @@
+/*
+ * This is a simple init for shared rootfs guests. This part should be limited
+ * to doing mounts and running stage 2 of the init process.
+ */
+#include <sys/mount.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <sys/reboot.h>
+
+static int run_process(char *filename)
+{
+ char *new_argv[] = { filename, NULL };
+ char *new_env[] = { "TERM=linux", "DISPLAY=192.168.33.1:0",
+ "HOME=/virt/home", NULL };
+
+ return execve(filename, new_argv, new_env);
+}
+
+static int run_process_sandbox(char *filename)
+{
+ char *new_argv[] = { filename, "/virt/sandbox.sh", NULL };
+ char *new_env[] = { "TERM=linux", "HOME=/virt/home", NULL };
+
+ return execve(filename, new_argv, new_env);
+}
+
+static void do_mounts(void)
+{
+#ifndef CONFIG_GUEST_PRE_INIT
+ mount("hostfs", "/host", "9p", MS_RDONLY, "trans=virtio,version=9p2000.L");
+#endif
+ mount("sysfs", "/sys", "sysfs", 0, NULL);
+ mount("proc", "/proc", "proc", 0, NULL);
+ mount("devtmpfs", "/dev", "devtmpfs", 0, NULL);
+ mkdir("/dev/pts", 0755);
+ mount("devpts", "/dev/pts", "devpts", 0, NULL);
+}
+
+int main(int argc, char *argv[])
+{
+ pid_t child;
+ int status;
+
+ puts("Mounting...");
+
+ do_mounts();
+
+ /* get session leader */
+ setsid();
+
+ /* set controlling terminal */
+ ioctl(0, TIOCSCTTY, 1);
+
+ child = fork();
+ if (child < 0) {
+ printf("Fatal: fork() failed with %d\n", child);
+ return 0;
+ } else if (child == 0) {
+ if (access("/virt/sandbox.sh", R_OK) == 0)
+ run_process_sandbox("/bin/sh");
+ else
+ run_process("/bin/sh");
+ } else {
+ pid_t corpse;
+
+ do {
+ corpse = waitpid(-1, &status, 0);
+ } while (corpse != child);
+ }
+
+ sync();
+ reboot(RB_AUTOBOOT);
+
+ printf("Init failed: %s\n", strerror(errno));
+
+ return 0;
+}
diff --git a/kvmtool/guest_compat.c b/kvmtool/guest_compat.c
new file mode 100644
index 0000000..fd4704b
--- /dev/null
+++ b/kvmtool/guest_compat.c
@@ -0,0 +1,99 @@
+#include "kvm/guest_compat.h"
+
+#include "kvm/mutex.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+struct compat_message {
+ int id;
+ char *title;
+ char *desc;
+
+ struct list_head list;
+};
+
+static int id;
+static DEFINE_MUTEX(compat_mtx);
+static LIST_HEAD(messages);
+
+static void compat__free(struct compat_message *msg)
+{
+ free(msg->title);
+ free(msg->desc);
+ free(msg);
+}
+
+int compat__add_message(const char *title, const char *desc)
+{
+ struct compat_message *msg;
+ int msg_id;
+
+ msg = malloc(sizeof(*msg));
+ if (msg == NULL)
+ goto cleanup;
+
+ msg->title = strdup(title);
+ msg->desc = strdup(desc);
+
+ if (msg->title == NULL || msg->desc == NULL)
+ goto cleanup;
+
+ mutex_lock(&compat_mtx);
+
+ msg->id = msg_id = id++;
+ list_add_tail(&msg->list, &messages);
+
+ mutex_unlock(&compat_mtx);
+
+ return msg_id;
+
+cleanup:
+ if (msg)
+ compat__free(msg);
+
+ return -ENOMEM;
+}
+
+int compat__remove_message(int id)
+{
+ struct compat_message *pos, *n;
+
+ mutex_lock(&compat_mtx);
+
+ list_for_each_entry_safe(pos, n, &messages, list) {
+ if (pos->id == id) {
+ list_del(&pos->list);
+ compat__free(pos);
+
+ mutex_unlock(&compat_mtx);
+
+ return 0;
+ }
+ }
+
+ mutex_unlock(&compat_mtx);
+
+ return -ENOENT;
+}
+
+int compat__print_all_messages(void)
+{
+ mutex_lock(&compat_mtx);
+
+ while (!list_empty(&messages)) {
+ struct compat_message *msg;
+
+ msg = list_first_entry(&messages, struct compat_message, list);
+
+ printf("\n # KVM compatibility warning.\n\t%s\n\t%s\n",
+ msg->title, msg->desc);
+
+ list_del(&msg->list);
+ compat__free(msg);
+ }
+
+ mutex_unlock(&compat_mtx);
+
+ return 0;
+}
diff --git a/kvmtool/hw/cfi_flash.c b/kvmtool/hw/cfi_flash.c
new file mode 100644
index 0000000..7faecdf
--- /dev/null
+++ b/kvmtool/hw/cfi_flash.c
@@ -0,0 +1,639 @@
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/sizes.h>
+#include <linux/types.h>
+
+#include "kvm/kvm.h"
+#include "kvm/kvm-arch.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/devices.h"
+#include "kvm/fdt.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+
+/*
+ * The EDK2 driver hardcodes two 16-bit chips on a 32-bit bus.
+ * This code supports one or two chips (enforced below).
+ */
+#define CFI_NR_FLASH_CHIPS 2
+
+/* We always emulate a 32 bit bus width. */
+#define CFI_BUS_WIDTH 4
+
+/* The *effective* size of an erase block (over all chips) */
+#define FLASH_BLOCK_SIZE SZ_64K
+#define FLASH_BLOCK_SIZE_PER_CHIP \
+ (FLASH_BLOCK_SIZE / CFI_NR_FLASH_CHIPS)
+
+#define PROGRAM_BUFF_SIZE_BITS 7
+#define PROGRAM_BUFF_SIZE (1U << PROGRAM_BUFF_SIZE_BITS)
+#define PROGRAM_BUFF_SIZE_BITS_PER_CHIP \
+ (PROGRAM_BUFF_SIZE_BITS + 1 - CFI_NR_FLASH_CHIPS)
+
+/* CFI commands */
+#define CFI_CMD_LOCK_BLOCK 0x01
+#define CFI_CMD_ALTERNATE_WORD_PROGRAM 0x10
+#define CFI_CMD_ERASE_BLOCK_SETUP 0x20
+#define CFI_CMD_WORD_PROGRAM 0x40
+#define CFI_CMD_CLEAR_STATUS_REG 0x50
+#define CFI_CMD_LOCK_BLOCK_SETUP 0x60
+#define CFI_CMD_READ_STATUS_REG 0x70
+#define CFI_CMD_READ_JEDEC_DEVID 0x90
+#define CFI_CMD_READ_CFI_QUERY 0x98
+#define CFI_CMD_CONFIRM 0xd0
+#define CFI_CMD_BUFFERED_PROGRAM_SETUP 0xe8
+#define CFI_CMD_READ_ARRAY 0xff
+
+#define CFI_STATUS_PROTECT_BIT 0x02
+#define CFI_STATUS_PROGRAM_LOCK_BIT 0x10
+#define CFI_STATUS_ERASE_CLEAR_LOCK_BIT 0x20
+#define CFI_STATUS_LOCK_ERROR CFI_STATUS_PROGRAM_LOCK_BIT | \
+ CFI_STATUS_PROTECT_BIT
+#define CFI_STATUS_ERASE_ERROR CFI_STATUS_ERASE_CLEAR_LOCK_BIT | \
+ CFI_STATUS_PROGRAM_LOCK_BIT
+#define CFI_STATUS_READY 0x80
+
+/*
+ * CFI query table contents, as far as it is constant.
+ * The dynamic information (size, etc.) will be generated on the fly.
+ */
+#define CFI_GEOM_OFFSET 0x27
+static const u8 cfi_query_table[] = {
+ /* CFI query identification string */
+ [0x10] = 'Q', 'R', 'Y', /* ID string */
+ 0x01, 0x00, /* primary command set: Intel/Sharp extended */
+ 0x31, 0x00, /* address of primary extended query table */
+ 0x00, 0x00, /* alternative command set: unused */
+ 0x00, 0x00, /* address of alternative extended query table*/
+ /* system interface information */
+ [0x1b] = 0x45, /* minimum Vcc voltage: 4.5V */
+ 0x55, /* maximum Vcc voltage: 5.5V */
+ 0x00, /* minimum Vpp voltage: 0.0V (unused) */
+ 0x00, /* maximum Vpp voltage: 0.0V *(unused) */
+ 0x01, /* timeout for single word program: 2 us */
+ 0x01, /* timeout for multi-byte program: 2 us */
+ 0x01, /* timeout for block erase: 2 ms */
+ 0x00, /* timeout for full chip erase: not supported */
+ 0x00, /* max timeout for single word program: 1x */
+ 0x00, /* max timeout for mulit-byte program: 1x */
+ 0x00, /* max timeout for block erase: 1x */
+ 0x00, /* max timeout for chip erase: not supported */
+ /* flash geometry information */
+ [0x27] = 0x00, /* size in power-of-2 bytes, filled later */
+ 0x05, 0x00, /* interface description: 32 and 16 bits */
+ PROGRAM_BUFF_SIZE_BITS_PER_CHIP, 0x00,
+ /* number of bytes in write buffer */
+ 0x01, /* one erase block region */
+ 0x00, 0x00, 0x00, 0x00, /* number and size of erase blocks, generated */
+ /* Intel primary algorithm extended query table */
+ [0x31] = 'P', 'R', 'I',
+ '1', '0', /* version 1.0 */
+ 0xa0, 0x00, 0x00, 0x00, /* optional features: instant lock & pm-read */
+ 0x00, /* no functions after suspend */
+ 0x01, 0x00, /* only lock bit supported */
+ 0x50, /* best Vcc value: 5.0V */
+ 0x00, /* best Vpp value: 0.0V (unused) */
+ 0x01, /* number of protection register fields */
+ 0x00, 0x00, 0x00, 0x00, /* protection field 1 description */
+};
+
+/*
+ * Those states represent a subset of the CFI flash state machine.
+ */
+enum cfi_flash_state {
+ READY,
+ LOCK_BLOCK_SETUP,
+ WORD_PROGRAM,
+ BUFFERED_PROGRAM_SETUP,
+ BUFFER_WRITE,
+ ERASE_BLOCK_SETUP,
+};
+
+/*
+ * The device can be in several **Read** modes.
+ * We don't implement the asynchronous burst mode.
+ */
+enum cfi_read_mode {
+ READ_ARRAY,
+ READ_STATUS_REG,
+ READ_JEDEC_DEVID,
+ READ_CFI_QUERY,
+};
+
+struct cfi_flash_device {
+ struct device_header dev_hdr;
+ /* Protects the CFI state machine variables in this data structure. */
+ struct mutex mutex;
+ u64 base_addr;
+ u32 size;
+
+ void *flash_memory;
+ u8 program_buffer[PROGRAM_BUFF_SIZE];
+ unsigned long *lock_bm;
+ u64 block_address;
+ unsigned int buff_written;
+ unsigned int buffer_length;
+
+ enum cfi_flash_state state;
+ enum cfi_read_mode read_mode;
+ u8 sr;
+ bool is_mapped;
+};
+
+static int nr_erase_blocks(struct cfi_flash_device *sfdev)
+{
+ return sfdev->size / FLASH_BLOCK_SIZE;
+}
+
+/*
+ * CFI queries always deal with one byte of information, possibly mirrored
+ * to other bytes on the bus. This is dealt with in the callers.
+ * The address provided is the one for 8-bit addressing, and would need to
+ * be adjusted for wider accesses.
+ */
+static u8 read_cfi(struct cfi_flash_device *sfdev, u64 faddr)
+{
+ if (faddr > sizeof(cfi_query_table)) {
+ pr_debug("CFI query read access beyond the end of table");
+ return 0;
+ }
+
+ /* Fixup dynamic information in the geometry part of the table. */
+ switch (faddr) {
+ case 0x27: /* device size in bytes, power of two */
+ return pow2_size(sfdev->size / CFI_NR_FLASH_CHIPS);
+ case 0x2d + 0: /* number of erase blocks, minus one */
+ return (nr_erase_blocks(sfdev) - 1) & 0xff;
+ case 0x2d + 1:
+ return ((nr_erase_blocks(sfdev) - 1) >> 8) & 0xff;
+ case 0x2d + 2: /* erase block size, in units of 256 */
+ return (FLASH_BLOCK_SIZE_PER_CHIP / 256) & 0xff;
+ case 0x2d + 3:
+ return ((FLASH_BLOCK_SIZE_PER_CHIP / 256) >> 8) & 0xff;
+ }
+
+ return cfi_query_table[faddr];
+}
+
+static bool block_is_locked(struct cfi_flash_device *sfdev, u64 faddr)
+{
+ int block_nr = faddr / FLASH_BLOCK_SIZE;
+
+ return test_bit(block_nr, sfdev->lock_bm);
+}
+
+#define DEV_ID_MASK 0x7ff
+static u16 read_dev_id(struct cfi_flash_device *sfdev, u64 faddr)
+{
+ switch ((faddr & DEV_ID_MASK) / CFI_BUS_WIDTH) {
+ case 0x0: /* vendor ID */
+ return 0x0000;
+ case 0x1: /* device ID */
+ return 0xffff;
+ case 0x2:
+ return block_is_locked(sfdev, faddr & ~DEV_ID_MASK);
+ default: /* Ignore the other entries. */
+ return 0;
+ }
+}
+
+static void lock_block(struct cfi_flash_device *sfdev, u64 faddr, bool lock)
+{
+ int block_nr = faddr / FLASH_BLOCK_SIZE;
+
+ if (lock)
+ set_bit(block_nr, sfdev->lock_bm);
+ else
+ clear_bit(block_nr, sfdev->lock_bm);
+}
+
+static void word_program(struct cfi_flash_device *sfdev,
+ u64 faddr, void *data, int len)
+{
+ if (block_is_locked(sfdev, faddr)) {
+ sfdev->sr |= CFI_STATUS_LOCK_ERROR;
+ return;
+ }
+
+ memcpy(sfdev->flash_memory + faddr, data, len);
+}
+
+/* Reset the program buffer state to prepare for follow-up writes. */
+static void buffer_setup(struct cfi_flash_device *sfdev)
+{
+ memset(sfdev->program_buffer, 0, sizeof(sfdev->program_buffer));
+ sfdev->block_address = ~0ULL;
+ sfdev->buff_written = 0;
+}
+
+static bool buffer_write(struct cfi_flash_device *sfdev,
+ u64 faddr, void *buffer, int len)
+{
+ unsigned int buff_addr;
+
+ if (sfdev->buff_written >= sfdev->buffer_length)
+ return false;
+
+ /*
+ * The first word written into the buffer after the setup command
+ * happens to be the base address for the buffer.
+ * All subsequent writes need to be within this address and this
+ * address plus the buffer size, so keep this value around.
+ */
+ if (sfdev->block_address == ~0ULL)
+ sfdev->block_address = faddr;
+
+ if (faddr < sfdev->block_address)
+ return false;
+ buff_addr = faddr - sfdev->block_address;
+ if (buff_addr >= PROGRAM_BUFF_SIZE)
+ return false;
+
+ memcpy(sfdev->program_buffer + buff_addr, buffer, len);
+ sfdev->buff_written += len;
+
+ return true;
+}
+
+static void buffer_confirm(struct cfi_flash_device *sfdev)
+{
+ if (block_is_locked(sfdev, sfdev->block_address)) {
+ sfdev->sr |= CFI_STATUS_LOCK_ERROR;
+ return;
+ }
+ memcpy(sfdev->flash_memory + sfdev->block_address,
+ sfdev->program_buffer, sfdev->buff_written);
+}
+
+static void block_erase_confirm(struct cfi_flash_device *sfdev, u64 faddr)
+{
+ if (block_is_locked(sfdev, faddr)) {
+ sfdev->sr |= CFI_STATUS_LOCK_ERROR;
+ return;
+ }
+
+ memset(sfdev->flash_memory + faddr, 0xff, FLASH_BLOCK_SIZE);
+}
+
+static void cfi_flash_read(struct cfi_flash_device *sfdev,
+ u64 faddr, u8 *data, u32 len)
+{
+ u16 cfi_value = 0;
+
+ switch (sfdev->read_mode) {
+ case READ_ARRAY:
+ /* just copy the requested bytes from the array */
+ memcpy(data, sfdev->flash_memory + faddr, len);
+ return;
+ case READ_STATUS_REG:
+ cfi_value = sfdev->sr;
+ break;
+ case READ_JEDEC_DEVID:
+ cfi_value = read_dev_id(sfdev, faddr);
+ break;
+ case READ_CFI_QUERY:
+ cfi_value = read_cfi(sfdev, faddr / CFI_BUS_WIDTH);
+ break;
+ }
+ switch (len) {
+ case 1:
+ *data = cfi_value;
+ break;
+ case 8: memset(data + 4, 0, 4);
+ /* fall-through */
+ case 4:
+ if (CFI_NR_FLASH_CHIPS == 2)
+ memcpy(data + 2, &cfi_value, 2);
+ else
+ memset(data + 2, 0, 2);
+ /* fall-through */
+ case 2:
+ memcpy(data, &cfi_value, 2);
+ break;
+ default:
+ pr_debug("CFI flash: illegal access length %d for read mode %d",
+ len, sfdev->read_mode);
+ break;
+ }
+}
+
+/*
+ * Any writes happening in "READY" state don't actually write to the memory,
+ * but are really treated as commands to advance the state machine and select
+ * the next action.
+ * Change the state and modes according to the value written. The address
+ * that value is written to does not matter and is ignored.
+ */
+static void cfi_flash_write_ready(struct cfi_flash_device *sfdev, u8 command)
+{
+ switch (command) {
+ case CFI_CMD_READ_JEDEC_DEVID:
+ sfdev->read_mode = READ_JEDEC_DEVID;
+ break;
+ case CFI_CMD_READ_STATUS_REG:
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+ case CFI_CMD_READ_CFI_QUERY:
+ sfdev->read_mode = READ_CFI_QUERY;
+ break;
+ case CFI_CMD_CLEAR_STATUS_REG:
+ sfdev->sr = CFI_STATUS_READY;
+ break;
+ case CFI_CMD_WORD_PROGRAM:
+ case CFI_CMD_ALTERNATE_WORD_PROGRAM:
+ sfdev->state = WORD_PROGRAM;
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+ case CFI_CMD_LOCK_BLOCK_SETUP:
+ sfdev->state = LOCK_BLOCK_SETUP;
+ break;
+ case CFI_CMD_ERASE_BLOCK_SETUP:
+ sfdev->state = ERASE_BLOCK_SETUP;
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+ case CFI_CMD_BUFFERED_PROGRAM_SETUP:
+ buffer_setup(sfdev);
+ sfdev->state = BUFFERED_PROGRAM_SETUP;
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+ case CFI_CMD_CONFIRM:
+ pr_debug("CFI flash: unexpected confirm command 0xd0");
+ break;
+ default:
+ pr_debug("CFI flash: unknown command 0x%x", command);
+ /* fall-through */
+ case CFI_CMD_READ_ARRAY:
+ sfdev->read_mode = READ_ARRAY;
+ break;
+ }
+}
+
+static void cfi_flash_write(struct cfi_flash_device *sfdev, u16 command,
+ u64 faddr, u8 *data, u32 len)
+{
+ switch (sfdev->state) {
+ case READY:
+ cfi_flash_write_ready(sfdev, command & 0xff);
+ return;
+ case LOCK_BLOCK_SETUP:
+ switch (command & 0xff) {
+ case CFI_CMD_LOCK_BLOCK:
+ lock_block(sfdev, faddr, true);
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+ case CFI_CMD_CONFIRM:
+ lock_block(sfdev, faddr, false);
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+ default:
+ sfdev->sr |= CFI_STATUS_ERASE_ERROR;
+ break;
+ }
+ sfdev->state = READY;
+ break;
+
+ case WORD_PROGRAM:
+ word_program(sfdev, faddr, data, len);
+ sfdev->read_mode = READ_STATUS_REG;
+ sfdev->state = READY;
+ break;
+
+ case BUFFER_WRITE:
+ if (buffer_write(sfdev, faddr, data, len))
+ break;
+
+ if ((command & 0xff) == CFI_CMD_CONFIRM) {
+ buffer_confirm(sfdev);
+ sfdev->read_mode = READ_STATUS_REG;
+ } else {
+ pr_debug("CFI flash: BUFFER_WRITE: expected CONFIRM(0xd0), got 0x%x @ 0x%llx",
+ command, faddr);
+ sfdev->sr |= CFI_STATUS_PROGRAM_LOCK_BIT;
+ }
+ sfdev->state = READY;
+ break;
+
+ case BUFFERED_PROGRAM_SETUP:
+ sfdev->buffer_length = (command + 1) * CFI_BUS_WIDTH;
+ if (sfdev->buffer_length > PROGRAM_BUFF_SIZE)
+ sfdev->buffer_length = PROGRAM_BUFF_SIZE;
+ sfdev->state = BUFFER_WRITE;
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+
+ case ERASE_BLOCK_SETUP:
+ if ((command & 0xff) == CFI_CMD_CONFIRM)
+ block_erase_confirm(sfdev, faddr);
+ else
+ sfdev->sr |= CFI_STATUS_ERASE_ERROR;
+
+ sfdev->state = READY;
+ sfdev->read_mode = READ_STATUS_REG;
+ break;
+ default:
+ pr_debug("CFI flash: unexpected/unknown command 0x%x", command);
+ break;
+ }
+}
+
+/*
+ * If we are in ARRAY_READ mode, we can map the flash array directly
+ * into the guest, just as read-only. This greatly improves read
+ * performance, and avoids problems with exits due to accesses from
+ * load instructions without syndrome information (on ARM).
+ * Also it could allow code to be executed XIP in there.
+ */
+static int map_flash_memory(struct kvm *kvm, struct cfi_flash_device *sfdev)
+{
+ int ret;
+
+ ret = kvm__register_mem(kvm, sfdev->base_addr, sfdev->size,
+ sfdev->flash_memory,
+ KVM_MEM_TYPE_RAM | KVM_MEM_TYPE_READONLY);
+ if (!ret)
+ sfdev->is_mapped = true;
+
+ return ret;
+}
+
+/*
+ * Any write access changing the read mode would need to bring us back to
+ * "trap everything", as the CFI query read need proper handholding.
+ */
+static int unmap_flash_memory(struct kvm *kvm, struct cfi_flash_device *sfdev)
+{
+ int ret;
+
+ ret = kvm__destroy_mem(kvm, sfdev->base_addr, sfdev->size,
+ sfdev->flash_memory);
+
+ if (!ret)
+ sfdev->is_mapped = false;
+
+ return ret;
+}
+
+static void cfi_flash_mmio(struct kvm_cpu *vcpu,
+ u64 addr, u8 *data, u32 len, u8 is_write,
+ void *context)
+{
+ struct cfi_flash_device *sfdev = context;
+ u64 faddr = addr - sfdev->base_addr;
+ u32 value;
+
+ if (!is_write) {
+ mutex_lock(&sfdev->mutex);
+
+ cfi_flash_read(sfdev, faddr, data, len);
+
+ mutex_unlock(&sfdev->mutex);
+
+ return;
+ }
+
+ if (len > 4) {
+ pr_info("CFI flash: MMIO %d-bit write access not supported",
+ len * 8);
+ return;
+ }
+
+ memcpy(&value, data, len);
+
+ mutex_lock(&sfdev->mutex);
+
+ cfi_flash_write(sfdev, value & 0xffff, faddr, data, len);
+
+ /* Adjust our mapping status accordingly. */
+ if (!sfdev->is_mapped && sfdev->read_mode == READ_ARRAY)
+ map_flash_memory(vcpu->kvm, sfdev);
+ else if (sfdev->is_mapped && sfdev->read_mode != READ_ARRAY)
+ unmap_flash_memory(vcpu->kvm, sfdev);
+
+ mutex_unlock(&sfdev->mutex);
+}
+
+#ifdef CONFIG_HAS_LIBFDT
+static void generate_cfi_flash_fdt_node(void *fdt,
+ struct device_header *dev_hdr,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq,
+ enum irq_type))
+{
+ struct cfi_flash_device *sfdev;
+ u64 reg_prop[2];
+
+ sfdev = container_of(dev_hdr, struct cfi_flash_device, dev_hdr);
+ reg_prop[0] = cpu_to_fdt64(sfdev->base_addr);
+ reg_prop[1] = cpu_to_fdt64(sfdev->size);
+
+ _FDT(fdt_begin_node(fdt, "flash"));
+ _FDT(fdt_property_cell(fdt, "bank-width", CFI_BUS_WIDTH));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x1));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x1));
+ _FDT(fdt_property_string(fdt, "compatible", "cfi-flash"));
+ _FDT(fdt_property_string(fdt, "label", "System-firmware"));
+ _FDT(fdt_property(fdt, "reg", ®_prop, sizeof(reg_prop)));
+ _FDT(fdt_end_node(fdt));
+}
+#else
+#define generate_cfi_flash_fdt_node NULL
+#endif
+
+static struct cfi_flash_device *create_flash_device_file(struct kvm *kvm,
+ const char *filename)
+{
+ struct cfi_flash_device *sfdev;
+ struct stat statbuf;
+ unsigned int value;
+ int ret;
+ int fd;
+
+ fd = open(filename, O_RDWR);
+ if (fd < 0)
+ return ERR_PTR(-errno);
+
+ if (fstat(fd, &statbuf) < 0) {
+ ret = -errno;
+ goto out_close;
+ }
+
+ sfdev = malloc(sizeof(struct cfi_flash_device));
+ if (!sfdev) {
+ ret = -ENOMEM;
+ goto out_close;
+ }
+
+ sfdev->size = statbuf.st_size;
+ /* Round down to nearest power-of-2 size value. */
+ sfdev->size = 1U << (pow2_size(sfdev->size + 1) - 1);
+ if (sfdev->size > KVM_FLASH_MAX_SIZE)
+ sfdev->size = KVM_FLASH_MAX_SIZE;
+ if (sfdev->size < statbuf.st_size) {
+ pr_info("flash file size (%llu bytes) is not a power of two",
+ (unsigned long long)statbuf.st_size);
+ pr_info("only using first %u bytes", sfdev->size);
+ }
+ sfdev->flash_memory = mmap(NULL, sfdev->size,
+ PROT_READ | PROT_WRITE, MAP_SHARED,
+ fd, 0);
+ if (sfdev->flash_memory == MAP_FAILED) {
+ ret = -errno;
+ goto out_free;
+ }
+ sfdev->base_addr = KVM_FLASH_MMIO_BASE;
+ sfdev->state = READY;
+ sfdev->read_mode = READ_ARRAY;
+ sfdev->sr = CFI_STATUS_READY;
+
+ map_flash_memory(kvm, sfdev);
+
+ value = roundup(nr_erase_blocks(sfdev), BITS_PER_LONG) / 8;
+ sfdev->lock_bm = malloc(value);
+ memset(sfdev->lock_bm, 0, value);
+
+ sfdev->dev_hdr.bus_type = DEVICE_BUS_MMIO;
+ sfdev->dev_hdr.data = generate_cfi_flash_fdt_node;
+ mutex_init(&sfdev->mutex);
+ ret = device__register(&sfdev->dev_hdr);
+ if (ret)
+ goto out_unmap;
+
+ ret = kvm__register_mmio(kvm,
+ sfdev->base_addr, sfdev->size,
+ false, cfi_flash_mmio, sfdev);
+ if (ret) {
+ device__unregister(&sfdev->dev_hdr);
+ goto out_unmap;
+ }
+
+ return sfdev;
+
+out_unmap:
+ munmap(sfdev->flash_memory, sfdev->size);
+out_free:
+ free(sfdev);
+out_close:
+ close(fd);
+
+ return ERR_PTR(ret);
+}
+
+static int cfi_flash__init(struct kvm *kvm)
+{
+ struct cfi_flash_device *sfdev;
+
+ BUILD_BUG_ON(CFI_NR_FLASH_CHIPS != 1 && CFI_NR_FLASH_CHIPS != 2);
+
+ if (!kvm->cfg.flash_filename)
+ return 0;
+
+ sfdev = create_flash_device_file(kvm, kvm->cfg.flash_filename);
+ if (IS_ERR(sfdev))
+ return PTR_ERR(sfdev);
+
+ return 0;
+}
+dev_init(cfi_flash__init);
diff --git a/kvmtool/hw/i8042.c b/kvmtool/hw/i8042.c
new file mode 100644
index 0000000..37a99a2
--- /dev/null
+++ b/kvmtool/hw/i8042.c
@@ -0,0 +1,367 @@
+#include "kvm/read-write.h"
+#include "kvm/ioport.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+#include "kvm/kvm.h"
+#include "kvm/i8042.h"
+#include "kvm/kvm-cpu.h"
+
+#include <stdint.h>
+
+/*
+ * IRQs
+ */
+#define KBD_IRQ 1
+#define AUX_IRQ 12
+
+/*
+ * Registers
+ */
+#define I8042_DATA_REG 0x60
+#define I8042_PORT_B_REG 0x61
+#define I8042_COMMAND_REG 0x64
+
+/*
+ * Commands
+ */
+#define I8042_CMD_CTL_RCTR 0x20
+#define I8042_CMD_CTL_WCTR 0x60
+#define I8042_CMD_AUX_LOOP 0xD3
+#define I8042_CMD_AUX_SEND 0xD4
+#define I8042_CMD_AUX_TEST 0xA9
+#define I8042_CMD_AUX_DISABLE 0xA7
+#define I8042_CMD_AUX_ENABLE 0xA8
+#define I8042_CMD_SYSTEM_RESET 0xFE
+
+#define RESPONSE_ACK 0xFA
+
+#define MODE_DISABLE_AUX 0x20
+
+#define AUX_ENABLE_REPORTING 0x20
+#define AUX_SCALING_FLAG 0x10
+#define AUX_DEFAULT_RESOLUTION 0x2
+#define AUX_DEFAULT_SAMPLE 100
+
+/*
+ * Status register bits
+ */
+#define I8042_STR_AUXDATA 0x20
+#define I8042_STR_KEYLOCK 0x10
+#define I8042_STR_CMDDAT 0x08
+#define I8042_STR_MUXERR 0x04
+#define I8042_STR_OBF 0x01
+
+#define KBD_MODE_KBD_INT 0x01
+#define KBD_MODE_SYS 0x02
+
+#define QUEUE_SIZE 128
+
+/*
+ * This represents the current state of the PS/2 keyboard system,
+ * including the AUX device (the mouse)
+ */
+struct kbd_state {
+ struct kvm *kvm;
+
+ char kq[QUEUE_SIZE]; /* Keyboard queue */
+ int kread, kwrite; /* Indexes into the queue */
+ int kcount; /* number of elements in queue */
+
+ char mq[QUEUE_SIZE];
+ int mread, mwrite;
+ int mcount;
+
+ u8 mstatus; /* Mouse status byte */
+ u8 mres; /* Current mouse resolution */
+ u8 msample; /* Current mouse samples/second */
+
+ u8 mode; /* i8042 mode register */
+ u8 status; /* i8042 status register */
+ /*
+ * Some commands (on port 0x64) have arguments;
+ * we store the command here while we wait for the argument
+ */
+ u32 write_cmd;
+};
+
+static struct kbd_state state;
+
+/*
+ * If there are packets to be read, set the appropriate IRQs high
+ */
+static void kbd_update_irq(void)
+{
+ u8 klevel = 0;
+ u8 mlevel = 0;
+
+ /* First, clear the kbd and aux output buffer full bits */
+ state.status &= ~(I8042_STR_OBF | I8042_STR_AUXDATA);
+
+ if (state.kcount > 0) {
+ state.status |= I8042_STR_OBF;
+ klevel = 1;
+ }
+
+ /* Keyboard has higher priority than mouse */
+ if (klevel == 0 && state.mcount != 0) {
+ state.status |= I8042_STR_OBF | I8042_STR_AUXDATA;
+ mlevel = 1;
+ }
+
+ kvm__irq_line(state.kvm, KBD_IRQ, klevel);
+ kvm__irq_line(state.kvm, AUX_IRQ, mlevel);
+}
+
+/*
+ * Add a byte to the mouse queue, then set IRQs
+ */
+void mouse_queue(u8 c)
+{
+ if (state.mcount >= QUEUE_SIZE)
+ return;
+
+ state.mq[state.mwrite++ % QUEUE_SIZE] = c;
+
+ state.mcount++;
+ kbd_update_irq();
+}
+
+/*
+ * Add a byte to the keyboard queue, then set IRQs
+ */
+void kbd_queue(u8 c)
+{
+ if (state.kcount >= QUEUE_SIZE)
+ return;
+
+ state.kq[state.kwrite++ % QUEUE_SIZE] = c;
+
+ state.kcount++;
+ kbd_update_irq();
+}
+
+static void kbd_write_command(struct kvm *kvm, u8 val)
+{
+ switch (val) {
+ case I8042_CMD_CTL_RCTR:
+ kbd_queue(state.mode);
+ break;
+ case I8042_CMD_CTL_WCTR:
+ case I8042_CMD_AUX_SEND:
+ case I8042_CMD_AUX_LOOP:
+ state.write_cmd = val;
+ break;
+ case I8042_CMD_AUX_TEST:
+ /* 0 means we're a normal PS/2 mouse */
+ mouse_queue(0);
+ break;
+ case I8042_CMD_AUX_DISABLE:
+ state.mode |= MODE_DISABLE_AUX;
+ break;
+ case I8042_CMD_AUX_ENABLE:
+ state.mode &= ~MODE_DISABLE_AUX;
+ break;
+ case I8042_CMD_SYSTEM_RESET:
+ kvm__reboot(kvm);
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * Called when the OS reads from port 0x60 (PS/2 data)
+ */
+static u32 kbd_read_data(void)
+{
+ u32 ret;
+ int i;
+
+ if (state.kcount != 0) {
+ /* Keyboard data gets read first */
+ ret = state.kq[state.kread++ % QUEUE_SIZE];
+ state.kcount--;
+ kvm__irq_line(state.kvm, KBD_IRQ, 0);
+ kbd_update_irq();
+ } else if (state.mcount > 0) {
+ /* Followed by the mouse */
+ ret = state.mq[state.mread++ % QUEUE_SIZE];
+ state.mcount--;
+ kvm__irq_line(state.kvm, AUX_IRQ, 0);
+ kbd_update_irq();
+ } else {
+ i = state.kread - 1;
+ if (i < 0)
+ i = QUEUE_SIZE;
+ ret = state.kq[i];
+ }
+ return ret;
+}
+
+/*
+ * Called when the OS read from port 0x64, the command port
+ */
+static u32 kbd_read_status(void)
+{
+ return (u32)state.status;
+}
+
+/*
+ * Called when the OS writes to port 0x60 (data port)
+ * Things written here are generally arguments to commands previously
+ * written to port 0x64 and stored in state.write_cmd
+ */
+static void kbd_write_data(u32 val)
+{
+ switch (state.write_cmd) {
+ case I8042_CMD_CTL_WCTR:
+ state.mode = val;
+ kbd_update_irq();
+ break;
+ case I8042_CMD_AUX_LOOP:
+ mouse_queue(val);
+ mouse_queue(RESPONSE_ACK);
+ break;
+ case I8042_CMD_AUX_SEND:
+ /* The OS wants to send a command to the mouse */
+ mouse_queue(RESPONSE_ACK);
+ switch (val) {
+ case 0xe6:
+ /* set scaling = 1:1 */
+ state.mstatus &= ~AUX_SCALING_FLAG;
+ break;
+ case 0xe8:
+ /* set resolution */
+ state.mres = val;
+ break;
+ case 0xe9:
+ /* Report mouse status/config */
+ mouse_queue(state.mstatus);
+ mouse_queue(state.mres);
+ mouse_queue(state.msample);
+ break;
+ case 0xf2:
+ /* send ID */
+ mouse_queue(0); /* normal mouse */
+ break;
+ case 0xf3:
+ /* set sample rate */
+ state.msample = val;
+ break;
+ case 0xf4:
+ /* enable reporting */
+ state.mstatus |= AUX_ENABLE_REPORTING;
+ break;
+ case 0xf5:
+ state.mstatus &= ~AUX_ENABLE_REPORTING;
+ break;
+ case 0xf6:
+ /* set defaults, just fall through to reset */
+ case 0xff:
+ /* reset */
+ state.mstatus = 0x0;
+ state.mres = AUX_DEFAULT_RESOLUTION;
+ state.msample = AUX_DEFAULT_SAMPLE;
+ break;
+ default:
+ break;
+ }
+ break;
+ case 0:
+ /* Just send the ID */
+ kbd_queue(RESPONSE_ACK);
+ kbd_queue(0xab);
+ kbd_queue(0x41);
+ kbd_update_irq();
+ break;
+ default:
+ /* Yeah whatever */
+ break;
+ }
+ state.write_cmd = 0;
+}
+
+static void kbd_reset(void)
+{
+ state = (struct kbd_state) {
+ .status = I8042_STR_MUXERR | I8042_STR_CMDDAT | I8042_STR_KEYLOCK, /* 0x1c */
+ .mode = KBD_MODE_KBD_INT | KBD_MODE_SYS, /* 0x3 */
+ .mres = AUX_DEFAULT_RESOLUTION,
+ .msample = AUX_DEFAULT_SAMPLE,
+ };
+}
+
+/*
+ * Called when the OS has written to one of the keyboard's ports (0x60 or 0x64)
+ */
+static bool kbd_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ switch (port) {
+ case I8042_COMMAND_REG: {
+ u8 value = kbd_read_status();
+ ioport__write8(data, value);
+ break;
+ }
+ case I8042_DATA_REG: {
+ u32 value = kbd_read_data();
+ ioport__write32(data, value);
+ break;
+ }
+ case I8042_PORT_B_REG: {
+ ioport__write8(data, 0x20);
+ break;
+ }
+ default:
+ return false;
+ }
+
+ return true;
+}
+
+static bool kbd_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ switch (port) {
+ case I8042_COMMAND_REG: {
+ u8 value = ioport__read8(data);
+ kbd_write_command(vcpu->kvm, value);
+ break;
+ }
+ case I8042_DATA_REG: {
+ u32 value = ioport__read32(data);
+ kbd_write_data(value);
+ break;
+ }
+ case I8042_PORT_B_REG: {
+ break;
+ }
+ default:
+ return false;
+ }
+
+ return true;
+}
+
+static struct ioport_operations kbd_ops = {
+ .io_in = kbd_in,
+ .io_out = kbd_out,
+};
+
+int kbd__init(struct kvm *kvm)
+{
+ int r;
+
+ kbd_reset();
+ state.kvm = kvm;
+ r = ioport__register(kvm, I8042_DATA_REG, &kbd_ops, 2, NULL);
+ if (r < 0)
+ return r;
+ r = ioport__register(kvm, I8042_COMMAND_REG, &kbd_ops, 2, NULL);
+ if (r < 0) {
+ ioport__unregister(kvm, I8042_DATA_REG);
+ return r;
+ }
+
+ return 0;
+}
+dev_init(kbd__init);
diff --git a/kvmtool/hw/rtc.c b/kvmtool/hw/rtc.c
new file mode 100644
index 0000000..5483879
--- /dev/null
+++ b/kvmtool/hw/rtc.c
@@ -0,0 +1,195 @@
+#include "kvm/rtc.h"
+
+#include "kvm/ioport.h"
+#include "kvm/kvm.h"
+
+#include <time.h>
+
+/*
+ * MC146818 RTC registers
+ */
+#define RTC_SECONDS 0x00
+#define RTC_SECONDS_ALARM 0x01
+#define RTC_MINUTES 0x02
+#define RTC_MINUTES_ALARM 0x03
+#define RTC_HOURS 0x04
+#define RTC_HOURS_ALARM 0x05
+#define RTC_DAY_OF_WEEK 0x06
+#define RTC_DAY_OF_MONTH 0x07
+#define RTC_MONTH 0x08
+#define RTC_YEAR 0x09
+#define RTC_CENTURY 0x32
+
+#define RTC_REG_A 0x0A
+#define RTC_REG_B 0x0B
+#define RTC_REG_C 0x0C
+#define RTC_REG_D 0x0D
+
+/*
+ * Register D Bits
+ */
+#define RTC_REG_D_VRT (1 << 7)
+
+struct rtc_device {
+ u8 cmos_idx;
+ u8 cmos_data[128];
+};
+
+static struct rtc_device rtc;
+
+static inline unsigned char bin2bcd(unsigned val)
+{
+ return ((val / 10) << 4) + val % 10;
+}
+
+static bool cmos_ram_data_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ struct tm *tm;
+ time_t ti;
+
+ time(&ti);
+
+ tm = gmtime(&ti);
+
+ switch (rtc.cmos_idx) {
+ case RTC_SECONDS:
+ ioport__write8(data, bin2bcd(tm->tm_sec));
+ break;
+ case RTC_MINUTES:
+ ioport__write8(data, bin2bcd(tm->tm_min));
+ break;
+ case RTC_HOURS:
+ ioport__write8(data, bin2bcd(tm->tm_hour));
+ break;
+ case RTC_DAY_OF_WEEK:
+ ioport__write8(data, bin2bcd(tm->tm_wday + 1));
+ break;
+ case RTC_DAY_OF_MONTH:
+ ioport__write8(data, bin2bcd(tm->tm_mday));
+ break;
+ case RTC_MONTH:
+ ioport__write8(data, bin2bcd(tm->tm_mon + 1));
+ break;
+ case RTC_YEAR: {
+ int year;
+
+ year = tm->tm_year + 1900;
+
+ ioport__write8(data, bin2bcd(year % 100));
+
+ break;
+ }
+ case RTC_CENTURY: {
+ int year;
+
+ year = tm->tm_year + 1900;
+
+ ioport__write8(data, bin2bcd(year / 100));
+
+ break;
+ }
+ default:
+ ioport__write8(data, rtc.cmos_data[rtc.cmos_idx]);
+ break;
+ }
+
+ return true;
+}
+
+static bool cmos_ram_data_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ switch (rtc.cmos_idx) {
+ case RTC_REG_C:
+ case RTC_REG_D:
+ /* Read-only */
+ break;
+ default:
+ rtc.cmos_data[rtc.cmos_idx] = ioport__read8(data);
+ break;
+ }
+
+ return true;
+}
+
+static struct ioport_operations cmos_ram_data_ioport_ops = {
+ .io_out = cmos_ram_data_out,
+ .io_in = cmos_ram_data_in,
+};
+
+static bool cmos_ram_index_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ u8 value = ioport__read8(data);
+
+ vcpu->kvm->nmi_disabled = value & (1UL << 7);
+ rtc.cmos_idx = value & ~(1UL << 7);
+
+ return true;
+}
+
+static struct ioport_operations cmos_ram_index_ioport_ops = {
+ .io_out = cmos_ram_index_out,
+};
+
+#ifdef CONFIG_HAS_LIBFDT
+static void generate_rtc_fdt_node(void *fdt,
+ struct device_header *dev_hdr,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq,
+ enum irq_type))
+{
+ u64 reg_prop[2] = { cpu_to_fdt64(0x70), cpu_to_fdt64(2) };
+
+ _FDT(fdt_begin_node(fdt, "rtc"));
+ _FDT(fdt_property_string(fdt, "compatible", "motorola,mc146818"));
+ _FDT(fdt_property(fdt, "reg", reg_prop, sizeof(reg_prop)));
+ _FDT(fdt_end_node(fdt));
+}
+#else
+#define generate_rtc_fdt_node NULL
+#endif
+
+struct device_header rtc_dev_hdr = {
+ .bus_type = DEVICE_BUS_IOPORT,
+ .data = generate_rtc_fdt_node,
+};
+
+int rtc__init(struct kvm *kvm)
+{
+ int r;
+
+ r = device__register(&rtc_dev_hdr);
+ if (r < 0)
+ return r;
+
+ /* PORT 0070-007F - CMOS RAM/RTC (REAL TIME CLOCK) */
+ r = ioport__register(kvm, 0x0070, &cmos_ram_index_ioport_ops, 1, NULL);
+ if (r < 0)
+ goto out_device;
+
+ r = ioport__register(kvm, 0x0071, &cmos_ram_data_ioport_ops, 1, NULL);
+ if (r < 0)
+ goto out_ioport;
+
+ /* Set the VRT bit in Register D to indicate valid RAM and time */
+ rtc.cmos_data[RTC_REG_D] = RTC_REG_D_VRT;
+
+ return r;
+
+out_ioport:
+ ioport__unregister(kvm, 0x0070);
+out_device:
+ device__unregister(&rtc_dev_hdr);
+
+ return r;
+}
+dev_init(rtc__init);
+
+int rtc__exit(struct kvm *kvm)
+{
+ /* PORT 0070-007F - CMOS RAM/RTC (REAL TIME CLOCK) */
+ ioport__unregister(kvm, 0x0070);
+ ioport__unregister(kvm, 0x0071);
+
+ return 0;
+}
+dev_exit(rtc__exit);
diff --git a/kvmtool/hw/serial.c b/kvmtool/hw/serial.c
new file mode 100644
index 0000000..13c4663
--- /dev/null
+++ b/kvmtool/hw/serial.c
@@ -0,0 +1,462 @@
+#include "kvm/8250-serial.h"
+
+#include "kvm/read-write.h"
+#include "kvm/ioport.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+#include "kvm/kvm.h"
+#include "kvm/fdt.h"
+
+#include <linux/types.h>
+#include <linux/serial_reg.h>
+
+#include <pthread.h>
+
+/*
+ * This fakes a U6_16550A. The fifo len needs to be 64 as the kernel
+ * expects that for autodetection.
+ */
+#define FIFO_LEN 64
+#define FIFO_MASK (FIFO_LEN - 1)
+
+#define UART_IIR_TYPE_BITS 0xc0
+
+struct serial8250_device {
+ struct mutex mutex;
+ u8 id;
+
+ u16 iobase;
+ u8 irq;
+ u8 irq_state;
+ int txcnt;
+ int rxcnt;
+ int rxdone;
+ char txbuf[FIFO_LEN];
+ char rxbuf[FIFO_LEN];
+
+ u8 dll;
+ u8 dlm;
+ u8 iir;
+ u8 ier;
+ u8 fcr;
+ u8 lcr;
+ u8 mcr;
+ u8 lsr;
+ u8 msr;
+ u8 scr;
+};
+
+#define SERIAL_REGS_SETTING \
+ .iir = UART_IIR_NO_INT, \
+ .lsr = UART_LSR_TEMT | UART_LSR_THRE, \
+ .msr = UART_MSR_DCD | UART_MSR_DSR | UART_MSR_CTS, \
+ .mcr = UART_MCR_OUT2,
+
+static struct serial8250_device devices[] = {
+ /* ttyS0 */
+ [0] = {
+ .mutex = MUTEX_INITIALIZER,
+
+ .id = 0,
+ .iobase = 0x3f8,
+ .irq = 4,
+
+ SERIAL_REGS_SETTING
+ },
+ /* ttyS1 */
+ [1] = {
+ .mutex = MUTEX_INITIALIZER,
+
+ .id = 1,
+ .iobase = 0x2f8,
+ .irq = 3,
+
+ SERIAL_REGS_SETTING
+ },
+ /* ttyS2 */
+ [2] = {
+ .mutex = MUTEX_INITIALIZER,
+
+ .id = 2,
+ .iobase = 0x3e8,
+ .irq = 4,
+
+ SERIAL_REGS_SETTING
+ },
+ /* ttyS3 */
+ [3] = {
+ .mutex = MUTEX_INITIALIZER,
+
+ .id = 3,
+ .iobase = 0x2e8,
+ .irq = 3,
+
+ SERIAL_REGS_SETTING
+ },
+};
+
+static void serial8250_flush_tx(struct kvm *kvm, struct serial8250_device *dev)
+{
+ dev->lsr |= UART_LSR_TEMT | UART_LSR_THRE;
+
+ if (dev->txcnt) {
+ term_putc(dev->txbuf, dev->txcnt, dev->id);
+ dev->txcnt = 0;
+ }
+}
+
+static void serial8250_update_irq(struct kvm *kvm, struct serial8250_device *dev)
+{
+ u8 iir = 0;
+
+ /* Handle clear rx */
+ if (dev->lcr & UART_FCR_CLEAR_RCVR) {
+ dev->lcr &= ~UART_FCR_CLEAR_RCVR;
+ dev->rxcnt = dev->rxdone = 0;
+ dev->lsr &= ~UART_LSR_DR;
+ }
+
+ /* Handle clear tx */
+ if (dev->lcr & UART_FCR_CLEAR_XMIT) {
+ dev->lcr &= ~UART_FCR_CLEAR_XMIT;
+ dev->txcnt = 0;
+ dev->lsr |= UART_LSR_TEMT | UART_LSR_THRE;
+ }
+
+ /* Data ready and rcv interrupt enabled ? */
+ if ((dev->ier & UART_IER_RDI) && (dev->lsr & UART_LSR_DR))
+ iir |= UART_IIR_RDI;
+
+ /* Transmitter empty and interrupt enabled ? */
+ if ((dev->ier & UART_IER_THRI) && (dev->lsr & UART_LSR_TEMT))
+ iir |= UART_IIR_THRI;
+
+ /* Now update the irq line, if necessary */
+ if (!iir) {
+ dev->iir = UART_IIR_NO_INT;
+ if (dev->irq_state)
+ kvm__irq_line(kvm, dev->irq, 0);
+ } else {
+ dev->iir = iir;
+ if (!dev->irq_state)
+ kvm__irq_line(kvm, dev->irq, 1);
+ }
+ dev->irq_state = iir;
+
+ /*
+ * If the kernel disabled the tx interrupt, we know that there
+ * is nothing more to transmit, so we can reset our tx logic
+ * here.
+ */
+ if (!(dev->ier & UART_IER_THRI))
+ serial8250_flush_tx(kvm, dev);
+}
+
+#define SYSRQ_PENDING_NONE 0
+
+static int sysrq_pending;
+
+static void serial8250__sysrq(struct kvm *kvm, struct serial8250_device *dev)
+{
+ dev->lsr |= UART_LSR_DR | UART_LSR_BI;
+ dev->rxbuf[dev->rxcnt++] = sysrq_pending;
+ sysrq_pending = SYSRQ_PENDING_NONE;
+}
+
+static void serial8250__receive(struct kvm *kvm, struct serial8250_device *dev,
+ bool handle_sysrq)
+{
+ int c;
+
+ if (dev->mcr & UART_MCR_LOOP)
+ return;
+
+ if ((dev->lsr & UART_LSR_DR) || dev->rxcnt)
+ return;
+
+ if (handle_sysrq && sysrq_pending) {
+ serial8250__sysrq(kvm, dev);
+ return;
+ }
+
+ if (kvm->cfg.active_console != CONSOLE_8250)
+ return;
+
+ while (term_readable(dev->id) &&
+ dev->rxcnt < FIFO_LEN) {
+
+ c = term_getc(kvm, dev->id);
+
+ if (c < 0)
+ break;
+ dev->rxbuf[dev->rxcnt++] = c;
+ dev->lsr |= UART_LSR_DR;
+ }
+}
+
+void serial8250__update_consoles(struct kvm *kvm)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(devices); i++) {
+ struct serial8250_device *dev = &devices[i];
+
+ mutex_lock(&dev->mutex);
+
+ /* Restrict sysrq injection to the first port */
+ serial8250__receive(kvm, dev, i == 0);
+
+ serial8250_update_irq(kvm, dev);
+
+ mutex_unlock(&dev->mutex);
+ }
+}
+
+void serial8250__inject_sysrq(struct kvm *kvm, char sysrq)
+{
+ sysrq_pending = sysrq;
+}
+
+static bool serial8250_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port,
+ void *data, int size)
+{
+ struct serial8250_device *dev = ioport->priv;
+ u16 offset;
+ bool ret = true;
+ char *addr = data;
+
+ mutex_lock(&dev->mutex);
+
+ offset = port - dev->iobase;
+
+ switch (offset) {
+ case UART_TX:
+ if (dev->lcr & UART_LCR_DLAB) {
+ dev->dll = ioport__read8(data);
+ break;
+ }
+
+ /* Loopback mode */
+ if (dev->mcr & UART_MCR_LOOP) {
+ if (dev->rxcnt < FIFO_LEN) {
+ dev->rxbuf[dev->rxcnt++] = *addr;
+ dev->lsr |= UART_LSR_DR;
+ }
+ break;
+ }
+
+ if (dev->txcnt < FIFO_LEN) {
+ dev->txbuf[dev->txcnt++] = *addr;
+ dev->lsr &= ~UART_LSR_TEMT;
+ if (dev->txcnt == FIFO_LEN / 2)
+ dev->lsr &= ~UART_LSR_THRE;
+ serial8250_flush_tx(vcpu->kvm, dev);
+ } else {
+ /* Should never happpen */
+ dev->lsr &= ~(UART_LSR_TEMT | UART_LSR_THRE);
+ }
+ break;
+ case UART_IER:
+ if (!(dev->lcr & UART_LCR_DLAB))
+ dev->ier = ioport__read8(data) & 0x0f;
+ else
+ dev->dlm = ioport__read8(data);
+ break;
+ case UART_FCR:
+ dev->fcr = ioport__read8(data);
+ break;
+ case UART_LCR:
+ dev->lcr = ioport__read8(data);
+ break;
+ case UART_MCR:
+ dev->mcr = ioport__read8(data);
+ break;
+ case UART_LSR:
+ /* Factory test */
+ break;
+ case UART_MSR:
+ /* Not used */
+ break;
+ case UART_SCR:
+ dev->scr = ioport__read8(data);
+ break;
+ default:
+ ret = false;
+ break;
+ }
+
+ serial8250_update_irq(vcpu->kvm, dev);
+
+ mutex_unlock(&dev->mutex);
+
+ return ret;
+}
+
+static void serial8250_rx(struct serial8250_device *dev, void *data)
+{
+ if (dev->rxdone == dev->rxcnt)
+ return;
+
+ /* Break issued ? */
+ if (dev->lsr & UART_LSR_BI) {
+ dev->lsr &= ~UART_LSR_BI;
+ ioport__write8(data, 0);
+ return;
+ }
+
+ ioport__write8(data, dev->rxbuf[dev->rxdone++]);
+ if (dev->rxcnt == dev->rxdone) {
+ dev->lsr &= ~UART_LSR_DR;
+ dev->rxcnt = dev->rxdone = 0;
+ }
+}
+
+static bool serial8250_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ struct serial8250_device *dev = ioport->priv;
+ u16 offset;
+ bool ret = true;
+
+ mutex_lock(&dev->mutex);
+
+ offset = port - dev->iobase;
+
+ switch (offset) {
+ case UART_RX:
+ if (dev->lcr & UART_LCR_DLAB)
+ ioport__write8(data, dev->dll);
+ else
+ serial8250_rx(dev, data);
+ break;
+ case UART_IER:
+ if (dev->lcr & UART_LCR_DLAB)
+ ioport__write8(data, dev->dlm);
+ else
+ ioport__write8(data, dev->ier);
+ break;
+ case UART_IIR:
+ ioport__write8(data, dev->iir | UART_IIR_TYPE_BITS);
+ break;
+ case UART_LCR:
+ ioport__write8(data, dev->lcr);
+ break;
+ case UART_MCR:
+ ioport__write8(data, dev->mcr);
+ break;
+ case UART_LSR:
+ ioport__write8(data, dev->lsr);
+ break;
+ case UART_MSR:
+ ioport__write8(data, dev->msr);
+ break;
+ case UART_SCR:
+ ioport__write8(data, dev->scr);
+ break;
+ default:
+ ret = false;
+ break;
+ }
+
+ serial8250_update_irq(vcpu->kvm, dev);
+
+ mutex_unlock(&dev->mutex);
+
+ return ret;
+}
+
+#ifdef CONFIG_HAS_LIBFDT
+
+char *fdt_stdout_path = NULL;
+
+#define DEVICE_NAME_MAX_LEN 32
+static
+void serial8250_generate_fdt_node(struct ioport *ioport, void *fdt,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq,
+ enum irq_type))
+{
+ char dev_name[DEVICE_NAME_MAX_LEN];
+ struct serial8250_device *dev = ioport->priv;
+ u64 addr = KVM_IOPORT_AREA + dev->iobase;
+ u64 reg_prop[] = {
+ cpu_to_fdt64(addr),
+ cpu_to_fdt64(8),
+ };
+
+ snprintf(dev_name, DEVICE_NAME_MAX_LEN, "U6_16550A@%llx", addr);
+
+ if (!fdt_stdout_path) {
+ fdt_stdout_path = malloc(strlen(dev_name) + 2);
+ /* Assumes that this node is a child of the root node. */
+ sprintf(fdt_stdout_path, "/%s", dev_name);
+ }
+
+ _FDT(fdt_begin_node(fdt, dev_name));
+ _FDT(fdt_property_string(fdt, "compatible", "ns16550a"));
+ _FDT(fdt_property(fdt, "reg", reg_prop, sizeof(reg_prop)));
+ generate_irq_prop(fdt, dev->irq, IRQ_TYPE_LEVEL_HIGH);
+ _FDT(fdt_property_cell(fdt, "clock-frequency", 1843200));
+ _FDT(fdt_end_node(fdt));
+}
+#else
+#define serial8250_generate_fdt_node NULL
+#endif
+
+static struct ioport_operations serial8250_ops = {
+ .io_in = serial8250_in,
+ .io_out = serial8250_out,
+ .generate_fdt_node = serial8250_generate_fdt_node,
+};
+
+static int serial8250__device_init(struct kvm *kvm, struct serial8250_device *dev)
+{
+ int r;
+
+ ioport__map_irq(&dev->irq);
+ r = ioport__register(kvm, dev->iobase, &serial8250_ops, 8, dev);
+
+ return r;
+}
+
+int serial8250__init(struct kvm *kvm)
+{
+ unsigned int i, j;
+ int r = 0;
+
+ for (i = 0; i < ARRAY_SIZE(devices); i++) {
+ struct serial8250_device *dev = &devices[i];
+
+ r = serial8250__device_init(kvm, dev);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ return r;
+cleanup:
+ for (j = 0; j <= i; j++) {
+ struct serial8250_device *dev = &devices[j];
+
+ ioport__unregister(kvm, dev->iobase);
+ }
+
+ return r;
+}
+dev_init(serial8250__init);
+
+int serial8250__exit(struct kvm *kvm)
+{
+ unsigned int i;
+ int r;
+
+ for (i = 0; i < ARRAY_SIZE(devices); i++) {
+ struct serial8250_device *dev = &devices[i];
+
+ r = ioport__unregister(kvm, dev->iobase);
+ if (r < 0)
+ return r;
+ }
+
+ return 0;
+}
+dev_exit(serial8250__exit);
diff --git a/kvmtool/hw/vesa.c b/kvmtool/hw/vesa.c
new file mode 100644
index 0000000..8659a00
--- /dev/null
+++ b/kvmtool/hw/vesa.c
@@ -0,0 +1,122 @@
+#include "kvm/vesa.h"
+
+#include "kvm/devices.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/framebuffer.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/ioport.h"
+#include "kvm/util.h"
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+
+#include <linux/byteorder.h>
+#include <sys/mman.h>
+#include <linux/err.h>
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <inttypes.h>
+#include <unistd.h>
+
+static struct pci_device_header vesa_pci_device = {
+ .vendor_id = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET),
+ .device_id = cpu_to_le16(PCI_DEVICE_ID_VESA),
+ .header_type = PCI_HEADER_TYPE_NORMAL,
+ .revision_id = 0,
+ .class[2] = 0x03,
+ .subsys_vendor_id = cpu_to_le16(PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET),
+ .subsys_id = cpu_to_le16(PCI_SUBSYSTEM_ID_VESA),
+ .bar[1] = cpu_to_le32(VESA_MEM_ADDR | PCI_BASE_ADDRESS_SPACE_MEMORY),
+ .bar_size[1] = VESA_MEM_SIZE,
+};
+
+static struct device_header vesa_device = {
+ .bus_type = DEVICE_BUS_PCI,
+ .data = &vesa_pci_device,
+};
+
+static struct framebuffer vesafb = {
+ .width = VESA_WIDTH,
+ .height = VESA_HEIGHT,
+ .depth = VESA_BPP,
+ .mem_addr = VESA_MEM_ADDR,
+ .mem_size = VESA_MEM_SIZE,
+};
+
+static bool vesa_pci_io_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static bool vesa_pci_io_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static struct ioport_operations vesa_io_ops = {
+ .io_in = vesa_pci_io_in,
+ .io_out = vesa_pci_io_out,
+};
+
+static int vesa__bar_activate(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ int bar_num, void *data)
+{
+ /* We don't support remapping of the framebuffer. */
+ return 0;
+}
+
+static int vesa__bar_deactivate(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ int bar_num, void *data)
+{
+ /* We don't support remapping of the framebuffer. */
+ return -EINVAL;
+}
+
+struct framebuffer *vesa__init(struct kvm *kvm)
+{
+ u16 vesa_base_addr;
+ char *mem;
+ int r;
+
+ BUILD_BUG_ON(!is_power_of_two(VESA_MEM_SIZE));
+ BUILD_BUG_ON(VESA_MEM_SIZE < VESA_BPP/8 * VESA_WIDTH * VESA_HEIGHT);
+
+ vesa_base_addr = pci_get_io_port_block(PCI_IO_SIZE);
+ r = ioport__register(kvm, vesa_base_addr, &vesa_io_ops, PCI_IO_SIZE, NULL);
+ if (r < 0)
+ goto out_error;
+
+ vesa_pci_device.bar[0] = cpu_to_le32(vesa_base_addr | PCI_BASE_ADDRESS_SPACE_IO);
+ vesa_pci_device.bar_size[0] = PCI_IO_SIZE;
+ r = pci__register_bar_regions(kvm, &vesa_pci_device, vesa__bar_activate,
+ vesa__bar_deactivate, NULL);
+ if (r < 0)
+ goto unregister_ioport;
+
+ r = device__register(&vesa_device);
+ if (r < 0)
+ goto unregister_ioport;
+
+ mem = mmap(NULL, VESA_MEM_SIZE, PROT_RW, MAP_ANON_NORESERVE, -1, 0);
+ if (mem == MAP_FAILED) {
+ r = -errno;
+ goto unregister_device;
+ }
+
+ r = kvm__register_dev_mem(kvm, VESA_MEM_ADDR, VESA_MEM_SIZE, mem);
+ if (r < 0)
+ goto unmap_dev;
+
+ vesafb.mem = mem;
+ vesafb.kvm = kvm;
+ return fb__register(&vesafb);
+
+unmap_dev:
+ munmap(mem, VESA_MEM_SIZE);
+unregister_device:
+ device__unregister(&vesa_device);
+unregister_ioport:
+ ioport__unregister(kvm, vesa_base_addr);
+out_error:
+ return ERR_PTR(r);
+}
diff --git a/kvmtool/include/asm/hweight.h b/kvmtool/include/asm/hweight.h
new file mode 100644
index 0000000..1a43977
--- /dev/null
+++ b/kvmtool/include/asm/hweight.h
@@ -0,0 +1,8 @@
+#ifndef _KVM_ASM_HWEIGHT_H_
+#define _KVM_ASM_HWEIGHT_H_
+
+#include <linux/types.h>
+unsigned int hweight32(unsigned int w);
+unsigned long hweight64(__u64 w);
+
+#endif /* _KVM_ASM_HWEIGHT_H_ */
diff --git a/kvmtool/include/common-cmds.h b/kvmtool/include/common-cmds.h
new file mode 100644
index 0000000..5b95676
--- /dev/null
+++ b/kvmtool/include/common-cmds.h
@@ -0,0 +1,19 @@
+struct cmdname_help
+{
+ char name[16];
+ char help[80];
+};
+
+static struct cmdname_help common_cmds[] = {
+ {"run", "Start the virtual machine"},
+ {"setup", "Setup a new virtual machine"},
+ {"pause", "Pause the virtual machine"},
+ {"resume", "Resume the virtual machine"},
+ {"version", "Print the version of the kernel tree kvm tools"},
+ {"list", "Print a list of running instances on the host."},
+ {"debug", "Print debug information from a running instance"},
+ {"balloon", "Inflate or deflate the virtio balloon"},
+ {"stop", "Stop a running instance"},
+ {"stat", "Print statistics about a running instance"},
+ {"sandbox", "Run a command in a sandboxed guest"},
+};
diff --git a/kvmtool/include/kvm/8250-serial.h b/kvmtool/include/kvm/8250-serial.h
new file mode 100644
index 0000000..e954551
--- /dev/null
+++ b/kvmtool/include/kvm/8250-serial.h
@@ -0,0 +1,11 @@
+#ifndef KVM__8250_SERIAL_H
+#define KVM__8250_SERIAL_H
+
+struct kvm;
+
+int serial8250__init(struct kvm *kvm);
+int serial8250__exit(struct kvm *kvm);
+void serial8250__update_consoles(struct kvm *kvm);
+void serial8250__inject_sysrq(struct kvm *kvm, char sysrq);
+
+#endif /* KVM__8250_SERIAL_H */
diff --git a/kvmtool/include/kvm/apic.h b/kvmtool/include/kvm/apic.h
new file mode 100644
index 0000000..2129997
--- /dev/null
+++ b/kvmtool/include/kvm/apic.h
@@ -0,0 +1,17 @@
+#ifndef KVM_APIC_H_
+#define KVM_APIC_H_
+
+#include <asm/apicdef.h>
+
+/*
+ * APIC, IOAPIC stuff
+ */
+#define APIC_BASE_ADDR_STEP 0x00400000
+#define IOAPIC_BASE_ADDR_STEP 0x00100000
+
+#define APIC_ADDR(apic) (APIC_DEFAULT_PHYS_BASE + apic * APIC_BASE_ADDR_STEP)
+#define IOAPIC_ADDR(ioapic) (IO_APIC_DEFAULT_PHYS_BASE + ioapic * IOAPIC_BASE_ADDR_STEP)
+
+#define KVM_APIC_VERSION 0x14 /* xAPIC */
+
+#endif /* KVM_APIC_H_ */
diff --git a/kvmtool/include/kvm/brlock.h b/kvmtool/include/kvm/brlock.h
new file mode 100644
index 0000000..1862210
--- /dev/null
+++ b/kvmtool/include/kvm/brlock.h
@@ -0,0 +1,39 @@
+#ifndef KVM__BRLOCK_H
+#define KVM__BRLOCK_H
+
+#include "kvm/kvm.h"
+#include "kvm/barrier.h"
+
+/*
+ * brlock is a lock which is very cheap for reads, but very expensive
+ * for writes.
+ * This lock will be used when updates are very rare and reads are common.
+ * This lock is currently implemented by stopping the guest while
+ * performing the updates. We assume that the only threads whichread from
+ * the locked data are VCPU threads, and the only writer isn't a VCPU thread.
+ */
+
+#ifndef barrier
+#define barrier() __asm__ __volatile__("": : :"memory")
+#endif
+
+#ifdef KVM_BRLOCK_DEBUG
+
+#include "kvm/rwsem.h"
+
+#define br_read_lock(kvm) down_read(&(kvm)->brlock_sem);
+#define br_read_unlock(kvm) up_read(&(kvm)->brlock_sem);
+
+#define br_write_lock(kvm) down_write(&(kvm)->brlock_sem);
+#define br_write_unlock(kvm) up_write(&(kvm)->brlock_sem);
+
+#else
+
+#define br_read_lock(kvm) barrier()
+#define br_read_unlock(kvm) barrier()
+
+#define br_write_lock(kvm) kvm__pause(kvm)
+#define br_write_unlock(kvm) kvm__continue(kvm)
+#endif
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-balloon.h b/kvmtool/include/kvm/builtin-balloon.h
new file mode 100644
index 0000000..77ee656
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-balloon.h
@@ -0,0 +1,9 @@
+#ifndef KVM__BALLOON_H
+#define KVM__BALLOON_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_balloon(int argc, const char **argv, const char *prefix);
+void kvm_balloon_help(void) NORETURN;
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-debug.h b/kvmtool/include/kvm/builtin-debug.h
new file mode 100644
index 0000000..efa0268
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-debug.h
@@ -0,0 +1,20 @@
+#ifndef KVM__DEBUG_H
+#define KVM__DEBUG_H
+
+#include <kvm/util.h>
+#include <linux/types.h>
+
+#define KVM_DEBUG_CMD_TYPE_DUMP (1 << 0)
+#define KVM_DEBUG_CMD_TYPE_NMI (1 << 1)
+#define KVM_DEBUG_CMD_TYPE_SYSRQ (1 << 2)
+
+struct debug_cmd_params {
+ u32 dbg_type;
+ u32 cpu;
+ char sysrq;
+};
+
+int kvm_cmd_debug(int argc, const char **argv, const char *prefix);
+void kvm_debug_help(void) NORETURN;
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-help.h b/kvmtool/include/kvm/builtin-help.h
new file mode 100644
index 0000000..2946743
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-help.h
@@ -0,0 +1,6 @@
+#ifndef __KVM_HELP_H__
+#define __KVM_HELP_H__
+
+int kvm_cmd_help(int argc, const char **argv, const char *prefix);
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-list.h b/kvmtool/include/kvm/builtin-list.h
new file mode 100644
index 0000000..47029ca
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-list.h
@@ -0,0 +1,10 @@
+#ifndef KVM__LIST_H
+#define KVM__LIST_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_list(int argc, const char **argv, const char *prefix);
+void kvm_list_help(void) NORETURN;
+int get_vmstate(int sock);
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-pause.h b/kvmtool/include/kvm/builtin-pause.h
new file mode 100644
index 0000000..84aaee3
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-pause.h
@@ -0,0 +1,9 @@
+#ifndef KVM__PAUSE_H
+#define KVM__PAUSE_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_pause(int argc, const char **argv, const char *prefix);
+void kvm_pause_help(void) NORETURN;
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-resume.h b/kvmtool/include/kvm/builtin-resume.h
new file mode 100644
index 0000000..7de999b
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-resume.h
@@ -0,0 +1,9 @@
+#ifndef KVM__RESUME_H
+#define KVM__RESUME_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_resume(int argc, const char **argv, const char *prefix);
+void kvm_resume_help(void) NORETURN;
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-run.h b/kvmtool/include/kvm/builtin-run.h
new file mode 100644
index 0000000..91521a5
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-run.h
@@ -0,0 +1,11 @@
+#ifndef __KVM_RUN_H__
+#define __KVM_RUN_H__
+
+#include <kvm/util.h>
+
+int kvm_cmd_run(int argc, const char **argv, const char *prefix);
+void kvm_run_help(void) NORETURN;
+
+void kvm_run_set_wrapper_sandbox(void);
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-sandbox.h b/kvmtool/include/kvm/builtin-sandbox.h
new file mode 100644
index 0000000..98cd6be
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-sandbox.h
@@ -0,0 +1,6 @@
+#ifndef KVM__SANDBOX_H
+#define KVM__SANDBOX_H
+
+int kvm_cmd_sandbox(int argc, const char **argv, const char *prefix);
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-setup.h b/kvmtool/include/kvm/builtin-setup.h
new file mode 100644
index 0000000..239bbbd
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-setup.h
@@ -0,0 +1,12 @@
+#ifndef KVM__SETUP_H
+#define KVM__SETUP_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_setup(int argc, const char **argv, const char *prefix);
+void kvm_setup_help(void) NORETURN;
+int kvm_setup_create_new(const char *guestfs_name);
+void kvm_setup_resolv(const char *guestfs_name);
+int kvm_setup_guest_init(const char *guestfs_name);
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-stat.h b/kvmtool/include/kvm/builtin-stat.h
new file mode 100644
index 0000000..4fecb37
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-stat.h
@@ -0,0 +1,9 @@
+#ifndef KVM__STAT_H
+#define KVM__STAT_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_stat(int argc, const char **argv, const char *prefix);
+void kvm_stat_help(void) NORETURN;
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-stop.h b/kvmtool/include/kvm/builtin-stop.h
new file mode 100644
index 0000000..b26b275
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-stop.h
@@ -0,0 +1,9 @@
+#ifndef KVM__STOP_H
+#define KVM__STOP_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_stop(int argc, const char **argv, const char *prefix);
+void kvm_stop_help(void) NORETURN;
+
+#endif
diff --git a/kvmtool/include/kvm/builtin-version.h b/kvmtool/include/kvm/builtin-version.h
new file mode 100644
index 0000000..83cac4d
--- /dev/null
+++ b/kvmtool/include/kvm/builtin-version.h
@@ -0,0 +1,6 @@
+#ifndef KVM__VERSION_H
+#define KVM__VERSION_H
+
+int kvm_cmd_version(int argc, const char **argv, const char *prefix);
+
+#endif
diff --git a/kvmtool/include/kvm/compiler.h b/kvmtool/include/kvm/compiler.h
new file mode 100644
index 0000000..2013a83
--- /dev/null
+++ b/kvmtool/include/kvm/compiler.h
@@ -0,0 +1,10 @@
+#ifndef KVM_COMPILER_H_
+#define KVM_COMPILER_H_
+
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
+#define notrace __attribute__((no_instrument_function))
+
+#endif /* KVM_COMPILER_H_ */
diff --git a/kvmtool/include/kvm/devices.h b/kvmtool/include/kvm/devices.h
new file mode 100644
index 0000000..e445db6
--- /dev/null
+++ b/kvmtool/include/kvm/devices.h
@@ -0,0 +1,30 @@
+#ifndef KVM__DEVICES_H
+#define KVM__DEVICES_H
+
+#include <linux/rbtree.h>
+#include <linux/types.h>
+#include <linux/compiler.h>
+
+enum device_bus_type {
+ DEVICE_BUS_PCI,
+ DEVICE_BUS_MMIO,
+ DEVICE_BUS_IOPORT,
+ DEVICE_BUS_MAX,
+};
+
+struct device_header {
+ enum device_bus_type bus_type;
+ void *data;
+ int dev_num;
+ struct rb_node node;
+};
+
+int __must_check device__register(struct device_header *dev);
+void device__unregister(struct device_header *dev);
+struct device_header *device__find_dev(enum device_bus_type bus_type,
+ u8 dev_num);
+
+struct device_header *device__first_dev(enum device_bus_type bus_type);
+struct device_header *device__next_dev(struct device_header *dev);
+
+#endif /* KVM__DEVICES_H */
diff --git a/kvmtool/include/kvm/disk-image.h b/kvmtool/include/kvm/disk-image.h
new file mode 100644
index 0000000..27d4f7d
--- /dev/null
+++ b/kvmtool/include/kvm/disk-image.h
@@ -0,0 +1,137 @@
+#ifndef KVM__DISK_IMAGE_H
+#define KVM__DISK_IMAGE_H
+
+#include "kvm/read-write.h"
+#include "kvm/util.h"
+#include "kvm/parse-options.h"
+
+#include <linux/types.h>
+#include <linux/fs.h> /* for BLKGETSIZE64 */
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <sys/uio.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+#ifdef CONFIG_HAS_AIO
+#include <libaio.h>
+#endif
+
+#define SECTOR_SHIFT 9
+#define SECTOR_SIZE (1UL << SECTOR_SHIFT)
+
+enum {
+ DISK_IMAGE_REGULAR,
+ DISK_IMAGE_MMAP,
+};
+
+#define MAX_DISK_IMAGES 4
+
+struct disk_image;
+
+struct disk_image_operations {
+ ssize_t (*read)(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ ssize_t (*write)(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ int (*flush)(struct disk_image *disk);
+ int (*wait)(struct disk_image *disk);
+ int (*close)(struct disk_image *disk);
+ bool async;
+};
+
+struct disk_image_params {
+ const char *filename;
+ /*
+ * wwpn == World Wide Port Number
+ * tpgt == Target Portal Group Tag
+ */
+ const char *wwpn;
+ const char *tpgt;
+ bool readonly;
+ bool direct;
+};
+
+struct disk_image {
+ int fd;
+ u64 size;
+ struct disk_image_operations *ops;
+ void *priv;
+ void *disk_req_cb_param;
+ void (*disk_req_cb)(void *param, long len);
+ bool readonly;
+ bool async;
+#ifdef CONFIG_HAS_AIO
+ io_context_t ctx;
+ int evt;
+ pthread_t thread;
+ u64 aio_inflight;
+#endif /* CONFIG_HAS_AIO */
+ const char *wwpn;
+ const char *tpgt;
+ int debug_iodelay;
+};
+
+int disk_img_name_parser(const struct option *opt, const char *arg, int unset);
+int disk_image__init(struct kvm *kvm);
+int disk_image__exit(struct kvm *kvm);
+struct disk_image *disk_image__new(int fd, u64 size, struct disk_image_operations *ops, int mmap);
+int disk_image__flush(struct disk_image *disk);
+int disk_image__wait(struct disk_image *disk);
+ssize_t disk_image__read(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ssize_t disk_image__write(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ssize_t disk_image__get_serial(struct disk_image *disk, void *buffer, ssize_t *len);
+
+struct disk_image *raw_image__probe(int fd, struct stat *st, bool readonly);
+struct disk_image *blkdev__probe(const char *filename, int flags, struct stat *st);
+
+ssize_t raw_image__read_sync(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+ssize_t raw_image__write_sync(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+ssize_t raw_image__read_mmap(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+ssize_t raw_image__write_mmap(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+int raw_image__close(struct disk_image *disk);
+void disk_image__set_callback(struct disk_image *disk, void (*disk_req_cb)(void *param, long len));
+
+#ifdef CONFIG_HAS_AIO
+int disk_aio_setup(struct disk_image *disk);
+void disk_aio_destroy(struct disk_image *disk);
+ssize_t raw_image__read_async(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+ssize_t raw_image__write_async(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+int raw_image__wait(struct disk_image *disk);
+
+#define raw_image__read raw_image__read_async
+#define raw_image__write raw_image__write_async
+
+#else /* !CONFIG_HAS_AIO */
+static inline int disk_aio_setup(struct disk_image *disk)
+{
+ /* No-op */
+ return 0;
+}
+static inline void disk_aio_destroy(struct disk_image *disk)
+{
+}
+
+static inline int raw_image__wait(struct disk_image *disk)
+{
+ return 0;
+}
+#define raw_image__read raw_image__read_sync
+#define raw_image__write raw_image__write_sync
+#endif /* CONFIG_HAS_AIO */
+
+#endif /* KVM__DISK_IMAGE_H */
diff --git a/kvmtool/include/kvm/fdt.h b/kvmtool/include/kvm/fdt.h
new file mode 100644
index 0000000..4e61572
--- /dev/null
+++ b/kvmtool/include/kvm/fdt.h
@@ -0,0 +1,40 @@
+#ifndef KVM__FDT_H
+#define KVM__FDT_H
+
+#ifdef CONFIG_HAS_LIBFDT
+#include <libfdt.h>
+#endif
+
+#include <linux/types.h>
+
+#include "kvm/fdt-arch.h"
+
+#define FDT_MAX_SIZE 0x10000
+
+/* Those definitions are generic FDT values for specifying IRQ
+ * types and are used in the Linux kernel internally as well as in
+ * the dts files and their documentation.
+ */
+enum irq_type {
+ IRQ_TYPE_NONE = 0x00000000,
+ IRQ_TYPE_EDGE_RISING = 0x00000001,
+ IRQ_TYPE_EDGE_FALLING = 0x00000002,
+ IRQ_TYPE_EDGE_BOTH = (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING),
+ IRQ_TYPE_LEVEL_HIGH = 0x00000004,
+ IRQ_TYPE_LEVEL_LOW = 0x00000008,
+ IRQ_TYPE_LEVEL_MASK = (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH),
+};
+
+extern char *fdt_stdout_path;
+
+/* Helper for the various bits of code that generate FDT nodes */
+#define _FDT(exp) \
+ do { \
+ int ret = (exp); \
+ if (ret < 0) { \
+ die("Error creating device tree: %s: %s\n", \
+ #exp, fdt_strerror(ret)); \
+ } \
+ } while (0)
+
+#endif /* KVM__FDT_H */
diff --git a/kvmtool/include/kvm/framebuffer.h b/kvmtool/include/kvm/framebuffer.h
new file mode 100644
index 0000000..e3200e5
--- /dev/null
+++ b/kvmtool/include/kvm/framebuffer.h
@@ -0,0 +1,36 @@
+#ifndef KVM__FRAMEBUFFER_H
+#define KVM__FRAMEBUFFER_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+struct framebuffer;
+
+struct fb_target_operations {
+ int (*start)(struct framebuffer *fb);
+ int (*stop)(struct framebuffer *fb);
+};
+
+#define FB_MAX_TARGETS 2
+
+struct framebuffer {
+ struct list_head node;
+
+ u32 width;
+ u32 height;
+ u8 depth;
+ char *mem;
+ u64 mem_addr;
+ u64 mem_size;
+ struct kvm *kvm;
+
+ unsigned long nr_targets;
+ struct fb_target_operations *targets[FB_MAX_TARGETS];
+};
+
+struct framebuffer *fb__register(struct framebuffer *fb);
+int fb__attach(struct framebuffer *fb, struct fb_target_operations *ops);
+int fb__init(struct kvm *kvm);
+int fb__exit(struct kvm *kvm);
+
+#endif /* KVM__FRAMEBUFFER_H */
diff --git a/kvmtool/include/kvm/gtk3.h b/kvmtool/include/kvm/gtk3.h
new file mode 100644
index 0000000..b02dc13
--- /dev/null
+++ b/kvmtool/include/kvm/gtk3.h
@@ -0,0 +1,28 @@
+#ifndef KVM__GTK3_H
+#define KVM__GTK3_H
+
+#include "kvm/util.h"
+
+struct framebuffer;
+
+#ifdef CONFIG_HAS_GTK3
+int kvm_gtk_init(struct kvm *kvm);
+int kvm_gtk_exit(struct kvm *kvm);
+#else
+static inline int kvm_gtk_init(struct kvm *kvm)
+{
+ if (kvm->cfg.gtk)
+ die("GTK3 support not compiled in. (install the gtk3-devel or libgtk3.0-dev package)");
+
+ return 0;
+}
+static inline int kvm_gtk_exit(struct kvm *kvm)
+{
+ if (kvm->cfg.gtk)
+ die("GTK3 support not compiled in. (install the gtk3-devel or libgtk3.0-dev package)");
+
+ return 0;
+}
+#endif
+
+#endif /* KVM__GTK3_H */
diff --git a/kvmtool/include/kvm/guest_compat.h b/kvmtool/include/kvm/guest_compat.h
new file mode 100644
index 0000000..ae7abbd
--- /dev/null
+++ b/kvmtool/include/kvm/guest_compat.h
@@ -0,0 +1,9 @@
+#ifndef KVM__GUEST_COMPAT_H
+#define KVM__GUEST_COMPAT_H
+
+int compat__print_all_messages(void);
+int compat__remove_message(int id);
+int compat__add_message(const char *title, const char *description);
+
+
+#endif
\ No newline at end of file
diff --git a/kvmtool/include/kvm/i8042.h b/kvmtool/include/kvm/i8042.h
new file mode 100644
index 0000000..3b4ab68
--- /dev/null
+++ b/kvmtool/include/kvm/i8042.h
@@ -0,0 +1,12 @@
+#ifndef KVM__PCKBD_H
+#define KVM__PCKBD_H
+
+#include <linux/types.h>
+
+struct kvm;
+
+void mouse_queue(u8 c);
+void kbd_queue(u8 c);
+int kbd__init(struct kvm *kvm);
+
+#endif
diff --git a/kvmtool/include/kvm/ioeventfd.h b/kvmtool/include/kvm/ioeventfd.h
new file mode 100644
index 0000000..a1cb841
--- /dev/null
+++ b/kvmtool/include/kvm/ioeventfd.h
@@ -0,0 +1,32 @@
+#ifndef KVM__IOEVENTFD_H
+#define KVM__IOEVENTFD_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <sys/eventfd.h>
+#include "kvm/util.h"
+
+struct kvm;
+
+struct ioevent {
+ u64 io_addr;
+ u8 io_len;
+ void (*fn)(struct kvm *kvm, void *ptr);
+ struct kvm *fn_kvm;
+ void *fn_ptr;
+ int fd;
+ u64 datamatch;
+ u32 flags;
+
+ struct list_head list;
+};
+
+#define IOEVENTFD_FLAG_PIO (1 << 0)
+#define IOEVENTFD_FLAG_USER_POLL (1 << 1)
+
+int ioeventfd__init(struct kvm *kvm);
+int ioeventfd__exit(struct kvm *kvm);
+int ioeventfd__add_event(struct ioevent *ioevent, int flags);
+int ioeventfd__del_event(u64 addr, u64 datamatch);
+
+#endif
diff --git a/kvmtool/include/kvm/ioport.h b/kvmtool/include/kvm/ioport.h
new file mode 100644
index 0000000..039633f
--- /dev/null
+++ b/kvmtool/include/kvm/ioport.h
@@ -0,0 +1,77 @@
+#ifndef KVM__IOPORT_H
+#define KVM__IOPORT_H
+
+#include "kvm/devices.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/rbtree-interval.h"
+#include "kvm/fdt.h"
+
+#include <stdbool.h>
+#include <limits.h>
+#include <asm/types.h>
+#include <linux/types.h>
+#include <linux/byteorder.h>
+
+/* some ports we reserve for own use */
+#define IOPORT_DBG 0xe0
+
+struct kvm;
+
+struct ioport {
+ struct rb_int_node node;
+ struct ioport_operations *ops;
+ void *priv;
+ struct device_header dev_hdr;
+ u32 refcount;
+ bool remove;
+};
+
+struct ioport_operations {
+ bool (*io_in)(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size);
+ bool (*io_out)(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size);
+ void (*generate_fdt_node)(struct ioport *ioport, void *fdt,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq,
+ enum irq_type));
+};
+
+int ioport__setup_arch(struct kvm *kvm);
+void ioport__map_irq(u8 *irq);
+
+int __must_check ioport__register(struct kvm *kvm, u16 port, struct ioport_operations *ops,
+ int count, void *param);
+int ioport__unregister(struct kvm *kvm, u16 port);
+int ioport__init(struct kvm *kvm);
+int ioport__exit(struct kvm *kvm);
+
+static inline u8 ioport__read8(u8 *data)
+{
+ return *data;
+}
+/* On BE platforms, PCI I/O is byteswapped, i.e. LE, so swap back. */
+static inline u16 ioport__read16(u16 *data)
+{
+ return le16_to_cpu(*data);
+}
+
+static inline u32 ioport__read32(u32 *data)
+{
+ return le32_to_cpu(*data);
+}
+
+static inline void ioport__write8(u8 *data, u8 value)
+{
+ *data = value;
+}
+
+static inline void ioport__write16(u16 *data, u16 value)
+{
+ *data = cpu_to_le16(value);
+}
+
+static inline void ioport__write32(u32 *data, u32 value)
+{
+ *data = cpu_to_le32(value);
+}
+
+#endif /* KVM__IOPORT_H */
diff --git a/kvmtool/include/kvm/iovec.h b/kvmtool/include/kvm/iovec.h
new file mode 100644
index 0000000..fe79dd4
--- /dev/null
+++ b/kvmtool/include/kvm/iovec.h
@@ -0,0 +1,21 @@
+#ifndef KVM_UTIL_IOVEC_H_
+#define KVM_UTIL_IOVEC_H_
+
+extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
+extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
+ size_t offset, int len);
+extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len);
+extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
+ size_t offset, int len);
+
+static inline size_t iov_size(const struct iovec *iovec, size_t len)
+{
+ size_t size = 0, i;
+
+ for (i = 0; i < len; i++)
+ size += iovec[i].iov_len;
+
+ return size;
+}
+
+#endif
diff --git a/kvmtool/include/kvm/irq.h b/kvmtool/include/kvm/irq.h
new file mode 100644
index 0000000..2a3f8c9
--- /dev/null
+++ b/kvmtool/include/kvm/irq.h
@@ -0,0 +1,55 @@
+#ifndef KVM__IRQ_H
+#define KVM__IRQ_H
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/kvm.h>
+
+#include "kvm/kvm-arch.h"
+#include "kvm/msi.h"
+
+struct kvm;
+
+struct msi_routing_ops {
+ int (*update_route)(struct kvm *kvm, struct kvm_irq_routing_entry *);
+ bool (*can_signal_msi)(struct kvm *kvm);
+ int (*signal_msi)(struct kvm *kvm, struct kvm_msi *msi);
+ int (*translate_gsi)(struct kvm *kvm, u32 gsi);
+};
+
+extern struct msi_routing_ops *msi_routing_ops;
+extern struct kvm_irq_routing *irq_routing;
+extern int next_gsi;
+
+int irq__alloc_line(void);
+int irq__get_nr_allocated_lines(void);
+
+int irq__init(struct kvm *kvm);
+int irq__exit(struct kvm *kvm);
+
+int irq__allocate_routing_entry(void);
+int irq__add_msix_route(struct kvm *kvm, struct msi_msg *msg, u32 device_id);
+void irq__update_msix_route(struct kvm *kvm, u32 gsi, struct msi_msg *msg);
+
+bool irq__can_signal_msi(struct kvm *kvm);
+int irq__signal_msi(struct kvm *kvm, struct kvm_msi *msi);
+
+/*
+ * The function takes two eventfd arguments, trigger_fd and resample_fd. If
+ * resample_fd is <= 0, resampling is disabled and the IRQ is edge-triggered
+ */
+int irq__common_add_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd,
+ int resample_fd);
+void irq__common_del_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd);
+
+#ifndef irq__add_irqfd
+#define irq__add_irqfd irq__common_add_irqfd
+#endif
+
+#ifndef irq__del_irqfd
+#define irq__del_irqfd irq__common_del_irqfd
+#endif
+
+#endif
diff --git a/kvmtool/include/kvm/kvm-cmd.h b/kvmtool/include/kvm/kvm-cmd.h
new file mode 100644
index 0000000..0a73bce
--- /dev/null
+++ b/kvmtool/include/kvm/kvm-cmd.h
@@ -0,0 +1,17 @@
+#ifndef __KVM_CMD_H__
+#define __KVM_CMD_H__
+
+struct cmd_struct {
+ const char *cmd;
+ int (*fn)(int, const char **, const char *);
+ void (*help)(void);
+ int option;
+};
+
+extern struct cmd_struct kvm_commands[];
+struct cmd_struct *kvm_get_command(struct cmd_struct *command,
+ const char *cmd);
+
+int handle_command(struct cmd_struct *command, int argc, const char **argv);
+
+#endif
diff --git a/kvmtool/include/kvm/kvm-config.h b/kvmtool/include/kvm/kvm-config.h
new file mode 100644
index 0000000..f4a8b83
--- /dev/null
+++ b/kvmtool/include/kvm/kvm-config.h
@@ -0,0 +1,66 @@
+#ifndef KVM_CONFIG_H_
+#define KVM_CONFIG_H_
+
+#include "kvm/disk-image.h"
+#include "kvm/vfio.h"
+#include "kvm/kvm-config-arch.h"
+
+#define DEFAULT_KVM_DEV "/dev/kvm"
+#define DEFAULT_CONSOLE "serial"
+#define DEFAULT_NETWORK "user"
+#define DEFAULT_HOST_ADDR "192.168.33.1"
+#define DEFAULT_GUEST_ADDR "192.168.33.15"
+#define DEFAULT_GUEST_MAC "02:15:15:15:15:15"
+#define DEFAULT_HOST_MAC "02:01:01:01:01:01"
+#define DEFAULT_SCRIPT "none"
+#define DEFAULT_SANDBOX_FILENAME "guest/sandbox.sh"
+
+#define MIN_RAM_SIZE_MB (64ULL)
+#define MIN_RAM_SIZE_BYTE (MIN_RAM_SIZE_MB << MB_SHIFT)
+
+struct kvm_config {
+ struct kvm_config_arch arch;
+ struct disk_image_params disk_image[MAX_DISK_IMAGES];
+ struct vfio_device_params *vfio_devices;
+ u64 ram_size;
+ u8 image_count;
+ u8 num_net_devices;
+ u8 num_vfio_devices;
+ bool virtio_rng;
+ int active_console;
+ int debug_iodelay;
+ int nrcpus;
+ const char *kernel_cmdline;
+ const char *kernel_filename;
+ const char *vmlinux_filename;
+ const char *initrd_filename;
+ const char *firmware_filename;
+ const char *flash_filename;
+ const char *console;
+ const char *dev;
+ const char *network;
+ const char *host_ip;
+ const char *guest_ip;
+ const char *guest_mac;
+ const char *host_mac;
+ const char *script;
+ const char *guest_name;
+ const char *sandbox;
+ const char *hugetlbfs_path;
+ const char *custom_rootfs_name;
+ const char *real_cmdline;
+ struct virtio_net_params *net_params;
+ bool single_step;
+ bool vnc;
+ bool gtk;
+ bool sdl;
+ bool balloon;
+ bool using_rootfs;
+ bool custom_rootfs;
+ bool no_net;
+ bool no_dhcp;
+ bool ioport_debug;
+ bool mmio_debug;
+};
+
+#endif
diff --git a/kvmtool/include/kvm/kvm-cpu.h b/kvmtool/include/kvm/kvm-cpu.h
new file mode 100644
index 0000000..0f16f8d
--- /dev/null
+++ b/kvmtool/include/kvm/kvm-cpu.h
@@ -0,0 +1,32 @@
+#ifndef KVM__KVM_CPU_H
+#define KVM__KVM_CPU_H
+
+#include "kvm/kvm-cpu-arch.h"
+#include <stdbool.h>
+
+struct kvm_cpu_task {
+ void (*func)(struct kvm_cpu *vcpu, void *data);
+ void *data;
+};
+
+int kvm_cpu__init(struct kvm *kvm);
+int kvm_cpu__exit(struct kvm *kvm);
+struct kvm_cpu *kvm_cpu__arch_init(struct kvm *kvm, unsigned long cpu_id);
+void kvm_cpu__delete(struct kvm_cpu *vcpu);
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu);
+void kvm_cpu__setup_cpuid(struct kvm_cpu *vcpu);
+void kvm_cpu__enable_singlestep(struct kvm_cpu *vcpu);
+void kvm_cpu__run(struct kvm_cpu *vcpu);
+int kvm_cpu__start(struct kvm_cpu *cpu);
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu);
+int kvm_cpu__get_endianness(struct kvm_cpu *vcpu);
+
+int kvm_cpu__get_debug_fd(void);
+void kvm_cpu__set_debug_fd(int fd);
+void kvm_cpu__show_code(struct kvm_cpu *vcpu);
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu);
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu);
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu);
+void kvm_cpu__run_on_all_cpus(struct kvm *kvm, struct kvm_cpu_task *task);
+
+#endif /* KVM__KVM_CPU_H */
diff --git a/kvmtool/include/kvm/kvm-ipc.h b/kvmtool/include/kvm/kvm-ipc.h
new file mode 100644
index 0000000..5494da4
--- /dev/null
+++ b/kvmtool/include/kvm/kvm-ipc.h
@@ -0,0 +1,26 @@
+#ifndef KVM__IPC_H_
+#define KVM__IPC_H_
+
+#include <linux/types.h>
+#include "kvm/kvm.h"
+
+enum {
+ KVM_IPC_BALLOON = 1,
+ KVM_IPC_DEBUG = 2,
+ KVM_IPC_STAT = 3,
+ KVM_IPC_PAUSE = 4,
+ KVM_IPC_RESUME = 5,
+ KVM_IPC_STOP = 6,
+ KVM_IPC_PID = 7,
+ KVM_IPC_VMSTATE = 8,
+};
+
+int kvm_ipc__register_handler(u32 type, void (*cb)(struct kvm *kvm,
+ int fd, u32 type, u32 len, u8 *msg));
+int kvm_ipc__init(struct kvm *kvm);
+int kvm_ipc__exit(struct kvm *kvm);
+
+int kvm_ipc__send(int fd, u32 type);
+int kvm_ipc__send_msg(int fd, u32 type, u32 len, u8 *msg);
+
+#endif
diff --git a/kvmtool/include/kvm/kvm.h b/kvmtool/include/kvm/kvm.h
new file mode 100644
index 0000000..53373b0
--- /dev/null
+++ b/kvmtool/include/kvm/kvm.h
@@ -0,0 +1,205 @@
+#ifndef KVM__KVM_H
+#define KVM__KVM_H
+
+#include "kvm/mutex.h"
+#include "kvm/kvm-arch.h"
+#include "kvm/kvm-config.h"
+#include "kvm/util-init.h"
+#include "kvm/kvm.h"
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <time.h>
+#include <signal.h>
+#include <sys/prctl.h>
+#include <limits.h>
+
+#define SIGKVMEXIT (SIGRTMIN + 0)
+#define SIGKVMPAUSE (SIGRTMIN + 1)
+#define SIGKVMTASK (SIGRTMIN + 2)
+
+#define KVM_PID_FILE_PATH "/.lkvm/"
+#define HOME_DIR getenv("HOME")
+#define KVM_BINARY_NAME "lkvm"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE (sysconf(_SC_PAGE_SIZE))
+#endif
+
+#define DEFINE_KVM_EXT(ext) \
+ .name = #ext, \
+ .code = ext
+
+enum {
+ KVM_VMSTATE_RUNNING,
+ KVM_VMSTATE_PAUSED,
+};
+
+enum kvm_mem_type {
+ KVM_MEM_TYPE_RAM = 1 << 0,
+ KVM_MEM_TYPE_DEVICE = 1 << 1,
+ KVM_MEM_TYPE_RESERVED = 1 << 2,
+ KVM_MEM_TYPE_READONLY = 1 << 3,
+
+ KVM_MEM_TYPE_ALL = KVM_MEM_TYPE_RAM
+ | KVM_MEM_TYPE_DEVICE
+ | KVM_MEM_TYPE_RESERVED
+ | KVM_MEM_TYPE_READONLY
+};
+
+struct kvm_ext {
+ const char *name;
+ int code;
+};
+
+struct kvm_mem_bank {
+ struct list_head list;
+ u64 guest_phys_addr;
+ void *host_addr;
+ u64 size;
+ enum kvm_mem_type type;
+ u32 slot;
+};
+
+struct kvm {
+ struct kvm_arch arch;
+ struct kvm_config cfg;
+ int sys_fd; /* For system ioctls(), i.e. /dev/kvm */
+ int vm_fd; /* For VM ioctls() */
+ timer_t timerid; /* Posix timer for interrupts */
+
+ int nrcpus; /* Number of cpus to run */
+ struct kvm_cpu **cpus;
+
+ u32 mem_slots; /* for KVM_SET_USER_MEMORY_REGION */
+ u64 ram_size;
+ void *ram_start;
+ u64 ram_pagesize;
+ struct mutex mem_banks_lock;
+ struct list_head mem_banks;
+
+ bool nmi_disabled;
+ bool msix_needs_devid;
+
+ const char *vmlinux;
+ struct disk_image **disks;
+ int nr_disks;
+
+ int vm_state;
+
+#ifdef KVM_BRLOCK_DEBUG
+ pthread_rwlock_t brlock_sem;
+#endif
+};
+
+void kvm__set_dir(const char *fmt, ...);
+const char *kvm__get_dir(void);
+
+int kvm__init(struct kvm *kvm);
+struct kvm *kvm__new(void);
+int kvm__recommended_cpus(struct kvm *kvm);
+int kvm__max_cpus(struct kvm *kvm);
+void kvm__init_ram(struct kvm *kvm);
+int kvm__exit(struct kvm *kvm);
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename);
+bool kvm__load_kernel(struct kvm *kvm, const char *kernel_filename,
+ const char *initrd_filename, const char *kernel_cmdline);
+int kvm_timer__init(struct kvm *kvm);
+int kvm_timer__exit(struct kvm *kvm);
+void kvm__irq_line(struct kvm *kvm, int irq, int level);
+void kvm__irq_trigger(struct kvm *kvm, int irq);
+bool kvm__emulate_io(struct kvm_cpu *vcpu, u16 port, void *data, int direction, int size, u32 count);
+bool kvm__emulate_mmio(struct kvm_cpu *vcpu, u64 phys_addr, u8 *data, u32 len, u8 is_write);
+int kvm__destroy_mem(struct kvm *kvm, u64 guest_phys, u64 size, void *userspace_addr);
+int kvm__register_mem(struct kvm *kvm, u64 guest_phys, u64 size, void *userspace_addr,
+ enum kvm_mem_type type);
+static inline int kvm__register_ram(struct kvm *kvm, u64 guest_phys, u64 size,
+ void *userspace_addr)
+{
+ return kvm__register_mem(kvm, guest_phys, size, userspace_addr,
+ KVM_MEM_TYPE_RAM);
+}
+
+static inline int kvm__register_dev_mem(struct kvm *kvm, u64 guest_phys,
+ u64 size, void *userspace_addr)
+{
+ return kvm__register_mem(kvm, guest_phys, size, userspace_addr,
+ KVM_MEM_TYPE_DEVICE);
+}
+
+static inline int kvm__reserve_mem(struct kvm *kvm, u64 guest_phys, u64 size)
+{
+ return kvm__register_mem(kvm, guest_phys, size, NULL,
+ KVM_MEM_TYPE_RESERVED);
+}
+
+int __must_check kvm__register_mmio(struct kvm *kvm, u64 phys_addr, u64 phys_addr_len, bool coalesce,
+ void (*mmio_fn)(struct kvm_cpu *vcpu, u64 addr, u8 *data, u32 len, u8 is_write, void *ptr),
+ void *ptr);
+bool kvm__deregister_mmio(struct kvm *kvm, u64 phys_addr);
+void kvm__reboot(struct kvm *kvm);
+void kvm__pause(struct kvm *kvm);
+void kvm__continue(struct kvm *kvm);
+void kvm__notify_paused(void);
+int kvm__get_sock_by_instance(const char *name);
+int kvm__enumerate_instances(int (*callback)(const char *name, int pid));
+void kvm__remove_socket(const char *name);
+
+void kvm__arch_set_cmdline(char *cmdline, bool video);
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size);
+void kvm__arch_delete_ram(struct kvm *kvm);
+int kvm__arch_setup_firmware(struct kvm *kvm);
+int kvm__arch_free_firmware(struct kvm *kvm);
+bool kvm__arch_cpu_supports_vm(void);
+void kvm__arch_read_term(struct kvm *kvm);
+
+void *guest_flat_to_host(struct kvm *kvm, u64 offset);
+u64 host_to_guest_flat(struct kvm *kvm, void *ptr);
+
+bool kvm__arch_load_kernel_image(struct kvm *kvm, int fd_kernel, int fd_initrd,
+ const char *kernel_cmdline);
+
+#define add_read_only(type, str) \
+ (((type) & KVM_MEM_TYPE_READONLY) ? str " (read-only)" : str)
+static inline const char *kvm_mem_type_to_string(enum kvm_mem_type type)
+{
+ switch (type & ~KVM_MEM_TYPE_READONLY) {
+ case KVM_MEM_TYPE_ALL:
+ return "(all)";
+ case KVM_MEM_TYPE_RAM:
+ return add_read_only(type, "RAM");
+ case KVM_MEM_TYPE_DEVICE:
+ return add_read_only(type, "device");
+ case KVM_MEM_TYPE_RESERVED:
+ return add_read_only(type, "reserved");
+ }
+
+ return "???";
+}
+
+int kvm__for_each_mem_bank(struct kvm *kvm, enum kvm_mem_type type,
+ int (*fun)(struct kvm *kvm, struct kvm_mem_bank *bank, void *data),
+ void *data);
+
+/*
+ * Debugging
+ */
+void kvm__dump_mem(struct kvm *kvm, unsigned long addr, unsigned long size, int debug_fd);
+
+extern const char *kvm_exit_reasons[];
+
+static inline bool host_ptr_in_ram(struct kvm *kvm, void *p)
+{
+ return kvm->ram_start <= p && p < (kvm->ram_start + kvm->ram_size);
+}
+
+bool kvm__supports_extension(struct kvm *kvm, unsigned int extension);
+bool kvm__supports_vm_extension(struct kvm *kvm, unsigned int extension);
+
+static inline void kvm__set_thread_name(const char *name)
+{
+ prctl(PR_SET_NAME, name);
+}
+
+#endif /* KVM__KVM_H */
diff --git a/kvmtool/include/kvm/msi.h b/kvmtool/include/kvm/msi.h
new file mode 100644
index 0000000..885eb5b
--- /dev/null
+++ b/kvmtool/include/kvm/msi.h
@@ -0,0 +1,10 @@
+#ifndef LKVM_MSI_H
+#define LKVM_MSI_H
+
+struct msi_msg {
+ u32 address_lo; /* low 32 bits of msi message address */
+ u32 address_hi; /* high 32 bits of msi message address */
+ u32 data; /* 16 bits of msi message data */
+};
+
+#endif /* LKVM_MSI_H */
diff --git a/kvmtool/include/kvm/mutex.h b/kvmtool/include/kvm/mutex.h
new file mode 100644
index 0000000..1f7d0f6
--- /dev/null
+++ b/kvmtool/include/kvm/mutex.h
@@ -0,0 +1,39 @@
+#ifndef KVM__MUTEX_H
+#define KVM__MUTEX_H
+
+#include <pthread.h>
+
+#include "kvm/util.h"
+
+/*
+ * Kernel-alike mutex API - to make it easier for kernel developers
+ * to write user-space code! :-)
+ */
+
+struct mutex {
+ pthread_mutex_t mutex;
+};
+#define MUTEX_INITIALIZER { .mutex = PTHREAD_MUTEX_INITIALIZER }
+
+#define DEFINE_MUTEX(mtx) struct mutex mtx = MUTEX_INITIALIZER
+
+static inline void mutex_init(struct mutex *lock)
+{
+ if (pthread_mutex_init(&lock->mutex, NULL) != 0)
+ die("unexpected pthread_mutex_init() failure!");
+}
+
+static inline void mutex_lock(struct mutex *lock)
+{
+ if (pthread_mutex_lock(&lock->mutex) != 0)
+ die("unexpected pthread_mutex_lock() failure!");
+
+}
+
+static inline void mutex_unlock(struct mutex *lock)
+{
+ if (pthread_mutex_unlock(&lock->mutex) != 0)
+ die("unexpected pthread_mutex_unlock() failure!");
+}
+
+#endif /* KVM__MUTEX_H */
diff --git a/kvmtool/include/kvm/of_pci.h b/kvmtool/include/kvm/of_pci.h
new file mode 100644
index 0000000..c8187ab
--- /dev/null
+++ b/kvmtool/include/kvm/of_pci.h
@@ -0,0 +1,44 @@
+#ifndef KVM__OF_PCI_H
+#define KVM__OF_PCI_H
+
+#include <linux/types.h>
+
+/*
+ * Definitions for implementing parts of the OpenFirmware PCI Bus Binding
+ * Specification (IEEE Std 1275-1994).
+ */
+
+struct of_pci_unit_address {
+ u32 hi, mid, lo;
+} __attribute__((packed));
+
+struct of_pci_irq_mask {
+ struct of_pci_unit_address pci_addr;
+ u32 pci_pin;
+} __attribute__((packed));
+
+struct of_pci_ranges_entry {
+ struct of_pci_unit_address pci_addr;
+ u64 cpu_addr;
+ u64 length;
+} __attribute__((packed));
+
+/* Macros to operate with address in OF binding to PCI */
+#define __b_x(x, p, l) (((x) & ((1<<(l))-1)) << (p))
+#define of_pci_b_n(x) __b_x((x), 31, 1) /* 0 if relocatable */
+#define of_pci_b_p(x) __b_x((x), 30, 1) /* 1 if prefetchable */
+#define of_pci_b_t(x) __b_x((x), 29, 1) /* 1 if the address is aliased */
+#define of_pci_b_ss(x) __b_x((x), 24, 2) /* the space code */
+#define of_pci_b_bbbbbbbb(x) __b_x((x), 16, 8) /* bus number */
+#define of_pci_b_ddddd(x) __b_x((x), 11, 5) /* device number */
+#define of_pci_b_fff(x) __b_x((x), 8, 3) /* function number */
+#define of_pci_b_rrrrrrrr(x) __b_x((x), 0, 8) /* register number */
+
+#define OF_PCI_SS_CONFIG 0
+#define OF_PCI_SS_IO 1
+#define OF_PCI_SS_M32 2
+#define OF_PCI_SS_M64 3
+
+#define OF_PCI_IRQ_MAP_MAX 256 /* 5 bit device + 3 bit pin */
+
+#endif /* KVM__OF_PCI_H */
diff --git a/kvmtool/include/kvm/parse-options.h b/kvmtool/include/kvm/parse-options.h
new file mode 100644
index 0000000..b03f151
--- /dev/null
+++ b/kvmtool/include/kvm/parse-options.h
@@ -0,0 +1,230 @@
+#ifndef __PARSE_OPTIONS_H__
+#define __PARSE_OPTIONS_H__
+
+#include <inttypes.h>
+#include <kvm/util.h>
+
+enum parse_opt_type {
+ /* special types */
+ OPTION_END,
+ OPTION_ARGUMENT,
+ OPTION_GROUP,
+ /* options with no arguments */
+ OPTION_BIT,
+ OPTION_BOOLEAN,
+ OPTION_INCR,
+ OPTION_SET_UINT,
+ OPTION_SET_PTR,
+ /* options with arguments (usually) */
+ OPTION_STRING,
+ OPTION_INTEGER,
+ OPTION_LONG,
+ OPTION_CALLBACK,
+ OPTION_U64,
+ OPTION_UINTEGER,
+};
+
+enum parse_opt_flags {
+ PARSE_OPT_KEEP_DASHDASH = 1,
+ PARSE_OPT_STOP_AT_NON_OPTION = 2,
+ PARSE_OPT_KEEP_ARGV0 = 4,
+ PARSE_OPT_KEEP_UNKNOWN = 8,
+ PARSE_OPT_NO_INTERNAL_HELP = 16,
+};
+
+enum parse_opt_option_flags {
+ PARSE_OPT_OPTARG = 1,
+ PARSE_OPT_NOARG = 2,
+ PARSE_OPT_NONEG = 4,
+ PARSE_OPT_HIDDEN = 8,
+ PARSE_OPT_LASTARG_DEFAULT = 16,
+};
+
+struct option;
+typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
+/*
+ * `type`::
+ * holds the type of the option, you must have an OPTION_END last in your
+ * array.
+ *
+ * `short_name`::
+ * the character to use as a short option name, '\0' if none.
+ *
+ * `long_name`::
+ * the long option name, without the leading dashes, NULL if none.
+ *
+ * `value`::
+ * stores pointers to the values to be filled.
+ *
+ * `argh`::
+ * token to explain the kind of argument this option wants. Keep it
+ * homogenous across the repository.
+ *
+ * `help`::
+ * the short help associated to what the option does.
+ * Must never be NULL (except for OPTION_END).
+ * OPTION_GROUP uses this pointer to store the group header.
+ *
+ * `flags`::
+ * mask of parse_opt_option_flags.
+ * PARSE_OPT_OPTARG: says that the argument is optionnal (not for BOOLEANs)
+ * PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs
+ * PARSE_OPT_NONEG: says that this option cannot be negated
+ * PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in
+ * the long one.
+ *
+ * `callback`::
+ * pointer to the callback to use for OPTION_CALLBACK.
+ *
+ * `defval`::
+ * default value to fill (*->value) with for PARSE_OPT_OPTARG.
+ * OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
+ * the value when met.
+ * CALLBACKS can use it like they want.
+ */
+struct option {
+ enum parse_opt_type type;
+ int short_name;
+ const char *long_name;
+ void *value;
+ const char *argh;
+ const char *help;
+ void *ptr;
+
+ int flags;
+ parse_opt_cb *callback;
+ intptr_t defval;
+};
+
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+#define check_vtype(v, type) \
+ (BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v)
+
+#define OPT_INTEGER(s, l, v, h) \
+{ \
+ .type = OPTION_INTEGER, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, int *), \
+ .help = (h) \
+}
+
+#define OPT_UINTEGER(s, l, v, h) \
+{ \
+ .type = OPTION_UINTEGER, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, unsigned int *), \
+ .help = (h) \
+}
+
+#define OPT_U64(s, l, v, h) \
+{ \
+ .type = OPTION_U64, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, u64 *), \
+ .help = (h) \
+}
+
+#define OPT_STRING(s, l, v, a, h) \
+{ \
+ .type = OPTION_STRING, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, const char **), (a), \
+ .help = (h) \
+}
+
+#define OPT_BOOLEAN(s, l, v, h) \
+{ \
+ .type = OPTION_BOOLEAN, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, bool *), \
+ .help = (h) \
+}
+
+#define OPT_INCR(s, l, v, h) \
+{ \
+ .type = OPTION_INCR, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, int *), \
+ .help = (h) \
+}
+
+#define OPT_GROUP(h) \
+{ \
+ .type = OPTION_GROUP, \
+ .help = (h) \
+}
+
+#define OPT_CALLBACK(s, l, v, a, h, f, p) \
+{ \
+ .type = OPTION_CALLBACK, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = (v), \
+ (a), \
+ .help = (h), \
+ .callback = (f), \
+ .ptr = (p), \
+}
+
+#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f, p) \
+{ \
+ .type = OPTION_CALLBACK, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = (v), \
+ (a), \
+ .help = (h), \
+ .callback = (f), \
+ .flags = PARSE_OPT_NOARG, \
+ .ptr = (p), \
+}
+
+#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d, p) \
+{ \
+ .type = OPTION_CALLBACK, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = (v), (a), \
+ .help = (h), \
+ .callback = (f), \
+ .defval = (intptr_t)d, \
+ .flags = PARSE_OPT_LASTARG_DEFAULT, \
+ .ptr = (p) \
+}
+
+#define OPT_END() { .type = OPTION_END }
+
+#define OPT_ARCH(cmd, cfg) \
+ OPT_ARCH_##cmd(OPT_GROUP("Arch-specific options:"), &(cfg)->arch)
+
+enum {
+ PARSE_OPT_HELP = -1,
+ PARSE_OPT_DONE,
+ PARSE_OPT_UNKNOWN,
+};
+
+/*
+ * It's okay for the caller to consume argv/argc in the usual way.
+ * Other fields of that structure are private to parse-options and should not
+ * be modified in any way.
+ **/
+struct parse_opt_ctx_t {
+ const char **argv;
+ const char **out;
+ int argc, cpidx;
+ const char *opt;
+ int flags;
+};
+
+/* global functions */
+void usage_with_options(const char * const *usagestr,
+ const struct option *opts) NORETURN;
+int parse_options(int argc, const char **argv, const struct option *options,
+ const char * const usagestr[], int flags);
+#endif
diff --git a/kvmtool/include/kvm/pci.h b/kvmtool/include/kvm/pci.h
new file mode 100644
index 0000000..bf81323
--- /dev/null
+++ b/kvmtool/include/kvm/pci.h
@@ -0,0 +1,243 @@
+#ifndef KVM__PCI_H
+#define KVM__PCI_H
+
+#include <linux/types.h>
+#include <linux/kvm.h>
+#include <linux/pci_regs.h>
+#include <endian.h>
+#include <stdbool.h>
+
+#include "kvm/devices.h"
+#include "kvm/msi.h"
+#include "kvm/fdt.h"
+
+#define pci_dev_err(pci_hdr, fmt, ...) \
+ pr_err("[%04x:%04x] " fmt, pci_hdr->vendor_id, pci_hdr->device_id, ##__VA_ARGS__)
+#define pci_dev_warn(pci_hdr, fmt, ...) \
+ pr_warning("[%04x:%04x] " fmt, pci_hdr->vendor_id, pci_hdr->device_id, ##__VA_ARGS__)
+#define pci_dev_info(pci_hdr, fmt, ...) \
+ pr_info("[%04x:%04x] " fmt, pci_hdr->vendor_id, pci_hdr->device_id, ##__VA_ARGS__)
+#define pci_dev_dbg(pci_hdr, fmt, ...) \
+ pr_debug("[%04x:%04x] " fmt, pci_hdr->vendor_id, pci_hdr->device_id, ##__VA_ARGS__)
+#define pci_dev_die(pci_hdr, fmt, ...) \
+ die("[%04x:%04x] " fmt, pci_hdr->vendor_id, pci_hdr->device_id, ##__VA_ARGS__)
+
+/*
+ * PCI Configuration Mechanism #1 I/O ports. See Section 3.7.4.1.
+ * ("Configuration Mechanism #1") of the PCI Local Bus Specification 2.1 for
+ * details.
+ */
+#define PCI_CONFIG_ADDRESS 0xcf8
+#define PCI_CONFIG_DATA 0xcfc
+#define PCI_CONFIG_BUS_FORWARD 0xcfa
+#define PCI_IO_SIZE 0x100
+#define PCI_IOPORT_START 0x6200
+#define PCI_CFG_SIZE (1ULL << 24)
+
+struct kvm;
+
+union pci_config_address {
+ struct {
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ unsigned reg_offset : 2; /* 1 .. 0 */
+ unsigned register_number : 6; /* 7 .. 2 */
+ unsigned function_number : 3; /* 10 .. 8 */
+ unsigned device_number : 5; /* 15 .. 11 */
+ unsigned bus_number : 8; /* 23 .. 16 */
+ unsigned reserved : 7; /* 30 .. 24 */
+ unsigned enable_bit : 1; /* 31 */
+#else
+ unsigned enable_bit : 1; /* 31 */
+ unsigned reserved : 7; /* 30 .. 24 */
+ unsigned bus_number : 8; /* 23 .. 16 */
+ unsigned device_number : 5; /* 15 .. 11 */
+ unsigned function_number : 3; /* 10 .. 8 */
+ unsigned register_number : 6; /* 7 .. 2 */
+ unsigned reg_offset : 2; /* 1 .. 0 */
+#endif
+ };
+ u32 w;
+};
+
+struct msix_table {
+ struct msi_msg msg;
+ u32 ctrl;
+};
+
+struct msix_cap {
+ u8 cap;
+ u8 next;
+ u16 ctrl;
+ u32 table_offset;
+ u32 pba_offset;
+};
+
+struct msi_cap_64 {
+ u8 cap;
+ u8 next;
+ u16 ctrl;
+ u32 address_lo;
+ u32 address_hi;
+ u16 data;
+ u16 _align;
+ u32 mask_bits;
+ u32 pend_bits;
+};
+
+struct msi_cap_32 {
+ u8 cap;
+ u8 next;
+ u16 ctrl;
+ u32 address_lo;
+ u16 data;
+ u16 _align;
+ u32 mask_bits;
+ u32 pend_bits;
+};
+
+struct pci_cap_hdr {
+ u8 type;
+ u8 next;
+};
+
+struct pci_device_header;
+
+typedef int (*bar_activate_fn_t)(struct kvm *kvm,
+ struct pci_device_header *pci_hdr,
+ int bar_num, void *data);
+typedef int (*bar_deactivate_fn_t)(struct kvm *kvm,
+ struct pci_device_header *pci_hdr,
+ int bar_num, void *data);
+
+#define PCI_BAR_OFFSET(b) (offsetof(struct pci_device_header, bar[b]))
+#define PCI_DEV_CFG_SIZE 256
+#define PCI_DEV_CFG_MASK (PCI_DEV_CFG_SIZE - 1)
+
+struct pci_config_operations {
+ void (*write)(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ u8 offset, void *data, int sz);
+ void (*read)(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ u8 offset, void *data, int sz);
+};
+
+struct pci_device_header {
+ /* Configuration space, as seen by the guest */
+ union {
+ struct {
+ u16 vendor_id;
+ u16 device_id;
+ u16 command;
+ u16 status;
+ u8 revision_id;
+ u8 class[3];
+ u8 cacheline_size;
+ u8 latency_timer;
+ u8 header_type;
+ u8 bist;
+ u32 bar[6];
+ u32 card_bus;
+ u16 subsys_vendor_id;
+ u16 subsys_id;
+ u32 exp_rom_bar;
+ u8 capabilities;
+ u8 reserved1[3];
+ u32 reserved2;
+ u8 irq_line;
+ u8 irq_pin;
+ u8 min_gnt;
+ u8 max_lat;
+ struct msix_cap msix;
+ } __attribute__((packed));
+ /* Pad to PCI config space size */
+ u8 __pad[PCI_DEV_CFG_SIZE];
+ };
+
+ /* Private to lkvm */
+ u32 bar_size[6];
+ bool bar_active[6];
+ bar_activate_fn_t bar_activate_fn;
+ bar_deactivate_fn_t bar_deactivate_fn;
+ void *data;
+ struct pci_config_operations cfg_ops;
+ /*
+ * PCI INTx# are level-triggered, but virtual device often feature
+ * edge-triggered INTx# for convenience.
+ */
+ enum irq_type irq_type;
+};
+
+#define PCI_CAP(pci_hdr, pos) ((void *)(pci_hdr) + (pos))
+
+#define pci_for_each_cap(pos, cap, hdr) \
+ for ((pos) = (hdr)->capabilities & ~3; \
+ (cap) = PCI_CAP(hdr, pos), (pos) != 0; \
+ (pos) = ((struct pci_cap_hdr *)(cap))->next & ~3)
+
+int pci__init(struct kvm *kvm);
+int pci__exit(struct kvm *kvm);
+struct pci_device_header *pci__find_dev(u8 dev_num);
+u32 pci_get_mmio_block(u32 size);
+u16 pci_get_io_port_block(u32 size);
+int pci__assign_irq(struct pci_device_header *pci_hdr);
+void pci__config_wr(struct kvm *kvm, union pci_config_address addr, void *data, int size);
+void pci__config_rd(struct kvm *kvm, union pci_config_address addr, void *data, int size);
+
+void *pci_find_cap(struct pci_device_header *hdr, u8 cap_type);
+
+int pci__register_bar_regions(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ bar_activate_fn_t bar_activate_fn,
+ bar_deactivate_fn_t bar_deactivate_fn, void *data);
+
+static inline bool __pci__memory_space_enabled(u16 command)
+{
+ return command & PCI_COMMAND_MEMORY;
+}
+
+static inline bool pci__memory_space_enabled(struct pci_device_header *pci_hdr)
+{
+ return __pci__memory_space_enabled(pci_hdr->command);
+}
+
+static inline bool __pci__io_space_enabled(u16 command)
+{
+ return command & PCI_COMMAND_IO;
+}
+
+static inline bool pci__io_space_enabled(struct pci_device_header *pci_hdr)
+{
+ return __pci__io_space_enabled(pci_hdr->command);
+}
+
+static inline bool __pci__bar_is_io(u32 bar)
+{
+ return bar & PCI_BASE_ADDRESS_SPACE_IO;
+}
+
+static inline bool pci__bar_is_io(struct pci_device_header *pci_hdr, int bar_num)
+{
+ return __pci__bar_is_io(pci_hdr->bar[bar_num]);
+}
+
+static inline bool pci__bar_is_memory(struct pci_device_header *pci_hdr, int bar_num)
+{
+ return !pci__bar_is_io(pci_hdr, bar_num);
+}
+
+static inline u32 __pci__bar_address(u32 bar)
+{
+ if (__pci__bar_is_io(bar))
+ return bar & PCI_BASE_ADDRESS_IO_MASK;
+ return bar & PCI_BASE_ADDRESS_MEM_MASK;
+}
+
+static inline u32 pci__bar_address(struct pci_device_header *pci_hdr, int bar_num)
+{
+ return __pci__bar_address(pci_hdr->bar[bar_num]);
+}
+
+static inline u32 pci__bar_size(struct pci_device_header *pci_hdr, int bar_num)
+{
+ return pci_hdr->bar_size[bar_num];
+}
+
+#endif /* KVM__PCI_H */
diff --git a/kvmtool/include/kvm/qcow.h b/kvmtool/include/kvm/qcow.h
new file mode 100644
index 0000000..f849246
--- /dev/null
+++ b/kvmtool/include/kvm/qcow.h
@@ -0,0 +1,133 @@
+#ifndef KVM__QCOW_H
+#define KVM__QCOW_H
+
+#include "kvm/mutex.h"
+
+#include <linux/types.h>
+#include <stdbool.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+
+#define QCOW_MAGIC (('Q' << 24) | ('F' << 16) | ('I' << 8) | 0xfb)
+
+#define QCOW1_VERSION 1
+#define QCOW2_VERSION 2
+
+#define QCOW1_OFLAG_COMPRESSED (1ULL << 63)
+
+#define QCOW2_OFLAG_COPIED (1ULL << 63)
+#define QCOW2_OFLAG_COMPRESSED (1ULL << 62)
+
+#define QCOW2_OFLAGS_MASK (QCOW2_OFLAG_COPIED|QCOW2_OFLAG_COMPRESSED)
+
+#define QCOW2_OFFSET_MASK (~QCOW2_OFLAGS_MASK)
+
+#define MAX_CACHE_NODES 32
+
+struct qcow_l2_table {
+ u64 offset;
+ struct rb_node node;
+ struct list_head list;
+ u8 dirty;
+ u64 table[];
+};
+
+struct qcow_l1_table {
+ u32 table_size;
+ u64 *l1_table;
+
+ /* Level2 caching data structures */
+ struct rb_root root;
+ struct list_head lru_list;
+ int nr_cached;
+};
+
+#define QCOW_REFCOUNT_BLOCK_SHIFT 1
+
+struct qcow_refcount_block {
+ u64 offset;
+ struct rb_node node;
+ struct list_head list;
+ u64 size;
+ u8 dirty;
+ u16 entries[];
+};
+
+struct qcow_refcount_table {
+ u32 rf_size;
+ u64 *rf_table;
+
+ /* Refcount block caching data structures */
+ struct rb_root root;
+ struct list_head lru_list;
+ int nr_cached;
+};
+
+struct qcow_header {
+ u64 size; /* in bytes */
+ u64 l1_table_offset;
+ u32 l1_size;
+ u8 cluster_bits;
+ u8 l2_bits;
+ u64 refcount_table_offset;
+ u32 refcount_table_size;
+};
+
+struct qcow {
+ struct mutex mutex;
+ struct qcow_header *header;
+ struct qcow_l1_table table;
+ struct qcow_refcount_table refcount_table;
+ int fd;
+ int csize_shift;
+ int csize_mask;
+ u32 version;
+ u64 cluster_size;
+ u64 cluster_offset_mask;
+ u64 free_clust_idx;
+ void *cluster_cache;
+ void *cluster_data;
+ void *copy_buff;
+};
+
+struct qcow1_header_disk {
+ u32 magic;
+ u32 version;
+
+ u64 backing_file_offset;
+ u32 backing_file_size;
+ u32 mtime;
+
+ u64 size; /* in bytes */
+
+ u8 cluster_bits;
+ u8 l2_bits;
+ u32 crypt_method;
+
+ u64 l1_table_offset;
+};
+
+struct qcow2_header_disk {
+ u32 magic;
+ u32 version;
+
+ u64 backing_file_offset;
+ u32 backing_file_size;
+
+ u32 cluster_bits;
+ u64 size; /* in bytes */
+ u32 crypt_method;
+
+ u32 l1_size;
+ u64 l1_table_offset;
+
+ u64 refcount_table_offset;
+ u32 refcount_table_clusters;
+
+ u32 nb_snapshots;
+ u64 snapshots_offset;
+};
+
+struct disk_image *qcow_probe(int fd, bool readonly);
+
+#endif /* KVM__QCOW_H */
diff --git a/kvmtool/include/kvm/rbtree-interval.h b/kvmtool/include/kvm/rbtree-interval.h
new file mode 100644
index 0000000..17cd3b5
--- /dev/null
+++ b/kvmtool/include/kvm/rbtree-interval.h
@@ -0,0 +1,32 @@
+#ifndef KVM__INTERVAL_RBTREE_H
+#define KVM__INTERVAL_RBTREE_H
+
+#include <linux/rbtree.h>
+#include <linux/types.h>
+
+#define RB_INT_INIT(l, h) \
+ (struct rb_int_node){.low = l, .high = h}
+#define rb_int(n) rb_entry(n, struct rb_int_node, node)
+#define rb_int_start(n) ((n)->low)
+#define rb_int_end(n) ((n)->low + (n)->high - 1)
+
+struct rb_int_node {
+ struct rb_node node;
+ u64 low;
+ u64 high;
+};
+
+/* Return the rb_int_node interval in which 'point' is located. */
+struct rb_int_node *rb_int_search_single(struct rb_root *root, u64 point);
+
+/* Return the rb_int_node in which start:len is located. */
+struct rb_int_node *rb_int_search_range(struct rb_root *root, u64 low, u64 high);
+
+int rb_int_insert(struct rb_root *root, struct rb_int_node *data);
+
+static inline void rb_int_erase(struct rb_root *root, struct rb_int_node *node)
+{
+ rb_erase(&node->node, root);
+}
+
+#endif
diff --git a/kvmtool/include/kvm/read-write.h b/kvmtool/include/kvm/read-write.h
new file mode 100644
index 0000000..8375d7c
--- /dev/null
+++ b/kvmtool/include/kvm/read-write.h
@@ -0,0 +1,34 @@
+#ifndef KVM_READ_WRITE_H
+#define KVM_READ_WRITE_H
+
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+
+ssize_t xread(int fd, void *buf, size_t count);
+ssize_t xwrite(int fd, const void *buf, size_t count);
+
+ssize_t read_file(int fd, char *buf, size_t max_size);
+
+ssize_t read_in_full(int fd, void *buf, size_t count);
+ssize_t write_in_full(int fd, const void *buf, size_t count);
+
+ssize_t xpread(int fd, void *buf, size_t count, off_t offset);
+ssize_t xpwrite(int fd, const void *buf, size_t count, off_t offset);
+
+ssize_t pread_in_full(int fd, void *buf, size_t count, off_t offset);
+ssize_t pwrite_in_full(int fd, const void *buf, size_t count, off_t offset);
+
+ssize_t xreadv(int fd, const struct iovec *iov, int iovcnt);
+ssize_t xwritev(int fd, const struct iovec *iov, int iovcnt);
+
+ssize_t readv_in_full(int fd, const struct iovec *iov, int iovcnt);
+ssize_t writev_in_full(int fd, const struct iovec *iov, int iovcnt);
+
+ssize_t xpreadv(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+ssize_t xpwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+
+ssize_t preadv_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+ssize_t pwritev_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+
+#endif /* KVM_READ_WRITE_H */
diff --git a/kvmtool/include/kvm/rtc.h b/kvmtool/include/kvm/rtc.h
new file mode 100644
index 0000000..6aa9299
--- /dev/null
+++ b/kvmtool/include/kvm/rtc.h
@@ -0,0 +1,9 @@
+#ifndef KVM__RTC_H
+#define KVM__RTC_H
+
+struct kvm;
+
+int rtc__init(struct kvm *kvm);
+int rtc__exit(struct kvm *kvm);
+
+#endif /* KVM__RTC_H */
diff --git a/kvmtool/include/kvm/rwsem.h b/kvmtool/include/kvm/rwsem.h
new file mode 100644
index 0000000..75a22f8
--- /dev/null
+++ b/kvmtool/include/kvm/rwsem.h
@@ -0,0 +1,39 @@
+#ifndef KVM__RWSEM_H
+#define KVM__RWSEM_H
+
+#include <pthread.h>
+
+#include "kvm/util.h"
+
+/*
+ * Kernel-alike rwsem API - to make it easier for kernel developers
+ * to write user-space code! :-)
+ */
+
+#define DECLARE_RWSEM(sem) pthread_rwlock_t sem = PTHREAD_RWLOCK_INITIALIZER
+
+static inline void down_read(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_rdlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_rdlock() failure!");
+}
+
+static inline void down_write(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_wrlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_wrlock() failure!");
+}
+
+static inline void up_read(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_unlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_unlock() failure!");
+}
+
+static inline void up_write(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_unlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_unlock() failure!");
+}
+
+#endif /* KVM__RWSEM_H */
diff --git a/kvmtool/include/kvm/sdl.h b/kvmtool/include/kvm/sdl.h
new file mode 100644
index 0000000..2f0c213
--- /dev/null
+++ b/kvmtool/include/kvm/sdl.h
@@ -0,0 +1,28 @@
+#ifndef KVM__SDL_H
+#define KVM__SDL_H
+
+#include "kvm/util.h"
+
+struct framebuffer;
+
+#ifdef CONFIG_HAS_SDL
+int sdl__init(struct kvm *kvm);
+int sdl__exit(struct kvm *kvm);
+#else
+static inline int sdl__init(struct kvm *kvm)
+{
+ if (kvm->cfg.sdl)
+ die("SDL support not compiled in. (install the SDL-dev[el] package)");
+
+ return 0;
+}
+static inline int sdl__exit(struct kvm *kvm)
+{
+ if (kvm->cfg.sdl)
+ die("SDL support not compiled in. (install the SDL-dev[el] package)");
+
+ return 0;
+}
+#endif
+
+#endif /* KVM__SDL_H */
diff --git a/kvmtool/include/kvm/strbuf.h b/kvmtool/include/kvm/strbuf.h
new file mode 100644
index 0000000..7657339
--- /dev/null
+++ b/kvmtool/include/kvm/strbuf.h
@@ -0,0 +1,22 @@
+#ifndef __STRBUF_H__
+#define __STRBUF_H__
+
+#include <sys/types.h>
+#include <string.h>
+
+int prefixcmp(const char *str, const char *prefix);
+
+#ifndef HAVE_STRLCPY
+extern size_t strlcat(char *dest, const char *src, size_t count);
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
+
+/* some inline functions */
+
+static inline const char *skip_prefix(const char *str, const char *prefix)
+{
+ size_t len = strlen(prefix);
+ return strncmp(str, prefix, len) ? NULL : str + len;
+}
+
+#endif
diff --git a/kvmtool/include/kvm/symbol.h b/kvmtool/include/kvm/symbol.h
new file mode 100644
index 0000000..725bbaf
--- /dev/null
+++ b/kvmtool/include/kvm/symbol.h
@@ -0,0 +1,30 @@
+#ifndef KVM__SYMBOL_H
+#define KVM__SYMBOL_H
+
+#include <stddef.h>
+#include <string.h>
+
+struct kvm;
+
+#define SYMBOL_DEFAULT_UNKNOWN "<unknown>"
+
+#ifdef CONFIG_HAS_BFD
+
+int symbol_init(struct kvm *kvm);
+int symbol_exit(struct kvm *kvm);
+char *symbol_lookup(struct kvm *kvm, unsigned long addr, char *sym, size_t size);
+
+#else
+
+static inline int symbol_init(struct kvm *kvm) { return 0; }
+static inline char *symbol_lookup(struct kvm *kvm, unsigned long addr, char *sym, size_t size)
+{
+ char *s = strncpy(sym, SYMBOL_DEFAULT_UNKNOWN, size);
+ sym[size - 1] = '\0';
+ return s;
+}
+static inline int symbol_exit(struct kvm *kvm) { return 0; }
+
+#endif
+
+#endif /* KVM__SYMBOL_H */
diff --git a/kvmtool/include/kvm/term.h b/kvmtool/include/kvm/term.h
new file mode 100644
index 0000000..b9793f0
--- /dev/null
+++ b/kvmtool/include/kvm/term.h
@@ -0,0 +1,23 @@
+#ifndef KVM__TERM_H
+#define KVM__TERM_H
+
+#include "kvm/kvm.h"
+
+#include <sys/uio.h>
+#include <stdbool.h>
+
+#define CONSOLE_8250 1
+#define CONSOLE_VIRTIO 2
+#define CONSOLE_HV 3
+
+#define TERM_MAX_DEVS 4
+
+int term_putc_iov(struct iovec *iov, int iovcnt, int term);
+int term_getc_iov(struct kvm *kvm, struct iovec *iov, int iovcnt, int term);
+int term_putc(char *addr, int cnt, int term);
+int term_getc(struct kvm *kvm, int term);
+
+bool term_readable(int term);
+int tty_parser(const struct option *opt, const char *arg, int unset);
+
+#endif /* KVM__TERM_H */
diff --git a/kvmtool/include/kvm/threadpool.h b/kvmtool/include/kvm/threadpool.h
new file mode 100644
index 0000000..880487a
--- /dev/null
+++ b/kvmtool/include/kvm/threadpool.h
@@ -0,0 +1,40 @@
+#ifndef KVM__THREADPOOL_H
+#define KVM__THREADPOOL_H
+
+#include "kvm/mutex.h"
+
+#include <linux/list.h>
+
+struct kvm;
+
+typedef void (*kvm_thread_callback_fn_t)(struct kvm *kvm, void *data);
+
+struct thread_pool__job {
+ kvm_thread_callback_fn_t callback;
+ struct kvm *kvm;
+ void *data;
+
+ int signalcount;
+ struct mutex mutex;
+
+ struct list_head queue;
+};
+
+static inline void thread_pool__init_job(struct thread_pool__job *job, struct kvm *kvm, kvm_thread_callback_fn_t callback, void *data)
+{
+ *job = (struct thread_pool__job) {
+ .kvm = kvm,
+ .callback = callback,
+ .data = data,
+ .mutex = MUTEX_INITIALIZER,
+ };
+ INIT_LIST_HEAD(&job->queue);
+}
+
+int thread_pool__init(struct kvm *kvm);
+int thread_pool__exit(struct kvm *kvm);
+
+void thread_pool__do_job(struct thread_pool__job *job);
+void thread_pool__cancel_job(struct thread_pool__job *job);
+
+#endif
diff --git a/kvmtool/include/kvm/uip.h b/kvmtool/include/kvm/uip.h
new file mode 100644
index 0000000..efa508a
--- /dev/null
+++ b/kvmtool/include/kvm/uip.h
@@ -0,0 +1,368 @@
+#ifndef KVM__UIP_H
+#define KVM__UIP_H
+
+#include "linux/types.h"
+#include "kvm/mutex.h"
+
+#include <netinet/in.h>
+#include <sys/uio.h>
+
+#define UIP_BUF_STATUS_FREE 0
+#define UIP_BUF_STATUS_INUSE 1
+#define UIP_BUF_STATUS_USED 2
+
+#define UIP_ETH_P_IP 0X0800
+#define UIP_ETH_P_ARP 0X0806
+
+#define UIP_IP_VER_4 0X40
+#define UIP_IP_HDR_LEN 0X05
+#define UIP_IP_TTL 0X40
+#define UIP_IP_P_UDP 0X11
+#define UIP_IP_P_TCP 0X06
+#define UIP_IP_P_ICMP 0X01
+
+#define UIP_TCP_HDR_LEN 0x50
+#define UIP_TCP_WIN_SIZE 14600
+#define UIP_TCP_FLAG_FIN 1
+#define UIP_TCP_FLAG_SYN 2
+#define UIP_TCP_FLAG_RST 4
+#define UIP_TCP_FLAG_PSH 8
+#define UIP_TCP_FLAG_ACK 16
+#define UIP_TCP_FLAG_URG 32
+
+#define UIP_BOOTP_VENDOR_SPECIFIC_LEN 64
+#define UIP_BOOTP_MAX_PAYLOAD_LEN 300
+#define UIP_DHCP_VENDOR_SPECIFIC_LEN 312
+#define UIP_DHCP_PORT_SERVER 67
+#define UIP_DHCP_PORT_CLIENT 68
+#define UIP_DHCP_MACPAD_LEN 10
+#define UIP_DHCP_HOSTNAME_LEN 64
+#define UIP_DHCP_FILENAME_LEN 128
+#define UIP_DHCP_MAGIC_COOKIE 0x63825363
+#define UIP_DHCP_MAGIC_COOKIE_LEN 4
+#define UIP_DHCP_LEASE_TIME 0x00003840
+#define UIP_DHCP_MAX_PAYLOAD_LEN (UIP_BOOTP_MAX_PAYLOAD_LEN - UIP_BOOTP_VENDOR_SPECIFIC_LEN + UIP_DHCP_VENDOR_SPECIFIC_LEN)
+#define UIP_DHCP_OPTION_LEN (UIP_DHCP_VENDOR_SPECIFIC_LEN - UIP_DHCP_MAGIC_COOKIE_LEN)
+#define UIP_DHCP_DISCOVER 1
+#define UIP_DHCP_OFFER 2
+#define UIP_DHCP_REQUEST 3
+#define UIP_DHCP_ACK 5
+#define UIP_DHCP_MAX_DNS_SERVER_NR 3
+#define UIP_DHCP_MAX_DOMAIN_NAME_LEN 256
+#define UIP_DHCP_TAG_MSG_TYPE 53
+#define UIP_DHCP_TAG_MSG_TYPE_LEN 1
+#define UIP_DHCP_TAG_SERVER_ID 54
+#define UIP_DHCP_TAG_SERVER_ID_LEN 4
+#define UIP_DHCP_TAG_LEASE_TIME 51
+#define UIP_DHCP_TAG_LEASE_TIME_LEN 4
+#define UIP_DHCP_TAG_SUBMASK 1
+#define UIP_DHCP_TAG_SUBMASK_LEN 4
+#define UIP_DHCP_TAG_ROUTER 3
+#define UIP_DHCP_TAG_ROUTER_LEN 4
+#define UIP_DHCP_TAG_ROOT 17
+#define UIP_DHCP_TAG_ROOT_LEN 4
+#define UIP_DHCP_TAG_DNS_SERVER 6
+#define UIP_DHCP_TAG_DNS_SERVER_LEN 4
+#define UIP_DHCP_TAG_DOMAIN_NAME 15
+#define UIP_DHCP_TAG_END 255
+
+/*
+ * IP package maxium len == 64 KBytes
+ * IP header == 20 Bytes
+ * TCP header == 20 Bytes
+ * UDP header == 8 Bytes
+ */
+#define UIP_MAX_TCP_PAYLOAD (64*1024 - 20 - 20 - 1)
+#define UIP_MAX_UDP_PAYLOAD (64*1024 - 20 - 8 - 1)
+
+struct uip_eth_addr {
+ u8 addr[6];
+};
+
+struct uip_eth {
+ struct uip_eth_addr dst;
+ struct uip_eth_addr src;
+ u16 type;
+} __attribute__((packed));
+
+struct uip_arp {
+ struct uip_eth eth;
+ u16 hwtype;
+ u16 proto;
+ u8 hwlen;
+ u8 protolen;
+ u16 op;
+ struct uip_eth_addr smac;
+ u32 sip;
+ struct uip_eth_addr dmac;
+ u32 dip;
+} __attribute__((packed));
+
+struct uip_ip {
+ struct uip_eth eth;
+ u8 vhl;
+ u8 tos;
+ /*
+ * len = IP hdr + IP payload
+ */
+ u16 len;
+ u16 id;
+ u16 flgfrag;
+ u8 ttl;
+ u8 proto;
+ u16 csum;
+ u32 sip;
+ u32 dip;
+} __attribute__((packed));
+
+struct uip_icmp {
+ struct uip_ip ip;
+ u8 type;
+ u8 code;
+ u16 csum;
+ u16 id;
+ u16 seq;
+} __attribute__((packed));
+
+struct uip_udp {
+ /*
+ * FIXME: IP Options (IP hdr len > 20 bytes) are not supported
+ */
+ struct uip_ip ip;
+ u16 sport;
+ u16 dport;
+ /*
+ * len = UDP hdr + UDP payload
+ */
+ u16 len;
+ u16 csum;
+ u8 payload[0];
+} __attribute__((packed));
+
+struct uip_tcp {
+ /*
+ * FIXME: IP Options (IP hdr len > 20 bytes) are not supported
+ */
+ struct uip_ip ip;
+ u16 sport;
+ u16 dport;
+ u32 seq;
+ u32 ack;
+ u8 off;
+ u8 flg;
+ u16 win;
+ u16 csum;
+ u16 urgent;
+} __attribute__((packed));
+
+struct uip_pseudo_hdr {
+ u32 sip;
+ u32 dip;
+ u8 zero;
+ u8 proto;
+ u16 len;
+} __attribute__((packed));
+
+struct uip_dhcp {
+ struct uip_udp udp;
+ u8 msg_type;
+ u8 hardware_type;
+ u8 hardware_len;
+ u8 hops;
+ u32 id;
+ u16 time;
+ u16 flg;
+ u32 client_ip;
+ u32 your_ip;
+ u32 server_ip;
+ u32 agent_ip;
+ struct uip_eth_addr client_mac;
+ u8 pad[UIP_DHCP_MACPAD_LEN];
+ u8 server_hostname[UIP_DHCP_HOSTNAME_LEN];
+ u8 boot_filename[UIP_DHCP_FILENAME_LEN];
+ u32 magic_cookie;
+ u8 option[UIP_DHCP_OPTION_LEN];
+} __attribute__((packed));
+
+struct uip_info {
+ struct list_head udp_socket_head;
+ struct list_head tcp_socket_head;
+ struct mutex udp_socket_lock;
+ struct mutex tcp_socket_lock;
+ struct uip_eth_addr guest_mac;
+ struct uip_eth_addr host_mac;
+ pthread_cond_t buf_free_cond;
+ pthread_cond_t buf_used_cond;
+ struct list_head buf_head;
+ struct mutex buf_lock;
+ pthread_t udp_thread;
+ u8 *udp_buf;
+ int udp_epollfd;
+ int buf_free_nr;
+ int buf_used_nr;
+ u32 guest_ip;
+ u32 guest_netmask;
+ u32 host_ip;
+ u32 dns_ip[UIP_DHCP_MAX_DNS_SERVER_NR];
+ char *domain_name;
+ u32 buf_nr;
+ u32 vnet_hdr_len;
+};
+
+struct uip_buf {
+ struct list_head list;
+ struct uip_info *info;
+ int vnet_len;
+ int eth_len;
+ int status;
+ unsigned char *vnet;
+ unsigned char *eth;
+ int id;
+};
+
+struct uip_udp_socket {
+ struct sockaddr_in addr;
+ struct list_head list;
+ struct mutex *lock;
+ u32 dport, sport;
+ u32 dip, sip;
+ int fd;
+};
+
+struct uip_tcp_socket {
+ struct sockaddr_in addr;
+ struct list_head list;
+ struct uip_info *info;
+ pthread_cond_t cond;
+ struct mutex *lock;
+ pthread_t thread;
+ u32 dport, sport;
+ u32 guest_acked;
+ u16 window_size;
+ /*
+ * Initial Sequence Number
+ */
+ u32 isn_server;
+ u32 isn_guest;
+ u32 ack_server;
+ u32 seq_server;
+ int write_done;
+ int read_done;
+ u32 dip, sip;
+ u8 *payload;
+ u8 *buf;
+ int fd;
+};
+
+struct uip_tx_arg {
+ void *vnet;
+ struct uip_info *info;
+ struct uip_eth *eth;
+ int vnet_len;
+ int eth_len;
+};
+
+static inline u16 uip_ip_hdrlen(struct uip_ip *ip)
+{
+ return (ip->vhl & 0x0f) * 4;
+}
+
+static inline u16 uip_ip_len(struct uip_ip *ip)
+{
+ return htons(ip->len);
+}
+
+static inline u16 uip_udp_hdrlen(struct uip_udp *udp)
+{
+ return 8;
+}
+
+static inline u16 uip_udp_len(struct uip_udp *udp)
+{
+ return ntohs(udp->len);
+}
+
+static inline u16 uip_tcp_hdrlen(struct uip_tcp *tcp)
+{
+ return (tcp->off >> 4) * 4;
+}
+
+static inline u16 uip_tcp_len(struct uip_tcp *tcp)
+{
+ struct uip_ip *ip;
+
+ ip = &tcp->ip;
+
+ return uip_ip_len(ip) - uip_ip_hdrlen(ip);
+}
+
+static inline u16 uip_tcp_payloadlen(struct uip_tcp *tcp)
+{
+ return uip_tcp_len(tcp) - uip_tcp_hdrlen(tcp);
+}
+
+static inline u8 *uip_tcp_payload(struct uip_tcp *tcp)
+{
+ return (u8 *)&tcp->sport + uip_tcp_hdrlen(tcp);
+}
+
+static inline bool uip_tcp_is_syn(struct uip_tcp *tcp)
+{
+ return (tcp->flg & UIP_TCP_FLAG_SYN) != 0;
+}
+
+static inline bool uip_tcp_is_fin(struct uip_tcp *tcp)
+{
+ return (tcp->flg & UIP_TCP_FLAG_FIN) != 0;
+}
+
+static inline u32 uip_tcp_isn(struct uip_tcp *tcp)
+{
+ return ntohl(tcp->seq);
+}
+
+static inline u32 uip_tcp_isn_alloc(void)
+{
+ /*
+ * FIXME: should increase every 4ms
+ */
+ return 10000000;
+}
+
+static inline u16 uip_eth_hdrlen(struct uip_eth *eth)
+{
+ return sizeof(*eth);
+}
+
+int uip_tx(struct iovec *iov, u16 out, struct uip_info *info);
+int uip_rx(struct iovec *iov, u16 in, struct uip_info *info);
+void uip_static_init(struct uip_info *info);
+int uip_init(struct uip_info *info);
+void uip_exit(struct uip_info *info);
+void uip_tcp_exit(struct uip_info *info);
+void uip_udp_exit(struct uip_info *info);
+
+int uip_tx_do_ipv4_udp_dhcp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4_icmp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4_tcp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4_udp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4(struct uip_tx_arg *arg);
+int uip_tx_do_arp(struct uip_tx_arg *arg);
+
+u16 uip_csum_icmp(struct uip_icmp *icmp);
+u16 uip_csum_udp(struct uip_udp *udp);
+u16 uip_csum_tcp(struct uip_tcp *tcp);
+u16 uip_csum_ip(struct uip_ip *ip);
+
+struct uip_buf *uip_buf_set_used(struct uip_info *info, struct uip_buf *buf);
+struct uip_buf *uip_buf_set_free(struct uip_info *info, struct uip_buf *buf);
+struct uip_buf *uip_buf_get_used(struct uip_info *info);
+struct uip_buf *uip_buf_get_free(struct uip_info *info);
+struct uip_buf *uip_buf_clone(struct uip_tx_arg *arg);
+
+int uip_udp_make_pkg(struct uip_info *info, struct uip_udp_socket *sk, struct uip_buf *buf, u8 *payload, int payload_len);
+bool uip_udp_is_dhcp(struct uip_udp *udp);
+
+int uip_dhcp_get_dns(struct uip_info *info);
+void uip_dhcp_exit(struct uip_info *info);
+#endif /* KVM__UIP_H */
diff --git a/kvmtool/include/kvm/util-init.h b/kvmtool/include/kvm/util-init.h
new file mode 100644
index 0000000..13d4f04
--- /dev/null
+++ b/kvmtool/include/kvm/util-init.h
@@ -0,0 +1,51 @@
+#ifndef KVM__UTIL_INIT_H
+#define KVM__UTIL_INIT_H
+
+struct kvm;
+
+struct init_item {
+ struct hlist_node n;
+ const char *fn_name;
+ int (*init)(struct kvm *);
+};
+
+int init_list__init(struct kvm *kvm);
+int init_list__exit(struct kvm *kvm);
+
+int init_list_add(struct init_item *t, int (*init)(struct kvm *),
+ int priority, const char *name);
+int exit_list_add(struct init_item *t, int (*init)(struct kvm *),
+ int priority, const char *name);
+
+#define __init_list_add(cb, l) \
+static void __attribute__ ((constructor)) __init__##cb(void) \
+{ \
+ static char name[] = #cb; \
+ static struct init_item t; \
+ init_list_add(&t, cb, l, name); \
+}
+
+#define __exit_list_add(cb, l) \
+static void __attribute__ ((constructor)) __init__##cb(void) \
+{ \
+ static char name[] = #cb; \
+ static struct init_item t; \
+ exit_list_add(&t, cb, l, name); \
+}
+
+#define core_init(cb) __init_list_add(cb, 0)
+#define base_init(cb) __init_list_add(cb, 2)
+#define dev_base_init(cb) __init_list_add(cb, 4)
+#define dev_init(cb) __init_list_add(cb, 5)
+#define virtio_dev_init(cb) __init_list_add(cb, 6)
+#define firmware_init(cb) __init_list_add(cb, 7)
+#define late_init(cb) __init_list_add(cb, 9)
+
+#define core_exit(cb) __exit_list_add(cb, 0)
+#define base_exit(cb) __exit_list_add(cb, 2)
+#define dev_base_exit(cb) __exit_list_add(cb, 4)
+#define dev_exit(cb) __exit_list_add(cb, 5)
+#define virtio_dev_exit(cb) __exit_list_add(cb, 6)
+#define firmware_exit(cb) __exit_list_add(cb, 7)
+#define late_exit(cb) __exit_list_add(cb, 9)
+#endif
diff --git a/kvmtool/include/kvm/util.h b/kvmtool/include/kvm/util.h
new file mode 100644
index 0000000..d76568a
--- /dev/null
+++ b/kvmtool/include/kvm/util.h
@@ -0,0 +1,136 @@
+#include <linux/stringify.h>
+
+#ifndef KVM__UTIL_H
+#define KVM__UTIL_H
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+/*
+ * Some bits are stolen from perf tool :)
+ */
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <errno.h>
+#include <limits.h>
+#include <sys/param.h>
+#include <sys/types.h>
+#include <linux/types.h>
+
+#ifdef __GNUC__
+#define NORETURN __attribute__((__noreturn__))
+#else
+#define NORETURN
+#ifndef __attribute__
+#define __attribute__(x)
+#endif
+#endif
+
+extern bool do_debug_print;
+
+#define PROT_RW (PROT_READ|PROT_WRITE)
+#define MAP_ANON_NORESERVE (MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE)
+
+extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
+extern void die_perror(const char *s) NORETURN;
+extern int pr_err(const char *err, ...) __attribute__((format (printf, 1, 2)));
+extern void pr_warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
+extern void pr_info(const char *err, ...) __attribute__((format (printf, 1, 2)));
+extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
+
+#define pr_debug(fmt, ...) \
+ do { \
+ if (do_debug_print) \
+ pr_info("(%s) %s:%d: " fmt, __FILE__, \
+ __func__, __LINE__, ##__VA_ARGS__); \
+ } while (0)
+
+
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+
+#ifndef BUG_ON_HANDLER
+# define BUG_ON_HANDLER(condition) \
+ do { \
+ if ((condition)) { \
+ pr_err("BUG at %s:%d", __FILE__, __LINE__); \
+ raise(SIGABRT); \
+ } \
+ } while (0)
+#endif
+
+#define BUG_ON(condition) BUG_ON_HANDLER((condition))
+
+#define DIE_IF(cnd) \
+do { \
+ if (cnd) \
+ die(" at (" __FILE__ ":" __stringify(__LINE__) "): " \
+ __stringify(cnd) "\n"); \
+} while (0)
+
+#define WARN_ON(condition) ({ \
+ int __ret_warn_on = !!(condition); \
+ if (__ret_warn_on) \
+ pr_warning("(%s) %s:%d: failed condition: %s", \
+ __FILE__, __func__, __LINE__, \
+ __stringify(condition)); \
+ __ret_warn_on; \
+})
+
+#define MSECS_TO_USECS(s) ((s) * 1000)
+
+/* Millisecond sleep */
+static inline void msleep(unsigned int msecs)
+{
+ usleep(MSECS_TO_USECS(msecs));
+}
+
+/*
+ * Find last (most significant) bit set. Same implementation as Linux:
+ * fls(0) = 0, fls(1) = 1, fls(1UL << 63) = 64
+ */
+static inline int fls_long(unsigned long x)
+{
+ return x ? sizeof(x) * 8 - __builtin_clzl(x) : 0;
+}
+
+static inline unsigned long roundup_pow_of_two(unsigned long x)
+{
+ return x ? 1UL << fls_long(x - 1) : 0;
+}
+
+#define is_power_of_two(x) ((x) > 0 ? ((x) & ((x) - 1)) == 0 : 0)
+
+/**
+ * pow2_size: return the number of bits needed to store values
+ * @x: number of distinct values to store (or number of bytes)
+ *
+ * Determines the number of bits needed to store @x different values.
