mirrors/qemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
fae6941629
qemu/nbd.c
Paolo Bonzini fae6941629 qemu-nbd: more robust handling of invalid requests 
Fail invalid requests with EINVAL instead of dropping them into
the void.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2011-12-22 11:53:58 +01:00

748 lines
19 KiB
C
Raw Blame History

/*
* Copyright (C) 2005 Anthony Liguori <anthony@codemonkey.ws>
*
* Network Block Device
*
* 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; under version 2 of the License.
*
* 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/>.
*/
#include "nbd.h"
#include "block.h"
#include <errno.h>
#include <string.h>
#ifndef _WIN32
#include <sys/ioctl.h>
#endif
#if defined(__sun__) || defined(__HAIKU__)
#include <sys/ioccom.h>
#endif
#include <ctype.h>
#include <inttypes.h>
#ifdef __linux__
#include <linux/fs.h>
#endif
#include "qemu_socket.h"
//#define DEBUG_NBD
#ifdef DEBUG_NBD
#define TRACE(msg, ...) do { \
LOG(msg, ## __VA_ARGS__); \
} while(0)
#else
#define TRACE(msg, ...) \
do { } while (0)
#endif
#define LOG(msg, ...) do { \
fprintf(stderr, "%s:%s():L%d: " msg "\n", \
__FILE__, __FUNCTION__, __LINE__, ## __VA_ARGS__); \
} while(0)
/* This is all part of the "official" NBD API */
#define NBD_REPLY_SIZE (4 + 4 + 8)
#define NBD_REQUEST_MAGIC 0x25609513
#define NBD_REPLY_MAGIC 0x67446698
#define NBD_SET_SOCK _IO(0xab, 0)
#define NBD_SET_BLKSIZE _IO(0xab, 1)
#define NBD_SET_SIZE _IO(0xab, 2)
#define NBD_DO_IT _IO(0xab, 3)
#define NBD_CLEAR_SOCK _IO(0xab, 4)
#define NBD_CLEAR_QUE _IO(0xab, 5)
#define NBD_PRINT_DEBUG _IO(0xab, 6)
#define NBD_SET_SIZE_BLOCKS _IO(0xab, 7)
#define NBD_DISCONNECT _IO(0xab, 8)
#define NBD_SET_TIMEOUT _IO(0xab, 9)
#define NBD_SET_FLAGS _IO(0xab, 10)
#define NBD_OPT_EXPORT_NAME (1 << 0)
/* That's all folks */
#define read_sync(fd, buffer, size) nbd_wr_sync(fd, buffer, size, true)
#define write_sync(fd, buffer, size) nbd_wr_sync(fd, buffer, size, false)
size_t nbd_wr_sync(int fd, void *buffer, size_t size, bool do_read)
{
size_t offset = 0;
if (qemu_in_coroutine()) {
if (do_read) {
return qemu_co_recv(fd, buffer, size);
} else {
return qemu_co_send(fd, buffer, size);
}
}
while (offset < size) {
ssize_t len;
if (do_read) {
len = qemu_recv(fd, buffer + offset, size - offset, 0);
} else {
len = send(fd, buffer + offset, size - offset, 0);
}
if (len == -1)
errno = socket_error();
/* recoverable error */
if (len == -1 && (errno == EAGAIN || errno == EINTR)) {
continue;
}
/* eof */
if (len == 0) {
break;
}
/* unrecoverable error */
if (len == -1) {
return 0;
}
offset += len;
}
return offset;
}
static void combine_addr(char *buf, size_t len, const char* address,
uint16_t port)
{
/* If the address-part contains a colon, it's an IPv6 IP so needs [] */
if (strstr(address, ":")) {
snprintf(buf, len, "[%s]:%u", address, port);
} else {
snprintf(buf, len, "%s:%u", address, port);
}
}
int tcp_socket_outgoing(const char *address, uint16_t port)
{
char address_and_port[128];
combine_addr(address_and_port, 128, address, port);
return tcp_socket_outgoing_spec(address_and_port);
}
int tcp_socket_outgoing_spec(const char *address_and_port)
{
return inet_connect(address_and_port, SOCK_STREAM);
}
int tcp_socket_incoming(const char *address, uint16_t port)
{
char address_and_port[128];
combine_addr(address_and_port, 128, address, port);
return tcp_socket_incoming_spec(address_and_port);
}
int tcp_socket_incoming_spec(const char *address_and_port)
{
char *ostr = NULL;
int olen = 0;
return inet_listen(address_and_port, ostr, olen, SOCK_STREAM, 0);
}
int unix_socket_incoming(const char *path)
{
char *ostr = NULL;
int olen = 0;
return unix_listen(path, ostr, olen);
}
int unix_socket_outgoing(const char *path)
{
return unix_connect(path);
}
/* Basic flow
Server Client
Negotiate
Request
Response
Request
Response
...
