Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-lguest

* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-lguest: (45 commits)
  Use "struct boot_params" in example launcher
  Loading bzImage directly.
  Revert lguest magic and use hook in head.S
  Update lguest documentation to reflect the new virtual block device name.
  generalize lgread_u32/lgwrite_u32.
  Example launcher handle guests not being ready for input
  Update example launcher for virtio
  Lguest support for Virtio
  Remove old lguest I/O infrrasructure.
  Remove old lguest bus and drivers.
  Virtio helper routines for a descriptor ringbuffer implementation
  Module autoprobing support for virtio drivers.
  Virtio console driver
  Block driver using virtio.
  Net driver using virtio
  Virtio interface
  Boot with virtual == physical to get closer to native Linux.
  Allow guest to specify syscall vector to use.
  Rename "cr3" to "gpgdir" to avoid x86-specific naming.
  Pagetables to use normal kernel types
  ...

70 files changed, 4822 insertions, 4401 deletions

diff --git a/Documentation/lguest/Makefile b/Documentation/lguest/Makefile
index c0b7a455639..bac037eb1cd 100644
--- a/Documentation/lguest/Makefile
+++ b/Documentation/lguest/Makefile
@@ -1,28 +1,8 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-
-# For those people that have a separate object dir, look there for .config
-KBUILD_OUTPUT := ../..
-ifdef O
-  ifeq ("$(origin O)", "command line")
-    KBUILD_OUTPUT := $(O)
-  endif
-endif
-# We rely on CONFIG_PAGE_OFFSET to know where to put lguest binary.
-include $(KBUILD_OUTPUT)/.config
-LGUEST_GUEST_TOP := ($(CONFIG_PAGE_OFFSET) - 0x08000000)
-
-CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -Wl,-T,lguest.lds
+CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include
 LDLIBS:=-lz
-# Removing this works for some versions of ld.so (eg. Ubuntu Feisty) and
-# not others (eg. FC7).
-LDFLAGS+=-static
-all: lguest.lds lguest
 
-# The linker script on x86 is so complex the only way of creating one
-# which will link our binary in the right place is to mangle the
-# default one.
-lguest.lds:
-	$(LD) --verbose | awk '/^==========/ { PRINT=1; next; } /SIZEOF_HEADERS/ { gsub(/0x[0-9A-F]*/, "$(LGUEST_GUEST_TOP)") } { if (PRINT) print $$0; }' > $@
+all: lguest
 
 clean:
-	rm -f lguest.lds lguest
+	rm -f lguest
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 103e346c8b6..5bdc37f8184 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -1,10 +1,7 @@
 /*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 <stdio.h>
@@ -15,6 +12,7 @@
 #include <stdlib.h>
 #include <elf.h>
 #include <sys/mman.h>
+#include <sys/param.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/wait.h>
@@ -34,7 +32,9 @@
 #include <termios.h>
 #include <getopt.h>
 #include <zlib.h>
-/*L:110 We can ignore the 28 include files we need for this program, but I do
+#include <assert.h>
+#include <sched.h>
+/*L:110 We can ignore the 30 include files we need for this program, but I do
  * want to draw attention to the use of kernel-style types.
  *
  * As Linus said, "C is a Spartan language, and so should your naming be."  I
@@ -45,8 +45,14 @@ typedef unsigned long long u64;
 typedef uint32_t u32;
 typedef uint16_t u16;
 typedef uint8_t u8;
-#include "../../include/linux/lguest_launcher.h"
-#include "../../include/asm-x86/e820_32.h"
+#include "linux/lguest_launcher.h"
+#include "linux/pci_ids.h"
+#include "linux/virtio_config.h"
+#include "linux/virtio_net.h"
+#include "linux/virtio_blk.h"
+#include "linux/virtio_console.h"
+#include "linux/virtio_ring.h"
+#include "asm-x86/bootparam.h"
 /*:*/
 