+ * Could be used to determine the number of address bits needed to
+ * store @x bytes.
+ *
+ * Example:
+ * pow2_size(255) => 8
+ * pow2_size(256) => 8
+ * pow2_size(257) => 9
+ *
+ * Return: number of bits
+ */
+static inline int pow2_size(unsigned long x)
+{
+ if (x <= 1)
+ return x;
+
+ return sizeof(x) * 8 - __builtin_clzl(x - 1);
+}
+
+struct kvm;
+void *mmap_hugetlbfs(struct kvm *kvm, const char *htlbfs_path, u64 size);
+void *mmap_anon_or_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 size);
+
+#endif /* KVM__UTIL_H */
diff --git a/kvmtool/include/kvm/vesa.h b/kvmtool/include/kvm/vesa.h
new file mode 100644
index 0000000..e7d9713
--- /dev/null
+++ b/kvmtool/include/kvm/vesa.h
@@ -0,0 +1,20 @@
+#ifndef KVM__VESA_H
+#define KVM__VESA_H
+
+#define VESA_WIDTH 640
+#define VESA_HEIGHT 480
+
+#define VESA_MEM_ADDR 0xd0000000
+#define VESA_BPP 32
+/*
+ * We actually only need VESA_BPP/8*VESA_WIDTH*VESA_HEIGHT bytes. But the memory
+ * size must be a power of 2, so we round up.
+ */
+#define VESA_MEM_SIZE (1 << 21)
+
+struct kvm;
+struct biosregs;
+
+struct framebuffer *vesa__init(struct kvm *self);
+
+#endif
diff --git a/kvmtool/include/kvm/vfio.h b/kvmtool/include/kvm/vfio.h
new file mode 100644
index 0000000..28223cf
--- /dev/null
+++ b/kvmtool/include/kvm/vfio.h
@@ -0,0 +1,128 @@
+#ifndef KVM__VFIO_H
+#define KVM__VFIO_H
+
+#include "kvm/mutex.h"
+#include "kvm/parse-options.h"
+#include "kvm/pci.h"
+
+#include <linux/vfio.h>
+
+#define vfio_dev_err(vdev, fmt, ...) \
+ pr_err("%s: " fmt, (vdev)->params->name, ##__VA_ARGS__)
+#define vfio_dev_warn(vdev, fmt, ...) \
+ pr_warning("%s: " fmt, (vdev)->params->name, ##__VA_ARGS__)
+#define vfio_dev_info(vdev, fmt, ...) \
+ pr_info("%s: " fmt, (vdev)->params->name, ##__VA_ARGS__)
+#define vfio_dev_dbg(vdev, fmt, ...) \
+ pr_debug("%s: " fmt, (vdev)->params->name, ##__VA_ARGS__)
+#define vfio_dev_die(vdev, fmt, ...) \
+ die("%s: " fmt, (vdev)->params->name, ##__VA_ARGS__)
+
+/* Currently limited by num_vfio_devices */
+#define MAX_VFIO_DEVICES 256
+
+enum vfio_device_type {
+ VFIO_DEVICE_PCI,
+};
+
+/* MSI/MSI-X capability enabled */
+#define VFIO_PCI_MSI_STATE_ENABLED (1 << 0)
+/* MSI/MSI-X capability or individual vector masked */
+#define VFIO_PCI_MSI_STATE_MASKED (1 << 1)
+/* MSI-X capability has no vector enabled yet */
+#define VFIO_PCI_MSI_STATE_EMPTY (1 << 2)
+
+struct vfio_pci_msi_entry {
+ struct msix_table config;
+ int gsi;
+ int eventfd;
+ u8 phys_state;
+ u8 virt_state;
+};
+
+struct vfio_pci_msix_table {
+ size_t size;
+ unsigned int bar;
+ u32 guest_phys_addr;
+};
+
+struct vfio_pci_msix_pba {
+ size_t size;
+ off_t offset; /* in VFIO device fd */
+ unsigned int bar;
+ u32 guest_phys_addr;
+};
+
+/* Common data for MSI and MSI-X */
+struct vfio_pci_msi_common {
+ off_t pos;
+ u8 virt_state;
+ u8 phys_state;
+ struct mutex mutex;
+ struct vfio_irq_info info;
+ struct vfio_irq_set *irq_set;
+ size_t nr_entries;
+ struct vfio_pci_msi_entry *entries;
+};
+
+#define VFIO_PCI_IRQ_MODE_INTX (1 << 0)
+#define VFIO_PCI_IRQ_MODE_MSI (1 << 1)
+#define VFIO_PCI_IRQ_MODE_MSIX (1 << 2)
+
+struct vfio_pci_device {
+ struct pci_device_header hdr;
+
+ unsigned long irq_modes;
+ int intx_fd;
+ int unmask_fd;
+ unsigned int intx_gsi;
+ struct vfio_pci_msi_common msi;
+ struct vfio_pci_msi_common msix;
+ struct vfio_pci_msix_table msix_table;
+ struct vfio_pci_msix_pba msix_pba;
+};
+
+struct vfio_region {
+ struct vfio_region_info info;
+ struct vfio_device *vdev;
+ u64 guest_phys_addr;
+ void *host_addr;
+ u32 port_base;
+ int is_ioport :1;
+};
+
+struct vfio_device {
+ struct device_header dev_hdr;
+ struct vfio_device_params *params;
+ struct vfio_group *group;
+
+ int fd;
+ struct vfio_device_info info;
+ struct vfio_region *regions;
+
+ char *sysfs_path;
+
+ struct vfio_pci_device pci;
+};
+
+struct vfio_device_params {
+ char *name;
+ const char *bus;
+ enum vfio_device_type type;
+};
+
+struct vfio_group {
+ unsigned long id; /* iommu_group number in sysfs */
+ int fd;
+ int refs;
+ struct list_head list;
+};
+
+int vfio_device_parser(const struct option *opt, const char *arg, int unset);
+int vfio_map_region(struct kvm *kvm, struct vfio_device *vdev,
+ struct vfio_region *region);
+void vfio_unmap_region(struct kvm *kvm, struct vfio_region *region);
+int vfio_pci_setup_device(struct kvm *kvm, struct vfio_device *device);
+void vfio_pci_teardown_device(struct kvm *kvm, struct vfio_device *vdev);
+
+#endif /* KVM__VFIO_H */
diff --git a/kvmtool/include/kvm/virtio-9p.h b/kvmtool/include/kvm/virtio-9p.h
new file mode 100644
index 0000000..3ea7698
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-9p.h
@@ -0,0 +1,75 @@
+#ifndef KVM__VIRTIO_9P_H
+#define KVM__VIRTIO_9P_H
+#include "kvm/virtio.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+#include "kvm/parse-options.h"
+
+#include <dirent.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+#define NUM_VIRT_QUEUES 1
+#define VIRTQUEUE_NUM 128
+#define VIRTIO_9P_DEFAULT_TAG "kvm_9p"
+#define VIRTIO_9P_HDR_LEN (sizeof(u32)+sizeof(u8)+sizeof(u16))
+#define VIRTIO_9P_VERSION_DOTL "9P2000.L"
+#define MAX_TAG_LEN 32
+
+struct p9_msg {
+ u32 size;
+ u8 cmd;
+ u16 tag;
+ u8 msg[0];
+} __attribute__((packed));
+
+struct p9_fid {
+ u32 fid;
+ u32 uid;
+ char abs_path[PATH_MAX];
+ char *path;
+ DIR *dir;
+ int fd;
+ struct rb_node node;
+};
+
+struct p9_dev_job {
+ struct virt_queue *vq;
+ struct p9_dev *p9dev;
+ struct thread_pool__job job_id;
+};
+
+struct p9_dev {
+ struct list_head list;
+ struct virtio_device vdev;
+ struct rb_root fids;
+
+ struct virtio_9p_config *config;
+ u32 features;
+
+ /* virtio queue */
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct p9_dev_job jobs[NUM_VIRT_QUEUES];
+ char root_dir[PATH_MAX];
+};
+
+struct p9_pdu {
+ u32 queue_head;
+ size_t read_offset;
+ size_t write_offset;
+ u16 out_iov_cnt;
+ u16 in_iov_cnt;
+ struct iovec in_iov[VIRTQUEUE_NUM];
+ struct iovec out_iov[VIRTQUEUE_NUM];
+};
+
+struct kvm;
+
+int virtio_9p_rootdir_parser(const struct option *opt, const char *arg, int unset);
+int virtio_9p_img_name_parser(const struct option *opt, const char *arg, int unset);
+int virtio_9p__register(struct kvm *kvm, const char *root, const char *tag_name);
+int virtio_9p__init(struct kvm *kvm);
+int virtio_p9_pdu_readf(struct p9_pdu *pdu, const char *fmt, ...);
+int virtio_p9_pdu_writef(struct p9_pdu *pdu, const char *fmt, ...);
+
+#endif
diff --git a/kvmtool/include/kvm/virtio-balloon.h b/kvmtool/include/kvm/virtio-balloon.h
new file mode 100644
index 0000000..844a1ba
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-balloon.h
@@ -0,0 +1,9 @@
+#ifndef KVM__BLN_VIRTIO_H
+#define KVM__BLN_VIRTIO_H
+
+struct kvm;
+
+int virtio_bln__init(struct kvm *kvm);
+int virtio_bln__exit(struct kvm *kvm);
+
+#endif /* KVM__BLN_VIRTIO_H */
diff --git a/kvmtool/include/kvm/virtio-blk.h b/kvmtool/include/kvm/virtio-blk.h
new file mode 100644
index 0000000..12e59b6
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-blk.h
@@ -0,0 +1,12 @@
+#ifndef KVM__BLK_VIRTIO_H
+#define KVM__BLK_VIRTIO_H
+
+#include "kvm/disk-image.h"
+
+struct kvm;
+
+int virtio_blk__init(struct kvm *kvm);
+int virtio_blk__exit(struct kvm *kvm);
+void virtio_blk_complete(void *param, long len);
+
+#endif /* KVM__BLK_VIRTIO_H */
diff --git a/kvmtool/include/kvm/virtio-console.h b/kvmtool/include/kvm/virtio-console.h
new file mode 100644
index 0000000..8980920
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-console.h
@@ -0,0 +1,10 @@
+#ifndef KVM__CONSOLE_VIRTIO_H
+#define KVM__CONSOLE_VIRTIO_H
+
+struct kvm;
+
+int virtio_console__init(struct kvm *kvm);
+void virtio_console__inject_interrupt(struct kvm *kvm);
+int virtio_console__exit(struct kvm *kvm);
+
+#endif /* KVM__CONSOLE_VIRTIO_H */
diff --git a/kvmtool/include/kvm/virtio-mmio.h b/kvmtool/include/kvm/virtio-mmio.h
new file mode 100644
index 0000000..6bc50bd
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-mmio.h
@@ -0,0 +1,60 @@
+#ifndef KVM__VIRTIO_MMIO_H
+#define KVM__VIRTIO_MMIO_H
+
+#include <linux/types.h>
+#include <linux/virtio_mmio.h>
+
+#define VIRTIO_MMIO_MAX_VQ 32
+#define VIRTIO_MMIO_MAX_CONFIG 1
+#define VIRTIO_MMIO_IO_SIZE 0x200
+
+struct kvm;
+
+struct virtio_mmio_ioevent_param {
+ struct virtio_device *vdev;
+ u32 vq;
+};
+
+struct virtio_mmio_hdr {
+ char magic[4];
+ u32 version;
+ u32 device_id;
+ u32 vendor_id;
+ u32 host_features;
+ u32 host_features_sel;
+ u32 reserved_1[2];
+ u32 guest_features;
+ u32 guest_features_sel;
+ u32 guest_page_size;
+ u32 reserved_2;
+ u32 queue_sel;
+ u32 queue_num_max;
+ u32 queue_num;
+ u32 queue_align;
+ u32 queue_pfn;
+ u32 reserved_3[3];
+ u32 queue_notify;
+ u32 reserved_4[3];
+ u32 interrupt_state;
+ u32 interrupt_ack;
+ u32 reserved_5[2];
+ u32 status;
+} __attribute__((packed));
+
+struct virtio_mmio {
+ u32 addr;
+ void *dev;
+ struct kvm *kvm;
+ u8 irq;
+ struct virtio_mmio_hdr hdr;
+ struct device_header dev_hdr;
+ struct virtio_mmio_ioevent_param ioeventfds[VIRTIO_MMIO_MAX_VQ];
+};
+
+int virtio_mmio_signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq);
+int virtio_mmio_signal_config(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_mmio_exit(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_mmio_reset(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_mmio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class);
+#endif
diff --git a/kvmtool/include/kvm/virtio-net.h b/kvmtool/include/kvm/virtio-net.h
new file mode 100644
index 0000000..d136a09
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-net.h
@@ -0,0 +1,33 @@
+#ifndef KVM__VIRTIO_NET_H
+#define KVM__VIRTIO_NET_H
+
+#include "kvm/parse-options.h"
+
+struct kvm;
+
+struct virtio_net_params {
+ const char *guest_ip;
+ const char *host_ip;
+ const char *script;
+ const char *downscript;
+ const char *trans;
+ const char *tapif;
+ char guest_mac[6];
+ char host_mac[6];
+ struct kvm *kvm;
+ int mode;
+ int vhost;
+ int fd;
+ int mq;
+};
+
+int virtio_net__init(struct kvm *kvm);
+int virtio_net__exit(struct kvm *kvm);
+int netdev_parser(const struct option *opt, const char *arg, int unset);
+
+enum {
+ NET_MODE_USER,
+ NET_MODE_TAP
+};
+
+#endif /* KVM__VIRTIO_NET_H */
diff --git a/kvmtool/include/kvm/virtio-pci-dev.h b/kvmtool/include/kvm/virtio-pci-dev.h
new file mode 100644
index 0000000..48ae018
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-pci-dev.h
@@ -0,0 +1,38 @@
+#ifndef VIRTIO_PCI_DEV_H_
+#define VIRTIO_PCI_DEV_H_
+
+#include <linux/virtio_ids.h>
+
+/*
+ * Virtio PCI device constants and resources
+ * they do use (such as irqs and pins).
+ */
+
+#define PCI_DEVICE_ID_VIRTIO_NET 0x1000
+#define PCI_DEVICE_ID_VIRTIO_BLK 0x1001
+#define PCI_DEVICE_ID_VIRTIO_CONSOLE 0x1003
+#define PCI_DEVICE_ID_VIRTIO_RNG 0x1004
+#define PCI_DEVICE_ID_VIRTIO_BLN 0x1005
+#define PCI_DEVICE_ID_VIRTIO_SCSI 0x1008
+#define PCI_DEVICE_ID_VIRTIO_9P 0x1009
+#define PCI_DEVICE_ID_VESA 0x2000
+#define PCI_DEVICE_ID_PCI_SHMEM 0x0001
+
+#define PCI_VENDOR_ID_REDHAT_QUMRANET 0x1af4
+#define PCI_VENDOR_ID_PCI_SHMEM 0x0001
+#define PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET 0x1af4
+
+#define PCI_SUBSYSTEM_ID_VESA 0x0004
+#define PCI_SUBSYSTEM_ID_PCI_SHMEM 0x0001
+
+#define PCI_CLASS_BLK 0x018000
+#define PCI_CLASS_NET 0x020000
+#define PCI_CLASS_CONSOLE 0x078000
+/*
+ * 0xFF Device does not fit in any defined classes
+ */
+#define PCI_CLASS_RNG 0xff0000
+#define PCI_CLASS_BLN 0xff0000
+#define PCI_CLASS_9P 0xff0000
+
+#endif /* VIRTIO_PCI_DEV_H_ */
diff --git a/kvmtool/include/kvm/virtio-pci.h b/kvmtool/include/kvm/virtio-pci.h
new file mode 100644
index 0000000..959b4b8
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-pci.h
@@ -0,0 +1,59 @@
+#ifndef KVM__VIRTIO_PCI_H
+#define KVM__VIRTIO_PCI_H
+
+#include "kvm/devices.h"
+#include "kvm/pci.h"
+
+#include <linux/types.h>
+
+#define VIRTIO_PCI_MAX_VQ 32
+#define VIRTIO_PCI_MAX_CONFIG 1
+
+struct kvm;
+
+struct virtio_pci_ioevent_param {
+ struct virtio_device *vdev;
+ u32 vq;
+};
+
+#define VIRTIO_PCI_F_SIGNAL_MSI (1 << 0)
+
+struct virtio_pci {
+ struct pci_device_header pci_hdr;
+ struct device_header dev_hdr;
+ void *dev;
+ struct kvm *kvm;
+
+ u8 status;
+ u8 isr;
+ u32 features;
+
+ /*
+ * We cannot rely on the INTERRUPT_LINE byte in the config space once
+ * we have run guest code, as the OS is allowed to use that field
+ * as a scratch pad to communicate between driver and PCI layer.
+ * So store our legacy interrupt line number in here for internal use.
+ */
+ u8 legacy_irq_line;
+
+ /* MSI-X */
+ u16 config_vector;
+ u32 config_gsi;
+ u32 vq_vector[VIRTIO_PCI_MAX_VQ];
+ u32 gsis[VIRTIO_PCI_MAX_VQ];
+ u64 msix_pba;
+ struct msix_table msix_table[VIRTIO_PCI_MAX_VQ + VIRTIO_PCI_MAX_CONFIG];
+
+ /* virtio queue */
+ u16 queue_selector;
+ struct virtio_pci_ioevent_param ioeventfds[VIRTIO_PCI_MAX_VQ];
+};
+
+int virtio_pci__signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq);
+int virtio_pci__signal_config(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_pci__exit(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_pci__reset(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_pci__init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class);
+
+#endif
diff --git a/kvmtool/include/kvm/virtio-rng.h b/kvmtool/include/kvm/virtio-rng.h
new file mode 100644
index 0000000..b585b37
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-rng.h
@@ -0,0 +1,9 @@
+#ifndef KVM__RNG_VIRTIO_H
+#define KVM__RNG_VIRTIO_H
+
+struct kvm;
+
+int virtio_rng__init(struct kvm *kvm);
+int virtio_rng__exit(struct kvm *kvm);
+
+#endif /* KVM__RNG_VIRTIO_H */
diff --git a/kvmtool/include/kvm/virtio-scsi.h b/kvmtool/include/kvm/virtio-scsi.h
new file mode 100644
index 0000000..d64aa7e
--- /dev/null
+++ b/kvmtool/include/kvm/virtio-scsi.h
@@ -0,0 +1,11 @@
+#ifndef KVM__SCSI_VIRTIO_H
+#define KVM__SCSI_VIRTIO_H
+
+#include "kvm/disk-image.h"
+
+struct kvm;
+
+int virtio_scsi_init(struct kvm *kvm);
+int virtio_scsi_exit(struct kvm *kvm);
+
+#endif /* KVM__SCSI_VIRTIO_H */
diff --git a/kvmtool/include/kvm/virtio.h b/kvmtool/include/kvm/virtio.h
new file mode 100644
index 0000000..3a311f5
--- /dev/null
+++ b/kvmtool/include/kvm/virtio.h
@@ -0,0 +1,234 @@
+#ifndef KVM__VIRTIO_H
+#define KVM__VIRTIO_H
+
+#include <endian.h>
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/virtio_config.h>
+#include <sys/uio.h>
+
+#include "kvm/barrier.h"
+#include "kvm/kvm.h"
+
+#define VIRTIO_IRQ_LOW 0
+#define VIRTIO_IRQ_HIGH 1
+
+#define VIRTIO_PCI_O_CONFIG 0
+#define VIRTIO_PCI_O_MSIX 1
+
+#define VIRTIO_ENDIAN_LE (1 << 0)
+#define VIRTIO_ENDIAN_BE (1 << 1)
+
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define VIRTIO_ENDIAN_HOST VIRTIO_ENDIAN_LE
+#else
+#define VIRTIO_ENDIAN_HOST VIRTIO_ENDIAN_BE
+#endif
+
+/* Reserved status bits */
+#define VIRTIO_CONFIG_S_MASK \
+ (VIRTIO_CONFIG_S_ACKNOWLEDGE | \
+ VIRTIO_CONFIG_S_DRIVER | \
+ VIRTIO_CONFIG_S_DRIVER_OK | \
+ VIRTIO_CONFIG_S_FEATURES_OK | \
+ VIRTIO_CONFIG_S_FAILED)
+
+/* Kvmtool status bits */
+/* Start the device */
+#define VIRTIO__STATUS_START (1 << 8)
+/* Stop the device */
+#define VIRTIO__STATUS_STOP (1 << 9)
+
+struct virt_queue {
+ struct vring vring;
+ u32 pfn;
+ /* The last_avail_idx field is an index to ->ring of struct vring_avail.
+ It's where we assume the next request index is at. */
+ u16 last_avail_idx;
+ u16 last_used_signalled;
+ u16 endian;
+ bool use_event_idx;
+ bool enabled;
+};
+
+/*
+ * The default policy is not to cope with the guest endianness.
+ * It also helps not breaking archs that do not care about supporting
+ * such a configuration.
+ */
+#ifndef VIRTIO_RING_ENDIAN
+#define VIRTIO_RING_ENDIAN VIRTIO_ENDIAN_HOST
+#endif
+
+#if VIRTIO_RING_ENDIAN != VIRTIO_ENDIAN_HOST
+
+static inline __u16 __virtio_g2h_u16(u16 endian, __u16 val)
+{
+ return (endian == VIRTIO_ENDIAN_LE) ? le16toh(val) : be16toh(val);
+}
+
+static inline __u16 __virtio_h2g_u16(u16 endian, __u16 val)
+{
+ return (endian == VIRTIO_ENDIAN_LE) ? htole16(val) : htobe16(val);
+}
+
+static inline __u32 __virtio_g2h_u32(u16 endian, __u32 val)
+{
+ return (endian == VIRTIO_ENDIAN_LE) ? le32toh(val) : be32toh(val);
+}
+
+static inline __u32 __virtio_h2g_u32(u16 endian, __u32 val)
+{
+ return (endian == VIRTIO_ENDIAN_LE) ? htole32(val) : htobe32(val);
+}
+
+static inline __u64 __virtio_g2h_u64(u16 endian, __u64 val)
+{
+ return (endian == VIRTIO_ENDIAN_LE) ? le64toh(val) : be64toh(val);
+}
+
+static inline __u64 __virtio_h2g_u64(u16 endian, __u64 val)
+{
+ return (endian == VIRTIO_ENDIAN_LE) ? htole64(val) : htobe64(val);
+}
+
+#define virtio_guest_to_host_u16(x, v) __virtio_g2h_u16((x)->endian, (v))
+#define virtio_host_to_guest_u16(x, v) __virtio_h2g_u16((x)->endian, (v))
+#define virtio_guest_to_host_u32(x, v) __virtio_g2h_u32((x)->endian, (v))
+#define virtio_host_to_guest_u32(x, v) __virtio_h2g_u32((x)->endian, (v))
+#define virtio_guest_to_host_u64(x, v) __virtio_g2h_u64((x)->endian, (v))
+#define virtio_host_to_guest_u64(x, v) __virtio_h2g_u64((x)->endian, (v))
+
+#else
+
+#define virtio_guest_to_host_u16(x, v) (v)
+#define virtio_host_to_guest_u16(x, v) (v)
+#define virtio_guest_to_host_u32(x, v) (v)
+#define virtio_host_to_guest_u32(x, v) (v)
+#define virtio_guest_to_host_u64(x, v) (v)
+#define virtio_host_to_guest_u64(x, v) (v)
+
+#endif
+
+static inline u16 virt_queue__pop(struct virt_queue *queue)
+{
+ __u16 guest_idx;
+
+ /*
+ * The guest updates the avail index after writing the ring entry.
+ * Ensure that we read the updated entry once virt_queue__available()
+ * observes the new index.
+ */
+ rmb();
+
+ guest_idx = queue->vring.avail->ring[queue->last_avail_idx++ % queue->vring.num];
+ return virtio_guest_to_host_u16(queue, guest_idx);
+}
+
+static inline struct vring_desc *virt_queue__get_desc(struct virt_queue *queue, u16 desc_ndx)
+{
+ return &queue->vring.desc[desc_ndx];
+}
+
+static inline bool virt_queue__available(struct virt_queue *vq)
+{
+ u16 last_avail_idx = virtio_host_to_guest_u16(vq, vq->last_avail_idx);
+
+ if (!vq->vring.avail)
+ return 0;
+
+ if (vq->use_event_idx) {
+ vring_avail_event(&vq->vring) = last_avail_idx;
+ /*
+ * After the driver writes a new avail index, it reads the event
+ * index to see if we need any notification. Ensure that it
+ * reads the updated index, or else we'll miss the notification.
+ */
+ mb();
+ }
+
+ return vq->vring.avail->idx != last_avail_idx;
+}
+
+void virt_queue__used_idx_advance(struct virt_queue *queue, u16 jump);
+struct vring_used_elem * virt_queue__set_used_elem_no_update(struct virt_queue *queue, u32 head, u32 len, u16 offset);
+struct vring_used_elem *virt_queue__set_used_elem(struct virt_queue *queue, u32 head, u32 len);
+
+bool virtio_queue__should_signal(struct virt_queue *vq);
+u16 virt_queue__get_iov(struct virt_queue *vq, struct iovec iov[],
+ u16 *out, u16 *in, struct kvm *kvm);
+u16 virt_queue__get_head_iov(struct virt_queue *vq, struct iovec iov[],
+ u16 *out, u16 *in, u16 head, struct kvm *kvm);
+u16 virt_queue__get_inout_iov(struct kvm *kvm, struct virt_queue *queue,
+ struct iovec in_iov[], struct iovec out_iov[],
+ u16 *in, u16 *out);
+int virtio__get_dev_specific_field(int offset, bool msix, u32 *config_off);
+
+enum virtio_trans {
+ VIRTIO_PCI,
+ VIRTIO_MMIO,
+};
+
+struct virtio_device {
+ bool use_vhost;
+ void *virtio;
+ struct virtio_ops *ops;
+ u16 endian;
+ u32 features;
+ u32 status;
+};
+
+struct virtio_ops {
+ u8 *(*get_config)(struct kvm *kvm, void *dev);
+ u32 (*get_host_features)(struct kvm *kvm, void *dev);
+ void (*set_guest_features)(struct kvm *kvm, void *dev, u32 features);
+ int (*get_vq_count)(struct kvm *kvm, void *dev);
+ int (*init_vq)(struct kvm *kvm, void *dev, u32 vq, u32 page_size,
+ u32 align, u32 pfn);
+ void (*exit_vq)(struct kvm *kvm, void *dev, u32 vq);
+ int (*notify_vq)(struct kvm *kvm, void *dev, u32 vq);
+ struct virt_queue *(*get_vq)(struct kvm *kvm, void *dev, u32 vq);
+ int (*get_size_vq)(struct kvm *kvm, void *dev, u32 vq);
+ int (*set_size_vq)(struct kvm *kvm, void *dev, u32 vq, int size);
+ void (*notify_vq_gsi)(struct kvm *kvm, void *dev, u32 vq, u32 gsi);
+ void (*notify_vq_eventfd)(struct kvm *kvm, void *dev, u32 vq, u32 efd);
+ int (*signal_vq)(struct kvm *kvm, struct virtio_device *vdev, u32 queueid);
+ int (*signal_config)(struct kvm *kvm, struct virtio_device *vdev);
+ void (*notify_status)(struct kvm *kvm, void *dev, u32 status);
+ int (*init)(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class);
+ int (*exit)(struct kvm *kvm, struct virtio_device *vdev);
+ int (*reset)(struct kvm *kvm, struct virtio_device *vdev);
+};
+
+int __must_check virtio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ struct virtio_ops *ops, enum virtio_trans trans,
+ int device_id, int subsys_id, int class);
+int virtio_compat_add_message(const char *device, const char *config);
+const char* virtio_trans_name(enum virtio_trans trans);
+
+static inline void *virtio_get_vq(struct kvm *kvm, u32 pfn, u32 page_size)
+{
+ return guest_flat_to_host(kvm, (u64)pfn * page_size);
+}
+
+static inline void virtio_init_device_vq(struct virtio_device *vdev,
+ struct virt_queue *vq)
+{
+ vq->endian = vdev->endian;
+ vq->use_event_idx = (vdev->features & VIRTIO_RING_F_EVENT_IDX);
+ vq->enabled = true;
+}
+
+void virtio_exit_vq(struct kvm *kvm, struct virtio_device *vdev, void *dev,
+ int num);
+void virtio_set_guest_features(struct kvm *kvm, struct virtio_device *vdev,
+ void *dev, u32 features);
+void virtio_notify_status(struct kvm *kvm, struct virtio_device *vdev,
+ void *dev, u8 status);
+
+#endif /* KVM__VIRTIO_H */
diff --git a/kvmtool/include/kvm/vnc.h b/kvmtool/include/kvm/vnc.h
new file mode 100644
index 0000000..c2934a4
--- /dev/null
+++ b/kvmtool/include/kvm/vnc.h
@@ -0,0 +1,22 @@
+#ifndef KVM__VNC_H
+#define KVM__VNC_H
+
+#include "kvm/kvm.h"
+
+struct framebuffer;
+
+#ifdef CONFIG_HAS_VNCSERVER
+int vnc__init(struct kvm *kvm);
+int vnc__exit(struct kvm *kvm);
+#else
+static inline int vnc__init(struct kvm *kvm)
+{
+ return 0;
+}
+static inline int vnc__exit(struct kvm *kvm)
+{
+ return 0;
+}
+#endif
+
+#endif /* KVM__VNC_H */
diff --git a/kvmtool/include/linux/9p.h b/kvmtool/include/linux/9p.h
new file mode 100644
index 0000000..c7cfd8e
--- /dev/null
+++ b/kvmtool/include/linux/9p.h
@@ -0,0 +1,600 @@
+/*
+ * include/net/9p/9p.h
+ *
+ * 9P protocol definitions.
+ *
+ * Copyright (C) 2005 by Latchesar Ionkov <lucho@ionkov.net>
+ * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
+ * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to:
+ * Free Software Foundation
+ * 51 Franklin Street, Fifth Floor
+ * Boston, MA 02111-1301 USA
+ *
+ */
+
+#ifndef NET_9P_H
+#define NET_9P_H
+
+/* These definitions are from Linux include/linux/uidgid.h */
+typedef struct {
+ uid_t val;
+} kuid_t;
+
+typedef struct {
+ gid_t val;
+} kgid_t;
+
+#define KUIDT_INIT(value) (kuid_t){ value }
+#define KGIDT_INIT(value) (kgid_t){ value }
+
+static inline uid_t __kuid_val(kuid_t uid)
+{
+ return uid.val;
+}
+
+static inline gid_t __kgid_val(kgid_t gid)
+{
+ return gid.val;
+}
+
+
+/**
+ * enum p9_debug_flags - bits for mount time debug parameter
+ * @P9_DEBUG_ERROR: more verbose error messages including original error string
+ * @P9_DEBUG_9P: 9P protocol tracing
+ * @P9_DEBUG_VFS: VFS API tracing
+ * @P9_DEBUG_CONV: protocol conversion tracing
+ * @P9_DEBUG_MUX: trace management of concurrent transactions
+ * @P9_DEBUG_TRANS: transport tracing
+ * @P9_DEBUG_SLABS: memory management tracing
+ * @P9_DEBUG_FCALL: verbose dump of protocol messages
+ * @P9_DEBUG_FID: fid allocation/deallocation tracking
+ * @P9_DEBUG_PKT: packet marshalling/unmarshalling
+ * @P9_DEBUG_FSC: FS-cache tracing
+ * @P9_DEBUG_VPKT: Verbose packet debugging (full packet dump)
+ *
+ * These flags are passed at mount time to turn on various levels of
+ * verbosity and tracing which will be output to the system logs.
+ */
+
+enum p9_debug_flags {
+ P9_DEBUG_ERROR = (1<<0),
+ P9_DEBUG_9P = (1<<2),
+ P9_DEBUG_VFS = (1<<3),
+ P9_DEBUG_CONV = (1<<4),
+ P9_DEBUG_MUX = (1<<5),
+ P9_DEBUG_TRANS = (1<<6),
+ P9_DEBUG_SLABS = (1<<7),
+ P9_DEBUG_FCALL = (1<<8),
+ P9_DEBUG_FID = (1<<9),
+ P9_DEBUG_PKT = (1<<10),
+ P9_DEBUG_FSC = (1<<11),
+ P9_DEBUG_VPKT = (1<<12),
+};
+
+#ifdef CONFIG_NET_9P_DEBUG
+extern unsigned int p9_debug_level;
+__printf(3, 4)
+void _p9_debug(enum p9_debug_flags level, const char *func,
+ const char *fmt, ...);
+#define p9_debug(level, fmt, ...) \
+ _p9_debug(level, __func__, fmt, ##__VA_ARGS__)
+#else
+#define p9_debug(level, fmt, ...) \
+ no_printk(fmt, ##__VA_ARGS__)
+#endif
+
+/**
+ * enum p9_msg_t - 9P message types
+ * @P9_TLERROR: not used
+ * @P9_RLERROR: response for any failed request for 9P2000.L
+ * @P9_TSTATFS: file system status request
+ * @P9_RSTATFS: file system status response
+ * @P9_TSYMLINK: make symlink request
+ * @P9_RSYMLINK: make symlink response
+ * @P9_TMKNOD: create a special file object request
+ * @P9_RMKNOD: create a special file object response
+ * @P9_TLCREATE: prepare a handle for I/O on an new file for 9P2000.L
+ * @P9_RLCREATE: response with file access information for 9P2000.L
+ * @P9_TRENAME: rename request
+ * @P9_RRENAME: rename response
+ * @P9_TMKDIR: create a directory request
+ * @P9_RMKDIR: create a directory response
+ * @P9_TVERSION: version handshake request
+ * @P9_RVERSION: version handshake response
+ * @P9_TAUTH: request to establish authentication channel
+ * @P9_RAUTH: response with authentication information
+ * @P9_TATTACH: establish user access to file service
+ * @P9_RATTACH: response with top level handle to file hierarchy
+ * @P9_TERROR: not used
+ * @P9_RERROR: response for any failed request
+ * @P9_TFLUSH: request to abort a previous request
+ * @P9_RFLUSH: response when previous request has been cancelled
+ * @P9_TWALK: descend a directory hierarchy
+ * @P9_RWALK: response with new handle for position within hierarchy
+ * @P9_TOPEN: prepare a handle for I/O on an existing file
+ * @P9_ROPEN: response with file access information
+ * @P9_TCREATE: prepare a handle for I/O on a new file
+ * @P9_RCREATE: response with file access information
+ * @P9_TREAD: request to transfer data from a file or directory
+ * @P9_RREAD: response with data requested
+ * @P9_TWRITE: reuqest to transfer data to a file
+ * @P9_RWRITE: response with out much data was transferred to file
+ * @P9_TCLUNK: forget about a handle to an entity within the file system
+ * @P9_RCLUNK: response when server has forgotten about the handle
+ * @P9_TREMOVE: request to remove an entity from the hierarchy
+ * @P9_RREMOVE: response when server has removed the entity
+ * @P9_TSTAT: request file entity attributes
+ * @P9_RSTAT: response with file entity attributes
+ * @P9_TWSTAT: request to update file entity attributes
+ * @P9_RWSTAT: response when file entity attributes are updated
+ *
+ * There are 14 basic operations in 9P2000, paired as
+ * requests and responses. The one special case is ERROR
+ * as there is no @P9_TERROR request for clients to transmit to
+ * the server, but the server may respond to any other request
+ * with an @P9_RERROR.
+ *
+ * See Also: http://plan9.bell-labs.com/sys/man/5/INDEX.html
+ */
+
+enum p9_msg_t {
+ P9_TLERROR = 6,
+ P9_RLERROR,
+ P9_TSTATFS = 8,
+ P9_RSTATFS,
+ P9_TLOPEN = 12,
+ P9_RLOPEN,
+ P9_TLCREATE = 14,
+ P9_RLCREATE,
+ P9_TSYMLINK = 16,
+ P9_RSYMLINK,
+ P9_TMKNOD = 18,
+ P9_RMKNOD,
+ P9_TRENAME = 20,
+ P9_RRENAME,
+ P9_TREADLINK = 22,
+ P9_RREADLINK,
+ P9_TGETATTR = 24,
+ P9_RGETATTR,
+ P9_TSETATTR = 26,
+ P9_RSETATTR,
+ P9_TXATTRWALK = 30,
+ P9_RXATTRWALK,
+ P9_TXATTRCREATE = 32,
+ P9_RXATTRCREATE,
+ P9_TREADDIR = 40,
+ P9_RREADDIR,
+ P9_TFSYNC = 50,
+ P9_RFSYNC,
+ P9_TLOCK = 52,
+ P9_RLOCK,
+ P9_TGETLOCK = 54,
+ P9_RGETLOCK,
+ P9_TLINK = 70,
+ P9_RLINK,
+ P9_TMKDIR = 72,
+ P9_RMKDIR,
+ P9_TRENAMEAT = 74,
+ P9_RRENAMEAT,
+ P9_TUNLINKAT = 76,
+ P9_RUNLINKAT,
+ P9_TVERSION = 100,
+ P9_RVERSION,
+ P9_TAUTH = 102,
+ P9_RAUTH,
+ P9_TATTACH = 104,
+ P9_RATTACH,
+ P9_TERROR = 106,
+ P9_RERROR,
+ P9_TFLUSH = 108,
+ P9_RFLUSH,
+ P9_TWALK = 110,
+ P9_RWALK,
+ P9_TOPEN = 112,
+ P9_ROPEN,
+ P9_TCREATE = 114,
+ P9_RCREATE,
+ P9_TREAD = 116,
+ P9_RREAD,
+ P9_TWRITE = 118,
+ P9_RWRITE,
+ P9_TCLUNK = 120,
+ P9_RCLUNK,
+ P9_TREMOVE = 122,
+ P9_RREMOVE,
+ P9_TSTAT = 124,
+ P9_RSTAT,
+ P9_TWSTAT = 126,
+ P9_RWSTAT,
+};
+
+/**
+ * enum p9_open_mode_t - 9P open modes
+ * @P9_OREAD: open file for reading only
+ * @P9_OWRITE: open file for writing only
+ * @P9_ORDWR: open file for reading or writing
+ * @P9_OEXEC: open file for execution
+ * @P9_OTRUNC: truncate file to zero-length before opening it
+ * @P9_OREXEC: close the file when an exec(2) system call is made
+ * @P9_ORCLOSE: remove the file when the file is closed
+ * @P9_OAPPEND: open the file and seek to the end
+ * @P9_OEXCL: only create a file, do not open it
+ *
+ * 9P open modes differ slightly from Posix standard modes.
+ * In particular, there are extra modes which specify different
+ * semantic behaviors than may be available on standard Posix
+ * systems. For example, @P9_OREXEC and @P9_ORCLOSE are modes that
+ * most likely will not be issued from the Linux VFS client, but may
+ * be supported by servers.
+ *
+ * See Also: http://plan9.bell-labs.com/magic/man2html/2/open
+ */
+
+enum p9_open_mode_t {
+ P9_OREAD = 0x00,
+ P9_OWRITE = 0x01,
+ P9_ORDWR = 0x02,
+ P9_OEXEC = 0x03,
+ P9_OTRUNC = 0x10,
+ P9_OREXEC = 0x20,
+ P9_ORCLOSE = 0x40,
+ P9_OAPPEND = 0x80,
+ P9_OEXCL = 0x1000,
+};
+
+/**
+ * enum p9_perm_t - 9P permissions
+ * @P9_DMDIR: mode bit for directories
+ * @P9_DMAPPEND: mode bit for is append-only
+ * @P9_DMEXCL: mode bit for excluse use (only one open handle allowed)
+ * @P9_DMMOUNT: mode bit for mount points
+ * @P9_DMAUTH: mode bit for authentication file
+ * @P9_DMTMP: mode bit for non-backed-up files
+ * @P9_DMSYMLINK: mode bit for symbolic links (9P2000.u)
+ * @P9_DMLINK: mode bit for hard-link (9P2000.u)
+ * @P9_DMDEVICE: mode bit for device files (9P2000.u)
+ * @P9_DMNAMEDPIPE: mode bit for named pipe (9P2000.u)
+ * @P9_DMSOCKET: mode bit for socket (9P2000.u)
+ * @P9_DMSETUID: mode bit for setuid (9P2000.u)
+ * @P9_DMSETGID: mode bit for setgid (9P2000.u)
+ * @P9_DMSETVTX: mode bit for sticky bit (9P2000.u)
+ *
+ * 9P permissions differ slightly from Posix standard modes.
+ *
+ * See Also: http://plan9.bell-labs.com/magic/man2html/2/stat
+ */
+enum p9_perm_t {
+ P9_DMDIR = 0x80000000,
+ P9_DMAPPEND = 0x40000000,
+ P9_DMEXCL = 0x20000000,
+ P9_DMMOUNT = 0x10000000,
+ P9_DMAUTH = 0x08000000,
+ P9_DMTMP = 0x04000000,
+/* 9P2000.u extensions */
+ P9_DMSYMLINK = 0x02000000,
+ P9_DMLINK = 0x01000000,
+ P9_DMDEVICE = 0x00800000,
+ P9_DMNAMEDPIPE = 0x00200000,
+ P9_DMSOCKET = 0x00100000,
+ P9_DMSETUID = 0x00080000,
+ P9_DMSETGID = 0x00040000,
+ P9_DMSETVTX = 0x00010000,
+};
+
+/* 9p2000.L open flags */
+#define P9_DOTL_RDONLY 00000000
+#define P9_DOTL_WRONLY 00000001
+#define P9_DOTL_RDWR 00000002
+#define P9_DOTL_NOACCESS 00000003
+#define P9_DOTL_CREATE 00000100
+#define P9_DOTL_EXCL 00000200
+#define P9_DOTL_NOCTTY 00000400
+#define P9_DOTL_TRUNC 00001000
+#define P9_DOTL_APPEND 00002000
+#define P9_DOTL_NONBLOCK 00004000
+#define P9_DOTL_DSYNC 00010000
+#define P9_DOTL_FASYNC 00020000
+#define P9_DOTL_DIRECT 00040000
+#define P9_DOTL_LARGEFILE 00100000
+#define P9_DOTL_DIRECTORY 00200000
+#define P9_DOTL_NOFOLLOW 00400000
+#define P9_DOTL_NOATIME 01000000
+#define P9_DOTL_CLOEXEC 02000000
+#define P9_DOTL_SYNC 04000000
+
+/* 9p2000.L at flags */
+#define P9_DOTL_AT_REMOVEDIR 0x200
+
+/* 9p2000.L lock type */
+#define P9_LOCK_TYPE_RDLCK 0
+#define P9_LOCK_TYPE_WRLCK 1
+#define P9_LOCK_TYPE_UNLCK 2
+
+/**
+ * enum p9_qid_t - QID types
+ * @P9_QTDIR: directory
+ * @P9_QTAPPEND: append-only
+ * @P9_QTEXCL: excluse use (only one open handle allowed)
+ * @P9_QTMOUNT: mount points
+ * @P9_QTAUTH: authentication file
+ * @P9_QTTMP: non-backed-up files
+ * @P9_QTSYMLINK: symbolic links (9P2000.u)
+ * @P9_QTLINK: hard-link (9P2000.u)
+ * @P9_QTFILE: normal files
+ *
+ * QID types are a subset of permissions - they are primarily
+ * used to differentiate semantics for a file system entity via
+ * a jump-table. Their value is also the most significant 16 bits
+ * of the permission_t
+ *
+ * See Also: http://plan9.bell-labs.com/magic/man2html/2/stat
+ */
+enum p9_qid_t {
+ P9_QTDIR = 0x80,
+ P9_QTAPPEND = 0x40,
+ P9_QTEXCL = 0x20,
+ P9_QTMOUNT = 0x10,
+ P9_QTAUTH = 0x08,
+ P9_QTTMP = 0x04,
+ P9_QTSYMLINK = 0x02,
+ P9_QTLINK = 0x01,
+ P9_QTFILE = 0x00,
+};
+
+/* 9P Magic Numbers */
+#define P9_NOTAG (u16)(~0)
+#define P9_NOFID (u32)(~0)
+#define P9_MAXWELEM 16
+
+/* ample room for Twrite/Rread header */
+#define P9_IOHDRSZ 24
+
+/* Room for readdir header */
+#define P9_READDIRHDRSZ 24
+
+/* size of header for zero copy read/write */
+#define P9_ZC_HDR_SZ 4096
+
+/**
+ * struct p9_qid - file system entity information
+ * @type: 8-bit type &p9_qid_t
+ * @version: 16-bit monotonically incrementing version number
+ * @path: 64-bit per-server-unique ID for a file system element
+ *
+ * qids are identifiers used by 9P servers to track file system
+ * entities. The type is used to differentiate semantics for operations
+ * on the entity (ie. read means something different on a directory than
+ * on a file). The path provides a server unique index for an entity
+ * (roughly analogous to an inode number), while the version is updated
+ * every time a file is modified and can be used to maintain cache
+ * coherency between clients and serves.
+ * Servers will often differentiate purely synthetic entities by setting
+ * their version to 0, signaling that they should never be cached and
+ * should be accessed synchronously.
+ *
+ * See Also://plan9.bell-labs.com/magic/man2html/2/stat
+ */
+
+struct p9_qid {
+ u8 type;
+ u32 version;
+ u64 path;
+};
+
+/**
+ * struct p9_wstat - file system metadata information
+ * @size: length prefix for this stat structure instance
+ * @type: the type of the server (equivalent to a major number)
+ * @dev: the sub-type of the server (equivalent to a minor number)
+ * @qid: unique id from the server of type &p9_qid
+ * @mode: Plan 9 format permissions of type &p9_perm_t
+ * @atime: Last access/read time
+ * @mtime: Last modify/write time
+ * @length: file length
+ * @name: last element of path (aka filename)
+ * @uid: owner name
+ * @gid: group owner
+ * @muid: last modifier
+ * @extension: area used to encode extended UNIX support
+ * @n_uid: numeric user id of owner (part of 9p2000.u extension)
+ * @n_gid: numeric group id (part of 9p2000.u extension)
+ * @n_muid: numeric user id of laster modifier (part of 9p2000.u extension)
+ *
+ * See Also: http://plan9.bell-labs.com/magic/man2html/2/stat
+ */
+
+struct p9_wstat {
+ u16 size;
+ u16 type;
+ u32 dev;
+ struct p9_qid qid;
+ u32 mode;
+ u32 atime;
+ u32 mtime;
+ u64 length;
+ char *name;
+ char *uid;
+ char *gid;
+ char *muid;
+ char *extension; /* 9p2000.u extensions */
+ kuid_t n_uid; /* 9p2000.u extensions */
+ kgid_t n_gid; /* 9p2000.u extensions */
+ kuid_t n_muid; /* 9p2000.u extensions */
+};
+
+struct p9_stat_dotl {
+ u64 st_result_mask;
+ struct p9_qid qid;
+ u32 st_mode;
+ kuid_t st_uid;
+ kgid_t st_gid;
+ u64 st_nlink;
+ u64 st_rdev;
+ u64 st_size;
+ u64 st_blksize;
+ u64 st_blocks;
+ u64 st_atime_sec;
+ u64 st_atime_nsec;
+ u64 st_mtime_sec;
+ u64 st_mtime_nsec;
+ u64 st_ctime_sec;
+ u64 st_ctime_nsec;
+ u64 st_btime_sec;
+ u64 st_btime_nsec;
+ u64 st_gen;
+ u64 st_data_version;
+};
+
+#define P9_STATS_MODE 0x00000001ULL
+#define P9_STATS_NLINK 0x00000002ULL
+#define P9_STATS_UID 0x00000004ULL
+#define P9_STATS_GID 0x00000008ULL
+#define P9_STATS_RDEV 0x00000010ULL
+#define P9_STATS_ATIME 0x00000020ULL
+#define P9_STATS_MTIME 0x00000040ULL
+#define P9_STATS_CTIME 0x00000080ULL
+#define P9_STATS_INO 0x00000100ULL
+#define P9_STATS_SIZE 0x00000200ULL
+#define P9_STATS_BLOCKS 0x00000400ULL
+
+#define P9_STATS_BTIME 0x00000800ULL
+#define P9_STATS_GEN 0x00001000ULL
+#define P9_STATS_DATA_VERSION 0x00002000ULL
+
+#define P9_STATS_BASIC 0x000007ffULL /* Mask for fields up to BLOCKS */
+#define P9_STATS_ALL 0x00003fffULL /* Mask for All fields above */
+
+/**
+ * struct p9_iattr_dotl - P9 inode attribute for setattr
+ * @valid: bitfield specifying which fields are valid
+ * same as in struct iattr
+ * @mode: File permission bits
+ * @uid: user id of owner
+ * @gid: group id
+ * @size: File size
+ * @atime_sec: Last access time, seconds
+ * @atime_nsec: Last access time, nanoseconds
+ * @mtime_sec: Last modification time, seconds
+ * @mtime_nsec: Last modification time, nanoseconds
+ */
+
+struct p9_iattr_dotl {
+ u32 valid;
+ u32 mode;
+ kuid_t uid;
+ kgid_t gid;
+ u64 size;
+ u64 atime_sec;
+ u64 atime_nsec;
+ u64 mtime_sec;
+ u64 mtime_nsec;
+};
+
+#define P9_LOCK_SUCCESS 0
+#define P9_LOCK_BLOCKED 1
+#define P9_LOCK_ERROR 2
+#define P9_LOCK_GRACE 3
+
+#define P9_LOCK_FLAGS_BLOCK 1
+#define P9_LOCK_FLAGS_RECLAIM 2
+
+/* struct p9_flock: POSIX lock structure
+ * @type - type of lock
+ * @flags - lock flags
+ * @start - starting offset of the lock
+ * @length - number of bytes
+ * @proc_id - process id which wants to take lock
+ * @client_id - client id
+ */
+
+struct p9_flock {
+ u8 type;
+ u32 flags;
+ u64 start;
+ u64 length;
+ u32 proc_id;
+ char *client_id;
+};
+
+/* struct p9_getlock: getlock structure
+ * @type - type of lock
+ * @start - starting offset of the lock
+ * @length - number of bytes
+ * @proc_id - process id which wants to take lock
+ * @client_id - client id
+ */
+
+struct p9_getlock {
+ u8 type;
+ u64 start;
+ u64 length;
+ u32 proc_id;
+ char *client_id;
+};
+
+struct p9_rstatfs {
+ u32 type;
+ u32 bsize;
+ u64 blocks;
+ u64 bfree;
+ u64 bavail;
+ u64 files;
+ u64 ffree;
+ u64 fsid;
+ u32 namelen;
+};
+
+/**
+ * struct p9_fcall - primary packet structure
+ * @size: prefixed length of the structure
+ * @id: protocol operating identifier of type &p9_msg_t
+ * @tag: transaction id of the request
+ * @offset: used by marshalling routines to track current position in buffer
+ * @capacity: used by marshalling routines to track total malloc'd capacity
+ * @sdata: payload
+ *
+ * &p9_fcall represents the structure for all 9P RPC
+ * transactions. Requests are packaged into fcalls, and reponses
+ * must be extracted from them.
+ *
+ * See Also: http://plan9.bell-labs.com/magic/man2html/2/fcall
+ */
+
+struct p9_fcall {
+ u32 size;
+ u8 id;
+ u16 tag;
+
+ size_t offset;
+ size_t capacity;
+
+ u8 *sdata;
+};
+
+struct p9_idpool;
+
+int p9_errstr2errno(char *errstr, int len);
+
+struct p9_idpool *p9_idpool_create(void);
+void p9_idpool_destroy(struct p9_idpool *);
+int p9_idpool_get(struct p9_idpool *p);
+void p9_idpool_put(int id, struct p9_idpool *p);
+int p9_idpool_check(int id, struct p9_idpool *p);
+
+int p9_error_init(void);
+int p9_trans_fd_init(void);
+void p9_trans_fd_exit(void);
+#endif /* NET_9P_H */
diff --git a/kvmtool/include/linux/bitops.h b/kvmtool/include/linux/bitops.h
new file mode 100644
index 0000000..56448b7
--- /dev/null
+++ b/kvmtool/include/linux/bitops.h
@@ -0,0 +1,33 @@
+#ifndef _KVM_LINUX_BITOPS_H_
+#define _KVM_LINUX_BITOPS_H_
+
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <asm/hweight.h>
+
+#define BITS_PER_LONG __WORDSIZE
+#define BITS_PER_BYTE 8
+#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+
+static inline void set_bit(int nr, unsigned long *addr)
+{
+ addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
+}
+
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+ addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
+}
+
+static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
+{
+ return ((1UL << (nr % BITS_PER_LONG)) &
+ (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+}
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+ return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
+
+#endif
diff --git a/kvmtool/include/linux/byteorder.h b/kvmtool/include/linux/byteorder.h
new file mode 100644
index 0000000..8176361
--- /dev/null
+++ b/kvmtool/include/linux/byteorder.h
@@ -0,0 +1,34 @@
+#ifndef __BYTE_ORDER_H__
+#define __BYTE_ORDER_H__
+
+#include <asm/byteorder.h>
+
+/* taken from include/linux/byteorder/generic.h */
+#define cpu_to_le64 __cpu_to_le64
+#define le64_to_cpu __le64_to_cpu
+#define cpu_to_le32 __cpu_to_le32
+#define le32_to_cpu __le32_to_cpu
+#define cpu_to_le16 __cpu_to_le16
+#define le16_to_cpu __le16_to_cpu
+#define cpu_to_be64 __cpu_to_be64
+#define be64_to_cpu __be64_to_cpu
+#define cpu_to_be32 __cpu_to_be32
+#define be32_to_cpu __be32_to_cpu
+#define cpu_to_be16 __cpu_to_be16
+#define be16_to_cpu __be16_to_cpu
+
+/* change in situ versions */
+#define cpu_to_le64s __cpu_to_le64s
+#define le64_to_cpus __le64_to_cpus
+#define cpu_to_le32s __cpu_to_le32s
+#define le32_to_cpus __le32_to_cpus
+#define cpu_to_le16s __cpu_to_le16s
+#define le16_to_cpus __le16_to_cpus
+#define cpu_to_be64s __cpu_to_be64s
+#define be64_to_cpus __be64_to_cpus
+#define cpu_to_be32s __cpu_to_be32s
+#define be32_to_cpus __be32_to_cpus
+#define cpu_to_be16s __cpu_to_be16s
+#define be16_to_cpus __be16_to_cpus
+
+#endif
diff --git a/kvmtool/include/linux/compiler.h b/kvmtool/include/linux/compiler.h
new file mode 100644
index 0000000..a662ba0
--- /dev/null
+++ b/kvmtool/include/linux/compiler.h
@@ -0,0 +1,20 @@
+#ifndef _PERF_LINUX_COMPILER_H_
+#define _PERF_LINUX_COMPILER_H_
+
+#ifndef __always_inline
+#define __always_inline inline
+#endif
+#define __user
+
+#ifndef __attribute_const__
+#define __attribute_const__
+#endif
+
+#define __used __attribute__((__unused__))
+#define __packed __attribute__((packed))
+#define __iomem
+#define __force
+#define __must_check __attribute__((warn_unused_result))
+#define unlikely
+
+#endif
diff --git a/kvmtool/include/linux/err.h b/kvmtool/include/linux/err.h
new file mode 100644
index 0000000..a729120
--- /dev/null
+++ b/kvmtool/include/linux/err.h
@@ -0,0 +1,69 @@
+#ifndef _LINUX_ERR_H
+#define _LINUX_ERR_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include <asm/errno.h>
+
+/*
+ * Kernel pointers have redundant information, so we can use a
+ * scheme where we can return either an error code or a normal
+ * pointer with the same return value.
+ *
+ * This should be a per-architecture thing, to allow different
+ * error and pointer decisions.
+ */
+#define MAX_ERRNO 4095
+
+#ifndef __ASSEMBLY__
+
+#define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO)
+
+static inline void * __must_check ERR_PTR(long error)
+{
+ return (void *) error;
+}
+
+static inline long __must_check PTR_ERR(__force const void *ptr)
+{
+ return (long) ptr;
+}
+
+static inline bool __must_check IS_ERR(__force const void *ptr)
+{
+ return IS_ERR_VALUE((unsigned long)ptr);
+}
+
+static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
+{
+ return !ptr || IS_ERR_VALUE((unsigned long)ptr);
+}
+
+/**
+ * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type
+ * @ptr: The pointer to cast.
+ *
+ * Explicitly cast an error-valued pointer to another pointer type in such a
+ * way as to make it clear that's what's going on.
+ */
+static inline void * __must_check ERR_CAST(__force const void *ptr)
+{
+ /* cast away the const */
+ return (void *) ptr;
+}
+
+static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
+{
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+ else
+ return 0;
+}
+
+/* Deprecated */
+#define PTR_RET(p) PTR_ERR_OR_ZERO(p)
+
+#endif
+
+#endif /* _LINUX_ERR_H */
diff --git a/kvmtool/include/linux/kernel.h b/kvmtool/include/linux/kernel.h
new file mode 100644
index 0000000..f2bff5f
--- /dev/null
+++ b/kvmtool/include/linux/kernel.h
@@ -0,0 +1,51 @@
+
+#ifndef KVM__LINUX_KERNEL_H_
+#define KVM__LINUX_KERNEL_H_
+
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1)
+#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask))
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+#ifndef container_of
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr: the pointer to the member.
+ * @type: the type of the container struct this is embedded in.
+ * @member: the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({ \
+ const typeof(((type *)0)->member) * __mptr = (ptr); \
+ (type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+
+#define max(x, y) ({ \
+ typeof(x) _max1 = (x); \
+ typeof(y) _max2 = (y); \
+ (void) (&_max1 == &_max2); \
+ _max1 > _max2 ? _max1 : _max2; })
+
+#define min_t(type, x, y) ({ \
+ type __min1 = (x); \
+ type __min2 = (y); \
+ __min1 < __min2 ? __min1: __min2; })
+
+#define max_t(type, x, y) ({ \
+ type __max1 = (x); \
+ type __max2 = (y); \
+ __max1 > __max2 ? __max1: __max2; })
+
+#define true 1
+
+#endif
diff --git a/kvmtool/include/linux/kvm.h b/kvmtool/include/linux/kvm.h
new file mode 100644
index 0000000..5e3f12d
--- /dev/null
+++ b/kvmtool/include/linux/kvm.h
@@ -0,0 +1,1609 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_KVM_H
+#define __LINUX_KVM_H
+
+/*
+ * Userspace interface for /dev/kvm - kernel based virtual machine
+ *
+ * Note: you must update KVM_API_VERSION if you change this interface.
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/ioctl.h>
+#include <asm/kvm.h>
+
+#define KVM_API_VERSION 12
+
+/* *** Deprecated interfaces *** */
+
+#define KVM_TRC_SHIFT 16
+
+#define KVM_TRC_ENTRYEXIT (1 << KVM_TRC_SHIFT)
+#define KVM_TRC_HANDLER (1 << (KVM_TRC_SHIFT + 1))
+
+#define KVM_TRC_VMENTRY (KVM_TRC_ENTRYEXIT + 0x01)
+#define KVM_TRC_VMEXIT (KVM_TRC_ENTRYEXIT + 0x02)
+#define KVM_TRC_PAGE_FAULT (KVM_TRC_HANDLER + 0x01)
+
+#define KVM_TRC_HEAD_SIZE 12
+#define KVM_TRC_CYCLE_SIZE 8
+#define KVM_TRC_EXTRA_MAX 7
+
+#define KVM_TRC_INJ_VIRQ (KVM_TRC_HANDLER + 0x02)
+#define KVM_TRC_REDELIVER_EVT (KVM_TRC_HANDLER + 0x03)
+#define KVM_TRC_PEND_INTR (KVM_TRC_HANDLER + 0x04)
+#define KVM_TRC_IO_READ (KVM_TRC_HANDLER + 0x05)
+#define KVM_TRC_IO_WRITE (KVM_TRC_HANDLER + 0x06)
+#define KVM_TRC_CR_READ (KVM_TRC_HANDLER + 0x07)
+#define KVM_TRC_CR_WRITE (KVM_TRC_HANDLER + 0x08)
+#define KVM_TRC_DR_READ (KVM_TRC_HANDLER + 0x09)
+#define KVM_TRC_DR_WRITE (KVM_TRC_HANDLER + 0x0A)
+#define KVM_TRC_MSR_READ (KVM_TRC_HANDLER + 0x0B)
+#define KVM_TRC_MSR_WRITE (KVM_TRC_HANDLER + 0x0C)
+#define KVM_TRC_CPUID (KVM_TRC_HANDLER + 0x0D)
+#define KVM_TRC_INTR (KVM_TRC_HANDLER + 0x0E)
+#define KVM_TRC_NMI (KVM_TRC_HANDLER + 0x0F)
+#define KVM_TRC_VMMCALL (KVM_TRC_HANDLER + 0x10)
+#define KVM_TRC_HLT (KVM_TRC_HANDLER + 0x11)
+#define KVM_TRC_CLTS (KVM_TRC_HANDLER + 0x12)
+#define KVM_TRC_LMSW (KVM_TRC_HANDLER + 0x13)
+#define KVM_TRC_APIC_ACCESS (KVM_TRC_HANDLER + 0x14)
+#define KVM_TRC_TDP_FAULT (KVM_TRC_HANDLER + 0x15)
+#define KVM_TRC_GTLB_WRITE (KVM_TRC_HANDLER + 0x16)
+#define KVM_TRC_STLB_WRITE (KVM_TRC_HANDLER + 0x17)
+#define KVM_TRC_STLB_INVAL (KVM_TRC_HANDLER + 0x18)
+#define KVM_TRC_PPC_INSTR (KVM_TRC_HANDLER + 0x19)
+
+struct kvm_user_trace_setup {
+ __u32 buf_size;
+ __u32 buf_nr;
+};
+
+#define __KVM_DEPRECATED_MAIN_W_0x06 \
+ _IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
+#define __KVM_DEPRECATED_MAIN_0x07 _IO(KVMIO, 0x07)
+#define __KVM_DEPRECATED_MAIN_0x08 _IO(KVMIO, 0x08)
+
+#define __KVM_DEPRECATED_VM_R_0x70 _IOR(KVMIO, 0x70, struct kvm_assigned_irq)
+
+struct kvm_breakpoint {
+ __u32 enabled;
+ __u32 padding;
+ __u64 address;
+};
+
+struct kvm_debug_guest {
+ __u32 enabled;
+ __u32 pad;
+ struct kvm_breakpoint breakpoints[4];
+ __u32 singlestep;
+};
+
+#define __KVM_DEPRECATED_VCPU_W_0x87 _IOW(KVMIO, 0x87, struct kvm_debug_guest)
+
+/* *** End of deprecated interfaces *** */
+
+
+/* for KVM_CREATE_MEMORY_REGION */
+struct kvm_memory_region {
+ __u32 slot;
+ __u32 flags;
+ __u64 guest_phys_addr;
+ __u64 memory_size; /* bytes */
+};
+
+/* for KVM_SET_USER_MEMORY_REGION */
+struct kvm_userspace_memory_region {
+ __u32 slot;
+ __u32 flags;
+ __u64 guest_phys_addr;
+ __u64 memory_size; /* bytes */
+ __u64 userspace_addr; /* start of the userspace allocated memory */
+};
+
+/*
+ * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
+ * other bits are reserved for kvm internal use which are defined in
+ * include/linux/kvm_host.h.
+ */
+#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
+#define KVM_MEM_READONLY (1UL << 1)
+
+/* for KVM_IRQ_LINE */
+struct kvm_irq_level {
+ /*
+ * ACPI gsi notion of irq.
+ * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
+ * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
+ * For ARM: See Documentation/virt/kvm/api.txt
+ */
+ union {
+ __u32 irq;
+ __s32 status;
+ };
+ __u32 level;
+};
+
+
+struct kvm_irqchip {
+ __u32 chip_id;
+ __u32 pad;
+ union {
+ char dummy[512]; /* reserving space */
+#ifdef __KVM_HAVE_PIT
+ struct kvm_pic_state pic;
+#endif
+#ifdef __KVM_HAVE_IOAPIC
+ struct kvm_ioapic_state ioapic;
+#endif
+ } chip;
+};
+
+/* for KVM_CREATE_PIT2 */
+struct kvm_pit_config {
+ __u32 flags;
+ __u32 pad[15];
+};
+
+#define KVM_PIT_SPEAKER_DUMMY 1
+
+struct kvm_s390_skeys {
+ __u64 start_gfn;
+ __u64 count;
+ __u64 skeydata_addr;
+ __u32 flags;
+ __u32 reserved[9];
+};
+
+#define KVM_S390_CMMA_PEEK (1 << 0)
+
+/**
+ * kvm_s390_cmma_log - Used for CMMA migration.
+ *
+ * Used both for input and output.
+ *
+ * @start_gfn: Guest page number to start from.
+ * @count: Size of the result buffer.
+ * @flags: Control operation mode via KVM_S390_CMMA_* flags
+ * @remaining: Used with KVM_S390_GET_CMMA_BITS. Indicates how many dirty
+ * pages are still remaining.
+ * @mask: Used with KVM_S390_SET_CMMA_BITS. Bitmap of bits to actually set
+ * in the PGSTE.
+ * @values: Pointer to the values buffer.
+ *
+ * Used in KVM_S390_{G,S}ET_CMMA_BITS ioctls.
+ */
+struct kvm_s390_cmma_log {
+ __u64 start_gfn;
+ __u32 count;
+ __u32 flags;
+ union {
+ __u64 remaining;
+ __u64 mask;
+ };
+ __u64 values;
+};
+
+struct kvm_hyperv_exit {
+#define KVM_EXIT_HYPERV_SYNIC 1
+#define KVM_EXIT_HYPERV_HCALL 2
+ __u32 type;
+ union {
+ struct {
+ __u32 msr;
+ __u64 control;
+ __u64 evt_page;
+ __u64 msg_page;
+ } synic;
+ struct {
+ __u64 input;
+ __u64 result;
+ __u64 params[2];
+ } hcall;
+ } u;
+};
+
+#define KVM_S390_GET_SKEYS_NONE 1
+#define KVM_S390_SKEYS_MAX 1048576
+
+#define KVM_EXIT_UNKNOWN 0
+#define KVM_EXIT_EXCEPTION 1
+#define KVM_EXIT_IO 2
+#define KVM_EXIT_HYPERCALL 3
+#define KVM_EXIT_DEBUG 4
+#define KVM_EXIT_HLT 5
+#define KVM_EXIT_MMIO 6
+#define KVM_EXIT_IRQ_WINDOW_OPEN 7
+#define KVM_EXIT_SHUTDOWN 8
+#define KVM_EXIT_FAIL_ENTRY 9
+#define KVM_EXIT_INTR 10
+#define KVM_EXIT_SET_TPR 11
+#define KVM_EXIT_TPR_ACCESS 12
+#define KVM_EXIT_S390_SIEIC 13
+#define KVM_EXIT_S390_RESET 14
+#define KVM_EXIT_DCR 15 /* deprecated */
+#define KVM_EXIT_NMI 16
+#define KVM_EXIT_INTERNAL_ERROR 17
+#define KVM_EXIT_OSI 18
+#define KVM_EXIT_PAPR_HCALL 19
+#define KVM_EXIT_S390_UCONTROL 20
+#define KVM_EXIT_WATCHDOG 21
+#define KVM_EXIT_S390_TSCH 22
+#define KVM_EXIT_EPR 23
+#define KVM_EXIT_SYSTEM_EVENT 24
+#define KVM_EXIT_S390_STSI 25
+#define KVM_EXIT_IOAPIC_EOI 26
+#define KVM_EXIT_HYPERV 27
+
+/* For KVM_EXIT_INTERNAL_ERROR */
+/* Emulate instruction failed. */
+#define KVM_INTERNAL_ERROR_EMULATION 1
+/* Encounter unexpected simultaneous exceptions. */
+#define KVM_INTERNAL_ERROR_SIMUL_EX 2
+/* Encounter unexpected vm-exit due to delivery event. */
+#define KVM_INTERNAL_ERROR_DELIVERY_EV 3
+
+/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
+struct kvm_run {
+ /* in */
+ __u8 request_interrupt_window;
+ __u8 immediate_exit;
+ __u8 padding1[6];
+
+ /* out */
+ __u32 exit_reason;
+ __u8 ready_for_interrupt_injection;
+ __u8 if_flag;
+ __u16 flags;
+
+ /* in (pre_kvm_run), out (post_kvm_run) */
+ __u64 cr8;
+ __u64 apic_base;
+
+#ifdef __KVM_S390
+ /* the processor status word for s390 */
+ __u64 psw_mask; /* psw upper half */
+ __u64 psw_addr; /* psw lower half */
+#endif
+ union {
+ /* KVM_EXIT_UNKNOWN */
+ struct {
+ __u64 hardware_exit_reason;
+ } hw;
+ /* KVM_EXIT_FAIL_ENTRY */
+ struct {
+ __u64 hardware_entry_failure_reason;
+ } fail_entry;
+ /* KVM_EXIT_EXCEPTION */
+ struct {
+ __u32 exception;
+ __u32 error_code;
+ } ex;
+ /* KVM_EXIT_IO */
+ struct {
+#define KVM_EXIT_IO_IN 0
+#define KVM_EXIT_IO_OUT 1
+ __u8 direction;
+ __u8 size; /* bytes */
+ __u16 port;
+ __u32 count;
+ __u64 data_offset; /* relative to kvm_run start */
+ } io;
+ /* KVM_EXIT_DEBUG */
+ struct {
+ struct kvm_debug_exit_arch arch;
+ } debug;
+ /* KVM_EXIT_MMIO */
+ struct {
+ __u64 phys_addr;
+ __u8 data[8];
+ __u32 len;
+ __u8 is_write;
+ } mmio;
+ /* KVM_EXIT_HYPERCALL */
+ struct {
+ __u64 nr;
+ __u64 args[6];
+ __u64 ret;
+ __u32 longmode;
+ __u32 pad;
+ } hypercall;
+ /* KVM_EXIT_TPR_ACCESS */
+ struct {
+ __u64 rip;
+ __u32 is_write;
+ __u32 pad;
+ } tpr_access;
+ /* KVM_EXIT_S390_SIEIC */
+ struct {
+ __u8 icptcode;
+ __u16 ipa;
+ __u32 ipb;
+ } s390_sieic;
+ /* KVM_EXIT_S390_RESET */
+#define KVM_S390_RESET_POR 1
+#define KVM_S390_RESET_CLEAR 2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT 8
+#define KVM_S390_RESET_IPL 16
+ __u64 s390_reset_flags;
+ /* KVM_EXIT_S390_UCONTROL */
+ struct {
+ __u64 trans_exc_code;
+ __u32 pgm_code;
+ } s390_ucontrol;
+ /* KVM_EXIT_DCR (deprecated) */
+ struct {
+ __u32 dcrn;
+ __u32 data;
+ __u8 is_write;
+ } dcr;
+ /* KVM_EXIT_INTERNAL_ERROR */
+ struct {
+ __u32 suberror;
+ /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */
+ __u32 ndata;
+ __u64 data[16];
+ } internal;
+ /* KVM_EXIT_OSI */
+ struct {
+ __u64 gprs[32];
+ } osi;
+ /* KVM_EXIT_PAPR_HCALL */
+ struct {
+ __u64 nr;
+ __u64 ret;
+ __u64 args[9];
+ } papr_hcall;
+ /* KVM_EXIT_S390_TSCH */
+ struct {
+ __u16 subchannel_id;
+ __u16 subchannel_nr;
+ __u32 io_int_parm;
+ __u32 io_int_word;
+ __u32 ipb;
+ __u8 dequeued;
+ } s390_tsch;
+ /* KVM_EXIT_EPR */
+ struct {
+ __u32 epr;
+ } epr;
+ /* KVM_EXIT_SYSTEM_EVENT */
+ struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN 1
+#define KVM_SYSTEM_EVENT_RESET 2
+#define KVM_SYSTEM_EVENT_CRASH 3
+ __u32 type;
+ __u64 flags;
+ } system_event;
+ /* KVM_EXIT_S390_STSI */
+ struct {
+ __u64 addr;
+ __u8 ar;
+ __u8 reserved;
+ __u8 fc;
+ __u8 sel1;
+ __u16 sel2;
+ } s390_stsi;
+ /* KVM_EXIT_IOAPIC_EOI */
+ struct {
+ __u8 vector;
+ } eoi;
+ /* KVM_EXIT_HYPERV */
+ struct kvm_hyperv_exit hyperv;
+ /* Fix the size of the union. */
+ char padding[256];
+ };
+
+ /* 2048 is the size of the char array used to bound/pad the size
+ * of the union that holds sync regs.
+ */
+ #define SYNC_REGS_SIZE_BYTES 2048
+ /*
+ * shared registers between kvm and userspace.
+ * kvm_valid_regs specifies the register classes set by the host
+ * kvm_dirty_regs specified the register classes dirtied by userspace
+ * struct kvm_sync_regs is architecture specific, as well as the
+ * bits for kvm_valid_regs and kvm_dirty_regs
+ */
+ __u64 kvm_valid_regs;
+ __u64 kvm_dirty_regs;
+ union {
+ struct kvm_sync_regs regs;
+ char padding[SYNC_REGS_SIZE_BYTES];
+ } s;
+};
+
+/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
+
+struct kvm_coalesced_mmio_zone {
+ __u64 addr;
+ __u32 size;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
+};
+
+struct kvm_coalesced_mmio {
+ __u64 phys_addr;
+ __u32 len;
+ union {
+ __u32 pad;
+ __u32 pio;
+ };
+ __u8 data[8];
+};
+
+struct kvm_coalesced_mmio_ring {
+ __u32 first, last;
+ struct kvm_coalesced_mmio coalesced_mmio[0];
+};
+
+#define KVM_COALESCED_MMIO_MAX \
+ ((PAGE_SIZE - sizeof(struct kvm_coalesced_mmio_ring)) / \
+ sizeof(struct kvm_coalesced_mmio))
+
+/* for KVM_TRANSLATE */
+struct kvm_translation {
+ /* in */
+ __u64 linear_address;
+
+ /* out */
+ __u64 physical_address;
+ __u8 valid;
+ __u8 writeable;
+ __u8 usermode;
+ __u8 pad[5];
+};
+
+/* for KVM_S390_MEM_OP */
+struct kvm_s390_mem_op {
+ /* in */
+ __u64 gaddr; /* the guest address */
+ __u64 flags; /* flags */
+ __u32 size; /* amount of bytes */
+ __u32 op; /* type of operation */
+ __u64 buf; /* buffer in userspace */
+ __u8 ar; /* the access register number */
+ __u8 reserved[31]; /* should be set to 0 */
+};
+/* types for kvm_s390_mem_op->op */
+#define KVM_S390_MEMOP_LOGICAL_READ 0
+#define KVM_S390_MEMOP_LOGICAL_WRITE 1
+/* flags for kvm_s390_mem_op->flags */
+#define KVM_S390_MEMOP_F_CHECK_ONLY (1ULL << 0)
+#define KVM_S390_MEMOP_F_INJECT_EXCEPTION (1ULL << 1)
+
+/* for KVM_INTERRUPT */
+struct kvm_interrupt {
+ /* in */
+ __u32 irq;
+};
+
+/* for KVM_GET_DIRTY_LOG */
+struct kvm_dirty_log {
+ __u32 slot;
+ __u32 padding1;
+ union {
+ void __user *dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
+/* for KVM_CLEAR_DIRTY_LOG */
+struct kvm_clear_dirty_log {
+ __u32 slot;
+ __u32 num_pages;
+ __u64 first_page;
+ union {
+ void __user *dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
+/* for KVM_SET_SIGNAL_MASK */
+struct kvm_signal_mask {
+ __u32 len;
+ __u8 sigset[0];
+};
+
+/* for KVM_TPR_ACCESS_REPORTING */
+struct kvm_tpr_access_ctl {
+ __u32 enabled;
+ __u32 flags;
+ __u32 reserved[8];
+};
+
+/* for KVM_SET_VAPIC_ADDR */
+struct kvm_vapic_addr {
+ __u64 vapic_addr;
+};
+
+/* for KVM_SET_MP_STATE */
+
+/* not all states are valid on all architectures */
+#define KVM_MP_STATE_RUNNABLE 0
+#define KVM_MP_STATE_UNINITIALIZED 1
+#define KVM_MP_STATE_INIT_RECEIVED 2
+#define KVM_MP_STATE_HALTED 3
+#define KVM_MP_STATE_SIPI_RECEIVED 4
+#define KVM_MP_STATE_STOPPED 5
+#define KVM_MP_STATE_CHECK_STOP 6
+#define KVM_MP_STATE_OPERATING 7
+#define KVM_MP_STATE_LOAD 8
+
+struct kvm_mp_state {
+ __u32 mp_state;
+};
+
+struct kvm_s390_psw {
+ __u64 mask;
+ __u64 addr;
+};
+
+/* valid values for type in kvm_s390_interrupt */
+#define KVM_S390_SIGP_STOP 0xfffe0000u
+#define KVM_S390_PROGRAM_INT 0xfffe0001u
+#define KVM_S390_SIGP_SET_PREFIX 0xfffe0002u
+#define KVM_S390_RESTART 0xfffe0003u
+#define KVM_S390_INT_PFAULT_INIT 0xfffe0004u
+#define KVM_S390_INT_PFAULT_DONE 0xfffe0005u
+#define KVM_S390_MCHK 0xfffe1000u
+#define KVM_S390_INT_CLOCK_COMP 0xffff1004u
+#define KVM_S390_INT_CPU_TIMER 0xffff1005u
+#define KVM_S390_INT_VIRTIO 0xffff2603u
+#define KVM_S390_INT_SERVICE 0xffff2401u
+#define KVM_S390_INT_EMERGENCY 0xffff1201u
+#define KVM_S390_INT_EXTERNAL_CALL 0xffff1202u
+/* Anything below 0xfffe0000u is taken by INT_IO */
+#define KVM_S390_INT_IO(ai,cssid,ssid,schid) \
+ (((schid)) | \
+ ((ssid) << 16) | \
+ ((cssid) << 18) | \
+ ((ai) << 26))
+#define KVM_S390_INT_IO_MIN 0x00000000u
+#define KVM_S390_INT_IO_MAX 0xfffdffffu
+#define KVM_S390_INT_IO_AI_MASK 0x04000000u
+
+
+struct kvm_s390_interrupt {
+ __u32 type;
+ __u32 parm;
+ __u64 parm64;
+};
+
+struct kvm_s390_io_info {
+ __u16 subchannel_id;
+ __u16 subchannel_nr;
+ __u32 io_int_parm;
+ __u32 io_int_word;
+};
+
+struct kvm_s390_ext_info {
+ __u32 ext_params;
+ __u32 pad;
+ __u64 ext_params2;
+};
+
+struct kvm_s390_pgm_info {
+ __u64 trans_exc_code;
+ __u64 mon_code;
+ __u64 per_address;
+ __u32 data_exc_code;
+ __u16 code;
+ __u16 mon_class_nr;
+ __u8 per_code;
+ __u8 per_atmid;
+ __u8 exc_access_id;
+ __u8 per_access_id;
+ __u8 op_access_id;
+#define KVM_S390_PGM_FLAGS_ILC_VALID 0x01
+#define KVM_S390_PGM_FLAGS_ILC_0 0x02
+#define KVM_S390_PGM_FLAGS_ILC_1 0x04
+#define KVM_S390_PGM_FLAGS_ILC_MASK 0x06
+#define KVM_S390_PGM_FLAGS_NO_REWIND 0x08
+ __u8 flags;
+ __u8 pad[2];
+};
+
+struct kvm_s390_prefix_info {
+ __u32 address;
+};
+
+struct kvm_s390_extcall_info {
+ __u16 code;
+};
+
+struct kvm_s390_emerg_info {
+ __u16 code;
+};
+
+#define KVM_S390_STOP_FLAG_STORE_STATUS 0x01
+struct kvm_s390_stop_info {
+ __u32 flags;
+};
+
+struct kvm_s390_mchk_info {
+ __u64 cr14;
+ __u64 mcic;
+ __u64 failing_storage_address;
+ __u32 ext_damage_code;
+ __u32 pad;
+ __u8 fixed_logout[16];
+};
+
+struct kvm_s390_irq {
+ __u64 type;
+ union {
+ struct kvm_s390_io_info io;
+ struct kvm_s390_ext_info ext;
+ struct kvm_s390_pgm_info pgm;
+ struct kvm_s390_emerg_info emerg;
+ struct kvm_s390_extcall_info extcall;
+ struct kvm_s390_prefix_info prefix;
+ struct kvm_s390_stop_info stop;
+ struct kvm_s390_mchk_info mchk;
+ char reserved[64];
+ } u;
+};
+
+struct kvm_s390_irq_state {
+ __u64 buf;
+ __u32 flags; /* will stay unused for compatibility reasons */
+ __u32 len;
+ __u32 reserved[4]; /* will stay unused for compatibility reasons */
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+
+#define KVM_GUESTDBG_ENABLE 0x00000001
+#define KVM_GUESTDBG_SINGLESTEP 0x00000002
+
+struct kvm_guest_debug {
+ __u32 control;
+ __u32 pad;
+ struct kvm_guest_debug_arch arch;
+};
+
+enum {
+ kvm_ioeventfd_flag_nr_datamatch,
+ kvm_ioeventfd_flag_nr_pio,
+ kvm_ioeventfd_flag_nr_deassign,
+ kvm_ioeventfd_flag_nr_virtio_ccw_notify,
+ kvm_ioeventfd_flag_nr_fast_mmio,
+ kvm_ioeventfd_flag_nr_max,
+};
+
+#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
+#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
+#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
+#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
+ (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
+
+#define KVM_IOEVENTFD_VALID_FLAG_MASK ((1 << kvm_ioeventfd_flag_nr_max) - 1)
+
+struct kvm_ioeventfd {
+ __u64 datamatch;
+ __u64 addr; /* legal pio/mmio address */
+ __u32 len; /* 1, 2, 4, or 8 bytes; or 0 to ignore length */
+ __s32 fd;
+ __u32 flags;
+ __u8 pad[36];
+};
+
+#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
+#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \
+ KVM_X86_DISABLE_EXITS_HLT | \
+ KVM_X86_DISABLE_EXITS_PAUSE | \
+ KVM_X86_DISABLE_EXITS_CSTATE)
+
+/* for KVM_ENABLE_CAP */
+struct kvm_enable_cap {
+ /* in */
+ __u32 cap;
+ __u32 flags;
+ __u64 args[4];
+ __u8 pad[64];
+};
+
+/* for KVM_PPC_GET_PVINFO */
+
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
+struct kvm_ppc_pvinfo {
+ /* out */
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
+/* for KVM_PPC_GET_SMMU_INFO */
+#define KVM_PPC_PAGE_SIZES_MAX_SZ 8
+
+struct kvm_ppc_one_page_size {
+ __u32 page_shift; /* Page shift (or 0) */
+ __u32 pte_enc; /* Encoding in the HPTE (>>12) */
+};
+
+struct kvm_ppc_one_seg_page_size {
+ __u32 page_shift; /* Base page shift of segment (or 0) */
+ __u32 slb_enc; /* SLB encoding for BookS */
+ struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+#define KVM_PPC_PAGE_SIZES_REAL 0x00000001
+#define KVM_PPC_1T_SEGMENTS 0x00000002
+#define KVM_PPC_NO_HASH 0x00000004
+
+struct kvm_ppc_smmu_info {
+ __u64 flags;
+ __u32 slb_size;
+ __u16 data_keys; /* # storage keys supported for data */
+ __u16 instr_keys; /* # storage keys supported for instructions */
+ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+};
+
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+ __u64 flags;
+ __u32 shift;
+ __u32 pad;
+};
+
+#define KVMIO 0xAE
+
+/* machine type bits, to be used as argument to KVM_CREATE_VM */
+#define KVM_VM_S390_UCONTROL 1
+
+/* on ppc, 0 indicate default, 1 should force HV and 2 PR */
+#define KVM_VM_PPC_HV 1
+#define KVM_VM_PPC_PR 2
+
+/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
+#define KVM_VM_MIPS_TE 0
+#define KVM_VM_MIPS_VZ 1
+
+#define KVM_S390_SIE_PAGE_OFFSET 1
+
+/*
+ * On arm64, machine type can be used to request the physical
+ * address size for the VM. Bits[7-0] are reserved for the guest
+ * PA size shift (i.e, log2(PA_Size)). For backward compatibility,
+ * value 0 implies the default IPA size, 40bits.
+ */
+#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK 0xffULL
+#define KVM_VM_TYPE_ARM_IPA_SIZE(x) \
+ ((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+/*
+ * ioctls for /dev/kvm fds:
+ */
+#define KVM_GET_API_VERSION _IO(KVMIO, 0x00)
+#define KVM_CREATE_VM _IO(KVMIO, 0x01) /* returns a VM fd */
+#define KVM_GET_MSR_INDEX_LIST _IOWR(KVMIO, 0x02, struct kvm_msr_list)
+
+#define KVM_S390_ENABLE_SIE _IO(KVMIO, 0x06)
+/*
+ * Check if a kvm extension is available. Argument is extension number,
+ * return is 1 (yes) or 0 (no, sorry).
+ */
+#define KVM_CHECK_EXTENSION _IO(KVMIO, 0x03)
+/*
+ * Get size for mmap(vcpu_fd)
+ */
+#define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */
+#define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
+#define KVM_TRACE_ENABLE __KVM_DEPRECATED_MAIN_W_0x06
+#define KVM_TRACE_PAUSE __KVM_DEPRECATED_MAIN_0x07
+#define KVM_TRACE_DISABLE __KVM_DEPRECATED_MAIN_0x08
+#define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
+#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
+
+/*
+ * Extension capability list.
+ */
+#define KVM_CAP_IRQCHIP 0
+#define KVM_CAP_HLT 1
+#define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2
+#define KVM_CAP_USER_MEMORY 3
+#define KVM_CAP_SET_TSS_ADDR 4
+#define KVM_CAP_VAPIC 6
+#define KVM_CAP_EXT_CPUID 7
+#define KVM_CAP_CLOCKSOURCE 8
+#define KVM_CAP_NR_VCPUS 9 /* returns recommended max vcpus per vm */
+#define KVM_CAP_NR_MEMSLOTS 10 /* returns max memory slots per vm */
+#define KVM_CAP_PIT 11
+#define KVM_CAP_NOP_IO_DELAY 12
+#define KVM_CAP_PV_MMU 13
+#define KVM_CAP_MP_STATE 14
+#define KVM_CAP_COALESCED_MMIO 15
+#define KVM_CAP_SYNC_MMU 16 /* Changes to host mmap are reflected in guest */
+#define KVM_CAP_IOMMU 18
+/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
+#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
+#define KVM_CAP_USER_NMI 22
+#ifdef __KVM_HAVE_GUEST_DEBUG
+#define KVM_CAP_SET_GUEST_DEBUG 23
+#endif
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_REINJECT_CONTROL 24
+#endif
+#define KVM_CAP_IRQ_ROUTING 25
+#define KVM_CAP_IRQ_INJECT_STATUS 26
+#define KVM_CAP_ASSIGN_DEV_IRQ 29
+/* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
+#define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
+#ifdef __KVM_HAVE_MCE
+#define KVM_CAP_MCE 31
+#endif
+#define KVM_CAP_IRQFD 32
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_PIT2 33
+#endif
+#define KVM_CAP_SET_BOOT_CPU_ID 34
+#ifdef __KVM_HAVE_PIT_STATE2
+#define KVM_CAP_PIT_STATE2 35
+#endif
+#define KVM_CAP_IOEVENTFD 36
+#define KVM_CAP_SET_IDENTITY_MAP_ADDR 37
+#ifdef __KVM_HAVE_XEN_HVM
+#define KVM_CAP_XEN_HVM 38
+#endif
+#define KVM_CAP_ADJUST_CLOCK 39
+#define KVM_CAP_INTERNAL_ERROR_DATA 40
+#ifdef __KVM_HAVE_VCPU_EVENTS
+#define KVM_CAP_VCPU_EVENTS 41
+#endif
+#define KVM_CAP_S390_PSW 42
+#define KVM_CAP_PPC_SEGSTATE 43
+#define KVM_CAP_HYPERV 44
+#define KVM_CAP_HYPERV_VAPIC 45
+#define KVM_CAP_HYPERV_SPIN 46
+#define KVM_CAP_PCI_SEGMENT 47
+#define KVM_CAP_PPC_PAIRED_SINGLES 48
+#define KVM_CAP_INTR_SHADOW 49
+#ifdef __KVM_HAVE_DEBUGREGS
+#define KVM_CAP_DEBUGREGS 50
+#endif
+#define KVM_CAP_X86_ROBUST_SINGLESTEP 51
+#define KVM_CAP_PPC_OSI 52
+#define KVM_CAP_PPC_UNSET_IRQ 53
+#define KVM_CAP_ENABLE_CAP 54
+#ifdef __KVM_HAVE_XSAVE
+#define KVM_CAP_XSAVE 55
+#endif
+#ifdef __KVM_HAVE_XCRS
+#define KVM_CAP_XCRS 56
+#endif
+#define KVM_CAP_PPC_GET_PVINFO 57
+#define KVM_CAP_PPC_IRQ_LEVEL 58
+#define KVM_CAP_ASYNC_PF 59
+#define KVM_CAP_TSC_CONTROL 60
+#define KVM_CAP_GET_TSC_KHZ 61
+#define KVM_CAP_PPC_BOOKE_SREGS 62
+#define KVM_CAP_SPAPR_TCE 63
+#define KVM_CAP_PPC_SMT 64
+#define KVM_CAP_PPC_RMA 65
+#define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */
+#define KVM_CAP_PPC_HIOR 67
+#define KVM_CAP_PPC_PAPR 68
+#define KVM_CAP_SW_TLB 69
+#define KVM_CAP_ONE_REG 70
+#define KVM_CAP_S390_GMAP 71
+#define KVM_CAP_TSC_DEADLINE_TIMER 72
+#define KVM_CAP_S390_UCONTROL 73
+#define KVM_CAP_SYNC_REGS 74
+#define KVM_CAP_PCI_2_3 75
+#define KVM_CAP_KVMCLOCK_CTRL 76
+#define KVM_CAP_SIGNAL_MSI 77
+#define KVM_CAP_PPC_GET_SMMU_INFO 78
+#define KVM_CAP_S390_COW 79
+#define KVM_CAP_PPC_ALLOC_HTAB 80
+#define KVM_CAP_READONLY_MEM 81
+#define KVM_CAP_IRQFD_RESAMPLE 82
+#define KVM_CAP_PPC_BOOKE_WATCHDOG 83
+#define KVM_CAP_PPC_HTAB_FD 84
+#define KVM_CAP_S390_CSS_SUPPORT 85
+#define KVM_CAP_PPC_EPR 86
+#define KVM_CAP_ARM_PSCI 87
+#define KVM_CAP_ARM_SET_DEVICE_ADDR 88
+#define KVM_CAP_DEVICE_CTRL 89
+#define KVM_CAP_IRQ_MPIC 90
+#define KVM_CAP_PPC_RTAS 91
+#define KVM_CAP_IRQ_XICS 92
+#define KVM_CAP_ARM_EL1_32BIT 93
+#define KVM_CAP_SPAPR_MULTITCE 94
+#define KVM_CAP_EXT_EMUL_CPUID 95
+#define KVM_CAP_HYPERV_TIME 96
+#define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
+#define KVM_CAP_ENABLE_CAP_VM 98
+#define KVM_CAP_S390_IRQCHIP 99
+#define KVM_CAP_IOEVENTFD_NO_LENGTH 100
+#define KVM_CAP_VM_ATTRIBUTES 101
+#define KVM_CAP_ARM_PSCI_0_2 102
+#define KVM_CAP_PPC_FIXUP_HCALL 103
+#define KVM_CAP_PPC_ENABLE_HCALL 104
+#define KVM_CAP_CHECK_EXTENSION_VM 105
+#define KVM_CAP_S390_USER_SIGP 106
+#define KVM_CAP_S390_VECTOR_REGISTERS 107
+#define KVM_CAP_S390_MEM_OP 108
+#define KVM_CAP_S390_USER_STSI 109
+#define KVM_CAP_S390_SKEYS 110
+#define KVM_CAP_MIPS_FPU 111
+#define KVM_CAP_MIPS_MSA 112
+#define KVM_CAP_S390_INJECT_IRQ 113
+#define KVM_CAP_S390_IRQ_STATE 114
+#define KVM_CAP_PPC_HWRNG 115
+#define KVM_CAP_DISABLE_QUIRKS 116
+#define KVM_CAP_X86_SMM 117
+#define KVM_CAP_MULTI_ADDRESS_SPACE 118
+#define KVM_CAP_GUEST_DEBUG_HW_BPS 119
+#define KVM_CAP_GUEST_DEBUG_HW_WPS 120
+#define KVM_CAP_SPLIT_IRQCHIP 121
+#define KVM_CAP_IOEVENTFD_ANY_LENGTH 122
+#define KVM_CAP_HYPERV_SYNIC 123
+#define KVM_CAP_S390_RI 124
+#define KVM_CAP_SPAPR_TCE_64 125
+#define KVM_CAP_ARM_PMU_V3 126
+#define KVM_CAP_VCPU_ATTRIBUTES 127
+#define KVM_CAP_MAX_VCPU_ID 128
+#define KVM_CAP_X2APIC_API 129
+#define KVM_CAP_S390_USER_INSTR0 130
+#define KVM_CAP_MSI_DEVID 131
+#define KVM_CAP_PPC_HTM 132
+#define KVM_CAP_SPAPR_RESIZE_HPT 133
+#define KVM_CAP_PPC_MMU_RADIX 134
+#define KVM_CAP_PPC_MMU_HASH_V3 135
+#define KVM_CAP_IMMEDIATE_EXIT 136
+#define KVM_CAP_MIPS_VZ 137
+#define KVM_CAP_MIPS_TE 138
+#define KVM_CAP_MIPS_64BIT 139
+#define KVM_CAP_S390_GS 140
+#define KVM_CAP_S390_AIS 141
+#define KVM_CAP_SPAPR_TCE_VFIO 142
+#define KVM_CAP_X86_DISABLE_EXITS 143
+#define KVM_CAP_ARM_USER_IRQ 144
+#define KVM_CAP_S390_CMMA_MIGRATION 145
+#define KVM_CAP_PPC_FWNMI 146
+#define KVM_CAP_PPC_SMT_POSSIBLE 147
+#define KVM_CAP_HYPERV_SYNIC2 148
+#define KVM_CAP_HYPERV_VP_INDEX 149
+#define KVM_CAP_S390_AIS_MIGRATION 150
+#define KVM_CAP_PPC_GET_CPU_CHAR 151
+#define KVM_CAP_S390_BPB 152
+#define KVM_CAP_GET_MSR_FEATURES 153
+#define KVM_CAP_HYPERV_EVENTFD 154
+#define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
+#define KVM_CAP_NESTED_STATE 157
+#define KVM_CAP_ARM_INJECT_SERROR_ESR 158
+#define KVM_CAP_MSR_PLATFORM_INFO 159
+#define KVM_CAP_PPC_NESTED_HV 160
+#define KVM_CAP_HYPERV_SEND_IPI 161
+#define KVM_CAP_COALESCED_PIO 162
+#define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163
+#define KVM_CAP_EXCEPTION_PAYLOAD 164
+#define KVM_CAP_ARM_VM_IPA_SIZE 165
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 /* Obsolete */
+#define KVM_CAP_HYPERV_CPUID 167
+#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168
+#define KVM_CAP_PPC_IRQ_XIVE 169
+#define KVM_CAP_ARM_SVE 170
+#define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
+#define KVM_CAP_ARM_PTRAUTH_GENERIC 172
+#define KVM_CAP_PMU_EVENT_FILTER 173
+
+#ifdef KVM_CAP_IRQ_ROUTING
+
+struct kvm_irq_routing_irqchip {
+ __u32 irqchip;
+ __u32 pin;
+};
+
+struct kvm_irq_routing_msi {
+ __u32 address_lo;
+ __u32 address_hi;
+ __u32 data;
+ union {
+ __u32 pad;
+ __u32 devid;
+ };
+};
+
+struct kvm_irq_routing_s390_adapter {
+ __u64 ind_addr;
+ __u64 summary_addr;
+ __u64 ind_offset;
+ __u32 summary_offset;
+ __u32 adapter_id;
+};
+
+struct kvm_irq_routing_hv_sint {
+ __u32 vcpu;
+ __u32 sint;
+};
+
+/* gsi routing entry types */
+#define KVM_IRQ_ROUTING_IRQCHIP 1
+#define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
+#define KVM_IRQ_ROUTING_HV_SINT 4
+
+struct kvm_irq_routing_entry {
+ __u32 gsi;
+ __u32 type;
+ __u32 flags;
+ __u32 pad;
+ union {
+ struct kvm_irq_routing_irqchip irqchip;
+ struct kvm_irq_routing_msi msi;
+ struct kvm_irq_routing_s390_adapter adapter;
+ struct kvm_irq_routing_hv_sint hv_sint;
+ __u32 pad[8];
+ } u;
+};
+
+struct kvm_irq_routing {
+ __u32 nr;
+ __u32 flags;
+ struct kvm_irq_routing_entry entries[0];
+};
+
+#endif
+
+#ifdef KVM_CAP_MCE
+/* x86 MCE */
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+#endif
+
+#ifdef KVM_CAP_XEN_HVM
+struct kvm_xen_hvm_config {
+ __u32 flags;
+ __u32 msr;
+ __u64 blob_addr_32;
+ __u64 blob_addr_64;
+ __u8 blob_size_32;
+ __u8 blob_size_64;
+ __u8 pad2[30];
+};
+#endif
+
+#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+/*
+ * Available with KVM_CAP_IRQFD_RESAMPLE
+ *
+ * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
+ * the irqfd to operate in resampling mode for level triggered interrupt
+ * emulation. See Documentation/virt/kvm/api.txt.
+ */
+#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
+
+struct kvm_irqfd {
+ __u32 fd;
+ __u32 gsi;
+ __u32 flags;
+ __u32 resamplefd;
+ __u8 pad[16];
+};
+
+/* For KVM_CAP_ADJUST_CLOCK */
+
+/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */
+#define KVM_CLOCK_TSC_STABLE 2
+
+struct kvm_clock_data {
+ __u64 clock;
+ __u32 flags;
+ __u32 pad[9];
+};
+
+/* For KVM_CAP_SW_TLB */
+
+#define KVM_MMU_FSL_BOOKE_NOHV 0
+#define KVM_MMU_FSL_BOOKE_HV 1
+
+struct kvm_config_tlb {
+ __u64 params;
+ __u64 array;
+ __u32 mmu_type;
+ __u32 array_len;
+};
+
+struct kvm_dirty_tlb {
+ __u64 bitmap;
+ __u32 num_dirty;
+};
+
+/* Available with KVM_CAP_ONE_REG */
+
+#define KVM_REG_ARCH_MASK 0xff00000000000000ULL
+#define KVM_REG_GENERIC 0x0000000000000000ULL
+
+/*
+ * Architecture specific registers are to be defined in arch headers and
+ * ORed with the arch identifier.
+ */
+#define KVM_REG_PPC 0x1000000000000000ULL
+#define KVM_REG_X86 0x2000000000000000ULL
+#define KVM_REG_IA64 0x3000000000000000ULL
+#define KVM_REG_ARM 0x4000000000000000ULL
+#define KVM_REG_S390 0x5000000000000000ULL
+#define KVM_REG_ARM64 0x6000000000000000ULL
+#define KVM_REG_MIPS 0x7000000000000000ULL
+
+#define KVM_REG_SIZE_SHIFT 52
+#define KVM_REG_SIZE_MASK 0x00f0000000000000ULL
+#define KVM_REG_SIZE_U8 0x0000000000000000ULL
+#define KVM_REG_SIZE_U16 0x0010000000000000ULL
+#define KVM_REG_SIZE_U32 0x0020000000000000ULL
+#define KVM_REG_SIZE_U64 0x0030000000000000ULL
+#define KVM_REG_SIZE_U128 0x0040000000000000ULL
+#define KVM_REG_SIZE_U256 0x0050000000000000ULL
+#define KVM_REG_SIZE_U512 0x0060000000000000ULL
+#define KVM_REG_SIZE_U1024 0x0070000000000000ULL
+#define KVM_REG_SIZE_U2048 0x0080000000000000ULL
+
+struct kvm_reg_list {
+ __u64 n; /* number of regs */
+ __u64 reg[0];
+};
+
+struct kvm_one_reg {
+ __u64 id;
+ __u64 addr;
+};
+
+#define KVM_MSI_VALID_DEVID (1U << 0)
+struct kvm_msi {
+ __u32 address_lo;
+ __u32 address_hi;
+ __u32 data;
+ __u32 flags;
+ __u32 devid;
+ __u8 pad[12];
+};
+
+struct kvm_arm_device_addr {
+ __u64 id;
+ __u64 addr;
+};
+
+/*
+ * Device control API, available with KVM_CAP_DEVICE_CTRL
+ */
+#define KVM_CREATE_DEVICE_TEST 1
+
+struct kvm_create_device {
+ __u32 type; /* in: KVM_DEV_TYPE_xxx */
+ __u32 fd; /* out: device handle */
+ __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */
+};
+
+struct kvm_device_attr {
+ __u32 flags; /* no flags currently defined */
+ __u32 group; /* device-defined */
+ __u64 attr; /* group-defined */
+ __u64 addr; /* userspace address of attr data */
+};
+
+#define KVM_DEV_VFIO_GROUP 1
+#define KVM_DEV_VFIO_GROUP_ADD 1
+#define KVM_DEV_VFIO_GROUP_DEL 2
+#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE 3
+
+enum kvm_device_type {
+ KVM_DEV_TYPE_FSL_MPIC_20 = 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20 KVM_DEV_TYPE_FSL_MPIC_20
+ KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42 KVM_DEV_TYPE_FSL_MPIC_42
+ KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS KVM_DEV_TYPE_XICS
+ KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO KVM_DEV_TYPE_VFIO
+ KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2 KVM_DEV_TYPE_ARM_VGIC_V2
+ KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC
+ KVM_DEV_TYPE_ARM_VGIC_V3,
+#define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3
+ KVM_DEV_TYPE_ARM_VGIC_ITS,
+#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS
+ KVM_DEV_TYPE_XIVE,
+#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE
+ KVM_DEV_TYPE_MAX,
+};
+
+struct kvm_vfio_spapr_tce {
+ __s32 groupfd;
+ __s32 tablefd;
+};
+
+/*
+ * ioctls for VM fds
+ */
+#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region)
+/*
+ * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
+ * a vcpu fd.
+ */
+#define KVM_CREATE_VCPU _IO(KVMIO, 0x41)
+#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log)
+/* KVM_SET_MEMORY_ALIAS is obsolete: */
+#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias)
+#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44)
+#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45)
+#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \
+ struct kvm_userspace_memory_region)
+#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47)
+#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64)
+
+/* enable ucontrol for s390 */
+struct kvm_s390_ucas_mapping {
+ __u64 user_addr;
+ __u64 vcpu_addr;
+ __u64 length;
+};
+#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping)
+#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping)
+#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long)
+
+/* Device model IOC */
+#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60)
+#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level)
+#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip)
+#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip)
+#define KVM_CREATE_PIT _IO(KVMIO, 0x64)
+#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state)
+#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state)
+#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level)
+#define KVM_REGISTER_COALESCED_MMIO \
+ _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone)
+#define KVM_UNREGISTER_COALESCED_MMIO \
+ _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone)
+#define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \
+ struct kvm_assigned_pci_dev)
+#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing)
+/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
+#define KVM_ASSIGN_IRQ __KVM_DEPRECATED_VM_R_0x70
+#define KVM_ASSIGN_DEV_IRQ _IOW(KVMIO, 0x70, struct kvm_assigned_irq)
+#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71)
+#define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \
+ struct kvm_assigned_pci_dev)
+#define KVM_ASSIGN_SET_MSIX_NR _IOW(KVMIO, 0x73, \
+ struct kvm_assigned_msix_nr)
+#define KVM_ASSIGN_SET_MSIX_ENTRY _IOW(KVMIO, 0x74, \
+ struct kvm_assigned_msix_entry)
+#define KVM_DEASSIGN_DEV_IRQ _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
+#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd)
+#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config)
+#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78)
+#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd)
+#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config)
+#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data)
+#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data)
+/* Available with KVM_CAP_PIT_STATE2 */
+#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2)
+#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2)
+/* Available with KVM_CAP_PPC_GET_PVINFO */
+#define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo)
+/* Available with KVM_CAP_TSC_CONTROL */
+#define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2)
+#define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3)
+/* Available with KVM_CAP_PCI_2_3 */
+#define KVM_ASSIGN_SET_INTX_MASK _IOW(KVMIO, 0xa4, \
+ struct kvm_assigned_pci_dev)
+/* Available with KVM_CAP_SIGNAL_MSI */
+#define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi)
+/* Available with KVM_CAP_PPC_GET_SMMU_INFO */
+#define KVM_PPC_GET_SMMU_INFO _IOR(KVMIO, 0xa6, struct kvm_ppc_smmu_info)
+/* Available with KVM_CAP_PPC_ALLOC_HTAB */
+#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32)
+#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce)
+#define KVM_CREATE_SPAPR_TCE_64 _IOW(KVMIO, 0xa8, \
+ struct kvm_create_spapr_tce_64)
+/* Available with KVM_CAP_RMA */
+#define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_PPC_HTAB_FD */
+#define KVM_PPC_GET_HTAB_FD _IOW(KVMIO, 0xaa, struct kvm_get_htab_fd)
+/* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */
+#define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr)
+/* Available with KVM_CAP_PPC_RTAS */
+#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO, 0xac, struct kvm_rtas_token_args)
+/* Available with KVM_CAP_SPAPR_RESIZE_HPT */
+#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
+#define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
+/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
+#define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg)
+/* Available with KVM_CAP_PPC_RADIX_MMU */
+#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info)
+/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
+#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char)
+/* Available with KVM_CAP_PMU_EVENT_FILTER */
+#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter)
+
+/* ioctl for vm fd */
+#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device)
+
+/* ioctls for fds returned by KVM_CREATE_DEVICE */
+#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xe1, struct kvm_device_attr)
+#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xe2, struct kvm_device_attr)
+#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xe3, struct kvm_device_attr)
+
+/*
+ * ioctls for vcpu fds
+ */
+#define KVM_RUN _IO(KVMIO, 0x80)
+#define KVM_GET_REGS _IOR(KVMIO, 0x81, struct kvm_regs)
+#define KVM_SET_REGS _IOW(KVMIO, 0x82, struct kvm_regs)
+#define KVM_GET_SREGS _IOR(KVMIO, 0x83, struct kvm_sregs)
+#define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs)
+#define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation)
+#define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt)
+/* KVM_DEBUG_GUEST is no longer supported, use KVM_SET_GUEST_DEBUG instead */
+#define KVM_DEBUG_GUEST __KVM_DEPRECATED_VCPU_W_0x87
+#define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs)
+#define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs)
+#define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid)
+#define KVM_SET_SIGNAL_MASK _IOW(KVMIO, 0x8b, struct kvm_signal_mask)
+#define KVM_GET_FPU _IOR(KVMIO, 0x8c, struct kvm_fpu)
+#define KVM_SET_FPU _IOW(KVMIO, 0x8d, struct kvm_fpu)
+#define KVM_GET_LAPIC _IOR(KVMIO, 0x8e, struct kvm_lapic_state)
+#define KVM_SET_LAPIC _IOW(KVMIO, 0x8f, struct kvm_lapic_state)
+#define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2)
+#define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl)
+/* Available with KVM_CAP_VAPIC */
+#define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr)
+/* valid for virtual machine (for floating interrupt)_and_ vcpu */
+#define KVM_S390_INTERRUPT _IOW(KVMIO, 0x94, struct kvm_s390_interrupt)
+/* store status for s390 */
+#define KVM_S390_STORE_STATUS_NOADDR (-1ul)
+#define KVM_S390_STORE_STATUS_PREFIXED (-2ul)
+#define KVM_S390_STORE_STATUS _IOW(KVMIO, 0x95, unsigned long)
+/* initial ipl psw for s390 */
+#define KVM_S390_SET_INITIAL_PSW _IOW(KVMIO, 0x96, struct kvm_s390_psw)
+/* initial reset for s390 */
+#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97)
+#define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state)
+#define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state)
+/* Available with KVM_CAP_USER_NMI */
+#define KVM_NMI _IO(KVMIO, 0x9a)
+/* Available with KVM_CAP_SET_GUEST_DEBUG */
+#define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug)
+/* MCE for x86 */
+#define KVM_X86_SETUP_MCE _IOW(KVMIO, 0x9c, __u64)
+#define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO, 0x9d, __u64)
+#define KVM_X86_SET_MCE _IOW(KVMIO, 0x9e, struct kvm_x86_mce)
+/* Available with KVM_CAP_VCPU_EVENTS */
+#define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events)
+#define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events)
+/* Available with KVM_CAP_DEBUGREGS */
+#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs)
+#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs)
+/*
+ * vcpu version available with KVM_ENABLE_CAP
+ * vm version available with KVM_CAP_ENABLE_CAP_VM
+ */
+#define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap)
+/* Available with KVM_CAP_XSAVE */
+#define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct kvm_xsave)
+#define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct kvm_xsave)
+/* Available with KVM_CAP_XCRS */
+#define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs)
+#define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs)
+/* Available with KVM_CAP_SW_TLB */
+#define KVM_DIRTY_TLB _IOW(KVMIO, 0xaa, struct kvm_dirty_tlb)
+/* Available with KVM_CAP_ONE_REG */
+#define KVM_GET_ONE_REG _IOW(KVMIO, 0xab, struct kvm_one_reg)
+#define KVM_SET_ONE_REG _IOW(KVMIO, 0xac, struct kvm_one_reg)
+/* VM is being stopped by host */
+#define KVM_KVMCLOCK_CTRL _IO(KVMIO, 0xad)
+#define KVM_ARM_VCPU_INIT _IOW(KVMIO, 0xae, struct kvm_vcpu_init)
+#define KVM_ARM_PREFERRED_TARGET _IOR(KVMIO, 0xaf, struct kvm_vcpu_init)
+#define KVM_GET_REG_LIST _IOWR(KVMIO, 0xb0, struct kvm_reg_list)
+/* Available with KVM_CAP_S390_MEM_OP */
+#define KVM_S390_MEM_OP _IOW(KVMIO, 0xb1, struct kvm_s390_mem_op)
+/* Available with KVM_CAP_S390_SKEYS */
+#define KVM_S390_GET_SKEYS _IOW(KVMIO, 0xb2, struct kvm_s390_skeys)
+#define KVM_S390_SET_SKEYS _IOW(KVMIO, 0xb3, struct kvm_s390_skeys)
+/* Available with KVM_CAP_S390_INJECT_IRQ */
+#define KVM_S390_IRQ _IOW(KVMIO, 0xb4, struct kvm_s390_irq)
+/* Available with KVM_CAP_S390_IRQ_STATE */
+#define KVM_S390_SET_IRQ_STATE _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state)
+#define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state)
+/* Available with KVM_CAP_X86_SMM */
+#define KVM_SMI _IO(KVMIO, 0xb7)
+/* Available with KVM_CAP_S390_CMMA_MIGRATION */
+#define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
+#define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
+/* Memory Encryption Commands */
+#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long)
+
+struct kvm_enc_region {
+ __u64 addr;
+ __u64 size;
+};
+
+#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region)
+#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+
+/* Available with KVM_CAP_HYPERV_EVENTFD */
+#define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd)
+
+/* Available with KVM_CAP_NESTED_STATE */
+#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state)
+#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state)
+
+/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
+#define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
+
+/* Available with KVM_CAP_HYPERV_CPUID */
+#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
+
+/* Available with KVM_CAP_ARM_SVE */
+#define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int)
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+ /* Guest initialization commands */
+ KVM_SEV_INIT = 0,
+ KVM_SEV_ES_INIT,
+ /* Guest launch commands */
+ KVM_SEV_LAUNCH_START,
+ KVM_SEV_LAUNCH_UPDATE_DATA,
+ KVM_SEV_LAUNCH_UPDATE_VMSA,
+ KVM_SEV_LAUNCH_SECRET,
+ KVM_SEV_LAUNCH_MEASURE,
+ KVM_SEV_LAUNCH_FINISH,
+ /* Guest migration commands (outgoing) */
+ KVM_SEV_SEND_START,
+ KVM_SEV_SEND_UPDATE_DATA,
+ KVM_SEV_SEND_UPDATE_VMSA,
+ KVM_SEV_SEND_FINISH,
+ /* Guest migration commands (incoming) */
+ KVM_SEV_RECEIVE_START,
+ KVM_SEV_RECEIVE_UPDATE_DATA,
+ KVM_SEV_RECEIVE_UPDATE_VMSA,
+ KVM_SEV_RECEIVE_FINISH,
+ /* Guest status and debug commands */
+ KVM_SEV_GUEST_STATUS,
+ KVM_SEV_DBG_DECRYPT,
+ KVM_SEV_DBG_ENCRYPT,
+ /* Guest certificates commands */
+ KVM_SEV_CERT_EXPORT,
+
+ KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+ __u32 id;
+ __u64 data;
+ __u32 error;
+ __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+ __u32 handle;
+ __u32 policy;
+ __u64 dh_uaddr;
+ __u32 dh_len;
+ __u64 session_uaddr;
+ __u32 session_len;
+};
+
+struct kvm_sev_launch_update_data {
+ __u64 uaddr;
+ __u32 len;
+};
+
+
+struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr;
+ __u32 hdr_len;
+ __u64 guest_uaddr;
+ __u32 guest_len;
+ __u64 trans_uaddr;
+ __u32 trans_len;
+};
+
+struct kvm_sev_launch_measure {
+ __u64 uaddr;
+ __u32 len;
+};
+
+struct kvm_sev_guest_status {
+ __u32 handle;
+ __u32 policy;
+ __u32 state;
+};
+
+struct kvm_sev_dbg {
+ __u64 src_uaddr;
+ __u64 dst_uaddr;
+ __u32 len;
+};
+
+#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
+#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
+#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
+
+struct kvm_assigned_pci_dev {
+ __u32 assigned_dev_id;
+ __u32 busnr;
+ __u32 devfn;
+ __u32 flags;
+ __u32 segnr;
+ union {
+ __u32 reserved[11];
+ };
+};
+
+#define KVM_DEV_IRQ_HOST_INTX (1 << 0)
+#define KVM_DEV_IRQ_HOST_MSI (1 << 1)
+#define KVM_DEV_IRQ_HOST_MSIX (1 << 2)
+
+#define KVM_DEV_IRQ_GUEST_INTX (1 << 8)
+#define KVM_DEV_IRQ_GUEST_MSI (1 << 9)
+#define KVM_DEV_IRQ_GUEST_MSIX (1 << 10)
+
+#define KVM_DEV_IRQ_HOST_MASK 0x00ff
+#define KVM_DEV_IRQ_GUEST_MASK 0xff00
+
+struct kvm_assigned_irq {
+ __u32 assigned_dev_id;
+ __u32 host_irq; /* ignored (legacy field) */
+ __u32 guest_irq;
+ __u32 flags;
+ union {
+ __u32 reserved[12];
+ };
+};
+
+struct kvm_assigned_msix_nr {
+ __u32 assigned_dev_id;
+ __u16 entry_nr;
+ __u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV 256
+struct kvm_assigned_msix_entry {
+ __u32 assigned_dev_id;
+ __u32 gsi;
+ __u16 entry; /* The index of entry in the MSI-X table */
+ __u16 padding[3];
+};
+
+#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+
+/* Available with KVM_CAP_ARM_USER_IRQ */
+
+/* Bits for run->s.regs.device_irq_level */
+#define KVM_ARM_DEV_EL1_VTIMER (1 << 0)
+#define KVM_ARM_DEV_EL1_PTIMER (1 << 1)
+#define KVM_ARM_DEV_PMU (1 << 2)
+
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
+#endif /* __LINUX_KVM_H */
diff --git a/kvmtool/include/linux/list.h b/kvmtool/include/linux/list.h
new file mode 100644
index 0000000..2e92b3f
--- /dev/null
+++ b/kvmtool/include/linux/list.h
@@ -0,0 +1,743 @@
+#ifndef _LINUX_LIST_H
+#define _LINUX_LIST_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/const.h>
+#include <linux/kernel.h>
+
+/*
+ * Simple doubly linked list implementation.
+ *
+ * Some of the internal functions ("__xxx") are useful when
+ * manipulating whole lists rather than single entries, as
+ * sometimes we already know the next/prev entries and we can
+ * generate better code by using them directly rather than
+ * using the generic single-entry routines.
+ */
+
+#define LIST_HEAD_INIT(name) { &(name), &(name) }
+
+#define LIST_HEAD(name) \
+ struct list_head name = LIST_HEAD_INIT(name)
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+ list->next = list;
+ list->prev = list;
+}
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_add(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ next->prev = new;
+ new->next = next;
+ new->prev = prev;
+ prev->next = new;
+}
+#else
+extern void __list_add(struct list_head *new,
+ struct list_head *prev,
+ struct list_head *next);
+#endif
+
+/**
+ * list_add - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ */
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head, head->next);
+}
+
+
+/**
+ * list_add_tail - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head.
+ * This is useful for implementing queues.
+ */
+static inline void list_add_tail(struct list_head *new, struct list_head *head)
+{
+ __list_add(new, head->prev, head);
+}
+
+/*
+ * Delete a list entry by making the prev/next entries
+ * point to each other.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+static inline void __list_del(struct list_head * prev, struct list_head * next)
+{
+ next->prev = prev;
+ prev->next = next;
+}
+
+/**
+ * list_del - deletes entry from list.
+ * @entry: the element to delete from the list.
+ * Note: list_empty() on entry does not return true after this, the entry is
+ * in an undefined state.
+ */
+#ifndef CONFIG_DEBUG_LIST
+static inline void __list_del_entry(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+}
+
+static inline void list_del(struct list_head *entry)
+{
+ __list_del(entry->prev, entry->next);
+ entry->next = NULL;
+ entry->prev = NULL;
+}
+#else
+extern void __list_del_entry(struct list_head *entry);
+extern void list_del(struct list_head *entry);
+#endif
+
+/**
+ * list_replace - replace old entry by new one
+ * @old : the element to be replaced
+ * @new : the new element to insert
+ *
+ * If @old was empty, it will be overwritten.
+ */
+static inline void list_replace(struct list_head *old,
+ struct list_head *new)
+{
+ new->next = old->next;
+ new->next->prev = new;
+ new->prev = old->prev;
+ new->prev->next = new;
+}
+
+static inline void list_replace_init(struct list_head *old,
+ struct list_head *new)
+{
+ list_replace(old, new);
+ INIT_LIST_HEAD(old);
+}
+
+/**
+ * list_del_init - deletes entry from list and reinitialize it.
+ * @entry: the element to delete from the list.
+ */
+static inline void list_del_init(struct list_head *entry)
+{
+ __list_del_entry(entry);
+ INIT_LIST_HEAD(entry);
+}
+
+/**
+ * list_move - delete from one list and add as another's head
+ * @list: the entry to move
+ * @head: the head that will precede our entry
+ */
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+ __list_del_entry(list);
+ list_add(list, head);
+}
+
+/**
+ * list_move_tail - delete from one list and add as another's tail
+ * @list: the entry to move
+ * @head: the head that will follow our entry
+ */
+static inline void list_move_tail(struct list_head *list,
+ struct list_head *head)
+{
+ __list_del_entry(list);
+ list_add_tail(list, head);
+}
+
+/**
+ * list_is_last - tests whether @list is the last entry in list @head
+ * @list: the entry to test
+ * @head: the head of the list
+ */
+static inline int list_is_last(const struct list_head *list,
+ const struct list_head *head)
+{
+ return list->next == head;
+}
+
+/**
+ * list_empty - tests whether a list is empty
+ * @head: the list to test.
+ */
+static inline int list_empty(const struct list_head *head)
+{
+ return head->next == head;
+}
+
+/**
+ * list_empty_careful - tests whether a list is empty and not being modified
+ * @head: the list to test
+ *
+ * Description:
+ * tests whether a list is empty _and_ checks that no other CPU might be
+ * in the process of modifying either member (next or prev)
+ *
+ * NOTE: using list_empty_careful() without synchronization
+ * can only be safe if the only activity that can happen
+ * to the list entry is list_del_init(). Eg. it cannot be used
+ * if another CPU could re-list_add() it.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+ struct list_head *next = head->next;
+ return (next == head) && (next == head->prev);
+}
+
+/**
+ * list_rotate_left - rotate the list to the left
+ * @head: the head of the list
+ */
+static inline void list_rotate_left(struct list_head *head)
+{
+ struct list_head *first;
+
+ if (!list_empty(head)) {
+ first = head->next;
+ list_move_tail(first, head);
+ }
+}
+
+/**
+ * list_is_singular - tests whether a list has just one entry.
+ * @head: the list to test.
+ */
+static inline int list_is_singular(const struct list_head *head)
+{
+ return !list_empty(head) && (head->next == head->prev);
+}
+
+static inline void __list_cut_position(struct list_head *list,
+ struct list_head *head, struct list_head *entry)
+{
+ struct list_head *new_first = entry->next;
+ list->next = head->next;
+ list->next->prev = list;
+ list->prev = entry;
+ entry->next = list;
+ head->next = new_first;
+ new_first->prev = head;
+}
+
+/**
+ * list_cut_position - cut a list into two
+ * @list: a new list to add all removed entries
+ * @head: a list with entries
+ * @entry: an entry within head, could be the head itself
+ * and if so we won't cut the list
+ *
+ * This helper moves the initial part of @head, up to and
+ * including @entry, from @head to @list. You should
+ * pass on @entry an element you know is on @head. @list
+ * should be an empty list or a list you do not care about
+ * losing its data.
+ *
+ */
+static inline void list_cut_position(struct list_head *list,
+ struct list_head *head, struct list_head *entry)
+{
+ if (list_empty(head))
+ return;
+ if (list_is_singular(head) &&
+ (head->next != entry && head != entry))
+ return;
+ if (entry == head)
+ INIT_LIST_HEAD(list);
+ else
+ __list_cut_position(list, head, entry);
+}
+
+static inline void __list_splice(const struct list_head *list,
+ struct list_head *prev,
+ struct list_head *next)
+{
+ struct list_head *first = list->next;
+ struct list_head *last = list->prev;
+
+ first->prev = prev;
+ prev->next = first;
+
+ last->next = next;
+ next->prev = last;
+}
+
+/**
+ * list_splice - join two lists, this is designed for stacks
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice(const struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list))
+ __list_splice(list, head, head->next);
+}
+
+/**
+ * list_splice_tail - join two lists, each list being a queue
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ */
+static inline void list_splice_tail(struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list))
+ __list_splice(list, head->prev, head);
+}
+
+/**
+ * list_splice_init - join two lists and reinitialise the emptied list.
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_init(struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list)) {
+ __list_splice(list, head, head->next);
+ INIT_LIST_HEAD(list);
+ }
+}
+
+/**
+ * list_splice_tail_init - join two lists and reinitialise the emptied list
+ * @list: the new list to add.
+ * @head: the place to add it in the first list.
+ *
+ * Each of the lists is a queue.
+ * The list at @list is reinitialised
+ */
+static inline void list_splice_tail_init(struct list_head *list,
+ struct list_head *head)
+{
+ if (!list_empty(list)) {
+ __list_splice(list, head->prev, head);
+ INIT_LIST_HEAD(list);
+ }
+}
+
+/**
+ * list_entry - get the struct for this entry
+ * @ptr: the &struct list_head pointer.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_entry(ptr, type, member) \
+ container_of(ptr, type, member)
+
+/**
+ * list_first_entry - get the first element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_first_entry(ptr, type, member) \
+ list_entry((ptr)->next, type, member)
+
+/**
+ * list_last_entry - get the last element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+/**
+ * list_first_entry_or_null - get the first element from a list
+ * @ptr: the list head to take the element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note that if the list is empty, it returns NULL.
+ */
+#define list_first_entry_or_null(ptr, type, member) \
+ (!list_empty(ptr) ? list_first_entry(ptr, type, member) : NULL)
+
+/**
+ * list_next_entry - get the next element in list
+ * @pos: the type * to cursor
+ * @member: the name of the list_head within the struct.
+ */
+#define list_next_entry(pos, member) \
+ list_entry((pos)->member.next, typeof(*(pos)), member)
+
+/**
+ * list_prev_entry - get the prev element in list
+ * @pos: the type * to cursor
+ * @member: the name of the list_head within the struct.
+ */
+#define list_prev_entry(pos, member) \
+ list_entry((pos)->member.prev, typeof(*(pos)), member)
+
+/**
+ * list_for_each - iterate over a list
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @head: the head for your list.
+ */
+#define list_for_each(pos, head) \
+ for (pos = (head)->next; pos != (head); pos = pos->next)
+
+/**
+ * list_for_each_prev - iterate over a list backwards
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @head: the head for your list.
+ */
+#define list_for_each_prev(pos, head) \
+ for (pos = (head)->prev; pos != (head); pos = pos->prev)
+
+/**
+ * list_for_each_safe - iterate over a list safe against removal of list entry
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @n: another &struct list_head to use as temporary storage
+ * @head: the head for your list.
+ */
+#define list_for_each_safe(pos, n, head) \
+ for (pos = (head)->next, n = pos->next; pos != (head); \
+ pos = n, n = pos->next)
+
+/**
+ * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry
+ * @pos: the &struct list_head to use as a loop cursor.
+ * @n: another &struct list_head to use as temporary storage
+ * @head: the head for your list.
+ */
+#define list_for_each_prev_safe(pos, n, head) \
+ for (pos = (head)->prev, n = pos->prev; \
+ pos != (head); \
+ pos = n, n = pos->prev)
+
+/**
+ * list_for_each_entry - iterate over list of given type
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_for_each_entry(pos, head, member) \
+ for (pos = list_first_entry(head, typeof(*pos), member); \
+ &pos->member != (head); \
+ pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_reverse - iterate backwards over list of given type.
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_for_each_entry_reverse(pos, head, member) \
+ for (pos = list_last_entry(head, typeof(*pos), member); \
+ &pos->member != (head); \
+ pos = list_prev_entry(pos, member))
+
+/**
+ * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue()
+ * @pos: the type * to use as a start point
+ * @head: the head of the list
+ * @member: the name of the list_head within the struct.
+ *
+ * Prepares a pos entry for use as a start point in list_for_each_entry_continue().
+ */
+#define list_prepare_entry(pos, head, member) \
+ ((pos) ? : list_entry(head, typeof(*pos), member))
+
+/**
+ * list_for_each_entry_continue - continue iteration over list of given type
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Continue to iterate over list of given type, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue(pos, head, member) \
+ for (pos = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_continue_reverse - iterate backwards from the given point
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Start to iterate over list of given type backwards, continuing after
+ * the current position.
+ */
+#define list_for_each_entry_continue_reverse(pos, head, member) \
+ for (pos = list_prev_entry(pos, member); \
+ &pos->member != (head); \
+ pos = list_prev_entry(pos, member))
+
+/**
+ * list_for_each_entry_from - iterate over list of given type from the current point
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing from current position.
+ */
+#define list_for_each_entry_from(pos, head, member) \
+ for (; &pos->member != (head); \
+ pos = list_next_entry(pos, member))
+
+/**
+ * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ */
+#define list_for_each_entry_safe(pos, n, head, member) \
+ for (pos = list_first_entry(head, typeof(*pos), member), \
+ n = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_continue - continue list iteration safe against removal
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate over list of given type, continuing after current point,
+ * safe against removal of list entry.
+ */
+#define list_for_each_entry_safe_continue(pos, n, head, member) \
+ for (pos = list_next_entry(pos, member), \
+ n = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_from - iterate over list from current point safe against removal
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate over list of given type from current point, safe against
+ * removal of list entry.
+ */
+#define list_for_each_entry_safe_from(pos, n, head, member) \
+ for (n = list_next_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_next_entry(n, member))
+
+/**
+ * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal
+ * @pos: the type * to use as a loop cursor.
+ * @n: another type * to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the list_head within the struct.
+ *
+ * Iterate backwards over list of given type, safe against removal
+ * of list entry.
+ */
+#define list_for_each_entry_safe_reverse(pos, n, head, member) \
+ for (pos = list_last_entry(head, typeof(*pos), member), \
+ n = list_prev_entry(pos, member); \
+ &pos->member != (head); \
+ pos = n, n = list_prev_entry(n, member))
+
+/**
+ * list_safe_reset_next - reset a stale list_for_each_entry_safe loop
+ * @pos: the loop cursor used in the list_for_each_entry_safe loop
+ * @n: temporary storage used in list_for_each_entry_safe
+ * @member: the name of the list_head within the struct.
+ *
+ * list_safe_reset_next is not safe to use in general if the list may be
+ * modified concurrently (eg. the lock is dropped in the loop body). An
+ * exception to this is if the cursor element (pos) is pinned in the list,
+ * and list_safe_reset_next is called after re-taking the lock and before
+ * completing the current iteration of the loop body.
+ */
+#define list_safe_reset_next(pos, n, member) \
+ n = list_next_entry(pos, member)
+
+/*
+ * Double linked lists with a single pointer list head.
+ * Mostly useful for hash tables where the two pointer list head is
+ * too wasteful.
+ * You lose the ability to access the tail in O(1).