...
Request (type == 2)
*/
int nbd_negotiate(int csock, off_t size, uint32_t flags)
{
char buf[8 + 8 + 8 + 128];
/* Negotiate
[ 0 .. 7] passwd ("NBDMAGIC")
[ 8 .. 15] magic (0x00420281861253)
[16 .. 23] size
[24 .. 27] flags
[28 .. 151] reserved (0)
*/
TRACE("Beginning negotiation.");
memcpy(buf, "NBDMAGIC", 8);
cpu_to_be64w((uint64_t*)(buf + 8), 0x00420281861253LL);
cpu_to_be64w((uint64_t*)(buf + 16), size);
cpu_to_be32w((uint32_t*)(buf + 24),
flags | NBD_FLAG_HAS_FLAGS | NBD_FLAG_SEND_TRIM |
NBD_FLAG_SEND_FLUSH | NBD_FLAG_SEND_FUA);
memset(buf + 28, 0, 124);
if (write_sync(csock, buf, sizeof(buf)) != sizeof(buf)) {
LOG("write failed");
errno = EINVAL;
return -1;
}
TRACE("Negotiation succeeded.");
return 0;
}
int nbd_receive_negotiate(int csock, const char *name, uint32_t *flags,
off_t *size, size_t *blocksize)
{
char buf[256];
uint64_t magic, s;
uint16_t tmp;
TRACE("Receiving negotiation.");
if (read_sync(csock, buf, 8) != 8) {
LOG("read failed");
errno = EINVAL;
return -1;
}
buf[8] = '\0';
if (strlen(buf) == 0) {
LOG("server connection closed");
errno = EINVAL;
return -1;
}
TRACE("Magic is %c%c%c%c%c%c%c%c",
qemu_isprint(buf[0]) ? buf[0] : '.',
qemu_isprint(buf[1]) ? buf[1] : '.',
qemu_isprint(buf[2]) ? buf[2] : '.',
qemu_isprint(buf[3]) ? buf[3] : '.',
qemu_isprint(buf[4]) ? buf[4] : '.',
qemu_isprint(buf[5]) ? buf[5] : '.',
qemu_isprint(buf[6]) ? buf[6] : '.',
qemu_isprint(buf[7]) ? buf[7] : '.');
if (memcmp(buf, "NBDMAGIC", 8) != 0) {
LOG("Invalid magic received");
errno = EINVAL;
return -1;
}
if (read_sync(csock, &magic, sizeof(magic)) != sizeof(magic)) {
LOG("read failed");
errno = EINVAL;
return -1;
}
magic = be64_to_cpu(magic);
TRACE("Magic is 0x%" PRIx64, magic);
if (name) {
uint32_t reserved = 0;
uint32_t opt;
uint32_t namesize;
TRACE("Checking magic (opts_magic)");
if (magic != 0x49484156454F5054LL) {
LOG("Bad magic received");
errno = EINVAL;
return -1;
}
if (read_sync(csock, &tmp, sizeof(tmp)) != sizeof(tmp)) {
LOG("flags read failed");
errno = EINVAL;
return -1;
}
*flags = be16_to_cpu(tmp) << 16;
/* reserved for future use */
if (write_sync(csock, &reserved, sizeof(reserved)) !=
sizeof(reserved)) {
LOG("write failed (reserved)");
errno = EINVAL;
return -1;
}
/* write the export name */
magic = cpu_to_be64(magic);
if (write_sync(csock, &magic, sizeof(magic)) != sizeof(magic)) {
LOG("write failed (magic)");
errno = EINVAL;
return -1;
}
opt = cpu_to_be32(NBD_OPT_EXPORT_NAME);
if (write_sync(csock, &opt, sizeof(opt)) != sizeof(opt)) {
LOG("write failed (opt)");
errno = EINVAL;
