summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAnand Avati <avati@redhat.com>2013-03-06 01:11:59 -0800
committerAnand Avati <avati@redhat.com>2013-09-03 11:25:33 -0700
commit0d60175bd684cf6a14f750579d82dbd1ba97fcbc (patch)
tree1571f530548196006526442f3fc027cb623bb6fa
parent7dbfbfd3694e02b90e8f3ce509f5279da1523a02 (diff)
contrib/qemu: Import qemu block source code
This qemu block format source code and its minimal dependency files will be used in the next patch to implement a qemu-block format translator. Change-Id: Ic87638972f7ea9b3df84d7a0539512a250c11c1c BUG: 986775 Signed-off-by: Anand Avati <avati@redhat.com> Reviewed-on: http://review.gluster.org/5366 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Brian Foster <bfoster@redhat.com>
-rw-r--r--contrib/qemu/block.c4604
-rw-r--r--contrib/qemu/block/qcow.c914
-rw-r--r--contrib/qemu/block/qcow2-cache.c323
-rw-r--r--contrib/qemu/block/qcow2-cluster.c1478
-rw-r--r--contrib/qemu/block/qcow2-refcount.c1374
-rw-r--r--contrib/qemu/block/qcow2-snapshot.c660
-rw-r--r--contrib/qemu/block/qcow2.c1825
-rw-r--r--contrib/qemu/block/qcow2.h437
-rw-r--r--contrib/qemu/block/qed-check.c248
-rw-r--r--contrib/qemu/block/qed-cluster.c165
-rw-r--r--contrib/qemu/block/qed-gencb.c32
-rw-r--r--contrib/qemu/block/qed-l2-cache.c187
-rw-r--r--contrib/qemu/block/qed-table.c296
-rw-r--r--contrib/qemu/block/qed.c1596
-rw-r--r--contrib/qemu/block/qed.h344
-rw-r--r--contrib/qemu/block/snapshot.c157
-rw-r--r--contrib/qemu/config-host.h74
-rw-r--r--contrib/qemu/include/block/aio.h247
-rw-r--r--contrib/qemu/include/block/block.h443
-rw-r--r--contrib/qemu/include/block/block_int.h421
-rw-r--r--contrib/qemu/include/block/blockjob.h278
-rw-r--r--contrib/qemu/include/block/coroutine.h218
-rw-r--r--contrib/qemu/include/block/coroutine_int.h53
-rw-r--r--contrib/qemu/include/block/snapshot.h53
-rw-r--r--contrib/qemu/include/config.h2
-rw-r--r--contrib/qemu/include/exec/cpu-common.h124
-rw-r--r--contrib/qemu/include/exec/hwaddr.h20
-rw-r--r--contrib/qemu/include/exec/poison.h63
-rw-r--r--contrib/qemu/include/fpu/softfloat.h641
-rw-r--r--contrib/qemu/include/glib-compat.h27
-rw-r--r--contrib/qemu/include/migration/migration.h157
-rw-r--r--contrib/qemu/include/migration/qemu-file.h266
-rw-r--r--contrib/qemu/include/migration/vmstate.h740
-rw-r--r--contrib/qemu/include/monitor/monitor.h104
-rw-r--r--contrib/qemu/include/monitor/readline.h55
-rw-r--r--contrib/qemu/include/qapi/error.h85
-rw-r--r--contrib/qemu/include/qapi/qmp/json-lexer.h51
-rw-r--r--contrib/qemu/include/qapi/qmp/json-parser.h24
-rw-r--r--contrib/qemu/include/qapi/qmp/json-streamer.h40
-rw-r--r--contrib/qemu/include/qapi/qmp/qbool.h29
-rw-r--r--contrib/qemu/include/qapi/qmp/qdict.h69
-rw-r--r--contrib/qemu/include/qapi/qmp/qerror.h249
-rw-r--r--contrib/qemu/include/qapi/qmp/qfloat.h29
-rw-r--r--contrib/qemu/include/qapi/qmp/qint.h28
-rw-r--r--contrib/qemu/include/qapi/qmp/qjson.h29
-rw-r--r--contrib/qemu/include/qapi/qmp/qlist.h63
-rw-r--r--contrib/qemu/include/qapi/qmp/qobject.h112
-rw-r--r--contrib/qemu/include/qapi/qmp/qstring.h36
-rw-r--r--contrib/qemu/include/qapi/qmp/types.h25
-rw-r--r--contrib/qemu/include/qemu-common.h478
-rw-r--r--contrib/qemu/include/qemu/aes.h45
-rw-r--r--contrib/qemu/include/qemu/atomic.h202
-rw-r--r--contrib/qemu/include/qemu/bitmap.h222
-rw-r--r--contrib/qemu/include/qemu/bitops.h276
-rw-r--r--contrib/qemu/include/qemu/bswap.h478
-rw-r--r--contrib/qemu/include/qemu/compiler.h55
-rw-r--r--contrib/qemu/include/qemu/error-report.h46
-rw-r--r--contrib/qemu/include/qemu/event_notifier.h46
-rw-r--r--contrib/qemu/include/qemu/hbitmap.h209
-rw-r--r--contrib/qemu/include/qemu/host-utils.h322
-rw-r--r--contrib/qemu/include/qemu/iov.h115
-rw-r--r--contrib/qemu/include/qemu/main-loop.h311
-rw-r--r--contrib/qemu/include/qemu/module.h40
-rw-r--r--contrib/qemu/include/qemu/notify.h72
-rw-r--r--contrib/qemu/include/qemu/option.h157
-rw-r--r--contrib/qemu/include/qemu/option_int.h54
-rw-r--r--contrib/qemu/include/qemu/osdep.h218
-rw-r--r--contrib/qemu/include/qemu/queue.h414
-rw-r--r--contrib/qemu/include/qemu/sockets.h83
-rw-r--r--contrib/qemu/include/qemu/thread-posix.h28
-rw-r--r--contrib/qemu/include/qemu/thread.h56
-rw-r--r--contrib/qemu/include/qemu/timer.h305
-rw-r--r--contrib/qemu/include/qemu/typedefs.h69
-rw-r--r--contrib/qemu/include/sysemu/os-posix.h52
-rw-r--r--contrib/qemu/include/sysemu/sysemu.h200
-rw-r--r--contrib/qemu/include/trace.h6
-rw-r--r--contrib/qemu/qapi-types.h2746
-rw-r--r--contrib/qemu/qemu-coroutine-lock.c178
-rw-r--r--contrib/qemu/qemu-coroutine-sleep.c39
-rw-r--r--contrib/qemu/qemu-coroutine.c135
-rw-r--r--contrib/qemu/qmp-commands.h204
-rw-r--r--contrib/qemu/qobject/json-lexer.c373
-rw-r--r--contrib/qemu/qobject/json-parser.c724
-rw-r--r--contrib/qemu/qobject/json-streamer.c122
-rw-r--r--contrib/qemu/qobject/qbool.c68
-rw-r--r--contrib/qemu/qobject/qdict.c478
-rw-r--r--contrib/qemu/qobject/qerror.c156
-rw-r--r--contrib/qemu/qobject/qfloat.c68
-rw-r--r--contrib/qemu/qobject/qint.c67
-rw-r--r--contrib/qemu/qobject/qjson.c282
-rw-r--r--contrib/qemu/qobject/qlist.c170
-rw-r--r--contrib/qemu/qobject/qstring.c149
-rw-r--r--contrib/qemu/trace/generated-tracers.h3759
-rw-r--r--contrib/qemu/util/aes.c1314
-rw-r--r--contrib/qemu/util/bitmap.c256
-rw-r--r--contrib/qemu/util/bitops.c158
-rw-r--r--contrib/qemu/util/cutils.c532
-rw-r--r--contrib/qemu/util/error.c120
-rw-r--r--contrib/qemu/util/hbitmap.c402
-rw-r--r--contrib/qemu/util/hexdump.c37
-rw-r--r--contrib/qemu/util/iov.c426
-rw-r--r--contrib/qemu/util/module.c81
-rw-r--r--contrib/qemu/util/oslib-posix.c243
-rw-r--r--contrib/qemu/util/qemu-error.c225
-rw-r--r--contrib/qemu/util/qemu-option.c1126
-rw-r--r--contrib/qemu/util/qemu-thread-posix.c327
-rw-r--r--contrib/qemu/util/unicode.c100
107 files changed, 39119 insertions, 0 deletions
diff --git a/contrib/qemu/block.c b/contrib/qemu/block.c
new file mode 100644
index 00000000000..b56024113b8
--- /dev/null
+++ b/contrib/qemu/block.c
@@ -0,0 +1,4604 @@
+/*
+ * QEMU System Emulator block driver
+ *
+ * Copyright (c) 2003 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "config-host.h"
+#include "qemu-common.h"
+#include "trace.h"
+#include "monitor/monitor.h"
+#include "block/block_int.h"
+#include "block/blockjob.h"
+#include "qemu/module.h"
+#include "qapi/qmp/qjson.h"
+#include "sysemu/sysemu.h"
+#include "qemu/notify.h"
+#include "block/coroutine.h"
+#include "qmp-commands.h"
+#include "qemu/timer.h"
+
+#ifdef CONFIG_BSD
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/queue.h>
+#ifndef __DragonFly__
+#include <sys/disk.h>
+#endif
+#endif
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+
+#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
+
+typedef enum {
+ BDRV_REQ_COPY_ON_READ = 0x1,
+ BDRV_REQ_ZERO_WRITE = 0x2,
+} BdrvRequestFlags;
+
+static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load);
+static BlockDriverAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+static BlockDriverAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ QEMUIOVector *iov);
+static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ QEMUIOVector *iov);
+static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
+ BdrvRequestFlags flags);
+static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
+ BdrvRequestFlags flags);
+static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov,
+ int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque,
+ bool is_write);
+static void coroutine_fn bdrv_co_do_rw(void *opaque);
+static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors);
+
+static bool bdrv_exceed_bps_limits(BlockDriverState *bs, int nb_sectors,
+ bool is_write, double elapsed_time, uint64_t *wait);
+static bool bdrv_exceed_iops_limits(BlockDriverState *bs, bool is_write,
+ double elapsed_time, uint64_t *wait);
+static bool bdrv_exceed_io_limits(BlockDriverState *bs, int nb_sectors,
+ bool is_write, int64_t *wait);
+
+static QTAILQ_HEAD(, BlockDriverState) bdrv_states =
+ QTAILQ_HEAD_INITIALIZER(bdrv_states);
+
+static QLIST_HEAD(, BlockDriver) bdrv_drivers =
+ QLIST_HEAD_INITIALIZER(bdrv_drivers);
+
+/* If non-zero, use only whitelisted block drivers */
+static int use_bdrv_whitelist;
+
+#ifdef _WIN32
+static int is_windows_drive_prefix(const char *filename)
+{
+ return (((filename[0] >= 'a' && filename[0] <= 'z') ||
+ (filename[0] >= 'A' && filename[0] <= 'Z')) &&
+ filename[1] == ':');
+}
+
+int is_windows_drive(const char *filename)
+{
+ if (is_windows_drive_prefix(filename) &&
+ filename[2] == '\0')
+ return 1;
+ if (strstart(filename, "\\\\.\\", NULL) ||
+ strstart(filename, "//./", NULL))
+ return 1;
+ return 0;
+}
+#endif
+
+/* throttling disk I/O limits */
+void bdrv_io_limits_disable(BlockDriverState *bs)
+{
+ bs->io_limits_enabled = false;
+
+ while (qemu_co_queue_next(&bs->throttled_reqs));
+
+ if (bs->block_timer) {
+ qemu_del_timer(bs->block_timer);
+ qemu_free_timer(bs->block_timer);
+ bs->block_timer = NULL;
+ }
+
+ bs->slice_start = 0;
+ bs->slice_end = 0;
+}
+
+static void bdrv_block_timer(void *opaque)
+{
+ BlockDriverState *bs = opaque;
+
+ qemu_co_queue_next(&bs->throttled_reqs);
+}
+
+void bdrv_io_limits_enable(BlockDriverState *bs)
+{
+ qemu_co_queue_init(&bs->throttled_reqs);
+ bs->block_timer = qemu_new_timer_ns(vm_clock, bdrv_block_timer, bs);
+ bs->io_limits_enabled = true;
+}
+
+bool bdrv_io_limits_enabled(BlockDriverState *bs)
+{
+ BlockIOLimit *io_limits = &bs->io_limits;
+ return io_limits->bps[BLOCK_IO_LIMIT_READ]
+ || io_limits->bps[BLOCK_IO_LIMIT_WRITE]
+ || io_limits->bps[BLOCK_IO_LIMIT_TOTAL]
+ || io_limits->iops[BLOCK_IO_LIMIT_READ]
+ || io_limits->iops[BLOCK_IO_LIMIT_WRITE]
+ || io_limits->iops[BLOCK_IO_LIMIT_TOTAL];
+}
+
+static void bdrv_io_limits_intercept(BlockDriverState *bs,
+ bool is_write, int nb_sectors)
+{
+ int64_t wait_time = -1;
+
+ if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
+ qemu_co_queue_wait(&bs->throttled_reqs);
+ }
+
+ /* In fact, we hope to keep each request's timing, in FIFO mode. The next
+ * throttled requests will not be dequeued until the current request is
+ * allowed to be serviced. So if the current request still exceeds the
+ * limits, it will be inserted to the head. All requests followed it will
+ * be still in throttled_reqs queue.
+ */
+
+ while (bdrv_exceed_io_limits(bs, nb_sectors, is_write, &wait_time)) {
+ qemu_mod_timer(bs->block_timer,
+ wait_time + qemu_get_clock_ns(vm_clock));
+ qemu_co_queue_wait_insert_head(&bs->throttled_reqs);
+ }
+
+ qemu_co_queue_next(&bs->throttled_reqs);
+}
+
+/* check if the path starts with "<protocol>:" */
+static int path_has_protocol(const char *path)
+{
+ const char *p;
+
+#ifdef _WIN32
+ if (is_windows_drive(path) ||
+ is_windows_drive_prefix(path)) {
+ return 0;
+ }
+ p = path + strcspn(path, ":/\\");
+#else
+ p = path + strcspn(path, ":/");
+#endif
+
+ return *p == ':';
+}
+
+int path_is_absolute(const char *path)
+{
+#ifdef _WIN32
+ /* specific case for names like: "\\.\d:" */
+ if (is_windows_drive(path) || is_windows_drive_prefix(path)) {
+ return 1;
+ }
+ return (*path == '/' || *path == '\\');
+#else
+ return (*path == '/');
+#endif
+}
+
+/* if filename is absolute, just copy it to dest. Otherwise, build a
+ path to it by considering it is relative to base_path. URL are
+ supported. */
+void path_combine(char *dest, int dest_size,
+ const char *base_path,
+ const char *filename)
+{
+ const char *p, *p1;
+ int len;
+
+ if (dest_size <= 0)
+ return;
+ if (path_is_absolute(filename)) {
+ pstrcpy(dest, dest_size, filename);
+ } else {
+ p = strchr(base_path, ':');
+ if (p)
+ p++;
+ else
+ p = base_path;
+ p1 = strrchr(base_path, '/');
+#ifdef _WIN32
+ {
+ const char *p2;
+ p2 = strrchr(base_path, '\\');
+ if (!p1 || p2 > p1)
+ p1 = p2;
+ }
+#endif
+ if (p1)
+ p1++;
+ else
+ p1 = base_path;
+ if (p1 > p)
+ p = p1;
+ len = p - base_path;
+ if (len > dest_size - 1)
+ len = dest_size - 1;
+ memcpy(dest, base_path, len);
+ dest[len] = '\0';
+ pstrcat(dest, dest_size, filename);
+ }
+}
+
+void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz)
+{
+ if (bs->backing_file[0] == '\0' || path_has_protocol(bs->backing_file)) {
+ pstrcpy(dest, sz, bs->backing_file);
+ } else {
+ path_combine(dest, sz, bs->filename, bs->backing_file);
+ }
+}
+
+void bdrv_register(BlockDriver *bdrv)
+{
+ /* Block drivers without coroutine functions need emulation */
+ if (!bdrv->bdrv_co_readv) {
+ bdrv->bdrv_co_readv = bdrv_co_readv_em;
+ bdrv->bdrv_co_writev = bdrv_co_writev_em;
+
+ /* bdrv_co_readv_em()/brdv_co_writev_em() work in terms of aio, so if
+ * the block driver lacks aio we need to emulate that too.
+ */
+ if (!bdrv->bdrv_aio_readv) {
+ /* add AIO emulation layer */
+ bdrv->bdrv_aio_readv = bdrv_aio_readv_em;
+ bdrv->bdrv_aio_writev = bdrv_aio_writev_em;
+ }
+ }
+
+ QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
+}
+
+/* create a new block device (by default it is empty) */
+BlockDriverState *bdrv_new(const char *device_name)
+{
+ BlockDriverState *bs;
+
+ bs = g_malloc0(sizeof(BlockDriverState));
+ pstrcpy(bs->device_name, sizeof(bs->device_name), device_name);
+ if (device_name[0] != '\0') {
+ QTAILQ_INSERT_TAIL(&bdrv_states, bs, list);
+ }
+ bdrv_iostatus_disable(bs);
+ notifier_list_init(&bs->close_notifiers);
+ notifier_with_return_list_init(&bs->before_write_notifiers);
+
+ return bs;
+}
+
+void bdrv_add_close_notifier(BlockDriverState *bs, Notifier *notify)
+{
+ notifier_list_add(&bs->close_notifiers, notify);
+}
+
+BlockDriver *bdrv_find_format(const char *format_name)
+{
+ BlockDriver *drv1;
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
+ if (!strcmp(drv1->format_name, format_name)) {
+ return drv1;
+ }
+ }
+ return NULL;
+}
+
+static int bdrv_is_whitelisted(BlockDriver *drv, bool read_only)
+{
+ static const char *whitelist_rw[] = {
+ CONFIG_BDRV_RW_WHITELIST
+ };
+ static const char *whitelist_ro[] = {
+ CONFIG_BDRV_RO_WHITELIST
+ };
+ const char **p;
+
+ if (!whitelist_rw[0] && !whitelist_ro[0]) {
+ return 1; /* no whitelist, anything goes */
+ }
+
+ for (p = whitelist_rw; *p; p++) {
+ if (!strcmp(drv->format_name, *p)) {
+ return 1;
+ }
+ }
+ if (read_only) {
+ for (p = whitelist_ro; *p; p++) {
+ if (!strcmp(drv->format_name, *p)) {
+ return 1;
+ }
+ }
+ }
+ return 0;
+}
+
+BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
+ bool read_only)
+{
+ BlockDriver *drv = bdrv_find_format(format_name);
+ return drv && bdrv_is_whitelisted(drv, read_only) ? drv : NULL;
+}
+
+typedef struct CreateCo {
+ BlockDriver *drv;
+ char *filename;
+ QEMUOptionParameter *options;
+ int ret;
+} CreateCo;
+
+static void coroutine_fn bdrv_create_co_entry(void *opaque)
+{
+ CreateCo *cco = opaque;
+ assert(cco->drv);
+
+ cco->ret = cco->drv->bdrv_create(cco->filename, cco->options);
+}
+
+int bdrv_create(BlockDriver *drv, const char* filename,
+ QEMUOptionParameter *options)
+{
+ int ret;
+
+ Coroutine *co;
+ CreateCo cco = {
+ .drv = drv,
+ .filename = g_strdup(filename),
+ .options = options,
+ .ret = NOT_DONE,
+ };
+
+ if (!drv->bdrv_create) {
+ ret = -ENOTSUP;
+ goto out;
+ }
+
+ if (qemu_in_coroutine()) {
+ /* Fast-path if already in coroutine context */
+ bdrv_create_co_entry(&cco);
+ } else {
+ co = qemu_coroutine_create(bdrv_create_co_entry);
+ qemu_coroutine_enter(co, &cco);
+ while (cco.ret == NOT_DONE) {
+ qemu_aio_wait();
+ }
+ }
+
+ ret = cco.ret;
+
+out:
+ g_free(cco.filename);
+ return ret;
+}
+
+int bdrv_create_file(const char* filename, QEMUOptionParameter *options)
+{
+ BlockDriver *drv;
+
+ drv = bdrv_find_protocol(filename, true);
+ if (drv == NULL) {
+ return -ENOENT;
+ }
+
+ return bdrv_create(drv, filename, options);
+}
+
+/*
+ * Create a uniquely-named empty temporary file.
+ * Return 0 upon success, otherwise a negative errno value.
+ */
+int get_tmp_filename(char *filename, int size)
+{
+#ifdef _WIN32
+ char temp_dir[MAX_PATH];
+ /* GetTempFileName requires that its output buffer (4th param)
+ have length MAX_PATH or greater. */
+ assert(size >= MAX_PATH);
+ return (GetTempPath(MAX_PATH, temp_dir)
+ && GetTempFileName(temp_dir, "qem", 0, filename)
+ ? 0 : -GetLastError());
+#else
+ int fd;
+ const char *tmpdir;
+ tmpdir = getenv("TMPDIR");
+ if (!tmpdir)
+ tmpdir = "/tmp";
+ if (snprintf(filename, size, "%s/vl.XXXXXX", tmpdir) >= size) {
+ return -EOVERFLOW;
+ }
+ fd = mkstemp(filename);
+ if (fd < 0) {
+ return -errno;
+ }
+ if (close(fd) != 0) {
+ unlink(filename);
+ return -errno;
+ }
+ return 0;
+#endif
+}
+
+/*
+ * Detect host devices. By convention, /dev/cdrom[N] is always
+ * recognized as a host CDROM.
+ */
+static BlockDriver *find_hdev_driver(const char *filename)
+{
+ int score_max = 0, score;
+ BlockDriver *drv = NULL, *d;
+
+ QLIST_FOREACH(d, &bdrv_drivers, list) {
+ if (d->bdrv_probe_device) {
+ score = d->bdrv_probe_device(filename);
+ if (score > score_max) {
+ score_max = score;
+ drv = d;
+ }
+ }
+ }
+
+ return drv;
+}
+
+BlockDriver *bdrv_find_protocol(const char *filename,
+ bool allow_protocol_prefix)
+{
+ BlockDriver *drv1;
+ char protocol[128];
+ int len;
+ const char *p;
+
+ /* TODO Drivers without bdrv_file_open must be specified explicitly */
+
+ /*
+ * XXX(hch): we really should not let host device detection
+ * override an explicit protocol specification, but moving this
+ * later breaks access to device names with colons in them.
+ * Thanks to the brain-dead persistent naming schemes on udev-
+ * based Linux systems those actually are quite common.
+ */
+ drv1 = find_hdev_driver(filename);
+ if (drv1) {
+ return drv1;
+ }
+
+ if (!path_has_protocol(filename) || !allow_protocol_prefix) {
+ return bdrv_find_format("file");
+ }
+
+ p = strchr(filename, ':');
+ assert(p != NULL);
+ len = p - filename;
+ if (len > sizeof(protocol) - 1)
+ len = sizeof(protocol) - 1;
+ memcpy(protocol, filename, len);
+ protocol[len] = '\0';
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
+ if (drv1->protocol_name &&
+ !strcmp(drv1->protocol_name, protocol)) {
+ return drv1;
+ }
+ }
+ return NULL;
+}
+
+static int find_image_format(BlockDriverState *bs, const char *filename,
+ BlockDriver **pdrv)
+{
+ int score, score_max;
+ BlockDriver *drv1, *drv;
+ uint8_t buf[2048];
+ int ret = 0;
+
+ /* Return the raw BlockDriver * to scsi-generic devices or empty drives */
+ if (bs->sg || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) {
+ drv = bdrv_find_format("raw");
+ if (!drv) {
+ ret = -ENOENT;
+ }
+ *pdrv = drv;
+ return ret;
+ }
+
+ ret = bdrv_pread(bs, 0, buf, sizeof(buf));
+ if (ret < 0) {
+ *pdrv = NULL;
+ return ret;
+ }
+
+ score_max = 0;
+ drv = NULL;
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
+ if (drv1->bdrv_probe) {
+ score = drv1->bdrv_probe(buf, ret, filename);
+ if (score > score_max) {
+ score_max = score;
+ drv = drv1;
+ }
+ }
+ }
+ if (!drv) {
+ ret = -ENOENT;
+ }
+ *pdrv = drv;
+ return ret;
+}
+
+/**
+ * Set the current 'total_sectors' value
+ */
+static int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
+{
+ BlockDriver *drv = bs->drv;
+
+ /* Do not attempt drv->bdrv_getlength() on scsi-generic devices */
+ if (bs->sg)
+ return 0;
+
+ /* query actual device if possible, otherwise just trust the hint */
+ if (drv->bdrv_getlength) {
+ int64_t length = drv->bdrv_getlength(bs);
+ if (length < 0) {
+ return length;
+ }
+ hint = length >> BDRV_SECTOR_BITS;
+ }
+
+ bs->total_sectors = hint;
+ return 0;
+}
+
+/**
+ * Set open flags for a given discard mode
+ *
+ * Return 0 on success, -1 if the discard mode was invalid.
+ */
+int bdrv_parse_discard_flags(const char *mode, int *flags)
+{
+ *flags &= ~BDRV_O_UNMAP;
+
+ if (!strcmp(mode, "off") || !strcmp(mode, "ignore")) {
+ /* do nothing */
+ } else if (!strcmp(mode, "on") || !strcmp(mode, "unmap")) {
+ *flags |= BDRV_O_UNMAP;
+ } else {
+ return -1;
+ }
+
+ return 0;
+}
+
+/**
+ * Set open flags for a given cache mode
+ *
+ * Return 0 on success, -1 if the cache mode was invalid.
+ */
+int bdrv_parse_cache_flags(const char *mode, int *flags)
+{
+ *flags &= ~BDRV_O_CACHE_MASK;
+
+ if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
+ *flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
+ } else if (!strcmp(mode, "directsync")) {
+ *flags |= BDRV_O_NOCACHE;
+ } else if (!strcmp(mode, "writeback")) {
+ *flags |= BDRV_O_CACHE_WB;
+ } else if (!strcmp(mode, "unsafe")) {
+ *flags |= BDRV_O_CACHE_WB;
+ *flags |= BDRV_O_NO_FLUSH;
+ } else if (!strcmp(mode, "writethrough")) {
+ /* this is the default */
+ } else {
+ return -1;
+ }
+
+ return 0;
+}
+
+/**
+ * The copy-on-read flag is actually a reference count so multiple users may
+ * use the feature without worrying about clobbering its previous state.
+ * Copy-on-read stays enabled until all users have called to disable it.
+ */
+void bdrv_enable_copy_on_read(BlockDriverState *bs)
+{
+ bs->copy_on_read++;
+}
+
+void bdrv_disable_copy_on_read(BlockDriverState *bs)
+{
+ assert(bs->copy_on_read > 0);
+ bs->copy_on_read--;
+}
+
+static int bdrv_open_flags(BlockDriverState *bs, int flags)
+{
+ int open_flags = flags | BDRV_O_CACHE_WB;
+
+ /*
+ * Clear flags that are internal to the block layer before opening the
+ * image.
+ */
+ open_flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
+
+ /*
+ * Snapshots should be writable.
+ */
+ if (bs->is_temporary) {
+ open_flags |= BDRV_O_RDWR;
+ }
+
+ return open_flags;
+}
+
+/*
+ * Common part for opening disk images and files
+ *
+ * Removes all processed options from *options.
+ */
+static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
+ QDict *options, int flags, BlockDriver *drv)
+{
+ int ret, open_flags;
+ const char *filename;
+
+ assert(drv != NULL);
+ assert(bs->file == NULL);
+ assert(options != NULL && bs->options != options);
+
+ if (file != NULL) {
+ filename = file->filename;
+ } else {
+ filename = qdict_get_try_str(options, "filename");
+ }
+
+ trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
+
+ /* bdrv_open() with directly using a protocol as drv. This layer is already
+ * opened, so assign it to bs (while file becomes a closed BlockDriverState)
+ * and return immediately. */
+ if (file != NULL && drv->bdrv_file_open) {
+ bdrv_swap(file, bs);
+ return 0;
+ }
+
+ bs->open_flags = flags;
+ bs->buffer_alignment = 512;
+ open_flags = bdrv_open_flags(bs, flags);
+ bs->read_only = !(open_flags & BDRV_O_RDWR);
+
+ if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
+ return -ENOTSUP;
+ }
+
+ assert(bs->copy_on_read == 0); /* bdrv_new() and bdrv_close() make it so */
+ if (!bs->read_only && (flags & BDRV_O_COPY_ON_READ)) {
+ bdrv_enable_copy_on_read(bs);
+ }
+
+ if (filename != NULL) {
+ pstrcpy(bs->filename, sizeof(bs->filename), filename);
+ } else {
+ bs->filename[0] = '\0';
+ }
+
+ bs->drv = drv;
+ bs->opaque = g_malloc0(drv->instance_size);
+
+ bs->enable_write_cache = !!(flags & BDRV_O_CACHE_WB);
+
+ /* Open the image, either directly or using a protocol */
+ if (drv->bdrv_file_open) {
+ assert(file == NULL);
+ assert(drv->bdrv_parse_filename || filename != NULL);
+ ret = drv->bdrv_file_open(bs, options, open_flags);
+ } else {
+ if (file == NULL) {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Can't use '%s' as a "
+ "block driver for the protocol level",
+ drv->format_name);
+ ret = -EINVAL;
+ goto free_and_fail;
+ }
+ assert(file != NULL);
+ bs->file = file;
+ ret = drv->bdrv_open(bs, options, open_flags);
+ }
+
+ if (ret < 0) {
+ goto free_and_fail;
+ }
+
+ ret = refresh_total_sectors(bs, bs->total_sectors);
+ if (ret < 0) {
+ goto free_and_fail;
+ }
+
+#ifndef _WIN32
+ if (bs->is_temporary) {
+ assert(filename != NULL);
+ unlink(filename);
+ }
+#endif
+ return 0;
+
+free_and_fail:
+ bs->file = NULL;
+ g_free(bs->opaque);
+ bs->opaque = NULL;
+ bs->drv = NULL;
+ return ret;
+}
+
+/*
+ * Opens a file using a protocol (file, host_device, nbd, ...)
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict belongs to the block layer
+ * after the call (even on failure), so if the caller intends to reuse the
+ * dictionary, it needs to use QINCREF() before calling bdrv_file_open.
+ */
+int bdrv_file_open(BlockDriverState **pbs, const char *filename,
+ QDict *options, int flags)
+{
+ BlockDriverState *bs;
+ BlockDriver *drv;
+ const char *drvname;
+ bool allow_protocol_prefix = false;
+ int ret;
+
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
+ }
+
+ bs = bdrv_new("");
+ bs->options = options;
+ options = qdict_clone_shallow(options);
+
+ /* Fetch the file name from the options QDict if necessary */
+ if (!filename) {
+ filename = qdict_get_try_str(options, "filename");
+ } else if (filename && !qdict_haskey(options, "filename")) {
+ qdict_put(options, "filename", qstring_from_str(filename));
+ allow_protocol_prefix = true;
+ } else {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Can't specify 'file' and "
+ "'filename' options at the same time");
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ /* Find the right block driver */
+ drvname = qdict_get_try_str(options, "driver");
+ if (drvname) {
+ drv = bdrv_find_whitelisted_format(drvname, !(flags & BDRV_O_RDWR));
+ qdict_del(options, "driver");
+ } else if (filename) {
+ drv = bdrv_find_protocol(filename, allow_protocol_prefix);
+ if (!drv) {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Unknown protocol");
+ }
+ } else {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR,
+ "Must specify either driver or file");
+ drv = NULL;
+ }
+
+ if (!drv) {
+ ret = -ENOENT;
+ goto fail;
+ }
+
+ /* Parse the filename and open it */
+ if (drv->bdrv_parse_filename && filename) {
+ Error *local_err = NULL;
+ drv->bdrv_parse_filename(filename, options, &local_err);
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ ret = -EINVAL;
+ goto fail;
+ }
+ qdict_del(options, "filename");
+ } else if (!drv->bdrv_parse_filename && !filename) {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR,
+ "The '%s' block driver requires a file name",
+ drv->format_name);
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ ret = bdrv_open_common(bs, NULL, options, flags, drv);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Check if any unknown options were used */
+ if (qdict_size(options) != 0) {
+ const QDictEntry *entry = qdict_first(options);
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Block protocol '%s' doesn't "
+ "support the option '%s'",
+ drv->format_name, entry->key);
+ ret = -EINVAL;
+ goto fail;
+ }
+ QDECREF(options);
+
+ bs->growable = 1;
+ *pbs = bs;
+ return 0;
+
+fail:
+ QDECREF(options);
+ if (!bs->drv) {
+ QDECREF(bs->options);
+ }
+ bdrv_delete(bs);
+ return ret;
+}
+
+/*
+ * Opens the backing file for a BlockDriverState if not yet open
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict is transferred to this
+ * function (even on failure), so if the caller intends to reuse the dictionary,
+ * it needs to use QINCREF() before calling bdrv_file_open.
+ */
+int bdrv_open_backing_file(BlockDriverState *bs, QDict *options)
+{
+ char backing_filename[PATH_MAX];
+ int back_flags, ret;
+ BlockDriver *back_drv = NULL;
+
+ if (bs->backing_hd != NULL) {
+ QDECREF(options);
+ return 0;
+ }
+
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
+ }
+
+ bs->open_flags &= ~BDRV_O_NO_BACKING;
+ if (qdict_haskey(options, "file.filename")) {
+ backing_filename[0] = '\0';
+ } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
+ QDECREF(options);
+ return 0;
+ }
+
+ bs->backing_hd = bdrv_new("");
+ bdrv_get_full_backing_filename(bs, backing_filename,
+ sizeof(backing_filename));
+
+ if (bs->backing_format[0] != '\0') {
+ back_drv = bdrv_find_format(bs->backing_format);
+ }
+
+ /* backing files always opened read-only */
+ back_flags = bs->open_flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT);
+
+ ret = bdrv_open(bs->backing_hd,
+ *backing_filename ? backing_filename : NULL, options,
+ back_flags, back_drv);
+ if (ret < 0) {
+ bdrv_delete(bs->backing_hd);
+ bs->backing_hd = NULL;
+ bs->open_flags |= BDRV_O_NO_BACKING;
+ return ret;
+ }
+ return 0;
+}
+
+static void extract_subqdict(QDict *src, QDict **dst, const char *start)
+{
+ const QDictEntry *entry, *next;
+ const char *p;
+
+ *dst = qdict_new();
+ entry = qdict_first(src);
+
+ while (entry != NULL) {
+ next = qdict_next(src, entry);
+ if (strstart(entry->key, start, &p)) {
+ qobject_incref(entry->value);
+ qdict_put_obj(*dst, p, entry->value);
+ qdict_del(src, entry->key);
+ }
+ entry = next;
+ }
+}
+
+/*
+ * Opens a disk image (raw, qcow2, vmdk, ...)
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict belongs to the block layer
+ * after the call (even on failure), so if the caller intends to reuse the
+ * dictionary, it needs to use QINCREF() before calling bdrv_open.
+ */
+int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
+ int flags, BlockDriver *drv)
+{
+ int ret;
+ /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
+ char tmp_filename[PATH_MAX + 1];
+ BlockDriverState *file = NULL;
+ QDict *file_options = NULL;
+
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
+ }
+
+ bs->options = options;
+ options = qdict_clone_shallow(options);
+
+ /* For snapshot=on, create a temporary qcow2 overlay */
+ if (flags & BDRV_O_SNAPSHOT) {
+ BlockDriverState *bs1;
+ int64_t total_size;
+ BlockDriver *bdrv_qcow2;
+ QEMUOptionParameter *create_options;
+ char backing_filename[PATH_MAX];
+
+ if (qdict_size(options) != 0) {
+ error_report("Can't use snapshot=on with driver-specific options");
+ ret = -EINVAL;
+ goto fail;
+ }
+ assert(filename != NULL);
+
+ /* if snapshot, we create a temporary backing file and open it
+ instead of opening 'filename' directly */
+
+ /* if there is a backing file, use it */
+ bs1 = bdrv_new("");
+ ret = bdrv_open(bs1, filename, NULL, 0, drv);
+ if (ret < 0) {
+ bdrv_delete(bs1);
+ goto fail;
+ }
+ total_size = bdrv_getlength(bs1) & BDRV_SECTOR_MASK;
+
+ bdrv_delete(bs1);
+
+ ret = get_tmp_filename(tmp_filename, sizeof(tmp_filename));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Real path is meaningless for protocols */
+ if (path_has_protocol(filename)) {
+ snprintf(backing_filename, sizeof(backing_filename),
+ "%s", filename);
+ } else if (!realpath(filename, backing_filename)) {
+ ret = -errno;
+ goto fail;
+ }
+
+ bdrv_qcow2 = bdrv_find_format("qcow2");
+ create_options = parse_option_parameters("", bdrv_qcow2->create_options,
+ NULL);
+
+ set_option_parameter_int(create_options, BLOCK_OPT_SIZE, total_size);
+ set_option_parameter(create_options, BLOCK_OPT_BACKING_FILE,
+ backing_filename);
+ if (drv) {
+ set_option_parameter(create_options, BLOCK_OPT_BACKING_FMT,
+ drv->format_name);
+ }
+
+ ret = bdrv_create(bdrv_qcow2, tmp_filename, create_options);
+ free_option_parameters(create_options);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ filename = tmp_filename;
+ drv = bdrv_qcow2;
+ bs->is_temporary = 1;
+ }
+
+ /* Open image file without format layer */
+ if (flags & BDRV_O_RDWR) {
+ flags |= BDRV_O_ALLOW_RDWR;
+ }
+
+ extract_subqdict(options, &file_options, "file.");
+
+ ret = bdrv_file_open(&file, filename, file_options,
+ bdrv_open_flags(bs, flags | BDRV_O_UNMAP));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Find the right image format driver */
+ if (!drv) {
+ ret = find_image_format(file, filename, &drv);
+ }
+
+ if (!drv) {
+ goto unlink_and_fail;
+ }
+
+ /* Open the image */
+ ret = bdrv_open_common(bs, file, options, flags, drv);
+ if (ret < 0) {
+ goto unlink_and_fail;
+ }
+
+ if (bs->file != file) {
+ bdrv_delete(file);
+ file = NULL;
+ }
+
+ /* If there is a backing file, use it */
+ if ((flags & BDRV_O_NO_BACKING) == 0) {
+ QDict *backing_options;
+
+ extract_subqdict(options, &backing_options, "backing.");
+ ret = bdrv_open_backing_file(bs, backing_options);
+ if (ret < 0) {
+ goto close_and_fail;
+ }
+ }
+
+ /* Check if any unknown options were used */
+ if (qdict_size(options) != 0) {
+ const QDictEntry *entry = qdict_first(options);
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Block format '%s' used by "
+ "device '%s' doesn't support the option '%s'",
+ drv->format_name, bs->device_name, entry->key);
+
+ ret = -EINVAL;
+ goto close_and_fail;
+ }
+ QDECREF(options);
+
+ if (!bdrv_key_required(bs)) {
+ bdrv_dev_change_media_cb(bs, true);
+ }
+
+ /* throttling disk I/O limits */
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_enable(bs);
+ }
+
+ return 0;
+
+unlink_and_fail:
+ if (file != NULL) {
+ bdrv_delete(file);
+ }
+ if (bs->is_temporary) {
+ unlink(filename);
+ }
+fail:
+ QDECREF(bs->options);
+ QDECREF(options);
+ bs->options = NULL;
+ return ret;
+
+close_and_fail:
+ bdrv_close(bs);
+ QDECREF(options);
+ return ret;
+}
+
+typedef struct BlockReopenQueueEntry {
+ bool prepared;
+ BDRVReopenState state;
+ QSIMPLEQ_ENTRY(BlockReopenQueueEntry) entry;
+} BlockReopenQueueEntry;
+
+/*
+ * Adds a BlockDriverState to a simple queue for an atomic, transactional
+ * reopen of multiple devices.
+ *
+ * bs_queue can either be an existing BlockReopenQueue that has had QSIMPLE_INIT
+ * already performed, or alternatively may be NULL a new BlockReopenQueue will
+ * be created and initialized. This newly created BlockReopenQueue should be
+ * passed back in for subsequent calls that are intended to be of the same
+ * atomic 'set'.
+ *
+ * bs is the BlockDriverState to add to the reopen queue.
+ *
+ * flags contains the open flags for the associated bs
+ *
+ * returns a pointer to bs_queue, which is either the newly allocated
+ * bs_queue, or the existing bs_queue being used.
+ *
+ */
+BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
+ BlockDriverState *bs, int flags)
+{
+ assert(bs != NULL);
+
+ BlockReopenQueueEntry *bs_entry;
+ if (bs_queue == NULL) {
+ bs_queue = g_new0(BlockReopenQueue, 1);
+ QSIMPLEQ_INIT(bs_queue);
+ }
+
+ if (bs->file) {
+ bdrv_reopen_queue(bs_queue, bs->file, flags);
+ }
+
+ bs_entry = g_new0(BlockReopenQueueEntry, 1);
+ QSIMPLEQ_INSERT_TAIL(bs_queue, bs_entry, entry);
+
+ bs_entry->state.bs = bs;
+ bs_entry->state.flags = flags;
+
+ return bs_queue;
+}
+
+/*
+ * Reopen multiple BlockDriverStates atomically & transactionally.
+ *
+ * The queue passed in (bs_queue) must have been built up previous
+ * via bdrv_reopen_queue().
+ *
+ * Reopens all BDS specified in the queue, with the appropriate
+ * flags. All devices are prepared for reopen, and failure of any
+ * device will cause all device changes to be abandonded, and intermediate
+ * data cleaned up.
+ *
+ * If all devices prepare successfully, then the changes are committed
+ * to all devices.
+ *
+ */
+int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp)
+{
+ int ret = -1;
+ BlockReopenQueueEntry *bs_entry, *next;
+ Error *local_err = NULL;
+
+ assert(bs_queue != NULL);
+
+ bdrv_drain_all();
+
+ QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
+ if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, &local_err)) {
+ error_propagate(errp, local_err);
+ goto cleanup;
+ }
+ bs_entry->prepared = true;
+ }
+
+ /* If we reach this point, we have success and just need to apply the
+ * changes
+ */
+ QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
+ bdrv_reopen_commit(&bs_entry->state);
+ }
+
+ ret = 0;
+
+cleanup:
+ QSIMPLEQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
+ if (ret && bs_entry->prepared) {
+ bdrv_reopen_abort(&bs_entry->state);
+ }
+ g_free(bs_entry);
+ }
+ g_free(bs_queue);
+ return ret;
+}
+
+
+/* Reopen a single BlockDriverState with the specified flags. */
+int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp)
+{
+ int ret = -1;
+ Error *local_err = NULL;
+ BlockReopenQueue *queue = bdrv_reopen_queue(NULL, bs, bdrv_flags);
+
+ ret = bdrv_reopen_multiple(queue, &local_err);
+ if (local_err != NULL) {
+ error_propagate(errp, local_err);
+ }
+ return ret;
+}
+
+
+/*
+ * Prepares a BlockDriverState for reopen. All changes are staged in the
+ * 'opaque' field of the BDRVReopenState, which is used and allocated by
+ * the block driver layer .bdrv_reopen_prepare()
+ *
+ * bs is the BlockDriverState to reopen
+ * flags are the new open flags
+ * queue is the reopen queue
+ *
+ * Returns 0 on success, non-zero on error. On error errp will be set
+ * as well.
+ *
+ * On failure, bdrv_reopen_abort() will be called to clean up any data.
+ * It is the responsibility of the caller to then call the abort() or
+ * commit() for any other BDS that have been left in a prepare() state
+ *
+ */
+int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
+ Error **errp)
+{
+ int ret = -1;
+ Error *local_err = NULL;
+ BlockDriver *drv;
+
+ assert(reopen_state != NULL);
+ assert(reopen_state->bs->drv != NULL);
+ drv = reopen_state->bs->drv;
+
+ /* if we are to stay read-only, do not allow permission change
+ * to r/w */
+ if (!(reopen_state->bs->open_flags & BDRV_O_ALLOW_RDWR) &&
+ reopen_state->flags & BDRV_O_RDWR) {
+ error_set(errp, QERR_DEVICE_IS_READ_ONLY,
+ reopen_state->bs->device_name);
+ goto error;
+ }
+
+
+ ret = bdrv_flush(reopen_state->bs);
+ if (ret) {
+ error_set(errp, ERROR_CLASS_GENERIC_ERROR, "Error (%s) flushing drive",
+ strerror(-ret));
+ goto error;
+ }
+
+ if (drv->bdrv_reopen_prepare) {
+ ret = drv->bdrv_reopen_prepare(reopen_state, queue, &local_err);
+ if (ret) {
+ if (local_err != NULL) {
+ error_propagate(errp, local_err);
+ } else {
+ error_setg(errp, "failed while preparing to reopen image '%s'",
+ reopen_state->bs->filename);
+ }
+ goto error;
+ }
+ } else {
+ /* It is currently mandatory to have a bdrv_reopen_prepare()
+ * handler for each supported drv. */
+ error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+ drv->format_name, reopen_state->bs->device_name,
+ "reopening of file");
+ ret = -1;
+ goto error;
+ }
+
+ ret = 0;
+
+error:
+ return ret;
+}
+
+/*
+ * Takes the staged changes for the reopen from bdrv_reopen_prepare(), and
+ * makes them final by swapping the staging BlockDriverState contents into
+ * the active BlockDriverState contents.
+ */
+void bdrv_reopen_commit(BDRVReopenState *reopen_state)
+{
+ BlockDriver *drv;
+
+ assert(reopen_state != NULL);
+ drv = reopen_state->bs->drv;
+ assert(drv != NULL);
+
+ /* If there are any driver level actions to take */
+ if (drv->bdrv_reopen_commit) {
+ drv->bdrv_reopen_commit(reopen_state);
+ }
+
+ /* set BDS specific flags now */
+ reopen_state->bs->open_flags = reopen_state->flags;
+ reopen_state->bs->enable_write_cache = !!(reopen_state->flags &
+ BDRV_O_CACHE_WB);
+ reopen_state->bs->read_only = !(reopen_state->flags & BDRV_O_RDWR);
+}
+
+/*
+ * Abort the reopen, and delete and free the staged changes in
+ * reopen_state
+ */
+void bdrv_reopen_abort(BDRVReopenState *reopen_state)
+{
+ BlockDriver *drv;
+
+ assert(reopen_state != NULL);
+ drv = reopen_state->bs->drv;
+ assert(drv != NULL);
+
+ if (drv->bdrv_reopen_abort) {
+ drv->bdrv_reopen_abort(reopen_state);
+ }
+}
+
+
+void bdrv_close(BlockDriverState *bs)
+{
+ if (bs->job) {
+ block_job_cancel_sync(bs->job);
+ }
+ bdrv_drain_all(); /* complete I/O */
+ bdrv_flush(bs);
+ bdrv_drain_all(); /* in case flush left pending I/O */
+ notifier_list_notify(&bs->close_notifiers, bs);
+
+ if (bs->drv) {
+ if (bs->backing_hd) {
+ bdrv_delete(bs->backing_hd);
+ bs->backing_hd = NULL;
+ }
+ bs->drv->bdrv_close(bs);
+ g_free(bs->opaque);
+#ifdef _WIN32
+ if (bs->is_temporary) {
+ unlink(bs->filename);
+ }
+#endif
+ bs->opaque = NULL;
+ bs->drv = NULL;
+ bs->copy_on_read = 0;
+ bs->backing_file[0] = '\0';
+ bs->backing_format[0] = '\0';
+ bs->total_sectors = 0;
+ bs->encrypted = 0;
+ bs->valid_key = 0;
+ bs->sg = 0;
+ bs->growable = 0;
+ QDECREF(bs->options);
+ bs->options = NULL;
+
+ if (bs->file != NULL) {
+ bdrv_delete(bs->file);
+ bs->file = NULL;
+ }
+ }
+
+ bdrv_dev_change_media_cb(bs, false);
+
+ /*throttling disk I/O limits*/
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_disable(bs);
+ }
+}
+
+void bdrv_close_all(void)
+{
+ BlockDriverState *bs;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ bdrv_close(bs);
+ }
+}
+
+/*
+ * Wait for pending requests to complete across all BlockDriverStates
+ *
+ * This function does not flush data to disk, use bdrv_flush_all() for that
+ * after calling this function.
+ *
+ * Note that completion of an asynchronous I/O operation can trigger any
+ * number of other I/O operations on other devices---for example a coroutine
+ * can be arbitrarily complex and a constant flow of I/O can come until the
+ * coroutine is complete. Because of this, it is not possible to have a
+ * function to drain a single device's I/O queue.
+ */
+void bdrv_drain_all(void)
+{
+ BlockDriverState *bs;
+ bool busy;
+
+ do {
+ busy = qemu_aio_wait();
+
+ /* FIXME: We do not have timer support here, so this is effectively
+ * a busy wait.
+ */
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
+ qemu_co_queue_restart_all(&bs->throttled_reqs);
+ busy = true;
+ }
+ }
+ } while (busy);
+
+ /* If requests are still pending there is a bug somewhere */
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ assert(QLIST_EMPTY(&bs->tracked_requests));
+ assert(qemu_co_queue_empty(&bs->throttled_reqs));
+ }
+}
+
+/* make a BlockDriverState anonymous by removing from bdrv_state list.
+ Also, NULL terminate the device_name to prevent double remove */
+void bdrv_make_anon(BlockDriverState *bs)
+{
+ if (bs->device_name[0] != '\0') {
+ QTAILQ_REMOVE(&bdrv_states, bs, list);
+ }
+ bs->device_name[0] = '\0';
+}
+
+static void bdrv_rebind(BlockDriverState *bs)
+{
+ if (bs->drv && bs->drv->bdrv_rebind) {
+ bs->drv->bdrv_rebind(bs);
+ }
+}
+
+static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
+ BlockDriverState *bs_src)
+{
+ /* move some fields that need to stay attached to the device */
+ bs_dest->open_flags = bs_src->open_flags;
+
+ /* dev info */
+ bs_dest->dev_ops = bs_src->dev_ops;
+ bs_dest->dev_opaque = bs_src->dev_opaque;
+ bs_dest->dev = bs_src->dev;
+ bs_dest->buffer_alignment = bs_src->buffer_alignment;
+ bs_dest->copy_on_read = bs_src->copy_on_read;
+
+ bs_dest->enable_write_cache = bs_src->enable_write_cache;
+
+ /* i/o timing parameters */
+ bs_dest->slice_start = bs_src->slice_start;
+ bs_dest->slice_end = bs_src->slice_end;
+ bs_dest->slice_submitted = bs_src->slice_submitted;
+ bs_dest->io_limits = bs_src->io_limits;
+ bs_dest->throttled_reqs = bs_src->throttled_reqs;
+ bs_dest->block_timer = bs_src->block_timer;
+ bs_dest->io_limits_enabled = bs_src->io_limits_enabled;
+
+ /* r/w error */
+ bs_dest->on_read_error = bs_src->on_read_error;
+ bs_dest->on_write_error = bs_src->on_write_error;
+
+ /* i/o status */
+ bs_dest->iostatus_enabled = bs_src->iostatus_enabled;
+ bs_dest->iostatus = bs_src->iostatus;
+
+ /* dirty bitmap */
+ bs_dest->dirty_bitmap = bs_src->dirty_bitmap;
+
+ /* job */
+ bs_dest->in_use = bs_src->in_use;
+ bs_dest->job = bs_src->job;
+
+ /* keep the same entry in bdrv_states */
+ pstrcpy(bs_dest->device_name, sizeof(bs_dest->device_name),
+ bs_src->device_name);
+ bs_dest->list = bs_src->list;
+}
+
+/*
+ * Swap bs contents for two image chains while they are live,
+ * while keeping required fields on the BlockDriverState that is
+ * actually attached to a device.
+ *
+ * This will modify the BlockDriverState fields, and swap contents
+ * between bs_new and bs_old. Both bs_new and bs_old are modified.
+ *
+ * bs_new is required to be anonymous.
+ *
+ * This function does not create any image files.
+ */
+void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
+{
+ BlockDriverState tmp;
+
+ /* bs_new must be anonymous and shouldn't have anything fancy enabled */
+ assert(bs_new->device_name[0] == '\0');
+ assert(bs_new->dirty_bitmap == NULL);
+ assert(bs_new->job == NULL);
+ assert(bs_new->dev == NULL);
+ assert(bs_new->in_use == 0);
+ assert(bs_new->io_limits_enabled == false);
+ assert(bs_new->block_timer == NULL);
+
+ tmp = *bs_new;
+ *bs_new = *bs_old;
+ *bs_old = tmp;
+
+ /* there are some fields that should not be swapped, move them back */
+ bdrv_move_feature_fields(&tmp, bs_old);
+ bdrv_move_feature_fields(bs_old, bs_new);
+ bdrv_move_feature_fields(bs_new, &tmp);
+
+ /* bs_new shouldn't be in bdrv_states even after the swap! */
+ assert(bs_new->device_name[0] == '\0');
+
+ /* Check a few fields that should remain attached to the device */
+ assert(bs_new->dev == NULL);
+ assert(bs_new->job == NULL);
+ assert(bs_new->in_use == 0);
+ assert(bs_new->io_limits_enabled == false);
+ assert(bs_new->block_timer == NULL);
+
+ bdrv_rebind(bs_new);
+ bdrv_rebind(bs_old);
+}
+
+/*
+ * Add new bs contents at the top of an image chain while the chain is
+ * live, while keeping required fields on the top layer.
+ *
+ * This will modify the BlockDriverState fields, and swap contents
+ * between bs_new and bs_top. Both bs_new and bs_top are modified.
+ *
+ * bs_new is required to be anonymous.
+ *
+ * This function does not create any image files.
+ */
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
+{
+ bdrv_swap(bs_new, bs_top);
+
+ /* The contents of 'tmp' will become bs_top, as we are
+ * swapping bs_new and bs_top contents. */
+ bs_top->backing_hd = bs_new;
+ bs_top->open_flags &= ~BDRV_O_NO_BACKING;
+ pstrcpy(bs_top->backing_file, sizeof(bs_top->backing_file),
+ bs_new->filename);
+ pstrcpy(bs_top->backing_format, sizeof(bs_top->backing_format),
+ bs_new->drv ? bs_new->drv->format_name : "");
+}
+
+void bdrv_delete(BlockDriverState *bs)
+{
+ assert(!bs->dev);
+ assert(!bs->job);
+ assert(!bs->in_use);
+
+ /* remove from list, if necessary */
+ bdrv_make_anon(bs);
+
+ bdrv_close(bs);
+
+ g_free(bs);
+}
+
+int bdrv_attach_dev(BlockDriverState *bs, void *dev)
+/* TODO change to DeviceState *dev when all users are qdevified */
+{
+ if (bs->dev) {
+ return -EBUSY;
+ }
+ bs->dev = dev;
+ bdrv_iostatus_reset(bs);
+ return 0;
+}
+
+/* TODO qdevified devices don't use this, remove when devices are qdevified */
+void bdrv_attach_dev_nofail(BlockDriverState *bs, void *dev)
+{
+ if (bdrv_attach_dev(bs, dev) < 0) {
+ abort();
+ }
+}
+
+void bdrv_detach_dev(BlockDriverState *bs, void *dev)
+/* TODO change to DeviceState *dev when all users are qdevified */
+{
+ assert(bs->dev == dev);
+ bs->dev = NULL;
+ bs->dev_ops = NULL;
+ bs->dev_opaque = NULL;
+ bs->buffer_alignment = 512;
+}
+
+/* TODO change to return DeviceState * when all users are qdevified */
+void *bdrv_get_attached_dev(BlockDriverState *bs)
+{
+ return bs->dev;
+}
+
+void bdrv_set_dev_ops(BlockDriverState *bs, const BlockDevOps *ops,
+ void *opaque)
+{
+ bs->dev_ops = ops;
+ bs->dev_opaque = opaque;
+}
+
+void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
+ enum MonitorEvent ev,
+ BlockErrorAction action, bool is_read)
+{
+ QObject *data;
+ const char *action_str;
+
+ switch (action) {
+ case BDRV_ACTION_REPORT:
+ action_str = "report";
+ break;
+ case BDRV_ACTION_IGNORE:
+ action_str = "ignore";
+ break;
+ case BDRV_ACTION_STOP:
+ action_str = "stop";
+ break;
+ default:
+ abort();
+ }
+
+ data = qobject_from_jsonf("{ 'device': %s, 'action': %s, 'operation': %s }",
+ bdrv->device_name,
+ action_str,
+ is_read ? "read" : "write");
+ monitor_protocol_event(ev, data);
+
+ qobject_decref(data);
+}
+
+static void bdrv_emit_qmp_eject_event(BlockDriverState *bs, bool ejected)
+{
+ QObject *data;
+
+ data = qobject_from_jsonf("{ 'device': %s, 'tray-open': %i }",
+ bdrv_get_device_name(bs), ejected);
+ monitor_protocol_event(QEVENT_DEVICE_TRAY_MOVED, data);
+
+ qobject_decref(data);
+}
+
+static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load)
+{
+ if (bs->dev_ops && bs->dev_ops->change_media_cb) {
+ bool tray_was_closed = !bdrv_dev_is_tray_open(bs);
+ bs->dev_ops->change_media_cb(bs->dev_opaque, load);
+ if (tray_was_closed) {
+ /* tray open */
+ bdrv_emit_qmp_eject_event(bs, true);
+ }
+ if (load) {
+ /* tray close */
+ bdrv_emit_qmp_eject_event(bs, false);
+ }
+ }
+}
+
+bool bdrv_dev_has_removable_media(BlockDriverState *bs)
+{
+ return !bs->dev || (bs->dev_ops && bs->dev_ops->change_media_cb);
+}
+
+void bdrv_dev_eject_request(BlockDriverState *bs, bool force)
+{
+ if (bs->dev_ops && bs->dev_ops->eject_request_cb) {
+ bs->dev_ops->eject_request_cb(bs->dev_opaque, force);
+ }
+}
+
+bool bdrv_dev_is_tray_open(BlockDriverState *bs)
+{
+ if (bs->dev_ops && bs->dev_ops->is_tray_open) {
+ return bs->dev_ops->is_tray_open(bs->dev_opaque);
+ }
+ return false;
+}
+
+static void bdrv_dev_resize_cb(BlockDriverState *bs)
+{
+ if (bs->dev_ops && bs->dev_ops->resize_cb) {
+ bs->dev_ops->resize_cb(bs->dev_opaque);
+ }
+}
+
+bool bdrv_dev_is_medium_locked(BlockDriverState *bs)
+{
+ if (bs->dev_ops && bs->dev_ops->is_medium_locked) {
+ return bs->dev_ops->is_medium_locked(bs->dev_opaque);
+ }
+ return false;
+}
+
+/*
+ * Run consistency checks on an image
+ *
+ * Returns 0 if the check could be completed (it doesn't mean that the image is
+ * free of errors) or -errno when an internal error occurred. The results of the
+ * check are stored in res.