+ */
+
+#define HLIST_HEAD_INIT { .first = NULL }
+#define HLIST_HEAD(name) struct hlist_head name = { .first = NULL }
+#define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL)
+static inline void INIT_HLIST_NODE(struct hlist_node *h)
+{
+ h->next = NULL;
+ h->pprev = NULL;
+}
+
+static inline int hlist_unhashed(const struct hlist_node *h)
+{
+ return !h->pprev;
+}
+
+static inline int hlist_empty(const struct hlist_head *h)
+{
+ return !h->first;
+}
+
+static inline void __hlist_del(struct hlist_node *n)
+{
+ struct hlist_node *next = n->next;
+ struct hlist_node **pprev = n->pprev;
+ *pprev = next;
+ if (next)
+ next->pprev = pprev;
+}
+
+static inline void hlist_del(struct hlist_node *n)
+{
+ __hlist_del(n);
+ n->next = NULL;
+ n->pprev = NULL;
+}
+
+static inline void hlist_del_init(struct hlist_node *n)
+{
+ if (!hlist_unhashed(n)) {
+ __hlist_del(n);
+ INIT_HLIST_NODE(n);
+ }
+}
+
+static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h)
+{
+ struct hlist_node *first = h->first;
+ n->next = first;
+ if (first)
+ first->pprev = &n->next;
+ h->first = n;
+ n->pprev = &h->first;
+}
+
+/* next must be != NULL */
+static inline void hlist_add_before(struct hlist_node *n,
+ struct hlist_node *next)
+{
+ n->pprev = next->pprev;
+ n->next = next;
+ next->pprev = &n->next;
+ *(n->pprev) = n;
+}
+
+static inline void hlist_add_behind(struct hlist_node *n,
+ struct hlist_node *prev)
+{
+ n->next = prev->next;
+ prev->next = n;
+ n->pprev = &prev->next;
+
+ if (n->next)
+ n->next->pprev = &n->next;
+}
+
+/* after that we'll appear to be on some hlist and hlist_del will work */
+static inline void hlist_add_fake(struct hlist_node *n)
+{
+ n->pprev = &n->next;
+}
+
+/*
+ * Move a list from one list head to another. Fixup the pprev
+ * reference of the first entry if it exists.
+ */
+static inline void hlist_move_list(struct hlist_head *old,
+ struct hlist_head *new)
+{
+ new->first = old->first;
+ if (new->first)
+ new->first->pprev = &new->first;
+ old->first = NULL;
+}
+
+#define hlist_entry(ptr, type, member) container_of(ptr,type,member)
+
+#define hlist_for_each(pos, head) \
+ for (pos = (head)->first; pos ; pos = pos->next)
+
+#define hlist_for_each_safe(pos, n, head) \
+ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \
+ pos = n)
+
+#define hlist_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \
+ })
+
+/**
+ * hlist_for_each_entry - iterate over list of given type
+ * @pos: the type * to use as a loop cursor.
+ * @head: the head for your list.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry(pos, head, member) \
+ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\
+ pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_continue - iterate over a hlist continuing after current point
+ * @pos: the type * to use as a loop cursor.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_continue(pos, member) \
+ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\
+ pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_from - iterate over a hlist continuing from current point
+ * @pos: the type * to use as a loop cursor.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_from(pos, member) \
+ for (; pos; \
+ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member))
+
+/**
+ * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @pos: the type * to use as a loop cursor.
+ * @n: another &struct hlist_node to use as temporary storage
+ * @head: the head for your list.
+ * @member: the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_safe(pos, n, head, member) \
+ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\
+ pos && ({ n = pos->member.next; 1; }); \
+ pos = hlist_entry_safe(n, typeof(*pos), member))
+
+#endif
diff --git a/kvmtool/include/linux/prefetch.h b/kvmtool/include/linux/prefetch.h
new file mode 100644
index 0000000..62f6788
--- /dev/null
+++ b/kvmtool/include/linux/prefetch.h
@@ -0,0 +1,6 @@
+#ifndef KVM__LINUX_PREFETCH_H
+#define KVM__LINUX_PREFETCH_H
+
+static inline void prefetch(void *a __attribute__((unused))) { }
+
+#endif
diff --git a/kvmtool/include/linux/psci.h b/kvmtool/include/linux/psci.h
new file mode 100644
index 0000000..310d83e
--- /dev/null
+++ b/kvmtool/include/linux/psci.h
@@ -0,0 +1,90 @@
+/*
+ * ARM Power State and Coordination Interface (PSCI) header
+ *
+ * This header holds common PSCI defines and macros shared
+ * by: ARM kernel, ARM64 kernel, KVM ARM/ARM64 and user space.
+ *
+ * Copyright (C) 2014 Linaro Ltd.
+ * Author: Anup Patel <anup.patel@linaro.org>
+ */
+
+#ifndef _UAPI_LINUX_PSCI_H
+#define _UAPI_LINUX_PSCI_H
+
+/*
+ * PSCI v0.1 interface
+ *
+ * The PSCI v0.1 function numbers are implementation defined.
+ *
+ * Only PSCI return values such as: SUCCESS, NOT_SUPPORTED,
+ * INVALID_PARAMS, and DENIED defined below are applicable
+ * to PSCI v0.1.
+ */
+
+/* PSCI v0.2 interface */
+#define PSCI_0_2_FN_BASE 0x84000000
+#define PSCI_0_2_FN(n) (PSCI_0_2_FN_BASE + (n))
+#define PSCI_0_2_64BIT 0x40000000
+#define PSCI_0_2_FN64_BASE \
+ (PSCI_0_2_FN_BASE + PSCI_0_2_64BIT)
+#define PSCI_0_2_FN64(n) (PSCI_0_2_FN64_BASE + (n))
+
+#define PSCI_0_2_FN_PSCI_VERSION PSCI_0_2_FN(0)
+#define PSCI_0_2_FN_CPU_SUSPEND PSCI_0_2_FN(1)
+#define PSCI_0_2_FN_CPU_OFF PSCI_0_2_FN(2)
+#define PSCI_0_2_FN_CPU_ON PSCI_0_2_FN(3)
+#define PSCI_0_2_FN_AFFINITY_INFO PSCI_0_2_FN(4)
+#define PSCI_0_2_FN_MIGRATE PSCI_0_2_FN(5)
+#define PSCI_0_2_FN_MIGRATE_INFO_TYPE PSCI_0_2_FN(6)
+#define PSCI_0_2_FN_MIGRATE_INFO_UP_CPU PSCI_0_2_FN(7)
+#define PSCI_0_2_FN_SYSTEM_OFF PSCI_0_2_FN(8)
+#define PSCI_0_2_FN_SYSTEM_RESET PSCI_0_2_FN(9)
+
+#define PSCI_0_2_FN64_CPU_SUSPEND PSCI_0_2_FN64(1)
+#define PSCI_0_2_FN64_CPU_ON PSCI_0_2_FN64(3)
+#define PSCI_0_2_FN64_AFFINITY_INFO PSCI_0_2_FN64(4)
+#define PSCI_0_2_FN64_MIGRATE PSCI_0_2_FN64(5)
+#define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU PSCI_0_2_FN64(7)
+
+/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
+#define PSCI_0_2_POWER_STATE_ID_MASK 0xffff
+#define PSCI_0_2_POWER_STATE_ID_SHIFT 0
+#define PSCI_0_2_POWER_STATE_TYPE_SHIFT 16
+#define PSCI_0_2_POWER_STATE_TYPE_MASK \
+ (0x1 << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
+#define PSCI_0_2_POWER_STATE_AFFL_SHIFT 24
+#define PSCI_0_2_POWER_STATE_AFFL_MASK \
+ (0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
+
+/* PSCI v0.2 affinity level state returned by AFFINITY_INFO */
+#define PSCI_0_2_AFFINITY_LEVEL_ON 0
+#define PSCI_0_2_AFFINITY_LEVEL_OFF 1
+#define PSCI_0_2_AFFINITY_LEVEL_ON_PENDING 2
+
+/* PSCI v0.2 multicore support in Trusted OS returned by MIGRATE_INFO_TYPE */
+#define PSCI_0_2_TOS_UP_MIGRATE 0
+#define PSCI_0_2_TOS_UP_NO_MIGRATE 1
+#define PSCI_0_2_TOS_MP 2
+
+/* PSCI version decoding (independent of PSCI version) */
+#define PSCI_VERSION_MAJOR_SHIFT 16
+#define PSCI_VERSION_MINOR_MASK \
+ ((1U << PSCI_VERSION_MAJOR_SHIFT) - 1)
+#define PSCI_VERSION_MAJOR_MASK ~PSCI_VERSION_MINOR_MASK
+#define PSCI_VERSION_MAJOR(ver) \
+ (((ver) & PSCI_VERSION_MAJOR_MASK) >> PSCI_VERSION_MAJOR_SHIFT)
+#define PSCI_VERSION_MINOR(ver) \
+ ((ver) & PSCI_VERSION_MINOR_MASK)
+
+/* PSCI return values (inclusive of all PSCI versions) */
+#define PSCI_RET_SUCCESS 0
+#define PSCI_RET_NOT_SUPPORTED -1
+#define PSCI_RET_INVALID_PARAMS -2
+#define PSCI_RET_DENIED -3
+#define PSCI_RET_ALREADY_ON -4
+#define PSCI_RET_ON_PENDING -5
+#define PSCI_RET_INTERNAL_FAILURE -6
+#define PSCI_RET_NOT_PRESENT -7
+#define PSCI_RET_DISABLED -8
+
+#endif /* _UAPI_LINUX_PSCI_H */
diff --git a/kvmtool/include/linux/rbtree.h b/kvmtool/include/linux/rbtree.h
new file mode 100644
index 0000000..33adf78
--- /dev/null
+++ b/kvmtool/include/linux/rbtree.h
@@ -0,0 +1,108 @@
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+ linux/include/linux/rbtree.h
+
+ To use rbtrees you'll have to implement your own insert and search cores.
+ This will avoid us to use callbacks and to drop drammatically performances.
+ I know it's not the cleaner way, but in C (not in C++) to get
+ performances and genericity...
+
+ See Documentation/rbtree.txt for documentation and samples.
+*/
+
+#ifndef _LINUX_RBTREE_H
+#define _LINUX_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node {
+ unsigned long __rb_parent_color;
+ struct rb_node *rb_right;
+ struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+ /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+ struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3))
+
+#define RB_ROOT { NULL, }
+#define rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root) ((root)->rb_node == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
+#define RB_EMPTY_NODE(node) \
+ ((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node) \
+ ((node)->__rb_parent_color = (unsigned long)(node))
+
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+ struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
+ struct rb_node ** rb_link)
+{
+ node->__rb_parent_color = (unsigned long)parent;
+ node->rb_left = node->rb_right = NULL;
+
+ *rb_link = node;
+}
+
+#define rb_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+ })
+
+/**
+ * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of
+ * given type safe against removal of rb_node entry
+ *
+ * @pos: the 'type *' to use as a loop cursor.
+ * @n: another 'type *' to use as temporary storage
+ * @root: 'rb_root *' of the rbtree.
+ * @field: the name of the rb_node field within 'type'.
+ */
+#define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
+ for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \
+ pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \
+ typeof(*pos), field); 1; }); \
+ pos = n)
+
+#endif /* _LINUX_RBTREE_H */
diff --git a/kvmtool/include/linux/rbtree_augmented.h b/kvmtool/include/linux/rbtree_augmented.h
new file mode 100644
index 0000000..378c5ee
--- /dev/null
+++ b/kvmtool/include/linux/rbtree_augmented.h
@@ -0,0 +1,242 @@
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+ (C) 2002 David Woodhouse <dwmw2@infradead.org>
+ (C) 2012 Michel Lespinasse <walken@google.com>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+ linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _LINUX_RBTREE_AUGMENTED_H
+#define _LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/rbtree.txt for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+ void (*propagate)(struct rb_node *node, struct rb_node *stop);
+ void (*copy)(struct rb_node *old, struct rb_node *new);
+ void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ __rb_insert_augmented(node, root, augment->rotate);
+}
+
+#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \
+ rbtype, rbaugmented, rbcompute) \
+static inline void \
+rbname ## _propagate(struct rb_node *rb, struct rb_node *stop) \
+{ \
+ while (rb != stop) { \
+ rbstruct *node = rb_entry(rb, rbstruct, rbfield); \
+ rbtype augmented = rbcompute(node); \
+ if (node->rbaugmented == augmented) \
+ break; \
+ node->rbaugmented = augmented; \
+ rb = rb_parent(&node->rbfield); \
+ } \
+} \
+static inline void \
+rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \
+{ \
+ rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \
+ rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \
+ new->rbaugmented = old->rbaugmented; \
+} \
+static void \
+rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \
+{ \
+ rbstruct *old = rb_entry(rb_old, rbstruct, rbfield); \
+ rbstruct *new = rb_entry(rb_new, rbstruct, rbfield); \
+ new->rbaugmented = old->rbaugmented; \
+ old->rbaugmented = rbcompute(old); \
+} \
+rbstatic const struct rb_augment_callbacks rbname = { \
+ rbname ## _propagate, rbname ## _copy, rbname ## _rotate \
+};
+
+
+#define RB_RED 0
+#define RB_BLACK 1
+
+#define __rb_parent(pc) ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc) ((pc) & 1)
+#define __rb_is_black(pc) __rb_color(pc)
+#define __rb_is_red(pc) (!__rb_color(pc))
+#define rb_color(rb) __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+ rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+ struct rb_node *p, int color)
+{
+ rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+ struct rb_node *parent, struct rb_root *root)
+{
+ if (parent) {
+ if (parent->rb_left == old)
+ parent->rb_left = new;
+ else
+ parent->rb_right = new;
+ } else
+ root->rb_node = new;
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+ struct rb_node *parent, *rebalance;
+ unsigned long pc;
+
+ if (!tmp) {
+ /*
+ * Case 1: node to erase has no more than 1 child (easy!)
+ *
+ * Note that if there is one child it must be red due to 5)
+ * and node must be black due to 4). We adjust colors locally
+ * so as to bypass __rb_erase_color() later on.
+ */
+ pc = node->__rb_parent_color;
+ parent = __rb_parent(pc);
+ __rb_change_child(node, child, parent, root);
+ if (child) {
+ child->__rb_parent_color = pc;
+ rebalance = NULL;
+ } else
+ rebalance = __rb_is_black(pc) ? parent : NULL;
+ tmp = parent;
+ } else if (!child) {
+ /* Still case 1, but this time the child is node->rb_left */
+ tmp->__rb_parent_color = pc = node->__rb_parent_color;
+ parent = __rb_parent(pc);
+ __rb_change_child(node, tmp, parent, root);
+ rebalance = NULL;
+ tmp = parent;
+ } else {
+ struct rb_node *successor = child, *child2;
+ tmp = child->rb_left;
+ if (!tmp) {
+ /*
+ * Case 2: node's successor is its right child
+ *
+ * (n) (s)
+ * / \ / \
+ * (x) (s) -> (x) (c)
+ * \
+ * (c)
+ */
+ parent = successor;
+ child2 = successor->rb_right;
+ augment->copy(node, successor);
+ } else {
+ /*
+ * Case 3: node's successor is leftmost under
+ * node's right child subtree
+ *
+ * (n) (s)
+ * / \ / \
+ * (x) (y) -> (x) (y)
+ * / /
+ * (p) (p)
+ * / /
+ * (s) (c)
+ * \
+ * (c)
+ */
+ do {
+ parent = successor;
+ successor = tmp;
+ tmp = tmp->rb_left;
+ } while (tmp);
+ parent->rb_left = child2 = successor->rb_right;
+ successor->rb_right = child;
+ rb_set_parent(child, successor);
+ augment->copy(node, successor);
+ augment->propagate(parent, successor);
+ }
+
+ successor->rb_left = tmp = node->rb_left;
+ rb_set_parent(tmp, successor);
+
+ pc = node->__rb_parent_color;
+ tmp = __rb_parent(pc);
+ __rb_change_child(node, successor, tmp, root);
+ if (child2) {
+ successor->__rb_parent_color = pc;
+ rb_set_parent_color(child2, parent, RB_BLACK);
+ rebalance = NULL;
+ } else {
+ unsigned long pc2 = successor->__rb_parent_color;
+ successor->__rb_parent_color = pc;
+ rebalance = __rb_is_black(pc2) ? parent : NULL;
+ }
+ tmp = successor;
+ }
+
+ augment->propagate(tmp, NULL);
+ return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+ const struct rb_augment_callbacks *augment)
+{
+ struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+ if (rebalance)
+ __rb_erase_color(rebalance, root, augment->rotate);
+}
+
+#endif /* _LINUX_RBTREE_AUGMENTED_H */
diff --git a/kvmtool/include/linux/sizes.h b/kvmtool/include/linux/sizes.h
new file mode 100644
index 0000000..ce3e815
--- /dev/null
+++ b/kvmtool/include/linux/sizes.h
@@ -0,0 +1,47 @@
+/*
+ * include/linux/sizes.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_SIZES_H__
+#define __LINUX_SIZES_H__
+
+#define SZ_1 0x00000001
+#define SZ_2 0x00000002
+#define SZ_4 0x00000004
+#define SZ_8 0x00000008
+#define SZ_16 0x00000010
+#define SZ_32 0x00000020
+#define SZ_64 0x00000040
+#define SZ_128 0x00000080
+#define SZ_256 0x00000100
+#define SZ_512 0x00000200
+
+#define SZ_1K 0x00000400
+#define SZ_2K 0x00000800
+#define SZ_4K 0x00001000
+#define SZ_8K 0x00002000
+#define SZ_16K 0x00004000
+#define SZ_32K 0x00008000
+#define SZ_64K 0x00010000
+#define SZ_128K 0x00020000
+#define SZ_256K 0x00040000
+#define SZ_512K 0x00080000
+
+#define SZ_1M 0x00100000
+#define SZ_2M 0x00200000
+#define SZ_4M 0x00400000
+#define SZ_8M 0x00800000
+#define SZ_16M 0x01000000
+#define SZ_32M 0x02000000
+#define SZ_64M 0x04000000
+#define SZ_128M 0x08000000
+#define SZ_256M 0x10000000
+#define SZ_512M 0x20000000
+
+#define SZ_1G 0x40000000
+#define SZ_2G 0x80000000
+
+#endif /* __LINUX_SIZES_H__ */
diff --git a/kvmtool/include/linux/stddef.h b/kvmtool/include/linux/stddef.h
new file mode 100644
index 0000000..39da808
--- /dev/null
+++ b/kvmtool/include/linux/stddef.h
@@ -0,0 +1,10 @@
+#ifndef _LINUX_STDDEF_H
+#define _LINUX_STDDEF_H
+
+#undef NULL
+#define NULL ((void *)0)
+
+#undef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+
+#endif
diff --git a/kvmtool/include/linux/stringify.h b/kvmtool/include/linux/stringify.h
new file mode 100644
index 0000000..841cec8
--- /dev/null
+++ b/kvmtool/include/linux/stringify.h
@@ -0,0 +1,12 @@
+#ifndef __LINUX_STRINGIFY_H
+#define __LINUX_STRINGIFY_H
+
+/* Indirect stringification. Doing two levels allows the parameter to be a
+ * macro itself. For example, compile with -DFOO=bar, __stringify(FOO)
+ * converts to "bar".
+ */
+
+#define __stringify_1(x...) #x
+#define __stringify(x...) __stringify_1(x)
+
+#endif /* !__LINUX_STRINGIFY_H */
diff --git a/kvmtool/include/linux/types.h b/kvmtool/include/linux/types.h
new file mode 100644
index 0000000..5e20f10
--- /dev/null
+++ b/kvmtool/include/linux/types.h
@@ -0,0 +1,51 @@
+#ifndef LINUX_TYPES_H
+#define LINUX_TYPES_H
+
+#include <kvm/compiler.h>
+#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */
+#include <asm/types.h>
+
+typedef __u64 u64;
+typedef __s64 s64;
+
+typedef __u32 u32;
+typedef __s32 s32;
+
+typedef __u16 u16;
+typedef __s16 s16;
+
+typedef __u8 u8;
+typedef __s8 s8;
+
+#ifdef __CHECKER__
+#define __bitwise__ __attribute__((bitwise))
+#else
+#define __bitwise__
+#endif
+#ifdef __CHECK_ENDIAN__
+#define __bitwise __bitwise__
+#else
+#define __bitwise
+#endif
+
+
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+struct list_head {
+ struct list_head *next, *prev;
+};
+
+struct hlist_head {
+ struct hlist_node *first;
+};
+
+struct hlist_node {
+ struct hlist_node *next, **pprev;
+};
+
+#endif /* LINUX_TYPES_H */
diff --git a/kvmtool/include/linux/vfio.h b/kvmtool/include/linux/vfio.h
new file mode 100644
index 0000000..4e7ab4c
--- /dev/null
+++ b/kvmtool/include/linux/vfio.h
@@ -0,0 +1,719 @@
+/*
+ * VFIO API definition
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All rights reserved.
+ * Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef VFIO_H
+#define VFIO_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define VFIO_API_VERSION 0
+
+
+/* Kernel & User level defines for VFIO IOCTLs. */
+
+/* Extensions */
+
+#define VFIO_TYPE1_IOMMU 1
+#define VFIO_SPAPR_TCE_IOMMU 2
+#define VFIO_TYPE1v2_IOMMU 3
+/*
+ * IOMMU enforces DMA cache coherence (ex. PCIe NoSnoop stripping). This
+ * capability is subject to change as groups are added or removed.
+ */
+#define VFIO_DMA_CC_IOMMU 4
+
+/* Check if EEH is supported */
+#define VFIO_EEH 5
+
+/* Two-stage IOMMU */
+#define VFIO_TYPE1_NESTING_IOMMU 6 /* Implies v2 */
+
+#define VFIO_SPAPR_TCE_v2_IOMMU 7
+
+/*
+ * The No-IOMMU IOMMU offers no translation or isolation for devices and
+ * supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU
+ * code will taint the host kernel and should be used with extreme caution.
+ */
+#define VFIO_NOIOMMU_IOMMU 8
+
+/*
+ * The IOCTL interface is designed for extensibility by embedding the
+ * structure length (argsz) and flags into structures passed between
+ * kernel and userspace. We therefore use the _IO() macro for these
+ * defines to avoid implicitly embedding a size into the ioctl request.
+ * As structure fields are added, argsz will increase to match and flag
+ * bits will be defined to indicate additional fields with valid data.
+ * It's *always* the caller's responsibility to indicate the size of
+ * the structure passed by setting argsz appropriately.
+ */
+
+#define VFIO_TYPE (';')
+#define VFIO_BASE 100
+
+/*
+ * For extension of INFO ioctls, VFIO makes use of a capability chain
+ * designed after PCI/e capabilities. A flag bit indicates whether
+ * this capability chain is supported and a field defined in the fixed
+ * structure defines the offset of the first capability in the chain.
+ * This field is only valid when the corresponding bit in the flags
+ * bitmap is set. This offset field is relative to the start of the
+ * INFO buffer, as is the next field within each capability header.
+ * The id within the header is a shared address space per INFO ioctl,
+ * while the version field is specific to the capability id. The
+ * contents following the header are specific to the capability id.
+ */
+struct vfio_info_cap_header {
+ __u16 id; /* Identifies capability */
+ __u16 version; /* Version specific to the capability ID */
+ __u32 next; /* Offset of next capability */
+};
+
+/*
+ * Callers of INFO ioctls passing insufficiently sized buffers will see
+ * the capability chain flag bit set, a zero value for the first capability
+ * offset (if available within the provided argsz), and argsz will be
+ * updated to report the necessary buffer size. For compatibility, the
+ * INFO ioctl will not report error in this case, but the capability chain
+ * will not be available.
+ */
+
+/* -------- IOCTLs for VFIO file descriptor (/dev/vfio/vfio) -------- */
+
+/**
+ * VFIO_GET_API_VERSION - _IO(VFIO_TYPE, VFIO_BASE + 0)
+ *
+ * Report the version of the VFIO API. This allows us to bump the entire
+ * API version should we later need to add or change features in incompatible
+ * ways.
+ * Return: VFIO_API_VERSION
+ * Availability: Always
+ */
+#define VFIO_GET_API_VERSION _IO(VFIO_TYPE, VFIO_BASE + 0)
+
+/**
+ * VFIO_CHECK_EXTENSION - _IOW(VFIO_TYPE, VFIO_BASE + 1, __u32)
+ *
+ * Check whether an extension is supported.
+ * Return: 0 if not supported, 1 (or some other positive integer) if supported.
+ * Availability: Always
+ */
+#define VFIO_CHECK_EXTENSION _IO(VFIO_TYPE, VFIO_BASE + 1)
+
+/**
+ * VFIO_SET_IOMMU - _IOW(VFIO_TYPE, VFIO_BASE + 2, __s32)
+ *
+ * Set the iommu to the given type. The type must be supported by an
+ * iommu driver as verified by calling CHECK_EXTENSION using the same
+ * type. A group must be set to this file descriptor before this
+ * ioctl is available. The IOMMU interfaces enabled by this call are
+ * specific to the value set.
+ * Return: 0 on success, -errno on failure
+ * Availability: When VFIO group attached
+ */
+#define VFIO_SET_IOMMU _IO(VFIO_TYPE, VFIO_BASE + 2)
+
+/* -------- IOCTLs for GROUP file descriptors (/dev/vfio/$GROUP) -------- */
+
+/**
+ * VFIO_GROUP_GET_STATUS - _IOR(VFIO_TYPE, VFIO_BASE + 3,
+ * struct vfio_group_status)
+ *
+ * Retrieve information about the group. Fills in provided
+ * struct vfio_group_info. Caller sets argsz.
+ * Return: 0 on succes, -errno on failure.
+ * Availability: Always
+ */
+struct vfio_group_status {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_GROUP_FLAGS_VIABLE (1 << 0)
+#define VFIO_GROUP_FLAGS_CONTAINER_SET (1 << 1)
+};
+#define VFIO_GROUP_GET_STATUS _IO(VFIO_TYPE, VFIO_BASE + 3)
+
+/**
+ * VFIO_GROUP_SET_CONTAINER - _IOW(VFIO_TYPE, VFIO_BASE + 4, __s32)
+ *
+ * Set the container for the VFIO group to the open VFIO file
+ * descriptor provided. Groups may only belong to a single
+ * container. Containers may, at their discretion, support multiple
+ * groups. Only when a container is set are all of the interfaces
+ * of the VFIO file descriptor and the VFIO group file descriptor
+ * available to the user.
+ * Return: 0 on success, -errno on failure.
+ * Availability: Always
+ */
+#define VFIO_GROUP_SET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 4)
+
+/**
+ * VFIO_GROUP_UNSET_CONTAINER - _IO(VFIO_TYPE, VFIO_BASE + 5)
+ *
+ * Remove the group from the attached container. This is the
+ * opposite of the SET_CONTAINER call and returns the group to
+ * an initial state. All device file descriptors must be released
+ * prior to calling this interface. When removing the last group
+ * from a container, the IOMMU will be disabled and all state lost,
+ * effectively also returning the VFIO file descriptor to an initial
+ * state.
+ * Return: 0 on success, -errno on failure.
+ * Availability: When attached to container
+ */
+#define VFIO_GROUP_UNSET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 5)
+
+/**
+ * VFIO_GROUP_GET_DEVICE_FD - _IOW(VFIO_TYPE, VFIO_BASE + 6, char)
+ *
+ * Return a new file descriptor for the device object described by
+ * the provided string. The string should match a device listed in
+ * the devices subdirectory of the IOMMU group sysfs entry. The
+ * group containing the device must already be added to this context.
+ * Return: new file descriptor on success, -errno on failure.
+ * Availability: When attached to container
+ */
+#define VFIO_GROUP_GET_DEVICE_FD _IO(VFIO_TYPE, VFIO_BASE + 6)
+
+/* --------------- IOCTLs for DEVICE file descriptors --------------- */
+
+/**
+ * VFIO_DEVICE_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 7,
+ * struct vfio_device_info)
+ *
+ * Retrieve information about the device. Fills in provided
+ * struct vfio_device_info. Caller sets argsz.
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_device_info {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_DEVICE_FLAGS_RESET (1 << 0) /* Device supports reset */
+#define VFIO_DEVICE_FLAGS_PCI (1 << 1) /* vfio-pci device */
+#define VFIO_DEVICE_FLAGS_PLATFORM (1 << 2) /* vfio-platform device */
+#define VFIO_DEVICE_FLAGS_AMBA (1 << 3) /* vfio-amba device */
+#define VFIO_DEVICE_FLAGS_CCW (1 << 4) /* vfio-ccw device */
+ __u32 num_regions; /* Max region index + 1 */
+ __u32 num_irqs; /* Max IRQ index + 1 */
+};
+#define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7)
+
+/*
+ * Vendor driver using Mediated device framework should provide device_api
+ * attribute in supported type attribute groups. Device API string should be one
+ * of the following corresponding to device flags in vfio_device_info structure.
+ */
+
+#define VFIO_DEVICE_API_PCI_STRING "vfio-pci"
+#define VFIO_DEVICE_API_PLATFORM_STRING "vfio-platform"
+#define VFIO_DEVICE_API_AMBA_STRING "vfio-amba"
+#define VFIO_DEVICE_API_CCW_STRING "vfio-ccw"
+
+/**
+ * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8,
+ * struct vfio_region_info)
+ *
+ * Retrieve information about a device region. Caller provides
+ * struct vfio_region_info with index value set. Caller sets argsz.
+ * Implementation of region mapping is bus driver specific. This is
+ * intended to describe MMIO, I/O port, as well as bus specific
+ * regions (ex. PCI config space). Zero sized regions may be used
+ * to describe unimplemented regions (ex. unimplemented PCI BARs).
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_region_info {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_REGION_INFO_FLAG_READ (1 << 0) /* Region supports read */
+#define VFIO_REGION_INFO_FLAG_WRITE (1 << 1) /* Region supports write */
+#define VFIO_REGION_INFO_FLAG_MMAP (1 << 2) /* Region supports mmap */
+#define VFIO_REGION_INFO_FLAG_CAPS (1 << 3) /* Info supports caps */
+ __u32 index; /* Region index */
+ __u32 cap_offset; /* Offset within info struct of first cap */
+ __u64 size; /* Region size (bytes) */
+ __u64 offset; /* Region offset from start of device fd */
+};
+#define VFIO_DEVICE_GET_REGION_INFO _IO(VFIO_TYPE, VFIO_BASE + 8)
+
+/*
+ * The sparse mmap capability allows finer granularity of specifying areas
+ * within a region with mmap support. When specified, the user should only
+ * mmap the offset ranges specified by the areas array. mmaps outside of the
+ * areas specified may fail (such as the range covering a PCI MSI-X table) or
+ * may result in improper device behavior.
+ *
+ * The structures below define version 1 of this capability.
+ */
+#define VFIO_REGION_INFO_CAP_SPARSE_MMAP 1
+
+struct vfio_region_sparse_mmap_area {
+ __u64 offset; /* Offset of mmap'able area within region */
+ __u64 size; /* Size of mmap'able area */
+};
+
+struct vfio_region_info_cap_sparse_mmap {
+ struct vfio_info_cap_header header;
+ __u32 nr_areas;
+ __u32 reserved;
+ struct vfio_region_sparse_mmap_area areas[];
+};
+
+/*
+ * The device specific type capability allows regions unique to a specific
+ * device or class of devices to be exposed. This helps solve the problem for
+ * vfio bus drivers of defining which region indexes correspond to which region
+ * on the device, without needing to resort to static indexes, as done by
+ * vfio-pci. For instance, if we were to go back in time, we might remove
+ * VFIO_PCI_VGA_REGION_INDEX and let vfio-pci simply define that all indexes
+ * greater than or equal to VFIO_PCI_NUM_REGIONS are device specific and we'd
+ * make a "VGA" device specific type to describe the VGA access space. This
+ * means that non-VGA devices wouldn't need to waste this index, and thus the
+ * address space associated with it due to implementation of device file
+ * descriptor offsets in vfio-pci.
+ *
+ * The current implementation is now part of the user ABI, so we can't use this
+ * for VGA, but there are other upcoming use cases, such as opregions for Intel
+ * IGD devices and framebuffers for vGPU devices. We missed VGA, but we'll
+ * use this for future additions.
+ *
+ * The structure below defines version 1 of this capability.
+ */
+#define VFIO_REGION_INFO_CAP_TYPE 2
+
+struct vfio_region_info_cap_type {
+ struct vfio_info_cap_header header;
+ __u32 type; /* global per bus driver */
+ __u32 subtype; /* type specific */
+};
+
+#define VFIO_REGION_TYPE_PCI_VENDOR_TYPE (1 << 31)
+#define VFIO_REGION_TYPE_PCI_VENDOR_MASK (0xffff)
+
+/* 8086 Vendor sub-types */
+#define VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION (1)
+#define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG (2)
+#define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG (3)
+
+/**
+ * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9,
+ * struct vfio_irq_info)
+ *
+ * Retrieve information about a device IRQ. Caller provides
+ * struct vfio_irq_info with index value set. Caller sets argsz.
+ * Implementation of IRQ mapping is bus driver specific. Indexes
+ * using multiple IRQs are primarily intended to support MSI-like
+ * interrupt blocks. Zero count irq blocks may be used to describe
+ * unimplemented interrupt types.
+ *
+ * The EVENTFD flag indicates the interrupt index supports eventfd based
+ * signaling.
+ *
+ * The MASKABLE flags indicates the index supports MASK and UNMASK
+ * actions described below.
+ *
+ * AUTOMASKED indicates that after signaling, the interrupt line is
+ * automatically masked by VFIO and the user needs to unmask the line
+ * to receive new interrupts. This is primarily intended to distinguish
+ * level triggered interrupts.
+ *
+ * The NORESIZE flag indicates that the interrupt lines within the index
+ * are setup as a set and new subindexes cannot be enabled without first
+ * disabling the entire index. This is used for interrupts like PCI MSI
+ * and MSI-X where the driver may only use a subset of the available
+ * indexes, but VFIO needs to enable a specific number of vectors
+ * upfront. In the case of MSI-X, where the user can enable MSI-X and
+ * then add and unmask vectors, it's up to userspace to make the decision
+ * whether to allocate the maximum supported number of vectors or tear
+ * down setup and incrementally increase the vectors as each is enabled.
+ */
+struct vfio_irq_info {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_IRQ_INFO_EVENTFD (1 << 0)
+#define VFIO_IRQ_INFO_MASKABLE (1 << 1)
+#define VFIO_IRQ_INFO_AUTOMASKED (1 << 2)
+#define VFIO_IRQ_INFO_NORESIZE (1 << 3)
+ __u32 index; /* IRQ index */
+ __u32 count; /* Number of IRQs within this index */
+};
+#define VFIO_DEVICE_GET_IRQ_INFO _IO(VFIO_TYPE, VFIO_BASE + 9)
+
+/**
+ * VFIO_DEVICE_SET_IRQS - _IOW(VFIO_TYPE, VFIO_BASE + 10, struct vfio_irq_set)
+ *
+ * Set signaling, masking, and unmasking of interrupts. Caller provides
+ * struct vfio_irq_set with all fields set. 'start' and 'count' indicate
+ * the range of subindexes being specified.
+ *
+ * The DATA flags specify the type of data provided. If DATA_NONE, the
+ * operation performs the specified action immediately on the specified
+ * interrupt(s). For example, to unmask AUTOMASKED interrupt [0,0]:
+ * flags = (DATA_NONE|ACTION_UNMASK), index = 0, start = 0, count = 1.
+ *
+ * DATA_BOOL allows sparse support for the same on arrays of interrupts.
+ * For example, to mask interrupts [0,1] and [0,3] (but not [0,2]):
+ * flags = (DATA_BOOL|ACTION_MASK), index = 0, start = 1, count = 3,
+ * data = {1,0,1}
+ *
+ * DATA_EVENTFD binds the specified ACTION to the provided __s32 eventfd.
+ * A value of -1 can be used to either de-assign interrupts if already
+ * assigned or skip un-assigned interrupts. For example, to set an eventfd
+ * to be trigger for interrupts [0,0] and [0,2]:
+ * flags = (DATA_EVENTFD|ACTION_TRIGGER), index = 0, start = 0, count = 3,
+ * data = {fd1, -1, fd2}
+ * If index [0,1] is previously set, two count = 1 ioctls calls would be
+ * required to set [0,0] and [0,2] without changing [0,1].
+ *
+ * Once a signaling mechanism is set, DATA_BOOL or DATA_NONE can be used
+ * with ACTION_TRIGGER to perform kernel level interrupt loopback testing
+ * from userspace (ie. simulate hardware triggering).
+ *
+ * Setting of an event triggering mechanism to userspace for ACTION_TRIGGER
+ * enables the interrupt index for the device. Individual subindex interrupts
+ * can be disabled using the -1 value for DATA_EVENTFD or the index can be
+ * disabled as a whole with: flags = (DATA_NONE|ACTION_TRIGGER), count = 0.
+ *
+ * Note that ACTION_[UN]MASK specify user->kernel signaling (irqfds) while
+ * ACTION_TRIGGER specifies kernel->user signaling.
+ */
+struct vfio_irq_set {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_IRQ_SET_DATA_NONE (1 << 0) /* Data not present */
+#define VFIO_IRQ_SET_DATA_BOOL (1 << 1) /* Data is bool (u8) */
+#define VFIO_IRQ_SET_DATA_EVENTFD (1 << 2) /* Data is eventfd (s32) */
+#define VFIO_IRQ_SET_ACTION_MASK (1 << 3) /* Mask interrupt */
+#define VFIO_IRQ_SET_ACTION_UNMASK (1 << 4) /* Unmask interrupt */
+#define VFIO_IRQ_SET_ACTION_TRIGGER (1 << 5) /* Trigger interrupt */
+ __u32 index;
+ __u32 start;
+ __u32 count;
+ __u8 data[];
+};
+#define VFIO_DEVICE_SET_IRQS _IO(VFIO_TYPE, VFIO_BASE + 10)
+
+#define VFIO_IRQ_SET_DATA_TYPE_MASK (VFIO_IRQ_SET_DATA_NONE | \
+ VFIO_IRQ_SET_DATA_BOOL | \
+ VFIO_IRQ_SET_DATA_EVENTFD)
+#define VFIO_IRQ_SET_ACTION_TYPE_MASK (VFIO_IRQ_SET_ACTION_MASK | \
+ VFIO_IRQ_SET_ACTION_UNMASK | \
+ VFIO_IRQ_SET_ACTION_TRIGGER)
+/**
+ * VFIO_DEVICE_RESET - _IO(VFIO_TYPE, VFIO_BASE + 11)
+ *
+ * Reset a device.
+ */
+#define VFIO_DEVICE_RESET _IO(VFIO_TYPE, VFIO_BASE + 11)
+
+/*
+ * The VFIO-PCI bus driver makes use of the following fixed region and
+ * IRQ index mapping. Unimplemented regions return a size of zero.
+ * Unimplemented IRQ types return a count of zero.
+ */
+
+enum {
+ VFIO_PCI_BAR0_REGION_INDEX,
+ VFIO_PCI_BAR1_REGION_INDEX,
+ VFIO_PCI_BAR2_REGION_INDEX,
+ VFIO_PCI_BAR3_REGION_INDEX,
+ VFIO_PCI_BAR4_REGION_INDEX,
+ VFIO_PCI_BAR5_REGION_INDEX,
+ VFIO_PCI_ROM_REGION_INDEX,
+ VFIO_PCI_CONFIG_REGION_INDEX,
+ /*
+ * Expose VGA regions defined for PCI base class 03, subclass 00.
+ * This includes I/O port ranges 0x3b0 to 0x3bb and 0x3c0 to 0x3df
+ * as well as the MMIO range 0xa0000 to 0xbffff. Each implemented
+ * range is found at it's identity mapped offset from the region
+ * offset, for example 0x3b0 is region_info.offset + 0x3b0. Areas
+ * between described ranges are unimplemented.
+ */
+ VFIO_PCI_VGA_REGION_INDEX,
+ VFIO_PCI_NUM_REGIONS = 9 /* Fixed user ABI, region indexes >=9 use */
+ /* device specific cap to define content. */
+};
+
+enum {
+ VFIO_PCI_INTX_IRQ_INDEX,
+ VFIO_PCI_MSI_IRQ_INDEX,
+ VFIO_PCI_MSIX_IRQ_INDEX,
+ VFIO_PCI_ERR_IRQ_INDEX,
+ VFIO_PCI_REQ_IRQ_INDEX,
+ VFIO_PCI_NUM_IRQS
+};
+
+/*
+ * The vfio-ccw bus driver makes use of the following fixed region and
+ * IRQ index mapping. Unimplemented regions return a size of zero.
+ * Unimplemented IRQ types return a count of zero.
+ */
+
+enum {
+ VFIO_CCW_CONFIG_REGION_INDEX,
+ VFIO_CCW_NUM_REGIONS
+};
+
+enum {
+ VFIO_CCW_IO_IRQ_INDEX,
+ VFIO_CCW_NUM_IRQS
+};
+
+/**
+ * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12,
+ * struct vfio_pci_hot_reset_info)
+ *
+ * Return: 0 on success, -errno on failure:
+ * -enospc = insufficient buffer, -enodev = unsupported for device.
+ */
+struct vfio_pci_dependent_device {
+ __u32 group_id;
+ __u16 segment;
+ __u8 bus;
+ __u8 devfn; /* Use PCI_SLOT/PCI_FUNC */
+};
+
+struct vfio_pci_hot_reset_info {
+ __u32 argsz;
+ __u32 flags;
+ __u32 count;
+ struct vfio_pci_dependent_device devices[];
+};
+
+#define VFIO_DEVICE_GET_PCI_HOT_RESET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
+
+/**
+ * VFIO_DEVICE_PCI_HOT_RESET - _IOW(VFIO_TYPE, VFIO_BASE + 13,
+ * struct vfio_pci_hot_reset)
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vfio_pci_hot_reset {
+ __u32 argsz;
+ __u32 flags;
+ __u32 count;
+ __s32 group_fds[];
+};
+
+#define VFIO_DEVICE_PCI_HOT_RESET _IO(VFIO_TYPE, VFIO_BASE + 13)
+
+/* -------- API for Type1 VFIO IOMMU -------- */
+
+/**
+ * VFIO_IOMMU_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 12, struct vfio_iommu_info)
+ *
+ * Retrieve information about the IOMMU object. Fills in provided
+ * struct vfio_iommu_info. Caller sets argsz.
+ *
+ * XXX Should we do these by CHECK_EXTENSION too?
+ */
+struct vfio_iommu_type1_info {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */
+ __u64 iova_pgsizes; /* Bitmap of supported page sizes */
+};
+
+#define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
+
+/**
+ * VFIO_IOMMU_MAP_DMA - _IOW(VFIO_TYPE, VFIO_BASE + 13, struct vfio_dma_map)
+ *
+ * Map process virtual addresses to IO virtual addresses using the
+ * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required.
+ */
+struct vfio_iommu_type1_dma_map {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */
+#define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */
+ __u64 vaddr; /* Process virtual address */
+ __u64 iova; /* IO virtual address */
+ __u64 size; /* Size of mapping (bytes) */
+};
+
+#define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13)
+
+/**
+ * VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14,
+ * struct vfio_dma_unmap)
+ *
+ * Unmap IO virtual addresses using the provided struct vfio_dma_unmap.
+ * Caller sets argsz. The actual unmapped size is returned in the size
+ * field. No guarantee is made to the user that arbitrary unmaps of iova
+ * or size different from those used in the original mapping call will
+ * succeed.
+ */
+struct vfio_iommu_type1_dma_unmap {
+ __u32 argsz;
+ __u32 flags;
+ __u64 iova; /* IO virtual address */
+ __u64 size; /* Size of mapping (bytes) */
+};
+
+#define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14)
+
+/*
+ * IOCTLs to enable/disable IOMMU container usage.
+ * No parameters are supported.
+ */
+#define VFIO_IOMMU_ENABLE _IO(VFIO_TYPE, VFIO_BASE + 15)
+#define VFIO_IOMMU_DISABLE _IO(VFIO_TYPE, VFIO_BASE + 16)
+
+/* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
+
+/*
+ * The SPAPR TCE DDW info struct provides the information about
+ * the details of Dynamic DMA window capability.
+ *
+ * @pgsizes contains a page size bitmask, 4K/64K/16M are supported.
+ * @max_dynamic_windows_supported tells the maximum number of windows
+ * which the platform can create.
+ * @levels tells the maximum number of levels in multi-level IOMMU tables;
+ * this allows splitting a table into smaller chunks which reduces
+ * the amount of physically contiguous memory required for the table.
+ */
+struct vfio_iommu_spapr_tce_ddw_info {
+ __u64 pgsizes; /* Bitmap of supported page sizes */
+ __u32 max_dynamic_windows_supported;
+ __u32 levels;
+};
+
+/*
+ * The SPAPR TCE info struct provides the information about the PCI bus
+ * address ranges available for DMA, these values are programmed into
+ * the hardware so the guest has to know that information.
+ *
+ * The DMA 32 bit window start is an absolute PCI bus address.
+ * The IOVA address passed via map/unmap ioctls are absolute PCI bus
+ * addresses too so the window works as a filter rather than an offset
+ * for IOVA addresses.
+ *
+ * Flags supported:
+ * - VFIO_IOMMU_SPAPR_INFO_DDW: informs the userspace that dynamic DMA windows
+ * (DDW) support is present. @ddw is only supported when DDW is present.
+ */
+struct vfio_iommu_spapr_tce_info {
+ __u32 argsz;
+ __u32 flags;
+#define VFIO_IOMMU_SPAPR_INFO_DDW (1 << 0) /* DDW supported */
+ __u32 dma32_window_start; /* 32 bit window start (bytes) */
+ __u32 dma32_window_size; /* 32 bit window size (bytes) */
+ struct vfio_iommu_spapr_tce_ddw_info ddw;
+};
+
+#define VFIO_IOMMU_SPAPR_TCE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)
+
+/*
+ * EEH PE operation struct provides ways to:
+ * - enable/disable EEH functionality;
+ * - unfreeze IO/DMA for frozen PE;
+ * - read PE state;
+ * - reset PE;
+ * - configure PE;
+ * - inject EEH error.
+ */
+struct vfio_eeh_pe_err {
+ __u32 type;
+ __u32 func;
+ __u64 addr;
+ __u64 mask;
+};
+
+struct vfio_eeh_pe_op {
+ __u32 argsz;
+ __u32 flags;
+ __u32 op;
+ union {
+ struct vfio_eeh_pe_err err;
+ };
+};
+
+#define VFIO_EEH_PE_DISABLE 0 /* Disable EEH functionality */
+#define VFIO_EEH_PE_ENABLE 1 /* Enable EEH functionality */
+#define VFIO_EEH_PE_UNFREEZE_IO 2 /* Enable IO for frozen PE */
+#define VFIO_EEH_PE_UNFREEZE_DMA 3 /* Enable DMA for frozen PE */
+#define VFIO_EEH_PE_GET_STATE 4 /* PE state retrieval */
+#define VFIO_EEH_PE_STATE_NORMAL 0 /* PE in functional state */
+#define VFIO_EEH_PE_STATE_RESET 1 /* PE reset in progress */
+#define VFIO_EEH_PE_STATE_STOPPED 2 /* Stopped DMA and IO */
+#define VFIO_EEH_PE_STATE_STOPPED_DMA 4 /* Stopped DMA only */
+#define VFIO_EEH_PE_STATE_UNAVAIL 5 /* State unavailable */
+#define VFIO_EEH_PE_RESET_DEACTIVATE 5 /* Deassert PE reset */
+#define VFIO_EEH_PE_RESET_HOT 6 /* Assert hot reset */
+#define VFIO_EEH_PE_RESET_FUNDAMENTAL 7 /* Assert fundamental reset */
+#define VFIO_EEH_PE_CONFIGURE 8 /* PE configuration */
+#define VFIO_EEH_PE_INJECT_ERR 9 /* Inject EEH error */
+
+#define VFIO_EEH_PE_OP _IO(VFIO_TYPE, VFIO_BASE + 21)
+
+/**
+ * VFIO_IOMMU_SPAPR_REGISTER_MEMORY - _IOW(VFIO_TYPE, VFIO_BASE + 17, struct vfio_iommu_spapr_register_memory)
+ *
+ * Registers user space memory where DMA is allowed. It pins
+ * user pages and does the locked memory accounting so
+ * subsequent VFIO_IOMMU_MAP_DMA/VFIO_IOMMU_UNMAP_DMA calls
+ * get faster.
+ */
+struct vfio_iommu_spapr_register_memory {
+ __u32 argsz;
+ __u32 flags;
+ __u64 vaddr; /* Process virtual address */
+ __u64 size; /* Size of mapping (bytes) */
+};
+#define VFIO_IOMMU_SPAPR_REGISTER_MEMORY _IO(VFIO_TYPE, VFIO_BASE + 17)
+
+/**
+ * VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY - _IOW(VFIO_TYPE, VFIO_BASE + 18, struct vfio_iommu_spapr_register_memory)
+ *
+ * Unregisters user space memory registered with
+ * VFIO_IOMMU_SPAPR_REGISTER_MEMORY.
+ * Uses vfio_iommu_spapr_register_memory for parameters.
+ */
+#define VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY _IO(VFIO_TYPE, VFIO_BASE + 18)
+
+/**
+ * VFIO_IOMMU_SPAPR_TCE_CREATE - _IOWR(VFIO_TYPE, VFIO_BASE + 19, struct vfio_iommu_spapr_tce_create)
+ *
+ * Creates an additional TCE table and programs it (sets a new DMA window)
+ * to every IOMMU group in the container. It receives page shift, window
+ * size and number of levels in the TCE table being created.
+ *
+ * It allocates and returns an offset on a PCI bus of the new DMA window.
+ */
+struct vfio_iommu_spapr_tce_create {
+ __u32 argsz;
+ __u32 flags;
+ /* in */
+ __u32 page_shift;
+ __u32 __resv1;
+ __u64 window_size;
+ __u32 levels;
+ __u32 __resv2;
+ /* out */
+ __u64 start_addr;
+};
+#define VFIO_IOMMU_SPAPR_TCE_CREATE _IO(VFIO_TYPE, VFIO_BASE + 19)
+
+/**
+ * VFIO_IOMMU_SPAPR_TCE_REMOVE - _IOW(VFIO_TYPE, VFIO_BASE + 20, struct vfio_iommu_spapr_tce_remove)
+ *
+ * Unprograms a TCE table from all groups in the container and destroys it.
+ * It receives a PCI bus offset as a window id.
+ */
+struct vfio_iommu_spapr_tce_remove {
+ __u32 argsz;
+ __u32 flags;
+ /* in */
+ __u64 start_addr;
+};
+#define VFIO_IOMMU_SPAPR_TCE_REMOVE _IO(VFIO_TYPE, VFIO_BASE + 20)
+
+/* ***************************************************************** */
+
+#endif /* VFIO_H */
diff --git a/kvmtool/include/linux/vhost.h b/kvmtool/include/linux/vhost.h
new file mode 100644
index 0000000..bb6a5b4
--- /dev/null
+++ b/kvmtool/include/linux/vhost.h
@@ -0,0 +1,158 @@
+#ifndef _LINUX_VHOST_H
+#define _LINUX_VHOST_H
+/* Userspace interface for in-kernel virtio accelerators. */
+
+/* vhost is used to reduce the number of system calls involved in virtio.
+ *
+ * Existing virtio net code is used in the guest without modification.
+ *
+ * This header includes interface used by userspace hypervisor for
+ * device configuration.
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/ioctl.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_vring_state {
+ unsigned int index;
+ unsigned int num;
+};
+
+struct vhost_vring_file {
+ unsigned int index;
+ int fd; /* Pass -1 to unbind from file. */
+
+};
+
+struct vhost_vring_addr {
+ unsigned int index;
+ /* Option flags. */
+ unsigned int flags;
+ /* Flag values: */
+ /* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+ /* Start of array of descriptors (virtually contiguous) */
+ __u64 desc_user_addr;
+ /* Used structure address. Must be 32 bit aligned */
+ __u64 used_user_addr;
+ /* Available structure address. Must be 16 bit aligned */
+ __u64 avail_user_addr;
+ /* Logging support. */
+ /* Log writes to used structure, at offset calculated from specified
+ * address. Address must be 32 bit aligned. */
+ __u64 log_guest_addr;
+};
+
+struct vhost_memory_region {
+ __u64 guest_phys_addr;
+ __u64 memory_size; /* bytes */
+ __u64 userspace_addr;
+ __u64 flags_padding; /* No flags are currently specified. */
+};
+
+/* All region addresses and sizes must be 4K aligned. */
+#define VHOST_PAGE_SIZE 0x1000
+
+struct vhost_memory {
+ __u32 nregions;
+ __u32 padding;
+ struct vhost_memory_region regions[0];
+};
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+/* Features bitmask for forward compatibility. Transport bits are used for
+ * vhost specific features. */
+#define VHOST_GET_FEATURES _IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES _IOW(VHOST_VIRTIO, 0x00, __u64)
+
+/* Set current process as the (exclusive) owner of this file descriptor. This
+ * must be called before any other vhost command. Further calls to
+ * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+/* Give up ownership, and reset the device to default values.
+ * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+
+/* Set up/modify memory layout */
+#define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
+
+/* Write logging setup. */
+/* Memory writes can optionally be logged by setting bit at an offset
+ * (calculated from the physical address) from specified log base.
+ * The bit is set using an atomic 32 bit operation. */
+/* Set base address for logging. */
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+/* Specify an eventfd file descriptor to signal on log write. */
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+
+/* Ring setup. */
+/* Set number of descriptors in ring. This parameter can not
+ * be modified while ring is running (bound to a device). */
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+/* Set addresses for the ring. */
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+/* Base value where queue looks for available descriptors */
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Get accessor: reads index, writes value in num */
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+
+/* The following ioctls use eventfd file descriptors to signal and poll
+ * for events. */
+
+/* Set eventfd to poll for added buffers */
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+/* Set eventfd to signal when buffers have beed used */
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+/* Set eventfd to signal an error */
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+
+/* VHOST_NET specific defines */
+
+/* Attach virtio net ring to a raw socket, or tap device.
+ * The socket must be already bound to an ethernet device, this device will be
+ * used for transmit. Pass fd -1 to unbind from the socket and the transmit
+ * device. This can be used to stop the ring (e.g. for migration). */
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/* Feature bits */
+/* Log all write descriptors. Can be changed while device is active. */
+#define VHOST_F_LOG_ALL 26
+/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
+#define VHOST_NET_F_VIRTIO_NET_HDR 27
+
+/* VHOST_SCSI specific definitions */
+
+/*
+ * Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
+ *
+ * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
+ * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage
+ * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
+ * All the targets under vhost_wwpn can be seen and used by guset.
+ */
+
+#define VHOST_SCSI_ABI_VERSION 1
+
+struct vhost_scsi_target {
+ int abi_version;
+ char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
+ unsigned short vhost_tpgt;
+ unsigned short reserved;
+};
+
+#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
+#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
+/* Changing this breaks userspace. */
+#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
+/* Set and get the events missed flag */
+#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
+#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
+
+#endif
diff --git a/kvmtool/include/linux/virtio_ids.h b/kvmtool/include/linux/virtio_ids.h
new file mode 100644
index 0000000..5f60aa4
--- /dev/null
+++ b/kvmtool/include/linux/virtio_ids.h
@@ -0,0 +1,44 @@
+#ifndef _LINUX_VIRTIO_IDS_H
+#define _LINUX_VIRTIO_IDS_H
+/*
+ * Virtio IDs
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
+
+#define VIRTIO_ID_NET 1 /* virtio net */
+#define VIRTIO_ID_BLOCK 2 /* virtio block */
+#define VIRTIO_ID_CONSOLE 3 /* virtio console */
+#define VIRTIO_ID_RNG 4 /* virtio rng */
+#define VIRTIO_ID_BALLOON 5 /* virtio balloon */
+#define VIRTIO_ID_RPMSG 7 /* virtio remote processor messaging */
+#define VIRTIO_ID_SCSI 8 /* virtio scsi */
+#define VIRTIO_ID_9P 9 /* 9p virtio console */
+#define VIRTIO_ID_RPROC_SERIAL 11 /* virtio remoteproc serial link */
+#define VIRTIO_ID_CAIF 12 /* Virtio caif */
+#define VIRTIO_ID_INPUT 18 /* virtio input */
+
+#endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/kvmtool/include/linux/virtio_mmio.h b/kvmtool/include/linux/virtio_mmio.h
new file mode 100644
index 0000000..5c7b6f0
--- /dev/null
+++ b/kvmtool/include/linux/virtio_mmio.h
@@ -0,0 +1,111 @@
+/*
+ * Virtio platform device driver
+ *
+ * Copyright 2011, ARM Ltd.
+ *
+ * Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_VIRTIO_MMIO_H
+#define _LINUX_VIRTIO_MMIO_H
+
+/*
+ * Control registers
+ */
+
+/* Magic value ("virt" string) - Read Only */
+#define VIRTIO_MMIO_MAGIC_VALUE 0x000
+
+/* Virtio device version - Read Only */
+#define VIRTIO_MMIO_VERSION 0x004
+
+/* Virtio device ID - Read Only */
+#define VIRTIO_MMIO_DEVICE_ID 0x008
+
+/* Virtio vendor ID - Read Only */
+#define VIRTIO_MMIO_VENDOR_ID 0x00c
+
+/* Bitmask of the features supported by the host
+ * (32 bits per set) - Read Only */
+#define VIRTIO_MMIO_HOST_FEATURES 0x010
+
+/* Host features set selector - Write Only */
+#define VIRTIO_MMIO_HOST_FEATURES_SEL 0x014
+
+/* Bitmask of features activated by the guest
+ * (32 bits per set) - Write Only */
+#define VIRTIO_MMIO_GUEST_FEATURES 0x020
+
+/* Activated features set selector - Write Only */
+#define VIRTIO_MMIO_GUEST_FEATURES_SEL 0x024
+
+/* Guest's memory page size in bytes - Write Only */
+#define VIRTIO_MMIO_GUEST_PAGE_SIZE 0x028
+
+/* Queue selector - Write Only */
+#define VIRTIO_MMIO_QUEUE_SEL 0x030
+
+/* Maximum size of the currently selected queue - Read Only */
+#define VIRTIO_MMIO_QUEUE_NUM_MAX 0x034
+
+/* Queue size for the currently selected queue - Write Only */
+#define VIRTIO_MMIO_QUEUE_NUM 0x038
+
+/* Used Ring alignment for the currently selected queue - Write Only */
+#define VIRTIO_MMIO_QUEUE_ALIGN 0x03c
+
+/* Guest's PFN for the currently selected queue - Read Write */
+#define VIRTIO_MMIO_QUEUE_PFN 0x040
+
+/* Queue notifier - Write Only */
+#define VIRTIO_MMIO_QUEUE_NOTIFY 0x050
+
+/* Interrupt status - Read Only */
+#define VIRTIO_MMIO_INTERRUPT_STATUS 0x060
+
+/* Interrupt acknowledge - Write Only */
+#define VIRTIO_MMIO_INTERRUPT_ACK 0x064
+
+/* Device status register - Read Write */
+#define VIRTIO_MMIO_STATUS 0x070
+
+/* The config space is defined by each driver as
+ * the per-driver configuration space - Read Write */
+#define VIRTIO_MMIO_CONFIG 0x100
+
+
+
+/*
+ * Interrupt flags (re: interrupt status & acknowledge registers)
+ */
+
+#define VIRTIO_MMIO_INT_VRING (1 << 0)
+#define VIRTIO_MMIO_INT_CONFIG (1 << 1)
+
+#endif
diff --git a/kvmtool/include/linux/virtio_net.h b/kvmtool/include/linux/virtio_net.h
new file mode 100644
index 0000000..172a7f0
--- /dev/null
+++ b/kvmtool/include/linux/virtio_net.h
@@ -0,0 +1,204 @@
+#ifndef _LINUX_VIRTIO_NET_H
+#define _LINUX_VIRTIO_NET_H
+/* This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ * may be used to endorse or promote products derived from this software
+ * without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
+#include <linux/types.h>
+#include <linux/virtio_ids.h>
+#include <linux/virtio_config.h>
+#include <linux/if_ether.h>
+
+/* The feature bitmap for virtio net */
+#define VIRTIO_NET_F_CSUM 0 /* Host handles pkts w/ partial csum */
+#define VIRTIO_NET_F_GUEST_CSUM 1 /* Guest handles pkts w/ partial csum */
+#define VIRTIO_NET_F_MAC 5 /* Host has given MAC address. */
+#define VIRTIO_NET_F_GSO 6 /* Host handles pkts w/ any GSO type */
+#define VIRTIO_NET_F_GUEST_TSO4 7 /* Guest can handle TSOv4 in. */
+#define VIRTIO_NET_F_GUEST_TSO6 8 /* Guest can handle TSOv6 in. */
+#define VIRTIO_NET_F_GUEST_ECN 9 /* Guest can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_GUEST_UFO 10 /* Guest can handle UFO in. */
+#define VIRTIO_NET_F_HOST_TSO4 11 /* Host can handle TSOv4 in. */
+#define VIRTIO_NET_F_HOST_TSO6 12 /* Host can handle TSOv6 in. */
+#define VIRTIO_NET_F_HOST_ECN 13 /* Host can handle TSO[6] w/ ECN in. */
+#define VIRTIO_NET_F_HOST_UFO 14 /* Host can handle UFO in. */
+#define VIRTIO_NET_F_MRG_RXBUF 15 /* Host can merge receive buffers. */
+#define VIRTIO_NET_F_STATUS 16 /* virtio_net_config.status available */
+#define VIRTIO_NET_F_CTRL_VQ 17 /* Control channel available */
+#define VIRTIO_NET_F_CTRL_RX 18 /* Control channel RX mode support */
+#define VIRTIO_NET_F_CTRL_VLAN 19 /* Control channel VLAN filtering */
+#define VIRTIO_NET_F_CTRL_RX_EXTRA 20 /* Extra RX mode control support */
+#define VIRTIO_NET_F_GUEST_ANNOUNCE 21 /* Guest can announce device on the
+ * network */
+#define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow
+ * Steering */
+#define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */
+
+#define VIRTIO_NET_S_LINK_UP 1 /* Link is up */
+#define VIRTIO_NET_S_ANNOUNCE 2 /* Announcement is needed */
+
+struct virtio_net_config {
+ /* The config defining mac address (if VIRTIO_NET_F_MAC) */
+ __u8 mac[ETH_ALEN];
+ /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
+ __u16 status;
+ /* Maximum number of each of transmit and receive queues;
+ * see VIRTIO_NET_F_MQ and VIRTIO_NET_CTRL_MQ.
+ * Legal values are between 1 and 0x8000
+ */
+ __u16 max_virtqueue_pairs;
+} __attribute__((packed));
+
+/* This header comes first in the scatter-gather list.
+ * If VIRTIO_F_ANY_LAYOUT is not negotiated, it must
+ * be the first element of the scatter-gather list. If you don't
+ * specify GSO or CSUM features, you can simply ignore the header. */
+struct virtio_net_hdr {
+#define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 // Use csum_start, csum_offset
+#define VIRTIO_NET_HDR_F_DATA_VALID 2 // Csum is valid
+ __u8 flags;
+#define VIRTIO_NET_HDR_GSO_NONE 0 // Not a GSO frame
+#define VIRTIO_NET_HDR_GSO_TCPV4 1 // GSO frame, IPv4 TCP (TSO)
+#define VIRTIO_NET_HDR_GSO_UDP 3 // GSO frame, IPv4 UDP (UFO)
+#define VIRTIO_NET_HDR_GSO_TCPV6 4 // GSO frame, IPv6 TCP
+#define VIRTIO_NET_HDR_GSO_ECN 0x80 // TCP has ECN set
+ __u8 gso_type;
+ __u16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */
+ __u16 gso_size; /* Bytes to append to hdr_len per frame */
+ __u16 csum_start; /* Position to start checksumming from */
+ __u16 csum_offset; /* Offset after that to place checksum */
+};
+
+/* This is the version of the header to use when the MRG_RXBUF
+ * feature has been negotiated. */
+struct virtio_net_hdr_mrg_rxbuf {
+ struct virtio_net_hdr hdr;
+ __u16 num_buffers; /* Number of merged rx buffers */
+};
+
+/*
+ * Control virtqueue data structures
+ *
+ * The control virtqueue expects a header in the first sg entry
+ * and an ack/status response in the last entry. Data for the
+ * command goes in between.
+ */
+struct virtio_net_ctrl_hdr {
+ __u8 class;
+ __u8 cmd;
+} __attribute__((packed));
+
+typedef __u8 virtio_net_ctrl_ack;
+
+#define VIRTIO_NET_OK 0
+#define VIRTIO_NET_ERR 1
+
+/*
+ * Control the RX mode, ie. promisucous, allmulti, etc...
+ * All commands require an "out" sg entry containing a 1 byte
+ * state value, zero = disable, non-zero = enable. Commands
+ * 0 and 1 are supported with the VIRTIO_NET_F_CTRL_RX feature.
+ * Commands 2-5 are added with VIRTIO_NET_F_CTRL_RX_EXTRA.
+ */
+#define VIRTIO_NET_CTRL_RX 0
+ #define VIRTIO_NET_CTRL_RX_PROMISC 0
+ #define VIRTIO_NET_CTRL_RX_ALLMULTI 1
+ #define VIRTIO_NET_CTRL_RX_ALLUNI 2
+ #define VIRTIO_NET_CTRL_RX_NOMULTI 3
+ #define VIRTIO_NET_CTRL_RX_NOUNI 4
+ #define VIRTIO_NET_CTRL_RX_NOBCAST 5
+
+/*
+ * Control the MAC
+ *
+ * The MAC filter table is managed by the hypervisor, the guest should
+ * assume the size is infinite. Filtering should be considered
+ * non-perfect, ie. based on hypervisor resources, the guest may
+ * received packets from sources not specified in the filter list.
+ *
+ * In addition to the class/cmd header, the TABLE_SET command requires
+ * two out scatterlists. Each contains a 4 byte count of entries followed
+ * by a concatenated byte stream of the ETH_ALEN MAC addresses. The
+ * first sg list contains unicast addresses, the second is for multicast.
+ * This functionality is present if the VIRTIO_NET_F_CTRL_RX feature
+ * is available.
+ *
+ * The ADDR_SET command requests one out scatterlist, it contains a
+ * 6 bytes MAC address. This functionality is present if the
+ * VIRTIO_NET_F_CTRL_MAC_ADDR feature is available.
+ */
+struct virtio_net_ctrl_mac {
+ __u32 entries;
+ __u8 macs[][ETH_ALEN];
+} __attribute__((packed));
+
+#define VIRTIO_NET_CTRL_MAC 1
+ #define VIRTIO_NET_CTRL_MAC_TABLE_SET 0
+ #define VIRTIO_NET_CTRL_MAC_ADDR_SET 1
+
+/*
+ * Control VLAN filtering
+ *
+ * The VLAN filter table is controlled via a simple ADD/DEL interface.
+ * VLAN IDs not added may be filterd by the hypervisor. Del is the
+ * opposite of add. Both commands expect an out entry containing a 2
+ * byte VLAN ID. VLAN filterting is available with the
+ * VIRTIO_NET_F_CTRL_VLAN feature bit.
+ */
+#define VIRTIO_NET_CTRL_VLAN 2
+ #define VIRTIO_NET_CTRL_VLAN_ADD 0
+ #define VIRTIO_NET_CTRL_VLAN_DEL 1
+
+/*
+ * Control link announce acknowledgement
+ *
+ * The command VIRTIO_NET_CTRL_ANNOUNCE_ACK is used to indicate that
+ * driver has recevied the notification; device would clear the
+ * VIRTIO_NET_S_ANNOUNCE bit in the status field after it receives
+ * this command.
+ */
+#define VIRTIO_NET_CTRL_ANNOUNCE 3
+ #define VIRTIO_NET_CTRL_ANNOUNCE_ACK 0
+
+/*
+ * Control Receive Flow Steering
+ *
+ * The command VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET
+ * enables Receive Flow Steering, specifying the number of the transmit and
+ * receive queues that will be used. After the command is consumed and acked by
+ * the device, the device will not steer new packets on receive virtqueues
+ * other than specified nor read from transmit virtqueues other than specified.
+ * Accordingly, driver should not transmit new packets on virtqueues other than
+ * specified.
+ */
+struct virtio_net_ctrl_mq {
+ __u16 virtqueue_pairs;
+};
+
+#define VIRTIO_NET_CTRL_MQ 4
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET 0
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN 1
+ #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX 0x8000
+
+#endif /* _LINUX_VIRTIO_NET_H */
diff --git a/kvmtool/include/linux/virtio_scsi.h b/kvmtool/include/linux/virtio_scsi.h
new file mode 100644
index 0000000..de429d1
--- /dev/null
+++ b/kvmtool/include/linux/virtio_scsi.h
@@ -0,0 +1,162 @@
+/*
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL AUTHOR OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef _LINUX_VIRTIO_SCSI_H
+#define _LINUX_VIRTIO_SCSI_H
+
+#define VIRTIO_SCSI_CDB_SIZE 32
+#define VIRTIO_SCSI_SENSE_SIZE 96
+
+/* SCSI command request, followed by data-out */
+struct virtio_scsi_cmd_req {
+ u8 lun[8]; /* Logical Unit Number */
+ u64 tag; /* Command identifier */
+ u8 task_attr; /* Task attribute */
+ u8 prio; /* SAM command priority field */
+ u8 crn;
+ u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __packed;
+
+/* SCSI command request, followed by protection information */
+struct virtio_scsi_cmd_req_pi {
+ u8 lun[8]; /* Logical Unit Number */
+ u64 tag; /* Command identifier */
+ u8 task_attr; /* Task attribute */
+ u8 prio; /* SAM command priority field */
+ u8 crn;
+ u32 pi_bytesout; /* DataOUT PI Number of bytes */
+ u32 pi_bytesin; /* DataIN PI Number of bytes */
+ u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __packed;
+
+/* Response, followed by sense data and data-in */
+struct virtio_scsi_cmd_resp {
+ u32 sense_len; /* Sense data length */
+ u32 resid; /* Residual bytes in data buffer */
+ u16 status_qualifier; /* Status qualifier */
+ u8 status; /* Command completion status */
+ u8 response; /* Response values */
+ u8 sense[VIRTIO_SCSI_SENSE_SIZE];
+} __packed;
+
+/* Task Management Request */
+struct virtio_scsi_ctrl_tmf_req {
+ u32 type;
+ u32 subtype;
+ u8 lun[8];
+ u64 tag;
+} __packed;
+
+struct virtio_scsi_ctrl_tmf_resp {
+ u8 response;
+} __packed;
+
+/* Asynchronous notification query/subscription */
+struct virtio_scsi_ctrl_an_req {
+ u32 type;
+ u8 lun[8];
+ u32 event_requested;
+} __packed;
+
+struct virtio_scsi_ctrl_an_resp {
+ u32 event_actual;
+ u8 response;
+} __packed;
+
+struct virtio_scsi_event {
+ u32 event;
+ u8 lun[8];
+ u32 reason;
+} __packed;
+
+struct virtio_scsi_config {
+ u32 num_queues;
+ u32 seg_max;
+ u32 max_sectors;
+ u32 cmd_per_lun;
+ u32 event_info_size;
+ u32 sense_size;
+ u32 cdb_size;
+ u16 max_channel;
+ u16 max_target;
+ u32 max_lun;
+} __packed;
+
+/* Feature Bits */
+#define VIRTIO_SCSI_F_INOUT 0
+#define VIRTIO_SCSI_F_HOTPLUG 1
+#define VIRTIO_SCSI_F_CHANGE 2
+#define VIRTIO_SCSI_F_T10_PI 3
+
+/* Response codes */
+#define VIRTIO_SCSI_S_OK 0
+#define VIRTIO_SCSI_S_OVERRUN 1
+#define VIRTIO_SCSI_S_ABORTED 2
+#define VIRTIO_SCSI_S_BAD_TARGET 3
+#define VIRTIO_SCSI_S_RESET 4
+#define VIRTIO_SCSI_S_BUSY 5
+#define VIRTIO_SCSI_S_TRANSPORT_FAILURE 6
+#define VIRTIO_SCSI_S_TARGET_FAILURE 7
+#define VIRTIO_SCSI_S_NEXUS_FAILURE 8
+#define VIRTIO_SCSI_S_FAILURE 9
+#define VIRTIO_SCSI_S_FUNCTION_SUCCEEDED 10
+#define VIRTIO_SCSI_S_FUNCTION_REJECTED 11
+#define VIRTIO_SCSI_S_INCORRECT_LUN 12
+
+/* Controlq type codes. */
+#define VIRTIO_SCSI_T_TMF 0
+#define VIRTIO_SCSI_T_AN_QUERY 1
+#define VIRTIO_SCSI_T_AN_SUBSCRIBE 2
+
+/* Valid TMF subtypes. */
+#define VIRTIO_SCSI_T_TMF_ABORT_TASK 0
+#define VIRTIO_SCSI_T_TMF_ABORT_TASK_SET 1
+#define VIRTIO_SCSI_T_TMF_CLEAR_ACA 2
+#define VIRTIO_SCSI_T_TMF_CLEAR_TASK_SET 3
+#define VIRTIO_SCSI_T_TMF_I_T_NEXUS_RESET 4
+#define VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET 5
+#define VIRTIO_SCSI_T_TMF_QUERY_TASK 6
+#define VIRTIO_SCSI_T_TMF_QUERY_TASK_SET 7
+
+/* Events. */
+#define VIRTIO_SCSI_T_EVENTS_MISSED 0x80000000
+#define VIRTIO_SCSI_T_NO_EVENT 0
+#define VIRTIO_SCSI_T_TRANSPORT_RESET 1
+#define VIRTIO_SCSI_T_ASYNC_NOTIFY 2
+#define VIRTIO_SCSI_T_PARAM_CHANGE 3
+
+/* Reasons of transport reset event */
+#define VIRTIO_SCSI_EVT_RESET_HARD 0
+#define VIRTIO_SCSI_EVT_RESET_RESCAN 1
+#define VIRTIO_SCSI_EVT_RESET_REMOVED 2
+
+#define VIRTIO_SCSI_S_SIMPLE 0
+#define VIRTIO_SCSI_S_ORDERED 1
+#define VIRTIO_SCSI_S_HEAD 2
+#define VIRTIO_SCSI_S_ACA 3
+
+
+#endif /* _LINUX_VIRTIO_SCSI_H */
diff --git a/kvmtool/ioeventfd.c b/kvmtool/ioeventfd.c
new file mode 100644
index 0000000..3ae8267
--- /dev/null
+++ b/kvmtool/ioeventfd.c
@@ -0,0 +1,224 @@
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <pthread.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <signal.h>
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/types.h>
+
+#include "kvm/ioeventfd.h"
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#define IOEVENTFD_MAX_EVENTS 20
+
+static struct epoll_event events[IOEVENTFD_MAX_EVENTS];
+static int epoll_fd, epoll_stop_fd;
+static LIST_HEAD(used_ioevents);
+static bool ioeventfd_avail;
+
+static void *ioeventfd__thread(void *param)
+{
+ u64 tmp = 1;
+
+ kvm__set_thread_name("ioeventfd-worker");
+
+ for (;;) {
+ int nfds, i;
+
+ nfds = epoll_wait(epoll_fd, events, IOEVENTFD_MAX_EVENTS, -1);
+ for (i = 0; i < nfds; i++) {
+ struct ioevent *ioevent;
+
+ if (events[i].data.fd == epoll_stop_fd)
+ goto done;
+
+ ioevent = events[i].data.ptr;
+
+ if (read(ioevent->fd, &tmp, sizeof(tmp)) < 0)
+ die("Failed reading event");
+
+ ioevent->fn(ioevent->fn_kvm, ioevent->fn_ptr);
+ }
+ }
+
+done:
+ tmp = write(epoll_stop_fd, &tmp, sizeof(tmp));
+
+ return NULL;
+}
+
+static int ioeventfd__start(void)
+{
+ pthread_t thread;
+
+ if (!ioeventfd_avail)
+ return -ENOSYS;
+
+ return pthread_create(&thread, NULL, ioeventfd__thread, NULL);
+}
+
+int ioeventfd__init(struct kvm *kvm)
+{
+ struct epoll_event epoll_event = {.events = EPOLLIN};
+ int r;
+
+ ioeventfd_avail = kvm__supports_extension(kvm, KVM_CAP_IOEVENTFD);
+ if (!ioeventfd_avail)
+ return 1; /* Not fatal, but let caller determine no-go. */
+
+ epoll_fd = epoll_create(IOEVENTFD_MAX_EVENTS);
+ if (epoll_fd < 0)
+ return -errno;
+
+ epoll_stop_fd = eventfd(0, 0);
+ epoll_event.data.fd = epoll_stop_fd;
+
+ r = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, epoll_stop_fd, &epoll_event);
+ if (r < 0)
+ goto cleanup;
+
+ r = ioeventfd__start();
+ if (r < 0)
+ goto cleanup;
+
+ r = 0;
+
+ return r;
+
+cleanup:
+ close(epoll_stop_fd);
+ close(epoll_fd);
+
+ return r;
+}
+base_init(ioeventfd__init);
+
+int ioeventfd__exit(struct kvm *kvm)
+{
+ u64 tmp = 1;
+ int r;
+
+ if (!ioeventfd_avail)
+ return 0;
+
+ r = write(epoll_stop_fd, &tmp, sizeof(tmp));
+ if (r < 0)
+ return r;
+
+ r = read(epoll_stop_fd, &tmp, sizeof(tmp));
+ if (r < 0)
+ return r;
+
+ close(epoll_fd);
+ close(epoll_stop_fd);
+
+ return 0;
+}
+base_exit(ioeventfd__exit);
+
+int ioeventfd__add_event(struct ioevent *ioevent, int flags)
+{
+ struct kvm_ioeventfd kvm_ioevent;
+ struct epoll_event epoll_event;
+ struct ioevent *new_ioevent;
+ int event, r;
+
+ if (!ioeventfd_avail)
+ return -ENOSYS;
+
+ new_ioevent = malloc(sizeof(*new_ioevent));
+ if (new_ioevent == NULL)
+ return -ENOMEM;
+
+ *new_ioevent = *ioevent;
+ event = new_ioevent->fd;
+
+ kvm_ioevent = (struct kvm_ioeventfd) {
+ .addr = ioevent->io_addr,
+ .len = ioevent->io_len,
+ .datamatch = ioevent->datamatch,
+ .fd = event,
+ .flags = KVM_IOEVENTFD_FLAG_DATAMATCH,
+ };
+
+ /*
+ * For architectures that don't recognize PIO accesses, always register
+ * on the MMIO bus. Otherwise PIO accesses will cause returns to
+ * userspace.
+ */
+ if (KVM_IOEVENTFD_HAS_PIO && flags & IOEVENTFD_FLAG_PIO)
+ kvm_ioevent.flags |= KVM_IOEVENTFD_FLAG_PIO;
+
+ r = ioctl(ioevent->fn_kvm->vm_fd, KVM_IOEVENTFD, &kvm_ioevent);
+ if (r) {
+ r = -errno;
+ goto cleanup;
+ }
+
+ if (flags & IOEVENTFD_FLAG_USER_POLL) {
+ epoll_event = (struct epoll_event) {
+ .events = EPOLLIN,
+ .data.ptr = new_ioevent,
+ };
+
+ r = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, event, &epoll_event);
+ if (r) {
+ r = -errno;
+ goto cleanup;
+ }
+ }
+
+ new_ioevent->flags = kvm_ioevent.flags;
+ list_add_tail(&new_ioevent->list, &used_ioevents);
+
+ return 0;
+
+cleanup:
+ free(new_ioevent);
+ return r;
+}
+
+int ioeventfd__del_event(u64 addr, u64 datamatch)
+{
+ struct kvm_ioeventfd kvm_ioevent;
+ struct ioevent *ioevent;
+ u8 found = 0;
+
+ if (!ioeventfd_avail)
+ return -ENOSYS;
+
+ list_for_each_entry(ioevent, &used_ioevents, list) {
+ if (ioevent->io_addr == addr &&
+ ioevent->datamatch == datamatch) {
+ found = 1;
+ break;
+ }
+ }
+
+ if (found == 0 || ioevent == NULL)
+ return -ENOENT;
+
+ kvm_ioevent = (struct kvm_ioeventfd) {
+ .fd = ioevent->fd,
+ .addr = ioevent->io_addr,
+ .len = ioevent->io_len,
+ .datamatch = ioevent->datamatch,
+ .flags = ioevent->flags
+ | KVM_IOEVENTFD_FLAG_DEASSIGN,
+ };
+
+ ioctl(ioevent->fn_kvm->vm_fd, KVM_IOEVENTFD, &kvm_ioevent);
+
+ epoll_ctl(epoll_fd, EPOLL_CTL_DEL, ioevent->fd, NULL);
+
+ list_del(&ioevent->list);
+
+ close(ioevent->fd);
+ free(ioevent);
+
+ return 0;
+}
diff --git a/kvmtool/ioport.c b/kvmtool/ioport.c
new file mode 100644
index 0000000..844a832
--- /dev/null
+++ b/kvmtool/ioport.c
@@ -0,0 +1,235 @@
+#include "kvm/ioport.h"
+
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+#include "kvm/rbtree-interval.h"
+#include "kvm/mutex.h"
+
+#include <linux/kvm.h> /* for KVM_EXIT_* */
+#include <linux/types.h>
+
+#include <stdbool.h>
+#include <limits.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#define ioport_node(n) rb_entry(n, struct ioport, node)
+
+static DEFINE_MUTEX(ioport_lock);
+
+static struct rb_root ioport_tree = RB_ROOT;
+
+static struct ioport *ioport_search(struct rb_root *root, u64 addr)
+{
+ struct rb_int_node *node;
+
+ node = rb_int_search_single(root, addr);
+ if (node == NULL)
+ return NULL;
+
+ return ioport_node(node);
+}
+
+static int ioport_insert(struct rb_root *root, struct ioport *data)
+{
+ return rb_int_insert(root, &data->node);
+}
+
+static void ioport_remove(struct rb_root *root, struct ioport *data)
+{
+ rb_int_erase(root, &data->node);
+}
+
+static struct ioport *ioport_get(struct rb_root *root, u64 addr)
+{
+ struct ioport *ioport;
+
+ mutex_lock(&ioport_lock);
+ ioport = ioport_search(root, addr);
+ if (ioport)
+ ioport->refcount++;
+ mutex_unlock(&ioport_lock);
+
+ return ioport;
+}
+
+/* Called with ioport_lock held. */
+static void ioport_unregister(struct rb_root *root, struct ioport *data)
+{
+ device__unregister(&data->dev_hdr);
+ ioport_remove(root, data);
+ free(data);
+}
+
+static void ioport_put(struct rb_root *root, struct ioport *data)
+{
+ mutex_lock(&ioport_lock);
+ data->refcount--;
+ if (data->remove && data->refcount == 0)
+ ioport_unregister(root, data);
+ mutex_unlock(&ioport_lock);
+}
+
+#ifdef CONFIG_HAS_LIBFDT
+static void generate_ioport_fdt_node(void *fdt,
+ struct device_header *dev_hdr,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq,
+ enum irq_type))
+{
+ struct ioport *ioport = container_of(dev_hdr, struct ioport, dev_hdr);
+ struct ioport_operations *ops = ioport->ops;
+
+ if (ops->generate_fdt_node)
+ ops->generate_fdt_node(ioport, fdt, generate_irq_prop);
+}
+#else
+static void generate_ioport_fdt_node(void *fdt,
+ struct device_header *dev_hdr,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq,
+ enum irq_type))
+{
+ die("Unable to generate device tree nodes without libfdt\n");
+}
+#endif
+
+int ioport__register(struct kvm *kvm, u16 port, struct ioport_operations *ops, int count, void *param)
+{
+ struct ioport *entry;
+ int r;
+
+ entry = malloc(sizeof(*entry));
+ if (entry == NULL)
+ return -ENOMEM;
+
+ *entry = (struct ioport) {
+ .node = RB_INT_INIT(port, port + count),
+ .ops = ops,
+ .priv = param,
+ .dev_hdr = (struct device_header) {
+ .bus_type = DEVICE_BUS_IOPORT,
+ .data = generate_ioport_fdt_node,
+ },
+ /*
+ * Start from 0 because ioport__unregister() doesn't decrement
+ * the reference count.
+ */
+ .refcount = 0,
+ .remove = false,
+ };
+
+ mutex_lock(&ioport_lock);
+ r = ioport_insert(&ioport_tree, entry);
+ if (r < 0)
+ goto out_free;
+ r = device__register(&entry->dev_hdr);
+ if (r < 0)
+ goto out_remove;
+ mutex_unlock(&ioport_lock);
+
+ return port;
+
+out_remove:
+ ioport_remove(&ioport_tree, entry);
+out_free:
+ free(entry);
+ mutex_unlock(&ioport_lock);
+ return r;
+}
+
+int ioport__unregister(struct kvm *kvm, u16 port)
+{
+ struct ioport *entry;
+
+ mutex_lock(&ioport_lock);
+ entry = ioport_search(&ioport_tree, port);
+ if (!entry) {
+ mutex_unlock(&ioport_lock);
+ return -ENOENT;
+ }
+ /* The same reasoning from kvm__deregister_mmio() applies. */
+ if (entry->refcount == 0)
+ ioport_unregister(&ioport_tree, entry);
+ else
+ entry->remove = true;
+ mutex_unlock(&ioport_lock);
+
+ return 0;
+}
+
+static void ioport__unregister_all(void)
+{
+ struct ioport *entry;
+ struct rb_node *rb;
+ struct rb_int_node *rb_node;
+
+ rb = rb_first(&ioport_tree);
+ while (rb) {
+ rb_node = rb_int(rb);
+ entry = ioport_node(rb_node);
+ ioport_unregister(&ioport_tree, entry);
+ rb = rb_first(&ioport_tree);
+ }
+}
+
+static const char *to_direction(int direction)
+{
+ if (direction == KVM_EXIT_IO_IN)
+ return "IN";
+ else
+ return "OUT";
+}
+
+static void ioport_error(u16 port, void *data, int direction, int size, u32 count)
+{
+ fprintf(stderr, "IO error: %s port=%x, size=%d, count=%u\n", to_direction(direction), port, size, count);
+}
+
+bool kvm__emulate_io(struct kvm_cpu *vcpu, u16 port, void *data, int direction, int size, u32 count)
+{
+ struct ioport_operations *ops;
+ bool ret = false;
+ struct ioport *entry;
+ void *ptr = data;
+ struct kvm *kvm = vcpu->kvm;
+
+ entry = ioport_get(&ioport_tree, port);
+ if (!entry)
+ goto out;
+
+ ops = entry->ops;
+
+ while (count--) {
+ if (direction == KVM_EXIT_IO_IN && ops->io_in)
+ ret = ops->io_in(entry, vcpu, port, ptr, size);
+ else if (direction == KVM_EXIT_IO_OUT && ops->io_out)
+ ret = ops->io_out(entry, vcpu, port, ptr, size);
+
+ ptr += size;
+ }
+
+ ioport_put(&ioport_tree, entry);
+
+out:
+ if (ret)
+ return true;
+
+ if (kvm->cfg.ioport_debug)
+ ioport_error(port, data, direction, size, count);
+
+ return !kvm->cfg.ioport_debug;
+}
+
+int ioport__init(struct kvm *kvm)
+{
+ return ioport__setup_arch(kvm);
+}
+dev_base_init(ioport__init);
+
+int ioport__exit(struct kvm *kvm)
+{
+ ioport__unregister_all();
+ return 0;
+}
+dev_base_exit(ioport__exit);
diff --git a/kvmtool/irq.c b/kvmtool/irq.c
new file mode 100644
index 0000000..cdcf992
--- /dev/null
+++ b/kvmtool/irq.c
@@ -0,0 +1,209 @@
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <linux/types.h>
+#include <linux/kvm.h>
+#include <errno.h>
+
+#include "kvm/kvm.h"
+#include "kvm/irq.h"
+#include "kvm/kvm-arch.h"
+
+static u8 next_line = KVM_IRQ_OFFSET;
+static int allocated_gsis = 0;
+
+int next_gsi;
+
+struct msi_routing_ops irq__default_routing_ops;
+struct msi_routing_ops *msi_routing_ops = &irq__default_routing_ops;
+
+struct kvm_irq_routing *irq_routing = NULL;
+
+int irq__alloc_line(void)
+{
+ return next_line++;
+}
+
+int irq__get_nr_allocated_lines(void)
+{
+ return next_line - KVM_IRQ_OFFSET;
+}
+
+int irq__allocate_routing_entry(void)
+{
+ size_t table_size = sizeof(struct kvm_irq_routing);
+ size_t old_size = table_size;
+ int nr_entries = 0;
+
+ if (irq_routing)
+ nr_entries = irq_routing->nr;
+
+ if (nr_entries < allocated_gsis)
+ return 0;
+
+ old_size += sizeof(struct kvm_irq_routing_entry) * allocated_gsis;
+ allocated_gsis = ALIGN(nr_entries + 1, 32);
+ table_size += sizeof(struct kvm_irq_routing_entry) * allocated_gsis;
+ irq_routing = realloc(irq_routing, table_size);
+
+ if (irq_routing == NULL)
+ return -ENOMEM;
+ memset((void *)irq_routing + old_size, 0, table_size - old_size);
+
+ irq_routing->nr = nr_entries;
+ irq_routing->flags = 0;
+
+ return 0;
+}
+
+static bool check_for_irq_routing(struct kvm *kvm)
+{
+ static int has_irq_routing = 0;
+
+ if (has_irq_routing == 0) {
+ if (kvm__supports_extension(kvm, KVM_CAP_IRQ_ROUTING))
+ has_irq_routing = 1;
+ else
+ has_irq_routing = -1;
+ }
+
+ return has_irq_routing > 0;
+}
+
+static int irq__update_msix_routes(struct kvm *kvm,
+ struct kvm_irq_routing_entry *entry)
+{
+ return ioctl(kvm->vm_fd, KVM_SET_GSI_ROUTING, irq_routing);
+}
+
+static bool irq__default_can_signal_msi(struct kvm *kvm)
+{
+ return kvm__supports_extension(kvm, KVM_CAP_SIGNAL_MSI);
+}
+
+static int irq__default_signal_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+ return ioctl(kvm->vm_fd, KVM_SIGNAL_MSI, msi);
+}
+
+struct msi_routing_ops irq__default_routing_ops = {
+ .update_route = irq__update_msix_routes,
+ .signal_msi = irq__default_signal_msi,
+ .can_signal_msi = irq__default_can_signal_msi,
+};
+
+bool irq__can_signal_msi(struct kvm *kvm)
+{
+ return msi_routing_ops->can_signal_msi(kvm);
+}
+
+int irq__signal_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+ return msi_routing_ops->signal_msi(kvm, msi);
+}
+
+int irq__add_msix_route(struct kvm *kvm, struct msi_msg *msg, u32 device_id)
+{
+ int r;
+ struct kvm_irq_routing_entry *entry;
+
+ if (!check_for_irq_routing(kvm))
+ return -ENXIO;
+
+ r = irq__allocate_routing_entry();
+ if (r)
+ return r;
+
+ entry = &irq_routing->entries[irq_routing->nr];
+ *entry = (struct kvm_irq_routing_entry) {
+ .gsi = next_gsi,
+ .type = KVM_IRQ_ROUTING_MSI,
+ .u.msi.address_hi = msg->address_hi,
+ .u.msi.address_lo = msg->address_lo,
+ .u.msi.data = msg->data,
+ };
+
+ if (kvm->msix_needs_devid) {
+ entry->flags = KVM_MSI_VALID_DEVID;
+ entry->u.msi.devid = device_id;
+ }
+
+ irq_routing->nr++;
+
+ r = msi_routing_ops->update_route(kvm, entry);
+ if (r)
+ return r;
+
+ return next_gsi++;
+}
+
+static bool update_data(u32 *ptr, u32 newdata)
+{
+ if (*ptr == newdata)
+ return false;
+
+ *ptr = newdata;
+ return true;
+}
+
+void irq__update_msix_route(struct kvm *kvm, u32 gsi, struct msi_msg *msg)
+{
+ struct kvm_irq_routing_msi *entry;
+ unsigned int i;
+ bool changed;
+
+ for (i = 0; i < irq_routing->nr; i++)
+ if (gsi == irq_routing->entries[i].gsi)
+ break;
+ if (i == irq_routing->nr)
+ return;
+
+ entry = &irq_routing->entries[i].u.msi;
+
+ changed = update_data(&entry->address_hi, msg->address_hi);
+ changed |= update_data(&entry->address_lo, msg->address_lo);
+ changed |= update_data(&entry->data, msg->data);
+
+ if (!changed)
+ return;
+
+ if (msi_routing_ops->update_route(kvm, &irq_routing->entries[i]))
+ die_perror("KVM_SET_GSI_ROUTING");
+}
+
+int irq__common_add_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd,
+ int resample_fd)
+{
+ struct kvm_irqfd irqfd = {
+ .fd = trigger_fd,
+ .gsi = gsi,
+ .flags = resample_fd > 0 ? KVM_IRQFD_FLAG_RESAMPLE : 0,
+ .resamplefd = resample_fd,
+ };
+
+ /* If we emulate MSI routing, translate the MSI to the corresponding IRQ */
+ if (msi_routing_ops->translate_gsi)
+ irqfd.gsi = msi_routing_ops->translate_gsi(kvm, gsi);
+
+ return ioctl(kvm->vm_fd, KVM_IRQFD, &irqfd);
+}
+
+void irq__common_del_irqfd(struct kvm *kvm, unsigned int gsi, int trigger_fd)
+{
+ struct kvm_irqfd irqfd = {
+ .fd = trigger_fd,
+ .gsi = gsi,
+ .flags = KVM_IRQFD_FLAG_DEASSIGN,
+ };
+
+ if (msi_routing_ops->translate_gsi)
+ irqfd.gsi = msi_routing_ops->translate_gsi(kvm, gsi);
+
+ ioctl(kvm->vm_fd, KVM_IRQFD, &irqfd);
+}
+
+int __attribute__((weak)) irq__exit(struct kvm *kvm)
+{
+ free(irq_routing);
+ return 0;
+}
+dev_base_exit(irq__exit);
diff --git a/kvmtool/kvm-cmd.c b/kvmtool/kvm-cmd.c
new file mode 100644
index 0000000..2520b08
--- /dev/null
+++ b/kvmtool/kvm-cmd.c
@@ -0,0 +1,91 @@
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+
+/* user defined header files */
+#include "kvm/builtin-debug.h"
+#include "kvm/builtin-pause.h"
+#include "kvm/builtin-resume.h"
+#include "kvm/builtin-balloon.h"
+#include "kvm/builtin-list.h"
+#include "kvm/builtin-version.h"
+#include "kvm/builtin-setup.h"
+#include "kvm/builtin-stop.h"
+#include "kvm/builtin-stat.h"
+#include "kvm/builtin-help.h"
+#include "kvm/builtin-sandbox.h"
+#include "kvm/kvm-cmd.h"
+#include "kvm/builtin-run.h"
+#include "kvm/util.h"
+
+struct cmd_struct kvm_commands[] = {
+ { "pause", kvm_cmd_pause, kvm_pause_help, 0 },
+ { "resume", kvm_cmd_resume, kvm_resume_help, 0 },
+ { "debug", kvm_cmd_debug, kvm_debug_help, 0 },
+ { "balloon", kvm_cmd_balloon, kvm_balloon_help, 0 },
+ { "list", kvm_cmd_list, kvm_list_help, 0 },
+ { "version", kvm_cmd_version, NULL, 0 },
+ { "--version", kvm_cmd_version, NULL, 0 },
+ { "stop", kvm_cmd_stop, kvm_stop_help, 0 },
+ { "stat", kvm_cmd_stat, kvm_stat_help, 0 },
+ { "help", kvm_cmd_help, NULL, 0 },
+ { "setup", kvm_cmd_setup, kvm_setup_help, 0 },
+ { "run", kvm_cmd_run, kvm_run_help, 0 },
+ { "sandbox", kvm_cmd_sandbox, kvm_run_help, 0 },
+ { NULL, NULL, NULL, 0 },
+};
+
+/*
+ * kvm_get_command: Searches the command in an array of the commands and
+ * returns a pointer to cmd_struct if a match is found.
+ *
+ * Input parameters:
+ * command: Array of possible commands. The last entry in the array must be
+ * NULL.
+ * cmd: A string command to search in the array
+ *
+ * Return Value:
+ * NULL: If the cmd is not matched with any of the command in the command array
+ * p: Pointer to cmd_struct of the matching command
+ */
+struct cmd_struct *kvm_get_command(struct cmd_struct *command,
+ const char *cmd)
+{
+ struct cmd_struct *p = command;
+
+ while (p->cmd) {
+ if (!strcmp(p->cmd, cmd))
+ return p;
+ p++;
+ }
+ return NULL;
+}
+
+int handle_command(struct cmd_struct *command, int argc, const char **argv)
+{
+ struct cmd_struct *p;
+ const char *prefix = NULL;
+ int ret = 0;
+
+ if (!argv || !*argv) {
+ p = kvm_get_command(command, "help");
+ BUG_ON(!p);
+ return p->fn(argc, argv, prefix);
+ }
+
+ p = kvm_get_command(command, argv[0]);
+ if (!p) {
+ p = kvm_get_command(command, "help");
+ BUG_ON(!p);
+ p->fn(0, NULL, prefix);
+ return EINVAL;
+ }
+
+ ret = p->fn(argc - 1, &argv[1], prefix);
+ if (ret < 0) {
+ if (errno == EPERM)
+ die("Permission error - are you root?");
+ }
+
+ return ret;
+}
diff --git a/kvmtool/kvm-cpu.c b/kvmtool/kvm-cpu.c
new file mode 100644
index 0000000..7dec088
--- /dev/null
+++ b/kvmtool/kvm-cpu.c
@@ -0,0 +1,335 @@
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/symbol.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/virtio.h"
+#include "kvm/mutex.h"
+#include "kvm/barrier.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/eventfd.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+
+extern __thread struct kvm_cpu *current_kvm_cpu;
+
+int __attribute__((weak)) kvm_cpu__get_endianness(struct kvm_cpu *vcpu)
+{
+ return VIRTIO_ENDIAN_HOST;
+}
+
+void kvm_cpu__enable_singlestep(struct kvm_cpu *vcpu)
+{
+ struct kvm_guest_debug debug = {
+ .control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP,
+ };
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_GUEST_DEBUG, &debug) < 0)
+ pr_warning("KVM_SET_GUEST_DEBUG failed");
+}
+
+void kvm_cpu__run(struct kvm_cpu *vcpu)
+{
+ int err;
+
+ if (!vcpu->is_running)
+ return;
+
+ err = ioctl(vcpu->vcpu_fd, KVM_RUN, 0);
+ if (err < 0 && (errno != EINTR && errno != EAGAIN))
+ die_perror("KVM_RUN failed");
+}
+
+static void kvm_cpu_signal_handler(int signum)
+{
+ if (signum == SIGKVMEXIT) {
+ if (current_kvm_cpu && current_kvm_cpu->is_running)
+ current_kvm_cpu->is_running = false;
+ } else if (signum == SIGKVMPAUSE) {
+ if (current_kvm_cpu->paused)
+ die("Pause signaled for already paused CPU\n");
+
+ /* pause_lock is held by kvm__pause() */
+ current_kvm_cpu->paused = 1;
+
+ /*
+ * This is a blocking function and uses locks. It is safe
+ * to call it for this signal as a second pause event should
+ * not be send to this thread until it acquires and releases
+ * the pause_lock.
+ */
+ kvm__notify_paused();
+ }
+
+ /* For SIGKVMTASK cpu->task is already set */
+}
+
+static void kvm_cpu__handle_coalesced_mmio(struct kvm_cpu *cpu)
+{
+ if (cpu->ring) {
+ while (cpu->ring->first != cpu->ring->last) {
+ struct kvm_coalesced_mmio *m;
+ m = &cpu->ring->coalesced_mmio[cpu->ring->first];
+ kvm_cpu__emulate_mmio(cpu,
+ m->phys_addr,
+ m->data,
+ m->len,
+ 1);
+ cpu->ring->first = (cpu->ring->first + 1) % KVM_COALESCED_MMIO_MAX;
+ }
+ }
+}
+
+static DEFINE_MUTEX(task_lock);
+static int task_eventfd;
+
+static void kvm_cpu__run_task(struct kvm_cpu *cpu)
+{
+ u64 inc = 1;
+
+ pr_debug("Running task %p on cpu %lu", cpu->task, cpu->cpu_id);
+
+ /* Make sure we see the store to cpu->task */
+ rmb();
+ cpu->task->func(cpu, cpu->task->data);
+
+ /* Clear task before we signal completion */
+ cpu->task = NULL;
+ wmb();
+
+ if (write(task_eventfd, &inc, sizeof(inc)) < 0)
+ die("Failed notifying of completed task.");
+}
+
+void kvm_cpu__run_on_all_cpus(struct kvm *kvm, struct kvm_cpu_task *task)
+{
+ int i, done = 0;
+
+ pr_debug("Running task %p on all cpus", task);
+
+ mutex_lock(&task_lock);
+
+ for (i = 0; i < kvm->nrcpus; i++) {
+ if (kvm->cpus[i]->task) {
+ /* Should never happen */
+ die("CPU %d already has a task pending!", i);
+ }
+
+ kvm->cpus[i]->task = task;
+ wmb();
+
+ if (kvm->cpus[i] == current_kvm_cpu)
+ kvm_cpu__run_task(current_kvm_cpu);
+ else
+ pthread_kill(kvm->cpus[i]->thread, SIGKVMTASK);
+ }
+
+ while (done < kvm->nrcpus) {
+ u64 count;
+
+ if (read(task_eventfd, &count, sizeof(count)) < 0)
+ die("Failed reading task eventfd");
+
+ done += count;
+ }
+
+ mutex_unlock(&task_lock);
+}
+
+int kvm_cpu__start(struct kvm_cpu *cpu)
+{
+ sigset_t sigset;
+
+ sigemptyset(&sigset);
+ sigaddset(&sigset, SIGALRM);
+
+ pthread_sigmask(SIG_BLOCK, &sigset, NULL);
+
+ signal(SIGKVMEXIT, kvm_cpu_signal_handler);
+ signal(SIGKVMPAUSE, kvm_cpu_signal_handler);
+ signal(SIGKVMTASK, kvm_cpu_signal_handler);
+
+ kvm_cpu__reset_vcpu(cpu);
+
+ if (cpu->kvm->cfg.single_step)
+ kvm_cpu__enable_singlestep(cpu);
+
+ while (cpu->is_running) {
+ if (cpu->needs_nmi) {
+ kvm_cpu__arch_nmi(cpu);
+ cpu->needs_nmi = 0;
+ }
+
+ if (cpu->task)
+ kvm_cpu__run_task(cpu);
+
+ kvm_cpu__run(cpu);
+
+ switch (cpu->kvm_run->exit_reason) {
+ case KVM_EXIT_UNKNOWN:
+ break;
+ case KVM_EXIT_DEBUG:
+ kvm_cpu__show_registers(cpu);
+ kvm_cpu__show_code(cpu);
+ break;
+ case KVM_EXIT_IO: {
+ bool ret;
+
+ ret = kvm_cpu__emulate_io(cpu,
+ cpu->kvm_run->io.port,
+ (u8 *)cpu->kvm_run +
+ cpu->kvm_run->io.data_offset,
+ cpu->kvm_run->io.direction,
+ cpu->kvm_run->io.size,
+ cpu->kvm_run->io.count);
+
+ if (!ret)
+ goto panic_kvm;
+ break;
+ }
+ case KVM_EXIT_MMIO: {
+ bool ret;
+
+ /*
+ * If we had MMIO exit, coalesced ring should be processed
+ * *before* processing the exit itself
+ */
+ kvm_cpu__handle_coalesced_mmio(cpu);
+
+ ret = kvm_cpu__emulate_mmio(cpu,
+ cpu->kvm_run->mmio.phys_addr,
+ cpu->kvm_run->mmio.data,
+ cpu->kvm_run->mmio.len,
+ cpu->kvm_run->mmio.is_write);
+
+ if (!ret)
+ goto panic_kvm;
+ break;
+ }
+ case KVM_EXIT_INTR:
+ if (cpu->is_running)
+ break;
+ goto exit_kvm;
+ case KVM_EXIT_SHUTDOWN:
+ goto exit_kvm;
+ case KVM_EXIT_SYSTEM_EVENT:
+ /*
+ * Print the type of system event and
+ * treat all system events as shutdown request.
+ */
+ switch (cpu->kvm_run->system_event.type) {
+ default:
+ pr_warning("unknown system event type %d",
+ cpu->kvm_run->system_event.type);
+ /* fall through for now */
+ case KVM_SYSTEM_EVENT_RESET:
+ /* Fall through for now */
+ case KVM_SYSTEM_EVENT_SHUTDOWN:
+ /*
+ * Ensure that all VCPUs are torn down,
+ * regardless of which CPU generated the event.
+ */
+ kvm__reboot(cpu->kvm);
+ goto exit_kvm;
+ };
+ break;
+ default: {
+ bool ret;
+
+ ret = kvm_cpu__handle_exit(cpu);
+ if (!ret)
+ goto panic_kvm;
+ break;
+ }
+ }
+ kvm_cpu__handle_coalesced_mmio(cpu);
+ }
+
+exit_kvm:
+ return 0;
+
+panic_kvm:
+ return 1;
+}
+
+int kvm_cpu__init(struct kvm *kvm)
+{
+ int max_cpus, recommended_cpus, i;
+
+ max_cpus = kvm__max_cpus(kvm);
+ recommended_cpus = kvm__recommended_cpus(kvm);
+
+ if (kvm->cfg.nrcpus > max_cpus) {
+ printf(" # Limit the number of CPUs to %d\n", max_cpus);
+ kvm->cfg.nrcpus = max_cpus;
+ } else if (kvm->cfg.nrcpus > recommended_cpus) {
+ printf(" # Warning: The maximum recommended amount of VCPUs"
+ " is %d\n", recommended_cpus);
+ }
+
+ kvm->nrcpus = kvm->cfg.nrcpus;
+
+ task_eventfd = eventfd(0, 0);
+ if (task_eventfd < 0) {
+ pr_warning("Couldn't create task_eventfd");
+ return task_eventfd;
+ }
+
+ /* Alloc one pointer too many, so array ends up 0-terminated */
+ kvm->cpus = calloc(kvm->nrcpus + 1, sizeof(void *));
+ if (!kvm->cpus) {
+ pr_warning("Couldn't allocate array for %d CPUs", kvm->nrcpus);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < kvm->nrcpus; i++) {
+ kvm->cpus[i] = kvm_cpu__arch_init(kvm, i);
+ if (!kvm->cpus[i]) {
+ pr_warning("unable to initialize KVM VCPU");
+ goto fail_alloc;
+ }
+ }
+
+ return 0;
+
+fail_alloc:
+ for (i = 0; i < kvm->nrcpus; i++)
+ free(kvm->cpus[i]);
+ return -ENOMEM;
+}
+base_init(kvm_cpu__init);
+
+int kvm_cpu__exit(struct kvm *kvm)
+{
+ int i, r;
+ void *ret = NULL;
+
+ kvm_cpu__delete(kvm->cpus[0]);
+ kvm->cpus[0] = NULL;
+
+ kvm__pause(kvm);
+ for (i = 1; i < kvm->nrcpus; i++) {
+ if (kvm->cpus[i]->is_running) {
+ pthread_kill(kvm->cpus[i]->thread, SIGKVMEXIT);
+ if (pthread_join(kvm->cpus[i]->thread, &ret) != 0)
+ die("pthread_join");
+ kvm_cpu__delete(kvm->cpus[i]);
+ }
+ if (ret == NULL)
+ r = 0;
+ }
+ kvm__continue(kvm);
+
+ free(kvm->cpus);
+
+ kvm->nrcpus = 0;
+
+ close(task_eventfd);
+
+ return r;
+}
diff --git a/kvmtool/kvm-ipc.c b/kvmtool/kvm-ipc.c
new file mode 100644
index 0000000..23f7b12
--- /dev/null
+++ b/kvmtool/kvm-ipc.c
@@ -0,0 +1,556 @@
+#include <sys/epoll.h>
+#include <sys/un.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/eventfd.h>
+#include <dirent.h>
+
+#include "kvm/kvm-ipc.h"
+#include "kvm/rwsem.h"
+#include "kvm/read-write.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/builtin-debug.h"
+#include "kvm/strbuf.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/8250-serial.h"
+
+struct kvm_ipc_head {
+ u32 type;
+ u32 len;
+};
+
+#define KVM_IPC_MAX_MSGS 16
+
+#define KVM_SOCK_SUFFIX ".sock"
+#define KVM_SOCK_SUFFIX_LEN ((ssize_t)sizeof(KVM_SOCK_SUFFIX) - 1)
+
+extern __thread struct kvm_cpu *current_kvm_cpu;
+static void (*msgs[KVM_IPC_MAX_MSGS])(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg);
+static DECLARE_RWSEM(msgs_rwlock);
+static int epoll_fd, server_fd, stop_fd;
+static pthread_t thread;
+
+static int kvm__create_socket(struct kvm *kvm)
+{
+ char full_name[PATH_MAX];
+ int s;
+ struct sockaddr_un local;
+ int len, r;
+
+ /* This usually 108 bytes long */
+ BUILD_BUG_ON(sizeof(local.sun_path) < 32);
+
+ snprintf(full_name, sizeof(full_name), "%s/%s%s",
+ kvm__get_dir(), kvm->cfg.guest_name, KVM_SOCK_SUFFIX);
+
+ s = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (s < 0) {
+ perror("socket");
+ return s;
+ }
+
+ local.sun_family = AF_UNIX;
+ strlcpy(local.sun_path, full_name, sizeof(local.sun_path));
+ len = strlen(local.sun_path) + sizeof(local.sun_family);
+ r = bind(s, (struct sockaddr *)&local, len);
+ /* Check for an existing socket file */
+ if (r < 0 && errno == EADDRINUSE) {
+ r = connect(s, (struct sockaddr *)&local, len);
+ if (r == 0) {
+ /*
+ * If we could connect, there is already a guest
+ * using this same name. This should not happen
+ * for PID derived names, but could happen for user
+ * provided guest names.
+ */
+ pr_err("Guest socket file %s already exists.",
+ full_name);
+ r = -EEXIST;
+ goto fail;
+ }
+ if (errno == ECONNREFUSED) {
+ /*
+ * This is a ghost socket file, with no-one listening
+ * on the other end. Since kvmtool will only bind
+ * above when creating a new guest, there is no
+ * danger in just removing the file and re-trying.
+ */
+ unlink(full_name);
+ pr_info("Removed ghost socket file \"%s\".", full_name);
+ r = bind(s, (struct sockaddr *)&local, len);
+ }
+ }
+ if (r < 0) {
+ perror("bind");
+ goto fail;
+ }
+
+ r = listen(s, 5);
+ if (r < 0) {
+ perror("listen");
+ goto fail;
+ }
+
+ return s;
+
+fail:
+ close(s);
+ return r;
+}
+
+void kvm__remove_socket(const char *name)
+{
+ char full_name[PATH_MAX];
+
+ snprintf(full_name, sizeof(full_name), "%s/%s%s",
+ kvm__get_dir(), name, KVM_SOCK_SUFFIX);
+ unlink(full_name);
+}
+
+int kvm__get_sock_by_instance(const char *name)
+{
+ int s, len, r;
+ char sock_file[PATH_MAX];
+ struct sockaddr_un local;
+
+ snprintf(sock_file, sizeof(sock_file), "%s/%s%s",
+ kvm__get_dir(), name, KVM_SOCK_SUFFIX);
+ s = socket(AF_UNIX, SOCK_STREAM, 0);
+
+ local.sun_family = AF_UNIX;
+ strlcpy(local.sun_path, sock_file, sizeof(local.sun_path));
+ len = strlen(local.sun_path) + sizeof(local.sun_family);
+
+ r = connect(s, (struct sockaddr *)&local, len);
+ if (r < 0 && errno == ECONNREFUSED) {
+ /* Clean up the ghost socket file */
+ unlink(local.sun_path);
+ pr_info("Removed ghost socket file \"%s\".", sock_file);
+ return r;
+ } else if (r < 0) {
+ return r;
+ }
+
+ return s;
+}
+
+static bool is_socket(const char *base_path, const struct dirent *dent)
+{
+ switch (dent->d_type) {
+ case DT_SOCK:
+ return true;
+
+ case DT_UNKNOWN: {
+ char path[PATH_MAX];
+ struct stat st;
+
+ sprintf(path, "%s/%s", base_path, dent->d_name);
+ if (stat(path, &st))
+ return false;
+
+ return S_ISSOCK(st.st_mode);
+ }
+ default:
+ return false;
+ }
+}
+
+int kvm__enumerate_instances(int (*callback)(const char *name, int fd))
+{
+ int sock;
+ DIR *dir;
+ struct dirent *entry;
+ int ret = 0;
+ const char *path;
+
+ path = kvm__get_dir();
+
+ dir = opendir(path);
+ if (!dir)
+ return -errno;
+
+ for (;;) {
+ entry = readdir(dir);
+ if (!entry)
+ break;
+ if (is_socket(path, entry)) {
+ ssize_t name_len = strlen(entry->d_name);
+ char *p;
+
+ if (name_len <= KVM_SOCK_SUFFIX_LEN)
+ continue;
+
+ p = &entry->d_name[name_len - KVM_SOCK_SUFFIX_LEN];
+ if (memcmp(KVM_SOCK_SUFFIX, p, KVM_SOCK_SUFFIX_LEN))
+ continue;
+
+ *p = 0;
+ sock = kvm__get_sock_by_instance(entry->d_name);
+ if (sock < 0)
+ continue;
+ ret = callback(entry->d_name, sock);
+ close(sock);
+ if (ret < 0)
+ break;
+ }
+ }
+
+ closedir(dir);
+
+ return ret;
+}
+
+int kvm_ipc__register_handler(u32 type, void (*cb)(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg))
+{
+ if (type >= KVM_IPC_MAX_MSGS)
+ return -ENOSPC;
+
+ down_write(&msgs_rwlock);
+ msgs[type] = cb;
+ up_write(&msgs_rwlock);
+
+ return 0;
+}
+
+int kvm_ipc__send(int fd, u32 type)
+{
+ struct kvm_ipc_head head = {.type = type, .len = 0,};
+
+ if (write_in_full(fd, &head, sizeof(head)) < 0)
+ return -1;
+
+ return 0;
+}
+
+int kvm_ipc__send_msg(int fd, u32 type, u32 len, u8 *msg)
+{
+ struct kvm_ipc_head head = {.type = type, .len = len,};
+
+ if (write_in_full(fd, &head, sizeof(head)) < 0)
+ return -1;
+
+ if (write_in_full(fd, msg, len) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int kvm_ipc__handle(struct kvm *kvm, int fd, u32 type, u32 len, u8 *data)
+{
+ void (*cb)(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg);
+
+ if (type >= KVM_IPC_MAX_MSGS)
+ return -ENOSPC;
+
+ down_read(&msgs_rwlock);
+ cb = msgs[type];
+ up_read(&msgs_rwlock);
+
+ if (cb == NULL) {
+ pr_warning("No device handles type %u\n", type);
+ return -ENODEV;
+ }
+
+ cb(kvm, fd, type, len, data);
+
+ return 0;
+}
+
+static int kvm_ipc__new_conn(int fd)
+{
+ int client;
+ struct epoll_event ev;
+
+ client = accept(fd, NULL, NULL);
+ if (client < 0)
+ return -1;
+
+ ev.events = EPOLLIN | EPOLLRDHUP;
+ ev.data.fd = client;
+ if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, client, &ev) < 0) {
+ close(client);
+ return -1;
+ }
+
+ return client;
+}
+
+static void kvm_ipc__close_conn(int fd)
+{
+ epoll_ctl(epoll_fd, EPOLL_CTL_DEL, fd, NULL);
+ close(fd);
+}
+
+static int kvm_ipc__receive(struct kvm *kvm, int fd)
+{
+ struct kvm_ipc_head head;
+ u8 *msg = NULL;
+ u32 n;
+
+ n = read(fd, &head, sizeof(head));
+ if (n != sizeof(head))
+ goto done;
+
+ msg = malloc(head.len);
+ if (msg == NULL)
+ goto done;
+
+ n = read_in_full(fd, msg, head.len);
+ if (n != head.len)
+ goto done;
+
+ kvm_ipc__handle(kvm, fd, head.type, head.len, msg);
+
+ return 0;
+
+done:
+ free(msg);
+ return -1;
+}
+
+static void *kvm_ipc__thread(void *param)
+{
+ struct epoll_event event;
+ struct kvm *kvm = param;
+
+ kvm__set_thread_name("kvm-ipc");
+
+ for (;;) {
+ int nfds;
+
+ nfds = epoll_wait(epoll_fd, &event, 1, -1);
+ if (nfds > 0) {
+ int fd = event.data.fd;
+
+ if (fd == stop_fd && event.events & EPOLLIN) {
+ break;
+ } else if (fd == server_fd) {
+ int client, r;
+
+ client = kvm_ipc__new_conn(fd);
+ /*
+ * Handle multiple IPC cmd at a time
+ */
+ do {
+ r = kvm_ipc__receive(kvm, client);
+ } while (r == 0);
+
+ } else if (event.events & (EPOLLERR | EPOLLRDHUP | EPOLLHUP)) {
+ kvm_ipc__close_conn(fd);
+ } else {
+ kvm_ipc__receive(kvm, fd);
+ }
+ }
+ }
+
+ return NULL;
+}
+
+static void kvm__pid(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg)
+{
+ pid_t pid = getpid();
+ int r = 0;
+
+ if (type == KVM_IPC_PID)
+ r = write(fd, &pid, sizeof(pid));
+
+ if (r < 0)
+ pr_warning("Failed sending PID");
+}
+
+static void handle_stop(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg)
+{
+ if (WARN_ON(type != KVM_IPC_STOP || len))
+ return;
+
+ kvm__reboot(kvm);
+}
+
+/* Pause/resume the guest using SIGUSR2 */
+static int is_paused;
+
+static void handle_pause(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg)
+{
+ if (WARN_ON(len))
+ return;
+
+ if (type == KVM_IPC_RESUME && is_paused) {
+ kvm->vm_state = KVM_VMSTATE_RUNNING;
+ kvm__continue(kvm);
+ } else if (type == KVM_IPC_PAUSE && !is_paused) {
+ kvm->vm_state = KVM_VMSTATE_PAUSED;
+ ioctl(kvm->vm_fd, KVM_KVMCLOCK_CTRL);
+ kvm__pause(kvm);
+ } else {
+ return;
+ }
+
+ is_paused = !is_paused;
+}
+
+static void handle_vmstate(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg)
+{
+ int r = 0;
+
+ if (type == KVM_IPC_VMSTATE)
+ r = write(fd, &kvm->vm_state, sizeof(kvm->vm_state));
+
+ if (r < 0)
+ pr_warning("Failed sending VMSTATE");
+}
+
+/*
+ * Serialize debug printout so that the output of multiple vcpus does not
+ * get mixed up:
+ */
+static int printout_done;
+
+static void handle_sigusr1(int sig)
+{
+ struct kvm_cpu *cpu = current_kvm_cpu;
+ int fd = kvm_cpu__get_debug_fd();
+
+ if (!cpu || cpu->needs_nmi)
+ return;
+
+ dprintf(fd, "\n #\n # vCPU #%ld's dump:\n #\n", cpu->cpu_id);
+ kvm_cpu__show_registers(cpu);
+ kvm_cpu__show_code(cpu);
+ kvm_cpu__show_page_tables(cpu);
+ fflush(stdout);
+ printout_done = 1;
+}
+
+static void handle_debug(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg)
+{
+ int i;
+ struct debug_cmd_params *params;
+ u32 dbg_type;
+ u32 vcpu;
+
+ if (WARN_ON(type != KVM_IPC_DEBUG || len != sizeof(*params)))
+ return;
+
+ params = (void *)msg;
+ dbg_type = params->dbg_type;
+ vcpu = params->cpu;
+
+ if (dbg_type & KVM_DEBUG_CMD_TYPE_SYSRQ)
+ serial8250__inject_sysrq(kvm, params->sysrq);
+
+ if (dbg_type & KVM_DEBUG_CMD_TYPE_NMI) {
+ if ((int)vcpu >= kvm->nrcpus)
+ return;
+
+ kvm->cpus[vcpu]->needs_nmi = 1;
+ pthread_kill(kvm->cpus[vcpu]->thread, SIGUSR1);
+ }
+
+ if (!(dbg_type & KVM_DEBUG_CMD_TYPE_DUMP))
+ return;
+
+ for (i = 0; i < kvm->nrcpus; i++) {
+ struct kvm_cpu *cpu = kvm->cpus[i];
+
+ if (!cpu)
+ continue;
+
+ printout_done = 0;
+
+ kvm_cpu__set_debug_fd(fd);
+ pthread_kill(cpu->thread, SIGUSR1);
+ /*
+ * Wait for the vCPU to dump state before signalling
+ * the next thread. Since this is debug code it does
+ * not matter that we are burning CPU time a bit:
+ */
+ while (!printout_done)
+ sleep(0);
+ }
+
+ close(fd);
+
+ serial8250__inject_sysrq(kvm, 'p');
+}
+
+int kvm_ipc__init(struct kvm *kvm)
+{
+ int ret;
+ int sock = kvm__create_socket(kvm);
+ struct epoll_event ev = {0};
+
+ server_fd = sock;
+
+ epoll_fd = epoll_create(KVM_IPC_MAX_MSGS);
+ if (epoll_fd < 0) {
+ perror("epoll_create");
+ ret = epoll_fd;
+ goto err;
+ }
+
+ ev.events = EPOLLIN | EPOLLET;
+ ev.data.fd = sock;
+ if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, sock, &ev) < 0) {
+ pr_err("Failed adding socket to epoll");
+ ret = -EFAULT;
+ goto err_epoll;
+ }
+
+ stop_fd = eventfd(0, 0);
+ if (stop_fd < 0) {
+ perror("eventfd");
+ ret = stop_fd;
+ goto err_epoll;
+ }
+
+ ev.events = EPOLLIN | EPOLLET;
+ ev.data.fd = stop_fd;
+ if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, stop_fd, &ev) < 0) {
+ pr_err("Failed adding stop event to epoll");
+ ret = -EFAULT;
+ goto err_stop;
+ }
+
+ if (pthread_create(&thread, NULL, kvm_ipc__thread, kvm) != 0) {
+ pr_err("Failed starting IPC thread");
+ ret = -EFAULT;
+ goto err_stop;
+ }
+
+ kvm_ipc__register_handler(KVM_IPC_PID, kvm__pid);
+ kvm_ipc__register_handler(KVM_IPC_DEBUG, handle_debug);
+ kvm_ipc__register_handler(KVM_IPC_PAUSE, handle_pause);
+ kvm_ipc__register_handler(KVM_IPC_RESUME, handle_pause);
+ kvm_ipc__register_handler(KVM_IPC_STOP, handle_stop);
+ kvm_ipc__register_handler(KVM_IPC_VMSTATE, handle_vmstate);
+ signal(SIGUSR1, handle_sigusr1);
+
+ return 0;
+
+err_stop:
+ close(stop_fd);
+err_epoll:
+ close(epoll_fd);
+err:
+ return ret;
+}
+base_init(kvm_ipc__init);
+
+int kvm_ipc__exit(struct kvm *kvm)
+{
+ u64 val = 1;
+ int ret;
+
+ ret = write(stop_fd, &val, sizeof(val));
+ if (ret < 0)
+ return ret;
+
+ close(server_fd);
+ close(epoll_fd);
+
+ kvm__remove_socket(kvm->cfg.guest_name);
+
+ return ret;
+}
+base_exit(kvm_ipc__exit);
diff --git a/kvmtool/kvm.c b/kvmtool/kvm.c
new file mode 100644
index 0000000..e327541
--- /dev/null
+++ b/kvmtool/kvm.c
@@ -0,0 +1,636 @@
+#include "kvm/kvm.h"
+#include "kvm/read-write.h"
+#include "kvm/util.h"
+#include "kvm/strbuf.h"
+#include "kvm/mutex.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/kvm-ipc.h"
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/list.h>
+#include <linux/err.h>
+
+#include <sys/un.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+#include <limits.h>
+#include <signal.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <time.h>
+#include <sys/eventfd.h>
+#include <asm/unistd.h>
+#include <dirent.h>
+
+#define DEFINE_KVM_EXIT_REASON(reason) [reason] = #reason
+
+const char *kvm_exit_reasons[] = {
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_UNKNOWN),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_EXCEPTION),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_IO),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_HYPERCALL),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_DEBUG),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_HLT),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_MMIO),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_IRQ_WINDOW_OPEN),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_SHUTDOWN),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_FAIL_ENTRY),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_INTR),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_SET_TPR),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_TPR_ACCESS),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_S390_SIEIC),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_S390_RESET),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_DCR),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_NMI),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_INTERNAL_ERROR),
+#ifdef CONFIG_PPC64
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_PAPR_HCALL),
+#endif
+};
+
+static int pause_event;
+static DEFINE_MUTEX(pause_lock);
+extern struct kvm_ext kvm_req_ext[];
+
+static char kvm_dir[PATH_MAX];
+
+extern __thread struct kvm_cpu *current_kvm_cpu;
+
+static int set_dir(const char *fmt, va_list args)
+{
+ char tmp[PATH_MAX];
+
+ vsnprintf(tmp, sizeof(tmp), fmt, args);
+
+ mkdir(tmp, 0777);
+
+ if (!realpath(tmp, kvm_dir))
+ return -errno;
+
+ strcat(kvm_dir, "/");
+
+ return 0;
+}
+
+void kvm__set_dir(const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ set_dir(fmt, args);
+ va_end(args);
+}
+
+const char *kvm__get_dir(void)
+{
+ return kvm_dir;
+}
+
+bool kvm__supports_vm_extension(struct kvm *kvm, unsigned int extension)
+{
+ static int supports_vm_ext_check = 0;
+ int ret;
+
+ switch (supports_vm_ext_check) {
+ case 0:
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION,
+ KVM_CAP_CHECK_EXTENSION_VM);
+ if (ret <= 0) {
+ supports_vm_ext_check = -1;
+ return false;
+ }
+ supports_vm_ext_check = 1;
+ /* fall through */
+ case 1:
+ break;
+ case -1:
+ return false;
+ }
+
+ ret = ioctl(kvm->vm_fd, KVM_CHECK_EXTENSION, extension);
+ if (ret < 0)
+ return false;
+
+ return ret;
+}
+
+bool kvm__supports_extension(struct kvm *kvm, unsigned int extension)
+{
+ int ret;
+
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, extension);
+ if (ret < 0)
+ return false;
+
+ return ret;
+}
+
+static int kvm__check_extensions(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; ; i++) {
+ if (!kvm_req_ext[i].name)
+ break;
+ if (!kvm__supports_extension(kvm, kvm_req_ext[i].code)) {
+ pr_err("Unsupported KVM extension detected: %s",
+ kvm_req_ext[i].name);
+ return -i;
+ }
+ }
+
+ return 0;
+}
+
+struct kvm *kvm__new(void)
+{
+ struct kvm *kvm = calloc(1, sizeof(*kvm));
+ if (!kvm)
+ return ERR_PTR(-ENOMEM);
+
+ mutex_init(&kvm->mem_banks_lock);
+ kvm->sys_fd = -1;
+ kvm->vm_fd = -1;
+
+#ifdef KVM_BRLOCK_DEBUG
+ kvm->brlock_sem = (pthread_rwlock_t) PTHREAD_RWLOCK_INITIALIZER;
+#endif
+
+ return kvm;
+}
+
+int kvm__exit(struct kvm *kvm)
+{
+ struct kvm_mem_bank *bank, *tmp;
+
+ kvm__arch_delete_ram(kvm);
+
+ list_for_each_entry_safe(bank, tmp, &kvm->mem_banks, list) {
+ list_del(&bank->list);
+ free(bank);
+ }
+
+ free(kvm);
+ return 0;
+}
+core_exit(kvm__exit);
+
+int kvm__destroy_mem(struct kvm *kvm, u64 guest_phys, u64 size,
+ void *userspace_addr)
+{
+ struct kvm_userspace_memory_region mem;
+ struct kvm_mem_bank *bank;
+ int ret;
+
+ mutex_lock(&kvm->mem_banks_lock);
+ list_for_each_entry(bank, &kvm->mem_banks, list)
+ if (bank->guest_phys_addr == guest_phys &&
+ bank->size == size && bank->host_addr == userspace_addr)
+ break;
+
+ if (&bank->list == &kvm->mem_banks) {
+ pr_err("Region [%llx-%llx] not found", guest_phys,
+ guest_phys + size - 1);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (bank->type == KVM_MEM_TYPE_RESERVED) {
+ pr_err("Cannot delete reserved region [%llx-%llx]",
+ guest_phys, guest_phys + size - 1);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mem = (struct kvm_userspace_memory_region) {
+ .slot = bank->slot,
+ .guest_phys_addr = guest_phys,
+ .memory_size = 0,
+ .userspace_addr = (unsigned long)userspace_addr,
+ };
+
+ ret = ioctl(kvm->vm_fd, KVM_SET_USER_MEMORY_REGION, &mem);
+ if (ret < 0) {
+ ret = -errno;
+ goto out;
+ }
+
+ list_del(&bank->list);
+ free(bank);
+ kvm->mem_slots--;
+ ret = 0;
+
+out:
+ mutex_unlock(&kvm->mem_banks_lock);
+ return ret;
+}
+
+int kvm__register_mem(struct kvm *kvm, u64 guest_phys, u64 size,
+ void *userspace_addr, enum kvm_mem_type type)
+{
+ struct kvm_userspace_memory_region mem;
+ struct kvm_mem_bank *merged = NULL;
+ struct kvm_mem_bank *bank;
+ struct list_head *prev_entry;
+ u32 slot;
+ u32 flags = 0;
+ int ret;
+
+ mutex_lock(&kvm->mem_banks_lock);
+ /* Check for overlap and find first empty slot. */
+ slot = 0;
+ prev_entry = &kvm->mem_banks;
+ list_for_each_entry(bank, &kvm->mem_banks, list) {
+ u64 bank_end = bank->guest_phys_addr + bank->size - 1;
+ u64 end = guest_phys + size - 1;
+ if (guest_phys > bank_end || end < bank->guest_phys_addr) {
+ /*
+ * Keep the banks sorted ascending by slot, so it's
+ * easier for us to find a free slot.
+ */
+ if (bank->slot == slot) {
+ slot++;
+ prev_entry = &bank->list;
+ }
+ continue;
+ }
+
+ /* Merge overlapping reserved regions */
+ if (bank->type == KVM_MEM_TYPE_RESERVED &&
+ type == KVM_MEM_TYPE_RESERVED) {
+ bank->guest_phys_addr = min(bank->guest_phys_addr, guest_phys);
+ bank->size = max(bank_end, end) - bank->guest_phys_addr + 1;
+
+ if (merged) {
+ /*
+ * This is at least the second merge, remove
+ * previous result.
+ */
+ list_del(&merged->list);
+ free(merged);
+ }
+
+ guest_phys = bank->guest_phys_addr;
+ size = bank->size;
+ merged = bank;
+
+ /* Keep checking that we don't overlap another region */
+ continue;
+ }
+
+ pr_err("%s region [%llx-%llx] would overlap %s region [%llx-%llx]",
+ kvm_mem_type_to_string(type), guest_phys, guest_phys + size - 1,
+ kvm_mem_type_to_string(bank->type), bank->guest_phys_addr,
+ bank->guest_phys_addr + bank->size - 1);
+
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (merged) {
+ ret = 0;
+ goto out;
+ }
+
+ bank = malloc(sizeof(*bank));
+ if (!bank) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ INIT_LIST_HEAD(&bank->list);
+ bank->guest_phys_addr = guest_phys;
+ bank->host_addr = userspace_addr;
+ bank->size = size;
+ bank->type = type;
+ bank->slot = slot;
+
+ if (type & KVM_MEM_TYPE_READONLY)
+ flags |= KVM_MEM_READONLY;
+
+ if (type != KVM_MEM_TYPE_RESERVED) {
+ mem = (struct kvm_userspace_memory_region) {
+ .slot = slot,
+ .flags = flags,
+ .guest_phys_addr = guest_phys,
+ .memory_size = size,
+ .userspace_addr = (unsigned long)userspace_addr,
+ };
+
+ ret = ioctl(kvm->vm_fd, KVM_SET_USER_MEMORY_REGION, &mem);
+ if (ret < 0) {
+ ret = -errno;
+ goto out;
+ }
+ }
+
+ list_add(&bank->list, prev_entry);
+ kvm->mem_slots++;
+ ret = 0;
+
+out:
+ mutex_unlock(&kvm->mem_banks_lock);
+ return ret;
+}
+
+void *guest_flat_to_host(struct kvm *kvm, u64 offset)
+{
+ struct kvm_mem_bank *bank;
+
+ list_for_each_entry(bank, &kvm->mem_banks, list) {
+ u64 bank_start = bank->guest_phys_addr;
+ u64 bank_end = bank_start + bank->size;
+
+ if (offset >= bank_start && offset < bank_end)
+ return bank->host_addr + (offset - bank_start);
+ }
+
+ pr_warning("unable to translate guest address 0x%llx to host",
+ (unsigned long long)offset);
+ return NULL;
+}
+
+u64 host_to_guest_flat(struct kvm *kvm, void *ptr)
+{
+ struct kvm_mem_bank *bank;
+
+ list_for_each_entry(bank, &kvm->mem_banks, list) {
+ void *bank_start = bank->host_addr;
+ void *bank_end = bank_start + bank->size;
+
+ if (ptr >= bank_start && ptr < bank_end)
+ return bank->guest_phys_addr + (ptr - bank_start);
+ }
+
+ pr_warning("unable to translate host address %p to guest", ptr);
+ return 0;
+}
+
+/*
+ * Iterate over each registered memory bank. Call @fun for each bank with @data
+ * as argument. @type is a bitmask that allows to filter banks according to
+ * their type.
+ *
+ * If one call to @fun returns a non-zero value, stop iterating and return the
+ * value. Otherwise, return zero.
+ */
+int kvm__for_each_mem_bank(struct kvm *kvm, enum kvm_mem_type type,
+ int (*fun)(struct kvm *kvm, struct kvm_mem_bank *bank, void *data),
+ void *data)
+{
+ int ret;
+ struct kvm_mem_bank *bank;
+
+ list_for_each_entry(bank, &kvm->mem_banks, list) {
+ if (type != KVM_MEM_TYPE_ALL && !(bank->type & type))
+ continue;
+
+ ret = fun(kvm, bank, data);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+int kvm__recommended_cpus(struct kvm *kvm)
+{
+ int ret;
+
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_NR_VCPUS);
+ if (ret <= 0)
+ /*
+ * api.txt states that if KVM_CAP_NR_VCPUS does not exist,
+ * assume 4.
+ */
+ return 4;
+
+ return ret;
+}
+
+int kvm__max_cpus(struct kvm *kvm)
+{
+ int ret;
+
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_MAX_VCPUS);
+ if (ret <= 0)
+ ret = kvm__recommended_cpus(kvm);
+
+ return ret;
+}
+
+int kvm__init(struct kvm *kvm)
+{
+ int ret;
+
+ if (!kvm__arch_cpu_supports_vm()) {
+ pr_err("Your CPU does not support hardware virtualization");
+ ret = -ENOSYS;
+ goto err;
+ }
+
+ kvm->sys_fd = open(kvm->cfg.dev, O_RDWR);
+ if (kvm->sys_fd < 0) {
+ if (errno == ENOENT)
+ pr_err("'%s' not found. Please make sure your kernel has CONFIG_KVM "
+ "enabled and that the KVM modules are loaded.", kvm->cfg.dev);
+ else if (errno == ENODEV)
+ pr_err("'%s' KVM driver not available.\n # (If the KVM "
+ "module is loaded then 'dmesg' may offer further clues "
+ "about the failure.)", kvm->cfg.dev);
+ else
+ pr_err("Could not open %s: ", kvm->cfg.dev);
+
+ ret = -errno;
+ goto err_free;
+ }
+
+ ret = ioctl(kvm->sys_fd, KVM_GET_API_VERSION, 0);
+ if (ret != KVM_API_VERSION) {
+ pr_err("KVM_API_VERSION ioctl");
+ ret = -errno;
+ goto err_sys_fd;
+ }
+
+ kvm->vm_fd = ioctl(kvm->sys_fd, KVM_CREATE_VM, KVM_VM_TYPE);
+ if (kvm->vm_fd < 0) {
+ pr_err("KVM_CREATE_VM ioctl");
+ ret = kvm->vm_fd;
+ goto err_sys_fd;
+ }
+
+ if (kvm__check_extensions(kvm)) {
+ pr_err("A required KVM extension is not supported by OS");
+ ret = -ENOSYS;
+ goto err_vm_fd;
+ }
+
+ kvm__arch_init(kvm, kvm->cfg.hugetlbfs_path, kvm->cfg.ram_size);
+
+ INIT_LIST_HEAD(&kvm->mem_banks);
+ kvm__init_ram(kvm);
+
+ if (!kvm->cfg.firmware_filename) {
+ if (!kvm__load_kernel(kvm, kvm->cfg.kernel_filename,
+ kvm->cfg.initrd_filename, kvm->cfg.real_cmdline))
+ die("unable to load kernel %s", kvm->cfg.kernel_filename);
+ }
+
+ if (kvm->cfg.firmware_filename) {
+ if (!kvm__load_firmware(kvm, kvm->cfg.firmware_filename))
+ die("unable to load firmware image %s: %s", kvm->cfg.firmware_filename, strerror(errno));
+ } else {
+ ret = kvm__arch_setup_firmware(kvm);
+ if (ret < 0)
+ die("kvm__arch_setup_firmware() failed with error %d\n", ret);
+ }
+
+ return 0;
+
+err_vm_fd:
+ close(kvm->vm_fd);
+err_sys_fd:
+ close(kvm->sys_fd);
+err_free:
+ free(kvm);
+err:
+ return ret;
+}
+core_init(kvm__init);
+
+/* RFC 1952 */
+#define GZIP_ID1 0x1f
+#define GZIP_ID2 0x8b
+#define CPIO_MAGIC "0707"
+/* initrd may be gzipped, or a plain cpio */
+static bool initrd_check(int fd)
+{
+ unsigned char id[4];
+
+ if (read_in_full(fd, id, ARRAY_SIZE(id)) < 0)
+ return false;
+
+ if (lseek(fd, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ return (id[0] == GZIP_ID1 && id[1] == GZIP_ID2) ||
+ !memcmp(id, CPIO_MAGIC, 4);
+}
+
+bool kvm__load_kernel(struct kvm *kvm, const char *kernel_filename,
+ const char *initrd_filename, const char *kernel_cmdline)
+{
+ bool ret;
+ int fd_kernel = -1, fd_initrd = -1;
+
+ fd_kernel = open(kernel_filename, O_RDONLY);
+ if (fd_kernel < 0)
+ die("Unable to open kernel %s", kernel_filename);
+
+ if (initrd_filename) {
+ fd_initrd = open(initrd_filename, O_RDONLY);
+ if (fd_initrd < 0)
+ die("Unable to open initrd %s", initrd_filename);
+
+ if (!initrd_check(fd_initrd))
+ die("%s is not an initrd", initrd_filename);
+ }
+
+ ret = kvm__arch_load_kernel_image(kvm, fd_kernel, fd_initrd,
+ kernel_cmdline);
+
+ if (initrd_filename)
+ close(fd_initrd);
+ close(fd_kernel);
+
+ if (!ret)
+ die("%s is not a valid kernel image", kernel_filename);
+ return ret;
+}
+
+void kvm__dump_mem(struct kvm *kvm, unsigned long addr, unsigned long size, int debug_fd)
+{
+ unsigned char *p;
+ unsigned long n;
+
+ size &= ~7; /* mod 8 */
+ if (!size)
+ return;
+
+ p = guest_flat_to_host(kvm, addr);
+
+ for (n = 0; n < size; n += 8) {
+ if (!host_ptr_in_ram(kvm, p + n)) {
+ dprintf(debug_fd, " 0x%08lx: <unknown>\n", addr + n);
+ continue;
+ }
+ dprintf(debug_fd, " 0x%08lx: %02x %02x %02x %02x %02x %02x %02x %02x\n",
+ addr + n, p[n + 0], p[n + 1], p[n + 2], p[n + 3],
+ p[n + 4], p[n + 5], p[n + 6], p[n + 7]);
+ }
+}
+
+void kvm__reboot(struct kvm *kvm)
+{
+ /* Check if the guest is running */
+ if (!kvm->cpus[0] || kvm->cpus[0]->thread == 0)
+ return;
+
+ pthread_kill(kvm->cpus[0]->thread, SIGKVMEXIT);
+}
+
+void kvm__continue(struct kvm *kvm)
+{
+ mutex_unlock(&pause_lock);
+}
+
+void kvm__pause(struct kvm *kvm)
+{
+ int i, paused_vcpus = 0;
+
+ mutex_lock(&pause_lock);
+
+ /* Check if the guest is running */
+ if (!kvm->cpus || !kvm->cpus[0] || kvm->cpus[0]->thread == 0)
+ return;
+
+ pause_event = eventfd(0, 0);
+ if (pause_event < 0)
+ die("Failed creating pause notification event");
+ for (i = 0; i < kvm->nrcpus; i++) {
+ if (kvm->cpus[i]->is_running && kvm->cpus[i]->paused == 0)
+ pthread_kill(kvm->cpus[i]->thread, SIGKVMPAUSE);
+ else
+ paused_vcpus++;
+ }
+
+ while (paused_vcpus < kvm->nrcpus) {
+ u64 cur_read;
+
+ if (read(pause_event, &cur_read, sizeof(cur_read)) < 0)
+ die("Failed reading pause event");
+ paused_vcpus += cur_read;
+ }
+ close(pause_event);
+}
+
+void kvm__notify_paused(void)
+{
+ u64 p = 1;
+
+ if (write(pause_event, &p, sizeof(p)) < 0)
+ die("Failed notifying of paused VCPU.");
+
+ mutex_lock(&pause_lock);
+ current_kvm_cpu->paused = 0;
+ mutex_unlock(&pause_lock);
+}
diff --git a/kvmtool/main.c b/kvmtool/main.c
new file mode 100644
index 0000000..05bc82c
--- /dev/null
+++ b/kvmtool/main.c
@@ -0,0 +1,19 @@
+#include "kvm/kvm.h"
+
+#include <stdlib.h>
+#include <stdio.h>
+
+/* user defined header files */
+#include <kvm/kvm-cmd.h>
+
+static int handle_kvm_command(int argc, char **argv)
+{
+ return handle_command(kvm_commands, argc, (const char **) &argv[0]);
+}
+
+int main(int argc, char *argv[])
+{
+ kvm__set_dir("%s/%s", HOME_DIR, KVM_PID_FILE_PATH);
+
+ return handle_kvm_command(argc - 1, &argv[1]);
+}
diff --git a/kvmtool/mips/include/asm/kvm.h b/kvmtool/mips/include/asm/kvm.h
new file mode 100644
index 0000000..edcf717
--- /dev/null
+++ b/kvmtool/mips/include/asm/kvm.h
@@ -0,0 +1,227 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved.
