diff --git a/Documentation/lguest/extract b/Documentation/lguest/extract new file mode 100644 index 00000000000..7730bb6e4b9 --- /dev/null +++ b/Documentation/lguest/extract @@ -0,0 +1,58 @@ +#! /bin/sh + +set -e + +PREFIX=$1 +shift + +trap 'rm -r $TMPDIR' 0 +TMPDIR=`mktemp -d` + +exec 3>/dev/null +for f; do + while IFS=" +" read -r LINE; do + case "$LINE" in + *$PREFIX:[0-9]*:\**) + NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` + if [ -f $TMPDIR/$NUM ]; then + echo "$TMPDIR/$NUM already exits prior to $f" + exit 1 + fi + exec 3>>$TMPDIR/$NUM + echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM + /bin/echo "$LINE" | sed -e "s/$PREFIX:[0-9]*//" -e "s/:\*/*/" >&3 + ;; + *$PREFIX:[0-9]*) + NUM=`echo "$LINE" | sed "s/.*$PREFIX:\([0-9]*\).*/\1/"` + if [ -f $TMPDIR/$NUM ]; then + echo "$TMPDIR/$NUM already exits prior to $f" + exit 1 + fi + exec 3>>$TMPDIR/$NUM + echo $f | sed 's,\.\./,,g' > $TMPDIR/.$NUM + /bin/echo "$LINE" | sed "s/$PREFIX:[0-9]*//" >&3 + ;; + *:\**) + /bin/echo "$LINE" | sed -e "s/:\*/*/" -e "s,/\*\*/,," >&3 + echo >&3 + exec 3>/dev/null + ;; + *) + /bin/echo "$LINE" >&3 + ;; + esac + done < $f + echo >&3 + exec 3>/dev/null +done + +LASTFILE="" +for f in $TMPDIR/*; do + if [ "$LASTFILE" != $(cat $TMPDIR/.$(basename $f) ) ]; then + LASTFILE=$(cat $TMPDIR/.$(basename $f) ) + echo "[ $LASTFILE ]" + fi + cat $f +done + diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 62a8133393e..fc1bf70abfb 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -1,5 +1,10 @@ -/* Simple program to layout "physical" memory for new lguest guest. - * Linked high to avoid likely physical memory. */ +/*P:100 This is the Launcher code, a simple program which lays out the + * "physical" memory for the new Guest by mapping the kernel image and the + * virtual devices, then reads repeatedly from /dev/lguest to run the Guest. + * + * The only trick: the Makefile links it at a high address so it will be clear + * of the guest memory region. It means that each Guest cannot have more than + * about 2.5G of memory on a normally configured Host. :*/ #define _LARGEFILE64_SOURCE #define _GNU_SOURCE #include diff --git a/drivers/lguest/Makefile b/drivers/lguest/Makefile index 55382c7d799..e5047471c33 100644 --- a/drivers/lguest/Makefile +++ b/drivers/lguest/Makefile @@ -5,3 +5,15 @@ obj-$(CONFIG_LGUEST_GUEST) += lguest.o lguest_asm.o lguest_bus.o obj-$(CONFIG_LGUEST) += lg.o lg-y := core.o hypercalls.o page_tables.o interrupts_and_traps.o \ segments.o io.o lguest_user.o switcher.o + +Preparation Preparation!: PREFIX=P +Guest: PREFIX=G +Drivers: PREFIX=D +Launcher: PREFIX=L +Host: PREFIX=H +Switcher: PREFIX=S +Mastery: PREFIX=M +Beer: + @for f in Preparation Guest Drivers Launcher Host Switcher Mastery; do echo "{==- $$f -==}"; make -s $$f; done; echo "{==-==}" +Preparation Preparation! Guest Drivers Launcher Host Switcher Mastery: + @sh ../../Documentation/lguest/extract $(PREFIX) `find ../../* -name '*.[chS]' -wholename '*lguest*'` diff --git a/drivers/lguest/README b/drivers/lguest/README new file mode 100644 index 00000000000..b7db39a64c6 --- /dev/null +++ b/drivers/lguest/README @@ -0,0 +1,47 @@ +Welcome, friend reader, to lguest. + +Lguest is an adventure, with you, the reader, as Hero. I can't think of many +5000-line projects which offer both such capability and glimpses of future +potential; it is an exciting time to be delving into the source! + +But be warned; this is an arduous journey of several hours or more! And as we +know, all true Heroes are driven by a Noble Goal. Thus I offer a Beer (or +equivalent) to anyone I meet who has completed this documentation. + +So get comfortable and keep your wits about you (both quick and humorous). +Along your way to the Noble Goal, you will also gain masterly insight into +lguest, and hypervisors and x86 virtualization in general. + +Our Quest is in seven parts: (best read with C highlighting turned on) + +I) Preparation + - In which our potential hero is flown quickly over the landscape for a + taste of its scope. Suitable for the armchair coders and other such + persons of faint constitution. + +II) Guest + - Where we encounter the first tantalising wisps of code, and come to + understand the details of the life of a Guest kernel. + +III) Drivers + - Whereby the Guest finds its voice and become useful, and our + understanding of the Guest is completed. + +IV) Launcher + - Where we trace back to the creation of the Guest, and thus begin our + understanding of the Host. + +V) Host + - Where we master the Host code, through a long and tortuous