+ */
+int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix)
+{
+ if (bs->drv->bdrv_check == NULL) {
+ return -ENOTSUP;
+ }
+
+ memset(res, 0, sizeof(*res));
+ return bs->drv->bdrv_check(bs, res, fix);
+}
+
+#define COMMIT_BUF_SECTORS 2048
+
+/* commit COW file into the raw image */
+int bdrv_commit(BlockDriverState *bs)
+{
+ BlockDriver *drv = bs->drv;
+ int64_t sector, total_sectors;
+ int n, ro, open_flags;
+ int ret = 0;
+ uint8_t *buf;
+ char filename[PATH_MAX];
+
+ if (!drv)
+ return -ENOMEDIUM;
+
+ if (!bs->backing_hd) {
+ return -ENOTSUP;
+ }
+
+ if (bdrv_in_use(bs) || bdrv_in_use(bs->backing_hd)) {
+ return -EBUSY;
+ }
+
+ ro = bs->backing_hd->read_only;
+ /* Use pstrcpy (not strncpy): filename must be NUL-terminated. */
+ pstrcpy(filename, sizeof(filename), bs->backing_hd->filename);
+ open_flags = bs->backing_hd->open_flags;
+
+ if (ro) {
+ if (bdrv_reopen(bs->backing_hd, open_flags | BDRV_O_RDWR, NULL)) {
+ return -EACCES;
+ }
+ }
+
+ total_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
+ buf = g_malloc(COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE);
+
+ for (sector = 0; sector < total_sectors; sector += n) {
+ if (bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n)) {
+
+ if (bdrv_read(bs, sector, buf, n) != 0) {
+ ret = -EIO;
+ goto ro_cleanup;
+ }
+
+ if (bdrv_write(bs->backing_hd, sector, buf, n) != 0) {
+ ret = -EIO;
+ goto ro_cleanup;
+ }
+ }
+ }
+
+ if (drv->bdrv_make_empty) {
+ ret = drv->bdrv_make_empty(bs);
+ bdrv_flush(bs);
+ }
+
+ /*
+ * Make sure all data we wrote to the backing device is actually
+ * stable on disk.
+ */
+ if (bs->backing_hd)
+ bdrv_flush(bs->backing_hd);
+
+ro_cleanup:
+ g_free(buf);
+
+ if (ro) {
+ /* ignoring error return here */
+ bdrv_reopen(bs->backing_hd, open_flags & ~BDRV_O_RDWR, NULL);
+ }
+
+ return ret;
+}
+
+int bdrv_commit_all(void)
+{
+ BlockDriverState *bs;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ if (bs->drv && bs->backing_hd) {
+ int ret = bdrv_commit(bs);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+ }
+ return 0;
+}
+
+/**
+ * Remove an active request from the tracked requests list
+ *
+ * This function should be called when a tracked request is completing.
+ */
+static void tracked_request_end(BdrvTrackedRequest *req)
+{
+ QLIST_REMOVE(req, list);
+ qemu_co_queue_restart_all(&req->wait_queue);
+}
+
+/**
+ * Add an active request to the tracked requests list
+ */
+static void tracked_request_begin(BdrvTrackedRequest *req,
+ BlockDriverState *bs,
+ int64_t sector_num,
+ int nb_sectors, bool is_write)
+{
+ *req = (BdrvTrackedRequest){
+ .bs = bs,
+ .sector_num = sector_num,
+ .nb_sectors = nb_sectors,
+ .is_write = is_write,
+ .co = qemu_coroutine_self(),
+ };
+
+ qemu_co_queue_init(&req->wait_queue);
+
+ QLIST_INSERT_HEAD(&bs->tracked_requests, req, list);
+}
+
+/**
+ * Round a region to cluster boundaries
+ */
+void bdrv_round_to_clusters(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ int64_t *cluster_sector_num,
+ int *cluster_nb_sectors)
+{
+ BlockDriverInfo bdi;
+
+ if (bdrv_get_info(bs, &bdi) < 0 || bdi.cluster_size == 0) {
+ *cluster_sector_num = sector_num;
+ *cluster_nb_sectors = nb_sectors;
+ } else {
+ int64_t c = bdi.cluster_size / BDRV_SECTOR_SIZE;
+ *cluster_sector_num = QEMU_ALIGN_DOWN(sector_num, c);
+ *cluster_nb_sectors = QEMU_ALIGN_UP(sector_num - *cluster_sector_num +
+ nb_sectors, c);
+ }
+}
+
+static bool tracked_request_overlaps(BdrvTrackedRequest *req,
+ int64_t sector_num, int nb_sectors) {
+ /* aaaa bbbb */
+ if (sector_num >= req->sector_num + req->nb_sectors) {
+ return false;
+ }
+ /* bbbb aaaa */
+ if (req->sector_num >= sector_num + nb_sectors) {
+ return false;
+ }
+ return true;
+}
+
+static void coroutine_fn wait_for_overlapping_requests(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors)
+{
+ BdrvTrackedRequest *req;
+ int64_t cluster_sector_num;
+ int cluster_nb_sectors;
+ bool retry;
+
+ /* If we touch the same cluster it counts as an overlap. This guarantees
+ * that allocating writes will be serialized and not race with each other
+ * for the same cluster. For example, in copy-on-read it ensures that the
+ * CoR read and write operations are atomic and guest writes cannot
+ * interleave between them.
+ */
+ bdrv_round_to_clusters(bs, sector_num, nb_sectors,
+ &cluster_sector_num, &cluster_nb_sectors);
+
+ do {
+ retry = false;
+ QLIST_FOREACH(req, &bs->tracked_requests, list) {
+ if (tracked_request_overlaps(req, cluster_sector_num,
+ cluster_nb_sectors)) {
+ /* Hitting this means there was a reentrant request, for
+ * example, a block driver issuing nested requests. This must
+ * never happen since it means deadlock.
+ */
+ assert(qemu_coroutine_self() != req->co);
+
+ qemu_co_queue_wait(&req->wait_queue);
+ retry = true;
+ break;
+ }
+ }
+ } while (retry);
+}
+
+/*
+ * Return values:
+ * 0 - success
+ * -EINVAL - backing format specified, but no file
+ * -ENOSPC - can't update the backing file because no space is left in the
+ * image file header
+ * -ENOTSUP - format driver doesn't support changing the backing file
+ */
+int bdrv_change_backing_file(BlockDriverState *bs,
+ const char *backing_file, const char *backing_fmt)
+{
+ BlockDriver *drv = bs->drv;
+ int ret;
+
+ /* Backing file format doesn't make sense without a backing file */
+ if (backing_fmt && !backing_file) {
+ return -EINVAL;
+ }
+
+ if (drv->bdrv_change_backing_file != NULL) {
+ ret = drv->bdrv_change_backing_file(bs, backing_file, backing_fmt);
+ } else {
+ ret = -ENOTSUP;
+ }
+
+ if (ret == 0) {
+ pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
+ pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
+ }
+ return ret;
+}
+
+/*
+ * Finds the image layer in the chain that has 'bs' as its backing file.
+ *
+ * active is the current topmost image.
+ *
+ * Returns NULL if bs is not found in active's image chain,
+ * or if active == bs.
+ */
+BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
+ BlockDriverState *bs)
+{
+ BlockDriverState *overlay = NULL;
+ BlockDriverState *intermediate;
+
+ assert(active != NULL);
+ assert(bs != NULL);
+
+ /* if bs is the same as active, then by definition it has no overlay
+ */
+ if (active == bs) {
+ return NULL;
+ }
+
+ intermediate = active;
+ while (intermediate->backing_hd) {
+ if (intermediate->backing_hd == bs) {
+ overlay = intermediate;
+ break;
+ }
+ intermediate = intermediate->backing_hd;
+ }
+
+ return overlay;
+}
+
+typedef struct BlkIntermediateStates {
+ BlockDriverState *bs;
+ QSIMPLEQ_ENTRY(BlkIntermediateStates) entry;
+} BlkIntermediateStates;
+
+
+/*
+ * Drops images above 'base' up to and including 'top', and sets the image
+ * above 'top' to have base as its backing file.
+ *
+ * Requires that the overlay to 'top' is opened r/w, so that the backing file
+ * information in 'bs' can be properly updated.
+ *
+ * E.g., this will convert the following chain:
+ * bottom <- base <- intermediate <- top <- active
+ *
+ * to
+ *
+ * bottom <- base <- active
+ *
+ * It is allowed for bottom==base, in which case it converts:
+ *
+ * base <- intermediate <- top <- active
+ *
+ * to
+ *
+ * base <- active
+ *
+ * Error conditions:
+ * if active == top, that is considered an error
+ *
+ */
+int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
+ BlockDriverState *base)
+{
+ BlockDriverState *intermediate;
+ BlockDriverState *base_bs = NULL;
+ BlockDriverState *new_top_bs = NULL;
+ BlkIntermediateStates *intermediate_state, *next;
+ int ret = -EIO;
+
+ QSIMPLEQ_HEAD(states_to_delete, BlkIntermediateStates) states_to_delete;
+ QSIMPLEQ_INIT(&states_to_delete);
+
+ if (!top->drv || !base->drv) {
+ goto exit;
+ }
+
+ new_top_bs = bdrv_find_overlay(active, top);
+
+ if (new_top_bs == NULL) {
+ /* we could not find the image above 'top', this is an error */
+ goto exit;
+ }
+
+ /* special case of new_top_bs->backing_hd already pointing to base - nothing
+ * to do, no intermediate images */
+ if (new_top_bs->backing_hd == base) {
+ ret = 0;
+ goto exit;
+ }
+
+ intermediate = top;
+
+ /* now we will go down through the list, and add each BDS we find
+ * into our deletion queue, until we hit the 'base'
+ */
+ while (intermediate) {
+ intermediate_state = g_malloc0(sizeof(BlkIntermediateStates));
+ intermediate_state->bs = intermediate;
+ QSIMPLEQ_INSERT_TAIL(&states_to_delete, intermediate_state, entry);
+
+ if (intermediate->backing_hd == base) {
+ base_bs = intermediate->backing_hd;
+ break;
+ }
+ intermediate = intermediate->backing_hd;
+ }
+ if (base_bs == NULL) {
+ /* something went wrong, we did not end at the base. safely
+ * unravel everything, and exit with error */
+ goto exit;
+ }
+
+ /* success - we can delete the intermediate states, and link top->base */
+ ret = bdrv_change_backing_file(new_top_bs, base_bs->filename,
+ base_bs->drv ? base_bs->drv->format_name : "");
+ if (ret) {
+ goto exit;
+ }
+ new_top_bs->backing_hd = base_bs;
+
+
+ QSIMPLEQ_FOREACH_SAFE(intermediate_state, &states_to_delete, entry, next) {
+ /* so that bdrv_close() does not recursively close the chain */
+ intermediate_state->bs->backing_hd = NULL;
+ bdrv_delete(intermediate_state->bs);
+ }
+ ret = 0;
+
+exit:
+ QSIMPLEQ_FOREACH_SAFE(intermediate_state, &states_to_delete, entry, next) {
+ g_free(intermediate_state);
+ }
+ return ret;
+}
+
+
+static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
+ size_t size)
+{
+ int64_t len;
+
+ if (!bdrv_is_inserted(bs))
+ return -ENOMEDIUM;
+
+ if (bs->growable)
+ return 0;
+
+ len = bdrv_getlength(bs);
+
+ if (offset < 0)
+ return -EIO;
+
+ if ((offset > len) || (len - offset < size))
+ return -EIO;
+
+ return 0;
+}
+
+static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors)
+{
+ return bdrv_check_byte_request(bs, sector_num * BDRV_SECTOR_SIZE,
+ nb_sectors * BDRV_SECTOR_SIZE);
+}
+
+typedef struct RwCo {
+ BlockDriverState *bs;
+ int64_t sector_num;
+ int nb_sectors;
+ QEMUIOVector *qiov;
+ bool is_write;
+ int ret;
+} RwCo;
+
+static void coroutine_fn bdrv_rw_co_entry(void *opaque)
+{
+ RwCo *rwco = opaque;
+
+ if (!rwco->is_write) {
+ rwco->ret = bdrv_co_do_readv(rwco->bs, rwco->sector_num,
+ rwco->nb_sectors, rwco->qiov, 0);
+ } else {
+ rwco->ret = bdrv_co_do_writev(rwco->bs, rwco->sector_num,
+ rwco->nb_sectors, rwco->qiov, 0);
+ }
+}
+
+/*
+ * Process a vectored synchronous request using coroutines
+ */
+static int bdrv_rwv_co(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *qiov, bool is_write)
+{
+ Coroutine *co;
+ RwCo rwco = {
+ .bs = bs,
+ .sector_num = sector_num,
+ .nb_sectors = qiov->size >> BDRV_SECTOR_BITS,
+ .qiov = qiov,
+ .is_write = is_write,
+ .ret = NOT_DONE,
+ };
+ assert((qiov->size & (BDRV_SECTOR_SIZE - 1)) == 0);
+
+ /**
+ * In sync call context, when the vcpu is blocked, this throttling timer
+ * will not fire; so the I/O throttling function has to be disabled here
+ * if it has been enabled.
+ */
+ if (bs->io_limits_enabled) {
+ fprintf(stderr, "Disabling I/O throttling on '%s' due "
+ "to synchronous I/O.\n", bdrv_get_device_name(bs));
+ bdrv_io_limits_disable(bs);
+ }
+
+ if (qemu_in_coroutine()) {
+ /* Fast-path if already in coroutine context */
+ bdrv_rw_co_entry(&rwco);
+ } else {
+ co = qemu_coroutine_create(bdrv_rw_co_entry);
+ qemu_coroutine_enter(co, &rwco);
+ while (rwco.ret == NOT_DONE) {
+ qemu_aio_wait();
+ }
+ }
+ return rwco.ret;
+}
+
+/*
+ * Process a synchronous request using coroutines
+ */
+static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
+ int nb_sectors, bool is_write)
+{
+ QEMUIOVector qiov;
+ struct iovec iov = {
+ .iov_base = (void *)buf,
+ .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
+ };
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ return bdrv_rwv_co(bs, sector_num, &qiov, is_write);
+}
+
+/* return < 0 if error. See bdrv_write() for the return codes */
+int bdrv_read(BlockDriverState *bs, int64_t sector_num,
+ uint8_t *buf, int nb_sectors)
+{
+ return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false);
+}
+
+/* Just like bdrv_read(), but with I/O throttling temporarily disabled */
+int bdrv_read_unthrottled(BlockDriverState *bs, int64_t sector_num,
+ uint8_t *buf, int nb_sectors)
+{
+ bool enabled;
+ int ret;
+
+ enabled = bs->io_limits_enabled;
+ bs->io_limits_enabled = false;
+ ret = bdrv_read(bs, 0, buf, 1);
+ bs->io_limits_enabled = enabled;
+ return ret;
+}
+
+/* Return < 0 if error. Important errors are:
+ -EIO generic I/O error (may happen for all errors)
+ -ENOMEDIUM No media inserted.
+ -EINVAL Invalid sector number or nb_sectors
+ -EACCES Trying to write a read-only device
+*/
+int bdrv_write(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors)
+{
+ return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true);
+}
+
+int bdrv_writev(BlockDriverState *bs, int64_t sector_num, QEMUIOVector *qiov)
+{
+ return bdrv_rwv_co(bs, sector_num, qiov, true);
+}
+
+int bdrv_pread(BlockDriverState *bs, int64_t offset,
+ void *buf, int count1)
+{
+ uint8_t tmp_buf[BDRV_SECTOR_SIZE];
+ int len, nb_sectors, count;
+ int64_t sector_num;
+ int ret;
+
+ count = count1;
+ /* first read to align to sector start */
+ len = (BDRV_SECTOR_SIZE - offset) & (BDRV_SECTOR_SIZE - 1);
+ if (len > count)
+ len = count;
+ sector_num = offset >> BDRV_SECTOR_BITS;
+ if (len > 0) {
+ if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
+ memcpy(buf, tmp_buf + (offset & (BDRV_SECTOR_SIZE - 1)), len);
+ count -= len;
+ if (count == 0)
+ return count1;
+ sector_num++;
+ buf += len;
+ }
+
+ /* read the sectors "in place" */
+ nb_sectors = count >> BDRV_SECTOR_BITS;
+ if (nb_sectors > 0) {
+ if ((ret = bdrv_read(bs, sector_num, buf, nb_sectors)) < 0)
+ return ret;
+ sector_num += nb_sectors;
+ len = nb_sectors << BDRV_SECTOR_BITS;
+ buf += len;
+ count -= len;
+ }
+
+ /* add data from the last sector */
+ if (count > 0) {
+ if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
+ memcpy(buf, tmp_buf, count);
+ }
+ return count1;
+}
+
+int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov)
+{
+ uint8_t tmp_buf[BDRV_SECTOR_SIZE];
+ int len, nb_sectors, count;
+ int64_t sector_num;
+ int ret;
+
+ count = qiov->size;
+
+ /* first write to align to sector start */
+ len = (BDRV_SECTOR_SIZE - offset) & (BDRV_SECTOR_SIZE - 1);
+ if (len > count)
+ len = count;
+ sector_num = offset >> BDRV_SECTOR_BITS;
+ if (len > 0) {
+ if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
+ qemu_iovec_to_buf(qiov, 0, tmp_buf + (offset & (BDRV_SECTOR_SIZE - 1)),
+ len);
+ if ((ret = bdrv_write(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
+ count -= len;
+ if (count == 0)
+ return qiov->size;
+ sector_num++;
+ }
+
+ /* write the sectors "in place" */
+ nb_sectors = count >> BDRV_SECTOR_BITS;
+ if (nb_sectors > 0) {
+ QEMUIOVector qiov_inplace;
+
+ qemu_iovec_init(&qiov_inplace, qiov->niov);
+ qemu_iovec_concat(&qiov_inplace, qiov, len,
+ nb_sectors << BDRV_SECTOR_BITS);
+ ret = bdrv_writev(bs, sector_num, &qiov_inplace);
+ qemu_iovec_destroy(&qiov_inplace);
+ if (ret < 0) {
+ return ret;
+ }
+
+ sector_num += nb_sectors;
+ len = nb_sectors << BDRV_SECTOR_BITS;
+ count -= len;
+ }
+
+ /* add data from the last sector */
+ if (count > 0) {
+ if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
+ qemu_iovec_to_buf(qiov, qiov->size - count, tmp_buf, count);
+ if ((ret = bdrv_write(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
+ }
+ return qiov->size;
+}
+
+int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
+ const void *buf, int count1)
+{
+ QEMUIOVector qiov;
+ struct iovec iov = {
+ .iov_base = (void *) buf,
+ .iov_len = count1,
+ };
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ return bdrv_pwritev(bs, offset, &qiov);
+}
+
+/*
+ * Writes to the file and ensures that no writes are reordered across this
+ * request (acts as a barrier)
+ *
+ * Returns 0 on success, -errno in error cases.
+ */
+int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
+ const void *buf, int count)
+{
+ int ret;
+
+ ret = bdrv_pwrite(bs, offset, buf, count);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* No flush needed for cache modes that already do it */
+ if (bs->enable_write_cache) {
+ bdrv_flush(bs);
+ }
+
+ return 0;
+}
+
+static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+ /* Perform I/O through a temporary buffer so that users who scribble over
+ * their read buffer while the operation is in progress do not end up
+ * modifying the image file. This is critical for zero-copy guest I/O
+ * where anything might happen inside guest memory.
+ */
+ void *bounce_buffer;
+
+ BlockDriver *drv = bs->drv;
+ struct iovec iov;
+ QEMUIOVector bounce_qiov;
+ int64_t cluster_sector_num;
+ int cluster_nb_sectors;
+ size_t skip_bytes;
+ int ret;
+
+ /* Cover entire cluster so no additional backing file I/O is required when
+ * allocating cluster in the image file.
+ */
+ bdrv_round_to_clusters(bs, sector_num, nb_sectors,
+ &cluster_sector_num, &cluster_nb_sectors);
+
+ trace_bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors,
+ cluster_sector_num, cluster_nb_sectors);
+
+ iov.iov_len = cluster_nb_sectors * BDRV_SECTOR_SIZE;
+ iov.iov_base = bounce_buffer = qemu_blockalign(bs, iov.iov_len);
+ qemu_iovec_init_external(&bounce_qiov, &iov, 1);
+
+ ret = drv->bdrv_co_readv(bs, cluster_sector_num, cluster_nb_sectors,
+ &bounce_qiov);
+ if (ret < 0) {
+ goto err;
+ }
+
+ if (drv->bdrv_co_write_zeroes &&
+ buffer_is_zero(bounce_buffer, iov.iov_len)) {
+ ret = bdrv_co_do_write_zeroes(bs, cluster_sector_num,
+ cluster_nb_sectors);
+ } else {
+ /* This does not change the data on the disk, it is not necessary
+ * to flush even in cache=writethrough mode.
+ */
+ ret = drv->bdrv_co_writev(bs, cluster_sector_num, cluster_nb_sectors,
+ &bounce_qiov);
+ }
+
+ if (ret < 0) {
+ /* It might be okay to ignore write errors for guest requests. If this
+ * is a deliberate copy-on-read then we don't want to ignore the error.
+ * Simply report it in all cases.
+ */
+ goto err;
+ }
+
+ skip_bytes = (sector_num - cluster_sector_num) * BDRV_SECTOR_SIZE;
+ qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes,
+ nb_sectors * BDRV_SECTOR_SIZE);
+
+err:
+ qemu_vfree(bounce_buffer);
+ return ret;
+}
+
+/*
+ * Handle a read request in coroutine context
+ */
+static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
+ BdrvRequestFlags flags)
+{
+ BlockDriver *drv = bs->drv;
+ BdrvTrackedRequest req;
+ int ret;
+
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (bdrv_check_request(bs, sector_num, nb_sectors)) {
+ return -EIO;
+ }
+
+ /* throttling disk read I/O */
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_intercept(bs, false, nb_sectors);
+ }
+
+ if (bs->copy_on_read) {
+ flags |= BDRV_REQ_COPY_ON_READ;
+ }
+ if (flags & BDRV_REQ_COPY_ON_READ) {
+ bs->copy_on_read_in_flight++;
+ }
+
+ if (bs->copy_on_read_in_flight) {
+ wait_for_overlapping_requests(bs, sector_num, nb_sectors);
+ }
+
+ tracked_request_begin(&req, bs, sector_num, nb_sectors, false);
+
+ if (flags & BDRV_REQ_COPY_ON_READ) {
+ int pnum;
+
+ ret = bdrv_co_is_allocated(bs, sector_num, nb_sectors, &pnum);
+ if (ret < 0) {
+ goto out;
+ }
+
+ if (!ret || pnum != nb_sectors) {
+ ret = bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors, qiov);
+ goto out;
+ }
+ }
+
+ ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+
+out:
+ tracked_request_end(&req);
+
+ if (flags & BDRV_REQ_COPY_ON_READ) {
+ bs->copy_on_read_in_flight--;
+ }
+
+ return ret;
+}
+
+int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov)
+{
+ trace_bdrv_co_readv(bs, sector_num, nb_sectors);
+
+ return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov, 0);
+}
+
+int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+ trace_bdrv_co_copy_on_readv(bs, sector_num, nb_sectors);
+
+ return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov,
+ BDRV_REQ_COPY_ON_READ);
+}
+
+static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors)
+{
+ BlockDriver *drv = bs->drv;
+ QEMUIOVector qiov;
+ struct iovec iov;
+ int ret;
+
+ /* TODO Emulate only part of misaligned requests instead of letting block
+ * drivers return -ENOTSUP and emulate everything */
+
+ /* First try the efficient write zeroes operation */
+ if (drv->bdrv_co_write_zeroes) {
+ ret = drv->bdrv_co_write_zeroes(bs, sector_num, nb_sectors);
+ if (ret != -ENOTSUP) {
+ return ret;
+ }
+ }
+
+ /* Fall back to bounce buffer if write zeroes is unsupported */
+ iov.iov_len = nb_sectors * BDRV_SECTOR_SIZE;
+ iov.iov_base = qemu_blockalign(bs, iov.iov_len);
+ memset(iov.iov_base, 0, iov.iov_len);
+ qemu_iovec_init_external(&qiov, &iov, 1);
+
+ ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, &qiov);
+
+ qemu_vfree(iov.iov_base);
+ return ret;
+}
+
+/*
+ * Handle a write request in coroutine context
+ */
+static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
+ BdrvRequestFlags flags)
+{
+ BlockDriver *drv = bs->drv;
+ BdrvTrackedRequest req;
+ int ret;
+
+ if (!bs->drv) {
+ return -ENOMEDIUM;
+ }
+ if (bs->read_only) {
+ return -EACCES;
+ }
+ if (bdrv_check_request(bs, sector_num, nb_sectors)) {
+ return -EIO;
+ }
+
+ /* throttling disk write I/O */
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_intercept(bs, true, nb_sectors);
+ }
+
+ if (bs->copy_on_read_in_flight) {
+ wait_for_overlapping_requests(bs, sector_num, nb_sectors);
+ }
+
+ tracked_request_begin(&req, bs, sector_num, nb_sectors, true);
+
+ ret = notifier_with_return_list_notify(&bs->before_write_notifiers, &req);
+
+ if (ret < 0) {
+ /* Do nothing, write notifier decided to fail this request */
+ } else if (flags & BDRV_REQ_ZERO_WRITE) {
+ ret = bdrv_co_do_write_zeroes(bs, sector_num, nb_sectors);
+ } else {
+ ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
+ }
+
+ if (ret == 0 && !bs->enable_write_cache) {
+ ret = bdrv_co_flush(bs);
+ }
+
+ if (bs->dirty_bitmap) {
+ bdrv_set_dirty(bs, sector_num, nb_sectors);
+ }
+
+ if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
+ bs->wr_highest_sector = sector_num + nb_sectors - 1;
+ }
+
+ tracked_request_end(&req);
+
+ return ret;
+}
+
+int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov)
+{
+ trace_bdrv_co_writev(bs, sector_num, nb_sectors);
+
+ return bdrv_co_do_writev(bs, sector_num, nb_sectors, qiov, 0);
+}
+
+int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors)
+{
+ trace_bdrv_co_write_zeroes(bs, sector_num, nb_sectors);
+
+ return bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
+ BDRV_REQ_ZERO_WRITE);
+}
+
+/**
+ * Truncate file to 'offset' bytes (needed only for file protocols)
+ */
+int bdrv_truncate(BlockDriverState *bs, int64_t offset)
+{
+ BlockDriver *drv = bs->drv;
+ int ret;
+ if (!drv)
+ return -ENOMEDIUM;
+ if (!drv->bdrv_truncate)
+ return -ENOTSUP;
+ if (bs->read_only)
+ return -EACCES;
+ if (bdrv_in_use(bs))
+ return -EBUSY;
+ ret = drv->bdrv_truncate(bs, offset);
+ if (ret == 0) {
+ ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
+ bdrv_dev_resize_cb(bs);
+ }
+ return ret;
+}
+
+/**
+ * Length of a allocated file in bytes. Sparse files are counted by actual
+ * allocated space. Return < 0 if error or unknown.
+ */
+int64_t bdrv_get_allocated_file_size(BlockDriverState *bs)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (drv->bdrv_get_allocated_file_size) {
+ return drv->bdrv_get_allocated_file_size(bs);
+ }
+ if (bs->file) {
+ return bdrv_get_allocated_file_size(bs->file);
+ }
+ return -ENOTSUP;
+}
+
+/**
+ * Length of a file in bytes. Return < 0 if error or unknown.
+ */
+int64_t bdrv_getlength(BlockDriverState *bs)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv)
+ return -ENOMEDIUM;
+
+ if (bs->growable || bdrv_dev_has_removable_media(bs)) {
+ if (drv->bdrv_getlength) {
+ return drv->bdrv_getlength(bs);
+ }
+ }
+ return bs->total_sectors * BDRV_SECTOR_SIZE;
+}
+
+/* return 0 as number of sectors if no device present or error */
+void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
+{
+ int64_t length;
+ length = bdrv_getlength(bs);
+ if (length < 0)
+ length = 0;
+ else
+ length = length >> BDRV_SECTOR_BITS;
+ *nb_sectors_ptr = length;
+}
+
+/* throttling disk io limits */
+void bdrv_set_io_limits(BlockDriverState *bs,
+ BlockIOLimit *io_limits)
+{
+ bs->io_limits = *io_limits;
+ bs->io_limits_enabled = bdrv_io_limits_enabled(bs);
+}
+
+void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
+ BlockdevOnError on_write_error)
+{
+ bs->on_read_error = on_read_error;
+ bs->on_write_error = on_write_error;
+}
+
+BlockdevOnError bdrv_get_on_error(BlockDriverState *bs, bool is_read)
+{
+ return is_read ? bs->on_read_error : bs->on_write_error;
+}
+
+BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int error)
+{
+ BlockdevOnError on_err = is_read ? bs->on_read_error : bs->on_write_error;
+
+ switch (on_err) {
+ case BLOCKDEV_ON_ERROR_ENOSPC:
+ return (error == ENOSPC) ? BDRV_ACTION_STOP : BDRV_ACTION_REPORT;
+ case BLOCKDEV_ON_ERROR_STOP:
+ return BDRV_ACTION_STOP;
+ case BLOCKDEV_ON_ERROR_REPORT:
+ return BDRV_ACTION_REPORT;
+ case BLOCKDEV_ON_ERROR_IGNORE:
+ return BDRV_ACTION_IGNORE;
+ default:
+ abort();
+ }
+}
+
+/* This is done by device models because, while the block layer knows
+ * about the error, it does not know whether an operation comes from
+ * the device or the block layer (from a job, for example).
+ */
+void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
+ bool is_read, int error)
+{
+ assert(error >= 0);
+ bdrv_emit_qmp_error_event(bs, QEVENT_BLOCK_IO_ERROR, action, is_read);
+ if (action == BDRV_ACTION_STOP) {
+ vm_stop(RUN_STATE_IO_ERROR);
+ bdrv_iostatus_set_err(bs, error);
+ }
+}
+
+int bdrv_is_read_only(BlockDriverState *bs)
+{
+ return bs->read_only;
+}
+
+int bdrv_is_sg(BlockDriverState *bs)
+{
+ return bs->sg;
+}
+
+int bdrv_enable_write_cache(BlockDriverState *bs)
+{
+ return bs->enable_write_cache;
+}
+
+void bdrv_set_enable_write_cache(BlockDriverState *bs, bool wce)
+{
+ bs->enable_write_cache = wce;
+
+ /* so a reopen() will preserve wce */
+ if (wce) {
+ bs->open_flags |= BDRV_O_CACHE_WB;
+ } else {
+ bs->open_flags &= ~BDRV_O_CACHE_WB;
+ }
+}
+
+int bdrv_is_encrypted(BlockDriverState *bs)
+{
+ if (bs->backing_hd && bs->backing_hd->encrypted)
+ return 1;
+ return bs->encrypted;
+}
+
+int bdrv_key_required(BlockDriverState *bs)
+{
+ BlockDriverState *backing_hd = bs->backing_hd;
+
+ if (backing_hd && backing_hd->encrypted && !backing_hd->valid_key)
+ return 1;
+ return (bs->encrypted && !bs->valid_key);
+}
+
+int bdrv_set_key(BlockDriverState *bs, const char *key)
+{
+ int ret;
+ if (bs->backing_hd && bs->backing_hd->encrypted) {
+ ret = bdrv_set_key(bs->backing_hd, key);
+ if (ret < 0)
+ return ret;
+ if (!bs->encrypted)
+ return 0;
+ }
+ if (!bs->encrypted) {
+ return -EINVAL;
+ } else if (!bs->drv || !bs->drv->bdrv_set_key) {
+ return -ENOMEDIUM;
+ }
+ ret = bs->drv->bdrv_set_key(bs, key);
+ if (ret < 0) {
+ bs->valid_key = 0;
+ } else if (!bs->valid_key) {
+ bs->valid_key = 1;
+ /* call the change callback now, we skipped it on open */
+ bdrv_dev_change_media_cb(bs, true);
+ }
+ return ret;
+}
+
+const char *bdrv_get_format_name(BlockDriverState *bs)
+{
+ return bs->drv ? bs->drv->format_name : NULL;
+}
+
+void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
+ void *opaque)
+{
+ BlockDriver *drv;
+
+ QLIST_FOREACH(drv, &bdrv_drivers, list) {
+ it(opaque, drv->format_name);
+ }
+}
+
+BlockDriverState *bdrv_find(const char *name)
+{
+ BlockDriverState *bs;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ if (!strcmp(name, bs->device_name)) {
+ return bs;
+ }
+ }
+ return NULL;
+}
+
+BlockDriverState *bdrv_next(BlockDriverState *bs)
+{
+ if (!bs) {
+ return QTAILQ_FIRST(&bdrv_states);
+ }
+ return QTAILQ_NEXT(bs, list);
+}
+
+void bdrv_iterate(void (*it)(void *opaque, BlockDriverState *bs), void *opaque)
+{
+ BlockDriverState *bs;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ it(opaque, bs);
+ }
+}
+
+const char *bdrv_get_device_name(BlockDriverState *bs)
+{
+ return bs->device_name;
+}
+
+int bdrv_get_flags(BlockDriverState *bs)
+{
+ return bs->open_flags;
+}
+
+int bdrv_flush_all(void)
+{
+ BlockDriverState *bs;
+ int result = 0;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ int ret = bdrv_flush(bs);
+ if (ret < 0 && !result) {
+ result = ret;
+ }
+ }
+
+ return result;
+}
+
+int bdrv_has_zero_init_1(BlockDriverState *bs)
+{
+ return 1;
+}
+
+int bdrv_has_zero_init(BlockDriverState *bs)
+{
+ assert(bs->drv);
+
+ if (bs->drv->bdrv_has_zero_init) {
+ return bs->drv->bdrv_has_zero_init(bs);
+ }
+
+ /* safe default */
+ return 0;
+}
+
+typedef struct BdrvCoIsAllocatedData {
+ BlockDriverState *bs;
+ BlockDriverState *base;
+ int64_t sector_num;
+ int nb_sectors;
+ int *pnum;
+ int ret;
+ bool done;
+} BdrvCoIsAllocatedData;
+
+/*
+ * Returns true iff the specified sector is present in the disk image. Drivers
+ * not implementing the functionality are assumed to not support backing files,
+ * hence all their sectors are reported as allocated.
+ *
+ * If 'sector_num' is beyond the end of the disk image the return value is 0
+ * and 'pnum' is set to 0.
+ *
+ * 'pnum' is set to the number of sectors (including and immediately following
+ * the specified sector) that are known to be in the same
+ * allocated/unallocated state.
+ *
+ * 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes
+ * beyond the end of the disk image it will be clamped.
+ */
+int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, int *pnum)
+{
+ int64_t n;
+
+ if (sector_num >= bs->total_sectors) {
+ *pnum = 0;
+ return 0;
+ }
+
+ n = bs->total_sectors - sector_num;
+ if (n < nb_sectors) {
+ nb_sectors = n;
+ }
+
+ if (!bs->drv->bdrv_co_is_allocated) {
+ *pnum = nb_sectors;
+ return 1;
+ }
+
+ return bs->drv->bdrv_co_is_allocated(bs, sector_num, nb_sectors, pnum);
+}
+
+/* Coroutine wrapper for bdrv_is_allocated() */
+static void coroutine_fn bdrv_is_allocated_co_entry(void *opaque)
+{
+ BdrvCoIsAllocatedData *data = opaque;
+ BlockDriverState *bs = data->bs;
+
+ data->ret = bdrv_co_is_allocated(bs, data->sector_num, data->nb_sectors,
+ data->pnum);
+ data->done = true;
+}
+
+/*
+ * Synchronous wrapper around bdrv_co_is_allocated().
+ *
+ * See bdrv_co_is_allocated() for details.
+ */
+int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+ int *pnum)
+{
+ Coroutine *co;
+ BdrvCoIsAllocatedData data = {
+ .bs = bs,
+ .sector_num = sector_num,
+ .nb_sectors = nb_sectors,
+ .pnum = pnum,
+ .done = false,
+ };
+
+ co = qemu_coroutine_create(bdrv_is_allocated_co_entry);
+ qemu_coroutine_enter(co, &data);
+ while (!data.done) {
+ qemu_aio_wait();
+ }
+ return data.ret;
+}
+
+/*
+ * Given an image chain: ... -> [BASE] -> [INTER1] -> [INTER2] -> [TOP]
+ *
+ * Return true if the given sector is allocated in any image between
+ * BASE and TOP (inclusive). BASE can be NULL to check if the given
+ * sector is allocated in any image of the chain. Return false otherwise.
+ *
+ * 'pnum' is set to the number of sectors (including and immediately following
+ * the specified sector) that are known to be in the same
+ * allocated/unallocated state.
+ *
+ */
+int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *top,
+ BlockDriverState *base,
+ int64_t sector_num,
+ int nb_sectors, int *pnum)
+{
+ BlockDriverState *intermediate;
+ int ret, n = nb_sectors;
+
+ intermediate = top;
+ while (intermediate && intermediate != base) {
+ int pnum_inter;
+ ret = bdrv_co_is_allocated(intermediate, sector_num, nb_sectors,
+ &pnum_inter);
+ if (ret < 0) {
+ return ret;
+ } else if (ret) {
+ *pnum = pnum_inter;
+ return 1;
+ }
+
+ /*
+ * [sector_num, nb_sectors] is unallocated on top but intermediate
+ * might have
+ *
+ * [sector_num+x, nr_sectors] allocated.
+ */
+ if (n > pnum_inter &&
+ (intermediate == top ||
+ sector_num + pnum_inter < intermediate->total_sectors)) {
+ n = pnum_inter;
+ }
+
+ intermediate = intermediate->backing_hd;
+ }
+
+ *pnum = n;
+ return 0;
+}
+
+/* Coroutine wrapper for bdrv_is_allocated_above() */
+static void coroutine_fn bdrv_is_allocated_above_co_entry(void *opaque)
+{
+ BdrvCoIsAllocatedData *data = opaque;
+ BlockDriverState *top = data->bs;
+ BlockDriverState *base = data->base;
+
+ data->ret = bdrv_co_is_allocated_above(top, base, data->sector_num,
+ data->nb_sectors, data->pnum);
+ data->done = true;
+}
+
+/*
+ * Synchronous wrapper around bdrv_co_is_allocated_above().
+ *
+ * See bdrv_co_is_allocated_above() for details.
+ */
+int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
+ int64_t sector_num, int nb_sectors, int *pnum)
+{
+ Coroutine *co;
+ BdrvCoIsAllocatedData data = {
+ .bs = top,
+ .base = base,
+ .sector_num = sector_num,
+ .nb_sectors = nb_sectors,
+ .pnum = pnum,
+ .done = false,
+ };
+
+ co = qemu_coroutine_create(bdrv_is_allocated_above_co_entry);
+ qemu_coroutine_enter(co, &data);
+ while (!data.done) {
+ qemu_aio_wait();
+ }
+ return data.ret;
+}
+
+const char *bdrv_get_encrypted_filename(BlockDriverState *bs)
+{
+ if (bs->backing_hd && bs->backing_hd->encrypted)
+ return bs->backing_file;
+ else if (bs->encrypted)
+ return bs->filename;
+ else
+ return NULL;
+}
+
+void bdrv_get_backing_filename(BlockDriverState *bs,
+ char *filename, int filename_size)
+{
+ pstrcpy(filename, filename_size, bs->backing_file);
+}
+
+int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv)
+ return -ENOMEDIUM;
+ if (!drv->bdrv_write_compressed)
+ return -ENOTSUP;
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return -EIO;
+
+ assert(!bs->dirty_bitmap);
+
+ return drv->bdrv_write_compressed(bs, sector_num, buf, nb_sectors);
+}
+
+int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv)
+ return -ENOMEDIUM;
+ if (!drv->bdrv_get_info)
+ return -ENOTSUP;
+ memset(bdi, 0, sizeof(*bdi));
+ return drv->bdrv_get_info(bs, bdi);
+}
+
+int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
+ int64_t pos, int size)
+{
+ QEMUIOVector qiov;
+ struct iovec iov = {
+ .iov_base = (void *) buf,
+ .iov_len = size,
+ };
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ return bdrv_writev_vmstate(bs, &qiov, pos);
+}
+
+int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (!drv) {
+ return -ENOMEDIUM;
+ } else if (drv->bdrv_save_vmstate) {
+ return drv->bdrv_save_vmstate(bs, qiov, pos);
+ } else if (bs->file) {
+ return bdrv_writev_vmstate(bs->file, qiov, pos);
+ }
+
+ return -ENOTSUP;
+}
+
+int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
+ int64_t pos, int size)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv)
+ return -ENOMEDIUM;
+ if (drv->bdrv_load_vmstate)
+ return drv->bdrv_load_vmstate(bs, buf, pos, size);
+ if (bs->file)
+ return bdrv_load_vmstate(bs->file, buf, pos, size);
+ return -ENOTSUP;
+}
+
+void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event)
+{
+ if (!bs || !bs->drv || !bs->drv->bdrv_debug_event) {
+ return;
+ }
+
+ bs->drv->bdrv_debug_event(bs, event);
+}
+
+int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
+ const char *tag)
+{
+ while (bs && bs->drv && !bs->drv->bdrv_debug_breakpoint) {
+ bs = bs->file;
+ }
+
+ if (bs && bs->drv && bs->drv->bdrv_debug_breakpoint) {
+ return bs->drv->bdrv_debug_breakpoint(bs, event, tag);
+ }
+
+ return -ENOTSUP;
+}
+
+int bdrv_debug_resume(BlockDriverState *bs, const char *tag)
+{
+ while (bs && bs->drv && !bs->drv->bdrv_debug_resume) {
+ bs = bs->file;
+ }
+
+ if (bs && bs->drv && bs->drv->bdrv_debug_resume) {
+ return bs->drv->bdrv_debug_resume(bs, tag);
+ }
+
+ return -ENOTSUP;
+}
+
+bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag)
+{
+ while (bs && bs->drv && !bs->drv->bdrv_debug_is_suspended) {
+ bs = bs->file;
+ }
+
+ if (bs && bs->drv && bs->drv->bdrv_debug_is_suspended) {
+ return bs->drv->bdrv_debug_is_suspended(bs, tag);
+ }
+
+ return false;
+}
+
+int bdrv_is_snapshot(BlockDriverState *bs)
+{
+ return !!(bs->open_flags & BDRV_O_SNAPSHOT);
+}
+
+/* backing_file can either be relative, or absolute, or a protocol. If it is
+ * relative, it must be relative to the chain. So, passing in bs->filename
+ * from a BDS as backing_file should not be done, as that may be relative to
+ * the CWD rather than the chain. */
+BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
+ const char *backing_file)
+{
+ char *filename_full = NULL;
+ char *backing_file_full = NULL;
+ char *filename_tmp = NULL;
+ int is_protocol = 0;
+ BlockDriverState *curr_bs = NULL;
+ BlockDriverState *retval = NULL;
+
+ if (!bs || !bs->drv || !backing_file) {
+ return NULL;
+ }
+
+ filename_full = g_malloc(PATH_MAX);
+ backing_file_full = g_malloc(PATH_MAX);
+ filename_tmp = g_malloc(PATH_MAX);
+
+ is_protocol = path_has_protocol(backing_file);
+
+ for (curr_bs = bs; curr_bs->backing_hd; curr_bs = curr_bs->backing_hd) {
+
+ /* If either of the filename paths is actually a protocol, then
+ * compare unmodified paths; otherwise make paths relative */
+ if (is_protocol || path_has_protocol(curr_bs->backing_file)) {
+ if (strcmp(backing_file, curr_bs->backing_file) == 0) {
+ retval = curr_bs->backing_hd;
+ break;
+ }
+ } else {
+ /* If not an absolute filename path, make it relative to the current
+ * image's filename path */
+ path_combine(filename_tmp, PATH_MAX, curr_bs->filename,
+ backing_file);
+
+ /* We are going to compare absolute pathnames */
+ if (!realpath(filename_tmp, filename_full)) {
+ continue;
+ }
+
+ /* We need to make sure the backing filename we are comparing against
+ * is relative to the current image filename (or absolute) */
+ path_combine(filename_tmp, PATH_MAX, curr_bs->filename,
+ curr_bs->backing_file);
+
+ if (!realpath(filename_tmp, backing_file_full)) {
+ continue;
+ }
+
+ if (strcmp(backing_file_full, filename_full) == 0) {
+ retval = curr_bs->backing_hd;
+ break;
+ }
+ }
+ }
+
+ g_free(filename_full);
+ g_free(backing_file_full);
+ g_free(filename_tmp);
+ return retval;
+}
+
+int bdrv_get_backing_file_depth(BlockDriverState *bs)
+{
+ if (!bs->drv) {
+ return 0;
+ }
+
+ if (!bs->backing_hd) {
+ return 0;
+ }
+
+ return 1 + bdrv_get_backing_file_depth(bs->backing_hd);
+}
+
+BlockDriverState *bdrv_find_base(BlockDriverState *bs)
+{
+ BlockDriverState *curr_bs = NULL;
+
+ if (!bs) {
+ return NULL;
+ }
+
+ curr_bs = bs;
+
+ while (curr_bs->backing_hd) {
+ curr_bs = curr_bs->backing_hd;
+ }
+ return curr_bs;
+}
+
+/**************************************************************/
+/* async I/Os */
+
+BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ trace_bdrv_aio_readv(bs, sector_num, nb_sectors, opaque);
+
+ return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors,
+ cb, opaque, false);
+}
+
+BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ trace_bdrv_aio_writev(bs, sector_num, nb_sectors, opaque);
+
+ return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors,
+ cb, opaque, true);
+}
+
+
+typedef struct MultiwriteCB {
+ int error;
+ int num_requests;
+ int num_callbacks;
+ struct {
+ BlockDriverCompletionFunc *cb;
+ void *opaque;
+ QEMUIOVector *free_qiov;
+ } callbacks[];
+} MultiwriteCB;
+
+static void multiwrite_user_cb(MultiwriteCB *mcb)
+{
+ int i;
+
+ for (i = 0; i < mcb->num_callbacks; i++) {
+ mcb->callbacks[i].cb(mcb->callbacks[i].opaque, mcb->error);
+ if (mcb->callbacks[i].free_qiov) {
+ qemu_iovec_destroy(mcb->callbacks[i].free_qiov);
+ }
+ g_free(mcb->callbacks[i].free_qiov);
+ }
+}
+
+static void multiwrite_cb(void *opaque, int ret)
+{
+ MultiwriteCB *mcb = opaque;
+
+ trace_multiwrite_cb(mcb, ret);
+
+ if (ret < 0 && !mcb->error) {
+ mcb->error = ret;
+ }
+
+ mcb->num_requests--;
+ if (mcb->num_requests == 0) {
+ multiwrite_user_cb(mcb);
+ g_free(mcb);
+ }
+}
+
+static int multiwrite_req_compare(const void *a, const void *b)
+{
+ const BlockRequest *req1 = a, *req2 = b;
+
+ /*
+ * Note that we can't simply subtract req2->sector from req1->sector
+ * here as that could overflow the return value.
+ */
+ if (req1->sector > req2->sector) {
+ return 1;
+ } else if (req1->sector < req2->sector) {
+ return -1;
+ } else {
+ return 0;
+ }
+}
+
+/*
+ * Takes a bunch of requests and tries to merge them. Returns the number of
+ * requests that remain after merging.
+ */
+static int multiwrite_merge(BlockDriverState *bs, BlockRequest *reqs,
+ int num_reqs, MultiwriteCB *mcb)
+{
+ int i, outidx;
+
+ // Sort requests by start sector
+ qsort(reqs, num_reqs, sizeof(*reqs), &multiwrite_req_compare);
+
+ // Check if adjacent requests touch the same clusters. If so, combine them,
+ // filling up gaps with zero sectors.
+ outidx = 0;
+ for (i = 1; i < num_reqs; i++) {
+ int merge = 0;
+ int64_t oldreq_last = reqs[outidx].sector + reqs[outidx].nb_sectors;
+
+ // Handle exactly sequential writes and overlapping writes.
+ if (reqs[i].sector <= oldreq_last) {
+ merge = 1;
+ }
+
+ if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 > IOV_MAX) {
+ merge = 0;
+ }
+
+ if (merge) {
+ size_t size;
+ QEMUIOVector *qiov = g_malloc0(sizeof(*qiov));
+ qemu_iovec_init(qiov,
+ reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1);
+
+ // Add the first request to the merged one. If the requests are
+ // overlapping, drop the last sectors of the first request.
+ size = (reqs[i].sector - reqs[outidx].sector) << 9;
+ qemu_iovec_concat(qiov, reqs[outidx].qiov, 0, size);
+
+ // We should need to add any zeros between the two requests
+ assert (reqs[i].sector <= oldreq_last);
+
+ // Add the second request
+ qemu_iovec_concat(qiov, reqs[i].qiov, 0, reqs[i].qiov->size);
+
+ reqs[outidx].nb_sectors = qiov->size >> 9;
+ reqs[outidx].qiov = qiov;
+
+ mcb->callbacks[i].free_qiov = reqs[outidx].qiov;
+ } else {
+ outidx++;
+ reqs[outidx].sector = reqs[i].sector;
+ reqs[outidx].nb_sectors = reqs[i].nb_sectors;
+ reqs[outidx].qiov = reqs[i].qiov;
+ }
+ }
+
+ return outidx + 1;
+}
+
+/*
+ * Submit multiple AIO write requests at once.
+ *
+ * On success, the function returns 0 and all requests in the reqs array have
+ * been submitted. In error case this function returns -1, and any of the
+ * requests may or may not be submitted yet. In particular, this means that the
+ * callback will be called for some of the requests, for others it won't. The
+ * caller must check the error field of the BlockRequest to wait for the right
+ * callbacks (if error != 0, no callback will be called).
+ *
+ * The implementation may modify the contents of the reqs array, e.g. to merge
+ * requests. However, the fields opaque and error are left unmodified as they
+ * are used to signal failure for a single request to the caller.
+ */
+int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs, int num_reqs)
+{
+ MultiwriteCB *mcb;
+ int i;
+
+ /* don't submit writes if we don't have a medium */
+ if (bs->drv == NULL) {
+ for (i = 0; i < num_reqs; i++) {
+ reqs[i].error = -ENOMEDIUM;
+ }
+ return -1;
+ }
+
+ if (num_reqs == 0) {
+ return 0;
+ }
+
+ // Create MultiwriteCB structure
+ mcb = g_malloc0(sizeof(*mcb) + num_reqs * sizeof(*mcb->callbacks));
+ mcb->num_requests = 0;
+ mcb->num_callbacks = num_reqs;
+
+ for (i = 0; i < num_reqs; i++) {
+ mcb->callbacks[i].cb = reqs[i].cb;
+ mcb->callbacks[i].opaque = reqs[i].opaque;
+ }
+
+ // Check for mergable requests
+ num_reqs = multiwrite_merge(bs, reqs, num_reqs, mcb);
+
+ trace_bdrv_aio_multiwrite(mcb, mcb->num_callbacks, num_reqs);
+
+ /* Run the aio requests. */
+ mcb->num_requests = num_reqs;
+ for (i = 0; i < num_reqs; i++) {
+ bdrv_aio_writev(bs, reqs[i].sector, reqs[i].qiov,
+ reqs[i].nb_sectors, multiwrite_cb, mcb);
+ }
+
+ return 0;
+}
+
+void bdrv_aio_cancel(BlockDriverAIOCB *acb)
+{
+ acb->aiocb_info->cancel(acb);
+}
+
+/* block I/O throttling */
+static bool bdrv_exceed_bps_limits(BlockDriverState *bs, int nb_sectors,
+ bool is_write, double elapsed_time, uint64_t *wait)
+{
+ uint64_t bps_limit = 0;
+ uint64_t extension;
+ double bytes_limit, bytes_base, bytes_res;
+ double slice_time, wait_time;
+
+ if (bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]) {
+ bps_limit = bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL];
+ } else if (bs->io_limits.bps[is_write]) {
+ bps_limit = bs->io_limits.bps[is_write];
+ } else {
+ if (wait) {
+ *wait = 0;
+ }
+
+ return false;
+ }
+
+ slice_time = bs->slice_end - bs->slice_start;
+ slice_time /= (NANOSECONDS_PER_SECOND);
+ bytes_limit = bps_limit * slice_time;
+ bytes_base = bs->slice_submitted.bytes[is_write];
+ if (bs->io_limits.bps[BLOCK_IO_LIMIT_TOTAL]) {
+ bytes_base += bs->slice_submitted.bytes[!is_write];
+ }
+
+ /* bytes_base: the bytes of data which have been read/written; and
+ * it is obtained from the history statistic info.
+ * bytes_res: the remaining bytes of data which need to be read/written.
+ * (bytes_base + bytes_res) / bps_limit: used to calcuate
+ * the total time for completing reading/writting all data.
+ */
+ bytes_res = (unsigned) nb_sectors * BDRV_SECTOR_SIZE;
+
+ if (bytes_base + bytes_res <= bytes_limit) {
+ if (wait) {
+ *wait = 0;
+ }
+
+ return false;
+ }
+
+ /* Calc approx time to dispatch */
+ wait_time = (bytes_base + bytes_res) / bps_limit - elapsed_time;
+
+ /* When the I/O rate at runtime exceeds the limits,
+ * bs->slice_end need to be extended in order that the current statistic
+ * info can be kept until the timer fire, so it is increased and tuned
+ * based on the result of experiment.