+ * Copyright (C) 2013 Cavium, Inc.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+#ifndef __LINUX_KVM_MIPS_H
+#define __LINUX_KVM_MIPS_H
+
+#include <linux/types.h>
+
+/*
+ * KVM MIPS specific structures and definitions.
+ *
+ * Some parts derived from the x86 version of this file.
+ */
+
+#define __KVM_HAVE_READONLY_MEM
+
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
+/*
+ * for KVM_GET_REGS and KVM_SET_REGS
+ *
+ * If Config[AT] is zero (32-bit CPU), the register contents are
+ * stored in the lower 32-bits of the struct kvm_regs fields and sign
+ * extended to 64-bits.
+ */
+struct kvm_regs {
+ /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+ __u64 gpr[32];
+ __u64 hi;
+ __u64 lo;
+ __u64 pc;
+};
+
+/*
+ * for KVM_GET_FPU and KVM_SET_FPU
+ */
+struct kvm_fpu {
+};
+
+
+/*
+ * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various
+ * registers. The id field is broken down as follows:
+ *
+ * bits[63..52] - As per linux/kvm.h
+ * bits[51..32] - Must be zero.
+ * bits[31..16] - Register set.
+ *
+ * Register set = 0: GP registers from kvm_regs (see definitions below).
+ *
+ * Register set = 1: CP0 registers.
+ * bits[15..8] - COP0 register set.
+ *
+ * COP0 register set = 0: Main CP0 registers.
+ * bits[7..3] - Register 'rd' index.
+ * bits[2..0] - Register 'sel' index.
+ *
+ * COP0 register set = 1: MAARs.
+ * bits[7..0] - MAAR index.
+ *
+ * Register set = 2: KVM specific registers (see definitions below).
+ *
+ * Register set = 3: FPU / MSA registers (see definitions below).
+ *
+ * Other sets registers may be added in the future. Each set would
+ * have its own identifier in bits[31..16].
+ */
+
+#define KVM_REG_MIPS_GP (KVM_REG_MIPS | 0x0000000000000000ULL)
+#define KVM_REG_MIPS_CP0 (KVM_REG_MIPS | 0x0000000000010000ULL)
+#define KVM_REG_MIPS_KVM (KVM_REG_MIPS | 0x0000000000020000ULL)
+#define KVM_REG_MIPS_FPU (KVM_REG_MIPS | 0x0000000000030000ULL)
+
+
+/*
+ * KVM_REG_MIPS_GP - General purpose registers from kvm_regs.
+ */
+
+#define KVM_REG_MIPS_R0 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_MIPS_R1 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 1)
+#define KVM_REG_MIPS_R2 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 2)
+#define KVM_REG_MIPS_R3 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 3)
+#define KVM_REG_MIPS_R4 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 4)
+#define KVM_REG_MIPS_R5 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 5)
+#define KVM_REG_MIPS_R6 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 6)
+#define KVM_REG_MIPS_R7 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 7)
+#define KVM_REG_MIPS_R8 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 8)
+#define KVM_REG_MIPS_R9 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 9)
+#define KVM_REG_MIPS_R10 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 10)
+#define KVM_REG_MIPS_R11 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 11)
+#define KVM_REG_MIPS_R12 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 12)
+#define KVM_REG_MIPS_R13 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 13)
+#define KVM_REG_MIPS_R14 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 14)
+#define KVM_REG_MIPS_R15 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 15)
+#define KVM_REG_MIPS_R16 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 16)
+#define KVM_REG_MIPS_R17 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 17)
+#define KVM_REG_MIPS_R18 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 18)
+#define KVM_REG_MIPS_R19 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 19)
+#define KVM_REG_MIPS_R20 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 20)
+#define KVM_REG_MIPS_R21 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 21)
+#define KVM_REG_MIPS_R22 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 22)
+#define KVM_REG_MIPS_R23 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 23)
+#define KVM_REG_MIPS_R24 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 24)
+#define KVM_REG_MIPS_R25 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 25)
+#define KVM_REG_MIPS_R26 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 26)
+#define KVM_REG_MIPS_R27 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 27)
+#define KVM_REG_MIPS_R28 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 28)
+#define KVM_REG_MIPS_R29 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 29)
+#define KVM_REG_MIPS_R30 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 30)
+#define KVM_REG_MIPS_R31 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 31)
+
+#define KVM_REG_MIPS_HI (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 32)
+#define KVM_REG_MIPS_LO (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 33)
+#define KVM_REG_MIPS_PC (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 34)
+
+
+/*
+ * KVM_REG_MIPS_CP0 - Coprocessor 0 registers.
+ */
+
+#define KVM_REG_MIPS_MAAR (KVM_REG_MIPS_CP0 | (1 << 8))
+#define KVM_REG_MIPS_CP0_MAAR(n) (KVM_REG_MIPS_MAAR | \
+ KVM_REG_SIZE_U64 | (n))
+
+
+/*
+ * KVM_REG_MIPS_KVM - KVM specific control registers.
+ */
+
+/*
+ * CP0_Count control
+ * DC: Set 0: Master disable CP0_Count and set COUNT_RESUME to now
+ * Set 1: Master re-enable CP0_Count with unchanged bias, handling timer
+ * interrupts since COUNT_RESUME
+ * This can be used to freeze the timer to get a consistent snapshot of
+ * the CP0_Count and timer interrupt pending state, while also resuming
+ * safely without losing time or guest timer interrupts.
+ * Other: Reserved, do not change.
+ */
+#define KVM_REG_MIPS_COUNT_CTL (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_MIPS_COUNT_CTL_DC 0x00000001
+
+/*
+ * CP0_Count resume monotonic nanoseconds
+ * The monotonic nanosecond time of the last set of COUNT_CTL.DC (master
+ * disable). Any reads and writes of Count related registers while
+ * COUNT_CTL.DC=1 will appear to occur at this time. When COUNT_CTL.DC is
+ * cleared again (master enable) any timer interrupts since this time will be
+ * emulated.
+ * Modifications to times in the future are rejected.
+ */
+#define KVM_REG_MIPS_COUNT_RESUME (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 1)
+/*
+ * CP0_Count rate in Hz
+ * Specifies the rate of the CP0_Count timer in Hz. Modifications occur without
+ * discontinuities in CP0_Count.
+ */
+#define KVM_REG_MIPS_COUNT_HZ (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 2)
+
+
+/*
+ * KVM_REG_MIPS_FPU - Floating Point and MIPS SIMD Architecture (MSA) registers.
+ *
+ * bits[15..8] - Register subset (see definitions below).
+ * bits[7..5] - Must be zero.
+ * bits[4..0] - Register number within register subset.
+ */
+
+#define KVM_REG_MIPS_FPR (KVM_REG_MIPS_FPU | 0x0000000000000000ULL)
+#define KVM_REG_MIPS_FCR (KVM_REG_MIPS_FPU | 0x0000000000000100ULL)
+#define KVM_REG_MIPS_MSACR (KVM_REG_MIPS_FPU | 0x0000000000000200ULL)
+
+/*
+ * KVM_REG_MIPS_FPR - Floating point / Vector registers.
+ */
+#define KVM_REG_MIPS_FPR_32(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U32 | (n))
+#define KVM_REG_MIPS_FPR_64(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U64 | (n))
+#define KVM_REG_MIPS_VEC_128(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U128 | (n))
+
+/*
+ * KVM_REG_MIPS_FCR - Floating point control registers.
+ */
+#define KVM_REG_MIPS_FCR_IR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 0)
+#define KVM_REG_MIPS_FCR_CSR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 31)
+
+/*
+ * KVM_REG_MIPS_MSACR - MIPS SIMD Architecture (MSA) control registers.
+ */
+#define KVM_REG_MIPS_MSA_IR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 0)
+#define KVM_REG_MIPS_MSA_CSR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 1)
+
+
+/*
+ * KVM MIPS specific structures and definitions
+ *
+ */
+struct kvm_debug_exit_arch {
+ __u64 epc;
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+};
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+/* dummy definition */
+struct kvm_sregs {
+};
+
+struct kvm_mips_interrupt {
+ /* in */
+ __u32 cpu;
+ __u32 irq;
+};
+
+#endif /* __LINUX_KVM_MIPS_H */
diff --git a/kvmtool/mips/include/kvm/barrier.h b/kvmtool/mips/include/kvm/barrier.h
new file mode 100644
index 0000000..45bfa72
--- /dev/null
+++ b/kvmtool/mips/include/kvm/barrier.h
@@ -0,0 +1,20 @@
+#ifndef _KVM_BARRIER_H_
+#define _KVM_BARRIER_H_
+
+#define barrier() asm volatile("": : :"memory")
+
+#define mb() asm volatile (".set push\n\t.set mips2\n\tsync\n\t.set pop": : :"memory")
+#define rmb() mb()
+#define wmb() mb()
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#endif
+
+#endif /* _KVM_BARRIER_H_ */
diff --git a/kvmtool/mips/include/kvm/fdt-arch.h b/kvmtool/mips/include/kvm/fdt-arch.h
new file mode 100644
index 0000000..b030245
--- /dev/null
+++ b/kvmtool/mips/include/kvm/fdt-arch.h
@@ -0,0 +1,6 @@
+#ifndef KVM__KVM_FDT_H
+#define KVM__KVM_FDT_H
+
+enum phandles {PHANDLE_RESERVED = 0, PHANDLES_MAX};
+
+#endif /* KVM__KVM_FDT_H */
diff --git a/kvmtool/mips/include/kvm/kvm-arch.h b/kvmtool/mips/include/kvm/kvm-arch.h
new file mode 100644
index 0000000..fdc09d8
--- /dev/null
+++ b/kvmtool/mips/include/kvm/kvm-arch.h
@@ -0,0 +1,50 @@
+#ifndef KVM__KVM_ARCH_H
+#define KVM__KVM_ARCH_H
+
+
+/*
+ * Guest memory map is:
+ * 0x00000000-0x0fffffff : System RAM
+ * 0x10000000-0x1fffffff : I/O (defined by KVM_MMIO_START and KVM_MMIO_SIZE)
+ * 0x20000000- ... : System RAM
+ * See also kvm__init_ram().
+ */
+
+#define KVM_MMIO_START 0x10000000
+#define KVM_PCI_CFG_AREA KVM_MMIO_START
+#define KVM_PCI_MMIO_AREA (KVM_MMIO_START + 0x1000000)
+#define KVM_VIRTIO_MMIO_AREA (KVM_MMIO_START + 0x2000000)
+#define KVM_MMIO_SIZE 0x10000000
+
+/*
+ * Just for reference. This and the above corresponds to what's used
+ * in mipsvz_page_fault() in kvm_mipsvz.c of the host kernel.
+ */
+#define KVM_MIPS_IOPORT_AREA 0x1e000000
+#define KVM_MIPS_IOPORT_SIZE 0x00010000
+#define KVM_MIPS_IRQCHIP_AREA 0x1e010000
+#define KVM_MIPS_IRQCHIP_SIZE 0x00010000
+
+#define KVM_IRQ_OFFSET 1
+
+/*
+ * MIPS-VZ (trap and emulate is 0)
+ */
+#define KVM_VM_TYPE 1
+
+#define KVM_IOEVENTFD_HAS_PIO 0
+
+#define VIRTIO_DEFAULT_TRANS(kvm) VIRTIO_PCI
+
+#include <stdbool.h>
+
+#include "linux/types.h"
+
+struct kvm_arch {
+ u64 entry_point;
+ u64 argc;
+ u64 argv;
+ bool is64bit;
+};
+
+#endif /* KVM__KVM_ARCH_H */
diff --git a/kvmtool/mips/include/kvm/kvm-config-arch.h b/kvmtool/mips/include/kvm/kvm-config-arch.h
new file mode 100644
index 0000000..8a28f9d
--- /dev/null
+++ b/kvmtool/mips/include/kvm/kvm-config-arch.h
@@ -0,0 +1,7 @@
+#ifndef KVM__KVM_CONFIG_ARCH_H
+#define KVM__KVM_CONFIG_ARCH_H
+
+struct kvm_config_arch {
+};
+
+#endif /* KVM__MIPS_KVM_CONFIG_ARCH_H */
diff --git a/kvmtool/mips/include/kvm/kvm-cpu-arch.h b/kvmtool/mips/include/kvm/kvm-cpu-arch.h
new file mode 100644
index 0000000..45e69f6
--- /dev/null
+++ b/kvmtool/mips/include/kvm/kvm-cpu-arch.h
@@ -0,0 +1,43 @@
+#ifndef KVM__KVM_CPU_ARCH_H
+#define KVM__KVM_CPU_ARCH_H
+
+#include <linux/kvm.h> /* for struct kvm_regs */
+#include "kvm/kvm.h" /* for kvm__emulate_{mm}io() */
+#include <pthread.h>
+
+struct kvm;
+
+struct kvm_cpu {
+ pthread_t thread; /* VCPU thread */
+
+ unsigned long cpu_id;
+
+ struct kvm *kvm; /* parent KVM */
+ int vcpu_fd; /* For VCPU ioctls() */
+ struct kvm_run *kvm_run;
+ struct kvm_cpu_task *task;
+
+ struct kvm_regs regs;
+
+ u8 is_running;
+ u8 paused;
+ u8 needs_nmi;
+
+ struct kvm_coalesced_mmio_ring *ring;
+};
+
+/*
+ * As these are such simple wrappers, let's have them in the header so they'll
+ * be cheaper to call:
+ */
+static inline bool kvm_cpu__emulate_io(struct kvm_cpu *vcpu, u16 port, void *data, int direction, int size, u32 count)
+{
+ return kvm__emulate_io(vcpu, port, data, direction, size, count);
+}
+
+static inline bool kvm_cpu__emulate_mmio(struct kvm_cpu *vcpu, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ return kvm__emulate_mmio(vcpu, phys_addr, data, len, is_write);
+}
+
+#endif /* KVM__KVM_CPU_ARCH_H */
diff --git a/kvmtool/mips/kvm-cpu.c b/kvmtool/mips/kvm-cpu.c
new file mode 100644
index 0000000..30a3de1
--- /dev/null
+++ b/kvmtool/mips/kvm-cpu.c
@@ -0,0 +1,219 @@
+#include "kvm/kvm-cpu.h"
+#include "kvm/term.h"
+
+#include <stdlib.h>
+
+static int debug_fd;
+
+void kvm_cpu__set_debug_fd(int fd)
+{
+ debug_fd = fd;
+}
+
+int kvm_cpu__get_debug_fd(void)
+{
+ return debug_fd;
+}
+
+void kvm_cpu__delete(struct kvm_cpu *vcpu)
+{
+ free(vcpu);
+}
+
+static struct kvm_cpu *kvm_cpu__new(struct kvm *kvm)
+{
+ struct kvm_cpu *vcpu;
+
+ vcpu = calloc(1, sizeof(*vcpu));
+ if (!vcpu)
+ return NULL;
+
+ vcpu->kvm = kvm;
+
+ return vcpu;
+}
+
+struct kvm_cpu *kvm_cpu__arch_init(struct kvm *kvm, unsigned long cpu_id)
+{
+ struct kvm_cpu *vcpu;
+ int mmap_size;
+ int coalesced_offset;
+
+ vcpu = kvm_cpu__new(kvm);
+ if (!vcpu)
+ return NULL;
+
+ vcpu->cpu_id = cpu_id;
+
+ vcpu->vcpu_fd = ioctl(vcpu->kvm->vm_fd, KVM_CREATE_VCPU, cpu_id);
+ if (vcpu->vcpu_fd < 0)
+ die_perror("KVM_CREATE_VCPU ioctl");
+
+ mmap_size = ioctl(vcpu->kvm->sys_fd, KVM_GET_VCPU_MMAP_SIZE, 0);
+ if (mmap_size < 0)
+ die_perror("KVM_GET_VCPU_MMAP_SIZE ioctl");
+
+ vcpu->kvm_run = mmap(NULL, mmap_size, PROT_RW, MAP_SHARED, vcpu->vcpu_fd, 0);
+ if (vcpu->kvm_run == MAP_FAILED)
+ die("unable to mmap vcpu fd");
+
+ vcpu->is_running = true;
+
+ coalesced_offset = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_COALESCED_MMIO);
+ if (coalesced_offset)
+ vcpu->ring = (void *)vcpu->kvm_run + (coalesced_offset * PAGE_SIZE);
+
+ return vcpu;
+}
+
+static void kvm_cpu__setup_regs(struct kvm_cpu *vcpu)
+{
+ uint32_t v;
+ struct kvm_one_reg one_reg;
+
+ memset(&vcpu->regs, 0, sizeof(vcpu->regs));
+ vcpu->regs.pc = vcpu->kvm->arch.entry_point;
+ vcpu->regs.gpr[4] = vcpu->kvm->arch.argc;
+ vcpu->regs.gpr[5] = vcpu->kvm->arch.argv;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_REGS, &vcpu->regs) < 0)
+ die_perror("KVM_SET_REGS failed");
+
+
+ one_reg.id = KVM_REG_MIPS | KVM_REG_SIZE_U32 | (0x10000 + 8 * 12 + 0); /* Status */
+ one_reg.addr = (unsigned long)(uint32_t *)&v;
+ v = 6;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, &one_reg) < 0)
+ die_perror("KVM_SET_ONE_REG failed");
+}
+
+/**
+ * kvm_cpu__reset_vcpu - reset virtual CPU to a known state
+ */
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu)
+{
+ kvm_cpu__setup_regs(vcpu);
+}
+
+static bool kvm_cpu__hypercall_write_cons(struct kvm_cpu *vcpu)
+{
+ int term = (int)vcpu->kvm_run->hypercall.args[0];
+ u64 addr = vcpu->kvm_run->hypercall.args[1];
+ int len = (int)vcpu->kvm_run->hypercall.args[2];
+ char *host_addr;
+
+ if (term < 0 || term >= TERM_MAX_DEVS) {
+ pr_warning("hypercall_write_cons term out of range <%d>", term);
+ return false;
+ }
+
+ if ((addr & 0xffffffffc0000000ull) == 0xffffffff80000000ull)
+ addr &= 0x1ffffffful; /* Convert KSEG{0,1} to physical. */
+ if ((addr & 0xc000000000000000ull) == 0x8000000000000000ull)
+ addr &= 0x07ffffffffffffffull; /* Convert XKPHYS to pysical */
+
+ host_addr = guest_flat_to_host(vcpu->kvm, addr);
+ if (!host_addr) {
+ pr_warning("hypercall_write_cons unmapped physaddr %llx", (unsigned long long)addr);
+ return false;
+ }
+
+ if ((len <= 0) || !host_ptr_in_ram(vcpu->kvm, host_addr + len)) {
+ pr_warning("hypercall_write_cons len out of range <%d>", len);
+ return false;
+ }
+
+ term_putc(host_addr, len, term);
+
+ return true;
+}
+
+#define KVM_HC_MIPS_CONSOLE_OUTPUT 8
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu)
+{
+ switch(vcpu->kvm_run->exit_reason) {
+ case KVM_EXIT_HYPERCALL:
+ if (vcpu->kvm_run->hypercall.nr == KVM_HC_MIPS_CONSOLE_OUTPUT) {
+ return kvm_cpu__hypercall_write_cons(vcpu);
+ } else {
+ pr_warning("KVM_EXIT_HYPERCALL unrecognized call %llu",
+ (unsigned long long)vcpu->kvm_run->hypercall.nr);
+ return false;
+ }
+ case KVM_EXIT_EXCEPTION:
+ case KVM_EXIT_INTERNAL_ERROR:
+ return false;
+ default:
+ break;
+ }
+ return false;
+}
+
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu)
+{
+}
+
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu)
+{
+ struct kvm_regs regs;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, ®s) < 0)
+ die("KVM_GET_REGS failed");
+ dprintf(debug_fd, "\n Registers:\n");
+ dprintf(debug_fd, " ----------\n");
+ dprintf(debug_fd, "$0 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[0],
+ (unsigned long long)regs.gpr[1],
+ (unsigned long long)regs.gpr[2],
+ (unsigned long long)regs.gpr[3]);
+ dprintf(debug_fd, "$4 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[4],
+ (unsigned long long)regs.gpr[5],
+ (unsigned long long)regs.gpr[6],
+ (unsigned long long)regs.gpr[7]);
+ dprintf(debug_fd, "$8 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[8],
+ (unsigned long long)regs.gpr[9],
+ (unsigned long long)regs.gpr[10],
+ (unsigned long long)regs.gpr[11]);
+ dprintf(debug_fd, "$12 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[12],
+ (unsigned long long)regs.gpr[13],
+ (unsigned long long)regs.gpr[14],
+ (unsigned long long)regs.gpr[15]);
+ dprintf(debug_fd, "$16 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[16],
+ (unsigned long long)regs.gpr[17],
+ (unsigned long long)regs.gpr[18],
+ (unsigned long long)regs.gpr[19]);
+ dprintf(debug_fd, "$20 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[20],
+ (unsigned long long)regs.gpr[21],
+ (unsigned long long)regs.gpr[22],
+ (unsigned long long)regs.gpr[23]);
+ dprintf(debug_fd, "$24 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[24],
+ (unsigned long long)regs.gpr[25],
+ (unsigned long long)regs.gpr[26],
+ (unsigned long long)regs.gpr[27]);
+ dprintf(debug_fd, "$28 : %016llx %016llx %016llx %016llx\n",
+ (unsigned long long)regs.gpr[28],
+ (unsigned long long)regs.gpr[29],
+ (unsigned long long)regs.gpr[30],
+ (unsigned long long)regs.gpr[31]);
+
+ dprintf(debug_fd, "hi : %016llx\n", (unsigned long long)regs.hi);
+ dprintf(debug_fd, "lo : %016llx\n", (unsigned long long)regs.lo);
+ dprintf(debug_fd, "epc : %016llx\n", (unsigned long long)regs.pc);
+
+ dprintf(debug_fd, "\n");
+}
+
+void kvm_cpu__show_code(struct kvm_cpu *vcpu)
+{
+}
+
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu)
+{
+}
diff --git a/kvmtool/mips/kvm.c b/kvmtool/mips/kvm.c
new file mode 100644
index 0000000..2635593
--- /dev/null
+++ b/kvmtool/mips/kvm.c
@@ -0,0 +1,365 @@
+#include "kvm/kvm.h"
+#include "kvm/ioport.h"
+#include "kvm/virtio-console.h"
+
+#include <linux/kvm.h>
+
+#include <ctype.h>
+#include <unistd.h>
+#include <elf.h>
+
+struct kvm_ext kvm_req_ext[] = {
+ { 0, 0 }
+};
+
+void kvm__arch_read_term(struct kvm *kvm)
+{
+ virtio_console__inject_interrupt(kvm);
+}
+
+void kvm__init_ram(struct kvm *kvm)
+{
+ u64 phys_start, phys_size;
+ void *host_mem;
+
+ if (kvm->ram_size <= KVM_MMIO_START) {
+ /* one region for all memory */
+ phys_start = 0;
+ phys_size = kvm->ram_size;
+ host_mem = kvm->ram_start;
+
+ kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+ } else {
+ /* one region for memory that fits below MMIO range */
+ phys_start = 0;
+ phys_size = KVM_MMIO_START;
+ host_mem = kvm->ram_start;
+
+ kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+
+ /* one region for rest of memory */
+ phys_start = KVM_MMIO_START + KVM_MMIO_SIZE;
+ phys_size = kvm->ram_size - KVM_MMIO_START;
+ host_mem = kvm->ram_start + KVM_MMIO_START;
+
+ kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+ }
+}
+
+void kvm__arch_delete_ram(struct kvm *kvm)
+{
+ munmap(kvm->ram_start, kvm->ram_size);
+}
+
+void kvm__arch_set_cmdline(char *cmdline, bool video)
+{
+
+}
+
+/* Architecture-specific KVM init */
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size)
+{
+ int ret;
+
+ kvm->ram_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path, ram_size);
+ kvm->ram_size = ram_size;
+
+ if (kvm->ram_start == MAP_FAILED)
+ die("out of memory");
+
+ madvise(kvm->ram_start, kvm->ram_size, MADV_MERGEABLE);
+
+ ret = ioctl(kvm->vm_fd, KVM_CREATE_IRQCHIP);
+ if (ret < 0)
+ die_perror("KVM_CREATE_IRQCHIP ioctl");
+}
+
+void kvm__irq_line(struct kvm *kvm, int irq, int level)
+{
+ struct kvm_irq_level irq_level;
+ int ret;
+
+ irq_level.irq = irq;
+ irq_level.level = level ? 1 : 0;
+
+ ret = ioctl(kvm->vm_fd, KVM_IRQ_LINE, &irq_level);
+ if (ret < 0)
+ die_perror("KVM_IRQ_LINE ioctl");
+}
+
+void kvm__irq_trigger(struct kvm *kvm, int irq)
+{
+ struct kvm_irq_level irq_level;
+ int ret;
+
+ irq_level.irq = irq;
+ irq_level.level = 1;
+
+ ret = ioctl(kvm->vm_fd, KVM_IRQ_LINE, &irq_level);
+ if (ret < 0)
+ die_perror("KVM_IRQ_LINE ioctl");
+}
+
+int ioport__setup_arch(struct kvm *kvm)
+{
+ return 0;
+}
+
+bool kvm__arch_cpu_supports_vm(void)
+{
+ return true;
+}
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename)
+{
+ return false;
+}
+int kvm__arch_setup_firmware(struct kvm *kvm)
+{
+ return 0;
+}
+
+static void kvm__mips_install_cmdline(struct kvm *kvm)
+{
+ char *p = kvm->ram_start;
+ u64 cmdline_offset = 0x2000;
+ u64 argv_start = 0x3000;
+ u64 argv_offset = argv_start;
+ u64 argc = 0;
+
+
+ if ((u64) kvm->ram_size <= KVM_MMIO_START)
+ sprintf(p + cmdline_offset, "mem=0x%llx@0 ",
+ (unsigned long long)kvm->ram_size);
+ else
+ sprintf(p + cmdline_offset, "mem=0x%llx@0 mem=0x%llx@0x%llx ",
+ (unsigned long long)KVM_MMIO_START,
+ (unsigned long long)kvm->ram_size - KVM_MMIO_START,
+ (unsigned long long)(KVM_MMIO_START + KVM_MMIO_SIZE));
+
+ strcat(p + cmdline_offset, kvm->cfg.real_cmdline); /* maximum size is 2K */
+
+ while (p[cmdline_offset]) {
+ if (!isspace(p[cmdline_offset])) {
+ if (kvm->arch.is64bit) {
+ *(u64 *)(p + argv_offset) = 0xffffffff80000000ull + cmdline_offset;
+ argv_offset += sizeof(u64);
+ } else {
+ *(u32 *)(p + argv_offset) = 0x80000000u + cmdline_offset;
+ argv_offset += sizeof(u32);
+ }
+ argc++;
+ while(p[cmdline_offset] && !isspace(p[cmdline_offset]))
+ cmdline_offset++;
+ continue;
+ }
+ /* Must be a space character skip over these*/
+ while(p[cmdline_offset] && isspace(p[cmdline_offset])) {
+ p[cmdline_offset] = 0;
+ cmdline_offset++;
+ }
+ }
+ kvm->arch.argc = argc;
+ kvm->arch.argv = 0xffffffff80000000ull + argv_start;
+}
+
+/* Load at the 1M point. */
+#define KERNEL_LOAD_ADDR 0x1000000
+
+static bool load_flat_binary(struct kvm *kvm, int fd_kernel)
+{
+ void *p;
+ void *k_start;
+ ssize_t kernel_size;
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ p = k_start = guest_flat_to_host(kvm, KERNEL_LOAD_ADDR);
+
+ kernel_size = read_file(fd_kernel, p,
+ kvm->cfg.ram_size - KERNEL_LOAD_ADDR);
+ if (kernel_size == -1) {
+ if (errno == ENOMEM)
+ die("kernel too big for guest memory");
+ else
+ die_perror("kernel read");
+ }
+
+ kvm->arch.is64bit = true;
+ kvm->arch.entry_point = 0xffffffff81000000ull;
+
+ pr_info("Loaded kernel to 0x%x (%zd bytes)", KERNEL_LOAD_ADDR,
+ kernel_size);
+
+ return true;
+}
+
+struct kvm__arch_elf_info {
+ u64 load_addr;
+ u64 entry_point;
+ size_t len;
+ size_t offset;
+};
+
+static bool kvm__arch_get_elf_64_info(Elf64_Ehdr *ehdr, int fd_kernel,
+ struct kvm__arch_elf_info *ei)
+{
+ int i;
+ Elf64_Phdr phdr;
+
+ if (ehdr->e_phentsize != sizeof(phdr)) {
+ pr_info("Incompatible ELF PHENTSIZE %d", ehdr->e_phentsize);
+ return false;
+ }
+
+ ei->entry_point = ehdr->e_entry;
+
+ if (lseek(fd_kernel, ehdr->e_phoff, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ phdr.p_type = PT_NULL;
+ for (i = 0; i < ehdr->e_phnum; i++) {
+ if (read_in_full(fd_kernel, &phdr, sizeof(phdr)) != sizeof(phdr)) {
+ pr_info("Couldn't read %d bytes for ELF PHDR.", (int)sizeof(phdr));
+ return false;
+ }
+ if (phdr.p_type == PT_LOAD)
+ break;
+ }
+ if (phdr.p_type != PT_LOAD) {
+ pr_info("No PT_LOAD Program Header found.");
+ return false;
+ }
+
+ ei->load_addr = phdr.p_paddr;
+
+ if ((ei->load_addr & 0xffffffffc0000000ull) == 0xffffffff80000000ull)
+ ei->load_addr &= 0x1ffffffful; /* Convert KSEG{0,1} to physical. */
+ if ((ei->load_addr & 0xc000000000000000ull) == 0x8000000000000000ull)
+ ei->load_addr &= 0x07ffffffffffffffull; /* Convert XKPHYS to pysical */
+
+
+ ei->len = phdr.p_filesz;
+ ei->offset = phdr.p_offset;
+
+ return true;
+}
+
+static bool kvm__arch_get_elf_32_info(Elf32_Ehdr *ehdr, int fd_kernel,
+ struct kvm__arch_elf_info *ei)
+{
+ int i;
+ Elf32_Phdr phdr;
+
+ if (ehdr->e_phentsize != sizeof(phdr)) {
+ pr_info("Incompatible ELF PHENTSIZE %d", ehdr->e_phentsize);
+ return false;
+ }
+
+ ei->entry_point = (s64)((s32)ehdr->e_entry);
+
+ if (lseek(fd_kernel, ehdr->e_phoff, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ phdr.p_type = PT_NULL;
+ for (i = 0; i < ehdr->e_phnum; i++) {
+ if (read_in_full(fd_kernel, &phdr, sizeof(phdr)) != sizeof(phdr)) {
+ pr_info("Couldn't read %d bytes for ELF PHDR.", (int)sizeof(phdr));
+ return false;
+ }
+ if (phdr.p_type == PT_LOAD)
+ break;
+ }
+ if (phdr.p_type != PT_LOAD) {
+ pr_info("No PT_LOAD Program Header found.");
+ return false;
+ }
+
+ ei->load_addr = (s64)((s32)phdr.p_paddr);
+
+ if ((ei->load_addr & 0xffffffffc0000000ull) == 0xffffffff80000000ull)
+ ei->load_addr &= 0x1fffffffull; /* Convert KSEG{0,1} to physical. */
+
+ ei->len = phdr.p_filesz;
+ ei->offset = phdr.p_offset;
+
+ return true;
+}
+
+static bool load_elf_binary(struct kvm *kvm, int fd_kernel)
+{
+ union {
+ Elf64_Ehdr ehdr;
+ Elf32_Ehdr ehdr32;
+ } eh;
+
+ size_t nr;
+ char *p;
+ struct kvm__arch_elf_info ei;
+
+ nr = read(fd_kernel, &eh, sizeof(eh));
+ if (nr != sizeof(eh)) {
+ pr_info("Couldn't read %d bytes for ELF header.", (int)sizeof(eh));
+ return false;
+ }
+
+ if (eh.ehdr.e_ident[EI_MAG0] != ELFMAG0 ||
+ eh.ehdr.e_ident[EI_MAG1] != ELFMAG1 ||
+ eh.ehdr.e_ident[EI_MAG2] != ELFMAG2 ||
+ eh.ehdr.e_ident[EI_MAG3] != ELFMAG3 ||
+ (eh.ehdr.e_ident[EI_CLASS] != ELFCLASS64 && eh.ehdr.e_ident[EI_CLASS] != ELFCLASS32) ||
+ eh.ehdr.e_ident[EI_VERSION] != EV_CURRENT) {
+ pr_info("Incompatible ELF header.");
+ return false;
+ }
+ if (eh.ehdr.e_type != ET_EXEC || eh.ehdr.e_machine != EM_MIPS) {
+ pr_info("Incompatible ELF not MIPS EXEC.");
+ return false;
+ }
+
+ if (eh.ehdr.e_ident[EI_CLASS] == ELFCLASS64) {
+ if (!kvm__arch_get_elf_64_info(&eh.ehdr, fd_kernel, &ei))
+ return false;
+ kvm->arch.is64bit = true;
+ } else {
+ if (!kvm__arch_get_elf_32_info(&eh.ehdr32, fd_kernel, &ei))
+ return false;
+ kvm->arch.is64bit = false;
+ }
+
+ kvm->arch.entry_point = ei.entry_point;
+
+ if (lseek(fd_kernel, ei.offset, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ p = guest_flat_to_host(kvm, ei.load_addr);
+
+ pr_info("ELF Loading 0x%lx bytes from 0x%llx to 0x%llx",
+ (unsigned long)ei.len, (unsigned long long)ei.offset,
+ (unsigned long long)ei.load_addr);
+
+ if (read_in_full(fd_kernel, p, ei.len) != (ssize_t)ei.len)
+ die_perror("read");
+
+ return true;
+}
+
+bool kvm__arch_load_kernel_image(struct kvm *kvm, int fd_kernel, int fd_initrd,
+ const char *kernel_cmdline)
+{
+ if (fd_initrd != -1) {
+ pr_err("Initrd not supported on MIPS.");
+ return false;
+ }
+
+ if (load_elf_binary(kvm, fd_kernel)) {
+ kvm__mips_install_cmdline(kvm);
+ return true;
+ }
+
+ return load_flat_binary(kvm, fd_kernel);
+}
+
+void ioport__map_irq(u8 *irq)
+{
+}
diff --git a/kvmtool/mmio.c b/kvmtool/mmio.c
new file mode 100644
index 0000000..cd141cd
--- /dev/null
+++ b/kvmtool/mmio.c
@@ -0,0 +1,196 @@
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/rbtree-interval.h"
+#include "kvm/mutex.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include <sys/ioctl.h>
+#include <linux/kvm.h>
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/err.h>
+#include <errno.h>
+
+#define mmio_node(n) rb_entry(n, struct mmio_mapping, node)
+
+static DEFINE_MUTEX(mmio_lock);
+
+struct mmio_mapping {
+ struct rb_int_node node;
+ void (*mmio_fn)(struct kvm_cpu *vcpu, u64 addr, u8 *data, u32 len, u8 is_write, void *ptr);
+ void *ptr;
+ u32 refcount;
+ bool remove;
+};
+
+static struct rb_root mmio_tree = RB_ROOT;
+
+static struct mmio_mapping *mmio_search(struct rb_root *root, u64 addr, u64 len)
+{
+ struct rb_int_node *node;
+
+ node = rb_int_search_range(root, addr, addr + len);
+ if (node == NULL)
+ return NULL;
+
+ return mmio_node(node);
+}
+
+/* Find lowest match, Check for overlap */
+static struct mmio_mapping *mmio_search_single(struct rb_root *root, u64 addr)
+{
+ struct rb_int_node *node;
+
+ node = rb_int_search_single(root, addr);
+ if (node == NULL)
+ return NULL;
+
+ return mmio_node(node);
+}
+
+static int mmio_insert(struct rb_root *root, struct mmio_mapping *data)
+{
+ return rb_int_insert(root, &data->node);
+}
+
+static void mmio_remove(struct rb_root *root, struct mmio_mapping *data)
+{
+ rb_int_erase(root, &data->node);
+}
+
+static const char *to_direction(u8 is_write)
+{
+ if (is_write)
+ return "write";
+
+ return "read";
+}
+
+static struct mmio_mapping *mmio_get(struct rb_root *root, u64 phys_addr, u32 len)
+{
+ struct mmio_mapping *mmio;
+
+ mutex_lock(&mmio_lock);
+ mmio = mmio_search(root, phys_addr, len);
+ if (mmio)
+ mmio->refcount++;
+ mutex_unlock(&mmio_lock);
+
+ return mmio;
+}
+
+/* Called with mmio_lock held. */
+static void mmio_deregister(struct kvm *kvm, struct rb_root *root, struct mmio_mapping *mmio)
+{
+ struct kvm_coalesced_mmio_zone zone = (struct kvm_coalesced_mmio_zone) {
+ .addr = rb_int_start(&mmio->node),
+ .size = 1,
+ };
+ ioctl(kvm->vm_fd, KVM_UNREGISTER_COALESCED_MMIO, &zone);
+
+ mmio_remove(root, mmio);
+ free(mmio);
+}
+
+static void mmio_put(struct kvm *kvm, struct rb_root *root, struct mmio_mapping *mmio)
+{
+ mutex_lock(&mmio_lock);
+ mmio->refcount--;
+ if (mmio->remove && mmio->refcount == 0)
+ mmio_deregister(kvm, root, mmio);
+ mutex_unlock(&mmio_lock);
+}
+
+int kvm__register_mmio(struct kvm *kvm, u64 phys_addr, u64 phys_addr_len, bool coalesce,
+ void (*mmio_fn)(struct kvm_cpu *vcpu, u64 addr, u8 *data, u32 len, u8 is_write, void *ptr),
+ void *ptr)
+{
+ struct mmio_mapping *mmio;
+ struct kvm_coalesced_mmio_zone zone;
+ int ret;
+
+ mmio = malloc(sizeof(*mmio));
+ if (mmio == NULL)
+ return -ENOMEM;
+
+ *mmio = (struct mmio_mapping) {
+ .node = RB_INT_INIT(phys_addr, phys_addr + phys_addr_len),
+ .mmio_fn = mmio_fn,
+ .ptr = ptr,
+ /*
+ * Start from 0 because kvm__deregister_mmio() doesn't decrement
+ * the reference count.
+ */
+ .refcount = 0,
+ .remove = false,
+ };
+
+ if (coalesce) {
+ zone = (struct kvm_coalesced_mmio_zone) {
+ .addr = phys_addr,
+ .size = phys_addr_len,
+ };
+ ret = ioctl(kvm->vm_fd, KVM_REGISTER_COALESCED_MMIO, &zone);
+ if (ret < 0) {
+ free(mmio);
+ return -errno;
+ }
+ }
+ mutex_lock(&mmio_lock);
+ ret = mmio_insert(&mmio_tree, mmio);
+ mutex_unlock(&mmio_lock);
+
+ return ret;
+}
+
+bool kvm__deregister_mmio(struct kvm *kvm, u64 phys_addr)
+{
+ struct mmio_mapping *mmio;
+
+ mutex_lock(&mmio_lock);
+ mmio = mmio_search_single(&mmio_tree, phys_addr);
+ if (mmio == NULL) {
+ mutex_unlock(&mmio_lock);
+ return false;
+ }
+ /*
+ * The PCI emulation code calls this function when memory access is
+ * disabled for a device, or when a BAR has a new address assigned. PCI
+ * emulation doesn't use any locks and as a result we can end up in a
+ * situation where we have called mmio_get() to do emulation on one VCPU
+ * thread (let's call it VCPU0), and several other VCPU threads have
+ * called kvm__deregister_mmio(). In this case, if we decrement refcount
+ * kvm__deregister_mmio() (either directly, or by calling mmio_put()),
+ * refcount will reach 0 and we will free the mmio node before VCPU0 has
+ * called mmio_put(). This will trigger use-after-free errors on VCPU0.
+ */
+ if (mmio->refcount == 0)
+ mmio_deregister(kvm, &mmio_tree, mmio);
+ else
+ mmio->remove = true;
+ mutex_unlock(&mmio_lock);
+
+ return true;
+}
+
+bool kvm__emulate_mmio(struct kvm_cpu *vcpu, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ struct mmio_mapping *mmio;
+
+ mmio = mmio_get(&mmio_tree, phys_addr, len);
+ if (!mmio) {
+ if (vcpu->kvm->cfg.mmio_debug)
+ fprintf(stderr, "Warning: Ignoring MMIO %s at %016llx (length %u)\n",
+ to_direction(is_write),
+ (unsigned long long)phys_addr, len);
+ goto out;
+ }
+
+ mmio->mmio_fn(vcpu, phys_addr, data, len, is_write, mmio->ptr);
+ mmio_put(vcpu->kvm, &mmio_tree, mmio);
+
+out:
+ return true;
+}
diff --git a/kvmtool/net/uip/arp.c b/kvmtool/net/uip/arp.c
new file mode 100644
index 0000000..98423da
--- /dev/null
+++ b/kvmtool/net/uip/arp.c
@@ -0,0 +1,30 @@
+#include "kvm/uip.h"
+
+int uip_tx_do_arp(struct uip_tx_arg *arg)
+{
+ struct uip_arp *arp, *arp2;
+ struct uip_info *info;
+ struct uip_buf *buf;
+
+ info = arg->info;
+ buf = uip_buf_clone(arg);
+
+ arp = (struct uip_arp *)(arg->eth);
+ arp2 = (struct uip_arp *)(buf->eth);
+
+ /*
+ * ARP replay code: 2
+ */
+ arp2->op = htons(0x2);
+ arp2->dmac = arp->smac;
+ arp2->dip = arp->sip;
+
+ if (arp->dip == htonl(info->host_ip)) {
+ arp2->smac = info->host_mac;
+ arp2->sip = htonl(info->host_ip);
+
+ uip_buf_set_used(info, buf);
+ }
+
+ return 0;
+}
diff --git a/kvmtool/net/uip/buf.c b/kvmtool/net/uip/buf.c
new file mode 100644
index 0000000..f29ad41
--- /dev/null
+++ b/kvmtool/net/uip/buf.c
@@ -0,0 +1,114 @@
+#include "kvm/uip.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+struct uip_buf *uip_buf_get_used(struct uip_info *info)
+{
+ struct uip_buf *buf;
+ bool found = false;
+
+ mutex_lock(&info->buf_lock);
+
+ while (!(info->buf_used_nr > 0))
+ pthread_cond_wait(&info->buf_used_cond, &info->buf_lock.mutex);
+
+ list_for_each_entry(buf, &info->buf_head, list) {
+ if (buf->status == UIP_BUF_STATUS_USED) {
+ /*
+ * Set status to INUSE immediately to prevent
+ * someone from using this buf until we free it
+ */
+ buf->status = UIP_BUF_STATUS_INUSE;
+ info->buf_used_nr--;
+ found = true;
+ break;
+ }
+ }
+
+ mutex_unlock(&info->buf_lock);
+
+ return found ? buf : NULL;
+}
+
+struct uip_buf *uip_buf_get_free(struct uip_info *info)
+{
+ struct uip_buf *buf;
+ bool found = false;
+
+ mutex_lock(&info->buf_lock);
+
+ while (!(info->buf_free_nr > 0))
+ pthread_cond_wait(&info->buf_free_cond, &info->buf_lock.mutex);
+
+ list_for_each_entry(buf, &info->buf_head, list) {
+ if (buf->status == UIP_BUF_STATUS_FREE) {
+ /*
+ * Set status to INUSE immediately to prevent
+ * someone from using this buf until we free it
+ */
+ buf->status = UIP_BUF_STATUS_INUSE;
+ info->buf_free_nr--;
+ found = true;
+ break;
+ }
+ }
+
+ mutex_unlock(&info->buf_lock);
+
+ return found ? buf : NULL;
+}
+
+struct uip_buf *uip_buf_set_used(struct uip_info *info, struct uip_buf *buf)
+{
+ mutex_lock(&info->buf_lock);
+
+ buf->status = UIP_BUF_STATUS_USED;
+ info->buf_used_nr++;
+ pthread_cond_signal(&info->buf_used_cond);
+
+ mutex_unlock(&info->buf_lock);
+
+ return buf;
+}
+
+struct uip_buf *uip_buf_set_free(struct uip_info *info, struct uip_buf *buf)
+{
+ mutex_lock(&info->buf_lock);
+
+ buf->status = UIP_BUF_STATUS_FREE;
+ info->buf_free_nr++;
+ pthread_cond_signal(&info->buf_free_cond);
+
+ mutex_unlock(&info->buf_lock);
+
+ return buf;
+}
+
+struct uip_buf *uip_buf_clone(struct uip_tx_arg *arg)
+{
+ struct uip_buf *buf;
+ struct uip_eth *eth2;
+ struct uip_info *info;
+
+ info = arg->info;
+
+ /*
+ * Get buffer from device to guest
+ */
+ buf = uip_buf_get_free(info);
+
+ /*
+ * Clone buffer
+ */
+ memcpy(buf->vnet, arg->vnet, arg->vnet_len);
+ memcpy(buf->eth, arg->eth, arg->eth_len);
+ buf->vnet_len = arg->vnet_len;
+ buf->eth_len = arg->eth_len;
+
+ eth2 = (struct uip_eth *)buf->eth;
+ eth2->src = info->host_mac;
+ eth2->dst = arg->eth->src;
+
+ return buf;
+}
diff --git a/kvmtool/net/uip/core.c b/kvmtool/net/uip/core.c
new file mode 100644
index 0000000..977b9b0
--- /dev/null
+++ b/kvmtool/net/uip/core.c
@@ -0,0 +1,173 @@
+#include "kvm/mutex.h"
+#include "kvm/uip.h"
+
+#include <linux/virtio_net.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <kvm/iovec.h>
+
+int uip_tx(struct iovec *iov, u16 out, struct uip_info *info)
+{
+ void *vnet;
+ struct uip_tx_arg arg;
+ int eth_len, vnet_len;
+ struct uip_eth *eth;
+ u8 *buf = NULL;
+ u16 proto;
+ int i;
+
+ /*
+ * Buffer from guest to device
+ */
+ vnet_len = iov[0].iov_len;
+ vnet = iov[0].iov_base;
+
+ eth_len = iov[1].iov_len;
+ eth = iov[1].iov_base;
+
+ /*
+ * In case, ethernet frame is in more than one iov entry.
+ * Copy iov buffer into one linear buffer.
+ */
+ if (out > 2) {
+ eth_len = 0;
+ for (i = 1; i < out; i++)
+ eth_len += iov[i].iov_len;
+
+ buf = malloc(eth_len);
+ if (!buf)
+ return -ENOMEM;
+
+ eth = (struct uip_eth *)buf;
+ for (i = 1; i < out; i++) {
+ memcpy(buf, iov[i].iov_base, iov[i].iov_len);
+ buf += iov[i].iov_len;
+ }
+ }
+
+ memset(&arg, 0, sizeof(arg));
+
+ arg.vnet_len = vnet_len;
+ arg.eth_len = eth_len;
+ arg.info = info;
+ arg.vnet = vnet;
+ arg.eth = eth;
+
+ /*
+ * Check package type
+ */
+ proto = ntohs(eth->type);
+
+ switch (proto) {
+ case UIP_ETH_P_ARP:
+ uip_tx_do_arp(&arg);
+ break;
+ case UIP_ETH_P_IP:
+ uip_tx_do_ipv4(&arg);
+ break;
+ default:
+ break;
+ }
+
+ if (out > 2 && buf)
+ free(eth);
+
+ return vnet_len + eth_len;
+}
+
+int uip_rx(struct iovec *iov, u16 in, struct uip_info *info)
+{
+ struct uip_buf *buf;
+ int len;
+
+ /*
+ * Sleep until there is a buffer for guest
+ */
+ buf = uip_buf_get_used(info);
+
+ memcpy_toiovecend(iov, buf->vnet, 0, buf->vnet_len);
+ memcpy_toiovecend(iov, buf->eth, buf->vnet_len, buf->eth_len);
+
+ len = buf->vnet_len + buf->eth_len;
+
+ uip_buf_set_free(info, buf);
+ return len;
+}
+
+void uip_static_init(struct uip_info *info)
+{
+ struct list_head *udp_socket_head;
+ struct list_head *tcp_socket_head;
+ struct list_head *buf_head;
+
+ udp_socket_head = &info->udp_socket_head;
+ tcp_socket_head = &info->tcp_socket_head;
+ buf_head = &info->buf_head;
+
+ INIT_LIST_HEAD(udp_socket_head);
+ INIT_LIST_HEAD(tcp_socket_head);
+ INIT_LIST_HEAD(buf_head);
+
+ mutex_init(&info->udp_socket_lock);
+ mutex_init(&info->tcp_socket_lock);
+ mutex_init(&info->buf_lock);
+
+ pthread_cond_init(&info->buf_used_cond, NULL);
+ pthread_cond_init(&info->buf_free_cond, NULL);
+
+ info->buf_used_nr = 0;
+}
+
+int uip_init(struct uip_info *info)
+{
+ struct list_head *buf_head;
+ struct uip_buf *buf;
+ int buf_nr;
+ int i;
+
+ buf_head = &info->buf_head;
+ buf_nr = info->buf_nr;
+
+ for (i = 0; i < buf_nr; i++) {
+ buf = malloc(sizeof(*buf));
+ memset(buf, 0, sizeof(*buf));
+
+ buf->status = UIP_BUF_STATUS_FREE;
+ buf->info = info;
+ buf->id = i;
+ list_add_tail(&buf->list, buf_head);
+ }
+
+ list_for_each_entry(buf, buf_head, list) {
+ buf->vnet_len = info->vnet_hdr_len;
+ buf->vnet = malloc(buf->vnet_len);
+ buf->eth_len = 1024*64 + sizeof(struct uip_pseudo_hdr);
+ buf->eth = malloc(buf->eth_len);
+
+ memset(buf->vnet, 0, buf->vnet_len);
+ memset(buf->eth, 0, buf->eth_len);
+ }
+
+ info->buf_free_nr = buf_nr;
+
+ uip_dhcp_get_dns(info);
+
+ return 0;
+}
+
+void uip_exit(struct uip_info *info)
+{
+ struct uip_buf *buf, *next;
+
+ uip_udp_exit(info);
+ uip_tcp_exit(info);
+ uip_dhcp_exit(info);
+
+ list_for_each_entry_safe(buf, next, &info->buf_head, list) {
+ free(buf->vnet);
+ free(buf->eth);
+ list_del(&buf->list);
+ free(buf);
+ }
+ uip_static_init(info);
+}
diff --git a/kvmtool/net/uip/csum.c b/kvmtool/net/uip/csum.c
new file mode 100644
index 0000000..6f5c4b3
--- /dev/null
+++ b/kvmtool/net/uip/csum.c
@@ -0,0 +1,90 @@
+#include "kvm/uip.h"
+
+static u16 uip_csum(u16 csum, u8 *addr, u16 count)
+{
+ long sum = csum;
+
+ while (count > 1) {
+ sum += *(u16 *)addr;
+ addr += 2;
+ count -= 2;
+ }
+
+ if (count > 0)
+ sum += *(unsigned char *)addr;
+
+ while (sum>>16)
+ sum = (sum & 0xffff) + (sum >> 16);
+
+ return ~sum;
+}
+
+u16 uip_csum_ip(struct uip_ip *ip)
+{
+ return uip_csum(0, &ip->vhl, uip_ip_hdrlen(ip));
+}
+
+u16 uip_csum_icmp(struct uip_icmp *icmp)
+{
+ struct uip_ip *ip;
+
+ ip = &icmp->ip;
+ return icmp->csum = uip_csum(0, &icmp->type, htons(ip->len) - uip_ip_hdrlen(ip) - 8); /* icmp header len = 8 */
+}
+
+u16 uip_csum_udp(struct uip_udp *udp)
+{
+ struct uip_pseudo_hdr hdr;
+ struct uip_ip *ip;
+ int udp_len;
+ u8 *udp_hdr = (u8 *)udp + offsetof(struct uip_udp, sport);
+
+ ip = &udp->ip;
+
+ hdr.sip = ip->sip;
+ hdr.dip = ip->dip;
+ hdr.zero = 0;
+ hdr.proto = ip->proto;
+ hdr.len = udp->len;
+
+ udp_len = uip_udp_len(udp);
+
+ if (udp_len % 2) {
+ udp_hdr[udp_len] = 0; /* zero padding */
+ memcpy(udp_hdr + udp_len + 1, &hdr, sizeof(hdr));
+ return uip_csum(0, udp_hdr, udp_len + 1 + sizeof(hdr));
+ } else {
+ memcpy(udp_hdr + udp_len, &hdr, sizeof(hdr));
+ return uip_csum(0, udp_hdr, udp_len + sizeof(hdr));
+ }
+
+}
+
+u16 uip_csum_tcp(struct uip_tcp *tcp)
+{
+ struct uip_pseudo_hdr hdr;
+ struct uip_ip *ip;
+ u16 tcp_len;
+ u8 *tcp_hdr = (u8 *)tcp + offsetof(struct uip_tcp, sport);
+
+ ip = &tcp->ip;
+ tcp_len = ntohs(ip->len) - uip_ip_hdrlen(ip);
+
+ hdr.sip = ip->sip;
+ hdr.dip = ip->dip;
+ hdr.zero = 0;
+ hdr.proto = ip->proto;
+ hdr.len = htons(tcp_len);
+
+ if (tcp_len > UIP_MAX_TCP_PAYLOAD + 20)
+ pr_warning("tcp_len(%d) is too large", tcp_len);
+
+ if (tcp_len % 2) {
+ tcp_hdr[tcp_len] = 0; /* zero padding */
+ memcpy(tcp_hdr + tcp_len + 1, &hdr, sizeof(hdr));
+ return uip_csum(0, tcp_hdr, tcp_len + 1 + sizeof(hdr));
+ } else {
+ memcpy(tcp_hdr + tcp_len, &hdr, sizeof(hdr));
+ return uip_csum(0, tcp_hdr, tcp_len + sizeof(hdr));
+ }
+}
diff --git a/kvmtool/net/uip/dhcp.c b/kvmtool/net/uip/dhcp.c
new file mode 100644
index 0000000..9de5588
--- /dev/null
+++ b/kvmtool/net/uip/dhcp.c
@@ -0,0 +1,208 @@
+#include "kvm/uip.h"
+
+#include <arpa/inet.h>
+
+#define EMPTY_ADDR "0.0.0.0"
+
+static inline bool uip_dhcp_is_discovery(struct uip_dhcp *dhcp)
+{
+ return (dhcp->option[2] == UIP_DHCP_DISCOVER &&
+ dhcp->option[1] == UIP_DHCP_TAG_MSG_TYPE_LEN &&
+ dhcp->option[0] == UIP_DHCP_TAG_MSG_TYPE);
+}
+
+static inline bool uip_dhcp_is_request(struct uip_dhcp *dhcp)
+{
+ return (dhcp->option[2] == UIP_DHCP_REQUEST &&
+ dhcp->option[1] == UIP_DHCP_TAG_MSG_TYPE_LEN &&
+ dhcp->option[0] == UIP_DHCP_TAG_MSG_TYPE);
+}
+
+bool uip_udp_is_dhcp(struct uip_udp *udp)
+{
+ struct uip_dhcp *dhcp;
+
+ if (ntohs(udp->sport) != UIP_DHCP_PORT_CLIENT ||
+ ntohs(udp->dport) != UIP_DHCP_PORT_SERVER)
+ return false;
+
+ dhcp = (struct uip_dhcp *)udp;
+
+ if (ntohl(dhcp->magic_cookie) != UIP_DHCP_MAGIC_COOKIE)
+ return false;
+
+ return true;
+}
+
+int uip_dhcp_get_dns(struct uip_info *info)
+{
+ char key[256], val[256];
+ struct in_addr addr;
+ int ret = -1;
+ int n = 0;
+ FILE *fp;
+ u32 ip;
+
+ fp = fopen("/etc/resolv.conf", "r");
+ if (!fp)
+ return ret;
+
+ while (!feof(fp)) {
+ if (fscanf(fp, "%s %s\n", key, val) != 2)
+ continue;
+ if (strncmp("domain", key, 6) == 0)
+ info->domain_name = strndup(val, UIP_DHCP_MAX_DOMAIN_NAME_LEN);
+ else if (strncmp("nameserver", key, 10) == 0) {
+ if (!inet_aton(val, &addr))
+ continue;
+ ip = ntohl(addr.s_addr);
+ if (n < UIP_DHCP_MAX_DNS_SERVER_NR)
+ info->dns_ip[n++] = ip;
+ ret = 0;
+ }
+ }
+
+ fclose(fp);
+ return ret;
+}
+
+static int uip_dhcp_fill_option_name_and_server(struct uip_info *info, u8 *opt, int i)
+{
+ u8 domain_name_len;
+ u32 *addr;
+ int n;
+
+ if (info->domain_name) {
+ domain_name_len = strlen(info->domain_name);
+ opt[i++] = UIP_DHCP_TAG_DOMAIN_NAME;
+ opt[i++] = domain_name_len;
+ memcpy(&opt[i], info->domain_name, domain_name_len);
+ i += domain_name_len;
+ }
+
+ for (n = 0; n < UIP_DHCP_MAX_DNS_SERVER_NR; n++) {
+ if (info->dns_ip[n] == 0)
+ continue;
+ opt[i++] = UIP_DHCP_TAG_DNS_SERVER;
+ opt[i++] = UIP_DHCP_TAG_DNS_SERVER_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->dns_ip[n]);
+ i += UIP_DHCP_TAG_DNS_SERVER_LEN;
+ }
+
+ return i;
+}
+static int uip_dhcp_fill_option(struct uip_info *info, struct uip_dhcp *dhcp, int reply_msg_type)
+{
+ int i = 0;
+ u32 *addr;
+ u8 *opt;
+
+ opt = dhcp->option;
+
+ opt[i++] = UIP_DHCP_TAG_MSG_TYPE;
+ opt[i++] = UIP_DHCP_TAG_MSG_TYPE_LEN;
+ opt[i++] = reply_msg_type;
+
+ opt[i++] = UIP_DHCP_TAG_SERVER_ID;
+ opt[i++] = UIP_DHCP_TAG_SERVER_ID_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->host_ip);
+ i += UIP_DHCP_TAG_SERVER_ID_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_LEASE_TIME;
+ opt[i++] = UIP_DHCP_TAG_LEASE_TIME_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(UIP_DHCP_LEASE_TIME);
+ i += UIP_DHCP_TAG_LEASE_TIME_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_SUBMASK;
+ opt[i++] = UIP_DHCP_TAG_SUBMASK_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->guest_netmask);
+ i += UIP_DHCP_TAG_SUBMASK_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_ROUTER;
+ opt[i++] = UIP_DHCP_TAG_ROUTER_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->host_ip);
+ i += UIP_DHCP_TAG_ROUTER_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_ROOT;
+ opt[i++] = strlen(EMPTY_ADDR);
+ addr = (u32 *)&opt[i];
+ strcpy((void *) addr, EMPTY_ADDR);
+ i += strlen(EMPTY_ADDR);
+
+ i = uip_dhcp_fill_option_name_and_server(info, opt, i);
+
+ opt[i++] = UIP_DHCP_TAG_END;
+
+ return 0;
+}
+
+static int uip_dhcp_make_pkg(struct uip_info *info, struct uip_udp_socket *sk, struct uip_buf *buf, u8 reply_msg_type)
+{
+ struct uip_dhcp *dhcp;
+
+ dhcp = (struct uip_dhcp *)buf->eth;
+
+ dhcp->msg_type = 2;
+ dhcp->client_ip = 0;
+ dhcp->your_ip = htonl(info->guest_ip);
+ dhcp->server_ip = htonl(info->host_ip);
+ dhcp->agent_ip = 0;
+
+ uip_dhcp_fill_option(info, dhcp, reply_msg_type);
+
+ sk->sip = htonl(info->guest_ip);
+ sk->dip = htonl(info->host_ip);
+ sk->sport = htons(UIP_DHCP_PORT_CLIENT);
+ sk->dport = htons(UIP_DHCP_PORT_SERVER);
+
+ return 0;
+}
+
+int uip_tx_do_ipv4_udp_dhcp(struct uip_tx_arg *arg)
+{
+ struct uip_udp_socket sk;
+ struct uip_dhcp *dhcp;
+ struct uip_info *info;
+ struct uip_buf *buf;
+ u8 reply_msg_type;
+
+ dhcp = (struct uip_dhcp *)arg->eth;
+
+ if (uip_dhcp_is_discovery(dhcp))
+ reply_msg_type = UIP_DHCP_OFFER;
+ else if (uip_dhcp_is_request(dhcp))
+ reply_msg_type = UIP_DHCP_ACK;
+ else
+ return -1;
+
+ buf = uip_buf_clone(arg);
+ info = arg->info;
+
+ /*
+ * Cook DHCP pkg
+ */
+ uip_dhcp_make_pkg(info, &sk, buf, reply_msg_type);
+
+ /*
+ * Cook UDP pkg
+ */
+ uip_udp_make_pkg(info, &sk, buf, NULL, UIP_DHCP_MAX_PAYLOAD_LEN);
+
+ /*
+ * Send data received from socket to guest
+ */
+ uip_buf_set_used(info, buf);
+
+ return 0;
+}
+
+void uip_dhcp_exit(struct uip_info *info)
+{
+ free(info->domain_name);
+ info->domain_name = NULL;
+}
diff --git a/kvmtool/net/uip/icmp.c b/kvmtool/net/uip/icmp.c
new file mode 100644
index 0000000..233297c
--- /dev/null
+++ b/kvmtool/net/uip/icmp.c
@@ -0,0 +1,29 @@
+#include "kvm/uip.h"
+
+int uip_tx_do_ipv4_icmp(struct uip_tx_arg *arg)
+{
+ struct uip_ip *ip, *ip2;
+ struct uip_icmp *icmp2;
+ struct uip_buf *buf;
+
+ buf = uip_buf_clone(arg);
+
+ icmp2 = (struct uip_icmp *)(buf->eth);
+ ip2 = (struct uip_ip *)(buf->eth);
+ ip = (struct uip_ip *)(arg->eth);
+
+ ip2->sip = ip->dip;
+ ip2->dip = ip->sip;
+ ip2->csum = 0;
+ /*
+ * ICMP reply: 0
+ */
+ icmp2->type = 0;
+ icmp2->csum = 0;
+ ip2->csum = uip_csum_ip(ip2);
+ icmp2->csum = uip_csum_icmp(icmp2);
+
+ uip_buf_set_used(arg->info, buf);
+
+ return 0;
+}
diff --git a/kvmtool/net/uip/ipv4.c b/kvmtool/net/uip/ipv4.c
new file mode 100644
index 0000000..58373fd
--- /dev/null
+++ b/kvmtool/net/uip/ipv4.c
@@ -0,0 +1,29 @@
+#include "kvm/uip.h"
+
+int uip_tx_do_ipv4(struct uip_tx_arg *arg)
+{
+ struct uip_ip *ip;
+
+ ip = (struct uip_ip *)(arg->eth);
+
+ if (uip_ip_hdrlen(ip) != 20) {
+ pr_warning("IP header length is not 20 bytes");
+ return -1;
+ }
+
+ switch (ip->proto) {
+ case UIP_IP_P_ICMP:
+ uip_tx_do_ipv4_icmp(arg);
+ break;
+ case UIP_IP_P_TCP:
+ uip_tx_do_ipv4_tcp(arg);
+ break;
+ case UIP_IP_P_UDP:
+ uip_tx_do_ipv4_udp(arg);
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
diff --git a/kvmtool/net/uip/tcp.c b/kvmtool/net/uip/tcp.c
new file mode 100644
index 0000000..8e0ad52
--- /dev/null
+++ b/kvmtool/net/uip/tcp.c
@@ -0,0 +1,382 @@
+#include "kvm/uip.h"
+
+#include <kvm/kvm.h>
+#include <linux/virtio_net.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <arpa/inet.h>
+
+static int uip_tcp_socket_close(struct uip_tcp_socket *sk, int how)
+{
+ shutdown(sk->fd, how);
+
+ if (sk->write_done && sk->read_done) {
+ shutdown(sk->fd, SHUT_RDWR);
+ close(sk->fd);
+
+ mutex_lock(sk->lock);
+ list_del(&sk->list);
+ mutex_unlock(sk->lock);
+
+ free(sk->buf);
+ free(sk);
+ }
+
+ return 0;
+}
+
+static struct uip_tcp_socket *uip_tcp_socket_find(struct uip_tx_arg *arg, u32 sip, u32 dip, u16 sport, u16 dport)
+{
+ struct list_head *sk_head;
+ struct mutex *sk_lock;
+ struct uip_tcp_socket *sk;
+
+ sk_head = &arg->info->tcp_socket_head;
+ sk_lock = &arg->info->tcp_socket_lock;
+
+ mutex_lock(sk_lock);
+ list_for_each_entry(sk, sk_head, list) {
+ if (sk->sip == sip && sk->dip == dip && sk->sport == sport && sk->dport == dport) {
+ mutex_unlock(sk_lock);
+ return sk;
+ }
+ }
+ mutex_unlock(sk_lock);
+
+ return NULL;
+}
+
+static struct uip_tcp_socket *uip_tcp_socket_alloc(struct uip_tx_arg *arg, u32 sip, u32 dip, u16 sport, u16 dport)
+{
+ struct list_head *sk_head;
+ struct uip_tcp_socket *sk;
+ struct mutex *sk_lock;
+ struct uip_tcp *tcp;
+ struct uip_ip *ip;
+ int ret;
+
+ tcp = (struct uip_tcp *)arg->eth;
+ ip = (struct uip_ip *)arg->eth;
+
+ sk_head = &arg->info->tcp_socket_head;
+ sk_lock = &arg->info->tcp_socket_lock;
+
+ sk = malloc(sizeof(*sk));
+ memset(sk, 0, sizeof(*sk));
+
+ sk->lock = sk_lock;
+ sk->info = arg->info;
+
+ sk->fd = socket(AF_INET, SOCK_STREAM, 0);
+ sk->addr.sin_family = AF_INET;
+ sk->addr.sin_port = dport;
+ sk->addr.sin_addr.s_addr = dip;
+
+ pthread_cond_init(&sk->cond, NULL);
+
+ if (ntohl(dip) == arg->info->host_ip)
+ sk->addr.sin_addr.s_addr = inet_addr("127.0.0.1");
+
+ ret = connect(sk->fd, (struct sockaddr *)&sk->addr, sizeof(sk->addr));
+ if (ret) {
+ free(sk);
+ return NULL;
+ }
+
+ sk->sip = ip->sip;
+ sk->dip = ip->dip;
+ sk->sport = tcp->sport;
+ sk->dport = tcp->dport;
+
+ mutex_lock(sk_lock);
+ list_add_tail(&sk->list, sk_head);
+ mutex_unlock(sk_lock);
+
+ return sk;
+}
+
+/* Caller holds the sk lock */
+static void uip_tcp_socket_free(struct uip_tcp_socket *sk)
+{
+ /*
+ * Here we assume that the virtqueues are already inactive so we don't
+ * race with uip_tx_do_ipv4_tcp. We are racing with
+ * uip_tcp_socket_thread though, but holding the sk lock ensures that it
+ * cannot free data concurrently.
+ */
+ if (sk->thread) {
+ pthread_cancel(sk->thread);
+ pthread_join(sk->thread, NULL);
+ }
+
+ sk->write_done = sk->read_done = 1;
+ uip_tcp_socket_close(sk, SHUT_RDWR);
+}
+
+static int uip_tcp_payload_send(struct uip_tcp_socket *sk, u8 flag, u16 payload_len)
+{
+ struct uip_info *info;
+ struct uip_eth *eth2;
+ struct uip_tcp *tcp2;
+ struct uip_buf *buf;
+ struct uip_ip *ip2;
+
+ info = sk->info;
+
+ /*
+ * Get free buffer to send data to guest
+ */
+ buf = uip_buf_get_free(info);
+
+ /*
+ * Cook a ethernet frame
+ */
+ tcp2 = (struct uip_tcp *)buf->eth;
+ eth2 = (struct uip_eth *)buf->eth;
+ ip2 = (struct uip_ip *)buf->eth;
+
+ eth2->src = info->host_mac;
+ eth2->dst = info->guest_mac;
+ eth2->type = htons(UIP_ETH_P_IP);
+
+ ip2->vhl = UIP_IP_VER_4 | UIP_IP_HDR_LEN;
+ ip2->tos = 0;
+ ip2->id = 0;
+ ip2->flgfrag = 0;
+ ip2->ttl = UIP_IP_TTL;
+ ip2->proto = UIP_IP_P_TCP;
+ ip2->csum = 0;
+ ip2->sip = sk->dip;
+ ip2->dip = sk->sip;
+
+ tcp2->sport = sk->dport;
+ tcp2->dport = sk->sport;
+ tcp2->seq = htonl(sk->seq_server);
+ tcp2->ack = htonl(sk->ack_server);
+ /*
+ * Diable TCP options, tcp hdr len equals 20 bytes
+ */
+ tcp2->off = UIP_TCP_HDR_LEN;
+ tcp2->flg = flag;
+ tcp2->win = htons(UIP_TCP_WIN_SIZE);
+ tcp2->csum = 0;
+ tcp2->urgent = 0;
+
+ if (payload_len > 0)
+ memcpy(uip_tcp_payload(tcp2), sk->payload, payload_len);
+
+ ip2->len = htons(uip_tcp_hdrlen(tcp2) + payload_len + uip_ip_hdrlen(ip2));
+ ip2->csum = uip_csum_ip(ip2);
+ tcp2->csum = uip_csum_tcp(tcp2);
+
+ /*
+ * virtio_net_hdr
+ */
+ buf->vnet_len = info->vnet_hdr_len;
+ memset(buf->vnet, 0, buf->vnet_len);
+
+ buf->eth_len = ntohs(ip2->len) + uip_eth_hdrlen(&ip2->eth);
+
+ /*
+ * Increase server seq
+ */
+ sk->seq_server += payload_len;
+
+ /*
+ * Send data received from socket to guest
+ */
+ uip_buf_set_used(info, buf);
+
+ return 0;
+}
+
+static void *uip_tcp_socket_thread(void *p)
+{
+ struct uip_tcp_socket *sk;
+ int len, left, ret;
+ u8 *pos;
+
+ kvm__set_thread_name("uip-tcp");
+
+ sk = p;
+
+ while (1) {
+ pos = sk->buf;
+
+ ret = read(sk->fd, sk->buf, UIP_MAX_TCP_PAYLOAD);
+
+ if (ret <= 0 || ret > UIP_MAX_TCP_PAYLOAD)
+ goto out;
+
+ left = ret;
+
+ while (left > 0) {
+ mutex_lock(sk->lock);
+ while ((len = sk->guest_acked + sk->window_size - sk->seq_server) <= 0)
+ pthread_cond_wait(&sk->cond, &sk->lock->mutex);
+ mutex_unlock(sk->lock);
+
+ sk->payload = pos;
+ if (len > left)
+ len = left;
+ if (len > UIP_MAX_TCP_PAYLOAD)
+ len = UIP_MAX_TCP_PAYLOAD;
+ left -= len;
+ pos += len;
+
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_ACK, len);
+ }
+ }
+
+out:
+ /*
+ * Close server to guest TCP connection
+ */
+ uip_tcp_socket_close(sk, SHUT_RD);
+
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_FIN | UIP_TCP_FLAG_ACK, 0);
+ sk->seq_server += 1;
+
+ sk->read_done = 1;
+
+ pthread_exit(NULL);
+
+ return NULL;
+}
+
+static int uip_tcp_socket_receive(struct uip_tcp_socket *sk)
+{
+ int ret;
+
+ if (sk->thread == 0) {
+ sk->buf = malloc(UIP_MAX_TCP_PAYLOAD);
+ if (!sk->buf)
+ return -ENOMEM;
+ ret = pthread_create(&sk->thread, NULL, uip_tcp_socket_thread,
+ (void *)sk);
+ if (ret)
+ free(sk->buf);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int uip_tcp_socket_send(struct uip_tcp_socket *sk, struct uip_tcp *tcp)
+{
+ int len;
+ int ret;
+ u8 *payload;
+
+ if (sk->write_done)
+ return 0;
+
+ payload = uip_tcp_payload(tcp);
+ len = uip_tcp_payloadlen(tcp);
+
+ ret = write(sk->fd, payload, len);
+ if (ret != len)
+ pr_warning("tcp send error");
+
+ return ret;
+}
+
+int uip_tx_do_ipv4_tcp(struct uip_tx_arg *arg)
+{
+ struct uip_tcp_socket *sk;
+ struct uip_tcp *tcp;
+ struct uip_ip *ip;
+ int ret;
+
+ tcp = (struct uip_tcp *)arg->eth;
+ ip = (struct uip_ip *)arg->eth;
+
+ /*
+ * Guest is trying to start a TCP session, let's fake SYN-ACK to guest
+ */
+ if (uip_tcp_is_syn(tcp)) {
+ sk = uip_tcp_socket_alloc(arg, ip->sip, ip->dip, tcp->sport, tcp->dport);
+ if (!sk)
+ return -1;
+
+ sk->window_size = ntohs(tcp->win);
+
+ /*
+ * Setup ISN number
+ */
+ sk->isn_guest = uip_tcp_isn(tcp);
+ sk->isn_server = uip_tcp_isn_alloc();
+
+ sk->seq_server = sk->isn_server;
+ sk->ack_server = sk->isn_guest + 1;
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_SYN | UIP_TCP_FLAG_ACK, 0);
+ sk->seq_server += 1;
+
+ /*
+ * Start receive thread for data from remote to guest
+ */
+ uip_tcp_socket_receive(sk);
+
+ goto out;
+ }
+
+ /*
+ * Find socket we have allocated
+ */
+ sk = uip_tcp_socket_find(arg, ip->sip, ip->dip, tcp->sport, tcp->dport);
+ if (!sk)
+ return -1;
+
+ mutex_lock(sk->lock);
+ sk->window_size = ntohs(tcp->win);
+ sk->guest_acked = ntohl(tcp->ack);
+ pthread_cond_signal(&sk->cond);
+ mutex_unlock(sk->lock);
+
+ if (uip_tcp_is_fin(tcp)) {
+ if (sk->write_done)
+ goto out;
+
+ sk->write_done = 1;
+ sk->ack_server += 1;
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_ACK, 0);
+
+ /*
+ * Close guest to server TCP connection
+ */
+ uip_tcp_socket_close(sk, SHUT_WR);
+
+ goto out;
+ }
+
+ /*
+ * Ignore guest to server frames with zero tcp payload
+ */
+ if (uip_tcp_payloadlen(tcp) == 0)
+ goto out;
+
+ /*
+ * Sent out TCP data to remote host
+ */
+ ret = uip_tcp_socket_send(sk, tcp);
+ if (ret < 0)
+ return -1;
+ /*
+ * Send ACK to guest imediately
+ */
+ sk->ack_server += ret;
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_ACK, 0);
+
+out:
+ return 0;
+}
+
+void uip_tcp_exit(struct uip_info *info)
+{
+ struct uip_tcp_socket *sk, *next;
+
+ mutex_lock(&info->tcp_socket_lock);
+ list_for_each_entry_safe(sk, next, &info->tcp_socket_head, list)
+ uip_tcp_socket_free(sk);
+ mutex_unlock(&info->tcp_socket_lock);
+}
diff --git a/kvmtool/net/uip/udp.c b/kvmtool/net/uip/udp.c
new file mode 100644
index 0000000..d2580d0
--- /dev/null
+++ b/kvmtool/net/uip/udp.c
@@ -0,0 +1,268 @@
+#include "kvm/uip.h"
+
+#include <kvm/kvm.h>
+#include <linux/virtio_net.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <sys/socket.h>
+#include <sys/epoll.h>
+#include <fcntl.h>
+
+#define UIP_UDP_MAX_EVENTS 1000
+
+static struct uip_udp_socket *uip_udp_socket_find(struct uip_tx_arg *arg, u32 sip, u32 dip, u16 sport, u16 dport)
+{
+ struct list_head *sk_head;
+ struct uip_udp_socket *sk;
+ struct mutex *sk_lock;
+ struct epoll_event ev;
+ int flags;
+ int ret;
+
+ sk_head = &arg->info->udp_socket_head;
+ sk_lock = &arg->info->udp_socket_lock;
+
+ /*
+ * Find existing sk
+ */
+ mutex_lock(sk_lock);
+ list_for_each_entry(sk, sk_head, list) {
+ if (sk->sip == sip && sk->dip == dip && sk->sport == sport && sk->dport == dport) {
+ mutex_unlock(sk_lock);
+ return sk;
+ }
+ }
+ mutex_unlock(sk_lock);
+
+ /*
+ * Allocate new one
+ */
+ sk = malloc(sizeof(*sk));
+ memset(sk, 0, sizeof(*sk));
+
+ sk->lock = sk_lock;
+
+ sk->fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (sk->fd < 0)
+ goto out;
+
+ /*
+ * Set non-blocking
+ */
+ flags = fcntl(sk->fd, F_GETFL, 0);
+ flags |= O_NONBLOCK;
+ fcntl(sk->fd, F_SETFL, flags);
+
+ /*
+ * Add sk->fd to epoll_wait
+ */
+ ev.events = EPOLLIN;
+ ev.data.fd = sk->fd;
+ ev.data.ptr = sk;
+ if (arg->info->udp_epollfd <= 0)
+ arg->info->udp_epollfd = epoll_create(UIP_UDP_MAX_EVENTS);
+ ret = epoll_ctl(arg->info->udp_epollfd, EPOLL_CTL_ADD, sk->fd, &ev);
+ if (ret == -1)
+ pr_warning("epoll_ctl error");
+
+ sk->addr.sin_family = AF_INET;
+ sk->addr.sin_addr.s_addr = dip;
+ sk->addr.sin_port = dport;
+
+ sk->sip = sip;
+ sk->dip = dip;
+ sk->sport = sport;
+ sk->dport = dport;
+
+ mutex_lock(sk_lock);
+ list_add_tail(&sk->list, sk_head);
+ mutex_unlock(sk_lock);
+
+ return sk;
+
+out:
+ free(sk);
+ return NULL;
+}
+
+static int uip_udp_socket_send(struct uip_udp_socket *sk, struct uip_udp *udp)
+{
+ int len;
+ int ret;
+
+ len = ntohs(udp->len) - uip_udp_hdrlen(udp);
+
+ ret = sendto(sk->fd, udp->payload, len, 0, (struct sockaddr *)&sk->addr, sizeof(sk->addr));
+ if (ret != len)
+ return -1;
+
+ return 0;
+}
+
+int uip_udp_make_pkg(struct uip_info *info, struct uip_udp_socket *sk, struct uip_buf *buf, u8* payload, int payload_len)
+{
+ struct uip_eth *eth2;
+ struct uip_udp *udp2;
+ struct uip_ip *ip2;
+
+ /*
+ * Cook a ethernet frame
+ */
+ udp2 = (struct uip_udp *)(buf->eth);
+ eth2 = (struct uip_eth *)buf->eth;
+ ip2 = (struct uip_ip *)(buf->eth);
+
+ eth2->src = info->host_mac;
+ eth2->dst = info->guest_mac;
+ eth2->type = htons(UIP_ETH_P_IP);
+
+ ip2->vhl = UIP_IP_VER_4 | UIP_IP_HDR_LEN;
+ ip2->tos = 0;
+ ip2->id = 0;
+ ip2->flgfrag = 0;
+ ip2->ttl = UIP_IP_TTL;
+ ip2->proto = UIP_IP_P_UDP;
+ ip2->csum = 0;
+
+ ip2->sip = sk->dip;
+ ip2->dip = sk->sip;
+ udp2->sport = sk->dport;
+ udp2->dport = sk->sport;
+
+ udp2->len = htons(payload_len + uip_udp_hdrlen(udp2));
+ udp2->csum = 0;
+
+ if (payload)
+ memcpy(udp2->payload, payload, payload_len);
+
+ ip2->len = udp2->len + htons(uip_ip_hdrlen(ip2));
+ ip2->csum = uip_csum_ip(ip2);
+ udp2->csum = uip_csum_udp(udp2);
+
+ /*
+ * virtio_net_hdr
+ */
+ buf->vnet_len = info->vnet_hdr_len;
+ memset(buf->vnet, 0, buf->vnet_len);
+
+ buf->eth_len = ntohs(ip2->len) + uip_eth_hdrlen(&ip2->eth);
+
+ return 0;
+}
+
+static void *uip_udp_socket_thread(void *p)
+{
+ struct epoll_event events[UIP_UDP_MAX_EVENTS];
+ struct uip_udp_socket *sk;
+ struct uip_info *info;
+ struct uip_buf *buf;
+ int payload_len;
+ u8 *payload;
+ int nfds;
+ int i;
+
+ kvm__set_thread_name("uip-udp");
+
+ info = p;
+ payload = info->udp_buf;
+
+ while (1) {
+ nfds = epoll_wait(info->udp_epollfd, events, UIP_UDP_MAX_EVENTS, -1);
+
+ if (nfds == -1)
+ continue;
+
+ for (i = 0; i < nfds; i++) {
+
+ sk = events[i].data.ptr;
+ payload_len = recvfrom(sk->fd, payload, UIP_MAX_UDP_PAYLOAD, 0, NULL, NULL);
+ if (payload_len < 0)
+ continue;
+
+ /*
+ * Get free buffer to send data to guest
+ */
+ buf = uip_buf_get_free(info);
+
+ uip_udp_make_pkg(info, sk, buf, payload, payload_len);
+
+ /*
+ * Send data received from socket to guest
+ */
+ uip_buf_set_used(info, buf);
+ }
+ }
+
+ mutex_lock(&info->udp_socket_lock);
+ free(info->udp_buf);
+ info->udp_buf = NULL;
+ mutex_unlock(&info->udp_socket_lock);
+
+ pthread_exit(NULL);
+ return NULL;
+}
+
+int uip_tx_do_ipv4_udp(struct uip_tx_arg *arg)
+{
+ struct uip_udp_socket *sk;
+ struct uip_info *info;
+ struct uip_udp *udp;
+ struct uip_ip *ip;
+ int ret;
+
+ udp = (struct uip_udp *)(arg->eth);
+ ip = (struct uip_ip *)(arg->eth);
+ info = arg->info;
+
+ if (uip_udp_is_dhcp(udp)) {
+ uip_tx_do_ipv4_udp_dhcp(arg);
+ return 0;
+ }
+
+ /*
+ * Find socket we have allocated before, otherwise allocate one
+ */
+ sk = uip_udp_socket_find(arg, ip->sip, ip->dip, udp->sport, udp->dport);
+ if (!sk)
+ return -1;
+
+ /*
+ * Send out UDP data to remote host
+ */
+ ret = uip_udp_socket_send(sk, udp);
+ if (ret)
+ return -1;
+
+ if (!info->udp_thread) {
+ info->udp_buf = malloc(UIP_MAX_UDP_PAYLOAD);
+ if (!info->udp_buf)
+ return -1;
+
+ pthread_create(&info->udp_thread, NULL, uip_udp_socket_thread, (void *)info);
+ }
+
+ return 0;
+}
+
+void uip_udp_exit(struct uip_info *info)
+{
+ struct uip_udp_socket *sk, *next;
+
+ mutex_lock(&info->udp_socket_lock);
+ if (info->udp_thread) {
+ pthread_cancel(info->udp_thread);
+ pthread_join(info->udp_thread, NULL);
+ info->udp_thread = 0;
+ free(info->udp_buf);
+ }
+ if (info->udp_epollfd > 0) {
+ close(info->udp_epollfd);
+ info->udp_epollfd = 0;
+ }
+
+ list_for_each_entry_safe(sk, next, &info->udp_socket_head, list) {
+ close(sk->fd);
+ free(sk);
+ }
+ mutex_unlock(&info->udp_socket_lock);
+}
diff --git a/kvmtool/pci.c b/kvmtool/pci.c
new file mode 100644
index 0000000..2e2c027
--- /dev/null
+++ b/kvmtool/pci.c
@@ -0,0 +1,545 @@
+#include "kvm/devices.h"
+#include "kvm/pci.h"
+#include "kvm/ioport.h"
+#include "kvm/irq.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include <linux/err.h>
+#include <assert.h>
+
+static u32 pci_config_address_bits;
+
+/* This is within our PCI gap - in an unused area.
+ * Note this is a PCI *bus address*, is used to assign BARs etc.!
+ * (That's why it can still 32bit even with 64bit guests-- 64bit
+ * PCI isn't currently supported.)
+ */
+static u32 mmio_blocks = KVM_PCI_MMIO_AREA;
+static u16 io_port_blocks = PCI_IOPORT_START;
+
+u16 pci_get_io_port_block(u32 size)
+{
+ u16 port = ALIGN(io_port_blocks, PCI_IO_SIZE);
+
+ io_port_blocks = port + size;
+ return port;
+}
+
+/*
+ * BARs must be naturally aligned, so enforce this in the allocator.
+ */
+u32 pci_get_mmio_block(u32 size)
+{
+ u32 block = ALIGN(mmio_blocks, size);
+ mmio_blocks = block + size;
+ return block;
+}
+
+void *pci_find_cap(struct pci_device_header *hdr, u8 cap_type)
+{
+ u8 pos;
+ struct pci_cap_hdr *cap;
+
+ pci_for_each_cap(pos, cap, hdr) {
+ if (cap->type == cap_type)
+ return cap;
+ }
+
+ return NULL;
+}
+
+int pci__assign_irq(struct pci_device_header *pci_hdr)
+{
+ /*
+ * PCI supports only INTA#,B#,C#,D# per device.
+ *
+ * A#,B#,C#,D# are allowed for multifunctional devices so stick
+ * with A# for our single function devices.
+ */
+ pci_hdr->irq_pin = 1;
+ pci_hdr->irq_line = irq__alloc_line();
+
+ if (!pci_hdr->irq_type)
+ pci_hdr->irq_type = IRQ_TYPE_EDGE_RISING;
+
+ return pci_hdr->irq_line;
+}
+
+static bool pci_bar_is_implemented(struct pci_device_header *pci_hdr, int bar_num)
+{
+ return pci__bar_size(pci_hdr, bar_num);
+}
+
+static bool pci_bar_is_active(struct pci_device_header *pci_hdr, int bar_num)
+{
+ return pci_hdr->bar_active[bar_num];
+}
+
+static void *pci_config_address_ptr(u16 port)
+{
+ unsigned long offset;
+ void *base;
+
+ offset = port - PCI_CONFIG_ADDRESS;
+ base = &pci_config_address_bits;
+
+ return base + offset;
+}
+
+static bool pci_config_address_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ void *p = pci_config_address_ptr(port);
+
+ memcpy(p, data, size);
+
+ return true;
+}
+
+static bool pci_config_address_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ void *p = pci_config_address_ptr(port);
+
+ memcpy(data, p, size);
+
+ return true;
+}
+
+static struct ioport_operations pci_config_address_ops = {
+ .io_in = pci_config_address_in,
+ .io_out = pci_config_address_out,
+};
+
+static bool pci_device_exists(u8 bus_number, u8 device_number, u8 function_number)
+{
+ union pci_config_address pci_config_address;
+
+ pci_config_address.w = ioport__read32(&pci_config_address_bits);
+
+ if (pci_config_address.bus_number != bus_number)
+ return false;
+
+ if (pci_config_address.function_number != function_number)
+ return false;
+
+ return !IS_ERR_OR_NULL(device__find_dev(DEVICE_BUS_PCI, device_number));
+}
+
+static bool pci_config_data_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ union pci_config_address pci_config_address;
+
+ if (size > 4)
+ size = 4;
+
+ pci_config_address.w = ioport__read32(&pci_config_address_bits);
+ /*
+ * If someone accesses PCI configuration space offsets that are not
+ * aligned to 4 bytes, it uses ioports to signify that.
+ */
+ pci_config_address.reg_offset = port - PCI_CONFIG_DATA;
+
+ pci__config_wr(vcpu->kvm, pci_config_address, data, size);
+
+ return true;
+}
+
+static bool pci_config_data_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ union pci_config_address pci_config_address;
+
+ if (size > 4)
+ size = 4;
+
+ pci_config_address.w = ioport__read32(&pci_config_address_bits);
+ /*
+ * If someone accesses PCI configuration space offsets that are not
+ * aligned to 4 bytes, it uses ioports to signify that.
+ */
+ pci_config_address.reg_offset = port - PCI_CONFIG_DATA;
+
+ pci__config_rd(vcpu->kvm, pci_config_address, data, size);
+
+ return true;
+}
+
+static struct ioport_operations pci_config_data_ops = {
+ .io_in = pci_config_data_in,
+ .io_out = pci_config_data_out,
+};
+
+static int pci_activate_bar(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ int bar_num)
+{
+ int r = 0;
+
+ if (pci_bar_is_active(pci_hdr, bar_num))
+ goto out;
+
+ r = pci_hdr->bar_activate_fn(kvm, pci_hdr, bar_num, pci_hdr->data);
+ if (r < 0) {
+ pci_dev_warn(pci_hdr, "Error activating emulation for BAR %d",
+ bar_num);
+ goto out;
+ }
+ pci_hdr->bar_active[bar_num] = true;
+
+out:
+ return r;
+}
+
+static int pci_deactivate_bar(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ int bar_num)
+{
+ int r = 0;
+
+ if (!pci_bar_is_active(pci_hdr, bar_num))
+ goto out;
+
+ r = pci_hdr->bar_deactivate_fn(kvm, pci_hdr, bar_num, pci_hdr->data);
+ if (r < 0) {
+ pci_dev_warn(pci_hdr, "Error deactivating emulation for BAR %d",
+ bar_num);
+ goto out;
+ }
+ pci_hdr->bar_active[bar_num] = false;
+
+out:
+ return r;
+}
+
+static void pci_config_command_wr(struct kvm *kvm,
+ struct pci_device_header *pci_hdr,
+ u16 new_command)
+{
+ int i;
+ bool toggle_io, toggle_mem;
+
+ toggle_io = (pci_hdr->command ^ new_command) & PCI_COMMAND_IO;
+ toggle_mem = (pci_hdr->command ^ new_command) & PCI_COMMAND_MEMORY;
+
+ for (i = 0; i < 6; i++) {
+ if (!pci_bar_is_implemented(pci_hdr, i))
+ continue;
+
+ if (toggle_io && pci__bar_is_io(pci_hdr, i)) {
+ if (__pci__io_space_enabled(new_command))
+ pci_activate_bar(kvm, pci_hdr, i);
+ else
+ pci_deactivate_bar(kvm, pci_hdr, i);
+ }
+
+ if (toggle_mem && pci__bar_is_memory(pci_hdr, i)) {
+ if (__pci__memory_space_enabled(new_command))
+ pci_activate_bar(kvm, pci_hdr, i);
+ else
+ pci_deactivate_bar(kvm, pci_hdr, i);
+ }
+ }
+
+ pci_hdr->command = new_command;
+}
+
+static int pci_toggle_bar_regions(bool activate, struct kvm *kvm, u32 start, u32 size)
+{
+ struct device_header *dev_hdr;
+ struct pci_device_header *tmp_hdr;
+ u32 tmp_start, tmp_size;
+ int i, r;
+
+ dev_hdr = device__first_dev(DEVICE_BUS_PCI);
+ while (dev_hdr) {
+ tmp_hdr = dev_hdr->data;
+ for (i = 0; i < 6; i++) {
+ if (!pci_bar_is_implemented(tmp_hdr, i))
+ continue;
+
+ tmp_start = pci__bar_address(tmp_hdr, i);
+ tmp_size = pci__bar_size(tmp_hdr, i);
+ if (tmp_start + tmp_size <= start ||
+ tmp_start >= start + size)
+ continue;
+
+ if (activate)
+ r = pci_activate_bar(kvm, tmp_hdr, i);
+ else
+ r = pci_deactivate_bar(kvm, tmp_hdr, i);
+ if (r < 0)
+ return r;
+ }
+ dev_hdr = device__next_dev(dev_hdr);
+ }
+
+ return 0;
+}
+
+static inline int pci_activate_bar_regions(struct kvm *kvm, u32 start, u32 size)
+{
+ return pci_toggle_bar_regions(true, kvm, start, size);
+}
+
+static inline int pci_deactivate_bar_regions(struct kvm *kvm, u32 start, u32 size)
+{
+ return pci_toggle_bar_regions(false, kvm, start, size);
+}
+
+static void pci_config_bar_wr(struct kvm *kvm,
+ struct pci_device_header *pci_hdr, int bar_num,
+ u32 value)
+{
+ u32 old_addr, new_addr, bar_size;
+ u32 mask;
+ int r;
+
+ if (pci__bar_is_io(pci_hdr, bar_num))
+ mask = (u32)PCI_BASE_ADDRESS_IO_MASK;
+ else
+ mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
+
+ /*
+ * If the kernel masks the BAR, it will expect to find the size of the
+ * BAR there next time it reads from it. After the kernel reads the
+ * size, it will write the address back.
+ *
+ * According to the PCI local bus specification REV 3.0: The number of
+ * upper bits that a device actually implements depends on how much of
+ * the address space the device will respond to. A device that wants a 1
+ * MB memory address space (using a 32-bit base address register) would
+ * build the top 12 bits of the address register, hardwiring the other
+ * bits to 0.
+ *
+ * Furthermore, software can determine how much address space the device
+ * requires by writing a value of all 1's to the register and then
+ * reading the value back. The device will return 0's in all don't-care
+ * address bits, effectively specifying the address space required.
+ *
+ * Software computes the size of the address space with the formula
+ * S = ~B + 1, where S is the memory size and B is the value read from
+ * the BAR. This means that the BAR value that kvmtool should return is
+ * B = ~(S - 1).
+ */
+ if (value == 0xffffffff) {
+ value = ~(pci__bar_size(pci_hdr, bar_num) - 1);
+ /* Preserve the special bits. */
+ value = (value & mask) | (pci_hdr->bar[bar_num] & ~mask);
+ pci_hdr->bar[bar_num] = value;
+ return;
+ }
+
+ value = (value & mask) | (pci_hdr->bar[bar_num] & ~mask);
+
+ /* Don't toggle emulation when region type access is disbled. */
+ if (pci__bar_is_io(pci_hdr, bar_num) &&
+ !pci__io_space_enabled(pci_hdr)) {
+ pci_hdr->bar[bar_num] = value;
+ return;
+ }
+
+ if (pci__bar_is_memory(pci_hdr, bar_num) &&
+ !pci__memory_space_enabled(pci_hdr)) {
+ pci_hdr->bar[bar_num] = value;
+ return;
+ }
+
+ /*
+ * BAR reassignment can be done while device access is enabled and
+ * memory regions for different devices can overlap as long as no access
+ * is made to the overlapping memory regions. To implement BAR
+ * reasignment, we deactivate emulation for the region described by the
+ * BAR value that the guest is changing, we disable emulation for the
+ * regions that overlap with the new one (by scanning through all PCI
+ * devices), we enable emulation for the new BAR value and finally we
+ * enable emulation for all device regions that were overlapping with
+ * the old value.
+ */
+ old_addr = pci__bar_address(pci_hdr, bar_num);
+ new_addr = __pci__bar_address(value);
+ bar_size = pci__bar_size(pci_hdr, bar_num);
+
+ r = pci_deactivate_bar(kvm, pci_hdr, bar_num);
+ if (r < 0)
+ return;
+
+ r = pci_deactivate_bar_regions(kvm, new_addr, bar_size);
+ if (r < 0) {
+ /*
+ * We cannot update the BAR because of an overlapping region
+ * that failed to deactivate emulation, so keep the old BAR
+ * value and re-activate emulation for it.
+ */
+ pci_activate_bar(kvm, pci_hdr, bar_num);
+ return;
+ }
+
+ pci_hdr->bar[bar_num] = value;
+ r = pci_activate_bar(kvm, pci_hdr, bar_num);
+ if (r < 0) {
+ /*
+ * New region cannot be emulated, re-enable the regions that
+ * were overlapping.
+ */
+ pci_activate_bar_regions(kvm, new_addr, bar_size);
+ return;
+ }
+
+ pci_activate_bar_regions(kvm, old_addr, bar_size);
+}
+
+void pci__config_wr(struct kvm *kvm, union pci_config_address addr, void *data, int size)
+{
+ void *base;
+ u8 bar, offset;
+ struct pci_device_header *pci_hdr;
+ u8 dev_num = addr.device_number;
+ u32 value = 0;
+
+ if (!pci_device_exists(addr.bus_number, dev_num, 0))
+ return;
+
+ offset = addr.w & PCI_DEV_CFG_MASK;
+ base = pci_hdr = device__find_dev(DEVICE_BUS_PCI, dev_num)->data;
+
+ if (pci_hdr->cfg_ops.write)
+ pci_hdr->cfg_ops.write(kvm, pci_hdr, offset, data, size);
+
+ /*
+ * legacy hack: ignore writes to uninitialized regions (e.g. ROM BAR).
+ * Not very nice but has been working so far.
+ */
+ if (*(u32 *)(base + offset) == 0)
+ return;
+
+ if (offset == PCI_COMMAND) {
+ memcpy(&value, data, size);
+ pci_config_command_wr(kvm, pci_hdr, (u16)value);
+ return;
+ }
+
+ bar = (offset - PCI_BAR_OFFSET(0)) / sizeof(u32);
+ if (bar < 6) {
+ memcpy(&value, data, size);
+ pci_config_bar_wr(kvm, pci_hdr, bar, value);
+ return;
+ }
+
+ memcpy(base + offset, data, size);
+}
+
+void pci__config_rd(struct kvm *kvm, union pci_config_address addr, void *data, int size)
+{
+ u8 offset;
+ struct pci_device_header *pci_hdr;
+ u8 dev_num = addr.device_number;
+
+ if (pci_device_exists(addr.bus_number, dev_num, 0)) {
+ pci_hdr = device__find_dev(DEVICE_BUS_PCI, dev_num)->data;
+ offset = addr.w & PCI_DEV_CFG_MASK;
+
+ if (pci_hdr->cfg_ops.read)
+ pci_hdr->cfg_ops.read(kvm, pci_hdr, offset, data, size);
+
+ memcpy(data, (void *)pci_hdr + offset, size);
+ } else {
+ memset(data, 0xff, size);
+ }
+}
+
+static void pci_config_mmio_access(struct kvm_cpu *vcpu, u64 addr, u8 *data,
+ u32 len, u8 is_write, void *kvm)
+{
+ union pci_config_address cfg_addr;
+
+ addr -= KVM_PCI_CFG_AREA;
+ cfg_addr.w = (u32)addr;
+ cfg_addr.enable_bit = 1;
+
+ if (len > 4)
+ len = 4;
+
+ if (is_write)
+ pci__config_wr(kvm, cfg_addr, data, len);
+ else
+ pci__config_rd(kvm, cfg_addr, data, len);
+}
+
+struct pci_device_header *pci__find_dev(u8 dev_num)
+{
+ struct device_header *hdr = device__find_dev(DEVICE_BUS_PCI, dev_num);
+
+ if (IS_ERR_OR_NULL(hdr))
+ return NULL;
+
+ return hdr->data;
+}
+
+int pci__register_bar_regions(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ bar_activate_fn_t bar_activate_fn,
+ bar_deactivate_fn_t bar_deactivate_fn, void *data)
+{
+ int i, r;
+
+ assert(bar_activate_fn && bar_deactivate_fn);
+
+ pci_hdr->bar_activate_fn = bar_activate_fn;
+ pci_hdr->bar_deactivate_fn = bar_deactivate_fn;
+ pci_hdr->data = data;
+
+ for (i = 0; i < 6; i++) {
+ if (!pci_bar_is_implemented(pci_hdr, i))
+ continue;
+
+ assert(!pci_bar_is_active(pci_hdr, i));
+
+ if (pci__bar_is_io(pci_hdr, i) &&
+ pci__io_space_enabled(pci_hdr)) {
+ r = pci_activate_bar(kvm, pci_hdr, i);
+ if (r < 0)
+ return r;
+ }
+
+ if (pci__bar_is_memory(pci_hdr, i) &&
+ pci__memory_space_enabled(pci_hdr)) {
+ r = pci_activate_bar(kvm, pci_hdr, i);
+ if (r < 0)
+ return r;
+ }
+ }
+
+ return 0;
+}
+
+int pci__init(struct kvm *kvm)
+{
+ int r;
+
+ r = ioport__register(kvm, PCI_CONFIG_DATA + 0, &pci_config_data_ops, 4, NULL);
+ if (r < 0)
+ return r;
+
+ r = ioport__register(kvm, PCI_CONFIG_ADDRESS + 0, &pci_config_address_ops, 4, NULL);
+ if (r < 0)
+ goto err_unregister_data;
+
+ r = kvm__register_mmio(kvm, KVM_PCI_CFG_AREA, PCI_CFG_SIZE, false,
+ pci_config_mmio_access, kvm);
+ if (r < 0)
+ goto err_unregister_addr;
+
+ return 0;
+
+err_unregister_addr:
+ ioport__unregister(kvm, PCI_CONFIG_ADDRESS);
+err_unregister_data:
+ ioport__unregister(kvm, PCI_CONFIG_DATA);
+ return r;
+}
+dev_base_init(pci__init);
+
+int pci__exit(struct kvm *kvm)
+{
+ ioport__unregister(kvm, PCI_CONFIG_DATA);
+ ioport__unregister(kvm, PCI_CONFIG_ADDRESS);
+
+ return 0;
+}
+dev_base_exit(pci__exit);
diff --git a/kvmtool/powerpc/boot.c b/kvmtool/powerpc/boot.c
new file mode 100644
index 0000000..2557fc0
--- /dev/null
+++ b/kvmtool/powerpc/boot.c
@@ -0,0 +1,8 @@
+#include "kvm/kvm.h"
+
+#include <stdbool.h>
+
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename)
+{
+ return false;
+}
diff --git a/kvmtool/powerpc/cpu_info.c b/kvmtool/powerpc/cpu_info.c
new file mode 100644
index 0000000..a9dfe39
--- /dev/null
+++ b/kvmtool/powerpc/cpu_info.c
@@ -0,0 +1,210 @@
+/*
+ * PPC CPU identification
+ *
+ * This is a very simple "host CPU info" struct to get us going.
+ * For the little host information we need, I don't want to grub about
+ * parsing stuff in /proc/device-tree so just match host PVR to differentiate
+ * PPC970 and POWER7 (which is all that's currently supported).
+ *
+ * Qemu does something similar but this is MUCH simpler!
+ *
+ * Copyright 2012 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <kvm/kvm.h>
+#include <sys/ioctl.h>
+
+#include "cpu_info.h"
+#include "kvm/util.h"
+
+/* POWER7 */
+
+static struct cpu_info cpu_power7_info = {
+ .name = "POWER7",
+ .tb_freq = 512000000,
+ .d_bsize = 128,
+ .i_bsize = 128,
+ .flags = CPUINFO_FLAG_DFP | CPUINFO_FLAG_VSX | CPUINFO_FLAG_VMX,
+ .mmu_info = {
+ .flags = KVM_PPC_PAGE_SIZES_REAL | KVM_PPC_1T_SEGMENTS,
+ .slb_size = 32,
+ },
+};
+
+/* POWER8 */
+
+static struct cpu_info cpu_power8_info = {
+ .name = "POWER8",
+ .tb_freq = 512000000,
+ .d_bsize = 128,
+ .i_bsize = 128,
+ .flags = CPUINFO_FLAG_DFP | CPUINFO_FLAG_VSX | CPUINFO_FLAG_VMX,
+ .mmu_info = {
+ .flags = KVM_PPC_PAGE_SIZES_REAL | KVM_PPC_1T_SEGMENTS,
+ .slb_size = 32,
+ },
+};
+
+/* PPC970/G5 */
+
+static struct cpu_info cpu_970_info = {
+ .name = "G5",
+ .tb_freq = 33333333,
+ .d_bsize = 128,
+ .i_bsize = 128,
+ .flags = CPUINFO_FLAG_VMX,
+};
+
+/* This is a default catchall for 'no match' on PVR: */
+static struct cpu_info cpu_dummy_info = { .name = "unknown" };
+
+static struct pvr_info host_pvr_info[] = {
+ { 0xffffffff, 0x0f000003, &cpu_power7_info },
+ { 0xffff0000, 0x003f0000, &cpu_power7_info },
+ { 0xffff0000, 0x004a0000, &cpu_power7_info },
+ { 0xffff0000, 0x004b0000, &cpu_power8_info },
+ { 0xffff0000, 0x00390000, &cpu_970_info },
+ { 0xffff0000, 0x003c0000, &cpu_970_info },
+ { 0xffff0000, 0x00440000, &cpu_970_info },
+ { 0xffff0000, 0x00450000, &cpu_970_info },
+};
+
+/* If we can't query the kernel for supported page sizes assume 4K and 16M */
+static struct kvm_ppc_one_seg_page_size fallback_sps[] = {
+ [0] = {
+ .page_shift = 12,
+ .slb_enc = 0,
+ .enc = {
+ [0] = {
+ .page_shift = 12,
+ .pte_enc = 0,
+ },
+ },
+ },
+ [1] = {
+ .page_shift = 24,
+ .slb_enc = 0x100,
+ .enc = {
+ [0] = {
+ .page_shift = 24,
+ .pte_enc = 0,
+ },
+ },
+ },
+};
+
+
+static void setup_mmu_info(struct kvm *kvm, struct cpu_info *cpu_info)
+{
+ static struct kvm_ppc_smmu_info *mmu_info;
+ struct kvm_ppc_one_seg_page_size *sps;
+ int i, j, k, valid;
+
+ if (!kvm__supports_extension(kvm, KVM_CAP_PPC_GET_SMMU_INFO)) {
+ memcpy(&cpu_info->mmu_info.sps, fallback_sps, sizeof(fallback_sps));
+ } else if (ioctl(kvm->vm_fd, KVM_PPC_GET_SMMU_INFO, &cpu_info->mmu_info) < 0) {
+ die_perror("KVM_PPC_GET_SMMU_INFO failed");
+ }
+
+ mmu_info = &cpu_info->mmu_info;
+
+ if (!(mmu_info->flags & KVM_PPC_PAGE_SIZES_REAL))
+ /* Guest pages are not restricted by the backing page size */
+ return;
+
+ /* Filter based on backing page size */
+
+ for (i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ sps = &mmu_info->sps[i];
+
+ if (!sps->page_shift)
+ break;
+
+ if (kvm->ram_pagesize < (1ul << sps->page_shift)) {
+ /* Mark the whole segment size invalid */
+ sps->page_shift = 0;
+ continue;
+ }
+
+ /* Check each page size for the segment */
+ for (j = 0, valid = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (!sps->enc[j].page_shift)
+ break;
+
+ if (kvm->ram_pagesize < (1ul << sps->enc[j].page_shift))
+ sps->enc[j].page_shift = 0;
+ else
+ valid++;
+ }
+
+ if (!valid) {
+ /* Mark the whole segment size invalid */
+ sps->page_shift = 0;
+ continue;
+ }
+
+ /* Mark any trailing entries invalid if we broke out early */
+ for (k = j; k < KVM_PPC_PAGE_SIZES_MAX_SZ; k++)
+ sps->enc[k].page_shift = 0;
+
+ /* Collapse holes */
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (sps->enc[j].page_shift)
+ continue;
+
+ for (k = j + 1; k < KVM_PPC_PAGE_SIZES_MAX_SZ; k++) {
+ if (sps->enc[k].page_shift) {
+ sps->enc[j] = sps->enc[k];
+ sps->enc[k].page_shift = 0;
+ break;
+ }
+ }
+ }
+ }
+
+ /* Mark any trailing entries invalid if we broke out early */
+ for (j = i; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++)
+ mmu_info->sps[j].page_shift = 0;
+
+ /* Collapse holes */
+ for (i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ if (mmu_info->sps[i].page_shift)
+ continue;
+
+ for (j = i + 1; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (mmu_info->sps[j].page_shift) {
+ mmu_info->sps[i] = mmu_info->sps[j];
+ mmu_info->sps[j].page_shift = 0;
+ break;
+ }
+ }
+ }
+}
+
+struct cpu_info *find_cpu_info(struct kvm *kvm)
+{
+ struct cpu_info *info;
+ unsigned int i;
+ u32 pvr = kvm->arch.pvr;
+
+ for (info = NULL, i = 0; i < ARRAY_SIZE(host_pvr_info); i++) {
+ if ((pvr & host_pvr_info[i].pvr_mask) == host_pvr_info[i].pvr) {
+ info = host_pvr_info[i].cpu_info;
+ break;
+ }
+ }
+
+ /* Didn't find anything? Rut-ro. */
+ if (!info) {
+ pr_warning("Host CPU unsupported by kvmtool\n");
+ info = &cpu_dummy_info;
+ }
+
+ setup_mmu_info(kvm, info);
+
+ return info;
+}
diff --git a/kvmtool/powerpc/cpu_info.h b/kvmtool/powerpc/cpu_info.h
new file mode 100644
index 0000000..f61707a
--- /dev/null
+++ b/kvmtool/powerpc/cpu_info.h
@@ -0,0 +1,42 @@
+/*
+ * PPC CPU identification
+ *
+ * Copyright 2012 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef CPU_INFO_H
+#define CPU_INFO_H
+
+#include <kvm/kvm.h>
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+
+struct cpu_info {
+ const char *name;
+ u32 tb_freq; /* timebase frequency */
+ u32 d_bsize; /* d-cache block size */
+ u32 i_bsize; /* i-cache block size */
+ u32 flags;
+ struct kvm_ppc_smmu_info mmu_info;
+};
+
+struct pvr_info {
+ u32 pvr_mask;
+ u32 pvr;
+ struct cpu_info *cpu_info;
+};
+
+/* Misc capabilities/CPU properties */
+#define CPUINFO_FLAG_DFP 0x00000001
+#define CPUINFO_FLAG_VMX 0x00000002
+#define CPUINFO_FLAG_VSX 0x00000004
+
+struct cpu_info *find_cpu_info(struct kvm *kvm);
+
+#endif
diff --git a/kvmtool/powerpc/include/asm/kvm.h b/kvmtool/powerpc/include/asm/kvm.h
new file mode 100644
index 0000000..b0f72de
--- /dev/null
+++ b/kvmtool/powerpc/include/asm/kvm.h
@@ -0,0 +1,726 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __LINUX_KVM_POWERPC_H
+#define __LINUX_KVM_POWERPC_H
+
+#include <linux/types.h>
+
+/* Select powerpc specific features in <linux/kvm.h> */
+#define __KVM_HAVE_SPAPR_TCE
+#define __KVM_HAVE_PPC_SMT
+#define __KVM_HAVE_IRQCHIP
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_GUEST_DEBUG
+
+/* Not always available, but if it is, this is the correct offset. */
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
+struct kvm_regs {
+ __u64 pc;
+ __u64 cr;
+ __u64 ctr;
+ __u64 lr;
+ __u64 xer;
+ __u64 msr;
+ __u64 srr0;
+ __u64 srr1;
+ __u64 pid;
+
+ __u64 sprg0;
+ __u64 sprg1;
+ __u64 sprg2;
+ __u64 sprg3;
+ __u64 sprg4;
+ __u64 sprg5;
+ __u64 sprg6;
+ __u64 sprg7;
+
+ __u64 gpr[32];
+};
+
+#define KVM_SREGS_E_IMPL_NONE 0
+#define KVM_SREGS_E_IMPL_FSL 1
+
+#define KVM_SREGS_E_FSL_PIDn (1 << 0) /* PID1/PID2 */
+
+/* flags for kvm_run.flags */
+#define KVM_RUN_PPC_NMI_DISP_MASK (3 << 0)
+#define KVM_RUN_PPC_NMI_DISP_FULLY_RECOV (1 << 0)
+#define KVM_RUN_PPC_NMI_DISP_LIMITED_RECOV (2 << 0)
+#define KVM_RUN_PPC_NMI_DISP_NOT_RECOV (3 << 0)
+
+/*
+ * Feature bits indicate which sections of the sregs struct are valid,
+ * both in KVM_GET_SREGS and KVM_SET_SREGS. On KVM_SET_SREGS, registers
+ * corresponding to unset feature bits will not be modified. This allows
+ * restoring a checkpoint made without that feature, while keeping the
+ * default values of the new registers.
+ *
+ * KVM_SREGS_E_BASE contains:
+ * CSRR0/1 (refers to SRR2/3 on 40x)
+ * ESR
+ * DEAR
+ * MCSR
+ * TSR
+ * TCR
+ * DEC
+ * TB
+ * VRSAVE (USPRG0)
+ */
+#define KVM_SREGS_E_BASE (1 << 0)
+
+/*
+ * KVM_SREGS_E_ARCH206 contains:
+ *
+ * PIR
+ * MCSRR0/1
+ * DECAR
+ * IVPR
+ */
+#define KVM_SREGS_E_ARCH206 (1 << 1)
+
+/*
+ * Contains EPCR, plus the upper half of 64-bit registers
+ * that are 32-bit on 32-bit implementations.
+ */
+#define KVM_SREGS_E_64 (1 << 2)
+
+#define KVM_SREGS_E_SPRG8 (1 << 3)
+#define KVM_SREGS_E_MCIVPR (1 << 4)
+
+/*
+ * IVORs are used -- contains IVOR0-15, plus additional IVORs
+ * in combination with an appropriate feature bit.
+ */
+#define KVM_SREGS_E_IVOR (1 << 5)
+
+/*
+ * Contains MAS0-4, MAS6-7, TLBnCFG, MMUCFG.
+ * Also TLBnPS if MMUCFG[MAVN] = 1.
+ */
+#define KVM_SREGS_E_ARCH206_MMU (1 << 6)
+
+/* DBSR, DBCR, IAC, DAC, DVC */
+#define KVM_SREGS_E_DEBUG (1 << 7)
+
+/* Enhanced debug -- DSRR0/1, SPRG9 */
+#define KVM_SREGS_E_ED (1 << 8)
+
+/* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_SPE (1 << 9)
+
+/*
+ * DEPRECATED! USE ONE_REG FOR THIS ONE!
+ * External Proxy (EXP) -- EPR
+ */
+#define KVM_SREGS_EXP (1 << 10)
+
+/* External PID (E.PD) -- EPSC/EPLC */
+#define KVM_SREGS_E_PD (1 << 11)
+
+/* Processor Control (E.PC) -- IVOR36-37 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PC (1 << 12)
+
+/* Page table (E.PT) -- EPTCFG */
+#define KVM_SREGS_E_PT (1 << 13)
+
+/* Embedded Performance Monitor (E.PM) -- IVOR35 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PM (1 << 14)
+
+/*
+ * Special updates:
+ *
+ * Some registers may change even while a vcpu is not running.
+ * To avoid losing these changes, by default these registers are
+ * not updated by KVM_SET_SREGS. To force an update, set the bit
+ * in u.e.update_special corresponding to the register to be updated.
+ *
+ * The update_special field is zero on return from KVM_GET_SREGS.
+ *
+ * When restoring a checkpoint, the caller can set update_special
+ * to 0xffffffff to ensure that everything is restored, even new features
+ * that the caller doesn't know about.
+ */
+#define KVM_SREGS_E_UPDATE_MCSR (1 << 0)
+#define KVM_SREGS_E_UPDATE_TSR (1 << 1)
+#define KVM_SREGS_E_UPDATE_DEC (1 << 2)
+#define KVM_SREGS_E_UPDATE_DBSR (1 << 3)
+
+/*
+ * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
+ * previous KVM_GET_REGS.
+ *
+ * Unless otherwise indicated, setting any register with KVM_SET_SREGS
+ * directly sets its value. It does not trigger any special semantics such
+ * as write-one-to-clear. Calling KVM_SET_SREGS on an unmodified struct
+ * just received from KVM_GET_SREGS is always a no-op.
+ */
+struct kvm_sregs {
+ __u32 pvr;
+ union {
+ struct {
+ __u64 sdr1;
+ struct {
+ struct {
+ __u64 slbe;
+ __u64 slbv;
+ } slb[64];
+ } ppc64;
+ struct {
+ __u32 sr[16];
+ __u64 ibat[8];
+ __u64 dbat[8];
+ } ppc32;
+ } s;
+ struct {
+ union {
+ struct { /* KVM_SREGS_E_IMPL_FSL */
+ __u32 features; /* KVM_SREGS_E_FSL_ */
+ __u32 svr;
+ __u64 mcar;
+ __u32 hid0;
+
+ /* KVM_SREGS_E_FSL_PIDn */
+ __u32 pid1, pid2;
+ } fsl;
+ __u8 pad[256];
+ } impl;
+
+ __u32 features; /* KVM_SREGS_E_ */
+ __u32 impl_id; /* KVM_SREGS_E_IMPL_ */
+ __u32 update_special; /* KVM_SREGS_E_UPDATE_ */
+ __u32 pir; /* read-only */
+ __u64 sprg8;
+ __u64 sprg9; /* E.ED */
+ __u64 csrr0;
+ __u64 dsrr0; /* E.ED */
+ __u64 mcsrr0;
+ __u32 csrr1;
+ __u32 dsrr1; /* E.ED */
+ __u32 mcsrr1;
+ __u32 esr;
+ __u64 dear;
+ __u64 ivpr;
+ __u64 mcivpr;
+ __u64 mcsr; /* KVM_SREGS_E_UPDATE_MCSR */
+
+ __u32 tsr; /* KVM_SREGS_E_UPDATE_TSR */
+ __u32 tcr;
+ __u32 decar;
+ __u32 dec; /* KVM_SREGS_E_UPDATE_DEC */
+
+ /*
+ * Userspace can read TB directly, but the
+ * value reported here is consistent with "dec".
+ *
+ * Read-only.
+ */
+ __u64 tb;
+
+ __u32 dbsr; /* KVM_SREGS_E_UPDATE_DBSR */
+ __u32 dbcr[3];
+ /*
+ * iac/dac registers are 64bit wide, while this API
+ * interface provides only lower 32 bits on 64 bit
+ * processors. ONE_REG interface is added for 64bit
+ * iac/dac registers.
+ */
+ __u32 iac[4];
+ __u32 dac[2];
+ __u32 dvc[2];
+ __u8 num_iac; /* read-only */
+ __u8 num_dac; /* read-only */
+ __u8 num_dvc; /* read-only */
+ __u8 pad;
+
+ __u32 epr; /* EXP */
+ __u32 vrsave; /* a.k.a. USPRG0 */
+ __u32 epcr; /* KVM_SREGS_E_64 */
+
+ __u32 mas0;
+ __u32 mas1;
+ __u64 mas2;
+ __u64 mas7_3;
+ __u32 mas4;
+ __u32 mas6;
+
+ __u32 ivor_low[16]; /* IVOR0-15 */
+ __u32 ivor_high[18]; /* IVOR32+, plus room to expand */
+
+ __u32 mmucfg; /* read-only */
+ __u32 eptcfg; /* E.PT, read-only */
+ __u32 tlbcfg[4];/* read-only */
+ __u32 tlbps[4]; /* read-only */
+
+ __u32 eplc, epsc; /* E.PD */
+ } e;
+ __u8 pad[1020];
+ } u;
+};
+
+struct kvm_fpu {
+ __u64 fpr[32];
+};
+
+/*
+ * Defines for h/w breakpoint, watchpoint (read, write or both) and
+ * software breakpoint.
+ * These are used as "type" in KVM_SET_GUEST_DEBUG ioctl and "status"
+ * for KVM_DEBUG_EXIT.
+ */
+#define KVMPPC_DEBUG_NONE 0x0
+#define KVMPPC_DEBUG_BREAKPOINT (1UL << 1)
+#define KVMPPC_DEBUG_WATCH_WRITE (1UL << 2)
+#define KVMPPC_DEBUG_WATCH_READ (1UL << 3)
+struct kvm_debug_exit_arch {
+ __u64 address;
+ /*
+ * exiting to userspace because of h/w breakpoint, watchpoint
+ * (read, write or both) and software breakpoint.
+ */
+ __u32 status;
+ __u32 reserved;
+};
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+ struct {
+ /* H/W breakpoint/watchpoint address */
+ __u64 addr;
+ /*
+ * Type denotes h/w breakpoint, read watchpoint, write
+ * watchpoint or watchpoint (both read and write).
+ */
+ __u32 type;
+ __u32 reserved;
+ } bp[16];
+};
+
+/* Debug related defines */
+/*
+ * kvm_guest_debug->control is a 32 bit field. The lower 16 bits are generic
+ * and upper 16 bits are architecture specific. Architecture specific defines
+ * that ioctl is for setting hardware breakpoint or software breakpoint.
+ */
+#define KVM_GUESTDBG_USE_SW_BP 0x00010000
+#define KVM_GUESTDBG_USE_HW_BP 0x00020000
+
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+#define KVM_INTERRUPT_SET -1U
+#define KVM_INTERRUPT_UNSET -2U
+#define KVM_INTERRUPT_SET_LEVEL -3U
+
+#define KVM_CPU_440 1
+#define KVM_CPU_E500V2 2
+#define KVM_CPU_3S_32 3
+#define KVM_CPU_3S_64 4
+#define KVM_CPU_E500MC 5
+
+/* for KVM_CAP_SPAPR_TCE */
+struct kvm_create_spapr_tce {
+ __u64 liobn;
+ __u32 window_size;
+};
+
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+ __u64 liobn;
+ __u32 page_shift;
+ __u32 flags;
+ __u64 offset; /* in pages */
+ __u64 size; /* in pages */
+};
+
+/* for KVM_ALLOCATE_RMA */
+struct kvm_allocate_rma {
+ __u64 rma_size;
+};
+
+/* for KVM_CAP_PPC_RTAS */
+struct kvm_rtas_token_args {
+ char name[120];
+ __u64 token; /* Use a token of 0 to undefine a mapping */
+};
+
+struct kvm_book3e_206_tlb_entry {
+ __u32 mas8;
+ __u32 mas1;
+ __u64 mas2;
+ __u64 mas7_3;
+};
+
+struct kvm_book3e_206_tlb_params {
+ /*
+ * For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+ *
+ * - The number of ways of TLB0 must be a power of two between 2 and
+ * 16.
+ * - TLB1 must be fully associative.
+ * - The size of TLB0 must be a multiple of the number of ways, and
+ * the number of sets must be a power of two.
+ * - The size of TLB1 may not exceed 64 entries.
+ * - TLB0 supports 4 KiB pages.
+ * - The page sizes supported by TLB1 are as indicated by
+ * TLB1CFG (if MMUCFG[MAVN] = 0) or TLB1PS (if MMUCFG[MAVN] = 1)
+ * as returned by KVM_GET_SREGS.
+ * - TLB2 and TLB3 are reserved, and their entries in tlb_sizes[]
+ * and tlb_ways[] must be zero.
+ *
+ * tlb_ways[n] = tlb_sizes[n] means the array is fully associative.
+ *
+ * KVM will adjust TLBnCFG based on the sizes configured here,
+ * though arrays greater than 2048 entries will have TLBnCFG[NENTRY]
+ * set to zero.
+ */
+ __u32 tlb_sizes[4];
+ __u32 tlb_ways[4];
+ __u32 reserved[8];
+};
+
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+ __u64 flags;
+ __u64 start_index;
+ __u64 reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1)
+#define KVM_GET_HTAB_WRITE ((__u64)0x2)
+
+/*
+ * Data read on the file descriptor is formatted as a series of
+ * records, each consisting of a header followed by a series of
+ * `n_valid' HPTEs (16 bytes each), which are all valid. Following
+ * those valid HPTEs there are `n_invalid' invalid HPTEs, which
+ * are not represented explicitly in the stream. The same format
+ * is used for writing.
+ */
+struct kvm_get_htab_header {
+ __u32 index;
+ __u16 n_valid;
+ __u16 n_invalid;
+};
+
+/* For KVM_PPC_CONFIGURE_V3_MMU */
+struct kvm_ppc_mmuv3_cfg {
+ __u64 flags;
+ __u64 process_table; /* second doubleword of partition table entry */
+};
+
+/* Flag values for KVM_PPC_CONFIGURE_V3_MMU */
+#define KVM_PPC_MMUV3_RADIX 1 /* 1 = radix mode, 0 = HPT */
+#define KVM_PPC_MMUV3_GTSE 2 /* global translation shootdown enb. */
+
+/* For KVM_PPC_GET_RMMU_INFO */
+struct kvm_ppc_rmmu_info {
+ struct kvm_ppc_radix_geom {
+ __u8 page_shift;
+ __u8 level_bits[4];
+ __u8 pad[3];
+ } geometries[8];
+ __u32 ap_encodings[8];
+};
+
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+ __u64 character; /* characteristics of the CPU */
+ __u64 behaviour; /* recommended software behaviour */
+ __u64 character_mask; /* valid bits in character */
+ __u64 behaviour_mask; /* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 (1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED (1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 (1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 (1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV (1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED (1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF (1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS (1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY (1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR (1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58)
+
+/* Per-vcpu XICS interrupt controller state */
+#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
+
+#define KVM_REG_PPC_ICP_CPPR_SHIFT 56 /* current proc priority */
+#define KVM_REG_PPC_ICP_CPPR_MASK 0xff
+#define KVM_REG_PPC_ICP_XISR_SHIFT 32 /* interrupt status field */
+#define KVM_REG_PPC_ICP_XISR_MASK 0xffffff
+#define KVM_REG_PPC_ICP_MFRR_SHIFT 24 /* pending IPI priority */
+#define KVM_REG_PPC_ICP_MFRR_MASK 0xff
+#define KVM_REG_PPC_ICP_PPRI_SHIFT 16 /* pending irq priority */
+#define KVM_REG_PPC_ICP_PPRI_MASK 0xff
+
+#define KVM_REG_PPC_VP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x8d)
+
+/* Device control API: PPC-specific devices */
+#define KVM_DEV_MPIC_GRP_MISC 1
+#define KVM_DEV_MPIC_BASE_ADDR 0 /* 64-bit */
+
+#define KVM_DEV_MPIC_GRP_REGISTER 2 /* 32-bit */
+#define KVM_DEV_MPIC_GRP_IRQ_ACTIVE 3 /* 32-bit */
+
+/* One-Reg API: PPC-specific registers */
+#define KVM_REG_PPC_HIOR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
+#define KVM_REG_PPC_IAC1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x2)
+#define KVM_REG_PPC_IAC2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3)
+#define KVM_REG_PPC_IAC3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_PPC_IAC4 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_PPC_DAC1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_PPC_DAC2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_PPC_DABR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_PPC_DSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9)
+#define KVM_REG_PPC_PURR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa)
+#define KVM_REG_PPC_SPURR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb)
+#define KVM_REG_PPC_DAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc)
+#define KVM_REG_PPC_DSISR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xd)
+#define KVM_REG_PPC_AMR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xe)
+#define KVM_REG_PPC_UAMOR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xf)
+
+#define KVM_REG_PPC_MMCR0 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x10)
+#define KVM_REG_PPC_MMCR1 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x11)
+#define KVM_REG_PPC_MMCRA (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x12)
+#define KVM_REG_PPC_MMCR2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x13)
+#define KVM_REG_PPC_MMCRS (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x14)
+#define KVM_REG_PPC_SIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x15)
+#define KVM_REG_PPC_SDAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x16)
+#define KVM_REG_PPC_SIER (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x17)
+
+#define KVM_REG_PPC_PMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x18)
+#define KVM_REG_PPC_PMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x19)
+#define KVM_REG_PPC_PMC3 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1a)
+#define KVM_REG_PPC_PMC4 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1b)
+#define KVM_REG_PPC_PMC5 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1c)
+#define KVM_REG_PPC_PMC6 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1d)
+#define KVM_REG_PPC_PMC7 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1e)
+#define KVM_REG_PPC_PMC8 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x1f)
+
+/* 32 floating-point registers */
+#define KVM_REG_PPC_FPR0 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x20)
+#define KVM_REG_PPC_FPR(n) (KVM_REG_PPC_FPR0 + (n))
+#define KVM_REG_PPC_FPR31 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x3f)
+
+/* 32 VMX/Altivec vector registers */
+#define KVM_REG_PPC_VR0 (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x40)
+#define KVM_REG_PPC_VR(n) (KVM_REG_PPC_VR0 + (n))
+#define KVM_REG_PPC_VR31 (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x5f)
+
+/* 32 double-width FP registers for VSX */
+/* High-order halves overlap with FP regs */
+#define KVM_REG_PPC_VSR0 (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x60)
+#define KVM_REG_PPC_VSR(n) (KVM_REG_PPC_VSR0 + (n))
+#define KVM_REG_PPC_VSR31 (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x7f)
+
+/* FP and vector status/control registers */
+#define KVM_REG_PPC_FPSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x80)
+/*
+ * VSCR register is documented as a 32-bit register in the ISA, but it can
+ * only be accesses via a vector register. Expose VSCR as a 32-bit register
+ * even though the kernel represents it as a 128-bit vector.
+ */
+#define KVM_REG_PPC_VSCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x81)
+
+/* Virtual processor areas */
+/* For SLB & DTL, address in high (first) half, length in low half */
+#define KVM_REG_PPC_VPA_ADDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x82)
+#define KVM_REG_PPC_VPA_SLB (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x83)
+#define KVM_REG_PPC_VPA_DTL (KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
+
+#define KVM_REG_PPC_EPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
+#define KVM_REG_PPC_EPR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
+
+/* Timer Status Register OR/CLEAR interface */
+#define KVM_REG_PPC_OR_TSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x87)
+#define KVM_REG_PPC_CLEAR_TSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x88)
+#define KVM_REG_PPC_TCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x89)
+#define KVM_REG_PPC_TSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8a)
+
+/* Debugging: Special instruction for software breakpoint */
+#define KVM_REG_PPC_DEBUG_INST (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8b)
+
+/* MMU registers */
+#define KVM_REG_PPC_MAS0 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8c)
+#define KVM_REG_PPC_MAS1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x8d)
+#define KVM_REG_PPC_MAS2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8e)
+#define KVM_REG_PPC_MAS7_3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8f)
+#define KVM_REG_PPC_MAS4 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x90)
+#define KVM_REG_PPC_MAS6 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x91)
+#define KVM_REG_PPC_MMUCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x92)
+/*
+ * TLBnCFG fields TLBnCFG_N_ENTRY and TLBnCFG_ASSOC can be changed only using
+ * KVM_CAP_SW_TLB ioctl
+ */
+#define KVM_REG_PPC_TLB0CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x93)
+#define KVM_REG_PPC_TLB1CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x94)
+#define KVM_REG_PPC_TLB2CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x95)
+#define KVM_REG_PPC_TLB3CFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x96)
+#define KVM_REG_PPC_TLB0PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x97)
+#define KVM_REG_PPC_TLB1PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x98)
+#define KVM_REG_PPC_TLB2PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x99)
+#define KVM_REG_PPC_TLB3PS (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9a)
+#define KVM_REG_PPC_EPTCFG (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9b)
+
+/* Timebase offset */
+#define KVM_REG_PPC_TB_OFFSET (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9c)
+
+/* POWER8 registers */
+#define KVM_REG_PPC_SPMC1 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9d)
+#define KVM_REG_PPC_SPMC2 (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x9e)
+#define KVM_REG_PPC_IAMR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x9f)
+#define KVM_REG_PPC_TFHAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa0)
+#define KVM_REG_PPC_TFIAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa1)
+#define KVM_REG_PPC_TEXASR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa2)
+#define KVM_REG_PPC_FSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa3)
+#define KVM_REG_PPC_PSPB (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xa4)
+#define KVM_REG_PPC_EBBHR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa5)
+#define KVM_REG_PPC_EBBRR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa6)
+#define KVM_REG_PPC_BESCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa7)
+#define KVM_REG_PPC_TAR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa8)
+#define KVM_REG_PPC_DPDES (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xa9)
+#define KVM_REG_PPC_DAWR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaa)
+#define KVM_REG_PPC_DAWRX (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xab)
+#define KVM_REG_PPC_CIABR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xac)
+#define KVM_REG_PPC_IC (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xad)
+#define KVM_REG_PPC_VTB (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xae)
+#define KVM_REG_PPC_CSIGR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xaf)
+#define KVM_REG_PPC_TACR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb0)
+#define KVM_REG_PPC_TCSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb1)
+#define KVM_REG_PPC_PID (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb2)
+#define KVM_REG_PPC_ACOP (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb3)
+
+#define KVM_REG_PPC_VRSAVE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
+#define KVM_REG_PPC_LPCR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
+#define KVM_REG_PPC_LPCR_64 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb5)
+#define KVM_REG_PPC_PPR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
+
+/* Architecture compatibility level */
+#define KVM_REG_PPC_ARCH_COMPAT (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb7)
+
+#define KVM_REG_PPC_DABRX (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb8)
+#define KVM_REG_PPC_WORT (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb9)
+#define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
+#define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
+
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
+#define KVM_REG_PPC_DEC_EXPIRY (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)
+#define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0)
+
+/* Transactional Memory checkpointed state:
+ * This is all GPRs, all VSX regs and a subset of SPRs
+ */
+#define KVM_REG_PPC_TM (KVM_REG_PPC | 0x80000000)
+/* TM GPRs */
+#define KVM_REG_PPC_TM_GPR0 (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0)
+#define KVM_REG_PPC_TM_GPR(n) (KVM_REG_PPC_TM_GPR0 + (n))
+#define KVM_REG_PPC_TM_GPR31 (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x1f)
+/* TM VSX */
+#define KVM_REG_PPC_TM_VSR0 (KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x20)
+#define KVM_REG_PPC_TM_VSR(n) (KVM_REG_PPC_TM_VSR0 + (n))
+#define KVM_REG_PPC_TM_VSR63 (KVM_REG_PPC_TM | KVM_REG_SIZE_U128 | 0x5f)
+/* TM SPRS */
+#define KVM_REG_PPC_TM_CR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x60)
+#define KVM_REG_PPC_TM_LR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x61)
+#define KVM_REG_PPC_TM_CTR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x62)
+#define KVM_REG_PPC_TM_FPSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x63)
+#define KVM_REG_PPC_TM_AMR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x64)
+#define KVM_REG_PPC_TM_PPR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x65)
+#define KVM_REG_PPC_TM_VRSAVE (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x66)
+#define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
+#define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
+#define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
+
+/* PPC64 eXternal Interrupt Controller Specification */
+#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */
+
+/* Layout of 64-bit source attribute values */
+#define KVM_XICS_DESTINATION_SHIFT 0
+#define KVM_XICS_DESTINATION_MASK 0xffffffffULL
+#define KVM_XICS_PRIORITY_SHIFT 32
+#define KVM_XICS_PRIORITY_MASK 0xff
+#define KVM_XICS_LEVEL_SENSITIVE (1ULL << 40)
+#define KVM_XICS_MASKED (1ULL << 41)
+#define KVM_XICS_PENDING (1ULL << 42)
+#define KVM_XICS_PRESENTED (1ULL << 43)
+#define KVM_XICS_QUEUED (1ULL << 44)
+
+/* POWER9 XIVE Native Interrupt Controller */
+#define KVM_DEV_XIVE_GRP_CTRL 1
+#define KVM_DEV_XIVE_RESET 1
+#define KVM_DEV_XIVE_EQ_SYNC 2
+#define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_CONFIG 3 /* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_EQ_CONFIG 4 /* 64-bit EQ identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_SYNC 5 /* 64-bit source identifier */
+
+/* Layout of 64-bit XIVE source attribute values */
+#define KVM_XIVE_LEVEL_SENSITIVE (1ULL << 0)
+#define KVM_XIVE_LEVEL_ASSERTED (1ULL << 1)
+
+/* Layout of 64-bit XIVE source configuration attribute values */
+#define KVM_XIVE_SOURCE_PRIORITY_SHIFT 0
+#define KVM_XIVE_SOURCE_PRIORITY_MASK 0x7
+#define KVM_XIVE_SOURCE_SERVER_SHIFT 3
+#define KVM_XIVE_SOURCE_SERVER_MASK 0xfffffff8ULL
+#define KVM_XIVE_SOURCE_MASKED_SHIFT 32
+#define KVM_XIVE_SOURCE_MASKED_MASK 0x100000000ULL
+#define KVM_XIVE_SOURCE_EISN_SHIFT 33
+#define KVM_XIVE_SOURCE_EISN_MASK 0xfffffffe00000000ULL
+
+/* Layout of 64-bit EQ identifier */
+#define KVM_XIVE_EQ_PRIORITY_SHIFT 0
+#define KVM_XIVE_EQ_PRIORITY_MASK 0x7
+#define KVM_XIVE_EQ_SERVER_SHIFT 3
+#define KVM_XIVE_EQ_SERVER_MASK 0xfffffff8ULL
+
+/* Layout of EQ configuration values (64 bytes) */
+struct kvm_ppc_xive_eq {
+ __u32 flags;
+ __u32 qshift;
+ __u64 qaddr;
+ __u32 qtoggle;
+ __u32 qindex;
+ __u8 pad[40];
+};
+
+#define KVM_XIVE_EQ_ALWAYS_NOTIFY 0x00000001
+
+#define KVM_XIVE_TIMA_PAGE_OFFSET 0
+#define KVM_XIVE_ESB_PAGE_OFFSET 4
+
+#endif /* __LINUX_KVM_POWERPC_H */
diff --git a/kvmtool/powerpc/include/kvm/barrier.h b/kvmtool/powerpc/include/kvm/barrier.h
new file mode 100644
index 0000000..4b708ae
--- /dev/null
+++ b/kvmtool/powerpc/include/kvm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef _KVM_BARRIER_H_
+#define _KVM_BARRIER_H_
+
+#define mb() asm volatile ("sync" : : : "memory")
+#define rmb() asm volatile ("sync" : : : "memory")
+#define wmb() asm volatile ("sync" : : : "memory")
+
+#endif /* _KVM_BARRIER_H_ */
diff --git a/kvmtool/powerpc/include/kvm/fdt-arch.h b/kvmtool/powerpc/include/kvm/fdt-arch.h
new file mode 100644
index 0000000..d48c055
--- /dev/null
+++ b/kvmtool/powerpc/include/kvm/fdt-arch.h
@@ -0,0 +1,6 @@
+#ifndef KVM__KVM_FDT_H
+#define KVM__KVM_FDT_H
+
+enum phandles {PHANDLE_RESERVED = 0, PHANDLE_XICP, PHANDLES_MAX};
+
+#endif /* KVM__KVM_FDT_H */
diff --git a/kvmtool/powerpc/include/kvm/kvm-arch.h b/kvmtool/powerpc/include/kvm/kvm-arch.h
new file mode 100644
index 0000000..26d440b
--- /dev/null
+++ b/kvmtool/powerpc/include/kvm/kvm-arch.h
@@ -0,0 +1,67 @@
+/*
+ * PPC64 architecture-specific definitions
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef KVM__KVM_ARCH_H
+#define KVM__KVM_ARCH_H
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <time.h>
+
+/*
+ * MMIO lives after RAM, but it'd be nice if it didn't constantly move.
+ * Choose a suitably high address, e.g. 63T... This limits RAM size.
+ */
+#define PPC_MMIO_START 0x3F0000000000UL
+#define PPC_MMIO_SIZE 0x010000000000UL
+
+#define KERNEL_LOAD_ADDR 0x0000000000000000
+#define KERNEL_START_ADDR 0x0000000000000000
+#define KERNEL_SECONDARY_START_ADDR 0x0000000000000060
+#define INITRD_LOAD_ADDR 0x0000000002800000
+
+#define RTAS_MAX_SIZE 0x10000
+
+#define TIMEBASE_FREQ 512000000ULL
+
+#define KVM_MMIO_START PPC_MMIO_START
+
+/*
+ * This is the address that pci_get_io_port_block() starts allocating
+ * from. Note that this is a PCI bus address.