 #define PAGE_PRESENT 0x7 	/* Present, RW, Execute */
@@ -55,6 +61,10 @@ typedef uint8_t u8;
 #ifndef SIOCBRADDIF
 #define SIOCBRADDIF	0x89a2		/* add interface to bridge      */
 #endif
+/* We can have up to 256 pages for devices. */
+#define DEVICE_PAGES 256
+/* This fits nicely in a single 4096-byte page. */
+#define VIRTQUEUE_NUM 127
 
 /*L:120 verbose is both a global flag and a macro.  The C preprocessor allows
  * this, and although I wouldn't recommend it, it works quite nicely here. */
@@ -65,8 +75,10 @@ static bool verbose;
 
 /* The pipe to send commands to the waker process */
 static int waker_fd;
-/* The top of guest physical memory. */
-static u32 top;
+/* The pointer to the start of guest memory. */
+static void *guest_base;
+/* The maximum guest physical address allowed, and maximum possible. */
+static unsigned long guest_limit, guest_max;
 
 /* This is our list of devices. */
 struct device_list
@@ -76,8 +88,17 @@ struct device_list
 	fd_set infds;
 	int max_infd;
 
+	/* Counter to assign interrupt numbers. */
+	unsigned int next_irq;
+
+	/* Counter to print out convenient device numbers. */
+	unsigned int device_num;
+
 	/* The descriptor page for the devices. */
-	struct lguest_device_desc *descs;
+	u8 *descpage;
+
+	/* The tail of the last descriptor. */
+	unsigned int desc_used;
 
 	/* A single linked list of devices. */
 	struct device *dev;
@@ -85,31 +106,111 @@ struct device_list
 	struct device **lastdev;
 };
 
+/* The list of Guest devices, based on command line arguments. */
+static struct device_list devices;
+
 /* The device structure describes a single device. */
 struct device
 {
 	/* The linked-list pointer. */
 	struct device *next;
-	/* The descriptor for this device, as mapped into the Guest. */
+
+	/* The this device's descriptor, as mapped into the Guest. */
 	struct lguest_device_desc *desc;
-	/* The memory page(s) of this device, if any.  Also mapped in Guest. */
-	void *mem;
+
+	/* The name of this device, for --verbose. */
+	const char *name;
 
 	/* If handle_input is set, it wants to be called when this file
 	 * descriptor is ready. */
 	int fd;
 	bool (*handle_input)(int fd, struct device *me);
 
-	/* If handle_output is set, it wants to be called when the Guest sends
-	 * DMA to this key. */
-	unsigned long watch_key;
-	u32 (*handle_output)(int fd, const struct iovec *iov,
-			     unsigned int num, struct device *me);
+	/* Any queues attached to this device */
+	struct virtqueue *vq;
 
 	/* Device-specific data. */
 	void *priv;
 };
 