+ */
+ extension = wait_time * NANOSECONDS_PER_SECOND;
+ extension = DIV_ROUND_UP(extension, BLOCK_IO_SLICE_TIME) *
+ BLOCK_IO_SLICE_TIME;
+ bs->slice_end += extension;
+ if (wait) {
+ *wait = wait_time * NANOSECONDS_PER_SECOND;
+ }
+
+ return true;
+}
+
+static bool bdrv_exceed_iops_limits(BlockDriverState *bs, bool is_write,
+ double elapsed_time, uint64_t *wait)
+{
+ uint64_t iops_limit = 0;
+ double ios_limit, ios_base;
+ double slice_time, wait_time;
+
+ if (bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL]) {
+ iops_limit = bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL];
+ } else if (bs->io_limits.iops[is_write]) {
+ iops_limit = bs->io_limits.iops[is_write];
+ } else {
+ if (wait) {
+ *wait = 0;
+ }
+
+ return false;
+ }
+
+ slice_time = bs->slice_end - bs->slice_start;
+ slice_time /= (NANOSECONDS_PER_SECOND);
+ ios_limit = iops_limit * slice_time;
+ ios_base = bs->slice_submitted.ios[is_write];
+ if (bs->io_limits.iops[BLOCK_IO_LIMIT_TOTAL]) {
+ ios_base += bs->slice_submitted.ios[!is_write];
+ }
+
+ if (ios_base + 1 <= ios_limit) {
+ if (wait) {
+ *wait = 0;
+ }
+
+ return false;
+ }
+
+ /* Calc approx time to dispatch, in seconds */
+ wait_time = (ios_base + 1) / iops_limit;
+ if (wait_time > elapsed_time) {
+ wait_time = wait_time - elapsed_time;
+ } else {
+ wait_time = 0;
+ }
+
+ /* Exceeded current slice, extend it by another slice time */
+ bs->slice_end += BLOCK_IO_SLICE_TIME;
+ if (wait) {
+ *wait = wait_time * NANOSECONDS_PER_SECOND;
+ }
+
+ return true;
+}
+
+static bool bdrv_exceed_io_limits(BlockDriverState *bs, int nb_sectors,
+ bool is_write, int64_t *wait)
+{
+ int64_t now, max_wait;
+ uint64_t bps_wait = 0, iops_wait = 0;
+ double elapsed_time;
+ int bps_ret, iops_ret;
+
+ now = qemu_get_clock_ns(vm_clock);
+ if (now > bs->slice_end) {
+ bs->slice_start = now;
+ bs->slice_end = now + BLOCK_IO_SLICE_TIME;
+ memset(&bs->slice_submitted, 0, sizeof(bs->slice_submitted));
+ }
+
+ elapsed_time = now - bs->slice_start;
+ elapsed_time /= (NANOSECONDS_PER_SECOND);
+
+ bps_ret = bdrv_exceed_bps_limits(bs, nb_sectors,
+ is_write, elapsed_time, &bps_wait);
+ iops_ret = bdrv_exceed_iops_limits(bs, is_write,
+ elapsed_time, &iops_wait);
+ if (bps_ret || iops_ret) {
+ max_wait = bps_wait > iops_wait ? bps_wait : iops_wait;
+ if (wait) {
+ *wait = max_wait;
+ }
+
+ now = qemu_get_clock_ns(vm_clock);
+ if (bs->slice_end < now + max_wait) {
+ bs->slice_end = now + max_wait;
+ }
+
+ return true;
+ }
+
+ if (wait) {
+ *wait = 0;
+ }
+
+ bs->slice_submitted.bytes[is_write] += (int64_t)nb_sectors *
+ BDRV_SECTOR_SIZE;
+ bs->slice_submitted.ios[is_write]++;
+
+ return false;
+}
+
+/**************************************************************/
+/* async block device emulation */
+
+typedef struct BlockDriverAIOCBSync {
+ BlockDriverAIOCB common;
+ QEMUBH *bh;
+ int ret;
+ /* vector translation state */
+ QEMUIOVector *qiov;
+ uint8_t *bounce;
+ int is_write;
+} BlockDriverAIOCBSync;
+
+static void bdrv_aio_cancel_em(BlockDriverAIOCB *blockacb)
+{
+ BlockDriverAIOCBSync *acb =
+ container_of(blockacb, BlockDriverAIOCBSync, common);
+ qemu_bh_delete(acb->bh);
+ acb->bh = NULL;
+ qemu_aio_release(acb);
+}
+
+static const AIOCBInfo bdrv_em_aiocb_info = {
+ .aiocb_size = sizeof(BlockDriverAIOCBSync),
+ .cancel = bdrv_aio_cancel_em,
+};
+
+static void bdrv_aio_bh_cb(void *opaque)
+{
+ BlockDriverAIOCBSync *acb = opaque;
+
+ if (!acb->is_write)
+ qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
+ qemu_vfree(acb->bounce);
+ acb->common.cb(acb->common.opaque, acb->ret);
+ qemu_bh_delete(acb->bh);
+ acb->bh = NULL;
+ qemu_aio_release(acb);
+}
+
+static BlockDriverAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov,
+ int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque,
+ int is_write)
+
+{
+ BlockDriverAIOCBSync *acb;
+
+ acb = qemu_aio_get(&bdrv_em_aiocb_info, bs, cb, opaque);
+ acb->is_write = is_write;
+ acb->qiov = qiov;
+ acb->bounce = qemu_blockalign(bs, qiov->size);
+ acb->bh = qemu_bh_new(bdrv_aio_bh_cb, acb);
+
+ if (is_write) {
+ qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
+ acb->ret = bs->drv->bdrv_write(bs, sector_num, acb->bounce, nb_sectors);
+ } else {
+ acb->ret = bs->drv->bdrv_read(bs, sector_num, acb->bounce, nb_sectors);
+ }
+
+ qemu_bh_schedule(acb->bh);
+
+ return &acb->common;
+}
+
+static BlockDriverAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ return bdrv_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
+}
+
+static BlockDriverAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ return bdrv_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
+}
+
+
+typedef struct BlockDriverAIOCBCoroutine {
+ BlockDriverAIOCB common;
+ BlockRequest req;
+ bool is_write;
+ bool *done;
+ QEMUBH* bh;
+} BlockDriverAIOCBCoroutine;
+
+static void bdrv_aio_co_cancel_em(BlockDriverAIOCB *blockacb)
+{
+ BlockDriverAIOCBCoroutine *acb =
+ container_of(blockacb, BlockDriverAIOCBCoroutine, common);
+ bool done = false;
+
+ acb->done = &done;
+ while (!done) {
+ qemu_aio_wait();
+ }
+}
+
+static const AIOCBInfo bdrv_em_co_aiocb_info = {
+ .aiocb_size = sizeof(BlockDriverAIOCBCoroutine),
+ .cancel = bdrv_aio_co_cancel_em,
+};
+
+static void bdrv_co_em_bh(void *opaque)
+{
+ BlockDriverAIOCBCoroutine *acb = opaque;
+
+ acb->common.cb(acb->common.opaque, acb->req.error);
+
+ if (acb->done) {
+ *acb->done = true;
+ }
+
+ qemu_bh_delete(acb->bh);
+ qemu_aio_release(acb);
+}
+
+/* Invoke bdrv_co_do_readv/bdrv_co_do_writev */
+static void coroutine_fn bdrv_co_do_rw(void *opaque)
+{
+ BlockDriverAIOCBCoroutine *acb = opaque;
+ BlockDriverState *bs = acb->common.bs;
+
+ if (!acb->is_write) {
+ acb->req.error = bdrv_co_do_readv(bs, acb->req.sector,
+ acb->req.nb_sectors, acb->req.qiov, 0);
+ } else {
+ acb->req.error = bdrv_co_do_writev(bs, acb->req.sector,
+ acb->req.nb_sectors, acb->req.qiov, 0);
+ }
+
+ acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
+ qemu_bh_schedule(acb->bh);
+}
+
+static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov,
+ int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque,
+ bool is_write)
+{
+ Coroutine *co;
+ BlockDriverAIOCBCoroutine *acb;
+
+ acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
+ acb->req.sector = sector_num;
+ acb->req.nb_sectors = nb_sectors;
+ acb->req.qiov = qiov;
+ acb->is_write = is_write;
+ acb->done = NULL;
+
+ co = qemu_coroutine_create(bdrv_co_do_rw);
+ qemu_coroutine_enter(co, acb);
+
+ return &acb->common;
+}
+
+static void coroutine_fn bdrv_aio_flush_co_entry(void *opaque)
+{
+ BlockDriverAIOCBCoroutine *acb = opaque;
+ BlockDriverState *bs = acb->common.bs;
+
+ acb->req.error = bdrv_co_flush(bs);
+ acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
+ qemu_bh_schedule(acb->bh);
+}
+
+BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ trace_bdrv_aio_flush(bs, opaque);
+
+ Coroutine *co;
+ BlockDriverAIOCBCoroutine *acb;
+
+ acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
+ acb->done = NULL;
+
+ co = qemu_coroutine_create(bdrv_aio_flush_co_entry);
+ qemu_coroutine_enter(co, acb);
+
+ return &acb->common;
+}
+
+static void coroutine_fn bdrv_aio_discard_co_entry(void *opaque)
+{
+ BlockDriverAIOCBCoroutine *acb = opaque;
+ BlockDriverState *bs = acb->common.bs;
+
+ acb->req.error = bdrv_co_discard(bs, acb->req.sector, acb->req.nb_sectors);
+ acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
+ qemu_bh_schedule(acb->bh);
+}
+
+BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ Coroutine *co;
+ BlockDriverAIOCBCoroutine *acb;
+
+ trace_bdrv_aio_discard(bs, sector_num, nb_sectors, opaque);
+
+ acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque);
+ acb->req.sector = sector_num;
+ acb->req.nb_sectors = nb_sectors;
+ acb->done = NULL;
+ co = qemu_coroutine_create(bdrv_aio_discard_co_entry);
+ qemu_coroutine_enter(co, acb);
+
+ return &acb->common;
+}
+
+void bdrv_init(void)
+{
+ module_call_init(MODULE_INIT_BLOCK);
+}
+
+void bdrv_init_with_whitelist(void)
+{
+ use_bdrv_whitelist = 1;
+ bdrv_init();
+}
+
+void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ BlockDriverAIOCB *acb;
+
+ acb = g_slice_alloc(aiocb_info->aiocb_size);
+ acb->aiocb_info = aiocb_info;
+ acb->bs = bs;
+ acb->cb = cb;
+ acb->opaque = opaque;
+ return acb;
+}
+
+void qemu_aio_release(void *p)
+{
+ BlockDriverAIOCB *acb = p;
+ g_slice_free1(acb->aiocb_info->aiocb_size, acb);
+}
+
+/**************************************************************/
+/* Coroutine block device emulation */
+
+typedef struct CoroutineIOCompletion {
+ Coroutine *coroutine;
+ int ret;
+} CoroutineIOCompletion;
+
+static void bdrv_co_io_em_complete(void *opaque, int ret)
+{
+ CoroutineIOCompletion *co = opaque;
+
+ co->ret = ret;
+ qemu_coroutine_enter(co->coroutine, NULL);
+}
+
+static int coroutine_fn bdrv_co_io_em(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *iov,
+ bool is_write)
+{
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+ BlockDriverAIOCB *acb;
+
+ if (is_write) {
+ acb = bs->drv->bdrv_aio_writev(bs, sector_num, iov, nb_sectors,
+ bdrv_co_io_em_complete, &co);
+ } else {
+ acb = bs->drv->bdrv_aio_readv(bs, sector_num, iov, nb_sectors,
+ bdrv_co_io_em_complete, &co);
+ }
+
+ trace_bdrv_co_io_em(bs, sector_num, nb_sectors, is_write, acb);
+ if (!acb) {
+ return -EIO;
+ }
+ qemu_coroutine_yield();
+
+ return co.ret;
+}
+
+static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ QEMUIOVector *iov)
+{
+ return bdrv_co_io_em(bs, sector_num, nb_sectors, iov, false);
+}
+
+static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ QEMUIOVector *iov)
+{
+ return bdrv_co_io_em(bs, sector_num, nb_sectors, iov, true);
+}
+
+static void coroutine_fn bdrv_flush_co_entry(void *opaque)
+{
+ RwCo *rwco = opaque;
+
+ rwco->ret = bdrv_co_flush(rwco->bs);
+}
+
+int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
+{
+ int ret;
+
+ if (!bs || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
+ return 0;
+ }
+
+ /* Write back cached data to the OS even with cache=unsafe */
+ BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_OS);
+ if (bs->drv->bdrv_co_flush_to_os) {
+ ret = bs->drv->bdrv_co_flush_to_os(bs);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ /* But don't actually force it to the disk with cache=unsafe */
+ if (bs->open_flags & BDRV_O_NO_FLUSH) {
+ goto flush_parent;
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_DISK);
+ if (bs->drv->bdrv_co_flush_to_disk) {
+ ret = bs->drv->bdrv_co_flush_to_disk(bs);
+ } else if (bs->drv->bdrv_aio_flush) {
+ BlockDriverAIOCB *acb;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ acb = bs->drv->bdrv_aio_flush(bs, bdrv_co_io_em_complete, &co);
+ if (acb == NULL) {
+ ret = -EIO;
+ } else {
+ qemu_coroutine_yield();
+ ret = co.ret;
+ }
+ } else {
+ /*
+ * Some block drivers always operate in either writethrough or unsafe
+ * mode and don't support bdrv_flush therefore. Usually qemu doesn't
+ * know how the server works (because the behaviour is hardcoded or
+ * depends on server-side configuration), so we can't ensure that
+ * everything is safe on disk. Returning an error doesn't work because
+ * that would break guests even if the server operates in writethrough
+ * mode.
+ *
+ * Let's hope the user knows what he's doing.
+ */
+ ret = 0;
+ }
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Now flush the underlying protocol. It will also have BDRV_O_NO_FLUSH
+ * in the case of cache=unsafe, so there are no useless flushes.
+ */
+flush_parent:
+ return bdrv_co_flush(bs->file);
+}
+
+void bdrv_invalidate_cache(BlockDriverState *bs)
+{
+ if (bs->drv && bs->drv->bdrv_invalidate_cache) {
+ bs->drv->bdrv_invalidate_cache(bs);
+ }
+}
+
+void bdrv_invalidate_cache_all(void)
+{
+ BlockDriverState *bs;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ bdrv_invalidate_cache(bs);
+ }
+}
+
+void bdrv_clear_incoming_migration_all(void)
+{
+ BlockDriverState *bs;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ bs->open_flags = bs->open_flags & ~(BDRV_O_INCOMING);
+ }
+}
+
+int bdrv_flush(BlockDriverState *bs)
+{
+ Coroutine *co;
+ RwCo rwco = {
+ .bs = bs,
+ .ret = NOT_DONE,
+ };
+
+ if (qemu_in_coroutine()) {
+ /* Fast-path if already in coroutine context */
+ bdrv_flush_co_entry(&rwco);
+ } else {
+ co = qemu_coroutine_create(bdrv_flush_co_entry);
+ qemu_coroutine_enter(co, &rwco);
+ while (rwco.ret == NOT_DONE) {
+ qemu_aio_wait();
+ }
+ }
+
+ return rwco.ret;
+}
+
+static void coroutine_fn bdrv_discard_co_entry(void *opaque)
+{
+ RwCo *rwco = opaque;
+
+ rwco->ret = bdrv_co_discard(rwco->bs, rwco->sector_num, rwco->nb_sectors);
+}
+
+int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors)
+{
+ if (!bs->drv) {
+ return -ENOMEDIUM;
+ } else if (bdrv_check_request(bs, sector_num, nb_sectors)) {
+ return -EIO;
+ } else if (bs->read_only) {
+ return -EROFS;
+ }
+
+ if (bs->dirty_bitmap) {
+ bdrv_reset_dirty(bs, sector_num, nb_sectors);
+ }
+
+ /* Do nothing if disabled. */
+ if (!(bs->open_flags & BDRV_O_UNMAP)) {
+ return 0;
+ }
+
+ if (bs->drv->bdrv_co_discard) {
+ return bs->drv->bdrv_co_discard(bs, sector_num, nb_sectors);
+ } else if (bs->drv->bdrv_aio_discard) {
+ BlockDriverAIOCB *acb;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ acb = bs->drv->bdrv_aio_discard(bs, sector_num, nb_sectors,
+ bdrv_co_io_em_complete, &co);
+ if (acb == NULL) {
+ return -EIO;
+ } else {
+ qemu_coroutine_yield();
+ return co.ret;
+ }
+ } else {
+ return 0;
+ }
+}
+
+int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
+{
+ Coroutine *co;
+ RwCo rwco = {
+ .bs = bs,
+ .sector_num = sector_num,
+ .nb_sectors = nb_sectors,
+ .ret = NOT_DONE,
+ };
+
+ if (qemu_in_coroutine()) {
+ /* Fast-path if already in coroutine context */
+ bdrv_discard_co_entry(&rwco);
+ } else {
+ co = qemu_coroutine_create(bdrv_discard_co_entry);
+ qemu_coroutine_enter(co, &rwco);
+ while (rwco.ret == NOT_DONE) {
+ qemu_aio_wait();
+ }
+ }
+
+ return rwco.ret;
+}
+
+/**************************************************************/
+/* removable device support */
+
+/**
+ * Return TRUE if the media is present
+ */
+int bdrv_is_inserted(BlockDriverState *bs)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (!drv)
+ return 0;
+ if (!drv->bdrv_is_inserted)
+ return 1;
+ return drv->bdrv_is_inserted(bs);
+}
+
+/**
+ * Return whether the media changed since the last call to this
+ * function, or -ENOTSUP if we don't know. Most drivers don't know.
+ */
+int bdrv_media_changed(BlockDriverState *bs)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (drv && drv->bdrv_media_changed) {
+ return drv->bdrv_media_changed(bs);
+ }
+ return -ENOTSUP;
+}
+
+/**
+ * If eject_flag is TRUE, eject the media. Otherwise, close the tray
+ */
+void bdrv_eject(BlockDriverState *bs, bool eject_flag)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (drv && drv->bdrv_eject) {
+ drv->bdrv_eject(bs, eject_flag);
+ }
+
+ if (bs->device_name[0] != '\0') {
+ bdrv_emit_qmp_eject_event(bs, eject_flag);
+ }
+}
+
+/**
+ * Lock or unlock the media (if it is locked, the user won't be able
+ * to eject it manually).
+ */
+void bdrv_lock_medium(BlockDriverState *bs, bool locked)
+{
+ BlockDriver *drv = bs->drv;
+
+ trace_bdrv_lock_medium(bs, locked);
+
+ if (drv && drv->bdrv_lock_medium) {
+ drv->bdrv_lock_medium(bs, locked);
+ }
+}
+
+/* needed for generic scsi interface */
+
+int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (drv && drv->bdrv_ioctl)
+ return drv->bdrv_ioctl(bs, req, buf);
+ return -ENOTSUP;
+}
+
+BlockDriverAIOCB *bdrv_aio_ioctl(BlockDriverState *bs,
+ unsigned long int req, void *buf,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (drv && drv->bdrv_aio_ioctl)
+ return drv->bdrv_aio_ioctl(bs, req, buf, cb, opaque);
+ return NULL;
+}
+
+void bdrv_set_buffer_alignment(BlockDriverState *bs, int align)
+{
+ bs->buffer_alignment = align;
+}
+
+void *qemu_blockalign(BlockDriverState *bs, size_t size)
+{
+ return qemu_memalign((bs && bs->buffer_alignment) ? bs->buffer_alignment : 512, size);
+}
+
+/*
+ * Check if all memory in this vector is sector aligned.
+ */
+bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
+{
+ int i;
+
+ for (i = 0; i < qiov->niov; i++) {
+ if ((uintptr_t) qiov->iov[i].iov_base % bs->buffer_alignment) {
+ return false;
+ }
+ }
+
+ return true;
+}
+
+void bdrv_set_dirty_tracking(BlockDriverState *bs, int granularity)
+{
+ int64_t bitmap_size;
+
+ assert((granularity & (granularity - 1)) == 0);
+
+ if (granularity) {
+ granularity >>= BDRV_SECTOR_BITS;
+ assert(!bs->dirty_bitmap);
+ bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS);
+ bs->dirty_bitmap = hbitmap_alloc(bitmap_size, ffs(granularity) - 1);
+ } else {
+ if (bs->dirty_bitmap) {
+ hbitmap_free(bs->dirty_bitmap);
+ bs->dirty_bitmap = NULL;
+ }
+ }
+}
+
+int bdrv_get_dirty(BlockDriverState *bs, int64_t sector)
+{
+ if (bs->dirty_bitmap) {
+ return hbitmap_get(bs->dirty_bitmap, sector);
+ } else {
+ return 0;
+ }
+}
+
+void bdrv_dirty_iter_init(BlockDriverState *bs, HBitmapIter *hbi)
+{
+ hbitmap_iter_init(hbi, bs->dirty_bitmap, 0);
+}
+
+void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
+ int nr_sectors)
+{
+ hbitmap_set(bs->dirty_bitmap, cur_sector, nr_sectors);
+}
+
+void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
+ int nr_sectors)
+{
+ hbitmap_reset(bs->dirty_bitmap, cur_sector, nr_sectors);
+}
+
+int64_t bdrv_get_dirty_count(BlockDriverState *bs)
+{
+ if (bs->dirty_bitmap) {
+ return hbitmap_count(bs->dirty_bitmap);
+ } else {
+ return 0;
+ }
+}
+
+void bdrv_set_in_use(BlockDriverState *bs, int in_use)
+{
+ assert(bs->in_use != in_use);
+ bs->in_use = in_use;
+}
+
+int bdrv_in_use(BlockDriverState *bs)
+{
+ return bs->in_use;
+}
+
+void bdrv_iostatus_enable(BlockDriverState *bs)
+{
+ bs->iostatus_enabled = true;
+ bs->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
+}
+
+/* The I/O status is only enabled if the drive explicitly
+ * enables it _and_ the VM is configured to stop on errors */
+bool bdrv_iostatus_is_enabled(const BlockDriverState *bs)
+{
+ return (bs->iostatus_enabled &&
+ (bs->on_write_error == BLOCKDEV_ON_ERROR_ENOSPC ||
+ bs->on_write_error == BLOCKDEV_ON_ERROR_STOP ||
+ bs->on_read_error == BLOCKDEV_ON_ERROR_STOP));
+}
+
+void bdrv_iostatus_disable(BlockDriverState *bs)
+{
+ bs->iostatus_enabled = false;
+}
+
+void bdrv_iostatus_reset(BlockDriverState *bs)
+{
+ if (bdrv_iostatus_is_enabled(bs)) {
+ bs->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
+ if (bs->job) {
+ block_job_iostatus_reset(bs->job);
+ }
+ }
+}
+
+void bdrv_iostatus_set_err(BlockDriverState *bs, int error)
+{
+ assert(bdrv_iostatus_is_enabled(bs));
+ if (bs->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
+ bs->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
+ BLOCK_DEVICE_IO_STATUS_FAILED;
+ }
+}
+
+void
+bdrv_acct_start(BlockDriverState *bs, BlockAcctCookie *cookie, int64_t bytes,
+ enum BlockAcctType type)
+{
+ assert(type < BDRV_MAX_IOTYPE);
+
+ cookie->bytes = bytes;
+ cookie->start_time_ns = get_clock();
+ cookie->type = type;
+}
+
+void
+bdrv_acct_done(BlockDriverState *bs, BlockAcctCookie *cookie)
+{
+ assert(cookie->type < BDRV_MAX_IOTYPE);
+
+ bs->nr_bytes[cookie->type] += cookie->bytes;
+ bs->nr_ops[cookie->type]++;
+ bs->total_time_ns[cookie->type] += get_clock() - cookie->start_time_ns;
+}
+
+void bdrv_img_create(const char *filename, const char *fmt,
+ const char *base_filename, const char *base_fmt,
+ char *options, uint64_t img_size, int flags,
+ Error **errp, bool quiet)
+{
+ QEMUOptionParameter *param = NULL, *create_options = NULL;
+ QEMUOptionParameter *backing_fmt, *backing_file, *size;
+ BlockDriverState *bs = NULL;
+ BlockDriver *drv, *proto_drv;
+ BlockDriver *backing_drv = NULL;
+ int ret = 0;
+
+ /* Find driver and parse its options */
+ drv = bdrv_find_format(fmt);
+ if (!drv) {
+ error_setg(errp, "Unknown file format '%s'", fmt);
+ return;
+ }
+
+ proto_drv = bdrv_find_protocol(filename, true);
+ if (!proto_drv) {
+ error_setg(errp, "Unknown protocol '%s'", filename);
+ return;
+ }
+
+ create_options = append_option_parameters(create_options,
+ drv->create_options);
+ create_options = append_option_parameters(create_options,
+ proto_drv->create_options);
+
+ /* Create parameter list with default values */
+ param = parse_option_parameters("", create_options, param);
+
+ set_option_parameter_int(param, BLOCK_OPT_SIZE, img_size);
+
+ /* Parse -o options */
+ if (options) {
+ param = parse_option_parameters(options, create_options, param);
+ if (param == NULL) {
+ error_setg(errp, "Invalid options for file format '%s'.", fmt);
+ goto out;
+ }
+ }
+
+ if (base_filename) {
+ if (set_option_parameter(param, BLOCK_OPT_BACKING_FILE,
+ base_filename)) {
+ error_setg(errp, "Backing file not supported for file format '%s'",
+ fmt);
+ goto out;
+ }
+ }
+
+ if (base_fmt) {
+ if (set_option_parameter(param, BLOCK_OPT_BACKING_FMT, base_fmt)) {
+ error_setg(errp, "Backing file format not supported for file "
+ "format '%s'", fmt);
+ goto out;
+ }
+ }
+
+ backing_file = get_option_parameter(param, BLOCK_OPT_BACKING_FILE);
+ if (backing_file && backing_file->value.s) {
+ if (!strcmp(filename, backing_file->value.s)) {
+ error_setg(errp, "Error: Trying to create an image with the "
+ "same filename as the backing file");
+ goto out;
+ }
+ }
+
+ backing_fmt = get_option_parameter(param, BLOCK_OPT_BACKING_FMT);
+ if (backing_fmt && backing_fmt->value.s) {
+ backing_drv = bdrv_find_format(backing_fmt->value.s);
+ if (!backing_drv) {
+ error_setg(errp, "Unknown backing file format '%s'",
+ backing_fmt->value.s);
+ goto out;
+ }
+ }
+
+ // The size for the image must always be specified, with one exception:
+ // If we are using a backing file, we can obtain the size from there
+ size = get_option_parameter(param, BLOCK_OPT_SIZE);
+ if (size && size->value.n == -1) {
+ if (backing_file && backing_file->value.s) {
+ uint64_t size;
+ char buf[32];
+ int back_flags;
+
+ /* backing files always opened read-only */
+ back_flags =
+ flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
+
+ bs = bdrv_new("");
+
+ ret = bdrv_open(bs, backing_file->value.s, NULL, back_flags,
+ backing_drv);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not open '%s'",
+ backing_file->value.s);
+ goto out;
+ }
+ bdrv_get_geometry(bs, &size);
+ size *= 512;
+
+ snprintf(buf, sizeof(buf), "%" PRId64, size);
+ set_option_parameter(param, BLOCK_OPT_SIZE, buf);
+ } else {
+ error_setg(errp, "Image creation needs a size parameter");
+ goto out;
+ }
+ }
+
+ if (!quiet) {
+ printf("Formatting '%s', fmt=%s ", filename, fmt);
+ print_option_parameters(param);
+ puts("");
+ }
+ ret = bdrv_create(drv, filename, param);
+ if (ret < 0) {
+ if (ret == -ENOTSUP) {
+ error_setg(errp,"Formatting or formatting option not supported for "
+ "file format '%s'", fmt);
+ } else if (ret == -EFBIG) {
+ const char *cluster_size_hint = "";
+ if (get_option_parameter(create_options, BLOCK_OPT_CLUSTER_SIZE)) {
+ cluster_size_hint = " (try using a larger cluster size)";
+ }
+ error_setg(errp, "The image size is too large for file format '%s'%s",
+ fmt, cluster_size_hint);
+ } else {
+ error_setg(errp, "%s: error while creating %s: %s", filename, fmt,
+ strerror(-ret));
+ }
+ }
+
+out:
+ free_option_parameters(create_options);
+ free_option_parameters(param);
+
+ if (bs) {
+ bdrv_delete(bs);
+ }
+}
+
+AioContext *bdrv_get_aio_context(BlockDriverState *bs)
+{
+ /* Currently BlockDriverState always uses the main loop AioContext */
+ return qemu_get_aio_context();
+}
+
+void bdrv_add_before_write_notifier(BlockDriverState *bs,
+ NotifierWithReturn *notifier)
+{
+ notifier_with_return_list_add(&bs->before_write_notifiers, notifier);
+}
diff --git a/contrib/qemu/block/qcow.c b/contrib/qemu/block/qcow.c
new file mode 100644
index 00000000000..5239bd68f1c
--- /dev/null
+++ b/contrib/qemu/block/qcow.c
@@ -0,0 +1,914 @@
+/*
+ * Block driver for the QCOW format
+ *
+ * Copyright (c) 2004-2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "qemu/module.h"
+#include <zlib.h>
+#include "qemu/aes.h"
+#include "migration/migration.h"
+
+/**************************************************************/
+/* QEMU COW block driver with compression and encryption support */
+
+#define QCOW_MAGIC (('Q' << 24) | ('F' << 16) | ('I' << 8) | 0xfb)
+#define QCOW_VERSION 1
+
+#define QCOW_CRYPT_NONE 0
+#define QCOW_CRYPT_AES 1
+
+#define QCOW_OFLAG_COMPRESSED (1LL << 63)
+
+typedef struct QCowHeader {
+ uint32_t magic;
+ uint32_t version;
+ uint64_t backing_file_offset;
+ uint32_t backing_file_size;
+ uint32_t mtime;
+ uint64_t size; /* in bytes */
+ uint8_t cluster_bits;
+ uint8_t l2_bits;
+ uint32_t crypt_method;
+ uint64_t l1_table_offset;
+} QCowHeader;
+
+#define L2_CACHE_SIZE 16
+
+typedef struct BDRVQcowState {
+ int cluster_bits;
+ int cluster_size;
+ int cluster_sectors;
+ int l2_bits;
+ int l2_size;
+ int l1_size;
+ uint64_t cluster_offset_mask;
+ uint64_t l1_table_offset;
+ uint64_t *l1_table;
+ uint64_t *l2_cache;
+ uint64_t l2_cache_offsets[L2_CACHE_SIZE];
+ uint32_t l2_cache_counts[L2_CACHE_SIZE];
+ uint8_t *cluster_cache;
+ uint8_t *cluster_data;
+ uint64_t cluster_cache_offset;
+ uint32_t crypt_method; /* current crypt method, 0 if no key yet */
+ uint32_t crypt_method_header;
+ AES_KEY aes_encrypt_key;
+ AES_KEY aes_decrypt_key;
+ CoMutex lock;
+ Error *migration_blocker;
+} BDRVQcowState;
+
+static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
+
+static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
+{
+ const QCowHeader *cow_header = (const void *)buf;
+
+ if (buf_size >= sizeof(QCowHeader) &&
+ be32_to_cpu(cow_header->magic) == QCOW_MAGIC &&
+ be32_to_cpu(cow_header->version) == QCOW_VERSION)
+ return 100;
+ else
+ return 0;
+}
+
+static int qcow_open(BlockDriverState *bs, QDict *options, int flags)
+{
+ BDRVQcowState *s = bs->opaque;
+ int len, i, shift, ret;
+ QCowHeader header;
+
+ ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
+ if (ret < 0) {
+ goto fail;
+ }
+ be32_to_cpus(&header.magic);
+ be32_to_cpus(&header.version);
+ be64_to_cpus(&header.backing_file_offset);
+ be32_to_cpus(&header.backing_file_size);
+ be32_to_cpus(&header.mtime);
+ be64_to_cpus(&header.size);
+ be32_to_cpus(&header.crypt_method);
+ be64_to_cpus(&header.l1_table_offset);
+
+ if (header.magic != QCOW_MAGIC) {
+ ret = -EMEDIUMTYPE;
+ goto fail;
+ }
+ if (header.version != QCOW_VERSION) {
+ char version[64];
+ snprintf(version, sizeof(version), "QCOW version %d", header.version);
+ qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+ bs->device_name, "qcow", version);
+ ret = -ENOTSUP;
+ goto fail;
+ }
+
+ if (header.size <= 1 || header.cluster_bits < 9) {
+ ret = -EINVAL;
+ goto fail;
+ }
+ if (header.crypt_method > QCOW_CRYPT_AES) {
+ ret = -EINVAL;
+ goto fail;
+ }
+ s->crypt_method_header = header.crypt_method;
+ if (s->crypt_method_header) {
+ bs->encrypted = 1;
+ }
+ s->cluster_bits = header.cluster_bits;
+ s->cluster_size = 1 << s->cluster_bits;
+ s->cluster_sectors = 1 << (s->cluster_bits - 9);
+ s->l2_bits = header.l2_bits;
+ s->l2_size = 1 << s->l2_bits;
+ bs->total_sectors = header.size / 512;
+ s->cluster_offset_mask = (1LL << (63 - s->cluster_bits)) - 1;
+
+ /* read the level 1 table */
+ shift = s->cluster_bits + s->l2_bits;
+ s->l1_size = (header.size + (1LL << shift) - 1) >> shift;
+
+ s->l1_table_offset = header.l1_table_offset;
+ s->l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
+
+ ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table,
+ s->l1_size * sizeof(uint64_t));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ for(i = 0;i < s->l1_size; i++) {
+ be64_to_cpus(&s->l1_table[i]);
+ }
+ /* alloc L2 cache */
+ s->l2_cache = g_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
+ s->cluster_cache = g_malloc(s->cluster_size);
+ s->cluster_data = g_malloc(s->cluster_size);
+ s->cluster_cache_offset = -1;
+
+ /* read the backing file name */
+ if (header.backing_file_offset != 0) {
+ len = header.backing_file_size;
+ if (len > 1023) {
+ len = 1023;
+ }
+ ret = bdrv_pread(bs->file, header.backing_file_offset,
+ bs->backing_file, len);
+ if (ret < 0) {
+ goto fail;
+ }
+ bs->backing_file[len] = '\0';
+ }
+
+ /* Disable migration when qcow images are used */
+ error_set(&s->migration_blocker,
+ QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+ "qcow", bs->device_name, "live migration");
+ migrate_add_blocker(s->migration_blocker);
+
+ qemu_co_mutex_init(&s->lock);
+ return 0;
+
+ fail:
+ g_free(s->l1_table);
+ g_free(s->l2_cache);
+ g_free(s->cluster_cache);
+ g_free(s->cluster_data);
+ return ret;
+}
+
+
+/* We have nothing to do for QCOW reopen, stubs just return
+ * success */
+static int qcow_reopen_prepare(BDRVReopenState *state,
+ BlockReopenQueue *queue, Error **errp)
+{
+ return 0;
+}
+
+static int qcow_set_key(BlockDriverState *bs, const char *key)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint8_t keybuf[16];
+ int len, i;
+
+ memset(keybuf, 0, 16);
+ len = strlen(key);
+ if (len > 16)
+ len = 16;
+ /* XXX: we could compress the chars to 7 bits to increase
+ entropy */
+ for(i = 0;i < len;i++) {
+ keybuf[i] = key[i];
+ }
+ s->crypt_method = s->crypt_method_header;
+
+ if (AES_set_encrypt_key(keybuf, 128, &s->aes_encrypt_key) != 0)
+ return -1;
+ if (AES_set_decrypt_key(keybuf, 128, &s->aes_decrypt_key) != 0)
+ return -1;
+ return 0;
+}
+
+/* The crypt function is compatible with the linux cryptoloop
+ algorithm for < 4 GB images. NOTE: out_buf == in_buf is
+ supported */
+static void encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
+ uint8_t *out_buf, const uint8_t *in_buf,
+ int nb_sectors, int enc,
+ const AES_KEY *key)
+{
+ union {
+ uint64_t ll[2];
+ uint8_t b[16];
+ } ivec;
+ int i;
+
+ for(i = 0; i < nb_sectors; i++) {
+ ivec.ll[0] = cpu_to_le64(sector_num);
+ ivec.ll[1] = 0;
+ AES_cbc_encrypt(in_buf, out_buf, 512, key,
+ ivec.b, enc);
+ sector_num++;
+ in_buf += 512;
+ out_buf += 512;
+ }
+}
+
+/* 'allocate' is:
+ *
+ * 0 to not allocate.
+ *
+ * 1 to allocate a normal cluster (for sector indexes 'n_start' to
+ * 'n_end')
+ *
+ * 2 to allocate a compressed cluster of size
+ * 'compressed_size'. 'compressed_size' must be > 0 and <
+ * cluster_size
+ *
+ * return 0 if not allocated.
+ */
+static uint64_t get_cluster_offset(BlockDriverState *bs,
+ uint64_t offset, int allocate,
+ int compressed_size,
+ int n_start, int n_end)
+{
+ BDRVQcowState *s = bs->opaque;
+ int min_index, i, j, l1_index, l2_index;
+ uint64_t l2_offset, *l2_table, cluster_offset, tmp;
+ uint32_t min_count;
+ int new_l2_table;
+
+ l1_index = offset >> (s->l2_bits + s->cluster_bits);
+ l2_offset = s->l1_table[l1_index];
+ new_l2_table = 0;
+ if (!l2_offset) {
+ if (!allocate)
+ return 0;
+ /* allocate a new l2 entry */
+ l2_offset = bdrv_getlength(bs->file);
+ /* round to cluster size */
+ l2_offset = (l2_offset + s->cluster_size - 1) & ~(s->cluster_size - 1);
+ /* update the L1 entry */
+ s->l1_table[l1_index] = l2_offset;
+ tmp = cpu_to_be64(l2_offset);
+ if (bdrv_pwrite_sync(bs->file,
+ s->l1_table_offset + l1_index * sizeof(tmp),
+ &tmp, sizeof(tmp)) < 0)
+ return 0;
+ new_l2_table = 1;
+ }
+ for(i = 0; i < L2_CACHE_SIZE; i++) {
+ if (l2_offset == s->l2_cache_offsets[i]) {
+ /* increment the hit count */
+ if (++s->l2_cache_counts[i] == 0xffffffff) {
+ for(j = 0; j < L2_CACHE_SIZE; j++) {
+ s->l2_cache_counts[j] >>= 1;
+ }
+ }
+ l2_table = s->l2_cache + (i << s->l2_bits);
+ goto found;
+ }
+ }
+ /* not found: load a new entry in the least used one */
+ min_index = 0;
+ min_count = 0xffffffff;
+ for(i = 0; i < L2_CACHE_SIZE; i++) {
+ if (s->l2_cache_counts[i] < min_count) {
+ min_count = s->l2_cache_counts[i];
+ min_index = i;
+ }
+ }
+ l2_table = s->l2_cache + (min_index << s->l2_bits);
+ if (new_l2_table) {
+ memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
+ if (bdrv_pwrite_sync(bs->file, l2_offset, l2_table,
+ s->l2_size * sizeof(uint64_t)) < 0)
+ return 0;
+ } else {
+ if (bdrv_pread(bs->file, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) !=
+ s->l2_size * sizeof(uint64_t))
+ return 0;
+ }
+ s->l2_cache_offsets[min_index] = l2_offset;
+ s->l2_cache_counts[min_index] = 1;
+ found:
+ l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
+ cluster_offset = be64_to_cpu(l2_table[l2_index]);
+ if (!cluster_offset ||
+ ((cluster_offset & QCOW_OFLAG_COMPRESSED) && allocate == 1)) {
+ if (!allocate)
+ return 0;
+ /* allocate a new cluster */
+ if ((cluster_offset & QCOW_OFLAG_COMPRESSED) &&
+ (n_end - n_start) < s->cluster_sectors) {
+ /* if the cluster is already compressed, we must
+ decompress it in the case it is not completely
+ overwritten */
+ if (decompress_cluster(bs, cluster_offset) < 0)
+ return 0;
+ cluster_offset = bdrv_getlength(bs->file);
+ cluster_offset = (cluster_offset + s->cluster_size - 1) &
+ ~(s->cluster_size - 1);
+ /* write the cluster content */
+ if (bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache, s->cluster_size) !=
+ s->cluster_size)
+ return -1;
+ } else {
+ cluster_offset = bdrv_getlength(bs->file);
+ if (allocate == 1) {
+ /* round to cluster size */
+ cluster_offset = (cluster_offset + s->cluster_size - 1) &
+ ~(s->cluster_size - 1);
+ bdrv_truncate(bs->file, cluster_offset + s->cluster_size);
+ /* if encrypted, we must initialize the cluster
+ content which won't be written */
+ if (s->crypt_method &&
+ (n_end - n_start) < s->cluster_sectors) {
+ uint64_t start_sect;
+ start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
+ memset(s->cluster_data + 512, 0x00, 512);
+ for(i = 0; i < s->cluster_sectors; i++) {
+ if (i < n_start || i >= n_end) {
+ encrypt_sectors(s, start_sect + i,
+ s->cluster_data,
+ s->cluster_data + 512, 1, 1,
+ &s->aes_encrypt_key);
+ if (bdrv_pwrite(bs->file, cluster_offset + i * 512,
+ s->cluster_data, 512) != 512)
+ return -1;
+ }
+ }
+ }
+ } else if (allocate == 2) {
+ cluster_offset |= QCOW_OFLAG_COMPRESSED |
+ (uint64_t)compressed_size << (63 - s->cluster_bits);
+ }
+ }
+ /* update L2 table */
+ tmp = cpu_to_be64(cluster_offset);
+ l2_table[l2_index] = tmp;
+ if (bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp),
+ &tmp, sizeof(tmp)) < 0)
+ return 0;
+ }
+ return cluster_offset;
+}
+
+static int coroutine_fn qcow_co_is_allocated(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, int *pnum)
+{
+ BDRVQcowState *s = bs->opaque;
+ int index_in_cluster, n;
+ uint64_t cluster_offset;
+
+ qemu_co_mutex_lock(&s->lock);
+ cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
+ qemu_co_mutex_unlock(&s->lock);
+ index_in_cluster = sector_num & (s->cluster_sectors - 1);
+ n = s->cluster_sectors - index_in_cluster;
+ if (n > nb_sectors)
+ n = nb_sectors;
+ *pnum = n;
+ return (cluster_offset != 0);
+}
+
+static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
+ const uint8_t *buf, int buf_size)
+{
+ z_stream strm1, *strm = &strm1;
+ int ret, out_len;
+
+ memset(strm, 0, sizeof(*strm));
+
+ strm->next_in = (uint8_t *)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;
+}
+
+static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret, csize;
+ uint64_t coffset;
+
+ coffset = cluster_offset & s->cluster_offset_mask;
+ if (s->cluster_cache_offset != coffset) {
+ csize = cluster_offset >> (63 - s->cluster_bits);
+ csize &= (s->cluster_size - 1);
+ ret = bdrv_pread(bs->file, coffset, s->cluster_data, csize);
+ if (ret != csize)
+ return -1;
+ if (decompress_buffer(s->cluster_cache, s->cluster_size,
+ s->cluster_data, csize) < 0) {
+ return -1;
+ }
+ s->cluster_cache_offset = coffset;
+ }
+ return 0;
+}
+
+static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov)
+{
+ BDRVQcowState *s = bs->opaque;
+ int index_in_cluster;
+ int ret = 0, n;
+ uint64_t cluster_offset;
+ struct iovec hd_iov;
+ QEMUIOVector hd_qiov;
+ uint8_t *buf;
+ void *orig_buf;
+
+ if (qiov->niov > 1) {
+ buf = orig_buf = qemu_blockalign(bs, qiov->size);
+ } else {
+ orig_buf = NULL;
+ buf = (uint8_t *)qiov->iov->iov_base;
+ }
+
+ qemu_co_mutex_lock(&s->lock);
+
+ while (nb_sectors != 0) {
+ /* prepare next request */
+ cluster_offset = get_cluster_offset(bs, sector_num << 9,
+ 0, 0, 0, 0);
+ index_in_cluster = sector_num & (s->cluster_sectors - 1);
+ n = s->cluster_sectors - index_in_cluster;
+ if (n > nb_sectors) {
+ n = nb_sectors;
+ }
+
+ if (!cluster_offset) {
+ if (bs->backing_hd) {
+ /* read from the base image */
+ hd_iov.iov_base = (void *)buf;
+ hd_iov.iov_len = n * 512;
+ qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_readv(bs->backing_hd, sector_num,
+ n, &hd_qiov);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ goto fail;
+ }
+ } else {
+ /* Note: in this case, no need to wait */
+ memset(buf, 0, 512 * n);
+ }
+ } else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
+ /* add AIO support for compressed blocks ? */
+ if (decompress_cluster(bs, cluster_offset) < 0) {
+ goto fail;
+ }
+ memcpy(buf,
+ s->cluster_cache + index_in_cluster * 512, 512 * n);
+ } else {
+ if ((cluster_offset & 511) != 0) {
+ goto fail;
+ }
+ hd_iov.iov_base = (void *)buf;
+ hd_iov.iov_len = n * 512;
+ qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_readv(bs->file,
+ (cluster_offset >> 9) + index_in_cluster,
+ n, &hd_qiov);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ break;
+ }
+ if (s->crypt_method) {
+ encrypt_sectors(s, sector_num, buf, buf,
+ n, 0,
+ &s->aes_decrypt_key);
+ }
+ }
+ ret = 0;
+
+ nb_sectors -= n;
+ sector_num += n;
+ buf += n * 512;
+ }
+
+done:
+ qemu_co_mutex_unlock(&s->lock);
+
+ if (qiov->niov > 1) {
+ qemu_iovec_from_buf(qiov, 0, orig_buf, qiov->size);
+ qemu_vfree(orig_buf);
+ }
+
+ return ret;
+
+fail:
+ ret = -EIO;
+ goto done;
+}
+
+static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov)
+{
+ BDRVQcowState *s = bs->opaque;
+ int index_in_cluster;
+ uint64_t cluster_offset;
+ const uint8_t *src_buf;
+ int ret = 0, n;
+ uint8_t *cluster_data = NULL;
+ struct iovec hd_iov;
+ QEMUIOVector hd_qiov;
+ uint8_t *buf;
+ void *orig_buf;
+
+ s->cluster_cache_offset = -1; /* disable compressed cache */
+
+ if (qiov->niov > 1) {
+ buf = orig_buf = qemu_blockalign(bs, qiov->size);
+ qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
+ } else {
+ orig_buf = NULL;
+ buf = (uint8_t *)qiov->iov->iov_base;
+ }
+
+ qemu_co_mutex_lock(&s->lock);
+
+ while (nb_sectors != 0) {
+
+ index_in_cluster = sector_num & (s->cluster_sectors - 1);
+ n = s->cluster_sectors - index_in_cluster;
+ if (n > nb_sectors) {
+ n = nb_sectors;
+ }
+ cluster_offset = get_cluster_offset(bs, sector_num << 9, 1, 0,
+ index_in_cluster,
+ index_in_cluster + n);
+ if (!cluster_offset || (cluster_offset & 511) != 0) {
+ ret = -EIO;
+ break;
+ }
+ if (s->crypt_method) {
+ if (!cluster_data) {
+ cluster_data = g_malloc0(s->cluster_size);
+ }
+ encrypt_sectors(s, sector_num, cluster_data, buf,
+ n, 1, &s->aes_encrypt_key);
+ src_buf = cluster_data;
+ } else {
+ src_buf = buf;
+ }
+
+ hd_iov.iov_base = (void *)src_buf;
+ hd_iov.iov_len = n * 512;
+ qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_writev(bs->file,
+ (cluster_offset >> 9) + index_in_cluster,
+ n, &hd_qiov);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ break;
+ }
+ ret = 0;
+
+ nb_sectors -= n;
+ sector_num += n;
+ buf += n * 512;
+ }
+ qemu_co_mutex_unlock(&s->lock);
+
+ if (qiov->niov > 1) {
+ qemu_vfree(orig_buf);
+ }
+ g_free(cluster_data);
+
+ return ret;
+}
+
+static void qcow_close(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+
+ g_free(s->l1_table);
+ g_free(s->l2_cache);
+ g_free(s->cluster_cache);
+ g_free(s->cluster_data);
+
+ migrate_del_blocker(s->migration_blocker);
+ error_free(s->migration_blocker);
+}
+
+static int qcow_create(const char *filename, QEMUOptionParameter *options)
+{
+ int header_size, backing_filename_len, l1_size, shift, i;
+ QCowHeader header;
+ uint8_t *tmp;
+ int64_t total_size = 0;
+ const char *backing_file = NULL;
+ int flags = 0;
+ int ret;
+ BlockDriverState *qcow_bs;
+
+ /* Read out options */
+ while (options && options->name) {
+ if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+ total_size = options->value.n / 512;
+ } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+ backing_file = options->value.s;
+ } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
+ flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
+ }
+ options++;
+ }
+
+ ret = bdrv_create_file(filename, options);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = bdrv_file_open(&qcow_bs, filename, NULL, BDRV_O_RDWR);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = bdrv_truncate(qcow_bs, 0);
+ if (ret < 0) {
+ goto exit;
+ }
+
+ memset(&header, 0, sizeof(header));
+ header.magic = cpu_to_be32(QCOW_MAGIC);
+ header.version = cpu_to_be32(QCOW_VERSION);
+ header.size = cpu_to_be64(total_size * 512);
+ header_size = sizeof(header);
+ backing_filename_len = 0;
+ if (backing_file) {
+ if (strcmp(backing_file, "fat:")) {
+ header.backing_file_offset = cpu_to_be64(header_size);
+ backing_filename_len = strlen(backing_file);
+ header.backing_file_size = cpu_to_be32(backing_filename_len);
+ header_size += backing_filename_len;
+ } else {
+ /* special backing file for vvfat */
+ backing_file = NULL;
+ }
+ header.cluster_bits = 9; /* 512 byte cluster to avoid copying
+ unmodifyed sectors */
+ header.l2_bits = 12; /* 32 KB L2 tables */
+ } else {
+ header.cluster_bits = 12; /* 4 KB clusters */
+ header.l2_bits = 9; /* 4 KB L2 tables */
+ }
+ header_size = (header_size + 7) & ~7;
+ shift = header.cluster_bits + header.l2_bits;
+ l1_size = ((total_size * 512) + (1LL << shift) - 1) >> shift;
+
+ header.l1_table_offset = cpu_to_be64(header_size);
+ if (flags & BLOCK_FLAG_ENCRYPT) {
+ header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
+ } else {
+ header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
+ }
+
+ /* write all the data */
+ ret = bdrv_pwrite(qcow_bs, 0, &header, sizeof(header));
+ if (ret != sizeof(header)) {
+ goto exit;
+ }
+
+ if (backing_file) {
+ ret = bdrv_pwrite(qcow_bs, sizeof(header),
+ backing_file, backing_filename_len);
+ if (ret != backing_filename_len) {
+ goto exit;
+ }
+ }
+
+ tmp = g_malloc0(BDRV_SECTOR_SIZE);
+ for (i = 0; i < ((sizeof(uint64_t)*l1_size + BDRV_SECTOR_SIZE - 1)/
+ BDRV_SECTOR_SIZE); i++) {
+ ret = bdrv_pwrite(qcow_bs, header_size +
+ BDRV_SECTOR_SIZE*i, tmp, BDRV_SECTOR_SIZE);
+ if (ret != BDRV_SECTOR_SIZE) {
+ g_free(tmp);
+ goto exit;
+ }
+ }
+
+ g_free(tmp);
+ ret = 0;
+exit:
+ bdrv_delete(qcow_bs);
+ return ret;
+}
+
+static int qcow_make_empty(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint32_t l1_length = s->l1_size * sizeof(uint64_t);
+ int ret;
+
+ memset(s->l1_table, 0, l1_length);
+ if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table,
+ l1_length) < 0)
+ return -1;
+ ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
+ if (ret < 0)
+ return ret;
+
+ memset(s->l2_cache, 0, s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
+ memset(s->l2_cache_offsets, 0, L2_CACHE_SIZE * sizeof(uint64_t));
+ memset(s->l2_cache_counts, 0, L2_CACHE_SIZE * sizeof(uint32_t));
+
+ return 0;
+}
+
+/* XXX: put compressed sectors first, then all the cluster aligned
+ tables to avoid losing bytes in alignment */
+static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors)
+{
+ BDRVQcowState *s = bs->opaque;
+ z_stream strm;
+ int ret, out_len;
+ uint8_t *out_buf;
+ uint64_t cluster_offset;
+
+ if (nb_sectors != s->cluster_sectors) {
+ ret = -EINVAL;
+
+ /* Zero-pad last write if image size is not cluster aligned */
+ if (sector_num + nb_sectors == bs->total_sectors &&
+ nb_sectors < s->cluster_sectors) {
+ uint8_t *pad_buf = qemu_blockalign(bs, s->cluster_size);
+ memset(pad_buf, 0, s->cluster_size);
+ memcpy(pad_buf, buf, nb_sectors * BDRV_SECTOR_SIZE);
+ ret = qcow_write_compressed(bs, sector_num,
+ pad_buf, s->cluster_sectors);
+ qemu_vfree(pad_buf);
+ }
+ return ret;
+ }
+
+ out_buf = g_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
+
+ /* best compression, small window, no zlib header */
+ memset(&strm, 0, sizeof(strm));
+ ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION,
+ Z_DEFLATED, -12,
+ 9, Z_DEFAULT_STRATEGY);
+ if (ret != 0) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ strm.avail_in = s->cluster_size;
+ strm.next_in = (uint8_t *)buf;
+ strm.avail_out = s->cluster_size;
+ strm.next_out = out_buf;
+
+ ret = deflate(&strm, Z_FINISH);
+ if (ret != Z_STREAM_END && ret != Z_OK) {
+ deflateEnd(&strm);
+ ret = -EINVAL;
+ goto fail;
+ }
+ out_len = strm.next_out - out_buf;
+
+ deflateEnd(&strm);
+
+ if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
+ /* could not compress: write normal cluster */
+ ret = bdrv_write(bs, sector_num, buf, s->cluster_sectors);
+ if (ret < 0) {
+ goto fail;
+ }
+ } else {
+ cluster_offset = get_cluster_offset(bs, sector_num << 9, 2,
+ out_len, 0, 0);
+ if (cluster_offset == 0) {
+ ret = -EIO;
+ goto fail;
+ }
+
+ cluster_offset &= s->cluster_offset_mask;
+ ret = bdrv_pwrite(bs->file, cluster_offset, out_buf, out_len);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ ret = 0;
+fail:
+ g_free(out_buf);
+ return ret;
+}
+
+static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
+{
+ BDRVQcowState *s = bs->opaque;
+ bdi->cluster_size = s->cluster_size;
+ return 0;
+}
+
+
+static QEMUOptionParameter qcow_create_options[] = {
+ {
+ .name = BLOCK_OPT_SIZE,
+ .type = OPT_SIZE,
+ .help = "Virtual disk size"
+ },
+ {
+ .name = BLOCK_OPT_BACKING_FILE,
+ .type = OPT_STRING,
+ .help = "File name of a base image"
+ },
+ {
+ .name = BLOCK_OPT_ENCRYPT,
+ .type = OPT_FLAG,
+ .help = "Encrypt the image"
+ },
+ { NULL }
+};
+
+static BlockDriver bdrv_qcow = {
+ .format_name = "qcow",
+ .instance_size = sizeof(BDRVQcowState),
+ .bdrv_probe = qcow_probe,
+ .bdrv_open = qcow_open,
+ .bdrv_close = qcow_close,
+ .bdrv_reopen_prepare = qcow_reopen_prepare,
+ .bdrv_create = qcow_create,
+ .bdrv_has_zero_init = bdrv_has_zero_init_1,
+
+ .bdrv_co_readv = qcow_co_readv,
+ .bdrv_co_writev = qcow_co_writev,
+ .bdrv_co_is_allocated = qcow_co_is_allocated,
+
+ .bdrv_set_key = qcow_set_key,
+ .bdrv_make_empty = qcow_make_empty,
+ .bdrv_write_compressed = qcow_write_compressed,
+ .bdrv_get_info = qcow_get_info,
+
+ .create_options = qcow_create_options,
+};
+
+static void bdrv_qcow_init(void)
+{
+ bdrv_register(&bdrv_qcow);
+}
+
+block_init(bdrv_qcow_init);
diff --git a/contrib/qemu/block/qcow2-cache.c b/contrib/qemu/block/qcow2-cache.c
new file mode 100644
index 00000000000..2f3114ecc24
--- /dev/null
+++ b/contrib/qemu/block/qcow2-cache.c
@@ -0,0 +1,323 @@
+/*
+ * L2/refcount table cache for the QCOW2 format
+ *
+ * Copyright (c) 2010 Kevin Wolf <kwolf@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "block/block_int.h"
+#include "qemu-common.h"
+#include "qcow2.h"
+#include "trace.h"
+
+typedef struct Qcow2CachedTable {
+ void* table;
+ int64_t offset;
+ bool dirty;
+ int cache_hits;
+ int ref;
+} Qcow2CachedTable;
+
+struct Qcow2Cache {
+ Qcow2CachedTable* entries;
+ struct Qcow2Cache* depends;
+ int size;
+ bool depends_on_flush;
+};
+
+Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
+{
+ BDRVQcowState *s = bs->opaque;
+ Qcow2Cache *c;
+ int i;
+
+ c = g_malloc0(sizeof(*c));
+ c->size = num_tables;
+ c->entries = g_malloc0(sizeof(*c->entries) * num_tables);
+
+ for (i = 0; i < c->size; i++) {
+ c->entries[i].table = qemu_blockalign(bs, s->cluster_size);
+ }
+
+ return c;
+}
+
+int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c)
+{
+ int i;
+
+ for (i = 0; i < c->size; i++) {
+ assert(c->entries[i].ref == 0);
+ qemu_vfree(c->entries[i].table);
+ }
+
+ g_free(c->entries);
+ g_free(c);
+
+ return 0;
+}
+
+static int qcow2_cache_flush_dependency(BlockDriverState *bs, Qcow2Cache *c)
+{
+ int ret;
+
+ ret = qcow2_cache_flush(bs, c->depends);
+ if (ret < 0) {
+ return ret;
+ }
+
+ c->depends = NULL;
+ c->depends_on_flush = false;
+
+ return 0;
+}
+
+static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret = 0;
+
+ if (!c->entries[i].dirty || !c->entries[i].offset) {
+ return 0;
+ }
+
+ trace_qcow2_cache_entry_flush(qemu_coroutine_self(),
+ c == s->l2_table_cache, i);
+
+ if (c->depends) {
+ ret = qcow2_cache_flush_dependency(bs, c);
+ } else if (c->depends_on_flush) {
+ ret = bdrv_flush(bs->file);
+ if (ret >= 0) {
+ c->depends_on_flush = false;
+ }
+ }
+
+ if (ret < 0) {
+ return ret;
+ }
+
+ if (c == s->refcount_block_cache) {
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_UPDATE_PART);
+ } else if (c == s->l2_table_cache) {
+ BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
+ }
+
+ ret = bdrv_pwrite(bs->file, c->entries[i].offset, c->entries[i].table,
+ s->cluster_size);
+ if (ret < 0) {
+ return ret;
+ }
+
+ c->entries[i].dirty = false;
+
+ return 0;
+}
+
+int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
+{
+ BDRVQcowState *s = bs->opaque;
+ int result = 0;
+ int ret;
+ int i;
+
+ trace_qcow2_cache_flush(qemu_coroutine_self(), c == s->l2_table_cache);
+
+ for (i = 0; i < c->size; i++) {
+ ret = qcow2_cache_entry_flush(bs, c, i);
+ if (ret < 0 && result != -ENOSPC) {
+ result = ret;
+ }
+ }
+
+ if (result == 0) {
+ ret = bdrv_flush(bs->file);
+ if (ret < 0) {
+ result = ret;
+ }
+ }
+
+ return result;
+}
+
+int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
+ Qcow2Cache *dependency)
+{
+ int ret;
+
+ if (dependency->depends) {
+ ret = qcow2_cache_flush_dependency(bs, dependency);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ if (c->depends && (c->depends != dependency)) {
+ ret = qcow2_cache_flush_dependency(bs, c);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ c->depends = dependency;
+ return 0;
+}
+
+void qcow2_cache_depends_on_flush(Qcow2Cache *c)
+{
+ c->depends_on_flush = true;
+}
+
+static int qcow2_cache_find_entry_to_replace(Qcow2Cache *c)
+{
+ int i;
+ int min_count = INT_MAX;
+ int min_index = -1;
+
+
+ for (i = 0; i < c->size; i++) {
+ if (c->entries[i].ref) {
+ continue;
+ }
+
+ if (c->entries[i].cache_hits < min_count) {
+ min_index = i;
+ min_count = c->entries[i].cache_hits;
+ }
+
+ /* Give newer hits priority */
+ /* TODO Check how to optimize the replacement strategy */
+ c->entries[i].cache_hits /= 2;
+ }
+
+ if (min_index == -1) {
+ /* This can't happen in current synchronous code, but leave the check
+ * here as a reminder for whoever starts using AIO with the cache */
+ abort();
+ }
+ return min_index;
+}
+
+static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
+ uint64_t offset, void **table, bool read_from_disk)
+{
+ BDRVQcowState *s = bs->opaque;
+ int i;
+ int ret;
+
+ trace_qcow2_cache_get(qemu_coroutine_self(), c == s->l2_table_cache,
+ offset, read_from_disk);
+
+ /* Check if the table is already cached */
+ for (i = 0; i < c->size; i++) {
+ if (c->entries[i].offset == offset) {
+ goto found;
+ }
+ }
+
+ /* If not, write a table back and replace it */
+ i = qcow2_cache_find_entry_to_replace(c);
+ trace_qcow2_cache_get_replace_entry(qemu_coroutine_self(),
+ c == s->l2_table_cache, i);
+ if (i < 0) {
+ return i;
+ }
+
+ ret = qcow2_cache_entry_flush(bs, c, i);
+ if (ret < 0) {
+ return ret;
+ }
+
+ trace_qcow2_cache_get_read(qemu_coroutine_self(),
+ c == s->l2_table_cache, i);
+ c->entries[i].offset = 0;
+ if (read_from_disk) {
+ if (c == s->l2_table_cache) {
+ BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
+ }
+
+ ret = bdrv_pread(bs->file, offset, c->entries[i].table, s->cluster_size);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ /* Give the table some hits for the start so that it won't be replaced
+ * immediately. The number 32 is completely arbitrary. */
+ c->entries[i].cache_hits = 32;
+ c->entries[i].offset = offset;
+
+ /* And return the right table */
+found:
+ c->entries[i].cache_hits++;
+ c->entries[i].ref++;
+ *table = c->entries[i].table;
+
+ trace_qcow2_cache_get_done(qemu_coroutine_self(),
+ c == s->l2_table_cache, i);
+
+ return 0;
+}
+
+int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
+ void **table)
+{
+ return qcow2_cache_do_get(bs, c, offset, table, true);
+}
+
+int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
+ void **table)
+{
+ return qcow2_cache_do_get(bs, c, offset, table, false);
+}
+
+int qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table)
+{
+ int i;
+
+ for (i = 0; i < c->size; i++) {
+ if (c->entries[i].table == *table) {
+ goto found;
+ }
+ }
+ return -ENOENT;
+
+found:
+ c->entries[i].ref--;
+ *table = NULL;
+
+ assert(c->entries[i].ref >= 0);
+ return 0;
+}
+
+void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table)
+{
+ int i;
+
+ for (i = 0; i < c->size; i++) {
+ if (c->entries[i].table == table) {
+ goto found;
+ }
+ }
+ abort();
+
+found:
+ c->entries[i].dirty = true;
+}
diff --git a/contrib/qemu/block/qcow2-cluster.c b/contrib/qemu/block/qcow2-cluster.c
new file mode 100644
index 00000000000..cca76d4fcdd
--- /dev/null
+++ b/contrib/qemu/block/qcow2-cluster.c
@@ -0,0 +1,1478 @@
+/*
+ * Block driver for the QCOW version 2 format
+ *
+ * Copyright (c) 2004-2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include <zlib.h>
+
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "block/qcow2.h"
+#include "trace.h"
+
+int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
+ bool exact_size)
+{
+ BDRVQcowState *s = bs->opaque;
+ int new_l1_size2, ret, i;
+ uint64_t *new_l1_table;
+ int64_t new_l1_table_offset, new_l1_size;
+ uint8_t data[12];
+
+ if (min_size <= s->l1_size)
+ return 0;
+
+ if (exact_size) {
+ new_l1_size = min_size;
+ } else {
+ /* Bump size up to reduce the number of times we have to grow */
+ new_l1_size = s->l1_size;
+ if (new_l1_size == 0) {
+ new_l1_size = 1;
+ }
+ while (min_size > new_l1_size) {
+ new_l1_size = (new_l1_size * 3 + 1) / 2;
+ }
+ }
+
+ if (new_l1_size > INT_MAX) {
+ return -EFBIG;
+ }
+
+#ifdef DEBUG_ALLOC2
+ fprintf(stderr, "grow l1_table from %d to %" PRId64 "\n",
+ s->l1_size, new_l1_size);
+#endif
+
+ new_l1_size2 = sizeof(uint64_t) * new_l1_size;
+ new_l1_table = g_malloc0(align_offset(new_l1_size2, 512));
+ memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));
+
+ /* write new table (align to cluster) */
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ALLOC_TABLE);
+ new_l1_table_offset = qcow2_alloc_clusters(bs, new_l1_size2);
+ if (new_l1_table_offset < 0) {
+ g_free(new_l1_table);
+ return new_l1_table_offset;
+ }
+
+ ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE);
+ for(i = 0; i < s->l1_size; i++)
+ new_l1_table[i] = cpu_to_be64(new_l1_table[i]);
+ ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset, new_l1_table, new_l1_size2);
+ if (ret < 0)
+ goto fail;
+ for(i = 0; i < s->l1_size; i++)
+ new_l1_table[i] = be64_to_cpu(new_l1_table[i]);
+
+ /* set new table */
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE);
+ cpu_to_be32w((uint32_t*)data, new_l1_size);
+ cpu_to_be64wu((uint64_t*)(data + 4), new_l1_table_offset);
+ ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), data,sizeof(data));
+ if (ret < 0) {
+ goto fail;
+ }
+ g_free(s->l1_table);
+ qcow2_free_clusters(bs, s->l1_table_offset, s->l1_size * sizeof(uint64_t),
+ QCOW2_DISCARD_OTHER);
+ s->l1_table_offset = new_l1_table_offset;
+ s->l1_table = new_l1_table;
+ s->l1_size = new_l1_size;
+ return 0;
+ fail:
+ g_free(new_l1_table);
+ qcow2_free_clusters(bs, new_l1_table_offset, new_l1_size2,
+ QCOW2_DISCARD_OTHER);
+ return ret;
+}
+
+/*
+ * l2_load
+ *
+ * Loads a L2 table into memory. If the table is in the cache, the cache
+ * is used; otherwise the L2 table is loaded from the image file.