+ */
+#define KVM_IOPORT_AREA 0x0
+#define KVM_PCI_CFG_AREA 0x1000000
+#define KVM_PCI_MMIO_AREA 0x2000000
+#define KVM_VIRTIO_MMIO_AREA 0x3000000
+
+#define KVM_IRQ_OFFSET 16
+
+#define KVM_VM_TYPE 0
+
+#define KVM_IOEVENTFD_HAS_PIO 0
+
+#define VIRTIO_DEFAULT_TRANS(kvm) VIRTIO_PCI
+
+struct spapr_phb;
+
+struct kvm_arch {
+ u64 sdr1;
+ u32 pvr;
+ unsigned long rtas_gra;
+ unsigned long rtas_size;
+ unsigned long fdt_gra;
+ unsigned long initrd_gra;
+ unsigned long initrd_size;
+ struct icp_state *icp;
+ struct spapr_phb *phb;
+};
+
+#endif /* KVM__KVM_ARCH_H */
diff --git a/kvmtool/powerpc/include/kvm/kvm-config-arch.h b/kvmtool/powerpc/include/kvm/kvm-config-arch.h
new file mode 100644
index 0000000..60f61de
--- /dev/null
+++ b/kvmtool/powerpc/include/kvm/kvm-config-arch.h
@@ -0,0 +1,7 @@
+#ifndef KVM__KVM_CONFIG_ARCH_H
+#define KVM__KVM_CONFIG_ARCH_H
+
+struct kvm_config_arch {
+};
+
+#endif /* KVM__KVM_CONFIG_ARCH_H */
diff --git a/kvmtool/powerpc/include/kvm/kvm-cpu-arch.h b/kvmtool/powerpc/include/kvm/kvm-cpu-arch.h
new file mode 100644
index 0000000..a69e0cc
--- /dev/null
+++ b/kvmtool/powerpc/include/kvm/kvm-cpu-arch.h
@@ -0,0 +1,79 @@
+/*
+ * PPC64 cpu-specific definitions
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef KVM__KVM_CPU_ARCH_H
+#define KVM__KVM_CPU_ARCH_H
+
+/* Architecture-specific kvm_cpu definitions. */
+
+#include <linux/kvm.h> /* for struct kvm_regs */
+#include <stdbool.h>
+#include <pthread.h>
+
+#define MSR_SF (1ULL<<63)
+#define MSR_HV (1ULL<<60)
+#define MSR_VEC (1ULL<<25)
+#define MSR_VSX (1ULL<<23)
+#define MSR_POW (1ULL<<18)
+#define MSR_EE (1ULL<<15)
+#define MSR_PR (1ULL<<14)
+#define MSR_FP (1ULL<<13)
+#define MSR_ME (1ULL<<12)
+#define MSR_FE0 (1ULL<<11)
+#define MSR_SE (1ULL<<10)
+#define MSR_BE (1ULL<<9)
+#define MSR_FE1 (1ULL<<8)
+#define MSR_IR (1ULL<<5)
+#define MSR_DR (1ULL<<4)
+#define MSR_PMM (1ULL<<2)
+#define MSR_RI (1ULL<<1)
+#define MSR_LE (1ULL<<0)
+
+#define POWER7_EXT_IRQ 0
+
+#define LPCR_ILE (1 << (63-38))
+
+struct kvm;
+
+struct kvm_cpu {
+ pthread_t thread; /* VCPU thread */
+
+ unsigned long cpu_id;
+
+ struct kvm *kvm; /* parent KVM */
+ int vcpu_fd; /* For VCPU ioctls() */
+ struct kvm_run *kvm_run;
+ struct kvm_cpu_task *task;
+
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_fpu fpu;
+
+ u8 is_running;
+ u8 paused;
+ u8 needs_nmi;
+ /*
+ * Although PPC KVM doesn't yet support coalesced MMIO, generic code
+ * needs this in our kvm_cpu:
+ */
+ struct kvm_coalesced_mmio_ring *ring;
+};
+
+void kvm_cpu__irq(struct kvm_cpu *vcpu, int pin, int level);
+
+/* This is never actually called on PPC. */
+static inline bool kvm_cpu__emulate_io(struct kvm_cpu *vcpu, u16 port, void *data, int direction, int size, u32 count)
+{
+ return false;
+}
+
+bool kvm_cpu__emulate_mmio(struct kvm_cpu *vcpu, u64 phys_addr, u8 *data, u32 len, u8 is_write);
+
+#endif /* KVM__KVM_CPU_ARCH_H */
diff --git a/kvmtool/powerpc/ioport.c b/kvmtool/powerpc/ioport.c
new file mode 100644
index 0000000..0c188b6
--- /dev/null
+++ b/kvmtool/powerpc/ioport.c
@@ -0,0 +1,23 @@
+/*
+ * PPC64 ioport platform setup. There isn't any! :-)
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/ioport.h"
+
+#include <stdlib.h>
+
+int ioport__setup_arch(struct kvm *kvm)
+{
+ /* PPC has no legacy ioports to set up */
+ return 0;
+}
+
+void ioport__map_irq(u8 *irq)
+{
+}
diff --git a/kvmtool/powerpc/kvm-cpu.c b/kvmtool/powerpc/kvm-cpu.c
new file mode 100644
index 0000000..461e0a9
--- /dev/null
+++ b/kvmtool/powerpc/kvm-cpu.c
@@ -0,0 +1,290 @@
+/*
+ * PPC64 processor support
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/symbol.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include "spapr.h"
+#include "spapr_pci.h"
+#include "xics.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+#include <assert.h>
+
+static int debug_fd;
+
+void kvm_cpu__set_debug_fd(int fd)
+{
+ debug_fd = fd;
+}
+
+int kvm_cpu__get_debug_fd(void)
+{
+ return debug_fd;
+}
+
+static struct kvm_cpu *kvm_cpu__new(struct kvm *kvm)
+{
+ struct kvm_cpu *vcpu;
+
+ vcpu = calloc(1, sizeof *vcpu);
+ if (!vcpu)
+ return NULL;
+
+ vcpu->kvm = kvm;
+
+ return vcpu;
+}
+
+void kvm_cpu__delete(struct kvm_cpu *vcpu)
+{
+ free(vcpu);
+}
+
+struct kvm_cpu *kvm_cpu__arch_init(struct kvm *kvm, unsigned long cpu_id)
+{
+ struct kvm_cpu *vcpu;
+ int mmap_size;
+ struct kvm_enable_cap papr_cap = { .cap = KVM_CAP_PPC_PAPR };
+
+ vcpu = kvm_cpu__new(kvm);
+ if (!vcpu)
+ return NULL;
+
+ vcpu->cpu_id = cpu_id;
+
+ vcpu->vcpu_fd = ioctl(vcpu->kvm->vm_fd, KVM_CREATE_VCPU, cpu_id);
+ if (vcpu->vcpu_fd < 0)
+ die_perror("KVM_CREATE_VCPU ioctl");
+
+ mmap_size = ioctl(vcpu->kvm->sys_fd, KVM_GET_VCPU_MMAP_SIZE, 0);
+ if (mmap_size < 0)
+ die_perror("KVM_GET_VCPU_MMAP_SIZE ioctl");
+
+ vcpu->kvm_run = mmap(NULL, mmap_size, PROT_RW, MAP_SHARED, vcpu->vcpu_fd, 0);
+ if (vcpu->kvm_run == MAP_FAILED)
+ die("unable to mmap vcpu fd");
+
+ if (ioctl(vcpu->vcpu_fd, KVM_ENABLE_CAP, &papr_cap) < 0)
+ die("unable to enable PAPR capability");
+
+ /*
+ * We start all CPUs, directing non-primary threads into the kernel's
+ * secondary start point. When we come to support SLOF, we will start
+ * only one and SLOF will RTAS call us to ask for others to be
+ * started. (FIXME: make more generic & interface with whichever
+ * firmware a platform may be using.)
+ */
+ vcpu->is_running = true;
+
+ return vcpu;
+}
+
+static void kvm_cpu__setup_fpu(struct kvm_cpu *vcpu)
+{
+ /* Don't have to do anything, there's no expected FPU state. */
+}
+
+static void kvm_cpu__setup_regs(struct kvm_cpu *vcpu)
+{
+ /*
+ * FIXME: This assumes PPC64 and Linux guest. It doesn't use the
+ * OpenFirmware entry method, but instead the "embedded" entry which
+ * passes the FDT address directly.
+ */
+ struct kvm_regs *r = &vcpu->regs;
+
+ if (vcpu->cpu_id == 0) {
+ r->pc = KERNEL_START_ADDR;
+ r->gpr[3] = vcpu->kvm->arch.fdt_gra;
+ r->gpr[5] = 0;
+ } else {
+ r->pc = KERNEL_SECONDARY_START_ADDR;
+ r->gpr[3] = vcpu->cpu_id;
+ }
+ r->msr = 0x8000000000001000UL; /* 64bit, non-HV, ME */
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_REGS, &vcpu->regs) < 0)
+ die_perror("KVM_SET_REGS failed");
+}
+
+static void kvm_cpu__setup_sregs(struct kvm_cpu *vcpu)
+{
+ /*
+ * Some sregs setup to initialise SDR1/PVR/HIOR on PPC64 SPAPR
+ * platforms using PR KVM. (Technically, this is all ignored on
+ * SPAPR HV KVM.) Different setup is required for non-PV non-SPAPR
+ * platforms! (FIXME.)
+ */
+ struct kvm_sregs sregs;
+ struct kvm_one_reg reg = {};
+ u64 value;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ sregs.u.s.sdr1 = vcpu->kvm->arch.sdr1;
+ sregs.pvr = vcpu->kvm->arch.pvr;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_SREGS, &sregs) < 0)
+ die("KVM_SET_SREGS failed");
+
+ reg.id = KVM_REG_PPC_HIOR;
+ value = 0;
+ reg.addr = (u64)(unsigned long)&value;
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die("KVM_SET_ONE_REG failed");
+}
+
+/**
+ * kvm_cpu__reset_vcpu - reset virtual CPU to a known state
+ */
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu)
+{
+ kvm_cpu__setup_regs(vcpu);
+ kvm_cpu__setup_sregs(vcpu);
+ kvm_cpu__setup_fpu(vcpu);
+}
+
+/* kvm_cpu__irq - set KVM's IRQ flag on this vcpu */
+void kvm_cpu__irq(struct kvm_cpu *vcpu, int pin, int level)
+{
+ unsigned int virq = level ? KVM_INTERRUPT_SET_LEVEL : KVM_INTERRUPT_UNSET;
+
+ /* FIXME: POWER-specific */
+ if (pin != POWER7_EXT_IRQ)
+ return;
+ if (ioctl(vcpu->vcpu_fd, KVM_INTERRUPT, &virq) < 0)
+ pr_warning("Could not KVM_INTERRUPT.");
+}
+
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu)
+{
+}
+
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu)
+{
+ bool ret = true;
+ struct kvm_run *run = vcpu->kvm_run;
+ switch(run->exit_reason) {
+ case KVM_EXIT_PAPR_HCALL:
+ run->papr_hcall.ret = spapr_hypercall(vcpu, run->papr_hcall.nr,
+ (target_ulong*)run->papr_hcall.args);
+ break;
+ default:
+ ret = false;
+ }
+ return ret;
+}
+
+bool kvm_cpu__emulate_mmio(struct kvm_cpu *vcpu, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ /*
+ * FIXME: This function will need to be split in order to support
+ * various PowerPC platforms/PHB types, etc. It currently assumes SPAPR
+ * PPC64 guest.
+ */
+ bool ret = false;
+
+ if ((phys_addr >= SPAPR_PCI_WIN_START) &&
+ (phys_addr < SPAPR_PCI_WIN_END)) {
+ ret = spapr_phb_mmio(vcpu, phys_addr, data, len, is_write);
+ } else {
+ pr_warning("MMIO %s unknown address %llx (size %d)!\n",
+ is_write ? "write to" : "read from",
+ phys_addr, len);
+ }
+ return ret;
+}
+
+#define CONDSTR_BIT(m, b) (((m) & MSR_##b) ? #b" " : "")
+
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu)
+{
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ int r;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, ®s) < 0)
+ die("KVM_GET_REGS failed");
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ dprintf(debug_fd, "\n Registers:\n");
+ dprintf(debug_fd, " NIP: %016llx MSR: %016llx "
+ "( %s%s%s%s%s%s%s%s%s%s%s%s)\n",
+ regs.pc, regs.msr,
+ CONDSTR_BIT(regs.msr, SF),
+ CONDSTR_BIT(regs.msr, HV), /* ! */
+ CONDSTR_BIT(regs.msr, VEC),
+ CONDSTR_BIT(regs.msr, VSX),
+ CONDSTR_BIT(regs.msr, EE),
+ CONDSTR_BIT(regs.msr, PR),
+ CONDSTR_BIT(regs.msr, FP),
+ CONDSTR_BIT(regs.msr, ME),
+ CONDSTR_BIT(regs.msr, IR),
+ CONDSTR_BIT(regs.msr, DR),
+ CONDSTR_BIT(regs.msr, RI),
+ CONDSTR_BIT(regs.msr, LE));
+ dprintf(debug_fd, " CTR: %016llx LR: %016llx CR: %08llx\n",
+ regs.ctr, regs.lr, regs.cr);
+ dprintf(debug_fd, " SRR0: %016llx SRR1: %016llx XER: %016llx\n",
+ regs.srr0, regs.srr1, regs.xer);
+ dprintf(debug_fd, " SPRG0: %016llx SPRG1: %016llx\n",
+ regs.sprg0, regs.sprg1);
+ dprintf(debug_fd, " SPRG2: %016llx SPRG3: %016llx\n",
+ regs.sprg2, regs.sprg3);
+ dprintf(debug_fd, " SPRG4: %016llx SPRG5: %016llx\n",
+ regs.sprg4, regs.sprg5);
+ dprintf(debug_fd, " SPRG6: %016llx SPRG7: %016llx\n",
+ regs.sprg6, regs.sprg7);
+ dprintf(debug_fd, " GPRs:\n ");
+ for (r = 0; r < 32; r++) {
+ dprintf(debug_fd, "%016llx ", regs.gpr[r]);
+ if ((r & 3) == 3)
+ dprintf(debug_fd, "\n ");
+ }
+ dprintf(debug_fd, "\n");
+
+ /* FIXME: Assumes SLB-based (book3s) guest */
+ for (r = 0; r < 32; r++) {
+ dprintf(debug_fd, " SLB%02d %016llx %016llx\n", r,
+ sregs.u.s.ppc64.slb[r].slbe,
+ sregs.u.s.ppc64.slb[r].slbv);
+ }
+ dprintf(debug_fd, "----------\n");
+}
+
+void kvm_cpu__show_code(struct kvm_cpu *vcpu)
+{
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, &vcpu->regs) < 0)
+ die("KVM_GET_REGS failed");
+
+ /* FIXME: Dump/disassemble some code...! */
+
+ dprintf(debug_fd, "\n Stack:\n");
+ dprintf(debug_fd, " ------\n");
+ /* Only works in real mode: */
+ kvm__dump_mem(vcpu->kvm, vcpu->regs.gpr[1], 32, debug_fd);
+}
+
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu)
+{
+ /* Does nothing yet */
+}
diff --git a/kvmtool/powerpc/kvm.c b/kvmtool/powerpc/kvm.c
new file mode 100644
index 0000000..702d67d
--- /dev/null
+++ b/kvmtool/powerpc/kvm.c
@@ -0,0 +1,521 @@
+/*
+ * PPC64 (SPAPR) platform support
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * Portions of FDT setup borrowed from QEMU, copyright 2010 David Gibson, IBM
+ * Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/fdt.h"
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+#include "cpu_info.h"
+
+#include "spapr.h"
+#include "spapr_hvcons.h"
+#include "spapr_pci.h"
+
+#include <linux/kvm.h>
+
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <asm/unistd.h>
+#include <errno.h>
+
+#include <linux/byteorder.h>
+
+#define HPT_ORDER 24
+
+#define HUGETLBFS_PATH "/var/lib/hugetlbfs/global/pagesize-16MB/"
+
+static char kern_cmdline[2048];
+
+struct kvm_ext kvm_req_ext[] = {
+ { DEFINE_KVM_EXT(KVM_CAP_PPC_UNSET_IRQ) },
+ { DEFINE_KVM_EXT(KVM_CAP_PPC_IRQ_LEVEL) },
+ { 0, 0 }
+};
+
+static uint32_t mfpvr(void)
+{
+ uint32_t r;
+ asm volatile ("mfpvr %0" : "=r"(r));
+ return r;
+}
+
+bool kvm__arch_cpu_supports_vm(void)
+{
+ return true;
+}
+
+void kvm__init_ram(struct kvm *kvm)
+{
+ u64 phys_start, phys_size;
+ void *host_mem;
+
+ phys_start = 0;
+ phys_size = kvm->ram_size;
+ host_mem = kvm->ram_start;
+
+ /*
+ * We put MMIO at PPC_MMIO_START, high up. Make sure that this doesn't
+ * crash into the end of RAM -- on PPC64 at least, this is so high
+ * (63TB!) that this is unlikely.
+ */
+ if (phys_size >= PPC_MMIO_START)
+ die("Too much memory (%lld, what a nice problem): "
+ "overlaps MMIO!\n",
+ phys_size);
+
+ kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+}
+
+void kvm__arch_set_cmdline(char *cmdline, bool video)
+{
+ /* We don't need anything unusual in here. */
+}
+
+/* Architecture-specific KVM init */
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size)
+{
+ int cap_ppc_rma;
+ unsigned long hpt;
+
+ kvm->ram_size = ram_size;
+
+ /* Map "default" hugetblfs path to the standard 16M mount point */
+ if (hugetlbfs_path && !strcmp(hugetlbfs_path, "default"))
+ hugetlbfs_path = HUGETLBFS_PATH;
+
+ kvm->ram_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path, kvm->ram_size);
+
+ if (kvm->ram_start == MAP_FAILED)
+ die("Couldn't map %lld bytes for RAM (%d)\n",
+ kvm->ram_size, errno);
+
+ /* FDT goes at top of memory, RTAS just below */
+ kvm->arch.fdt_gra = kvm->ram_size - FDT_MAX_SIZE;
+ /* FIXME: Not all PPC systems have RTAS */
+ kvm->arch.rtas_gra = kvm->arch.fdt_gra - RTAS_MAX_SIZE;
+ madvise(kvm->ram_start, kvm->ram_size, MADV_MERGEABLE);
+
+ /* FIXME: SPAPR-PR specific; allocate a guest HPT. */
+ if (posix_memalign((void **)&hpt, (1<<HPT_ORDER), (1<<HPT_ORDER)))
+ die("Can't allocate %d bytes for HPT\n", (1<<HPT_ORDER));
+
+ kvm->arch.sdr1 = ((hpt + 0x3ffffULL) & ~0x3ffffULL) | (HPT_ORDER-18);
+
+ kvm->arch.pvr = mfpvr();
+
+ /* FIXME: This is book3s-specific */
+ cap_ppc_rma = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_PPC_RMA);
+ if (cap_ppc_rma == 2)
+ die("Need contiguous RMA allocation on this hardware, "
+ "which is not yet supported.");
+
+ /* Do these before FDT setup, IRQ setup, etc. */
+ /* FIXME: SPAPR-specific */
+ hypercall_init();
+ register_core_rtas();
+ /* Now that hypercalls are initialised, register a couple for the console: */
+ spapr_hvcons_init();
+ spapr_create_phb(kvm, "pci", SPAPR_PCI_BUID,
+ SPAPR_PCI_MEM_WIN_ADDR,
+ SPAPR_PCI_MEM_WIN_SIZE,
+ SPAPR_PCI_IO_WIN_ADDR,
+ SPAPR_PCI_IO_WIN_SIZE);
+}
+
+void kvm__arch_delete_ram(struct kvm *kvm)
+{
+ munmap(kvm->ram_start, kvm->ram_size);
+}
+
+void kvm__irq_trigger(struct kvm *kvm, int irq)
+{
+ kvm__irq_line(kvm, irq, 1);
+ kvm__irq_line(kvm, irq, 0);
+}
+
+void kvm__arch_read_term(struct kvm *kvm)
+{
+ /* FIXME: Should register callbacks to platform-specific polls */
+ spapr_hvcons_poll(kvm);
+}
+
+bool kvm__arch_load_kernel_image(struct kvm *kvm, int fd_kernel, int fd_initrd,
+ const char *kernel_cmdline)
+{
+ void *p;
+ void *k_start;
+ ssize_t filesize;
+
+ p = k_start = guest_flat_to_host(kvm, KERNEL_LOAD_ADDR);
+
+ filesize = read_file(fd_kernel, p, INITRD_LOAD_ADDR - KERNEL_LOAD_ADDR);
+ if (filesize < 0) {
+ if (errno == ENOMEM)
+ die("Kernel overlaps initrd!");
+
+ die_perror("kernel read");
+ }
+ pr_info("Loaded kernel to 0x%x (%ld bytes)", KERNEL_LOAD_ADDR,
+ filesize);
+ if (fd_initrd != -1) {
+ if (p-k_start > INITRD_LOAD_ADDR)
+ die("Kernel overlaps initrd!");
+
+ /* Round up kernel size to 8byte alignment, and load initrd right after. */
+ p = guest_flat_to_host(kvm, INITRD_LOAD_ADDR);
+
+ filesize = read_file(fd_initrd, p,
+ (kvm->ram_start + kvm->ram_size) - p);
+ if (filesize < 0) {
+ if (errno == ENOMEM)
+ die("initrd too big to contain in guest RAM.\n");
+ die_perror("initrd read");
+ }
+
+ pr_info("Loaded initrd to 0x%x (%ld bytes)",
+ INITRD_LOAD_ADDR, filesize);
+ kvm->arch.initrd_gra = INITRD_LOAD_ADDR;
+ kvm->arch.initrd_size = filesize;
+ } else {
+ kvm->arch.initrd_size = 0;
+ }
+ strncpy(kern_cmdline, kernel_cmdline, 2048);
+ kern_cmdline[2047] = '\0';
+
+ return true;
+}
+
+struct fdt_prop {
+ void *value;
+ int size;
+};
+
+static void generate_segment_page_sizes(struct kvm_ppc_smmu_info *info, struct fdt_prop *prop)
+{
+ struct kvm_ppc_one_seg_page_size *sps;
+ int i, j, size;
+ u32 *p;
+
+ for (size = 0, i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ sps = &info->sps[i];
+
+ if (sps->page_shift == 0)
+ break;
+
+ /* page shift, slb enc & count */
+ size += 3;
+
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (info->sps[i].enc[j].page_shift == 0)
+ break;
+
+ /* page shift & pte enc */
+ size += 2;
+ }
+ }
+
+ if (!size) {
+ prop->value = NULL;
+ prop->size = 0;
+ return;
+ }
+
+ /* Convert size to bytes */
+ prop->size = size * sizeof(u32);
+
+ prop->value = malloc(prop->size);
+ if (!prop->value)
+ die_perror("malloc failed");
+
+ p = (u32 *)prop->value;
+ for (i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ sps = &info->sps[i];
+
+ if (sps->page_shift == 0)
+ break;
+
+ *p++ = cpu_to_be32(sps->page_shift);
+ *p++ = cpu_to_be32(sps->slb_enc);
+
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++)
+ if (!info->sps[i].enc[j].page_shift)
+ break;
+
+ *p++ = cpu_to_be32(j); /* count of enc */
+
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (!info->sps[i].enc[j].page_shift)
+ break;
+
+ *p++ = cpu_to_be32(info->sps[i].enc[j].page_shift);
+ *p++ = cpu_to_be32(info->sps[i].enc[j].pte_enc);
+ }
+ }
+}
+
+#define SMT_THREADS 4
+
+/*
+ * Set up the FDT for the kernel: This function is currently fairly SPAPR-heavy,
+ * and whilst most PPC targets will require CPU/memory nodes, others like RTAS
+ * should eventually be added separately.
+ */
+static int setup_fdt(struct kvm *kvm)
+{
+ uint64_t mem_reg_property[] = { 0, cpu_to_be64(kvm->ram_size) };
+ int smp_cpus = kvm->nrcpus;
+ uint32_t int_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
+ char hypertas_prop_kvm[] = "hcall-pft\0hcall-term\0"
+ "hcall-dabr\0hcall-interrupt\0hcall-tce\0hcall-vio\0"
+ "hcall-splpar\0hcall-bulk\0hcall-set-mode";
+ int i, j;
+ char cpu_name[30];
+ u8 staging_fdt[FDT_MAX_SIZE];
+ struct cpu_info *cpu_info = find_cpu_info(kvm);
+ struct fdt_prop segment_page_sizes;
+ u32 segment_sizes_1T[] = {cpu_to_be32(0x1c), cpu_to_be32(0x28), 0xffffffff, 0xffffffff};
+
+ /* Generate an appropriate DT at kvm->arch.fdt_gra */
+ void *fdt_dest = guest_flat_to_host(kvm, kvm->arch.fdt_gra);
+ void *fdt = staging_fdt;
+
+ _FDT(fdt_create(fdt, FDT_MAX_SIZE));
+ _FDT(fdt_finish_reservemap(fdt));
+
+ _FDT(fdt_begin_node(fdt, ""));
+
+ _FDT(fdt_property_string(fdt, "device_type", "chrp"));
+ _FDT(fdt_property_string(fdt, "model", "IBM pSeries (kvmtool)"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x2));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x2));
+
+ /* RTAS */
+ _FDT(fdt_begin_node(fdt, "rtas"));
+ /* This is what the kernel uses to switch 'We're an LPAR'! */
+ _FDT(fdt_property(fdt, "ibm,hypertas-functions", hypertas_prop_kvm,
+ sizeof(hypertas_prop_kvm)));
+ _FDT(fdt_property_cell(fdt, "linux,rtas-base", kvm->arch.rtas_gra));
+ _FDT(fdt_property_cell(fdt, "linux,rtas-entry", kvm->arch.rtas_gra));
+ _FDT(fdt_property_cell(fdt, "rtas-size", kvm->arch.rtas_size));
+ /* Now add properties for all RTAS tokens: */
+ if (spapr_rtas_fdt_setup(kvm, fdt))
+ die("Couldn't create RTAS FDT properties\n");
+
+ _FDT(fdt_end_node(fdt));
+
+ /* /chosen */
+ _FDT(fdt_begin_node(fdt, "chosen"));
+ /* cmdline */
+ _FDT(fdt_property_string(fdt, "bootargs", kern_cmdline));
+ /* Initrd */
+ if (kvm->arch.initrd_size != 0) {
+ uint32_t ird_st_prop = cpu_to_be32(kvm->arch.initrd_gra);
+ uint32_t ird_end_prop = cpu_to_be32(kvm->arch.initrd_gra +
+ kvm->arch.initrd_size);
+ _FDT(fdt_property(fdt, "linux,initrd-start",
+ &ird_st_prop, sizeof(ird_st_prop)));
+ _FDT(fdt_property(fdt, "linux,initrd-end",
+ &ird_end_prop, sizeof(ird_end_prop)));
+ }
+
+ /*
+ * stdout-path: This is assuming we're using the HV console. Also, the
+ * address is hardwired until we do a VIO bus.
+ */
+ _FDT(fdt_property_string(fdt, "linux,stdout-path",
+ "/vdevice/vty@30000000"));
+ _FDT(fdt_end_node(fdt));
+
+ /*
+ * Memory: We don't alloc. a separate RMA yet. If we ever need to
+ * (CAP_PPC_RMA == 2) then have one memory node for 0->RMAsize, and
+ * another RMAsize->endOfMem.
+ */
+ _FDT(fdt_begin_node(fdt, "memory@0"));
+ _FDT(fdt_property_string(fdt, "device_type", "memory"));
+ _FDT(fdt_property(fdt, "reg", mem_reg_property,
+ sizeof(mem_reg_property)));
+ _FDT(fdt_end_node(fdt));
+
+ generate_segment_page_sizes(&cpu_info->mmu_info, &segment_page_sizes);
+
+ /* CPUs */
+ _FDT(fdt_begin_node(fdt, "cpus"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x1));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x0));
+
+ for (i = 0; i < smp_cpus; i += SMT_THREADS) {
+ int32_t pft_size_prop[] = { 0, cpu_to_be32(HPT_ORDER) };
+ uint32_t servers_prop[SMT_THREADS];
+ uint32_t gservers_prop[SMT_THREADS * 2];
+ int threads = (smp_cpus - i) >= SMT_THREADS ? SMT_THREADS :
+ smp_cpus - i;
+
+ sprintf(cpu_name, "PowerPC,%s@%d", cpu_info->name, i);
+ _FDT(fdt_begin_node(fdt, cpu_name));
+ sprintf(cpu_name, "PowerPC,%s", cpu_info->name);
+ _FDT(fdt_property_string(fdt, "name", cpu_name));
+ _FDT(fdt_property_string(fdt, "device_type", "cpu"));
+
+ _FDT(fdt_property_cell(fdt, "reg", i));
+ _FDT(fdt_property_cell(fdt, "cpu-version", kvm->arch.pvr));
+
+ _FDT(fdt_property_cell(fdt, "dcache-block-size", cpu_info->d_bsize));
+ _FDT(fdt_property_cell(fdt, "icache-block-size", cpu_info->i_bsize));
+
+ if (cpu_info->tb_freq)
+ _FDT(fdt_property_cell(fdt, "timebase-frequency", cpu_info->tb_freq));
+
+ /* Lies, but safeish lies! */
+ _FDT(fdt_property_cell(fdt, "clock-frequency", 0xddbab200));
+
+ if (cpu_info->mmu_info.slb_size)
+ _FDT(fdt_property_cell(fdt, "ibm,slb-size", cpu_info->mmu_info.slb_size));
+
+ /*
+ * HPT size is hardwired; KVM currently fixes it at 16MB but the
+ * moment that changes we'll need to read it out of the kernel.
+ */
+ _FDT(fdt_property(fdt, "ibm,pft-size", pft_size_prop,
+ sizeof(pft_size_prop)));
+
+ _FDT(fdt_property_string(fdt, "status", "okay"));
+ _FDT(fdt_property(fdt, "64-bit", NULL, 0));
+ /* A server for each thread in this core */
+ for (j = 0; j < SMT_THREADS; j++) {
+ servers_prop[j] = cpu_to_be32(i+j);
+ /*
+ * Hack borrowed from QEMU, direct the group queues back
+ * to cpu 0:
+ */
+ gservers_prop[j*2] = cpu_to_be32(i+j);
+ gservers_prop[j*2 + 1] = 0;
+ }
+ _FDT(fdt_property(fdt, "ibm,ppc-interrupt-server#s",
+ servers_prop, threads * sizeof(uint32_t)));
+ _FDT(fdt_property(fdt, "ibm,ppc-interrupt-gserver#s",
+ gservers_prop,
+ threads * 2 * sizeof(uint32_t)));
+
+ if (segment_page_sizes.value)
+ _FDT(fdt_property(fdt, "ibm,segment-page-sizes",
+ segment_page_sizes.value,
+ segment_page_sizes.size));
+
+ if (cpu_info->mmu_info.flags & KVM_PPC_1T_SEGMENTS)
+ _FDT(fdt_property(fdt, "ibm,processor-segment-sizes",
+ segment_sizes_1T, sizeof(segment_sizes_1T)));
+
+ /* VSX / DFP options: */
+ if (cpu_info->flags & CPUINFO_FLAG_VMX)
+ _FDT(fdt_property_cell(fdt, "ibm,vmx",
+ (cpu_info->flags &
+ CPUINFO_FLAG_VSX) ? 2 : 1));
+ if (cpu_info->flags & CPUINFO_FLAG_DFP)
+ _FDT(fdt_property_cell(fdt, "ibm,dfp", 0x1));
+ _FDT(fdt_end_node(fdt));
+ }
+ _FDT(fdt_end_node(fdt));
+
+ /* IRQ controller */
+ _FDT(fdt_begin_node(fdt, "interrupt-controller@0"));
+
+ _FDT(fdt_property_string(fdt, "device_type",
+ "PowerPC-External-Interrupt-Presentation"));
+ _FDT(fdt_property_string(fdt, "compatible", "IBM,ppc-xicp"));
+ _FDT(fdt_property_cell(fdt, "reg", 0));
+ _FDT(fdt_property(fdt, "interrupt-controller", NULL, 0));
+ _FDT(fdt_property(fdt, "ibm,interrupt-server-ranges",
+ int_server_ranges_prop,
+ sizeof(int_server_ranges_prop)));
+ _FDT(fdt_property_cell(fdt, "#interrupt-cells", 2));
+ _FDT(fdt_property_cell(fdt, "linux,phandle", PHANDLE_XICP));
+ _FDT(fdt_property_cell(fdt, "phandle", PHANDLE_XICP));
+ _FDT(fdt_end_node(fdt));
+
+ /*
+ * VIO: See comment in linux,stdout-path; we don't yet represent a VIO
+ * bus/address allocation so addresses are hardwired here.
+ */
+ _FDT(fdt_begin_node(fdt, "vdevice"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x1));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x0));
+ _FDT(fdt_property_string(fdt, "device_type", "vdevice"));
+ _FDT(fdt_property_string(fdt, "compatible", "IBM,vdevice"));
+ _FDT(fdt_begin_node(fdt, "vty@30000000"));
+ _FDT(fdt_property_string(fdt, "name", "vty"));
+ _FDT(fdt_property_string(fdt, "device_type", "serial"));
+ _FDT(fdt_property_string(fdt, "compatible", "hvterm1"));
+ _FDT(fdt_property_cell(fdt, "reg", 0x30000000));
+ _FDT(fdt_end_node(fdt));
+ _FDT(fdt_end_node(fdt));
+
+ /* Finalise: */
+ _FDT(fdt_end_node(fdt)); /* Root node */
+ _FDT(fdt_finish(fdt));
+
+ _FDT(fdt_open_into(fdt, fdt_dest, FDT_MAX_SIZE));
+
+ /* PCI */
+ if (spapr_populate_pci_devices(kvm, PHANDLE_XICP, fdt_dest))
+ die("Fail populating PCI device nodes");
+
+ _FDT(fdt_add_mem_rsv(fdt_dest, kvm->arch.rtas_gra, kvm->arch.rtas_size));
+ _FDT(fdt_pack(fdt_dest));
+
+ free(segment_page_sizes.value);
+
+ return 0;
+}
+firmware_init(setup_fdt);
+
+/**
+ * kvm__arch_setup_firmware
+ */
+int kvm__arch_setup_firmware(struct kvm *kvm)
+{
+ /*
+ * Set up RTAS stub. All it is is a single hypercall:
+ * 0: 7c 64 1b 78 mr r4,r3
+ * 4: 3c 60 00 00 lis r3,0
+ * 8: 60 63 f0 00 ori r3,r3,61440
+ * c: 44 00 00 22 sc 1
+ * 10: 4e 80 00 20 blr
+ */
+ uint32_t *rtas = guest_flat_to_host(kvm, kvm->arch.rtas_gra);
+
+ rtas[0] = cpu_to_be32(0x7c641b78);
+ rtas[1] = cpu_to_be32(0x3c600000);
+ rtas[2] = cpu_to_be32(0x6063f000);
+ rtas[3] = cpu_to_be32(0x44000022);
+ rtas[4] = cpu_to_be32(0x4e800020);
+ kvm->arch.rtas_size = 20;
+
+ pr_info("Set up %ld bytes of RTAS at 0x%lx\n",
+ kvm->arch.rtas_size, kvm->arch.rtas_gra);
+
+ /* Load SLOF */
+
+ return 0;
+}
+
+int kvm__arch_free_firmware(struct kvm *kvm)
+{
+ return 0;
+}
diff --git a/kvmtool/powerpc/spapr.h b/kvmtool/powerpc/spapr.h
new file mode 100644
index 0000000..f851f4a
--- /dev/null
+++ b/kvmtool/powerpc/spapr.h
@@ -0,0 +1,120 @@
+/*
+ * SPAPR definitions and declarations
+ *
+ * Borrowed heavily from QEMU's spapr.h,
+ * Copyright (c) 2010 David Gibson, IBM Corporation.
+ *
+ * Modifications by Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#if !defined(__HW_SPAPR_H__)
+#define __HW_SPAPR_H__
+
+#include <inttypes.h>
+#include <linux/byteorder.h>
+
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+typedef unsigned long target_ulong;
+typedef uintptr_t target_phys_addr_t;
+
+#define H_SUCCESS 0
+#define H_HARDWARE -1 /* Hardware error */
+#define H_FUNCTION -2 /* Function not supported */
+#define H_PARAMETER -4 /* Parameter invalid, out-of-range or conflicting */
+#define H_P2 -55
+#define H_SET_DABR 0x28
+#define H_LOGICAL_CI_LOAD 0x3c
+#define H_LOGICAL_CI_STORE 0x40
+#define H_LOGICAL_CACHE_LOAD 0x44
+#define H_LOGICAL_CACHE_STORE 0x48
+#define H_LOGICAL_ICBI 0x4c
+#define H_LOGICAL_DCBF 0x50
+#define H_GET_TERM_CHAR 0x54
+#define H_PUT_TERM_CHAR 0x58
+#define H_CPPR 0x68
+#define H_EOI 0x64
+#define H_IPI 0x6c
+#define H_XIRR 0x74
+#define H_SET_MODE 0x31C
+#define MAX_HCALL_OPCODE H_SET_MODE
+
+/* Values for 2nd argument to H_SET_MODE */
+#define H_SET_MODE_RESOURCE_SET_CIABR 1
+#define H_SET_MODE_RESOURCE_SET_DAWR 2
+#define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3
+#define H_SET_MODE_RESOURCE_LE 4
+
+/* Flags for H_SET_MODE_RESOURCE_LE */
+#define H_SET_MODE_ENDIAN_BIG 0
+#define H_SET_MODE_ENDIAN_LITTLE 1
+
+/*
+ * The hcalls above are standardized in PAPR and implemented by pHyp
+ * as well.
+ *
+ * We also need some hcalls which are specific to qemu / KVM-on-POWER.
+ * So far we just need one for H_RTAS, but in future we'll need more
+ * for extensions like virtio. We put those into the 0xf000-0xfffc
+ * range which is reserved by PAPR for "platform-specific" hcalls.
+ */
+#define KVMPPC_HCALL_BASE 0xf000
+#define KVMPPC_H_RTAS (KVMPPC_HCALL_BASE + 0x0)
+#define KVMPPC_HCALL_MAX KVMPPC_H_RTAS
+
+#define DEBUG_SPAPR_HCALLS
+
+#ifdef DEBUG_SPAPR_HCALLS
+#define hcall_dprintf(fmt, ...) \
+ do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
+#else
+#define hcall_dprintf(fmt, ...) \
+ do { } while (0)
+#endif
+
+typedef target_ulong (*spapr_hcall_fn)(struct kvm_cpu *vcpu,
+ target_ulong opcode,
+ target_ulong *args);
+
+void hypercall_init(void);
+void register_core_rtas(void);
+
+void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn);
+target_ulong spapr_hypercall(struct kvm_cpu *vcpu, target_ulong opcode,
+ target_ulong *args);
+
+int spapr_rtas_fdt_setup(struct kvm *kvm, void *fdt);
+
+static inline uint32_t rtas_ld(struct kvm *kvm, target_ulong phys, int n)
+{
+ return cpu_to_be32(*((uint32_t *)guest_flat_to_host(kvm, phys + 4*n)));
+}
+
+static inline void rtas_st(struct kvm *kvm, target_ulong phys, int n, uint32_t val)
+{
+ *((uint32_t *)guest_flat_to_host(kvm, phys + 4*n)) = cpu_to_be32(val);
+}
+
+typedef void (*spapr_rtas_fn)(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets);
+void spapr_rtas_register(const char *name, spapr_rtas_fn fn);
+target_ulong spapr_rtas_call(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets);
+
+#define SPAPR_PCI_BUID 0x800000020000001ULL
+#define SPAPR_PCI_MEM_WIN_ADDR (KVM_MMIO_START + 0xA0000000)
+#define SPAPR_PCI_MEM_WIN_SIZE 0x20000000
+#define SPAPR_PCI_IO_WIN_ADDR (SPAPR_PCI_MEM_WIN_ADDR + SPAPR_PCI_MEM_WIN_SIZE)
+#define SPAPR_PCI_IO_WIN_SIZE 0x2000000
+
+#define SPAPR_PCI_WIN_START SPAPR_PCI_MEM_WIN_ADDR
+#define SPAPR_PCI_WIN_END (SPAPR_PCI_IO_WIN_ADDR + SPAPR_PCI_IO_WIN_SIZE)
+
+#endif /* !defined (__HW_SPAPR_H__) */
diff --git a/kvmtool/powerpc/spapr_hcall.c b/kvmtool/powerpc/spapr_hcall.c
new file mode 100644
index 0000000..25bec82
--- /dev/null
+++ b/kvmtool/powerpc/spapr_hcall.c
@@ -0,0 +1,200 @@
+/*
+ * SPAPR hypercalls
+ *
+ * Borrowed heavily from QEMU's spapr_hcall.c,
+ * Copyright (c) 2010 David Gibson, IBM Corporation.
+ *
+ * Copyright (c) 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "spapr.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+#include <stdio.h>
+#include <assert.h>
+#include <sys/eventfd.h>
+
+static spapr_hcall_fn papr_hypercall_table[(MAX_HCALL_OPCODE / 4) + 1];
+static spapr_hcall_fn kvmppc_hypercall_table[KVMPPC_HCALL_MAX -
+ KVMPPC_HCALL_BASE + 1];
+
+static target_ulong h_set_dabr(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* FIXME: Implement this for -PR. (-HV does this in kernel.) */
+ return H_HARDWARE;
+}
+
+static target_ulong h_rtas(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ target_ulong rtas_r3 = args[0];
+ /*
+ * Pointer read from phys mem; these ptrs cannot be MMIO (!) so just
+ * reference guest RAM directly.
+ */
+ uint32_t token, nargs, nret;
+
+ token = rtas_ld(vcpu->kvm, rtas_r3, 0);
+ nargs = rtas_ld(vcpu->kvm, rtas_r3, 1);
+ nret = rtas_ld(vcpu->kvm, rtas_r3, 2);
+
+ return spapr_rtas_call(vcpu, token, nargs, rtas_r3 + 12,
+ nret, rtas_r3 + 12 + 4*nargs);
+}
+
+static target_ulong h_logical_load(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* SLOF will require these, though kernel doesn't. */
+ die(__PRETTY_FUNCTION__);
+ return H_PARAMETER;
+}
+
+static target_ulong h_logical_store(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* SLOF will require these, though kernel doesn't. */
+ die(__PRETTY_FUNCTION__);
+ return H_PARAMETER;
+}
+
+static target_ulong h_logical_icbi(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* KVM will trap this in the kernel. Die if it misses. */
+ die(__PRETTY_FUNCTION__);
+ return H_SUCCESS;
+}
+
+static target_ulong h_logical_dcbf(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* KVM will trap this in the kernel. Die if it misses. */
+ die(__PRETTY_FUNCTION__);
+ return H_SUCCESS;
+}
+
+struct lpcr_data {
+ struct kvm_cpu *cpu;
+ int mode;
+};
+
+static void get_cpu_lpcr(struct kvm_cpu *vcpu, target_ulong *lpcr)
+{
+ struct kvm_one_reg reg = {
+ .id = KVM_REG_PPC_LPCR_64,
+ .addr = (__u64)lpcr
+ };
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_ONE_REG, ®))
+ die("Couldn't read vcpu reg?!");
+}
+
+static void set_cpu_lpcr(struct kvm_cpu *vcpu, target_ulong *lpcr)
+{
+ struct kvm_one_reg reg = {
+ .id = KVM_REG_PPC_LPCR_64,
+ .addr = (__u64)lpcr
+ };
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®))
+ die("Couldn't write vcpu reg?!");
+}
+
+static void set_endian_task(struct kvm_cpu *vcpu, void *data)
+{
+ target_ulong mflags = (target_ulong)data;
+ target_ulong lpcr;
+
+ get_cpu_lpcr(vcpu, &lpcr);
+
+ if (mflags == H_SET_MODE_ENDIAN_BIG)
+ lpcr &= ~LPCR_ILE;
+ else
+ lpcr |= LPCR_ILE;
+
+ set_cpu_lpcr(vcpu, &lpcr);
+}
+
+static target_ulong h_set_mode(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ int ret;
+
+ switch (args[1]) {
+ case H_SET_MODE_RESOURCE_LE: {
+ struct kvm_cpu_task task;
+ task.func = set_endian_task;
+ task.data = (void *)args[0];
+ kvm_cpu__run_on_all_cpus(vcpu->kvm, &task);
+ ret = H_SUCCESS;
+ break;
+ }
+ default:
+ ret = H_FUNCTION;
+ break;
+ }
+
+ return ret;
+}
+
+
+void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn)
+{
+ spapr_hcall_fn *slot;
+
+ if (opcode <= MAX_HCALL_OPCODE) {
+ assert((opcode & 0x3) == 0);
+
+ slot = &papr_hypercall_table[opcode / 4];
+ } else {
+ assert((opcode >= KVMPPC_HCALL_BASE) &&
+ (opcode <= KVMPPC_HCALL_MAX));
+
+ slot = &kvmppc_hypercall_table[opcode - KVMPPC_HCALL_BASE];
+ }
+
+ assert(!(*slot) || (fn == *slot));
+ *slot = fn;
+}
+
+target_ulong spapr_hypercall(struct kvm_cpu *vcpu, target_ulong opcode,
+ target_ulong *args)
+{
+ if ((opcode <= MAX_HCALL_OPCODE)
+ && ((opcode & 0x3) == 0)) {
+ spapr_hcall_fn fn = papr_hypercall_table[opcode / 4];
+
+ if (fn) {
+ return fn(vcpu, opcode, args);
+ }
+ } else if ((opcode >= KVMPPC_HCALL_BASE) &&
+ (opcode <= KVMPPC_HCALL_MAX)) {
+ spapr_hcall_fn fn = kvmppc_hypercall_table[opcode -
+ KVMPPC_HCALL_BASE];
+
+ if (fn) {
+ return fn(vcpu, opcode, args);
+ }
+ }
+
+ hcall_dprintf("Unimplemented hcall 0x%lx\n", opcode);
+ return H_FUNCTION;
+}
+
+void hypercall_init(void)
+{
+ /* hcall-dabr */
+ spapr_register_hypercall(H_SET_DABR, h_set_dabr);
+
+ spapr_register_hypercall(H_LOGICAL_CI_LOAD, h_logical_load);
+ spapr_register_hypercall(H_LOGICAL_CI_STORE, h_logical_store);
+ spapr_register_hypercall(H_LOGICAL_CACHE_LOAD, h_logical_load);
+ spapr_register_hypercall(H_LOGICAL_CACHE_STORE, h_logical_store);
+ spapr_register_hypercall(H_LOGICAL_ICBI, h_logical_icbi);
+ spapr_register_hypercall(H_LOGICAL_DCBF, h_logical_dcbf);
+ spapr_register_hypercall(H_SET_MODE, h_set_mode);
+
+ /* KVM-PPC specific hcalls */
+ spapr_register_hypercall(KVMPPC_H_RTAS, h_rtas);
+}
diff --git a/kvmtool/powerpc/spapr_hvcons.c b/kvmtool/powerpc/spapr_hvcons.c
new file mode 100644
index 0000000..605367b
--- /dev/null
+++ b/kvmtool/powerpc/spapr_hvcons.c
@@ -0,0 +1,105 @@
+/*
+ * SPAPR HV console
+ *
+ * Borrowed lightly from QEMU's spapr_vty.c, Copyright (c) 2010 David Gibson,
+ * IBM Corporation.
+ *
+ * Copyright (c) 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/term.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+#include "spapr.h"
+#include "spapr_hvcons.h"
+
+#include <stdio.h>
+#include <sys/uio.h>
+#include <errno.h>
+
+#include <linux/byteorder.h>
+
+union hv_chario {
+ struct {
+ uint64_t char0_7;
+ uint64_t char8_15;
+ } a;
+ uint8_t buf[16];
+};
+
+static unsigned long h_put_term_char(struct kvm_cpu *vcpu, unsigned long opcode, unsigned long *args)
+{
+ /* To do: Read register from args[0], and check it. */
+ unsigned long len = args[1];
+ union hv_chario data;
+ struct iovec iov;
+
+ if (len > 16) {
+ return H_PARAMETER;
+ }
+ data.a.char0_7 = cpu_to_be64(args[2]);
+ data.a.char8_15 = cpu_to_be64(args[3]);
+
+ iov.iov_base = data.buf;
+ iov.iov_len = len;
+ do {
+ int ret;
+
+ ret = term_putc_iov(&iov, 1, 0);
+ if (ret < 0) {
+ die("term_putc_iov error %d!\n", errno);
+ }
+ iov.iov_base += ret;
+ iov.iov_len -= ret;
+ } while (iov.iov_len > 0);
+
+ return H_SUCCESS;
+}
+
+
+static unsigned long h_get_term_char(struct kvm_cpu *vcpu, unsigned long opcode, unsigned long *args)
+{
+ /* To do: Read register from args[0], and check it. */
+ unsigned long *len = args + 0;
+ unsigned long *char0_7 = args + 1;
+ unsigned long *char8_15 = args + 2;
+ union hv_chario data;
+ struct iovec iov;
+
+ if (vcpu->kvm->cfg.active_console != CONSOLE_HV)
+ return H_SUCCESS;
+
+ if (term_readable(0)) {
+ iov.iov_base = data.buf;
+ iov.iov_len = 16;
+
+ *len = term_getc_iov(vcpu->kvm, &iov, 1, 0);
+ *char0_7 = be64_to_cpu(data.a.char0_7);
+ *char8_15 = be64_to_cpu(data.a.char8_15);
+ } else {
+ *len = 0;
+ }
+
+ return H_SUCCESS;
+}
+
+void spapr_hvcons_poll(struct kvm *kvm)
+{
+ if (term_readable(0)) {
+ /*
+ * We can inject an IRQ to guest here if we want. The guest
+ * will happily poll, though, so not required.
+ */
+ }
+}
+
+void spapr_hvcons_init(void)
+{
+ spapr_register_hypercall(H_PUT_TERM_CHAR, h_put_term_char);
+ spapr_register_hypercall(H_GET_TERM_CHAR, h_get_term_char);
+}
diff --git a/kvmtool/powerpc/spapr_hvcons.h b/kvmtool/powerpc/spapr_hvcons.h
new file mode 100644
index 0000000..d3e4414
--- /dev/null
+++ b/kvmtool/powerpc/spapr_hvcons.h
@@ -0,0 +1,19 @@
+/*
+ * SPAPR HV console
+ *
+ * Copyright (c) 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef spapr_hvcons_H
+#define spapr_hvcons_H
+
+#include "kvm/kvm.h"
+
+void spapr_hvcons_init(void);
+void spapr_hvcons_poll(struct kvm *kvm);
+
+#endif
diff --git a/kvmtool/powerpc/spapr_pci.c b/kvmtool/powerpc/spapr_pci.c
new file mode 100644
index 0000000..7be44d9
--- /dev/null
+++ b/kvmtool/powerpc/spapr_pci.c
@@ -0,0 +1,412 @@
+/*
+ * SPAPR PHB emulation, RTAS interface to PCI config space, device tree nodes
+ * for enumerated devices.
+ *
+ * Borrowed heavily from QEMU's spapr_pci.c,
+ * Copyright (c) 2011 Alexey Kardashevskiy, IBM Corporation.
+ * Copyright (c) 2011 David Gibson, IBM Corporation.
+ *
+ * Modifications copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "spapr.h"
+#include "spapr_pci.h"
+#include "kvm/devices.h"
+#include "kvm/fdt.h"
+#include "kvm/util.h"
+#include "kvm/of_pci.h"
+#include "kvm/pci.h"
+
+#include <linux/pci_regs.h>
+#include <linux/byteorder.h>
+
+
+/* #define DEBUG_PHB yes */
+#ifdef DEBUG_PHB
+#define phb_dprintf(fmt, ...) \
+ do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
+#else
+#define phb_dprintf(fmt, ...) \
+ do { } while (0)
+#endif
+
+static const uint32_t bars[] = {
+ PCI_BASE_ADDRESS_0, PCI_BASE_ADDRESS_1,
+ PCI_BASE_ADDRESS_2, PCI_BASE_ADDRESS_3,
+ PCI_BASE_ADDRESS_4, PCI_BASE_ADDRESS_5
+ /*, PCI_ROM_ADDRESS*/
+};
+
+#define PCI_NUM_REGIONS 7
+
+static struct spapr_phb phb;
+
+static void rtas_ibm_read_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ uint32_t val = 0;
+ uint64_t buid = ((uint64_t)rtas_ld(vcpu->kvm, args, 1) << 32) | rtas_ld(vcpu->kvm, args, 2);
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 3);
+
+ if (buid != phb.buid || !dev || (size > 4)) {
+ phb_dprintf("- cfgRd buid 0x%lx cfg addr 0x%x size %d not found\n",
+ buid, addr.w, size);
+
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+ pci__config_rd(vcpu->kvm, addr, &val, size);
+ /* It appears this wants a byteswapped result... */
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val>>16);
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ phb_dprintf("- cfgRd buid 0x%lx addr 0x%x (/%d): b%d,d%d,f%d,r0x%x, val 0x%x\n",
+ buid, addr.w, size, addr.bus_number, addr.device_number, addr.function_number,
+ addr.register_number, val);
+
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, val);
+}
+
+static void rtas_read_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ uint32_t val;
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 1);
+
+ if (!dev || (size > 4)) {
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+ pci__config_rd(vcpu->kvm, addr, &val, size);
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val>>16); /* We're yuck-endian. */
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ phb_dprintf("- cfgRd addr 0x%x size %d, val 0x%x\n", addr.w, size, val);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, val);
+}
+
+static void rtas_ibm_write_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ uint64_t buid = ((uint64_t)rtas_ld(vcpu->kvm, args, 1) << 32) | rtas_ld(vcpu->kvm, args, 2);
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 3);
+ uint32_t val = rtas_ld(vcpu->kvm, args, 4);
+
+ if (buid != phb.buid || !dev || (size > 4)) {
+ phb_dprintf("- cfgWr buid 0x%lx cfg addr 0x%x/%d error (val 0x%x)\n",
+ buid, addr.w, size, val);
+
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+ phb_dprintf("- cfgWr buid 0x%lx addr 0x%x (/%d): b%d,d%d,f%d,r0x%x, val 0x%x\n",
+ buid, addr.w, size, addr.bus_number, addr.device_number, addr.function_number,
+ addr.register_number, val);
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val) << 16;
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ pci__config_wr(vcpu->kvm, addr, &val, size);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+static void rtas_write_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 1);
+ uint32_t val = rtas_ld(vcpu->kvm, args, 2);
+
+ if (!dev || (size > 4)) {
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+
+ phb_dprintf("- cfgWr addr 0x%x (/%d): b%d,d%d,f%d,r0x%x, val 0x%x\n",
+ addr.w, size, addr.bus_number, addr.device_number, addr.function_number,
+ addr.register_number, val);
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val) << 16;
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ pci__config_wr(vcpu->kvm, addr, &val, size);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+void spapr_create_phb(struct kvm *kvm,
+ const char *busname, uint64_t buid,
+ uint64_t mem_win_addr, uint64_t mem_win_size,
+ uint64_t io_win_addr, uint64_t io_win_size)
+{
+ /*
+ * Since kvmtool doesn't really have any concept of buses etc.,
+ * there's nothing to register here. Just register RTAS.
+ */
+ spapr_rtas_register("read-pci-config", rtas_read_pci_config);
+ spapr_rtas_register("write-pci-config", rtas_write_pci_config);
+ spapr_rtas_register("ibm,read-pci-config", rtas_ibm_read_pci_config);
+ spapr_rtas_register("ibm,write-pci-config", rtas_ibm_write_pci_config);
+
+ phb.buid = buid;
+ phb.mem_addr = mem_win_addr;
+ phb.mem_size = mem_win_size;
+ phb.io_addr = io_win_addr;
+ phb.io_size = io_win_size;
+
+ kvm->arch.phb = &phb;
+}
+
+static uint32_t bar_to_ss(unsigned long bar)
+{
+ if ((bar & PCI_BASE_ADDRESS_SPACE) ==
+ PCI_BASE_ADDRESS_SPACE_IO)
+ return OF_PCI_SS_IO;
+ else if (bar & PCI_BASE_ADDRESS_MEM_TYPE_64)
+ return OF_PCI_SS_M64;
+ else
+ return OF_PCI_SS_M32;
+}
+
+static unsigned long bar_to_addr(unsigned long bar)
+{
+ if ((bar & PCI_BASE_ADDRESS_SPACE) ==
+ PCI_BASE_ADDRESS_SPACE_IO)
+ return bar & PCI_BASE_ADDRESS_IO_MASK;
+ else
+ return bar & PCI_BASE_ADDRESS_MEM_MASK;
+}
+
+int spapr_populate_pci_devices(struct kvm *kvm,
+ uint32_t xics_phandle,
+ void *fdt)
+{
+ int bus_off, node_off = 0, devid, fn, i, n, devices;
+ struct device_header *dev_hdr;
+ char nodename[256];
+ struct of_pci_unit64_address {
+ u32 phys_hi;
+ u64 addr;
+ u64 size;
+ } __attribute((packed)) reg[PCI_NUM_REGIONS + 1], assigned_addresses[PCI_NUM_REGIONS];
+ uint32_t bus_range[] = { cpu_to_be32(0), cpu_to_be32(0xff) };
+ struct of_pci_ranges_entry ranges[] = {
+ {
+ {
+ cpu_to_be32(of_pci_b_ss(1)),
+ cpu_to_be32(0),
+ cpu_to_be32(0),
+ },
+ cpu_to_be64(phb.io_addr),
+ cpu_to_be64(phb.io_size),
+ },
+ {
+ {
+ cpu_to_be32(of_pci_b_ss(2)),
+ cpu_to_be32(0),
+ cpu_to_be32(0),
+ },
+ cpu_to_be64(phb.mem_addr),
+ cpu_to_be64(phb.mem_size),
+ },
+ };
+ uint64_t bus_reg[] = { cpu_to_be64(phb.buid), 0 };
+ uint32_t interrupt_map_mask[] = {
+ cpu_to_be32(of_pci_b_ddddd(-1)|of_pci_b_fff(-1)), 0x0, 0x0, 0x0};
+ uint32_t interrupt_map[SPAPR_PCI_NUM_LSI][7];
+
+ /* Start populating the FDT */
+ sprintf(nodename, "pci@%" PRIx64, phb.buid);
+ bus_off = fdt_add_subnode(fdt, 0, nodename);
+ if (bus_off < 0) {
+ die("error making bus subnode, %s\n", fdt_strerror(bus_off));
+ return bus_off;
+ }
+
+ /* Write PHB properties */
+ _FDT(fdt_setprop_string(fdt, bus_off, "device_type", "pci"));
+ _FDT(fdt_setprop_string(fdt, bus_off, "compatible", "IBM,Logical_PHB"));
+ _FDT(fdt_setprop_cell(fdt, bus_off, "#address-cells", 0x3));
+ _FDT(fdt_setprop_cell(fdt, bus_off, "#size-cells", 0x2));
+ _FDT(fdt_setprop_cell(fdt, bus_off, "#interrupt-cells", 0x1));
+ _FDT(fdt_setprop(fdt, bus_off, "used-by-rtas", NULL, 0));
+ _FDT(fdt_setprop(fdt, bus_off, "bus-range", &bus_range, sizeof(bus_range)));
+ _FDT(fdt_setprop(fdt, bus_off, "ranges", &ranges, sizeof(ranges)));
+ _FDT(fdt_setprop(fdt, bus_off, "reg", &bus_reg, sizeof(bus_reg)));
+ _FDT(fdt_setprop(fdt, bus_off, "interrupt-map-mask",
+ &interrupt_map_mask, sizeof(interrupt_map_mask)));
+
+ /* Populate PCI devices and allocate IRQs */
+ devices = 0;
+ dev_hdr = device__first_dev(DEVICE_BUS_PCI);
+ while (dev_hdr) {
+ uint32_t *irqmap = interrupt_map[devices];
+ struct pci_device_header *hdr = dev_hdr->data;
+
+ if (!hdr)
+ continue;
+
+ devid = dev_hdr->dev_num;
+ fn = 0; /* kvmtool doesn't yet do multifunction devices */
+
+ sprintf(nodename, "pci@%u,%u", devid, fn);
+
+ /* Allocate interrupt from the map */
+ if (devid > SPAPR_PCI_NUM_LSI) {
+ die("Unexpected behaviour in spapr_populate_pci_devices,"
+ "wrong devid %u\n", devid);
+ }
+ irqmap[0] = cpu_to_be32(of_pci_b_ddddd(devid)|of_pci_b_fff(fn));
+ irqmap[1] = 0;
+ irqmap[2] = 0;
+ irqmap[3] = 0;
+ irqmap[4] = cpu_to_be32(xics_phandle);
+ /*
+ * This is nasty; the PCI devs are set up such that their own
+ * header's irq_line indicates the direct XICS IRQ number to
+ * use. There REALLY needs to be a hierarchical system in place
+ * to 'raise' an IRQ on the bridge which indexes/looks up which
+ * XICS IRQ to fire.
+ */
+ irqmap[5] = cpu_to_be32(hdr->irq_line);
+ irqmap[6] = cpu_to_be32(0x8);
+
+ /* Add node to FDT */
+ node_off = fdt_add_subnode(fdt, bus_off, nodename);
+ if (node_off < 0) {
+ die("error making node subnode, %s\n", fdt_strerror(bus_off));
+ return node_off;
+ }
+
+ _FDT(fdt_setprop_cell(fdt, node_off, "vendor-id",
+ le16_to_cpu(hdr->vendor_id)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "device-id",
+ le16_to_cpu(hdr->device_id)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "revision-id",
+ hdr->revision_id));
+ _FDT(fdt_setprop_cell(fdt, node_off, "class-code",
+ hdr->class[0] | (hdr->class[1] << 8) | (hdr->class[2] << 16)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "subsystem-id",
+ le16_to_cpu(hdr->subsys_id)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "subsystem-vendor-id",
+ le16_to_cpu(hdr->subsys_vendor_id)));
+
+ /* Config space region comes first */
+ reg[0].phys_hi = cpu_to_be32(
+ of_pci_b_n(0) |
+ of_pci_b_p(0) |
+ of_pci_b_t(0) |
+ of_pci_b_ss(OF_PCI_SS_CONFIG) |
+ of_pci_b_bbbbbbbb(0) |
+ of_pci_b_ddddd(devid) |
+ of_pci_b_fff(fn));
+ reg[0].addr = 0;
+ reg[0].size = 0;
+
+ n = 0;
+ /* Six BARs, no ROM supported, addresses are 32bit */
+ for (i = 0; i < 6; ++i) {
+ if (0 == hdr->bar[i]) {
+ continue;
+ }
+
+ reg[n+1].phys_hi = cpu_to_be32(
+ of_pci_b_n(0) |
+ of_pci_b_p(0) |
+ of_pci_b_t(0) |
+ of_pci_b_ss(bar_to_ss(le32_to_cpu(hdr->bar[i]))) |
+ of_pci_b_bbbbbbbb(0) |
+ of_pci_b_ddddd(devid) |
+ of_pci_b_fff(fn) |
+ of_pci_b_rrrrrrrr(bars[i]));
+ reg[n+1].size = cpu_to_be64(pci__bar_size(hdr, i));
+ reg[n+1].addr = 0;
+
+ assigned_addresses[n].phys_hi = cpu_to_be32(
+ of_pci_b_n(1) |
+ of_pci_b_p(0) |
+ of_pci_b_t(0) |
+ of_pci_b_ss(bar_to_ss(le32_to_cpu(hdr->bar[i]))) |
+ of_pci_b_bbbbbbbb(0) |
+ of_pci_b_ddddd(devid) |
+ of_pci_b_fff(fn) |
+ of_pci_b_rrrrrrrr(bars[i]));
+
+ /*
+ * Writing zeroes to assigned_addresses causes the guest kernel to
+ * reassign BARs
+ */
+ assigned_addresses[n].addr = cpu_to_be64(bar_to_addr(le32_to_cpu(hdr->bar[i])));
+ assigned_addresses[n].size = reg[n+1].size;
+
+ ++n;
+ }
+ _FDT(fdt_setprop(fdt, node_off, "reg", reg, sizeof(reg[0])*(n+1)));
+ _FDT(fdt_setprop(fdt, node_off, "assigned-addresses",
+ assigned_addresses,
+ sizeof(assigned_addresses[0])*(n)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "interrupts",
+ hdr->irq_pin));
+
+ /* We don't set ibm,dma-window property as we don't have an IOMMU. */
+
+ ++devices;
+ dev_hdr = device__next_dev(dev_hdr);
+ }
+
+ /* Write interrupt map */
+ _FDT(fdt_setprop(fdt, bus_off, "interrupt-map", &interrupt_map,
+ devices * sizeof(interrupt_map[0])));
+
+ return 0;
+}
diff --git a/kvmtool/powerpc/spapr_pci.h b/kvmtool/powerpc/spapr_pci.h
new file mode 100644
index 0000000..f659eda
--- /dev/null
+++ b/kvmtool/powerpc/spapr_pci.h
@@ -0,0 +1,57 @@
+/*
+ * SPAPR PHB definitions
+ *
+ * Modifications by Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef SPAPR_PCI_H
+#define SPAPR_PCI_H
+
+#include "kvm/kvm.h"
+#include "spapr.h"
+#include <inttypes.h>
+
+/* With XICS, we can easily accomodate 1 IRQ per PCI device. */
+
+#define SPAPR_PCI_NUM_LSI 256
+
+struct spapr_phb {
+ uint64_t buid;
+ uint64_t mem_addr;
+ uint64_t mem_size;
+ uint64_t io_addr;
+ uint64_t io_size;
+};
+
+void spapr_create_phb(struct kvm *kvm,
+ const char *busname, uint64_t buid,
+ uint64_t mem_win_addr, uint64_t mem_win_size,
+ uint64_t io_win_addr, uint64_t io_win_size);
+
+int spapr_populate_pci_devices(struct kvm *kvm,
+ uint32_t xics_phandle,
+ void *fdt);
+
+static inline bool spapr_phb_mmio(struct kvm_cpu *vcpu, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ if ((phys_addr >= SPAPR_PCI_IO_WIN_ADDR) &&
+ (phys_addr < SPAPR_PCI_IO_WIN_ADDR +
+ SPAPR_PCI_IO_WIN_SIZE)) {
+ return kvm__emulate_io(vcpu, phys_addr - SPAPR_PCI_IO_WIN_ADDR,
+ data, is_write ? KVM_EXIT_IO_OUT :
+ KVM_EXIT_IO_IN,
+ len, 1);
+ } else if ((phys_addr >= SPAPR_PCI_MEM_WIN_ADDR) &&
+ (phys_addr < SPAPR_PCI_MEM_WIN_ADDR +
+ SPAPR_PCI_MEM_WIN_SIZE)) {
+ return kvm__emulate_mmio(vcpu, phys_addr - SPAPR_PCI_MEM_WIN_ADDR,
+ data, len, is_write);
+ }
+ return false;
+}
+
+#endif
diff --git a/kvmtool/powerpc/spapr_rtas.c b/kvmtool/powerpc/spapr_rtas.c
new file mode 100644
index 0000000..b898ff2
--- /dev/null
+++ b/kvmtool/powerpc/spapr_rtas.c
@@ -0,0 +1,246 @@
+/*
+ * SPAPR base RTAS calls
+ *
+ * Borrowed heavily from QEMU's spapr_rtas.c
+ * Copyright (c) 2010-2011 David Gibson, IBM Corporation.
+ *
+ * Modifications copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+
+#include "spapr.h"
+
+#include <libfdt.h>
+#include <stdio.h>
+#include <assert.h>
+
+#define TOKEN_BASE 0x2000
+#define TOKEN_MAX 0x100
+
+#define RTAS_CONSOLE
+
+static struct rtas_call {
+ const char *name;
+ spapr_rtas_fn fn;
+} rtas_table[TOKEN_MAX];
+
+struct rtas_call *rtas_next = rtas_table;
+
+
+static void rtas_display_character(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ char c = rtas_ld(vcpu->kvm, args, 0);
+ term_putc(&c, 1, 0);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+#ifdef RTAS_CONSOLE
+static void rtas_put_term_char(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ char c = rtas_ld(vcpu->kvm, args, 0);
+
+ term_putc(&c, 1, 0);
+
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+static void rtas_get_term_char(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ int c;
+
+ if (vcpu->kvm->cfg.active_console == CONSOLE_HV && term_readable(0) &&
+ (c = term_getc(vcpu->kvm, 0)) >= 0) {
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, c);
+ } else {
+ rtas_st(vcpu->kvm, rets, 0, -2);
+ }
+}
+#endif
+
+static void rtas_get_time_of_day(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct tm tm;
+ time_t tnow;
+
+ if (nret != 8) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ tnow = time(NULL);
+ /* Guest time is currently not offset in any way. */
+ gmtime_r(&tnow, &tm);
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+ rtas_st(vcpu->kvm, rets, 1, tm.tm_year + 1900);
+ rtas_st(vcpu->kvm, rets, 2, tm.tm_mon + 1);
+ rtas_st(vcpu->kvm, rets, 3, tm.tm_mday);
+ rtas_st(vcpu->kvm, rets, 4, tm.tm_hour);
+ rtas_st(vcpu->kvm, rets, 5, tm.tm_min);
+ rtas_st(vcpu->kvm, rets, 6, tm.tm_sec);
+ rtas_st(vcpu->kvm, rets, 7, 0);
+}
+
+static void rtas_set_time_of_day(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ pr_warning("%s called; TOD set ignored.\n", __FUNCTION__);
+}
+
+static void rtas_power_off(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if (nargs != 2 || nret != 1) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+ kvm__reboot(vcpu->kvm);
+}
+
+static void rtas_system_reboot(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if (nargs != 0 || nret != 1) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ /* NB this actually halts the VM */
+ kvm__reboot(vcpu->kvm);
+}
+
+static void rtas_query_cpu_stopped_state(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if (nargs != 1 || nret != 2) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ /*
+ * Can read id = rtas_ld(vcpu->kvm, args, 0), but
+ * we currently start all CPUs. So just return true.
+ */
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, 2);
+}
+
+static void rtas_start_cpu(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ die(__FUNCTION__);
+}
+
+target_ulong spapr_rtas_call(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if ((token >= TOKEN_BASE)
+ && ((token - TOKEN_BASE) < TOKEN_MAX)) {
+ struct rtas_call *call = rtas_table + (token - TOKEN_BASE);
+
+ if (call->fn) {
+ call->fn(vcpu, token, nargs, args, nret, rets);
+ return H_SUCCESS;
+ }
+ }
+
+ /*
+ * HACK: Some Linux early debug code uses RTAS display-character,
+ * but assumes the token value is 0xa (which it is on some real
+ * machines) without looking it up in the device tree. This
+ * special case makes this work
+ */
+ if (token == 0xa) {
+ rtas_display_character(vcpu, 0xa, nargs, args, nret, rets);
+ return H_SUCCESS;
+ }
+
+ hcall_dprintf("Unknown RTAS token 0x%x\n", token);
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return H_PARAMETER;
+}
+
+void spapr_rtas_register(const char *name, spapr_rtas_fn fn)
+{
+ assert(rtas_next < (rtas_table + TOKEN_MAX));
+
+ rtas_next->name = name;
+ rtas_next->fn = fn;
+
+ rtas_next++;
+}
+
+/*
+ * This is called from the context of an open /rtas node, in order to add
+ * properties for the rtas call tokens.
+ */
+int spapr_rtas_fdt_setup(struct kvm *kvm, void *fdt)
+{
+ int ret;
+ int i;
+
+ for (i = 0; i < TOKEN_MAX; i++) {
+ struct rtas_call *call = &rtas_table[i];
+
+ if (!call->fn) {
+ continue;
+ }
+
+ ret = fdt_property_cell(fdt, call->name, i + TOKEN_BASE);
+
+ if (ret < 0) {
+ pr_warning("Couldn't add rtas token for %s: %s\n",
+ call->name, fdt_strerror(ret));
+ return ret;
+ }
+
+ }
+ return 0;
+}
+
+void register_core_rtas(void)
+{
+ spapr_rtas_register("display-character", rtas_display_character);
+ spapr_rtas_register("get-time-of-day", rtas_get_time_of_day);
+ spapr_rtas_register("set-time-of-day", rtas_set_time_of_day);
+ spapr_rtas_register("power-off", rtas_power_off);
+ spapr_rtas_register("system-reboot", rtas_system_reboot);
+ spapr_rtas_register("query-cpu-stopped-state",
+ rtas_query_cpu_stopped_state);
+ spapr_rtas_register("start-cpu", rtas_start_cpu);
+#ifdef RTAS_CONSOLE
+ /* These are unused: We do console I/O via hcalls, not rtas. */
+ spapr_rtas_register("put-term-char", rtas_put_term_char);
+ spapr_rtas_register("get-term-char", rtas_get_term_char);
+#endif
+}
diff --git a/kvmtool/powerpc/xics.c b/kvmtool/powerpc/xics.c
new file mode 100644
index 0000000..071b928
--- /dev/null
+++ b/kvmtool/powerpc/xics.c
@@ -0,0 +1,495 @@
+/*
+ * PAPR Virtualized Interrupt System, aka ICS/ICP aka xics
+ *
+ * Borrowed heavily from QEMU's xics.c,
+ * Copyright (c) 2010,2011 David Gibson, IBM Corporation.
+ *
+ * Modifications copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "spapr.h"
+#include "xics.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include <stdio.h>
+#include <malloc.h>
+
+#define XICS_NUM_IRQS 1024
+
+
+/* #define DEBUG_XICS yes */
+#ifdef DEBUG_XICS
+#define xics_dprintf(fmt, ...) \
+ do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
+#else
+#define xics_dprintf(fmt, ...) \
+ do { } while (0)
+#endif
+
+/*
+ * ICP: Presentation layer
+ */
+
+struct icp_server_state {
+ uint32_t xirr;
+ uint8_t pending_priority;
+ uint8_t mfrr;
+ struct kvm_cpu *cpu;
+};
+
+#define XICS_IRQ_OFFSET KVM_IRQ_OFFSET
+#define XISR_MASK 0x00ffffff
+#define CPPR_MASK 0xff000000
+
+#define XISR(ss) (((ss)->xirr) & XISR_MASK)
+#define CPPR(ss) (((ss)->xirr) >> 24)
+
+struct ics_state;
+
+struct icp_state {
+ unsigned long nr_servers;
+ struct icp_server_state *ss;
+ struct ics_state *ics;
+};
+
+static void ics_reject(struct ics_state *ics, int nr);
+static void ics_resend(struct ics_state *ics);
+static void ics_eoi(struct ics_state *ics, int nr);
+
+static inline void cpu_irq_raise(struct kvm_cpu *vcpu)
+{
+ xics_dprintf("INT1[%p]\n", vcpu);
+ kvm_cpu__irq(vcpu, POWER7_EXT_IRQ, 1);
+}
+
+static inline void cpu_irq_lower(struct kvm_cpu *vcpu)
+{
+ xics_dprintf("INT0[%p]\n", vcpu);
+ kvm_cpu__irq(vcpu, POWER7_EXT_IRQ, 0);
+}
+
+static void icp_check_ipi(struct icp_state *icp, int server)
+{
+ struct icp_server_state *ss = icp->ss + server;
+
+ if (XISR(ss) && (ss->pending_priority <= ss->mfrr)) {
+ return;
+ }
+
+ if (XISR(ss)) {
+ ics_reject(icp->ics, XISR(ss));
+ }
+
+ ss->xirr = (ss->xirr & ~XISR_MASK) | XICS_IPI;
+ ss->pending_priority = ss->mfrr;
+ cpu_irq_raise(ss->cpu);
+}
+
+static void icp_resend(struct icp_state *icp, int server)
+{
+ struct icp_server_state *ss = icp->ss + server;
+
+ if (ss->mfrr < CPPR(ss)) {
+ icp_check_ipi(icp, server);
+ }
+ ics_resend(icp->ics);
+}
+
+static void icp_set_cppr(struct icp_state *icp, int server, uint8_t cppr)
+{
+ struct icp_server_state *ss = icp->ss + server;
+ uint8_t old_cppr;
+ uint32_t old_xisr;
+
+ old_cppr = CPPR(ss);
+ ss->xirr = (ss->xirr & ~CPPR_MASK) | (cppr << 24);
+
+ if (cppr < old_cppr) {
+ if (XISR(ss) && (cppr <= ss->pending_priority)) {
+ old_xisr = XISR(ss);
+ ss->xirr &= ~XISR_MASK; /* Clear XISR */
+ cpu_irq_lower(ss->cpu);
+ ics_reject(icp->ics, old_xisr);
+ }
+ } else {
+ if (!XISR(ss)) {
+ icp_resend(icp, server);
+ }
+ }
+}
+
+static void icp_set_mfrr(struct icp_state *icp, int nr, uint8_t mfrr)
+{
+ struct icp_server_state *ss = icp->ss + nr;
+
+ ss->mfrr = mfrr;
+ if (mfrr < CPPR(ss)) {
+ icp_check_ipi(icp, nr);
+ }
+}
+
+static uint32_t icp_accept(struct icp_server_state *ss)
+{
+ uint32_t xirr;
+
+ cpu_irq_lower(ss->cpu);
+ xirr = ss->xirr;
+ ss->xirr = ss->pending_priority << 24;
+ return xirr;
+}
+
+static void icp_eoi(struct icp_state *icp, int server, uint32_t xirr)
+{
+ struct icp_server_state *ss = icp->ss + server;
+
+ ics_eoi(icp->ics, xirr & XISR_MASK);
+ /* Send EOI -> ICS */
+ ss->xirr = (ss->xirr & ~CPPR_MASK) | (xirr & CPPR_MASK);
+ if (!XISR(ss)) {
+ icp_resend(icp, server);
+ }
+}
+
+static void icp_irq(struct icp_state *icp, int server, int nr, uint8_t priority)
+{
+ struct icp_server_state *ss = icp->ss + server;
+ xics_dprintf("icp_irq(nr %d, server %d, prio 0x%x)\n", nr, server, priority);
+ if ((priority >= CPPR(ss))
+ || (XISR(ss) && (ss->pending_priority <= priority))) {
+ xics_dprintf("reject %d, CPPR 0x%x, XISR 0x%x, pprio 0x%x, prio 0x%x\n",
+ nr, CPPR(ss), XISR(ss), ss->pending_priority, priority);
+ ics_reject(icp->ics, nr);
+ } else {
+ if (XISR(ss)) {
+ xics_dprintf("reject %d, CPPR 0x%x, XISR 0x%x, pprio 0x%x, prio 0x%x\n",
+ nr, CPPR(ss), XISR(ss), ss->pending_priority, priority);
+ ics_reject(icp->ics, XISR(ss));
+ }
+ ss->xirr = (ss->xirr & ~XISR_MASK) | (nr & XISR_MASK);
+ ss->pending_priority = priority;
+ cpu_irq_raise(ss->cpu);
+ }
+}
+
+/*
+ * ICS: Source layer
+ */
+
+struct ics_irq_state {
+ int server;
+ uint8_t priority;
+ uint8_t saved_priority;
+ int rejected:1;
+ int masked_pending:1;
+};
+
+struct ics_state {
+ unsigned int nr_irqs;
+ unsigned int offset;
+ struct ics_irq_state *irqs;
+ struct icp_state *icp;
+};
+
+static int ics_valid_irq(struct ics_state *ics, uint32_t nr)
+{
+ return (nr >= ics->offset)
+ && (nr < (ics->offset + ics->nr_irqs));
+}
+
+static void ics_set_irq_msi(struct ics_state *ics, int srcno, int val)
+{
+ struct ics_irq_state *irq = ics->irqs + srcno;
+
+ if (val) {
+ if (irq->priority == 0xff) {
+ xics_dprintf(" irq pri ff, masked pending\n");
+ irq->masked_pending = 1;
+ } else {
+ icp_irq(ics->icp, irq->server, srcno + ics->offset, irq->priority);
+ }
+ }
+}
+
+static void ics_reject_msi(struct ics_state *ics, int nr)
+{
+ struct ics_irq_state *irq = ics->irqs + nr - ics->offset;
+
+ irq->rejected = 1;
+}
+
+static void ics_resend_msi(struct ics_state *ics)
+{
+ unsigned int i;
+
+ for (i = 0; i < ics->nr_irqs; i++) {
+ struct ics_irq_state *irq = ics->irqs + i;
+
+ /* FIXME: filter by server#? */
+ if (irq->rejected) {
+ irq->rejected = 0;
+ if (irq->priority != 0xff) {
+ icp_irq(ics->icp, irq->server, i + ics->offset, irq->priority);
+ }
+ }
+ }
+}
+
+static void ics_write_xive_msi(struct ics_state *ics, int nr, int server,
+ uint8_t priority)
+{
+ struct ics_irq_state *irq = ics->irqs + nr - ics->offset;
+
+ irq->server = server;
+ irq->priority = priority;
+ xics_dprintf("ics_write_xive_msi(nr %d, server %d, pri 0x%x)\n", nr, server, priority);
+
+ if (!irq->masked_pending || (priority == 0xff)) {
+ return;
+ }
+
+ irq->masked_pending = 0;
+ icp_irq(ics->icp, server, nr, priority);
+}
+
+static void ics_reject(struct ics_state *ics, int nr)
+{
+ ics_reject_msi(ics, nr);
+}
+
+static void ics_resend(struct ics_state *ics)
+{
+ ics_resend_msi(ics);
+}
+
+static void ics_eoi(struct ics_state *ics, int nr)
+{
+}
+
+/*
+ * Exported functions
+ */
+
+static target_ulong h_cppr(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ target_ulong cppr = args[0];
+
+ xics_dprintf("h_cppr(%lx)\n", cppr);
+ icp_set_cppr(vcpu->kvm->arch.icp, vcpu->cpu_id, cppr);
+ return H_SUCCESS;
+}
+
+static target_ulong h_ipi(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ target_ulong server = args[0];
+ target_ulong mfrr = args[1];
+
+ xics_dprintf("h_ipi(%lx, %lx)\n", server, mfrr);
+ if (server >= vcpu->kvm->arch.icp->nr_servers) {
+ return H_PARAMETER;
+ }
+
+ icp_set_mfrr(vcpu->kvm->arch.icp, server, mfrr);
+ return H_SUCCESS;
+}
+
+static target_ulong h_xirr(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ uint32_t xirr = icp_accept(vcpu->kvm->arch.icp->ss + vcpu->cpu_id);
+
+ xics_dprintf("h_xirr() = %x\n", xirr);
+ args[0] = xirr;
+ return H_SUCCESS;
+}
+
+static target_ulong h_eoi(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ target_ulong xirr = args[0];
+
+ xics_dprintf("h_eoi(%lx)\n", xirr);
+ icp_eoi(vcpu->kvm->arch.icp, vcpu->cpu_id, xirr);
+ return H_SUCCESS;
+}
+
+static void rtas_set_xive(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->arch.icp->ics;
+ uint32_t nr, server, priority;
+
+ if ((nargs != 3) || (nret != 1)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+ server = rtas_ld(vcpu->kvm, args, 1);
+ priority = rtas_ld(vcpu->kvm, args, 2);
+
+ xics_dprintf("rtas_set_xive(%x,%x,%x)\n", nr, server, priority);
+ if (!ics_valid_irq(ics, nr) || (server >= ics->icp->nr_servers)
+ || (priority > 0xff)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ ics_write_xive_msi(ics, nr, server, priority);
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+}
+
+static void rtas_get_xive(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->arch.icp->ics;
+ uint32_t nr;
+
+ if ((nargs != 1) || (nret != 3)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+
+ if (!ics_valid_irq(ics, nr)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+ rtas_st(vcpu->kvm, rets, 1, ics->irqs[nr - ics->offset].server);
+ rtas_st(vcpu->kvm, rets, 2, ics->irqs[nr - ics->offset].priority);
+}
+
+static void rtas_int_off(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->arch.icp->ics;
+ uint32_t nr;
+
+ if ((nargs != 1) || (nret != 1)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+
+ if (!ics_valid_irq(ics, nr)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ /* ME: QEMU wrote xive_msi here, in #if 0. Deleted. */
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+}
+
+static void rtas_int_on(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->arch.icp->ics;
+ uint32_t nr;
+
+ if ((nargs != 1) || (nret != 1)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+
+ if (!ics_valid_irq(ics, nr)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ /* ME: QEMU wrote xive_msi here, in #if 0. Deleted. */
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+}
+
+static int xics_init(struct kvm *kvm)
+{
+ unsigned int i;
+ struct icp_state *icp;
+ struct ics_state *ics;
+ int j;
+
+ icp = malloc(sizeof(*icp));
+ icp->nr_servers = kvm->nrcpus;
+ icp->ss = malloc(icp->nr_servers * sizeof(struct icp_server_state));
+
+ for (i = 0; i < icp->nr_servers; i++) {
+ icp->ss[i].xirr = 0;
+ icp->ss[i].pending_priority = 0;
+ icp->ss[i].cpu = 0;
+ icp->ss[i].mfrr = 0xff;
+ }
+
+ /*
+ * icp->ss[env->cpu_index].cpu is set by CPUs calling in to
+ * xics_cpu_register().
+ */
+
+ ics = malloc(sizeof(*ics));
+ ics->nr_irqs = XICS_NUM_IRQS;
+ ics->offset = XICS_IRQ_OFFSET;
+ ics->irqs = malloc(ics->nr_irqs * sizeof(struct ics_irq_state));
+
+ icp->ics = ics;
+ ics->icp = icp;
+
+ for (i = 0; i < ics->nr_irqs; i++) {
+ ics->irqs[i].server = 0;
+ ics->irqs[i].priority = 0xff;
+ ics->irqs[i].saved_priority = 0xff;
+ ics->irqs[i].rejected = 0;
+ ics->irqs[i].masked_pending = 0;
+ }
+
+ spapr_register_hypercall(H_CPPR, h_cppr);
+ spapr_register_hypercall(H_IPI, h_ipi);
+ spapr_register_hypercall(H_XIRR, h_xirr);
+ spapr_register_hypercall(H_EOI, h_eoi);
+
+ spapr_rtas_register("ibm,set-xive", rtas_set_xive);
+ spapr_rtas_register("ibm,get-xive", rtas_get_xive);
+ spapr_rtas_register("ibm,int-off", rtas_int_off);
+ spapr_rtas_register("ibm,int-on", rtas_int_on);
+
+ for (j = 0; j < kvm->nrcpus; j++) {
+ struct kvm_cpu *vcpu = kvm->cpus[j];
+
+ if (vcpu->cpu_id >= icp->nr_servers)
+ die("Invalid server number for cpuid %ld\n", vcpu->cpu_id);
+
+ icp->ss[vcpu->cpu_id].cpu = vcpu;
+ }
+
+ kvm->arch.icp = icp;
+
+ return 0;
+}
+dev_base_init(xics_init);
+
+
+void kvm__irq_line(struct kvm *kvm, int irq, int level)
+{
+ /*
+ * Route event to ICS, which routes to ICP, which eventually does a
+ * kvm_cpu__irq(vcpu, POWER7_EXT_IRQ, 1)
+ */
+ xics_dprintf("Raising IRQ %d -> %d\n", irq, level);
+ ics_set_irq_msi(kvm->arch.icp->ics, irq - kvm->arch.icp->ics->offset, level);
+}
diff --git a/kvmtool/powerpc/xics.h b/kvmtool/powerpc/xics.h
new file mode 100644
index 0000000..d5bc6f9
--- /dev/null
+++ b/kvmtool/powerpc/xics.h
@@ -0,0 +1,18 @@
+/*
+ * PAPR Virtualized Interrupt System, aka ICS/ICP aka xics
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef XICS_H
+#define XICS_H
+
+#define XICS_IPI 0x2
+
+int xics_alloc_irqnum(void);
+
+#endif
diff --git a/kvmtool/symbol.c b/kvmtool/symbol.c
new file mode 100644
index 0000000..07dd9d5
--- /dev/null
+++ b/kvmtool/symbol.c
@@ -0,0 +1,133 @@
+#include "kvm/symbol.h"
+
+#include "kvm/kvm.h"
+
+#include <linux/err.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <bfd.h>
+
+static bfd *abfd;
+
+int symbol_init(struct kvm *kvm)
+{
+ int ret = 0;
+
+ if (!kvm->vmlinux)
+ return 0;
+
+ bfd_init();
+
+ abfd = bfd_openr(kvm->vmlinux, NULL);
+ if (abfd == NULL) {
+ bfd_error_type err = bfd_get_error();
+
+ switch (err) {
+ case bfd_error_no_memory:
+ ret = -ENOMEM;
+ break;
+ case bfd_error_invalid_target:
+ ret = -EINVAL;
+ break;
+ default:
+ ret = -EFAULT;
+ break;
+ }
+ }
+
+ return ret;
+}
+late_init(symbol_init);
+
+static asymbol *lookup(asymbol **symbols, int nr_symbols, const char *symbol_name)
+{
+ int i, ret;
+
+ ret = -ENOENT;
+
+ for (i = 0; i < nr_symbols; i++) {
+ asymbol *symbol = symbols[i];
+
+ if (!strcmp(bfd_asymbol_name(symbol), symbol_name))
+ return symbol;
+ }
+
+ return ERR_PTR(ret);
+}
+
+char *symbol_lookup(struct kvm *kvm, unsigned long addr, char *sym, size_t size)
+{
+ const char *filename;
+ bfd_vma sym_offset;
+ bfd_vma sym_start;
+ asection *section;
+ unsigned int line;
+ const char *func;
+ long symtab_size;
+ asymbol *symbol;
+ asymbol **syms;
+ int nr_syms, ret;
+
+ ret = -ENOENT;
+ if (!abfd)
+ goto not_found;
+
+ if (!bfd_check_format(abfd, bfd_object))
+ goto not_found;
+
+ symtab_size = bfd_get_symtab_upper_bound(abfd);
+ if (!symtab_size)
+ goto not_found;
+
+ ret = -ENOMEM;
+ syms = malloc(symtab_size);
+ if (!syms)
+ goto not_found;
+
+ nr_syms = bfd_canonicalize_symtab(abfd, syms);
+
+ ret = -ENOENT;
+ section = bfd_get_section_by_name(abfd, ".debug_aranges");
+ if (!section)
+ goto not_found;
+
+ if (!bfd_find_nearest_line(abfd, section, NULL, addr, &filename, &func, &line))
+ goto not_found;
+
+ if (!func)
+ goto not_found;
+
+ symbol = lookup(syms, nr_syms, func);
+ if (IS_ERR(symbol))
+ goto not_found;
+
+ sym_start = bfd_asymbol_value(symbol);
+
+ sym_offset = addr - sym_start;
+
+ snprintf(sym, size, "%s+%llx (%s:%i)", func, (long long) sym_offset, filename, line);
+
+ sym[size - 1] = '\0';
+
+ free(syms);
+
+ return sym;
+
+not_found:
+ return ERR_PTR(ret);
+}
+
+int symbol_exit(struct kvm *kvm)
+{
+ bfd_boolean ret = TRUE;
+
+ if (abfd)
+ ret = bfd_close(abfd);
+
+ if (ret == TRUE)
+ return 0;
+
+ return -EFAULT;
+}
+late_exit(symbol_exit);
diff --git a/kvmtool/term.c b/kvmtool/term.c
new file mode 100644
index 0000000..b8a70fe
--- /dev/null
+++ b/kvmtool/term.c
@@ -0,0 +1,213 @@
+#include <poll.h>
+#include <stdbool.h>
+#include <termios.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/uio.h>
+#include <signal.h>
+#include <pty.h>
+#include <utmp.h>
+
+#include "kvm/read-write.h"
+#include "kvm/term.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+#define TERM_FD_IN 0
+#define TERM_FD_OUT 1
+
+static struct termios orig_term;
+
+static int term_fds[TERM_MAX_DEVS][2];
+
+static pthread_t term_poll_thread;
+
+/* ctrl-a is used for escape */
+#define term_escape_char 0x01
+
+int term_getc(struct kvm *kvm, int term)
+{
+ static bool term_got_escape = false;
+ unsigned char c;
+
+ if (read_in_full(term_fds[term][TERM_FD_IN], &c, 1) < 0)
+ return -1;
+
+ if (term_got_escape) {
+ term_got_escape = false;
+ if (c == 'x')
+ kvm__reboot(kvm);
+ if (c == term_escape_char)
+ return c;
+ }
+
+ if (c == term_escape_char) {
+ term_got_escape = true;
+ return -1;
+ }
+
+ return c;
+}
+
+int term_putc(char *addr, int cnt, int term)
+{
+ int ret;
+ int num_remaining = cnt;
+
+ while (num_remaining) {
+ ret = write(term_fds[term][TERM_FD_OUT], addr, num_remaining);
+ if (ret < 0)
+ return cnt - num_remaining;
+ num_remaining -= ret;
+ addr += ret;
+ }
+
+ return cnt;
+}
+
+int term_getc_iov(struct kvm *kvm, struct iovec *iov, int iovcnt, int term)
+{
+ int c;
+
+ c = term_getc(kvm, term);
+
+ if (c < 0)
+ return 0;
+
+ *((char *)iov[TERM_FD_IN].iov_base) = (char)c;
+
+ return sizeof(char);
+}
+
+int term_putc_iov(struct iovec *iov, int iovcnt, int term)
+{
+ return writev(term_fds[term][TERM_FD_OUT], iov, iovcnt);
+}
+
+bool term_readable(int term)
+{
+ struct pollfd pollfd = (struct pollfd) {
+ .fd = term_fds[term][TERM_FD_IN],
+ .events = POLLIN,
+ .revents = 0,
+ };
+ int err;
+
+ err = poll(&pollfd, 1, 0);
+ return (err > 0 && (pollfd.revents & POLLIN));
+}
+
+static void *term_poll_thread_loop(void *param)
+{
+ struct pollfd fds[TERM_MAX_DEVS];
+ struct kvm *kvm = (struct kvm *) param;
+ int i;
+
+ kvm__set_thread_name("term-poll");
+
+ for (i = 0; i < TERM_MAX_DEVS; i++) {
+ fds[i].fd = term_fds[i][TERM_FD_IN];
+ fds[i].events = POLLIN;
+ fds[i].revents = 0;
+ }
+
+ while (1) {
+ /* Poll with infinite timeout */
+ if(poll(fds, TERM_MAX_DEVS, -1) < 1)
+ break;
+ kvm__arch_read_term(kvm);
+ }
+
+ die("term_poll_thread_loop: error polling device fds %d\n", errno);
+ return NULL;
+}
+
+static void term_cleanup(void)
+{
+ int i;
+
+ for (i = 0; i < TERM_MAX_DEVS; i++)
+ tcsetattr(term_fds[i][TERM_FD_IN], TCSANOW, &orig_term);
+}
+
+static void term_sig_cleanup(int sig)
+{
+ term_cleanup();
+ signal(sig, SIG_DFL);
+ raise(sig);
+}
+
+static void term_set_tty(int term)
+{
+ struct termios orig_term;
+ int master, slave;
+ char new_pty[PATH_MAX];
+
+ if (tcgetattr(STDIN_FILENO, &orig_term) < 0)
+ die("unable to save initial standard input settings");
+
+ orig_term.c_lflag &= ~(ICANON | ECHO | ISIG);
+
+ if (openpty(&master, &slave, new_pty, &orig_term, NULL) < 0)
+ return;
+
+ close(slave);
+
+ pr_info("Assigned terminal %d to pty %s\n", term, new_pty);
+
+ term_fds[term][TERM_FD_IN] = term_fds[term][TERM_FD_OUT] = master;
+}
+
+int tty_parser(const struct option *opt, const char *arg, int unset)
+{
+ int tty = atoi(arg);
+
+ term_set_tty(tty);
+
+ return 0;
+}
+
+static int term_init(struct kvm *kvm)
+{
+ struct termios term;
+ int i, r;
+
+ for (i = 0; i < TERM_MAX_DEVS; i++)
+ if (term_fds[i][TERM_FD_IN] == 0) {
+ term_fds[i][TERM_FD_IN] = STDIN_FILENO;
+ term_fds[i][TERM_FD_OUT] = STDOUT_FILENO;
+ }
+
+ if (!isatty(STDIN_FILENO) || !isatty(STDOUT_FILENO))
+ return 0;
+
+ r = tcgetattr(STDIN_FILENO, &orig_term);
+ if (r < 0) {
+ pr_warning("unable to save initial standard input settings");
+ return r;
+ }
+
+
+ term = orig_term;
+ term.c_iflag &= ~(ICRNL);
+ term.c_lflag &= ~(ICANON | ECHO | ISIG);
+ tcsetattr(STDIN_FILENO, TCSANOW, &term);
+
+
+ /* Use our own blocking thread to read stdin, don't require a tick */
+ if(pthread_create(&term_poll_thread, NULL, term_poll_thread_loop,kvm))
+ die("Unable to create console input poll thread\n");
+
+ signal(SIGTERM, term_sig_cleanup);
+ atexit(term_cleanup);
+
+ return 0;
+}
+dev_init(term_init);
+
+static int term_exit(struct kvm *kvm)
+{
+ return 0;
+}
+dev_exit(term_exit);
diff --git a/kvmtool/tests/Makefile b/kvmtool/tests/Makefile
new file mode 100644
index 0000000..cad14ec
--- /dev/null
+++ b/kvmtool/tests/Makefile
@@ -0,0 +1,19 @@
+all: kernel pit boot
+
+kernel:
+ $(MAKE) -C kernel
+.PHONY: kernel
+
+pit:
+ $(MAKE) -C pit
+.PHONY: pit
+
+boot:
+ $(MAKE) -C boot
+.PHONY: boot
+
+clean:
+ $(MAKE) -C kernel clean
+ $(MAKE) -C pit clean
+ $(MAKE) -C boot clean
+.PHONY: clean
diff --git a/kvmtool/tests/boot/Makefile b/kvmtool/tests/boot/Makefile
new file mode 100644
index 0000000..2b950d2
--- /dev/null
+++ b/kvmtool/tests/boot/Makefile
@@ -0,0 +1,21 @@
+NAME := init
+
+OBJ := $(NAME).o
+MKISOFS := $(shell which mkisofs)
+ifndef MKISOFS
+MKISOFS := $(shell which xorrisofs)
+endif
+
+all: $(.o)
+ rm -rf rootfs
+ mkdir rootfs
+ gcc -static init.c -o rootfs/init
+ifdef MKISOFS
+ $(MKISOFS) rootfs -o boot_test.iso
+else
+ $(error "mkisofs or xorriso needed to build boot_test.iso")
+endif
+
+clean:
+ rm -rf rootfs boot_test.iso
+.PHONY: clean
diff --git a/kvmtool/tests/boot/init.c b/kvmtool/tests/boot/init.c
new file mode 100644
index 0000000..094f8ba
--- /dev/null
+++ b/kvmtool/tests/boot/init.c
@@ -0,0 +1,11 @@
+#include <linux/reboot.h>
+#include <unistd.h>
+
+int main(int argc, char *argv[])
+{
+ puts("hello, KVM guest!\r");
+
+ reboot(LINUX_REBOOT_CMD_RESTART);
+
+ return 0;
+}
diff --git a/kvmtool/tests/kernel/.gitignore b/kvmtool/tests/kernel/.gitignore
new file mode 100644
index 0000000..d0cd209
--- /dev/null
+++ b/kvmtool/tests/kernel/.gitignore
@@ -0,0 +1,2 @@
+kernel.bin
+kernel.elf
diff --git a/kvmtool/tests/kernel/Makefile b/kvmtool/tests/kernel/Makefile
new file mode 100644
index 0000000..c7dd8da
--- /dev/null
+++ b/kvmtool/tests/kernel/Makefile
@@ -0,0 +1,20 @@
+NAME := kernel
+
+BIN := $(NAME).bin
+ELF := $(NAME).elf
+OBJ := $(NAME).o
+
+all: $(BIN)
+
+$(BIN): $(ELF)
+ objcopy -O binary $< $@
+
+$(ELF): $(OBJ)
+ ld -Ttext=0x00 -nostdlib -static $< -o $@
+
+%.o: %.S
+ gcc -nostdinc -c $< -o $@
+
+clean:
+ rm -f $(BIN) $(ELF) $(OBJ)
+.PHONY: clean
diff --git a/kvmtool/tests/kernel/README b/kvmtool/tests/kernel/README
new file mode 100644
index 0000000..2923777
--- /dev/null
+++ b/kvmtool/tests/kernel/README
@@ -0,0 +1,16 @@
+Compiling
+---------
+
+You can simply type:
+
+ $ make
+
+to build a 16-bit binary that uses the i8086 instruction set.
+
+Disassembling
+-------------
+
+Use the "-m i8086" command line option with objdump to make sure it knows we're
+dealing with i8086 instruction set:
+
+ $ objdump -d -m i8086 i8086.elf
diff --git a/kvmtool/tests/kernel/kernel.S b/kvmtool/tests/kernel/kernel.S
new file mode 100644
index 0000000..2824b64
--- /dev/null
+++ b/kvmtool/tests/kernel/kernel.S
@@ -0,0 +1,8 @@
+ .code16gcc
+ .text
+ .globl _start
+ .type _start, @function
+_start:
+ # "This is probably the largest possible kernel that is bug free." -- Avi Kivity
+ 1:
+ jmp 1b
diff --git a/kvmtool/tests/pit/.gitignore b/kvmtool/tests/pit/.gitignore
new file mode 100644
index 0000000..43f0aa8
--- /dev/null
+++ b/kvmtool/tests/pit/.gitignore
@@ -0,0 +1,2 @@
+*.bin
+*.elf
diff --git a/kvmtool/tests/pit/Makefile b/kvmtool/tests/pit/Makefile
new file mode 100644
index 0000000..2fae9b2
--- /dev/null
+++ b/kvmtool/tests/pit/Makefile
@@ -0,0 +1,20 @@
+NAME := tick
+
+BIN := $(NAME).bin
+ELF := $(NAME).elf
+OBJ := $(NAME).o
+
+all: $(BIN)
+
+$(BIN): $(ELF)
+ objcopy -O binary $< $@
+
+$(ELF): $(OBJ)
+ ld -Ttext=0x00 -nostdlib -static $< -o $@
+
+%.o: %.S
+ gcc -nostdinc -c $< -o $@
+
+clean:
+ rm -f $(BIN) $(ELF) $(OBJ)
+.PHONY: clean
diff --git a/kvmtool/tests/pit/README b/kvmtool/tests/pit/README
new file mode 100644
index 0000000..2923777
--- /dev/null
+++ b/kvmtool/tests/pit/README
@@ -0,0 +1,16 @@
+Compiling
+---------
+
+You can simply type:
+
+ $ make
+
+to build a 16-bit binary that uses the i8086 instruction set.
+
+Disassembling
+-------------
+
+Use the "-m i8086" command line option with objdump to make sure it knows we're
+dealing with i8086 instruction set:
+
+ $ objdump -d -m i8086 i8086.elf
diff --git a/kvmtool/tests/pit/tick.S b/kvmtool/tests/pit/tick.S
new file mode 100644
index 0000000..635dc8d
--- /dev/null
+++ b/kvmtool/tests/pit/tick.S
@@ -0,0 +1,101 @@
+#define IO_PIC 0x20
+#define IRQ_OFFSET 32
+#define IO_PIT 0x40
+#define TIMER_FREQ 1193182
+#define TIMER_DIV(x) ((TIMER_FREQ+(x)/2)/(x))
+
+#define TEST_COUNT 0x0200
+
+ .code16gcc
+ .text
+ .globl _start
+ .type _start, @function
+_start:
+/*
+ * fill up noop handlers
+ */
+ xorw %ax, %ax
+ xorw %di, %di
+ movw %ax, %es
+ movw $256, %cx
+fill_noop_idt:
+ movw $noop_handler, %es:(%di)
+ movw %cs, %es:2(%di)
+ add $4, %di
+ loop fill_noop_idt
+
+set_idt:
+ movw $timer_isr, %es:(IRQ_OFFSET*4)
+ movw %cs, %es:(IRQ_OFFSET*4+2)
+
+set_pic:
+ # ICW1
+ mov $0x11, %al
+ mov $(IO_PIC), %dx
+ out %al,%dx
+ # ICW2
+ mov $(IRQ_OFFSET), %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+ # ICW3
+ mov $0x00, %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+ # ICW4
+ mov $0x3, %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+
+set_pit:
+ # set 8254 mode
+ mov $(IO_PIT+3), %dx
+ mov $0x34, %al
+ outb %al, %dx
+ # set 8254 freq 1KHz
+ mov $(IO_PIT), %dx
+ movb $(TIMER_DIV(1000) % 256), %al
+ outb %al, %dx
+ movb $(TIMER_DIV(1000) / 256), %al
+ outb %al, %dx
+
+enable_irq0:
+ mov $0xfe, %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+ sti
+loop:
+ 1:
+ jmp 1b
+
+test_ok:
+ mov $0x3f8,%dx
+ cs lea msg2, %si
+ mov $(msg2_end-msg2), %cx
+ cs rep/outsb
+
+ /* Reboot by using the i8042 reboot line */
+ mov $0xfe, %al
+ outb %al, $0x64
+
+timer_isr:
+ cli
+ pushaw
+ pushfw
+ mov $0x3f8,%dx
+ mov $0x2e, %al # .
+ out %al,%dx
+ decw count
+ jz test_ok
+ popfw
+ popaw
+ iretw
+
+noop_handler:
+ iretw
+
+count:
+ .word TEST_COUNT
+
+msg2:
+ .asciz "\nTest OK\n"
+msg2_end:
diff --git a/kvmtool/ui/gtk3.c b/kvmtool/ui/gtk3.c
new file mode 100644
index 0000000..1e08a8f
--- /dev/null
+++ b/kvmtool/ui/gtk3.c
@@ -0,0 +1,326 @@
+#include "kvm/gtk3.h"
+
+#include "kvm/framebuffer.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/i8042.h"
+#include "kvm/vesa.h"
+#include "kvm/kvm.h"
+
+#include <gtk/gtk.h>
+#include <pthread.h>
+#include <linux/err.h>
+
+#define FRAME_RATE 25
+
+#define SCANCODE_UNKNOWN 0
+#define SCANCODE_NORMAL 1
+#define SCANCODE_ESCAPED 2
+#define SCANCODE_KEY_PAUSE 3
+#define SCANCODE_KEY_PRNTSCRN 4
+
+struct set2_scancode {
+ u8 code;
+ u8 type;
+};
+
+#define DEFINE_SC(_code) { \
+ .code = _code, \
+ .type = SCANCODE_NORMAL, \
+}
+
+/* escaped scancodes */
+#define DEFINE_ESC(_code) { \
+ .code = _code, \
+ .type = SCANCODE_ESCAPED, \
+}
+
+static const struct set2_scancode keymap[256] = {
+ [9] = DEFINE_SC(0x76), /* <esc> */
+ [10] = DEFINE_SC(0x16), /* 1 */
+ [11] = DEFINE_SC(0x1e), /* 2 */
+ [12] = DEFINE_SC(0x26), /* 3 */
+ [13] = DEFINE_SC(0x25), /* 4 */
+ [14] = DEFINE_SC(0x2e), /* 5 */
+ [15] = DEFINE_SC(0x36), /* 6 */
+ [16] = DEFINE_SC(0x3d), /* 7 */
+ [17] = DEFINE_SC(0x3e), /* 8 */
+ [18] = DEFINE_SC(0x46), /* 9 */
+ [19] = DEFINE_SC(0x45), /* 9 */
+ [20] = DEFINE_SC(0x4e), /* - */
+ [21] = DEFINE_SC(0x55), /* + */
+ [22] = DEFINE_SC(0x66), /* <backspace> */
+ [23] = DEFINE_SC(0x0d), /* <tab> */
+ [24] = DEFINE_SC(0x15), /* q */
+ [25] = DEFINE_SC(0x1d), /* w */
+ [26] = DEFINE_SC(0x24), /* e */
+ [27] = DEFINE_SC(0x2d), /* r */
+ [28] = DEFINE_SC(0x2c), /* t */
+ [29] = DEFINE_SC(0x35), /* y */
+ [30] = DEFINE_SC(0x3c), /* u */
+ [31] = DEFINE_SC(0x43), /* i */
+ [32] = DEFINE_SC(0x44), /* o */
+ [33] = DEFINE_SC(0x4d), /* p */
+ [34] = DEFINE_SC(0x54), /* [ */
+ [35] = DEFINE_SC(0x5b), /* ] */
+ [36] = DEFINE_SC(0x5a), /* <enter> */
+ [37] = DEFINE_SC(0x14), /* <left ctrl> */
+ [38] = DEFINE_SC(0x1c), /* a */
+ [39] = DEFINE_SC(0x1b), /* s */
+ [40] = DEFINE_SC(0x23), /* d */
+ [41] = DEFINE_SC(0x2b), /* f */
+ [42] = DEFINE_SC(0x34), /* g */
+ [43] = DEFINE_SC(0x33), /* h */
+ [44] = DEFINE_SC(0x3b), /* j */
+ [45] = DEFINE_SC(0x42), /* k */
+ [46] = DEFINE_SC(0x4b), /* l */
+ [47] = DEFINE_SC(0x4c), /* ; */
+ [48] = DEFINE_SC(0x52), /* ' */
+ [49] = DEFINE_SC(0x0e), /* ` */
+ [50] = DEFINE_SC(0x12), /* <left shift> */
+ [51] = DEFINE_SC(0x5d), /* \ */
+ [52] = DEFINE_SC(0x1a), /* z */
+ [53] = DEFINE_SC(0x22), /* x */
+ [54] = DEFINE_SC(0x21), /* c */
+ [55] = DEFINE_SC(0x2a), /* v */
+ [56] = DEFINE_SC(0x32), /* b */
+ [57] = DEFINE_SC(0x31), /* n */
+ [58] = DEFINE_SC(0x3a), /* m */
+ [59] = DEFINE_SC(0x41), /* < */
+ [60] = DEFINE_SC(0x49), /* > */
+ [61] = DEFINE_SC(0x4a), /* / */
+ [62] = DEFINE_SC(0x59), /* <right shift> */
+ [63] = DEFINE_SC(0x7c), /* keypad * */
+ [64] = DEFINE_SC(0x11), /* <left alt> */
+ [65] = DEFINE_SC(0x29), /* <space> */
+
+ [67] = DEFINE_SC(0x05), /* <F1> */
+ [68] = DEFINE_SC(0x06), /* <F2> */
+ [69] = DEFINE_SC(0x04), /* <F3> */
+ [70] = DEFINE_SC(0x0c), /* <F4> */
+ [71] = DEFINE_SC(0x03), /* <F5> */
+ [72] = DEFINE_SC(0x0b), /* <F6> */
+ [73] = DEFINE_SC(0x83), /* <F7> */
+ [74] = DEFINE_SC(0x0a), /* <F8> */
+ [75] = DEFINE_SC(0x01), /* <F9> */
+ [76] = DEFINE_SC(0x09), /* <F10> */
+
+ [79] = DEFINE_SC(0x6c), /* keypad 7 */
+ [80] = DEFINE_SC(0x75), /* keypad 8 */
+ [81] = DEFINE_SC(0x7d), /* keypad 9 */
+ [82] = DEFINE_SC(0x7b), /* keypad - */
+ [83] = DEFINE_SC(0x6b), /* keypad 4 */
+ [84] = DEFINE_SC(0x73), /* keypad 5 */
+ [85] = DEFINE_SC(0x74), /* keypad 6 */
+ [86] = DEFINE_SC(0x79), /* keypad + */
+ [87] = DEFINE_SC(0x69), /* keypad 1 */
+ [88] = DEFINE_SC(0x72), /* keypad 2 */
+ [89] = DEFINE_SC(0x7a), /* keypad 3 */
+ [90] = DEFINE_SC(0x70), /* keypad 0 */
+ [91] = DEFINE_SC(0x71), /* keypad . */
+
+ [94] = DEFINE_SC(0x61), /* <INT 1> */
+ [95] = DEFINE_SC(0x78), /* <F11> */
+ [96] = DEFINE_SC(0x07), /* <F12> */
+
+ [104] = DEFINE_ESC(0x5a), /* keypad <enter> */
+ [105] = DEFINE_ESC(0x14), /* <right ctrl> */
+ [106] = DEFINE_ESC(0x4a), /* keypad / */
+ [108] = DEFINE_ESC(0x11), /* <right alt> */
+ [110] = DEFINE_ESC(0x6c), /* <home> */
+ [111] = DEFINE_ESC(0x75), /* <up> */
+ [112] = DEFINE_ESC(0x7d), /* <pag up> */
+ [113] = DEFINE_ESC(0x6b), /* <left> */
+ [114] = DEFINE_ESC(0x74), /* <right> */
+ [115] = DEFINE_ESC(0x69), /* <end> */
+ [116] = DEFINE_ESC(0x72), /* <down> */
+ [117] = DEFINE_ESC(0x7a), /* <pag down> */
+ [118] = DEFINE_ESC(0x70), /* <ins> */
+ [119] = DEFINE_ESC(0x71), /* <delete> */
+};
+
+static cairo_surface_t *surface;
+static bool done;
+
+static const struct set2_scancode *to_code(u8 scancode)
+{
+ return &keymap[scancode];
+}
+
+static gboolean
+kvm_gtk_configure_event(GtkWidget * widget, GdkEventConfigure * event, gpointer data)
+{
+ struct framebuffer *fb = data;
+ int stride;
+
+ if (surface)
+ cairo_surface_destroy(surface);
+
+ stride = cairo_format_stride_for_width(CAIRO_FORMAT_RGB24, fb->width);
+
+ surface =
+ cairo_image_surface_create_for_data((void *) fb->mem,
+ CAIRO_FORMAT_RGB24,
+ fb->width,
+ fb->height,
+ stride);
+
+ return TRUE;
+}
+
+static gboolean kvm_gtk_draw(GtkWidget *widget, cairo_t *cr, gpointer data)
+{
+ cairo_set_source_surface(cr, surface, 0, 0);
+
+ cairo_paint(cr);
+
+ return FALSE;
+}
+
+static void kvm_gtk_destroy(void)
+{
+ if (surface)
+ cairo_surface_destroy(surface);
+
+ gtk_main_quit();
+}
+
+static gboolean kvm_gtk_redraw(GtkWidget * window)
+{
+ gtk_widget_queue_draw(window);
+
+ return TRUE;
+}
+
+static gboolean
+kvm_gtk_key_press(GtkWidget *widget, GdkEventKey *event, gpointer user_data)
+{
+ const struct set2_scancode *sc = to_code(event->hardware_keycode);
+
+ switch (sc->type) {
+ case SCANCODE_ESCAPED:
+ kbd_queue(0xe0);
+ /* fallthrough */
+ case SCANCODE_NORMAL:
+ kbd_queue(sc->code);
+ break;
+ case SCANCODE_KEY_PAUSE:
+ kbd_queue(0xe1);
+ kbd_queue(0x14);
+ kbd_queue(0x77);
+ kbd_queue(0xe1);
+ kbd_queue(0xf0);
+ kbd_queue(0x14);
+ kbd_queue(0x77);
+ break;
+ case SCANCODE_KEY_PRNTSCRN:
+ kbd_queue(0xe0);
+ kbd_queue(0x12);
+ kbd_queue(0xe0);
+ kbd_queue(0x7c);
+ break;
+ }
+
+ return TRUE;
+}
+
+static void *kvm_gtk_thread(void *p)
+{
+ struct framebuffer *fb = p;
+ GtkWidget *window;
+ GtkWidget *frame;
+ GtkWidget *da;
+
+ gtk_init(NULL, NULL);
+
+ window = gtk_window_new(GTK_WINDOW_TOPLEVEL);
+
+ gtk_window_set_title(GTK_WINDOW(window), "VM");
+
+ g_signal_connect(window, "destroy", G_CALLBACK(kvm_gtk_destroy), NULL);
+
+ gtk_container_set_border_width(GTK_CONTAINER(window), 8);
+
+ frame = gtk_frame_new(NULL);
+
+ gtk_frame_set_shadow_type(GTK_FRAME(frame), GTK_SHADOW_IN);
+ gtk_container_add(GTK_CONTAINER(window), frame);
+
+ da = gtk_drawing_area_new();
+
+ gtk_widget_set_size_request(da, 100, 100);
+
+ gtk_container_add(GTK_CONTAINER(frame), da);
+
+ g_signal_connect(da, "draw", G_CALLBACK(kvm_gtk_draw), NULL);
+ g_signal_connect(da, "configure-event",
+ G_CALLBACK(kvm_gtk_configure_event), fb);
+ g_signal_connect(G_OBJECT (window), "key_press_event", G_CALLBACK(kvm_gtk_key_press), NULL);
+
+
+ gtk_widget_set_events(da, gtk_widget_get_events(da)
+ | GDK_BUTTON_PRESS_MASK
+ | GDK_POINTER_MOTION_MASK
+ | GDK_POINTER_MOTION_HINT_MASK);
+
+ gtk_widget_show_all(window);
+
+ g_timeout_add(1000 / FRAME_RATE, (GSourceFunc) kvm_gtk_redraw, window);
+
+ gtk_main();
+
+ done = true;
+
+ return NULL;
+}
+
+static int kvm_gtk_start(struct framebuffer *fb)
+{
+ pthread_t thread;
+
+ if (pthread_create(&thread, NULL, kvm_gtk_thread, fb) != 0)
+ return -1;
+
+ return 0;
+}
+
+static int kvm_gtk_stop(struct framebuffer *fb)
+{
+ gtk_main_quit();
+
+ while (!done)
+ sleep(0);
+
+ return 0;
+}
+
+static struct fb_target_operations kvm_gtk_ops = {
+ .start = kvm_gtk_start,
+ .stop = kvm_gtk_stop,
+};
+
+int kvm_gtk_init(struct kvm *kvm)
+{
+ struct framebuffer *fb;
+
+ if (!kvm->cfg.gtk)
+ return 0;
+
+ fb = vesa__init(kvm);
+ if (IS_ERR(fb)) {
+ pr_err("vesa__init() failed with error %ld\n", PTR_ERR(fb));
+ return PTR_ERR(fb);
+ }
+
+ return fb__attach(fb, &kvm_gtk_ops);
+}
+
+int kvm_gtk_exit(struct kvm *kvm)
+{
+ if (kvm->cfg.gtk)
+ return kvm_gtk_stop(NULL);
+
+ return 0;
+}
+
+dev_init(kvm_gtk_init);
+dev_exit(kvm_gtk_exit);
diff --git a/kvmtool/ui/sdl.c b/kvmtool/ui/sdl.c
new file mode 100644
index 0000000..5035405
--- /dev/null
+++ b/kvmtool/ui/sdl.c
@@ -0,0 +1,324 @@
+#include "kvm/sdl.h"
+
+#include "kvm/framebuffer.h"
+#include "kvm/i8042.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/vesa.h"
+
+#include <SDL/SDL.h>
+#include <pthread.h>
+#include <signal.h>
+#include <linux/err.h>
+
+#define FRAME_RATE 25
+
+#define SCANCODE_UNKNOWN 0
+#define SCANCODE_NORMAL 1
+#define SCANCODE_ESCAPED 2
+#define SCANCODE_KEY_PAUSE 3
+#define SCANCODE_KEY_PRNTSCRN 4
+
+struct set2_scancode {
+ u8 code;
+ u8 type;
+};
+
+#define DEFINE_SC(_code) {\
+ .code = _code,\
+ .type = SCANCODE_NORMAL,\
+}
+
+/* escaped scancodes */
+#define DEFINE_ESC(_code) {\
+ .code = _code,\
+ .type = SCANCODE_ESCAPED,\
+}
+
+static const struct set2_scancode keymap[256] = {
+ [9] = DEFINE_SC(0x76), /* <esc> */
+ [10] = DEFINE_SC(0x16), /* 1 */
+ [11] = DEFINE_SC(0x1e), /* 2 */
+ [12] = DEFINE_SC(0x26), /* 3 */
+ [13] = DEFINE_SC(0x25), /* 4 */
+ [14] = DEFINE_SC(0x2e), /* 5 */
+ [15] = DEFINE_SC(0x36), /* 6 */
+ [16] = DEFINE_SC(0x3d), /* 7 */
+ [17] = DEFINE_SC(0x3e), /* 8 */
+ [18] = DEFINE_SC(0x46), /* 9 */
+ [19] = DEFINE_SC(0x45), /* 9 */
+ [20] = DEFINE_SC(0x4e), /* - */
+ [21] = DEFINE_SC(0x55), /* + */
+ [22] = DEFINE_SC(0x66), /* <backspace> */
+ [23] = DEFINE_SC(0x0d), /* <tab> */
+ [24] = DEFINE_SC(0x15), /* q */
+ [25] = DEFINE_SC(0x1d), /* w */
+ [26] = DEFINE_SC(0x24), /* e */
+ [27] = DEFINE_SC(0x2d), /* r */
+ [28] = DEFINE_SC(0x2c), /* t */
+ [29] = DEFINE_SC(0x35), /* y */
+ [30] = DEFINE_SC(0x3c), /* u */
+ [31] = DEFINE_SC(0x43), /* i */
+ [32] = DEFINE_SC(0x44), /* o */
+ [33] = DEFINE_SC(0x4d), /* p */
+ [34] = DEFINE_SC(0x54), /* [ */
+ [35] = DEFINE_SC(0x5b), /* ] */
+ [36] = DEFINE_SC(0x5a), /* <enter> */
+ [37] = DEFINE_SC(0x14), /* <left ctrl> */
+ [38] = DEFINE_SC(0x1c), /* a */
+ [39] = DEFINE_SC(0x1b), /* s */
+ [40] = DEFINE_SC(0x23), /* d */
+ [41] = DEFINE_SC(0x2b), /* f */
+ [42] = DEFINE_SC(0x34), /* g */
+ [43] = DEFINE_SC(0x33), /* h */
+ [44] = DEFINE_SC(0x3b), /* j */
+ [45] = DEFINE_SC(0x42), /* k */
+ [46] = DEFINE_SC(0x4b), /* l */
+ [47] = DEFINE_SC(0x4c), /* ; */
+ [48] = DEFINE_SC(0x52), /* ' */
+ [49] = DEFINE_SC(0x0e), /* ` */
+ [50] = DEFINE_SC(0x12), /* <left shift> */
+ [51] = DEFINE_SC(0x5d), /* \ */
+ [52] = DEFINE_SC(0x1a), /* z */
+ [53] = DEFINE_SC(0x22), /* x */
+ [54] = DEFINE_SC(0x21), /* c */
+ [55] = DEFINE_SC(0x2a), /* v */
+ [56] = DEFINE_SC(0x32), /* b */
+ [57] = DEFINE_SC(0x31), /* n */
+ [58] = DEFINE_SC(0x3a), /* m */
+ [59] = DEFINE_SC(0x41), /* < */
+ [60] = DEFINE_SC(0x49), /* > */
+ [61] = DEFINE_SC(0x4a), /* / */
+ [62] = DEFINE_SC(0x59), /* <right shift> */
+ [63] = DEFINE_SC(0x7c), /* keypad * */
+ [64] = DEFINE_SC(0x11), /* <left alt> */
+ [65] = DEFINE_SC(0x29), /* <space> */
+
+ [67] = DEFINE_SC(0x05), /* <F1> */
+ [68] = DEFINE_SC(0x06), /* <F2> */
+ [69] = DEFINE_SC(0x04), /* <F3> */
+ [70] = DEFINE_SC(0x0c), /* <F4> */
+ [71] = DEFINE_SC(0x03), /* <F5> */
+ [72] = DEFINE_SC(0x0b), /* <F6> */
+ [73] = DEFINE_SC(0x83), /* <F7> */
+ [74] = DEFINE_SC(0x0a), /* <F8> */
+ [75] = DEFINE_SC(0x01), /* <F9> */
+ [76] = DEFINE_SC(0x09), /* <F10> */
+
+ [79] = DEFINE_SC(0x6c), /* keypad 7 */
+ [80] = DEFINE_SC(0x75), /* keypad 8 */
+ [81] = DEFINE_SC(0x7d), /* keypad 9 */
+ [82] = DEFINE_SC(0x7b), /* keypad - */
+ [83] = DEFINE_SC(0x6b), /* keypad 4 */
+ [84] = DEFINE_SC(0x73), /* keypad 5 */
+ [85] = DEFINE_SC(0x74), /* keypad 6 */
+ [86] = DEFINE_SC(0x79), /* keypad + */
+ [87] = DEFINE_SC(0x69), /* keypad 1 */
+ [88] = DEFINE_SC(0x72), /* keypad 2 */
+ [89] = DEFINE_SC(0x7a), /* keypad 3 */
+ [90] = DEFINE_SC(0x70), /* keypad 0 */
+ [91] = DEFINE_SC(0x71), /* keypad . */
+
+ [94] = DEFINE_SC(0x61), /* <INT 1> */
+ [95] = DEFINE_SC(0x78), /* <F11> */
+ [96] = DEFINE_SC(0x07), /* <F12> */
+
+ [104] = DEFINE_ESC(0x5a), /* keypad <enter> */
+ [105] = DEFINE_ESC(0x14), /* <right ctrl> */
+ [106] = DEFINE_ESC(0x4a), /* keypad / */
+ [108] = DEFINE_ESC(0x11), /* <right alt> */
+ [110] = DEFINE_ESC(0x6c), /* <home> */
+ [111] = DEFINE_ESC(0x75), /* <up> */
+ [112] = DEFINE_ESC(0x7d), /* <pag up> */
+ [113] = DEFINE_ESC(0x6b), /* <left> */
+ [114] = DEFINE_ESC(0x74), /* <right> */
+ [115] = DEFINE_ESC(0x69), /* <end> */
+ [116] = DEFINE_ESC(0x72), /* <down> */
+ [117] = DEFINE_ESC(0x7a), /* <pag down> */
+ [118] = DEFINE_ESC(0x70), /* <ins> */
+ [119] = DEFINE_ESC(0x71), /* <delete> */
+};
+static bool running, done;
+
+static const struct set2_scancode *to_code(u8 scancode)
+{
+ return &keymap[scancode];
+}
+
+static void key_press(const struct set2_scancode *sc)
+{
+ switch (sc->type) {
+ case SCANCODE_ESCAPED:
+ kbd_queue(0xe0);
+ /* fallthrough */
+ case SCANCODE_NORMAL:
+ kbd_queue(sc->code);
+ break;
+ case SCANCODE_KEY_PAUSE:
+ kbd_queue(0xe1);
+ kbd_queue(0x14);
+ kbd_queue(0x77);
+ kbd_queue(0xe1);
+ kbd_queue(0xf0);
+ kbd_queue(0x14);
+ kbd_queue(0x77);
+ break;
+ case SCANCODE_KEY_PRNTSCRN:
+ kbd_queue(0xe0);
+ kbd_queue(0x12);
+ kbd_queue(0xe0);
+ kbd_queue(0x7c);
+ break;
+ }
+}
+
+static void key_release(const struct set2_scancode *sc)
+{
+ switch (sc->type) {
+ case SCANCODE_ESCAPED:
+ kbd_queue(0xe0);
+ /* fallthrough */
+ case SCANCODE_NORMAL:
+ kbd_queue(0xf0);
+ kbd_queue(sc->code);
+ break;
+ case SCANCODE_KEY_PAUSE:
+ /* nothing to do */
+ break;
+ case SCANCODE_KEY_PRNTSCRN:
+ kbd_queue(0xe0);
+ kbd_queue(0xf0);
+ kbd_queue(0x7c);
+ kbd_queue(0xe0);
+ kbd_queue(0xf0);
+ kbd_queue(0x12);
+ break;
+ }
+}
+
+static void *sdl__thread(void *p)
+{
+ Uint32 rmask, gmask, bmask, amask;
+ struct framebuffer *fb = p;
+ SDL_Surface *guest_screen;
+ SDL_Surface *screen;
+ SDL_Event ev;
+ Uint32 flags;
+
+ kvm__set_thread_name("kvm-sdl-worker");
+
+ if (SDL_Init(SDL_INIT_VIDEO) != 0)
+ die("Unable to initialize SDL");
+
+ rmask = 0x000000ff;
+ gmask = 0x0000ff00;
+ bmask = 0x00ff0000;
+ amask = 0x00000000;
+
+ guest_screen = SDL_CreateRGBSurfaceFrom(fb->mem, fb->width, fb->height, fb->depth, fb->width * fb->depth / 8, rmask, gmask, bmask, amask);
+ if (!guest_screen)
+ die("Unable to create SDL RBG surface");
+
+ flags = SDL_HWSURFACE | SDL_ASYNCBLIT | SDL_HWACCEL | SDL_DOUBLEBUF;
+
+ SDL_WM_SetCaption("KVM tool", "KVM tool");
+
+ screen = SDL_SetVideoMode(fb->width, fb->height, fb->depth, flags);
+ if (!screen)
+ die("Unable to set SDL video mode");
+
+ SDL_EnableKeyRepeat(200, 50);
+
+ while (running) {
+ SDL_BlitSurface(guest_screen, NULL, screen, NULL);
+ SDL_Flip(screen);
+
+ while (SDL_PollEvent(&ev)) {
+ switch (ev.type) {
+ case SDL_KEYDOWN: {
+ const struct set2_scancode *sc = to_code(ev.key.keysym.scancode);
+ if (sc->type == SCANCODE_UNKNOWN) {
+ pr_warning("key '%d' not found in keymap", ev.key.keysym.scancode);
+ break;
+ }
+ key_press(sc);
+ break;
+ }
+ case SDL_KEYUP: {
+ const struct set2_scancode *sc = to_code(ev.key.keysym.scancode);
+ if (sc->type == SCANCODE_UNKNOWN)
+ break;
+ key_release(sc);
+ break;
+ }
+ case SDL_QUIT:
+ goto exit;
+ }
+ }
+
+ SDL_Delay(1000 / FRAME_RATE);
+ }
+
+ if (running == false && done == false) {
+ done = true;
+ return NULL;
+ }
+exit:
+ done = true;
+ kvm__reboot(fb->kvm);
+
+ return NULL;
+}
+
+static int sdl__start(struct framebuffer *fb)
+{
+ pthread_t thread;
+
+ running = true;
+
+ if (pthread_create(&thread, NULL, sdl__thread, fb) != 0)
+ return -1;
+
+ return 0;
+}
+
+static int sdl__stop(struct framebuffer *fb)
+{
+ running = false;
+ while (done == false)
+ sleep(0);
+
+ return 0;
+}
+
+static struct fb_target_operations sdl_ops = {
+ .start = sdl__start,
+ .stop = sdl__stop,
+};
+
+int sdl__init(struct kvm *kvm)
+{
+ struct framebuffer *fb;
+
+ if (!kvm->cfg.sdl)
+ return 0;
+
+ fb = vesa__init(kvm);
+ if (IS_ERR(fb)) {
+ pr_err("vesa__init() failed with error %ld\n", PTR_ERR(fb));
+ return PTR_ERR(fb);
+ }
+
+ return fb__attach(fb, &sdl_ops);
+}
+dev_init(sdl__init);
+
+int sdl__exit(struct kvm *kvm)
+{
+ if (kvm->cfg.sdl)
+ return sdl__stop(NULL);
+
+ return 0;
+}
+dev_exit(sdl__exit);
diff --git a/kvmtool/ui/vnc.c b/kvmtool/ui/vnc.c
new file mode 100644
index 0000000..12e4bd5
--- /dev/null
+++ b/kvmtool/ui/vnc.c
@@ -0,0 +1,250 @@
+#include "kvm/vnc.h"
+
+#include "kvm/framebuffer.h"
+#include "kvm/i8042.h"
+#include "kvm/vesa.h"
+
+#include <linux/types.h>
+#include <rfb/keysym.h>
+#include <rfb/rfb.h>
+#include <pthread.h>
+#include <linux/err.h>
+
+#define VESA_QUEUE_SIZE 128
+#define VESA_IRQ 14
+
+/*
+ * This "6000" value is pretty much the result of experimentation
+ * It seems that around this value, things update pretty smoothly
+ */
+#define VESA_UPDATE_TIME 6000
+
+/*
+ * We can map the letters and numbers without a fuss,
+ * but the other characters not so much.
+ */
+static char letters[26] = {
+ 0x1c, 0x32, 0x21, 0x23, 0x24, /* a-e */
+ 0x2b, 0x34, 0x33, 0x43, 0x3b, /* f-j */
+ 0x42, 0x4b, 0x3a, 0x31, 0x44, /* k-o */
+ 0x4d, 0x15, 0x2d, 0x1b, 0x2c, /* p-t */
+ 0x3c, 0x2a, 0x1d, 0x22, 0x35, /* u-y */
+ 0x1a,
+};
+
+static rfbScreenInfoPtr server;
+static char num[10] = {
+ 0x45, 0x16, 0x1e, 0x26, 0x2e, 0x23, 0x36, 0x3d, 0x3e, 0x46,
+};
+
+/*
+ * This is called when the VNC server receives a key event
+ * The reason this function is such a beast is that we have
+ * to convert from ASCII characters (which is what VNC gets)
+ * to PC keyboard scancodes, which is what Linux expects to
+ * get from its keyboard. ASCII and the scancode set don't
+ * really seem to mesh in any good way beyond some basics with
+ * the letters and numbers.
+ */
+static void kbd_handle_key(rfbBool down, rfbKeySym key, rfbClientPtr cl)
+{
+ char tosend = 0;
+
+ if (key >= 0x41 && key <= 0x5a)
+ key += 0x20; /* convert to lowercase */
+
+ if (key >= 0x61 && key <= 0x7a) /* a-z */
+ tosend = letters[key - 0x61];
+
+ if (key >= 0x30 && key <= 0x39)
+ tosend = num[key - 0x30];
+
+ switch (key) {
+ case XK_Insert: kbd_queue(0xe0); tosend = 0x70; break;
+ case XK_Delete: kbd_queue(0xe0); tosend = 0x71; break;
+ case XK_Up: kbd_queue(0xe0); tosend = 0x75; break;
+ case XK_Down: kbd_queue(0xe0); tosend = 0x72; break;
+ case XK_Left: kbd_queue(0xe0); tosend = 0x6b; break;
+ case XK_Right: kbd_queue(0xe0); tosend = 0x74; break;
+ case XK_Page_Up: kbd_queue(0xe0); tosend = 0x7d; break;
+ case XK_Page_Down: kbd_queue(0xe0); tosend = 0x7a; break;
+ case XK_Home: kbd_queue(0xe0); tosend = 0x6c; break;
+ case XK_BackSpace: tosend = 0x66; break;
+ case XK_Tab: tosend = 0x0d; break;
+ case XK_Return: tosend = 0x5a; break;
+ case XK_Escape: tosend = 0x76; break;
+ case XK_End: tosend = 0x69; break;
+ case XK_Shift_L: tosend = 0x12; break;
+ case XK_Shift_R: tosend = 0x59; break;
+ case XK_Control_R: kbd_queue(0xe0);
+ case XK_Control_L: tosend = 0x14; break;
+ case XK_Alt_R: kbd_queue(0xe0);
+ case XK_Alt_L: tosend = 0x11; break;
+ case XK_quoteleft: tosend = 0x0e; break;
+ case XK_minus: tosend = 0x4e; break;
+ case XK_equal: tosend = 0x55; break;
+ case XK_bracketleft: tosend = 0x54; break;
+ case XK_bracketright: tosend = 0x5b; break;
+ case XK_backslash: tosend = 0x5d; break;
+ case XK_Caps_Lock: tosend = 0x58; break;
+ case XK_semicolon: tosend = 0x4c; break;
+ case XK_quoteright: tosend = 0x52; break;
+ case XK_comma: tosend = 0x41; break;
+ case XK_period: tosend = 0x49; break;
+ case XK_slash: tosend = 0x4a; break;
+ case XK_space: tosend = 0x29; break;
+
+ /*
+ * This is where I handle the shifted characters.
+ * They don't really map nicely the way A-Z maps to a-z,
+ * so I'm doing it manually
+ */
+ case XK_exclam: tosend = 0x16; break;
+ case XK_quotedbl: tosend = 0x52; break;
+ case XK_numbersign: tosend = 0x26; break;
+ case XK_dollar: tosend = 0x25; break;
+ case XK_percent: tosend = 0x2e; break;
+ case XK_ampersand: tosend = 0x3d; break;
+ case XK_parenleft: tosend = 0x46; break;
+ case XK_parenright: tosend = 0x45; break;
+ case XK_asterisk: tosend = 0x3e; break;
+ case XK_plus: tosend = 0x55; break;
+ case XK_colon: tosend = 0x4c; break;
+ case XK_less: tosend = 0x41; break;
+ case XK_greater: tosend = 0x49; break;
+ case XK_question: tosend = 0x4a; break;
+ case XK_at: tosend = 0x1e; break;
+ case XK_asciicircum: tosend = 0x36; break;
+ case XK_underscore: tosend = 0x4e; break;
+ case XK_braceleft: tosend = 0x54; break;
+ case XK_braceright: tosend = 0x5b; break;
+ case XK_bar: tosend = 0x5d; break;
+ case XK_asciitilde: tosend = 0x0e; break;
+ default: break;
+ }
+
+ /*
+ * If this is a "key up" event (the user has released the key, we
+ * need to send 0xf0 first.
+ */
+ if (!down && tosend != 0x0)
+ kbd_queue(0xf0);
+
+ if (tosend)
+ kbd_queue(tosend);
+}
+
+/* The previous X and Y coordinates of the mouse */
+static int xlast, ylast = -1;
+
+/*
+ * This function is called by the VNC server whenever a mouse event occurs.
+ */
+static void kbd_handle_ptr(int buttonMask, int x, int y, rfbClientPtr cl)
+{
+ int dx, dy;
+ char b1 = 0x8;
+
+ /* The VNC mask and the PS/2 button encoding are the same */
+ b1 |= buttonMask;
+
+ if (xlast >= 0 && ylast >= 0) {
+ /* The PS/2 mouse sends deltas, not absolutes */
+ dx = x - xlast;
+ dy = ylast - y;
+
+ /* Set overflow bits if needed */
+ if (dy > 255)
+ b1 |= 0x80;
+ if (dx > 255)
+ b1 |= 0x40;
+
+ /* Set negative bits if needed */
+ if (dy < 0)
+ b1 |= 0x20;
+ if (dx < 0)
+ b1 |= 0x10;
+
+ mouse_queue(b1);
+ mouse_queue(dx);
+ mouse_queue(dy);
+ }
+
+ xlast = x;
+ ylast = y;
+ rfbDefaultPtrAddEvent(buttonMask, x, y, cl);
+}
+
+static void *vnc__thread(void *p)
+{
+ struct framebuffer *fb = p;
+ /*
+ * Make a fake argc and argv because the getscreen function
+ * seems to want it.
+ */
+ char argv[1][1] = {{0}};
+ int argc = 1;
+
+ kvm__set_thread_name("kvm-vnc-worker");
+
+ server = rfbGetScreen(&argc, (char **) argv, fb->width, fb->height, 8, 3, 4);
+ server->frameBuffer = fb->mem;
+ server->alwaysShared = TRUE;
+ server->kbdAddEvent = kbd_handle_key;
+ server->ptrAddEvent = kbd_handle_ptr;
+ rfbInitServer(server);
+
+ while (rfbIsActive(server)) {
+ rfbMarkRectAsModified(server, 0, 0, fb->width, fb->height);
+ rfbProcessEvents(server, server->deferUpdateTime * VESA_UPDATE_TIME);
+ }
+ return NULL;
+}
+
+static int vnc__start(struct framebuffer *fb)
+{
+ pthread_t thread;
+
+ if (pthread_create(&thread, NULL, vnc__thread, fb) != 0)
+ return -1;
+
+ return 0;
+}
+
+static int vnc__stop(struct framebuffer *fb)
+{
+ rfbShutdownServer(server, TRUE);
+
+ return 0;
+}
+
+static struct fb_target_operations vnc_ops = {
+ .start = vnc__start,
+ .stop = vnc__stop,
+};
+
+int vnc__init(struct kvm *kvm)
+{
+ struct framebuffer *fb;
+
+ if (!kvm->cfg.vnc)
+ return 0;
+
+ fb = vesa__init(kvm);
+ if (IS_ERR(fb)) {
+ pr_err("vesa__init() failed with error %ld\n", PTR_ERR(fb));
+ return PTR_ERR(fb);
+ }
+
+ return fb__attach(fb, &vnc_ops);
+}
+dev_init(vnc__init);
+
+int vnc__exit(struct kvm *kvm)
+{
+ if (kvm->cfg.vnc)
+ return vnc__stop(NULL);
+
+ return 0;
+}
+dev_exit(vnc__exit);
diff --git a/kvmtool/util/KVMTOOLS-VERSION-GEN b/kvmtool/util/KVMTOOLS-VERSION-GEN
new file mode 100755
index 0000000..91ee2c2
--- /dev/null
+++ b/kvmtool/util/KVMTOOLS-VERSION-GEN
@@ -0,0 +1,39 @@
+#!/bin/sh
+
+if [ $# -eq 1 ] ; then
+ OUTPUT=$1
+fi
+
+GVF=${OUTPUT}KVMTOOLS-VERSION-FILE
+
+LF='
+'
+
+# First check if there is a .git to get the version from git describe
+# otherwise try to get the version from the kernel makefile
+if test -d .git -o -f .git &&
+ VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
+ case "$VN" in
+ *$LF*) (exit 1) ;;
+ v[0-9]*)
+ git update-index -q --refresh
+ test -z "$(git diff-index --name-only HEAD --)" ||
+ VN="$VN-dirty" ;;
+ esac
+then
+ VN=$(echo "$VN" | sed -e 's/-/./g');
+else
+ VN=3.18.0
+fi
+
+VN=$(expr "$VN" : v*'\(.*\)')
+
+if test -r $GVF
+then
+ VC=$(sed -e 's/^KVMTOOLS_VERSION = //' <$GVF)
+else
+ VC=unset
+fi
+test "$VN" = "$VC" || {
+ echo "KVMTOOLS_VERSION = $VN" >$GVF
+}
diff --git a/kvmtool/util/generate-cmdlist.sh b/kvmtool/util/generate-cmdlist.sh
new file mode 100755
index 0000000..c8be0bd
--- /dev/null
+++ b/kvmtool/util/generate-cmdlist.sh
@@ -0,0 +1,23 @@
+#!/bin/sh
+
+echo "/* Automatically generated by $0 */
+struct cmdname_help
+{
+ char name[16];
+ char help[80];
+};
+
+static struct cmdname_help common_cmds[] = {"
+
+sed -n 's/^lkvm-\([^ \t]*\).*common/\1/p' command-list.txt |
+while read cmd
+do
+ # TODO following sed command should be fixed
+ sed -n '/^NAME/,/^lkvm-'"$cmd"'/ {
+ /NAME/d
+ /--/d
+ s/.*kvm-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/
+ p
+ }' "Documentation/kvm-$cmd.txt"
+done
+echo "};"
diff --git a/kvmtool/util/init.c b/kvmtool/util/init.c
new file mode 100644
index 0000000..d4ce144
--- /dev/null
+++ b/kvmtool/util/init.c
@@ -0,0 +1,67 @@
+#include <linux/list.h>
+#include <linux/kernel.h>
+
+#include "kvm/kvm.h"
+#include "kvm/util-init.h"
+
+#define PRIORITY_LISTS 10
+
+static struct hlist_head init_lists[PRIORITY_LISTS];
+static struct hlist_head exit_lists[PRIORITY_LISTS];
+
+int init_list_add(struct init_item *t, int (*init)(struct kvm *),
+ int priority, const char *name)
+{
+ t->init = init;
+ t->fn_name = name;
+ hlist_add_head(&t->n, &init_lists[priority]);
+
+ return 0;
+}
+
+int exit_list_add(struct init_item *t, int (*init)(struct kvm *),
+ int priority, const char *name)
+{
+ t->init = init;
+ t->fn_name = name;
+ hlist_add_head(&t->n, &exit_lists[priority]);
+
+ return 0;
+}
+
+int init_list__init(struct kvm *kvm)
+{
+ unsigned int i;
+ int r = 0;
+ struct init_item *t;
+
+ for (i = 0; i < ARRAY_SIZE(init_lists); i++)
+ hlist_for_each_entry(t, &init_lists[i], n) {
+ r = t->init(kvm);
+ if (r < 0) {
+ pr_warning("Failed init: %s\n", t->fn_name);
+ goto fail;
+ }
+ }
+
+fail:
+ return r;
+}
+
+int init_list__exit(struct kvm *kvm)
+{
+ int i;
+ int r = 0;
+ struct init_item *t;
+
+ for (i = ARRAY_SIZE(exit_lists) - 1; i >= 0; i--)
+ hlist_for_each_entry(t, &exit_lists[i], n) {
+ r = t->init(kvm);
+ if (r < 0) {
+ pr_warning("%s failed.\n", t->fn_name);
+ goto fail;
+ }
+ }
+fail:
+ return r;
+}
diff --git a/kvmtool/util/iovec.c b/kvmtool/util/iovec.c
new file mode 100644
index 0000000..089f105
--- /dev/null
+++ b/kvmtool/util/iovec.c
@@ -0,0 +1,121 @@
+/*
+ * iovec manipulation routines.