journey. + Indeed, it is here that our hero is tested in the Bit of Despair. + +VI) Switcher + - Where our understanding of the intertwined nature of Guests and Hosts + is completed. + +VII) Mastery + - Where our fully fledged hero grapples with the Great Question: + "What next?" + +make Preparation! +Rusty Russell. diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index ce909ec5749..2cea0c80c99 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -1,5 +1,8 @@ -/* World's simplest hypervisor, to test paravirt_ops and show - * unbelievers that virtualization is the future. Plus, it's fun! */ +/*P:400 This contains run_guest() which actually calls into the Host<->Guest + * Switcher and analyzes the return, such as determining if the Guest wants the + * Host to do something. This file also contains useful helper routines, and a + * couple of non-obvious setup and teardown pieces which were implemented after + * days of debugging pain. :*/ #include #include #include diff --git a/drivers/lguest/hypercalls.c b/drivers/lguest/hypercalls.c index ea52ca451f7..fb546b04644 100644 --- a/drivers/lguest/hypercalls.c +++ b/drivers/lguest/hypercalls.c @@ -1,5 +1,10 @@ -/* Actual hypercalls, which allow guests to actually do something. - Copyright (C) 2006 Rusty Russell IBM Corporation +/*P:500 Just as userspace programs request kernel operations through a system + * call, the Guest requests Host operations through a "hypercall". You might + * notice this nomenclature doesn't really follow any logic, but the name has + * been around for long enough that we're stuck with it. As you'd expect, this + * code is basically a one big switch statement. :*/ + +/* Copyright (C) 2006 Rusty Russell IBM Corporation 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 diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c index bee029bb2c7..b2647974e1a 100644 --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -1,3 +1,16 @@ +/*P:800 Interrupts (traps) are complicated enough to earn their own file. + * There are three classes of interrupts: + * + * 1) Real hardware interrupts which occur while we're running the Guest, + * 2) Interrupts for virtual devices attached to the Guest, and + * 3) Traps and faults from the Guest. + * + * Real hardware interrupts must be delivered to the Host, not the Guest. + * Virtual interrupts must be delivered to the Guest, but we make them look + * just like real hardware would deliver them. Traps from the Guest can be set + * up to go directly back into the Guest, but sometimes the Host wants to see + * them first, so we also have a way of "reflecting" them into the Guest as if + * they had been delivered to it directly. :*/ #include #include "lg.h" diff --git a/drivers/lguest/io.c b/drivers/lguest/io.c index c8eb7926699..d2f02f0653c 100644 --- a/drivers/lguest/io.c +++ b/drivers/lguest/io.c @@ -1,5 +1,9 @@ -/* Simple I/O model for guests, based on shared memory. - * Copyright (C) 2006 Rusty Russell IBM Corporation +/*P:300 The I/O mechanism in lguest is simple yet flexible, allowing the Guest + * to talk to the Launcher or directly to another Guest. It uses familiar + * concepts of DMA and interrupts, plus some neat code stolen from + * futexes... :*/ + +/* Copyright (C) 2006 Rusty Russell IBM Corporation * * 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 diff --git a/drivers/lguest/lguest.c b/drivers/lguest/lguest.c index 18dade06d4a..e7d128312b2 100644 --- a/drivers/lguest/lguest.c +++ b/drivers/lguest/lguest.c @@ -1,6 +1,32 @@ -/* - * Lguest specific paravirt-ops implementation +/*P:010 + * A hypervisor allows multiple Operating Systems to run on a single machine. + * To quote David Wheeler: "Any problem in computer science can be solved with + * another layer of indirection." * + * We keep things simple in two ways. First, we start with a normal Linux + * kernel and insert a module (lg.ko) which allows us to run other Linux + * kernels the same way we'd run processes. We call the first kernel the Host, + * and the others the Guests. The program which sets up and configures Guests + * (such as the example in Documentation/lguest/lguest.c) is called the + * Launcher. + * + * Secondly, we only run specially modified Guests, not normal kernels. When + * you set CONFIG_LGUEST to 'y' or 'm', this automatically sets + * CONFIG_LGUEST_GUEST=y, which compiles this file into the kernel so it knows + * how to be a Guest. This means that you can use the same kernel you boot + * normally (ie. as a Host) as a Guest. + * + * These Guests know that they cannot do privileged