+ *
+ * Returns a pointer to the L2 table on success, or NULL if the read from
+ * the image file failed.
+ */
+
+static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
+ uint64_t **l2_table)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret;
+
+ ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, (void**) l2_table);
+
+ return ret;
+}
+
+/*
+ * Writes one sector of the L1 table to the disk (can't update single entries
+ * and we really don't want bdrv_pread to perform a read-modify-write)
+ */
+#define L1_ENTRIES_PER_SECTOR (512 / 8)
+static int write_l1_entry(BlockDriverState *bs, int l1_index)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t buf[L1_ENTRIES_PER_SECTOR];
+ int l1_start_index;
+ int i, ret;
+
+ l1_start_index = l1_index & ~(L1_ENTRIES_PER_SECTOR - 1);
+ for (i = 0; i < L1_ENTRIES_PER_SECTOR; i++) {
+ buf[i] = cpu_to_be64(s->l1_table[l1_start_index + i]);
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE);
+ ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + 8 * l1_start_index,
+ buf, sizeof(buf));
+ if (ret < 0) {
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * l2_allocate
+ *
+ * Allocate a new l2 entry in the file. If l1_index points to an already
+ * used entry in the L2 table (i.e. we are doing a copy on write for the L2
+ * table) copy the contents of the old L2 table into the newly allocated one.
+ * Otherwise the new table is initialized with zeros.
+ *
+ */
+
+static int l2_allocate(BlockDriverState *bs, int l1_index, uint64_t **table)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t old_l2_offset;
+ uint64_t *l2_table;
+ int64_t l2_offset;
+ int ret;
+
+ old_l2_offset = s->l1_table[l1_index];
+
+ trace_qcow2_l2_allocate(bs, l1_index);
+
+ /* allocate a new l2 entry */
+
+ l2_offset = qcow2_alloc_clusters(bs, s->l2_size * sizeof(uint64_t));
+ if (l2_offset < 0) {
+ return l2_offset;
+ }
+
+ ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* allocate a new entry in the l2 cache */
+
+ trace_qcow2_l2_allocate_get_empty(bs, l1_index);
+ ret = qcow2_cache_get_empty(bs, s->l2_table_cache, l2_offset, (void**) table);
+ if (ret < 0) {
+ return ret;
+ }
+
+ l2_table = *table;
+
+ if ((old_l2_offset & L1E_OFFSET_MASK) == 0) {
+ /* if there was no old l2 table, clear the new table */
+ memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
+ } else {
+ uint64_t* old_table;
+
+ /* if there was an old l2 table, read it from the disk */
+ BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_COW_READ);
+ ret = qcow2_cache_get(bs, s->l2_table_cache,
+ old_l2_offset & L1E_OFFSET_MASK,
+ (void**) &old_table);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ memcpy(l2_table, old_table, s->cluster_size);
+
+ ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &old_table);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ /* write the l2 table to the file */
+ BLKDBG_EVENT(bs->file, BLKDBG_L2_ALLOC_WRITE);
+
+ trace_qcow2_l2_allocate_write_l2(bs, l1_index);
+ qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+ ret = qcow2_cache_flush(bs, s->l2_table_cache);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* update the L1 entry */
+ trace_qcow2_l2_allocate_write_l1(bs, l1_index);
+ s->l1_table[l1_index] = l2_offset | QCOW_OFLAG_COPIED;
+ ret = write_l1_entry(bs, l1_index);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ *table = l2_table;
+ trace_qcow2_l2_allocate_done(bs, l1_index, 0);
+ return 0;
+
+fail:
+ trace_qcow2_l2_allocate_done(bs, l1_index, ret);
+ qcow2_cache_put(bs, s->l2_table_cache, (void**) table);
+ s->l1_table[l1_index] = old_l2_offset;
+ return ret;
+}
+
+/*
+ * Checks how many clusters in a given L2 table are contiguous in the image
+ * file. As soon as one of the flags in the bitmask stop_flags changes compared
+ * to the first cluster, the search is stopped and the cluster is not counted
+ * as contiguous. (This allows it, for example, to stop at the first compressed
+ * cluster which may require a different handling)
+ */
+static int count_contiguous_clusters(uint64_t nb_clusters, int cluster_size,
+ uint64_t *l2_table, uint64_t start, uint64_t stop_flags)
+{
+ int i;
+ uint64_t mask = stop_flags | L2E_OFFSET_MASK;
+ uint64_t offset = be64_to_cpu(l2_table[0]) & mask;
+
+ if (!offset)
+ return 0;
+
+ for (i = start; i < start + nb_clusters; i++) {
+ uint64_t l2_entry = be64_to_cpu(l2_table[i]) & mask;
+ if (offset + (uint64_t) i * cluster_size != l2_entry) {
+ break;
+ }
+ }
+
+ return (i - start);
+}
+
+static int count_contiguous_free_clusters(uint64_t nb_clusters, uint64_t *l2_table)
+{
+ int i;
+
+ for (i = 0; i < nb_clusters; i++) {
+ int type = qcow2_get_cluster_type(be64_to_cpu(l2_table[i]));
+
+ if (type != QCOW2_CLUSTER_UNALLOCATED) {
+ break;
+ }
+ }
+
+ return i;
+}
+
+/* The crypt function is compatible with the linux cryptoloop
+ algorithm for < 4 GB images. NOTE: out_buf == in_buf is
+ supported */
+void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
+ uint8_t *out_buf, const uint8_t *in_buf,
+ int nb_sectors, int enc,
+ const AES_KEY *key)
+{
+ union {
+ uint64_t ll[2];
+ uint8_t b[16];
+ } ivec;
+ int i;
+
+ for(i = 0; i < nb_sectors; i++) {
+ ivec.ll[0] = cpu_to_le64(sector_num);
+ ivec.ll[1] = 0;
+ AES_cbc_encrypt(in_buf, out_buf, 512, key,
+ ivec.b, enc);
+ sector_num++;
+ in_buf += 512;
+ out_buf += 512;
+ }
+}
+
+static int coroutine_fn copy_sectors(BlockDriverState *bs,
+ uint64_t start_sect,
+ uint64_t cluster_offset,
+ int n_start, int n_end)
+{
+ BDRVQcowState *s = bs->opaque;
+ QEMUIOVector qiov;
+ struct iovec iov;
+ int n, ret;
+
+ /*
+ * If this is the last cluster and it is only partially used, we must only
+ * copy until the end of the image, or bdrv_check_request will fail for the
+ * bdrv_read/write calls below.
+ */
+ if (start_sect + n_end > bs->total_sectors) {
+ n_end = bs->total_sectors - start_sect;
+ }
+
+ n = n_end - n_start;
+ if (n <= 0) {
+ return 0;
+ }
+
+ iov.iov_len = n * BDRV_SECTOR_SIZE;
+ iov.iov_base = qemu_blockalign(bs, iov.iov_len);
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+
+ BLKDBG_EVENT(bs->file, BLKDBG_COW_READ);
+
+ /* Call .bdrv_co_readv() directly instead of using the public block-layer
+ * interface. This avoids double I/O throttling and request tracking,
+ * which can lead to deadlock when block layer copy-on-read is enabled.
+ */
+ ret = bs->drv->bdrv_co_readv(bs, start_sect + n_start, n, &qiov);
+ if (ret < 0) {
+ goto out;
+ }
+
+ if (s->crypt_method) {
+ qcow2_encrypt_sectors(s, start_sect + n_start,
+ iov.iov_base, iov.iov_base, n, 1,
+ &s->aes_encrypt_key);
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE);
+ ret = bdrv_co_writev(bs->file, (cluster_offset >> 9) + n_start, n, &qiov);
+ if (ret < 0) {
+ goto out;
+ }
+
+ ret = 0;
+out:
+ qemu_vfree(iov.iov_base);
+ return ret;
+}
+
+
+/*
+ * get_cluster_offset
+ *
+ * For a given offset of the disk image, find the cluster offset in
+ * qcow2 file. The offset is stored in *cluster_offset.
+ *
+ * on entry, *num is the number of contiguous sectors we'd like to
+ * access following offset.
+ *
+ * on exit, *num is the number of contiguous sectors we can read.
+ *
+ * Returns the cluster type (QCOW2_CLUSTER_*) on success, -errno in error
+ * cases.
+ */
+int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
+ int *num, uint64_t *cluster_offset)
+{
+ BDRVQcowState *s = bs->opaque;
+ unsigned int l2_index;
+ uint64_t l1_index, l2_offset, *l2_table;
+ int l1_bits, c;
+ unsigned int index_in_cluster, nb_clusters;
+ uint64_t nb_available, nb_needed;
+ int ret;
+
+ index_in_cluster = (offset >> 9) & (s->cluster_sectors - 1);
+ nb_needed = *num + index_in_cluster;
+
+ l1_bits = s->l2_bits + s->cluster_bits;
+
+ /* compute how many bytes there are between the offset and
+ * the end of the l1 entry
+ */
+
+ nb_available = (1ULL << l1_bits) - (offset & ((1ULL << l1_bits) - 1));
+
+ /* compute the number of available sectors */
+
+ nb_available = (nb_available >> 9) + index_in_cluster;
+
+ if (nb_needed > nb_available) {
+ nb_needed = nb_available;
+ }
+
+ *cluster_offset = 0;
+
+ /* seek the the l2 offset in the l1 table */
+
+ l1_index = offset >> l1_bits;
+ if (l1_index >= s->l1_size) {
+ ret = QCOW2_CLUSTER_UNALLOCATED;
+ goto out;
+ }
+
+ l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
+ if (!l2_offset) {
+ ret = QCOW2_CLUSTER_UNALLOCATED;
+ goto out;
+ }
+
+ /* load the l2 table in memory */
+
+ ret = l2_load(bs, l2_offset, &l2_table);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* find the cluster offset for the given disk offset */
+
+ l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
+ *cluster_offset = be64_to_cpu(l2_table[l2_index]);
+ nb_clusters = size_to_clusters(s, nb_needed << 9);
+
+ ret = qcow2_get_cluster_type(*cluster_offset);
+ switch (ret) {
+ case QCOW2_CLUSTER_COMPRESSED:
+ /* Compressed clusters can only be processed one by one */
+ c = 1;
+ *cluster_offset &= L2E_COMPRESSED_OFFSET_SIZE_MASK;
+ break;
+ case QCOW2_CLUSTER_ZERO:
+ if (s->qcow_version < 3) {
+ return -EIO;
+ }
+ c = count_contiguous_clusters(nb_clusters, s->cluster_size,
+ &l2_table[l2_index], 0,
+ QCOW_OFLAG_COMPRESSED | QCOW_OFLAG_ZERO);
+ *cluster_offset = 0;
+ break;
+ case QCOW2_CLUSTER_UNALLOCATED:
+ /* how many empty clusters ? */
+ c = count_contiguous_free_clusters(nb_clusters, &l2_table[l2_index]);
+ *cluster_offset = 0;
+ break;
+ case QCOW2_CLUSTER_NORMAL:
+ /* how many allocated clusters ? */
+ c = count_contiguous_clusters(nb_clusters, s->cluster_size,
+ &l2_table[l2_index], 0,
+ QCOW_OFLAG_COMPRESSED | QCOW_OFLAG_ZERO);
+ *cluster_offset &= L2E_OFFSET_MASK;
+ break;
+ default:
+ abort();
+ }
+
+ qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+
+ nb_available = (c * s->cluster_sectors);
+
+out:
+ if (nb_available > nb_needed)
+ nb_available = nb_needed;
+
+ *num = nb_available - index_in_cluster;
+
+ return ret;
+}
+
+/*
+ * get_cluster_table
+ *
+ * for a given disk offset, load (and allocate if needed)
+ * the l2 table.
+ *
+ * the l2 table offset in the qcow2 file and the cluster index
+ * in the l2 table are given to the caller.
+ *
+ * Returns 0 on success, -errno in failure case
+ */
+static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
+ uint64_t **new_l2_table,
+ int *new_l2_index)
+{
+ BDRVQcowState *s = bs->opaque;
+ unsigned int l2_index;
+ uint64_t l1_index, l2_offset;
+ uint64_t *l2_table = NULL;
+ int ret;
+
+ /* seek the the l2 offset in the l1 table */
+
+ l1_index = offset >> (s->l2_bits + s->cluster_bits);
+ if (l1_index >= s->l1_size) {
+ ret = qcow2_grow_l1_table(bs, l1_index + 1, false);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ assert(l1_index < s->l1_size);
+ l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
+
+ /* seek the l2 table of the given l2 offset */
+
+ if (s->l1_table[l1_index] & QCOW_OFLAG_COPIED) {
+ /* load the l2 table in memory */
+ ret = l2_load(bs, l2_offset, &l2_table);
+ if (ret < 0) {
+ return ret;
+ }
+ } else {
+ /* First allocate a new L2 table (and do COW if needed) */
+ ret = l2_allocate(bs, l1_index, &l2_table);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Then decrease the refcount of the old table */
+ if (l2_offset) {
+ qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t),
+ QCOW2_DISCARD_OTHER);
+ }
+ }
+
+ /* find the cluster offset for the given disk offset */
+
+ l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
+
+ *new_l2_table = l2_table;
+ *new_l2_index = l2_index;
+
+ return 0;
+}
+
+/*
+ * alloc_compressed_cluster_offset
+ *
+ * For a given offset of the disk image, return cluster offset in
+ * qcow2 file.
+ *
+ * If the offset is not found, allocate a new compressed cluster.
+ *
+ * Return the cluster offset if successful,
+ * Return 0, otherwise.
+ *
+ */
+
+uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
+ uint64_t offset,
+ int compressed_size)
+{
+ BDRVQcowState *s = bs->opaque;
+ int l2_index, ret;
+ uint64_t *l2_table;
+ int64_t cluster_offset;
+ int nb_csectors;
+
+ ret = get_cluster_table(bs, offset, &l2_table, &l2_index);
+ if (ret < 0) {
+ return 0;
+ }
+
+ /* Compression can't overwrite anything. Fail if the cluster was already
+ * allocated. */
+ cluster_offset = be64_to_cpu(l2_table[l2_index]);
+ if (cluster_offset & L2E_OFFSET_MASK) {
+ qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ return 0;
+ }
+
+ cluster_offset = qcow2_alloc_bytes(bs, compressed_size);
+ if (cluster_offset < 0) {
+ qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ return 0;
+ }
+
+ nb_csectors = ((cluster_offset + compressed_size - 1) >> 9) -
+ (cluster_offset >> 9);
+
+ cluster_offset |= QCOW_OFLAG_COMPRESSED |
+ ((uint64_t)nb_csectors << s->csize_shift);
+
+ /* update L2 table */
+
+ /* compressed clusters never have the copied flag */
+
+ BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE_COMPRESSED);
+ qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+ l2_table[l2_index] = cpu_to_be64(cluster_offset);
+ ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ if (ret < 0) {
+ return 0;
+ }
+
+ return cluster_offset;
+}
+
+static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret;
+
+ if (r->nb_sectors == 0) {
+ return 0;
+ }
+
+ qemu_co_mutex_unlock(&s->lock);
+ ret = copy_sectors(bs, m->offset / BDRV_SECTOR_SIZE, m->alloc_offset,
+ r->offset / BDRV_SECTOR_SIZE,
+ r->offset / BDRV_SECTOR_SIZE + r->nb_sectors);
+ qemu_co_mutex_lock(&s->lock);
+
+ if (ret < 0) {
+ return ret;
+ }
+
+ /*
+ * Before we update the L2 table to actually point to the new cluster, we
+ * need to be sure that the refcounts have been increased and COW was
+ * handled.
+ */
+ qcow2_cache_depends_on_flush(s->l2_table_cache);
+
+ return 0;
+}
+
+int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
+{
+ BDRVQcowState *s = bs->opaque;
+ int i, j = 0, l2_index, ret;
+ uint64_t *old_cluster, *l2_table;
+ uint64_t cluster_offset = m->alloc_offset;
+
+ trace_qcow2_cluster_link_l2(qemu_coroutine_self(), m->nb_clusters);
+ assert(m->nb_clusters > 0);
+
+ old_cluster = g_malloc(m->nb_clusters * sizeof(uint64_t));
+
+ /* copy content of unmodified sectors */
+ ret = perform_cow(bs, m, &m->cow_start);
+ if (ret < 0) {
+ goto err;
+ }
+
+ ret = perform_cow(bs, m, &m->cow_end);
+ if (ret < 0) {
+ goto err;
+ }
+
+ /* Update L2 table. */
+ if (s->use_lazy_refcounts) {
+ qcow2_mark_dirty(bs);
+ }
+ if (qcow2_need_accurate_refcounts(s)) {
+ qcow2_cache_set_dependency(bs, s->l2_table_cache,
+ s->refcount_block_cache);
+ }
+
+ ret = get_cluster_table(bs, m->offset, &l2_table, &l2_index);
+ if (ret < 0) {
+ goto err;
+ }
+ qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+
+ for (i = 0; i < m->nb_clusters; i++) {
+ /* if two concurrent writes happen to the same unallocated cluster
+ * each write allocates separate cluster and writes data concurrently.
+ * The first one to complete updates l2 table with pointer to its
+ * cluster the second one has to do RMW (which is done above by
+ * copy_sectors()), update l2 table with its cluster pointer and free
+ * old cluster. This is what this loop does */
+ if(l2_table[l2_index + i] != 0)
+ old_cluster[j++] = l2_table[l2_index + i];
+
+ l2_table[l2_index + i] = cpu_to_be64((cluster_offset +
+ (i << s->cluster_bits)) | QCOW_OFLAG_COPIED);
+ }
+
+
+ ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ if (ret < 0) {
+ goto err;
+ }
+
+ /*
+ * If this was a COW, we need to decrease the refcount of the old cluster.
+ * Also flush bs->file to get the right order for L2 and refcount update.
+ *
+ * Don't discard clusters that reach a refcount of 0 (e.g. compressed
+ * clusters), the next write will reuse them anyway.
+ */
+ if (j != 0) {
+ for (i = 0; i < j; i++) {
+ qcow2_free_any_clusters(bs, be64_to_cpu(old_cluster[i]), 1,
+ QCOW2_DISCARD_NEVER);
+ }
+ }
+
+ ret = 0;
+err:
+ g_free(old_cluster);
+ return ret;
+ }
+
+/*
+ * Returns the number of contiguous clusters that can be used for an allocating
+ * write, but require COW to be performed (this includes yet unallocated space,
+ * which must copy from the backing file)
+ */
+static int count_cow_clusters(BDRVQcowState *s, int nb_clusters,
+ uint64_t *l2_table, int l2_index)
+{
+ int i;
+
+ for (i = 0; i < nb_clusters; i++) {
+ uint64_t l2_entry = be64_to_cpu(l2_table[l2_index + i]);
+ int cluster_type = qcow2_get_cluster_type(l2_entry);
+
+ switch(cluster_type) {
+ case QCOW2_CLUSTER_NORMAL:
+ if (l2_entry & QCOW_OFLAG_COPIED) {
+ goto out;
+ }
+ break;
+ case QCOW2_CLUSTER_UNALLOCATED:
+ case QCOW2_CLUSTER_COMPRESSED:
+ case QCOW2_CLUSTER_ZERO:
+ break;
+ default:
+ abort();
+ }
+ }
+
+out:
+ assert(i <= nb_clusters);
+ return i;
+}
+
+/*
+ * Check if there already is an AIO write request in flight which allocates
+ * the same cluster. In this case we need to wait until the previous
+ * request has completed and updated the L2 table accordingly.
+ *
+ * Returns:
+ * 0 if there was no dependency. *cur_bytes indicates the number of
+ * bytes from guest_offset that can be read before the next
+ * dependency must be processed (or the request is complete)
+ *
+ * -EAGAIN if we had to wait for another request, previously gathered
+ * information on cluster allocation may be invalid now. The caller
+ * must start over anyway, so consider *cur_bytes undefined.
+ */
+static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
+ uint64_t *cur_bytes, QCowL2Meta **m)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowL2Meta *old_alloc;
+ uint64_t bytes = *cur_bytes;
+
+ QLIST_FOREACH(old_alloc, &s->cluster_allocs, next_in_flight) {
+
+ uint64_t start = guest_offset;
+ uint64_t end = start + bytes;
+ uint64_t old_start = l2meta_cow_start(old_alloc);
+ uint64_t old_end = l2meta_cow_end(old_alloc);
+
+ if (end <= old_start || start >= old_end) {
+ /* No intersection */
+ } else {
+ if (start < old_start) {
+ /* Stop at the start of a running allocation */
+ bytes = old_start - start;
+ } else {
+ bytes = 0;
+ }
+
+ /* Stop if already an l2meta exists. After yielding, it wouldn't
+ * be valid any more, so we'd have to clean up the old L2Metas
+ * and deal with requests depending on them before starting to
+ * gather new ones. Not worth the trouble. */
+ if (bytes == 0 && *m) {
+ *cur_bytes = 0;
+ return 0;
+ }
+
+ if (bytes == 0) {
+ /* Wait for the dependency to complete. We need to recheck
+ * the free/allocated clusters when we continue. */
+ qemu_co_mutex_unlock(&s->lock);
+ qemu_co_queue_wait(&old_alloc->dependent_requests);
+ qemu_co_mutex_lock(&s->lock);
+ return -EAGAIN;
+ }
+ }
+ }
+
+ /* Make sure that existing clusters and new allocations are only used up to
+ * the next dependency if we shortened the request above */
+ *cur_bytes = bytes;
+
+ return 0;
+}
+
+/*
+ * Checks how many already allocated clusters that don't require a copy on
+ * write there are at the given guest_offset (up to *bytes). If
+ * *host_offset is not zero, only physically contiguous clusters beginning at
+ * this host offset are counted.
+ *
+ * Note that guest_offset may not be cluster aligned. In this case, the
+ * returned *host_offset points to exact byte referenced by guest_offset and
+ * therefore isn't cluster aligned as well.
+ *
+ * Returns:
+ * 0: if no allocated clusters are available at the given offset.
+ * *bytes is normally unchanged. It is set to 0 if the cluster
+ * is allocated and doesn't need COW, but doesn't have the right
+ * physical offset.
+ *
+ * 1: if allocated clusters that don't require a COW are available at
+ * the requested offset. *bytes may have decreased and describes
+ * the length of the area that can be written to.
+ *
+ * -errno: in error cases
+ */
+static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
+ uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m)
+{
+ BDRVQcowState *s = bs->opaque;
+ int l2_index;
+ uint64_t cluster_offset;
+ uint64_t *l2_table;
+ unsigned int nb_clusters;
+ unsigned int keep_clusters;
+ int ret, pret;
+
+ trace_qcow2_handle_copied(qemu_coroutine_self(), guest_offset, *host_offset,
+ *bytes);
+
+ assert(*host_offset == 0 || offset_into_cluster(s, guest_offset)
+ == offset_into_cluster(s, *host_offset));
+
+ /*
+ * Calculate the number of clusters to look for. We stop at L2 table
+ * boundaries to keep things simple.
+ */
+ nb_clusters =
+ size_to_clusters(s, offset_into_cluster(s, guest_offset) + *bytes);
+
+ l2_index = offset_to_l2_index(s, guest_offset);
+ nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+
+ /* Find L2 entry for the first involved cluster */
+ ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
+ if (ret < 0) {
+ return ret;
+ }
+
+ cluster_offset = be64_to_cpu(l2_table[l2_index]);
+
+ /* Check how many clusters are already allocated and don't need COW */
+ if (qcow2_get_cluster_type(cluster_offset) == QCOW2_CLUSTER_NORMAL
+ && (cluster_offset & QCOW_OFLAG_COPIED))
+ {
+ /* If a specific host_offset is required, check it */
+ bool offset_matches =
+ (cluster_offset & L2E_OFFSET_MASK) == *host_offset;
+
+ if (*host_offset != 0 && !offset_matches) {
+ *bytes = 0;
+ ret = 0;
+ goto out;
+ }
+
+ /* We keep all QCOW_OFLAG_COPIED clusters */
+ keep_clusters =
+ count_contiguous_clusters(nb_clusters, s->cluster_size,
+ &l2_table[l2_index], 0,
+ QCOW_OFLAG_COPIED | QCOW_OFLAG_ZERO);
+ assert(keep_clusters <= nb_clusters);
+
+ *bytes = MIN(*bytes,
+ keep_clusters * s->cluster_size
+ - offset_into_cluster(s, guest_offset));
+
+ ret = 1;
+ } else {
+ ret = 0;
+ }
+
+ /* Cleanup */
+out:
+ pret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ if (pret < 0) {
+ return pret;
+ }
+
+ /* Only return a host offset if we actually made progress. Otherwise we
+ * would make requirements for handle_alloc() that it can't fulfill */
+ if (ret) {
+ *host_offset = (cluster_offset & L2E_OFFSET_MASK)
+ + offset_into_cluster(s, guest_offset);
+ }
+
+ return ret;
+}
+
+/*
+ * Allocates new clusters for the given guest_offset.
+ *
+ * At most *nb_clusters are allocated, and on return *nb_clusters is updated to
+ * contain the number of clusters that have been allocated and are contiguous
+ * in the image file.
+ *
+ * If *host_offset is non-zero, it specifies the offset in the image file at
+ * which the new clusters must start. *nb_clusters can be 0 on return in this
+ * case if the cluster at host_offset is already in use. If *host_offset is
+ * zero, the clusters can be allocated anywhere in the image file.
+ *
+ * *host_offset is updated to contain the offset into the image file at which
+ * the first allocated cluster starts.
+ *
+ * Return 0 on success and -errno in error cases. -EAGAIN means that the
+ * function has been waiting for another request and the allocation must be
+ * restarted, but the whole request should not be failed.
+ */
+static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
+ uint64_t *host_offset, unsigned int *nb_clusters)
+{
+ BDRVQcowState *s = bs->opaque;
+
+ trace_qcow2_do_alloc_clusters_offset(qemu_coroutine_self(), guest_offset,
+ *host_offset, *nb_clusters);
+
+ /* Allocate new clusters */
+ trace_qcow2_cluster_alloc_phys(qemu_coroutine_self());
+ if (*host_offset == 0) {
+ int64_t cluster_offset =
+ qcow2_alloc_clusters(bs, *nb_clusters * s->cluster_size);
+ if (cluster_offset < 0) {
+ return cluster_offset;
+ }
+ *host_offset = cluster_offset;
+ return 0;
+ } else {
+ int ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
+ if (ret < 0) {
+ return ret;
+ }
+ *nb_clusters = ret;
+ return 0;
+ }
+}
+
+/*
+ * Allocates new clusters for an area that either is yet unallocated or needs a
+ * copy on write. If *host_offset is non-zero, clusters are only allocated if
+ * the new allocation can match the specified host offset.
+ *
+ * Note that guest_offset may not be cluster aligned. In this case, the
+ * returned *host_offset points to exact byte referenced by guest_offset and
+ * therefore isn't cluster aligned as well.
+ *
+ * Returns:
+ * 0: if no clusters could be allocated. *bytes is set to 0,
+ * *host_offset is left unchanged.
+ *
+ * 1: if new clusters were allocated. *bytes may be decreased if the
+ * new allocation doesn't cover all of the requested area.
+ * *host_offset is updated to contain the host offset of the first
+ * newly allocated cluster.
+ *
+ * -errno: in error cases
+ */
+static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
+ uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m)
+{
+ BDRVQcowState *s = bs->opaque;
+ int l2_index;
+ uint64_t *l2_table;
+ uint64_t entry;
+ unsigned int nb_clusters;
+ int ret;
+
+ uint64_t alloc_cluster_offset;
+
+ trace_qcow2_handle_alloc(qemu_coroutine_self(), guest_offset, *host_offset,
+ *bytes);
+ assert(*bytes > 0);
+
+ /*
+ * Calculate the number of clusters to look for. We stop at L2 table
+ * boundaries to keep things simple.
+ */
+ nb_clusters =
+ size_to_clusters(s, offset_into_cluster(s, guest_offset) + *bytes);
+
+ l2_index = offset_to_l2_index(s, guest_offset);
+ nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+
+ /* Find L2 entry for the first involved cluster */
+ ret = get_cluster_table(bs, guest_offset, &l2_table, &l2_index);
+ if (ret < 0) {
+ return ret;
+ }
+
+ entry = be64_to_cpu(l2_table[l2_index]);
+
+ /* For the moment, overwrite compressed clusters one by one */
+ if (entry & QCOW_OFLAG_COMPRESSED) {
+ nb_clusters = 1;
+ } else {
+ nb_clusters = count_cow_clusters(s, nb_clusters, l2_table, l2_index);
+ }
+
+ /* This function is only called when there were no non-COW clusters, so if
+ * we can't find any unallocated or COW clusters either, something is
+ * wrong with our code. */
+ assert(nb_clusters > 0);
+
+ ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Allocate, if necessary at a given offset in the image file */
+ alloc_cluster_offset = start_of_cluster(s, *host_offset);
+ ret = do_alloc_cluster_offset(bs, guest_offset, &alloc_cluster_offset,
+ &nb_clusters);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Can't extend contiguous allocation */
+ if (nb_clusters == 0) {
+ *bytes = 0;
+ return 0;
+ }
+
+ /*
+ * Save info needed for meta data update.
+ *
+ * requested_sectors: Number of sectors from the start of the first
+ * newly allocated cluster to the end of the (possibly shortened
+ * before) write request.
+ *
+ * avail_sectors: Number of sectors from the start of the first
+ * newly allocated to the end of the last newly allocated cluster.
+ *
+ * nb_sectors: The number of sectors from the start of the first
+ * newly allocated cluster to the end of the area that the write
+ * request actually writes to (excluding COW at the end)
+ */
+ int requested_sectors =
+ (*bytes + offset_into_cluster(s, guest_offset))
+ >> BDRV_SECTOR_BITS;
+ int avail_sectors = nb_clusters
+ << (s->cluster_bits - BDRV_SECTOR_BITS);
+ int alloc_n_start = offset_into_cluster(s, guest_offset)
+ >> BDRV_SECTOR_BITS;
+ int nb_sectors = MIN(requested_sectors, avail_sectors);
+ QCowL2Meta *old_m = *m;
+
+ *m = g_malloc0(sizeof(**m));
+
+ **m = (QCowL2Meta) {
+ .next = old_m,
+
+ .alloc_offset = alloc_cluster_offset,
+ .offset = start_of_cluster(s, guest_offset),
+ .nb_clusters = nb_clusters,
+ .nb_available = nb_sectors,
+
+ .cow_start = {
+ .offset = 0,
+ .nb_sectors = alloc_n_start,
+ },
+ .cow_end = {
+ .offset = nb_sectors * BDRV_SECTOR_SIZE,
+ .nb_sectors = avail_sectors - nb_sectors,
+ },
+ };
+ qemu_co_queue_init(&(*m)->dependent_requests);
+ QLIST_INSERT_HEAD(&s->cluster_allocs, *m, next_in_flight);
+
+ *host_offset = alloc_cluster_offset + offset_into_cluster(s, guest_offset);
+ *bytes = MIN(*bytes, (nb_sectors * BDRV_SECTOR_SIZE)
+ - offset_into_cluster(s, guest_offset));
+ assert(*bytes != 0);
+
+ return 1;
+
+fail:
+ if (*m && (*m)->nb_clusters > 0) {
+ QLIST_REMOVE(*m, next_in_flight);
+ }
+ return ret;
+}
+
+/*
+ * alloc_cluster_offset
+ *
+ * For a given offset on the virtual disk, find the cluster offset in qcow2
+ * file. If the offset is not found, allocate a new cluster.
+ *
+ * If the cluster was already allocated, m->nb_clusters is set to 0 and
+ * other fields in m are meaningless.
+ *
+ * If the cluster is newly allocated, m->nb_clusters is set to the number of
+ * contiguous clusters that have been allocated. In this case, the other
+ * fields of m are valid and contain information about the first allocated
+ * cluster.
+ *
+ * If the request conflicts with another write request in flight, the coroutine
+ * is queued and will be reentered when the dependency has completed.
+ *
+ * Return 0 on success and -errno in error cases
+ */
+int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
+ int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t start, remaining;
+ uint64_t cluster_offset;
+ uint64_t cur_bytes;
+ int ret;
+
+ trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset,
+ n_start, n_end);
+
+ assert(n_start * BDRV_SECTOR_SIZE == offset_into_cluster(s, offset));
+ offset = start_of_cluster(s, offset);
+
+again:
+ start = offset + (n_start << BDRV_SECTOR_BITS);
+ remaining = (n_end - n_start) << BDRV_SECTOR_BITS;
+ cluster_offset = 0;
+ *host_offset = 0;
+ cur_bytes = 0;
+ *m = NULL;
+
+ while (true) {
+
+ if (!*host_offset) {
+ *host_offset = start_of_cluster(s, cluster_offset);
+ }
+
+ assert(remaining >= cur_bytes);
+
+ start += cur_bytes;
+ remaining -= cur_bytes;
+ cluster_offset += cur_bytes;
+
+ if (remaining == 0) {
+ break;
+ }
+
+ cur_bytes = remaining;
+
+ /*
+ * Now start gathering as many contiguous clusters as possible:
+ *
+ * 1. Check for overlaps with in-flight allocations
+ *
+ * a) Overlap not in the first cluster -> shorten this request and
+ * let the caller handle the rest in its next loop iteration.
+ *
+ * b) Real overlaps of two requests. Yield and restart the search
+ * for contiguous clusters (the situation could have changed
+ * while we were sleeping)
+ *
+ * c) TODO: Request starts in the same cluster as the in-flight
+ * allocation ends. Shorten the COW of the in-fight allocation,
+ * set cluster_offset to write to the same cluster and set up
+ * the right synchronisation between the in-flight request and
+ * the new one.
+ */
+ ret = handle_dependencies(bs, start, &cur_bytes, m);
+ if (ret == -EAGAIN) {
+ /* Currently handle_dependencies() doesn't yield if we already had
+ * an allocation. If it did, we would have to clean up the L2Meta
+ * structs before starting over. */
+ assert(*m == NULL);
+ goto again;
+ } else if (ret < 0) {
+ return ret;
+ } else if (cur_bytes == 0) {
+ break;
+ } else {
+ /* handle_dependencies() may have decreased cur_bytes (shortened
+ * the allocations below) so that the next dependency is processed
+ * correctly during the next loop iteration. */
+ }
+
+ /*
+ * 2. Count contiguous COPIED clusters.
+ */
+ ret = handle_copied(bs, start, &cluster_offset, &cur_bytes, m);
+ if (ret < 0) {
+ return ret;
+ } else if (ret) {
+ continue;
+ } else if (cur_bytes == 0) {
+ break;
+ }
+
+ /*
+ * 3. If the request still hasn't completed, allocate new clusters,
+ * considering any cluster_offset of steps 1c or 2.
+ */
+ ret = handle_alloc(bs, start, &cluster_offset, &cur_bytes, m);
+ if (ret < 0) {
+ return ret;
+ } else if (ret) {
+ continue;
+ } else {
+ assert(cur_bytes == 0);
+ break;
+ }
+ }
+
+ *num = (n_end - n_start) - (remaining >> BDRV_SECTOR_BITS);
+ assert(*num > 0);
+ assert(*host_offset != 0);
+
+ return 0;
+}
+
+static int decompress_buffer(uint8_t *out_buf, int out_buf_size,
+ const uint8_t *buf, int buf_size)
+{
+ z_stream strm1, *strm = &strm1;
+ int ret, out_len;
+
+ memset(strm, 0, sizeof(*strm));
+
+ strm->next_in = (uint8_t *)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;
+}
+
+int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret, csize, nb_csectors, sector_offset;
+ uint64_t coffset;
+
+ coffset = cluster_offset & s->cluster_offset_mask;
+ if (s->cluster_cache_offset != coffset) {
+ nb_csectors = ((cluster_offset >> s->csize_shift) & s->csize_mask) + 1;
+ sector_offset = coffset & 511;
+ csize = nb_csectors * 512 - sector_offset;
+ BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED);
+ ret = bdrv_read(bs->file, coffset >> 9, s->cluster_data, nb_csectors);
+ if (ret < 0) {
+ return ret;
+ }
+ if (decompress_buffer(s->cluster_cache, s->cluster_size,
+ s->cluster_data + sector_offset, csize) < 0) {
+ return -EIO;
+ }
+ s->cluster_cache_offset = coffset;
+ }
+ return 0;
+}
+
+/*
+ * This discards as many clusters of nb_clusters as possible at once (i.e.
+ * all clusters in the same L2 table) and returns the number of discarded
+ * clusters.
+ */
+static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
+ unsigned int nb_clusters)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t *l2_table;
+ int l2_index;
+ int ret;
+ int i;
+
+ ret = get_cluster_table(bs, offset, &l2_table, &l2_index);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Limit nb_clusters to one L2 table */
+ nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+
+ for (i = 0; i < nb_clusters; i++) {
+ uint64_t old_offset;
+
+ old_offset = be64_to_cpu(l2_table[l2_index + i]);
+ if ((old_offset & L2E_OFFSET_MASK) == 0) {
+ continue;
+ }
+
+ /* First remove L2 entries */
+ qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+ l2_table[l2_index + i] = cpu_to_be64(0);
+
+ /* Then decrease the refcount */
+ qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST);
+ }
+
+ ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return nb_clusters;
+}
+
+int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
+ int nb_sectors)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t end_offset;
+ unsigned int nb_clusters;
+ int ret;
+
+ end_offset = offset + (nb_sectors << BDRV_SECTOR_BITS);
+
+ /* Round start up and end down */
+ offset = align_offset(offset, s->cluster_size);
+ end_offset &= ~(s->cluster_size - 1);
+
+ if (offset > end_offset) {
+ return 0;
+ }
+
+ nb_clusters = size_to_clusters(s, end_offset - offset);
+
+ s->cache_discards = true;
+
+ /* Each L2 table is handled by its own loop iteration */
+ while (nb_clusters > 0) {
+ ret = discard_single_l2(bs, offset, nb_clusters);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ nb_clusters -= ret;
+ offset += (ret * s->cluster_size);
+ }
+
+ ret = 0;
+fail:
+ s->cache_discards = false;
+ qcow2_process_discards(bs, ret);
+
+ return ret;
+}
+
+/*
+ * This zeroes as many clusters of nb_clusters as possible at once (i.e.
+ * all clusters in the same L2 table) and returns the number of zeroed
+ * clusters.
+ */
+static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
+ unsigned int nb_clusters)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t *l2_table;
+ int l2_index;
+ int ret;
+ int i;
+
+ ret = get_cluster_table(bs, offset, &l2_table, &l2_index);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Limit nb_clusters to one L2 table */
+ nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+
+ for (i = 0; i < nb_clusters; i++) {
+ uint64_t old_offset;
+
+ old_offset = be64_to_cpu(l2_table[l2_index + i]);
+
+ /* Update L2 entries */
+ qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+ if (old_offset & QCOW_OFLAG_COMPRESSED) {
+ l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
+ qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST);
+ } else {
+ l2_table[l2_index + i] |= cpu_to_be64(QCOW_OFLAG_ZERO);
+ }
+ }
+
+ ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return nb_clusters;
+}
+
+int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors)
+{
+ BDRVQcowState *s = bs->opaque;
+ unsigned int nb_clusters;
+ int ret;
+
+ /* The zero flag is only supported by version 3 and newer */
+ if (s->qcow_version < 3) {
+ return -ENOTSUP;
+ }
+
+ /* Each L2 table is handled by its own loop iteration */
+ nb_clusters = size_to_clusters(s, nb_sectors << BDRV_SECTOR_BITS);
+
+ s->cache_discards = true;
+
+ while (nb_clusters > 0) {
+ ret = zero_single_l2(bs, offset, nb_clusters);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ nb_clusters -= ret;
+ offset += (ret * s->cluster_size);
+ }
+
+ ret = 0;
+fail:
+ s->cache_discards = false;
+ qcow2_process_discards(bs, ret);
+
+ return ret;
+}
diff --git a/contrib/qemu/block/qcow2-refcount.c b/contrib/qemu/block/qcow2-refcount.c
new file mode 100644
index 00000000000..1244693f39e
--- /dev/null
+++ b/contrib/qemu/block/qcow2-refcount.c
@@ -0,0 +1,1374 @@
+/*
+ * Block driver for the QCOW version 2 format
+ *
+ * Copyright (c) 2004-2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "block/qcow2.h"
+
+static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size);
+static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
+ int64_t offset, int64_t length,
+ int addend, enum qcow2_discard_type type);
+
+
+/*********************************************************/
+/* refcount handling */
+
+int qcow2_refcount_init(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret, refcount_table_size2, i;
+
+ refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
+ s->refcount_table = g_malloc(refcount_table_size2);
+ if (s->refcount_table_size > 0) {
+ BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD);
+ ret = bdrv_pread(bs->file, s->refcount_table_offset,
+ s->refcount_table, refcount_table_size2);
+ if (ret != refcount_table_size2)
+ goto fail;
+ for(i = 0; i < s->refcount_table_size; i++)
+ be64_to_cpus(&s->refcount_table[i]);
+ }
+ return 0;
+ fail:
+ return -ENOMEM;
+}
+
+void qcow2_refcount_close(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ g_free(s->refcount_table);
+}
+
+
+static int load_refcount_block(BlockDriverState *bs,
+ int64_t refcount_block_offset,
+ void **refcount_block)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret;
+
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_LOAD);
+ ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
+ refcount_block);
+
+ return ret;
+}
+
+/*
+ * Returns the refcount of the cluster given by its index. Any non-negative
+ * return value is the refcount of the cluster, negative values are -errno
+ * and indicate an error.
+ */
+static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
+{
+ BDRVQcowState *s = bs->opaque;
+ int refcount_table_index, block_index;
+ int64_t refcount_block_offset;
+ int ret;
+ uint16_t *refcount_block;
+ uint16_t refcount;
+
+ refcount_table_index = cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
+ if (refcount_table_index >= s->refcount_table_size)
+ return 0;
+ refcount_block_offset = s->refcount_table[refcount_table_index];
+ if (!refcount_block_offset)
+ return 0;
+
+ ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
+ (void**) &refcount_block);
+ if (ret < 0) {
+ return ret;
+ }
+
+ block_index = cluster_index &
+ ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
+ refcount = be16_to_cpu(refcount_block[block_index]);
+
+ ret = qcow2_cache_put(bs, s->refcount_block_cache,
+ (void**) &refcount_block);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return refcount;
+}
+
+/*
+ * Rounds the refcount table size up to avoid growing the table for each single
+ * refcount block that is allocated.
+ */
+static unsigned int next_refcount_table_size(BDRVQcowState *s,
+ unsigned int min_size)
+{
+ unsigned int min_clusters = (min_size >> (s->cluster_bits - 3)) + 1;
+ unsigned int refcount_table_clusters =
+ MAX(1, s->refcount_table_size >> (s->cluster_bits - 3));
+
+ while (min_clusters > refcount_table_clusters) {
+ refcount_table_clusters = (refcount_table_clusters * 3 + 1) / 2;
+ }
+
+ return refcount_table_clusters << (s->cluster_bits - 3);
+}
+
+
+/* Checks if two offsets are described by the same refcount block */
+static int in_same_refcount_block(BDRVQcowState *s, uint64_t offset_a,
+ uint64_t offset_b)
+{
+ uint64_t block_a = offset_a >> (2 * s->cluster_bits - REFCOUNT_SHIFT);
+ uint64_t block_b = offset_b >> (2 * s->cluster_bits - REFCOUNT_SHIFT);
+
+ return (block_a == block_b);
+}
+
+/*
+ * Loads a refcount block. If it doesn't exist yet, it is allocated first
+ * (including growing the refcount table if needed).
+ *
+ * Returns 0 on success or -errno in error case
+ */
+static int alloc_refcount_block(BlockDriverState *bs,
+ int64_t cluster_index, uint16_t **refcount_block)
+{
+ BDRVQcowState *s = bs->opaque;
+ unsigned int refcount_table_index;
+ int ret;
+
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC);
+
+ /* Find the refcount block for the given cluster */
+ refcount_table_index = cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
+
+ if (refcount_table_index < s->refcount_table_size) {
+
+ uint64_t refcount_block_offset =
+ s->refcount_table[refcount_table_index] & REFT_OFFSET_MASK;
+
+ /* If it's already there, we're done */
+ if (refcount_block_offset) {
+ return load_refcount_block(bs, refcount_block_offset,
+ (void**) refcount_block);
+ }
+ }
+
+ /*
+ * If we came here, we need to allocate something. Something is at least
+ * a cluster for the new refcount block. It may also include a new refcount
+ * table if the old refcount table is too small.
+ *
+ * Note that allocating clusters here needs some special care:
+ *
+ * - We can't use the normal qcow2_alloc_clusters(), it would try to
+ * increase the refcount and very likely we would end up with an endless
+ * recursion. Instead we must place the refcount blocks in a way that
+ * they can describe them themselves.
+ *
+ * - We need to consider that at this point we are inside update_refcounts
+ * and doing the initial refcount increase. This means that some clusters
+ * have already been allocated by the caller, but their refcount isn't
+ * accurate yet. free_cluster_index tells us where this allocation ends
+ * as long as we don't overwrite it by freeing clusters.
+ *
+ * - alloc_clusters_noref and qcow2_free_clusters may load a different
+ * refcount block into the cache
+ */
+
+ *refcount_block = NULL;
+
+ /* We write to the refcount table, so we might depend on L2 tables */
+ ret = qcow2_cache_flush(bs, s->l2_table_cache);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Allocate the refcount block itself and mark it as used */
+ int64_t new_block = alloc_clusters_noref(bs, s->cluster_size);
+ if (new_block < 0) {
+ return new_block;
+ }
+
+#ifdef DEBUG_ALLOC2
+ fprintf(stderr, "qcow2: Allocate refcount block %d for %" PRIx64
+ " at %" PRIx64 "\n",
+ refcount_table_index, cluster_index << s->cluster_bits, new_block);
+#endif
+
+ if (in_same_refcount_block(s, new_block, cluster_index << s->cluster_bits)) {
+ /* Zero the new refcount block before updating it */
+ ret = qcow2_cache_get_empty(bs, s->refcount_block_cache, new_block,
+ (void**) refcount_block);
+ if (ret < 0) {
+ goto fail_block;
+ }
+
+ memset(*refcount_block, 0, s->cluster_size);
+
+ /* The block describes itself, need to update the cache */
+ int block_index = (new_block >> s->cluster_bits) &
+ ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
+ (*refcount_block)[block_index] = cpu_to_be16(1);
+ } else {
+ /* Described somewhere else. This can recurse at most twice before we
+ * arrive at a block that describes itself. */
+ ret = update_refcount(bs, new_block, s->cluster_size, 1,
+ QCOW2_DISCARD_NEVER);
+ if (ret < 0) {
+ goto fail_block;
+ }
+
+ ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+ if (ret < 0) {
+ goto fail_block;
+ }
+
+ /* Initialize the new refcount block only after updating its refcount,
+ * update_refcount uses the refcount cache itself */
+ ret = qcow2_cache_get_empty(bs, s->refcount_block_cache, new_block,
+ (void**) refcount_block);
+ if (ret < 0) {
+ goto fail_block;
+ }
+
+ memset(*refcount_block, 0, s->cluster_size);
+ }
+
+ /* Now the new refcount block needs to be written to disk */
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE);
+ qcow2_cache_entry_mark_dirty(s->refcount_block_cache, *refcount_block);
+ ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+ if (ret < 0) {
+ goto fail_block;
+ }
+
+ /* If the refcount table is big enough, just hook the block up there */
+ if (refcount_table_index < s->refcount_table_size) {
+ uint64_t data64 = cpu_to_be64(new_block);
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_HOOKUP);
+ ret = bdrv_pwrite_sync(bs->file,
+ s->refcount_table_offset + refcount_table_index * sizeof(uint64_t),
+ &data64, sizeof(data64));
+ if (ret < 0) {
+ goto fail_block;
+ }
+
+ s->refcount_table[refcount_table_index] = new_block;
+ return 0;
+ }
+
+ ret = qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
+ if (ret < 0) {
+ goto fail_block;
+ }
+
+ /*
+ * If we come here, we need to grow the refcount table. Again, a new
+ * refcount table needs some space and we can't simply allocate to avoid
+ * endless recursion.
+ *
+ * Therefore let's grab new refcount blocks at the end of the image, which
+ * will describe themselves and the new refcount table. This way we can
+ * reference them only in the new table and do the switch to the new
+ * refcount table at once without producing an inconsistent state in
+ * between.