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Fixes:
+ * Andrew Lunn : Errors in iovec copying.
+ * Pedro Roque : Added memcpy_fromiovecend and
+ * csum_..._fromiovecend.
+ * Andi Kleen : fixed error handling for 2.1
+ * Alexey Kuznetsov: 2.1 optimisations
+ * Andi Kleen : Fix csum*fromiovecend for IPv6.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <sys/uio.h>
+#include <kvm/iovec.h>
+#include <string.h>
+
+/*
+ * Copy kernel to iovec. Returns -EFAULT on error.
+ *
+ * Note: this modifies the original iovec.
+ */
+
+int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len)
+{
+ while (len > 0) {
+ if (iov->iov_len) {
+ int copy = min_t(unsigned int, iov->iov_len, len);
+ memcpy(iov->iov_base, kdata, copy);
+ kdata += copy;
+ len -= copy;
+ iov->iov_len -= copy;
+ iov->iov_base += copy;
+ }
+ iov++;
+ }
+
+ return 0;
+}
+
+/*
+ * Copy kernel to iovec. Returns -EFAULT on error.
+ */
+
+int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
+ size_t offset, int len)
+{
+ int copy;
+ for (; len > 0; ++iov) {
+ /* Skip over the finished iovecs */
+ if (unlikely(offset >= iov->iov_len)) {
+ offset -= iov->iov_len;
+ continue;
+ }
+ copy = min_t(unsigned int, iov->iov_len - offset, len);
+ memcpy(iov->iov_base + offset, kdata, copy);
+ offset = 0;
+ kdata += copy;
+ len -= copy;
+ }
+
+ return 0;
+}
+
+/*
+ * Copy iovec to kernel. Returns -EFAULT on error.
+ *
+ * Note: this modifies the original iovec.
+ */
+
+int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len)
+{
+ while (len > 0) {
+ if (iov->iov_len) {
+ int copy = min_t(unsigned int, len, iov->iov_len);
+ memcpy(kdata, iov->iov_base, copy);
+ len -= copy;
+ kdata += copy;
+ iov->iov_base += copy;
+ iov->iov_len -= copy;
+ }
+ iov++;
+ }
+
+ return 0;
+}
+
+/*
+ * Copy iovec from kernel. Returns -EFAULT on error.
+ */
+
+int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
+ size_t offset, int len)
+{
+ /* Skip over the finished iovecs */
+ while (offset >= iov->iov_len) {
+ offset -= iov->iov_len;
+ iov++;
+ }
+
+ while (len > 0) {
+ char *base = iov->iov_base + offset;
+ int copy = min_t(unsigned int, len, iov->iov_len - offset);
+
+ offset = 0;
+ memcpy(kdata, base, copy);
+ len -= copy;
+ kdata += copy;
+ iov++;
+ }
+
+ return 0;
+}
diff --git a/kvmtool/util/kvm-ifup-vbr0 b/kvmtool/util/kvm-ifup-vbr0
new file mode 100755
index 0000000..a91c37f
--- /dev/null
+++ b/kvmtool/util/kvm-ifup-vbr0
@@ -0,0 +1,6 @@
+#!/bin/sh
+switch=vbr0
+/sbin/ifconfig $1 0.0.0.0 up
+/usr/sbin/brctl addif ${switch} $1
+/usr/sbin/brctl setfd ${switch} 0
+/usr/sbin/brctl stp ${switch} off
diff --git a/kvmtool/util/parse-options.c b/kvmtool/util/parse-options.c
new file mode 100644
index 0000000..9a1bbee
--- /dev/null
+++ b/kvmtool/util/parse-options.c
@@ -0,0 +1,577 @@
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <stdbool.h>
+
+/* user defined includes */
+#include <linux/types.h>
+#include <kvm/util.h>
+#include <kvm/parse-options.h>
+#include <kvm/strbuf.h>
+
+#define OPT_SHORT 1
+#define OPT_UNSET 2
+
+static int opterror(const struct option *opt, const char *reason, int flags)
+{
+ if (flags & OPT_SHORT)
+ return pr_err("switch `%c' %s", opt->short_name, reason);
+ if (flags & OPT_UNSET)
+ return pr_err("option `no-%s' %s", opt->long_name, reason);
+ return pr_err("option `%s' %s", opt->long_name, reason);
+}
+
+static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt,
+ int flags, const char **arg)
+{
+ if (p->opt) {
+ *arg = p->opt;
+ p->opt = NULL;
+ } else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 ||
+ **(p->argv + 1) == '-')) {
+ *arg = (const char *)opt->defval;
+ } else if (p->argc > 1) {
+ p->argc--;
+ *arg = *++p->argv;
+ } else
+ return opterror(opt, "requires a value", flags);
+ return 0;
+}
+
+static int readnum(const struct option *opt, int flags,
+ const char *str, char **end)
+{
+ switch (opt->type) {
+ case OPTION_INTEGER:
+ *(int *)opt->value = strtol(str, end, 0);
+ break;
+ case OPTION_UINTEGER:
+ *(unsigned int *)opt->value = strtol(str, end, 0);
+ break;
+ case OPTION_LONG:
+ *(long *)opt->value = strtol(str, end, 0);
+ break;
+ case OPTION_U64:
+ *(u64 *)opt->value = strtoull(str, end, 0);
+ break;
+ default:
+ return opterror(opt, "invalid numeric conversion", flags);
+ }
+
+ return 0;
+}
+
+static int get_value(struct parse_opt_ctx_t *p,
+ const struct option *opt, int flags)
+{
+ const char *s, *arg = NULL;
+ const int unset = flags & OPT_UNSET;
+
+ if (unset && p->opt)
+ return opterror(opt, "takes no value", flags);
+ if (unset && (opt->flags & PARSE_OPT_NONEG))
+ return opterror(opt, "isn't available", flags);
+
+ if (!(flags & OPT_SHORT) && p->opt) {
+ switch (opt->type) {
+ case OPTION_CALLBACK:
+ if (!(opt->flags & PARSE_OPT_NOARG))
+ break;
+ /* FALLTHROUGH */
+ case OPTION_BOOLEAN:
+ case OPTION_INCR:
+ case OPTION_BIT:
+ case OPTION_SET_UINT:
+ case OPTION_SET_PTR:
+ return opterror(opt, "takes no value", flags);
+ case OPTION_END:
+ case OPTION_ARGUMENT:
+ case OPTION_GROUP:
+ case OPTION_STRING:
+ case OPTION_INTEGER:
+ case OPTION_UINTEGER:
+ case OPTION_LONG:
+ case OPTION_U64:
+ default:
+ break;
+ }
+ }
+
+ switch (opt->type) {
+ case OPTION_BIT:
+ if (unset)
+ *(int *)opt->value &= ~opt->defval;
+ else
+ *(int *)opt->value |= opt->defval;
+ return 0;
+
+ case OPTION_BOOLEAN:
+ *(bool *)opt->value = unset ? false : true;
+ return 0;
+
+ case OPTION_INCR:
+ *(int *)opt->value = unset ? 0 : *(int *)opt->value + 1;
+ return 0;
+
+ case OPTION_SET_UINT:
+ *(unsigned int *)opt->value = unset ? 0 : opt->defval;
+ return 0;
+
+ case OPTION_SET_PTR:
+ *(void **)opt->value = unset ? NULL : (void *)opt->defval;
+ return 0;
+
+ case OPTION_STRING:
+ if (unset)
+ *(const char **)opt->value = NULL;
+ else if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+ *(const char **)opt->value = (const char *)opt->defval;
+ else
+ return get_arg(p, opt, flags,
+ (const char **)opt->value);
+ return 0;
+
+ case OPTION_CALLBACK:
+ if (unset)
+ return (*opt->callback)(opt, NULL, 1) ? (-1) : 0;
+ if (opt->flags & PARSE_OPT_NOARG)
+ return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+ return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return (*opt->callback)(opt, arg, 0) ? (-1) : 0;
+
+ case OPTION_INTEGER:
+ if (unset) {
+ *(int *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(int *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_UINTEGER:
+ if (unset) {
+ *(unsigned int *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(unsigned int *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_LONG:
+ if (unset) {
+ *(long *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(long *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_U64:
+ if (unset) {
+ *(u64 *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(u64 *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_END:
+ case OPTION_ARGUMENT:
+ case OPTION_GROUP:
+ default:
+ die("should not happen, someone must be hit on the forehead");
+ }
+}
+
+#define USAGE_OPTS_WIDTH 24
+#define USAGE_GAP 2
+
+static int usage_with_options_internal(const char * const *usagestr,
+ const struct option *opts, int full)
+{
+ if (!usagestr)
+ return PARSE_OPT_HELP;
+
+ fprintf(stderr, "\n usage: %s\n", *usagestr++);
+ while (*usagestr && **usagestr)
+ fprintf(stderr, " or: %s\n", *usagestr++);
+ while (*usagestr) {
+ fprintf(stderr, "%s%s\n",
+ **usagestr ? " " : "",
+ *usagestr);
+ usagestr++;
+ }
+
+ if (opts->type != OPTION_GROUP)
+ fputc('\n', stderr);
+
+ for (; opts->type != OPTION_END; opts++) {
+ size_t pos;
+ int pad;
+
+ if (opts->type == OPTION_GROUP) {
+ fputc('\n', stderr);
+ if (*opts->help)
+ fprintf(stderr, "%s\n", opts->help);
+ continue;
+ }
+ if (!full && (opts->flags & PARSE_OPT_HIDDEN))
+ continue;
+
+ pos = fprintf(stderr, " ");
+ if (opts->short_name)
+ pos += fprintf(stderr, "-%c", opts->short_name);
+ else
+ pos += fprintf(stderr, " ");
+
+ if (opts->long_name && opts->short_name)
+ pos += fprintf(stderr, ", ");
+ if (opts->long_name)
+ pos += fprintf(stderr, "--%s", opts->long_name);
+
+ switch (opts->type) {
+ case OPTION_ARGUMENT:
+ break;
+ case OPTION_LONG:
+ case OPTION_U64:
+ case OPTION_INTEGER:
+ case OPTION_UINTEGER:
+ if (opts->flags & PARSE_OPT_OPTARG)
+ if (opts->long_name)
+ pos += fprintf(stderr, "[=<n>]");
+ else
+ pos += fprintf(stderr, "[<n>]");
+ else
+ pos += fprintf(stderr, " <n>");
+ break;
+ case OPTION_CALLBACK:
+ if (opts->flags & PARSE_OPT_NOARG)
+ break;
+ /* FALLTHROUGH */
+ case OPTION_STRING:
+ if (opts->argh) {
+ if (opts->flags & PARSE_OPT_OPTARG)
+ if (opts->long_name)
+ pos += fprintf(stderr, "[=<%s>]", opts->argh);
+ else
+ pos += fprintf(stderr, "[<%s>]", opts->argh);
+ else
+ pos += fprintf(stderr, " <%s>", opts->argh);
+ } else {
+ if (opts->flags & PARSE_OPT_OPTARG)
+ if (opts->long_name)
+ pos += fprintf(stderr, "[=...]");
+ else
+ pos += fprintf(stderr, "[...]");
+ else
+ pos += fprintf(stderr, " ...");
+ }
+ break;
+ default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
+ case OPTION_END:
+ case OPTION_GROUP:
+ case OPTION_BIT:
+ case OPTION_BOOLEAN:
+ case OPTION_INCR:
+ case OPTION_SET_UINT:
+ case OPTION_SET_PTR:
+ break;
+ }
+ if (pos <= USAGE_OPTS_WIDTH)
+ pad = USAGE_OPTS_WIDTH - pos;
+ else {
+ fputc('\n', stderr);
+ pad = USAGE_OPTS_WIDTH;
+ }
+ fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
+ }
+ fputc('\n', stderr);
+
+ return PARSE_OPT_HELP;
+}
+
+void usage_with_options(const char * const *usagestr,
+ const struct option *opts)
+{
+ usage_with_options_internal(usagestr, opts, 0);
+ exit(129);
+}
+
+static void check_typos(const char *arg, const struct option *options)
+{
+ if (strlen(arg) < 3)
+ return;
+
+ if (!prefixcmp(arg, "no-")) {
+ pr_err("did you mean `--%s` (with two dashes ?)", arg);
+ exit(129);
+ }
+
+ for (; options->type != OPTION_END; options++) {
+ if (!options->long_name)
+ continue;
+ if (!prefixcmp(options->long_name, arg)) {
+ pr_err("did you mean `--%s` (with two dashes ?)", arg);
+ exit(129);
+ }
+ }
+}
+
+static int parse_options_usage(const char * const *usagestr,
+ const struct option *opts)
+{
+ return usage_with_options_internal(usagestr, opts, 0);
+}
+
+static int parse_short_opt(struct parse_opt_ctx_t *p,
+ const struct option *options)
+{
+ for (; options->type != OPTION_END; options++) {
+ if (options->short_name == *p->opt) {
+ p->opt = p->opt[1] ? p->opt + 1 : NULL;
+ return get_value(p, options, OPT_SHORT);
+ }
+ }
+ return -2;
+}
+
+static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
+ const struct option *options)
+{
+ const char *arg_end = strchr(arg, '=');
+ const struct option *abbrev_option = NULL, *ambiguous_option = NULL;
+ int abbrev_flags = 0, ambiguous_flags = 0;
+
+ if (!arg_end)
+ arg_end = arg + strlen(arg);
+
+ for (; options->type != OPTION_END; options++) {
+ const char *rest;
+ int flags = 0;
+
+ if (!options->long_name)
+ continue;
+
+ rest = skip_prefix(arg, options->long_name);
+ if (options->type == OPTION_ARGUMENT) {
+ if (!rest)
+ continue;
+ if (*rest == '=')
+ return opterror(options, "takes no value",
+ flags);
+ if (*rest)
+ continue;
+ p->out[p->cpidx++] = arg - 2;
+ return 0;
+ }
+ if (!rest) {
+ /* abbreviated? */
+ if (!strncmp(options->long_name, arg, arg_end - arg)) {
+is_abbreviated:
+ if (abbrev_option) {
+ /*
+ * If this is abbreviated, it is
+ * ambiguous. So when there is no
+ * exact match later, we need to
+ * error out.
+ */
+ ambiguous_option = abbrev_option;
+ ambiguous_flags = abbrev_flags;
+ }
+ if (!(flags & OPT_UNSET) && *arg_end)
+ p->opt = arg_end + 1;
+ abbrev_option = options;
+ abbrev_flags = flags;
+ continue;
+ }
+ /* negated and abbreviated very much? */
+ if (!prefixcmp("no-", arg)) {
+ flags |= OPT_UNSET;
+ goto is_abbreviated;
+ }
+ /* negated? */
+ if (strncmp(arg, "no-", 3))
+ continue;
+ flags |= OPT_UNSET;
+ rest = skip_prefix(arg + 3, options->long_name);
+ /* abbreviated and negated? */
+ if (!rest && !prefixcmp(options->long_name, arg + 3))
+ goto is_abbreviated;
+ if (!rest)
+ continue;
+ }
+ if (*rest) {
+ if (*rest != '=')
+ continue;
+ p->opt = rest + 1;
+ }
+ return get_value(p, options, flags);
+ }
+
+ if (ambiguous_option)
+ return pr_err("Ambiguous option: %s "
+ "(could be --%s%s or --%s%s)",
+ arg,
+ (ambiguous_flags & OPT_UNSET) ? "no-" : "",
+ ambiguous_option->long_name,
+ (abbrev_flags & OPT_UNSET) ? "no-" : "",
+ abbrev_option->long_name);
+ if (abbrev_option)
+ return get_value(p, abbrev_option, abbrev_flags);
+ return -2;
+}
+
+
+static void parse_options_start(struct parse_opt_ctx_t *ctx, int argc,
+ const char **argv, int flags)
+{
+ memset(ctx, 0, sizeof(*ctx));
+ ctx->argc = argc;
+ ctx->argv = argv;
+ ctx->out = argv;
+ ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0);
+ ctx->flags = flags;
+ if ((flags & PARSE_OPT_KEEP_UNKNOWN) &&
+ (flags & PARSE_OPT_STOP_AT_NON_OPTION))
+ die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together");
+}
+
+static int parse_options_end(struct parse_opt_ctx_t *ctx)
+{
+ memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out));
+ ctx->out[ctx->cpidx + ctx->argc] = NULL;
+ return ctx->cpidx + ctx->argc;
+}
+
+
+static int parse_options_step(struct parse_opt_ctx_t *ctx,
+ const struct option *options, const char * const usagestr[])
+{
+ int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
+
+ /* we must reset ->opt, unknown short option leave it dangling */
+ ctx->opt = NULL;
+
+ for (; ctx->argc; ctx->argc--, ctx->argv++) {
+ const char *arg = ctx->argv[0];
+
+ if (*arg != '-' || !arg[1]) {
+ if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
+ break;
+ ctx->out[ctx->cpidx++] = ctx->argv[0];
+ continue;
+ }
+
+ if (arg[1] != '-') {
+ ctx->opt = arg + 1;
+ if (internal_help && *ctx->opt == 'h')
+ return parse_options_usage(usagestr, options);
+ switch (parse_short_opt(ctx, options)) {
+ case -1:
+ return parse_options_usage(usagestr, options);
+ case -2:
+ goto unknown;
+ default:
+ break;
+ }
+ if (ctx->opt)
+ check_typos(arg + 1, options);
+ while (ctx->opt) {
+ if (internal_help && *ctx->opt == 'h')
+ return parse_options_usage(usagestr,
+ options);
+ switch (parse_short_opt(ctx, options)) {
+ case -1:
+ return parse_options_usage(usagestr,
+ options);
+ case -2:
+ /* fake a short option thing to hide
+ * the fact that we may have
+ * started to parse aggregated stuff
+ *
+ * This is leaky, too bad.
+ */
+ ctx->argv[0] = strdup(ctx->opt - 1);
+ *(char *)ctx->argv[0] = '-';
+ goto unknown;
+ default:
+ break;
+ }
+ }
+ continue;
+ }
+
+ if (!arg[2]) { /* "--" */
+ if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) {
+ ctx->argc--;
+ ctx->argv++;
+ }
+ break;
+ }
+
+ if (internal_help && !strcmp(arg + 2, "help-all"))
+ return usage_with_options_internal(usagestr, options,
+ 1);
+ if (internal_help && !strcmp(arg + 2, "help"))
+ return parse_options_usage(usagestr, options);
+ switch (parse_long_opt(ctx, arg + 2, options)) {
+ case -1:
+ return parse_options_usage(usagestr, options);
+ case -2:
+ goto unknown;
+ default:
+ break;
+ }
+ continue;
+unknown:
+ if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN))
+ return PARSE_OPT_UNKNOWN;
+ ctx->out[ctx->cpidx++] = ctx->argv[0];
+ ctx->opt = NULL;
+ }
+ return PARSE_OPT_DONE;
+}
+
+int parse_options(int argc, const char **argv, const struct option *options,
+ const char * const usagestr[], int flags)
+{
+ struct parse_opt_ctx_t ctx;
+
+ parse_options_start(&ctx, argc, argv, flags);
+ switch (parse_options_step(&ctx, options, usagestr)) {
+ case PARSE_OPT_HELP:
+ exit(129);
+ case PARSE_OPT_DONE:
+ break;
+ default: /* PARSE_OPT_UNKNOWN */
+ if (ctx.argv[0][1] == '-') {
+ pr_err("unknown option `%s'", ctx.argv[0] + 2);
+ } else {
+ pr_err("unknown switch `%c'", *ctx.opt);
+ }
+ usage_with_options(usagestr, options);
+ }
+
+ return parse_options_end(&ctx);
+}
diff --git a/kvmtool/util/rbtree-interval.c b/kvmtool/util/rbtree-interval.c
new file mode 100644
index 0000000..3630a6d
--- /dev/null
+++ b/kvmtool/util/rbtree-interval.c
@@ -0,0 +1,58 @@
+#include <kvm/rbtree-interval.h>
+#include <stddef.h>
+#include <errno.h>
+
+struct rb_int_node *rb_int_search_single(struct rb_root *root, u64 point)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct rb_int_node *cur = rb_int(node);
+
+ if (point < cur->low)
+ node = node->rb_left;
+ else if (cur->high <= point)
+ node = node->rb_right;
+ else
+ return cur;
+ }
+
+ return NULL;
+}
+
+struct rb_int_node *rb_int_search_range(struct rb_root *root, u64 low, u64 high)
+{
+ struct rb_int_node *range;
+
+ range = rb_int_search_single(root, low);
+ if (range == NULL)
+ return NULL;
+
+ /* We simply verify that 'high' is smaller than the end of the range where 'low' is located */
+ if (range->high < high)
+ return NULL;
+
+ return range;
+}
+
+int rb_int_insert(struct rb_root *root, struct rb_int_node *i_node)
+{
+ struct rb_node **node = &root->rb_node, *parent = NULL;
+
+ while (*node) {
+ struct rb_int_node *cur = rb_int(*node);
+
+ parent = *node;
+ if (i_node->high <= cur->low)
+ node = &cur->node.rb_left;
+ else if (cur->high <= i_node->low)
+ node = &cur->node.rb_right;
+ else
+ return -EEXIST;
+ }
+
+ rb_link_node(&i_node->node, parent, node);
+ rb_insert_color(&i_node->node, root);
+
+ return 0;
+}
diff --git a/kvmtool/util/rbtree.c b/kvmtool/util/rbtree.c
new file mode 100644
index 0000000..9c2dedb
--- /dev/null
+++ b/kvmtool/util/rbtree.c
@@ -0,0 +1,548 @@
+/*
+ Red Black Trees
+ (C) 1999 Andrea Arcangeli <andrea@suse.de>
+ (C) 2002 David Woodhouse <dwmw2@infradead.org>
+ (C) 2012 Michel Lespinasse <walken@google.com>
+
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 2 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, write to the Free Software
+ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+
+ linux/lib/rbtree.c
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * red-black trees properties: http://en.wikipedia.org/wiki/Rbtree
+ *
+ * 1) A node is either red or black
+ * 2) The root is black
+ * 3) All leaves (NULL) are black
+ * 4) Both children of every red node are black
+ * 5) Every simple path from root to leaves contains the same number
+ * of black nodes.
+ *
+ * 4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two
+ * consecutive red nodes in a path and every red node is therefore followed by
+ * a black. So if B is the number of black nodes on every simple path (as per
+ * 5), then the longest possible path due to 4 is 2B.
+ *
+ * We shall indicate color with case, where black nodes are uppercase and red
+ * nodes will be lowercase. Unknown color nodes shall be drawn as red within
+ * parentheses and have some accompanying text comment.
+ */
+
+static inline void rb_set_black(struct rb_node *rb)
+{
+ rb->__rb_parent_color |= RB_BLACK;
+}
+
+static inline struct rb_node *rb_red_parent(struct rb_node *red)
+{
+ return (struct rb_node *)red->__rb_parent_color;
+}
+
+/*
+ * Helper function for rotations:
+ * - old's parent and color get assigned to new
+ * - old gets assigned new as a parent and 'color' as a color.
+ */
+static inline void
+__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
+ struct rb_root *root, int color)
+{
+ struct rb_node *parent = rb_parent(old);
+ new->__rb_parent_color = old->__rb_parent_color;
+ rb_set_parent_color(old, new, color);
+ __rb_change_child(old, new, parent, root);
+}
+
+static __always_inline void
+__rb_insert(struct rb_node *node, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+
+ while (true) {
+ /*
+ * Loop invariant: node is red
+ *
+ * If there is a black parent, we are done.
+ * Otherwise, take some corrective action as we don't
+ * want a red root or two consecutive red nodes.
+ */
+ if (!parent) {
+ rb_set_parent_color(node, NULL, RB_BLACK);
+ break;
+ } else if (rb_is_black(parent))
+ break;
+
+ gparent = rb_red_parent(parent);
+
+ tmp = gparent->rb_right;
+ if (parent != tmp) { /* parent == gparent->rb_left */
+ if (tmp && rb_is_red(tmp)) {
+ /*
+ * Case 1 - color flips
+ *
+ * G g
+ * / \ / \
+ * p u --> P U
+ * / /
+ * n n
+ *
+ * However, since g's parent might be red, and
+ * 4) does not allow this, we need to recurse
+ * at g.
+ */
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ rb_set_parent_color(parent, gparent, RB_BLACK);
+ node = gparent;
+ parent = rb_parent(node);
+ rb_set_parent_color(node, parent, RB_RED);
+ continue;
+ }
+
+ tmp = parent->rb_right;
+ if (node == tmp) {
+ /*
+ * Case 2 - left rotate at parent
+ *
+ * G G
+ * / \ / \
+ * p U --> n U
+ * \ /
+ * n p
+ *
+ * This still leaves us in violation of 4), the
+ * continuation into Case 3 will fix that.
+ */
+ parent->rb_right = tmp = node->rb_left;
+ node->rb_left = parent;
+ if (tmp)
+ rb_set_parent_color(tmp, parent,
+ RB_BLACK);
+ rb_set_parent_color(parent, node, RB_RED);
+ augment_rotate(parent, node);
+ parent = node;
+ tmp = node->rb_right;
+ }
+
+ /*
+ * Case 3 - right rotate at gparent
+ *
+ * G P
+ * / \ / \
+ * p U --> n g
+ * / \
+ * n U
+ */
+ gparent->rb_left = tmp; /* == parent->rb_right */
+ parent->rb_right = gparent;
+ if (tmp)
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ __rb_rotate_set_parents(gparent, parent, root, RB_RED);
+ augment_rotate(gparent, parent);
+ break;
+ } else {
+ tmp = gparent->rb_left;
+ if (tmp && rb_is_red(tmp)) {
+ /* Case 1 - color flips */
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ rb_set_parent_color(parent, gparent, RB_BLACK);
+ node = gparent;
+ parent = rb_parent(node);
+ rb_set_parent_color(node, parent, RB_RED);
+ continue;
+ }
+
+ tmp = parent->rb_left;
+ if (node == tmp) {
+ /* Case 2 - right rotate at parent */
+ parent->rb_left = tmp = node->rb_right;
+ node->rb_right = parent;
+ if (tmp)
+ rb_set_parent_color(tmp, parent,
+ RB_BLACK);
+ rb_set_parent_color(parent, node, RB_RED);
+ augment_rotate(parent, node);
+ parent = node;
+ tmp = node->rb_left;
+ }
+
+ /* Case 3 - left rotate at gparent */
+ gparent->rb_right = tmp; /* == parent->rb_left */
+ parent->rb_left = gparent;
+ if (tmp)
+ rb_set_parent_color(tmp, gparent, RB_BLACK);
+ __rb_rotate_set_parents(gparent, parent, root, RB_RED);
+ augment_rotate(gparent, parent);
+ break;
+ }
+ }
+}
+
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
+
+ while (true) {
+ /*
+ * Loop invariants:
+ * - node is black (or NULL on first iteration)
+ * - node is not the root (parent is not NULL)
+ * - All leaf paths going through parent and node have a
+ * black node count that is 1 lower than other leaf paths.
+ */
+ sibling = parent->rb_right;
+ if (node != sibling) { /* node == parent->rb_left */
+ if (rb_is_red(sibling)) {
+ /*
+ * Case 1 - left rotate at parent
+ *
+ * P S
+ * / \ / \
+ * N s --> p Sr
+ * / \ / \
+ * Sl Sr N Sl
+ */
+ parent->rb_right = tmp1 = sibling->rb_left;
+ sibling->rb_left = parent;
+ rb_set_parent_color(tmp1, parent, RB_BLACK);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_RED);
+ augment_rotate(parent, sibling);
+ sibling = tmp1;
+ }
+ tmp1 = sibling->rb_right;
+ if (!tmp1 || rb_is_black(tmp1)) {
+ tmp2 = sibling->rb_left;
+ if (!tmp2 || rb_is_black(tmp2)) {
+ /*
+ * Case 2 - sibling color flip
+ * (p could be either color here)
+ *
+ * (p) (p)
+ * / \ / \
+ * N S --> N s
+ * / \ / \
+ * Sl Sr Sl Sr
+ *
+ * This leaves us violating 5) which
+ * can be fixed by flipping p to black
+ * if it was red, or by recursing at p.
+ * p is red when coming from Case 1.
+ */
+ rb_set_parent_color(sibling, parent,
+ RB_RED);
+ if (rb_is_red(parent))
+ rb_set_black(parent);
+ else {
+ node = parent;
+ parent = rb_parent(node);
+ if (parent)
+ continue;
+ }
+ break;
+ }
+ /*
+ * Case 3 - right rotate at sibling
+ * (p could be either color here)
+ *
+ * (p) (p)
+ * / \ / \
+ * N S --> N Sl
+ * / \ \
+ * sl Sr s
+ * \
+ * Sr
+ */
+ sibling->rb_left = tmp1 = tmp2->rb_right;
+ tmp2->rb_right = sibling;
+ parent->rb_right = tmp2;
+ if (tmp1)
+ rb_set_parent_color(tmp1, sibling,
+ RB_BLACK);
+ augment_rotate(sibling, tmp2);
+ tmp1 = sibling;
+ sibling = tmp2;
+ }
+ /*
+ * Case 4 - left rotate at parent + color flips
+ * (p and sl could be either color here.
+ * After rotation, p becomes black, s acquires
+ * p's color, and sl keeps its color)
+ *
+ * (p) (s)
+ * / \ / \
+ * N S --> P Sr
+ * / \ / \
+ * (sl) sr N (sl)
+ */
+ parent->rb_right = tmp2 = sibling->rb_left;
+ sibling->rb_left = parent;
+ rb_set_parent_color(tmp1, sibling, RB_BLACK);
+ if (tmp2)
+ rb_set_parent(tmp2, parent);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_BLACK);
+ augment_rotate(parent, sibling);
+ break;
+ } else {
+ sibling = parent->rb_left;
+ if (rb_is_red(sibling)) {
+ /* Case 1 - right rotate at parent */
+ parent->rb_left = tmp1 = sibling->rb_right;
+ sibling->rb_right = parent;
+ rb_set_parent_color(tmp1, parent, RB_BLACK);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_RED);
+ augment_rotate(parent, sibling);
+ sibling = tmp1;
+ }
+ tmp1 = sibling->rb_left;
+ if (!tmp1 || rb_is_black(tmp1)) {
+ tmp2 = sibling->rb_right;
+ if (!tmp2 || rb_is_black(tmp2)) {
+ /* Case 2 - sibling color flip */
+ rb_set_parent_color(sibling, parent,
+ RB_RED);
+ if (rb_is_red(parent))
+ rb_set_black(parent);
+ else {
+ node = parent;
+ parent = rb_parent(node);
+ if (parent)
+ continue;
+ }
+ break;
+ }
+ /* Case 3 - right rotate at sibling */
+ sibling->rb_right = tmp1 = tmp2->rb_left;
+ tmp2->rb_left = sibling;
+ parent->rb_left = tmp2;
+ if (tmp1)
+ rb_set_parent_color(tmp1, sibling,
+ RB_BLACK);
+ augment_rotate(sibling, tmp2);
+ tmp1 = sibling;
+ sibling = tmp2;
+ }
+ /* Case 4 - left rotate at parent + color flips */
+ parent->rb_left = tmp2 = sibling->rb_right;
+ sibling->rb_right = parent;
+ rb_set_parent_color(tmp1, sibling, RB_BLACK);
+ if (tmp2)
+ rb_set_parent(tmp2, parent);
+ __rb_rotate_set_parents(parent, sibling, root,
+ RB_BLACK);
+ augment_rotate(parent, sibling);
+ break;
+ }
+ }
+}
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ ____rb_erase_color(parent, root, augment_rotate);
+}
+
+/*
+ * Non-augmented rbtree manipulation functions.
+ *
+ * We use dummy augmented callbacks here, and have the compiler optimize them
+ * out of the rb_insert_color() and rb_erase() function definitions.
+ */
+
+static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {}
+static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
+static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
+
+static const struct rb_augment_callbacks dummy_callbacks = {
+ dummy_propagate, dummy_copy, dummy_rotate
+};
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+ __rb_insert(node, root, dummy_rotate);
+}
+
+void rb_erase(struct rb_node *node, struct rb_root *root)
+{
+ struct rb_node *rebalance;
+ rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+ if (rebalance)
+ ____rb_erase_color(rebalance, root, dummy_rotate);
+}
+
+/*
+ * Augmented rbtree manipulation functions.
+ *
+ * This instantiates the same __always_inline functions as in the non-augmented
+ * case, but this time with user-defined callbacks.
+ */
+
+void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+ void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+ __rb_insert(node, root, augment_rotate);
+}
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(const struct rb_root *root)
+{
+ struct rb_node *n;
+
+ n = root->rb_node;
+ if (!n)
+ return NULL;
+ while (n->rb_left)
+ n = n->rb_left;
+ return n;
+}
+
+struct rb_node *rb_last(const struct rb_root *root)
+{
+ struct rb_node *n;
+
+ n = root->rb_node;
+ if (!n)
+ return NULL;
+ while (n->rb_right)
+ n = n->rb_right;
+ return n;
+}
+
+struct rb_node *rb_next(const struct rb_node *node)
+{
+ struct rb_node *parent;
+
+ if (RB_EMPTY_NODE(node))
+ return NULL;
+
+ /*
+ * If we have a right-hand child, go down and then left as far
+ * as we can.
+ */
+ if (node->rb_right) {
+ node = node->rb_right;
+ while (node->rb_left)
+ node=node->rb_left;
+ return (struct rb_node *)node;
+ }
+
+ /*
+ * No right-hand children. Everything down and left is smaller than us,
+ * so any 'next' node must be in the general direction of our parent.
+ * Go up the tree; any time the ancestor is a right-hand child of its
+ * parent, keep going up. First time it's a left-hand child of its
+ * parent, said parent is our 'next' node.
+ */
+ while ((parent = rb_parent(node)) && node == parent->rb_right)
+ node = parent;
+
+ return parent;
+}
+
+struct rb_node *rb_prev(const struct rb_node *node)
+{
+ struct rb_node *parent;
+
+ if (RB_EMPTY_NODE(node))
+ return NULL;
+
+ /*
+ * If we have a left-hand child, go down and then right as far
+ * as we can.
+ */
+ if (node->rb_left) {
+ node = node->rb_left;
+ while (node->rb_right)
+ node=node->rb_right;
+ return (struct rb_node *)node;
+ }
+
+ /*
+ * No left-hand children. Go up till we find an ancestor which
+ * is a right-hand child of its parent.
+ */
+ while ((parent = rb_parent(node)) && node == parent->rb_left)
+ node = parent;
+
+ return parent;
+}
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+ struct rb_root *root)
+{
+ struct rb_node *parent = rb_parent(victim);
+
+ /* Set the surrounding nodes to point to the replacement */
+ __rb_change_child(victim, new, parent, root);
+ if (victim->rb_left)
+ rb_set_parent(victim->rb_left, new);
+ if (victim->rb_right)
+ rb_set_parent(victim->rb_right, new);
+
+ /* Copy the pointers/colour from the victim to the replacement */
+ *new = *victim;
+}
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+ for (;;) {
+ if (node->rb_left)
+ node = node->rb_left;
+ else if (node->rb_right)
+ node = node->rb_right;
+ else
+ return (struct rb_node *)node;
+ }
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+ const struct rb_node *parent;
+ if (!node)
+ return NULL;
+ parent = rb_parent(node);
+
+ /* If we're sitting on node, we've already seen our children */
+ if (parent && node == parent->rb_left && parent->rb_right) {
+ /* If we are the parent's left node, go to the parent's right
+ * node then all the way down to the left */
+ return rb_left_deepest_node(parent->rb_right);
+ } else
+ /* Otherwise we are the parent's right node, and the parent
+ * should be next */
+ return (struct rb_node *)parent;
+}
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+ if (!root->rb_node)
+ return NULL;
+
+ return rb_left_deepest_node(root->rb_node);
+}
diff --git a/kvmtool/util/read-write.c b/kvmtool/util/read-write.c
new file mode 100644
index 0000000..06fc0df
--- /dev/null
+++ b/kvmtool/util/read-write.c
@@ -0,0 +1,339 @@
+#include "kvm/read-write.h"
+
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+
+/* Same as read(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xread(int fd, void *buf, size_t count)
+{
+ ssize_t nr;
+
+restart:
+ nr = read(fd, buf, count);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as write(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xwrite(int fd, const void *buf, size_t count)
+{
+ ssize_t nr;
+
+restart:
+ nr = write(fd, buf, count);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/*
+ * Read in the whole file while not exceeding max_size bytes of the buffer.
+ * Returns -1 (with errno set) in case of an error (ENOMEM if buffer was
+ * too small) or the filesize if the whole file could be read.
+ */
+ssize_t read_file(int fd, char *buf, size_t max_size)
+{
+ ssize_t ret;
+ char dummy;
+
+ errno = 0;
+ ret = read_in_full(fd, buf, max_size);
+
+ /* Probe whether we reached EOF. */
+ if (xread(fd, &dummy, 1) == 0)
+ return ret;
+
+ errno = ENOMEM;
+ return -1;
+}
+
+ssize_t read_in_full(int fd, void *buf, size_t count)
+{
+ ssize_t total = 0;
+ char *p = buf;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xread(fd, p, count);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ count -= nr;
+ total += nr;
+ p += nr;
+ }
+
+ return total;
+}
+
+ssize_t write_in_full(int fd, const void *buf, size_t count)
+{
+ const char *p = buf;
+ ssize_t total = 0;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xwrite(fd, p, count);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+ count -= nr;
+ total += nr;
+ p += nr;
+ }
+
+ return total;
+}
+
+/* Same as pread(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpread(int fd, void *buf, size_t count, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = pread(fd, buf, count, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as pwrite(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpwrite(int fd, const void *buf, size_t count, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = pwrite(fd, buf, count, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+ssize_t pread_in_full(int fd, void *buf, size_t count, off_t offset)
+{
+ ssize_t total = 0;
+ char *p = buf;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpread(fd, p, count, offset);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ count -= nr;
+ total += nr;
+ p += nr;
+ offset += nr;
+ }
+
+ return total;
+}
+
+ssize_t pwrite_in_full(int fd, const void *buf, size_t count, off_t offset)
+{
+ const char *p = buf;
+ ssize_t total = 0;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpwrite(fd, p, count, offset);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+ count -= nr;
+ total += nr;
+ p += nr;
+ offset += nr;
+ }
+
+ return total;
+}
+
+/* Same as readv(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xreadv(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t nr;
+
+restart:
+ nr = readv(fd, iov, iovcnt);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as writev(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xwritev(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t nr;
+
+restart:
+ nr = writev(fd, iov, iovcnt);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+static inline ssize_t get_iov_size(const struct iovec *iov, int iovcnt)
+{
+ size_t size = 0;
+ while (iovcnt--)
+ size += (iov++)->iov_len;
+
+ return size;
+}
+
+static inline void shift_iovec(const struct iovec **iov, int *iovcnt,
+ size_t nr, ssize_t *total, size_t *count, off_t *offset)
+{
+ while (nr >= (*iov)->iov_len) {
+ nr -= (*iov)->iov_len;
+ *total += (*iov)->iov_len;
+ *count -= (*iov)->iov_len;
+ if (offset)
+ *offset += (*iov)->iov_len;
+ (*iovcnt)--;
+ (*iov)++;
+ }
+}
+
+ssize_t readv_in_full(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xreadv(fd, iov, iovcnt);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, NULL);
+ }
+
+ return total;
+}
+
+ssize_t writev_in_full(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xwritev(fd, iov, iovcnt);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, NULL);
+ }
+
+ return total;
+}
+
+/* Same as preadv(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpreadv(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = preadv(fd, iov, iovcnt, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as pwritev(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = pwritev(fd, iov, iovcnt, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+ssize_t preadv_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpreadv(fd, iov, iovcnt, offset);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, &offset);
+ }
+
+ return total;
+}
+
+ssize_t pwritev_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpwritev(fd, iov, iovcnt, offset);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, &offset);
+ }
+
+ return total;
+}
diff --git a/kvmtool/util/set_private_br.sh b/kvmtool/util/set_private_br.sh
new file mode 100755
index 0000000..49867dd
--- /dev/null
+++ b/kvmtool/util/set_private_br.sh
@@ -0,0 +1,51 @@
+#!/bin/bash
+#
+# Author: Amos Kong <kongjianjun@gmail.com>
+# Date: Apr 14, 2011
+# Description: this script is used to create/delete a private bridge,
+# launch a dhcp server on the bridge by dnsmasq.
+#
+# @ ./set_private_br.sh $bridge_name $subnet_prefix
+# @ ./set_private_br.sh vbr0 192.168.33
+
+brname='vbr0'
+subnet='192.168.33'
+
+add_br()
+{
+ echo "add new private bridge: $brname"
+ /usr/sbin/brctl addbr $brname
+ echo 1 > /proc/sys/net/ipv6/conf/$brname/disable_ipv6
+ echo 1 > /proc/sys/net/ipv4/ip_forward
+ /usr/sbin/brctl stp $brname on
+ /usr/sbin/brctl setfd $brname 0
+ ifconfig $brname $subnet.1
+ ifconfig $brname up
+ # Add forward rule, then guest can access public network
+ iptables -t nat -A POSTROUTING -s $subnet.254/24 ! -d $subnet.254/24 -j MASQUERADE
+ /etc/init.d/dnsmasq stop
+ /etc/init.d/tftpd-hpa stop 2>/dev/null
+ dnsmasq --strict-order --bind-interfaces --listen-address $subnet.1 --dhcp-range $subnet.1,$subnet.254 $tftp_cmd
+}
+
+del_br()
+{
+ echo "cleanup bridge setup"
+ kill -9 `pgrep dnsmasq|tail -1`
+ ifconfig $brname down
+ /usr/sbin/brctl delbr $brname
+ iptables -t nat -D POSTROUTING -s $subnet.254/24 ! -d $subnet.254/24 -j MASQUERADE
+}
+
+
+if [ $# = 0 ]; then
+ del_br 2>/dev/null
+ exit
+fi
+if [ $# > 1 ]; then
+ brname="$1"
+fi
+if [ $# = 2 ]; then
+ subnet="$2"
+fi
+add_br
diff --git a/kvmtool/util/strbuf.c b/kvmtool/util/strbuf.c
new file mode 100644
index 0000000..2c6e8ad
--- /dev/null
+++ b/kvmtool/util/strbuf.c
@@ -0,0 +1,64 @@
+
+/* user defined headers */
+#include <kvm/util.h>
+#include <kvm/strbuf.h>
+
+int prefixcmp(const char *str, const char *prefix)
+{
+ for (; ; str++, prefix++) {
+ if (!*prefix)
+ return 0;
+ else if (*str != *prefix)
+ return (unsigned char)*prefix - (unsigned char)*str;
+ }
+}
+
+#ifndef HAVE_STRLCPY
+/**
+ * strlcat - Append a length-limited, %NUL-terminated string to another
+ * @dest: The string to be appended to
+ * @src: The string to append to it
+ * @count: The size of the destination buffer.
+ */
+size_t strlcat(char *dest, const char *src, size_t count)
+{
+ size_t dsize = strlen(dest);
+ size_t len = strlen(src);
+ size_t res = dsize + len;
+
+ DIE_IF(dsize >= count);
+
+ dest += dsize;
+ count -= dsize;
+ if (len >= count)
+ len = count - 1;
+
+ memcpy(dest, src, len);
+ dest[len] = 0;
+
+ return res;
+}
+
+/**
+ * strlcpy - Copy a %NUL terminated string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @size: size of destination buffer
+ *
+ * Compatible with *BSD: the result is always a valid
+ * NUL-terminated string that fits in the buffer (unless,
+ * of course, the buffer size is zero). It does not pad
+ * out the result like strncpy() does.
+ */
+size_t strlcpy(char *dest, const char *src, size_t size)
+{
+ size_t ret = strlen(src);
+
+ if (size) {
+ size_t len = (ret >= size) ? size - 1 : ret;
+ memcpy(dest, src, len);
+ dest[len] = '\0';
+ }
+ return ret;
+}
+#endif
diff --git a/kvmtool/util/threadpool.c b/kvmtool/util/threadpool.c
new file mode 100644
index 0000000..1dc3bf7
--- /dev/null
+++ b/kvmtool/util/threadpool.c
@@ -0,0 +1,198 @@
+#include "kvm/threadpool.h"
+#include "kvm/mutex.h"
+#include "kvm/kvm.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <pthread.h>
+#include <stdbool.h>
+
+static DEFINE_MUTEX(job_mutex);
+static DEFINE_MUTEX(thread_mutex);
+static pthread_cond_t job_cond = PTHREAD_COND_INITIALIZER;
+
+static LIST_HEAD(head);
+
+static pthread_t *threads;
+static long threadcount;
+static bool running;
+
+static struct thread_pool__job *thread_pool__job_pop_locked(void)
+{
+ struct thread_pool__job *job;
+
+ if (list_empty(&head))
+ return NULL;
+
+ job = list_first_entry(&head, struct thread_pool__job, queue);
+ list_del_init(&job->queue);
+
+ return job;
+}
+
+static void thread_pool__job_push_locked(struct thread_pool__job *job)
+{
+ list_add_tail(&job->queue, &head);
+}
+
+static struct thread_pool__job *thread_pool__job_pop(void)
+{
+ struct thread_pool__job *job;
+
+ mutex_lock(&job_mutex);
+ job = thread_pool__job_pop_locked();
+ mutex_unlock(&job_mutex);
+ return job;
+}
+
+static void thread_pool__job_push(struct thread_pool__job *job)
+{
+ mutex_lock(&job_mutex);
+ thread_pool__job_push_locked(job);
+ mutex_unlock(&job_mutex);
+}
+
+static void thread_pool__handle_job(struct thread_pool__job *job)
+{
+ while (job) {
+ job->callback(job->kvm, job->data);
+
+ mutex_lock(&job->mutex);
+
+ if (--job->signalcount > 0)
+ /* If the job was signaled again while we were working */
+ thread_pool__job_push(job);
+
+ mutex_unlock(&job->mutex);
+
+ job = thread_pool__job_pop();
+ }
+}
+
+static void thread_pool__threadfunc_cleanup(void *param)
+{
+ mutex_unlock(&job_mutex);
+}
+
+static void *thread_pool__threadfunc(void *param)
+{
+ pthread_cleanup_push(thread_pool__threadfunc_cleanup, NULL);
+
+ kvm__set_thread_name("threadpool-worker");
+
+ while (running) {
+ struct thread_pool__job *curjob = NULL;
+
+ mutex_lock(&job_mutex);
+ while (running && (curjob = thread_pool__job_pop_locked()) == NULL)
+ pthread_cond_wait(&job_cond, &job_mutex.mutex);
+ mutex_unlock(&job_mutex);
+
+ if (running)
+ thread_pool__handle_job(curjob);
+ }
+
+ pthread_cleanup_pop(0);
+
+ return NULL;
+}
+
+static int thread_pool__addthread(void)
+{
+ int res;
+ void *newthreads;
+
+ mutex_lock(&thread_mutex);
+ newthreads = realloc(threads, (threadcount + 1) * sizeof(pthread_t));
+ if (newthreads == NULL) {
+ mutex_unlock(&thread_mutex);
+ return -1;
+ }
+
+ threads = newthreads;
+
+ res = pthread_create(threads + threadcount, NULL,
+ thread_pool__threadfunc, NULL);
+
+ if (res == 0)
+ threadcount++;
+ mutex_unlock(&thread_mutex);
+
+ return res;
+}
+
+int thread_pool__init(struct kvm *kvm)
+{
+ unsigned long i;
+ unsigned int thread_count = sysconf(_SC_NPROCESSORS_ONLN);
+
+ running = true;
+
+ for (i = 0; i < thread_count; i++)
+ if (thread_pool__addthread() < 0)
+ return i;
+
+ return i;
+}
+late_init(thread_pool__init);
+
+int thread_pool__exit(struct kvm *kvm)
+{
+ int i;
+ void *NUL = NULL;
+
+ running = false;
+
+ for (i = 0; i < threadcount; i++) {
+ mutex_lock(&job_mutex);
+ pthread_cond_signal(&job_cond);
+ mutex_unlock(&job_mutex);
+ }
+
+ for (i = 0; i < threadcount; i++) {
+ pthread_join(threads[i], NUL);
+ }
+
+ return 0;
+}
+late_exit(thread_pool__exit);
+
+void thread_pool__do_job(struct thread_pool__job *job)
+{
+ struct thread_pool__job *jobinfo = job;
+
+ if (jobinfo == NULL || jobinfo->callback == NULL)
+ return;
+
+ mutex_lock(&jobinfo->mutex);
+ if (jobinfo->signalcount++ == 0)
+ thread_pool__job_push(job);
+ mutex_unlock(&jobinfo->mutex);
+
+ mutex_lock(&job_mutex);
+ pthread_cond_signal(&job_cond);
+ mutex_unlock(&job_mutex);
+}
+
+void thread_pool__cancel_job(struct thread_pool__job *job)
+{
+ bool running;
+
+ /*
+ * If the job is queued but not running, remove it. Otherwise, wait for
+ * the signalcount to drop to 0, indicating that it has finished
+ * running. We assume that nobody is queueing this job -
+ * thread_pool__do_job() isn't called - while this function is running.
+ */
+ do {
+ mutex_lock(&job_mutex);
+ if (list_empty(&job->queue)) {
+ running = job->signalcount > 0;
+ } else {
+ list_del_init(&job->queue);
+ job->signalcount = 0;
+ running = false;
+ }
+ mutex_unlock(&job_mutex);
+ } while (running);
+}
diff --git a/kvmtool/util/update_headers.sh b/kvmtool/util/update_headers.sh
new file mode 100755
index 0000000..bf87ef6
--- /dev/null
+++ b/kvmtool/util/update_headers.sh
@@ -0,0 +1,49 @@
+#!/bin/sh
+
+########################################################################
+# Updates the kvmtool tree with up-to-date public header files from
+# a Linux source tree.
+# If no directory is given on the command line, it will try to find one
+# using the lib/modules/`uname -r`/source link.
+########################################################################
+
+set -ue
+
+if [ "$#" -ge 1 ]
+then
+ LINUX_ROOT="$1"
+else
+ LINUX_ROOT="/lib/modules/$(uname -r)/source"
+fi
+
+if [ ! -d "$LINUX_ROOT/include/uapi/linux" ]
+then
+ echo "$LINUX_ROOT does not seem to be valid Linux source tree."
+ echo "usage: $0 [path-to-Linux-source-tree]"
+ exit 1
+fi
+
+cp -- "$LINUX_ROOT/include/uapi/linux/kvm.h" include/linux
+
+unset KVMTOOL_PATH
+
+copy_optional_arch () {
+ local src="$LINUX_ROOT/arch/$arch/include/uapi/$1"
+
+ if [ -r "$src" ]
+ then
+ cp -- "$src" "$KVMTOOL_PATH/include/asm/"
+ fi
+}
+
+for arch in arm arm64 mips powerpc x86
+do
+ case "$arch" in
+ arm) KVMTOOL_PATH=arm/aarch32 ;;
+ arm64) KVMTOOL_PATH=arm/aarch64
+ copy_optional_arch asm/sve_context.h ;;
+ *) KVMTOOL_PATH=$arch ;;
+ esac
+ cp -- "$LINUX_ROOT/arch/$arch/include/uapi/asm/kvm.h" \
+ "$KVMTOOL_PATH/include/asm"
+done
diff --git a/kvmtool/util/util.c b/kvmtool/util/util.c
new file mode 100644
index 0000000..1877105
--- /dev/null
+++ b/kvmtool/util/util.c
@@ -0,0 +1,133 @@
+/*
+ * Taken from perf which in turn take it from GIT
+ */
+
+#include "kvm/util.h"
+
+#include <kvm/kvm.h>
+#include <linux/magic.h> /* For HUGETLBFS_MAGIC */
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/statfs.h>
+
+static void report(const char *prefix, const char *err, va_list params)
+{
+ char msg[1024];
+ vsnprintf(msg, sizeof(msg), err, params);
+ fprintf(stderr, " %s%s\n", prefix, msg);
+}
+
+static NORETURN void die_builtin(const char *err, va_list params)
+{
+ report(" Fatal: ", err, params);
+ exit(128);
+}
+
+static void error_builtin(const char *err, va_list params)
+{
+ report(" Error: ", err, params);
+}
+
+static void warn_builtin(const char *warn, va_list params)
+{
+ report(" Warning: ", warn, params);
+}
+
+static void info_builtin(const char *info, va_list params)
+{
+ report(" Info: ", info, params);
+}
+
+void die(const char *err, ...)
+{
+ va_list params;
+
+ va_start(params, err);
+ die_builtin(err, params);
+ va_end(params);
+}
+
+int pr_err(const char *err, ...)
+{
+ va_list params;
+
+ va_start(params, err);
+ error_builtin(err, params);
+ va_end(params);
+ return -1;
+}
+
+void pr_warning(const char *warn, ...)
+{
+ va_list params;
+
+ va_start(params, warn);
+ warn_builtin(warn, params);
+ va_end(params);
+}
+
+void pr_info(const char *info, ...)
+{
+ va_list params;
+
+ va_start(params, info);
+ info_builtin(info, params);
+ va_end(params);
+}
+
+void die_perror(const char *s)
+{
+ perror(s);
+ exit(1);
+}
+
+void *mmap_hugetlbfs(struct kvm *kvm, const char *htlbfs_path, u64 size)
+{
+ char mpath[PATH_MAX];
+ int fd;
+ struct statfs sfs;
+ void *addr;
+ unsigned long blk_size;
+
+ if (statfs(htlbfs_path, &sfs) < 0)
+ die("Can't stat %s\n", htlbfs_path);
+
+ if ((unsigned int)sfs.f_type != HUGETLBFS_MAGIC)
+ die("%s is not hugetlbfs!\n", htlbfs_path);
+
+ blk_size = (unsigned long)sfs.f_bsize;
+ if (sfs.f_bsize == 0 || blk_size > size) {
+ die("Can't use hugetlbfs pagesize %ld for mem size %lld\n",
+ blk_size, (unsigned long long)size);
+ }
+
+ kvm->ram_pagesize = blk_size;
+
+ snprintf(mpath, PATH_MAX, "%s/kvmtoolXXXXXX", htlbfs_path);
+ fd = mkstemp(mpath);
+ if (fd < 0)
+ die("Can't open %s for hugetlbfs map\n", mpath);
+ unlink(mpath);
+ if (ftruncate(fd, size) < 0)
+ die("Can't ftruncate for mem mapping size %lld\n",
+ (unsigned long long)size);
+ addr = mmap(NULL, size, PROT_RW, MAP_PRIVATE, fd, 0);
+ close(fd);
+
+ return addr;
+}
+
+/* This function wraps the decision between hugetlbfs map (if requested) or normal mmap */
+void *mmap_anon_or_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 size)
+{
+ if (hugetlbfs_path)
+ /*
+ * We don't /need/ to map guest RAM from hugetlbfs, but we do so
+ * if the user specifies a hugetlbfs path.
+ */
+ return mmap_hugetlbfs(kvm, hugetlbfs_path, size);
+ else {
+ kvm->ram_pagesize = getpagesize();
+ return mmap(NULL, size, PROT_RW, MAP_ANON_NORESERVE, -1, 0);
+ }
+}
diff --git a/kvmtool/vfio/core.c b/kvmtool/vfio/core.c
new file mode 100644
index 0000000..0b45e78
--- /dev/null
+++ b/kvmtool/vfio/core.c
@@ -0,0 +1,690 @@
+#include "kvm/kvm.h"
+#include "kvm/vfio.h"
+#include "kvm/ioport.h"
+
+#include <linux/list.h>
+
+#define VFIO_DEV_DIR "/dev/vfio"
+#define VFIO_DEV_NODE VFIO_DEV_DIR "/vfio"
+#define IOMMU_GROUP_DIR "/sys/kernel/iommu_groups"
+
+static int vfio_container;
+static LIST_HEAD(vfio_groups);
+static struct vfio_device *vfio_devices;
+
+static int vfio_device_pci_parser(const struct option *opt, char *arg,
+ struct vfio_device_params *dev)
+{
+ unsigned int domain, bus, devnr, fn;
+
+ int nr = sscanf(arg, "%4x:%2x:%2x.%1x", &domain, &bus, &devnr, &fn);
+ if (nr < 4) {
+ domain = 0;
+ nr = sscanf(arg, "%2x:%2x.%1x", &bus, &devnr, &fn);
+ if (nr < 3) {
+ pr_err("Invalid device identifier %s", arg);
+ return -EINVAL;
+ }
+ }
+
+ dev->type = VFIO_DEVICE_PCI;
+ dev->bus = "pci";
+ dev->name = malloc(13);
+ if (!dev->name)
+ return -ENOMEM;
+
+ snprintf(dev->name, 13, "%04x:%02x:%02x.%x", domain, bus, devnr, fn);
+
+ return 0;
+}
+
+int vfio_device_parser(const struct option *opt, const char *arg, int unset)
+{
+ int ret = -EINVAL;
+ static int idx = 0;
+ struct kvm *kvm = opt->ptr;
+ struct vfio_device_params *dev, *devs;
+ char *cur, *buf = strdup(arg);
+
+ if (!buf)
+ return -ENOMEM;
+
+ if (idx >= MAX_VFIO_DEVICES) {
+ pr_warning("Too many VFIO devices");
+ goto out_free_buf;
+ }
+
+ devs = realloc(kvm->cfg.vfio_devices, sizeof(*dev) * (idx + 1));
+ if (!devs) {
+ ret = -ENOMEM;
+ goto out_free_buf;
+ }
+
+ kvm->cfg.vfio_devices = devs;
+ dev = &devs[idx];
+
+ cur = strtok(buf, ",");
+ if (!cur)
+ goto out_free_buf;
+
+ if (!strcmp(opt->long_name, "vfio-pci"))
+ ret = vfio_device_pci_parser(opt, cur, dev);
+ else
+ ret = -EINVAL;
+
+ if (!ret)
+ kvm->cfg.num_vfio_devices = ++idx;
+
+out_free_buf:
+ free(buf);
+
+ return ret;
+}
+
+static bool vfio_ioport_in(struct ioport *ioport, struct kvm_cpu *vcpu,
+ u16 port, void *data, int len)
+{
+ u32 val;
+ ssize_t nr;
+ struct vfio_region *region = ioport->priv;
+ struct vfio_device *vdev = region->vdev;
+
+ u32 offset = port - region->port_base;
+
+ if (!(region->info.flags & VFIO_REGION_INFO_FLAG_READ))
+ return false;
+
+ nr = pread(vdev->fd, &val, len, region->info.offset + offset);
+ if (nr != len) {
+ vfio_dev_err(vdev, "could not read %d bytes from I/O port 0x%x\n",
+ len, port);
+ return false;
+ }
+
+ switch (len) {
+ case 1:
+ ioport__write8(data, val);
+ break;
+ case 2:
+ ioport__write16(data, val);
+ break;
+ case 4:
+ ioport__write32(data, val);
+ break;
+ default:
+ return false;
+ }
+
+ return true;
+}
+
+static bool vfio_ioport_out(struct ioport *ioport, struct kvm_cpu *vcpu,
+ u16 port, void *data, int len)
+{
+ u32 val;
+ ssize_t nr;
+ struct vfio_region *region = ioport->priv;
+ struct vfio_device *vdev = region->vdev;
+
+ u32 offset = port - region->port_base;
+
+ if (!(region->info.flags & VFIO_REGION_INFO_FLAG_WRITE))
+ return false;
+
+ switch (len) {
+ case 1:
+ val = ioport__read8(data);
+ break;
+ case 2:
+ val = ioport__read16(data);
+ break;
+ case 4:
+ val = ioport__read32(data);
+ break;
+ default:
+ return false;
+ }
+
+ nr = pwrite(vdev->fd, &val, len, region->info.offset + offset);
+ if (nr != len)
+ vfio_dev_err(vdev, "could not write %d bytes to I/O port 0x%x",
+ len, port);
+
+ return nr == len;
+}
+
+static struct ioport_operations vfio_ioport_ops = {
+ .io_in = vfio_ioport_in,
+ .io_out = vfio_ioport_out,
+};
+
+static void vfio_mmio_access(struct kvm_cpu *vcpu, u64 addr, u8 *data, u32 len,
+ u8 is_write, void *ptr)
+{
+ u64 val;
+ ssize_t nr;
+ struct vfio_region *region = ptr;
+ struct vfio_device *vdev = region->vdev;
+
+ u32 offset = addr - region->guest_phys_addr;
+
+ if (len < 1 || len > 8)
+ goto err_report;
+
+ if (is_write) {
+ if (!(region->info.flags & VFIO_REGION_INFO_FLAG_WRITE))
+ goto err_report;
+
+ memcpy(&val, data, len);
+
+ nr = pwrite(vdev->fd, &val, len, region->info.offset + offset);
+ if ((u32)nr != len)
+ goto err_report;
+ } else {
+ if (!(region->info.flags & VFIO_REGION_INFO_FLAG_READ))
+ goto err_report;
+
+ nr = pread(vdev->fd, &val, len, region->info.offset + offset);
+ if ((u32)nr != len)
+ goto err_report;
+
+ memcpy(data, &val, len);
+ }
+
+ return;
+
+err_report:
+ vfio_dev_err(vdev, "could not %s %u bytes at 0x%x (0x%llx)", is_write ?
+ "write" : "read", len, offset, addr);
+}
+
+static int vfio_setup_trap_region(struct kvm *kvm, struct vfio_device *vdev,
+ struct vfio_region *region)
+{
+ if (region->is_ioport) {
+ int port = ioport__register(kvm, region->port_base,
+ &vfio_ioport_ops, region->info.size,
+ region);
+ if (port < 0)
+ return port;
+ return 0;
+ }
+
+ return kvm__register_mmio(kvm, region->guest_phys_addr,
+ region->info.size, false, vfio_mmio_access,
+ region);
+}
+
+int vfio_map_region(struct kvm *kvm, struct vfio_device *vdev,
+ struct vfio_region *region)
+{
+ void *base;
+ int ret, prot = 0;
+ /* KVM needs page-aligned regions */
+ u64 map_size = ALIGN(region->info.size, PAGE_SIZE);
+
+ if (!(region->info.flags & VFIO_REGION_INFO_FLAG_MMAP))
+ return vfio_setup_trap_region(kvm, vdev, region);
+
+ /*
+ * KVM_SET_USER_MEMORY_REGION will fail because the guest physical
+ * address isn't page aligned, let's emulate the region ourselves.
+ */
+ if (region->guest_phys_addr & (PAGE_SIZE - 1))
+ return kvm__register_mmio(kvm, region->guest_phys_addr,
+ region->info.size, false,
+ vfio_mmio_access, region);
+
+ if (region->info.flags & VFIO_REGION_INFO_FLAG_READ)
+ prot |= PROT_READ;
+ if (region->info.flags & VFIO_REGION_INFO_FLAG_WRITE)
+ prot |= PROT_WRITE;
+
+ base = mmap(NULL, region->info.size, prot, MAP_SHARED, vdev->fd,
+ region->info.offset);
+ if (base == MAP_FAILED) {
+ /* TODO: support sparse mmap */
+ vfio_dev_warn(vdev, "failed to mmap region %u (0x%llx bytes), falling back to trapping",
+ region->info.index, region->info.size);
+ return vfio_setup_trap_region(kvm, vdev, region);
+ }
+ region->host_addr = base;
+
+ ret = kvm__register_dev_mem(kvm, region->guest_phys_addr, map_size,
+ region->host_addr);
+ if (ret) {
+ vfio_dev_err(vdev, "failed to register region with KVM");
+ return ret;
+ }
+
+ return 0;
+}
+
+void vfio_unmap_region(struct kvm *kvm, struct vfio_region *region)
+{
+ u64 map_size;
+
+ if (region->host_addr) {
+ map_size = ALIGN(region->info.size, PAGE_SIZE);
+ kvm__destroy_mem(kvm, region->guest_phys_addr, map_size,
+ region->host_addr);
+ munmap(region->host_addr, region->info.size);
+ region->host_addr = NULL;
+ } else if (region->is_ioport) {
+ ioport__unregister(kvm, region->port_base);
+ } else {
+ kvm__deregister_mmio(kvm, region->guest_phys_addr);
+ }
+}
+
+static int vfio_configure_device(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int ret;
+ struct vfio_group *group = vdev->group;
+
+ vdev->fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD,
+ vdev->params->name);
+ if (vdev->fd < 0) {
+ vfio_dev_warn(vdev, "failed to get fd");
+
+ /* The device might be a bridge without an fd */
+ return 0;
+ }
+
+ vdev->info.argsz = sizeof(vdev->info);
+ if (ioctl(vdev->fd, VFIO_DEVICE_GET_INFO, &vdev->info)) {
+ ret = -errno;
+ vfio_dev_err(vdev, "failed to get info");
+ goto err_close_device;
+ }
+
+ if (vdev->info.flags & VFIO_DEVICE_FLAGS_RESET &&
+ ioctl(vdev->fd, VFIO_DEVICE_RESET) < 0)
+ vfio_dev_warn(vdev, "failed to reset device");
+
+ vdev->regions = calloc(vdev->info.num_regions, sizeof(*vdev->regions));
+ if (!vdev->regions) {
+ ret = -ENOMEM;
+ goto err_close_device;
+ }
+
+ /* Now for the bus-specific initialization... */
+ switch (vdev->params->type) {
+ case VFIO_DEVICE_PCI:
+ BUG_ON(!(vdev->info.flags & VFIO_DEVICE_FLAGS_PCI));
+ ret = vfio_pci_setup_device(kvm, vdev);
+ break;
+ default:
+ BUG_ON(1);
+ ret = -EINVAL;
+ }
+
+ if (ret)
+ goto err_free_regions;
+
+ vfio_dev_info(vdev, "assigned to device number 0x%x in group %lu",
+ vdev->dev_hdr.dev_num, group->id);
+
+ return 0;
+
+err_free_regions:
+ free(vdev->regions);
+err_close_device:
+ close(vdev->fd);
+
+ return ret;
+}
+
+static int vfio_configure_devices(struct kvm *kvm)
+{
+ int i, ret;
+
+ for (i = 0; i < kvm->cfg.num_vfio_devices; ++i) {
+ ret = vfio_configure_device(kvm, &vfio_devices[i]);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int vfio_get_iommu_type(void)
+{
+ if (ioctl(vfio_container, VFIO_CHECK_EXTENSION, VFIO_TYPE1v2_IOMMU))
+ return VFIO_TYPE1v2_IOMMU;
+
+ if (ioctl(vfio_container, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU))
+ return VFIO_TYPE1_IOMMU;
+
+ return -ENODEV;
+}
+
+static int vfio_map_mem_bank(struct kvm *kvm, struct kvm_mem_bank *bank, void *data)
+{
+ int ret = 0;
+ struct vfio_iommu_type1_dma_map dma_map = {
+ .argsz = sizeof(dma_map),
+ .flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE,
+ .vaddr = (unsigned long)bank->host_addr,
+ .iova = (u64)bank->guest_phys_addr,
+ .size = bank->size,
+ };
+
+ /* Map the guest memory for DMA (i.e. provide isolation) */
+ if (ioctl(vfio_container, VFIO_IOMMU_MAP_DMA, &dma_map)) {
+ ret = -errno;
+ pr_err("Failed to map 0x%llx -> 0x%llx (%llu) for DMA",
+ dma_map.iova, dma_map.vaddr, dma_map.size);
+ }
+
+ return ret;
+}
+
+static int vfio_unmap_mem_bank(struct kvm *kvm, struct kvm_mem_bank *bank, void *data)
+{
+ struct vfio_iommu_type1_dma_unmap dma_unmap = {
+ .argsz = sizeof(dma_unmap),
+ .size = bank->size,
+ .iova = bank->guest_phys_addr,
+ };
+
+ ioctl(vfio_container, VFIO_IOMMU_UNMAP_DMA, &dma_unmap);
+
+ return 0;
+}
+
+static int vfio_configure_reserved_regions(struct kvm *kvm,
+ struct vfio_group *group)
+{
+ FILE *file;
+ int ret = 0;
+ char type[9];
+ char filename[PATH_MAX];
+ unsigned long long start, end;
+
+ snprintf(filename, PATH_MAX, IOMMU_GROUP_DIR "/%lu/reserved_regions",
+ group->id);
+
+ /* reserved_regions might not be present on older systems */
+ if (access(filename, F_OK))
+ return 0;
+
+ file = fopen(filename, "r");
+ if (!file)
+ return -errno;
+
+ while (fscanf(file, "0x%llx 0x%llx %8s\n", &start, &end, type) == 3) {
+ ret = kvm__reserve_mem(kvm, start, end - start + 1);
+ if (ret)
+ break;
+ }
+
+ fclose(file);
+
+ return ret;
+}
+
+static int vfio_configure_groups(struct kvm *kvm)
+{
+ int ret;
+ struct vfio_group *group;
+
+ list_for_each_entry(group, &vfio_groups, list) {
+ ret = vfio_configure_reserved_regions(kvm, group);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static struct vfio_group *vfio_group_create(struct kvm *kvm, unsigned long id)
+{
+ int ret;
+ struct vfio_group *group;
+ char group_node[PATH_MAX];
+ struct vfio_group_status group_status = {
+ .argsz = sizeof(group_status),
+ };
+
+ group = calloc(1, sizeof(*group));
+ if (!group)
+ return NULL;
+
+ group->id = id;
+ group->refs = 1;
+
+ ret = snprintf(group_node, PATH_MAX, VFIO_DEV_DIR "/%lu", id);
+ if (ret < 0 || ret == PATH_MAX)
+ return NULL;
+
+ group->fd = open(group_node, O_RDWR);
+ if (group->fd < 0) {
+ pr_err("Failed to open IOMMU group %s", group_node);
+ goto err_free_group;
+ }
+
+ if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &group_status)) {
+ pr_err("Failed to determine status of IOMMU group %lu", id);
+ goto err_close_group;
+ }
+
+ if (!(group_status.flags & VFIO_GROUP_FLAGS_VIABLE)) {
+ pr_err("IOMMU group %lu is not viable", id);
+ goto err_close_group;
+ }
+
+ if (ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &vfio_container)) {
+ pr_err("Failed to add IOMMU group %lu to VFIO container", id);
+ goto err_close_group;
+ }
+
+ list_add(&group->list, &vfio_groups);
+
+ return group;
+
+err_close_group:
+ close(group->fd);
+err_free_group:
+ free(group);
+
+ return NULL;
+}
+
+static void vfio_group_exit(struct kvm *kvm, struct vfio_group *group)
+{
+ if (--group->refs != 0)
+ return;
+
+ ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER);
+
+ list_del(&group->list);
+ close(group->fd);
+ free(group);
+}
+
+static struct vfio_group *
+vfio_group_get_for_dev(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int dirfd;
+ ssize_t ret;
+ char *group_name;
+ unsigned long group_id;
+ char group_path[PATH_MAX];
+ struct vfio_group *group = NULL;
+
+ /* Find IOMMU group for this device */
+ dirfd = open(vdev->sysfs_path, O_DIRECTORY | O_PATH | O_RDONLY);
+ if (dirfd < 0) {
+ vfio_dev_err(vdev, "failed to open '%s'", vdev->sysfs_path);
+ return NULL;
+ }
+
+ ret = readlinkat(dirfd, "iommu_group", group_path, PATH_MAX);
+ if (ret < 0) {
+ vfio_dev_err(vdev, "no iommu_group");
+ goto out_close;
+ }
+ if (ret == PATH_MAX)
+ goto out_close;
+
+ group_path[ret] = '\0';
+
+ group_name = basename(group_path);
+ errno = 0;
+ group_id = strtoul(group_name, NULL, 10);
+ if (errno)
+ goto out_close;
+
+ list_for_each_entry(group, &vfio_groups, list) {
+ if (group->id == group_id) {
+ group->refs++;
+ return group;
+ }
+ }
+
+ group = vfio_group_create(kvm, group_id);
+
+out_close:
+ close(dirfd);
+ return group;
+}
+
+static int vfio_device_init(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int ret;
+ char dev_path[PATH_MAX];
+ struct vfio_group *group;
+
+ ret = snprintf(dev_path, PATH_MAX, "/sys/bus/%s/devices/%s",
+ vdev->params->bus, vdev->params->name);
+ if (ret < 0 || ret == PATH_MAX)
+ return -EINVAL;
+
+ vdev->sysfs_path = strndup(dev_path, PATH_MAX);
+ if (!vdev->sysfs_path)
+ return -errno;
+
+ group = vfio_group_get_for_dev(kvm, vdev);
+ if (!group) {
+ free(vdev->sysfs_path);
+ return -EINVAL;
+ }
+
+ vdev->group = group;
+
+ return 0;
+}
+
+static void vfio_device_exit(struct kvm *kvm, struct vfio_device *vdev)
+{
+ vfio_group_exit(kvm, vdev->group);
+
+ switch (vdev->params->type) {
+ case VFIO_DEVICE_PCI:
+ vfio_pci_teardown_device(kvm, vdev);
+ break;
+ default:
+ vfio_dev_warn(vdev, "no teardown function for device");
+ }
+
+ close(vdev->fd);
+
+ free(vdev->regions);
+ free(vdev->sysfs_path);
+}
+
+static int vfio_container_init(struct kvm *kvm)
+{
+ int api, i, ret, iommu_type;;
+
+ /* Create a container for our IOMMU groups */
+ vfio_container = open(VFIO_DEV_NODE, O_RDWR);
+ if (vfio_container == -1) {
+ ret = errno;
+ pr_err("Failed to open %s", VFIO_DEV_NODE);
+ return ret;
+ }
+
+ api = ioctl(vfio_container, VFIO_GET_API_VERSION);
+ if (api != VFIO_API_VERSION) {
+ pr_err("Unknown VFIO API version %d", api);
+ return -ENODEV;
+ }
+
+ iommu_type = vfio_get_iommu_type();
+ if (iommu_type < 0) {
+ pr_err("VFIO type-1 IOMMU not supported on this platform");
+ return iommu_type;
+ }
+
+ /* Create groups for our devices and add them to the container */
+ for (i = 0; i < kvm->cfg.num_vfio_devices; ++i) {
+ vfio_devices[i].params = &kvm->cfg.vfio_devices[i];
+
+ ret = vfio_device_init(kvm, &vfio_devices[i]);
+ if (ret)
+ return ret;
+ }
+
+ /* Finalise the container */
+ if (ioctl(vfio_container, VFIO_SET_IOMMU, iommu_type)) {
+ ret = -errno;
+ pr_err("Failed to set IOMMU type %d for VFIO container",
+ iommu_type);
+ return ret;
+ } else {
+ pr_info("Using IOMMU type %d for VFIO container", iommu_type);
+ }
+
+ return kvm__for_each_mem_bank(kvm, KVM_MEM_TYPE_RAM, vfio_map_mem_bank,
+ NULL);
+}
+
+static int vfio__init(struct kvm *kvm)
+{
+ int ret;
+
+ if (!kvm->cfg.num_vfio_devices)
+ return 0;
+
+ vfio_devices = calloc(kvm->cfg.num_vfio_devices, sizeof(*vfio_devices));
+ if (!vfio_devices)
+ return -ENOMEM;
+
+ ret = vfio_container_init(kvm);
+ if (ret)
+ return ret;
+
+ ret = vfio_configure_groups(kvm);
+ if (ret)
+ return ret;
+
+ ret = vfio_configure_devices(kvm);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+dev_base_init(vfio__init);
+
+static int vfio__exit(struct kvm *kvm)
+{
+ int i;
+
+ if (!kvm->cfg.num_vfio_devices)
+ return 0;
+
+ for (i = 0; i < kvm->cfg.num_vfio_devices; i++)
+ vfio_device_exit(kvm, &vfio_devices[i]);
+
+ free(vfio_devices);
+
+ kvm__for_each_mem_bank(kvm, KVM_MEM_TYPE_RAM, vfio_unmap_mem_bank, NULL);
+ close(vfio_container);
+
+ free(kvm->cfg.vfio_devices);
+
+ return 0;
+}
+dev_base_exit(vfio__exit);
diff --git a/kvmtool/vfio/pci.c b/kvmtool/vfio/pci.c
new file mode 100644
index 0000000..49ecd12
--- /dev/null
+++ b/kvmtool/vfio/pci.c
@@ -0,0 +1,1373 @@
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/vfio.h"
+
+#include <assert.h>
+
+#include <sys/ioctl.h>
+#include <sys/eventfd.h>
+#include <sys/resource.h>
+#include <sys/time.h>
+
+#include <assert.h>
+
+/* Wrapper around UAPI vfio_irq_set */
+union vfio_irq_eventfd {
+ struct vfio_irq_set irq;
+ u8 buffer[sizeof(struct vfio_irq_set) + sizeof(int)];
+};
+
+static void set_vfio_irq_eventd_payload(union vfio_irq_eventfd *evfd, int fd)
+{
+ memcpy(&evfd->irq.data, &fd, sizeof(fd));
+}
+
+#define msi_is_enabled(state) ((state) & VFIO_PCI_MSI_STATE_ENABLED)
+#define msi_is_masked(state) ((state) & VFIO_PCI_MSI_STATE_MASKED)
+#define msi_is_empty(state) ((state) & VFIO_PCI_MSI_STATE_EMPTY)
+
+#define msi_update_state(state, val, bit) \
+ (state) = (val) ? (state) | bit : (state) & ~bit;
+#define msi_set_enabled(state, val) \
+ msi_update_state(state, val, VFIO_PCI_MSI_STATE_ENABLED)
+#define msi_set_masked(state, val) \
+ msi_update_state(state, val, VFIO_PCI_MSI_STATE_MASKED)
+#define msi_set_empty(state, val) \
+ msi_update_state(state, val, VFIO_PCI_MSI_STATE_EMPTY)
+
+static void vfio_pci_disable_intx(struct kvm *kvm, struct vfio_device *vdev);
+static int vfio_pci_enable_intx(struct kvm *kvm, struct vfio_device *vdev);
+
+static int vfio_pci_enable_msis(struct kvm *kvm, struct vfio_device *vdev,
+ bool msix)
+{
+ size_t i;
+ int ret = 0;
+ int *eventfds;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_pci_msi_common *msis = msix ? &pdev->msix : &pdev->msi;
+ union vfio_irq_eventfd single = {
+ .irq = {
+ .argsz = sizeof(single),
+ .flags = VFIO_IRQ_SET_DATA_EVENTFD |
+ VFIO_IRQ_SET_ACTION_TRIGGER,
+ .index = msis->info.index,
+ .count = 1,
+ },
+ };
+
+ if (!msi_is_enabled(msis->virt_state))
+ return 0;
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_INTX)
+ /*
+ * PCI (and VFIO) forbids enabling INTx, MSI or MSIX at the same
+ * time. Since INTx has to be enabled from the start (we don't
+ * have a reliable way to know when the guest starts using it),
+ * disable it now.
+ */
+ vfio_pci_disable_intx(kvm, vdev);
+
+ eventfds = (void *)msis->irq_set + sizeof(struct vfio_irq_set);
+
+ /*
+ * Initial registration of the full range. This enables the physical
+ * MSI/MSI-X capability, which might have desired side effects. For
+ * instance when assigning virtio legacy devices, enabling the MSI
+ * capability modifies the config space layout!
+ *
+ * As an optimization, only update MSIs when guest unmasks the
+ * capability. This greatly reduces the initialization time for Linux
+ * guest with 2048+ MSIs. Linux guest starts by enabling the MSI-X cap
+ * masked, then fills individual vectors, then unmasks the whole
+ * function. So we only do one VFIO ioctl when enabling for the first
+ * time, and then one when unmasking.
+ *
+ * phys_state is empty when it is enabled but no vector has been
+ * registered via SET_IRQS yet.
+ */
+ if (!msi_is_enabled(msis->phys_state) ||
+ (!msi_is_masked(msis->virt_state) &&
+ msi_is_empty(msis->phys_state))) {
+ bool empty = true;
+
+ for (i = 0; i < msis->nr_entries; i++) {
+ eventfds[i] = msis->entries[i].gsi >= 0 ?
+ msis->entries[i].eventfd : -1;
+
+ if (eventfds[i] >= 0)
+ empty = false;
+ }
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, msis->irq_set);
+ if (ret < 0) {
+ perror("VFIO_DEVICE_SET_IRQS(multi)");
+ return ret;
+ }
+
+ msi_set_enabled(msis->phys_state, true);
+ msi_set_empty(msis->phys_state, empty);
+
+ return 0;
+ }
+
+ if (msi_is_masked(msis->virt_state)) {
+ /* TODO: if phys_state is not empty nor masked, mask all vectors */
+ return 0;
+ }
+
+ /* Update individual vectors to avoid breaking those in use */
+ for (i = 0; i < msis->nr_entries; i++) {
+ struct vfio_pci_msi_entry *entry = &msis->entries[i];
+ int fd = entry->gsi >= 0 ? entry->eventfd : -1;
+
+ if (fd == eventfds[i])
+ continue;
+
+ single.irq.start = i;
+ set_vfio_irq_eventd_payload(&single, fd);
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &single);
+ if (ret < 0) {
+ perror("VFIO_DEVICE_SET_IRQS(single)");
+ break;
+ }
+
+ eventfds[i] = fd;
+
+ if (msi_is_empty(msis->phys_state) && fd >= 0)
+ msi_set_empty(msis->phys_state, false);
+ }
+
+ return ret;
+}
+
+static int vfio_pci_disable_msis(struct kvm *kvm, struct vfio_device *vdev,
+ bool msix)
+{
+ int ret;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_pci_msi_common *msis = msix ? &pdev->msix : &pdev->msi;
+ struct vfio_irq_set irq_set = {
+ .argsz = sizeof(irq_set),
+ .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
+ .index = msis->info.index,
+ .start = 0,
+ .count = 0,
+ };
+
+ if (!msi_is_enabled(msis->phys_state))
+ return 0;
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ if (ret < 0) {
+ perror("VFIO_DEVICE_SET_IRQS(NONE)");
+ return ret;
+ }
+
+ msi_set_enabled(msis->phys_state, false);
+ msi_set_empty(msis->phys_state, true);
+
+ /*
+ * When MSI or MSIX is disabled, this might be called when
+ * PCI driver detects the MSI interrupt failure and wants to
+ * rollback to INTx mode. Thus enable INTx if the device
+ * supports INTx mode in this case.
+ */
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_INTX)
+ ret = vfio_pci_enable_intx(kvm, vdev);
+
+ return ret >= 0 ? 0 : ret;
+}
+
+static int vfio_pci_update_msi_entry(struct kvm *kvm, struct vfio_device *vdev,
+ struct vfio_pci_msi_entry *entry)
+{
+ int ret;
+
+ if (entry->eventfd < 0) {
+ entry->eventfd = eventfd(0, 0);
+ if (entry->eventfd < 0) {
+ ret = -errno;
+ vfio_dev_err(vdev, "cannot create eventfd");
+ return ret;
+ }
+ }
+
+ /* Allocate IRQ if necessary */
+ if (entry->gsi < 0) {
+ int ret = irq__add_msix_route(kvm, &entry->config.msg,
+ vdev->dev_hdr.dev_num << 3);
+ if (ret < 0) {
+ vfio_dev_err(vdev, "cannot create MSI-X route");
+ return ret;
+ }
+ entry->gsi = ret;
+ } else {
+ irq__update_msix_route(kvm, entry->gsi, &entry->config.msg);
+ }
+
+ /*
+ * MSI masking is unimplemented in VFIO, so we have to handle it by
+ * disabling/enabling IRQ route instead. We do it on the KVM side rather
+ * than VFIO, because:
+ * - it is 8x faster
+ * - it allows to decouple masking logic from capability state.
+ * - in masked state, after removing irqfd route, we could easily plug
+ * the eventfd in a local handler, in order to serve Pending Bit reads
+ * to the guest.
+ *
+ * So entry->phys_state is masked when there is no active irqfd route.
+ */
+ if (msi_is_masked(entry->virt_state) == msi_is_masked(entry->phys_state))
+ return 0;
+
+ if (msi_is_masked(entry->phys_state)) {
+ ret = irq__add_irqfd(kvm, entry->gsi, entry->eventfd, -1);
+ if (ret < 0) {
+ vfio_dev_err(vdev, "cannot setup irqfd");
+ return ret;
+ }
+ } else {
+ irq__del_irqfd(kvm, entry->gsi, entry->eventfd);
+ }
+
+ msi_set_masked(entry->phys_state, msi_is_masked(entry->virt_state));
+
+ return 0;
+}
+
+static void vfio_pci_msix_pba_access(struct kvm_cpu *vcpu, u64 addr, u8 *data,
+ u32 len, u8 is_write, void *ptr)
+{
+ struct vfio_pci_device *pdev = ptr;
+ struct vfio_pci_msix_pba *pba = &pdev->msix_pba;
+ u64 offset = addr - pba->guest_phys_addr;
+ struct vfio_device *vdev = container_of(pdev, struct vfio_device, pci);
+
+ if (is_write)
+ return;
+
+ /*
+ * TODO: emulate PBA. Hardware MSI-X is never masked, so reading the PBA
+ * is completely useless here. Note that Linux doesn't use PBA.
+ */
+ if (pread(vdev->fd, data, len, pba->offset + offset) != (ssize_t)len)
+ vfio_dev_err(vdev, "cannot access MSIX PBA\n");
+}
+
+static void vfio_pci_msix_table_access(struct kvm_cpu *vcpu, u64 addr, u8 *data,
+ u32 len, u8 is_write, void *ptr)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct vfio_pci_msi_entry *entry;
+ struct vfio_pci_device *pdev = ptr;
+ struct vfio_device *vdev = container_of(pdev, struct vfio_device, pci);
+
+ u64 offset = addr - pdev->msix_table.guest_phys_addr;
+
+ size_t vector = offset / PCI_MSIX_ENTRY_SIZE;
+ off_t field = offset % PCI_MSIX_ENTRY_SIZE;
+
+ /*
+ * PCI spec says that software must use aligned 4 or 8 bytes accesses
+ * for the MSI-X tables.
+ */
+ if ((len != 4 && len != 8) || addr & (len - 1)) {
+ vfio_dev_warn(vdev, "invalid MSI-X table access");
+ return;
+ }
+
+ entry = &pdev->msix.entries[vector];
+
+ mutex_lock(&pdev->msix.mutex);
+
+ if (!is_write) {
+ memcpy(data, (void *)&entry->config + field, len);
+ goto out_unlock;
+ }
+
+ memcpy((void *)&entry->config + field, data, len);
+
+ /*
+ * Check if access touched the vector control register, which is at the
+ * end of the MSI-X entry.
+ */
+ if (field + len <= PCI_MSIX_ENTRY_VECTOR_CTRL)
+ goto out_unlock;
+
+ msi_set_masked(entry->virt_state, entry->config.ctrl &
+ PCI_MSIX_ENTRY_CTRL_MASKBIT);
+
+ if (vfio_pci_update_msi_entry(kvm, vdev, entry) < 0)
+ /* Not much we can do here. */
+ vfio_dev_err(vdev, "failed to configure MSIX vector %zu", vector);
+
+ /* Update the physical capability if necessary */
+ if (vfio_pci_enable_msis(kvm, vdev, true))
+ vfio_dev_err(vdev, "cannot enable MSIX");
+
+out_unlock:
+ mutex_unlock(&pdev->msix.mutex);
+}
+
+static void vfio_pci_msix_cap_write(struct kvm *kvm,
+ struct vfio_device *vdev, u8 off,
+ void *data, int sz)
+{
+ struct vfio_pci_device *pdev = &vdev->pci;
+ off_t enable_pos = PCI_MSIX_FLAGS + 1;
+ bool enable;
+ u16 flags;
+
+ off -= pdev->msix.pos;
+
+ /* Check if access intersects with the MSI-X Enable bit */
+ if (off > enable_pos || off + sz <= enable_pos)
+ return;
+
+ /* Read byte that contains the Enable bit */
+ flags = *(u8 *)(data + enable_pos - off) << 8;
+
+ mutex_lock(&pdev->msix.mutex);
+
+ msi_set_masked(pdev->msix.virt_state, flags & PCI_MSIX_FLAGS_MASKALL);
+ enable = flags & PCI_MSIX_FLAGS_ENABLE;
+ msi_set_enabled(pdev->msix.virt_state, enable);
+
+ if (enable && vfio_pci_enable_msis(kvm, vdev, true))
+ vfio_dev_err(vdev, "cannot enable MSIX");
+ else if (!enable && vfio_pci_disable_msis(kvm, vdev, true))
+ vfio_dev_err(vdev, "cannot disable MSIX");
+
+ mutex_unlock(&pdev->msix.mutex);
+}
+
+static int vfio_pci_msi_vector_write(struct kvm *kvm, struct vfio_device *vdev,
+ u8 off, u8 *data, u32 sz)
+{
+ size_t i;
+ u32 mask = 0;
+ size_t mask_pos, start, limit;
+ struct vfio_pci_msi_entry *entry;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct msi_cap_64 *msi_cap_64 = PCI_CAP(&pdev->hdr, pdev->msi.pos);
+
+ if (!(msi_cap_64->ctrl & PCI_MSI_FLAGS_MASKBIT))
+ return 0;
+
+ if (msi_cap_64->ctrl & PCI_MSI_FLAGS_64BIT)
+ mask_pos = PCI_MSI_MASK_64;
+ else
+ mask_pos = PCI_MSI_MASK_32;
+
+ if (off >= mask_pos + 4 || off + sz <= mask_pos)
+ return 0;
+
+ /* Set mask to current state */
+ for (i = 0; i < pdev->msi.nr_entries; i++) {
+ entry = &pdev->msi.entries[i];
+ mask |= !!msi_is_masked(entry->virt_state) << i;
+ }
+
+ /* Update mask following the intersection of access and register */
+ start = max_t(size_t, off, mask_pos);
+ limit = min_t(size_t, off + sz, mask_pos + 4);
+
+ memcpy((void *)&mask + start - mask_pos, data + start - off,
+ limit - start);
+
+ /* Update states if necessary */
+ for (i = 0; i < pdev->msi.nr_entries; i++) {
+ bool masked = mask & (1 << i);
+
+ entry = &pdev->msi.entries[i];
+ if (masked != msi_is_masked(entry->virt_state)) {
+ msi_set_masked(entry->virt_state, masked);
+ vfio_pci_update_msi_entry(kvm, vdev, entry);
+ }
+ }
+
+ return 1;
+}
+
+static void vfio_pci_msi_cap_write(struct kvm *kvm, struct vfio_device *vdev,
+ u8 off, u8 *data, u32 sz)
+{
+ u8 ctrl;
+ struct msi_msg msg;
+ size_t i, nr_vectors;
+ struct vfio_pci_msi_entry *entry;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct msi_cap_64 *msi_cap_64 = PCI_CAP(&pdev->hdr, pdev->msi.pos);
+
+ off -= pdev->msi.pos;
+
+ mutex_lock(&pdev->msi.mutex);
+
+ /* Check if the guest is trying to update mask bits */
+ if (vfio_pci_msi_vector_write(kvm, vdev, off, data, sz))
+ goto out_unlock;
+
+ /* Only modify routes when guest pokes the enable bit */
+ if (off > PCI_MSI_FLAGS || off + sz <= PCI_MSI_FLAGS)
+ goto out_unlock;
+
+ ctrl = *(u8 *)(data + PCI_MSI_FLAGS - off);
+
+ msi_set_enabled(pdev->msi.virt_state, ctrl & PCI_MSI_FLAGS_ENABLE);
+
+ if (!msi_is_enabled(pdev->msi.virt_state)) {
+ vfio_pci_disable_msis(kvm, vdev, false);
+ goto out_unlock;
+ }
+
+ /* Create routes for the requested vectors */
+ nr_vectors = 1 << ((ctrl & PCI_MSI_FLAGS_QSIZE) >> 4);
+
+ msg.address_lo = msi_cap_64->address_lo;
+ if (msi_cap_64->ctrl & PCI_MSI_FLAGS_64BIT) {
+ msg.address_hi = msi_cap_64->address_hi;
+ msg.data = msi_cap_64->data;
+ } else {
+ struct msi_cap_32 *msi_cap_32 = (void *)msi_cap_64;
+ msg.address_hi = 0;
+ msg.data = msi_cap_32->data;
+ }
+
+ for (i = 0; i < nr_vectors; i++) {
+ entry = &pdev->msi.entries[i];
+
+ /*
+ * Set the MSI data value as required by the PCI local
+ * bus specifications, MSI capability, "Message Data".
+ */
+ msg.data &= ~(nr_vectors - 1);
+ msg.data |= i;
+
+ entry->config.msg = msg;
+ vfio_pci_update_msi_entry(kvm, vdev, entry);
+ }
+
+ /* Update the physical capability if necessary */
+ if (vfio_pci_enable_msis(kvm, vdev, false))
+ vfio_dev_err(vdev, "cannot enable MSI");
+
+out_unlock:
+ mutex_unlock(&pdev->msi.mutex);
+}
+
+static int vfio_pci_bar_activate(struct kvm *kvm,
+ struct pci_device_header *pci_hdr,
+ int bar_num, void *data)
+{
+ struct vfio_device *vdev = data;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_pci_msix_pba *pba = &pdev->msix_pba;
+ struct vfio_pci_msix_table *table = &pdev->msix_table;
+ struct vfio_region *region;
+ u32 bar_addr;
+ bool has_msix;
+ int ret;
+
+ assert((u32)bar_num < vdev->info.num_regions);
+
+ region = &vdev->regions[bar_num];
+ has_msix = pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSIX;
+
+ bar_addr = pci__bar_address(pci_hdr, bar_num);
+ if (pci__bar_is_io(pci_hdr, bar_num))
+ region->port_base = bar_addr;
+ else
+ region->guest_phys_addr = bar_addr;
+
+ if (has_msix && (u32)bar_num == table->bar) {
+ table->guest_phys_addr = region->guest_phys_addr;
+ ret = kvm__register_mmio(kvm, table->guest_phys_addr,
+ table->size, false,
+ vfio_pci_msix_table_access, pdev);
+ /*
+ * The MSIX table and the PBA structure can share the same BAR,
+ * but for convenience we register different regions for mmio
+ * emulation. We want to we update both if they share the same
+ * BAR.
+ */
+ if (ret < 0 || table->bar != pba->bar)
+ goto out;
+ }
+
+ if (has_msix && (u32)bar_num == pba->bar) {
+ if (pba->bar == table->bar)
+ pba->guest_phys_addr = table->guest_phys_addr + table->size;
+ else
+ pba->guest_phys_addr = region->guest_phys_addr;
+ ret = kvm__register_mmio(kvm, pba->guest_phys_addr,
+ pba->size, false,
+ vfio_pci_msix_pba_access, pdev);
+ goto out;
+ }
+
+ ret = vfio_map_region(kvm, vdev, region);
+out:
+ return ret;
+}
+
+static int vfio_pci_bar_deactivate(struct kvm *kvm,
+ struct pci_device_header *pci_hdr,
+ int bar_num, void *data)
+{
+ struct vfio_device *vdev = data;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_pci_msix_pba *pba = &pdev->msix_pba;
+ struct vfio_pci_msix_table *table = &pdev->msix_table;
+ struct vfio_region *region;
+ bool has_msix, success;
+ int ret;
+
+ assert((u32)bar_num < vdev->info.num_regions);
+
+ region = &vdev->regions[bar_num];
+ has_msix = pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSIX;
+
+ if (has_msix && (u32)bar_num == table->bar) {
+ success = kvm__deregister_mmio(kvm, table->guest_phys_addr);
+ /* kvm__deregister_mmio fails when the region is not found. */
+ ret = (success ? 0 : -ENOENT);
+ /* See vfio_pci_bar_activate(). */
+ if (ret < 0 || table->bar!= pba->bar)
+ goto out;
+ }
+
+ if (has_msix && (u32)bar_num == pba->bar) {
+ success = kvm__deregister_mmio(kvm, pba->guest_phys_addr);
+ ret = (success ? 0 : -ENOENT);
+ goto out;
+ }
+
+ vfio_unmap_region(kvm, region);
+ ret = 0;
+
+out:
+ return ret;
+}
+
+static void vfio_pci_cfg_read(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ u8 offset, void *data, int sz)
+{
+ struct vfio_region_info *info;
+ struct vfio_pci_device *pdev;
+ struct vfio_device *vdev;
+ char base[sz];
+
+ pdev = container_of(pci_hdr, struct vfio_pci_device, hdr);
+ vdev = container_of(pdev, struct vfio_device, pci);
+ info = &vdev->regions[VFIO_PCI_CONFIG_REGION_INDEX].info;
+
+ /* Dummy read in case of side-effects */
+ if (pread(vdev->fd, base, sz, info->offset + offset) != sz)
+ vfio_dev_warn(vdev, "failed to read %d bytes from Configuration Space at 0x%x",
+ sz, offset);
+}
+
+static void vfio_pci_cfg_write(struct kvm *kvm, struct pci_device_header *pci_hdr,
+ u8 offset, void *data, int sz)
+{
+ struct vfio_region_info *info;
+ struct vfio_pci_device *pdev;
+ struct vfio_device *vdev;
+ u32 tmp;
+
+ /* Make sure a larger size will not overrun tmp on the stack. */
+ assert(sz <= 4);
+
+ if (offset == PCI_ROM_ADDRESS)
+ return;
+
+ pdev = container_of(pci_hdr, struct vfio_pci_device, hdr);
+ vdev = container_of(pdev, struct vfio_device, pci);
+ info = &vdev->regions[VFIO_PCI_CONFIG_REGION_INDEX].info;
+
+ if (pwrite(vdev->fd, data, sz, info->offset + offset) != sz)
+ vfio_dev_warn(vdev, "Failed to write %d bytes to Configuration Space at 0x%x",
+ sz, offset);
+
+ /* Handle MSI write now, since it might update the hardware capability */
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSIX)
+ vfio_pci_msix_cap_write(kvm, vdev, offset, data, sz);
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSI)
+ vfio_pci_msi_cap_write(kvm, vdev, offset, data, sz);
+
+ if (pread(vdev->fd, &tmp, sz, info->offset + offset) != sz)
+ vfio_dev_warn(vdev, "Failed to read %d bytes from Configuration Space at 0x%x",
+ sz, offset);
+}
+
+static ssize_t vfio_pci_msi_cap_size(struct msi_cap_64 *cap_hdr)
+{
+ size_t size = 10;
+
+ if (cap_hdr->ctrl & PCI_MSI_FLAGS_64BIT)
+ size += 4;
+ if (cap_hdr->ctrl & PCI_MSI_FLAGS_MASKBIT)
+ size += 10;
+
+ return size;
+}
+
+static ssize_t vfio_pci_cap_size(struct pci_cap_hdr *cap_hdr)
+{
+ switch (cap_hdr->type) {
+ case PCI_CAP_ID_MSIX:
+ return PCI_CAP_MSIX_SIZEOF;
+ case PCI_CAP_ID_MSI:
+ return vfio_pci_msi_cap_size((void *)cap_hdr);
+ default:
+ pr_err("unknown PCI capability 0x%x", cap_hdr->type);
+ return 0;
+ }
+}
+
+static int vfio_pci_add_cap(struct vfio_device *vdev, u8 *virt_hdr,
+ struct pci_cap_hdr *cap, off_t pos)
+{
+ struct pci_cap_hdr *last;
+ struct pci_device_header *hdr = &vdev->pci.hdr;
+
+ cap->next = 0;
+
+ if (!hdr->capabilities) {
+ hdr->capabilities = pos;
+ hdr->status |= PCI_STATUS_CAP_LIST;
+ } else {
+ last = PCI_CAP(virt_hdr, hdr->capabilities);
+
+ while (last->next)
+ last = PCI_CAP(virt_hdr, last->next);
+
+ last->next = pos;
+ }
+
+ memcpy(virt_hdr + pos, cap, vfio_pci_cap_size(cap));
+
+ return 0;
+}
+
+static int vfio_pci_parse_caps(struct vfio_device *vdev)
+{
+ int ret;
+ size_t size;
+ u8 pos, next;
+ struct pci_cap_hdr *cap;
+ u8 virt_hdr[PCI_DEV_CFG_SIZE];
+ struct vfio_pci_device *pdev = &vdev->pci;
+
+ if (!(pdev->hdr.status & PCI_STATUS_CAP_LIST))
+ return 0;
+
+ memset(virt_hdr, 0, PCI_DEV_CFG_SIZE);
+
+ pos = pdev->hdr.capabilities & ~3;
+
+ pdev->hdr.status &= ~PCI_STATUS_CAP_LIST;
+ pdev->hdr.capabilities = 0;
+
+ for (; pos; pos = next) {
+ cap = PCI_CAP(&pdev->hdr, pos);
+ next = cap->next;
+
+ switch (cap->type) {
+ case PCI_CAP_ID_MSIX:
+ ret = vfio_pci_add_cap(vdev, virt_hdr, cap, pos);
+ if (ret)
+ return ret;
+
+ pdev->msix.pos = pos;
+ pdev->irq_modes |= VFIO_PCI_IRQ_MODE_MSIX;
+ break;
+ case PCI_CAP_ID_MSI:
+ ret = vfio_pci_add_cap(vdev, virt_hdr, cap, pos);
+ if (ret)
+ return ret;
+
+ pdev->msi.pos = pos;
+ pdev->irq_modes |= VFIO_PCI_IRQ_MODE_MSI;
+ break;
+ }
+ }
+
+ /* Wipe remaining capabilities */
+ pos = PCI_STD_HEADER_SIZEOF;
+ size = PCI_DEV_CFG_SIZE - PCI_STD_HEADER_SIZEOF;
+ memcpy((void *)&pdev->hdr + pos, virt_hdr + pos, size);
+
+ return 0;
+}
+
+static int vfio_pci_parse_cfg_space(struct vfio_device *vdev)
+{
+ ssize_t sz = PCI_DEV_CFG_SIZE;
+ struct vfio_region_info *info;
+ struct vfio_pci_device *pdev = &vdev->pci;
+
+ if (vdev->info.num_regions < VFIO_PCI_CONFIG_REGION_INDEX) {
+ vfio_dev_err(vdev, "Config Space not found");
+ return -ENODEV;
+ }
+
+ info = &vdev->regions[VFIO_PCI_CONFIG_REGION_INDEX].info;
+ *info = (struct vfio_region_info) {
+ .argsz = sizeof(*info),
+ .index = VFIO_PCI_CONFIG_REGION_INDEX,
+ };
+
+ ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
+ if (!info->size) {
+ vfio_dev_err(vdev, "Config Space has size zero?!");
+ return -EINVAL;
+ }
+
+ /* Read standard headers and capabilities */
+ if (pread(vdev->fd, &pdev->hdr, sz, info->offset) != sz) {
+ vfio_dev_err(vdev, "failed to read %zd bytes of Config Space", sz);
+ return -EIO;
+ }
+
+ /* Strip bit 7, that indicates multifunction */
+ pdev->hdr.header_type &= 0x7f;
+
+ if (pdev->hdr.header_type != PCI_HEADER_TYPE_NORMAL) {
+ vfio_dev_err(vdev, "unsupported header type %u",
+ pdev->hdr.header_type);
+ return -EOPNOTSUPP;
+ }
+
+ if (pdev->hdr.irq_pin)
+ pdev->irq_modes |= VFIO_PCI_IRQ_MODE_INTX;
+
+ vfio_pci_parse_caps(vdev);
+
+ return 0;
+}
+
+static int vfio_pci_fixup_cfg_space(struct vfio_device *vdev)
+{
+ int i;
+ u64 base;
+ ssize_t hdr_sz;
+ struct msix_cap *msix;
+ struct vfio_region_info *info;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_region *region;
+
+ /* Initialise the BARs */
+ for (i = VFIO_PCI_BAR0_REGION_INDEX; i <= VFIO_PCI_BAR5_REGION_INDEX; ++i) {
+ if ((u32)i == vdev->info.num_regions)
+ break;
+
+ region = &vdev->regions[i];
+ /* Construct a fake reg to match what we've mapped. */
+ if (region->is_ioport) {
+ base = (region->port_base & PCI_BASE_ADDRESS_IO_MASK) |
+ PCI_BASE_ADDRESS_SPACE_IO;
+ } else {
+ base = (region->guest_phys_addr &
+ PCI_BASE_ADDRESS_MEM_MASK) |
+ PCI_BASE_ADDRESS_SPACE_MEMORY;
+ }
+
+ pdev->hdr.bar[i] = base;
+
+ if (!base)
+ continue;
+
+ pdev->hdr.bar_size[i] = region->info.size;
+ }
+
+ /* I really can't be bothered to support cardbus. */
+ pdev->hdr.card_bus = 0;
+
+ /*
+ * Nuke the expansion ROM for now. If we want to do this properly,
+ * we need to save its size somewhere and map into the guest.
+ */
+ pdev->hdr.exp_rom_bar = 0;
+
+ /* Plumb in our fake MSI-X capability, if we have it. */
+ msix = pci_find_cap(&pdev->hdr, PCI_CAP_ID_MSIX);
+ if (msix) {
+ /* Add a shortcut to the PBA region for the MMIO handler */
+ int pba_index = VFIO_PCI_BAR0_REGION_INDEX + pdev->msix_pba.bar;
+ pdev->msix_pba.offset = vdev->regions[pba_index].info.offset +
+ (msix->pba_offset & PCI_MSIX_PBA_OFFSET);
+
+ /* Tidy up the capability */
+ msix->table_offset &= PCI_MSIX_TABLE_BIR;
+ msix->pba_offset &= PCI_MSIX_PBA_BIR;
+ if (pdev->msix_table.bar == pdev->msix_pba.bar)
+ msix->pba_offset |= pdev->msix_table.size &
+ PCI_MSIX_PBA_OFFSET;
+ }
+
+ /* Install our fake Configuration Space */
+ info = &vdev->regions[VFIO_PCI_CONFIG_REGION_INDEX].info;
+ hdr_sz = PCI_DEV_CFG_SIZE;
+ if (pwrite(vdev->fd, &pdev->hdr, hdr_sz, info->offset) != hdr_sz) {
+ vfio_dev_err(vdev, "failed to write %zd bytes to Config Space",
+ hdr_sz);
+ return -EIO;
+ }
+
+ /* Register callbacks for cfg accesses */
+ pdev->hdr.cfg_ops = (struct pci_config_operations) {
+ .read = vfio_pci_cfg_read,
+ .write = vfio_pci_cfg_write,
+ };
+
+ pdev->hdr.irq_type = IRQ_TYPE_LEVEL_HIGH;
+
+ return 0;
+}
+
+static int vfio_pci_get_region_info(struct vfio_device *vdev, u32 index,
+ struct vfio_region_info *info)
+{
+ int ret;
+
+ *info = (struct vfio_region_info) {
+ .argsz = sizeof(*info),
+ .index = index,
+ };
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_GET_REGION_INFO, info);
+ if (ret) {
+ ret = -errno;
+ vfio_dev_err(vdev, "cannot get info for BAR %u", index);
+ return ret;
+ }
+
+ if (info->size && !is_power_of_two(info->size)) {
+ vfio_dev_err(vdev, "region is not power of two: 0x%llx",
+ info->size);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int vfio_pci_create_msix_table(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int ret;
+ size_t i;
+ size_t map_size;
+ size_t nr_entries;
+ struct vfio_pci_msi_entry *entries;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_pci_msix_pba *pba = &pdev->msix_pba;
+ struct vfio_pci_msix_table *table = &pdev->msix_table;
+ struct msix_cap *msix = PCI_CAP(&pdev->hdr, pdev->msix.pos);
+ struct vfio_region_info info;
+
+ table->bar = msix->table_offset & PCI_MSIX_TABLE_BIR;
+ pba->bar = msix->pba_offset & PCI_MSIX_TABLE_BIR;
+
+ /*
+ * KVM needs memory regions to be multiple of and aligned on PAGE_SIZE.
+ */
+ nr_entries = (msix->ctrl & PCI_MSIX_FLAGS_QSIZE) + 1;
+ table->size = ALIGN(nr_entries * PCI_MSIX_ENTRY_SIZE, PAGE_SIZE);
+ pba->size = ALIGN(DIV_ROUND_UP(nr_entries, 64), PAGE_SIZE);
+
+ entries = calloc(nr_entries, sizeof(struct vfio_pci_msi_entry));
+ if (!entries)
+ return -ENOMEM;
+
+ for (i = 0; i < nr_entries; i++)
+ entries[i].config.ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
+
+ ret = vfio_pci_get_region_info(vdev, table->bar, &info);
+ if (ret)
+ return ret;
+ if (!info.size)
+ return -EINVAL;
+ map_size = info.size;
+
+ if (table->bar != pba->bar) {
+ ret = vfio_pci_get_region_info(vdev, pba->bar, &info);
+ if (ret)
+ return ret;
+ if (!info.size)
+ return -EINVAL;
+ map_size += info.size;
+ }
+
+ /*
+ * To ease MSI-X cap configuration in case they share the same BAR,
+ * collapse table and pending array. The size of the BAR regions must be
+ * powers of two.
+ */
+ map_size = ALIGN(map_size, PAGE_SIZE);
+ table->guest_phys_addr = pci_get_mmio_block(map_size);
+ if (!table->guest_phys_addr) {
+ pr_err("cannot allocate MMIO space");
+ ret = -ENOMEM;
+ goto out_free;
+ }
+
+ /*
+ * We could map the physical PBA directly into the guest, but it's
+ * likely smaller than a page, and we can only hand full pages to the
+ * guest. Even though the PCI spec disallows sharing a page used for
+ * MSI-X with any other resource, it allows to share the same page
+ * between MSI-X table and PBA. For the sake of isolation, create a
+ * virtual PBA.
+ */
+ pba->guest_phys_addr = table->guest_phys_addr + table->size;
+
+ pdev->msix.entries = entries;
+ pdev->msix.nr_entries = nr_entries;
+
+ return 0;
+
+out_free:
+ free(entries);
+
+ return ret;
+}
+
+static int vfio_pci_create_msi_cap(struct kvm *kvm, struct vfio_pci_device *pdev)
+{
+ struct msi_cap_64 *cap = PCI_CAP(&pdev->hdr, pdev->msi.pos);
+
+ pdev->msi.nr_entries = 1 << ((cap->ctrl & PCI_MSI_FLAGS_QMASK) >> 1),
+ pdev->msi.entries = calloc(pdev->msi.nr_entries,
+ sizeof(struct vfio_pci_msi_entry));
+ if (!pdev->msi.entries)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int vfio_pci_configure_bar(struct kvm *kvm, struct vfio_device *vdev,
+ size_t nr)
+{
+ int ret;
+ u32 bar;
+ size_t map_size;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_region *region;
+
+ if (nr >= vdev->info.num_regions)
+ return 0;
+
+ region = &vdev->regions[nr];
+ bar = pdev->hdr.bar[nr];
+
+ region->vdev = vdev;
+ region->is_ioport = !!(bar & PCI_BASE_ADDRESS_SPACE_IO);
+
+ ret = vfio_pci_get_region_info(vdev, nr, ®ion->info);
+ if (ret)
+ return ret;
+
+ /* Ignore invalid or unimplemented regions */
+ if (!region->info.size)
+ return 0;
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSIX) {
+ /* Trap and emulate MSI-X table */
+ if (nr == pdev->msix_table.bar) {
+ region->guest_phys_addr = pdev->msix_table.guest_phys_addr;
+ return 0;
+ } else if (nr == pdev->msix_pba.bar) {
+ region->guest_phys_addr = pdev->msix_pba.guest_phys_addr;
+ return 0;
+ }
+ }
+
+ if (region->is_ioport) {
+ region->port_base = pci_get_io_port_block(region->info.size);
+ } else {
+ /* Grab some MMIO space in the guest */
+ map_size = ALIGN(region->info.size, PAGE_SIZE);
+ region->guest_phys_addr = pci_get_mmio_block(map_size);
+ }
+
+ return 0;
+}
+
+static int vfio_pci_configure_dev_regions(struct kvm *kvm,
+ struct vfio_device *vdev)
+{
+ int ret;
+ u32 bar;
+ size_t i;
+ bool is_64bit = false;
+ struct vfio_pci_device *pdev = &vdev->pci;
+
+ ret = vfio_pci_parse_cfg_space(vdev);
+ if (ret)
+ return ret;
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSIX) {
+ ret = vfio_pci_create_msix_table(kvm, vdev);
+ if (ret)
+ return ret;
+ }
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSI) {
+ ret = vfio_pci_create_msi_cap(kvm, pdev);
+ if (ret)
+ return ret;
+ }
+
+ for (i = VFIO_PCI_BAR0_REGION_INDEX; i <= VFIO_PCI_BAR5_REGION_INDEX; ++i) {
+ /* Ignore top half of 64-bit BAR */
+ if (is_64bit) {
+ is_64bit = false;
+ continue;
+ }
+
+ ret = vfio_pci_configure_bar(kvm, vdev, i);
+ if (ret)
+ return ret;
+
+ bar = pdev->hdr.bar[i];
+ is_64bit = (bar & PCI_BASE_ADDRESS_SPACE) ==
+ PCI_BASE_ADDRESS_SPACE_MEMORY &&
+ bar & PCI_BASE_ADDRESS_MEM_TYPE_64;
+ }
+
+ /* We've configured the BARs, fake up a Configuration Space */
+ ret = vfio_pci_fixup_cfg_space(vdev);
+ if (ret)
+ return ret;
+
+ return pci__register_bar_regions(kvm, &pdev->hdr, vfio_pci_bar_activate,
+ vfio_pci_bar_deactivate, vdev);
+}
+
+/*
+ * Attempt to update the FD limit, if opening an eventfd for each IRQ vector
+ * would hit the limit. Which is likely to happen when a device uses 2048 MSIs.
+ */
+static int vfio_pci_reserve_irq_fds(size_t num)
+{
+ /*
+ * I counted around 27 fds under normal load. Let's add 100 for good
+ * measure.
+ */
+ static size_t needed = 128;
+ struct rlimit fd_limit, new_limit;
+
+ needed += num;
+
+ if (getrlimit(RLIMIT_NOFILE, &fd_limit)) {
+ perror("getrlimit(RLIMIT_NOFILE)");
+ return 0;
+ }
+
+ if (fd_limit.rlim_cur >= needed)
+ return 0;
+
+ new_limit.rlim_cur = needed;
+
+ if (fd_limit.rlim_max < needed)
+ /* Try to bump hard limit (root only) */
+ new_limit.rlim_max = needed;
+ else
+ new_limit.rlim_max = fd_limit.rlim_max;
+
+ if (setrlimit(RLIMIT_NOFILE, &new_limit)) {
+ perror("setrlimit(RLIMIT_NOFILE)");
+ pr_warning("not enough FDs for full MSI-X support (estimated need: %zu)",
+ (size_t)(needed - fd_limit.rlim_cur));
+ }
+
+ return 0;
+}
+
+static int vfio_pci_init_msis(struct kvm *kvm, struct vfio_device *vdev,
+ struct vfio_pci_msi_common *msis)
+{
+ int ret;
+ size_t i;
+ int *eventfds;
+ size_t irq_set_size;
+ struct vfio_pci_msi_entry *entry;
+ size_t nr_entries = msis->nr_entries;
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO, &msis->info);
+ if (ret || msis->info.count == 0) {
+ vfio_dev_err(vdev, "no MSI reported by VFIO");
+ return -ENODEV;
+ }
+
+ if (!(msis->info.flags & VFIO_IRQ_INFO_EVENTFD)) {
+ vfio_dev_err(vdev, "interrupt not EVENTFD capable");
+ return -EINVAL;
+ }
+
+ if (msis->info.count != nr_entries) {
+ vfio_dev_err(vdev, "invalid number of MSIs reported by VFIO");
+ return -EINVAL;
+ }
+
+ mutex_init(&msis->mutex);
+
+ vfio_pci_reserve_irq_fds(nr_entries);
+
+ irq_set_size = sizeof(struct vfio_irq_set) + nr_entries * sizeof(int);
+ msis->irq_set = malloc(irq_set_size);
+ if (!msis->irq_set)
+ return -ENOMEM;
+
+ *msis->irq_set = (struct vfio_irq_set) {
+ .argsz = irq_set_size,
+ .flags = VFIO_IRQ_SET_DATA_EVENTFD |
+ VFIO_IRQ_SET_ACTION_TRIGGER,
+ .index = msis->info.index,
+ .start = 0,
+ .count = nr_entries,
+ };
+
+ eventfds = (void *)msis->irq_set + sizeof(struct vfio_irq_set);
+
+ for (i = 0; i < nr_entries; i++) {
+ entry = &msis->entries[i];
+ entry->gsi = -1;
+ entry->eventfd = -1;
+ msi_set_masked(entry->virt_state, true);
+ msi_set_masked(entry->phys_state, true);
+ eventfds[i] = -1;
+ }
+
+ return 0;
+}
+
+static void vfio_pci_disable_intx(struct kvm *kvm, struct vfio_device *vdev)
+{
+ struct vfio_pci_device *pdev = &vdev->pci;
+ int gsi = pdev->intx_gsi;
+ struct vfio_irq_set irq_set = {
+ .argsz = sizeof(irq_set),
+ .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER,
+ .index = VFIO_PCI_INTX_IRQ_INDEX,
+ };
+
+ if (pdev->intx_fd == -1)
+ return;
+
+ pr_debug("user requested MSI, disabling INTx %d", gsi);
+
+ ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &irq_set);
+ irq__del_irqfd(kvm, gsi, pdev->intx_fd);
+
+ close(pdev->intx_fd);
+ close(pdev->unmask_fd);
+ pdev->intx_fd = -1;
+}
+
+static int vfio_pci_enable_intx(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int ret;
+ int trigger_fd, unmask_fd;
+ union vfio_irq_eventfd trigger;
+ union vfio_irq_eventfd unmask;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ int gsi = pdev->intx_gsi;
+
+ if (pdev->intx_fd != -1)
+ return 0;
+
+ /*
+ * PCI IRQ is level-triggered, so we use two eventfds. trigger_fd
+ * signals an interrupt from host to guest, and unmask_fd signals the
+ * deassertion of the line from guest to host.
+ */
+ trigger_fd = eventfd(0, 0);
+ if (trigger_fd < 0) {
+ vfio_dev_err(vdev, "failed to create trigger eventfd");
+ return trigger_fd;
+ }
+
+ unmask_fd = eventfd(0, 0);
+ if (unmask_fd < 0) {
+ vfio_dev_err(vdev, "failed to create unmask eventfd");
+ close(trigger_fd);
+ return unmask_fd;
+ }
+
+ ret = irq__add_irqfd(kvm, gsi, trigger_fd, unmask_fd);
+ if (ret)
+ goto err_close;
+
+ trigger.irq = (struct vfio_irq_set) {
+ .argsz = sizeof(trigger),
+ .flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER,
+ .index = VFIO_PCI_INTX_IRQ_INDEX,
+ .start = 0,
+ .count = 1,
+ };
+ set_vfio_irq_eventd_payload(&trigger, trigger_fd);
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &trigger);
+ if (ret < 0) {
+ vfio_dev_err(vdev, "failed to setup VFIO IRQ");
+ goto err_delete_line;
+ }
+
+ unmask.irq = (struct vfio_irq_set) {
+ .argsz = sizeof(unmask),
+ .flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_UNMASK,
+ .index = VFIO_PCI_INTX_IRQ_INDEX,
+ .start = 0,
+ .count = 1,
+ };
+ set_vfio_irq_eventd_payload(&unmask, unmask_fd);
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &unmask);
+ if (ret < 0) {
+ vfio_dev_err(vdev, "failed to setup unmask IRQ");
+ goto err_remove_event;
+ }
+
+ pdev->intx_fd = trigger_fd;
+ pdev->unmask_fd = unmask_fd;
+
+ return 0;
+
+err_remove_event:
+ /* Remove trigger event */
+ trigger.irq.flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER;
+ trigger.irq.count = 0;
+ ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, &trigger);
+
+err_delete_line:
+ irq__del_irqfd(kvm, gsi, trigger_fd);
+
+err_close:
+ close(trigger_fd);
+ close(unmask_fd);
+ return ret;
+}
+
+static int vfio_pci_init_intx(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int ret;
+ struct vfio_pci_device *pdev = &vdev->pci;
+ struct vfio_irq_info irq_info = {
+ .argsz = sizeof(irq_info),
+ .index = VFIO_PCI_INTX_IRQ_INDEX,
+ };
+
+ vfio_pci_reserve_irq_fds(2);
+
+ ret = ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info);
+ if (ret || irq_info.count == 0) {
+ vfio_dev_err(vdev, "no INTx reported by VFIO");
+ return -ENODEV;
+ }
+
+ if (!(irq_info.flags & VFIO_IRQ_INFO_EVENTFD)) {
+ vfio_dev_err(vdev, "interrupt not eventfd capable");
+ return -EINVAL;
+ }
+
+ if (!(irq_info.flags & VFIO_IRQ_INFO_AUTOMASKED)) {
+ vfio_dev_err(vdev, "INTx interrupt not AUTOMASKED");
+ return -EINVAL;
+ }
+
+ /* Guest is going to ovewrite our irq_line... */
+ pdev->intx_gsi = pdev->hdr.irq_line - KVM_IRQ_OFFSET;
+
+ pdev->intx_fd = -1;
+
+ return 0;
+}
+
+static int vfio_pci_configure_dev_irqs(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int ret = 0;
+ struct vfio_pci_device *pdev = &vdev->pci;
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSIX) {
+ pdev->msix.info = (struct vfio_irq_info) {
+ .argsz = sizeof(pdev->msix.info),
+ .index = VFIO_PCI_MSIX_IRQ_INDEX,
+ };
+ ret = vfio_pci_init_msis(kvm, vdev, &pdev->msix);
+ if (ret)
+ return ret;
+ }
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_MSI) {
+ pdev->msi.info = (struct vfio_irq_info) {
+ .argsz = sizeof(pdev->msi.info),
+ .index = VFIO_PCI_MSI_IRQ_INDEX,
+ };
+ ret = vfio_pci_init_msis(kvm, vdev, &pdev->msi);
+ if (ret)
+ return ret;
+ }
+
+ if (pdev->irq_modes & VFIO_PCI_IRQ_MODE_INTX) {
+ pci__assign_irq(&vdev->pci.hdr);
+
+ ret = vfio_pci_init_intx(kvm, vdev);
+ if (ret)
+ return ret;
+
+ ret = vfio_pci_enable_intx(kvm, vdev);
+ }
+
+ return ret;
+}
+
+int vfio_pci_setup_device(struct kvm *kvm, struct vfio_device *vdev)
+{
+ int ret;
+
+ ret = vfio_pci_configure_dev_regions(kvm, vdev);
+ if (ret) {
+ vfio_dev_err(vdev, "failed to configure regions");
+ return ret;
+ }
+
+ vdev->dev_hdr = (struct device_header) {
+ .bus_type = DEVICE_BUS_PCI,
+ .data = &vdev->pci.hdr,
+ };
+
+ ret = device__register(&vdev->dev_hdr);
+ if (ret) {
+ vfio_dev_err(vdev, "failed to register VFIO device");
+ return ret;
+ }
+
+ ret = vfio_pci_configure_dev_irqs(kvm, vdev);
+ if (ret) {
+ vfio_dev_err(vdev, "failed to configure IRQs");
+ return ret;
+ }
+
+ return 0;
+}
+
+void vfio_pci_teardown_device(struct kvm *kvm, struct vfio_device *vdev)
+{
+ size_t i;
+ struct vfio_pci_device *pdev = &vdev->pci;
+
+ for (i = 0; i < vdev->info.num_regions; i++)
+ vfio_unmap_region(kvm, &vdev->regions[i]);
+
+ device__unregister(&vdev->dev_hdr);
+
+ free(pdev->msix.irq_set);
+ free(pdev->msix.entries);
+ free(pdev->msi.irq_set);
+ free(pdev->msi.entries);
+}
diff --git a/kvmtool/virtio/9p-pdu.c b/kvmtool/virtio/9p-pdu.c
new file mode 100644
index 0000000..c0b95e0
--- /dev/null
+++ b/kvmtool/virtio/9p-pdu.c
@@ -0,0 +1,289 @@
+#include "kvm/util.h"
+#include "kvm/virtio-9p.h"
+
+#include <endian.h>
+#include <stdint.h>
+
+#include <linux/compiler.h>
+#include <linux/9p.h>
+
+static void virtio_p9_pdu_read(struct p9_pdu *pdu, void *data, size_t size)
+{
+ size_t len;
+ int i, copied = 0;
+ u16 iov_cnt = pdu->out_iov_cnt;
+ size_t offset = pdu->read_offset;
+ struct iovec *iov = pdu->out_iov;
+
+ for (i = 0; i < iov_cnt && size; i++) {
+ if (offset >= iov[i].iov_len) {
+ offset -= iov[i].iov_len;
+ continue;
+ } else {
+ len = MIN(iov[i].iov_len - offset, size);
+ memcpy(data, iov[i].iov_base + offset, len);
+ size -= len;
+ data += len;
+ offset = 0;
+ copied += len;
+ }
+ }
+ pdu->read_offset += copied;
+}
+
+static void virtio_p9_pdu_write(struct p9_pdu *pdu,
+ const void *data, size_t size)
+{
+ size_t len;
+ int i, copied = 0;
+ u16 iov_cnt = pdu->in_iov_cnt;
+ size_t offset = pdu->write_offset;
+ struct iovec *iov = pdu->in_iov;
+
+ for (i = 0; i < iov_cnt && size; i++) {
+ if (offset >= iov[i].iov_len) {
+ offset -= iov[i].iov_len;
+ continue;
+ } else {
+ len = MIN(iov[i].iov_len - offset, size);
+ memcpy(iov[i].iov_base + offset, data, len);
+ size -= len;
+ data += len;
+ offset = 0;
+ copied += len;
+ }
+ }
+ pdu->write_offset += copied;
+}
+
+static void virtio_p9_wstat_free(struct p9_wstat *stbuf)
+{
+ free(stbuf->name);
+ free(stbuf->uid);
+ free(stbuf->gid);
+ free(stbuf->muid);
+}
+
+static int virtio_p9_decode(struct p9_pdu *pdu, const char *fmt, va_list ap)
+{
+ int retval = 0;
+ const char *ptr;
+
+ for (ptr = fmt; *ptr; ptr++) {
+ switch (*ptr) {
+ case 'b':
+ {
+ int8_t *val = va_arg(ap, int8_t *);
+ virtio_p9_pdu_read(pdu, val, sizeof(*val));
+ }
+ break;
+ case 'w':
+ {
+ int16_t le_val;
+ int16_t *val = va_arg(ap, int16_t *);
+ virtio_p9_pdu_read(pdu, &le_val, sizeof(le_val));
+ *val = le16toh(le_val);
+ }
+ break;
+ case 'd':
+ {
+ int32_t le_val;
+ int32_t *val = va_arg(ap, int32_t *);
+ virtio_p9_pdu_read(pdu, &le_val, sizeof(le_val));
+ *val = le32toh(le_val);
+ }
+ break;
+ case 'q':
+ {
+ int64_t le_val;
+ int64_t *val = va_arg(ap, int64_t *);
+ virtio_p9_pdu_read(pdu, &le_val, sizeof(le_val));
+ *val = le64toh(le_val);
+ }
+ break;
+ case 's':
+ {
+ int16_t len;
+ char **str = va_arg(ap, char **);
+
+ virtio_p9_pdu_readf(pdu, "w", &len);
+ *str = malloc(len + 1);
+ if (*str == NULL) {
+ retval = ENOMEM;
+ break;
+ }
+ virtio_p9_pdu_read(pdu, *str, len);
+ (*str)[len] = 0;
+ }
+ break;
+ case 'Q':
+ {
+ struct p9_qid *qid = va_arg(ap, struct p9_qid *);
+ retval = virtio_p9_pdu_readf(pdu, "bdq",
+ &qid->type, &qid->version,
+ &qid->path);
+ }
+ break;
+ case 'S':
+ {
+ struct p9_wstat *stbuf = va_arg(ap, struct p9_wstat *);
+ memset(stbuf, 0, sizeof(struct p9_wstat));
+ stbuf->n_uid = KUIDT_INIT(-1);
+ stbuf->n_gid = KGIDT_INIT(-1);
+ stbuf->n_muid = KUIDT_INIT(-1);
+ retval = virtio_p9_pdu_readf(pdu, "wwdQdddqssss",
+ &stbuf->size, &stbuf->type,
+ &stbuf->dev, &stbuf->qid,
+ &stbuf->mode, &stbuf->atime,
+ &stbuf->mtime, &stbuf->length,
+ &stbuf->name, &stbuf->uid,
+ &stbuf->gid, &stbuf->muid);
+ if (retval)
+ virtio_p9_wstat_free(stbuf);
+ }
+ break;
+ case 'I':
+ {
+ struct p9_iattr_dotl *p9attr = va_arg(ap,
+ struct p9_iattr_dotl *);
+
+ retval = virtio_p9_pdu_readf(pdu, "ddddqqqqq",
+ &p9attr->valid,
+ &p9attr->mode,
+ &p9attr->uid,
+ &p9attr->gid,
+ &p9attr->size,
+ &p9attr->atime_sec,
+ &p9attr->atime_nsec,
+ &p9attr->mtime_sec,
+ &p9attr->mtime_nsec);
+ }
+ break;
+ default:
+ retval = EINVAL;
+ break;
+ }
+ }
+ return retval;
+}
+
+static int virtio_p9_pdu_encode(struct p9_pdu *pdu, const char *fmt, va_list ap)
+{
+ int retval = 0;
+ const char *ptr;
+
+ for (ptr = fmt; *ptr; ptr++) {
+ switch (*ptr) {
+ case 'b':
+ {
+ int8_t val = va_arg(ap, int);
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 'w':
+ {
+ int16_t val = htole16(va_arg(ap, int));
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 'd':
+ {
+ int32_t val = htole32(va_arg(ap, int32_t));
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 'q':
+ {
+ int64_t val = htole64(va_arg(ap, int64_t));
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 's':
+ {
+ uint16_t len = 0;
+ const char *s = va_arg(ap, char *);
+ if (s)
+ len = MIN(strlen(s), USHRT_MAX);
+ virtio_p9_pdu_writef(pdu, "w", len);
+ virtio_p9_pdu_write(pdu, s, len);
+ }
+ break;
+ case 'Q':
+ {
+ struct p9_qid *qid = va_arg(ap, struct p9_qid *);
+ retval = virtio_p9_pdu_writef(pdu, "bdq",
+ qid->type, qid->version,
+ qid->path);
+ }
+ break;
+ case 'S':
+ {
+ struct p9_wstat *stbuf = va_arg(ap, struct p9_wstat *);
+ retval = virtio_p9_pdu_writef(pdu, "wwdQdddqssss",
+ stbuf->size, stbuf->type,
+ stbuf->dev, &stbuf->qid,
+ stbuf->mode, stbuf->atime,
+ stbuf->mtime, stbuf->length,
+ stbuf->name, stbuf->uid,
+ stbuf->gid, stbuf->muid);
+ }
+ break;
+ case 'A':
+ {
+ struct p9_stat_dotl *stbuf = va_arg(ap,
+ struct p9_stat_dotl *);
+ retval = virtio_p9_pdu_writef(pdu,
+ "qQdddqqqqqqqqqqqqqqq",
+ stbuf->st_result_mask,
+ &stbuf->qid,
+ stbuf->st_mode,
+ stbuf->st_uid,
+ stbuf->st_gid,
+ stbuf->st_nlink,
+ stbuf->st_rdev,
+ stbuf->st_size,
+ stbuf->st_blksize,
+ stbuf->st_blocks,
+ stbuf->st_atime_sec,
+ stbuf->st_atime_nsec,
+ stbuf->st_mtime_sec,
+ stbuf->st_mtime_nsec,
+ stbuf->st_ctime_sec,
+ stbuf->st_ctime_nsec,
+ stbuf->st_btime_sec,
+ stbuf->st_btime_nsec,
+ stbuf->st_gen,
+ stbuf->st_data_version);
+ }
+ break;
+ default:
+ retval = EINVAL;
+ break;
+ }
+ }
+ return retval;
+}
+
+int virtio_p9_pdu_readf(struct p9_pdu *pdu, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ va_start(ap, fmt);
+ ret = virtio_p9_decode(pdu, fmt, ap);
+ va_end(ap);
+
+ return ret;
+}
+
+int virtio_p9_pdu_writef(struct p9_pdu *pdu, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ va_start(ap, fmt);
+ ret = virtio_p9_pdu_encode(pdu, fmt, ap);
+ va_end(ap);
+
+ return ret;
+}
diff --git a/kvmtool/virtio/9p.c b/kvmtool/virtio/9p.c
new file mode 100644
index 0000000..b78f2b3
--- /dev/null
+++ b/kvmtool/virtio/9p.c
@@ -0,0 +1,1609 @@
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/ioport.h"
+#include "kvm/util.h"
+#include "kvm/threadpool.h"
+#include "kvm/irq.h"
+#include "kvm/virtio-9p.h"
+#include "kvm/guest_compat.h"
+#include "kvm/builtin-setup.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <sys/sysmacros.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/vfs.h>
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_9p.h>
+#include <linux/9p.h>
+
+static LIST_HEAD(devs);
+static int compat_id = -1;
+
+static int insert_new_fid(struct p9_dev *dev, struct p9_fid *fid);
+static struct p9_fid *find_or_create_fid(struct p9_dev *dev, u32 fid)
+{
+ struct rb_node *node = dev->fids.rb_node;
+ struct p9_fid *pfid = NULL;
+ size_t len;
+
+ while (node) {
+ struct p9_fid *cur = rb_entry(node, struct p9_fid, node);
+
+ if (fid < cur->fid) {
+ node = node->rb_left;
+ } else if (fid > cur->fid) {
+ node = node->rb_right;
+ } else {
+ return cur;
+ }
+ }
+
+ pfid = calloc(sizeof(*pfid), 1);
+ if (!pfid)
+ return NULL;
+
+ len = strlen(dev->root_dir);
+ if (len >= sizeof(pfid->abs_path)) {
+ free(pfid);
+ return NULL;
+ }
+
+ pfid->fid = fid;
+ strcpy(pfid->abs_path, dev->root_dir);
+ pfid->path = pfid->abs_path + strlen(pfid->abs_path);
+
+ insert_new_fid(dev, pfid);
+
+ return pfid;
+}
+
+static int insert_new_fid(struct p9_dev *dev, struct p9_fid *fid)
+{
+ struct rb_node **node = &(dev->fids.rb_node), *parent = NULL;
+
+ while (*node) {
+ int result = fid->fid - rb_entry(*node, struct p9_fid, node)->fid;
+
+ parent = *node;
+ if (result < 0)
+ node = &((*node)->rb_left);
+ else if (result > 0)
+ node = &((*node)->rb_right);
+ else
+ return -EEXIST;
+ }
+
+ rb_link_node(&fid->node, parent, node);
+ rb_insert_color(&fid->node, &dev->fids);
+ return 0;
+}
+
+static struct p9_fid *get_fid(struct p9_dev *p9dev, int fid)
+{
+ struct p9_fid *new;
+
+ new = find_or_create_fid(p9dev, fid);
+
+ return new;
+}
+
+static void stat2qid(struct stat *st, struct p9_qid *qid)
+{
+ *qid = (struct p9_qid) {
+ .path = st->st_ino,
+ .version = st->st_mtime,
+ };
+
+ if (S_ISDIR(st->st_mode))
+ qid->type |= P9_QTDIR;
+}
+
+static void close_fid(struct p9_dev *p9dev, u32 fid)
+{
+ struct p9_fid *pfid = get_fid(p9dev, fid);
+
+ if (pfid->fd > 0)
+ close(pfid->fd);
+
+ if (pfid->dir)
+ closedir(pfid->dir);
+
+ rb_erase(&pfid->node, &p9dev->fids);
+ free(pfid);
+}
+
+static void virtio_p9_set_reply_header(struct p9_pdu *pdu, u32 size)
+{
+ u8 cmd;
+ u16 tag;
+
+ pdu->read_offset = sizeof(u32);
+ virtio_p9_pdu_readf(pdu, "bw", &cmd, &tag);
+ pdu->write_offset = 0;
+ /* cmd + 1 is the reply message */
+ virtio_p9_pdu_writef(pdu, "dbw", size, cmd + 1, tag);
+}
+
+static u16 virtio_p9_update_iov_cnt(struct iovec iov[], u32 count, int iov_cnt)
+{
+ int i;
+ u32 total = 0;
+ for (i = 0; (i < iov_cnt) && (total < count); i++) {
+ if (total + iov[i].iov_len > count) {
+ /* we don't need this iov fully */
+ iov[i].iov_len -= ((total + iov[i].iov_len) - count);
+ i++;
+ break;
+ }
+ total += iov[i].iov_len;
+ }
+ return i;
+}
+
+static void virtio_p9_error_reply(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, int err, u32 *outlen)
+{
+ u16 tag;
+
+ /* EMFILE at server implies ENFILE for the VM */
+ if (err == EMFILE)
+ err = ENFILE;
+
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", err);
+ *outlen = pdu->write_offset;
+
+ /* read the tag from input */
+ pdu->read_offset = sizeof(u32) + sizeof(u8);
+ virtio_p9_pdu_readf(pdu, "w", &tag);
+
+ /* Update the header */
+ pdu->write_offset = 0;
+ virtio_p9_pdu_writef(pdu, "dbw", *outlen, P9_RLERROR, tag);
+}
+
+static void virtio_p9_version(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 msize;
+ char *version;
+ virtio_p9_pdu_readf(pdu, "ds", &msize, &version);
+ /*
+ * reply with the same msize the client sent us
+ * Error out if the request is not for 9P2000.L
+ */
+ if (!strcmp(version, VIRTIO_9P_VERSION_DOTL))
+ virtio_p9_pdu_writef(pdu, "ds", msize, version);
+ else
+ virtio_p9_pdu_writef(pdu, "ds", msize, "unknown");
+
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(version);
+ return;
+}
+
+static void virtio_p9_clunk(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid;
+
+ virtio_p9_pdu_readf(pdu, "d", &fid);
+ close_fid(p9dev, fid);
+
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+}
+
+/*
+ * FIXME!! Need to map to protocol independent value. Upstream
+ * 9p also have the same BUG
+ */
+static int virtio_p9_openflags(int flags)
+{
+ flags &= ~(O_NOCTTY | O_ASYNC | O_CREAT | O_DIRECT);
+ flags |= O_NOFOLLOW;
+ return flags;
+}
+
+static bool is_dir(struct p9_fid *fid)
+{
+ struct stat st;
+
+ stat(fid->abs_path, &st);
+
+ return S_ISDIR(st.st_mode);
+}
+
+/* path is always absolute */
+static bool path_is_illegal(const char *path)
+{
+ size_t len;
+
+ if (strstr(path, "/../") != NULL)
+ return true;
+
+ len = strlen(path);
+ if (len >= 3 && strcmp(path + len - 3, "/..") == 0)
+ return true;
+
+ return false;
+}
+
+static int get_full_path_helper(char *full_path, size_t size,
+ const char *dirname, const char *name)
+{
+ int ret;
+
+ ret = snprintf(full_path, size, "%s/%s", dirname, name);
+ if (ret >= (int)size) {
+ errno = ENAMETOOLONG;
+ return -1;
+ }
+
+ if (path_is_illegal(full_path)) {
+ errno = EACCES;
+ return -1;
+ }
+
+ return 0;
+}
+
+static int get_full_path(char *full_path, size_t size, struct p9_fid *fid,
+ const char *name)
+{
+ return get_full_path_helper(full_path, size, fid->abs_path, name);
+}
+
+static int stat_rel(struct p9_dev *p9dev, const char *path, struct stat *st)
+{
+ char full_path[PATH_MAX];
+
+ if (get_full_path_helper(full_path, sizeof(full_path), p9dev->root_dir, path) != 0)
+ return -1;
+
+ if (lstat(full_path, st) != 0)
+ return -1;
+
+ return 0;
+}
+
+static void virtio_p9_open(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid, flags;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *new_fid;
+
+
+ virtio_p9_pdu_readf(pdu, "dd", &fid, &flags);
+ new_fid = get_fid(p9dev, fid);
+
+ if (lstat(new_fid->abs_path, &st) < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+
+ if (is_dir(new_fid)) {
+ new_fid->dir = opendir(new_fid->abs_path);
+ if (!new_fid->dir)
+ goto err_out;
+ } else {
+ new_fid->fd = open(new_fid->abs_path,
+ virtio_p9_openflags(flags));
+ if (new_fid->fd < 0)
+ goto err_out;
+ }
+ /* FIXME!! need ot send proper iounit */
+ virtio_p9_pdu_writef(pdu, "Qd", &qid, 0);
+
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_create(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int fd, ret;
+ char *name;
+ size_t size;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *dfid;
+ char full_path[PATH_MAX];
+ char *tmp_path;
+ u32 dfid_val, flags, mode, gid;
+
+ virtio_p9_pdu_readf(pdu, "dsddd", &dfid_val,
+ &name, &flags, &mode, &gid);
+ dfid = get_fid(p9dev, dfid_val);
+
+ if (get_full_path(full_path, sizeof(full_path), dfid, name) != 0)
+ goto err_out;
+
+ size = sizeof(dfid->abs_path) - (dfid->path - dfid->abs_path);
+
+ tmp_path = strdup(dfid->path);
+ if (!tmp_path)
+ goto err_out;
+
+ ret = snprintf(dfid->path, size, "%s/%s", tmp_path, name);
+ free(tmp_path);
+ if (ret >= (int)size) {
+ errno = ENAMETOOLONG;
+ if (size > 0)
+ dfid->path[size] = '\x00';
+ goto err_out;
+ }
+
+ flags = virtio_p9_openflags(flags);
+
+ fd = open(full_path, flags | O_CREAT, mode);
+ if (fd < 0)
+ goto err_out;
+ dfid->fd = fd;
+
+ if (lstat(full_path, &st) < 0)
+ goto err_out;
+
+ ret = chmod(full_path, mode & 0777);
+ if (ret < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Qd", &qid, 0);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(name);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_mkdir(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *dfid;
+ char full_path[PATH_MAX];
+ u32 dfid_val, mode, gid;
+
+ virtio_p9_pdu_readf(pdu, "dsdd", &dfid_val,
+ &name, &mode, &gid);
+ dfid = get_fid(p9dev, dfid_val);
+
+ if (get_full_path(full_path, sizeof(full_path), dfid, name) != 0)
+ goto err_out;
+
+ ret = mkdir(full_path, mode);
+ if (ret < 0)
+ goto err_out;
+
+ if (lstat(full_path, &st) < 0)
+ goto err_out;
+
+ ret = chmod(full_path, mode & 0777);
+ if (ret < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Qd", &qid, 0);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(name);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static int join_path(struct p9_fid *fid, const char *name)
+{
+ size_t len, size;
+
+ size = sizeof(fid->abs_path) - (fid->path - fid->abs_path);
+ len = strlen(name);
+ if (len >= size)
+ return -1;
+
+ strncpy(fid->path, name, size);
+ return 0;
+}
+
+static void virtio_p9_walk(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u8 i;
+ u16 nwqid;
+ u16 nwname;
+ struct p9_qid wqid;
+ struct p9_fid *new_fid, *old_fid;
+ u32 fid_val, newfid_val;
+
+
+ virtio_p9_pdu_readf(pdu, "ddw", &fid_val, &newfid_val, &nwname);
+ new_fid = get_fid(p9dev, newfid_val);
+
+ nwqid = 0;
+ if (nwname) {
+ struct p9_fid *fid = get_fid(p9dev, fid_val);
+
+ if (join_path(new_fid, fid->path) != 0) {
+ errno = ENAMETOOLONG;
+ goto err_out;
+ }
+
+ /* skip the space for count */
+ pdu->write_offset += sizeof(u16);
+ for (i = 0; i < nwname; i++) {
+ struct stat st;
+ char tmp[PATH_MAX] = {0};
+ char *str;
+ int ret;
+
+ virtio_p9_pdu_readf(pdu, "s", &str);
+
+ /* Format the new path we're 'walk'ing into */
+ ret = snprintf(tmp, sizeof(tmp), "%s/%s", new_fid->path, str);
+ if (ret >= (int)sizeof(tmp)) {
+ errno = ENAMETOOLONG;
+ goto err_out;
+ }
+
+ free(str);
+
+ if (stat_rel(p9dev, tmp, &st) != 0)
+ goto err_out;
+
+ stat2qid(&st, &wqid);
+ if (join_path(new_fid, tmp) != 0) {
+ errno = ENAMETOOLONG;
+ goto err_out;
+ }
+ new_fid->uid = fid->uid;
+ nwqid++;
+ virtio_p9_pdu_writef(pdu, "Q", &wqid);
+ }
+ } else {
+ /*
+ * update write_offset so our outlen get correct value
+ */
+ pdu->write_offset += sizeof(u16);
+ old_fid = get_fid(p9dev, fid_val);
+ if (join_path(new_fid, old_fid->path) != 0) {
+ errno = ENAMETOOLONG;
+ goto err_out;
+ }
+ new_fid->uid = old_fid->uid;
+ }
+ *outlen = pdu->write_offset;
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", nwqid);
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_attach(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ char *uname;
+ char *aname;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *fid;
+ u32 fid_val, afid, uid;
+
+ virtio_p9_pdu_readf(pdu, "ddssd", &fid_val, &afid,
+ &uname, &aname, &uid);
+
+ free(uname);
+ free(aname);
+
+ if (lstat(p9dev->root_dir, &st) < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+
+ fid = get_fid(p9dev, fid_val);
+ fid->uid = uid;
+ if (join_path(fid, "/") != 0) {
+ errno = ENAMETOOLONG;
+ goto err_out;
+ }
+
+ virtio_p9_pdu_writef(pdu, "Q", &qid);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_fill_stat(struct p9_dev *p9dev,
+ struct stat *st, struct p9_stat_dotl *statl)
+{
+ memset(statl, 0, sizeof(*statl));
+ statl->st_mode = st->st_mode;
+ statl->st_nlink = st->st_nlink;
+ statl->st_uid = KUIDT_INIT(st->st_uid);
+ statl->st_gid = KGIDT_INIT(st->st_gid);
+ statl->st_rdev = st->st_rdev;
+ statl->st_size = st->st_size;
+ statl->st_blksize = st->st_blksize;
+ statl->st_blocks = st->st_blocks;
+ statl->st_atime_sec = st->st_atime;
+ statl->st_atime_nsec = st->st_atim.tv_nsec;
+ statl->st_mtime_sec = st->st_mtime;
+ statl->st_mtime_nsec = st->st_mtim.tv_nsec;
+ statl->st_ctime_sec = st->st_ctime;
+ statl->st_ctime_nsec = st->st_ctim.tv_nsec;
+ /* Currently we only support BASIC fields in stat */
+ statl->st_result_mask = P9_STATS_BASIC;
+ stat2qid(st, &statl->qid);
+}
+
+static void virtio_p9_read(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u64 offset;
+ u32 fid_val;
+ u16 iov_cnt;
+ void *iov_base;
+ size_t iov_len;
+ u32 count, rcount;
+ struct p9_fid *fid;
+
+
+ rcount = 0;
+ virtio_p9_pdu_readf(pdu, "dqd", &fid_val, &offset, &count);
+ fid = get_fid(p9dev, fid_val);
+
+ iov_base = pdu->in_iov[0].iov_base;
+ iov_len = pdu->in_iov[0].iov_len;
+ iov_cnt = pdu->in_iov_cnt;
+ pdu->in_iov[0].iov_base += VIRTIO_9P_HDR_LEN + sizeof(u32);
+ pdu->in_iov[0].iov_len -= VIRTIO_9P_HDR_LEN + sizeof(u32);
+ pdu->in_iov_cnt = virtio_p9_update_iov_cnt(pdu->in_iov,
+ count,
+ pdu->in_iov_cnt);
+ rcount = preadv(fid->fd, pdu->in_iov,
+ pdu->in_iov_cnt, offset);
+ if (rcount > count)
+ rcount = count;
+ /*
+ * Update the iov_base back, so that rest of
+ * pdu_writef works correctly.