return -1;
}
namesize = cpu_to_be32(strlen(name));
if (write_sync(csock, &namesize, sizeof(namesize)) !=
sizeof(namesize)) {
LOG("write failed (namesize)");
errno = EINVAL;
return -1;
}
if (write_sync(csock, (char*)name, strlen(name)) != strlen(name)) {
LOG("write failed (name)");
errno = EINVAL;
return -1;
}
} else {
TRACE("Checking magic (cli_magic)");
if (magic != 0x00420281861253LL) {
LOG("Bad magic received");
errno = EINVAL;
return -1;
}
}
if (read_sync(csock, &s, sizeof(s)) != sizeof(s)) {
LOG("read failed");
errno = EINVAL;
return -1;
}
*size = be64_to_cpu(s);
*blocksize = 1024;
TRACE("Size is %" PRIu64, *size);
if (!name) {
if (read_sync(csock, flags, sizeof(*flags)) != sizeof(*flags)) {
LOG("read failed (flags)");
errno = EINVAL;
return -1;
}
*flags = be32_to_cpup(flags);
} else {
if (read_sync(csock, &tmp, sizeof(tmp)) != sizeof(tmp)) {
LOG("read failed (tmp)");
errno = EINVAL;
return -1;
}
*flags |= be32_to_cpu(tmp);
}
if (read_sync(csock, &buf, 124) != 124) {
LOG("read failed (buf)");
errno = EINVAL;
return -1;
}
return 0;
}
#ifdef __linux__
int nbd_init(int fd, int csock, uint32_t flags, off_t size, size_t blocksize)
{
TRACE("Setting NBD socket");
if (ioctl(fd, NBD_SET_SOCK, csock) == -1) {
int serrno = errno;
LOG("Failed to set NBD socket");
errno = serrno;
return -1;
}
TRACE("Setting block size to %lu", (unsigned long)blocksize);
if (ioctl(fd, NBD_SET_BLKSIZE, blocksize) == -1) {
int serrno = errno;
LOG("Failed setting NBD block size");
errno = serrno;
return -1;
}
TRACE("Setting size to %zd block(s)", (size_t)(size / blocksize));
if (ioctl(fd, NBD_SET_SIZE_BLOCKS, size / blocksize) == -1) {
int serrno = errno;
LOG("Failed setting size (in blocks)");
errno = serrno;
return -1;
}
if (flags & NBD_FLAG_READ_ONLY) {
int read_only = 1;
TRACE("Setting readonly attribute");
if (ioctl(fd, BLKROSET, (unsigned long) &read_only) < 0) {
int serrno = errno;
LOG("Failed setting read-only attribute");
errno = serrno;
return -1;
}
}
if (ioctl(fd, NBD_SET_FLAGS, flags) < 0
&& errno != ENOTTY) {
int serrno = errno;
LOG("Failed setting flags");
errno = serrno;
return -1;
}
TRACE("Negotiation ended");
return 0;
}
int nbd_disconnect(int fd)
{
ioctl(fd, NBD_CLEAR_QUE);
ioctl(fd, NBD_DISCONNECT);
ioctl(fd, NBD_CLEAR_SOCK);
return 0;
}
int nbd_client(int fd)
{
int ret;
int serrno;
TRACE("Doing NBD loop");
ret = ioctl(fd, NBD_DO_IT);
if (ret == -1 && errno == EPIPE) {
/* NBD_DO_IT normally returns EPIPE when someone has disconnected
* the socket via NBD_DISCONNECT. We do not want to return 1 in
* that case.