+ */
+ BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_GROW);
+
+ /* Calculate the number of refcount blocks needed so far */
+ uint64_t refcount_block_clusters = 1 << (s->cluster_bits - REFCOUNT_SHIFT);
+ uint64_t blocks_used = (s->free_cluster_index +
+ refcount_block_clusters - 1) / refcount_block_clusters;
+
+ /* And now we need at least one block more for the new metadata */
+ uint64_t table_size = next_refcount_table_size(s, blocks_used + 1);
+ uint64_t last_table_size;
+ uint64_t blocks_clusters;
+ do {
+ uint64_t table_clusters =
+ size_to_clusters(s, table_size * sizeof(uint64_t));
+ blocks_clusters = 1 +
+ ((table_clusters + refcount_block_clusters - 1)
+ / refcount_block_clusters);
+ uint64_t meta_clusters = table_clusters + blocks_clusters;
+
+ last_table_size = table_size;
+ table_size = next_refcount_table_size(s, blocks_used +
+ ((meta_clusters + refcount_block_clusters - 1)
+ / refcount_block_clusters));
+
+ } while (last_table_size != table_size);
+
+#ifdef DEBUG_ALLOC2
+ fprintf(stderr, "qcow2: Grow refcount table %" PRId32 " => %" PRId64 "\n",
+ s->refcount_table_size, table_size);
+#endif
+
+ /* Create the new refcount table and blocks */
+ uint64_t meta_offset = (blocks_used * refcount_block_clusters) *
+ s->cluster_size;
+ uint64_t table_offset = meta_offset + blocks_clusters * s->cluster_size;
+ uint16_t *new_blocks = g_malloc0(blocks_clusters * s->cluster_size);
+ uint64_t *new_table = g_malloc0(table_size * sizeof(uint64_t));
+
+ assert(meta_offset >= (s->free_cluster_index * s->cluster_size));
+
+ /* Fill the new refcount table */
+ memcpy(new_table, s->refcount_table,
+ s->refcount_table_size * sizeof(uint64_t));
+ new_table[refcount_table_index] = new_block;
+
+ int i;
+ for (i = 0; i < blocks_clusters; i++) {
+ new_table[blocks_used + i] = meta_offset + (i * s->cluster_size);
+ }
+
+ /* Fill the refcount blocks */
+ uint64_t table_clusters = size_to_clusters(s, table_size * sizeof(uint64_t));
+ int block = 0;
+ for (i = 0; i < table_clusters + blocks_clusters; i++) {
+ new_blocks[block++] = cpu_to_be16(1);
+ }
+
+ /* Write refcount blocks to disk */
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS);
+ ret = bdrv_pwrite_sync(bs->file, meta_offset, new_blocks,
+ blocks_clusters * s->cluster_size);
+ g_free(new_blocks);
+ if (ret < 0) {
+ goto fail_table;
+ }
+
+ /* Write refcount table to disk */
+ for(i = 0; i < table_size; i++) {
+ cpu_to_be64s(&new_table[i]);
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE);
+ ret = bdrv_pwrite_sync(bs->file, table_offset, new_table,
+ table_size * sizeof(uint64_t));
+ if (ret < 0) {
+ goto fail_table;
+ }
+
+ for(i = 0; i < table_size; i++) {
+ be64_to_cpus(&new_table[i]);
+ }
+
+ /* Hook up the new refcount table in the qcow2 header */
+ uint8_t data[12];
+ cpu_to_be64w((uint64_t*)data, table_offset);
+ cpu_to_be32w((uint32_t*)(data + 8), table_clusters);
+ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE);
+ ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, refcount_table_offset),
+ data, sizeof(data));
+ if (ret < 0) {
+ goto fail_table;
+ }
+
+ /* And switch it in memory */
+ uint64_t old_table_offset = s->refcount_table_offset;
+ uint64_t old_table_size = s->refcount_table_size;
+
+ g_free(s->refcount_table);
+ s->refcount_table = new_table;
+ s->refcount_table_size = table_size;
+ s->refcount_table_offset = table_offset;
+
+ /* Free old table. Remember, we must not change free_cluster_index */
+ uint64_t old_free_cluster_index = s->free_cluster_index;
+ qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t),
+ QCOW2_DISCARD_OTHER);
+ s->free_cluster_index = old_free_cluster_index;
+
+ ret = load_refcount_block(bs, new_block, (void**) refcount_block);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return 0;
+
+fail_table:
+ g_free(new_table);
+fail_block:
+ if (*refcount_block != NULL) {
+ qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
+ }
+ return ret;
+}
+
+void qcow2_process_discards(BlockDriverState *bs, int ret)
+{
+ BDRVQcowState *s = bs->opaque;
+ Qcow2DiscardRegion *d, *next;
+
+ QTAILQ_FOREACH_SAFE(d, &s->discards, next, next) {
+ QTAILQ_REMOVE(&s->discards, d, next);
+
+ /* Discard is optional, ignore the return value */
+ if (ret >= 0) {
+ bdrv_discard(bs->file,
+ d->offset >> BDRV_SECTOR_BITS,
+ d->bytes >> BDRV_SECTOR_BITS);
+ }
+
+ g_free(d);
+ }
+}
+
+static void update_refcount_discard(BlockDriverState *bs,
+ uint64_t offset, uint64_t length)
+{
+ BDRVQcowState *s = bs->opaque;
+ Qcow2DiscardRegion *d, *p, *next;
+
+ QTAILQ_FOREACH(d, &s->discards, next) {
+ uint64_t new_start = MIN(offset, d->offset);
+ uint64_t new_end = MAX(offset + length, d->offset + d->bytes);
+
+ if (new_end - new_start <= length + d->bytes) {
+ /* There can't be any overlap, areas ending up here have no
+ * references any more and therefore shouldn't get freed another
+ * time. */
+ assert(d->bytes + length == new_end - new_start);
+ d->offset = new_start;
+ d->bytes = new_end - new_start;
+ goto found;
+ }
+ }
+
+ d = g_malloc(sizeof(*d));
+ *d = (Qcow2DiscardRegion) {
+ .bs = bs,
+ .offset = offset,
+ .bytes = length,
+ };
+ QTAILQ_INSERT_TAIL(&s->discards, d, next);
+
+found:
+ /* Merge discard requests if they are adjacent now */
+ QTAILQ_FOREACH_SAFE(p, &s->discards, next, next) {
+ if (p == d
+ || p->offset > d->offset + d->bytes
+ || d->offset > p->offset + p->bytes)
+ {
+ continue;
+ }
+
+ /* Still no overlap possible */
+ assert(p->offset == d->offset + d->bytes
+ || d->offset == p->offset + p->bytes);
+
+ QTAILQ_REMOVE(&s->discards, p, next);
+ d->offset = MIN(d->offset, p->offset);
+ d->bytes += p->bytes;
+ }
+}
+
+/* XXX: cache several refcount block clusters ? */
+static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
+ int64_t offset, int64_t length, int addend, enum qcow2_discard_type type)
+{
+ BDRVQcowState *s = bs->opaque;
+ int64_t start, last, cluster_offset;
+ uint16_t *refcount_block = NULL;
+ int64_t old_table_index = -1;
+ int ret;
+
+#ifdef DEBUG_ALLOC2
+ fprintf(stderr, "update_refcount: offset=%" PRId64 " size=%" PRId64 " addend=%d\n",
+ offset, length, addend);
+#endif
+ if (length < 0) {
+ return -EINVAL;
+ } else if (length == 0) {
+ return 0;
+ }
+
+ if (addend < 0) {
+ qcow2_cache_set_dependency(bs, s->refcount_block_cache,
+ s->l2_table_cache);
+ }
+
+ start = offset & ~(s->cluster_size - 1);
+ last = (offset + length - 1) & ~(s->cluster_size - 1);
+ for(cluster_offset = start; cluster_offset <= last;
+ cluster_offset += s->cluster_size)
+ {
+ int block_index, refcount;
+ int64_t cluster_index = cluster_offset >> s->cluster_bits;
+ int64_t table_index =
+ cluster_index >> (s->cluster_bits - REFCOUNT_SHIFT);
+
+ /* Load the refcount block and allocate it if needed */
+ if (table_index != old_table_index) {
+ if (refcount_block) {
+ ret = qcow2_cache_put(bs, s->refcount_block_cache,
+ (void**) &refcount_block);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ ret = alloc_refcount_block(bs, cluster_index, &refcount_block);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+ old_table_index = table_index;
+
+ qcow2_cache_entry_mark_dirty(s->refcount_block_cache, refcount_block);
+
+ /* we can update the count and save it */
+ block_index = cluster_index &
+ ((1 << (s->cluster_bits - REFCOUNT_SHIFT)) - 1);
+
+ refcount = be16_to_cpu(refcount_block[block_index]);
+ refcount += addend;
+ if (refcount < 0 || refcount > 0xffff) {
+ ret = -EINVAL;
+ goto fail;
+ }
+ if (refcount == 0 && cluster_index < s->free_cluster_index) {
+ s->free_cluster_index = cluster_index;
+ }
+ refcount_block[block_index] = cpu_to_be16(refcount);
+
+ if (refcount == 0 && s->discard_passthrough[type]) {
+ update_refcount_discard(bs, cluster_offset, s->cluster_size);
+ }
+ }
+
+ ret = 0;
+fail:
+ if (!s->cache_discards) {
+ qcow2_process_discards(bs, ret);
+ }
+
+ /* Write last changed block to disk */
+ if (refcount_block) {
+ int wret;
+ wret = qcow2_cache_put(bs, s->refcount_block_cache,
+ (void**) &refcount_block);
+ if (wret < 0) {
+ return ret < 0 ? ret : wret;
+ }
+ }
+
+ /*
+ * Try do undo any updates if an error is returned (This may succeed in
+ * some cases like ENOSPC for allocating a new refcount block)
+ */
+ if (ret < 0) {
+ int dummy;
+ dummy = update_refcount(bs, offset, cluster_offset - offset, -addend,
+ QCOW2_DISCARD_NEVER);
+ (void)dummy;
+ }
+
+ return ret;
+}
+
+/*
+ * Increases or decreases the refcount of a given cluster by one.
+ * addend must be 1 or -1.
+ *
+ * If the return value is non-negative, it is the new refcount of the cluster.
+ * If it is negative, it is -errno and indicates an error.
+ */
+static int update_cluster_refcount(BlockDriverState *bs,
+ int64_t cluster_index,
+ int addend,
+ enum qcow2_discard_type type)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret;
+
+ ret = update_refcount(bs, cluster_index << s->cluster_bits, 1, addend,
+ type);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return get_refcount(bs, cluster_index);
+}
+
+
+
+/*********************************************************/
+/* cluster allocation functions */
+
+
+
+/* return < 0 if error */
+static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size)
+{
+ BDRVQcowState *s = bs->opaque;
+ int i, nb_clusters, refcount;
+
+ nb_clusters = size_to_clusters(s, size);
+retry:
+ for(i = 0; i < nb_clusters; i++) {
+ int64_t next_cluster_index = s->free_cluster_index++;
+ refcount = get_refcount(bs, next_cluster_index);
+
+ if (refcount < 0) {
+ return refcount;
+ } else if (refcount != 0) {
+ goto retry;
+ }
+ }
+#ifdef DEBUG_ALLOC2
+ fprintf(stderr, "alloc_clusters: size=%" PRId64 " -> %" PRId64 "\n",
+ size,
+ (s->free_cluster_index - nb_clusters) << s->cluster_bits);
+#endif
+ return (s->free_cluster_index - nb_clusters) << s->cluster_bits;
+}
+
+int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size)
+{
+ int64_t offset;
+ int ret;
+
+ BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC);
+ offset = alloc_clusters_noref(bs, size);
+ if (offset < 0) {
+ return offset;
+ }
+
+ ret = update_refcount(bs, offset, size, 1, QCOW2_DISCARD_NEVER);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return offset;
+}
+
+int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
+ int nb_clusters)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t cluster_index;
+ uint64_t old_free_cluster_index;
+ int i, refcount, ret;
+
+ /* Check how many clusters there are free */
+ cluster_index = offset >> s->cluster_bits;
+ for(i = 0; i < nb_clusters; i++) {
+ refcount = get_refcount(bs, cluster_index++);
+
+ if (refcount < 0) {
+ return refcount;
+ } else if (refcount != 0) {
+ break;
+ }
+ }
+
+ /* And then allocate them */
+ old_free_cluster_index = s->free_cluster_index;
+ s->free_cluster_index = cluster_index + i;
+
+ ret = update_refcount(bs, offset, i << s->cluster_bits, 1,
+ QCOW2_DISCARD_NEVER);
+ if (ret < 0) {
+ return ret;
+ }
+
+ s->free_cluster_index = old_free_cluster_index;
+
+ return i;
+}
+
+/* only used to allocate compressed sectors. We try to allocate
+ contiguous sectors. size must be <= cluster_size */
+int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
+{
+ BDRVQcowState *s = bs->opaque;
+ int64_t offset, cluster_offset;
+ int free_in_cluster;
+
+ BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC_BYTES);
+ assert(size > 0 && size <= s->cluster_size);
+ if (s->free_byte_offset == 0) {
+ offset = qcow2_alloc_clusters(bs, s->cluster_size);
+ if (offset < 0) {
+ return offset;
+ }
+ s->free_byte_offset = offset;
+ }
+ redo:
+ free_in_cluster = s->cluster_size -
+ (s->free_byte_offset & (s->cluster_size - 1));
+ if (size <= free_in_cluster) {
+ /* enough space in current cluster */
+ offset = s->free_byte_offset;
+ s->free_byte_offset += size;
+ free_in_cluster -= size;
+ if (free_in_cluster == 0)
+ s->free_byte_offset = 0;
+ if ((offset & (s->cluster_size - 1)) != 0)
+ update_cluster_refcount(bs, offset >> s->cluster_bits, 1,
+ QCOW2_DISCARD_NEVER);
+ } else {
+ offset = qcow2_alloc_clusters(bs, s->cluster_size);
+ if (offset < 0) {
+ return offset;
+ }
+ cluster_offset = s->free_byte_offset & ~(s->cluster_size - 1);
+ if ((cluster_offset + s->cluster_size) == offset) {
+ /* we are lucky: contiguous data */
+ offset = s->free_byte_offset;
+ update_cluster_refcount(bs, offset >> s->cluster_bits, 1,
+ QCOW2_DISCARD_NEVER);
+ s->free_byte_offset += size;
+ } else {
+ s->free_byte_offset = offset;
+ goto redo;
+ }
+ }
+
+ /* The cluster refcount was incremented, either by qcow2_alloc_clusters()
+ * or explicitly by update_cluster_refcount(). Refcount blocks must be
+ * flushed before the caller's L2 table updates.
+ */
+ qcow2_cache_set_dependency(bs, s->l2_table_cache, s->refcount_block_cache);
+ return offset;
+}
+
+void qcow2_free_clusters(BlockDriverState *bs,
+ int64_t offset, int64_t size,
+ enum qcow2_discard_type type)
+{
+ int ret;
+
+ BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_FREE);
+ ret = update_refcount(bs, offset, size, -1, type);
+ if (ret < 0) {
+ fprintf(stderr, "qcow2_free_clusters failed: %s\n", strerror(-ret));
+ /* TODO Remember the clusters to free them later and avoid leaking */
+ }
+}
+
+/*
+ * Free a cluster using its L2 entry (handles clusters of all types, e.g.
+ * normal cluster, compressed cluster, etc.)
+ */
+void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
+ int nb_clusters, enum qcow2_discard_type type)
+{
+ BDRVQcowState *s = bs->opaque;
+
+ switch (qcow2_get_cluster_type(l2_entry)) {
+ case QCOW2_CLUSTER_COMPRESSED:
+ {
+ int nb_csectors;
+ nb_csectors = ((l2_entry >> s->csize_shift) &
+ s->csize_mask) + 1;
+ qcow2_free_clusters(bs,
+ (l2_entry & s->cluster_offset_mask) & ~511,
+ nb_csectors * 512, type);
+ }
+ break;
+ case QCOW2_CLUSTER_NORMAL:
+ qcow2_free_clusters(bs, l2_entry & L2E_OFFSET_MASK,
+ nb_clusters << s->cluster_bits, type);
+ break;
+ case QCOW2_CLUSTER_UNALLOCATED:
+ case QCOW2_CLUSTER_ZERO:
+ break;
+ default:
+ abort();
+ }
+}
+
+
+
+/*********************************************************/
+/* snapshots and image creation */
+
+
+
+/* update the refcounts of snapshots and the copied flag */
+int qcow2_update_snapshot_refcount(BlockDriverState *bs,
+ int64_t l1_table_offset, int l1_size, int addend)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t *l1_table, *l2_table, l2_offset, offset, l1_size2, l1_allocated;
+ int64_t old_offset, old_l2_offset;
+ int i, j, l1_modified = 0, nb_csectors, refcount;
+ int ret;
+
+ l2_table = NULL;
+ l1_table = NULL;
+ l1_size2 = l1_size * sizeof(uint64_t);
+
+ s->cache_discards = true;
+
+ /* WARNING: qcow2_snapshot_goto relies on this function not using the
+ * l1_table_offset when it is the current s->l1_table_offset! Be careful
+ * when changing this! */
+ if (l1_table_offset != s->l1_table_offset) {
+ l1_table = g_malloc0(align_offset(l1_size2, 512));
+ l1_allocated = 1;
+
+ ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ for(i = 0;i < l1_size; i++)
+ be64_to_cpus(&l1_table[i]);
+ } else {
+ assert(l1_size == s->l1_size);
+ l1_table = s->l1_table;
+ l1_allocated = 0;
+ }
+
+ for(i = 0; i < l1_size; i++) {
+ l2_offset = l1_table[i];
+ if (l2_offset) {
+ old_l2_offset = l2_offset;
+ l2_offset &= L1E_OFFSET_MASK;
+
+ ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset,
+ (void**) &l2_table);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ for(j = 0; j < s->l2_size; j++) {
+ offset = be64_to_cpu(l2_table[j]);
+ if (offset != 0) {
+ old_offset = offset;
+ offset &= ~QCOW_OFLAG_COPIED;
+ if (offset & QCOW_OFLAG_COMPRESSED) {
+ nb_csectors = ((offset >> s->csize_shift) &
+ s->csize_mask) + 1;
+ if (addend != 0) {
+ int ret;
+ ret = update_refcount(bs,
+ (offset & s->cluster_offset_mask) & ~511,
+ nb_csectors * 512, addend,
+ QCOW2_DISCARD_SNAPSHOT);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+ /* compressed clusters are never modified */
+ refcount = 2;
+ } else {
+ uint64_t cluster_index = (offset & L2E_OFFSET_MASK) >> s->cluster_bits;
+ if (addend != 0) {
+ refcount = update_cluster_refcount(bs, cluster_index, addend,
+ QCOW2_DISCARD_SNAPSHOT);
+ } else {
+ refcount = get_refcount(bs, cluster_index);
+ }
+
+ if (refcount < 0) {
+ ret = refcount;
+ goto fail;
+ }
+ }
+
+ if (refcount == 1) {
+ offset |= QCOW_OFLAG_COPIED;
+ }
+ if (offset != old_offset) {
+ if (addend > 0) {
+ qcow2_cache_set_dependency(bs, s->l2_table_cache,
+ s->refcount_block_cache);
+ }
+ l2_table[j] = cpu_to_be64(offset);
+ qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+ }
+ }
+ }
+
+ ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ if (ret < 0) {
+ goto fail;
+ }
+
+
+ if (addend != 0) {
+ refcount = update_cluster_refcount(bs, l2_offset >> s->cluster_bits, addend,
+ QCOW2_DISCARD_SNAPSHOT);
+ } else {
+ refcount = get_refcount(bs, l2_offset >> s->cluster_bits);
+ }
+ if (refcount < 0) {
+ ret = refcount;
+ goto fail;
+ } else if (refcount == 1) {
+ l2_offset |= QCOW_OFLAG_COPIED;
+ }
+ if (l2_offset != old_l2_offset) {
+ l1_table[i] = l2_offset;
+ l1_modified = 1;
+ }
+ }
+ }
+
+ ret = bdrv_flush(bs);
+fail:
+ if (l2_table) {
+ qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+ }
+
+ s->cache_discards = false;
+ qcow2_process_discards(bs, ret);
+
+ /* Update L1 only if it isn't deleted anyway (addend = -1) */
+ if (ret == 0 && addend >= 0 && l1_modified) {
+ for (i = 0; i < l1_size; i++) {
+ cpu_to_be64s(&l1_table[i]);
+ }
+
+ ret = bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table, l1_size2);
+
+ for (i = 0; i < l1_size; i++) {
+ be64_to_cpus(&l1_table[i]);
+ }
+ }
+ if (l1_allocated)
+ g_free(l1_table);
+ return ret;
+}
+
+
+
+
+/*********************************************************/
+/* refcount checking functions */
+
+
+
+/*
+ * Increases the refcount for a range of clusters in a given refcount table.
+ * This is used to construct a temporary refcount table out of L1 and L2 tables
+ * which can be compared the the refcount table saved in the image.
+ *
+ * Modifies the number of errors in res.
+ */
+static void inc_refcounts(BlockDriverState *bs,
+ BdrvCheckResult *res,
+ uint16_t *refcount_table,
+ int refcount_table_size,
+ int64_t offset, int64_t size)
+{
+ BDRVQcowState *s = bs->opaque;
+ int64_t start, last, cluster_offset;
+ int k;
+
+ if (size <= 0)
+ return;
+
+ start = offset & ~(s->cluster_size - 1);
+ last = (offset + size - 1) & ~(s->cluster_size - 1);
+ for(cluster_offset = start; cluster_offset <= last;
+ cluster_offset += s->cluster_size) {
+ k = cluster_offset >> s->cluster_bits;
+ if (k < 0) {
+ fprintf(stderr, "ERROR: invalid cluster offset=0x%" PRIx64 "\n",
+ cluster_offset);
+ res->corruptions++;
+ } else if (k >= refcount_table_size) {
+ fprintf(stderr, "Warning: cluster offset=0x%" PRIx64 " is after "
+ "the end of the image file, can't properly check refcounts.\n",
+ cluster_offset);
+ res->check_errors++;
+ } else {
+ if (++refcount_table[k] == 0) {
+ fprintf(stderr, "ERROR: overflow cluster offset=0x%" PRIx64
+ "\n", cluster_offset);
+ res->corruptions++;
+ }
+ }
+ }
+}
+
+/* Flags for check_refcounts_l1() and check_refcounts_l2() */
+enum {
+ CHECK_OFLAG_COPIED = 0x1, /* check QCOW_OFLAG_COPIED matches refcount */
+ CHECK_FRAG_INFO = 0x2, /* update BlockFragInfo counters */
+};
+
+/*
+ * Increases the refcount in the given refcount table for the all clusters
+ * referenced in the L2 table. While doing so, performs some checks on L2
+ * entries.
+ *
+ * Returns the number of errors found by the checks or -errno if an internal
+ * error occurred.
+ */
+static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
+ uint16_t *refcount_table, int refcount_table_size, int64_t l2_offset,
+ int flags)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t *l2_table, l2_entry;
+ uint64_t next_contiguous_offset = 0;
+ int i, l2_size, nb_csectors, refcount;
+
+ /* Read L2 table from disk */
+ l2_size = s->l2_size * sizeof(uint64_t);
+ l2_table = g_malloc(l2_size);
+
+ if (bdrv_pread(bs->file, l2_offset, l2_table, l2_size) != l2_size)
+ goto fail;
+
+ /* Do the actual checks */
+ for(i = 0; i < s->l2_size; i++) {
+ l2_entry = be64_to_cpu(l2_table[i]);
+
+ switch (qcow2_get_cluster_type(l2_entry)) {
+ case QCOW2_CLUSTER_COMPRESSED:
+ /* Compressed clusters don't have QCOW_OFLAG_COPIED */
+ if (l2_entry & QCOW_OFLAG_COPIED) {
+ fprintf(stderr, "ERROR: cluster %" PRId64 ": "
+ "copied flag must never be set for compressed "
+ "clusters\n", l2_entry >> s->cluster_bits);
+ l2_entry &= ~QCOW_OFLAG_COPIED;
+ res->corruptions++;
+ }
+
+ /* Mark cluster as used */
+ nb_csectors = ((l2_entry >> s->csize_shift) &
+ s->csize_mask) + 1;
+ l2_entry &= s->cluster_offset_mask;
+ inc_refcounts(bs, res, refcount_table, refcount_table_size,
+ l2_entry & ~511, nb_csectors * 512);
+
+ if (flags & CHECK_FRAG_INFO) {
+ res->bfi.allocated_clusters++;
+ res->bfi.compressed_clusters++;
+
+ /* Compressed clusters are fragmented by nature. Since they
+ * take up sub-sector space but we only have sector granularity
+ * I/O we need to re-read the same sectors even for adjacent
+ * compressed clusters.
+ */
+ res->bfi.fragmented_clusters++;
+ }
+ break;
+
+ case QCOW2_CLUSTER_ZERO:
+ if ((l2_entry & L2E_OFFSET_MASK) == 0) {
+ break;
+ }
+ /* fall through */
+
+ case QCOW2_CLUSTER_NORMAL:
+ {
+ /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
+ uint64_t offset = l2_entry & L2E_OFFSET_MASK;
+
+ if (flags & CHECK_OFLAG_COPIED) {
+ refcount = get_refcount(bs, offset >> s->cluster_bits);
+ if (refcount < 0) {
+ fprintf(stderr, "Can't get refcount for offset %"
+ PRIx64 ": %s\n", l2_entry, strerror(-refcount));
+ goto fail;
+ }
+ if ((refcount == 1) != ((l2_entry & QCOW_OFLAG_COPIED) != 0)) {
+ fprintf(stderr, "ERROR OFLAG_COPIED: offset=%"
+ PRIx64 " refcount=%d\n", l2_entry, refcount);
+ res->corruptions++;
+ }
+ }
+
+ if (flags & CHECK_FRAG_INFO) {
+ res->bfi.allocated_clusters++;
+ if (next_contiguous_offset &&
+ offset != next_contiguous_offset) {
+ res->bfi.fragmented_clusters++;
+ }
+ next_contiguous_offset = offset + s->cluster_size;
+ }
+
+ /* Mark cluster as used */
+ inc_refcounts(bs, res, refcount_table,refcount_table_size,
+ offset, s->cluster_size);
+
+ /* Correct offsets are cluster aligned */
+ if (offset & (s->cluster_size - 1)) {
+ fprintf(stderr, "ERROR offset=%" PRIx64 ": Cluster is not "
+ "properly aligned; L2 entry corrupted.\n", offset);
+ res->corruptions++;
+ }
+ break;
+ }
+
+ case QCOW2_CLUSTER_UNALLOCATED:
+ break;
+
+ default:
+ abort();
+ }
+ }
+
+ g_free(l2_table);
+ return 0;
+
+fail:
+ fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n");
+ g_free(l2_table);
+ return -EIO;
+}
+
+/*
+ * Increases the refcount for the L1 table, its L2 tables and all referenced
+ * clusters in the given refcount table. While doing so, performs some checks
+ * on L1 and L2 entries.
+ *
+ * Returns the number of errors found by the checks or -errno if an internal
+ * error occurred.
+ */
+static int check_refcounts_l1(BlockDriverState *bs,
+ BdrvCheckResult *res,
+ uint16_t *refcount_table,
+ int refcount_table_size,
+ int64_t l1_table_offset, int l1_size,
+ int flags)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t *l1_table, l2_offset, l1_size2;
+ int i, refcount, ret;
+
+ l1_size2 = l1_size * sizeof(uint64_t);
+
+ /* Mark L1 table as used */
+ inc_refcounts(bs, res, refcount_table, refcount_table_size,
+ l1_table_offset, l1_size2);
+
+ /* Read L1 table entries from disk */
+ if (l1_size2 == 0) {
+ l1_table = NULL;
+ } else {
+ l1_table = g_malloc(l1_size2);
+ if (bdrv_pread(bs->file, l1_table_offset,
+ l1_table, l1_size2) != l1_size2)
+ goto fail;
+ for(i = 0;i < l1_size; i++)
+ be64_to_cpus(&l1_table[i]);
+ }
+
+ /* Do the actual checks */
+ for(i = 0; i < l1_size; i++) {
+ l2_offset = l1_table[i];
+ if (l2_offset) {
+ /* QCOW_OFLAG_COPIED must be set iff refcount == 1 */
+ if (flags & CHECK_OFLAG_COPIED) {
+ refcount = get_refcount(bs, (l2_offset & ~QCOW_OFLAG_COPIED)
+ >> s->cluster_bits);
+ if (refcount < 0) {
+ fprintf(stderr, "Can't get refcount for l2_offset %"
+ PRIx64 ": %s\n", l2_offset, strerror(-refcount));
+ goto fail;
+ }
+ if ((refcount == 1) != ((l2_offset & QCOW_OFLAG_COPIED) != 0)) {
+ fprintf(stderr, "ERROR OFLAG_COPIED: l2_offset=%" PRIx64
+ " refcount=%d\n", l2_offset, refcount);
+ res->corruptions++;
+ }
+ }
+
+ /* Mark L2 table as used */
+ l2_offset &= L1E_OFFSET_MASK;
+ inc_refcounts(bs, res, refcount_table, refcount_table_size,
+ l2_offset, s->cluster_size);
+
+ /* L2 tables are cluster aligned */
+ if (l2_offset & (s->cluster_size - 1)) {
+ fprintf(stderr, "ERROR l2_offset=%" PRIx64 ": Table is not "
+ "cluster aligned; L1 entry corrupted\n", l2_offset);
+ res->corruptions++;
+ }
+
+ /* Process and check L2 entries */
+ ret = check_refcounts_l2(bs, res, refcount_table,
+ refcount_table_size, l2_offset, flags);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+ }
+ g_free(l1_table);
+ return 0;
+
+fail:
+ fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n");
+ res->check_errors++;
+ g_free(l1_table);
+ return -EIO;
+}
+
+/*
+ * Checks an image for refcount consistency.
+ *
+ * Returns 0 if no errors are found, the number of errors in case the image is
+ * detected as corrupted, and -errno when an internal error occurred.
+ */
+int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
+ BdrvCheckMode fix)
+{
+ BDRVQcowState *s = bs->opaque;
+ int64_t size, i, highest_cluster;
+ int nb_clusters, refcount1, refcount2;
+ QCowSnapshot *sn;
+ uint16_t *refcount_table;
+ int ret;
+
+ size = bdrv_getlength(bs->file);
+ nb_clusters = size_to_clusters(s, size);
+ refcount_table = g_malloc0(nb_clusters * sizeof(uint16_t));
+
+ res->bfi.total_clusters =
+ size_to_clusters(s, bs->total_sectors * BDRV_SECTOR_SIZE);
+
+ /* header */
+ inc_refcounts(bs, res, refcount_table, nb_clusters,
+ 0, s->cluster_size);
+
+ /* current L1 table */
+ ret = check_refcounts_l1(bs, res, refcount_table, nb_clusters,
+ s->l1_table_offset, s->l1_size,
+ CHECK_OFLAG_COPIED | CHECK_FRAG_INFO);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* snapshots */
+ for(i = 0; i < s->nb_snapshots; i++) {
+ sn = s->snapshots + i;
+ ret = check_refcounts_l1(bs, res, refcount_table, nb_clusters,
+ sn->l1_table_offset, sn->l1_size, 0);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+ inc_refcounts(bs, res, refcount_table, nb_clusters,
+ s->snapshots_offset, s->snapshots_size);
+
+ /* refcount data */
+ inc_refcounts(bs, res, refcount_table, nb_clusters,
+ s->refcount_table_offset,
+ s->refcount_table_size * sizeof(uint64_t));
+
+ for(i = 0; i < s->refcount_table_size; i++) {
+ uint64_t offset, cluster;
+ offset = s->refcount_table[i];
+ cluster = offset >> s->cluster_bits;
+
+ /* Refcount blocks are cluster aligned */
+ if (offset & (s->cluster_size - 1)) {
+ fprintf(stderr, "ERROR refcount block %" PRId64 " is not "
+ "cluster aligned; refcount table entry corrupted\n", i);
+ res->corruptions++;
+ continue;
+ }
+
+ if (cluster >= nb_clusters) {
+ fprintf(stderr, "ERROR refcount block %" PRId64
+ " is outside image\n", i);
+ res->corruptions++;
+ continue;
+ }
+
+ if (offset != 0) {
+ inc_refcounts(bs, res, refcount_table, nb_clusters,
+ offset, s->cluster_size);
+ if (refcount_table[cluster] != 1) {
+ fprintf(stderr, "ERROR refcount block %" PRId64
+ " refcount=%d\n",
+ i, refcount_table[cluster]);
+ res->corruptions++;
+ }
+ }
+ }
+
+ /* compare ref counts */
+ for (i = 0, highest_cluster = 0; i < nb_clusters; i++) {
+ refcount1 = get_refcount(bs, i);
+ if (refcount1 < 0) {
+ fprintf(stderr, "Can't get refcount for cluster %" PRId64 ": %s\n",
+ i, strerror(-refcount1));
+ res->check_errors++;
+ continue;
+ }
+
+ refcount2 = refcount_table[i];
+
+ if (refcount1 > 0 || refcount2 > 0) {
+ highest_cluster = i;
+ }
+
+ if (refcount1 != refcount2) {
+
+ /* Check if we're allowed to fix the mismatch */
+ int *num_fixed = NULL;
+ if (refcount1 > refcount2 && (fix & BDRV_FIX_LEAKS)) {
+ num_fixed = &res->leaks_fixed;
+ } else if (refcount1 < refcount2 && (fix & BDRV_FIX_ERRORS)) {
+ num_fixed = &res->corruptions_fixed;
+ }
+
+ fprintf(stderr, "%s cluster %" PRId64 " refcount=%d reference=%d\n",
+ num_fixed != NULL ? "Repairing" :
+ refcount1 < refcount2 ? "ERROR" :
+ "Leaked",
+ i, refcount1, refcount2);
+
+ if (num_fixed) {
+ ret = update_refcount(bs, i << s->cluster_bits, 1,
+ refcount2 - refcount1,
+ QCOW2_DISCARD_ALWAYS);
+ if (ret >= 0) {
+ (*num_fixed)++;
+ continue;
+ }
+ }
+
+ /* And if we couldn't, print an error */
+ if (refcount1 < refcount2) {
+ res->corruptions++;
+ } else {
+ res->leaks++;
+ }
+ }
+ }
+
+ res->image_end_offset = (highest_cluster + 1) * s->cluster_size;
+ ret = 0;
+
+fail:
+ g_free(refcount_table);
+
+ return ret;
+}
+
diff --git a/contrib/qemu/block/qcow2-snapshot.c b/contrib/qemu/block/qcow2-snapshot.c
new file mode 100644
index 00000000000..0caac9055f8
--- /dev/null
+++ b/contrib/qemu/block/qcow2-snapshot.c
@@ -0,0 +1,660 @@
+/*
+ * Block driver for the QCOW version 2 format
+ *
+ * Copyright (c) 2004-2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "block/qcow2.h"
+
+typedef struct QEMU_PACKED QCowSnapshotHeader {
+ /* header is 8 byte aligned */
+ uint64_t l1_table_offset;
+
+ uint32_t l1_size;
+ uint16_t id_str_size;
+ uint16_t name_size;
+
+ uint32_t date_sec;
+ uint32_t date_nsec;
+
+ uint64_t vm_clock_nsec;
+
+ uint32_t vm_state_size;
+ uint32_t extra_data_size; /* for extension */
+ /* extra data follows */
+ /* id_str follows */
+ /* name follows */
+} QCowSnapshotHeader;
+
+typedef struct QEMU_PACKED QCowSnapshotExtraData {
+ uint64_t vm_state_size_large;
+ uint64_t disk_size;
+} QCowSnapshotExtraData;
+
+void qcow2_free_snapshots(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ int i;
+
+ for(i = 0; i < s->nb_snapshots; i++) {
+ g_free(s->snapshots[i].name);
+ g_free(s->snapshots[i].id_str);
+ }
+ g_free(s->snapshots);
+ s->snapshots = NULL;
+ s->nb_snapshots = 0;
+}
+
+int qcow2_read_snapshots(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowSnapshotHeader h;
+ QCowSnapshotExtraData extra;
+ QCowSnapshot *sn;
+ int i, id_str_size, name_size;
+ int64_t offset;
+ uint32_t extra_data_size;
+ int ret;
+
+ if (!s->nb_snapshots) {
+ s->snapshots = NULL;
+ s->snapshots_size = 0;
+ return 0;
+ }
+
+ offset = s->snapshots_offset;
+ s->snapshots = g_malloc0(s->nb_snapshots * sizeof(QCowSnapshot));
+
+ for(i = 0; i < s->nb_snapshots; i++) {
+ /* Read statically sized part of the snapshot header */
+ offset = align_offset(offset, 8);
+ ret = bdrv_pread(bs->file, offset, &h, sizeof(h));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ offset += sizeof(h);
+ sn = s->snapshots + i;
+ sn->l1_table_offset = be64_to_cpu(h.l1_table_offset);
+ sn->l1_size = be32_to_cpu(h.l1_size);
+ sn->vm_state_size = be32_to_cpu(h.vm_state_size);
+ sn->date_sec = be32_to_cpu(h.date_sec);
+ sn->date_nsec = be32_to_cpu(h.date_nsec);
+ sn->vm_clock_nsec = be64_to_cpu(h.vm_clock_nsec);
+ extra_data_size = be32_to_cpu(h.extra_data_size);
+
+ id_str_size = be16_to_cpu(h.id_str_size);
+ name_size = be16_to_cpu(h.name_size);
+
+ /* Read extra data */
+ ret = bdrv_pread(bs->file, offset, &extra,
+ MIN(sizeof(extra), extra_data_size));
+ if (ret < 0) {
+ goto fail;
+ }
+ offset += extra_data_size;
+
+ if (extra_data_size >= 8) {
+ sn->vm_state_size = be64_to_cpu(extra.vm_state_size_large);
+ }
+
+ if (extra_data_size >= 16) {
+ sn->disk_size = be64_to_cpu(extra.disk_size);
+ } else {
+ sn->disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;
+ }
+
+ /* Read snapshot ID */
+ sn->id_str = g_malloc(id_str_size + 1);
+ ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size);
+ if (ret < 0) {
+ goto fail;
+ }
+ offset += id_str_size;
+ sn->id_str[id_str_size] = '\0';
+
+ /* Read snapshot name */
+ sn->name = g_malloc(name_size + 1);
+ ret = bdrv_pread(bs->file, offset, sn->name, name_size);
+ if (ret < 0) {
+ goto fail;
+ }
+ offset += name_size;
+ sn->name[name_size] = '\0';
+ }
+
+ s->snapshots_size = offset - s->snapshots_offset;
+ return 0;
+
+fail:
+ qcow2_free_snapshots(bs);
+ return ret;
+}
+
+/* add at the end of the file a new list of snapshots */
+static int qcow2_write_snapshots(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowSnapshot *sn;
+ QCowSnapshotHeader h;
+ QCowSnapshotExtraData extra;
+ int i, name_size, id_str_size, snapshots_size;
+ struct {
+ uint32_t nb_snapshots;
+ uint64_t snapshots_offset;
+ } QEMU_PACKED header_data;
+ int64_t offset, snapshots_offset;
+ int ret;
+
+ /* compute the size of the snapshots */
+ offset = 0;
+ for(i = 0; i < s->nb_snapshots; i++) {
+ sn = s->snapshots + i;
+ offset = align_offset(offset, 8);
+ offset += sizeof(h);
+ offset += sizeof(extra);
+ offset += strlen(sn->id_str);
+ offset += strlen(sn->name);
+ }
+ snapshots_size = offset;
+
+ /* Allocate space for the new snapshot list */
+ snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size);
+ offset = snapshots_offset;
+ if (offset < 0) {
+ return offset;
+ }
+ ret = bdrv_flush(bs);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Write all snapshots to the new list */
+ for(i = 0; i < s->nb_snapshots; i++) {
+ sn = s->snapshots + i;
+ memset(&h, 0, sizeof(h));
+ h.l1_table_offset = cpu_to_be64(sn->l1_table_offset);
+ h.l1_size = cpu_to_be32(sn->l1_size);
+ /* If it doesn't fit in 32 bit, older implementations should treat it
+ * as a disk-only snapshot rather than truncate the VM state */
+ if (sn->vm_state_size <= 0xffffffff) {
+ h.vm_state_size = cpu_to_be32(sn->vm_state_size);
+ }
+ h.date_sec = cpu_to_be32(sn->date_sec);
+ h.date_nsec = cpu_to_be32(sn->date_nsec);
+ h.vm_clock_nsec = cpu_to_be64(sn->vm_clock_nsec);
+ h.extra_data_size = cpu_to_be32(sizeof(extra));
+
+ memset(&extra, 0, sizeof(extra));
+ extra.vm_state_size_large = cpu_to_be64(sn->vm_state_size);
+ extra.disk_size = cpu_to_be64(sn->disk_size);
+
+ id_str_size = strlen(sn->id_str);
+ name_size = strlen(sn->name);
+ h.id_str_size = cpu_to_be16(id_str_size);
+ h.name_size = cpu_to_be16(name_size);
+ offset = align_offset(offset, 8);
+
+ ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h));
+ if (ret < 0) {
+ goto fail;
+ }
+ offset += sizeof(h);
+
+ ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra));
+ if (ret < 0) {
+ goto fail;
+ }
+ offset += sizeof(extra);
+
+ ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size);
+ if (ret < 0) {
+ goto fail;
+ }
+ offset += id_str_size;
+
+ ret = bdrv_pwrite(bs->file, offset, sn->name, name_size);
+ if (ret < 0) {
+ goto fail;
+ }
+ offset += name_size;
+ }
+
+ /*
+ * Update the header to point to the new snapshot table. This requires the
+ * new table and its refcounts to be stable on disk.
+ */
+ ret = bdrv_flush(bs);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ QEMU_BUILD_BUG_ON(offsetof(QCowHeader, snapshots_offset) !=
+ offsetof(QCowHeader, nb_snapshots) + sizeof(header_data.nb_snapshots));
+
+ header_data.nb_snapshots = cpu_to_be32(s->nb_snapshots);
+ header_data.snapshots_offset = cpu_to_be64(snapshots_offset);
+
+ ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots),
+ &header_data, sizeof(header_data));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* free the old snapshot table */
+ qcow2_free_clusters(bs, s->snapshots_offset, s->snapshots_size,
+ QCOW2_DISCARD_SNAPSHOT);
+ s->snapshots_offset = snapshots_offset;
+ s->snapshots_size = snapshots_size;
+ return 0;
+
+fail:
+ return ret;
+}
+
+static void find_new_snapshot_id(BlockDriverState *bs,
+ char *id_str, int id_str_size)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowSnapshot *sn;
+ int i, id, id_max = 0;
+
+ for(i = 0; i < s->nb_snapshots; i++) {
+ sn = s->snapshots + i;
+ id = strtoul(sn->id_str, NULL, 10);
+ if (id > id_max)
+ id_max = id;
+ }
+ snprintf(id_str, id_str_size, "%d", id_max + 1);
+}
+
+static int find_snapshot_by_id(BlockDriverState *bs, const char *id_str)
+{
+ BDRVQcowState *s = bs->opaque;
+ int i;
+
+ for(i = 0; i < s->nb_snapshots; i++) {
+ if (!strcmp(s->snapshots[i].id_str, id_str))
+ return i;
+ }
+ return -1;
+}
+
+static int find_snapshot_by_id_or_name(BlockDriverState *bs, const char *name)
+{
+ BDRVQcowState *s = bs->opaque;
+ int i, ret;
+
+ ret = find_snapshot_by_id(bs, name);
+ if (ret >= 0)
+ return ret;
+ for(i = 0; i < s->nb_snapshots; i++) {
+ if (!strcmp(s->snapshots[i].name, name))
+ return i;
+ }
+ return -1;
+}
+
+/* if no id is provided, a new one is constructed */
+int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowSnapshot *new_snapshot_list = NULL;
+ QCowSnapshot *old_snapshot_list = NULL;
+ QCowSnapshot sn1, *sn = &sn1;
+ int i, ret;
+ uint64_t *l1_table = NULL;
+ int64_t l1_table_offset;
+
+ memset(sn, 0, sizeof(*sn));
+
+ /* Generate an ID if it wasn't passed */
+ if (sn_info->id_str[0] == '\0') {
+ find_new_snapshot_id(bs, sn_info->id_str, sizeof(sn_info->id_str));
+ }
+
+ /* Check that the ID is unique */
+ if (find_snapshot_by_id(bs, sn_info->id_str) >= 0) {
+ return -EEXIST;
+ }
+
+ /* Populate sn with passed data */
+ sn->id_str = g_strdup(sn_info->id_str);
+ sn->name = g_strdup(sn_info->name);
+
+ sn->disk_size = bs->total_sectors * BDRV_SECTOR_SIZE;
+ sn->vm_state_size = sn_info->vm_state_size;
+ sn->date_sec = sn_info->date_sec;
+ sn->date_nsec = sn_info->date_nsec;
+ sn->vm_clock_nsec = sn_info->vm_clock_nsec;
+
+ /* Allocate the L1 table of the snapshot and copy the current one there. */
+ l1_table_offset = qcow2_alloc_clusters(bs, s->l1_size * sizeof(uint64_t));
+ if (l1_table_offset < 0) {
+ ret = l1_table_offset;
+ goto fail;
+ }
+
+ sn->l1_table_offset = l1_table_offset;
+ sn->l1_size = s->l1_size;
+
+ l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
+ for(i = 0; i < s->l1_size; i++) {
+ l1_table[i] = cpu_to_be64(s->l1_table[i]);
+ }
+
+ ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table,
+ s->l1_size * sizeof(uint64_t));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ g_free(l1_table);
+ l1_table = NULL;
+
+ /*
+ * Increase the refcounts of all clusters and make sure everything is
+ * stable on disk before updating the snapshot table to contain a pointer
+ * to the new L1 table.
+ */
+ ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 1);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Append the new snapshot to the snapshot list */
+ new_snapshot_list = g_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
+ if (s->snapshots) {
+ memcpy(new_snapshot_list, s->snapshots,
+ s->nb_snapshots * sizeof(QCowSnapshot));
+ old_snapshot_list = s->snapshots;
+ }
+ s->snapshots = new_snapshot_list;
+ s->snapshots[s->nb_snapshots++] = *sn;
+
+ ret = qcow2_write_snapshots(bs);
+ if (ret < 0) {
+ g_free(s->snapshots);
+ s->snapshots = old_snapshot_list;
+ goto fail;
+ }
+
+ g_free(old_snapshot_list);
+
+#ifdef DEBUG_ALLOC
+ {
+ BdrvCheckResult result = {0};
+ qcow2_check_refcounts(bs, &result, 0);
+ }
+#endif
+ return 0;
+
+fail:
+ g_free(sn->id_str);
+ g_free(sn->name);
+ g_free(l1_table);
+
+ return ret;
+}
+
+/* copy the snapshot 'snapshot_name' into the current disk image */
+int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowSnapshot *sn;
+ int i, snapshot_index;
+ int cur_l1_bytes, sn_l1_bytes;
+ int ret;
+ uint64_t *sn_l1_table = NULL;
+
+ /* Search the snapshot */
+ snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
+ if (snapshot_index < 0) {
+ return -ENOENT;
+ }
+ sn = &s->snapshots[snapshot_index];
+
+ if (sn->disk_size != bs->total_sectors * BDRV_SECTOR_SIZE) {
+ error_report("qcow2: Loading snapshots with different disk "
+ "size is not implemented");
+ ret = -ENOTSUP;
+ goto fail;
+ }
+
+ /*
+ * Make sure that the current L1 table is big enough to contain the whole
+ * L1 table of the snapshot. If the snapshot L1 table is smaller, the
+ * current one must be padded with zeros.
+ */
+ ret = qcow2_grow_l1_table(bs, sn->l1_size, true);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ cur_l1_bytes = s->l1_size * sizeof(uint64_t);
+ sn_l1_bytes = sn->l1_size * sizeof(uint64_t);
+
+ /*
+ * Copy the snapshot L1 table to the current L1 table.
+ *
+ * Before overwriting the old current L1 table on disk, make sure to
+ * increase all refcounts for the clusters referenced by the new one.
+ * Decrease the refcount referenced by the old one only when the L1
+ * table is overwritten.
+ */
+ sn_l1_table = g_malloc0(cur_l1_bytes);
+
+ ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = qcow2_update_snapshot_refcount(bs, sn->l1_table_offset,
+ sn->l1_size, 1);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table,
+ cur_l1_bytes);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /*
+ * Decrease refcount of clusters of current L1 table.
+ *
+ * At this point, the in-memory s->l1_table points to the old L1 table,
+ * whereas on disk we already have the new one.
+ *
+ * qcow2_update_snapshot_refcount special cases the current L1 table to use
+ * the in-memory data instead of really using the offset to load a new one,
+ * which is why this works.
+ */
+ ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset,
+ s->l1_size, -1);
+
+ /*
+ * Now update the in-memory L1 table to be in sync with the on-disk one. We
+ * need to do this even if updating refcounts failed.
+ */
+ for(i = 0;i < s->l1_size; i++) {
+ s->l1_table[i] = be64_to_cpu(sn_l1_table[i]);
+ }
+
+ if (ret < 0) {
+ goto fail;
+ }
+
+ g_free(sn_l1_table);
+ sn_l1_table = NULL;
+
+ /*
+ * Update QCOW_OFLAG_COPIED in the active L1 table (it may have changed
+ * when we decreased the refcount of the old snapshot.
+ */
+ ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
+ if (ret < 0) {
+ goto fail;
+ }
+
+#ifdef DEBUG_ALLOC
+ {
+ BdrvCheckResult result = {0};
+ qcow2_check_refcounts(bs, &result, 0);
+ }
+#endif
+ return 0;
+
+fail:
+ g_free(sn_l1_table);
+ return ret;
+}
+
+int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowSnapshot sn;
+ int snapshot_index, ret;
+
+ /* Search the snapshot */
+ snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_id);
+ if (snapshot_index < 0) {
+ return -ENOENT;
+ }
+ sn = s->snapshots[snapshot_index];
+
+ /* Remove it from the snapshot list */
+ memmove(s->snapshots + snapshot_index,
+ s->snapshots + snapshot_index + 1,
+ (s->nb_snapshots - snapshot_index - 1) * sizeof(sn));
+ s->nb_snapshots--;
+ ret = qcow2_write_snapshots(bs);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /*
+ * The snapshot is now unused, clean up. If we fail after this point, we
+ * won't recover but just leak clusters.
+ */
+ g_free(sn.id_str);
+ g_free(sn.name);
+
+ /*
+ * Now decrease the refcounts of clusters referenced by the snapshot and
+ * free the L1 table.
+ */
+ ret = qcow2_update_snapshot_refcount(bs, sn.l1_table_offset,
+ sn.l1_size, -1);
+ if (ret < 0) {
+ return ret;
+ }
+ qcow2_free_clusters(bs, sn.l1_table_offset, sn.l1_size * sizeof(uint64_t),
+ QCOW2_DISCARD_SNAPSHOT);
+
+ /* must update the copied flag on the current cluster offsets */
+ ret = qcow2_update_snapshot_refcount(bs, s->l1_table_offset, s->l1_size, 0);
+ if (ret < 0) {
+ return ret;
+ }
+
+#ifdef DEBUG_ALLOC
+ {
+ BdrvCheckResult result = {0};
+ qcow2_check_refcounts(bs, &result, 0);
+ }
+#endif
+ return 0;
+}
+
+int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
+{
+ BDRVQcowState *s = bs->opaque;
+ QEMUSnapshotInfo *sn_tab, *sn_info;
+ QCowSnapshot *sn;
+ int i;
+
+ if (!s->nb_snapshots) {
+ *psn_tab = NULL;
+ return s->nb_snapshots;
+ }
+
+ sn_tab = g_malloc0(s->nb_snapshots * sizeof(QEMUSnapshotInfo));
+ for(i = 0; i < s->nb_snapshots; i++) {
+ sn_info = sn_tab + i;
+ sn = s->snapshots + i;
+ pstrcpy(sn_info->id_str, sizeof(sn_info->id_str),
+ sn->id_str);
+ pstrcpy(sn_info->name, sizeof(sn_info->name),
+ sn->name);
+ sn_info->vm_state_size = sn->vm_state_size;
+ sn_info->date_sec = sn->date_sec;
+ sn_info->date_nsec = sn->date_nsec;
+ sn_info->vm_clock_nsec = sn->vm_clock_nsec;
+ }
+ *psn_tab = sn_tab;
+ return s->nb_snapshots;
+}
+
+int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name)
+{
+ int i, snapshot_index;
+ BDRVQcowState *s = bs->opaque;
+ QCowSnapshot *sn;
+ uint64_t *new_l1_table;
+ int new_l1_bytes;
+ int ret;
+
+ assert(bs->read_only);
+
+ /* Search the snapshot */
+ snapshot_index = find_snapshot_by_id_or_name(bs, snapshot_name);
+ if (snapshot_index < 0) {
+ return -ENOENT;
+ }
+ sn = &s->snapshots[snapshot_index];
+
+ /* Allocate and read in the snapshot's L1 table */
+ new_l1_bytes = s->l1_size * sizeof(uint64_t);
+ new_l1_table = g_malloc0(align_offset(new_l1_bytes, 512));
+
+ ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);
+ if (ret < 0) {
+ g_free(new_l1_table);
+ return ret;
+ }
+
+ /* Switch the L1 table */
+ g_free(s->l1_table);
+
+ s->l1_size = sn->l1_size;
+ s->l1_table_offset = sn->l1_table_offset;
+ s->l1_table = new_l1_table;
+
+ for(i = 0;i < s->l1_size; i++) {
+ be64_to_cpus(&s->l1_table[i]);
+ }
+
+ return 0;
+}
diff --git a/contrib/qemu/block/qcow2.c b/contrib/qemu/block/qcow2.c
new file mode 100644
index 00000000000..0eceefe2cd9
--- /dev/null
+++ b/contrib/qemu/block/qcow2.c
@@ -0,0 +1,1825 @@
+/*
+ * Block driver for the QCOW version 2 format
+ *
+ * Copyright (c) 2004-2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "qemu/module.h"
+#include <zlib.h>
+#include "qemu/aes.h"
+#include "block/qcow2.h"
+#include "qemu/error-report.h"
+#include "qapi/qmp/qerror.h"
+#include "qapi/qmp/qbool.h"
+#include "trace.h"
+
+/*
+ Differences with QCOW:
+
+ - Support for multiple incremental snapshots.
+ - Memory management by reference counts.
+ - Clusters which have a reference count of one have the bit
+ QCOW_OFLAG_COPIED to optimize write performance.
+ - Size of compressed clusters is stored in sectors to reduce bit usage
+ in the cluster offsets.
+ - Support for storing additional data (such as the VM state) in the
+ snapshots.
+ - If a backing store is used, the cluster size is not constrained
+ (could be backported to QCOW).
+ - L2 tables have always a size of one cluster.
+*/
+
+
+typedef struct {
+ uint32_t magic;
+ uint32_t len;
+} QCowExtension;
+
+#define QCOW2_EXT_MAGIC_END 0
+#define QCOW2_EXT_MAGIC_BACKING_FORMAT 0xE2792ACA
+#define QCOW2_EXT_MAGIC_FEATURE_TABLE 0x6803f857
+
+static int qcow2_probe(const uint8_t *buf, int buf_size, const char *filename)
+{
+ const QCowHeader *cow_header = (const void *)buf;
+
+ if (buf_size >= sizeof(QCowHeader) &&
+ be32_to_cpu(cow_header->magic) == QCOW_MAGIC &&
+ be32_to_cpu(cow_header->version) >= 2)
+ return 100;
+ else
+ return 0;
+}
+
+
+/*
+ * read qcow2 extension and fill bs
+ * start reading from start_offset
+ * finish reading upon magic of value 0 or when end_offset reached
+ * unknown magic is skipped (future extension this version knows nothing about)
+ * return 0 upon success, non-0 otherwise
+ */
+static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,
+ uint64_t end_offset, void **p_feature_table)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowExtension ext;
+ uint64_t offset;
+ int ret;
+
+#ifdef DEBUG_EXT
+ printf("qcow2_read_extensions: start=%ld end=%ld\n", start_offset, end_offset);
+#endif
+ offset = start_offset;
+ while (offset < end_offset) {
+
+#ifdef DEBUG_EXT
+ /* Sanity check */
+ if (offset > s->cluster_size)
+ printf("qcow2_read_extension: suspicious offset %lu\n", offset);
+
+ printf("attempting to read extended header in offset %lu\n", offset);
+#endif
+
+ if (bdrv_pread(bs->file, offset, &ext, sizeof(ext)) != sizeof(ext)) {
+ fprintf(stderr, "qcow2_read_extension: ERROR: "
+ "pread fail from offset %" PRIu64 "\n",
+ offset);
+ return 1;
+ }
+ be32_to_cpus(&ext.magic);
+ be32_to_cpus(&ext.len);
+ offset += sizeof(ext);
+#ifdef DEBUG_EXT
+ printf("ext.magic = 0x%x\n", ext.magic);
+#endif
+ if (ext.len > end_offset - offset) {
+ error_report("Header extension too large");
+ return -EINVAL;
+ }
+
+ switch (ext.magic) {
+ case QCOW2_EXT_MAGIC_END:
+ return 0;
+
+ case QCOW2_EXT_MAGIC_BACKING_FORMAT:
+ if (ext.len >= sizeof(bs->backing_format)) {
+ fprintf(stderr, "ERROR: ext_backing_format: len=%u too large"
+ " (>=%zu)\n",
+ ext.len, sizeof(bs->backing_format));
+ return 2;
+ }
+ if (bdrv_pread(bs->file, offset , bs->backing_format,
+ ext.len) != ext.len)
+ return 3;
+ bs->backing_format[ext.len] = '\0';
+#ifdef DEBUG_EXT
+ printf("Qcow2: Got format extension %s\n", bs->backing_format);
+#endif
+ break;
+
+ case QCOW2_EXT_MAGIC_FEATURE_TABLE:
+ if (p_feature_table != NULL) {
+ void* feature_table = g_malloc0(ext.len + 2 * sizeof(Qcow2Feature));
+ ret = bdrv_pread(bs->file, offset , feature_table, ext.len);
+ if (ret < 0) {
+ return ret;
+ }
+
+ *p_feature_table = feature_table;
+ }
+ break;
+
+ default:
+ /* unknown magic - save it in case we need to rewrite the header */
+ {
+ Qcow2UnknownHeaderExtension *uext;
+
+ uext = g_malloc0(sizeof(*uext) + ext.len);
+ uext->magic = ext.magic;
+ uext->len = ext.len;
+ QLIST_INSERT_HEAD(&s->unknown_header_ext, uext, next);
+
+ ret = bdrv_pread(bs->file, offset , uext->data, uext->len);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+ break;
+ }
+
+ offset += ((ext.len + 7) & ~7);
+ }
+
+ return 0;
+}
+
+static void cleanup_unknown_header_ext(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ Qcow2UnknownHeaderExtension *uext, *next;
+
+ QLIST_FOREACH_SAFE(uext, &s->unknown_header_ext, next, next) {
+ QLIST_REMOVE(uext, next);
+ g_free(uext);
+ }
+}
+
+static void GCC_FMT_ATTR(2, 3) report_unsupported(BlockDriverState *bs,
+ const char *fmt, ...)