+ */
+ pdu->in_iov[0].iov_base = iov_base;
+ pdu->in_iov[0].iov_len = iov_len;
+ pdu->in_iov_cnt = iov_cnt;
+
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", rcount);
+ *outlen = pdu->write_offset + rcount;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+}
+
+static int virtio_p9_dentry_size(struct dirent *dent)
+{
+ /*
+ * Size of each dirent:
+ * qid(13) + offset(8) + type(1) + name_len(2) + name
+ */
+ return 24 + strlen(dent->d_name);
+}
+
+static void virtio_p9_readdir(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid_val;
+ u32 count, rcount;
+ struct stat st;
+ struct p9_fid *fid;
+ struct dirent *dent;
+ u64 offset, old_offset;
+
+ rcount = 0;
+ virtio_p9_pdu_readf(pdu, "dqd", &fid_val, &offset, &count);
+ fid = get_fid(p9dev, fid_val);
+
+ if (!is_dir(fid)) {
+ errno = EINVAL;
+ goto err_out;
+ }
+
+ /* Move the offset specified */
+ seekdir(fid->dir, offset);
+
+ old_offset = offset;
+ /* If reading a dir, fill the buffer with p9_stat entries */
+ dent = readdir(fid->dir);
+
+ /* Skip the space for writing count */
+ pdu->write_offset += sizeof(u32);
+ while (dent) {
+ u32 read;
+ struct p9_qid qid;
+
+ if ((rcount + virtio_p9_dentry_size(dent)) > count) {
+ /* seek to the previous offset and return */
+ seekdir(fid->dir, old_offset);
+ break;
+ }
+ old_offset = dent->d_off;
+ if (stat_rel(p9dev, dent->d_name, &st) != 0)
+ memset(&st, -1, sizeof(st));
+ stat2qid(&st, &qid);
+ read = pdu->write_offset;
+ virtio_p9_pdu_writef(pdu, "Qqbs", &qid, dent->d_off,
+ dent->d_type, dent->d_name);
+ rcount += pdu->write_offset - read;
+ dent = readdir(fid->dir);
+ }
+
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", rcount);
+ *outlen = pdu->write_offset + rcount;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+
+static void virtio_p9_getattr(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid_val;
+ struct stat st;
+ u64 request_mask;
+ struct p9_fid *fid;
+ struct p9_stat_dotl statl;
+
+ virtio_p9_pdu_readf(pdu, "dq", &fid_val, &request_mask);
+ fid = get_fid(p9dev, fid_val);
+ if (lstat(fid->abs_path, &st) < 0)
+ goto err_out;
+
+ virtio_p9_fill_stat(p9dev, &st, &statl);
+ virtio_p9_pdu_writef(pdu, "A", &statl);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+/* FIXME!! from linux/fs.h */
+/*
+ * Attribute flags. These should be or-ed together to figure out what
+ * has been changed!
+ */
+#define ATTR_MODE (1 << 0)
+#define ATTR_UID (1 << 1)
+#define ATTR_GID (1 << 2)
+#define ATTR_SIZE (1 << 3)
+#define ATTR_ATIME (1 << 4)
+#define ATTR_MTIME (1 << 5)
+#define ATTR_CTIME (1 << 6)
+#define ATTR_ATIME_SET (1 << 7)
+#define ATTR_MTIME_SET (1 << 8)
+#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */
+#define ATTR_ATTR_FLAG (1 << 10)
+#define ATTR_KILL_SUID (1 << 11)
+#define ATTR_KILL_SGID (1 << 12)
+#define ATTR_FILE (1 << 13)
+#define ATTR_KILL_PRIV (1 << 14)
+#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
+#define ATTR_TIMES_SET (1 << 16)
+
+#define ATTR_MASK 127
+
+static void virtio_p9_setattr(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret = 0;
+ u32 fid_val;
+ struct p9_fid *fid;
+ struct p9_iattr_dotl p9attr;
+
+ virtio_p9_pdu_readf(pdu, "dI", &fid_val, &p9attr);
+ fid = get_fid(p9dev, fid_val);
+
+ if (p9attr.valid & ATTR_MODE) {
+ ret = chmod(fid->abs_path, p9attr.mode);
+ if (ret < 0)
+ goto err_out;
+ }
+ if (p9attr.valid & (ATTR_ATIME | ATTR_MTIME)) {
+ struct timespec times[2];
+ if (p9attr.valid & ATTR_ATIME) {
+ if (p9attr.valid & ATTR_ATIME_SET) {
+ times[0].tv_sec = p9attr.atime_sec;
+ times[0].tv_nsec = p9attr.atime_nsec;
+ } else {
+ times[0].tv_nsec = UTIME_NOW;
+ }
+ } else {
+ times[0].tv_nsec = UTIME_OMIT;
+ }
+ if (p9attr.valid & ATTR_MTIME) {
+ if (p9attr.valid & ATTR_MTIME_SET) {
+ times[1].tv_sec = p9attr.mtime_sec;
+ times[1].tv_nsec = p9attr.mtime_nsec;
+ } else {
+ times[1].tv_nsec = UTIME_NOW;
+ }
+ } else
+ times[1].tv_nsec = UTIME_OMIT;
+
+ ret = utimensat(-1, fid->abs_path, times, AT_SYMLINK_NOFOLLOW);
+ if (ret < 0)
+ goto err_out;
+ }
+ /*
+ * If the only valid entry in iattr is ctime we can call
+ * chown(-1,-1) to update the ctime of the file
+ */
+ if ((p9attr.valid & (ATTR_UID | ATTR_GID)) ||
+ ((p9attr.valid & ATTR_CTIME)
+ && !((p9attr.valid & ATTR_MASK) & ~ATTR_CTIME))) {
+ if (!(p9attr.valid & ATTR_UID))
+ p9attr.uid = KUIDT_INIT(-1);
+
+ if (!(p9attr.valid & ATTR_GID))
+ p9attr.gid = KGIDT_INIT(-1);
+
+ ret = lchown(fid->abs_path, __kuid_val(p9attr.uid),
+ __kgid_val(p9attr.gid));
+ if (ret < 0)
+ goto err_out;
+ }
+ if (p9attr.valid & (ATTR_SIZE)) {
+ ret = truncate(fid->abs_path, p9attr.size);
+ if (ret < 0)
+ goto err_out;
+ }
+ *outlen = VIRTIO_9P_HDR_LEN;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_write(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+
+ u64 offset;
+ u32 fid_val;
+ u32 count;
+ ssize_t res;
+ u16 iov_cnt;
+ void *iov_base;
+ size_t iov_len;
+ struct p9_fid *fid;
+ /* u32 fid + u64 offset + u32 count */
+ int twrite_size = sizeof(u32) + sizeof(u64) + sizeof(u32);
+
+ virtio_p9_pdu_readf(pdu, "dqd", &fid_val, &offset, &count);
+ fid = get_fid(p9dev, fid_val);
+
+ iov_base = pdu->out_iov[0].iov_base;
+ iov_len = pdu->out_iov[0].iov_len;
+ iov_cnt = pdu->out_iov_cnt;
+
+ /* Adjust the iovec to skip the header and meta data */
+ pdu->out_iov[0].iov_base += (sizeof(struct p9_msg) + twrite_size);
+ pdu->out_iov[0].iov_len -= (sizeof(struct p9_msg) + twrite_size);
+ pdu->out_iov_cnt = virtio_p9_update_iov_cnt(pdu->out_iov, count,
+ pdu->out_iov_cnt);
+ res = pwritev(fid->fd, pdu->out_iov, pdu->out_iov_cnt, offset);
+ /*
+ * Update the iov_base back, so that rest of
+ * pdu_readf works correctly.
+ */
+ pdu->out_iov[0].iov_base = iov_base;
+ pdu->out_iov[0].iov_len = iov_len;
+ pdu->out_iov_cnt = iov_cnt;
+
+ if (res < 0)
+ goto err_out;
+ virtio_p9_pdu_writef(pdu, "d", res);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_remove(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u32 fid_val;
+ struct p9_fid *fid;
+
+ virtio_p9_pdu_readf(pdu, "d", &fid_val);
+ fid = get_fid(p9dev, fid_val);
+
+ ret = remove(fid->abs_path);
+ if (ret < 0)
+ goto err_out;
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_rename(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u32 fid_val, new_fid_val;
+ struct p9_fid *fid, *new_fid;
+ char full_path[PATH_MAX], *new_name;
+
+ virtio_p9_pdu_readf(pdu, "dds", &fid_val, &new_fid_val, &new_name);
+ fid = get_fid(p9dev, fid_val);
+ new_fid = get_fid(p9dev, new_fid_val);
+
+ if (get_full_path(full_path, sizeof(full_path), new_fid, new_name) != 0)
+ goto err_out;
+
+ ret = rename(fid->abs_path, full_path);
+ if (ret < 0)
+ goto err_out;
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_readlink(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u32 fid_val;
+ struct p9_fid *fid;
+ char target_path[PATH_MAX];
+
+ virtio_p9_pdu_readf(pdu, "d", &fid_val);
+ fid = get_fid(p9dev, fid_val);
+
+ memset(target_path, 0, PATH_MAX);
+ ret = readlink(fid->abs_path, target_path, PATH_MAX - 1);
+ if (ret < 0)
+ goto err_out;
+
+ virtio_p9_pdu_writef(pdu, "s", target_path);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_statfs(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u64 fsid;
+ u32 fid_val;
+ struct p9_fid *fid;
+ struct statfs stat_buf;
+
+ virtio_p9_pdu_readf(pdu, "d", &fid_val);
+ fid = get_fid(p9dev, fid_val);
+
+ ret = statfs(fid->abs_path, &stat_buf);
+ if (ret < 0)
+ goto err_out;
+ /* FIXME!! f_blocks needs update based on client msize */
+ fsid = (unsigned int) stat_buf.f_fsid.__val[0] |
+ (unsigned long long)stat_buf.f_fsid.__val[1] << 32;
+ virtio_p9_pdu_writef(pdu, "ddqqqqqqd", stat_buf.f_type,
+ stat_buf.f_bsize, stat_buf.f_blocks,
+ stat_buf.f_bfree, stat_buf.f_bavail,
+ stat_buf.f_files, stat_buf.f_ffree,
+ fsid, stat_buf.f_namelen);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_mknod(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ struct stat st;
+ struct p9_fid *dfid;
+ struct p9_qid qid;
+ char full_path[PATH_MAX];
+ u32 fid_val, mode, major, minor, gid;
+
+ virtio_p9_pdu_readf(pdu, "dsdddd", &fid_val, &name, &mode,
+ &major, &minor, &gid);
+
+ dfid = get_fid(p9dev, fid_val);
+
+ if (get_full_path(full_path, sizeof(full_path), dfid, name) != 0)
+ goto err_out;
+
+ ret = mknod(full_path, mode, makedev(major, minor));
+ if (ret < 0)
+ goto err_out;
+
+ if (lstat(full_path, &st) < 0)
+ goto err_out;
+
+ ret = chmod(full_path, mode & 0777);
+ if (ret < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Q", &qid);
+ free(name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_fsync(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret, fd;
+ struct p9_fid *fid;
+ u32 fid_val, datasync;
+
+ virtio_p9_pdu_readf(pdu, "dd", &fid_val, &datasync);
+ fid = get_fid(p9dev, fid_val);
+
+ if (fid->dir)
+ fd = dirfd(fid->dir);
+ else
+ fd = fid->fd;
+
+ if (datasync)
+ ret = fdatasync(fd);
+ else
+ ret = fsync(fd);
+ if (ret < 0)
+ goto err_out;
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_symlink(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ struct stat st;
+ u32 fid_val, gid;
+ struct p9_qid qid;
+ struct p9_fid *dfid;
+ char new_name[PATH_MAX];
+ char *old_path, *name;
+
+ virtio_p9_pdu_readf(pdu, "dssd", &fid_val, &name, &old_path, &gid);
+
+ dfid = get_fid(p9dev, fid_val);
+
+ if (get_full_path(new_name, sizeof(new_name), dfid, name) != 0)
+ goto err_out;
+
+ ret = symlink(old_path, new_name);
+ if (ret < 0)
+ goto err_out;
+
+ if (lstat(new_name, &st) < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Q", &qid);
+ free(name);
+ free(old_path);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ free(old_path);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_link(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ u32 fid_val, dfid_val;
+ struct p9_fid *dfid, *fid;
+ char full_path[PATH_MAX];
+
+ virtio_p9_pdu_readf(pdu, "dds", &dfid_val, &fid_val, &name);
+
+ dfid = get_fid(p9dev, dfid_val);
+ fid = get_fid(p9dev, fid_val);
+
+ if (get_full_path(full_path, sizeof(full_path), dfid, name) != 0)
+ goto err_out;
+
+ ret = link(fid->abs_path, full_path);
+ if (ret < 0)
+ goto err_out;
+ free(name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+
+}
+
+static void virtio_p9_lock(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u8 ret;
+ u32 fid_val;
+ struct p9_flock flock;
+
+ virtio_p9_pdu_readf(pdu, "dbdqqds", &fid_val, &flock.type,
+ &flock.flags, &flock.start, &flock.length,
+ &flock.proc_id, &flock.client_id);
+
+ /* Just return success */
+ ret = P9_LOCK_SUCCESS;
+ virtio_p9_pdu_writef(pdu, "d", ret);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(flock.client_id);
+ return;
+}
+
+static void virtio_p9_getlock(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid_val;
+ struct p9_getlock glock;
+ virtio_p9_pdu_readf(pdu, "dbqqds", &fid_val, &glock.type,
+ &glock.start, &glock.length, &glock.proc_id,
+ &glock.client_id);
+
+ /* Just return success */
+ glock.type = F_UNLCK;
+ virtio_p9_pdu_writef(pdu, "bqqds", glock.type,
+ glock.start, glock.length, glock.proc_id,
+ glock.client_id);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(glock.client_id);
+ return;
+}
+
+static int virtio_p9_ancestor(char *path, char *ancestor)
+{
+ int size = strlen(ancestor);
+ if (!strncmp(path, ancestor, size)) {
+ /*
+ * Now check whether ancestor is a full name or
+ * or directory component and not just part
+ * of a name.
+ */
+ if (path[size] == '\0' || path[size] == '/')
+ return 1;
+ }
+ return 0;
+}
+
+static int virtio_p9_fix_path(struct p9_fid *fid, char *old_name, char *new_name)
+{
+ int ret;
+ char *p, tmp_name[PATH_MAX];
+ size_t rp_sz = strlen(old_name);
+
+ if (rp_sz == strlen(fid->path)) {
+ /* replace the full name */
+ p = new_name;
+ } else {
+ /* save the trailing path details */
+ ret = snprintf(tmp_name, sizeof(tmp_name), "%s%s", new_name, fid->path + rp_sz);
+ if (ret >= (int)sizeof(tmp_name))
+ return -1;
+ p = tmp_name;
+ }
+
+ return join_path(fid, p);
+}
+
+static void rename_fids(struct p9_dev *p9dev, char *old_name, char *new_name)
+{
+ struct rb_node *node = rb_first(&p9dev->fids);
+
+ while (node) {
+ struct p9_fid *fid = rb_entry(node, struct p9_fid, node);
+
+ if (fid->fid != P9_NOFID && virtio_p9_ancestor(fid->path, old_name)) {
+ virtio_p9_fix_path(fid, old_name, new_name);
+ }
+ node = rb_next(node);
+ }
+}
+
+static void virtio_p9_renameat(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *old_name, *new_name;
+ u32 old_dfid_val, new_dfid_val;
+ struct p9_fid *old_dfid, *new_dfid;
+ char old_full_path[PATH_MAX], new_full_path[PATH_MAX];
+
+
+ virtio_p9_pdu_readf(pdu, "dsds", &old_dfid_val, &old_name,
+ &new_dfid_val, &new_name);
+
+ old_dfid = get_fid(p9dev, old_dfid_val);
+ new_dfid = get_fid(p9dev, new_dfid_val);
+
+ if (get_full_path(old_full_path, sizeof(old_full_path), old_dfid, old_name) != 0)
+ goto err_out;
+
+ if (get_full_path(new_full_path, sizeof(new_full_path), new_dfid, new_name) != 0)
+ goto err_out;
+
+ ret = rename(old_full_path, new_full_path);
+ if (ret < 0)
+ goto err_out;
+ /*
+ * Now fix path in other fids, if the renamed path is part of
+ * that.
+ */
+ rename_fids(p9dev, old_name, new_name);
+ free(old_name);
+ free(new_name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(old_name);
+ free(new_name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_unlinkat(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ u32 fid_val, flags;
+ struct p9_fid *fid;
+ char full_path[PATH_MAX];
+
+ virtio_p9_pdu_readf(pdu, "dsd", &fid_val, &name, &flags);
+ fid = get_fid(p9dev, fid_val);
+
+ if (get_full_path(full_path, sizeof(full_path), fid, name) != 0)
+ goto err_out;
+
+ ret = remove(full_path);
+ if (ret < 0)
+ goto err_out;
+ free(name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_flush(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u16 tag, oldtag;
+
+ virtio_p9_pdu_readf(pdu, "ww", &tag, &oldtag);
+ virtio_p9_pdu_writef(pdu, "w", tag);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+
+ return;
+}
+
+static void virtio_p9_eopnotsupp(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ return virtio_p9_error_reply(p9dev, pdu, EOPNOTSUPP, outlen);
+}
+
+typedef void p9_handler(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen);
+
+/* FIXME should be removed when merging with latest linus tree */
+#define P9_TRENAMEAT 74
+#define P9_TUNLINKAT 76
+
+static p9_handler *virtio_9p_dotl_handler [] = {
+ [P9_TREADDIR] = virtio_p9_readdir,
+ [P9_TSTATFS] = virtio_p9_statfs,
+ [P9_TGETATTR] = virtio_p9_getattr,
+ [P9_TSETATTR] = virtio_p9_setattr,
+ [P9_TXATTRWALK] = virtio_p9_eopnotsupp,
+ [P9_TXATTRCREATE] = virtio_p9_eopnotsupp,
+ [P9_TMKNOD] = virtio_p9_mknod,
+ [P9_TLOCK] = virtio_p9_lock,
+ [P9_TGETLOCK] = virtio_p9_getlock,
+ [P9_TRENAMEAT] = virtio_p9_renameat,
+ [P9_TREADLINK] = virtio_p9_readlink,
+ [P9_TUNLINKAT] = virtio_p9_unlinkat,
+ [P9_TMKDIR] = virtio_p9_mkdir,
+ [P9_TVERSION] = virtio_p9_version,
+ [P9_TLOPEN] = virtio_p9_open,
+ [P9_TATTACH] = virtio_p9_attach,
+ [P9_TWALK] = virtio_p9_walk,
+ [P9_TCLUNK] = virtio_p9_clunk,
+ [P9_TFSYNC] = virtio_p9_fsync,
+ [P9_TREAD] = virtio_p9_read,
+ [P9_TFLUSH] = virtio_p9_flush,
+ [P9_TLINK] = virtio_p9_link,
+ [P9_TSYMLINK] = virtio_p9_symlink,
+ [P9_TLCREATE] = virtio_p9_create,
+ [P9_TWRITE] = virtio_p9_write,
+ [P9_TREMOVE] = virtio_p9_remove,
+ [P9_TRENAME] = virtio_p9_rename,
+};
+
+static struct p9_pdu *virtio_p9_pdu_init(struct kvm *kvm, struct virt_queue *vq)
+{
+ struct p9_pdu *pdu = calloc(1, sizeof(*pdu));
+ if (!pdu)
+ return NULL;
+
+ /* skip the pdu header p9_msg */
+ pdu->read_offset = VIRTIO_9P_HDR_LEN;
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ pdu->queue_head = virt_queue__get_inout_iov(kvm, vq, pdu->in_iov,
+ pdu->out_iov, &pdu->in_iov_cnt, &pdu->out_iov_cnt);
+ return pdu;
+}
+
+static u8 virtio_p9_get_cmd(struct p9_pdu *pdu)
+{
+ struct p9_msg *msg;
+ /*
+ * we can peek directly into pdu for a u8
+ * value. The host endianess won't be an issue
+ */
+ msg = pdu->out_iov[0].iov_base;
+ return msg->cmd;
+}
+
+static bool virtio_p9_do_io_request(struct kvm *kvm, struct p9_dev_job *job)
+{
+ u8 cmd;
+ u32 len = 0;
+ p9_handler *handler;
+ struct p9_dev *p9dev;
+ struct virt_queue *vq;
+ struct p9_pdu *p9pdu;
+
+ vq = job->vq;
+ p9dev = job->p9dev;
+
+ p9pdu = virtio_p9_pdu_init(kvm, vq);
+ cmd = virtio_p9_get_cmd(p9pdu);
+
+ if ((cmd >= ARRAY_SIZE(virtio_9p_dotl_handler)) ||
+ !virtio_9p_dotl_handler[cmd])
+ handler = virtio_p9_eopnotsupp;
+ else
+ handler = virtio_9p_dotl_handler[cmd];
+
+ handler(p9dev, p9pdu, &len);
+ virt_queue__set_used_elem(vq, p9pdu->queue_head, len);
+ free(p9pdu);
+ return true;
+}
+
+static void virtio_p9_do_io(struct kvm *kvm, void *param)
+{
+ struct p9_dev_job *job = (struct p9_dev_job *)param;
+ struct p9_dev *p9dev = job->p9dev;
+ struct virt_queue *vq = job->vq;
+
+ while (virt_queue__available(vq)) {
+ virtio_p9_do_io_request(kvm, job);
+ p9dev->vdev.ops->signal_vq(kvm, &p9dev->vdev, vq - p9dev->vqs);
+ }
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct p9_dev *p9dev = dev;
+
+ return ((u8 *)(p9dev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1 << VIRTIO_9P_MOUNT_TAG;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct p9_dev *p9dev = dev;
+ struct virtio_9p_config *conf = p9dev->config;
+
+ p9dev->features = features;
+ conf->tag_len = virtio_host_to_guest_u16(&p9dev->vdev, conf->tag_len);
+}
+
+static void notify_status(struct kvm *kvm, void *dev, u32 status)
+{
+ struct p9_dev *p9dev = dev;
+ struct p9_fid *pfid, *next;
+
+ if (!(status & VIRTIO__STATUS_STOP))
+ return;
+
+ rbtree_postorder_for_each_entry_safe(pfid, next, &p9dev->fids, node)
+ close_fid(p9dev, pfid->fid);
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 page_size, u32 align,
+ u32 pfn)
+{
+ struct p9_dev *p9dev = dev;
+ struct p9_dev_job *job;
+ struct virt_queue *queue;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &p9dev->vqs[vq];
+ queue->pfn = pfn;
+ p = virtio_get_vq(kvm, queue->pfn, page_size);
+ job = &p9dev->jobs[vq];
+
+ vring_init(&queue->vring, VIRTQUEUE_NUM, p, align);
+ virtio_init_device_vq(&p9dev->vdev, queue);
+
+ *job = (struct p9_dev_job) {
+ .vq = queue,
+ .p9dev = p9dev,
+ };
+ thread_pool__init_job(&job->job_id, kvm, virtio_p9_do_io, job);
+
+ return 0;
+}
+
+static void exit_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct p9_dev *p9dev = dev;
+
+ thread_pool__cancel_job(&p9dev->jobs[vq].job_id);
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct p9_dev *p9dev = dev;
+
+ thread_pool__do_job(&p9dev->jobs[vq].job_id);
+
+ return 0;
+}
+
+static struct virt_queue *get_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct p9_dev *p9dev = dev;
+
+ return &p9dev->vqs[vq];
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTQUEUE_NUM;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static int get_vq_count(struct kvm *kvm, void *dev)
+{
+ return NUM_VIRT_QUEUES;
+}
+
+struct virtio_ops p9_dev_virtio_ops = {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .exit_vq = exit_vq,
+ .notify_status = notify_status,
+ .notify_vq = notify_vq,
+ .get_vq = get_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+ .get_vq_count = get_vq_count,
+};
+
+int virtio_9p_rootdir_parser(const struct option *opt, const char *arg, int unset)
+{
+ char *tag_name;
+ char tmp[PATH_MAX];
+ struct kvm *kvm = opt->ptr;
+
+ /*
+ * 9p dir can be of the form dirname,tag_name or
+ * just dirname. In the later case we use the
+ * default tag name
+ */
+ tag_name = strstr(arg, ",");
+ if (tag_name) {
+ *tag_name = '\0';
+ tag_name++;
+ }
+ if (realpath(arg, tmp)) {
+ if (virtio_9p__register(kvm, tmp, tag_name) < 0)
+ die("Unable to initialize virtio 9p");
+ } else
+ die("Failed resolving 9p path");
+ return 0;
+}
+
+int virtio_9p_img_name_parser(const struct option *opt, const char *arg, int unset)
+{
+ char path[PATH_MAX];
+ struct stat st;
+ struct kvm *kvm = opt->ptr;
+
+ if (stat(arg, &st) == 0 &&
+ S_ISDIR(st.st_mode)) {
+ char tmp[PATH_MAX];
+
+ if (kvm->cfg.using_rootfs)
+ die("Please use only one rootfs directory atmost");
+
+ if (realpath(arg, tmp) == 0 ||
+ virtio_9p__register(kvm, tmp, "/dev/root") < 0)
+ die("Unable to initialize virtio 9p");
+ kvm->cfg.using_rootfs = 1;
+ return 0;
+ }
+
+ snprintf(path, PATH_MAX, "%s%s", kvm__get_dir(), arg);
+
+ if (stat(path, &st) == 0 &&
+ S_ISDIR(st.st_mode)) {
+ char tmp[PATH_MAX];
+
+ if (kvm->cfg.using_rootfs)
+ die("Please use only one rootfs directory atmost");
+
+ if (realpath(path, tmp) == 0 ||
+ virtio_9p__register(kvm, tmp, "/dev/root") < 0)
+ die("Unable to initialize virtio 9p");
+ if (virtio_9p__register(kvm, "/", "hostfs") < 0)
+ die("Unable to initialize virtio 9p");
+ kvm_setup_resolv(arg);
+ kvm->cfg.using_rootfs = kvm->cfg.custom_rootfs = 1;
+ kvm->cfg.custom_rootfs_name = arg;
+ return 0;
+ }
+
+ return -1;
+}
+
+int virtio_9p__init(struct kvm *kvm)
+{
+ struct p9_dev *p9dev;
+ int r;
+
+ list_for_each_entry(p9dev, &devs, list) {
+ r = virtio_init(kvm, p9dev, &p9dev->vdev, &p9_dev_virtio_ops,
+ VIRTIO_DEFAULT_TRANS(kvm), PCI_DEVICE_ID_VIRTIO_9P,
+ VIRTIO_ID_9P, PCI_CLASS_9P);
+ if (r < 0)
+ return r;
+ }
+
+ return 0;
+}
+virtio_dev_init(virtio_9p__init);
+
+int virtio_9p__register(struct kvm *kvm, const char *root, const char *tag_name)
+{
+ struct p9_dev *p9dev;
+ int err = 0;
+
+ p9dev = calloc(1, sizeof(*p9dev));
+ if (!p9dev)
+ return -ENOMEM;
+
+ if (!tag_name)
+ tag_name = VIRTIO_9P_DEFAULT_TAG;
+
+ p9dev->config = calloc(1, sizeof(*p9dev->config) + strlen(tag_name) + 1);
+ if (p9dev->config == NULL) {
+ err = -ENOMEM;
+ goto free_p9dev;
+ }
+
+ strncpy(p9dev->root_dir, root, sizeof(p9dev->root_dir));
+ p9dev->root_dir[sizeof(p9dev->root_dir)-1] = '\x00';
+
+ p9dev->config->tag_len = strlen(tag_name);
+ if (p9dev->config->tag_len > MAX_TAG_LEN) {
+ err = -EINVAL;
+ goto free_p9dev_config;
+ }
+
+ memcpy(&p9dev->config->tag, tag_name, strlen(tag_name));
+
+ list_add(&p9dev->list, &devs);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-9p", "CONFIG_NET_9P_VIRTIO");
+
+ return err;
+
+free_p9dev_config:
+ free(p9dev->config);
+free_p9dev:
+ free(p9dev);
+ return err;
+}
diff --git a/kvmtool/virtio/balloon.c b/kvmtool/virtio/balloon.c
new file mode 100644
index 0000000..8e8803f
--- /dev/null
+++ b/kvmtool/virtio/balloon.c
@@ -0,0 +1,295 @@
+#include "kvm/virtio-balloon.h"
+
+#include "kvm/virtio-pci-dev.h"
+
+#include "kvm/virtio.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+#include "kvm/guest_compat.h"
+#include "kvm/kvm-ipc.h"
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_balloon.h>
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <sys/eventfd.h>
+
+#define NUM_VIRT_QUEUES 3
+#define VIRTIO_BLN_QUEUE_SIZE 128
+#define VIRTIO_BLN_INFLATE 0
+#define VIRTIO_BLN_DEFLATE 1
+#define VIRTIO_BLN_STATS 2
+
+struct bln_dev {
+ struct list_head list;
+ struct virtio_device vdev;
+
+ u32 features;
+
+ /* virtio queue */
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct thread_pool__job jobs[NUM_VIRT_QUEUES];
+
+ struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
+ struct virtio_balloon_stat *cur_stat;
+ u32 cur_stat_head;
+ u16 stat_count;
+ int stat_waitfd;
+
+ struct virtio_balloon_config config;
+};
+
+static struct bln_dev bdev;
+static int compat_id = -1;
+
+static bool virtio_bln_do_io_request(struct kvm *kvm, struct bln_dev *bdev, struct virt_queue *queue)
+{
+ struct iovec iov[VIRTIO_BLN_QUEUE_SIZE];
+ unsigned int len = 0;
+ u16 out, in, head;
+ u32 *ptrs, i;
+
+ head = virt_queue__get_iov(queue, iov, &out, &in, kvm);
+ ptrs = iov[0].iov_base;
+ len = iov[0].iov_len / sizeof(u32);
+
+ for (i = 0 ; i < len ; i++) {
+ void *guest_ptr;
+
+ guest_ptr = guest_flat_to_host(kvm, (u64)ptrs[i] << VIRTIO_BALLOON_PFN_SHIFT);
+ if (queue == &bdev->vqs[VIRTIO_BLN_INFLATE]) {
+ madvise(guest_ptr, 1 << VIRTIO_BALLOON_PFN_SHIFT, MADV_DONTNEED);
+ bdev->config.actual++;
+ } else if (queue == &bdev->vqs[VIRTIO_BLN_DEFLATE]) {
+ bdev->config.actual--;
+ }
+ }
+
+ virt_queue__set_used_elem(queue, head, len);
+
+ return true;
+}
+
+static bool virtio_bln_do_stat_request(struct kvm *kvm, struct bln_dev *bdev, struct virt_queue *queue)
+{
+ struct iovec iov[VIRTIO_BLN_QUEUE_SIZE];
+ u16 out, in, head;
+ struct virtio_balloon_stat *stat;
+ u64 wait_val = 1;
+
+ head = virt_queue__get_iov(queue, iov, &out, &in, kvm);
+ stat = iov[0].iov_base;
+
+ /* Initial empty stat buffer */
+ if (bdev->cur_stat == NULL) {
+ bdev->cur_stat = stat;
+ bdev->cur_stat_head = head;
+
+ return true;
+ }
+
+ memcpy(bdev->stats, stat, iov[0].iov_len);
+
+ bdev->stat_count = iov[0].iov_len / sizeof(struct virtio_balloon_stat);
+ bdev->cur_stat = stat;
+ bdev->cur_stat_head = head;
+
+ if (write(bdev->stat_waitfd, &wait_val, sizeof(wait_val)) <= 0)
+ return -EFAULT;
+
+ return 1;
+}
+
+static void virtio_bln_do_io(struct kvm *kvm, void *param)
+{
+ struct virt_queue *vq = param;
+
+ if (vq == &bdev.vqs[VIRTIO_BLN_STATS]) {
+ virtio_bln_do_stat_request(kvm, &bdev, vq);
+ bdev.vdev.ops->signal_vq(kvm, &bdev.vdev, VIRTIO_BLN_STATS);
+ return;
+ }
+
+ while (virt_queue__available(vq)) {
+ virtio_bln_do_io_request(kvm, &bdev, vq);
+ bdev.vdev.ops->signal_vq(kvm, &bdev.vdev, vq - bdev.vqs);
+ }
+}
+
+static int virtio_bln__collect_stats(struct kvm *kvm)
+{
+ u64 tmp;
+
+ virt_queue__set_used_elem(&bdev.vqs[VIRTIO_BLN_STATS], bdev.cur_stat_head,
+ sizeof(struct virtio_balloon_stat));
+ bdev.vdev.ops->signal_vq(kvm, &bdev.vdev, VIRTIO_BLN_STATS);
+
+ if (read(bdev.stat_waitfd, &tmp, sizeof(tmp)) <= 0)
+ return -EFAULT;
+
+ return 0;
+}
+
+static void virtio_bln__print_stats(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg)
+{
+ int r;
+
+ if (WARN_ON(type != KVM_IPC_STAT || len))
+ return;
+
+ if (virtio_bln__collect_stats(kvm) < 0)
+ return;
+
+ r = write(fd, bdev.stats, sizeof(bdev.stats));
+ if (r < 0)
+ pr_warning("Failed sending memory stats");
+}
+
+static void handle_mem(struct kvm *kvm, int fd, u32 type, u32 len, u8 *msg)
+{
+ int mem;
+
+ if (WARN_ON(type != KVM_IPC_BALLOON || len != sizeof(int)))
+ return;
+
+ mem = *(int *)msg;
+ if (mem > 0) {
+ bdev.config.num_pages += 256 * mem;
+ } else if (mem < 0) {
+ if (bdev.config.num_pages < (u32)(256 * (-mem)))
+ return;
+
+ bdev.config.num_pages += 256 * mem;
+ }
+
+ /* Notify that the configuration space has changed */
+ bdev.vdev.ops->signal_config(kvm, &bdev.vdev);
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct bln_dev *bdev = dev;
+
+ return ((u8 *)(&bdev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1 << VIRTIO_BALLOON_F_STATS_VQ;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct bln_dev *bdev = dev;
+
+ bdev->features = features;
+}
+
+static void notify_status(struct kvm *kvm, void *dev, u32 status)
+{
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 page_size, u32 align,
+ u32 pfn)
+{
+ struct bln_dev *bdev = dev;
+ struct virt_queue *queue;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &bdev->vqs[vq];
+ queue->pfn = pfn;
+ p = virtio_get_vq(kvm, queue->pfn, page_size);
+
+ thread_pool__init_job(&bdev->jobs[vq], kvm, virtio_bln_do_io, queue);
+ vring_init(&queue->vring, VIRTIO_BLN_QUEUE_SIZE, p, align);
+ virtio_init_device_vq(&bdev->vdev, queue);
+
+ return 0;
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct bln_dev *bdev = dev;
+
+ thread_pool__do_job(&bdev->jobs[vq]);
+
+ return 0;
+}
+
+static struct virt_queue *get_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct bln_dev *bdev = dev;
+
+ return &bdev->vqs[vq];
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_BLN_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static int get_vq_count(struct kvm *kvm, void *dev)
+{
+ return NUM_VIRT_QUEUES;
+}
+
+struct virtio_ops bln_dev_virtio_ops = {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .notify_status = notify_status,
+ .notify_vq = notify_vq,
+ .get_vq = get_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+ .get_vq_count = get_vq_count,
+};
+
+int virtio_bln__init(struct kvm *kvm)
+{
+ int r;
+
+ if (!kvm->cfg.balloon)
+ return 0;
+
+ kvm_ipc__register_handler(KVM_IPC_BALLOON, handle_mem);
+ kvm_ipc__register_handler(KVM_IPC_STAT, virtio_bln__print_stats);
+
+ bdev.stat_waitfd = eventfd(0, 0);
+ memset(&bdev.config, 0, sizeof(struct virtio_balloon_config));
+
+ r = virtio_init(kvm, &bdev, &bdev.vdev, &bln_dev_virtio_ops,
+ VIRTIO_DEFAULT_TRANS(kvm), PCI_DEVICE_ID_VIRTIO_BLN,
+ VIRTIO_ID_BALLOON, PCI_CLASS_BLN);
+ if (r < 0)
+ return r;
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-balloon", "CONFIG_VIRTIO_BALLOON");
+
+ return 0;
+}
+virtio_dev_init(virtio_bln__init);
+
+int virtio_bln__exit(struct kvm *kvm)
+{
+ return 0;
+}
+virtio_dev_exit(virtio_bln__exit);
diff --git a/kvmtool/virtio/blk.c b/kvmtool/virtio/blk.c
new file mode 100644
index 0000000..4d02d10
--- /dev/null
+++ b/kvmtool/virtio/blk.c
@@ -0,0 +1,381 @@
+#include "kvm/virtio-blk.h"
+
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/disk-image.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/guest_compat.h"
+#include "kvm/virtio-pci.h"
+#include "kvm/virtio.h"
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_blk.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include <pthread.h>
+
+#define VIRTIO_BLK_MAX_DEV 4
+
+/*
+ * the header and status consume too entries
+ */
+#define DISK_SEG_MAX (VIRTIO_BLK_QUEUE_SIZE - 2)
+#define VIRTIO_BLK_QUEUE_SIZE 256
+#define NUM_VIRT_QUEUES 1
+
+struct blk_dev_req {
+ struct virt_queue *vq;
+ struct blk_dev *bdev;
+ struct iovec iov[VIRTIO_BLK_QUEUE_SIZE];
+ u16 out, in, head;
+ struct kvm *kvm;
+};
+
+struct blk_dev {
+ struct mutex mutex;
+
+ struct list_head list;
+
+ struct virtio_device vdev;
+ struct virtio_blk_config blk_config;
+ struct disk_image *disk;
+ u32 features;
+
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct blk_dev_req reqs[VIRTIO_BLK_QUEUE_SIZE];
+
+ pthread_t io_thread;
+ int io_efd;
+
+ struct kvm *kvm;
+};
+
+static LIST_HEAD(bdevs);
+static int compat_id = -1;
+
+void virtio_blk_complete(void *param, long len)
+{
+ struct blk_dev_req *req = param;
+ struct blk_dev *bdev = req->bdev;
+ int queueid = req->vq - bdev->vqs;
+ u8 *status;
+
+ /* status */
+ status = req->iov[req->out + req->in - 1].iov_base;
+ *status = (len < 0) ? VIRTIO_BLK_S_IOERR : VIRTIO_BLK_S_OK;
+
+ mutex_lock(&bdev->mutex);
+ virt_queue__set_used_elem(req->vq, req->head, len);
+ mutex_unlock(&bdev->mutex);
+
+ if (virtio_queue__should_signal(&bdev->vqs[queueid]))
+ bdev->vdev.ops->signal_vq(req->kvm, &bdev->vdev, queueid);
+}
+
+static void virtio_blk_do_io_request(struct kvm *kvm, struct virt_queue *vq, struct blk_dev_req *req)
+{
+ struct virtio_blk_outhdr *req_hdr;
+ ssize_t block_cnt;
+ struct blk_dev *bdev;
+ struct iovec *iov;
+ u16 out, in;
+ u32 type;
+ u64 sector;
+
+ block_cnt = -1;
+ bdev = req->bdev;
+ iov = req->iov;
+ out = req->out;
+ in = req->in;
+ req_hdr = iov[0].iov_base;
+
+ type = virtio_guest_to_host_u32(vq, req_hdr->type);
+ sector = virtio_guest_to_host_u64(vq, req_hdr->sector);
+
+ switch (type) {
+ case VIRTIO_BLK_T_IN:
+ block_cnt = disk_image__read(bdev->disk, sector,
+ iov + 1, in + out - 2, req);
+ break;
+ case VIRTIO_BLK_T_OUT:
+ block_cnt = disk_image__write(bdev->disk, sector,
+ iov + 1, in + out - 2, req);
+ break;
+ case VIRTIO_BLK_T_FLUSH:
+ block_cnt = disk_image__flush(bdev->disk);
+ virtio_blk_complete(req, block_cnt);
+ break;
+ case VIRTIO_BLK_T_GET_ID:
+ block_cnt = VIRTIO_BLK_ID_BYTES;
+ disk_image__get_serial(bdev->disk,
+ (iov + 1)->iov_base, &block_cnt);
+ virtio_blk_complete(req, block_cnt);
+ break;
+ default:
+ pr_warning("request type %d", type);
+ block_cnt = -1;
+ break;
+ }
+}
+
+static void virtio_blk_do_io(struct kvm *kvm, struct virt_queue *vq, struct blk_dev *bdev)
+{
+ struct blk_dev_req *req;
+ u16 head;
+
+ while (virt_queue__available(vq)) {
+ head = virt_queue__pop(vq);
+ req = &bdev->reqs[head];
+ req->head = virt_queue__get_head_iov(vq, req->iov, &req->out,
+ &req->in, head, kvm);
+ req->vq = vq;
+
+ virtio_blk_do_io_request(kvm, vq, req);
+ }
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct blk_dev *bdev = dev;
+
+ return ((u8 *)(&bdev->blk_config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ struct blk_dev *bdev = dev;
+
+ return 1UL << VIRTIO_BLK_F_SEG_MAX
+ | 1UL << VIRTIO_BLK_F_FLUSH
+ | 1UL << VIRTIO_RING_F_EVENT_IDX
+ | 1UL << VIRTIO_RING_F_INDIRECT_DESC
+ | (bdev->disk->readonly ? 1UL << VIRTIO_BLK_F_RO : 0);
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct blk_dev *bdev = dev;
+ struct virtio_blk_config *conf = &bdev->blk_config;
+
+ bdev->features = features;
+
+ conf->capacity = virtio_host_to_guest_u64(&bdev->vdev, conf->capacity);
+ conf->size_max = virtio_host_to_guest_u32(&bdev->vdev, conf->size_max);
+ conf->seg_max = virtio_host_to_guest_u32(&bdev->vdev, conf->seg_max);
+
+ /* Geometry */
+ conf->geometry.cylinders = virtio_host_to_guest_u16(&bdev->vdev,
+ conf->geometry.cylinders);
+
+ conf->blk_size = virtio_host_to_guest_u32(&bdev->vdev, conf->blk_size);
+ conf->min_io_size = virtio_host_to_guest_u16(&bdev->vdev, conf->min_io_size);
+ conf->opt_io_size = virtio_host_to_guest_u32(&bdev->vdev, conf->opt_io_size);
+}
+
+static void notify_status(struct kvm *kvm, void *dev, u32 status)
+{
+}
+
+static void *virtio_blk_thread(void *dev)
+{
+ struct blk_dev *bdev = dev;
+ u64 data;
+ int r;
+
+ kvm__set_thread_name("virtio-blk-io");
+
+ while (1) {
+ r = read(bdev->io_efd, &data, sizeof(u64));
+ if (r < 0)
+ continue;
+ virtio_blk_do_io(bdev->kvm, &bdev->vqs[0], bdev);
+ }
+
+ pthread_exit(NULL);
+ return NULL;
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 page_size, u32 align,
+ u32 pfn)
+{
+ unsigned int i;
+ struct blk_dev *bdev = dev;
+ struct virt_queue *queue;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &bdev->vqs[vq];
+ queue->pfn = pfn;
+ p = virtio_get_vq(kvm, queue->pfn, page_size);
+
+ vring_init(&queue->vring, VIRTIO_BLK_QUEUE_SIZE, p, align);
+ virtio_init_device_vq(&bdev->vdev, queue);
+
+ if (vq != 0)
+ return 0;
+
+ for (i = 0; i < ARRAY_SIZE(bdev->reqs); i++) {
+ bdev->reqs[i] = (struct blk_dev_req) {
+ .bdev = bdev,
+ .kvm = kvm,
+ };
+ }
+
+ mutex_init(&bdev->mutex);
+ bdev->io_efd = eventfd(0, 0);
+ if (bdev->io_efd < 0)
+ return -errno;
+
+ if (pthread_create(&bdev->io_thread, NULL, virtio_blk_thread, bdev))
+ return -errno;
+
+ return 0;
+}
+
+static void exit_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct blk_dev *bdev = dev;
+
+ if (vq != 0)
+ return;
+
+ close(bdev->io_efd);
+ pthread_cancel(bdev->io_thread);
+ pthread_join(bdev->io_thread, NULL);
+
+ disk_image__wait(bdev->disk);
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct blk_dev *bdev = dev;
+ u64 data = 1;
+ int r;
+
+ r = write(bdev->io_efd, &data, sizeof(data));
+ if (r < 0)
+ return r;
+
+ return 0;
+}
+
+static struct virt_queue *get_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct blk_dev *bdev = dev;
+
+ return &bdev->vqs[vq];
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ /* FIXME: dynamic */
+ return VIRTIO_BLK_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static int get_vq_count(struct kvm *kvm, void *dev)
+{
+ return NUM_VIRT_QUEUES;
+}
+
+static struct virtio_ops blk_dev_virtio_ops = {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .get_vq_count = get_vq_count,
+ .init_vq = init_vq,
+ .exit_vq = exit_vq,
+ .notify_status = notify_status,
+ .notify_vq = notify_vq,
+ .get_vq = get_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+};
+
+static int virtio_blk__init_one(struct kvm *kvm, struct disk_image *disk)
+{
+ struct blk_dev *bdev;
+ int r;
+
+ if (!disk)
+ return -EINVAL;
+
+ bdev = calloc(1, sizeof(struct blk_dev));
+ if (bdev == NULL)
+ return -ENOMEM;
+
+ *bdev = (struct blk_dev) {
+ .disk = disk,
+ .blk_config = (struct virtio_blk_config) {
+ .capacity = disk->size / SECTOR_SIZE,
+ .seg_max = DISK_SEG_MAX,
+ },
+ .kvm = kvm,
+ };
+
+ list_add_tail(&bdev->list, &bdevs);
+
+ r = virtio_init(kvm, bdev, &bdev->vdev, &blk_dev_virtio_ops,
+ VIRTIO_DEFAULT_TRANS(kvm), PCI_DEVICE_ID_VIRTIO_BLK,
+ VIRTIO_ID_BLOCK, PCI_CLASS_BLK);
+ if (r < 0)
+ return r;
+
+ disk_image__set_callback(bdev->disk, virtio_blk_complete);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-blk", "CONFIG_VIRTIO_BLK");
+
+ return 0;
+}
+
+static int virtio_blk__exit_one(struct kvm *kvm, struct blk_dev *bdev)
+{
+ list_del(&bdev->list);
+ free(bdev);
+
+ return 0;
+}
+
+int virtio_blk__init(struct kvm *kvm)
+{
+ int i, r = 0;
+
+ for (i = 0; i < kvm->nr_disks; i++) {
+ if (kvm->disks[i]->wwpn)
+ continue;
+ r = virtio_blk__init_one(kvm, kvm->disks[i]);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ return 0;
+cleanup:
+ virtio_blk__exit(kvm);
+ return r;
+}
+virtio_dev_init(virtio_blk__init);
+
+int virtio_blk__exit(struct kvm *kvm)
+{
+ while (!list_empty(&bdevs)) {
+ struct blk_dev *bdev;
+
+ bdev = list_first_entry(&bdevs, struct blk_dev, list);
+ virtio_blk__exit_one(kvm, bdev);
+ }
+
+ return 0;
+}
+virtio_dev_exit(virtio_blk__exit);
diff --git a/kvmtool/virtio/console.c b/kvmtool/virtio/console.c
new file mode 100644
index 0000000..e0b98df
--- /dev/null
+++ b/kvmtool/virtio/console.c
@@ -0,0 +1,255 @@
+#include "kvm/virtio-console.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/disk-image.h"
+#include "kvm/virtio.h"
+#include "kvm/ioport.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+#include "kvm/mutex.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+#include "kvm/irq.h"
+#include "kvm/guest_compat.h"
+
+#include <linux/virtio_console.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_blk.h>
+
+#include <sys/uio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <termios.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+#define VIRTIO_CONSOLE_QUEUE_SIZE 128
+#define VIRTIO_CONSOLE_NUM_QUEUES 2
+#define VIRTIO_CONSOLE_RX_QUEUE 0
+#define VIRTIO_CONSOLE_TX_QUEUE 1
+
+struct con_dev {
+ struct mutex mutex;
+
+ struct virtio_device vdev;
+ struct virt_queue vqs[VIRTIO_CONSOLE_NUM_QUEUES];
+ struct virtio_console_config config;
+ u32 features;
+ int vq_ready;
+
+ struct thread_pool__job jobs[VIRTIO_CONSOLE_NUM_QUEUES];
+};
+
+static struct con_dev cdev = {
+ .mutex = MUTEX_INITIALIZER,
+
+ .vq_ready = 0,
+
+ .config = {
+ .cols = 80,
+ .rows = 24,
+ .max_nr_ports = 1,
+ },
+};
+
+static int compat_id = -1;
+
+/*
+ * Interrupts are injected for hvc0 only.
+ */
+static void virtio_console__inject_interrupt_callback(struct kvm *kvm, void *param)
+{
+ struct iovec iov[VIRTIO_CONSOLE_QUEUE_SIZE];
+ struct virt_queue *vq;
+ u16 out, in;
+ u16 head;
+ int len;
+
+ mutex_lock(&cdev.mutex);
+
+ vq = param;
+
+ if (term_readable(0) && virt_queue__available(vq)) {
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ len = term_getc_iov(kvm, iov, in, 0);
+ virt_queue__set_used_elem(vq, head, len);
+ cdev.vdev.ops->signal_vq(kvm, &cdev.vdev, vq - cdev.vqs);
+ }
+
+ mutex_unlock(&cdev.mutex);
+}
+
+void virtio_console__inject_interrupt(struct kvm *kvm)
+{
+ if (kvm->cfg.active_console != CONSOLE_VIRTIO)
+ return;
+
+ mutex_lock(&cdev.mutex);
+ if (cdev.vq_ready)
+ thread_pool__do_job(&cdev.jobs[VIRTIO_CONSOLE_RX_QUEUE]);
+ mutex_unlock(&cdev.mutex);
+}
+
+static void virtio_console_handle_callback(struct kvm *kvm, void *param)
+{
+ struct iovec iov[VIRTIO_CONSOLE_QUEUE_SIZE];
+ struct virt_queue *vq;
+ u16 out, in;
+ u16 head;
+ u32 len;
+
+ vq = param;
+
+ /*
+ * The current Linux implementation polls for the buffer
+ * to be used, rather than waiting for an interrupt.
+ * So there is no need to inject an interrupt for the tx path.
+ */
+
+ while (virt_queue__available(vq)) {
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ len = term_putc_iov(iov, out, 0);
+ virt_queue__set_used_elem(vq, head, len);
+ }
+
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct con_dev *cdev = dev;
+
+ return ((u8 *)(&cdev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 0;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct con_dev *cdev = dev;
+ struct virtio_console_config *conf = &cdev->config;
+
+ conf->cols = virtio_host_to_guest_u16(&cdev->vdev, conf->cols);
+ conf->rows = virtio_host_to_guest_u16(&cdev->vdev, conf->rows);
+ conf->max_nr_ports = virtio_host_to_guest_u32(&cdev->vdev, conf->max_nr_ports);
+}
+
+static void notify_status(struct kvm *kvm, void *dev, u32 status)
+{
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 page_size, u32 align,
+ u32 pfn)
+{
+ struct virt_queue *queue;
+ void *p;
+
+ BUG_ON(vq >= VIRTIO_CONSOLE_NUM_QUEUES);
+
+ compat__remove_message(compat_id);
+
+ queue = &cdev.vqs[vq];
+ queue->pfn = pfn;
+ p = virtio_get_vq(kvm, queue->pfn, page_size);
+
+ vring_init(&queue->vring, VIRTIO_CONSOLE_QUEUE_SIZE, p, align);
+ virtio_init_device_vq(&cdev.vdev, queue);
+
+ if (vq == VIRTIO_CONSOLE_TX_QUEUE) {
+ thread_pool__init_job(&cdev.jobs[vq], kvm, virtio_console_handle_callback, queue);
+ } else if (vq == VIRTIO_CONSOLE_RX_QUEUE) {
+ thread_pool__init_job(&cdev.jobs[vq], kvm, virtio_console__inject_interrupt_callback, queue);
+ /* Tell the waiting poll thread that we're ready to go */
+ mutex_lock(&cdev.mutex);
+ cdev.vq_ready = 1;
+ mutex_unlock(&cdev.mutex);
+ }
+
+ return 0;
+}
+
+static void exit_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ if (vq == VIRTIO_CONSOLE_RX_QUEUE) {
+ mutex_lock(&cdev.mutex);
+ cdev.vq_ready = 0;
+ mutex_unlock(&cdev.mutex);
+ thread_pool__cancel_job(&cdev.jobs[vq]);
+ } else if (vq == VIRTIO_CONSOLE_TX_QUEUE) {
+ thread_pool__cancel_job(&cdev.jobs[vq]);
+ }
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct con_dev *cdev = dev;
+
+ thread_pool__do_job(&cdev->jobs[vq]);
+
+ return 0;
+}
+
+static struct virt_queue *get_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct con_dev *cdev = dev;
+
+ return &cdev->vqs[vq];
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_CONSOLE_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static int get_vq_count(struct kvm *kvm, void *dev)
+{
+ return VIRTIO_CONSOLE_NUM_QUEUES;
+}
+
+static struct virtio_ops con_dev_virtio_ops = {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .get_vq_count = get_vq_count,
+ .init_vq = init_vq,
+ .exit_vq = exit_vq,
+ .notify_status = notify_status,
+ .notify_vq = notify_vq,
+ .get_vq = get_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+};
+
+int virtio_console__init(struct kvm *kvm)
+{
+ int r;
+
+ if (kvm->cfg.active_console != CONSOLE_VIRTIO)
+ return 0;
+
+ r = virtio_init(kvm, &cdev, &cdev.vdev, &con_dev_virtio_ops,
+ VIRTIO_DEFAULT_TRANS(kvm), PCI_DEVICE_ID_VIRTIO_CONSOLE,
+ VIRTIO_ID_CONSOLE, PCI_CLASS_CONSOLE);
+ if (r < 0)
+ return r;
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-console", "CONFIG_VIRTIO_CONSOLE");
+
+ return 0;
+}
+virtio_dev_init(virtio_console__init);
+
+int virtio_console__exit(struct kvm *kvm)
+{
+ return 0;
+}
+virtio_dev_exit(virtio_console__exit);
diff --git a/kvmtool/virtio/core.c b/kvmtool/virtio/core.c
new file mode 100644
index 0000000..f5b3c07
--- /dev/null
+++ b/kvmtool/virtio/core.c
@@ -0,0 +1,328 @@
+#include <linux/virtio_ring.h>
+#include <linux/types.h>
+#include <sys/uio.h>
+#include <stdlib.h>
+
+#include "kvm/guest_compat.h"
+#include "kvm/barrier.h"
+#include "kvm/virtio.h"
+#include "kvm/virtio-pci.h"
+#include "kvm/virtio-mmio.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+
+const char* virtio_trans_name(enum virtio_trans trans)
+{
+ if (trans == VIRTIO_PCI)
+ return "pci";
+ else if (trans == VIRTIO_MMIO)
+ return "mmio";
+ return "unknown";
+}
+
+void virt_queue__used_idx_advance(struct virt_queue *queue, u16 jump)
+{
+ u16 idx = virtio_guest_to_host_u16(queue, queue->vring.used->idx);
+
+ /*
+ * Use wmb to assure that used elem was updated with head and len.
+ * We need a wmb here since we can't advance idx unless we're ready
+ * to pass the used element to the guest.
+ */
+ wmb();
+ idx += jump;
+ queue->vring.used->idx = virtio_host_to_guest_u16(queue, idx);
+
+ /*
+ * Use wmb to assure used idx has been increased before we signal the guest.
+ * Without a wmb here the guest may ignore the queue since it won't see
+ * an updated idx.
+ */
+ wmb();
+}
+
+struct vring_used_elem *
+virt_queue__set_used_elem_no_update(struct virt_queue *queue, u32 head,
+ u32 len, u16 offset)
+{
+ struct vring_used_elem *used_elem;
+ u16 idx = virtio_guest_to_host_u16(queue, queue->vring.used->idx);
+
+ idx += offset;
+ used_elem = &queue->vring.used->ring[idx % queue->vring.num];
+ used_elem->id = virtio_host_to_guest_u32(queue, head);
+ used_elem->len = virtio_host_to_guest_u32(queue, len);
+
+ return used_elem;
+}
+
+struct vring_used_elem *virt_queue__set_used_elem(struct virt_queue *queue, u32 head, u32 len)
+{
+ struct vring_used_elem *used_elem;
+
+ used_elem = virt_queue__set_used_elem_no_update(queue, head, len, 0);
+ virt_queue__used_idx_advance(queue, 1);
+
+ return used_elem;
+}
+
+static inline bool virt_desc__test_flag(struct virt_queue *vq,
+ struct vring_desc *desc, u16 flag)
+{
+ return !!(virtio_guest_to_host_u16(vq, desc->flags) & flag);
+}
+
+/*
+ * Each buffer in the virtqueues is actually a chain of descriptors. This
+ * function returns the next descriptor in the chain, or max if we're at the
+ * end.
+ */
+static unsigned next_desc(struct virt_queue *vq, struct vring_desc *desc,
+ unsigned int i, unsigned int max)
+{
+ unsigned int next;
+
+ /* If this descriptor says it doesn't chain, we're done. */
+ if (!virt_desc__test_flag(vq, &desc[i], VRING_DESC_F_NEXT))
+ return max;
+
+ next = virtio_guest_to_host_u16(vq, desc[i].next);
+
+ /* Ensure they're not leading us off end of descriptors. */
+ return min(next, max);
+}
+
+u16 virt_queue__get_head_iov(struct virt_queue *vq, struct iovec iov[], u16 *out, u16 *in, u16 head, struct kvm *kvm)
+{
+ struct vring_desc *desc;
+ u16 idx;
+ u16 max;
+
+ idx = head;
+ *out = *in = 0;
+ max = vq->vring.num;
+ desc = vq->vring.desc;
+
+ if (virt_desc__test_flag(vq, &desc[idx], VRING_DESC_F_INDIRECT)) {
+ max = virtio_guest_to_host_u32(vq, desc[idx].len) / sizeof(struct vring_desc);
+ desc = guest_flat_to_host(kvm, virtio_guest_to_host_u64(vq, desc[idx].addr));
+ idx = 0;
+ }
+
+ do {
+ /* Grab the first descriptor, and check it's OK. */
+ iov[*out + *in].iov_len = virtio_guest_to_host_u32(vq, desc[idx].len);
+ iov[*out + *in].iov_base = guest_flat_to_host(kvm,
+ virtio_guest_to_host_u64(vq, desc[idx].addr));
+ /* If this is an input descriptor, increment that count. */
+ if (virt_desc__test_flag(vq, &desc[idx], VRING_DESC_F_WRITE))
+ (*in)++;
+ else
+ (*out)++;
+ } while ((idx = next_desc(vq, desc, idx, max)) != max);
+
+ return head;
+}
+
+u16 virt_queue__get_iov(struct virt_queue *vq, struct iovec iov[], u16 *out, u16 *in, struct kvm *kvm)
+{
+ u16 head;
+
+ head = virt_queue__pop(vq);
+
+ return virt_queue__get_head_iov(vq, iov, out, in, head, kvm);
+}
+
+/* in and out are relative to guest */
+u16 virt_queue__get_inout_iov(struct kvm *kvm, struct virt_queue *queue,
+ struct iovec in_iov[], struct iovec out_iov[],
+ u16 *in, u16 *out)
+{
+ struct vring_desc *desc;
+ u16 head, idx;
+
+ idx = head = virt_queue__pop(queue);
+ *out = *in = 0;
+ do {
+ u64 addr;
+ desc = virt_queue__get_desc(queue, idx);
+ addr = virtio_guest_to_host_u64(queue, desc->addr);
+ if (virt_desc__test_flag(queue, desc, VRING_DESC_F_WRITE)) {
+ in_iov[*in].iov_base = guest_flat_to_host(kvm, addr);
+ in_iov[*in].iov_len = virtio_guest_to_host_u32(queue, desc->len);
+ (*in)++;
+ } else {
+ out_iov[*out].iov_base = guest_flat_to_host(kvm, addr);
+ out_iov[*out].iov_len = virtio_guest_to_host_u32(queue, desc->len);
+ (*out)++;
+ }
+ if (virt_desc__test_flag(queue, desc, VRING_DESC_F_NEXT))
+ idx = virtio_guest_to_host_u16(queue, desc->next);
+ else
+ break;
+ } while (1);
+
+ return head;
+}
+
+void virtio_exit_vq(struct kvm *kvm, struct virtio_device *vdev,
+ void *dev, int num)
+{
+ struct virt_queue *vq = vdev->ops->get_vq(kvm, dev, num);
+
+ if (vq->enabled && vdev->ops->exit_vq)
+ vdev->ops->exit_vq(kvm, dev, num);
+ memset(vq, 0, sizeof(*vq));
+}
+
+int virtio__get_dev_specific_field(int offset, bool msix, u32 *config_off)
+{
+ if (msix) {
+ if (offset < 4)
+ return VIRTIO_PCI_O_MSIX;
+ else
+ offset -= 4;
+ }
+
+ *config_off = offset;
+
+ return VIRTIO_PCI_O_CONFIG;
+}
+
+bool virtio_queue__should_signal(struct virt_queue *vq)
+{
+ u16 old_idx, new_idx, event_idx;
+
+ if (!vq->use_event_idx) {
+ /*
+ * When VIRTIO_RING_F_EVENT_IDX isn't negotiated, interrupt the
+ * guest if it didn't explicitly request to be left alone.
+ */
+ return !(virtio_guest_to_host_u16(vq, vq->vring.avail->flags) &
+ VRING_AVAIL_F_NO_INTERRUPT);
+ }
+
+ old_idx = vq->last_used_signalled;
+ new_idx = virtio_guest_to_host_u16(vq, vq->vring.used->idx);
+ event_idx = virtio_guest_to_host_u16(vq, vring_used_event(&vq->vring));
+
+ if (vring_need_event(event_idx, new_idx, old_idx)) {
+ vq->last_used_signalled = new_idx;
+ return true;
+ }
+
+ return false;
+}
+
+void virtio_set_guest_features(struct kvm *kvm, struct virtio_device *vdev,
+ void *dev, u32 features)
+{
+ /* TODO: fail negotiation if features & ~host_features */
+
+ vdev->features = features;
+ vdev->ops->set_guest_features(kvm, dev, features);
+}
+
+void virtio_notify_status(struct kvm *kvm, struct virtio_device *vdev,
+ void *dev, u8 status)
+{
+ u32 ext_status = status;
+
+ vdev->status &= ~VIRTIO_CONFIG_S_MASK;
+ vdev->status |= status;
+
+ /* Add a few hints to help devices */
+ if ((status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+ !(vdev->status & VIRTIO__STATUS_START)) {
+ vdev->status |= VIRTIO__STATUS_START;
+ ext_status |= VIRTIO__STATUS_START;
+
+ } else if (!status && (vdev->status & VIRTIO__STATUS_START)) {
+ vdev->status &= ~VIRTIO__STATUS_START;
+ ext_status |= VIRTIO__STATUS_STOP;
+
+ /*
+ * Reset virtqueues and stop all traffic now, so that the device
+ * can safely reset the backend in notify_status().
+ */
+ if (ext_status & VIRTIO__STATUS_STOP)
+ vdev->ops->reset(kvm, vdev);
+ }
+
+ if (vdev->ops->notify_status)
+ vdev->ops->notify_status(kvm, dev, ext_status);
+}
+
+int virtio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ struct virtio_ops *ops, enum virtio_trans trans,
+ int device_id, int subsys_id, int class)
+{
+ void *virtio;
+ int r;
+
+ switch (trans) {
+ case VIRTIO_PCI:
+ virtio = calloc(sizeof(struct virtio_pci), 1);
+ if (!virtio)
+ return -ENOMEM;
+ vdev->virtio = virtio;
+ vdev->ops = ops;
+ vdev->ops->signal_vq = virtio_pci__signal_vq;
+ vdev->ops->signal_config = virtio_pci__signal_config;
+ vdev->ops->init = virtio_pci__init;
+ vdev->ops->exit = virtio_pci__exit;
+ vdev->ops->reset = virtio_pci__reset;
+ r = vdev->ops->init(kvm, dev, vdev, device_id, subsys_id, class);
+ break;
+ case VIRTIO_MMIO:
+ virtio = calloc(sizeof(struct virtio_mmio), 1);
+ if (!virtio)
+ return -ENOMEM;
+ vdev->virtio = virtio;
+ vdev->ops = ops;
+ vdev->ops->signal_vq = virtio_mmio_signal_vq;
+ vdev->ops->signal_config = virtio_mmio_signal_config;
+ vdev->ops->init = virtio_mmio_init;
+ vdev->ops->exit = virtio_mmio_exit;
+ vdev->ops->reset = virtio_mmio_reset;
+ r = vdev->ops->init(kvm, dev, vdev, device_id, subsys_id, class);
+ break;
+ default:
+ r = -1;
+ };
+
+ return r;
+}
+
+int virtio_compat_add_message(const char *device, const char *config)
+{
+ int len = 1024;
+ int compat_id;
+ char *title;
+ char *desc;
+
+ title = malloc(len);
+ if (!title)
+ return -ENOMEM;
+
+ desc = malloc(len);
+ if (!desc) {
+ free(title);
+ return -ENOMEM;
+ }
+
+ snprintf(title, len, "%s device was not detected.", device);
+ snprintf(desc, len, "While you have requested a %s device, "
+ "the guest kernel did not initialize it.\n"
+ "\tPlease make sure that the guest kernel was "
+ "compiled with %s=y enabled in .config.",
+ device, config);
+
+ compat_id = compat__add_message(title, desc);
+
+ free(desc);
+ free(title);
+
+ return compat_id;
+}
diff --git a/kvmtool/virtio/mmio.c b/kvmtool/virtio/mmio.c
new file mode 100644
index 0000000..875a288
--- /dev/null
+++ b/kvmtool/virtio/mmio.c
@@ -0,0 +1,350 @@
+#include "kvm/devices.h"
+#include "kvm/virtio-mmio.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/ioport.h"
+#include "kvm/virtio.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/irq.h"
+#include "kvm/fdt.h"
+
+#include <linux/virtio_mmio.h>
+#include <string.h>
+
+static u32 virtio_mmio_io_space_blocks = KVM_VIRTIO_MMIO_AREA;
+
+static u32 virtio_mmio_get_io_space_block(u32 size)
+{
+ u32 block = virtio_mmio_io_space_blocks;
+ virtio_mmio_io_space_blocks += size;
+
+ return block;
+}
+
+static void virtio_mmio_ioevent_callback(struct kvm *kvm, void *param)
+{
+ struct virtio_mmio_ioevent_param *ioeventfd = param;
+ struct virtio_mmio *vmmio = ioeventfd->vdev->virtio;
+
+ ioeventfd->vdev->ops->notify_vq(kvm, vmmio->dev, ioeventfd->vq);
+}
+
+static int virtio_mmio_init_ioeventfd(struct kvm *kvm,
+ struct virtio_device *vdev, u32 vq)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ struct ioevent ioevent;
+ int err;
+
+ vmmio->ioeventfds[vq] = (struct virtio_mmio_ioevent_param) {
+ .vdev = vdev,
+ .vq = vq,
+ };
+
+ ioevent = (struct ioevent) {
+ .io_addr = vmmio->addr + VIRTIO_MMIO_QUEUE_NOTIFY,
+ .io_len = sizeof(u32),
+ .fn = virtio_mmio_ioevent_callback,
+ .fn_ptr = &vmmio->ioeventfds[vq],
+ .datamatch = vq,
+ .fn_kvm = kvm,
+ .fd = eventfd(0, 0),
+ };
+
+ if (vdev->use_vhost)
+ /*
+ * Vhost will poll the eventfd in host kernel side,
+ * no need to poll in userspace.
+ */
+ err = ioeventfd__add_event(&ioevent, 0);
+ else
+ /* Need to poll in userspace. */
+ err = ioeventfd__add_event(&ioevent, IOEVENTFD_FLAG_USER_POLL);
+ if (err)
+ return err;
+
+ if (vdev->ops->notify_vq_eventfd)
+ vdev->ops->notify_vq_eventfd(kvm, vmmio->dev, vq, ioevent.fd);
+
+ return 0;
+}
+
+int virtio_mmio_signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+
+ vmmio->hdr.interrupt_state |= VIRTIO_MMIO_INT_VRING;
+ kvm__irq_trigger(vmmio->kvm, vmmio->irq);
+
+ return 0;
+}
+
+static void virtio_mmio_exit_vq(struct kvm *kvm, struct virtio_device *vdev,
+ int vq)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+
+ ioeventfd__del_event(vmmio->addr + VIRTIO_MMIO_QUEUE_NOTIFY, vq);
+ virtio_exit_vq(kvm, vdev, vmmio->dev, vq);
+}
+
+int virtio_mmio_signal_config(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+
+ vmmio->hdr.interrupt_state |= VIRTIO_MMIO_INT_CONFIG;
+ kvm__irq_trigger(vmmio->kvm, vmmio->irq);
+
+ return 0;
+}
+
+static void virtio_mmio_device_specific(struct kvm_cpu *vcpu,
+ u64 addr, u8 *data, u32 len,
+ u8 is_write, struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ u32 i;
+
+ for (i = 0; i < len; i++) {
+ if (is_write)
+ vdev->ops->get_config(vmmio->kvm, vmmio->dev)[addr + i] =
+ *(u8 *)data + i;
+ else
+ data[i] = vdev->ops->get_config(vmmio->kvm,
+ vmmio->dev)[addr + i];
+ }
+}
+
+static void virtio_mmio_config_in(struct kvm_cpu *vcpu,
+ u64 addr, void *data, u32 len,
+ struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ struct virt_queue *vq;
+ u32 val = 0;
+
+ switch (addr) {
+ case VIRTIO_MMIO_MAGIC_VALUE:
+ case VIRTIO_MMIO_VERSION:
+ case VIRTIO_MMIO_DEVICE_ID:
+ case VIRTIO_MMIO_VENDOR_ID:
+ case VIRTIO_MMIO_STATUS:
+ case VIRTIO_MMIO_INTERRUPT_STATUS:
+ ioport__write32(data, *(u32 *)(((void *)&vmmio->hdr) + addr));
+ break;
+ case VIRTIO_MMIO_HOST_FEATURES:
+ if (vmmio->hdr.host_features_sel == 0)
+ val = vdev->ops->get_host_features(vmmio->kvm,
+ vmmio->dev);
+ ioport__write32(data, val);
+ break;
+ case VIRTIO_MMIO_QUEUE_PFN:
+ vq = vdev->ops->get_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel);
+ ioport__write32(data, vq->pfn);
+ break;
+ case VIRTIO_MMIO_QUEUE_NUM_MAX:
+ val = vdev->ops->get_size_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel);
+ ioport__write32(data, val);
+ break;
+ default:
+ break;
+ }
+}
+
+static void virtio_mmio_config_out(struct kvm_cpu *vcpu,
+ u64 addr, void *data, u32 len,
+ struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ struct kvm *kvm = vmmio->kvm;
+ u32 val = 0;
+
+ switch (addr) {
+ case VIRTIO_MMIO_HOST_FEATURES_SEL:
+ case VIRTIO_MMIO_GUEST_FEATURES_SEL:
+ case VIRTIO_MMIO_QUEUE_SEL:
+ val = ioport__read32(data);
+ *(u32 *)(((void *)&vmmio->hdr) + addr) = val;
+ break;
+ case VIRTIO_MMIO_STATUS:
+ vmmio->hdr.status = ioport__read32(data);
+ if (!vmmio->hdr.status) /* Sample endianness on reset */
+ vdev->endian = kvm_cpu__get_endianness(vcpu);
+ virtio_notify_status(kvm, vdev, vmmio->dev, vmmio->hdr.status);
+ break;
+ case VIRTIO_MMIO_GUEST_FEATURES:
+ if (vmmio->hdr.guest_features_sel == 0) {
+ val = ioport__read32(data);
+ virtio_set_guest_features(vmmio->kvm, vdev,
+ vmmio->dev, val);
+ }
+ break;
+ case VIRTIO_MMIO_GUEST_PAGE_SIZE:
+ val = ioport__read32(data);
+ vmmio->hdr.guest_page_size = val;
+ break;
+ case VIRTIO_MMIO_QUEUE_NUM:
+ val = ioport__read32(data);
+ vmmio->hdr.queue_num = val;
+ vdev->ops->set_size_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel, val);
+ break;
+ case VIRTIO_MMIO_QUEUE_ALIGN:
+ val = ioport__read32(data);
+ vmmio->hdr.queue_align = val;
+ break;
+ case VIRTIO_MMIO_QUEUE_PFN:
+ val = ioport__read32(data);
+ if (val) {
+ virtio_mmio_init_ioeventfd(vmmio->kvm, vdev,
+ vmmio->hdr.queue_sel);
+ vdev->ops->init_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel,
+ vmmio->hdr.guest_page_size,
+ vmmio->hdr.queue_align,
+ val);
+ } else {
+ virtio_mmio_exit_vq(kvm, vdev, vmmio->hdr.queue_sel);
+ }
+ break;
+ case VIRTIO_MMIO_QUEUE_NOTIFY:
+ val = ioport__read32(data);
+ vdev->ops->notify_vq(vmmio->kvm, vmmio->dev, val);
+ break;
+ case VIRTIO_MMIO_INTERRUPT_ACK:
+ val = ioport__read32(data);
+ vmmio->hdr.interrupt_state &= ~val;
+ break;
+ default:
+ break;
+ };
+}
+
+static void virtio_mmio_mmio_callback(struct kvm_cpu *vcpu,
+ u64 addr, u8 *data, u32 len,
+ u8 is_write, void *ptr)
+{
+ struct virtio_device *vdev = ptr;
+ struct virtio_mmio *vmmio = vdev->virtio;
+ u32 offset = addr - vmmio->addr;
+
+ if (offset >= VIRTIO_MMIO_CONFIG) {
+ offset -= VIRTIO_MMIO_CONFIG;
+ virtio_mmio_device_specific(vcpu, offset, data, len, is_write, ptr);
+ return;
+ }
+
+ if (is_write)
+ virtio_mmio_config_out(vcpu, offset, data, len, ptr);
+ else
+ virtio_mmio_config_in(vcpu, offset, data, len, ptr);
+}
+
+#ifdef CONFIG_HAS_LIBFDT
+#define DEVICE_NAME_MAX_LEN 32
+static
+void generate_virtio_mmio_fdt_node(void *fdt,
+ struct device_header *dev_hdr,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq,
+ enum irq_type))
+{
+ char dev_name[DEVICE_NAME_MAX_LEN];
+ struct virtio_mmio *vmmio = container_of(dev_hdr,
+ struct virtio_mmio,
+ dev_hdr);
+ u64 addr = vmmio->addr;
+ u64 reg_prop[] = {
+ cpu_to_fdt64(addr),
+ cpu_to_fdt64(VIRTIO_MMIO_IO_SIZE),
+ };
+
+ snprintf(dev_name, DEVICE_NAME_MAX_LEN, "virtio@%llx", addr);
+
+ _FDT(fdt_begin_node(fdt, dev_name));
+ _FDT(fdt_property_string(fdt, "compatible", "virtio,mmio"));
+ _FDT(fdt_property(fdt, "reg", reg_prop, sizeof(reg_prop)));
+ _FDT(fdt_property(fdt, "dma-coherent", NULL, 0));
+ generate_irq_prop(fdt, vmmio->irq, IRQ_TYPE_EDGE_RISING);
+ _FDT(fdt_end_node(fdt));
+}
+#else
+static void generate_virtio_mmio_fdt_node(void *fdt,
+ struct device_header *dev_hdr,
+ void (*generate_irq_prop)(void *fdt,
+ u8 irq))
+{
+ die("Unable to generate device tree nodes without libfdt\n");
+}
+#endif
+
+int virtio_mmio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ int r;
+
+ vmmio->addr = virtio_mmio_get_io_space_block(VIRTIO_MMIO_IO_SIZE);
+ vmmio->kvm = kvm;
+ vmmio->dev = dev;
+
+ r = kvm__register_mmio(kvm, vmmio->addr, VIRTIO_MMIO_IO_SIZE,
+ false, virtio_mmio_mmio_callback, vdev);
+ if (r < 0)
+ return r;
+
+ vmmio->hdr = (struct virtio_mmio_hdr) {
+ .magic = {'v', 'i', 'r', 't'},
+ .version = 1,
+ .device_id = subsys_id,
+ .vendor_id = 0x4d564b4c , /* 'LKVM' */
+ .queue_num_max = 256,
+ };
+
+ vmmio->dev_hdr = (struct device_header) {
+ .bus_type = DEVICE_BUS_MMIO,
+ .data = generate_virtio_mmio_fdt_node,
+ };
+
+ vmmio->irq = irq__alloc_line();
+
+ r = device__register(&vmmio->dev_hdr);
+ if (r < 0) {
+ kvm__deregister_mmio(kvm, vmmio->addr);
+ return r;
+ }
+
+ /*
+ * Instantiate guest virtio-mmio devices using kernel command line
+ * (or module) parameter, e.g
+ *
+ * virtio_mmio.devices=0x200@0xd2000000:5,0x200@0xd2000200:6
+ */
+ pr_debug("virtio-mmio.devices=0x%x@0x%x:%d", VIRTIO_MMIO_IO_SIZE,
+ vmmio->addr, vmmio->irq);
+
+ return 0;
+}
+
+int virtio_mmio_reset(struct kvm *kvm, struct virtio_device *vdev)
+{
+ int vq;
+ struct virtio_mmio *vmmio = vdev->virtio;
+
+ for (vq = 0; vq < vdev->ops->get_vq_count(kvm, vmmio->dev); vq++)
+ virtio_mmio_exit_vq(kvm, vdev, vq);
+
+ return 0;
+}
+
+int virtio_mmio_exit(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+
+ virtio_mmio_reset(kvm, vdev);
+ kvm__deregister_mmio(kvm, vmmio->addr);
+
+ return 0;
+}
diff --git a/kvmtool/virtio/net.c b/kvmtool/virtio/net.c
new file mode 100644
index 0000000..1ee3c19
--- /dev/null
+++ b/kvmtool/virtio/net.c
@@ -0,0 +1,1042 @@
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/virtio-net.h"
+#include "kvm/virtio.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/irq.h"
+#include "kvm/uip.h"
+#include "kvm/guest_compat.h"
+#include "kvm/iovec.h"
+#include "kvm/strbuf.h"
+
+#include <linux/vhost.h>
+#include <linux/virtio_net.h>
+#include <linux/if_tun.h>
+#include <linux/types.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include <unistd.h>
+#include <fcntl.h>
+
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/eventfd.h>
+
+#define VIRTIO_NET_QUEUE_SIZE 256
+#define VIRTIO_NET_NUM_QUEUES 8
+
+struct net_dev;
+
+struct net_dev_operations {
+ int (*rx)(struct iovec *iov, u16 in, struct net_dev *ndev);
+ int (*tx)(struct iovec *iov, u16 in, struct net_dev *ndev);
+};
+
+struct net_dev_queue {
+ int id;
+ struct net_dev *ndev;
+ struct virt_queue vq;
+ pthread_t thread;
+ struct mutex lock;
+ pthread_cond_t cond;
+ int gsi;
+ int irqfd;
+};
+
+struct net_dev {
+ struct mutex mutex;
+ struct virtio_device vdev;
+ struct list_head list;
+
+ struct net_dev_queue queues[VIRTIO_NET_NUM_QUEUES * 2 + 1];
+ struct virtio_net_config config;
+ u32 features, queue_pairs;
+
+ int vhost_fd;
+ int tap_fd;
+ char tap_name[IFNAMSIZ];
+ bool tap_ufo;
+
+ int mode;
+
+ struct uip_info info;
+ struct net_dev_operations *ops;
+ struct kvm *kvm;
+
+ struct virtio_net_params *params;
+};
+
+static LIST_HEAD(ndevs);
+static int compat_id = -1;
+
+#define MAX_PACKET_SIZE 65550
+
+static bool has_virtio_feature(struct net_dev *ndev, u32 feature)
+{
+ return ndev->features & (1 << feature);
+}
+
+static void virtio_net_fix_tx_hdr(struct virtio_net_hdr *hdr, struct net_dev *ndev)
+{
+ hdr->hdr_len = virtio_guest_to_host_u16(&ndev->vdev, hdr->hdr_len);
+ hdr->gso_size = virtio_guest_to_host_u16(&ndev->vdev, hdr->gso_size);
+ hdr->csum_start = virtio_guest_to_host_u16(&ndev->vdev, hdr->csum_start);
+ hdr->csum_offset = virtio_guest_to_host_u16(&ndev->vdev, hdr->csum_offset);
+}
+
+static void virtio_net_fix_rx_hdr(struct virtio_net_hdr *hdr, struct net_dev *ndev)
+{
+ hdr->hdr_len = virtio_host_to_guest_u16(&ndev->vdev, hdr->hdr_len);
+ hdr->gso_size = virtio_host_to_guest_u16(&ndev->vdev, hdr->gso_size);
+ hdr->csum_start = virtio_host_to_guest_u16(&ndev->vdev, hdr->csum_start);
+ hdr->csum_offset = virtio_host_to_guest_u16(&ndev->vdev, hdr->csum_offset);
+}
+
+static void *virtio_net_rx_thread(void *p)
+{
+ struct iovec iov[VIRTIO_NET_QUEUE_SIZE];
+ struct net_dev_queue *queue = p;
+ struct virt_queue *vq = &queue->vq;
+ struct net_dev *ndev = queue->ndev;
+ struct kvm *kvm;
+ u16 out, in;
+ u16 head;
+ int len, copied;
+
+ kvm__set_thread_name("virtio-net-rx");
+
+ kvm = ndev->kvm;
+ while (1) {
+ mutex_lock(&queue->lock);
+ if (!virt_queue__available(vq))
+ pthread_cond_wait(&queue->cond, &queue->lock.mutex);
+ mutex_unlock(&queue->lock);
+
+ while (virt_queue__available(vq)) {
+ unsigned char buffer[MAX_PACKET_SIZE + sizeof(struct virtio_net_hdr_mrg_rxbuf)];
+ struct iovec dummy_iov = {
+ .iov_base = buffer,
+ .iov_len = sizeof(buffer),
+ };
+ struct virtio_net_hdr_mrg_rxbuf *hdr;
+ u16 num_buffers;
+
+ len = ndev->ops->rx(&dummy_iov, 1, ndev);
+ if (len < 0) {
+ pr_warning("%s: rx on vq %u failed (%d), exiting thread\n",
+ __func__, queue->id, len);
+ goto out_err;
+ }
+
+ copied = num_buffers = 0;
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ hdr = iov[0].iov_base;
+ while (copied < len) {
+ size_t iovsize = min_t(size_t, len - copied, iov_size(iov, in));
+
+ memcpy_toiovec(iov, buffer + copied, iovsize);
+ copied += iovsize;
+ virt_queue__set_used_elem_no_update(vq, head, iovsize, num_buffers++);
+ if (copied == len)
+ break;
+ while (!virt_queue__available(vq))
+ sleep(0);
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ }
+
+ virtio_net_fix_rx_hdr(&hdr->hdr, ndev);
+ if (has_virtio_feature(ndev, VIRTIO_NET_F_MRG_RXBUF))
+ hdr->num_buffers = virtio_host_to_guest_u16(vq, num_buffers);
+
+ virt_queue__used_idx_advance(vq, num_buffers);
+
+ /* We should interrupt guest right now, otherwise latency is huge. */
+ if (virtio_queue__should_signal(vq))
+ ndev->vdev.ops->signal_vq(kvm, &ndev->vdev, queue->id);
+ }
+ }
+
+out_err:
+ pthread_exit(NULL);
+ return NULL;
+
+}
+
+static void *virtio_net_tx_thread(void *p)
+{
+ struct iovec iov[VIRTIO_NET_QUEUE_SIZE];
+ struct net_dev_queue *queue = p;
+ struct virt_queue *vq = &queue->vq;
+ struct net_dev *ndev = queue->ndev;
+ struct kvm *kvm;
+ u16 out, in;
+ u16 head;
+ int len;
+
+ kvm__set_thread_name("virtio-net-tx");
+
+ kvm = ndev->kvm;
+
+ while (1) {
+ mutex_lock(&queue->lock);
+ if (!virt_queue__available(vq))
+ pthread_cond_wait(&queue->cond, &queue->lock.mutex);
+ mutex_unlock(&queue->lock);
+
+ while (virt_queue__available(vq)) {
+ struct virtio_net_hdr *hdr;
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ hdr = iov[0].iov_base;
+ virtio_net_fix_tx_hdr(hdr, ndev);
+ len = ndev->ops->tx(iov, out, ndev);
+ if (len < 0) {
+ pr_warning("%s: tx on vq %u failed (%d)\n",
+ __func__, queue->id, errno);
+ goto out_err;
+ }
+
+ virt_queue__set_used_elem(vq, head, len);
+ }
+
+ if (virtio_queue__should_signal(vq))
+ ndev->vdev.ops->signal_vq(kvm, &ndev->vdev, queue->id);
+ }
+
+out_err:
+ pthread_exit(NULL);
+ return NULL;
+}
+
+static virtio_net_ctrl_ack virtio_net_handle_mq(struct kvm* kvm, struct net_dev *ndev, struct virtio_net_ctrl_hdr *ctrl)
+{
+ /* Not much to do here */
+ return VIRTIO_NET_OK;
+}
+
+static void *virtio_net_ctrl_thread(void *p)
+{
+ struct iovec iov[VIRTIO_NET_QUEUE_SIZE];
+ struct net_dev_queue *queue = p;
+ struct virt_queue *vq = &queue->vq;
+ struct net_dev *ndev = queue->ndev;
+ u16 out, in, head;
+ struct kvm *kvm = ndev->kvm;
+ struct virtio_net_ctrl_hdr *ctrl;
+ virtio_net_ctrl_ack *ack;
+
+ kvm__set_thread_name("virtio-net-ctrl");
+
+ while (1) {
+ mutex_lock(&queue->lock);
+ if (!virt_queue__available(vq))
+ pthread_cond_wait(&queue->cond, &queue->lock.mutex);
+ mutex_unlock(&queue->lock);
+
+ while (virt_queue__available(vq)) {
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ ctrl = iov[0].iov_base;
+ ack = iov[out].iov_base;
+
+ switch (ctrl->class) {
+ case VIRTIO_NET_CTRL_MQ:
+ *ack = virtio_net_handle_mq(kvm, ndev, ctrl);
+ break;
+ default:
+ *ack = VIRTIO_NET_ERR;
+ break;
+ }
+ virt_queue__set_used_elem(vq, head, iov[out].iov_len);
+ }
+
+ if (virtio_queue__should_signal(vq))
+ ndev->vdev.ops->signal_vq(kvm, &ndev->vdev, queue->id);
+ }
+
+ pthread_exit(NULL);
+
+ return NULL;
+}
+
+static void virtio_net_handle_callback(struct kvm *kvm, struct net_dev *ndev, int queue)
+{
+ struct net_dev_queue *net_queue = &ndev->queues[queue];
+
+ if ((u32)queue >= (ndev->queue_pairs * 2 + 1)) {
+ pr_warning("Unknown queue index %u", queue);
+ return;
+ }
+
+ mutex_lock(&net_queue->lock);
+ pthread_cond_signal(&net_queue->cond);
+ mutex_unlock(&net_queue->lock);
+}
+
+static int virtio_net_request_tap(struct net_dev *ndev, struct ifreq *ifr,
+ const char *tapname)
+{
+ int ret;
+
+ memset(ifr, 0, sizeof(*ifr));
+ ifr->ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
+ if (tapname)
+ strlcpy(ifr->ifr_name, tapname, sizeof(ifr->ifr_name));
+
+ ret = ioctl(ndev->tap_fd, TUNSETIFF, ifr);
+
+ if (ret >= 0)
+ strlcpy(ndev->tap_name, ifr->ifr_name, sizeof(ndev->tap_name));
+ return ret;
+}
+
+static int virtio_net_exec_script(const char* script, const char *tap_name)
+{
+ pid_t pid;
+ int status;
+
+ pid = fork();
+ if (pid == 0) {
+ execl(script, script, tap_name, NULL);
+ _exit(1);
+ } else {
+ waitpid(pid, &status, 0);
+ if (WIFEXITED(status) && WEXITSTATUS(status) != 0) {
+ pr_warning("Fail to setup tap by %s", script);
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static bool virtio_net__tap_init(struct net_dev *ndev)
+{
+ int sock = socket(AF_INET, SOCK_STREAM, 0);
+ int hdr_len;
+ struct sockaddr_in sin = {0};
+ struct ifreq ifr;
+ const struct virtio_net_params *params = ndev->params;
+ bool skipconf = !!params->tapif;
+
+ hdr_len = has_virtio_feature(ndev, VIRTIO_NET_F_MRG_RXBUF) ?
+ sizeof(struct virtio_net_hdr_mrg_rxbuf) :
+ sizeof(struct virtio_net_hdr);
+ if (ioctl(ndev->tap_fd, TUNSETVNETHDRSZ, &hdr_len) < 0)
+ pr_warning("Config tap device TUNSETVNETHDRSZ error");
+
+ if (strcmp(params->script, "none")) {
+ if (virtio_net_exec_script(params->script, ndev->tap_name) < 0)
+ goto fail;
+ } else if (!skipconf) {
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy(ifr.ifr_name, ndev->tap_name, sizeof(ifr.ifr_name));
+ sin.sin_addr.s_addr = inet_addr(params->host_ip);
+ memcpy(&(ifr.ifr_addr), &sin, sizeof(ifr.ifr_addr));
+ ifr.ifr_addr.sa_family = AF_INET;
+ if (ioctl(sock, SIOCSIFADDR, &ifr) < 0) {
+ pr_warning("Could not set ip address on tap device");
+ goto fail;
+ }
+ }
+
+ if (!skipconf) {
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy(ifr.ifr_name, ndev->tap_name, sizeof(ifr.ifr_name));
+ ioctl(sock, SIOCGIFFLAGS, &ifr);
+ ifr.ifr_flags |= IFF_UP | IFF_RUNNING;
+ if (ioctl(sock, SIOCSIFFLAGS, &ifr) < 0)
+ pr_warning("Could not bring tap device up");
+ }
+
+ close(sock);
+
+ return 1;
+
+fail:
+ if (sock >= 0)
+ close(sock);
+ if (ndev->tap_fd >= 0)
+ close(ndev->tap_fd);
+
+ return 0;
+}
+
+static void virtio_net__tap_exit(struct net_dev *ndev)
+{
+ int sock;
+ struct ifreq ifr;
+
+ if (ndev->params->tapif)
+ return;
+
+ sock = socket(AF_INET, SOCK_STREAM, 0);
+ strncpy(ifr.ifr_name, ndev->tap_name, sizeof(ifr.ifr_name));
+ ioctl(sock, SIOCGIFFLAGS, &ifr);
+ ifr.ifr_flags &= ~(IFF_UP | IFF_RUNNING);
+ if (ioctl(sock, SIOCGIFFLAGS, &ifr) < 0)
+ pr_warning("Count not bring tap device down");
+ close(sock);
+}
+
+static bool virtio_net__tap_create(struct net_dev *ndev)
+{
+ int offload;
+ struct ifreq ifr;
+ const struct virtio_net_params *params = ndev->params;
+ bool macvtap = (!!params->tapif) && (params->tapif[0] == '/');
+
+ /* Did the user already gave us the FD? */
+ if (params->fd)
+ ndev->tap_fd = params->fd;
+ else {
+ const char *tap_file = "/dev/net/tun";
+
+ /* Did the user ask us to use macvtap? */
+ if (macvtap)
+ tap_file = params->tapif;
+
+ ndev->tap_fd = open(tap_file, O_RDWR);
+ if (ndev->tap_fd < 0) {
+ pr_warning("Unable to open %s", tap_file);
+ return 0;
+ }
+ }
+
+ if (!macvtap &&
+ virtio_net_request_tap(ndev, &ifr, params->tapif) < 0) {
+ pr_warning("Config tap device error. Are you root?");
+ goto fail;
+ }
+
+ /*
+ * The UFO support had been removed from kernel in commit:
+ * ID: fb652fdfe83710da0ca13448a41b7ed027d0a984
+ * https://www.spinics.net/lists/netdev/msg443562.html
+ * In oder to support the older kernels without this commit,
+ * we set the TUN_F_UFO to offload by default to test the status of
+ * UFO kernel support.
+ */
+ ndev->tap_ufo = true;
+ offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_UFO;
+ if (ioctl(ndev->tap_fd, TUNSETOFFLOAD, offload) < 0) {
+ /*
+ * Is this failure caused by kernel remove the UFO support?
+ * Try TUNSETOFFLOAD without TUN_F_UFO.
+ */
+ offload &= ~TUN_F_UFO;
+ if (ioctl(ndev->tap_fd, TUNSETOFFLOAD, offload) < 0) {
+ pr_warning("Config tap device TUNSETOFFLOAD error");
+ goto fail;
+ }
+ ndev->tap_ufo = false;
+ }
+
+ return 1;
+
+fail:
+ if ((ndev->tap_fd >= 0) || (!params->fd) )
+ close(ndev->tap_fd);
+
+ return 0;
+}
+
+static inline int tap_ops_tx(struct iovec *iov, u16 out, struct net_dev *ndev)
+{
+ return writev(ndev->tap_fd, iov, out);
+}
+
+static inline int tap_ops_rx(struct iovec *iov, u16 in, struct net_dev *ndev)
+{
+ return readv(ndev->tap_fd, iov, in);
+}
+
+static inline int uip_ops_tx(struct iovec *iov, u16 out, struct net_dev *ndev)
+{
+ return uip_tx(iov, out, &ndev->info);
+}
+
+static inline int uip_ops_rx(struct iovec *iov, u16 in, struct net_dev *ndev)
+{
+ return uip_rx(iov, in, &ndev->info);
+}
+
+static struct net_dev_operations tap_ops = {
+ .rx = tap_ops_rx,
+ .tx = tap_ops_tx,
+};
+
+static struct net_dev_operations uip_ops = {
+ .rx = uip_ops_rx,
+ .tx = uip_ops_tx,
+};
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct net_dev *ndev = dev;
+
+ return ((u8 *)(&ndev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ u32 features;
+ struct net_dev *ndev = dev;
+
+ features = 1UL << VIRTIO_NET_F_MAC
+ | 1UL << VIRTIO_NET_F_CSUM
+ | 1UL << VIRTIO_NET_F_HOST_TSO4
+ | 1UL << VIRTIO_NET_F_HOST_TSO6
+ | 1UL << VIRTIO_NET_F_GUEST_TSO4
+ | 1UL << VIRTIO_NET_F_GUEST_TSO6
+ | 1UL << VIRTIO_RING_F_EVENT_IDX
+ | 1UL << VIRTIO_RING_F_INDIRECT_DESC
+ | 1UL << VIRTIO_NET_F_CTRL_VQ
+ | 1UL << VIRTIO_NET_F_MRG_RXBUF
+ | 1UL << (ndev->queue_pairs > 1 ? VIRTIO_NET_F_MQ : 0);
+
+ /*
+ * The UFO feature for host and guest only can be enabled when the
+ * kernel has TAP UFO support.
+ */
+ if (ndev->tap_ufo)
+ features |= (1UL << VIRTIO_NET_F_HOST_UFO
+ | 1UL << VIRTIO_NET_F_GUEST_UFO);
+
+ return features;
+}
+
+static int virtio_net__vhost_set_features(struct net_dev *ndev)
+{
+ u64 features = 1UL << VIRTIO_RING_F_EVENT_IDX;
+ u64 vhost_features;
+
+ if (ioctl(ndev->vhost_fd, VHOST_GET_FEATURES, &vhost_features) != 0)
+ die_perror("VHOST_GET_FEATURES failed");
+
+ /* make sure both side support mergable rx buffers */
+ if (vhost_features & 1UL << VIRTIO_NET_F_MRG_RXBUF &&
+ has_virtio_feature(ndev, VIRTIO_NET_F_MRG_RXBUF))
+ features |= 1UL << VIRTIO_NET_F_MRG_RXBUF;
+
+ return ioctl(ndev->vhost_fd, VHOST_SET_FEATURES, &features);
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct net_dev *ndev = dev;
+ struct virtio_net_config *conf = &ndev->config;
+
+ ndev->features = features;
+
+ conf->status = virtio_host_to_guest_u16(&ndev->vdev, conf->status);
+ conf->max_virtqueue_pairs = virtio_host_to_guest_u16(&ndev->vdev,
+ conf->max_virtqueue_pairs);
+}
+
+static void virtio_net_start(struct net_dev *ndev)
+{
+ if (ndev->mode == NET_MODE_TAP) {
+ if (!virtio_net__tap_init(ndev))
+ die_perror("TAP device initialized failed because");
+
+ if (ndev->vhost_fd &&
+ virtio_net__vhost_set_features(ndev) != 0)
+ die_perror("VHOST_SET_FEATURES failed");
+ } else {
+ ndev->info.vnet_hdr_len = has_virtio_feature(ndev, VIRTIO_NET_F_MRG_RXBUF) ?
+ sizeof(struct virtio_net_hdr_mrg_rxbuf) :
+ sizeof(struct virtio_net_hdr);
+ uip_init(&ndev->info);
+ }
+}
+
+static void virtio_net_stop(struct net_dev *ndev)
+{
+ /* Undo whatever start() did */
+ if (ndev->mode == NET_MODE_TAP)
+ virtio_net__tap_exit(ndev);
+ else
+ uip_exit(&ndev->info);
+}
+
+static void notify_status(struct kvm *kvm, void *dev, u32 status)
+{
+ if (status & VIRTIO__STATUS_START)
+ virtio_net_start(dev);
+ else if (status & VIRTIO__STATUS_STOP)
+ virtio_net_stop(dev);
+}
+
+static bool is_ctrl_vq(struct net_dev *ndev, u32 vq)
+{
+ return vq == (u32)(ndev->queue_pairs * 2);
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 page_size, u32 align,
+ u32 pfn)
+{
+ struct vhost_vring_state state = { .index = vq };
+ struct net_dev_queue *net_queue;
+ struct vhost_vring_addr addr;
+ struct net_dev *ndev = dev;
+ struct virt_queue *queue;
+ void *p;
+ int r;
+
+ compat__remove_message(compat_id);
+
+ net_queue = &ndev->queues[vq];
+ net_queue->id = vq;
+ net_queue->ndev = ndev;
+ queue = &net_queue->vq;
+ queue->pfn = pfn;
+ p = virtio_get_vq(kvm, queue->pfn, page_size);
+
+ vring_init(&queue->vring, VIRTIO_NET_QUEUE_SIZE, p, align);
+ virtio_init_device_vq(&ndev->vdev, queue);
+
+ mutex_init(&net_queue->lock);
+ pthread_cond_init(&net_queue->cond, NULL);
+ if (is_ctrl_vq(ndev, vq)) {
+ pthread_create(&net_queue->thread, NULL, virtio_net_ctrl_thread,
+ net_queue);
+
+ return 0;
+ } else if (ndev->vhost_fd == 0 ) {
+ if (vq & 1)
+ pthread_create(&net_queue->thread, NULL,
+ virtio_net_tx_thread, net_queue);
+ else
+ pthread_create(&net_queue->thread, NULL,
+ virtio_net_rx_thread, net_queue);
+
+ return 0;
+ }
+
+ if (queue->endian != VIRTIO_ENDIAN_HOST)
+ die_perror("VHOST requires the same endianness in guest and host");
+
+ state.num = queue->vring.num;
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_NUM, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_NUM failed");
+ state.num = 0;
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_BASE, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_BASE failed");
+
+ addr = (struct vhost_vring_addr) {
+ .index = vq,
+ .desc_user_addr = (u64)(unsigned long)queue->vring.desc,
+ .avail_user_addr = (u64)(unsigned long)queue->vring.avail,
+ .used_user_addr = (u64)(unsigned long)queue->vring.used,
+ };
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_ADDR, &addr);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_ADDR failed");
+
+ return 0;
+}
+
+static void exit_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct net_dev *ndev = dev;
+ struct net_dev_queue *queue = &ndev->queues[vq];
+
+ if (!is_ctrl_vq(ndev, vq) && queue->gsi) {
+ irq__del_irqfd(kvm, queue->gsi, queue->irqfd);
+ close(queue->irqfd);
+ queue->gsi = queue->irqfd = 0;
+ }
+
+ /*
+ * TODO: vhost reset owner. It's the only way to cleanly stop vhost, but
+ * we can't restart it at the moment.
+ */
+ if (ndev->vhost_fd && !is_ctrl_vq(ndev, vq)) {
+ pr_warning("Cannot reset VHOST queue");
+ ioctl(ndev->vhost_fd, VHOST_RESET_OWNER);
+ return;
+ }
+
+ /*
+ * Threads are waiting on cancellation points (readv or
+ * pthread_cond_wait) and should stop gracefully.
+ */
+ pthread_cancel(queue->thread);
+ pthread_join(queue->thread, NULL);
+}
+
+static void notify_vq_gsi(struct kvm *kvm, void *dev, u32 vq, u32 gsi)
+{
+ struct net_dev *ndev = dev;
+ struct net_dev_queue *queue = &ndev->queues[vq];
+ struct vhost_vring_file file;
+ int r;
+
+ if (ndev->vhost_fd == 0)
+ return;
+
+ file = (struct vhost_vring_file) {
+ .index = vq,
+ .fd = eventfd(0, 0),
+ };
+
+ r = irq__add_irqfd(kvm, gsi, file.fd, -1);
+ if (r < 0)
+ die_perror("KVM_IRQFD failed");
+
+ queue->irqfd = file.fd;
+ queue->gsi = gsi;
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_CALL, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_CALL failed");
+ file.fd = ndev->tap_fd;
+ r = ioctl(ndev->vhost_fd, VHOST_NET_SET_BACKEND, &file);
+ if (r != 0)
+ die("VHOST_NET_SET_BACKEND failed %d", errno);
+
+}
+
+static void notify_vq_eventfd(struct kvm *kvm, void *dev, u32 vq, u32 efd)
+{
+ struct net_dev *ndev = dev;
+ struct vhost_vring_file file = {
+ .index = vq,
+ .fd = efd,
+ };
+ int r;
+
+ if (ndev->vhost_fd == 0 || is_ctrl_vq(ndev, vq))
+ return;
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_KICK, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_KICK failed");
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct net_dev *ndev = dev;
+
+ virtio_net_handle_callback(kvm, ndev, vq);
+
+ return 0;
+}
+
+static struct virt_queue *get_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct net_dev *ndev = dev;
+
+ return &ndev->queues[vq].vq;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ /* FIXME: dynamic */
+ return VIRTIO_NET_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static int get_vq_count(struct kvm *kvm, void *dev)
+{
+ struct net_dev *ndev = dev;
+
+ return ndev->queue_pairs * 2 + 1;
+}
+
+static struct virtio_ops net_dev_virtio_ops = {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .get_vq_count = get_vq_count,
+ .init_vq = init_vq,
+ .exit_vq = exit_vq,
+ .get_vq = get_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+ .notify_vq = notify_vq,
+ .notify_vq_gsi = notify_vq_gsi,
+ .notify_vq_eventfd = notify_vq_eventfd,
+ .notify_status = notify_status,
+};
+
+static void virtio_net__vhost_init(struct kvm *kvm, struct net_dev *ndev)
+{
+ struct kvm_mem_bank *bank;
+ struct vhost_memory *mem;
+ int r, i;
+
+ ndev->vhost_fd = open("/dev/vhost-net", O_RDWR);
+ if (ndev->vhost_fd < 0)
+ die_perror("Failed openning vhost-net device");
+
+ mem = calloc(1, sizeof(*mem) + kvm->mem_slots * sizeof(struct vhost_memory_region));
+ if (mem == NULL)
+ die("Failed allocating memory for vhost memory map");
+
+ i = 0;
+ list_for_each_entry(bank, &kvm->mem_banks, list) {
+ mem->regions[i] = (struct vhost_memory_region) {
+ .guest_phys_addr = bank->guest_phys_addr,
+ .memory_size = bank->size,
+ .userspace_addr = (unsigned long)bank->host_addr,
+ };
+ i++;
+ }
+ mem->nregions = i;
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_OWNER);
+ if (r != 0)
+ die_perror("VHOST_SET_OWNER failed");
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_MEM_TABLE, mem);
+ if (r != 0)
+ die_perror("VHOST_SET_MEM_TABLE failed");
+
+ ndev->vdev.use_vhost = true;
+
+ free(mem);
+}
+
+static inline void str_to_mac(const char *str, char *mac)
+{
+ sscanf(str, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
+ mac, mac+1, mac+2, mac+3, mac+4, mac+5);
+}
+static int set_net_param(struct kvm *kvm, struct virtio_net_params *p,
+ const char *param, const char *val)
+{
+ if (strcmp(param, "guest_mac") == 0) {
+ str_to_mac(val, p->guest_mac);
+ } else if (strcmp(param, "mode") == 0) {
+ if (!strncmp(val, "user", 4)) {
+ int i;
+
+ for (i = 0; i < kvm->cfg.num_net_devices; i++)
+ if (kvm->cfg.net_params[i].mode == NET_MODE_USER)
+ die("Only one usermode network device allowed at a time");
+ p->mode = NET_MODE_USER;
+ } else if (!strncmp(val, "tap", 3)) {
+ p->mode = NET_MODE_TAP;
+ } else if (!strncmp(val, "none", 4)) {
+ kvm->cfg.no_net = 1;
+ return -1;
+ } else
+ die("Unknown network mode %s, please use user, tap or none", kvm->cfg.network);
+ } else if (strcmp(param, "script") == 0) {
+ p->script = strdup(val);
+ } else if (strcmp(param, "downscript") == 0) {
+ p->downscript = strdup(val);
+ } else if (strcmp(param, "guest_ip") == 0) {
+ p->guest_ip = strdup(val);
+ } else if (strcmp(param, "host_ip") == 0) {
+ p->host_ip = strdup(val);
+ } else if (strcmp(param, "trans") == 0) {
+ p->trans = strdup(val);
+ } else if (strcmp(param, "tapif") == 0) {
+ p->tapif = strdup(val);
+ } else if (strcmp(param, "vhost") == 0) {
+ p->vhost = atoi(val);
+ } else if (strcmp(param, "fd") == 0) {
+ p->fd = atoi(val);
+ } else if (strcmp(param, "mq") == 0) {
+ p->mq = atoi(val);
+ } else
+ die("Unknown network parameter %s", param);
+
+ return 0;
+}
+
+int netdev_parser(const struct option *opt, const char *arg, int unset)
+{
+ struct virtio_net_params p;
+ char *buf = NULL, *cmd = NULL, *cur = NULL;
+ bool on_cmd = true;
+ struct kvm *kvm = opt->ptr;
+
+ if (arg) {
+ buf = strdup(arg);
+ if (buf == NULL)
+ die("Failed allocating new net buffer");
+ cur = strtok(buf, ",=");
+ }
+
+ p = (struct virtio_net_params) {
+ .guest_ip = DEFAULT_GUEST_ADDR,
+ .host_ip = DEFAULT_HOST_ADDR,
+ .script = DEFAULT_SCRIPT,
+ .downscript = DEFAULT_SCRIPT,
+ .mode = NET_MODE_TAP,
+ };
+
+ str_to_mac(DEFAULT_GUEST_MAC, p.guest_mac);
+ p.guest_mac[5] += kvm->cfg.num_net_devices;
+
+ while (cur) {
+ if (on_cmd) {
+ cmd = cur;
+ } else {
+ if (set_net_param(kvm, &p, cmd, cur) < 0)
+ goto done;
+ }
+ on_cmd = !on_cmd;
+
+ cur = strtok(NULL, ",=");
+ };
+
+ kvm->cfg.num_net_devices++;
+
+ kvm->cfg.net_params = realloc(kvm->cfg.net_params, kvm->cfg.num_net_devices * sizeof(*kvm->cfg.net_params));
+ if (kvm->cfg.net_params == NULL)
+ die("Failed adding new network device");
+
+ kvm->cfg.net_params[kvm->cfg.num_net_devices - 1] = p;
+
+done:
+ free(buf);
+ return 0;
+}
+
+static int virtio_net__init_one(struct virtio_net_params *params)
+{
+ int i, r;
+ struct net_dev *ndev;
+ struct virtio_ops *ops;
+ enum virtio_trans trans = VIRTIO_DEFAULT_TRANS(params->kvm);
+
+ ndev = calloc(1, sizeof(struct net_dev));
+ if (ndev == NULL)
+ return -ENOMEM;
+
+ list_add_tail(&ndev->list, &ndevs);
+
+ ops = malloc(sizeof(*ops));
+ if (ops == NULL)
+ return -ENOMEM;
+
+ ndev->kvm = params->kvm;
+ ndev->params = params;
+
+ mutex_init(&ndev->mutex);
+ ndev->queue_pairs = max(1, min(VIRTIO_NET_NUM_QUEUES, params->mq));
+ ndev->config.status = VIRTIO_NET_S_LINK_UP;
+ if (ndev->queue_pairs > 1)
+ ndev->config.max_virtqueue_pairs = ndev->queue_pairs;
+
+ for (i = 0 ; i < 6 ; i++) {
+ ndev->config.mac[i] = params->guest_mac[i];
+ ndev->info.guest_mac.addr[i] = params->guest_mac[i];
+ ndev->info.host_mac.addr[i] = params->host_mac[i];
+ }
+
+ ndev->mode = params->mode;
+ if (ndev->mode == NET_MODE_TAP) {
+ ndev->ops = &tap_ops;
+ if (!virtio_net__tap_create(ndev))
+ die_perror("You have requested a TAP device, but creation of one has failed because");
+ } else {
+ ndev->info.host_ip = ntohl(inet_addr(params->host_ip));
+ ndev->info.guest_ip = ntohl(inet_addr(params->guest_ip));
+ ndev->info.guest_netmask = ntohl(inet_addr("255.255.255.0"));
+ ndev->info.buf_nr = 20,
+ ndev->ops = &uip_ops;
+ uip_static_init(&ndev->info);
+ }
+
+ *ops = net_dev_virtio_ops;
+
+ if (params->trans) {
+ if (strcmp(params->trans, "mmio") == 0)
+ trans = VIRTIO_MMIO;
+ else if (strcmp(params->trans, "pci") == 0)
+ trans = VIRTIO_PCI;
+ else
+ pr_warning("virtio-net: Unknown transport method : %s, "
+ "falling back to %s.", params->trans,
+ virtio_trans_name(trans));
+ }
+
+ r = virtio_init(params->kvm, ndev, &ndev->vdev, ops, trans,
+ PCI_DEVICE_ID_VIRTIO_NET, VIRTIO_ID_NET, PCI_CLASS_NET);
+ if (r < 0) {
+ free(ops);
+ return r;
+ }
+
+ if (params->vhost)
+ virtio_net__vhost_init(params->kvm, ndev);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-net", "CONFIG_VIRTIO_NET");
+
+ return 0;
+}
+
+int virtio_net__init(struct kvm *kvm)
+{
+ int i, r;
+
+ for (i = 0; i < kvm->cfg.num_net_devices; i++) {
+ kvm->cfg.net_params[i].kvm = kvm;
+ r = virtio_net__init_one(&kvm->cfg.net_params[i]);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ if (kvm->cfg.num_net_devices == 0 && kvm->cfg.no_net == 0) {
+ static struct virtio_net_params net_params;
+
+ net_params = (struct virtio_net_params) {
+ .guest_ip = kvm->cfg.guest_ip,
+ .host_ip = kvm->cfg.host_ip,
+ .kvm = kvm,
+ .script = kvm->cfg.script,
+ .mode = NET_MODE_USER,
+ };
+ str_to_mac(kvm->cfg.guest_mac, net_params.guest_mac);
+ str_to_mac(kvm->cfg.host_mac, net_params.host_mac);
+
+ r = virtio_net__init_one(&net_params);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ return 0;
+
+cleanup:
+ virtio_net__exit(kvm);
+ return r;
+}
+virtio_dev_init(virtio_net__init);
+
+int virtio_net__exit(struct kvm *kvm)
+{
+ struct virtio_net_params *params;
+ struct net_dev *ndev;
+ struct list_head *ptr, *n;
+
+ list_for_each_safe(ptr, n, &ndevs) {
+ ndev = list_entry(ptr, struct net_dev, list);
+ params = ndev->params;
+ /* Cleanup any tap device which attached to bridge */
+ if (ndev->mode == NET_MODE_TAP &&
+ strcmp(params->downscript, "none"))
+ virtio_net_exec_script(params->downscript, ndev->tap_name);
+
+ list_del(&ndev->list);
+ free(ndev);
+ }
+ return 0;
+}
+virtio_dev_exit(virtio_net__exit);
diff --git a/kvmtool/virtio/pci.c b/kvmtool/virtio/pci.c
new file mode 100644
index 0000000..6eea6c6
--- /dev/null
+++ b/kvmtool/virtio/pci.c
@@ -0,0 +1,631 @@
+#include "kvm/virtio-pci.h"
+
+#include "kvm/ioport.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/irq.h"
+#include "kvm/virtio.h"
+#include "kvm/ioeventfd.h"
+
+#include <sys/ioctl.h>
+#include <linux/virtio_pci.h>
+#include <linux/byteorder.h>
+#include <assert.h>
+#include <string.h>
+
+static u16 virtio_pci__port_addr(struct virtio_pci *vpci)
+{
+ return pci__bar_address(&vpci->pci_hdr, 0);
+}
+
+static u32 virtio_pci__mmio_addr(struct virtio_pci *vpci)
+{
+ return pci__bar_address(&vpci->pci_hdr, 1);
+}
+
+static u32 virtio_pci__msix_io_addr(struct virtio_pci *vpci)
+{
+ return pci__bar_address(&vpci->pci_hdr, 2);
+}
+
+static void virtio_pci__ioevent_callback(struct kvm *kvm, void *param)
+{
+ struct virtio_pci_ioevent_param *ioeventfd = param;
+ struct virtio_pci *vpci = ioeventfd->vdev->virtio;
+
+ ioeventfd->vdev->ops->notify_vq(kvm, vpci->dev, ioeventfd->vq);
+}
+
+static int virtio_pci__init_ioeventfd(struct kvm *kvm, struct virtio_device *vdev, u32 vq)
+{
+ struct ioevent ioevent;
+ struct virtio_pci *vpci = vdev->virtio;
+ u32 mmio_addr = virtio_pci__mmio_addr(vpci);
+ u16 port_addr = virtio_pci__port_addr(vpci);
+ int r, flags = 0;
+ int fd;
+
+ vpci->ioeventfds[vq] = (struct virtio_pci_ioevent_param) {
+ .vdev = vdev,
+ .vq = vq,
+ };
+
+ ioevent = (struct ioevent) {
+ .fn = virtio_pci__ioevent_callback,
+ .fn_ptr = &vpci->ioeventfds[vq],
+ .datamatch = vq,
+ .fn_kvm = kvm,
+ };
+
+ /*
+ * Vhost will poll the eventfd in host kernel side, otherwise we
+ * need to poll in userspace.
+ */
+ if (!vdev->use_vhost)
+ flags |= IOEVENTFD_FLAG_USER_POLL;
+
+ /* ioport */
+ ioevent.io_addr = port_addr + VIRTIO_PCI_QUEUE_NOTIFY;
+ ioevent.io_len = sizeof(u16);
+ ioevent.fd = fd = eventfd(0, 0);
+ r = ioeventfd__add_event(&ioevent, flags | IOEVENTFD_FLAG_PIO);
+ if (r)
+ return r;
+
+ /* mmio */
+ ioevent.io_addr = mmio_addr + VIRTIO_PCI_QUEUE_NOTIFY;
+ ioevent.io_len = sizeof(u16);
+ ioevent.fd = eventfd(0, 0);
+ r = ioeventfd__add_event(&ioevent, flags);
+ if (r)
+ goto free_ioport_evt;
+
+ if (vdev->ops->notify_vq_eventfd)
+ vdev->ops->notify_vq_eventfd(kvm, vpci->dev, vq, fd);
+ return 0;
+
+free_ioport_evt:
+ ioeventfd__del_event(port_addr + VIRTIO_PCI_QUEUE_NOTIFY, vq);
+ return r;
+}
+
+static void virtio_pci_exit_vq(struct kvm *kvm, struct virtio_device *vdev,
+ int vq)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ u32 mmio_addr = virtio_pci__mmio_addr(vpci);
+ u16 port_addr = virtio_pci__port_addr(vpci);
+
+ ioeventfd__del_event(mmio_addr + VIRTIO_PCI_QUEUE_NOTIFY, vq);
+ ioeventfd__del_event(port_addr + VIRTIO_PCI_QUEUE_NOTIFY, vq);
+ virtio_exit_vq(kvm, vdev, vpci->dev, vq);
+}
+
+static inline bool virtio_pci__msix_enabled(struct virtio_pci *vpci)
+{
+ return vpci->pci_hdr.msix.ctrl & cpu_to_le16(PCI_MSIX_FLAGS_ENABLE);
+}
+
+static bool virtio_pci__specific_data_in(struct kvm *kvm, struct virtio_device *vdev,
+ void *data, int size, unsigned long offset)
+{
+ u32 config_offset;
+ struct virtio_pci *vpci = vdev->virtio;
+ int type = virtio__get_dev_specific_field(offset - 20,
+ virtio_pci__msix_enabled(vpci),
+ &config_offset);
+ if (type == VIRTIO_PCI_O_MSIX) {
+ switch (offset) {
+ case VIRTIO_MSI_CONFIG_VECTOR:
+ ioport__write16(data, vpci->config_vector);
+ break;
+ case VIRTIO_MSI_QUEUE_VECTOR:
+ ioport__write16(data, vpci->vq_vector[vpci->queue_selector]);
+ break;
+ };
+
+ return true;
+ } else if (type == VIRTIO_PCI_O_CONFIG) {
+ u8 cfg;
+
+ cfg = vdev->ops->get_config(kvm, vpci->dev)[config_offset];
+ ioport__write8(data, cfg);
+ return true;
+ }
+
+ return false;
+}
+
+static bool virtio_pci__data_in(struct kvm_cpu *vcpu, struct virtio_device *vdev,
+ unsigned long offset, void *data, int size)
+{
+ bool ret = true;
+ struct virtio_pci *vpci;
+ struct virt_queue *vq;
+ struct kvm *kvm;
+ u32 val;
+
+ kvm = vcpu->kvm;
+ vpci = vdev->virtio;
+
+ switch (offset) {
+ case VIRTIO_PCI_HOST_FEATURES:
+ val = vdev->ops->get_host_features(kvm, vpci->dev);
+ ioport__write32(data, val);
+ break;
+ case VIRTIO_PCI_QUEUE_PFN:
+ vq = vdev->ops->get_vq(kvm, vpci->dev, vpci->queue_selector);
+ ioport__write32(data, vq->pfn);
+ break;
+ case VIRTIO_PCI_QUEUE_NUM:
+ val = vdev->ops->get_size_vq(kvm, vpci->dev, vpci->queue_selector);
+ ioport__write16(data, val);
+ break;
+ case VIRTIO_PCI_STATUS:
+ ioport__write8(data, vpci->status);
+ break;
+ case VIRTIO_PCI_ISR:
+ ioport__write8(data, vpci->isr);
+ kvm__irq_line(kvm, vpci->legacy_irq_line, VIRTIO_IRQ_LOW);
+ vpci->isr = VIRTIO_IRQ_LOW;
+ break;
+ default:
+ ret = virtio_pci__specific_data_in(kvm, vdev, data, size, offset);
+ break;
+ };
+
+ return ret;
+}
+
+static bool virtio_pci__io_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ struct virtio_device *vdev = ioport->priv;
+ struct virtio_pci *vpci = vdev->virtio;
+ unsigned long offset = port - virtio_pci__port_addr(vpci);
+
+ return virtio_pci__data_in(vcpu, vdev, offset, data, size);
+}
+
+static void update_msix_map(struct virtio_pci *vpci,
+ struct msix_table *msix_entry, u32 vecnum)
+{
+ u32 gsi, i;
+
+ /* Find the GSI number used for that vector */
+ if (vecnum == vpci->config_vector) {
+ gsi = vpci->config_gsi;
+ } else {
+ for (i = 0; i < VIRTIO_PCI_MAX_VQ; i++)
+ if (vpci->vq_vector[i] == vecnum)
+ break;
+ if (i == VIRTIO_PCI_MAX_VQ)
+ return;
+ gsi = vpci->gsis[i];
+ }
+
+ if (gsi == 0)
+ return;
+
+ msix_entry = &msix_entry[vecnum];
+ irq__update_msix_route(vpci->kvm, gsi, &msix_entry->msg);
+}
+
+static bool virtio_pci__specific_data_out(struct kvm *kvm, struct virtio_device *vdev,
+ void *data, int size, unsigned long offset)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ u32 config_offset, vec;
+ int gsi;
+ int type = virtio__get_dev_specific_field(offset - 20, virtio_pci__msix_enabled(vpci),
+ &config_offset);
+ if (type == VIRTIO_PCI_O_MSIX) {
+ switch (offset) {
+ case VIRTIO_MSI_CONFIG_VECTOR:
+ vec = vpci->config_vector = ioport__read16(data);
+ if (vec == VIRTIO_MSI_NO_VECTOR)
+ break;
+
+ gsi = irq__add_msix_route(kvm,
+ &vpci->msix_table[vec].msg,
+ vpci->dev_hdr.dev_num << 3);
+ /*
+ * We don't need IRQ routing if we can use
+ * MSI injection via the KVM_SIGNAL_MSI ioctl.
+ */
+ if (gsi == -ENXIO &&
+ vpci->features & VIRTIO_PCI_F_SIGNAL_MSI)
+ break;
+
+ if (gsi < 0) {
+ die("failed to configure MSIs");
+ break;
+ }
+
+ vpci->config_gsi = gsi;
+ break;
+ case VIRTIO_MSI_QUEUE_VECTOR:
+ vec = ioport__read16(data);
+ vpci->vq_vector[vpci->queue_selector] = vec;
+
+ if (vec == VIRTIO_MSI_NO_VECTOR)
+ break;
+
+ gsi = irq__add_msix_route(kvm,
+ &vpci->msix_table[vec].msg,
+ vpci->dev_hdr.dev_num << 3);
+ /*
+ * We don't need IRQ routing if we can use
+ * MSI injection via the KVM_SIGNAL_MSI ioctl.
+ */
+ if (gsi == -ENXIO &&
+ vpci->features & VIRTIO_PCI_F_SIGNAL_MSI)
+ break;
+
+ if (gsi < 0) {
+ die("failed to configure MSIs");
+ break;
+ }
+
+ vpci->gsis[vpci->queue_selector] = gsi;
+ if (vdev->ops->notify_vq_gsi)
+ vdev->ops->notify_vq_gsi(kvm, vpci->dev,
+ vpci->queue_selector,
+ gsi);
+ break;
+ };
+
+ return true;
+ } else if (type == VIRTIO_PCI_O_CONFIG) {
+ vdev->ops->get_config(kvm, vpci->dev)[config_offset] = *(u8 *)data;
+
+ return true;
+ }
+
+ return false;
+}
+
+static bool virtio_pci__data_out(struct kvm_cpu *vcpu, struct virtio_device *vdev,
+ unsigned long offset, void *data, int size)
+{
+ bool ret = true;
+ struct virtio_pci *vpci;
+ struct kvm *kvm;
+ u32 val;
+
+ kvm = vcpu->kvm;
+ vpci = vdev->virtio;
+
+ switch (offset) {
+ case VIRTIO_PCI_GUEST_FEATURES:
+ val = ioport__read32(data);
+ virtio_set_guest_features(kvm, vdev, vpci->dev, val);
+ break;
+ case VIRTIO_PCI_QUEUE_PFN:
+ val = ioport__read32(data);
+ if (val) {
+ virtio_pci__init_ioeventfd(kvm, vdev,
+ vpci->queue_selector);
+ vdev->ops->init_vq(kvm, vpci->dev, vpci->queue_selector,
+ 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT,
+ VIRTIO_PCI_VRING_ALIGN, val);
+ } else {
+ virtio_pci_exit_vq(kvm, vdev, vpci->queue_selector);
+ }
+ break;
+ case VIRTIO_PCI_QUEUE_SEL:
+ vpci->queue_selector = ioport__read16(data);
+ break;
+ case VIRTIO_PCI_QUEUE_NOTIFY:
+ val = ioport__read16(data);
+ vdev->ops->notify_vq(kvm, vpci->dev, val);
+ break;
+ case VIRTIO_PCI_STATUS:
+ vpci->status = ioport__read8(data);
+ if (!vpci->status) /* Sample endianness on reset */
+ vdev->endian = kvm_cpu__get_endianness(vcpu);
+ virtio_notify_status(kvm, vdev, vpci->dev, vpci->status);
+ break;
+ default:
+ ret = virtio_pci__specific_data_out(kvm, vdev, data, size, offset);
+ break;
+ };
+
+ return ret;
+}
+
+static bool virtio_pci__io_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ struct virtio_device *vdev = ioport->priv;
+ struct virtio_pci *vpci = vdev->virtio;
+ unsigned long offset = port - virtio_pci__port_addr(vpci);
+
+ return virtio_pci__data_out(vcpu, vdev, offset, data, size);
+}
+
+static struct ioport_operations virtio_pci__io_ops = {
+ .io_in = virtio_pci__io_in,
+ .io_out = virtio_pci__io_out,
+};
+
+static void virtio_pci__msix_mmio_callback(struct kvm_cpu *vcpu,
+ u64 addr, u8 *data, u32 len,
+ u8 is_write, void *ptr)
+{
+ struct virtio_device *vdev = ptr;
+ struct virtio_pci *vpci = vdev->virtio;
+ struct msix_table *table;
+ u32 msix_io_addr = virtio_pci__msix_io_addr(vpci);
+ int vecnum;
+ size_t offset;
+
+ if (addr > msix_io_addr + PCI_IO_SIZE) {
+ if (is_write)
+ return;
+ table = (struct msix_table *)&vpci->msix_pba;
+ offset = addr - (msix_io_addr + PCI_IO_SIZE);
+ } else {
+ table = vpci->msix_table;
+ offset = addr - msix_io_addr;
+ }
+ vecnum = offset / sizeof(struct msix_table);
+ offset = offset % sizeof(struct msix_table);
+
+ if (!is_write) {
+ memcpy(data, (void *)&table[vecnum] + offset, len);
+ return;
+ }
+
+ memcpy((void *)&table[vecnum] + offset, data, len);
+
+ /* Did we just update the address or payload? */
+ if (offset < offsetof(struct msix_table, ctrl))
+ update_msix_map(vpci, table, vecnum);
+}
+
+static void virtio_pci__signal_msi(struct kvm *kvm, struct virtio_pci *vpci,
+ int vec)
+{
+ struct kvm_msi msi = {
+ .address_lo = vpci->msix_table[vec].msg.address_lo,
+ .address_hi = vpci->msix_table[vec].msg.address_hi,
+ .data = vpci->msix_table[vec].msg.data,
+ };
+
+ if (kvm->msix_needs_devid) {
+ msi.flags = KVM_MSI_VALID_DEVID;
+ msi.devid = vpci->dev_hdr.dev_num << 3;
+ }
+
+ irq__signal_msi(kvm, &msi);
+}
+
+int virtio_pci__signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ int tbl = vpci->vq_vector[vq];
+
+ if (virtio_pci__msix_enabled(vpci) && tbl != VIRTIO_MSI_NO_VECTOR) {
+ if (vpci->pci_hdr.msix.ctrl & cpu_to_le16(PCI_MSIX_FLAGS_MASKALL) ||
+ vpci->msix_table[tbl].ctrl & cpu_to_le16(PCI_MSIX_ENTRY_CTRL_MASKBIT)) {
+
+ vpci->msix_pba |= 1 << tbl;
+ return 0;
+ }
+
+ if (vpci->features & VIRTIO_PCI_F_SIGNAL_MSI)
+ virtio_pci__signal_msi(kvm, vpci, vpci->vq_vector[vq]);
+ else
+ kvm__irq_trigger(kvm, vpci->gsis[vq]);
+ } else {
+ vpci->isr = VIRTIO_IRQ_HIGH;
+ kvm__irq_trigger(kvm, vpci->legacy_irq_line);
+ }
+ return 0;
+}
+
+int virtio_pci__signal_config(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ int tbl = vpci->config_vector;
+
+ if (virtio_pci__msix_enabled(vpci) && tbl != VIRTIO_MSI_NO_VECTOR) {
+ if (vpci->pci_hdr.msix.ctrl & cpu_to_le16(PCI_MSIX_FLAGS_MASKALL) ||
+ vpci->msix_table[tbl].ctrl & cpu_to_le16(PCI_MSIX_ENTRY_CTRL_MASKBIT)) {
+
+ vpci->msix_pba |= 1 << tbl;
+ return 0;
+ }
+
+ if (vpci->features & VIRTIO_PCI_F_SIGNAL_MSI)
+ virtio_pci__signal_msi(kvm, vpci, tbl);
+ else
+ kvm__irq_trigger(kvm, vpci->config_gsi);
+ } else {
+ vpci->isr = VIRTIO_PCI_ISR_CONFIG;
+ kvm__irq_trigger(kvm, vpci->legacy_irq_line);
+ }
+
+ return 0;
+}
+
+static void virtio_pci__io_mmio_callback(struct kvm_cpu *vcpu,
+ u64 addr, u8 *data, u32 len,
+ u8 is_write, void *ptr)
+{
+ struct virtio_device *vdev = ptr;
+ struct virtio_pci *vpci = vdev->virtio;
+ u32 mmio_addr = virtio_pci__mmio_addr(vpci);
+
+ if (!is_write)
+ virtio_pci__data_in(vcpu, vdev, addr - mmio_addr, data, len);
+ else
+ virtio_pci__data_out(vcpu, vdev, addr - mmio_addr, data, len);
+}
+
+static int virtio_pci__bar_activate(struct kvm *kvm,
+ struct pci_device_header *pci_hdr,
+ int bar_num, void *data)
+{
+ struct virtio_device *vdev = data;
+ u32 bar_addr, bar_size;
+ int r = -EINVAL;
+
+ assert(bar_num <= 2);
+
+ bar_addr = pci__bar_address(pci_hdr, bar_num);
+ bar_size = pci__bar_size(pci_hdr, bar_num);
+
+ switch (bar_num) {
+ case 0:
+ r = ioport__register(kvm, bar_addr, &virtio_pci__io_ops,
+ bar_size, vdev);
+ if (r > 0)
+ r = 0;
+ break;
+ case 1:
+ r = kvm__register_mmio(kvm, bar_addr, bar_size, false,
+ virtio_pci__io_mmio_callback, vdev);
+ break;
+ case 2:
+ r = kvm__register_mmio(kvm, bar_addr, bar_size, false,
+ virtio_pci__msix_mmio_callback, vdev);
+ break;
+ }
+
+ return r;
+}
+
+static int virtio_pci__bar_deactivate(struct kvm *kvm,
+ struct pci_device_header *pci_hdr,
+ int bar_num, void *data)
+{
+ u32 bar_addr;
+ bool success;
+ int r = -EINVAL;
+
+ assert(bar_num <= 2);
+
+ bar_addr = pci__bar_address(pci_hdr, bar_num);
+
+ switch (bar_num) {
+ case 0:
+ r = ioport__unregister(kvm, bar_addr);
+ break;
+ case 1:
+ case 2:
+ success = kvm__deregister_mmio(kvm, bar_addr);
+ /* kvm__deregister_mmio fails when the region is not found. */
+ r = (success ? 0 : -ENOENT);
+ break;
+ }
+
+ return r;
+}
+
+int virtio_pci__init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ u32 mmio_addr, msix_io_block;
+ u16 port_addr;
+ int r;
+
+ vpci->kvm = kvm;
+ vpci->dev = dev;
+
+ BUILD_BUG_ON(!is_power_of_two(PCI_IO_SIZE));
+
+ port_addr = pci_get_io_port_block(PCI_IO_SIZE);
+ mmio_addr = pci_get_mmio_block(PCI_IO_SIZE);
+ msix_io_block = pci_get_mmio_block(PCI_IO_SIZE * 2);
+
+ vpci->pci_hdr = (struct pci_device_header) {
+ .vendor_id = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET),
+ .device_id = cpu_to_le16(device_id),
+ .command = PCI_COMMAND_IO | PCI_COMMAND_MEMORY,
+ .header_type = PCI_HEADER_TYPE_NORMAL,
+ .revision_id = 0,
+ .class[0] = class & 0xff,
+ .class[1] = (class >> 8) & 0xff,
+ .class[2] = (class >> 16) & 0xff,
+ .subsys_vendor_id = cpu_to_le16(PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET),
+ .subsys_id = cpu_to_le16(subsys_id),
+ .bar[0] = cpu_to_le32(port_addr
+ | PCI_BASE_ADDRESS_SPACE_IO),
+ .bar[1] = cpu_to_le32(mmio_addr
+ | PCI_BASE_ADDRESS_SPACE_MEMORY),
+ .bar[2] = cpu_to_le32(msix_io_block
+ | PCI_BASE_ADDRESS_SPACE_MEMORY),
+ .status = cpu_to_le16(PCI_STATUS_CAP_LIST),
+ .capabilities = (void *)&vpci->pci_hdr.msix - (void *)&vpci->pci_hdr,
+ .bar_size[0] = cpu_to_le32(PCI_IO_SIZE),
+ .bar_size[1] = cpu_to_le32(PCI_IO_SIZE),
+ .bar_size[2] = cpu_to_le32(PCI_IO_SIZE*2),
+ };
+
+ r = pci__register_bar_regions(kvm, &vpci->pci_hdr,
+ virtio_pci__bar_activate,
+ virtio_pci__bar_deactivate, vdev);
+ if (r < 0)
+ return r;
+
+ vpci->dev_hdr = (struct device_header) {
+ .bus_type = DEVICE_BUS_PCI,
+ .data = &vpci->pci_hdr,
+ };
+
+ vpci->pci_hdr.msix.cap = PCI_CAP_ID_MSIX;
+ vpci->pci_hdr.msix.next = 0;
+ /*
+ * We at most have VIRTIO_PCI_MAX_VQ entries for virt queue,
+ * VIRTIO_PCI_MAX_CONFIG entries for config.
+ *
+ * To quote the PCI spec:
+ *
+ * System software reads this field to determine the
+ * MSI-X Table Size N, which is encoded as N-1.
+ * For example, a returned value of "00000000011"
+ * indicates a table size of 4.