+/* The virtqueue structure describes a queue attached to a device. */
+struct virtqueue
+{
+	struct virtqueue *next;
+
+	/* Which device owns me. */
+	struct device *dev;
+
+	/* The configuration for this queue. */
+	struct lguest_vqconfig config;
+
+	/* The actual ring of buffers. */
+	struct vring vring;
+
+	/* Last available index we saw. */
+	u16 last_avail_idx;
+
+	/* The routine to call when the Guest pings us. */
+	void (*handle_output)(int fd, struct virtqueue *me);
+};
+
+/* Since guest is UP and we don't run at the same time, we don't need barriers.
+ * But I include them in the code in case others copy it. */
+#define wmb()
+
+/* Convert an iovec element to the given type.
+ *
+ * This is a fairly ugly trick: we need to know the size of the type and
+ * alignment requirement to check the pointer is kosher.  It's also nice to
+ * have the name of the type in case we report failure.
+ *
+ * Typing those three things all the time is cumbersome and error prone, so we
+ * have a macro which sets them all up and passes to the real function. */
+#define convert(iov, type) \
+	((type *)_convert((iov), sizeof(type), __alignof__(type), #type))
+
+static void *_convert(struct iovec *iov, size_t size, size_t align,
+		      const char *name)
+{
+	if (iov->iov_len != size)
+		errx(1, "Bad iovec size %zu for %s", iov->iov_len, name);
+	if ((unsigned long)iov->iov_base % align != 0)
+		errx(1, "Bad alignment %p for %s", iov->iov_base, name);
+	return iov->iov_base;
+}
+
+/* The virtio configuration space is defined to be little-endian.  x86 is
+ * little-endian too, but it's nice to be explicit so we have these helpers. */
+#define cpu_to_le16(v16) (v16)
+#define cpu_to_le32(v32) (v32)
+#define cpu_to_le64(v64) (v64)
+#define le16_to_cpu(v16) (v16)
+#define le32_to_cpu(v32) (v32)
+#define le64_to_cpu(v32) (v64)
+
+/*L:100 The Launcher code itself takes us out into userspace, that scary place
+ * where pointers run wild and free!  Unfortunately, like most userspace
+ * programs, it's quite boring (which is why everyone likes to hack on the
+ * kernel!).  Perhaps if you make up an Lguest Drinking Game at this point, it
+ * will get you through this section.  Or, maybe not.
+ *
+ * The Launcher sets up a big chunk of memory to be the Guest's "physical"
+ * memory and stores it in "guest_base".  In other words, Guest physical ==
+ * Launcher virtual with an offset.
+ *
+ * This can be tough to get your head around, but usually it just means that we
+ * use these trivial conversion functions when the Guest gives us it's
+ * "physical" addresses: */
+static void *from_guest_phys(unsigned long addr)
+{
+	return guest_base + addr;
+}
+
+static unsigned long to_guest_phys(const void *addr)
+{
+	return (addr - guest_base);
+}
+
 /*L:130
  * Loading the Kernel.
  *
@@ -123,43 +224,55 @@ static int open_or_die(const char *name, int flags)
 	return fd;
 }
 
-/* map_zeroed_pages() takes a (page-aligned) address and a number of pages. */
-static void *map_zeroed_pages(unsigned long addr, unsigned int num)
+/* map_zeroed_pages() takes a number of pages. */
+static void *map_zeroed_pages(unsigned int num)
 {
-	/* We cache the /dev/zero file-descriptor so we only open it once. */
-	static int fd = -1;
-
-	if (fd == -1)
-		fd = open_or_die("/dev/zero", O_RDONLY);
+	int fd = open_or_die("/dev/zero", O_RDONLY);
+	void *addr;
 
 	/* We use a private mapping (ie. if we write to the page, it will be
-	 * copied), and obviously we insist that it be mapped where we ask. */
-	if (mmap((void *)addr, getpagesize() * num,
-		 PROT_READ|PROT_WRITE|PROT_EXEC, MAP_FIXED|MAP_PRIVATE, fd, 0)
-	    != (void *)addr)
-		err(1, "Mmaping %u pages of /dev/zero @%p", num, (void *)addr);
-
-	/* Returning the address is just a courtesy: can simplify callers. */
-	return (void *)addr;
+	 * copied). */
+	addr = mmap(NULL, getpagesize() * num,
+		    PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
+	if (addr == MAP_FAILED)
+		err(1, "Mmaping %u pages of /dev/zero", num);
+
+	return addr;
 }
 
-/* To find out where to start we look for the magic Guest string, which marks
- * the code we see in lguest_asm.S.  This is a hack which we are currently
- * plotting to replace with the normal Linux entry point. */
-static unsigned long entry_point(void *start, void *end,
-				 unsigned long page_offset)
+/* Get some more pages for a device. */
+static void *get_pages(unsigned int num)
 {
-	void *p;
+	void *addr = from_guest_phys(guest_limit);
 
-	/* The scan gives us the physical starting address.  We want the
-	 * virtual address in this case, and fortunately, we already figured
-	 * out the physical-virtual difference and passed it here in
-	 * "page_offset". */
-	for (p = start; p < end; p++)
-		if (memcmp(p, "GenuineLguest", strlen("GenuineLguest")) == 0)
-			return (long)p + strlen("GenuineLguest") + page_offset;
+	guest_limit += num * getpagesize();
+	if (guest_limit > guest_max)
+		errx(1, "Not enough memory for devices");
+	return addr;
+}
 