*/
ret = 0;
}
serrno = errno;
TRACE("NBD loop returned %d: %s", ret, strerror(serrno));
TRACE("Clearing NBD queue");
ioctl(fd, NBD_CLEAR_QUE);
TRACE("Clearing NBD socket");
ioctl(fd, NBD_CLEAR_SOCK);
errno = serrno;
return ret;
}
#else
int nbd_init(int fd, int csock, uint32_t flags, off_t size, size_t blocksize)
{
errno = ENOTSUP;
return -1;
}
int nbd_disconnect(int fd)
{
errno = ENOTSUP;
return -1;
}
int nbd_client(int fd)
{
errno = ENOTSUP;
return -1;
}
#endif
int nbd_send_request(int csock, struct nbd_request *request)
{
uint8_t buf[4 + 4 + 8 + 8 + 4];
cpu_to_be32w((uint32_t*)buf, NBD_REQUEST_MAGIC);
cpu_to_be32w((uint32_t*)(buf + 4), request->type);
cpu_to_be64w((uint64_t*)(buf + 8), request->handle);
cpu_to_be64w((uint64_t*)(buf + 16), request->from);
cpu_to_be32w((uint32_t*)(buf + 24), request->len);
TRACE("Sending request to client: "
"{ .from = %" PRIu64", .len = %u, .handle = %" PRIu64", .type=%i}",
request->from, request->len, request->handle, request->type);
if (write_sync(csock, buf, sizeof(buf)) != sizeof(buf)) {
LOG("writing to socket failed");
errno = EINVAL;
return -1;
}
return 0;
}
static int nbd_receive_request(int csock, struct nbd_request *request)
{
uint8_t buf[4 + 4 + 8 + 8 + 4];
uint32_t magic;
if (read_sync(csock, buf, sizeof(buf)) != sizeof(buf)) {
LOG("read failed");
errno = EINVAL;
return -1;
}
/* Request
[ 0 .. 3] magic (NBD_REQUEST_MAGIC)
[ 4 .. 7] type (0 == READ, 1 == WRITE)
[ 8 .. 15] handle
[16 .. 23] from
[24 .. 27] len
*/
magic = be32_to_cpup((uint32_t*)buf);
request->type = be32_to_cpup((uint32_t*)(buf + 4));
request->handle = be64_to_cpup((uint64_t*)(buf + 8));
request->from = be64_to_cpup((uint64_t*)(buf + 16));
request->len = be32_to_cpup((uint32_t*)(buf + 24));
TRACE("Got request: "
"{ magic = 0x%x, .type = %d, from = %" PRIu64" , len = %u }",
magic, request->type, request->from, request->len);
if (magic != NBD_REQUEST_MAGIC) {
LOG("invalid magic (got 0x%x)", magic);
errno = EINVAL;
return -1;
}
return 0;
}
int nbd_receive_reply(int csock, struct nbd_reply *reply)
{
uint8_t buf[NBD_REPLY_SIZE];
uint32_t magic;
memset(buf, 0xAA, sizeof(buf));
if (read_sync(csock, buf, sizeof(buf)) != sizeof(buf)) {
LOG("read failed");
errno = EINVAL;
return -1;
}
/* Reply
[ 0 .. 3] magic (NBD_REPLY_MAGIC)
[ 4 .. 7] error (0 == no error)
[ 7 .. 15] handle
*/
magic = be32_to_cpup((uint32_t*)buf);
reply->error = be32_to_cpup((uint32_t*)(buf + 4));
reply->handle = be64_to_cpup((uint64_t*)(buf + 8));
TRACE("Got reply: "
"{ magic = 0x%x, .error = %d, handle = %" PRIu64" }",
magic, reply->error, reply->handle);
if (magic != NBD_REPLY_MAGIC) {
LOG("invalid magic (got 0x%x)", magic);
errno = EINVAL;
return -1;
}
return 0;
}
static int nbd_send_reply(int csock, struct nbd_reply *reply)
{
uint8_t buf[4 + 4 + 8];
/* Reply
[ 0 .. 3] magic (NBD_REPLY_MAGIC)
[ 4 .. 7] error (0 == no error)
[ 7 .. 15] handle
*/
cpu_to_be32w((uint32_t*)buf, NBD_REPLY_MAGIC);
cpu_to_be32w((uint32_t*)(buf + 4), reply->error);
cpu_to_be64w((uint64_t*)(buf + 8), reply->handle);
TRACE("Sending response to client");
if (write_sync(csock, buf, sizeof(buf)) != sizeof(buf)) {
LOG("writing to socket failed");
errno = EINVAL;
return -1;
}
return 0;
}