+ */
+ vpci->pci_hdr.msix.ctrl = cpu_to_le16(VIRTIO_PCI_MAX_VQ + VIRTIO_PCI_MAX_CONFIG - 1);
+
+ /* Both table and PBA are mapped to the same BAR (2) */
+ vpci->pci_hdr.msix.table_offset = cpu_to_le32(2);
+ vpci->pci_hdr.msix.pba_offset = cpu_to_le32(2 | PCI_IO_SIZE);
+ vpci->config_vector = 0;
+
+ if (irq__can_signal_msi(kvm))
+ vpci->features |= VIRTIO_PCI_F_SIGNAL_MSI;
+
+ vpci->legacy_irq_line = pci__assign_irq(&vpci->pci_hdr);
+
+ r = device__register(&vpci->dev_hdr);
+ if (r < 0)
+ return r;
+
+ return 0;
+}
+
+int virtio_pci__reset(struct kvm *kvm, struct virtio_device *vdev)
+{
+ int vq;
+ struct virtio_pci *vpci = vdev->virtio;
+
+ for (vq = 0; vq < vdev->ops->get_vq_count(kvm, vpci->dev); vq++)
+ virtio_pci_exit_vq(kvm, vdev, vq);
+
+ return 0;
+}
+
+int virtio_pci__exit(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+
+ virtio_pci__reset(kvm, vdev);
+ kvm__deregister_mmio(kvm, virtio_pci__mmio_addr(vpci));
+ kvm__deregister_mmio(kvm, virtio_pci__msix_io_addr(vpci));
+ ioport__unregister(kvm, virtio_pci__port_addr(vpci));
+
+ return 0;
+}
diff --git a/kvmtool/virtio/rng.c b/kvmtool/virtio/rng.c
new file mode 100644
index 0000000..78eaa64
--- /dev/null
+++ b/kvmtool/virtio/rng.c
@@ -0,0 +1,211 @@
+#include "kvm/virtio-rng.h"
+
+#include "kvm/virtio-pci-dev.h"
+
+#include "kvm/virtio.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/threadpool.h"
+#include "kvm/guest_compat.h"
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_rng.h>
+
+#include <linux/list.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <pthread.h>
+#include <linux/kernel.h>
+
+#define NUM_VIRT_QUEUES 1
+#define VIRTIO_RNG_QUEUE_SIZE 128
+
+struct rng_dev_job {
+ struct virt_queue *vq;
+ struct rng_dev *rdev;
+ struct thread_pool__job job_id;
+};
+
+struct rng_dev {
+ struct list_head list;
+ struct virtio_device vdev;
+
+ int fd;
+
+ /* virtio queue */
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct rng_dev_job jobs[NUM_VIRT_QUEUES];
+};
+
+static LIST_HEAD(rdevs);
+static int compat_id = -1;
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ /* Unused */
+ return 0;
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ /* Unused */
+ return 0;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ /* Unused */
+}
+
+static bool virtio_rng_do_io_request(struct kvm *kvm, struct rng_dev *rdev, struct virt_queue *queue)
+{
+ struct iovec iov[VIRTIO_RNG_QUEUE_SIZE];
+ ssize_t len = 0;
+ u16 out, in, head;
+
+ head = virt_queue__get_iov(queue, iov, &out, &in, kvm);
+ len = readv(rdev->fd, iov, in);
+ if (len < 0 && errno == EAGAIN)
+ len = 0;
+
+ virt_queue__set_used_elem(queue, head, len);
+
+ return true;
+}
+
+static void virtio_rng_do_io(struct kvm *kvm, void *param)
+{
+ struct rng_dev_job *job = param;
+ struct virt_queue *vq = job->vq;
+ struct rng_dev *rdev = job->rdev;
+
+ while (virt_queue__available(vq))
+ virtio_rng_do_io_request(kvm, rdev, vq);
+
+ rdev->vdev.ops->signal_vq(kvm, &rdev->vdev, vq - rdev->vqs);
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 page_size, u32 align,
+ u32 pfn)
+{
+ struct rng_dev *rdev = dev;
+ struct virt_queue *queue;
+ struct rng_dev_job *job;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &rdev->vqs[vq];
+ queue->pfn = pfn;
+ p = virtio_get_vq(kvm, queue->pfn, page_size);
+
+ job = &rdev->jobs[vq];
+
+ vring_init(&queue->vring, VIRTIO_RNG_QUEUE_SIZE, p, align);
+ virtio_init_device_vq(&rdev->vdev, queue);
+
+ *job = (struct rng_dev_job) {
+ .vq = queue,
+ .rdev = rdev,
+ };
+
+ thread_pool__init_job(&job->job_id, kvm, virtio_rng_do_io, job);
+
+ return 0;
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct rng_dev *rdev = dev;
+
+ thread_pool__do_job(&rdev->jobs[vq].job_id);
+
+ return 0;
+}
+
+static struct virt_queue *get_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct rng_dev *rdev = dev;
+
+ return &rdev->vqs[vq];
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_RNG_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static int get_vq_count(struct kvm *kvm, void *dev)
+{
+ return NUM_VIRT_QUEUES;
+}
+
+static struct virtio_ops rng_dev_virtio_ops = {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .notify_vq = notify_vq,
+ .get_vq = get_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+ .get_vq_count = get_vq_count,
+};
+
+int virtio_rng__init(struct kvm *kvm)
+{
+ struct rng_dev *rdev;
+ int r;
+
+ if (!kvm->cfg.virtio_rng)
+ return 0;
+
+ rdev = malloc(sizeof(*rdev));
+ if (rdev == NULL)
+ return -ENOMEM;
+
+ rdev->fd = open("/dev/random", O_RDONLY | O_NONBLOCK);
+ if (rdev->fd < 0) {
+ r = rdev->fd;
+ goto cleanup;
+ }
+
+ r = virtio_init(kvm, rdev, &rdev->vdev, &rng_dev_virtio_ops,
+ VIRTIO_DEFAULT_TRANS(kvm), PCI_DEVICE_ID_VIRTIO_RNG,
+ VIRTIO_ID_RNG, PCI_CLASS_RNG);
+ if (r < 0)
+ goto cleanup;
+
+ list_add_tail(&rdev->list, &rdevs);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-rng", "CONFIG_HW_RANDOM_VIRTIO");
+ return 0;
+cleanup:
+ close(rdev->fd);
+ free(rdev);
+
+ return r;
+}
+virtio_dev_init(virtio_rng__init);
+
+int virtio_rng__exit(struct kvm *kvm)
+{
+ struct rng_dev *rdev, *tmp;
+
+ list_for_each_entry_safe(rdev, tmp, &rdevs, list) {
+ list_del(&rdev->list);
+ rdev->vdev.ops->exit(kvm, &rdev->vdev);
+ free(rdev);
+ }
+
+ return 0;
+}
+virtio_dev_exit(virtio_rng__exit);
diff --git a/kvmtool/virtio/scsi.c b/kvmtool/virtio/scsi.c
new file mode 100644
index 0000000..16a86cb
--- /dev/null
+++ b/kvmtool/virtio/scsi.c
@@ -0,0 +1,324 @@
+#include "kvm/virtio-scsi.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/disk-image.h"
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/guest_compat.h"
+#include "kvm/virtio-pci.h"
+#include "kvm/virtio.h"
+#include "kvm/strbuf.h"
+
+#include <linux/kernel.h>
+#include <linux/virtio_scsi.h>
+#include <linux/vhost.h>
+
+#define VIRTIO_SCSI_QUEUE_SIZE 128
+#define NUM_VIRT_QUEUES 3
+
+static LIST_HEAD(sdevs);
+static int compat_id = -1;
+
+struct scsi_dev {
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct virtio_scsi_config config;
+ struct vhost_scsi_target target;
+ u32 features;
+ int vhost_fd;
+ struct virtio_device vdev;
+ struct list_head list;
+ struct kvm *kvm;
+};
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct scsi_dev *sdev = dev;
+
+ return ((u8 *)(&sdev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1UL << VIRTIO_RING_F_EVENT_IDX |
+ 1UL << VIRTIO_RING_F_INDIRECT_DESC;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct scsi_dev *sdev = dev;
+
+ sdev->features = features;
+}
+
+static void notify_status(struct kvm *kvm, void *dev, u32 status)
+{
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 page_size, u32 align,
+ u32 pfn)
+{
+ struct vhost_vring_state state = { .index = vq };
+ struct vhost_vring_addr addr;
+ struct scsi_dev *sdev = dev;
+ struct virt_queue *queue;
+ void *p;
+ int r;
+
+ compat__remove_message(compat_id);
+
+ queue = &sdev->vqs[vq];
+ queue->pfn = pfn;
+ p = virtio_get_vq(kvm, queue->pfn, page_size);
+
+ vring_init(&queue->vring, VIRTIO_SCSI_QUEUE_SIZE, p, align);
+ virtio_init_device_vq(&sdev->vdev, queue);
+
+ if (sdev->vhost_fd == 0)
+ return 0;
+
+ state.num = queue->vring.num;
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_NUM, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_NUM failed");
+ state.num = 0;
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_BASE, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_BASE failed");
+
+ addr = (struct vhost_vring_addr) {
+ .index = vq,
+ .desc_user_addr = (u64)(unsigned long)queue->vring.desc,
+ .avail_user_addr = (u64)(unsigned long)queue->vring.avail,
+ .used_user_addr = (u64)(unsigned long)queue->vring.used,
+ };
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_ADDR, &addr);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_ADDR failed");
+
+ return 0;
+}
+
+static void notify_vq_gsi(struct kvm *kvm, void *dev, u32 vq, u32 gsi)
+{
+ struct vhost_vring_file file;
+ struct scsi_dev *sdev = dev;
+ int r;
+
+ if (sdev->vhost_fd == 0)
+ return;
+
+ file = (struct vhost_vring_file) {
+ .index = vq,
+ .fd = eventfd(0, 0),
+ };
+
+ r = irq__add_irqfd(kvm, gsi, file.fd, -1);
+ if (r < 0)
+ die_perror("KVM_IRQFD failed");
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_CALL, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_CALL failed");
+
+ if (vq > 0)
+ return;
+
+ r = ioctl(sdev->vhost_fd, VHOST_SCSI_SET_ENDPOINT, &sdev->target);
+ if (r != 0)
+ die("VHOST_SCSI_SET_ENDPOINT failed %d", errno);
+}
+
+static void notify_vq_eventfd(struct kvm *kvm, void *dev, u32 vq, u32 efd)
+{
+ struct scsi_dev *sdev = dev;
+ struct vhost_vring_file file = {
+ .index = vq,
+ .fd = efd,
+ };
+ int r;
+
+ if (sdev->vhost_fd == 0)
+ return;
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_KICK, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_KICK failed");
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return 0;
+}
+
+static struct virt_queue *get_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct scsi_dev *sdev = dev;
+
+ return &sdev->vqs[vq];
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_SCSI_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ return size;
+}
+
+static int get_vq_count(struct kvm *kvm, void *dev)
+{
+ return NUM_VIRT_QUEUES;
+}
+
+static struct virtio_ops scsi_dev_virtio_ops = {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .get_vq = get_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+ .notify_status = notify_status,
+ .notify_vq = notify_vq,
+ .notify_vq_gsi = notify_vq_gsi,
+ .notify_vq_eventfd = notify_vq_eventfd,
+ .get_vq_count = get_vq_count,
+};
+
+static void virtio_scsi_vhost_init(struct kvm *kvm, struct scsi_dev *sdev)
+{
+ struct vhost_memory *mem;
+ u64 features;
+ int r;
+
+ sdev->vhost_fd = open("/dev/vhost-scsi", O_RDWR);
+ if (sdev->vhost_fd < 0)
+ die_perror("Failed openning vhost-scsi device");
+
+ mem = calloc(1, sizeof(*mem) + sizeof(struct vhost_memory_region));
+ if (mem == NULL)
+ die("Failed allocating memory for vhost memory map");
+
+ mem->nregions = 1;
+ mem->regions[0] = (struct vhost_memory_region) {
+ .guest_phys_addr = 0,
+ .memory_size = kvm->ram_size,
+ .userspace_addr = (unsigned long)kvm->ram_start,
+ };
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_OWNER);
+ if (r != 0)
+ die_perror("VHOST_SET_OWNER failed");
+
+ r = ioctl(sdev->vhost_fd, VHOST_GET_FEATURES, &features);
+ if (r != 0)
+ die_perror("VHOST_GET_FEATURES failed");
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_FEATURES, &features);
+ if (r != 0)
+ die_perror("VHOST_SET_FEATURES failed");
+ r = ioctl(sdev->vhost_fd, VHOST_SET_MEM_TABLE, mem);
+ if (r != 0)
+ die_perror("VHOST_SET_MEM_TABLE failed");
+
+ sdev->vdev.use_vhost = true;
+
+ free(mem);
+}
+
+
+static int virtio_scsi_init_one(struct kvm *kvm, struct disk_image *disk)
+{
+ struct scsi_dev *sdev;
+ int r;
+
+ if (!disk)
+ return -EINVAL;
+
+ sdev = calloc(1, sizeof(struct scsi_dev));
+ if (sdev == NULL)
+ return -ENOMEM;
+
+ *sdev = (struct scsi_dev) {
+ .config = (struct virtio_scsi_config) {
+ .num_queues = NUM_VIRT_QUEUES - 2,
+ .seg_max = VIRTIO_SCSI_CDB_SIZE - 2,
+ .max_sectors = 65535,
+ .cmd_per_lun = 128,
+ .sense_size = VIRTIO_SCSI_SENSE_SIZE,
+ .cdb_size = VIRTIO_SCSI_CDB_SIZE,
+ .max_channel = 0,
+ .max_target = 0,
+ .max_lun = 16383,
+ .event_info_size = sizeof(struct virtio_scsi_event),
+ },
+ .kvm = kvm,
+ };
+ strlcpy((char *)&sdev->target.vhost_wwpn, disk->wwpn, sizeof(sdev->target.vhost_wwpn));
+ sdev->target.vhost_tpgt = strtol(disk->tpgt, NULL, 0);
+
+ list_add_tail(&sdev->list, &sdevs);
+
+ r = virtio_init(kvm, sdev, &sdev->vdev, &scsi_dev_virtio_ops,
+ VIRTIO_DEFAULT_TRANS(kvm), PCI_DEVICE_ID_VIRTIO_SCSI,
+ VIRTIO_ID_SCSI, PCI_CLASS_BLK);
+ if (r < 0)
+ return r;
+
+ virtio_scsi_vhost_init(kvm, sdev);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-scsi", "CONFIG_VIRTIO_SCSI");
+
+ return 0;
+}
+
+static int virtio_scsi_exit_one(struct kvm *kvm, struct scsi_dev *sdev)
+{
+ int r;
+
+ r = ioctl(sdev->vhost_fd, VHOST_SCSI_CLEAR_ENDPOINT, &sdev->target);
+ if (r != 0)
+ die("VHOST_SCSI_CLEAR_ENDPOINT failed %d", errno);
+
+ list_del(&sdev->list);
+ free(sdev);
+
+ return 0;
+}
+
+int virtio_scsi_init(struct kvm *kvm)
+{
+ int i, r = 0;
+
+ for (i = 0; i < kvm->nr_disks; i++) {
+ if (!kvm->disks[i]->wwpn)
+ continue;
+ r = virtio_scsi_init_one(kvm, kvm->disks[i]);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ return 0;
+cleanup:
+ virtio_scsi_exit(kvm);
+ return r;
+}
+virtio_dev_init(virtio_scsi_init);
+
+int virtio_scsi_exit(struct kvm *kvm)
+{
+ while (!list_empty(&sdevs)) {
+ struct scsi_dev *sdev;
+
+ sdev = list_first_entry(&sdevs, struct scsi_dev, list);
+ virtio_scsi_exit_one(kvm, sdev);
+ }
+
+ return 0;
+}
+virtio_dev_exit(virtio_scsi_exit);
diff --git a/kvmtool/x86/bios.c b/kvmtool/x86/bios.c
new file mode 100644
index 0000000..5ac9e24
--- /dev/null
+++ b/kvmtool/x86/bios.c
@@ -0,0 +1,173 @@
+#include "kvm/kvm.h"
+#include "kvm/boot-protocol.h"
+#include "kvm/e820.h"
+#include "kvm/interrupt.h"
+#include "kvm/util.h"
+
+#include <string.h>
+
+#include "bios/bios-rom.h"
+
+struct irq_handler {
+ unsigned long address;
+ unsigned int irq;
+ void *handler;
+ size_t size;
+};
+
+#define BIOS_IRQ_PA_ADDR(name) (MB_BIOS_BEGIN + BIOS_OFFSET__##name)
+#define BIOS_IRQ_FUNC(name) ((char *)&bios_rom[BIOS_OFFSET__##name])
+#define BIOS_IRQ_SIZE(name) (BIOS_ENTRY_SIZE(BIOS_OFFSET__##name))
+
+#define DEFINE_BIOS_IRQ_HANDLER(_irq, _handler) \
+ { \
+ .irq = _irq, \
+ .address = BIOS_IRQ_PA_ADDR(_handler), \
+ .handler = BIOS_IRQ_FUNC(_handler), \
+ .size = BIOS_IRQ_SIZE(_handler), \
+ }
+
+static struct irq_handler bios_irq_handlers[] = {
+ DEFINE_BIOS_IRQ_HANDLER(0x10, bios_int10),
+ DEFINE_BIOS_IRQ_HANDLER(0x15, bios_int15),
+};
+
+static void setup_irq_handler(struct kvm *kvm, struct irq_handler *handler)
+{
+ struct real_intr_desc intr_desc;
+ void *p;
+
+ p = guest_flat_to_host(kvm, handler->address);
+ memcpy(p, handler->handler, handler->size);
+
+ intr_desc = (struct real_intr_desc) {
+ .segment = REAL_SEGMENT(MB_BIOS_BEGIN),
+ .offset = handler->address - MB_BIOS_BEGIN,
+ };
+
+ DIE_IF((handler->address - MB_BIOS_BEGIN) > 0xffffUL);
+
+ interrupt_table__set(&kvm->arch.interrupt_table, &intr_desc, handler->irq);
+}
+
+/**
+ * e820_setup - setup some simple E820 memory map
+ * @kvm - guest system descriptor
+ */
+static void e820_setup(struct kvm *kvm)
+{
+ struct e820map *e820;
+ struct e820entry *mem_map;
+ unsigned int i = 0;
+
+ e820 = guest_flat_to_host(kvm, E820_MAP_START);
+ mem_map = e820->map;
+
+ mem_map[i++] = (struct e820entry) {
+ .addr = REAL_MODE_IVT_BEGIN,
+ .size = EBDA_START - REAL_MODE_IVT_BEGIN,
+ .type = E820_RAM,
+ };
+ mem_map[i++] = (struct e820entry) {
+ .addr = EBDA_START,
+ .size = VGA_RAM_BEGIN - EBDA_START,
+ .type = E820_RESERVED,
+ };
+ mem_map[i++] = (struct e820entry) {
+ .addr = MB_BIOS_BEGIN,
+ .size = MB_BIOS_END - MB_BIOS_BEGIN,
+ .type = E820_RESERVED,
+ };
+ if (kvm->ram_size < KVM_32BIT_GAP_START) {
+ mem_map[i++] = (struct e820entry) {
+ .addr = BZ_KERNEL_START,
+ .size = kvm->ram_size - BZ_KERNEL_START,
+ .type = E820_RAM,
+ };
+ } else {
+ mem_map[i++] = (struct e820entry) {
+ .addr = BZ_KERNEL_START,
+ .size = KVM_32BIT_GAP_START - BZ_KERNEL_START,
+ .type = E820_RAM,
+ };
+ mem_map[i++] = (struct e820entry) {
+ .addr = KVM_32BIT_MAX_MEM_SIZE,
+ .size = kvm->ram_size - KVM_32BIT_MAX_MEM_SIZE,
+ .type = E820_RAM,
+ };
+ }
+
+ BUG_ON(i > E820_X_MAX);
+
+ e820->nr_map = i;
+}
+
+static void setup_vga_rom(struct kvm *kvm)
+{
+ u16 *mode;
+ void *p;
+
+ p = guest_flat_to_host(kvm, VGA_ROM_OEM_STRING);
+ memset(p, 0, VGA_ROM_OEM_STRING_SIZE);
+ strncpy(p, "KVM VESA", VGA_ROM_OEM_STRING_SIZE);
+
+ mode = guest_flat_to_host(kvm, VGA_ROM_MODES);
+ mode[0] = 0x0112;
+ mode[1] = 0xffff;
+}
+
+/**
+ * setup_bios - inject BIOS into guest memory
+ * @kvm - guest system descriptor
+ */
+void setup_bios(struct kvm *kvm)
+{
+ unsigned long address = MB_BIOS_BEGIN;
+ struct real_intr_desc intr_desc;
+ unsigned int i;
+ void *p;
+
+ /*
+ * before anything else -- clean some known areas
+ * we definitely don't want any trash here
+ */
+ p = guest_flat_to_host(kvm, BDA_START);
+ memset(p, 0, BDA_END - BDA_START);
+
+ p = guest_flat_to_host(kvm, EBDA_START);
+ memset(p, 0, EBDA_END - EBDA_START);
+
+ p = guest_flat_to_host(kvm, MB_BIOS_BEGIN);
+ memset(p, 0, MB_BIOS_END - MB_BIOS_BEGIN);
+
+ p = guest_flat_to_host(kvm, VGA_ROM_BEGIN);
+ memset(p, 0, VGA_ROM_END - VGA_ROM_BEGIN);
+
+ /* just copy the bios rom into the place */
+ p = guest_flat_to_host(kvm, MB_BIOS_BEGIN);
+ memcpy(p, bios_rom, bios_rom_size);
+
+ /* E820 memory map must be present */
+ e820_setup(kvm);
+
+ /* VESA needs own tricks */
+ setup_vga_rom(kvm);
+
+ /*
+ * Setup a *fake* real mode vector table, it has only
+ * one real handler which does just iret
+ */
+ address = BIOS_IRQ_PA_ADDR(bios_intfake);
+ intr_desc = (struct real_intr_desc) {
+ .segment = REAL_SEGMENT(MB_BIOS_BEGIN),
+ .offset = address - MB_BIOS_BEGIN,
+ };
+ interrupt_table__setup(&kvm->arch.interrupt_table, &intr_desc);
+
+ for (i = 0; i < ARRAY_SIZE(bios_irq_handlers); i++)
+ setup_irq_handler(kvm, &bios_irq_handlers[i]);
+
+ /* we almost done */
+ p = guest_flat_to_host(kvm, 0);
+ interrupt_table__copy(&kvm->arch.interrupt_table, p, REAL_INTR_SIZE);
+}
diff --git a/kvmtool/x86/bios/.gitignore b/kvmtool/x86/bios/.gitignore
new file mode 100644
index 0000000..1f0080b
--- /dev/null
+++ b/kvmtool/x86/bios/.gitignore
@@ -0,0 +1,3 @@
+bios-rom.bin
+bios-rom.bin.elf
+bios-rom.h
diff --git a/kvmtool/x86/bios/bios-rom.S b/kvmtool/x86/bios/bios-rom.S
new file mode 100644
index 0000000..3269ce9
--- /dev/null
+++ b/kvmtool/x86/bios/bios-rom.S
@@ -0,0 +1,12 @@
+#include <kvm/assembly.h>
+
+ .org 0
+#ifdef CONFIG_X86_64
+ .code64
+#else
+ .code32
+#endif
+
+GLOBAL(bios_rom)
+ .incbin "x86/bios/bios.bin"
+END(bios_rom)
diff --git a/kvmtool/x86/bios/e820.c b/kvmtool/x86/bios/e820.c
new file mode 100644
index 0000000..51576b4
--- /dev/null
+++ b/kvmtool/x86/bios/e820.c
@@ -0,0 +1,81 @@
+#include "asm/bios/types.h"
+#include "kvm/e820.h"
+
+#include "kvm/bios.h"
+
+#include <asm/processor-flags.h>
+
+static inline u16 flat_to_seg16(u32 address)
+{
+ return address >> 4;
+}
+
+static inline u16 flat_to_off16(u32 address, u32 segment)
+{
+ return address - (segment << 4);
+}
+
+static inline void set_fs(u16 seg)
+{
+ asm volatile("movw %0,%%fs" : : "rm" (seg));
+}
+
+static inline u8 rdfs8(unsigned long addr)
+{
+ u8 v;
+
+ asm volatile("addr32 movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+
+ return v;
+}
+
+static inline u32 rdfs32(unsigned long addr)
+{
+ u32 v;
+
+ asm volatile("addr32 movl %%fs:%1,%0" : "=q" (v) : "m" (*(u32 *)addr));
+
+ return v;
+}
+
+bioscall void e820_query_map(struct biosregs *regs)
+{
+ struct e820map *e820;
+ u32 map_size;
+ u16 fs_seg;
+ u32 ndx;
+
+ e820 = (struct e820map *)E820_MAP_START;
+ fs_seg = flat_to_seg16(E820_MAP_START);
+ set_fs(fs_seg);
+
+ ndx = regs->ebx;
+
+ map_size = rdfs32(flat_to_off16((u32)&e820->nr_map, fs_seg));
+
+ if (ndx < map_size) {
+ u32 start;
+ unsigned int i;
+ u8 *p;
+
+ fs_seg = flat_to_seg16(E820_MAP_START);
+ set_fs(fs_seg);
+
+ start = (u32)&e820->map[ndx];
+
+ p = (void *) regs->edi;
+
+ for (i = 0; i < sizeof(struct e820entry); i++)
+ *p++ = rdfs8(flat_to_off16(start + i, fs_seg));
+ }
+
+ regs->eax = SMAP;
+ regs->ecx = sizeof(struct e820entry);
+ regs->ebx = ++ndx;
+
+ /* Clear CF to indicate success. */
+ regs->eflags &= ~X86_EFLAGS_CF;
+
+ if (ndx >= map_size)
+ regs->ebx = 0; /* end of map */
+}
diff --git a/kvmtool/x86/bios/entry.S b/kvmtool/x86/bios/entry.S
new file mode 100644
index 0000000..85056e9
--- /dev/null
+++ b/kvmtool/x86/bios/entry.S
@@ -0,0 +1,92 @@
+/*
+ * Our pretty trivial BIOS emulation
+ */
+
+#include <kvm/bios.h>
+#include <kvm/assembly.h>
+
+ .org 0
+ .code16gcc
+
+#define EFLAGS_CF (1 << 0)
+
+#include "macro.S"
+
+/* If you change these macros, remember to update 'struct biosregs' */
+.macro SAVE_BIOSREGS
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %edi
+ pushl %esi
+ pushl %ebp
+ pushl %esp
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ pushl %eax
+.endm
+
+.macro RESTORE_BIOSREGS
+ popl %eax
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esp
+ popl %ebp
+ popl %esi
+ popl %edi
+ popl %ds
+ popl %es
+ popl %fs
+.endm
+
+/*
+ * fake interrupt handler, nothing can be faster ever
+ */
+ENTRY(bios_intfake)
+ /*
+ * Set CF to indicate failure. We don't want callers to think that the
+ * interrupt handler succeeded and then treat the return values in
+ * registers as valid data.
+ */
+ orl $EFLAGS_CF, 0x4(%esp)
+
+ IRET
+ENTRY_END(bios_intfake)
+
+/*
+ * int 10 - video - service
+ */
+ENTRY(bios_int10)
+ SAVE_BIOSREGS
+
+ movl %esp, %eax
+ /* this is way easier than doing it in assembly */
+ /* just push all the regs and jump to a C handler */
+ call int10_handler
+
+ RESTORE_BIOSREGS
+
+ /* Clear CF to indicate success. */
+ andl $~EFLAGS_CF, 0x4(%esp)
+
+ IRET
+ENTRY_END(bios_int10)
+
+ENTRY(bios_int15)
+ SAVE_BIOSREGS
+
+ movl %esp, %eax
+ call int15_handler
+
+ RESTORE_BIOSREGS
+
+ IRET
+ENTRY_END(bios_int15)
+
+GLOBAL(__locals)
+
+#include "local.S"
+
+END(__locals)
diff --git a/kvmtool/x86/bios/gen-offsets.sh b/kvmtool/x86/bios/gen-offsets.sh
new file mode 100644
index 0000000..8771bbe
--- /dev/null
+++ b/kvmtool/x86/bios/gen-offsets.sh
@@ -0,0 +1,14 @@
+#!/bin/sh
+
+echo "/* Autogenerated file, don't edit */"
+echo "#ifndef BIOS_OFFSETS_H"
+echo "#define BIOS_OFFSETS_H"
+
+echo ""
+echo "#define BIOS_ENTRY_SIZE(name) (name##_end - name)"
+echo ""
+
+nm bios.bin.elf | grep ' [Tt] ' | awk '{ print "#define BIOS_OFFSET__" $3 " 0x" $1; }'
+
+echo ""
+echo "#endif"
diff --git a/kvmtool/x86/bios/int10.c b/kvmtool/x86/bios/int10.c
new file mode 100644
index 0000000..d164cf5
--- /dev/null
+++ b/kvmtool/x86/bios/int10.c
@@ -0,0 +1,109 @@
+#include "kvm/bios.h"
+#include "kvm/vesa.h"
+
+#include "asm/bios/memcpy.h"
+
+#include "asm/bios/vesa.h"
+
+static far_ptr gen_far_ptr(unsigned int pa)
+{
+ far_ptr ptr;
+
+ ptr.seg = (pa >> 4);
+ ptr.off = pa - (ptr.seg << 4);
+
+ return ptr;
+}
+
+static inline void outb(unsigned short port, unsigned char val)
+{
+ asm volatile("outb %0, %1" : : "a"(val), "Nd"(port));
+}
+
+/*
+ * It's probably much more useful to make this print to the serial
+ * line rather than print to a non-displayed VGA memory
+ */
+static inline void int10_putchar(struct biosregs *args)
+{
+ u8 al = args->eax & 0xFF;
+
+ outb(0x3f8, al);
+}
+
+static void vbe_get_mode(struct biosregs *args)
+{
+ struct vesa_mode_info *info = (struct vesa_mode_info *) args->edi;
+
+ *info = (struct vesa_mode_info) {
+ .mode_attr = 0xd9, /* 11011011 */
+ .logical_scan = VESA_WIDTH*4,
+ .h_res = VESA_WIDTH,
+ .v_res = VESA_HEIGHT,
+ .bpp = VESA_BPP,
+ .memory_layout = 6,
+ .memory_planes = 1,
+ .lfb_ptr = VESA_MEM_ADDR,
+ .rmask = 8,
+ .gmask = 8,
+ .bmask = 8,
+ .resv_mask = 8,
+ .resv_pos = 24,
+ .bpos = 16,
+ .gpos = 8,
+ };
+}
+
+static void vbe_get_info(struct biosregs *args)
+{
+ struct vesa_general_info *infop = (struct vesa_general_info *) args->edi;
+ struct vesa_general_info info;
+
+ info = (struct vesa_general_info) {
+ .signature = VESA_MAGIC,
+ .version = 0x102,
+ .vendor_string = gen_far_ptr(VGA_ROM_BEGIN),
+ .capabilities = 0x10,
+ .video_mode_ptr = gen_far_ptr(VGA_ROM_MODES),
+ .total_memory = (4 * VESA_WIDTH * VESA_HEIGHT) / 0x10000,
+ };
+
+ memcpy16(args->es, infop, args->ds, &info, sizeof(info));
+}
+
+#define VBE_STATUS_OK 0x004F
+
+static void int10_vesa(struct biosregs *args)
+{
+ u8 al;
+
+ al = args->eax & 0xff;
+
+ switch (al) {
+ case 0x00:
+ vbe_get_info(args);
+ break;
+ case 0x01:
+ vbe_get_mode(args);
+ break;
+ }
+
+ args->eax = VBE_STATUS_OK;
+}
+
+bioscall void int10_handler(struct biosregs *args)
+{
+ u8 ah;
+
+ ah = (args->eax & 0xff00) >> 8;
+
+ switch (ah) {
+ case 0x0e:
+ int10_putchar(args);
+ break;
+ case 0x4f:
+ int10_vesa(args);
+ break;
+ }
+
+}
diff --git a/kvmtool/x86/bios/int15.c b/kvmtool/x86/bios/int15.c
new file mode 100644
index 0000000..faf5343
--- /dev/null
+++ b/kvmtool/x86/bios/int15.c
@@ -0,0 +1,18 @@
+#include "kvm/bios.h"
+
+#include "kvm/e820.h"
+
+#include <asm/processor-flags.h>
+
+bioscall void int15_handler(struct biosregs *regs)
+{
+ switch (regs->eax) {
+ case 0xe820:
+ e820_query_map(regs);
+ break;
+ default:
+ /* Set CF to indicate failure. */
+ regs->eflags |= X86_EFLAGS_CF;
+ break;
+ }
+}
diff --git a/kvmtool/x86/bios/local.S b/kvmtool/x86/bios/local.S
new file mode 100644
index 0000000..f2cdbf4
--- /dev/null
+++ b/kvmtool/x86/bios/local.S
@@ -0,0 +1,7 @@
+/*
+ * Local variables for almost every BIOS irq handler
+ * Must be put somewhere inside irq handler body
+ */
+__CALLER_SS: .int 0
+__CALLER_SP: .long 0
+__CALLER_CLOBBER: .long 0
diff --git a/kvmtool/x86/bios/macro.S b/kvmtool/x86/bios/macro.S
new file mode 100644
index 0000000..0d5e567
--- /dev/null
+++ b/kvmtool/x86/bios/macro.S
@@ -0,0 +1,25 @@
+/*
+ * handy BIOS macros
+ */
+
+/*
+ * switch to BIOS stack
+ */
+.macro stack_swap
+ movw %ss, %cs:(__CALLER_SS)
+ movl %esp, %cs:(__CALLER_SP)
+ movl %edx, %cs:(__CALLER_CLOBBER)
+ movw $MB_BIOS_SS, %dx
+ movw %dx, %ss
+ movw $MB_BIOS_SP, %sp
+ movl %cs:(__CALLER_CLOBBER), %edx
+.endm
+
+/*
+ * restore the original stack
+ */
+.macro stack_restore
+ movl %cs:(__CALLER_SP), %esp
+ movw %cs:(__CALLER_SS), %ss
+.endm
+
diff --git a/kvmtool/x86/bios/memcpy.c b/kvmtool/x86/bios/memcpy.c
new file mode 100644
index 0000000..2be3a27
--- /dev/null
+++ b/kvmtool/x86/bios/memcpy.c
@@ -0,0 +1,23 @@
+#include "asm/bios/memcpy.h"
+
+/*
+ * Copy memory area in 16-bit real mode.
+ */
+void memcpy16(u16 dst_seg, void *dst, u16 src_seg, const void *src, size_t len)
+{
+ __asm__ __volatile__ (
+ "pushw %%ds \n"
+ "pushw %%es \n"
+ "movw %[src_seg], %%ds \n"
+ "movw %[dst_seg], %%es \n"
+ "rep movsb %%ds:(%%si), %%es:(%%di) \n"
+ "popw %%es \n"
+ "popw %%ds \n"
+ :
+ : "S"(src),
+ "D"(dst),
+ "c"(len),
+ [src_seg] "r"(src_seg),
+ [dst_seg] "r"(dst_seg)
+ : "cc", "memory");
+}
diff --git a/kvmtool/x86/bios/rom.ld.S b/kvmtool/x86/bios/rom.ld.S
new file mode 100644
index 0000000..f4f1835
--- /dev/null
+++ b/kvmtool/x86/bios/rom.ld.S
@@ -0,0 +1,16 @@
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+
+SECTIONS {
+ .text 0 : {
+ *(.text)
+ }
+
+ /DISCARD/ : {
+ *(.debug*)
+ *(.data)
+ *(.bss)
+ *(.eh_frame*)
+ }
+}
+
diff --git a/kvmtool/x86/boot.c b/kvmtool/x86/boot.c
new file mode 100644
index 0000000..61535eb
--- /dev/null
+++ b/kvmtool/x86/boot.c
@@ -0,0 +1,41 @@
+#include "kvm/kvm.h"
+
+#include "kvm/util.h"
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <fcntl.h>
+
+#define BIOS_SELECTOR 0xf000
+#define BIOS_IP 0xfff0
+#define BIOS_SP 0x8000
+
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename)
+{
+ struct stat st;
+ void *p;
+ int fd;
+ int nr;
+
+ fd = open(firmware_filename, O_RDONLY);
+ if (fd < 0)
+ return false;
+
+ if (fstat(fd, &st))
+ return false;
+
+ if (st.st_size > MB_FIRMWARE_BIOS_SIZE)
+ die("firmware image %s is too big to fit in memory (%Lu KB).\n", firmware_filename, (u64)(st.st_size / 1024));
+
+ p = guest_flat_to_host(kvm, MB_FIRMWARE_BIOS_BEGIN);
+
+ while ((nr = read(fd, p, st.st_size)) > 0)
+ p += nr;
+
+ kvm->arch.boot_selector = BIOS_SELECTOR;
+ kvm->arch.boot_ip = BIOS_IP;
+ kvm->arch.boot_sp = BIOS_SP;
+
+ return true;
+}
diff --git a/kvmtool/x86/cpuid.c b/kvmtool/x86/cpuid.c
new file mode 100644
index 0000000..c3b67d9
--- /dev/null
+++ b/kvmtool/x86/cpuid.c
@@ -0,0 +1,89 @@
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#include <sys/ioctl.h>
+#include <stdlib.h>
+
+#define MAX_KVM_CPUID_ENTRIES 100
+
+static void filter_cpuid(struct kvm_cpuid2 *kvm_cpuid)
+{
+ unsigned int signature[3];
+ unsigned int i;
+
+ /*
+ * Filter CPUID functions that are not supported by the hypervisor.
+ */
+ for (i = 0; i < kvm_cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *entry = &kvm_cpuid->entries[i];
+
+ switch (entry->function) {
+ case 0:
+ /* Vendor name */
+ memcpy(signature, "LKVMLKVMLKVM", 12);
+ entry->ebx = signature[0];
+ entry->ecx = signature[1];
+ entry->edx = signature[2];
+ break;
+ case 1:
+ /* Set X86_FEATURE_HYPERVISOR */
+ if (entry->index == 0)
+ entry->ecx |= (1 << 31);
+ break;
+ case 6:
+ /* Clear X86_FEATURE_EPB */
+ entry->ecx = entry->ecx & ~(1 << 3);
+ break;
+ case 10: { /* Architectural Performance Monitoring */
+ union cpuid10_eax {
+ struct {
+ unsigned int version_id :8;
+ unsigned int num_counters :8;
+ unsigned int bit_width :8;
+ unsigned int mask_length :8;
+ } split;
+ unsigned int full;
+ } eax;
+
+ /*
+ * If the host has perf system running,
+ * but no architectural events available
+ * through kvm pmu -- disable perf support,
+ * thus guest won't even try to access msr
+ * registers.
+ */
+ if (entry->eax) {
+ eax.full = entry->eax;
+ if (eax.split.version_id != 2 ||
+ !eax.split.num_counters)
+ entry->eax = 0;
+ }
+ break;
+ }
+ default:
+ /* Keep the CPUID function as -is */
+ break;
+ };
+ }
+}
+
+void kvm_cpu__setup_cpuid(struct kvm_cpu *vcpu)
+{
+ struct kvm_cpuid2 *kvm_cpuid;
+
+ kvm_cpuid = calloc(1, sizeof(*kvm_cpuid) +
+ MAX_KVM_CPUID_ENTRIES * sizeof(*kvm_cpuid->entries));
+
+ kvm_cpuid->nent = MAX_KVM_CPUID_ENTRIES;
+ if (ioctl(vcpu->kvm->sys_fd, KVM_GET_SUPPORTED_CPUID, kvm_cpuid) < 0)
+ die_perror("KVM_GET_SUPPORTED_CPUID failed");
+
+ filter_cpuid(kvm_cpuid);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_CPUID2, kvm_cpuid) < 0)
+ die_perror("KVM_SET_CPUID2 failed");
+
+ free(kvm_cpuid);
+}
diff --git a/kvmtool/x86/include/asm/apicdef.h b/kvmtool/x86/include/asm/apicdef.h
new file mode 100644
index 0000000..c46bb99
--- /dev/null
+++ b/kvmtool/x86/include/asm/apicdef.h
@@ -0,0 +1,445 @@
+#ifndef _ASM_X86_APICDEF_H
+#define _ASM_X86_APICDEF_H
+
+/*
+ * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
+ *
+ * Alan Cox <Alan.Cox@linux.org>, 1995.
+ * Ingo Molnar <mingo@redhat.com>, 1999, 2000
+ */
+
+#define IO_APIC_DEFAULT_PHYS_BASE 0xfec00000
+#define APIC_DEFAULT_PHYS_BASE 0xfee00000
+
+/*
+ * This is the IO-APIC register space as specified
+ * by Intel docs:
+ */
+#define IO_APIC_SLOT_SIZE 1024
+
+#define APIC_ID 0x20
+
+#define APIC_LVR 0x30
+#define APIC_LVR_MASK 0xFF00FF
+#define APIC_LVR_DIRECTED_EOI (1 << 24)
+#define GET_APIC_VERSION(x) ((x) & 0xFFu)
+#define GET_APIC_MAXLVT(x) (((x) >> 16) & 0xFFu)
+#ifdef CONFIG_X86_32
+# define APIC_INTEGRATED(x) ((x) & 0xF0u)
+#else
+# define APIC_INTEGRATED(x) (1)
+#endif
+#define APIC_XAPIC(x) ((x) >= 0x14)
+#define APIC_EXT_SPACE(x) ((x) & 0x80000000)
+#define APIC_TASKPRI 0x80
+#define APIC_TPRI_MASK 0xFFu
+#define APIC_ARBPRI 0x90
+#define APIC_ARBPRI_MASK 0xFFu
+#define APIC_PROCPRI 0xA0
+#define APIC_EOI 0xB0
+#define APIC_EOI_ACK 0x0 /* Docs say 0 for future compat. */
+#define APIC_RRR 0xC0
+#define APIC_LDR 0xD0
+#define APIC_LDR_MASK (0xFFu << 24)
+#define GET_APIC_LOGICAL_ID(x) (((x) >> 24) & 0xFFu)
+#define SET_APIC_LOGICAL_ID(x) (((x) << 24))
+#define APIC_ALL_CPUS 0xFFu
+#define APIC_DFR 0xE0
+#define APIC_DFR_CLUSTER 0x0FFFFFFFul
+#define APIC_DFR_FLAT 0xFFFFFFFFul
+#define APIC_SPIV 0xF0
+#define APIC_SPIV_DIRECTED_EOI (1 << 12)
+#define APIC_SPIV_FOCUS_DISABLED (1 << 9)
+#define APIC_SPIV_APIC_ENABLED (1 << 8)
+#define APIC_ISR 0x100
+#define APIC_ISR_NR 0x8 /* Number of 32 bit ISR registers. */
+#define APIC_TMR 0x180
+#define APIC_IRR 0x200
+#define APIC_ESR 0x280
+#define APIC_ESR_SEND_CS 0x00001
+#define APIC_ESR_RECV_CS 0x00002
+#define APIC_ESR_SEND_ACC 0x00004
+#define APIC_ESR_RECV_ACC 0x00008
+#define APIC_ESR_SENDILL 0x00020
+#define APIC_ESR_RECVILL 0x00040
+#define APIC_ESR_ILLREGA 0x00080
+#define APIC_LVTCMCI 0x2f0
+#define APIC_ICR 0x300
+#define APIC_DEST_SELF 0x40000
+#define APIC_DEST_ALLINC 0x80000
+#define APIC_DEST_ALLBUT 0xC0000
+#define APIC_ICR_RR_MASK 0x30000
+#define APIC_ICR_RR_INVALID 0x00000
+#define APIC_ICR_RR_INPROG 0x10000
+#define APIC_ICR_RR_VALID 0x20000
+#define APIC_INT_LEVELTRIG 0x08000
+#define APIC_INT_ASSERT 0x04000
+#define APIC_ICR_BUSY 0x01000
+#define APIC_DEST_LOGICAL 0x00800
+#define APIC_DEST_PHYSICAL 0x00000
+#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
+#define APIC_DM_LOWEST 0x00100
+#define APIC_DM_SMI 0x00200
+#define APIC_DM_REMRD 0x00300
+#define APIC_DM_NMI 0x00400
+#define APIC_DM_INIT 0x00500
+#define APIC_DM_STARTUP 0x00600
+#define APIC_DM_EXTINT 0x00700
+#define APIC_VECTOR_MASK 0x000FF
+#define APIC_ICR2 0x310
+#define GET_APIC_DEST_FIELD(x) (((x) >> 24) & 0xFF)
+#define SET_APIC_DEST_FIELD(x) ((x) << 24)
+#define APIC_LVTT 0x320
+#define APIC_LVTTHMR 0x330
+#define APIC_LVTPC 0x340
+#define APIC_LVT0 0x350
+#define APIC_LVT_TIMER_BASE_MASK (0x3 << 18)
+#define GET_APIC_TIMER_BASE(x) (((x) >> 18) & 0x3)
+#define SET_APIC_TIMER_BASE(x) (((x) << 18))
+#define APIC_TIMER_BASE_CLKIN 0x0
+#define APIC_TIMER_BASE_TMBASE 0x1
+#define APIC_TIMER_BASE_DIV 0x2
+#define APIC_LVT_TIMER_ONESHOT (0 << 17)
+#define APIC_LVT_TIMER_PERIODIC (1 << 17)
+#define APIC_LVT_TIMER_TSCDEADLINE (2 << 17)
+#define APIC_LVT_MASKED (1 << 16)
+#define APIC_LVT_LEVEL_TRIGGER (1 << 15)
+#define APIC_LVT_REMOTE_IRR (1 << 14)
+#define APIC_INPUT_POLARITY (1 << 13)
+#define APIC_SEND_PENDING (1 << 12)
+#define APIC_MODE_MASK 0x700
+#define GET_APIC_DELIVERY_MODE(x) (((x) >> 8) & 0x7)
+#define SET_APIC_DELIVERY_MODE(x, y) (((x) & ~0x700) | ((y) << 8))
+#define APIC_MODE_FIXED 0x0
+#define APIC_MODE_NMI 0x4
+#define APIC_MODE_EXTINT 0x7
+#define APIC_LVT1 0x360
+#define APIC_LVTERR 0x370
+#define APIC_TMICT 0x380
+#define APIC_TMCCT 0x390
+#define APIC_TDCR 0x3E0
+#define APIC_SELF_IPI 0x3F0
+#define APIC_TDR_DIV_TMBASE (1 << 2)
+#define APIC_TDR_DIV_1 0xB
+#define APIC_TDR_DIV_2 0x0
+#define APIC_TDR_DIV_4 0x1
+#define APIC_TDR_DIV_8 0x2
+#define APIC_TDR_DIV_16 0x3
+#define APIC_TDR_DIV_32 0x8
+#define APIC_TDR_DIV_64 0x9
+#define APIC_TDR_DIV_128 0xA
+#define APIC_EFEAT 0x400
+#define APIC_ECTRL 0x410
+#define APIC_EILVTn(n) (0x500 + 0x10 * n)
+#define APIC_EILVT_NR_AMD_K8 1 /* # of extended interrupts */
+#define APIC_EILVT_NR_AMD_10H 4
+#define APIC_EILVT_NR_MAX APIC_EILVT_NR_AMD_10H
+#define APIC_EILVT_LVTOFF(x) (((x) >> 4) & 0xF)
+#define APIC_EILVT_MSG_FIX 0x0
+#define APIC_EILVT_MSG_SMI 0x2
+#define APIC_EILVT_MSG_NMI 0x4
+#define APIC_EILVT_MSG_EXT 0x7
+#define APIC_EILVT_MASKED (1 << 16)
+
+#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
+#define APIC_BASE_MSR 0x800
+#define XAPIC_ENABLE (1UL << 11)
+#define X2APIC_ENABLE (1UL << 10)
+
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+# define MAX_LOCAL_APIC 256
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+/*
+ * All x86-64 systems are xAPIC compatible.
+ * In the following, "apicid" is a physical APIC ID.
+ */
+#define XAPIC_DEST_CPUS_SHIFT 4
+#define XAPIC_DEST_CPUS_MASK ((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
+#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
+#define APIC_CLUSTER(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK)
+#define APIC_CLUSTERID(apicid) (APIC_CLUSTER(apicid) >> XAPIC_DEST_CPUS_SHIFT)
+#define APIC_CPUID(apicid) ((apicid) & XAPIC_DEST_CPUS_MASK)
+#define NUM_APIC_CLUSTERS ((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT)
+
+/*
+ * the local APIC register structure, memory mapped. Not terribly well
+ * tested, but we might eventually use this one in the future - the
+ * problem why we cannot use it right now is the P5 APIC, it has an
+ * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
+ */
+#define u32 unsigned int
+
+struct local_apic {
+
+/*000*/ struct { u32 __reserved[4]; } __reserved_01;
+
+/*010*/ struct { u32 __reserved[4]; } __reserved_02;
+
+/*020*/ struct { /* APIC ID Register */
+ u32 __reserved_1 : 24,
+ phys_apic_id : 4,
+ __reserved_2 : 4;
+ u32 __reserved[3];
+ } id;
+
+/*030*/ const
+ struct { /* APIC Version Register */
+ u32 version : 8,
+ __reserved_1 : 8,
+ max_lvt : 8,
+ __reserved_2 : 8;
+ u32 __reserved[3];
+ } version;
+
+/*040*/ struct { u32 __reserved[4]; } __reserved_03;
+
+/*050*/ struct { u32 __reserved[4]; } __reserved_04;
+
+/*060*/ struct { u32 __reserved[4]; } __reserved_05;
+
+/*070*/ struct { u32 __reserved[4]; } __reserved_06;
+
+/*080*/ struct { /* Task Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } tpr;
+
+/*090*/ const
+ struct { /* Arbitration Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } apr;
+
+/*0A0*/ const
+ struct { /* Processor Priority Register */
+ u32 priority : 8,
+ __reserved_1 : 24;
+ u32 __reserved_2[3];
+ } ppr;
+
+/*0B0*/ struct { /* End Of Interrupt Register */
+ u32 eoi;
+ u32 __reserved[3];
+ } eoi;
+
+/*0C0*/ struct { u32 __reserved[4]; } __reserved_07;
+
+/*0D0*/ struct { /* Logical Destination Register */
+ u32 __reserved_1 : 24,
+ logical_dest : 8;
+ u32 __reserved_2[3];
+ } ldr;
+
+/*0E0*/ struct { /* Destination Format Register */
+ u32 __reserved_1 : 28,
+ model : 4;
+ u32 __reserved_2[3];
+ } dfr;
+
+/*0F0*/ struct { /* Spurious Interrupt Vector Register */
+ u32 spurious_vector : 8,
+ apic_enabled : 1,
+ focus_cpu : 1,
+ __reserved_2 : 22;
+ u32 __reserved_3[3];
+ } svr;
+
+/*100*/ struct { /* In Service Register */
+/*170*/ u32 bitfield;
+ u32 __reserved[3];
+ } isr [8];
+
+/*180*/ struct { /* Trigger Mode Register */
+/*1F0*/ u32 bitfield;
+ u32 __reserved[3];
+ } tmr [8];
+
+/*200*/ struct { /* Interrupt Request Register */
+/*270*/ u32 bitfield;
+ u32 __reserved[3];
+ } irr [8];
+
+/*280*/ union { /* Error Status Register */
+ struct {
+ u32 send_cs_error : 1,
+ receive_cs_error : 1,
+ send_accept_error : 1,
+ receive_accept_error : 1,
+ __reserved_1 : 1,
+ send_illegal_vector : 1,
+ receive_illegal_vector : 1,
+ illegal_register_address : 1,
+ __reserved_2 : 24;
+ u32 __reserved_3[3];
+ } error_bits;
+ struct {
+ u32 errors;
+ u32 __reserved_3[3];
+ } all_errors;
+ } esr;
+
+/*290*/ struct { u32 __reserved[4]; } __reserved_08;
+
+/*2A0*/ struct { u32 __reserved[4]; } __reserved_09;
+
+/*2B0*/ struct { u32 __reserved[4]; } __reserved_10;
+
+/*2C0*/ struct { u32 __reserved[4]; } __reserved_11;
+
+/*2D0*/ struct { u32 __reserved[4]; } __reserved_12;
+
+/*2E0*/ struct { u32 __reserved[4]; } __reserved_13;
+
+/*2F0*/ struct { u32 __reserved[4]; } __reserved_14;
+
+/*300*/ struct { /* Interrupt Command Register 1 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ destination_mode : 1,
+ delivery_status : 1,
+ __reserved_1 : 1,
+ level : 1,
+ trigger : 1,
+ __reserved_2 : 2,
+ shorthand : 2,
+ __reserved_3 : 12;
+ u32 __reserved_4[3];
+ } icr1;
+
+/*310*/ struct { /* Interrupt Command Register 2 */
+ union {
+ u32 __reserved_1 : 24,
+ phys_dest : 4,
+ __reserved_2 : 4;
+ u32 __reserved_3 : 24,
+ logical_dest : 8;
+ } dest;
+ u32 __reserved_4[3];
+ } icr2;
+
+/*320*/ struct { /* LVT - Timer */
+ u32 vector : 8,
+ __reserved_1 : 4,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ timer_mode : 1,
+ __reserved_3 : 14;
+ u32 __reserved_4[3];
+ } lvt_timer;
+
+/*330*/ struct { /* LVT - Thermal Sensor */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ __reserved_3 : 15;
+ u32 __reserved_4[3];
+ } lvt_thermal;
+
+/*340*/ struct { /* LVT - Performance Counter */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ __reserved_3 : 15;
+ u32 __reserved_4[3];
+ } lvt_pc;
+
+/*350*/ struct { /* LVT - LINT0 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ polarity : 1,
+ remote_irr : 1,
+ trigger : 1,
+ mask : 1,
+ __reserved_2 : 15;
+ u32 __reserved_3[3];
+ } lvt_lint0;
+
+/*360*/ struct { /* LVT - LINT1 */
+ u32 vector : 8,
+ delivery_mode : 3,
+ __reserved_1 : 1,
+ delivery_status : 1,
+ polarity : 1,
+ remote_irr : 1,
+ trigger : 1,
+ mask : 1,
+ __reserved_2 : 15;
+ u32 __reserved_3[3];
+ } lvt_lint1;
+
+/*370*/ struct { /* LVT - Error */
+ u32 vector : 8,
+ __reserved_1 : 4,
+ delivery_status : 1,
+ __reserved_2 : 3,
+ mask : 1,
+ __reserved_3 : 15;
+ u32 __reserved_4[3];
+ } lvt_error;
+
+/*380*/ struct { /* Timer Initial Count Register */
+ u32 initial_count;
+ u32 __reserved_2[3];
+ } timer_icr;
+
+/*390*/ const
+ struct { /* Timer Current Count Register */
+ u32 curr_count;
+ u32 __reserved_2[3];
+ } timer_ccr;
+
+/*3A0*/ struct { u32 __reserved[4]; } __reserved_16;
+
+/*3B0*/ struct { u32 __reserved[4]; } __reserved_17;
+
+/*3C0*/ struct { u32 __reserved[4]; } __reserved_18;
+
+/*3D0*/ struct { u32 __reserved[4]; } __reserved_19;
+
+/*3E0*/ struct { /* Timer Divide Configuration Register */
+ u32 divisor : 4,
+ __reserved_1 : 28;
+ u32 __reserved_2[3];
+ } timer_dcr;
+
+/*3F0*/ struct { u32 __reserved[4]; } __reserved_20;
+
+} __attribute__ ((packed));
+
+#undef u32
+
+#ifdef CONFIG_X86_32
+ #define BAD_APICID 0xFFu
+#else
+ #define BAD_APICID 0xFFFFu
+#endif
+
+enum ioapic_irq_destination_types {
+ dest_Fixed = 0,
+ dest_LowestPrio = 1,
+ dest_SMI = 2,
+ dest__reserved_1 = 3,
+ dest_NMI = 4,
+ dest_INIT = 5,
+ dest__reserved_2 = 6,
+ dest_ExtINT = 7
+};
+
+#endif /* _ASM_X86_APICDEF_H */
diff --git a/kvmtool/x86/include/asm/bios/memcpy.h b/kvmtool/x86/include/asm/bios/memcpy.h
new file mode 100644
index 0000000..eec9d20
--- /dev/null
+++ b/kvmtool/x86/include/asm/bios/memcpy.h
@@ -0,0 +1,9 @@
+#ifndef KVM_BIOS_MEMCPY_H
+#define KVM_BIOS_MEMCPY_H
+
+#include <asm/bios/types.h>
+#include <stddef.h>
+
+void memcpy16(u16 dst_seg, void *dst, u16 src_seg, const void *src, size_t len);
+
+#endif /* KVM_BIOS_MEMCPY_H */
diff --git a/kvmtool/x86/include/asm/bios/types.h b/kvmtool/x86/include/asm/bios/types.h
new file mode 100644
index 0000000..19e55df
--- /dev/null
+++ b/kvmtool/x86/include/asm/bios/types.h
@@ -0,0 +1,9 @@
+#ifndef __X86_ASM_BIOS_TYPES_H
+#define __X86_ASM_BIOS_TYPES_H
+
+typedef unsigned char u8;
+typedef unsigned short u16;
+typedef unsigned int u32;
+typedef unsigned long long u64;
+
+#endif
diff --git a/kvmtool/x86/include/asm/bios/vesa.h b/kvmtool/x86/include/asm/bios/vesa.h
new file mode 100644
index 0000000..468e444
--- /dev/null
+++ b/kvmtool/x86/include/asm/bios/vesa.h
@@ -0,0 +1,72 @@
+/* ----------------------------------------------------------------------- *
+ *
+ * Copyright 1999-2007 H. Peter Anvin - All Rights Reserved
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ * Boston MA 02111-1307, USA; either version 2 of the License, or
+ * (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+#ifndef BOOT_VESA_H
+#define BOOT_VESA_H
+
+typedef struct {
+ u16 off, seg;
+} far_ptr;
+
+/* VESA General Information table */
+struct vesa_general_info {
+ u32 signature; /* 0 Magic number = "VESA" */
+ u16 version; /* 4 */
+ far_ptr vendor_string; /* 6 */
+ u32 capabilities; /* 10 */
+ far_ptr video_mode_ptr; /* 14 */
+ u16 total_memory; /* 18 */
+
+ u8 reserved[236]; /* 20 */
+} __attribute__ ((packed));
+
+#define VESA_MAGIC ('V' + ('E' << 8) + ('S' << 16) + ('A' << 24))
+
+struct vesa_mode_info {
+ u16 mode_attr; /* 0 */
+ u8 win_attr[2]; /* 2 */
+ u16 win_grain; /* 4 */
+ u16 win_size; /* 6 */
+ u16 win_seg[2]; /* 8 */
+ far_ptr win_scheme; /* 12 */
+ u16 logical_scan; /* 16 */
+
+ u16 h_res; /* 18 */
+ u16 v_res; /* 20 */
+ u8 char_width; /* 22 */
+ u8 char_height; /* 23 */
+ u8 memory_planes; /* 24 */
+ u8 bpp; /* 25 */
+ u8 banks; /* 26 */
+ u8 memory_layout; /* 27 */
+ u8 bank_size; /* 28 */
+ u8 image_planes; /* 29 */
+ u8 page_function; /* 30 */
+
+ u8 rmask; /* 31 */
+ u8 rpos; /* 32 */
+ u8 gmask; /* 33 */
+ u8 gpos; /* 34 */
+ u8 bmask; /* 35 */
+ u8 bpos; /* 36 */
+ u8 resv_mask; /* 37 */
+ u8 resv_pos; /* 38 */
+ u8 dcm_info; /* 39 */
+
+ u32 lfb_ptr; /* 40 Linear frame buffer address */
+ u32 offscreen_ptr; /* 44 Offscreen memory address */
+ u16 offscreen_size; /* 48 */
+
+ u8 reserved[206]; /* 50 */
+} __attribute__ ((packed));
+
+#endif /* LIB_SYS_VESA_H */
diff --git a/kvmtool/x86/include/asm/kvm.h b/kvmtool/x86/include/asm/kvm.h
new file mode 100644
index 0000000..503d3f4
--- /dev/null
+++ b/kvmtool/x86/include/asm/kvm.h
@@ -0,0 +1,449 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _ASM_X86_KVM_H
+#define _ASM_X86_KVM_H
+
+/*
+ * KVM x86 specific structures and definitions
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define KVM_PIO_PAGE_OFFSET 1
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+
+#define DE_VECTOR 0
+#define DB_VECTOR 1
+#define BP_VECTOR 3
+#define OF_VECTOR 4
+#define BR_VECTOR 5
+#define UD_VECTOR 6
+#define NM_VECTOR 7
+#define DF_VECTOR 8
+#define TS_VECTOR 10
+#define NP_VECTOR 11
+#define SS_VECTOR 12
+#define GP_VECTOR 13
+#define PF_VECTOR 14
+#define MF_VECTOR 16
+#define AC_VECTOR 17
+#define MC_VECTOR 18
+#define XM_VECTOR 19
+#define VE_VECTOR 20
+
+/* Select x86 specific features in <linux/kvm.h> */
+#define __KVM_HAVE_PIT
+#define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_MSI
+#define __KVM_HAVE_USER_NMI
+#define __KVM_HAVE_GUEST_DEBUG
+#define __KVM_HAVE_MSIX
+#define __KVM_HAVE_MCE
+#define __KVM_HAVE_PIT_STATE2
+#define __KVM_HAVE_XEN_HVM
+#define __KVM_HAVE_VCPU_EVENTS
+#define __KVM_HAVE_DEBUGREGS
+#define __KVM_HAVE_XSAVE
+#define __KVM_HAVE_XCRS
+#define __KVM_HAVE_READONLY_MEM
+
+/* Architectural interrupt line count. */
+#define KVM_NR_INTERRUPTS 256
+
+struct kvm_memory_alias {
+ __u32 slot; /* this has a different namespace than memory slots */
+ __u32 flags;
+ __u64 guest_phys_addr;
+ __u64 memory_size;
+ __u64 target_phys_addr;
+};
+
+/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
+struct kvm_pic_state {
+ __u8 last_irr; /* edge detection */
+ __u8 irr; /* interrupt request register */
+ __u8 imr; /* interrupt mask register */
+ __u8 isr; /* interrupt service register */
+ __u8 priority_add; /* highest irq priority */
+ __u8 irq_base;
+ __u8 read_reg_select;
+ __u8 poll;
+ __u8 special_mask;
+ __u8 init_state;
+ __u8 auto_eoi;
+ __u8 rotate_on_auto_eoi;
+ __u8 special_fully_nested_mode;
+ __u8 init4; /* true if 4 byte init */
+ __u8 elcr; /* PIIX edge/trigger selection */
+ __u8 elcr_mask;
+};
+
+#define KVM_IOAPIC_NUM_PINS 24
+struct kvm_ioapic_state {
+ __u64 base_address;
+ __u32 ioregsel;
+ __u32 id;
+ __u32 irr;
+ __u32 pad;
+ union {
+ __u64 bits;
+ struct {
+ __u8 vector;
+ __u8 delivery_mode:3;
+ __u8 dest_mode:1;
+ __u8 delivery_status:1;
+ __u8 polarity:1;
+ __u8 remote_irr:1;
+ __u8 trig_mode:1;
+ __u8 mask:1;
+ __u8 reserve:7;
+ __u8 reserved[4];
+ __u8 dest_id;
+ } fields;
+ } redirtbl[KVM_IOAPIC_NUM_PINS];
+};
+
+#define KVM_IRQCHIP_PIC_MASTER 0
+#define KVM_IRQCHIP_PIC_SLAVE 1
+#define KVM_IRQCHIP_IOAPIC 2
+#define KVM_NR_IRQCHIPS 3
+
+#define KVM_RUN_X86_SMM (1 << 0)
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+ /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+ __u64 rax, rbx, rcx, rdx;
+ __u64 rsi, rdi, rsp, rbp;
+ __u64 r8, r9, r10, r11;
+ __u64 r12, r13, r14, r15;
+ __u64 rip, rflags;
+};
+
+/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
+#define KVM_APIC_REG_SIZE 0x400
+struct kvm_lapic_state {
+ char regs[KVM_APIC_REG_SIZE];
+};
+
+struct kvm_segment {
+ __u64 base;
+ __u32 limit;
+ __u16 selector;
+ __u8 type;
+ __u8 present, dpl, db, s, l, g, avl;
+ __u8 unusable;
+ __u8 padding;
+};
+
+struct kvm_dtable {
+ __u64 base;
+ __u16 limit;
+ __u16 padding[3];
+};
+
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+ /* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
+ struct kvm_segment cs, ds, es, fs, gs, ss;
+ struct kvm_segment tr, ldt;
+ struct kvm_dtable gdt, idt;
+ __u64 cr0, cr2, cr3, cr4, cr8;
+ __u64 efer;
+ __u64 apic_base;
+ __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+ __u8 fpr[8][16];
+ __u16 fcw;
+ __u16 fsw;
+ __u8 ftwx; /* in fxsave format */
+ __u8 pad1;
+ __u16 last_opcode;
+ __u64 last_ip;
+ __u64 last_dp;
+ __u8 xmm[16][16];
+ __u32 mxcsr;
+ __u32 pad2;
+};
+
+struct kvm_msr_entry {
+ __u32 index;
+ __u32 reserved;
+ __u64 data;
+};
+
+/* for KVM_GET_MSRS and KVM_SET_MSRS */
+struct kvm_msrs {
+ __u32 nmsrs; /* number of msrs in entries */
+ __u32 pad;
+
+ struct kvm_msr_entry entries[0];
+};
+
+/* for KVM_GET_MSR_INDEX_LIST */
+struct kvm_msr_list {
+ __u32 nmsrs; /* number of msrs in entries */
+ __u32 indices[0];
+};
+
+
+struct kvm_cpuid_entry {
+ __u32 function;
+ __u32 eax;
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 padding;
+};
+
+/* for KVM_SET_CPUID */
+struct kvm_cpuid {
+ __u32 nent;
+ __u32 padding;
+ struct kvm_cpuid_entry entries[0];
+};
+
+struct kvm_cpuid_entry2 {
+ __u32 function;
+ __u32 index;
+ __u32 flags;
+ __u32 eax;
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 padding[3];
+};
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX (1 << 0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC (1 << 1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT (1 << 2)
+
+/* for KVM_SET_CPUID2 */
+struct kvm_cpuid2 {
+ __u32 nent;
+ __u32 padding;
+ struct kvm_cpuid_entry2 entries[0];
+};
+
+/* for KVM_GET_PIT and KVM_SET_PIT */
+struct kvm_pit_channel_state {
+ __u32 count; /* can be 65536 */
+ __u16 latched_count;
+ __u8 count_latched;
+ __u8 status_latched;
+ __u8 status;
+ __u8 read_state;
+ __u8 write_state;
+ __u8 write_latch;
+ __u8 rw_mode;
+ __u8 mode;
+ __u8 bcd;
+ __u8 gate;
+ __s64 count_load_time;
+};
+
+struct kvm_debug_exit_arch {
+ __u32 exception;
+ __u32 pad;
+ __u64 pc;
+ __u64 dr6;
+ __u64 dr7;
+};
+
+#define KVM_GUESTDBG_USE_SW_BP 0x00010000
+#define KVM_GUESTDBG_USE_HW_BP 0x00020000
+#define KVM_GUESTDBG_INJECT_DB 0x00040000
+#define KVM_GUESTDBG_INJECT_BP 0x00080000
+
+/* for KVM_SET_GUEST_DEBUG */
+struct kvm_guest_debug_arch {
+ __u64 debugreg[8];
+};
+
+struct kvm_pit_state {
+ struct kvm_pit_channel_state channels[3];
+};
+
+#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
+
+struct kvm_pit_state2 {
+ struct kvm_pit_channel_state channels[3];
+ __u32 flags;
+ __u32 reserved[9];
+};
+
+struct kvm_reinject_control {
+ __u8 pit_reinject;
+ __u8 reserved[31];
+};
+
+/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
+#define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001
+#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
+#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
+#define KVM_VCPUEVENT_VALID_SMM 0x00000008
+#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
+
+/* Interrupt shadow states */
+#define KVM_X86_SHADOW_INT_MOV_SS 0x01
+#define KVM_X86_SHADOW_INT_STI 0x02
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+ struct {
+ __u8 injected;
+ __u8 nr;
+ __u8 has_error_code;
+ __u8 pending;
+ __u32 error_code;
+ } exception;
+ struct {
+ __u8 injected;
+ __u8 nr;
+ __u8 soft;
+ __u8 shadow;
+ } interrupt;
+ struct {
+ __u8 injected;
+ __u8 pending;
+ __u8 masked;
+ __u8 pad;
+ } nmi;
+ __u32 sipi_vector;
+ __u32 flags;
+ struct {
+ __u8 smm;
+ __u8 pending;
+ __u8 smm_inside_nmi;
+ __u8 latched_init;
+ } smi;
+ __u8 reserved[27];
+ __u8 exception_has_payload;
+ __u64 exception_payload;
+};
+
+/* for KVM_GET/SET_DEBUGREGS */
+struct kvm_debugregs {
+ __u64 db[4];
+ __u64 dr6;
+ __u64 dr7;
+ __u64 flags;
+ __u64 reserved[9];
+};
+
+/* for KVM_CAP_XSAVE */
+struct kvm_xsave {
+ __u32 region[1024];
+};
+
+#define KVM_MAX_XCRS 16
+
+struct kvm_xcr {
+ __u32 xcr;
+ __u32 reserved;
+ __u64 value;
+};
+
+struct kvm_xcrs {
+ __u32 nr_xcrs;
+ __u32 flags;
+ struct kvm_xcr xcrs[KVM_MAX_XCRS];
+ __u64 padding[16];
+};
+
+#define KVM_SYNC_X86_REGS (1UL << 0)
+#define KVM_SYNC_X86_SREGS (1UL << 1)
+#define KVM_SYNC_X86_EVENTS (1UL << 2)
+
+#define KVM_SYNC_X86_VALID_FIELDS \
+ (KVM_SYNC_X86_REGS| \
+ KVM_SYNC_X86_SREGS| \
+ KVM_SYNC_X86_EVENTS)
+
+/* kvm_sync_regs struct included by kvm_run struct */
+struct kvm_sync_regs {
+ /* Members of this structure are potentially malicious.
+ * Care must be taken by code reading, esp. interpreting,
+ * data fields from them inside KVM to prevent TOCTOU and
+ * double-fetch types of vulnerabilities.
+ */
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_vcpu_events events;
+};
+
+#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
+#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
+
+#define KVM_STATE_NESTED_FORMAT_VMX 0
+#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
+
+#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
+#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
+#define KVM_STATE_NESTED_EVMCS 0x00000004
+
+#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
+#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
+
+#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
+
+struct kvm_vmx_nested_state_data {
+ __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+ __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+};
+
+struct kvm_vmx_nested_state_hdr {
+ __u64 vmxon_pa;
+ __u64 vmcs12_pa;
+
+ struct {
+ __u16 flags;
+ } smm;
+};
+
+/* for KVM_CAP_NESTED_STATE */
+struct kvm_nested_state {
+ __u16 flags;
+ __u16 format;
+ __u32 size;
+
+ union {
+ struct kvm_vmx_nested_state_hdr vmx;
+
+ /* Pad the header to 128 bytes. */
+ __u8 pad[120];
+ } hdr;
+
+ /*
+ * Define data region as 0 bytes to preserve backwards-compatability
+ * to old definition of kvm_nested_state in order to avoid changing
+ * KVM_{GET,PUT}_NESTED_STATE ioctl values.
+ */
+ union {
+ struct kvm_vmx_nested_state_data vmx[0];
+ } data;
+};
+
+/* for KVM_CAP_PMU_EVENT_FILTER */
+struct kvm_pmu_event_filter {
+ __u32 action;
+ __u32 nevents;
+ __u32 fixed_counter_bitmap;
+ __u32 flags;
+ __u32 pad[4];
+ __u64 events[0];
+};
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
+#endif /* _ASM_X86_KVM_H */
diff --git a/kvmtool/x86/include/asm/mpspec_def.h b/kvmtool/x86/include/asm/mpspec_def.h
new file mode 100644
index 0000000..b31f8c0
--- /dev/null
+++ b/kvmtool/x86/include/asm/mpspec_def.h
@@ -0,0 +1,173 @@
+#ifndef _ASM_X86_MPSPEC_DEF_H
+#define _ASM_X86_MPSPEC_DEF_H
+
+/*
+ * Structure definitions for SMP machines following the
+ * Intel Multiprocessing Specification 1.1 and 1.4.
+ */
+
+/*
+ * This tag identifies where the SMP configuration
+ * information is.
+ */
+
+#define SMP_MAGIC_IDENT (('_'<<24) | ('P'<<16) | ('M'<<8) | '_')
+
+#ifdef CONFIG_X86_32
+# define MAX_MPC_ENTRY 1024
+#endif
+
+/* Intel MP Floating Pointer Structure */
+struct mpf_intel {
+ char signature[4]; /* "_MP_" */
+ unsigned int physptr; /* Configuration table address */
+ unsigned char length; /* Our length (paragraphs) */
+ unsigned char specification; /* Specification version */
+ unsigned char checksum; /* Checksum (makes sum 0) */
+ unsigned char feature1; /* Standard or configuration ? */
+ unsigned char feature2; /* Bit7 set for IMCR|PIC */
+ unsigned char feature3; /* Unused (0) */
+ unsigned char feature4; /* Unused (0) */
+ unsigned char feature5; /* Unused (0) */
+};
+
+#define MPC_SIGNATURE "PCMP"
+
+struct mpc_table {
+ char signature[4];
+ unsigned short length; /* Size of table */
+ char spec; /* 0x01 */
+ char checksum;
+ char oem[8];
+ char productid[12];
+ unsigned int oemptr; /* 0 if not present */
+ unsigned short oemsize; /* 0 if not present */
+ unsigned short oemcount;
+ unsigned int lapic; /* APIC address */
+ unsigned int reserved;
+};
+
+/* Followed by entries */
+
+#define MP_PROCESSOR 0
+#define MP_BUS 1
+#define MP_IOAPIC 2
+#define MP_INTSRC 3
+#define MP_LINTSRC 4
+/* Used by IBM NUMA-Q to describe node locality */
+#define MP_TRANSLATION 192
+
+#define CPU_ENABLED 1 /* Processor is available */
+#define CPU_BOOTPROCESSOR 2 /* Processor is the BP */
+
+#define CPU_STEPPING_MASK 0x000F
+#define CPU_MODEL_MASK 0x00F0
+#define CPU_FAMILY_MASK 0x0F00
+
+struct mpc_cpu {
+ unsigned char type;
+ unsigned char apicid; /* Local APIC number */
+ unsigned char apicver; /* Its versions */
+ unsigned char cpuflag;
+ unsigned int cpufeature;
+ unsigned int featureflag; /* CPUID feature value */
+ unsigned int reserved[2];
+};
+
+struct mpc_bus {
+ unsigned char type;
+ unsigned char busid;
+ unsigned char bustype[6];
+};
+
+/* List of Bus Type string values, Intel MP Spec. */
+#define BUSTYPE_EISA "EISA"
+#define BUSTYPE_ISA "ISA"
+#define BUSTYPE_INTERN "INTERN" /* Internal BUS */
+#define BUSTYPE_MCA "MCA" /* Obsolete */
+#define BUSTYPE_VL "VL" /* Local bus */
+#define BUSTYPE_PCI "PCI"
+#define BUSTYPE_PCMCIA "PCMCIA"
+#define BUSTYPE_CBUS "CBUS"
+#define BUSTYPE_CBUSII "CBUSII"
+#define BUSTYPE_FUTURE "FUTURE"
+#define BUSTYPE_MBI "MBI"
+#define BUSTYPE_MBII "MBII"
+#define BUSTYPE_MPI "MPI"
+#define BUSTYPE_MPSA "MPSA"
+#define BUSTYPE_NUBUS "NUBUS"
+#define BUSTYPE_TC "TC"
+#define BUSTYPE_VME "VME"
+#define BUSTYPE_XPRESS "XPRESS"
+
+#define MPC_APIC_USABLE 0x01
+
+struct mpc_ioapic {
+ unsigned char type;
+ unsigned char apicid;
+ unsigned char apicver;
+ unsigned char flags;
+ unsigned int apicaddr;
+};
+
+struct mpc_intsrc {
+ unsigned char type;
+ unsigned char irqtype;
+ unsigned short irqflag;
+ unsigned char srcbus;
+ unsigned char srcbusirq;
+ unsigned char dstapic;
+ unsigned char dstirq;
+};
+
+enum mp_irq_source_types {
+ mp_INT = 0,
+ mp_NMI = 1,
+ mp_SMI = 2,
+ mp_ExtINT = 3
+};
+
+#define MP_IRQDIR_DEFAULT 0
+#define MP_IRQDIR_HIGH 1
+#define MP_IRQDIR_LOW 3
+
+#define MP_APIC_ALL 0xFF
+
+struct mpc_lintsrc {
+ unsigned char type;
+ unsigned char irqtype;
+ unsigned short irqflag;
+ unsigned char srcbusid;
+ unsigned char srcbusirq;
+ unsigned char destapic;
+ unsigned char destapiclint;
+};
+
+#define MPC_OEM_SIGNATURE "_OEM"
+
+struct mpc_oemtable {
+ char signature[4];
+ unsigned short length; /* Size of table */
+ char rev; /* 0x01 */
+ char checksum;
+ char mpc[8];
+};
+
+/*
+ * Default configurations
+ *
+ * 1 2 CPU ISA 82489DX
+ * 2 2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
+ * 3 2 CPU EISA 82489DX
+ * 4 2 CPU MCA 82489DX
+ * 5 2 CPU ISA+PCI
+ * 6 2 CPU EISA+PCI
+ * 7 2 CPU MCA+PCI
+ */
+
+enum mp_bustype {
+ MP_BUS_ISA = 1,
+ MP_BUS_EISA,
+ MP_BUS_PCI,
+};
+#endif /* _ASM_X86_MPSPEC_DEF_H */
diff --git a/kvmtool/x86/include/asm/processor-flags.h b/kvmtool/x86/include/asm/processor-flags.h
new file mode 100644
index 0000000..07c2834
--- /dev/null
+++ b/kvmtool/x86/include/asm/processor-flags.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_X86_PROCESSOR_FLAGS_H
+#define _ASM_X86_PROCESSOR_FLAGS_H
+/* Various flags defined: can be included from assembler. */
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */
+
+#endif
diff --git a/kvmtool/x86/include/kvm/assembly.h b/kvmtool/x86/include/kvm/assembly.h
new file mode 100644
index 0000000..e70baab
--- /dev/null
+++ b/kvmtool/x86/include/kvm/assembly.h
@@ -0,0 +1,24 @@
+#ifndef ASSEMBLY_H_
+#define ASSEMBLY_H_
+
+#define __ALIGN .p2align 4, 0x90
+#define ENTRY(name) \
+ __ALIGN; \
+ .globl name; \
+ name:
+
+#define GLOBAL(name) \
+ .globl name; \
+ name:
+
+#define ENTRY_END(name) GLOBAL(name##_end)
+#define END(name) GLOBAL(name##_end)
+
+/*
+ * gas produces size override prefix with which
+ * we are unhappy, lets make it hardcoded for
+ * 16 bit mode
+ */
+#define IRET .byte 0xcf
+
+#endif /* ASSEMBLY_H_ */
diff --git a/kvmtool/x86/include/kvm/barrier.h b/kvmtool/x86/include/kvm/barrier.h
new file mode 100644
index 0000000..46d14f6
--- /dev/null
+++ b/kvmtool/x86/include/kvm/barrier.h
@@ -0,0 +1,20 @@
+#ifndef _KVM_BARRIER_H_
+#define _KVM_BARRIER_H_
+
+#define barrier() asm volatile("": : :"memory")
+
+#define mb() asm volatile ("mfence": : :"memory")
+#define rmb() asm volatile ("lfence": : :"memory")
+#define wmb() asm volatile ("sfence": : :"memory")
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#endif
+
+#endif /* _KVM_BARRIER_H_ */
diff --git a/kvmtool/x86/include/kvm/bios-export.h b/kvmtool/x86/include/kvm/bios-export.h
new file mode 100644
index 0000000..23825aa
--- /dev/null
+++ b/kvmtool/x86/include/kvm/bios-export.h
@@ -0,0 +1,13 @@
+#ifndef BIOS_EXPORT_H_
+#define BIOS_EXPORT_H_
+
+struct kvm;
+
+extern char bios_rom[0];
+extern char bios_rom_end[0];
+
+#define bios_rom_size (bios_rom_end - bios_rom)
+
+extern void setup_bios(struct kvm *kvm);
+
+#endif /* BIOS_EXPORT_H_ */
diff --git a/kvmtool/x86/include/kvm/bios.h b/kvmtool/x86/include/kvm/bios.h
new file mode 100644
index 0000000..edeab17
--- /dev/null
+++ b/kvmtool/x86/include/kvm/bios.h
@@ -0,0 +1,93 @@
+#ifndef BIOS_H_
+#define BIOS_H_
+
+/*
+ * X86-32 Memory Map (typical)
+ * start end
+ * Real Mode Interrupt Vector Table 0x00000000 0x000003FF
+ * BDA area 0x00000400 0x000004FF
+ * Conventional Low Memory 0x00000500 0x0009FBFF
+ * EBDA area 0x0009FC00 0x0009FFFF
+ * VIDEO RAM 0x000A0000 0x000BFFFF
+ * VIDEO ROM (BIOS) 0x000C0000 0x000C7FFF
+ * ROMs & unus. space (mapped hw & misc)0x000C8000 0x000EFFFF 160 KiB (typically)
+ * Motherboard BIOS 0x000F0000 0x000FFFFF
+ * Extended Memory 0x00100000 0xFEBFFFFF
+ * Reserved (configs, ACPI, PnP, etc) 0xFEC00000 0xFFFFFFFF
+ */
+
+#define REAL_MODE_IVT_BEGIN 0x00000000
+#define REAL_MODE_IVT_END 0x000003ff
+
+#define BDA_START 0x00000400
+#define BDA_END 0x000004ff
+
+#define EBDA_START 0x0009fc00
+#define EBDA_END 0x0009ffff
+
+#define E820_MAP_START EBDA_START
+
+#define MB_BIOS_BEGIN 0x000f0000
+#define MB_FIRMWARE_BIOS_BEGIN 0x000e0000
+#define MB_BIOS_END 0x000fffff
+
+#define MB_BIOS_SIZE (MB_BIOS_END - MB_BIOS_BEGIN + 1)
+#define MB_FIRMWARE_BIOS_SIZE (MB_BIOS_END - MB_FIRMWARE_BIOS_BEGIN + 1)
+
+#define VGA_RAM_BEGIN 0x000a0000
+#define VGA_RAM_END 0x000bffff
+
+#define VGA_ROM_BEGIN 0x000c0000
+#define VGA_ROM_OEM_STRING VGA_ROM_BEGIN
+#define VGA_ROM_OEM_STRING_SIZE 16
+#define VGA_ROM_MODES (VGA_ROM_OEM_STRING + VGA_ROM_OEM_STRING_SIZE)
+#define VGA_ROM_MODES_SIZE 32
+#define VGA_ROM_END 0x000c7fff
+
+/* we handle one page only */
+#define VGA_RAM_SEG (VGA_RAM_BEGIN >> 4)
+#define VGA_PAGE_SIZE 0x007d0 /* 80x25 */
+
+/* real mode interrupt vector table */
+#define REAL_INTR_BASE REAL_MODE_IVT_BEGIN
+#define REAL_INTR_VECTORS 256
+
+/*
+ * BIOS stack must be at absolute predefined memory address
+ * We reserve 64 bytes for BIOS stack
+ */
+#define MB_BIOS_SS 0xfff7
+#define MB_BIOS_SP 0x40
+
+/*
+ * When interfere with assembler code we need to be sure how
+ * arguments are passed in real mode.
+ */
+#define bioscall __attribute__((regparm(3)))
+
+#ifndef __ASSEMBLER__
+
+#include <asm/bios/types.h>
+
+struct biosregs {
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+ u32 esp;
+ u32 ebp;
+ u32 esi;
+ u32 edi;
+ u32 ds;
+ u32 es;
+ u32 fs;
+ u32 eip;
+ u32 eflags;
+};
+
+extern bioscall void int10_handler(struct biosregs *regs);
+extern bioscall void int15_handler(struct biosregs *regs);
+
+#endif
+
+#endif /* BIOS_H_ */
diff --git a/kvmtool/x86/include/kvm/boot-protocol.h b/kvmtool/x86/include/kvm/boot-protocol.h
new file mode 100644
index 0000000..85b637f
--- /dev/null
+++ b/kvmtool/x86/include/kvm/boot-protocol.h
@@ -0,0 +1,16 @@
+/*
+ * Linux boot protocol specifics
+ */
+
+#ifndef BOOT_PROTOCOL_H_
+#define BOOT_PROTOCOL_H_
+
+/*
+ * The protected mode kernel part of a modern bzImage is loaded
+ * at 1 MB by default.
+ */
+#define BZ_DEFAULT_SETUP_SECTS 4
+#define BZ_KERNEL_START 0x100000UL
+#define INITRD_START 0x1000000UL
+
+#endif /* BOOT_PROTOCOL_H_ */
diff --git a/kvmtool/x86/include/kvm/cpufeature.h b/kvmtool/x86/include/kvm/cpufeature.h
new file mode 100644
index 0000000..bc4abbb
--- /dev/null
+++ b/kvmtool/x86/include/kvm/cpufeature.h
@@ -0,0 +1,41 @@
+#ifndef KVM__CPUFEATURE_H
+#define KVM__CPUFEATURE_H
+
+#define CPUID_VENDOR_INTEL_1 0x756e6547 /* "Genu" */
+#define CPUID_VENDOR_INTEL_2 0x49656e69 /* "ineI" */
+#define CPUID_VENDOR_INTEL_3 0x6c65746e /* "ntel" */
+
+#define CPUID_VENDOR_AMD_1 0x68747541 /* "Auth" */
+#define CPUID_VENDOR_AMD_2 0x69746e65 /* "enti" */
+#define CPUID_VENDOR_AMD_3 0x444d4163 /* "cAMD" */
+
+/*
+ * CPUID flags we need to deal with
+ */
+#define KVM__X86_FEATURE_VMX 5 /* Hardware virtualization */
+#define KVM__X86_FEATURE_SVM 2 /* Secure virtual machine */
+#define KVM__X86_FEATURE_XSAVE 26 /* XSAVE/XRSTOR/XSETBV/XGETBV */
+
+#define cpu_feature_disable(reg, feature) \
+ ((reg) & ~(1 << (feature)))
+#define cpu_feature_enable(reg, feature) \
+ ((reg) | (1 << (feature)))
+
+struct cpuid_regs {
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+};
+
+static inline void host_cpuid(struct cpuid_regs *regs)
+{
+ asm volatile("cpuid"
+ : "=a" (regs->eax),
+ "=b" (regs->ebx),
+ "=c" (regs->ecx),
+ "=d" (regs->edx)
+ : "0" (regs->eax), "2" (regs->ecx));
+}
+
+#endif /* KVM__CPUFEATURE_H */
diff --git a/kvmtool/x86/include/kvm/e820.h b/kvmtool/x86/include/kvm/e820.h
new file mode 100644
index 0000000..f2889da
--- /dev/null
+++ b/kvmtool/x86/include/kvm/e820.h
@@ -0,0 +1,29 @@
+#ifndef KVM_E820_H
+#define KVM_E820_H
+
+#include <kvm/bios.h>
+
+#define SMAP 0x534d4150 /* ASCII "SMAP" */
+
+#define E820MAX 128 /* number of entries in E820MAP */
+#define E820_X_MAX E820MAX
+
+#define E820_RAM 1
+#define E820_RESERVED 2
+
+struct e820entry {
+ u64 addr; /* start of memory segment */
+ u64 size; /* size of memory segment */
+ u32 type; /* type of memory segment */
+} __attribute__((packed));
+
+struct e820map {
+ u32 nr_map;
+ struct e820entry map[E820_X_MAX];
+};
+
+struct biosregs;
+
+extern bioscall void e820_query_map(struct biosregs *regs);
+
+#endif /* KVM_E820_H */
diff --git a/kvmtool/x86/include/kvm/fdt-arch.h b/kvmtool/x86/include/kvm/fdt-arch.h
new file mode 100644
index 0000000..eebd73f
--- /dev/null
+++ b/kvmtool/x86/include/kvm/fdt-arch.h
@@ -0,0 +1,6 @@
+#ifndef X86__FDT_ARCH_H
+#define X86__FDT_ARCH_H
+
+enum phandles {PHANDLE_RESERVED = 0, PHANDLES_MAX};
+
+#endif /* KVM__KVM_FDT_H */
diff --git a/kvmtool/x86/include/kvm/interrupt.h b/kvmtool/x86/include/kvm/interrupt.h
new file mode 100644
index 0000000..00c7ed7
--- /dev/null
+++ b/kvmtool/x86/include/kvm/interrupt.h
@@ -0,0 +1,26 @@
+#ifndef KVM__INTERRUPT_H
+#define KVM__INTERRUPT_H
+
+#include <linux/types.h>
+#include "kvm/bios.h"
+#include "kvm/bios-export.h"
+
+struct real_intr_desc {
+ u16 offset;
+ u16 segment;
+} __attribute__((packed));
+
+#define REAL_SEGMENT_SHIFT 4
+#define REAL_SEGMENT(addr) ((addr) >> REAL_SEGMENT_SHIFT)
+#define REAL_OFFSET(addr) ((addr) & ((1 << REAL_SEGMENT_SHIFT) - 1))
+#define REAL_INTR_SIZE (REAL_INTR_VECTORS * sizeof(struct real_intr_desc))
+
+struct interrupt_table {
+ struct real_intr_desc entries[REAL_INTR_VECTORS];
+};
+
+void interrupt_table__copy(struct interrupt_table *itable, void *dst, unsigned int size);
+void interrupt_table__setup(struct interrupt_table *itable, struct real_intr_desc *entry);
+void interrupt_table__set(struct interrupt_table *itable, struct real_intr_desc *entry, unsigned int num);
+
+#endif /* KVM__INTERRUPT_H */
diff --git a/kvmtool/x86/include/kvm/kvm-arch.h b/kvmtool/x86/include/kvm/kvm-arch.h
new file mode 100644
index 0000000..85cd336
--- /dev/null
+++ b/kvmtool/x86/include/kvm/kvm-arch.h
@@ -0,0 +1,43 @@
+#ifndef KVM__KVM_ARCH_H
+#define KVM__KVM_ARCH_H
+
+#include "kvm/interrupt.h"
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <time.h>
+
+/*
+ * The hole includes VESA framebuffer and PCI memory.
+ */
+#define KVM_32BIT_MAX_MEM_SIZE (1ULL << 32)
+#define KVM_32BIT_GAP_SIZE (768 << 20)
+#define KVM_32BIT_GAP_START (KVM_32BIT_MAX_MEM_SIZE - KVM_32BIT_GAP_SIZE)
+
+#define KVM_MMIO_START KVM_32BIT_GAP_START
+
+/* This is the address that pci_get_io_port_block() starts allocating
+ * from. Note that this is a PCI bus address (though same on x86).
+ */
+#define KVM_IOPORT_AREA 0x0
+#define KVM_PCI_CFG_AREA (KVM_MMIO_START + 0x1000000)
+#define KVM_PCI_MMIO_AREA (KVM_MMIO_START + 0x2000000)
+#define KVM_VIRTIO_MMIO_AREA (KVM_MMIO_START + 0x3000000)
+
+#define KVM_IRQ_OFFSET 5
+
+#define KVM_VM_TYPE 0
+
+#define KVM_IOEVENTFD_HAS_PIO 1
+
+#define VIRTIO_DEFAULT_TRANS(kvm) VIRTIO_PCI
+
+struct kvm_arch {
+ u16 boot_selector;
+ u16 boot_ip;
+ u16 boot_sp;
+
+ struct interrupt_table interrupt_table;
+};
+
+#endif /* KVM__KVM_ARCH_H */
diff --git a/kvmtool/x86/include/kvm/kvm-config-arch.h b/kvmtool/x86/include/kvm/kvm-config-arch.h
new file mode 100644
index 0000000..3eae8db
--- /dev/null
+++ b/kvmtool/x86/include/kvm/kvm-config-arch.h
@@ -0,0 +1,15 @@
+#ifndef KVM__KVM_CONFIG_ARCH_H
+#define KVM__KVM_CONFIG_ARCH_H
+
+#include "kvm/parse-options.h"
+
+struct kvm_config_arch {
+ int vidmode;
+};
+
+#define OPT_ARCH_RUN(pfx, cfg) \
+ pfx, \
+ OPT_GROUP("BIOS options:"), \
+ OPT_INTEGER('\0', "vidmode", &(cfg)->vidmode, "Video mode"),
+
+#endif /* KVM__KVM_CONFIG_ARCH_H */
diff --git a/kvmtool/x86/include/kvm/kvm-cpu-arch.h b/kvmtool/x86/include/kvm/kvm-cpu-arch.h
new file mode 100644
index 0000000..05e5bb6
--- /dev/null
+++ b/kvmtool/x86/include/kvm/kvm-cpu-arch.h
@@ -0,0 +1,50 @@
+#ifndef KVM__KVM_CPU_ARCH_H
+#define KVM__KVM_CPU_ARCH_H
+
+/* Architecture-specific kvm_cpu definitions. */
+
+#include <linux/kvm.h> /* for struct kvm_regs */
+#include "kvm/kvm.h" /* for kvm__emulate_{mm}io() */
+#include <stdbool.h>
+#include <pthread.h>
+
+struct kvm;
+
+struct kvm_cpu {
+ pthread_t thread; /* VCPU thread */
+
+ unsigned long cpu_id;
+
+ struct kvm *kvm; /* parent KVM */
+ int vcpu_fd; /* For VCPU ioctls() */
+ struct kvm_run *kvm_run;
+ struct kvm_cpu_task *task;
+
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_fpu fpu;
+
+ struct kvm_msrs *msrs; /* dynamically allocated */
+
+ u8 is_running;
+ u8 paused;
+ u8 needs_nmi;
+
+ struct kvm_coalesced_mmio_ring *ring;
+};
+
+/*
+ * As these are such simple wrappers, let's have them in the header so they'll
+ * be cheaper to call:
+ */
+static inline bool kvm_cpu__emulate_io(struct kvm_cpu *vcpu, u16 port, void *data, int direction, int size, u32 count)
+{
+ return kvm__emulate_io(vcpu, port, data, direction, size, count);
+}
+
+static inline bool kvm_cpu__emulate_mmio(struct kvm_cpu *vcpu, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ return kvm__emulate_mmio(vcpu, phys_addr, data, len, is_write);
+}
+
+#endif /* KVM__KVM_CPU_ARCH_H */
diff --git a/kvmtool/x86/include/kvm/mptable.h b/kvmtool/x86/include/kvm/mptable.h
new file mode 100644
index 0000000..9e3cfa6
--- /dev/null
+++ b/kvmtool/x86/include/kvm/mptable.h
@@ -0,0 +1,9 @@
+#ifndef KVM_MPTABLE_H_
+#define KVM_MPTABLE_H_
+
+struct kvm;
+
+int mptable__init(struct kvm *kvm);
+int mptable__exit(struct kvm *kvm);
+
+#endif /* KVM_MPTABLE_H_ */
diff --git a/kvmtool/x86/init.S b/kvmtool/x86/init.S
new file mode 100644
index 0000000..488a93f
--- /dev/null
+++ b/kvmtool/x86/init.S
@@ -0,0 +1,38 @@
+.data
+
+.m_dev:
+.string "hostfs"
+.m_dir:
+.string "/host"
+.m_typ:
+.string "9p"
+.m_opt:
+.string "trans=virtio,version=9p2000.L"
+
+.e_nam:
+.string "/virt/init"
+
+.text
+.globl _start
+_start:
+
+ mov $165, %rax # __NR_mount
+ mov $.m_dev, %rdi
+ mov $.m_dir, %rsi
+ mov $.m_typ, %rdx
+ mov $1, %r10 # MS_RDONLY
+ mov $.m_opt, %r8
+ syscall
+
+ mov $59, %rax # __NR_execve
+ mov $.e_nam, %rdi
+ lea 8(%rsp), %rsi # argv[]
+ mov %rdi, (%rsi) # change argv[0]
+ pop %rcx # argc
+ inc %rcx
+ lea (%rsi,%rcx,8), %rdx # envp[]
+ syscall
+
+ mov $60, %rax # __NR_exit
+ mov $1, %rdi
+ syscall # panic
diff --git a/kvmtool/x86/interrupt.c b/kvmtool/x86/interrupt.c
new file mode 100644
index 0000000..7d47869
--- /dev/null
+++ b/kvmtool/x86/interrupt.c
@@ -0,0 +1,28 @@
+#include "kvm/interrupt.h"
+
+#include "kvm/util.h"
+
+#include <string.h>
+
+void interrupt_table__copy(struct interrupt_table *itable, void *dst, unsigned int size)
+{
+ if (size < sizeof(itable->entries))
+ die("An attempt to overwrite host memory");
+
+ memcpy(dst, itable->entries, sizeof(itable->entries));
+}
+
+void interrupt_table__setup(struct interrupt_table *itable, struct real_intr_desc *entry)
+{
+ unsigned int i;
+
+ for (i = 0; i < REAL_INTR_VECTORS; i++)
+ itable->entries[i] = *entry;
+}
+
+void interrupt_table__set(struct interrupt_table *itable,
+ struct real_intr_desc *entry, unsigned int num)
+{
+ if (num < REAL_INTR_VECTORS)
+ itable->entries[num] = *entry;
+}
diff --git a/kvmtool/x86/ioport.c b/kvmtool/x86/ioport.c
new file mode 100644
index 0000000..7ad7b8f
--- /dev/null
+++ b/kvmtool/x86/ioport.c
@@ -0,0 +1,152 @@
+#include "kvm/ioport.h"
+
+#include <stdlib.h>
+#include <stdio.h>
+
+static bool debug_io_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ return 0;
+}
+
+static struct ioport_operations debug_ops = {
+ .io_out = debug_io_out,
+};
+
+static bool seabios_debug_io_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ char ch;
+
+ ch = ioport__read8(data);
+
+ putchar(ch);
+
+ return true;
+}
+
+static struct ioport_operations seabios_debug_ops = {
+ .io_out = seabios_debug_io_out,
+};
+
+static bool dummy_io_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static bool dummy_io_out(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static struct ioport_operations dummy_read_write_ioport_ops = {
+ .io_in = dummy_io_in,
+ .io_out = dummy_io_out,
+};
+
+static struct ioport_operations dummy_write_only_ioport_ops = {
+ .io_out = dummy_io_out,
+};
+
+/*
+ * The "fast A20 gate"
+ */
+
+static bool ps2_control_a_io_in(struct ioport *ioport, struct kvm_cpu *vcpu, u16 port, void *data, int size)
+{
+ /*
+ * A20 is always enabled.
+ */
+ ioport__write8(data, 0x02);
+
+ return true;
+}
+
+static struct ioport_operations ps2_control_a_ops = {
+ .io_in = ps2_control_a_io_in,
+ .io_out = dummy_io_out,
+};
+
+void ioport__map_irq(u8 *irq)
+{
+}
+
+int ioport__setup_arch(struct kvm *kvm)
+{
+ int r;
+
+ /* Legacy ioport setup */
+
+ /* 0000 - 001F - DMA1 controller */
+ r = ioport__register(kvm, 0x0000, &dummy_read_write_ioport_ops, 32, NULL);
+ if (r < 0)
+ return r;
+
+ /* 0x0020 - 0x003F - 8259A PIC 1 */
+ r = ioport__register(kvm, 0x0020, &dummy_read_write_ioport_ops, 2, NULL);
+ if (r < 0)
+ return r;
+
+ /* PORT 0040-005F - PIT - PROGRAMMABLE INTERVAL TIMER (8253, 8254) */
+ r = ioport__register(kvm, 0x0040, &dummy_read_write_ioport_ops, 4, NULL);
+ if (r < 0)
+ return r;
+
+ /* 0092 - PS/2 system control port A */
+ r = ioport__register(kvm, 0x0092, &ps2_control_a_ops, 1, NULL);
+ if (r < 0)
+ return r;
+
+ /* 0x00A0 - 0x00AF - 8259A PIC 2 */
+ r = ioport__register(kvm, 0x00A0, &dummy_read_write_ioport_ops, 2, NULL);
+ if (r < 0)
+ return r;
+
+ /* 00C0 - 001F - DMA2 controller */
+ r = ioport__register(kvm, 0x00C0, &dummy_read_write_ioport_ops, 32, NULL);
+ if (r < 0)
+ return r;
+
+ /* PORT 00E0-00EF are 'motherboard specific' so we use them for our
+ internal debugging purposes. */
+ r = ioport__register(kvm, IOPORT_DBG, &debug_ops, 1, NULL);
+ if (r < 0)
+ return r;
+
+ /* PORT 00ED - DUMMY PORT FOR DELAY??? */
+ r = ioport__register(kvm, 0x00ED, &dummy_write_only_ioport_ops, 1, NULL);
+ if (r < 0)
+ return r;
+
+ /* 0x00F0 - 0x00FF - Math co-processor */
+ r = ioport__register(kvm, 0x00F0, &dummy_write_only_ioport_ops, 2, NULL);
+ if (r < 0)
+ return r;
+
+ /* PORT 0278-027A - PARALLEL PRINTER PORT (usually LPT1, sometimes LPT2) */
+ r = ioport__register(kvm, 0x0278, &dummy_read_write_ioport_ops, 3, NULL);
+ if (r < 0)
+ return r;
+
+ /* PORT 0378-037A - PARALLEL PRINTER PORT (usually LPT2, sometimes LPT3) */
+ r = ioport__register(kvm, 0x0378, &dummy_read_write_ioport_ops, 3, NULL);
+ if (r < 0)
+ return r;
+
+ /* PORT 03D4-03D5 - COLOR VIDEO - CRT CONTROL REGISTERS */
+ r = ioport__register(kvm, 0x03D4, &dummy_read_write_ioport_ops, 1, NULL);
+ if (r < 0)
+ return r;
+ r = ioport__register(kvm, 0x03D5, &dummy_write_only_ioport_ops, 1, NULL);
+ if (r < 0)
+ return r;
+
+ r = ioport__register(kvm, 0x402, &seabios_debug_ops, 1, NULL);
+ if (r < 0)
+ return r;
+
+ /* 0510 - QEMU BIOS configuration register */
+ r = ioport__register(kvm, 0x510, &dummy_read_write_ioport_ops, 2, NULL);
+ if (r < 0)
+ return r;
+
+ return 0;
+}
diff --git a/kvmtool/x86/irq.c b/kvmtool/x86/irq.c
new file mode 100644
index 0000000..db465a1
--- /dev/null
+++ b/kvmtool/x86/irq.c
@@ -0,0 +1,66 @@
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/kvm.h>
+#include <sys/ioctl.h>
+
+#include <stddef.h>
+#include <stdlib.h>
+
+#define IRQCHIP_MASTER 0
+#define IRQCHIP_SLAVE 1
+#define IRQCHIP_IOAPIC 2
+
+static int irq__add_routing(u32 gsi, u32 type, u32 irqchip, u32 pin)
+{
+ int r = irq__allocate_routing_entry();
+ if (r)
+ return r;
+
+ irq_routing->entries[irq_routing->nr++] =
+ (struct kvm_irq_routing_entry) {
+ .gsi = gsi,
+ .type = type,
+ .u.irqchip.irqchip = irqchip,
+ .u.irqchip.pin = pin,
+ };
+
+ return 0;
+}
+
+int irq__init(struct kvm *kvm)
+{
+ int i, r;
+
+ /* Hook first 8 GSIs to master IRQCHIP */
+ for (i = 0; i < 8; i++)
+ if (i != 2)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_MASTER, i);
+
+ /* Hook next 8 GSIs to slave IRQCHIP */
+ for (i = 8; i < 16; i++)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_SLAVE, i - 8);
+
+ /* Last but not least, IOAPIC */
+ for (i = 0; i < 24; i++) {
+ if (i == 0)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_IOAPIC, 2);
+ else if (i != 2)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_IOAPIC, i);
+ }
+
+ r = ioctl(kvm->vm_fd, KVM_SET_GSI_ROUTING, irq_routing);
+ if (r) {
+ free(irq_routing);
+ return errno;
+ }
+
+ next_gsi = i;
+
+ return 0;
+}
+dev_base_init(irq__init);
diff --git a/kvmtool/x86/kvm-cpu.c b/kvmtool/x86/kvm-cpu.c
new file mode 100644
index 0000000..b02ff65
--- /dev/null
+++ b/kvmtool/x86/kvm-cpu.c
@@ -0,0 +1,446 @@
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/symbol.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include <asm/apicdef.h>
+#include <linux/err.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+
+static int debug_fd;
+
+void kvm_cpu__set_debug_fd(int fd)
+{
+ debug_fd = fd;
+}
+
+int kvm_cpu__get_debug_fd(void)
+{
+ return debug_fd;
+}
+
+static inline bool is_in_protected_mode(struct kvm_cpu *vcpu)
+{
+ return vcpu->sregs.cr0 & 0x01;
+}
+
+static inline u64 ip_to_flat(struct kvm_cpu *vcpu, u64 ip)
+{
+ u64 cs;
+
+ /*
+ * NOTE! We should take code segment base address into account here.
+ * Luckily it's usually zero because Linux uses flat memory model.
+ */
+ if (is_in_protected_mode(vcpu))
+ return ip;
+
+ cs = vcpu->sregs.cs.selector;
+
+ return ip + (cs << 4);
+}
+
+static inline u32 selector_to_base(u16 selector)
+{
+ /*
+ * KVM on Intel requires 'base' to be 'selector * 16' in real mode.
+ */
+ return (u32)selector << 4;
+}
+
+static struct kvm_cpu *kvm_cpu__new(struct kvm *kvm)
+{
+ struct kvm_cpu *vcpu;
+
+ vcpu = calloc(1, sizeof(*vcpu));
+ if (!vcpu)
+ return NULL;
+
+ vcpu->kvm = kvm;
+
+ return vcpu;
+}
+
+void kvm_cpu__delete(struct kvm_cpu *vcpu)
+{
+ if (vcpu->msrs)
+ free(vcpu->msrs);
+
+ free(vcpu);
+}
+
+static int kvm_cpu__set_lint(struct kvm_cpu *vcpu)
+{
+ struct local_apic lapic;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_LAPIC, &lapic))
+ return -1;
+
+ lapic.lvt_lint0.delivery_mode = APIC_MODE_EXTINT;
+ lapic.lvt_lint1.delivery_mode = APIC_MODE_NMI;
+
+ return ioctl(vcpu->vcpu_fd, KVM_SET_LAPIC, &lapic);
+}
+
+struct kvm_cpu *kvm_cpu__arch_init(struct kvm *kvm, unsigned long cpu_id)
+{
+ struct kvm_cpu *vcpu;
+ int mmap_size;
+ int coalesced_offset;
+
+ vcpu = kvm_cpu__new(kvm);
+ if (!vcpu)
+ return NULL;
+
+ vcpu->cpu_id = cpu_id;
+
+ vcpu->vcpu_fd = ioctl(vcpu->kvm->vm_fd, KVM_CREATE_VCPU, cpu_id);
+ if (vcpu->vcpu_fd < 0)
+ die_perror("KVM_CREATE_VCPU ioctl");
+
+ mmap_size = ioctl(vcpu->kvm->sys_fd, KVM_GET_VCPU_MMAP_SIZE, 0);
+ if (mmap_size < 0)
+ die_perror("KVM_GET_VCPU_MMAP_SIZE ioctl");
+
+ vcpu->kvm_run = mmap(NULL, mmap_size, PROT_RW, MAP_SHARED, vcpu->vcpu_fd, 0);
+ if (vcpu->kvm_run == MAP_FAILED)
+ die("unable to mmap vcpu fd");
+
+ coalesced_offset = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_COALESCED_MMIO);
+ if (coalesced_offset)
+ vcpu->ring = (void *)vcpu->kvm_run + (coalesced_offset * PAGE_SIZE);
+
+ if (kvm_cpu__set_lint(vcpu))
+ die_perror("KVM_SET_LAPIC failed");
+
+ vcpu->is_running = true;
+
+ return vcpu;
+}
+
+static struct kvm_msrs *kvm_msrs__new(size_t nmsrs)
+{
+ struct kvm_msrs *vcpu = calloc(1, sizeof(*vcpu) + (sizeof(struct kvm_msr_entry) * nmsrs));
+
+ if (!vcpu)
+ die("out of memory");
+
+ return vcpu;
+}
+
+#define MSR_IA32_SYSENTER_CS 0x00000174
+#define MSR_IA32_SYSENTER_ESP 0x00000175
+#define MSR_IA32_SYSENTER_EIP 0x00000176
+
+#define MSR_STAR 0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR 0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR 0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK 0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */
+
+#define MSR_IA32_TSC 0x00000010
+#define MSR_IA32_MISC_ENABLE 0x000001a0
+
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT 0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+
+#define KVM_MSR_ENTRY(_index, _data) \
+ (struct kvm_msr_entry) { .index = _index, .data = _data }
+
+static void kvm_cpu__setup_msrs(struct kvm_cpu *vcpu)
+{
+ unsigned long ndx = 0;
+
+ vcpu->msrs = kvm_msrs__new(100);
+
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_SYSENTER_CS, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_SYSENTER_ESP, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_SYSENTER_EIP, 0x0);
+#ifdef CONFIG_X86_64
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_STAR, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_CSTAR, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_KERNEL_GS_BASE, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_SYSCALL_MASK, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_LSTAR, 0x0);
+#endif
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_TSC, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_MISC_ENABLE,
+ MSR_IA32_MISC_ENABLE_FAST_STRING);
+
+ vcpu->msrs->nmsrs = ndx;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_MSRS, vcpu->msrs) < 0)
+ die_perror("KVM_SET_MSRS failed");
+}
+
+static void kvm_cpu__setup_fpu(struct kvm_cpu *vcpu)
+{
+ vcpu->fpu = (struct kvm_fpu) {
+ .fcw = 0x37f,
+ .mxcsr = 0x1f80,
+ };
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_FPU, &vcpu->fpu) < 0)
+ die_perror("KVM_SET_FPU failed");
+}
+
+static void kvm_cpu__setup_regs(struct kvm_cpu *vcpu)
+{
+ vcpu->regs = (struct kvm_regs) {
+ /* We start the guest in 16-bit real mode */
+ .rflags = 0x0000000000000002ULL,
+
+ .rip = vcpu->kvm->arch.boot_ip,
+ .rsp = vcpu->kvm->arch.boot_sp,
+ .rbp = vcpu->kvm->arch.boot_sp,
+ };
+
+ if (vcpu->regs.rip > USHRT_MAX)
+ die("ip 0x%llx is too high for real mode", (u64)vcpu->regs.rip);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_REGS, &vcpu->regs) < 0)
+ die_perror("KVM_SET_REGS failed");
+}
+
+static void kvm_cpu__setup_sregs(struct kvm_cpu *vcpu)
+{
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &vcpu->sregs) < 0)
+ die_perror("KVM_GET_SREGS failed");
+
+ vcpu->sregs.cs.selector = vcpu->kvm->arch.boot_selector;
+ vcpu->sregs.cs.base = selector_to_base(vcpu->kvm->arch.boot_selector);
+ vcpu->sregs.ss.selector = vcpu->kvm->arch.boot_selector;
+ vcpu->sregs.ss.base = selector_to_base(vcpu->kvm->arch.boot_selector);
+ vcpu->sregs.ds.selector = vcpu->kvm->arch.boot_selector;
+ vcpu->sregs.ds.base = selector_to_base(vcpu->kvm->arch.boot_selector);
+ vcpu->sregs.es.selector = vcpu->kvm->arch.boot_selector;
+ vcpu->sregs.es.base = selector_to_base(vcpu->kvm->arch.boot_selector);
+ vcpu->sregs.fs.selector = vcpu->kvm->arch.boot_selector;
+ vcpu->sregs.fs.base = selector_to_base(vcpu->kvm->arch.boot_selector);
+ vcpu->sregs.gs.selector = vcpu->kvm->arch.boot_selector;
+ vcpu->sregs.gs.base = selector_to_base(vcpu->kvm->arch.boot_selector);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_SREGS, &vcpu->sregs) < 0)
+ die_perror("KVM_SET_SREGS failed");
+}
+
+/**
+ * kvm_cpu__reset_vcpu - reset virtual CPU to a known state
+ */
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu)
+{
+ kvm_cpu__setup_cpuid(vcpu);
+ kvm_cpu__setup_sregs(vcpu);
+ kvm_cpu__setup_regs(vcpu);
+ kvm_cpu__setup_fpu(vcpu);
+ kvm_cpu__setup_msrs(vcpu);
+}
+
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu)
+{
+ return false;
+}
+
+static void print_dtable(const char *name, struct kvm_dtable *dtable)
+{
+ dprintf(debug_fd, " %s %016llx %08hx\n",
+ name, (u64) dtable->base, (u16) dtable->limit);
+}
+
+static void print_segment(const char *name, struct kvm_segment *seg)
+{
+ dprintf(debug_fd, " %s %04hx %016llx %08x %02hhx %x %x %x %x %x %x %x\n",
+ name, (u16) seg->selector, (u64) seg->base, (u32) seg->limit,
+ (u8) seg->type, seg->present, seg->dpl, seg->db, seg->s, seg->l, seg->g, seg->avl);
+}
+
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu)
+{
+ unsigned long cr0, cr2, cr3;
+ unsigned long cr4, cr8;
+ unsigned long rax, rbx, rcx;
+ unsigned long rdx, rsi, rdi;
+ unsigned long rbp, r8, r9;
+ unsigned long r10, r11, r12;
+ unsigned long r13, r14, r15;
+ unsigned long rip, rsp;
+ struct kvm_sregs sregs;
+ unsigned long rflags;
+ struct kvm_regs regs;
+ int i;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, ®s) < 0)
+ die("KVM_GET_REGS failed");
+
+ rflags = regs.rflags;
+
+ rip = regs.rip; rsp = regs.rsp;
+ rax = regs.rax; rbx = regs.rbx; rcx = regs.rcx;
+ rdx = regs.rdx; rsi = regs.rsi; rdi = regs.rdi;
+ rbp = regs.rbp; r8 = regs.r8; r9 = regs.r9;
+ r10 = regs.r10; r11 = regs.r11; r12 = regs.r12;
+ r13 = regs.r13; r14 = regs.r14; r15 = regs.r15;
+
+ dprintf(debug_fd, "\n Registers:\n");
+ dprintf(debug_fd, " ----------\n");
+ dprintf(debug_fd, " rip: %016lx rsp: %016lx flags: %016lx\n", rip, rsp, rflags);
+ dprintf(debug_fd, " rax: %016lx rbx: %016lx rcx: %016lx\n", rax, rbx, rcx);
+ dprintf(debug_fd, " rdx: %016lx rsi: %016lx rdi: %016lx\n", rdx, rsi, rdi);
+ dprintf(debug_fd, " rbp: %016lx r8: %016lx r9: %016lx\n", rbp, r8, r9);
+ dprintf(debug_fd, " r10: %016lx r11: %016lx r12: %016lx\n", r10, r11, r12);
+ dprintf(debug_fd, " r13: %016lx r14: %016lx r15: %016lx\n", r13, r14, r15);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &sregs) < 0)
+ die("KVM_GET_REGS failed");
+
+ cr0 = sregs.cr0; cr2 = sregs.cr2; cr3 = sregs.cr3;
+ cr4 = sregs.cr4; cr8 = sregs.cr8;
+
+ dprintf(debug_fd, " cr0: %016lx cr2: %016lx cr3: %016lx\n", cr0, cr2, cr3);
+ dprintf(debug_fd, " cr4: %016lx cr8: %016lx\n", cr4, cr8);
+ dprintf(debug_fd, "\n Segment registers:\n");
+ dprintf(debug_fd, " ------------------\n");
+ dprintf(debug_fd, " register selector base limit type p dpl db s l g avl\n");
+ print_segment("cs ", &sregs.cs);
+ print_segment("ss ", &sregs.ss);
+ print_segment("ds ", &sregs.ds);
+ print_segment("es ", &sregs.es);
+ print_segment("fs ", &sregs.fs);
+ print_segment("gs ", &sregs.gs);
+ print_segment("tr ", &sregs.tr);
+ print_segment("ldt", &sregs.ldt);
+ print_dtable("gdt", &sregs.gdt);
+ print_dtable("idt", &sregs.idt);
+
+ dprintf(debug_fd, "\n APIC:\n");
+ dprintf(debug_fd, " -----\n");
+ dprintf(debug_fd, " efer: %016llx apic base: %016llx nmi: %s\n",
+ (u64) sregs.efer, (u64) sregs.apic_base,
+ (vcpu->kvm->nmi_disabled ? "disabled" : "enabled"));
+
+ dprintf(debug_fd, "\n Interrupt bitmap:\n");
+ dprintf(debug_fd, " -----------------\n");
+ for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++)
+ dprintf(debug_fd, " %016llx", (u64) sregs.interrupt_bitmap[i]);
+ dprintf(debug_fd, "\n");
+}
+
+#define MAX_SYM_LEN 128
+
+void kvm_cpu__show_code(struct kvm_cpu *vcpu)
+{
+ unsigned int code_bytes = 64;
+ unsigned int code_prologue = 43;
+ unsigned int code_len = code_bytes;
+ char sym[MAX_SYM_LEN] = SYMBOL_DEFAULT_UNKNOWN, *psym;
+ unsigned char c;
+ unsigned int i;
+ u8 *ip;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, &vcpu->regs) < 0)
+ die("KVM_GET_REGS failed");
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &vcpu->sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ ip = guest_flat_to_host(vcpu->kvm, ip_to_flat(vcpu, vcpu->regs.rip) - code_prologue);
+
+ dprintf(debug_fd, "\n Code:\n");
+ dprintf(debug_fd, " -----\n");
+
+ psym = symbol_lookup(vcpu->kvm, vcpu->regs.rip, sym, MAX_SYM_LEN);
+ if (IS_ERR(psym))
+ dprintf(debug_fd,
+ "Warning: symbol_lookup() failed to find symbol "
+ "with error: %ld\n", PTR_ERR(psym));
+
+ dprintf(debug_fd, " rip: [<%016lx>] %s\n\n", (unsigned long) vcpu->regs.rip, sym);
+
+ for (i = 0; i < code_len; i++, ip++) {
+ if (!host_ptr_in_ram(vcpu->kvm, ip))
+ break;
+
+ c = *ip;
+
+ if (ip == guest_flat_to_host(vcpu->kvm, ip_to_flat(vcpu, vcpu->regs.rip)))
+ dprintf(debug_fd, " <%02x>", c);
+ else
+ dprintf(debug_fd, " %02x", c);
+ }
+
+ dprintf(debug_fd, "\n");
+
+ dprintf(debug_fd, "\n Stack:\n");
+ dprintf(debug_fd, " ------\n");
+ dprintf(debug_fd, " rsp: [<%016lx>] \n", (unsigned long) vcpu->regs.rsp);
+ kvm__dump_mem(vcpu->kvm, vcpu->regs.rsp, 32, debug_fd);
+}
+
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu)
+{
+ u64 *pte1;
+ u64 *pte2;
+ u64 *pte3;
+ u64 *pte4;
+
+ if (!is_in_protected_mode(vcpu)) {
+ dprintf(debug_fd, "\n Page Tables:\n");
+ dprintf(debug_fd, " ------\n");
+ dprintf(debug_fd, " Not in protected mode\n");
+ return;
+ }
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &vcpu->sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ pte4 = guest_flat_to_host(vcpu->kvm, vcpu->sregs.cr3);
+ if (!host_ptr_in_ram(vcpu->kvm, pte4))
+ return;
+
+ pte3 = guest_flat_to_host(vcpu->kvm, (*pte4 & ~0xfff));
+ if (!host_ptr_in_ram(vcpu->kvm, pte3))
+ return;
+
+ pte2 = guest_flat_to_host(vcpu->kvm, (*pte3 & ~0xfff));
+ if (!host_ptr_in_ram(vcpu->kvm, pte2))
+ return;
+
+ pte1 = guest_flat_to_host(vcpu->kvm, (*pte2 & ~0xfff));
+ if (!host_ptr_in_ram(vcpu->kvm, pte1))
+ return;
+
+ dprintf(debug_fd, "\n Page Tables:\n");
+ dprintf(debug_fd, " ------\n");
+ if (*pte2 & (1 << 7))
+ dprintf(debug_fd, " pte4: %016llx pte3: %016llx"
+ " pte2: %016llx\n",
+ *pte4, *pte3, *pte2);
+ else
+ dprintf(debug_fd, " pte4: %016llx pte3: %016llx pte2: %016"
+ "llx pte1: %016llx\n",
+ *pte4, *pte3, *pte2, *pte1);
+}
+
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu)
+{
+ struct kvm_lapic_state klapic;
+ struct local_apic *lapic = (void *)&klapic;
+
+ if (ioctl(cpu->vcpu_fd, KVM_GET_LAPIC, &klapic) != 0)
+ return;
+
+ if (lapic->lvt_lint1.mask)
+ return;
+
+ if (lapic->lvt_lint1.delivery_mode != APIC_MODE_NMI)
+ return;
+
+ ioctl(cpu->vcpu_fd, KVM_NMI);
+}
diff --git a/kvmtool/x86/kvm.c b/kvmtool/x86/kvm.c
new file mode 100644
index 0000000..3e0f0b7
--- /dev/null
+++ b/kvmtool/x86/kvm.c
@@ -0,0 +1,378 @@
+#include "kvm/kvm.h"
+#include "kvm/boot-protocol.h"
+#include "kvm/cpufeature.h"
+#include "kvm/interrupt.h"
+#include "kvm/mptable.h"
+#include "kvm/util.h"
+#include "kvm/8250-serial.h"
+#include "kvm/virtio-console.h"
+
+#include <asm/bootparam.h>
+#include <linux/kvm.h>
+#include <linux/kernel.h>
+
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <fcntl.h>
+
+struct kvm_ext kvm_req_ext[] = {
+ { DEFINE_KVM_EXT(KVM_CAP_COALESCED_MMIO) },
+ { DEFINE_KVM_EXT(KVM_CAP_SET_TSS_ADDR) },
+ { DEFINE_KVM_EXT(KVM_CAP_PIT2) },
+ { DEFINE_KVM_EXT(KVM_CAP_USER_MEMORY) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQ_ROUTING) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQCHIP) },
+ { DEFINE_KVM_EXT(KVM_CAP_HLT) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQ_INJECT_STATUS) },
+ { DEFINE_KVM_EXT(KVM_CAP_EXT_CPUID) },
+ { 0, 0 }
+};
+
+bool kvm__arch_cpu_supports_vm(void)
+{
+ struct cpuid_regs regs;
+ u32 eax_base;
+ int feature;
+
+ regs = (struct cpuid_regs) {
+ .eax = 0x00,
+ };
+ host_cpuid(®s);
+
+ switch (regs.ebx) {
+ case CPUID_VENDOR_INTEL_1:
+ eax_base = 0x00;
+ feature = KVM__X86_FEATURE_VMX;
+ break;
+
+ case CPUID_VENDOR_AMD_1:
+ eax_base = 0x80000000;
+ feature = KVM__X86_FEATURE_SVM;
+ break;
+
+ default:
+ return false;
+ }
+
+ regs = (struct cpuid_regs) {
+ .eax = eax_base,
+ };
+ host_cpuid(®s);
+
+ if (regs.eax < eax_base + 0x01)
+ return false;
+
+ regs = (struct cpuid_regs) {
+ .eax = eax_base + 0x01
+ };
+ host_cpuid(®s);
+
+ return regs.ecx & (1 << feature);
+}
+
+/*
+ * Allocating RAM size bigger than 4GB requires us to leave a gap
+ * in the RAM which is used for PCI MMIO, hotplug, and unconfigured
+ * devices (see documentation of e820_setup_gap() for details).
+ *
+ * If we're required to initialize RAM bigger than 4GB, we will create
+ * a gap between 0xe0000000 and 0x100000000 in the guest virtual mem space.
+ */
+
+void kvm__init_ram(struct kvm *kvm)
+{
+ u64 phys_start, phys_size;
+ void *host_mem;
+
+ if (kvm->ram_size < KVM_32BIT_GAP_START) {
+ /* Use a single block of RAM for 32bit RAM */
+
+ phys_start = 0;
+ phys_size = kvm->ram_size;
+ host_mem = kvm->ram_start;
+
+ kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+ } else {
+ /* First RAM range from zero to the PCI gap: */
+
+ phys_start = 0;
+ phys_size = KVM_32BIT_GAP_START;
+ host_mem = kvm->ram_start;
+
+ kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+
+ /* Second RAM range from 4GB to the end of RAM: */
+
+ phys_start = KVM_32BIT_MAX_MEM_SIZE;
+ phys_size = kvm->ram_size - phys_start;
+ host_mem = kvm->ram_start + phys_start;
+
+ kvm__register_ram(kvm, phys_start, phys_size, host_mem);
+ }
+}
+
+/* Arch-specific commandline setup */
+void kvm__arch_set_cmdline(char *cmdline, bool video)
+{
+ strcpy(cmdline, "noapic noacpi pci=conf1 reboot=k panic=1 i8042.direct=1 "
+ "i8042.dumbkbd=1 i8042.nopnp=1");
+ if (video)
+ strcat(cmdline, " video=vesafb");
+ else
+ strcat(cmdline, " earlyprintk=serial i8042.noaux=1");
+}
+
+/* Architecture-specific KVM init */
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size)
+{
+ struct kvm_pit_config pit_config = { .flags = 0, };
+ int ret;
+
+ ret = ioctl(kvm->vm_fd, KVM_SET_TSS_ADDR, 0xfffbd000);
+ if (ret < 0)
+ die_perror("KVM_SET_TSS_ADDR ioctl");
+
+ ret = ioctl(kvm->vm_fd, KVM_CREATE_PIT2, &pit_config);
+ if (ret < 0)
+ die_perror("KVM_CREATE_PIT2 ioctl");
+
+ if (ram_size < KVM_32BIT_GAP_START) {
+ kvm->ram_size = ram_size;
+ kvm->ram_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path, ram_size);
+ } else {
+ kvm->ram_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path, ram_size + KVM_32BIT_GAP_SIZE);
+ kvm->ram_size = ram_size + KVM_32BIT_GAP_SIZE;
+ if (kvm->ram_start != MAP_FAILED)
+ /*
+ * We mprotect the gap (see kvm__init_ram() for details) PROT_NONE so that
+ * if we accidently write to it, we will know.
+ */
+ mprotect(kvm->ram_start + KVM_32BIT_GAP_START, KVM_32BIT_GAP_SIZE, PROT_NONE);
+ }
+ if (kvm->ram_start == MAP_FAILED)
+ die("out of memory");
+
+ madvise(kvm->ram_start, kvm->ram_size, MADV_MERGEABLE);
+
+ ret = ioctl(kvm->vm_fd, KVM_CREATE_IRQCHIP);
+ if (ret < 0)
+ die_perror("KVM_CREATE_IRQCHIP ioctl");
+}
+
+void kvm__arch_delete_ram(struct kvm *kvm)
+{
+ munmap(kvm->ram_start, kvm->ram_size);
+}
+
+void kvm__irq_line(struct kvm *kvm, int irq, int level)
+{
+ struct kvm_irq_level irq_level;
+
+ irq_level = (struct kvm_irq_level) {
+ {
+ .irq = irq,
+ },
+ .level = level,
+ };
+
+ if (ioctl(kvm->vm_fd, KVM_IRQ_LINE, &irq_level) < 0)
+ die_perror("KVM_IRQ_LINE failed");
+}
+
+void kvm__irq_trigger(struct kvm *kvm, int irq)
+{
+ kvm__irq_line(kvm, irq, 1);
+ kvm__irq_line(kvm, irq, 0);
+}
+
+#define BOOT_LOADER_SELECTOR 0x1000
+#define BOOT_LOADER_IP 0x0000
+#define BOOT_LOADER_SP 0x8000
+#define BOOT_CMDLINE_OFFSET 0x20000
+
+#define BOOT_PROTOCOL_REQUIRED 0x206
+#define LOAD_HIGH 0x01
+
+static inline void *guest_real_to_host(struct kvm *kvm, u16 selector, u16 offset)
+{
+ unsigned long flat = ((u32)selector << 4) + offset;
+
+ return guest_flat_to_host(kvm, flat);
+}
+
+static bool load_flat_binary(struct kvm *kvm, int fd_kernel)
+{
+ void *p;
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ p = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
+
+ if (read_file(fd_kernel, p, kvm->cfg.ram_size) < 0)
+ die_perror("read");
+
+ kvm->arch.boot_selector = BOOT_LOADER_SELECTOR;
+ kvm->arch.boot_ip = BOOT_LOADER_IP;
+ kvm->arch.boot_sp = BOOT_LOADER_SP;
+
+ return true;
+}
+
+static const char *BZIMAGE_MAGIC = "HdrS";
+
+static bool load_bzimage(struct kvm *kvm, int fd_kernel, int fd_initrd,
+ const char *kernel_cmdline)
+{
+ struct boot_params *kern_boot;
+ struct boot_params boot;
+ size_t cmdline_size;
+ ssize_t file_size;
+ void *p;
+ u16 vidmode;
+
+ /*
+ * See Documentation/x86/boot.txt for details no bzImage on-disk and
+ * memory layout.
+ */
+
+ if (read_in_full(fd_kernel, &boot, sizeof(boot)) != sizeof(boot))
+ return false;
+
+ if (memcmp(&boot.hdr.header, BZIMAGE_MAGIC, strlen(BZIMAGE_MAGIC)))
+ return false;
+
+ if (boot.hdr.version < BOOT_PROTOCOL_REQUIRED)
+ die("Too old kernel");
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ if (!boot.hdr.setup_sects)
+ boot.hdr.setup_sects = BZ_DEFAULT_SETUP_SECTS;
+ file_size = (boot.hdr.setup_sects + 1) << 9;
+ p = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
+ if (read_in_full(fd_kernel, p, file_size) != file_size)
+ die_perror("kernel setup read");
+
+ /* read actual kernel image (vmlinux.bin) to BZ_KERNEL_START */
+ p = guest_flat_to_host(kvm, BZ_KERNEL_START);
+ file_size = read_file(fd_kernel, p,
+ kvm->cfg.ram_size - BZ_KERNEL_START);
+ if (file_size < 0)
+ die_perror("kernel read");
+
+ p = guest_flat_to_host(kvm, BOOT_CMDLINE_OFFSET);
+ if (kernel_cmdline) {
+ cmdline_size = strlen(kernel_cmdline) + 1;
+ if (cmdline_size > boot.hdr.cmdline_size)
+ cmdline_size = boot.hdr.cmdline_size;
+
+ memset(p, 0, boot.hdr.cmdline_size);
+ memcpy(p, kernel_cmdline, cmdline_size - 1);
+ }
+
+ /* vidmode should be either specified or set by default */
+ if (kvm->cfg.vnc || kvm->cfg.sdl || kvm->cfg.gtk) {
+ if (!kvm->cfg.arch.vidmode)
+ vidmode = 0x312;
+ else
+ vidmode = kvm->cfg.arch.vidmode;
+ } else {
+ vidmode = 0;
+ }
+
+ kern_boot = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, 0x00);
+
+ kern_boot->hdr.cmd_line_ptr = BOOT_CMDLINE_OFFSET;
+ kern_boot->hdr.type_of_loader = 0xff;
+ kern_boot->hdr.heap_end_ptr = 0xfe00;
+ kern_boot->hdr.loadflags |= CAN_USE_HEAP;
+ kern_boot->hdr.vid_mode = vidmode;
+
+ /*
+ * Read initrd image into guest memory
+ */
+ if (fd_initrd >= 0) {
+ struct stat initrd_stat;
+ unsigned long addr;
+
+ if (fstat(fd_initrd, &initrd_stat))
+ die_perror("fstat");
+
+ addr = boot.hdr.initrd_addr_max & ~0xfffff;
+ for (;;) {
+ if (addr < BZ_KERNEL_START)
+ die("Not enough memory for initrd");
+ else if (addr < (kvm->ram_size - initrd_stat.st_size))
+ break;
+ addr -= 0x100000;
+ }
+
+ p = guest_flat_to_host(kvm, addr);
+ if (read_in_full(fd_initrd, p, initrd_stat.st_size) < 0)
+ die("Failed to read initrd");
+
+ kern_boot->hdr.ramdisk_image = addr;
+ kern_boot->hdr.ramdisk_size = initrd_stat.st_size;
+ }
+
+ kvm->arch.boot_selector = BOOT_LOADER_SELECTOR;
+ /*
+ * The real-mode setup code starts at offset 0x200 of a bzImage. See
+ * Documentation/x86/boot.txt for details.
+ */
+ kvm->arch.boot_ip = BOOT_LOADER_IP + 0x200;
+ kvm->arch.boot_sp = BOOT_LOADER_SP;
+
+ return true;
+}
+
+bool kvm__arch_load_kernel_image(struct kvm *kvm, int fd_kernel, int fd_initrd,
+ const char *kernel_cmdline)
+{
+ if (load_bzimage(kvm, fd_kernel, fd_initrd, kernel_cmdline))
+ return true;
+ pr_warning("Kernel image is not a bzImage.");
+ pr_warning("Trying to load it as a flat binary (no cmdline support)");
+
+ if (fd_initrd != -1)
+ pr_warning("Loading initrd with flat binary not supported.");
+
+ return load_flat_binary(kvm, fd_kernel);
+}
+
+/**
+ * kvm__arch_setup_firmware - inject BIOS into guest system memory
+ * @kvm - guest system descriptor
+ *
+ * This function is a main routine where we poke guest memory
+ * and install BIOS there.
+ */
+int kvm__arch_setup_firmware(struct kvm *kvm)
+{
+ /* standart minimal configuration */
+ setup_bios(kvm);
+
+ /* FIXME: SMP, ACPI and friends here */
+
+ return 0;
+}
+
+int kvm__arch_free_firmware(struct kvm *kvm)
+{
+ return 0;
+}
+
+void kvm__arch_read_term(struct kvm *kvm)
+{
+ serial8250__update_consoles(kvm);
+ virtio_console__inject_interrupt(kvm);
+}
diff --git a/kvmtool/x86/mptable.c b/kvmtool/x86/mptable.c
new file mode 100644
index 0000000..a984de9
--- /dev/null
+++ b/kvmtool/x86/mptable.c
@@ -0,0 +1,280 @@
+#include "kvm/kvm.h"
+#include "kvm/bios.h"
+#include "kvm/apic.h"
+#include "kvm/mptable.h"
+#include "kvm/util.h"
+#include "kvm/devices.h"
+#include "kvm/pci.h"
+
+#include <linux/kernel.h>
+#include <string.h>
+
+#include <asm/mpspec_def.h>
+#include <linux/types.h>
+
+/*
+ * FIXME: please make sure the addresses borrowed
+ * for apic/ioapic never overlaped! We need a global
+ * tracker of system resources (including io, mmio,
+ * and friends).
+ */
+
+static unsigned int mpf_checksum(unsigned char *mp, int len)
+{
+ unsigned int sum = 0;
+
+ while (len--)
+ sum += *mp++;
+
+ return sum & 0xFF;
+}
+
+static unsigned int gen_cpu_flag(unsigned int cpu, unsigned int ncpu)
+{
+ /* sets enabled/disabled | BSP/AP processor */
+ return ( (cpu < ncpu) ? CPU_ENABLED : 0) |
+ ((cpu == 0) ? CPU_BOOTPROCESSOR : 0x00);
+}
+
+#define MPTABLE_SIG_FLOATING "_MP_"
+#define MPTABLE_OEM "KVMCPU00"
+#define MPTABLE_PRODUCTID "0.1 "
+#define MPTABLE_PCIBUSTYPE "PCI "
+#define MPTABLE_ISABUSTYPE "ISA "
+
+#define MPTABLE_STRNCPY(d, s) memcpy(d, s, sizeof(d))
+
+/* It should be more than enough */
+#define MPTABLE_MAX_SIZE (32 << 20)
+
+/*
+ * Too many cpus will require x2apic mode
+ * and rather ACPI support so we limit it
+ * here for a while.
+ */
+#define MPTABLE_MAX_CPUS 255
+
+static void mptable_add_irq_src(struct mpc_intsrc *mpc_intsrc,
+ u16 srcbusid, u16 srcbusirq,
+ u16 dstapic, u16 dstirq)
+{
+ *mpc_intsrc = (struct mpc_intsrc) {
+ .type = MP_INTSRC,
+ .irqtype = mp_INT,
+ .irqflag = MP_IRQDIR_DEFAULT,
+ .srcbus = srcbusid,
+ .srcbusirq = srcbusirq,
+ .dstapic = dstapic,
+ .dstirq = dstirq
+ };
+}
+
+/**
+ * mptable_setup - create mptable and fill guest memory with it
+ */
+int mptable__init(struct kvm *kvm)
+{
+ unsigned long real_mpc_table, real_mpf_intel, size;
+ struct mpf_intel *mpf_intel;
+ struct mpc_table *mpc_table;
+ struct mpc_cpu *mpc_cpu;
+ struct mpc_bus *mpc_bus;
+ struct mpc_ioapic *mpc_ioapic;
+ struct mpc_intsrc *mpc_intsrc;
+ struct device_header *dev_hdr;
+
+ const int pcibusid = 0;
+ const int isabusid = 1;
+
+ unsigned int i, nentries = 0, ncpus = kvm->nrcpus;
+ unsigned int ioapicid;
+ void *last_addr;
+
+ /* That is where MP table will be in guest memory */
+ real_mpc_table = ALIGN(MB_BIOS_BEGIN + bios_rom_size, 16);
+
+ if (ncpus > MPTABLE_MAX_CPUS) {
+ pr_warning("Too many cpus: %d limited to %d",
+ ncpus, MPTABLE_MAX_CPUS);
+ ncpus = MPTABLE_MAX_CPUS;
+ }
+
+ mpc_table = calloc(1, MPTABLE_MAX_SIZE);
+ if (!mpc_table)
+ return -ENOMEM;
+
+ MPTABLE_STRNCPY(mpc_table->signature, MPC_SIGNATURE);
+ MPTABLE_STRNCPY(mpc_table->oem, MPTABLE_OEM);
+ MPTABLE_STRNCPY(mpc_table->productid, MPTABLE_PRODUCTID);
+
+ mpc_table->spec = 4;
+ mpc_table->lapic = APIC_ADDR(0);
+ mpc_table->oemcount = ncpus; /* will be updated again at end */
+
+ /*
+ * CPUs enumeration. Technically speaking we should
+ * ask either host or HV for apic version supported
+ * but for a while we simply put some random value
+ * here.
+ */
+ mpc_cpu = (void *)&mpc_table[1];
+ for (i = 0; i < ncpus; i++) {
+ mpc_cpu->type = MP_PROCESSOR;
+ mpc_cpu->apicid = i;
+ mpc_cpu->apicver = KVM_APIC_VERSION;
+ mpc_cpu->cpuflag = gen_cpu_flag(i, ncpus);
+ mpc_cpu->cpufeature = 0x600; /* some default value */
+ mpc_cpu->featureflag = 0x201; /* some default value */
+ mpc_cpu++;
+ }
+
+ last_addr = (void *)mpc_cpu;
+ nentries += ncpus;
+
+ /*
+ * PCI buses.
+ * FIXME: Some callback here to obtain real number
+ * of PCI buses present in system.
+ */
+ mpc_bus = last_addr;
+ mpc_bus->type = MP_BUS;
+ mpc_bus->busid = pcibusid;
+ MPTABLE_STRNCPY(mpc_bus->bustype, MPTABLE_PCIBUSTYPE);
+
+ last_addr = (void *)&mpc_bus[1];
+ nentries++;
+
+ /*
+ * ISA bus.
+ * FIXME: Same issue as for PCI bus.
+ */
+ mpc_bus = last_addr;
+ mpc_bus->type = MP_BUS;
+ mpc_bus->busid = isabusid;
+ MPTABLE_STRNCPY(mpc_bus->bustype, MPTABLE_ISABUSTYPE);
+
+ last_addr = (void *)&mpc_bus[1];
+ nentries++;
+
+ /*
+ * IO-APIC chip.
+ */
+ ioapicid = ncpus + 1;
+ mpc_ioapic = last_addr;
+ mpc_ioapic->type = MP_IOAPIC;
+ mpc_ioapic->apicid = ioapicid;
+ mpc_ioapic->apicver = KVM_APIC_VERSION;
+ mpc_ioapic->flags = MPC_APIC_USABLE;
+ mpc_ioapic->apicaddr = IOAPIC_ADDR(0);
+
+ last_addr = (void *)&mpc_ioapic[1];
+ nentries++;
+
+ /*
+ * IRQ sources.
+ * Also note we use PCI irqs here, no for ISA bus yet.
+ */
+
+ dev_hdr = device__first_dev(DEVICE_BUS_PCI);
+ while (dev_hdr) {
+ unsigned char srcbusirq;
+ struct pci_device_header *pci_hdr = dev_hdr->data;
+
+ srcbusirq = (pci_hdr->subsys_id << 2) | (pci_hdr->irq_pin - 1);
+ mpc_intsrc = last_addr;
+ mptable_add_irq_src(mpc_intsrc, pcibusid, srcbusirq, ioapicid, pci_hdr->irq_line);
+
+ last_addr = (void *)&mpc_intsrc[dev_hdr->dev_num];
+ nentries++;
+ dev_hdr = device__next_dev(dev_hdr);
+ }
+
+ /*
+ * Local IRQs assignment (LINT0, LINT1)
+ */
+ mpc_intsrc = last_addr;
+ mpc_intsrc->type = MP_LINTSRC;
+ mpc_intsrc->irqtype = mp_ExtINT;
+ mpc_intsrc->irqtype = mp_INT;
+ mpc_intsrc->irqflag = MP_IRQDIR_DEFAULT;
+ mpc_intsrc->srcbus = isabusid;
+ mpc_intsrc->srcbusirq = 0;
+ mpc_intsrc->dstapic = 0; /* FIXME: BSP apic */
+ mpc_intsrc->dstirq = 0; /* LINT0 */
+
+ last_addr = (void *)&mpc_intsrc[1];
+ nentries++;
+
+ mpc_intsrc = last_addr;
+ mpc_intsrc->type = MP_LINTSRC;
+ mpc_intsrc->irqtype = mp_NMI;
+ mpc_intsrc->irqflag = MP_IRQDIR_DEFAULT;
+ mpc_intsrc->srcbus = isabusid;
+ mpc_intsrc->srcbusirq = 0;
+ mpc_intsrc->dstapic = 0; /* FIXME: BSP apic */
+ mpc_intsrc->dstirq = 1; /* LINT1 */
+
+ last_addr = (void *)&mpc_intsrc[1];
+ nentries++;
+
+ /*
+ * Floating MP table finally.
+ */
+ real_mpf_intel = ALIGN((unsigned long)last_addr - (unsigned long)mpc_table, 16);
+ mpf_intel = (void *)((unsigned long)mpc_table + real_mpf_intel);
+
+ MPTABLE_STRNCPY(mpf_intel->signature, MPTABLE_SIG_FLOATING);
+ mpf_intel->length = 1;
+ mpf_intel->specification= 4;
+ mpf_intel->physptr = (unsigned int)real_mpc_table;
+ mpf_intel->checksum = -mpf_checksum((unsigned char *)mpf_intel, sizeof(*mpf_intel));
+
+ /*
+ * No last_addr inclrement here please, we need last
+ * active position here to compute table size.
+ */
+
+ /*
+ * Don't forget to update header in fixed table.
+ */
+ mpc_table->oemcount = nentries;
+ mpc_table->length = last_addr - (void *)mpc_table;
+ mpc_table->checksum = -mpf_checksum((unsigned char *)mpc_table, mpc_table->length);
+
+
+ /*
+ * We will copy the whole table, no need to separate
+ * floating structure and table itkvm.
+ */
+ size = (unsigned long)mpf_intel + sizeof(*mpf_intel) - (unsigned long)mpc_table;
+
+ /*
+ * The finial check -- never get out of system bios
+ * area. Lets also check for allocated memory overrun,
+ * in real it's late but still usefull.
+ */
+
+ if (size > (unsigned long)(MB_BIOS_END - bios_rom_size) ||
+ size > MPTABLE_MAX_SIZE) {
+ free(mpc_table);
+ pr_err("MP table is too big");
+
+ return -E2BIG;
+ }
+
+ /*
+ * OK, it is time to move it to guest memory.
+ */
+ memcpy(guest_flat_to_host(kvm, real_mpc_table), mpc_table, size);
+
+ free(mpc_table);
+
+ return 0;
+}
+firmware_init(mptable__init);
+
+int mptable__exit(struct kvm *kvm)
+{
+ return 0;
+}
+firmware_exit(mptable__exit);