operations, such as disable + * interrupts, and that they have to ask the Host to do such things explicitly. + * This file consists of all the replacements for such low-level native + * hardware operations: these special Guest versions call the Host. + * + * So how does the kernel know it's a Guest? The Guest starts at a special + * entry point marked with a magic string, which sets up a few things then + * calls here. We replace the native functions in "struct paravirt_ops" + * with our Guest versions, then boot like normal. :*/ + +/* * Copyright (C) 2006, Rusty Russell IBM Corporation. * * This program is free software; you can redistribute it and/or modify diff --git a/drivers/lguest/lguest_bus.c b/drivers/lguest/lguest_bus.c index 18d6ab21a43..9a22d199502 100644 --- a/drivers/lguest/lguest_bus.c +++ b/drivers/lguest/lguest_bus.c @@ -1,3 +1,6 @@ +/*P:050 Lguest guests use a very simple bus for devices. It's a simple array + * of device descriptors contained just above the top of normal memory. The + * lguest bus is 80% tedious boilerplate code. :*/ #include #include #include diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index e90d7a783da..6ae86f20ce3 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -1,4 +1,9 @@ -/* Userspace control of the guest, via /dev/lguest. */ +/*P:200 This contains all the /dev/lguest code, whereby the userspace launcher + * controls and communicates with the Guest. For example, the first write will + * tell us the memory size, pagetable, entry point and kernel address offset. + * A read will run the Guest until a signal is pending (-EINTR), or the Guest + * does a DMA out to the Launcher. Writes are also used to get a DMA buffer + * registered by the Guest and to send the Guest an interrupt. :*/ #include #include #include diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c index 1b0ba09b126..f9ca50d8046 100644 --- a/drivers/lguest/page_tables.c +++ b/drivers/lguest/page_tables.c @@ -1,5 +1,11 @@ -/* Shadow page table operations. - * Copyright (C) Rusty Russell IBM Corporation 2006. +/*P:700 The pagetable code, on the other hand, still shows the scars of + * previous encounters. It's functional, and as neat as it can be in the + * circumstances, but be wary, for these things are subtle and break easily. + * The Guest provides a virtual to physical mapping, but we can neither trust + * it nor use it: we verify and convert it here to point the hardware to the + * actual Guest pages when running the Guest. :*/ + +/* Copyright (C) Rusty Russell IBM Corporation 2006. * GPL v2 and any later version */ #include #include diff --git a/drivers/lguest/segments.c b/drivers/lguest/segments.c index 1b2cfe89dcd..c4fc7293b84 100644 --- a/drivers/lguest/segments.c +++ b/drivers/lguest/segments.c @@ -1,3 +1,14 @@ +/*P:600 The x86 architecture has segments, which involve a table of descriptors + * which can be used to do funky things with virtual address interpretation. + * We originally used to use segments so the Guest couldn't alter the + * Guest<->Host Switcher, and then we had to trim Guest segments, and restore + * for userspace per-thread segments, but trim again for on userspace->kernel + * transitions... This nightmarish creation was contained within this file, + * where we knew not to tread without heavy armament and a change of underwear. + * + * In these modern times, the segment handling code consists of simple sanity + * checks, and the worst you'll experience reading this code is butterfly-rash + * from frolicking through its parklike serenity. :*/ #include "lg.h" static int desc_ok(const struct desc_struct *gdt) diff --git a/drivers/lguest/switcher.S b/drivers/lguest/switcher.S index eadd4cc299d..e7cb8c12355 100644 --- a/drivers/lguest/switcher.S +++ b/drivers/lguest/switcher.S @@ -1,10 +1,11 @@ -/* This code sits at 0xFFC00000 to do the low-level guest<->host switch. +/*P:900 This is the Switcher: code which sits at 0xFFC00000 to do the low-level + * Guest<->Host switch. It is as simple as it can be made, but it's naturally + * very specific to x86. + * + * You have now completed Preparation. If this has whet your appetite; if you + * are feeling invigorated and refreshed then the next, more challenging stage + * can be found in "make Guest". :*/ - There is are two pages above us for this CPU (struct lguest_pages). - The second page (struct lguest_ro_state) becomes read-only after the - context switch. The first page (the stack for traps) remains writable, - but while we're in here, the guest cannot be running. -*/ #include #include #include "lg.h"