static int nbd_do_send_reply(int csock, struct nbd_reply *reply,
uint8_t *data, int len)
{
int rc, ret;
if (!len) {
rc = nbd_send_reply(csock, reply);
if (rc == -1) {
rc = -errno;
}
} else {
socket_set_cork(csock, 1);
rc = nbd_send_reply(csock, reply);
if (rc != -1) {
ret = write_sync(csock, data, len);
if (ret != len) {
errno = EIO;
rc = -1;
}
}
if (rc == -1) {
rc = -errno;
}
socket_set_cork(csock, 0);
}
return rc;
}
int nbd_trip(BlockDriverState *bs, int csock, off_t size,
uint64_t dev_offset, uint32_t nbdflags,
uint8_t *data)
{
struct nbd_request request;
struct nbd_reply reply;
int ret;
TRACE("Reading request.");
if (nbd_receive_request(csock, &request) == -1)
return -1;
reply.handle = request.handle;
reply.error = 0;
if (request.len > NBD_BUFFER_SIZE) {
LOG("len (%u) is larger than max len (%u)",
request.len, NBD_BUFFER_SIZE);
goto invalid_request;
}
if ((request.from + request.len) < request.from) {
LOG("integer overflow detected! "
"you're probably being attacked");
goto invalid_request;
}
if ((request.from + request.len) > size) {
LOG("From: %" PRIu64 ", Len: %u, Size: %" PRIu64
", Offset: %" PRIu64 "\n",
request.from, request.len, (uint64_t)size, dev_offset);
LOG("requested operation past EOF--bad client?");
goto invalid_request;
}
TRACE("Decoding type");
switch (request.type & NBD_CMD_MASK_COMMAND) {
case NBD_CMD_READ:
TRACE("Request type is READ");
ret = bdrv_read(bs, (request.from + dev_offset) / 512,
data, request.len / 512);
if (ret < 0) {
LOG("reading from file failed");
reply.error = -ret;
goto error_reply;
}
TRACE("Read %u byte(s)", request.len);
if (nbd_do_send_reply(csock, &reply, data, request.len) < 0)
return -1;
break;
case NBD_CMD_WRITE:
TRACE("Request type is WRITE");
TRACE("Reading %u byte(s)", request.len);
if (read_sync(csock, data, request.len) != request.len) {
LOG("reading from socket failed");
errno = EINVAL;
return -1;
}
if (nbdflags & NBD_FLAG_READ_ONLY) {
TRACE("Server is read-only, return error");
reply.error = EROFS;
goto error_reply;
}
TRACE("Writing to device");
ret = bdrv_write(bs, (request.from + dev_offset) / 512,
data, request.len / 512);
if (ret < 0) {
LOG("writing to file failed");
reply.error = -ret;
goto error_reply;
}
if (request.type & NBD_CMD_FLAG_FUA) {
ret = bdrv_flush(bs);
if (ret < 0) {
LOG("flush failed");
reply.error = -ret;
goto error_reply;
}
}
if (nbd_do_send_reply(csock, &reply, NULL, 0) < 0)
return -1;
break;
case NBD_CMD_DISC:
TRACE("Request type is DISCONNECT");
errno = 0;
return 1;
case NBD_CMD_FLUSH:
TRACE("Request type is FLUSH");
ret = bdrv_flush(bs);
if (ret < 0) {
LOG("flush failed");
reply.error = -ret;
}
if (nbd_do_send_reply(csock, &reply, NULL, 0) < 0)
return -1;
break;
case NBD_CMD_TRIM:
TRACE("Request type is TRIM");
ret = bdrv_discard(bs, (request.from + dev_offset) / 512,
request.len / 512);
if (ret < 0) {
LOG("discard failed");
reply.error = -ret;
}
if (nbd_do_send_reply(csock, &reply, NULL, 0) < 0)
return -1;
break;
default:
LOG("invalid request type (%u) received", request.type);
invalid_request:
reply.error = -EINVAL;
error_reply:
if (nbd_do_send_reply(csock, &reply, NULL, 0) == -1)
return -1;
break;
}
TRACE("Request/Reply complete");
return 0;
}
Reference in New Issue View Git Blame Copy Permalink