-	err(1, "Is this image a genuine lguest?");
+/* This routine is used to load the kernel or initrd.  It tries mmap, but if
+ * that fails (Plan 9's kernel file isn't nicely aligned on page boundaries),
+ * it falls back to reading the memory in. */
+static void map_at(int fd, void *addr, unsigned long offset, unsigned long len)
+{
+	ssize_t r;
+
+	/* We map writable even though for some segments are marked read-only.
+	 * The kernel really wants to be writable: it patches its own
+	 * instructions.
+	 *
+	 * MAP_PRIVATE means that the page won't be copied until a write is
+	 * done to it.  This allows us to share untouched memory between
+	 * Guests. */
+	if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC,
+		 MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED)
+		return;
+
+	/* pread does a seek and a read in one shot: saves a few lines. */
+	r = pread(fd, addr, len, offset);
+	if (r != len)
+		err(1, "Reading offset %lu len %lu gave %zi", offset, len, r);
 }
 
 /* This routine takes an open vmlinux image, which is in ELF, and maps it into
@@ -167,19 +280,14 @@ static unsigned long entry_point(void *start, void *end,
  * by all modern binaries on Linux including the kernel.
  *
  * The ELF headers give *two* addresses: a physical address, and a virtual
- * address.  The Guest kernel expects to be placed in memory at the physical
- * address, and the page tables set up so it will correspond to that virtual
- * address.  We return the difference between the virtual and physical
- * addresses in the "page_offset" pointer.
+ * address.  We use the physical address; the Guest will map itself to the
+ * virtual address.
  *
  * We return the starting address. */
-static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr,
-			     unsigned long *page_offset)
+static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr)
 {
-	void *addr;
 	Elf32_Phdr phdr[ehdr->e_phnum];
 	unsigned int i;
-	unsigned long start = -1UL, end = 0;
 
 	/* Sanity checks on the main ELF header: an x86 executable with a
 	 * reasonable number of correctly-sized program headers. */
@@ -199,9 +307,6 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr,
 	if (read(elf_fd, phdr, sizeof(phdr)) != sizeof(phdr))
 		err(1, "Reading program headers");
 
-	/* We don't know page_offset yet. */
-	*page_offset = 0;
-
 	/* Try all the headers: there are usually only three.  A read-only one,
 	 * a read-write one, and a "note" section which isn't loadable. */
 	for (i = 0; i < ehdr->e_phnum; i++) {
@@ -212,158 +317,53 @@ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr,
 		verbose("Section %i: size %i addr %p\n",
 			i, phdr[i].p_memsz, (void *)phdr[i].p_paddr);
 
-		/* We expect a simple linear address space: every segment must
-		 * have the same difference between virtual (p_vaddr) and
-		 * physical (p_paddr) address. */
-		if (!*page_offset)
-			*page_offset = phdr[i].p_vaddr - phdr[i].p_paddr;
-		else if (*page_offset != phdr[i].p_vaddr - phdr[i].p_paddr)
-			errx(1, "Page offset of section %i different", i);
-
-		/* We track the first and last address we mapped, so we can
-		 * tell entry_point() where to scan. */
-		if (phdr[i].p_paddr < start)
-			start = phdr[i].p_paddr;
-		if (phdr[i].p_paddr + phdr[i].p_filesz > end)
-			end = phdr[i].p_paddr + phdr[i].p_filesz;
-
-		/* We map this section of the file at its physical address.  We
-		 * map it read & write even if the header says this segment is
-		 * read-only.  The kernel really wants to be writable: it
-		 * patches its own instructions which would normally be
-		 * read-only.
-		 *
-		 * MAP_PRIVATE means that the page won't be copied until a
-		 * write is done to it.  This allows us to share much of the
-		 * kernel memory between Guests. */
-		addr = mmap((void *)phdr[i].p_paddr,
-			    phdr[i].p_filesz,
-			    PROT_READ|PROT_WRITE|PROT_EXEC,
-			    MAP_FIXED|MAP_PRIVATE,
-			    elf_fd, phdr[i].p_offset);
-		if (addr != (void *)phdr[i].p_paddr)
-			err(1, "Mmaping vmlinux seg %i gave %p not %p",
-			    i, addr, (void *)phdr[i].p_paddr);
+		/* We map this section of the file at its physical address. */
+		map_at(elf_fd, from_guest_phys(phdr[i].p_paddr),
+		       phdr[i].p_offset, phdr[i].p_filesz);
 	}
 