+{
+ char msg[64];
+ va_list ap;
+
+ va_start(ap, fmt);
+ vsnprintf(msg, sizeof(msg), fmt, ap);
+ va_end(ap);
+
+ qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+ bs->device_name, "qcow2", msg);
+}
+
+static void report_unsupported_feature(BlockDriverState *bs,
+ Qcow2Feature *table, uint64_t mask)
+{
+ while (table && table->name[0] != '\0') {
+ if (table->type == QCOW2_FEAT_TYPE_INCOMPATIBLE) {
+ if (mask & (1 << table->bit)) {
+ report_unsupported(bs, "%.46s",table->name);
+ mask &= ~(1 << table->bit);
+ }
+ }
+ table++;
+ }
+
+ if (mask) {
+ report_unsupported(bs, "Unknown incompatible feature: %" PRIx64, mask);
+ }
+}
+
+/*
+ * Sets the dirty bit and flushes afterwards if necessary.
+ *
+ * The incompatible_features bit is only set if the image file header was
+ * updated successfully. Therefore it is not required to check the return
+ * value of this function.
+ */
+int qcow2_mark_dirty(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t val;
+ int ret;
+
+ assert(s->qcow_version >= 3);
+
+ if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
+ return 0; /* already dirty */
+ }
+
+ val = cpu_to_be64(s->incompatible_features | QCOW2_INCOMPAT_DIRTY);
+ ret = bdrv_pwrite(bs->file, offsetof(QCowHeader, incompatible_features),
+ &val, sizeof(val));
+ if (ret < 0) {
+ return ret;
+ }
+ ret = bdrv_flush(bs->file);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Only treat image as dirty if the header was updated successfully */
+ s->incompatible_features |= QCOW2_INCOMPAT_DIRTY;
+ return 0;
+}
+
+/*
+ * Clears the dirty bit and flushes before if necessary. Only call this
+ * function when there are no pending requests, it does not guard against
+ * concurrent requests dirtying the image.
+ */
+static int qcow2_mark_clean(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+
+ if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
+ int ret = bdrv_flush(bs);
+ if (ret < 0) {
+ return ret;
+ }
+
+ s->incompatible_features &= ~QCOW2_INCOMPAT_DIRTY;
+ return qcow2_update_header(bs);
+ }
+ return 0;
+}
+
+static int qcow2_check(BlockDriverState *bs, BdrvCheckResult *result,
+ BdrvCheckMode fix)
+{
+ int ret = qcow2_check_refcounts(bs, result, fix);
+ if (ret < 0) {
+ return ret;
+ }
+
+ if (fix && result->check_errors == 0 && result->corruptions == 0) {
+ return qcow2_mark_clean(bs);
+ }
+ return ret;
+}
+
+static QemuOptsList qcow2_runtime_opts = {
+ .name = "qcow2",
+ .head = QTAILQ_HEAD_INITIALIZER(qcow2_runtime_opts.head),
+ .desc = {
+ {
+ .name = "lazy_refcounts",
+ .type = QEMU_OPT_BOOL,
+ .help = "Postpone refcount updates",
+ },
+ {
+ .name = QCOW2_OPT_DISCARD_REQUEST,
+ .type = QEMU_OPT_BOOL,
+ .help = "Pass guest discard requests to the layer below",
+ },
+ {
+ .name = QCOW2_OPT_DISCARD_SNAPSHOT,
+ .type = QEMU_OPT_BOOL,
+ .help = "Generate discard requests when snapshot related space "
+ "is freed",
+ },
+ {
+ .name = QCOW2_OPT_DISCARD_OTHER,
+ .type = QEMU_OPT_BOOL,
+ .help = "Generate discard requests when other clusters are freed",
+ },
+ { /* end of list */ }
+ },
+};
+
+static int qcow2_open(BlockDriverState *bs, QDict *options, int flags)
+{
+ BDRVQcowState *s = bs->opaque;
+ int len, i, ret = 0;
+ QCowHeader header;
+ QemuOpts *opts;
+ Error *local_err = NULL;
+ uint64_t ext_end;
+ uint64_t l1_vm_state_index;
+
+ ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
+ if (ret < 0) {
+ goto fail;
+ }
+ be32_to_cpus(&header.magic);
+ be32_to_cpus(&header.version);
+ be64_to_cpus(&header.backing_file_offset);
+ be32_to_cpus(&header.backing_file_size);
+ be64_to_cpus(&header.size);
+ be32_to_cpus(&header.cluster_bits);
+ be32_to_cpus(&header.crypt_method);
+ be64_to_cpus(&header.l1_table_offset);
+ be32_to_cpus(&header.l1_size);
+ be64_to_cpus(&header.refcount_table_offset);
+ be32_to_cpus(&header.refcount_table_clusters);
+ be64_to_cpus(&header.snapshots_offset);
+ be32_to_cpus(&header.nb_snapshots);
+
+ if (header.magic != QCOW_MAGIC) {
+ ret = -EMEDIUMTYPE;
+ goto fail;
+ }
+ if (header.version < 2 || header.version > 3) {
+ report_unsupported(bs, "QCOW version %d", header.version);
+ ret = -ENOTSUP;
+ goto fail;
+ }
+
+ s->qcow_version = header.version;
+
+ /* Initialise version 3 header fields */
+ if (header.version == 2) {
+ header.incompatible_features = 0;
+ header.compatible_features = 0;
+ header.autoclear_features = 0;
+ header.refcount_order = 4;
+ header.header_length = 72;
+ } else {
+ be64_to_cpus(&header.incompatible_features);
+ be64_to_cpus(&header.compatible_features);
+ be64_to_cpus(&header.autoclear_features);
+ be32_to_cpus(&header.refcount_order);
+ be32_to_cpus(&header.header_length);
+ }
+
+ if (header.header_length > sizeof(header)) {
+ s->unknown_header_fields_size = header.header_length - sizeof(header);
+ s->unknown_header_fields = g_malloc(s->unknown_header_fields_size);
+ ret = bdrv_pread(bs->file, sizeof(header), s->unknown_header_fields,
+ s->unknown_header_fields_size);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ if (header.backing_file_offset) {
+ ext_end = header.backing_file_offset;
+ } else {
+ ext_end = 1 << header.cluster_bits;
+ }
+
+ /* Handle feature bits */
+ s->incompatible_features = header.incompatible_features;
+ s->compatible_features = header.compatible_features;
+ s->autoclear_features = header.autoclear_features;
+
+ if (s->incompatible_features & ~QCOW2_INCOMPAT_MASK) {
+ void *feature_table = NULL;
+ qcow2_read_extensions(bs, header.header_length, ext_end,
+ &feature_table);
+ report_unsupported_feature(bs, feature_table,
+ s->incompatible_features &
+ ~QCOW2_INCOMPAT_MASK);
+ ret = -ENOTSUP;
+ goto fail;
+ }
+
+ /* Check support for various header values */
+ if (header.refcount_order != 4) {
+ report_unsupported(bs, "%d bit reference counts",
+ 1 << header.refcount_order);
+ ret = -ENOTSUP;
+ goto fail;
+ }
+
+ if (header.cluster_bits < MIN_CLUSTER_BITS ||
+ header.cluster_bits > MAX_CLUSTER_BITS) {
+ ret = -EINVAL;
+ goto fail;
+ }
+ if (header.crypt_method > QCOW_CRYPT_AES) {
+ ret = -EINVAL;
+ goto fail;
+ }
+ s->crypt_method_header = header.crypt_method;
+ if (s->crypt_method_header) {
+ bs->encrypted = 1;
+ }
+ s->cluster_bits = header.cluster_bits;
+ s->cluster_size = 1 << s->cluster_bits;
+ s->cluster_sectors = 1 << (s->cluster_bits - 9);
+ s->l2_bits = s->cluster_bits - 3; /* L2 is always one cluster */
+ s->l2_size = 1 << s->l2_bits;
+ bs->total_sectors = header.size / 512;
+ s->csize_shift = (62 - (s->cluster_bits - 8));
+ s->csize_mask = (1 << (s->cluster_bits - 8)) - 1;
+ s->cluster_offset_mask = (1LL << s->csize_shift) - 1;
+ s->refcount_table_offset = header.refcount_table_offset;
+ s->refcount_table_size =
+ header.refcount_table_clusters << (s->cluster_bits - 3);
+
+ s->snapshots_offset = header.snapshots_offset;
+ s->nb_snapshots = header.nb_snapshots;
+
+ /* read the level 1 table */
+ s->l1_size = header.l1_size;
+
+ l1_vm_state_index = size_to_l1(s, header.size);
+ if (l1_vm_state_index > INT_MAX) {
+ ret = -EFBIG;
+ goto fail;
+ }
+ s->l1_vm_state_index = l1_vm_state_index;
+
+ /* the L1 table must contain at least enough entries to put
+ header.size bytes */
+ if (s->l1_size < s->l1_vm_state_index) {
+ ret = -EINVAL;
+ goto fail;
+ }
+ s->l1_table_offset = header.l1_table_offset;
+ if (s->l1_size > 0) {
+ s->l1_table = g_malloc0(
+ align_offset(s->l1_size * sizeof(uint64_t), 512));
+ ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table,
+ s->l1_size * sizeof(uint64_t));
+ if (ret < 0) {
+ goto fail;
+ }
+ for(i = 0;i < s->l1_size; i++) {
+ be64_to_cpus(&s->l1_table[i]);
+ }
+ }
+
+ /* alloc L2 table/refcount block cache */
+ s->l2_table_cache = qcow2_cache_create(bs, L2_CACHE_SIZE);
+ s->refcount_block_cache = qcow2_cache_create(bs, REFCOUNT_CACHE_SIZE);
+
+ s->cluster_cache = g_malloc(s->cluster_size);
+ /* one more sector for decompressed data alignment */
+ s->cluster_data = qemu_blockalign(bs, QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size
+ + 512);
+ s->cluster_cache_offset = -1;
+ s->flags = flags;
+
+ ret = qcow2_refcount_init(bs);
+ if (ret != 0) {
+ goto fail;
+ }
+
+ QLIST_INIT(&s->cluster_allocs);
+ QTAILQ_INIT(&s->discards);
+
+ /* read qcow2 extensions */
+ if (qcow2_read_extensions(bs, header.header_length, ext_end, NULL)) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ /* read the backing file name */
+ if (header.backing_file_offset != 0) {
+ len = header.backing_file_size;
+ if (len > 1023) {
+ len = 1023;
+ }
+ ret = bdrv_pread(bs->file, header.backing_file_offset,
+ bs->backing_file, len);
+ if (ret < 0) {
+ goto fail;
+ }
+ bs->backing_file[len] = '\0';
+ }
+
+ ret = qcow2_read_snapshots(bs);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Clear unknown autoclear feature bits */
+ if (!bs->read_only && s->autoclear_features != 0) {
+ s->autoclear_features = 0;
+ ret = qcow2_update_header(bs);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ /* Initialise locks */
+ qemu_co_mutex_init(&s->lock);
+
+ /* Repair image if dirty */
+ if (!(flags & BDRV_O_CHECK) && !bs->read_only &&
+ (s->incompatible_features & QCOW2_INCOMPAT_DIRTY)) {
+ BdrvCheckResult result = {0};
+
+ ret = qcow2_check(bs, &result, BDRV_FIX_ERRORS);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ /* Enable lazy_refcounts according to image and command line options */
+ opts = qemu_opts_create_nofail(&qcow2_runtime_opts);
+ qemu_opts_absorb_qdict(opts, options, &local_err);
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ s->use_lazy_refcounts = qemu_opt_get_bool(opts, QCOW2_OPT_LAZY_REFCOUNTS,
+ (s->compatible_features & QCOW2_COMPAT_LAZY_REFCOUNTS));
+
+ s->discard_passthrough[QCOW2_DISCARD_NEVER] = false;
+ s->discard_passthrough[QCOW2_DISCARD_ALWAYS] = true;
+ s->discard_passthrough[QCOW2_DISCARD_REQUEST] =
+ qemu_opt_get_bool(opts, QCOW2_OPT_DISCARD_REQUEST,
+ flags & BDRV_O_UNMAP);
+ s->discard_passthrough[QCOW2_DISCARD_SNAPSHOT] =
+ qemu_opt_get_bool(opts, QCOW2_OPT_DISCARD_SNAPSHOT, true);
+ s->discard_passthrough[QCOW2_DISCARD_OTHER] =
+ qemu_opt_get_bool(opts, QCOW2_OPT_DISCARD_OTHER, false);
+
+ qemu_opts_del(opts);
+
+ if (s->use_lazy_refcounts && s->qcow_version < 3) {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Lazy refcounts require "
+ "a qcow2 image with at least qemu 1.1 compatibility level");
+ ret = -EINVAL;
+ goto fail;
+ }
+
+#ifdef DEBUG_ALLOC
+ {
+ BdrvCheckResult result = {0};
+ qcow2_check_refcounts(bs, &result, 0);
+ }
+#endif
+ return ret;
+
+ fail:
+ g_free(s->unknown_header_fields);
+ cleanup_unknown_header_ext(bs);
+ qcow2_free_snapshots(bs);
+ qcow2_refcount_close(bs);
+ g_free(s->l1_table);
+ if (s->l2_table_cache) {
+ qcow2_cache_destroy(bs, s->l2_table_cache);
+ }
+ g_free(s->cluster_cache);
+ qemu_vfree(s->cluster_data);
+ return ret;
+}
+
+static int qcow2_set_key(BlockDriverState *bs, const char *key)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint8_t keybuf[16];
+ int len, i;
+
+ memset(keybuf, 0, 16);
+ len = strlen(key);
+ if (len > 16)
+ len = 16;
+ /* XXX: we could compress the chars to 7 bits to increase
+ entropy */
+ for(i = 0;i < len;i++) {
+ keybuf[i] = key[i];
+ }
+ s->crypt_method = s->crypt_method_header;
+
+ if (AES_set_encrypt_key(keybuf, 128, &s->aes_encrypt_key) != 0)
+ return -1;
+ if (AES_set_decrypt_key(keybuf, 128, &s->aes_decrypt_key) != 0)
+ return -1;
+#if 0
+ /* test */
+ {
+ uint8_t in[16];
+ uint8_t out[16];
+ uint8_t tmp[16];
+ for(i=0;i<16;i++)
+ in[i] = i;
+ AES_encrypt(in, tmp, &s->aes_encrypt_key);
+ AES_decrypt(tmp, out, &s->aes_decrypt_key);
+ for(i = 0; i < 16; i++)
+ printf(" %02x", tmp[i]);
+ printf("\n");
+ for(i = 0; i < 16; i++)
+ printf(" %02x", out[i]);
+ printf("\n");
+ }
+#endif
+ return 0;
+}
+
+/* We have nothing to do for QCOW2 reopen, stubs just return
+ * success */
+static int qcow2_reopen_prepare(BDRVReopenState *state,
+ BlockReopenQueue *queue, Error **errp)
+{
+ return 0;
+}
+
+static int coroutine_fn qcow2_co_is_allocated(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, int *pnum)
+{
+ BDRVQcowState *s = bs->opaque;
+ uint64_t cluster_offset;
+ int ret;
+
+ *pnum = nb_sectors;
+ /* FIXME We can get errors here, but the bdrv_co_is_allocated interface
+ * can't pass them on today */
+ qemu_co_mutex_lock(&s->lock);
+ ret = qcow2_get_cluster_offset(bs, sector_num << 9, pnum, &cluster_offset);
+ qemu_co_mutex_unlock(&s->lock);
+ if (ret < 0) {
+ *pnum = 0;
+ }
+
+ return (cluster_offset != 0) || (ret == QCOW2_CLUSTER_ZERO);
+}
+
+/* handle reading after the end of the backing file */
+int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
+ int64_t sector_num, int nb_sectors)
+{
+ int n1;
+ if ((sector_num + nb_sectors) <= bs->total_sectors)
+ return nb_sectors;
+ if (sector_num >= bs->total_sectors)
+ n1 = 0;
+ else
+ n1 = bs->total_sectors - sector_num;
+
+ qemu_iovec_memset(qiov, 512 * n1, 0, 512 * (nb_sectors - n1));
+
+ return n1;
+}
+
+static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
+ int remaining_sectors, QEMUIOVector *qiov)
+{
+ BDRVQcowState *s = bs->opaque;
+ int index_in_cluster, n1;
+ int ret;
+ int cur_nr_sectors; /* number of sectors in current iteration */
+ uint64_t cluster_offset = 0;
+ uint64_t bytes_done = 0;
+ QEMUIOVector hd_qiov;
+ uint8_t *cluster_data = NULL;
+
+ qemu_iovec_init(&hd_qiov, qiov->niov);
+
+ qemu_co_mutex_lock(&s->lock);
+
+ while (remaining_sectors != 0) {
+
+ /* prepare next request */
+ cur_nr_sectors = remaining_sectors;
+ if (s->crypt_method) {
+ cur_nr_sectors = MIN(cur_nr_sectors,
+ QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors);
+ }
+
+ ret = qcow2_get_cluster_offset(bs, sector_num << 9,
+ &cur_nr_sectors, &cluster_offset);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ index_in_cluster = sector_num & (s->cluster_sectors - 1);
+
+ qemu_iovec_reset(&hd_qiov);
+ qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
+ cur_nr_sectors * 512);
+
+ switch (ret) {
+ case QCOW2_CLUSTER_UNALLOCATED:
+
+ if (bs->backing_hd) {
+ /* read from the base image */
+ n1 = qcow2_backing_read1(bs->backing_hd, &hd_qiov,
+ sector_num, cur_nr_sectors);
+ if (n1 > 0) {
+ BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_readv(bs->backing_hd, sector_num,
+ n1, &hd_qiov);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+ } else {
+ /* Note: in this case, no need to wait */
+ qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+ }
+ break;
+
+ case QCOW2_CLUSTER_ZERO:
+ qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+ break;
+
+ case QCOW2_CLUSTER_COMPRESSED:
+ /* add AIO support for compressed blocks ? */
+ ret = qcow2_decompress_cluster(bs, cluster_offset);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ qemu_iovec_from_buf(&hd_qiov, 0,
+ s->cluster_cache + index_in_cluster * 512,
+ 512 * cur_nr_sectors);
+ break;
+
+ case QCOW2_CLUSTER_NORMAL:
+ if ((cluster_offset & 511) != 0) {
+ ret = -EIO;
+ goto fail;
+ }
+
+ if (s->crypt_method) {
+ /*
+ * For encrypted images, read everything into a temporary
+ * contiguous buffer on which the AES functions can work.
+ */
+ if (!cluster_data) {
+ cluster_data =
+ qemu_blockalign(bs, QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
+ }
+
+ assert(cur_nr_sectors <=
+ QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors);
+ qemu_iovec_reset(&hd_qiov);
+ qemu_iovec_add(&hd_qiov, cluster_data,
+ 512 * cur_nr_sectors);
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_readv(bs->file,
+ (cluster_offset >> 9) + index_in_cluster,
+ cur_nr_sectors, &hd_qiov);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ goto fail;
+ }
+ if (s->crypt_method) {
+ qcow2_encrypt_sectors(s, sector_num, cluster_data,
+ cluster_data, cur_nr_sectors, 0, &s->aes_decrypt_key);
+ qemu_iovec_from_buf(qiov, bytes_done,
+ cluster_data, 512 * cur_nr_sectors);
+ }
+ break;
+
+ default:
+ g_assert_not_reached();
+ ret = -EIO;
+ goto fail;
+ }
+
+ remaining_sectors -= cur_nr_sectors;
+ sector_num += cur_nr_sectors;
+ bytes_done += cur_nr_sectors * 512;
+ }
+ ret = 0;
+
+fail:
+ qemu_co_mutex_unlock(&s->lock);
+
+ qemu_iovec_destroy(&hd_qiov);
+ qemu_vfree(cluster_data);
+
+ return ret;
+}
+
+static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
+ int64_t sector_num,
+ int remaining_sectors,
+ QEMUIOVector *qiov)
+{
+ BDRVQcowState *s = bs->opaque;
+ int index_in_cluster;
+ int n_end;
+ int ret;
+ int cur_nr_sectors; /* number of sectors in current iteration */
+ uint64_t cluster_offset;
+ QEMUIOVector hd_qiov;
+ uint64_t bytes_done = 0;
+ uint8_t *cluster_data = NULL;
+ QCowL2Meta *l2meta = NULL;
+
+ trace_qcow2_writev_start_req(qemu_coroutine_self(), sector_num,
+ remaining_sectors);
+
+ qemu_iovec_init(&hd_qiov, qiov->niov);
+
+ s->cluster_cache_offset = -1; /* disable compressed cache */
+
+ qemu_co_mutex_lock(&s->lock);
+
+ while (remaining_sectors != 0) {
+
+ l2meta = NULL;
+
+ trace_qcow2_writev_start_part(qemu_coroutine_self());
+ index_in_cluster = sector_num & (s->cluster_sectors - 1);
+ n_end = index_in_cluster + remaining_sectors;
+ if (s->crypt_method &&
+ n_end > QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors) {
+ n_end = QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors;
+ }
+
+ ret = qcow2_alloc_cluster_offset(bs, sector_num << 9,
+ index_in_cluster, n_end, &cur_nr_sectors, &cluster_offset, &l2meta);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ assert((cluster_offset & 511) == 0);
+
+ qemu_iovec_reset(&hd_qiov);
+ qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
+ cur_nr_sectors * 512);
+
+ if (s->crypt_method) {
+ if (!cluster_data) {
+ cluster_data = qemu_blockalign(bs, QCOW_MAX_CRYPT_CLUSTERS *
+ s->cluster_size);
+ }
+
+ assert(hd_qiov.size <=
+ QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
+ qemu_iovec_to_buf(&hd_qiov, 0, cluster_data, hd_qiov.size);
+
+ qcow2_encrypt_sectors(s, sector_num, cluster_data,
+ cluster_data, cur_nr_sectors, 1, &s->aes_encrypt_key);
+
+ qemu_iovec_reset(&hd_qiov);
+ qemu_iovec_add(&hd_qiov, cluster_data,
+ cur_nr_sectors * 512);
+ }
+
+ qemu_co_mutex_unlock(&s->lock);
+ BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
+ trace_qcow2_writev_data(qemu_coroutine_self(),
+ (cluster_offset >> 9) + index_in_cluster);
+ ret = bdrv_co_writev(bs->file,
+ (cluster_offset >> 9) + index_in_cluster,
+ cur_nr_sectors, &hd_qiov);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ while (l2meta != NULL) {
+ QCowL2Meta *next;
+
+ ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Take the request off the list of running requests */
+ if (l2meta->nb_clusters != 0) {
+ QLIST_REMOVE(l2meta, next_in_flight);
+ }
+
+ qemu_co_queue_restart_all(&l2meta->dependent_requests);
+
+ next = l2meta->next;
+ g_free(l2meta);
+ l2meta = next;
+ }
+
+ remaining_sectors -= cur_nr_sectors;
+ sector_num += cur_nr_sectors;
+ bytes_done += cur_nr_sectors * 512;
+ trace_qcow2_writev_done_part(qemu_coroutine_self(), cur_nr_sectors);
+ }
+ ret = 0;
+
+fail:
+ qemu_co_mutex_unlock(&s->lock);
+
+ while (l2meta != NULL) {
+ QCowL2Meta *next;
+
+ if (l2meta->nb_clusters != 0) {
+ QLIST_REMOVE(l2meta, next_in_flight);
+ }
+ qemu_co_queue_restart_all(&l2meta->dependent_requests);
+
+ next = l2meta->next;
+ g_free(l2meta);
+ l2meta = next;
+ }
+
+ qemu_iovec_destroy(&hd_qiov);
+ qemu_vfree(cluster_data);
+ trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
+
+ return ret;
+}
+
+static void qcow2_close(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ g_free(s->l1_table);
+
+ qcow2_cache_flush(bs, s->l2_table_cache);
+ qcow2_cache_flush(bs, s->refcount_block_cache);
+
+ qcow2_mark_clean(bs);
+
+ qcow2_cache_destroy(bs, s->l2_table_cache);
+ qcow2_cache_destroy(bs, s->refcount_block_cache);
+
+ g_free(s->unknown_header_fields);
+ cleanup_unknown_header_ext(bs);
+
+ g_free(s->cluster_cache);
+ qemu_vfree(s->cluster_data);
+ qcow2_refcount_close(bs);
+ qcow2_free_snapshots(bs);
+}
+
+static void qcow2_invalidate_cache(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ int flags = s->flags;
+ AES_KEY aes_encrypt_key;
+ AES_KEY aes_decrypt_key;
+ uint32_t crypt_method = 0;
+ QDict *options;
+
+ /*
+ * Backing files are read-only which makes all of their metadata immutable,
+ * that means we don't have to worry about reopening them here.
+ */
+
+ if (s->crypt_method) {
+ crypt_method = s->crypt_method;
+ memcpy(&aes_encrypt_key, &s->aes_encrypt_key, sizeof(aes_encrypt_key));
+ memcpy(&aes_decrypt_key, &s->aes_decrypt_key, sizeof(aes_decrypt_key));
+ }
+
+ qcow2_close(bs);
+
+ options = qdict_new();
+ qdict_put(options, QCOW2_OPT_LAZY_REFCOUNTS,
+ qbool_from_int(s->use_lazy_refcounts));
+
+ memset(s, 0, sizeof(BDRVQcowState));
+ qcow2_open(bs, options, flags);
+
+ QDECREF(options);
+
+ if (crypt_method) {
+ s->crypt_method = crypt_method;
+ memcpy(&s->aes_encrypt_key, &aes_encrypt_key, sizeof(aes_encrypt_key));
+ memcpy(&s->aes_decrypt_key, &aes_decrypt_key, sizeof(aes_decrypt_key));
+ }
+}
+
+static size_t header_ext_add(char *buf, uint32_t magic, const void *s,
+ size_t len, size_t buflen)
+{
+ QCowExtension *ext_backing_fmt = (QCowExtension*) buf;
+ size_t ext_len = sizeof(QCowExtension) + ((len + 7) & ~7);
+
+ if (buflen < ext_len) {
+ return -ENOSPC;
+ }
+
+ *ext_backing_fmt = (QCowExtension) {
+ .magic = cpu_to_be32(magic),
+ .len = cpu_to_be32(len),
+ };
+ memcpy(buf + sizeof(QCowExtension), s, len);
+
+ return ext_len;
+}
+
+/*
+ * Updates the qcow2 header, including the variable length parts of it, i.e.
+ * the backing file name and all extensions. qcow2 was not designed to allow
+ * such changes, so if we run out of space (we can only use the first cluster)
+ * this function may fail.
+ *
+ * Returns 0 on success, -errno in error cases.
+ */
+int qcow2_update_header(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ QCowHeader *header;
+ char *buf;
+ size_t buflen = s->cluster_size;
+ int ret;
+ uint64_t total_size;
+ uint32_t refcount_table_clusters;
+ size_t header_length;
+ Qcow2UnknownHeaderExtension *uext;
+
+ buf = qemu_blockalign(bs, buflen);
+
+ /* Header structure */
+ header = (QCowHeader*) buf;
+
+ if (buflen < sizeof(*header)) {
+ ret = -ENOSPC;
+ goto fail;
+ }
+
+ header_length = sizeof(*header) + s->unknown_header_fields_size;
+ total_size = bs->total_sectors * BDRV_SECTOR_SIZE;
+ refcount_table_clusters = s->refcount_table_size >> (s->cluster_bits - 3);
+
+ *header = (QCowHeader) {
+ /* Version 2 fields */
+ .magic = cpu_to_be32(QCOW_MAGIC),
+ .version = cpu_to_be32(s->qcow_version),
+ .backing_file_offset = 0,
+ .backing_file_size = 0,
+ .cluster_bits = cpu_to_be32(s->cluster_bits),
+ .size = cpu_to_be64(total_size),
+ .crypt_method = cpu_to_be32(s->crypt_method_header),
+ .l1_size = cpu_to_be32(s->l1_size),
+ .l1_table_offset = cpu_to_be64(s->l1_table_offset),
+ .refcount_table_offset = cpu_to_be64(s->refcount_table_offset),
+ .refcount_table_clusters = cpu_to_be32(refcount_table_clusters),
+ .nb_snapshots = cpu_to_be32(s->nb_snapshots),
+ .snapshots_offset = cpu_to_be64(s->snapshots_offset),
+
+ /* Version 3 fields */
+ .incompatible_features = cpu_to_be64(s->incompatible_features),
+ .compatible_features = cpu_to_be64(s->compatible_features),
+ .autoclear_features = cpu_to_be64(s->autoclear_features),
+ .refcount_order = cpu_to_be32(3 + REFCOUNT_SHIFT),
+ .header_length = cpu_to_be32(header_length),
+ };
+
+ /* For older versions, write a shorter header */
+ switch (s->qcow_version) {
+ case 2:
+ ret = offsetof(QCowHeader, incompatible_features);
+ break;
+ case 3:
+ ret = sizeof(*header);
+ break;
+ default:
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ buf += ret;
+ buflen -= ret;
+ memset(buf, 0, buflen);
+
+ /* Preserve any unknown field in the header */
+ if (s->unknown_header_fields_size) {
+ if (buflen < s->unknown_header_fields_size) {
+ ret = -ENOSPC;
+ goto fail;
+ }
+
+ memcpy(buf, s->unknown_header_fields, s->unknown_header_fields_size);
+ buf += s->unknown_header_fields_size;
+ buflen -= s->unknown_header_fields_size;
+ }
+
+ /* Backing file format header extension */
+ if (*bs->backing_format) {
+ ret = header_ext_add(buf, QCOW2_EXT_MAGIC_BACKING_FORMAT,
+ bs->backing_format, strlen(bs->backing_format),
+ buflen);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ buf += ret;
+ buflen -= ret;
+ }
+
+ /* Feature table */
+ Qcow2Feature features[] = {
+ {
+ .type = QCOW2_FEAT_TYPE_INCOMPATIBLE,
+ .bit = QCOW2_INCOMPAT_DIRTY_BITNR,
+ .name = "dirty bit",
+ },
+ {
+ .type = QCOW2_FEAT_TYPE_COMPATIBLE,
+ .bit = QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
+ .name = "lazy refcounts",
+ },
+ };
+
+ ret = header_ext_add(buf, QCOW2_EXT_MAGIC_FEATURE_TABLE,
+ features, sizeof(features), buflen);
+ if (ret < 0) {
+ goto fail;
+ }
+ buf += ret;
+ buflen -= ret;
+
+ /* Keep unknown header extensions */
+ QLIST_FOREACH(uext, &s->unknown_header_ext, next) {
+ ret = header_ext_add(buf, uext->magic, uext->data, uext->len, buflen);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ buf += ret;
+ buflen -= ret;
+ }
+
+ /* End of header extensions */
+ ret = header_ext_add(buf, QCOW2_EXT_MAGIC_END, NULL, 0, buflen);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ buf += ret;
+ buflen -= ret;
+
+ /* Backing file name */
+ if (*bs->backing_file) {
+ size_t backing_file_len = strlen(bs->backing_file);
+
+ if (buflen < backing_file_len) {
+ ret = -ENOSPC;
+ goto fail;
+ }
+
+ /* Using strncpy is ok here, since buf is not NUL-terminated. */
+ strncpy(buf, bs->backing_file, buflen);
+
+ header->backing_file_offset = cpu_to_be64(buf - ((char*) header));
+ header->backing_file_size = cpu_to_be32(backing_file_len);
+ }
+
+ /* Write the new header */
+ ret = bdrv_pwrite(bs->file, 0, header, s->cluster_size);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ ret = 0;
+fail:
+ qemu_vfree(header);
+ return ret;
+}
+
+static int qcow2_change_backing_file(BlockDriverState *bs,
+ const char *backing_file, const char *backing_fmt)
+{
+ pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
+ pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
+
+ return qcow2_update_header(bs);
+}
+
+static int preallocate(BlockDriverState *bs)
+{
+ uint64_t nb_sectors;
+ uint64_t offset;
+ uint64_t host_offset = 0;
+ int num;
+ int ret;
+ QCowL2Meta *meta;
+
+ nb_sectors = bdrv_getlength(bs) >> 9;
+ offset = 0;
+
+ while (nb_sectors) {
+ num = MIN(nb_sectors, INT_MAX >> 9);
+ ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num,
+ &host_offset, &meta);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = qcow2_alloc_cluster_link_l2(bs, meta);
+ if (ret < 0) {
+ qcow2_free_any_clusters(bs, meta->alloc_offset, meta->nb_clusters,
+ QCOW2_DISCARD_NEVER);
+ return ret;
+ }
+
+ /* There are no dependent requests, but we need to remove our request
+ * from the list of in-flight requests */
+ if (meta != NULL) {
+ QLIST_REMOVE(meta, next_in_flight);
+ }
+
+ /* TODO Preallocate data if requested */
+
+ nb_sectors -= num;
+ offset += num << 9;
+ }
+
+ /*
+ * It is expected that the image file is large enough to actually contain
+ * all of the allocated clusters (otherwise we get failing reads after
+ * EOF). Extend the image to the last allocated sector.
+ */
+ if (host_offset != 0) {
+ uint8_t buf[512];
+ memset(buf, 0, 512);
+ ret = bdrv_write(bs->file, (host_offset >> 9) + num - 1, buf, 1);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int qcow2_create2(const char *filename, int64_t total_size,
+ const char *backing_file, const char *backing_format,
+ int flags, size_t cluster_size, int prealloc,
+ QEMUOptionParameter *options, int version)
+{
+ /* Calculate cluster_bits */
+ int cluster_bits;
+ cluster_bits = ffs(cluster_size) - 1;
+ if (cluster_bits < MIN_CLUSTER_BITS || cluster_bits > MAX_CLUSTER_BITS ||
+ (1 << cluster_bits) != cluster_size)
+ {
+ error_report(
+ "Cluster size must be a power of two between %d and %dk",
+ 1 << MIN_CLUSTER_BITS, 1 << (MAX_CLUSTER_BITS - 10));
+ return -EINVAL;
+ }
+
+ /*
+ * Open the image file and write a minimal qcow2 header.
+ *
+ * We keep things simple and start with a zero-sized image. We also
+ * do without refcount blocks or a L1 table for now. We'll fix the
+ * inconsistency later.
+ *
+ * We do need a refcount table because growing the refcount table means
+ * allocating two new refcount blocks - the seconds of which would be at
+ * 2 GB for 64k clusters, and we don't want to have a 2 GB initial file
+ * size for any qcow2 image.
+ */
+ BlockDriverState* bs;
+ QCowHeader header;
+ uint8_t* refcount_table;
+ int ret;
+
+ ret = bdrv_create_file(filename, options);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Write the header */
+ memset(&header, 0, sizeof(header));
+ header.magic = cpu_to_be32(QCOW_MAGIC);
+ header.version = cpu_to_be32(version);
+ header.cluster_bits = cpu_to_be32(cluster_bits);
+ header.size = cpu_to_be64(0);
+ header.l1_table_offset = cpu_to_be64(0);
+ header.l1_size = cpu_to_be32(0);
+ header.refcount_table_offset = cpu_to_be64(cluster_size);
+ header.refcount_table_clusters = cpu_to_be32(1);
+ header.refcount_order = cpu_to_be32(3 + REFCOUNT_SHIFT);
+ header.header_length = cpu_to_be32(sizeof(header));
+
+ if (flags & BLOCK_FLAG_ENCRYPT) {
+ header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
+ } else {
+ header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
+ }
+
+ if (flags & BLOCK_FLAG_LAZY_REFCOUNTS) {
+ header.compatible_features |=
+ cpu_to_be64(QCOW2_COMPAT_LAZY_REFCOUNTS);
+ }
+
+ ret = bdrv_pwrite(bs, 0, &header, sizeof(header));
+ if (ret < 0) {
+ goto out;
+ }
+
+ /* Write an empty refcount table */
+ refcount_table = g_malloc0(cluster_size);
+ ret = bdrv_pwrite(bs, cluster_size, refcount_table, cluster_size);
+ g_free(refcount_table);
+
+ if (ret < 0) {
+ goto out;
+ }
+
+ bdrv_close(bs);
+
+ /*
+ * And now open the image and make it consistent first (i.e. increase the
+ * refcount of the cluster that is occupied by the header and the refcount
+ * table)
+ */
+ BlockDriver* drv = bdrv_find_format("qcow2");
+ assert(drv != NULL);
+ ret = bdrv_open(bs, filename, NULL,
+ BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, drv);
+ if (ret < 0) {
+ goto out;
+ }
+
+ ret = qcow2_alloc_clusters(bs, 2 * cluster_size);
+ if (ret < 0) {
+ goto out;
+
+ } else if (ret != 0) {
+ error_report("Huh, first cluster in empty image is already in use?");
+ abort();
+ }
+
+ /* Okay, now that we have a valid image, let's give it the right size */
+ ret = bdrv_truncate(bs, total_size * BDRV_SECTOR_SIZE);
+ if (ret < 0) {
+ goto out;
+ }
+
+ /* Want a backing file? There you go.*/
+ if (backing_file) {
+ ret = bdrv_change_backing_file(bs, backing_file, backing_format);
+ if (ret < 0) {
+ goto out;
+ }
+ }
+
+ /* And if we're supposed to preallocate metadata, do that now */
+ if (prealloc) {
+ BDRVQcowState *s = bs->opaque;
+ qemu_co_mutex_lock(&s->lock);
+ ret = preallocate(bs);
+ qemu_co_mutex_unlock(&s->lock);
+ if (ret < 0) {
+ goto out;
+ }
+ }
+
+ ret = 0;
+out:
+ bdrv_delete(bs);
+ return ret;
+}
+
+static int qcow2_create(const char *filename, QEMUOptionParameter *options)
+{
+ const char *backing_file = NULL;
+ const char *backing_fmt = NULL;
+ uint64_t sectors = 0;
+ int flags = 0;
+ size_t cluster_size = DEFAULT_CLUSTER_SIZE;
+ int prealloc = 0;
+ int version = 2;
+
+ /* Read out options */
+ while (options && options->name) {
+ if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+ sectors = options->value.n / 512;
+ } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+ backing_file = options->value.s;
+ } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) {
+ backing_fmt = options->value.s;
+ } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
+ flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
+ } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
+ if (options->value.n) {
+ cluster_size = options->value.n;
+ }
+ } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
+ if (!options->value.s || !strcmp(options->value.s, "off")) {
+ prealloc = 0;
+ } else if (!strcmp(options->value.s, "metadata")) {
+ prealloc = 1;
+ } else {
+ fprintf(stderr, "Invalid preallocation mode: '%s'\n",
+ options->value.s);
+ return -EINVAL;
+ }
+ } else if (!strcmp(options->name, BLOCK_OPT_COMPAT_LEVEL)) {
+ if (!options->value.s || !strcmp(options->value.s, "0.10")) {
+ version = 2;
+ } else if (!strcmp(options->value.s, "1.1")) {
+ version = 3;
+ } else {
+ fprintf(stderr, "Invalid compatibility level: '%s'\n",
+ options->value.s);
+ return -EINVAL;
+ }
+ } else if (!strcmp(options->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
+ flags |= options->value.n ? BLOCK_FLAG_LAZY_REFCOUNTS : 0;
+ }
+ options++;
+ }
+
+ if (backing_file && prealloc) {
+ fprintf(stderr, "Backing file and preallocation cannot be used at "
+ "the same time\n");
+ return -EINVAL;
+ }
+
+ if (version < 3 && (flags & BLOCK_FLAG_LAZY_REFCOUNTS)) {
+ fprintf(stderr, "Lazy refcounts only supported with compatibility "
+ "level 1.1 and above (use compat=1.1 or greater)\n");
+ return -EINVAL;
+ }
+
+ return qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
+ cluster_size, prealloc, options, version);
+}
+
+static int qcow2_make_empty(BlockDriverState *bs)
+{
+#if 0
+ /* XXX: not correct */
+ BDRVQcowState *s = bs->opaque;
+ uint32_t l1_length = s->l1_size * sizeof(uint64_t);
+ int ret;
+
+ memset(s->l1_table, 0, l1_length);
+ if (bdrv_pwrite(bs->file, s->l1_table_offset, s->l1_table, l1_length) < 0)
+ return -1;
+ ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
+ if (ret < 0)
+ return ret;
+
+ l2_cache_reset(bs);
+#endif
+ return 0;
+}
+
+static coroutine_fn int qcow2_co_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors)
+{
+ int ret;
+ BDRVQcowState *s = bs->opaque;
+
+ /* Emulate misaligned zero writes */
+ if (sector_num % s->cluster_sectors || nb_sectors % s->cluster_sectors) {
+ return -ENOTSUP;
+ }
+
+ /* Whatever is left can use real zero clusters */
+ qemu_co_mutex_lock(&s->lock);
+ ret = qcow2_zero_clusters(bs, sector_num << BDRV_SECTOR_BITS,
+ nb_sectors);
+ qemu_co_mutex_unlock(&s->lock);
+
+ return ret;
+}
+
+static coroutine_fn int qcow2_co_discard(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors)
+{
+ int ret;
+ BDRVQcowState *s = bs->opaque;
+
+ qemu_co_mutex_lock(&s->lock);
+ ret = qcow2_discard_clusters(bs, sector_num << BDRV_SECTOR_BITS,
+ nb_sectors);
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
+}
+
+static int qcow2_truncate(BlockDriverState *bs, int64_t offset)
+{
+ BDRVQcowState *s = bs->opaque;
+ int64_t new_l1_size;
+ int ret;
+
+ if (offset & 511) {
+ error_report("The new size must be a multiple of 512");
+ return -EINVAL;
+ }
+
+ /* cannot proceed if image has snapshots */
+ if (s->nb_snapshots) {
+ error_report("Can't resize an image which has snapshots");
+ return -ENOTSUP;
+ }
+
+ /* shrinking is currently not supported */
+ if (offset < bs->total_sectors * 512) {
+ error_report("qcow2 doesn't support shrinking images yet");
+ return -ENOTSUP;
+ }
+
+ new_l1_size = size_to_l1(s, offset);
+ ret = qcow2_grow_l1_table(bs, new_l1_size, true);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* write updated header.size */
+ offset = cpu_to_be64(offset);
+ ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, size),
+ &offset, sizeof(uint64_t));
+ if (ret < 0) {
+ return ret;
+ }
+
+ s->l1_vm_state_index = new_l1_size;
+ return 0;
+}
+
+/* XXX: put compressed sectors first, then all the cluster aligned
+ tables to avoid losing bytes in alignment */
+static int qcow2_write_compressed(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors)
+{
+ BDRVQcowState *s = bs->opaque;
+ z_stream strm;
+ int ret, out_len;
+ uint8_t *out_buf;
+ uint64_t cluster_offset;
+
+ if (nb_sectors == 0) {
+ /* align end of file to a sector boundary to ease reading with
+ sector based I/Os */
+ cluster_offset = bdrv_getlength(bs->file);
+ cluster_offset = (cluster_offset + 511) & ~511;
+ bdrv_truncate(bs->file, cluster_offset);
+ return 0;
+ }
+
+ if (nb_sectors != s->cluster_sectors) {
+ ret = -EINVAL;
+
+ /* Zero-pad last write if image size is not cluster aligned */
+ if (sector_num + nb_sectors == bs->total_sectors &&
+ nb_sectors < s->cluster_sectors) {
+ uint8_t *pad_buf = qemu_blockalign(bs, s->cluster_size);
+ memset(pad_buf, 0, s->cluster_size);
+ memcpy(pad_buf, buf, nb_sectors * BDRV_SECTOR_SIZE);
+ ret = qcow2_write_compressed(bs, sector_num,
+ pad_buf, s->cluster_sectors);
+ qemu_vfree(pad_buf);
+ }
+ return ret;
+ }
+
+ out_buf = g_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
+
+ /* best compression, small window, no zlib header */
+ memset(&strm, 0, sizeof(strm));
+ ret = deflateInit2(&strm, Z_DEFAULT_COMPRESSION,
+ Z_DEFLATED, -12,
+ 9, Z_DEFAULT_STRATEGY);
+ if (ret != 0) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ strm.avail_in = s->cluster_size;
+ strm.next_in = (uint8_t *)buf;
+ strm.avail_out = s->cluster_size;
+ strm.next_out = out_buf;
+
+ ret = deflate(&strm, Z_FINISH);
+ if (ret != Z_STREAM_END && ret != Z_OK) {
+ deflateEnd(&strm);
+ ret = -EINVAL;
+ goto fail;
+ }
+ out_len = strm.next_out - out_buf;
+
+ deflateEnd(&strm);
+
+ if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
+ /* could not compress: write normal cluster */
+ ret = bdrv_write(bs, sector_num, buf, s->cluster_sectors);
+ if (ret < 0) {
+ goto fail;
+ }
+ } else {
+ cluster_offset = qcow2_alloc_compressed_cluster_offset(bs,
+ sector_num << 9, out_len);
+ if (!cluster_offset) {
+ ret = -EIO;
+ goto fail;
+ }
+ cluster_offset &= s->cluster_offset_mask;
+ BLKDBG_EVENT(bs->file, BLKDBG_WRITE_COMPRESSED);
+ ret = bdrv_pwrite(bs->file, cluster_offset, out_buf, out_len);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ ret = 0;
+fail:
+ g_free(out_buf);
+ return ret;
+}
+
+static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ int ret;
+
+ qemu_co_mutex_lock(&s->lock);
+ ret = qcow2_cache_flush(bs, s->l2_table_cache);
+ if (ret < 0) {
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
+ }
+
+ if (qcow2_need_accurate_refcounts(s)) {
+ ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+ if (ret < 0) {
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
+ }
+ }
+ qemu_co_mutex_unlock(&s->lock);
+
+ return 0;
+}
+
+static int64_t qcow2_vm_state_offset(BDRVQcowState *s)
+{
+ return (int64_t)s->l1_vm_state_index << (s->cluster_bits + s->l2_bits);
+}
+
+static int qcow2_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
+{
+ BDRVQcowState *s = bs->opaque;
+ bdi->cluster_size = s->cluster_size;
+ bdi->vm_state_offset = qcow2_vm_state_offset(s);
+ return 0;
+}
+
+#if 0
+static void dump_refcounts(BlockDriverState *bs)
+{
+ BDRVQcowState *s = bs->opaque;
+ int64_t nb_clusters, k, k1, size;
+ int refcount;
+
+ size = bdrv_getlength(bs->file);
+ nb_clusters = size_to_clusters(s, size);
+ for(k = 0; k < nb_clusters;) {
+ k1 = k;
+ refcount = get_refcount(bs, k);
+ k++;
+ while (k < nb_clusters && get_refcount(bs, k) == refcount)
+ k++;
+ printf("%" PRId64 ": refcount=%d nb=%" PRId64 "\n", k, refcount,
+ k - k1);
+ }
+}
+#endif
+
+static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
+ int64_t pos)
+{
+ BDRVQcowState *s = bs->opaque;
+ int growable = bs->growable;
+ int ret;
+
+ BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_SAVE);
+ bs->growable = 1;
+ ret = bdrv_pwritev(bs, qcow2_vm_state_offset(s) + pos, qiov);
+ bs->growable = growable;
+
+ return ret;
+}
+
+static int qcow2_load_vmstate(BlockDriverState *bs, uint8_t *buf,
+ int64_t pos, int size)
+{
+ BDRVQcowState *s = bs->opaque;
+ int growable = bs->growable;
+ int ret;
+
+ BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_LOAD);
+ bs->growable = 1;
+ ret = bdrv_pread(bs, qcow2_vm_state_offset(s) + pos, buf, size);
+ bs->growable = growable;
+
+ return ret;
+}
+
+static QEMUOptionParameter qcow2_create_options[] = {
+ {
+ .name = BLOCK_OPT_SIZE,
+ .type = OPT_SIZE,
+ .help = "Virtual disk size"
+ },
+ {
+ .name = BLOCK_OPT_COMPAT_LEVEL,
+ .type = OPT_STRING,
+ .help = "Compatibility level (0.10 or 1.1)"
+ },
+ {
+ .name = BLOCK_OPT_BACKING_FILE,
+ .type = OPT_STRING,
+ .help = "File name of a base image"
+ },
+ {
+ .name = BLOCK_OPT_BACKING_FMT,
+ .type = OPT_STRING,
+ .help = "Image format of the base image"
+ },
+ {
+ .name = BLOCK_OPT_ENCRYPT,
+ .type = OPT_FLAG,
+ .help = "Encrypt the image"
+ },
+ {
+ .name = BLOCK_OPT_CLUSTER_SIZE,
+ .type = OPT_SIZE,
+ .help = "qcow2 cluster size",
+ .value = { .n = DEFAULT_CLUSTER_SIZE },
+ },
+ {
+ .name = BLOCK_OPT_PREALLOC,
+ .type = OPT_STRING,
+ .help = "Preallocation mode (allowed values: off, metadata)"
+ },
+ {
+ .name = BLOCK_OPT_LAZY_REFCOUNTS,
+ .type = OPT_FLAG,
+ .help = "Postpone refcount updates",
+ },
+ { NULL }
+};
+
+static BlockDriver bdrv_qcow2 = {
+ .format_name = "qcow2",
+ .instance_size = sizeof(BDRVQcowState),
+ .bdrv_probe = qcow2_probe,
+ .bdrv_open = qcow2_open,
+ .bdrv_close = qcow2_close,
+ .bdrv_reopen_prepare = qcow2_reopen_prepare,
+ .bdrv_create = qcow2_create,
+ .bdrv_has_zero_init = bdrv_has_zero_init_1,
+ .bdrv_co_is_allocated = qcow2_co_is_allocated,
+ .bdrv_set_key = qcow2_set_key,
+ .bdrv_make_empty = qcow2_make_empty,
+
+ .bdrv_co_readv = qcow2_co_readv,
+ .bdrv_co_writev = qcow2_co_writev,
+ .bdrv_co_flush_to_os = qcow2_co_flush_to_os,
+
+ .bdrv_co_write_zeroes = qcow2_co_write_zeroes,
+ .bdrv_co_discard = qcow2_co_discard,
+ .bdrv_truncate = qcow2_truncate,
+ .bdrv_write_compressed = qcow2_write_compressed,
+
+ .bdrv_snapshot_create = qcow2_snapshot_create,
+ .bdrv_snapshot_goto = qcow2_snapshot_goto,
+ .bdrv_snapshot_delete = qcow2_snapshot_delete,
+ .bdrv_snapshot_list = qcow2_snapshot_list,
+ .bdrv_snapshot_load_tmp = qcow2_snapshot_load_tmp,
+ .bdrv_get_info = qcow2_get_info,
+
+ .bdrv_save_vmstate = qcow2_save_vmstate,
+ .bdrv_load_vmstate = qcow2_load_vmstate,
+
+ .bdrv_change_backing_file = qcow2_change_backing_file,
+
+ .bdrv_invalidate_cache = qcow2_invalidate_cache,
+
+ .create_options = qcow2_create_options,
+ .bdrv_check = qcow2_check,
+};
+
+static void bdrv_qcow2_init(void)
+{
+ bdrv_register(&bdrv_qcow2);
+}
+
+block_init(bdrv_qcow2_init);
diff --git a/contrib/qemu/block/qcow2.h b/contrib/qemu/block/qcow2.h
new file mode 100644
index 00000000000..3b2d5cda71f
--- /dev/null
+++ b/contrib/qemu/block/qcow2.h
@@ -0,0 +1,437 @@
+/*
+ * Block driver for the QCOW version 2 format
+ *
+ * Copyright (c) 2004-2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef BLOCK_QCOW2_H
+#define BLOCK_QCOW2_H
+
+#include "qemu/aes.h"
+#include "block/coroutine.h"
+
+//#define DEBUG_ALLOC
+//#define DEBUG_ALLOC2
+//#define DEBUG_EXT
+
+#define QCOW_MAGIC (('Q' << 24) | ('F' << 16) | ('I' << 8) | 0xfb)
+
+#define QCOW_CRYPT_NONE 0
+#define QCOW_CRYPT_AES 1
+
+#define QCOW_MAX_CRYPT_CLUSTERS 32
+
+/* indicate that the refcount of the referenced cluster is exactly one. */
+#define QCOW_OFLAG_COPIED (1LL << 63)
+/* indicate that the cluster is compressed (they never have the copied flag) */
+#define QCOW_OFLAG_COMPRESSED (1LL << 62)
+/* The cluster reads as all zeros */
+#define QCOW_OFLAG_ZERO (1LL << 0)
+
+#define REFCOUNT_SHIFT 1 /* refcount size is 2 bytes */
+
+#define MIN_CLUSTER_BITS 9
+#define MAX_CLUSTER_BITS 21
+
+#define L2_CACHE_SIZE 16
+
+/* Must be at least 4 to cover all cases of refcount table growth */
+#define REFCOUNT_CACHE_SIZE 4
+
+#define DEFAULT_CLUSTER_SIZE 65536
+
+
+#define QCOW2_OPT_LAZY_REFCOUNTS "lazy_refcounts"
+#define QCOW2_OPT_DISCARD_REQUEST "pass_discard_request"
+#define QCOW2_OPT_DISCARD_SNAPSHOT "pass_discard_snapshot"
+#define QCOW2_OPT_DISCARD_OTHER "pass_discard_other"
+
+typedef struct QCowHeader {
+ uint32_t magic;
+ uint32_t version;
+ uint64_t backing_file_offset;
+ uint32_t backing_file_size;
+ uint32_t cluster_bits;
+ uint64_t size; /* in bytes */
+ uint32_t crypt_method;
+ uint32_t l1_size; /* XXX: save number of clusters instead ? */
+ uint64_t l1_table_offset;
+ uint64_t refcount_table_offset;
+ uint32_t refcount_table_clusters;
+ uint32_t nb_snapshots;
+ uint64_t snapshots_offset;
+
+ /* The following fields are only valid for version >= 3 */
+ uint64_t incompatible_features;
+ uint64_t compatible_features;
+ uint64_t autoclear_features;
+
+ uint32_t refcount_order;
+ uint32_t header_length;
+} QCowHeader;
+
+typedef struct QCowSnapshot {
+ uint64_t l1_table_offset;
+ uint32_t l1_size;
+ char *id_str;
+ char *name;
+ uint64_t disk_size;
+ uint64_t vm_state_size;
+ uint32_t date_sec;
+ uint32_t date_nsec;
+ uint64_t vm_clock_nsec;
+} QCowSnapshot;
+
+struct Qcow2Cache;
+typedef struct Qcow2Cache Qcow2Cache;
+
+typedef struct Qcow2UnknownHeaderExtension {
+ uint32_t magic;
+ uint32_t len;
+ QLIST_ENTRY(Qcow2UnknownHeaderExtension) next;
+ uint8_t data[];
+} Qcow2UnknownHeaderExtension;
+
+enum {
+ QCOW2_FEAT_TYPE_INCOMPATIBLE = 0,
+ QCOW2_FEAT_TYPE_COMPATIBLE = 1,
+ QCOW2_FEAT_TYPE_AUTOCLEAR = 2,
+};
+
+/* Incompatible feature bits */
+enum {
+ QCOW2_INCOMPAT_DIRTY_BITNR = 0,
+ QCOW2_INCOMPAT_DIRTY = 1 << QCOW2_INCOMPAT_DIRTY_BITNR,
+
+ QCOW2_INCOMPAT_MASK = QCOW2_INCOMPAT_DIRTY,
+};
+
+/* Compatible feature bits */
+enum {
+ QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR = 0,
+ QCOW2_COMPAT_LAZY_REFCOUNTS = 1 << QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
+
+ QCOW2_COMPAT_FEAT_MASK = QCOW2_COMPAT_LAZY_REFCOUNTS,
+};
+
+enum qcow2_discard_type {
+ QCOW2_DISCARD_NEVER = 0,
+ QCOW2_DISCARD_ALWAYS,
+ QCOW2_DISCARD_REQUEST,
+ QCOW2_DISCARD_SNAPSHOT,
+ QCOW2_DISCARD_OTHER,
+ QCOW2_DISCARD_MAX
+};
+
+typedef struct Qcow2Feature {
+ uint8_t type;
+ uint8_t bit;
+ char name[46];
+} QEMU_PACKED Qcow2Feature;
+
+typedef struct Qcow2DiscardRegion {
+ BlockDriverState *bs;
+ uint64_t offset;
+ uint64_t bytes;
+ QTAILQ_ENTRY(Qcow2DiscardRegion) next;
+} Qcow2DiscardRegion;
+
+typedef struct BDRVQcowState {
+ int cluster_bits;
+ int cluster_size;
+ int cluster_sectors;
+ int l2_bits;
+ int l2_size;
+ int l1_size;
+ int l1_vm_state_index;
+ int csize_shift;
+ int csize_mask;
+ uint64_t cluster_offset_mask;
+ uint64_t l1_table_offset;
+ uint64_t *l1_table;
+
+ Qcow2Cache* l2_table_cache;
+ Qcow2Cache* refcount_block_cache;
+
+ uint8_t *cluster_cache;
+ uint8_t *cluster_data;
+ uint64_t cluster_cache_offset;
+ QLIST_HEAD(QCowClusterAlloc, QCowL2Meta) cluster_allocs;
+
+ uint64_t *refcount_table;
+ uint64_t refcount_table_offset;
+ uint32_t refcount_table_size;
+ int64_t free_cluster_index;
+ int64_t free_byte_offset;
+
+ CoMutex lock;
+
+ uint32_t crypt_method; /* current crypt method, 0 if no key yet */
+ uint32_t crypt_method_header;
+ AES_KEY aes_encrypt_key;
+ AES_KEY aes_decrypt_key;
+ uint64_t snapshots_offset;
+ int snapshots_size;
+ int nb_snapshots;
+ QCowSnapshot *snapshots;
+
+ int flags;
+ int qcow_version;
+ bool use_lazy_refcounts;
+
+ bool discard_passthrough[QCOW2_DISCARD_MAX];
+
+ uint64_t incompatible_features;
+ uint64_t compatible_features;
+ uint64_t autoclear_features;
+
+ size_t unknown_header_fields_size;
+ void* unknown_header_fields;
+ QLIST_HEAD(, Qcow2UnknownHeaderExtension) unknown_header_ext;
+ QTAILQ_HEAD (, Qcow2DiscardRegion) discards;
+ bool cache_discards;
+} BDRVQcowState;
+
+/* XXX: use std qcow open function ? */
+typedef struct QCowCreateState {
+ int cluster_size;
+ int cluster_bits;
+ uint16_t *refcount_block;
+ uint64_t *refcount_table;
+ int64_t l1_table_offset;
+ int64_t refcount_table_offset;
+ int64_t refcount_block_offset;
+} QCowCreateState;
+
+struct QCowAIOCB;
+
+typedef struct Qcow2COWRegion {
+ /**
+ * Offset of the COW region in bytes from the start of the first cluster
+ * touched by the request.
