diff options
95 files changed, 6980 insertions, 4079 deletions
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c index 9ebcd6ef361..950cde6d6e5 100644 --- a/Documentation/lguest/lguest.c +++ b/Documentation/lguest/lguest.c @@ -1,7 +1,9 @@ -/*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 opens /dev/lguest to tell the kernel - * about the Guest and control it. :*/ +/*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 opens /dev/lguest to tell the kernel about the Guest and + * control it. +:*/ #define _LARGEFILE64_SOURCE #define _GNU_SOURCE #include <stdio.h> @@ -46,13 +48,15 @@ #include "linux/virtio_rng.h" #include "linux/virtio_ring.h" #include "asm/bootparam.h" -/*L:110 We can ignore the 39 include files we need for this program, but I do - * want to draw attention to the use of kernel-style types. +/*L:110 + * We can ignore the 42 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 * like these abbreviations, so we define them here. Note that u64 is always * unsigned long long, which works on all Linux systems: this means that we can - * use %llu in printf for any u64. */ + * use %llu in printf for any u64. + */ typedef unsigned long long u64; typedef uint32_t u32; typedef uint16_t u16; @@ -69,8 +73,10 @@ typedef uint8_t u8; /* This will occupy 3 pages: it must be a power of 2. */ #define VIRTQUEUE_NUM 256 -/*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. */ +/*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. + */ static bool verbose; #define verbose(args...) \ do { if (verbose) printf(args); } while(0) @@ -87,8 +93,7 @@ static int lguest_fd; static unsigned int __thread cpu_id; /* This is our list of devices. */ -struct device_list -{ +struct device_list { /* Counter to assign interrupt numbers. */ unsigned int next_irq; @@ -100,8 +105,7 @@ struct device_list /* A single linked list of devices. */ struct device *dev; - /* And a pointer to the last device for easy append and also for - * configuration appending. */ + /* And a pointer to the last device for easy append. */ struct device *lastdev; }; @@ -109,8 +113,7 @@ struct device_list static struct device_list devices; /* The device structure describes a single device. */ -struct device -{ +struct device { /* The linked-list pointer. */ struct device *next; @@ -135,8 +138,7 @@ struct device }; /* The virtqueue structure describes a queue attached to a device. */ -struct virtqueue -{ +struct virtqueue { struct virtqueue *next; /* Which device owns me. */ @@ -168,20 +170,24 @@ static char **main_args; /* The original tty settings to restore on exit. */ static struct termios orig_term; -/* We have to be careful with barriers: our devices are all run in separate +/* + * We have to be careful with barriers: our devices are all run in separate * threads and so we need to make sure that changes visible to the Guest happen - * in precise order. */ + * in precise order. + */ #define wmb() __asm__ __volatile__("" : : : "memory") #define mb() __asm__ __volatile__("" : : : "memory") -/* Convert an iovec element to the given type. +/* + * 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. */ + * 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)) @@ -198,8 +204,10 @@ static void *_convert(struct iovec *iov, size_t size, size_t align, /* Wrapper for the last available index. Makes it easier to change. */ #define lg_last_avail(vq) ((vq)->last_avail_idx) -/* 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. */ +/* + * 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) @@ -241,11 +249,12 @@ static u8 *get_feature_bits(struct device *dev) + dev->num_vq * sizeof(struct lguest_vqconfig); } -/*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. +/*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 == @@ -253,7 +262,8 @@ static u8 *get_feature_bits(struct device *dev) * * 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: */ + * "physical" addresses: + */ static void *from_guest_phys(unsigned long addr) { return guest_base + addr; @@ -268,7 +278,8 @@ static unsigned long to_guest_phys(const void *addr) * Loading the Kernel. * * We start with couple of simple helper routines. open_or_die() avoids - * error-checking code cluttering the callers: */ + * error-checking code cluttering the callers: + */ static int open_or_die(const char *name, int flags) { int fd = open(name, flags); @@ -283,12 +294,19 @@ static void *map_zeroed_pages(unsigned int num) 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). */ + /* + * We use a private mapping (ie. if we write to the page, it will be + * 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); + + /* + * One neat mmap feature is that you can close the fd, and it + * stays mapped. + */ close(fd); return addr; @@ -305,20 +323,24 @@ static void *get_pages(unsigned int num) return addr; } -/* This routine is used to load the kernel or initrd. It tries mmap, but if +/* + * 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. */ + * 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. + /* + * 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. */ + * Guests. + */ if (mmap(addr, len, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_FIXED|MAP_PRIVATE, fd, offset) != MAP_FAILED) return; @@ -329,7 +351,8 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long 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 +/* + * This routine takes an open vmlinux image, which is in ELF, and maps it into * the Guest memory. ELF = Embedded Linking Format, which is the format used * by all modern binaries on Linux including the kernel. * @@ -337,23 +360,28 @@ static void map_at(int fd, void *addr, unsigned long offset, unsigned long len) * address. We use the physical address; the Guest will map itself to the * virtual address. * - * We return the starting address. */ + * We return the starting address. + */ static unsigned long map_elf(int elf_fd, const Elf32_Ehdr *ehdr) { Elf32_Phdr phdr[ehdr->e_phnum]; unsigned int i; - /* Sanity checks on the main ELF header: an x86 executable with a - * reasonable number of correctly-sized program headers. */ + /* + * Sanity checks on the main ELF header: an x86 executable with a + * reasonable number of correctly-sized program headers. + */ if (ehdr->e_type != ET_EXEC || ehdr->e_machine != EM_386 || ehdr->e_phentsize != sizeof(Elf32_Phdr) || ehdr->e_phnum < 1 || ehdr->e_phnum > 65536U/sizeof(Elf32_Phdr)) errx(1, "Malformed elf header"); - /* An ELF executable contains an ELF header and a number of "program" + /* + * |