-	return entry_point((void *)start, (void *)end, *page_offset);
+	/* The entry point is given in the ELF header. */
+	return ehdr->e_entry;
 }
 
-/*L:170 Prepare to be SHOCKED and AMAZED.  And possibly a trifle nauseated.
- *
- * We know that CONFIG_PAGE_OFFSET sets what virtual address the kernel expects
- * to be.  We don't know what that option was, but we can figure it out
- * approximately by looking at the addresses in the code.  I chose the common
- * case of reading a memory location into the %eax register:
- *
- *  movl <some-address>, %eax
- *
- * This gets encoded as five bytes: "0xA1 <4-byte-address>".  For example,
- * "0xA1 0x18 0x60 0x47 0xC0" reads the address 0xC0476018 into %eax.
- *
- * In this example can guess that the kernel was compiled with
- * CONFIG_PAGE_OFFSET set to 0xC0000000 (it's always a round number).  If the
- * kernel were larger than 16MB, we might see 0xC1 addresses show up, but our
- * kernel isn't that bloated yet.
- *
- * Unfortunately, x86 has variable-length instructions, so finding this
- * particular instruction properly involves writing a disassembler.  Instead,
- * we rely on statistics.  We look for "0xA1" and tally the different bytes
- * which occur 4 bytes later (the "0xC0" in our example above).  When one of
- * those bytes appears three times, we can be reasonably confident that it
- * forms the start of CONFIG_PAGE_OFFSET.
+/*L:150 A bzImage, unlike an ELF file, is not meant to be loaded.  You're
+ * supposed to jump into it and it will unpack itself.  We used to have to
+ * perform some hairy magic because the unpacking code scared me.
  *
- * This is amazingly reliable. */
-static unsigned long intuit_page_offset(unsigned char *img, unsigned long len)
+ * Fortunately, Jeremy Fitzhardinge convinced me it wasn't that hard and wrote
+ * a small patch to jump over the tricky bits in the Guest, so now we just read
+ * the funky header so we know where in the file to load, and away we go! */
+static unsigned long load_bzimage(int fd)
 {
-	unsigned int i, possibilities[256] = { 0 };
+	struct boot_params boot;
+	int r;
+	/* Modern bzImages get loaded at 1M. */
+	void *p = from_guest_phys(0x100000);
 
-	for (i = 0; i + 4 < len; i++) {
-		/* mov 0xXXXXXXXX,%eax */
-		if (img[i] == 0xA1 && ++possibilities[img[i+4]] > 3)
-			return (unsigned long)img[i+4] << 24;
-	}
-	errx(1, "could not determine page offset");
-}
+	/* Go back to the start of the file and read the header.  It should be
+	 * a Linux boot header (see Documentation/i386/boot.txt) */
+	lseek(fd, 0, SEEK_SET);
+	read(fd, &boot, sizeof(boot));
 
-/*L:160 Unfortunately the entire ELF image isn't compressed: the segments
- * which need loading are extracted and compressed raw.  This denies us the
- * information we need to make a fully-general loader. */
-static unsigned long unpack_bzimage(int fd, unsigned long *page_offset)
-{
-	gzFile f;
-	int ret, len = 0;
-	/* A bzImage always gets loaded at physical address 1M.  This is
-	 * actually configurable as CONFIG_PHYSICAL_START, but as the comment
-	 * there says, "Don't change this unless you know what you are doing".
-	 * Indeed. */
-	void *img = (void *)0x100000;
-
-	/* gzdopen takes our file descriptor (carefully pla