+ */
+ uint64_t offset;
+
+ /** Number of sectors to copy */
+ int nb_sectors;
+} Qcow2COWRegion;
+
+/**
+ * Describes an in-flight (part of a) write request that writes to clusters
+ * that are not referenced in their L2 table yet.
+ */
+typedef struct QCowL2Meta
+{
+ /** Guest offset of the first newly allocated cluster */
+ uint64_t offset;
+
+ /** Host offset of the first newly allocated cluster */
+ uint64_t alloc_offset;
+
+ /**
+ * Number of sectors from the start of the first allocated cluster to
+ * the end of the (possibly shortened) request
+ */
+ int nb_available;
+
+ /** Number of newly allocated clusters */
+ int nb_clusters;
+
+ /**
+ * Requests that overlap with this allocation and wait to be restarted
+ * when the allocating request has completed.
+ */
+ CoQueue dependent_requests;
+
+ /**
+ * The COW Region between the start of the first allocated cluster and the
+ * area the guest actually writes to.
+ */
+ Qcow2COWRegion cow_start;
+
+ /**
+ * The COW Region between the area the guest actually writes to and the
+ * end of the last allocated cluster.
+ */
+ Qcow2COWRegion cow_end;
+
+ /** Pointer to next L2Meta of the same write request */
+ struct QCowL2Meta *next;
+
+ QLIST_ENTRY(QCowL2Meta) next_in_flight;
+} QCowL2Meta;
+
+enum {
+ QCOW2_CLUSTER_UNALLOCATED,
+ QCOW2_CLUSTER_NORMAL,
+ QCOW2_CLUSTER_COMPRESSED,
+ QCOW2_CLUSTER_ZERO
+};
+
+#define L1E_OFFSET_MASK 0x00ffffffffffff00ULL
+#define L2E_OFFSET_MASK 0x00ffffffffffff00ULL
+#define L2E_COMPRESSED_OFFSET_SIZE_MASK 0x3fffffffffffffffULL
+
+#define REFT_OFFSET_MASK 0xffffffffffffff00ULL
+
+static inline int64_t start_of_cluster(BDRVQcowState *s, int64_t offset)
+{
+ return offset & ~(s->cluster_size - 1);
+}
+
+static inline int64_t offset_into_cluster(BDRVQcowState *s, int64_t offset)
+{
+ return offset & (s->cluster_size - 1);
+}
+
+static inline int size_to_clusters(BDRVQcowState *s, int64_t size)
+{
+ return (size + (s->cluster_size - 1)) >> s->cluster_bits;
+}
+
+static inline int64_t size_to_l1(BDRVQcowState *s, int64_t size)
+{
+ int shift = s->cluster_bits + s->l2_bits;
+ return (size + (1ULL << shift) - 1) >> shift;
+}
+
+static inline int offset_to_l2_index(BDRVQcowState *s, int64_t offset)
+{
+ return (offset >> s->cluster_bits) & (s->l2_size - 1);
+}
+
+static inline int64_t align_offset(int64_t offset, int n)
+{
+ offset = (offset + n - 1) & ~(n - 1);
+ return offset;
+}
+
+static inline int qcow2_get_cluster_type(uint64_t l2_entry)
+{
+ if (l2_entry & QCOW_OFLAG_COMPRESSED) {
+ return QCOW2_CLUSTER_COMPRESSED;
+ } else if (l2_entry & QCOW_OFLAG_ZERO) {
+ return QCOW2_CLUSTER_ZERO;
+ } else if (!(l2_entry & L2E_OFFSET_MASK)) {
+ return QCOW2_CLUSTER_UNALLOCATED;
+ } else {
+ return QCOW2_CLUSTER_NORMAL;
+ }
+}
+
+/* Check whether refcounts are eager or lazy */
+static inline bool qcow2_need_accurate_refcounts(BDRVQcowState *s)
+{
+ return !(s->incompatible_features & QCOW2_INCOMPAT_DIRTY);
+}
+
+static inline uint64_t l2meta_cow_start(QCowL2Meta *m)
+{
+ return m->offset + m->cow_start.offset;
+}
+
+static inline uint64_t l2meta_cow_end(QCowL2Meta *m)
+{
+ return m->offset + m->cow_end.offset
+ + (m->cow_end.nb_sectors << BDRV_SECTOR_BITS);
+}
+
+// FIXME Need qcow2_ prefix to global functions
+
+/* qcow2.c functions */
+int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
+ int64_t sector_num, int nb_sectors);
+
+int qcow2_mark_dirty(BlockDriverState *bs);
+int qcow2_update_header(BlockDriverState *bs);
+
+/* qcow2-refcount.c functions */
+int qcow2_refcount_init(BlockDriverState *bs);
+void qcow2_refcount_close(BlockDriverState *bs);
+
+int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size);
+int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
+ int nb_clusters);
+int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);
+void qcow2_free_clusters(BlockDriverState *bs,
+ int64_t offset, int64_t size,
+ enum qcow2_discard_type type);
+void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
+ int nb_clusters, enum qcow2_discard_type type);
+
+int qcow2_update_snapshot_refcount(BlockDriverState *bs,
+ int64_t l1_table_offset, int l1_size, int addend);
+
+int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
+ BdrvCheckMode fix);
+
+void qcow2_process_discards(BlockDriverState *bs, int ret);
+
+/* qcow2-cluster.c functions */
+int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
+ bool exact_size);
+void qcow2_l2_cache_reset(BlockDriverState *bs);
+int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
+void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
+ uint8_t *out_buf, const uint8_t *in_buf,
+ int nb_sectors, int enc,
+ const AES_KEY *key);
+
+int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
+ int *num, uint64_t *cluster_offset);
+int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
+ int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m);
+uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
+ uint64_t offset,
+ int compressed_size);
+
+int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
+int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
+ int nb_sectors);
+int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
+
+/* qcow2-snapshot.c functions */
+int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
+int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id);
+int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
+int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab);
+int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name);
+
+void qcow2_free_snapshots(BlockDriverState *bs);
+int qcow2_read_snapshots(BlockDriverState *bs);
+
+/* qcow2-cache.c functions */
+Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables);
+int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c);
+
+void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table);
+int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c);
+int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
+ Qcow2Cache *dependency);
+void qcow2_cache_depends_on_flush(Qcow2Cache *c);
+
+int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
+ void **table);
+int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset,
+ void **table);
+int qcow2_cache_put(BlockDriverState *bs, Qcow2Cache *c, void **table);
+
+#endif
diff --git a/contrib/qemu/block/qed-check.c b/contrib/qemu/block/qed-check.c
new file mode 100644
index 00000000000..b473dcd61f6
--- /dev/null
+++ b/contrib/qemu/block/qed-check.c
@@ -0,0 +1,248 @@
+/*
+ * QEMU Enhanced Disk Format Consistency Check
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qed.h"
+
+typedef struct {
+ BDRVQEDState *s;
+ BdrvCheckResult *result;
+ bool fix; /* whether to fix invalid offsets */
+
+ uint64_t nclusters;
+ uint32_t *used_clusters; /* referenced cluster bitmap */
+
+ QEDRequest request;
+} QEDCheck;
+
+static bool qed_test_bit(uint32_t *bitmap, uint64_t n) {
+ return !!(bitmap[n / 32] & (1 << (n % 32)));
+}
+
+static void qed_set_bit(uint32_t *bitmap, uint64_t n) {
+ bitmap[n / 32] |= 1 << (n % 32);
+}
+
+/**
+ * Set bitmap bits for clusters
+ *
+ * @check: Check structure
+ * @offset: Starting offset in bytes
+ * @n: Number of clusters
+ */
+static bool qed_set_used_clusters(QEDCheck *check, uint64_t offset,
+ unsigned int n)
+{
+ uint64_t cluster = qed_bytes_to_clusters(check->s, offset);
+ unsigned int corruptions = 0;
+
+ while (n-- != 0) {
+ /* Clusters should only be referenced once */
+ if (qed_test_bit(check->used_clusters, cluster)) {
+ corruptions++;
+ }
+
+ qed_set_bit(check->used_clusters, cluster);
+ cluster++;
+ }
+
+ check->result->corruptions += corruptions;
+ return corruptions == 0;
+}
+
+/**
+ * Check an L2 table
+ *
+ * @ret: Number of invalid cluster offsets
+ */
+static unsigned int qed_check_l2_table(QEDCheck *check, QEDTable *table)
+{
+ BDRVQEDState *s = check->s;
+ unsigned int i, num_invalid = 0;
+ uint64_t last_offset = 0;
+
+ for (i = 0; i < s->table_nelems; i++) {
+ uint64_t offset = table->offsets[i];
+
+ if (qed_offset_is_unalloc_cluster(offset) ||
+ qed_offset_is_zero_cluster(offset)) {
+ continue;
+ }
+ check->result->bfi.allocated_clusters++;
+ if (last_offset && (last_offset + s->header.cluster_size != offset)) {
+ check->result->bfi.fragmented_clusters++;
+ }
+ last_offset = offset;
+
+ /* Detect invalid cluster offset */
+ if (!qed_check_cluster_offset(s, offset)) {
+ if (check->fix) {
+ table->offsets[i] = 0;
+ check->result->corruptions_fixed++;
+ } else {
+ check->result->corruptions++;
+ }
+
+ num_invalid++;
+ continue;
+ }
+
+ qed_set_used_clusters(check, offset, 1);
+ }
+
+ return num_invalid;
+}
+
+/**
+ * Descend tables and check each cluster is referenced once only
+ */
+static int qed_check_l1_table(QEDCheck *check, QEDTable *table)
+{
+ BDRVQEDState *s = check->s;
+ unsigned int i, num_invalid_l1 = 0;
+ int ret, last_error = 0;
+
+ /* Mark L1 table clusters used */
+ qed_set_used_clusters(check, s->header.l1_table_offset,
+ s->header.table_size);
+
+ for (i = 0; i < s->table_nelems; i++) {
+ unsigned int num_invalid_l2;
+ uint64_t offset = table->offsets[i];
+
+ if (qed_offset_is_unalloc_cluster(offset)) {
+ continue;
+ }
+
+ /* Detect invalid L2 offset */
+ if (!qed_check_table_offset(s, offset)) {
+ /* Clear invalid offset */
+ if (check->fix) {
+ table->offsets[i] = 0;
+ check->result->corruptions_fixed++;
+ } else {
+ check->result->corruptions++;
+ }
+
+ num_invalid_l1++;
+ continue;
+ }
+
+ if (!qed_set_used_clusters(check, offset, s->header.table_size)) {
+ continue; /* skip an invalid table */
+ }
+
+ ret = qed_read_l2_table_sync(s, &check->request, offset);
+ if (ret) {
+ check->result->check_errors++;
+ last_error = ret;
+ continue;
+ }
+
+ num_invalid_l2 = qed_check_l2_table(check,
+ check->request.l2_table->table);
+
+ /* Write out fixed L2 table */
+ if (num_invalid_l2 > 0 && check->fix) {
+ ret = qed_write_l2_table_sync(s, &check->request, 0,
+ s->table_nelems, false);
+ if (ret) {
+ check->result->check_errors++;
+ last_error = ret;
+ continue;
+ }
+ }
+ }
+
+ /* Drop reference to final table */
+ qed_unref_l2_cache_entry(check->request.l2_table);
+ check->request.l2_table = NULL;
+
+ /* Write out fixed L1 table */
+ if (num_invalid_l1 > 0 && check->fix) {
+ ret = qed_write_l1_table_sync(s, 0, s->table_nelems);
+ if (ret) {
+ check->result->check_errors++;
+ last_error = ret;
+ }
+ }
+
+ return last_error;
+}
+
+/**
+ * Check for unreferenced (leaked) clusters
+ */
+static void qed_check_for_leaks(QEDCheck *check)
+{
+ BDRVQEDState *s = check->s;
+ uint64_t i;
+
+ for (i = s->header.header_size; i < check->nclusters; i++) {
+ if (!qed_test_bit(check->used_clusters, i)) {
+ check->result->leaks++;
+ }
+ }
+}
+
+/**
+ * Mark an image clean once it passes check or has been repaired
+ */
+static void qed_check_mark_clean(BDRVQEDState *s, BdrvCheckResult *result)
+{
+ /* Skip if there were unfixable corruptions or I/O errors */
+ if (result->corruptions > 0 || result->check_errors > 0) {
+ return;
+ }
+
+ /* Skip if image is already marked clean */
+ if (!(s->header.features & QED_F_NEED_CHECK)) {
+ return;
+ }
+
+ /* Ensure fixes reach storage before clearing check bit */
+ bdrv_flush(s->bs);
+
+ s->header.features &= ~QED_F_NEED_CHECK;
+ qed_write_header_sync(s);
+}
+
+int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix)
+{
+ QEDCheck check = {
+ .s = s,
+ .result = result,
+ .nclusters = qed_bytes_to_clusters(s, s->file_size),
+ .request = { .l2_table = NULL },
+ .fix = fix,
+ };
+ int ret;
+
+ check.used_clusters = g_malloc0(((check.nclusters + 31) / 32) *
+ sizeof(check.used_clusters[0]));
+
+ check.result->bfi.total_clusters =
+ (s->header.image_size + s->header.cluster_size - 1) /
+ s->header.cluster_size;
+ ret = qed_check_l1_table(&check, s->l1_table);
+ if (ret == 0) {
+ /* Only check for leaks if entire image was scanned successfully */
+ qed_check_for_leaks(&check);
+
+ if (fix) {
+ qed_check_mark_clean(s, result);
+ }
+ }
+
+ g_free(check.used_clusters);
+ return ret;
+}
diff --git a/contrib/qemu/block/qed-cluster.c b/contrib/qemu/block/qed-cluster.c
new file mode 100644
index 00000000000..f64b2af8f7e
--- /dev/null
+++ b/contrib/qemu/block/qed-cluster.c
@@ -0,0 +1,165 @@
+/*
+ * QEMU Enhanced Disk Format Cluster functions
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qed.h"
+
+/**
+ * Count the number of contiguous data clusters
+ *
+ * @s: QED state
+ * @table: L2 table
+ * @index: First cluster index
+ * @n: Maximum number of clusters
+ * @offset: Set to first cluster offset
+ *
+ * This function scans tables for contiguous clusters. A contiguous run of
+ * clusters may be allocated, unallocated, or zero.
+ */
+static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s,
+ QEDTable *table,
+ unsigned int index,
+ unsigned int n,
+ uint64_t *offset)
+{
+ unsigned int end = MIN(index + n, s->table_nelems);
+ uint64_t last = table->offsets[index];
+ unsigned int i;
+
+ *offset = last;
+
+ for (i = index + 1; i < end; i++) {
+ if (qed_offset_is_unalloc_cluster(last)) {
+ /* Counting unallocated clusters */
+ if (!qed_offset_is_unalloc_cluster(table->offsets[i])) {
+ break;
+ }
+ } else if (qed_offset_is_zero_cluster(last)) {
+ /* Counting zero clusters */
+ if (!qed_offset_is_zero_cluster(table->offsets[i])) {
+ break;
+ }
+ } else {
+ /* Counting allocated clusters */
+ if (table->offsets[i] != last + s->header.cluster_size) {
+ break;
+ }
+ last = table->offsets[i];
+ }
+ }
+ return i - index;
+}
+
+typedef struct {
+ BDRVQEDState *s;
+ uint64_t pos;
+ size_t len;
+
+ QEDRequest *request;
+
+ /* User callback */
+ QEDFindClusterFunc *cb;
+ void *opaque;
+} QEDFindClusterCB;
+
+static void qed_find_cluster_cb(void *opaque, int ret)
+{
+ QEDFindClusterCB *find_cluster_cb = opaque;
+ BDRVQEDState *s = find_cluster_cb->s;
+ QEDRequest *request = find_cluster_cb->request;
+ uint64_t offset = 0;
+ size_t len = 0;
+ unsigned int index;
+ unsigned int n;
+
+ if (ret) {
+ goto out;
+ }
+
+ index = qed_l2_index(s, find_cluster_cb->pos);
+ n = qed_bytes_to_clusters(s,
+ qed_offset_into_cluster(s, find_cluster_cb->pos) +
+ find_cluster_cb->len);
+ n = qed_count_contiguous_clusters(s, request->l2_table->table,
+ index, n, &offset);
+
+ if (qed_offset_is_unalloc_cluster(offset)) {
+ ret = QED_CLUSTER_L2;
+ } else if (qed_offset_is_zero_cluster(offset)) {
+ ret = QED_CLUSTER_ZERO;
+ } else if (qed_check_cluster_offset(s, offset)) {
+ ret = QED_CLUSTER_FOUND;
+ } else {
+ ret = -EINVAL;
+ }
+
+ len = MIN(find_cluster_cb->len, n * s->header.cluster_size -
+ qed_offset_into_cluster(s, find_cluster_cb->pos));
+
+out:
+ find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len);
+ g_free(find_cluster_cb);
+}
+
+/**
+ * Find the offset of a data cluster
+ *
+ * @s: QED state
+ * @request: L2 cache entry
+ * @pos: Byte position in device
+ * @len: Number of bytes
+ * @cb: Completion function
+ * @opaque: User data for completion function
+ *
+ * This function translates a position in the block device to an offset in the
+ * image file. It invokes the cb completion callback to report back the
+ * translated offset or unallocated range in the image file.
+ *
+ * If the L2 table exists, request->l2_table points to the L2 table cache entry
+ * and the caller must free the reference when they are finished. The cache
+ * entry is exposed in this way to avoid callers having to read the L2 table
+ * again later during request processing. If request->l2_table is non-NULL it
+ * will be unreferenced before taking on the new cache entry.
+ */
+void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
+ size_t len, QEDFindClusterFunc *cb, void *opaque)
+{
+ QEDFindClusterCB *find_cluster_cb;
+ uint64_t l2_offset;
+
+ /* Limit length to L2 boundary. Requests are broken up at the L2 boundary
+ * so that a request acts on one L2 table at a time.
+ */
+ len = MIN(len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos);
+
+ l2_offset = s->l1_table->offsets[qed_l1_index(s, pos)];
+ if (qed_offset_is_unalloc_cluster(l2_offset)) {
+ cb(opaque, QED_CLUSTER_L1, 0, len);
+ return;
+ }
+ if (!qed_check_table_offset(s, l2_offset)) {
+ cb(opaque, -EINVAL, 0, 0);
+ return;
+ }
+
+ find_cluster_cb = g_malloc(sizeof(*find_cluster_cb));
+ find_cluster_cb->s = s;
+ find_cluster_cb->pos = pos;
+ find_cluster_cb->len = len;
+ find_cluster_cb->cb = cb;
+ find_cluster_cb->opaque = opaque;
+ find_cluster_cb->request = request;
+
+ qed_read_l2_table(s, request, l2_offset,
+ qed_find_cluster_cb, find_cluster_cb);
+}
diff --git a/contrib/qemu/block/qed-gencb.c b/contrib/qemu/block/qed-gencb.c
new file mode 100644
index 00000000000..7d7ac1ffc8e
--- /dev/null
+++ b/contrib/qemu/block/qed-gencb.c
@@ -0,0 +1,32 @@
+/*
+ * QEMU Enhanced Disk Format
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qed.h"
+
+void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque)
+{
+ GenericCB *gencb = g_malloc(len);
+ gencb->cb = cb;
+ gencb->opaque = opaque;
+ return gencb;
+}
+
+void gencb_complete(void *opaque, int ret)
+{
+ GenericCB *gencb = opaque;
+ BlockDriverCompletionFunc *cb = gencb->cb;
+ void *user_opaque = gencb->opaque;
+
+ g_free(gencb);
+ cb(user_opaque, ret);
+}
diff --git a/contrib/qemu/block/qed-l2-cache.c b/contrib/qemu/block/qed-l2-cache.c
new file mode 100644
index 00000000000..e9b2aae44d9
--- /dev/null
+++ b/contrib/qemu/block/qed-l2-cache.c
@@ -0,0 +1,187 @@
+/*
+ * QEMU Enhanced Disk Format L2 Cache
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+/*
+ * L2 table cache usage is as follows:
+ *
+ * An open image has one L2 table cache that is used to avoid accessing the
+ * image file for recently referenced L2 tables.
+ *
+ * Cluster offset lookup translates the logical offset within the block device
+ * to a cluster offset within the image file. This is done by indexing into
+ * the L1 and L2 tables which store cluster offsets. It is here where the L2
+ * table cache serves up recently referenced L2 tables.
+ *
+ * If there is a cache miss, that L2 table is read from the image file and
+ * committed to the cache. Subsequent accesses to that L2 table will be served
+ * from the cache until the table is evicted from the cache.
+ *
+ * L2 tables are also committed to the cache when new L2 tables are allocated
+ * in the image file. Since the L2 table cache is write-through, the new L2
+ * table is first written out to the image file and then committed to the
+ * cache.
+ *
+ * Multiple I/O requests may be using an L2 table cache entry at any given
+ * time. That means an entry may be in use across several requests and
+ * reference counting is needed to free the entry at the correct time. In
+ * particular, an entry evicted from the cache will only be freed once all
+ * references are dropped.
+ *
+ * An in-flight I/O request will hold a reference to a L2 table cache entry for
+ * the period during which it needs to access the L2 table. This includes
+ * cluster offset lookup, L2 table allocation, and L2 table update when a new
+ * data cluster has been allocated.
+ *
+ * An interesting case occurs when two requests need to access an L2 table that
+ * is not in the cache. Since the operation to read the table from the image
+ * file takes some time to complete, both requests may see a cache miss and
+ * start reading the L2 table from the image file. The first to finish will
+ * commit its L2 table into the cache. When the second tries to commit its
+ * table will be deleted in favor of the existing cache entry.
+ */
+
+#include "trace.h"
+#include "qed.h"
+
+/* Each L2 holds 2GB so this let's us fully cache a 100GB disk */
+#define MAX_L2_CACHE_SIZE 50
+
+/**
+ * Initialize the L2 cache
+ */
+void qed_init_l2_cache(L2TableCache *l2_cache)
+{
+ QTAILQ_INIT(&l2_cache->entries);
+ l2_cache->n_entries = 0;
+}
+
+/**
+ * Free the L2 cache
+ */
+void qed_free_l2_cache(L2TableCache *l2_cache)
+{
+ CachedL2Table *entry, *next_entry;
+
+ QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next_entry) {
+ qemu_vfree(entry->table);
+ g_free(entry);
+ }
+}
+
+/**
+ * Allocate an uninitialized entry from the cache
+ *
+ * The returned entry has a reference count of 1 and is owned by the caller.
+ * The caller must allocate the actual table field for this entry and it must
+ * be freeable using qemu_vfree().
+ */
+CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache)
+{
+ CachedL2Table *entry;
+
+ entry = g_malloc0(sizeof(*entry));
+ entry->ref++;
+
+ trace_qed_alloc_l2_cache_entry(l2_cache, entry);
+
+ return entry;
+}
+
+/**
+ * Decrease an entry's reference count and free if necessary when the reference
+ * count drops to zero.
+ */
+void qed_unref_l2_cache_entry(CachedL2Table *entry)
+{
+ if (!entry) {
+ return;
+ }
+
+ entry->ref--;
+ trace_qed_unref_l2_cache_entry(entry, entry->ref);
+ if (entry->ref == 0) {
+ qemu_vfree(entry->table);
+ g_free(entry);
+ }
+}
+
+/**
+ * Find an entry in the L2 cache. This may return NULL and it's up to the
+ * caller to satisfy the cache miss.
+ *
+ * For a cached entry, this function increases the reference count and returns
+ * the entry.
+ */
+CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset)
+{
+ CachedL2Table *entry;
+
+ QTAILQ_FOREACH(entry, &l2_cache->entries, node) {
+ if (entry->offset == offset) {
+ trace_qed_find_l2_cache_entry(l2_cache, entry, offset, entry->ref);
+ entry->ref++;
+ return entry;
+ }
+ }
+ return NULL;
+}
+
+/**
+ * Commit an L2 cache entry into the cache. This is meant to be used as part of
+ * the process to satisfy a cache miss. A caller would allocate an entry which
+ * is not actually in the L2 cache and then once the entry was valid and
+ * present on disk, the entry can be committed into the cache.
+ *
+ * Since the cache is write-through, it's important that this function is not
+ * called until the entry is present on disk and the L1 has been updated to
+ * point to the entry.
+ *
+ * N.B. This function steals a reference to the l2_table from the caller so the
+ * caller must obtain a new reference by issuing a call to
+ * qed_find_l2_cache_entry().
+ */
+void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table)
+{
+ CachedL2Table *entry;
+
+ entry = qed_find_l2_cache_entry(l2_cache, l2_table->offset);
+ if (entry) {
+ qed_unref_l2_cache_entry(entry);
+ qed_unref_l2_cache_entry(l2_table);
+ return;
+ }
+
+ /* Evict an unused cache entry so we have space. If all entries are in use
+ * we can grow the cache temporarily and we try to shrink back down later.
+ */
+ if (l2_cache->n_entries >= MAX_L2_CACHE_SIZE) {
+ CachedL2Table *next;
+ QTAILQ_FOREACH_SAFE(entry, &l2_cache->entries, node, next) {
+ if (entry->ref > 1) {
+ continue;
+ }
+
+ QTAILQ_REMOVE(&l2_cache->entries, entry, node);
+ l2_cache->n_entries--;
+ qed_unref_l2_cache_entry(entry);
+
+ /* Stop evicting when we've shrunk back to max size */
+ if (l2_cache->n_entries < MAX_L2_CACHE_SIZE) {
+ break;
+ }
+ }
+ }
+
+ l2_cache->n_entries++;
+ QTAILQ_INSERT_TAIL(&l2_cache->entries, l2_table, node);
+}
diff --git a/contrib/qemu/block/qed-table.c b/contrib/qemu/block/qed-table.c
new file mode 100644
index 00000000000..76d2dcccf81
--- /dev/null
+++ b/contrib/qemu/block/qed-table.c
@@ -0,0 +1,296 @@
+/*
+ * QEMU Enhanced Disk Format Table I/O
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "trace.h"
+#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
+#include "qed.h"
+
+typedef struct {
+ GenericCB gencb;
+ BDRVQEDState *s;
+ QEDTable *table;
+
+ struct iovec iov;
+ QEMUIOVector qiov;
+} QEDReadTableCB;
+
+static void qed_read_table_cb(void *opaque, int ret)
+{
+ QEDReadTableCB *read_table_cb = opaque;
+ QEDTable *table = read_table_cb->table;
+ int noffsets = read_table_cb->qiov.size / sizeof(uint64_t);
+ int i;
+
+ /* Handle I/O error */
+ if (ret) {
+ goto out;
+ }
+
+ /* Byteswap offsets */
+ for (i = 0; i < noffsets; i++) {
+ table->offsets[i] = le64_to_cpu(table->offsets[i]);
+ }
+
+out:
+ /* Completion */
+ trace_qed_read_table_cb(read_table_cb->s, read_table_cb->table, ret);
+ gencb_complete(&read_table_cb->gencb, ret);
+}
+
+static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ QEDReadTableCB *read_table_cb = gencb_alloc(sizeof(*read_table_cb),
+ cb, opaque);
+ QEMUIOVector *qiov = &read_table_cb->qiov;
+
+ trace_qed_read_table(s, offset, table);
+
+ read_table_cb->s = s;
+ read_table_cb->table = table;
+ read_table_cb->iov.iov_base = table->offsets,
+ read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size,
+
+ qemu_iovec_init_external(qiov, &read_table_cb->iov, 1);
+ bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov,
+ qiov->size / BDRV_SECTOR_SIZE,
+ qed_read_table_cb, read_table_cb);
+}
+
+typedef struct {
+ GenericCB gencb;
+ BDRVQEDState *s;
+ QEDTable *orig_table;
+ QEDTable *table;
+ bool flush; /* flush after write? */
+
+ struct iovec iov;
+ QEMUIOVector qiov;
+} QEDWriteTableCB;
+
+static void qed_write_table_cb(void *opaque, int ret)
+{
+ QEDWriteTableCB *write_table_cb = opaque;
+
+ trace_qed_write_table_cb(write_table_cb->s,
+ write_table_cb->orig_table,
+ write_table_cb->flush,
+ ret);
+
+ if (ret) {
+ goto out;
+ }
+
+ if (write_table_cb->flush) {
+ /* We still need to flush first */
+ write_table_cb->flush = false;
+ bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb,
+ write_table_cb);
+ return;
+ }
+
+out:
+ qemu_vfree(write_table_cb->table);
+ gencb_complete(&write_table_cb->gencb, ret);
+}
+
+/**
+ * Write out an updated part or all of a table
+ *
+ * @s: QED state
+ * @offset: Offset of table in image file, in bytes
+ * @table: Table
+ * @index: Index of first element
+ * @n: Number of elements
+ * @flush: Whether or not to sync to disk
+ * @cb: Completion function
+ * @opaque: Argument for completion function
+ */
+static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
+ unsigned int index, unsigned int n, bool flush,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ QEDWriteTableCB *write_table_cb;
+ unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1;
+ unsigned int start, end, i;
+ size_t len_bytes;
+
+ trace_qed_write_table(s, offset, table, index, n);
+
+ /* Calculate indices of the first and one after last elements */
+ start = index & ~sector_mask;
+ end = (index + n + sector_mask) & ~sector_mask;
+
+ len_bytes = (end - start) * sizeof(uint64_t);
+
+ write_table_cb = gencb_alloc(sizeof(*write_table_cb), cb, opaque);
+ write_table_cb->s = s;
+ write_table_cb->orig_table = table;
+ write_table_cb->flush = flush;
+ write_table_cb->table = qemu_blockalign(s->bs, len_bytes);
+ write_table_cb->iov.iov_base = write_table_cb->table->offsets;
+ write_table_cb->iov.iov_len = len_bytes;
+ qemu_iovec_init_external(&write_table_cb->qiov, &write_table_cb->iov, 1);
+
+ /* Byteswap table */
+ for (i = start; i < end; i++) {
+ uint64_t le_offset = cpu_to_le64(table->offsets[i]);
+ write_table_cb->table->offsets[i - start] = le_offset;
+ }
+
+ /* Adjust for offset into table */
+ offset += start * sizeof(uint64_t);
+
+ bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
+ &write_table_cb->qiov,
+ write_table_cb->qiov.size / BDRV_SECTOR_SIZE,
+ qed_write_table_cb, write_table_cb);
+}
+
+/**
+ * Propagate return value from async callback
+ */
+static void qed_sync_cb(void *opaque, int ret)
+{
+ *(int *)opaque = ret;
+}
+
+int qed_read_l1_table_sync(BDRVQEDState *s)
+{
+ int ret = -EINPROGRESS;
+
+ qed_read_table(s, s->header.l1_table_offset,
+ s->l1_table, qed_sync_cb, &ret);
+ while (ret == -EINPROGRESS) {
+ qemu_aio_wait();
+ }
+
+ return ret;
+}
+
+void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ BLKDBG_EVENT(s->bs->file, BLKDBG_L1_UPDATE);
+ qed_write_table(s, s->header.l1_table_offset,
+ s->l1_table, index, n, false, cb, opaque);
+}
+
+int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
+ unsigned int n)
+{
+ int ret = -EINPROGRESS;
+
+ qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
+ while (ret == -EINPROGRESS) {
+ qemu_aio_wait();
+ }
+
+ return ret;
+}
+
+typedef struct {
+ GenericCB gencb;
+ BDRVQEDState *s;
+ uint64_t l2_offset;
+ QEDRequest *request;
+} QEDReadL2TableCB;
+
+static void qed_read_l2_table_cb(void *opaque, int ret)
+{
+ QEDReadL2TableCB *read_l2_table_cb = opaque;
+ QEDRequest *request = read_l2_table_cb->request;
+ BDRVQEDState *s = read_l2_table_cb->s;
+ CachedL2Table *l2_table = request->l2_table;
+ uint64_t l2_offset = read_l2_table_cb->l2_offset;
+
+ if (ret) {
+ /* can't trust loaded L2 table anymore */
+ qed_unref_l2_cache_entry(l2_table);
+ request->l2_table = NULL;
+ } else {
+ l2_table->offset = l2_offset;
+
+ qed_commit_l2_cache_entry(&s->l2_cache, l2_table);
+
+ /* This is guaranteed to succeed because we just committed the entry
+ * to the cache.
+ */
+ request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset);
+ assert(request->l2_table != NULL);
+ }
+
+ gencb_complete(&read_l2_table_cb->gencb, ret);
+}
+
+void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ QEDReadL2TableCB *read_l2_table_cb;
+
+ qed_unref_l2_cache_entry(request->l2_table);
+
+ /* Check for cached L2 entry */
+ request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, offset);
+ if (request->l2_table) {
+ cb(opaque, 0);
+ return;
+ }
+
+ request->l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
+ request->l2_table->table = qed_alloc_table(s);
+
+ read_l2_table_cb = gencb_alloc(sizeof(*read_l2_table_cb), cb, opaque);
+ read_l2_table_cb->s = s;
+ read_l2_table_cb->l2_offset = offset;
+ read_l2_table_cb->request = request;
+
+ BLKDBG_EVENT(s->bs->file, BLKDBG_L2_LOAD);
+ qed_read_table(s, offset, request->l2_table->table,
+ qed_read_l2_table_cb, read_l2_table_cb);
+}
+
+int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset)
+{
+ int ret = -EINPROGRESS;
+
+ qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
+ while (ret == -EINPROGRESS) {
+ qemu_aio_wait();
+ }
+
+ return ret;
+}
+
+void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
+ unsigned int index, unsigned int n, bool flush,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ BLKDBG_EVENT(s->bs->file, BLKDBG_L2_UPDATE);
+ qed_write_table(s, request->l2_table->offset,
+ request->l2_table->table, index, n, flush, cb, opaque);
+}
+
+int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
+ unsigned int index, unsigned int n, bool flush)
+{
+ int ret = -EINPROGRESS;
+
+ qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
+ while (ret == -EINPROGRESS) {
+ qemu_aio_wait();
+ }
+
+ return ret;
+}
diff --git a/contrib/qemu/block/qed.c b/contrib/qemu/block/qed.c
new file mode 100644
index 00000000000..f767b0528ce
--- /dev/null
+++ b/contrib/qemu/block/qed.c
@@ -0,0 +1,1596 @@
+/*
+ * QEMU Enhanced Disk Format
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qemu/timer.h"
+#include "trace.h"
+#include "qed.h"
+#include "qapi/qmp/qerror.h"
+#include "migration/migration.h"
+
+static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
+{
+ QEDAIOCB *acb = (QEDAIOCB *)blockacb;
+ bool finished = false;
+
+ /* Wait for the request to finish */
+ acb->finished = &finished;
+ while (!finished) {
+ qemu_aio_wait();
+ }
+}
+
+static const AIOCBInfo qed_aiocb_info = {
+ .aiocb_size = sizeof(QEDAIOCB),
+ .cancel = qed_aio_cancel,
+};
+
+static int bdrv_qed_probe(const uint8_t *buf, int buf_size,
+ const char *filename)
+{
+ const QEDHeader *header = (const QEDHeader *)buf;
+
+ if (buf_size < sizeof(*header)) {
+ return 0;
+ }
+ if (le32_to_cpu(header->magic) != QED_MAGIC) {
+ return 0;
+ }
+ return 100;
+}
+
+/**
+ * Check whether an image format is raw
+ *
+ * @fmt: Backing file format, may be NULL
+ */
+static bool qed_fmt_is_raw(const char *fmt)
+{
+ return fmt && strcmp(fmt, "raw") == 0;
+}
+
+static void qed_header_le_to_cpu(const QEDHeader *le, QEDHeader *cpu)
+{
+ cpu->magic = le32_to_cpu(le->magic);
+ cpu->cluster_size = le32_to_cpu(le->cluster_size);
+ cpu->table_size = le32_to_cpu(le->table_size);
+ cpu->header_size = le32_to_cpu(le->header_size);
+ cpu->features = le64_to_cpu(le->features);
+ cpu->compat_features = le64_to_cpu(le->compat_features);
+ cpu->autoclear_features = le64_to_cpu(le->autoclear_features);
+ cpu->l1_table_offset = le64_to_cpu(le->l1_table_offset);
+ cpu->image_size = le64_to_cpu(le->image_size);
+ cpu->backing_filename_offset = le32_to_cpu(le->backing_filename_offset);
+ cpu->backing_filename_size = le32_to_cpu(le->backing_filename_size);
+}
+
+static void qed_header_cpu_to_le(const QEDHeader *cpu, QEDHeader *le)
+{
+ le->magic = cpu_to_le32(cpu->magic);
+ le->cluster_size = cpu_to_le32(cpu->cluster_size);
+ le->table_size = cpu_to_le32(cpu->table_size);
+ le->header_size = cpu_to_le32(cpu->header_size);
+ le->features = cpu_to_le64(cpu->features);
+ le->compat_features = cpu_to_le64(cpu->compat_features);
+ le->autoclear_features = cpu_to_le64(cpu->autoclear_features);
+ le->l1_table_offset = cpu_to_le64(cpu->l1_table_offset);
+ le->image_size = cpu_to_le64(cpu->image_size);
+ le->backing_filename_offset = cpu_to_le32(cpu->backing_filename_offset);
+ le->backing_filename_size = cpu_to_le32(cpu->backing_filename_size);
+}
+
+int qed_write_header_sync(BDRVQEDState *s)
+{
+ QEDHeader le;
+ int ret;
+
+ qed_header_cpu_to_le(&s->header, &le);
+ ret = bdrv_pwrite(s->bs->file, 0, &le, sizeof(le));
+ if (ret != sizeof(le)) {
+ return ret;
+ }
+ return 0;
+}
+
+typedef struct {
+ GenericCB gencb;
+ BDRVQEDState *s;
+ struct iovec iov;
+ QEMUIOVector qiov;
+ int nsectors;
+ uint8_t *buf;
+} QEDWriteHeaderCB;
+
+static void qed_write_header_cb(void *opaque, int ret)
+{
+ QEDWriteHeaderCB *write_header_cb = opaque;
+
+ qemu_vfree(write_header_cb->buf);
+ gencb_complete(write_header_cb, ret);
+}
+
+static void qed_write_header_read_cb(void *opaque, int ret)
+{
+ QEDWriteHeaderCB *write_header_cb = opaque;
+ BDRVQEDState *s = write_header_cb->s;
+
+ if (ret) {
+ qed_write_header_cb(write_header_cb, ret);
+ return;
+ }
+
+ /* Update header */
+ qed_header_cpu_to_le(&s->header, (QEDHeader *)write_header_cb->buf);
+
+ bdrv_aio_writev(s->bs->file, 0, &write_header_cb->qiov,
+ write_header_cb->nsectors, qed_write_header_cb,
+ write_header_cb);
+}
+
+/**
+ * Update header in-place (does not rewrite backing filename or other strings)
+ *
+ * This function only updates known header fields in-place and does not affect
+ * extra data after the QED header.
+ */
+static void qed_write_header(BDRVQEDState *s, BlockDriverCompletionFunc cb,
+ void *opaque)
+{
+ /* We must write full sectors for O_DIRECT but cannot necessarily generate
+ * the data following the header if an unrecognized compat feature is
+ * active. Therefore, first read the sectors containing the header, update
+ * them, and write back.
+ */
+
+ int nsectors = (sizeof(QEDHeader) + BDRV_SECTOR_SIZE - 1) /
+ BDRV_SECTOR_SIZE;
+ size_t len = nsectors * BDRV_SECTOR_SIZE;
+ QEDWriteHeaderCB *write_header_cb = gencb_alloc(sizeof(*write_header_cb),
+ cb, opaque);
+
+ write_header_cb->s = s;
+ write_header_cb->nsectors = nsectors;
+ write_header_cb->buf = qemu_blockalign(s->bs, len);
+ write_header_cb->iov.iov_base = write_header_cb->buf;
+ write_header_cb->iov.iov_len = len;
+ qemu_iovec_init_external(&write_header_cb->qiov, &write_header_cb->iov, 1);
+
+ bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors,
+ qed_write_header_read_cb, write_header_cb);
+}
+
+static uint64_t qed_max_image_size(uint32_t cluster_size, uint32_t table_size)
+{
+ uint64_t table_entries;
+ uint64_t l2_size;
+
+ table_entries = (table_size * cluster_size) / sizeof(uint64_t);
+ l2_size = table_entries * cluster_size;
+
+ return l2_size * table_entries;
+}
+
+static bool qed_is_cluster_size_valid(uint32_t cluster_size)
+{
+ if (cluster_size < QED_MIN_CLUSTER_SIZE ||
+ cluster_size > QED_MAX_CLUSTER_SIZE) {
+ return false;
+ }
+ if (cluster_size & (cluster_size - 1)) {
+ return false; /* not power of 2 */
+ }
+ return true;
+}
+
+static bool qed_is_table_size_valid(uint32_t table_size)
+{
+ if (table_size < QED_MIN_TABLE_SIZE ||
+ table_size > QED_MAX_TABLE_SIZE) {
+ return false;
+ }
+ if (table_size & (table_size - 1)) {
+ return false; /* not power of 2 */
+ }
+ return true;
+}
+
+static bool qed_is_image_size_valid(uint64_t image_size, uint32_t cluster_size,
+ uint32_t table_size)
+{
+ if (image_size % BDRV_SECTOR_SIZE != 0) {
+ return false; /* not multiple of sector size */
+ }
+ if (image_size > qed_max_image_size(cluster_size, table_size)) {
+ return false; /* image is too large */
+ }
+ return true;
+}
+
+/**
+ * Read a string of known length from the image file
+ *
+ * @file: Image file
+ * @offset: File offset to start of string, in bytes
+ * @n: String length in bytes
+ * @buf: Destination buffer
+ * @buflen: Destination buffer length in bytes
+ * @ret: 0 on success, -errno on failure
+ *
+ * The string is NUL-terminated.
+ */
+static int qed_read_string(BlockDriverState *file, uint64_t offset, size_t n,
+ char *buf, size_t buflen)
+{
+ int ret;
+ if (n >= buflen) {
+ return -EINVAL;
+ }
+ ret = bdrv_pread(file, offset, buf, n);
+ if (ret < 0) {
+ return ret;
+ }
+ buf[n] = '\0';
+ return 0;
+}
+
+/**
+ * Allocate new clusters
+ *
+ * @s: QED state
+ * @n: Number of contiguous clusters to allocate
+ * @ret: Offset of first allocated cluster
+ *
+ * This function only produces the offset where the new clusters should be
+ * written. It updates BDRVQEDState but does not make any changes to the image
+ * file.
+ */
+static uint64_t qed_alloc_clusters(BDRVQEDState *s, unsigned int n)
+{
+ uint64_t offset = s->file_size;
+ s->file_size += n * s->header.cluster_size;
+ return offset;
+}
+
+QEDTable *qed_alloc_table(BDRVQEDState *s)
+{
+ /* Honor O_DIRECT memory alignment requirements */
+ return qemu_blockalign(s->bs,
+ s->header.cluster_size * s->header.table_size);
+}
+
+/**
+ * Allocate a new zeroed L2 table
+ */
+static CachedL2Table *qed_new_l2_table(BDRVQEDState *s)
+{
+ CachedL2Table *l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
+
+ l2_table->table = qed_alloc_table(s);
+ l2_table->offset = qed_alloc_clusters(s, s->header.table_size);
+
+ memset(l2_table->table->offsets, 0,
+ s->header.cluster_size * s->header.table_size);
+ return l2_table;
+}
+
+static void qed_aio_next_io(void *opaque, int ret);
+
+static void qed_plug_allocating_write_reqs(BDRVQEDState *s)
+{
+ assert(!s->allocating_write_reqs_plugged);
+
+ s->allocating_write_reqs_plugged = true;
+}
+
+static void qed_unplug_allocating_write_reqs(BDRVQEDState *s)
+{
+ QEDAIOCB *acb;
+
+ assert(s->allocating_write_reqs_plugged);
+
+ s->allocating_write_reqs_plugged = false;
+
+ acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
+ if (acb) {
+ qed_aio_next_io(acb, 0);
+ }
+}
+
+static void qed_finish_clear_need_check(void *opaque, int ret)
+{
+ /* Do nothing */
+}
+
+static void qed_flush_after_clear_need_check(void *opaque, int ret)
+{
+ BDRVQEDState *s = opaque;
+
+ bdrv_aio_flush(s->bs, qed_finish_clear_need_check, s);
+
+ /* No need to wait until flush completes */
+ qed_unplug_allocating_write_reqs(s);
+}
+
+static void qed_clear_need_check(void *opaque, int ret)
+{
+ BDRVQEDState *s = opaque;
+
+ if (ret) {
+ qed_unplug_allocating_write_reqs(s);
+ return;
+ }
+
+ s->header.features &= ~QED_F_NEED_CHECK;
+ qed_write_header(s, qed_flush_after_clear_need_check, s);
+}
+
+static void qed_need_check_timer_cb(void *opaque)
+{
+ BDRVQEDState *s = opaque;
+
+ /* The timer should only fire when allocating writes have drained */
+ assert(!QSIMPLEQ_FIRST(&s->allocating_write_reqs));
+
+ trace_qed_need_check_timer_cb(s);
+
+ qed_plug_allocating_write_reqs(s);
+
+ /* Ensure writes are on disk before clearing flag */
+ bdrv_aio_flush(s->bs, qed_clear_need_check, s);
+}
+
+static void qed_start_need_check_timer(BDRVQEDState *s)
+{
+ trace_qed_start_need_check_timer(s);
+
+ /* Use vm_clock so we don't alter the image file while suspended for
+ * migration.
+ */
+ qemu_mod_timer(s->need_check_timer, qemu_get_clock_ns(vm_clock) +
+ get_ticks_per_sec() * QED_NEED_CHECK_TIMEOUT);
+}
+
+/* It's okay to call this multiple times or when no timer is started */
+static void qed_cancel_need_check_timer(BDRVQEDState *s)
+{
+ trace_qed_cancel_need_check_timer(s);
+ qemu_del_timer(s->need_check_timer);
+}
+
+static void bdrv_qed_rebind(BlockDriverState *bs)
+{
+ BDRVQEDState *s = bs->opaque;
+ s->bs = bs;
+}
+
+static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags)
+{
+ BDRVQEDState *s = bs->opaque;
+ QEDHeader le_header;
+ int64_t file_size;
+ int ret;
+
+ s->bs = bs;
+ QSIMPLEQ_INIT(&s->allocating_write_reqs);
+
+ ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header));
+ if (ret < 0) {
+ return ret;
+ }
+ qed_header_le_to_cpu(&le_header, &s->header);
+
+ if (s->header.magic != QED_MAGIC) {
+ return -EMEDIUMTYPE;
+ }
+ if (s->header.features & ~QED_FEATURE_MASK) {
+ /* image uses unsupported feature bits */
+ char buf[64];
+ snprintf(buf, sizeof(buf), "%" PRIx64,
+ s->header.features & ~QED_FEATURE_MASK);
+ qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+ bs->device_name, "QED", buf);
+ return -ENOTSUP;
+ }
+ if (!qed_is_cluster_size_valid(s->header.cluster_size)) {
+ return -EINVAL;
+ }
+
+ /* Round down file size to the last cluster */
+ file_size = bdrv_getlength(bs->file);
+ if (file_size < 0) {
+ return file_size;
+ }
+ s->file_size = qed_start_of_cluster(s, file_size);
+
+ if (!qed_is_table_size_valid(s->header.table_size)) {
+ return -EINVAL;
+ }
+ if (!qed_is_image_size_valid(s->header.image_size,
+ s->header.cluster_size,
+ s->header.table_size)) {
+ return -EINVAL;
+ }
+ if (!qed_check_table_offset(s, s->header.l1_table_offset)) {
+ return -EINVAL;
+ }
+
+ s->table_nelems = (s->header.cluster_size * s->header.table_size) /
+ sizeof(uint64_t);
+ s->l2_shift = ffs(s->header.cluster_size) - 1;
+ s->l2_mask = s->table_nelems - 1;
+ s->l1_shift = s->l2_shift + ffs(s->table_nelems) - 1;
+
+ if ((s->header.features & QED_F_BACKING_FILE)) {
+ if ((uint64_t)s->header.backing_filename_offset +
+ s->header.backing_filename_size >
+ s->header.cluster_size * s->header.header_size) {
+ return -EINVAL;
+ }
+
+ ret = qed_read_string(bs->file, s->header.backing_filename_offset,
+ s->header.backing_filename_size, bs->backing_file,
+ sizeof(bs->backing_file));
+ if (ret < 0) {
+ return ret;
+ }
+
+ if (s->header.features & QED_F_BACKING_FORMAT_NO_PROBE) {
+ pstrcpy(bs->backing_format, sizeof(bs->backing_format), "raw");
+ }
+ }
+
+ /* Reset unknown autoclear feature bits. This is a backwards
+ * compatibility mechanism that allows images to be opened by older
+ * programs, which "knock out" unknown feature bits. When an image is
+ * opened by a newer program again it can detect that the autoclear
+ * feature is no longer valid.
+ */
+ if ((s->header.autoclear_features & ~QED_AUTOCLEAR_FEATURE_MASK) != 0 &&
+ !bdrv_is_read_only(bs->file) && !(flags & BDRV_O_INCOMING)) {
+ s->header.autoclear_features &= QED_AUTOCLEAR_FEATURE_MASK;
+
+ ret = qed_write_header_sync(s);
+ if (ret) {
+ return ret;
+ }
+
+ /* From here on only known autoclear feature bits are valid */
+ bdrv_flush(bs->file);
+ }
+
+ s->l1_table = qed_alloc_table(s);
+ qed_init_l2_cache(&s->l2_cache);
+
+ ret = qed_read_l1_table_sync(s);
+ if (ret) {
+ goto out;
+ }
+
+ /* If image was not closed cleanly, check consistency */
+ if (!(flags & BDRV_O_CHECK) && (s->header.features & QED_F_NEED_CHECK)) {
+ /* Read-only images cannot be fixed. There is no risk of corruption
+ * since write operations are not possible. Therefore, allow
+ * potentially inconsistent images to be opened read-only. This can
+ * aid data recovery from an otherwise inconsistent image.
+ */
+ if (!bdrv_is_read_only(bs->file) &&
+ !(flags & BDRV_O_INCOMING)) {
+ BdrvCheckResult result = {0};
+
+ ret = qed_check(s, &result, true);
+ if (ret) {
+ goto out;
+ }
+ }
+ }
+
+ s->need_check_timer = qemu_new_timer_ns(vm_clock,
+ qed_need_check_timer_cb, s);
+
+out:
+ if (ret) {
+ qed_free_l2_cache(&s->l2_cache);
+ qemu_vfree(s->l1_table);
+ }
+ return ret;
+}
+
+/* We have nothing to do for QED reopen, stubs just return
+ * success */
+static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
+ BlockReopenQueue *queue, Error **errp)
+{
+ return 0;
+}
+
+static void bdrv_qed_close(BlockDriverState *bs)
+{
+ BDRVQEDState *s = bs->opaque;
+
+ qed_cancel_need_check_timer(s);
+ qemu_free_timer(s->need_check_timer);
+
+ /* Ensure writes reach stable storage */
+ bdrv_flush(bs->file);
+
+ /* Clean shutdown, no check required on next open */
+ if (s->header.features & QED_F_NEED_CHECK) {
+ s->header.features &= ~QED_F_NEED_CHECK;
+ qed_write_header_sync(s);
+ }
+
+ qed_free_l2_cache(&s->l2_cache);
+ qemu_vfree(s->l1_table);
+}
+
+static int qed_create(const char *filename, uint32_t cluster_size,
+ uint64_t image_size, uint32_t table_size,
+ const char *backing_file, const char *backing_fmt)
+{
+ QEDHeader header = {
+ .magic = QED_MAGIC,
+ .cluster_size = cluster_size,
+ .table_size = table_size,
+ .header_size = 1,
+ .features = 0,
+ .compat_features = 0,
+ .l1_table_offset = cluster_size,
+ .image_size = image_size,
+ };
+ QEDHeader le_header;
+ uint8_t *l1_table = NULL;
+ size_t l1_size = header.cluster_size * header.table_size;
+ int ret = 0;
+ BlockDriverState *bs = NULL;
+
+ ret = bdrv_create_file(filename, NULL);
+ if (ret < 0) {
+ return ret;
+ }
+
+ ret = bdrv_file_open(&bs, filename, NULL, BDRV_O_RDWR | BDRV_O_CACHE_WB);
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* File must start empty and grow, check truncate is supported */
+ ret = bdrv_truncate(bs, 0);
+ if (ret < 0) {
+ goto out;
+ }
+
+ if (backing_file) {
+ header.features |= QED_F_BACKING_FILE;
+ header.backing_filename_offset = sizeof(le_header);
+ header.backing_filename_size = strlen(backing_file);
+
+ if (qed_fmt_is_raw(backing_fmt)) {
+ header.features |= QED_F_BACKING_FORMAT_NO_PROBE;
+ }
+ }
+
+ qed_header_cpu_to_le(&header, &le_header);
+ ret = bdrv_pwrite(bs, 0, &le_header, sizeof(le_header));
+ if (ret < 0) {
+ goto out;
+ }
+ ret = bdrv_pwrite(bs, sizeof(le_header), backing_file,
+ header.backing_filename_size);
+ if (ret < 0) {
+ goto out;
+ }
+
+ l1_table = g_malloc0(l1_size);
+ ret = bdrv_pwrite(bs, header.l1_table_offset, l1_table, l1_size);
+ if (ret < 0) {
+ goto out;
+ }
+
+ ret = 0; /* success */
+out:
+ g_free(l1_table);
+ bdrv_delete(bs);
+ return ret;
+}
+
+static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options)
+{
+ uint64_t image_size = 0;
+ uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE;
+ uint32_t table_size = QED_DEFAULT_TABLE_SIZE;
+ const char *backing_file = NULL;
+ const char *backing_fmt = NULL;
+
+ while (options && options->name) {
+ if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+ image_size = options->value.n;
+ } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+ backing_file = options->value.s;
+ } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) {
+ backing_fmt = options->value.s;
+ } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
+ if (options->value.n) {
+ cluster_size = options->value.n;
+ }
+ } else if (!strcmp(options->name, BLOCK_OPT_TABLE_SIZE)) {
+ if (options->value.n) {
+ table_size = options->value.n;
+ }
+ }
+ options++;
+ }
+
+ if (!qed_is_cluster_size_valid(cluster_size)) {
+ fprintf(stderr, "QED cluster size must be within range [%u, %u] and power of 2\n",
+ QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
+ return -EINVAL;
+ }
+ if (!qed_is_table_size_valid(table_size)) {
+ fprintf(stderr, "QED table size must be within range [%u, %u] and power of 2\n",
+ QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
+ return -EINVAL;
+ }
+ if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) {
+ fprintf(stderr, "QED image size must be a non-zero multiple of "
+ "cluster size and less than %" PRIu64 " bytes\n",
+ qed_max_image_size(cluster_size, table_size));
+ return -EINVAL;
+ }
+
+ return qed_create(filename, cluster_size, image_size, table_size,
+ backing_file, backing_fmt);
+}
+
+typedef struct {
+ Coroutine *co;
+ int is_allocated;
+ int *pnum;
+} QEDIsAllocatedCB;
+
+static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t len)
+{
+ QEDIsAllocatedCB *cb = opaque;
+ *cb->pnum = len / BDRV_SECTOR_SIZE;
+ cb->is_allocated = (ret == QED_CLUSTER_FOUND || ret == QED_CLUSTER_ZERO);
+ if (cb->co) {
+ qemu_coroutine_enter(cb->co, NULL);
+ }
+}
+
+static int coroutine_fn bdrv_qed_co_is_allocated(BlockDriverState *bs,
+ int64_t sector_num,
+ int nb_sectors, int *pnum)
+{
+ BDRVQEDState *s = bs->opaque;
+ uint64_t pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
+ size_t len = (size_t)nb_sectors * BDRV_SECTOR_SIZE;
+ QEDIsAllocatedCB cb = {
+ .is_allocated = -1,
+ .pnum = pnum,
+ };
+ QEDRequest request = { .l2_table = NULL };
+
+ qed_find_cluster(s, &request, pos, len, qed_is_allocated_cb, &cb);
+
+ /* Now sleep if the callback wasn't invoked immediately */
+ while (cb.is_allocated == -1) {
+ cb.co = qemu_coroutine_self();
+ qemu_coroutine_yield();
+ }
+
+ qed_unref_l2_cache_entry(request.l2_table);
+
+ return cb.is_allocated;
+}
+
+static int bdrv_qed_make_empty(BlockDriverState *bs)
+{
+ return -ENOTSUP;
+}
+
+static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
+{
+ return acb->common.bs->opaque;
+}
+
+/**
+ * Read from the backing file or zero-fill if no backing file
+ *
+ * @s: QED state
+ * @pos: Byte position in device
+ * @qiov: Destination I/O vector
+ * @cb: Completion function
+ * @opaque: User data for completion function
+ *
+ * This function reads qiov->size bytes starting at pos from the backing file.
+ * If there is no backing file then zeroes are read.
+ */
+static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
+ QEMUIOVector *qiov,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ uint64_t backing_length = 0;
+ size_t size;
+
+ /* If there is a backing file, get its length. Treat the absence of a
+ * backing file like a zero length backing file.
+ */
+ if (s->bs->backing_hd) {
+ int64_t l = bdrv_getlength(s->bs->backing_hd);
+ if (l < 0) {
+ cb(opaque, l);
+ return;
+ }
+ backing_length = l;
+ }
+
+ /* Zero all sectors if reading beyond the end of the backing file */
+ if (pos >= backing_length ||
+ pos + qiov->size > backing_length) {
+ qemu_iovec_memset(qiov, 0, 0, qiov->size);
+ }
+
+ /* Complete now if there are no backing file sectors to read */
+ if (pos >= backing_length) {
+ cb(opaque, 0);
+ return;
+ }
+
+ /* If the read straddles the end of the backing file, shorten it */
+ size = MIN((uint64_t)backing_length - pos, qiov->size);
+
+ BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
+ bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
+ qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
+}
+
+typedef struct {
+ GenericCB gencb;
+ BDRVQEDState *s;
+ QEMUIOVector qiov;
+ struct iovec iov;
+ uint64_t offset;
+} CopyFromBackingFileCB;
+
+static void qed_copy_from_backing_file_cb(void *opaque, int ret)
+{
+ CopyFromBackingFileCB *copy_cb = opaque;
+ qemu_vfree(copy_cb->iov.iov_base);
+ gencb_complete(&copy_cb->gencb, ret);
+}
+
+static void qed_copy_from_backing_file_write(void *opaque, int ret)
+{
+ CopyFromBackingFileCB *copy_cb = opaque;
+ BDRVQEDState *s = copy_cb->s;
+
+ if (ret) {
+ qed_copy_from_backing_file_cb(copy_cb, ret);
+ return;
+ }
+
+ BLKDBG_EVENT(s->bs->file, BLKDBG_COW_WRITE);
+ bdrv_aio_writev(s->bs->file, copy_cb->offset / BDRV_SECTOR_SIZE,
+ &copy_cb->qiov, copy_cb->qiov.size / BDRV_SECTOR_SIZE,
+ qed_copy_from_backing_file_cb, copy_cb);
+}
+
+/**
+ * Copy data from backing file into the image
+ *
+ * @s: QED state
+ * @pos: Byte position in device
+ * @len: Number of bytes
+ * @offset: Byte offset in image file
+ * @cb: Completion function
+ * @opaque: User data for completion function
+ */
+static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos,
+ uint64_t len, uint64_t offset,
+ BlockDriverCompletionFunc *cb,
+ void *opaque)
+{
+ CopyFromBackingFileCB *copy_cb;
+
+ /* Skip copy entirely if there is no work to do */
+ if (len == 0) {
+ cb(opaque, 0);
+ return;
+ }
+
+ copy_cb = gencb_alloc(sizeof(*copy_cb), cb, opaque);
+ copy_cb->s = s;
+ copy_cb->offset = offset;
+ copy_cb->iov.iov_base = qemu_blockalign(s->bs, len);
+ copy_cb->iov.iov_len = len;
+ qemu_iovec_init_external(&copy_cb->qiov, &copy_cb->iov, 1);
+
+ qed_read_backing_file(s, pos, &copy_cb->qiov,
+ qed_copy_from_backing_file_write, copy_cb);
+}
+
+/**
+ * Link one or more contiguous clusters into a table
+ *
+ * @s: QED state
+ * @table: L2 table
+ * @index: First cluster index
+ * @n: Number of contiguous clusters
+ * @cluster: First cluster offset
+ *
+ * The cluster offset may be an allocated byte offset in the image file, the
+ * zero cluster marker, or the unallocated cluster marker.
+ */
+static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index,
+ unsigned int n, uint64_t cluster)
+{
+ int i;
+ for (i = index; i < index + n; i++) {
+ table->offsets[i] = cluster;
+ if (!qed_offset_is_unalloc_cluster(cluster) &&
+ !qed_offset_is_zero_cluster(cluster)) {
+ cluster += s->header.cluster_size;
+ }
+ }
+}
+
+static void qed_aio_complete_bh(void *opaque)
+{
+ QEDAIOCB *acb = opaque;
+ BlockDriverCompletionFunc *cb = acb->common.cb;
+ void *user_opaque = acb->common.opaque;
+ int ret = acb->bh_ret;
+ bool *finished = acb->finished;
+
+ qemu_bh_delete(acb->bh);
+ qemu_aio_release(acb);
+
+ /* Invoke callback */
+ cb(user_opaque, ret);
+
+ /* Signal cancel completion */
+ if (finished) {
+ *finished = true;
+ }
+}
+
+static void qed_aio_complete(QEDAIOCB *acb, int ret)
+{
+ BDRVQEDState *s = acb_to_s(acb);
+
+ trace_qed_aio_complete(s, acb, ret);
+
+ /* Free resources */
+ qemu_iovec_destroy(&acb->cur_qiov);
+ qed_unref_l2_cache_entry(acb->request.l2_table);
+
+ /* Free the buffer we may have allocated for zero writes */
+ if (acb->flags & QED_AIOCB_ZERO) {
+ qemu_vfree(acb->qiov->iov[0].iov_base);
+ acb->qiov->iov[0].iov_base = NULL;
+ }
+
+ /* Arrange for a bh to invoke the completion function */
+ acb->bh_ret = ret;
+ acb->bh = qemu_bh_new(qed_aio_complete_bh, acb);
+ qemu_bh_schedule(acb->bh);
+
+ /* Start next allocating write request waiting behind this one. Note that
+ * requests enqueue themselves when they first hit an unallocated cluster
+ * but they wait until the entire request is finished before waking up the
+ * next request in the queue. This ensures that we don't cycle through
+ * requests multiple times but rather finish one at a time completely.
+ */
+ if (acb == QSIMPLEQ_FIRST(&s->allocating_write_reqs)) {
+ QSIMPLEQ_REMOVE_HEAD(&s->allocating_write_reqs, next);
+ acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
+ if (acb) {
+ qed_aio_next_io(acb, 0);
+ } else if (s->header.features & QED_F_NEED_CHECK) {
+ qed_start_need_check_timer(s);
+ }
+ }
+}
+
+/**
+ * Commit the current L2 table to the cache
+ */
+static void qed_commit_l2_update(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ CachedL2Table *l2_table = acb->request.l2_table;
+ uint64_t l2_offset = l2_table->offset;
+
+ qed_commit_l2_cache_entry(&s->l2_cache, l2_table);
+
+ /* This is guaranteed to succeed because we just committed the entry to the
+ * cache.
+ */
+ acb->request.l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset);
+ assert(acb->request.l2_table != NULL);
+
+ qed_aio_next_io(opaque, ret);
+}
+
+/**
+ * Update L1 table with new L2 table offset and write it out
+ */
+static void qed_aio_write_l1_update(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ int index;
+
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ index = qed_l1_index(s, acb->cur_pos);
+ s->l1_table->offsets[index] = acb->request.l2_table->offset;
+
+ qed_write_l1_table(s, index, 1, qed_commit_l2_update, acb);
+}
+
+/**
+ * Update L2 table with new cluster offsets and write them out
+ */
+static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset)
+{
+ BDRVQEDState *s = acb_to_s(acb);
+ bool need_alloc = acb->find_cluster_ret == QED_CLUSTER_L1;
+ int index;
+
+ if (ret) {
+ goto err;
+ }
+
+ if (need_alloc) {
+ qed_unref_l2_cache_entry(acb->request.l2_table);
+ acb->request.l2_table = qed_new_l2_table(s);
+ }
+
+ index = qed_l2_index(s, acb->cur_pos);
+ qed_update_l2_table(s, acb->request.l2_table->table, index, acb->cur_nclusters,
+ offset);
+
+ if (need_alloc) {
+ /* Write out the whole new L2 table */
+ qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true,
+ qed_aio_write_l1_update, acb);
+ } else {
+ /* Write out only the updated part of the L2 table */
+ qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, false,
+ qed_aio_next_io, acb);
+ }
+ return;
+
+err:
+ qed_aio_complete(acb, ret);
+}
+
+static void qed_aio_write_l2_update_cb(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ qed_aio_write_l2_update(acb, ret, acb->cur_cluster);
+}
+
+/**
+ * Flush new data clusters before updating the L2 table
+ *
+ * This flush is necessary when a backing file is in use. A crash during an
+ * allocating write could result in empty clusters in the image. If the write
+ * only touched a subregion of the cluster, then backing image sectors have
+ * been lost in the untouched region. The solution is to flush after writing a
+ * new data cluster and before updating the L2 table.
+ */
+static void qed_aio_write_flush_before_l2_update(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+
+ if (!bdrv_aio_flush(s->bs->file, qed_aio_write_l2_update_cb, opaque)) {
+ qed_aio_complete(acb, -EIO);
+ }
+}
+
+/**
+ * Write data to the image file
+ */
+static void qed_aio_write_main(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ uint64_t offset = acb->cur_cluster +
+ qed_offset_into_cluster(s, acb->cur_pos);
+ BlockDriverCompletionFunc *next_fn;
+
+ trace_qed_aio_write_main(s, acb, ret, offset, acb->cur_qiov.size);
+
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ if (acb->find_cluster_ret == QED_CLUSTER_FOUND) {
+ next_fn = qed_aio_next_io;
+ } else {
+ if (s->bs->backing_hd) {
+ next_fn = qed_aio_write_flush_before_l2_update;
+ } else {
+ next_fn = qed_aio_write_l2_update_cb;
+ }
+ }
+
+ BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO);
+ bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE,
+ &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE,
+ next_fn, acb);
+}
+
+/**
+ * Populate back untouched region of new data cluster
+ */
+static void qed_aio_write_postfill(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ uint64_t start = acb->cur_pos + acb->cur_qiov.size;
+ uint64_t len =
+ qed_start_of_cluster(s, start + s->header.cluster_size - 1) - start;
+ uint64_t offset = acb->cur_cluster +
+ qed_offset_into_cluster(s, acb->cur_pos) +
+ acb->cur_qiov.size;
+
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ trace_qed_aio_write_postfill(s, acb, start, len, offset);
+ qed_copy_from_backing_file(s, start, len, offset,
+ qed_aio_write_main, acb);
+}
+
+/**
+ * Populate front untouched region of new data cluster
+ */
+static void qed_aio_write_prefill(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ uint64_t start = qed_start_of_cluster(s, acb->cur_pos);
+ uint64_t len = qed_offset_into_cluster(s, acb->cur_pos);
+
+ trace_qed_aio_write_prefill(s, acb, start, len, acb->cur_cluster);
+ qed_copy_from_backing_file(s, start, len, acb->cur_cluster,
+ qed_aio_write_postfill, acb);
+}
+
+/**
+ * Check if the QED_F_NEED_CHECK bit should be set during allocating write
+ */
+static bool qed_should_set_need_check(BDRVQEDState *s)
+{
+ /* The flush before L2 update path ensures consistency */
+ if (s->bs->backing_hd) {
+ return false;
+ }
+
+ return !(s->header.features & QED_F_NEED_CHECK);
+}
+
+static void qed_aio_write_zero_cluster(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ qed_aio_write_l2_update(acb, 0, 1);
+}
+
+/**
+ * Write new data cluster
+ *
+ * @acb: Write request
+ * @len: Length in bytes
+ *
+ * This path is taken when writing to previously unallocated clusters.
+ */
+static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
+{
+ BDRVQEDState *s = acb_to_s(acb);
+ BlockDriverCompletionFunc *cb;
+
+ /* Cancel timer when the first allocating request comes in */
+ if (QSIMPLEQ_EMPTY(&s->allocating_write_reqs)) {
+ qed_cancel_need_check_timer(s);
+ }
+
+ /* Freeze this request if another allocating write is in progress */
+ if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs)) {
+ QSIMPLEQ_INSERT_TAIL(&s->allocating_write_reqs, acb, next);
+ }
+ if (acb != QSIMPLEQ_FIRST(&s->allocating_write_reqs) ||
+ s->allocating_write_reqs_plugged) {
+ return; /* wait for existing request to finish */
+ }
+
+ acb->cur_nclusters = qed_bytes_to_clusters(s,
+ qed_offset_into_cluster(s, acb->cur_pos) + len);
+ qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+
+ if (acb->flags & QED_AIOCB_ZERO) {
+ /* Skip ahead if the clusters are already zero */
+ if (acb->find_cluster_ret == QED_CLUSTER_ZERO) {
+ qed_aio_next_io(acb, 0);
+ return;
+ }
+
+ cb = qed_aio_write_zero_cluster;
+ } else {
+ cb = qed_aio_write_prefill;
+ acb->cur_cluster = qed_alloc_clusters(s, acb->cur_nclusters);
+ }
+
+ if (qed_should_set_need_check(s)) {
+ s->header.features |= QED_F_NEED_CHECK;
+ qed_write_header(s, cb, acb);
+ } else {
+ cb(acb, 0);
+ }
+}
+
+/**
+ * Write data cluster in place
+ *
+ * @acb: Write request
+ * @offset: Cluster offset in bytes
+ * @len: Length in bytes
+ *
+ * This path is taken when writing to already allocated clusters.
+ */
+static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len)
+{
+ /* Allocate buffer for zero writes */
+ if (acb->flags & QED_AIOCB_ZERO) {
+ struct iovec *iov = acb->qiov->iov;
+
+ if (!iov->iov_base) {
+ iov->iov_base = qemu_blockalign(acb->common.bs, iov->iov_len);
+ memset(iov->iov_base, 0, iov->iov_len);
+ }
+ }
+
+ /* Calculate the I/O vector */
+ acb->cur_cluster = offset;
+ qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+
+ /* Do the actual write */
+ qed_aio_write_main(acb, 0);
+}
+
+/**
+ * Write data cluster
+ *
+ * @opaque: Write request
+ * @ret: QED_CLUSTER_FOUND, QED_CLUSTER_L2, QED_CLUSTER_L1,
+ * or -errno
+ * @offset: Cluster offset in bytes
+ * @len: Length in bytes
+ *
+ * Callback from qed_find_cluster().
+ */
+static void qed_aio_write_data(void *opaque, int ret,
+ uint64_t offset, size_t len)
+{
+ QEDAIOCB *acb = opaque;
+
+ trace_qed_aio_write_data(acb_to_s(acb), acb, ret, offset, len);
+
+ acb->find_cluster_ret = ret;
+
+ switch (ret) {
+ case QED_CLUSTER_FOUND:
+ qed_aio_write_inplace(acb, offset, len);
+ break;
+
+ case QED_CLUSTER_L2:
+ case QED_CLUSTER_L1:
+ case QED_CLUSTER_ZERO:
+ qed_aio_write_alloc(acb, len);
+ break;
+
+ default:
+ qed_aio_complete(acb, ret);
+ break;
+ }
+}
+
+/**
+ * Read data cluster
+ *
+ * @opaque: Read request
+ * @ret: QED_CLUSTER_FOUND, QED_CLUSTER_L2, QED_CLUSTER_L1,
+ * or -errno
+ * @offset: Cluster offset in bytes
+ * @len: Length in bytes
+ *
+ * Callback from qed_find_cluster().
+ */
+static void qed_aio_read_data(void *opaque, int ret,
+ uint64_t offset, size_t len)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ BlockDriverState *bs = acb->common.bs;
+
+ /* Adjust offset into cluster */
+ offset += qed_offset_into_cluster(s, acb->cur_pos);
+
+ trace_qed_aio_read_data(s, acb, ret, offset, len);
+
+ if (ret < 0) {
+ goto err;
+ }
+
+ qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+
+ /* Handle zero cluster and backing file reads */
+ if (ret == QED_CLUSTER_ZERO) {
+ qemu_iovec_memset(&acb->cur_qiov, 0, 0, acb->cur_qiov.size);
+ qed_aio_next_io(acb, 0);
+ return;
+ } else if (ret != QED_CLUSTER_FOUND) {
+ qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov,
+ qed_aio_next_io, acb);
+ return;
+ }
+
+ BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
+ bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE,
+ &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE,
+ qed_aio_next_io, acb);
+ return;
+
+err:
+ qed_aio_complete(acb, ret);
+}
+
+/**
+ * Begin next I/O or complete the request
+ */
+static void qed_aio_next_io(void *opaque, int ret)
+{
+ QEDAIOCB *acb = opaque;
+ BDRVQEDState *s = acb_to_s(acb);
+ QEDFindClusterFunc *io_fn = (acb->flags & QED_AIOCB_WRITE) ?
+ qed_aio_write_data : qed_aio_read_data;
+
+ trace_qed_aio_next_io(s, acb, ret, acb->cur_pos + acb->cur_qiov.size);
+
+ /* Handle I/O error */
+ if (ret) {
+ qed_aio_complete(acb, ret);
+ return;
+ }
+
+ acb->qiov_offset += acb->cur_qiov.size;
+ acb->cur_pos += acb->cur_qiov.size;
+ qemu_iovec_reset(&acb->cur_qiov);
+
+ /* Complete request */
+ if (acb->cur_pos >= acb->end_pos) {
+ qed_aio_complete(acb, 0);
+ return;
+ }
+
+ /* Find next cluster and start I/O */
+ qed_find_cluster(s, &acb->request,
+ acb->cur_pos, acb->end_pos - acb->cur_pos,
+ io_fn, acb);
+}
+
+static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque, int flags)
+{
+ QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, cb, opaque);
+
+ trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors,
+ opaque, flags);
+
+ acb->flags = flags;
+ acb->finished = NULL;
+ acb->qiov = qiov;
+ acb->qiov_offset = 0;
+ acb->cur_pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
+ acb->end_pos = acb->cur_pos + nb_sectors * BDRV_SECTOR_SIZE;
+ acb->request.l2_table = NULL;
+ qemu_iovec_init(&acb->cur_qiov, qiov->niov);
+
+ /* Start request */
+ qed_aio_next_io(acb, 0);
+ return &acb->common;
+}
+
+static BlockDriverAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque)
+{
+ return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
+}
+
+static BlockDriverAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs,
+ int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb,
+ void *opaque)
+{
+ return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb,
+ opaque, QED_AIOCB_WRITE);
+}
+
+typedef struct {
+ Coroutine *co;
+ int ret;
+ bool done;
+} QEDWriteZeroesCB;
+
+static void coroutine_fn qed_co_write_zeroes_cb(void *opaque, int ret)
+{
+ QEDWriteZeroesCB *cb = opaque;
+
+ cb->done = true;
+ cb->ret = ret;
+ if (cb->co) {
+ qemu_coroutine_enter(cb->co, NULL);
+ }
+}
+
+static int coroutine_fn bdrv_qed_co_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num,
+ int nb_sectors)
+{
+ BlockDriverAIOCB *blockacb;
+ BDRVQEDState *s = bs->opaque;
+ QEDWriteZeroesCB cb = { .done = false };
+ QEMUIOVector qiov;
+ struct iovec iov;
+
+ /* Refuse if there are untouched backing file sectors */
+ if (bs->backing_hd) {
+ if (qed_offset_into_cluster(s, sector_num * BDRV_SECTOR_SIZE) != 0) {
+ return -ENOTSUP;
+ }
+ if (qed_offset_into_cluster(s, nb_sectors * BDRV_SECTOR_SIZE) != 0) {
+ return -ENOTSUP;
+ }
+ }
+
+ /* Zero writes start without an I/O buffer. If a buffer becomes necessary
+ * then it will be allocated during request processing.
+ */
+ iov.iov_base = NULL,
+ iov.iov_len = nb_sectors * BDRV_SECTOR_SIZE,
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ blockacb = qed_aio_setup(bs, sector_num, &qiov, nb_sectors,
+ qed_co_write_zeroes_cb, &cb,
+ QED_AIOCB_WRITE | QED_AIOCB_ZERO);
+ if (!blockacb) {
+ return -EIO;
+ }
+ if (!cb.done) {
+ cb.co = qemu_coroutine_self();
+ qemu_coroutine_yield();
+ }
+ assert(cb.done);
+ return cb.ret;
+}
+
+static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset)
+{
+ BDRVQEDState *s = bs->opaque;
+ uint64_t old_image_size;
+ int ret;
+
+ if (!qed_is_image_size_valid(offset, s->header.cluster_size,
+ s->header.table_size)) {
+ return -EINVAL;
+ }
+
+ /* Shrinking is currently not supported */
+ if ((uint64_t)offset < s->header.image_size) {
+ return -ENOTSUP;
+ }
+
+ old_image_size = s->header.image_size;
+ s->header.image_size = offset;
+ ret = qed_write_header_sync(s);
+ if (ret < 0) {
+ s->header.image_size = old_image_size;
+ }
+ return ret;
+}
+
+static int64_t bdrv_qed_getlength(BlockDriverState *bs)
+{
+ BDRVQEDState *s = bs->opaque;
+ return s->header.image_size;
+}
+
+static int bdrv_qed_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
+{
+ BDRVQEDState *s = bs->opaque;
+
+ memset(bdi, 0, sizeof(*bdi));
+ bdi->cluster_size = s->header.cluster_size;
+ bdi->is_dirty = s->header.features & QED_F_NEED_CHECK;
+ return 0;
+}
+
+static int bdrv_qed_change_backing_file(BlockDriverState *bs,
+ const char *backing_file,
+ const char *backing_fmt)
+{
+ BDRVQEDState *s = bs->opaque;
+ QEDHeader new_header, le_header;
+ void *buffer;
+ size_t buffer_len, backing_file_len;
+ int ret;
+
+ /* Refuse to set backing filename if unknown compat feature bits are
+ * active. If the image uses an unknown compat feature then we may not
+ * know the layout of data following the header structure and cannot safely
+ * add a new string.
+ */
+ if (backing_file && (s->header.compat_features &
+ ~QED_COMPAT_FEATURE_MASK)) {
+ return -ENOTSUP;
+ }
+
+ memcpy(&new_header, &s->header, sizeof(new_header));
+
+ new_header.features &= ~(QED_F_BACKING_FILE |
+ QED_F_BACKING_FORMAT_NO_PROBE);
+
+ /* Adjust feature flags */
+ if (backing_file) {
+ new_header.features |= QED_F_BACKING_FILE;
+
+ if (qed_fmt_is_raw(backing_fmt)) {
+ new_header.features |= QED_F_BACKING_FORMAT_NO_PROBE;
+ }
+ }
+
+ /* Calculate new header size */
+ backing_file_len = 0;
+
+ if (backing_file) {
+ backing_file_len = strlen(backing_file);
+ }
+
+ buffer_len = sizeof(new_header);
+ new_header.backing_filename_offset = buffer_len;
+ new_header.backing_filename_size = backing_file_len;
+ buffer_len += backing_file_len;
+
+ /* Make sure we can rewrite header without failing */
+ if (buffer_len > new_header.header_size * new_header.cluster_size) {
+ return -ENOSPC;
+ }
+
+ /* Prepare new header */
+ buffer = g_malloc(buffer_len);
+
+ qed_header_cpu_to_le(&new_header, &le_header);
+ memcpy(buffer, &le_header, sizeof(le_header));
+ buffer_len = sizeof(le_header);
+
+ if (backing_file) {
+ memcpy(buffer + buffer_len, backing_file, backing_file_len);
+ buffer_len += backing_file_len;
+ }
+
+ /* Write new header */
+ ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len);
+ g_free(buffer);
+ if (ret == 0) {
+ memcpy(&s->header, &new_header, sizeof(new_header));
+ }
+ return ret;
+}
+
+static void bdrv_qed_invalidate_cache(BlockDriverState *bs)
+{
+ BDRVQEDState *s = bs->opaque;
+
+ bdrv_qed_close(bs);
+ memset(s, 0, sizeof(BDRVQEDState));
+ bdrv_qed_open(bs, NULL, bs->open_flags);
+}
+
+static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
+ BdrvCheckMode fix)
+{
+ BDRVQEDState *s = bs->opaque;
+
+ return qed_check(s, result, !!fix);
+}
+
+static QEMUOptionParameter qed_create_options[] = {
+ {
+ .name = BLOCK_OPT_SIZE,
+ .type = OPT_SIZE,
+ .help = "Virtual disk size (in bytes)"
+ }, {
+ .name = BLOCK_OPT_BACKING_FILE,
+ .type = OPT_STRING,
+ .help = "File name of a base image"
+ }, {
+ .name = BLOCK_OPT_BACKING_FMT,
+ .type = OPT_STRING,
+ .help = "Image format of the base image"
+ }, {
+ .name = BLOCK_OPT_CLUSTER_SIZE,
+ .type = OPT_SIZE,
+ .help = "Cluster size (in bytes)",
+ .value = { .n = QED_DEFAULT_CLUSTER_SIZE },
+ }, {
+ .name = BLOCK_OPT_TABLE_SIZE,
+ .type = OPT_SIZE,
+ .help = "L1/L2 table size (in clusters)"
+ },
+ { /* end of list */ }
+};
+
+static BlockDriver bdrv_qed = {
+ .format_name = "qed",
+ .instance_size = sizeof(BDRVQEDState),
+ .create_options = qed_create_options,
+
+ .bdrv_probe = bdrv_qed_probe,
+ .bdrv_rebind = bdrv_qed_rebind,
+ .bdrv_open = bdrv_qed_open,
+ .bdrv_close = bdrv_qed_close,
+ .bdrv_reopen_prepare = bdrv_qed_reopen_prepare,
+ .bdrv_create = bdrv_qed_create,
+ .bdrv_has_zero_init = bdrv_has_zero_init_1,
+ .bdrv_co_is_allocated = bdrv_qed_co_is_allocated,
+ .bdrv_make_empty = bdrv_qed_make_empty,
+ .bdrv_aio_readv = bdrv_qed_aio_readv,
+ .bdrv_aio_writev = bdrv_qed_aio_writev,
+ .bdrv_co_write_zeroes = bdrv_qed_co_write_zeroes,
+ .bdrv_truncate = bdrv_qed_truncate,
+ .bdrv_getlength = bdrv_qed_getlength,
+ .bdrv_get_info = bdrv_qed_get_info,
+ .bdrv_change_backing_file = bdrv_qed_change_backing_file,
+ .bdrv_invalidate_cache = bdrv_qed_invalidate_cache,
+ .bdrv_check = bdrv_qed_check,
+};
+
+static void bdrv_qed_init(void)
+{
+ bdrv_register(&bdrv_qed);
+}
+
+block_init(bdrv_qed_init);
diff --git a/contrib/qemu/block/qed.h b/contrib/qemu/block/qed.h
new file mode 100644
index 00000000000..2b4ddedf313
--- /dev/null
+++ b/contrib/qemu/block/qed.h
@@ -0,0 +1,344 @@
+/*
+ * QEMU Enhanced Disk Format
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef BLOCK_QED_H
+#define BLOCK_QED_H
+
+#include "block/block_int.h"
+
+/* The layout of a QED file is as follows:
+ *
+ * +--------+----------+----------+----------+-----+
+ * | header | L1 table | cluster0 | cluster1 | ... |
+ * +--------+----------+----------+----------+-----+
+ *
+ * There is a 2-level pagetable for cluster allocation:
+ *
+ * +----------+
+ * | L1 table |
+ * +----------+
+ * ,------' | '------.
+ * +----------+ | +----------+
+ * | L2 table | ... | L2 table |
+ * +----------+ +----------+
+ * ,------' | '------.
+ * +----------+ | +----------+
+ * | Data | ... | Data |
+ * +----------+ +----------+
+ *
+ * The L1 table is fixed size and always present. L2 tables are allocated on
+ * demand. The L1 table size determines the maximum possible image size; it
+ * can be influenced using the cluster_size and table_size values.
+ *
+ * All fields are little-endian on disk.
+ */
+
+enum {
+ QED_MAGIC = 'Q' | 'E' << 8 | 'D' << 16 | '\0' << 24,
+
+ /* The image supports a backing file */
+ QED_F_BACKING_FILE = 0x01,
+
+ /* The image needs a consistency check before use */
+ QED_F_NEED_CHECK = 0x02,
+
+ /* The backing file format must not be probed, treat as raw image */
+ QED_F_BACKING_FORMAT_NO_PROBE = 0x04,
+
+ /* Feature bits must be used when the on-disk format changes */
+ QED_FEATURE_MASK = QED_F_BACKING_FILE | /* supported feature bits */
+ QED_F_NEED_CHECK |
+ QED_F_BACKING_FORMAT_NO_PROBE,
+ QED_COMPAT_FEATURE_MASK = 0, /* supported compat feature bits */
+ QED_AUTOCLEAR_FEATURE_MASK = 0, /* supported autoclear feature bits */
+
+ /* Data is stored in groups of sectors called clusters. Cluster size must
+ * be large to avoid keeping too much metadata. I/O requests that have
+ * sub-cluster size will require read-modify-write.
+ */
+ QED_MIN_CLUSTER_SIZE = 4 * 1024, /* in bytes */
+ QED_MAX_CLUSTER_SIZE = 64 * 1024 * 1024,
+ QED_DEFAULT_CLUSTER_SIZE = 64 * 1024,
+
+ /* Allocated clusters are tracked using a 2-level pagetable. Table size is
+ * a multiple of clusters so large maximum image sizes can be supported
+ * without jacking up the cluster size too much.
+ */
+ QED_MIN_TABLE_SIZE = 1, /* in clusters */
+ QED_MAX_TABLE_SIZE = 16,
+ QED_DEFAULT_TABLE_SIZE = 4,
+
+ /* Delay to flush and clean image after last allocating write completes */
+ QED_NEED_CHECK_TIMEOUT = 5, /* in seconds */
+};
+
+typedef struct {
+ uint32_t magic; /* QED\0 */
+
+ uint32_t cluster_size; /* in bytes */
+ uint32_t table_size; /* for L1 and L2 tables, in clusters */
+ uint32_t header_size; /* in clusters */
+
+ uint64_t features; /* format feature bits */
+ uint64_t compat_features; /* compatible feature bits */
+ uint64_t autoclear_features; /* self-resetting feature bits */
+
+ uint64_t l1_table_offset; /* in bytes */
+ uint64_t image_size; /* total logical image size, in bytes */
+
+ /* if (features & QED_F_BACKING_FILE) */
+ uint32_t backing_filename_offset; /* in bytes from start of header */
+ uint32_t backing_filename_size; /* in bytes */
+} QEDHeader;
+
+typedef struct {
+ uint64_t offsets[0]; /* in bytes */
+} QEDTable;
+
+/* The L2 cache is a simple write-through cache for L2 structures */
+typedef struct CachedL2Table {
+ QEDTable *table;
+ uint64_t offset; /* offset=0 indicates an invalidate entry */
+ QTAILQ_ENTRY(CachedL2Table) node;
+ int ref;
+} CachedL2Table;
+
+typedef struct {
+ QTAILQ_HEAD(, CachedL2Table) entries;
+ unsigned int n_entries;
+} L2TableCache;
+
+typedef struct QEDRequest {
+ CachedL2Table *l2_table;
+} QEDRequest;
+
+enum {
+ QED_AIOCB_WRITE = 0x0001, /* read or write? */
+ QED_AIOCB_ZERO = 0x0002, /* zero write, used with QED_AIOCB_WRITE */
+};
+
+typedef struct QEDAIOCB {
+ BlockDriverAIOCB common;
+ QEMUBH *bh;
+ int bh_ret; /* final return status for completion bh */
+ QSIMPLEQ_ENTRY(QEDAIOCB) next; /* next request */
+ int flags; /* QED_AIOCB_* bits ORed together */
+ bool *finished; /* signal for cancel completion */
+ uint64_t end_pos; /* request end on block device, in bytes */
+
+ /* User scatter-gather list */
+ QEMUIOVector *qiov;
+ size_t qiov_offset; /* byte count already processed */
+
+ /* Current cluster scatter-gather list */
+ QEMUIOVector cur_qiov;
+ uint64_t cur_pos; /* position on block device, in bytes */
+ uint64_t cur_cluster; /* cluster offset in image file */
+ unsigned int cur_nclusters; /* number of clusters being accessed */
+ int find_cluster_ret; /* used for L1/L2 update */
+
+ QEDRequest request;
+} QEDAIOCB;
+
+typedef struct {
+ BlockDriverState *bs; /* device */
+ uint64_t file_size; /* length of image file, in bytes */
+
+ QEDHeader header; /* always cpu-endian */
+ QEDTable *l1_table;
+ L2TableCache l2_cache; /* l2 table cache */
+ uint32_t table_nelems;
+ uint32_t l1_shift;
+ uint32_t l2_shift;
+ uint32_t l2_mask;
+
+ /* Allocating write request queue */
+ QSIMPLEQ_HEAD(, QEDAIOCB) allocating_write_reqs;
+ bool allocating_write_reqs_plugged;
+
+ /* Periodic flush and clear need check flag */
+ QEMUTimer *need_check_timer;
+} BDRVQEDState;
+
+enum {
+ QED_CLUSTER_FOUND, /* cluster found */
+ QED_CLUSTER_ZERO, /* zero cluster found */
+ QED_CLUSTER_L2, /* cluster missing in L2 */
+ QED_CLUSTER_L1, /* cluster missing in L1 */
+};
+
+/**
+ * qed_find_cluster() completion callback
+ *
+ * @opaque: User data for completion callback
+ * @ret: QED_CLUSTER_FOUND Success
+ * QED_CLUSTER_L2 Data cluster unallocated in L2
+ * QED_CLUSTER_L1 L2 unallocated in L1
+ * -errno POSIX error occurred
+ * @offset: Data cluster offset
+ * @len: Contiguous bytes starting from cluster offset
+ *
+ * This function is invoked when qed_find_cluster() completes.
+ *
+ * On success ret is QED_CLUSTER_FOUND and offset/len are a contiguous range
+ * in the image file.
+ *
+ * On failure ret is QED_CLUSTER_L2 or QED_CLUSTER_L1 for missing L2 or L1
+ * table offset, respectively. len is number of contiguous unallocated bytes.
+ */
+typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t len);
+
+/**
+ * Generic callback for chaining async callbacks
+ */
+typedef struct {
+ BlockDriverCompletionFunc *cb;
+ void *opaque;
+} GenericCB;
+
+void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque);
+void gencb_complete(void *opaque, int ret);
+
+/**
+ * Header functions
+ */
+int qed_write_header_sync(BDRVQEDState *s);
+
+/**
+ * L2 cache functions
+ */
+void qed_init_l2_cache(L2TableCache *l2_cache);
+void qed_free_l2_cache(L2TableCache *l2_cache);
+CachedL2Table *qed_alloc_l2_cache_entry(L2TableCache *l2_cache);
+void qed_unref_l2_cache_entry(CachedL2Table *entry);
+CachedL2Table *qed_find_l2_cache_entry(L2TableCache *l2_cache, uint64_t offset);
+void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table);
+
+/**
+ * Table I/O functions
+ */
+int qed_read_l1_table_sync(BDRVQEDState *s);
+void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
+ BlockDriverCompletionFunc *cb, void *opaque);
+int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
+ unsigned int n);
+int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
+ uint64_t offset);
+void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
+ BlockDriverCompletionFunc *cb, void *opaque);
+void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
+ unsigned int index, unsigned int n, bool flush,
+ BlockDriverCompletionFunc *cb, void *opaque);
+int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
+ unsigned int index, unsigned int n, bool flush);
+
+/**
+ * Cluster functions
+ */
+void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
+ size_t len, QEDFindClusterFunc *cb, void *opaque);
+
+/**
+ * Consistency check
+ */
+int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix);
+
+QEDTable *qed_alloc_table(BDRVQEDState *s);
+
+/**
+ * Round down to the start of a cluster
+ */
+static inline uint64_t qed_start_of_cluster(BDRVQEDState *s, uint64_t offset)
+{
+ return offset & ~(uint64_t)(s->header.cluster_size - 1);
+}
+
+static inline uint64_t qed_offset_into_cluster(BDRVQEDState *s, uint64_t offset)
+{
+ return offset & (s->header.cluster_size - 1);
+}
+
+static inline uint64_t qed_bytes_to_clusters(BDRVQEDState *s, uint64_t bytes)
+{
+ return qed_start_of_cluster(s, bytes + (s->header.cluster_size - 1)) /
+ (s->header.cluster_size - 1);
+}
+
+static inline unsigned int qed_l1_index(BDRVQEDState *s, uint64_t pos)
+{
+ return pos >> s->l1_shift;
+}
+
+static inline unsigned int qed_l2_index(BDRVQEDState *s, uint64_t pos)
+{
+ return (pos >> s->l2_shift) & s->l2_mask;
+}
+
+/**
+ * Test if a cluster offset is valid
+ */
+static inline bool qed_check_cluster_offset(BDRVQEDState *s, uint64_t offset)
+{
+ uint64_t header_size = (uint64_t)s->header.header_size *
+ s->header.cluster_size;
+
+ if (offset & (s->header.cluster_size - 1)) {
+ return false;
+ }
+ return offset >= header_size && offset < s->file_size;
+}
+
+/**
+ * Test if a table offset is valid
+ */
+static inline bool qed_check_table_offset(BDRVQEDState *s, uint64_t offset)
+{
+ uint64_t end_offset = offset + (s->header.table_size - 1) *
+ s->header.cluster_size;
+
+ /* Overflow check */
+ if (end_offset <= offset) {
+ return false;
+ }
+
+ return qed_check_cluster_offset(s, offset) &&
+ qed_check_cluster_offset(s, end_offset);
+}
+
+static inline bool qed_offset_is_cluster_aligned(BDRVQEDState *s,
+ uint64_t offset)
+{
+ if (qed_offset_into_cluster(s, offset)) {
+ return false;
+ }
+ return true;
+}
+
+static inline bool qed_offset_is_unalloc_cluster(uint64_t offset)
+{
+ if (offset == 0) {
+ return true;
+ }
+ return false;
+}
+
+static inline bool qed_offset_is_zero_cluster(uint64_t offset)
+{
+ if (offset == 1) {
+ return true;
+ }
+ return false;
+}
+
+#endif /* BLOCK_QED_H */
diff --git a/contrib/qemu/block/snapshot.c b/contrib/qemu/block/snapshot.c
new file mode 100644
index 00000000000..6c6d9deea1f
--- /dev/null
+++ b/contrib/qemu/block/snapshot.c
@@ -0,0 +1,157 @@
+/*
+ * Block layer snapshot related functions
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "block/snapshot.h"
+#include "block/block_int.h"
+
+int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
+ const char *name)
+{
+ QEMUSnapshotInfo *sn_tab, *sn;
+ int nb_sns, i, ret;
+
+ ret = -ENOENT;
+ nb_sns = bdrv_snapshot_list(bs, &sn_tab);
+ if (nb_sns < 0) {
+ return ret;
+ }
+ for (i = 0; i < nb_sns; i++) {
+ sn = &sn_tab[i];
+ if (!strcmp(sn->id_str, name) || !strcmp(sn->name, name)) {
+ *sn_info = *sn;
+ ret = 0;
+ break;
+ }
+ }
+ g_free(sn_tab);
+ return ret;
+}
+
+int bdrv_can_snapshot(BlockDriverState *bs)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv || !bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) {
+ return 0;
+ }
+
+ if (!drv->bdrv_snapshot_create) {
+ if (bs->file != NULL) {
+ return bdrv_can_snapshot(bs->file);
+ }
+ return 0;
+ }
+
+ return 1;
+}
+
+int bdrv_snapshot_create(BlockDriverState *bs,
+ QEMUSnapshotInfo *sn_info)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (drv->bdrv_snapshot_create) {
+ return drv->bdrv_snapshot_create(bs, sn_info);
+ }
+ if (bs->file) {
+ return bdrv_snapshot_create(bs->file, sn_info);
+ }
+ return -ENOTSUP;
+}
+
+int bdrv_snapshot_goto(BlockDriverState *bs,
+ const char *snapshot_id)
+{
+ BlockDriver *drv = bs->drv;
+ int ret, open_ret;
+
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (drv->bdrv_snapshot_goto) {
+ return drv->bdrv_snapshot_goto(bs, snapshot_id);
+ }
+
+ if (bs->file) {
+ drv->bdrv_close(bs);
+ ret = bdrv_snapshot_goto(bs->file, snapshot_id);
+ open_ret = drv->bdrv_open(bs, NULL, bs->open_flags);
+ if (open_ret < 0) {
+ bdrv_delete(bs->file);
+ bs->drv = NULL;
+ return open_ret;
+ }
+ return ret;
+ }
+
+ return -ENOTSUP;
+}
+
+int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (drv->bdrv_snapshot_delete) {
+ return drv->bdrv_snapshot_delete(bs, snapshot_id);
+ }
+ if (bs->file) {
+ return bdrv_snapshot_delete(bs->file, snapshot_id);
+ }
+ return -ENOTSUP;
+}
+
+int bdrv_snapshot_list(BlockDriverState *bs,
+ QEMUSnapshotInfo **psn_info)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (drv->bdrv_snapshot_list) {
+ return drv->bdrv_snapshot_list(bs, psn_info);
+ }
+ if (bs->file) {
+ return bdrv_snapshot_list(bs->file, psn_info);
+ }
+ return -ENOTSUP;
+}
+
+int bdrv_snapshot_load_tmp(BlockDriverState *bs,
+ const char *snapshot_name)
+{
+ BlockDriver *drv = bs->drv;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+ if (!bs->read_only) {
+ return -EINVAL;
+ }
+ if (drv->bdrv_snapshot_load_tmp) {
+ return drv->bdrv_snapshot_load_tmp(bs, snapshot_name);
+ }
+ return -ENOTSUP;
+}
diff --git a/contrib/qemu/config-host.h b/contrib/qemu/config-host.h
new file mode 100644
index 00000000000..874b04053bc
--- /dev/null
+++ b/contrib/qemu/config-host.h
@@ -0,0 +1,74 @@
+/* Automatically generated by create_config - do not modify */
+#define CONFIG_QEMU_CONFDIR "/usr/local/etc/qemu"
+#define CONFIG_QEMU_DATADIR "/usr/local/share/qemu"
+#define CONFIG_QEMU_DOCDIR "/usr/local/share/doc/qemu"
+#define CONFIG_QEMU_LOCALSTATEDIR "/usr/local/var"
+#define CONFIG_QEMU_HELPERDIR "/usr/local/libexec"
+#define CONFIG_QEMU_LOCALEDIR "/usr/local/share/locale"
+#define HOST_X86_64 1
+#define CONFIG_QEMU_LDST_OPTIMIZATION 1
+#define CONFIG_POSIX 1
+#define CONFIG_LINUX 1
+#define CONFIG_SLIRP 1
+#define CONFIG_SMBD_COMMAND "/usr/sbin/smbd"
+#define CONFIG_AUDIO_DRIVERS \
+ &oss_audio_driver,\
+
+#define CONFIG_OSS 1
+#define CONFIG_BDRV_RW_WHITELIST\
+ NULL
+#define CONFIG_BDRV_RO_WHITELIST\
+ NULL
+#define CONFIG_VNC 1
+#define CONFIG_VNC_TLS 1
+#define CONFIG_VNC_SASL 1
+#define CONFIG_VNC_WS 1
+#define CONFIG_FNMATCH 1
+#define CONFIG_UUID 1
+#define CONFIG_XFS 1
+#define QEMU_VERSION "1.5.50"
+#define QEMU_PKGVERSION ""
+#define CONFIG_CURSES 1
+#define CONFIG_UTIMENSAT 1
+#define CONFIG_PIPE2 1
+#define CONFIG_ACCEPT4 1
+#define CONFIG_SPLICE 1
+#define CONFIG_EVENTFD 1
+#define CONFIG_FALLOCATE 1
+#define CONFIG_FALLOCATE_PUNCH_HOLE 1
+#define CONFIG_SYNC_FILE_RANGE 1
+#define CONFIG_FIEMAP 1
+#define CONFIG_DUP3 1
+#define CONFIG_EPOLL 1
+#define CONFIG_EPOLL_CREATE1 1
+#define CONFIG_EPOLL_PWAIT 1
+#define CONFIG_SENDFILE 1
+#define CONFIG_INOTIFY 1
+#define CONFIG_INOTIFY1 1
+#define CONFIG_BYTESWAP_H 1
+#define CONFIG_CURL 1
+#define CONFIG_LINUX_AIO 1
+#define CONFIG_ATTR 1
+#define CONFIG_VHOST_SCSI 1
+#define CONFIG_IOVEC 1
+#define CONFIG_PREADV 1
+#define CONFIG_FDT 1
+#define CONFIG_SIGNALFD 1
+#define CONFIG_FDATASYNC 1
+#define CONFIG_MADVISE 1
+#define CONFIG_POSIX_MADVISE 1
+#define CONFIG_SIGEV_THREAD_ID 1
+#define CONFIG_UNAME_RELEASE ""
+#define CONFIG_QOM_CAST_DEBUG 1
+#define CONFIG_COROUTINE_BACKEND ucontext
+#define CONFIG_OPEN_BY_HANDLE 1
+#define CONFIG_LINUX_MAGIC_H 1
+#define CONFIG_PRAGMA_DIAGNOSTIC_AVAILABLE 1
+#define CONFIG_VALGRIND_H 1
+#define CONFIG_HAS_ENVIRON 1
+#define CONFIG_CPUID_H 1
+#define CONFIG_INT128 1
+#define CONFIG_VIRTIO_BLK_DATA_PLANE $(CONFIG_VIRTIO)
+#define CONFIG_TRACE_NOP 1
+#define CONFIG_TRACE_FILE trace
+#define CONFIG_TRACE_DEFAULT 1
diff --git a/contrib/qemu/include/block/aio.h b/contrib/qemu/include/block/aio.h
new file mode 100644
index 00000000000..183679374fa
--- /dev/null
+++ b/contrib/qemu/include/block/aio.h
@@ -0,0 +1,247 @@
+/*
+ * QEMU aio implementation
+ *
+ * Copyright IBM, Corp. 2008
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_AIO_H
+#define QEMU_AIO_H
+
+#include "qemu-common.h"
+#include "qemu/queue.h"
+#include "qemu/event_notifier.h"
+
+typedef struct BlockDriverAIOCB BlockDriverAIOCB;
+typedef void BlockDriverCompletionFunc(void *opaque, int ret);
+
+typedef struct AIOCBInfo {
+ void (*cancel)(BlockDriverAIOCB *acb);
+ size_t aiocb_size;
+} AIOCBInfo;
+
+struct BlockDriverAIOCB {
+ const AIOCBInfo *aiocb_info;
+ BlockDriverState *bs;
+ BlockDriverCompletionFunc *cb;
+ void *opaque;
+};
+
+void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque);
+void qemu_aio_release(void *p);
+
+typedef struct AioHandler AioHandler;
+typedef void QEMUBHFunc(void *opaque);
+typedef void IOHandler(void *opaque);
+
+typedef struct AioContext {
+ GSource source;
+
+ /* The list of registered AIO handlers */
+ QLIST_HEAD(, AioHandler) aio_handlers;
+
+ /* This is a simple lock used to protect the aio_handlers list.
+ * Specifically, it's used to ensure that no callbacks are removed while
+ * we're walking and dispatching callbacks.
+ */
+ int walking_handlers;
+
+ /* Anchor of the list of Bottom Halves belonging to the context */
+ struct QEMUBH *first_bh;
+
+ /* A simple lock used to protect the first_bh list, and ensure that
+ * no callbacks are removed while we're walking and dispatching callbacks.
+ */
+ int walking_bh;
+
+ /* Used for aio_notify. */
+ EventNotifier notifier;
+
+ /* GPollFDs for aio_poll() */
+ GArray *pollfds;
+
+ /* Thread pool for performing work and receiving completion callbacks */
+ struct ThreadPool *thread_pool;
+} AioContext;
+
+/* Returns 1 if there are still outstanding AIO requests; 0 otherwise */
+typedef int (AioFlushEventNotifierHandler)(EventNotifier *e);
+
+/**
+ * aio_context_new: Allocate a new AioContext.
+ *
+ * AioContext provide a mini event-loop that can be waited on synchronously.
+ * They also provide bottom halves, a service to execute a piece of code
+ * as soon as possible.
+ */
+AioContext *aio_context_new(void);
+
+/**
+ * aio_context_ref:
+ * @ctx: The AioContext to operate on.
+ *
+ * Add a reference to an AioContext.
+ */
+void aio_context_ref(AioContext *ctx);
+
+/**
+ * aio_context_unref:
+ * @ctx: The AioContext to operate on.
+ *
+ * Drop a reference to an AioContext.
+ */
+void aio_context_unref(AioContext *ctx);
+
+/**
+ * aio_bh_new: Allocate a new bottom half structure.
+ *
+ * Bottom halves are lightweight callbacks whose invocation is guaranteed
+ * to be wait-free, thread-safe and signal-safe. The #QEMUBH structure
+ * is opaque and must be allocated prior to its use.
+ */
+QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
+
+/**
+ * aio_notify: Force processing of pending events.
+ *
+ * Similar to signaling a condition variable, aio_notify forces
+ * aio_wait to exit, so that the next call will re-examine pending events.
+ * The caller of aio_notify will usually call aio_wait again very soon,
+ * or go through another iteration of the GLib main loop. Hence, aio_notify
+ * also has the side effect of recalculating the sets of file descriptors
+ * that the main loop waits for.
+ *
+ * Calling aio_notify is rarely necessary, because for example scheduling
+ * a bottom half calls it already.
+ */
+void aio_notify(AioContext *ctx);
+
+/**
+ * aio_bh_poll: Poll bottom halves for an AioContext.
+ *
+ * These are internal functions used by the QEMU main loop.
+ */
+int aio_bh_poll(AioContext *ctx);
+
+/**
+ * qemu_bh_schedule: Schedule a bottom half.
+ *
+ * Scheduling a bottom half interrupts the main loop and causes the
+ * execution of the callback that was passed to qemu_bh_new.
+ *
+ * Bottom halves that are scheduled from a bottom half handler are instantly
+ * invoked. This can create an infinite loop if a bottom half handler
+ * schedules itself.
+ *
+ * @bh: The bottom half to be scheduled.
+ */
+void qemu_bh_schedule(QEMUBH *bh);
+
+/**
+ * qemu_bh_cancel: Cancel execution of a bottom half.
+ *
+ * Canceling execution of a bottom half undoes the effect of calls to
+ * qemu_bh_schedule without freeing its resources yet. While cancellation
+ * itself is also wait-free and thread-safe, it can of course race with the
+ * loop that executes bottom halves unless you are holding the iothread
+ * mutex. This makes it mostly useless if you are not holding the mutex.
+ *
+ * @bh: The bottom half to be canceled.
+ */
+void qemu_bh_cancel(QEMUBH *bh);
+
+/**
+ *qemu_bh_delete: Cancel execution of a bottom half and free its resources.
+ *
+ * Deleting a bottom half frees the memory that was allocated for it by
+ * qemu_bh_new. It also implies canceling the bottom half if it was
+ * scheduled.
+ *
+ * @bh: The bottom half to be deleted.
+ */
+void qemu_bh_delete(QEMUBH *bh);
+
+/* Return whether there are any pending callbacks from the GSource
+ * attached to the AioContext.
+ *
+ * This is used internally in the implementation of the GSource.
+ */
+bool aio_pending(AioContext *ctx);
+
+/* Progress in completing AIO work to occur. This can issue new pending
+ * aio as a result of executing I/O completion or bh callbacks.
+ *
+ * If there is no pending AIO operation or completion (bottom half),
+ * return false. If there are pending AIO operations of bottom halves,
+ * return true.
+ *
+ * If there are no pending bottom halves, but there are pending AIO
+ * operations, it may not be possible to make any progress without
+ * blocking. If @blocking is true, this function will wait until one
+ * or more AIO events have completed, to ensure something has moved
+ * before returning.
+ */
+bool aio_poll(AioContext *ctx, bool blocking);
+
+#ifdef CONFIG_POSIX
+/* Returns 1 if there are still outstanding AIO requests; 0 otherwise */
+typedef int (AioFlushHandler)(void *opaque);
+
+/* Register a file descriptor and associated callbacks. Behaves very similarly
+ * to qemu_set_fd_handler2. Unlike qemu_set_fd_handler2, these callbacks will
+ * be invoked when using qemu_aio_wait().
+ *
+ * Code that invokes AIO completion functions should rely on this function
+ * instead of qemu_set_fd_handler[2].
+ */
+void aio_set_fd_handler(AioContext *ctx,
+ int fd,
+ IOHandler *io_read,
+ IOHandler *io_write,
+ AioFlushHandler *io_flush,
+ void *opaque);
+#endif
+
+/* Register an event notifier and associated callbacks. Behaves very similarly
+ * to event_notifier_set_handler. Unlike event_notifier_set_handler, these callbacks
+ * will be invoked when using qemu_aio_wait().
+ *
+ * Code that invokes AIO completion functions should rely on this function
+ * instead of event_notifier_set_handler.
+ */
+void aio_set_event_notifier(AioContext *ctx,
+ EventNotifier *notifier,
+ EventNotifierHandler *io_read,
+ AioFlushEventNotifierHandler *io_flush);
+
+/* Return a GSource that lets the main loop poll the file descriptors attached
+ * to this AioContext.
+ */
+GSource *aio_get_g_source(AioContext *ctx);
+
+/* Return the ThreadPool bound to this AioContext */
+struct ThreadPool *aio_get_thread_pool(AioContext *ctx);
+
+/* Functions to operate on the main QEMU AioContext. */
+
+bool qemu_aio_wait(void);
+void qemu_aio_set_event_notifier(EventNotifier *notifier,
+ EventNotifierHandler *io_read,
+ AioFlushEventNotifierHandler *io_flush);
+
+#ifdef CONFIG_POSIX
+void qemu_aio_set_fd_handler(int fd,
+ IOHandler *io_read,
+ IOHandler *io_write,
+ AioFlushHandler *io_flush,
+ void *opaque);
+#endif
+
+#endif
diff --git a/contrib/qemu/include/block/block.h b/contrib/qemu/include/block/block.h
new file mode 100644
index 00000000000..b6b9014a9ce
--- /dev/null
+++ b/contrib/qemu/include/block/block.h
@@ -0,0 +1,443 @@
+#ifndef BLOCK_H
+#define BLOCK_H
+
+#include "block/aio.h"
+#include "qemu-common.h"
+#include "qemu/option.h"
+#include "block/coroutine.h"
+#include "qapi/qmp/qobject.h"
+#include "qapi-types.h"
+
+/* block.c */
+typedef struct BlockDriver BlockDriver;
+typedef struct BlockJob BlockJob;
+
+typedef struct BlockDriverInfo {
+ /* in bytes, 0 if irrelevant */
+ int cluster_size;
+ /* offset at which the VM state can be saved (0 if not possible) */
+ int64_t vm_state_offset;
+ bool is_dirty;
+} BlockDriverInfo;
+
+typedef struct BlockFragInfo {
+ uint64_t allocated_clusters;
+ uint64_t total_clusters;
+ uint64_t fragmented_clusters;
+ uint64_t compressed_clusters;
+} BlockFragInfo;
+
+/* Callbacks for block device models */
+typedef struct BlockDevOps {
+ /*
+ * Runs when virtual media changed (monitor commands eject, change)
+ * Argument load is true on load and false on eject.
+ * Beware: doesn't run when a host device's physical media
+ * changes. Sure would be useful if it did.
+ * Device models with removable media must implement this callback.
+ */
+ void (*change_media_cb)(void *opaque, bool load);
+ /*
+ * Runs when an eject request is issued from the monitor, the tray
+ * is closed, and the medium is locked.
+ * Device models that do not implement is_medium_locked will not need
+ * this callback. Device models that can lock the medium or tray might
+ * want to implement the callback and unlock the tray when "force" is
+ * true, even if they do not support eject requests.
+ */
+ void (*eject_request_cb)(void *opaque, bool force);
+ /*
+ * Is the virtual tray open?
+ * Device models implement this only when the device has a tray.
+ */
+ bool (*is_tray_open)(void *opaque);
+ /*
+ * Is the virtual medium locked into the device?
+ * Device models implement this only when device has such a lock.
+ */
+ bool (*is_medium_locked)(void *opaque);
+ /*
+ * Runs when the size changed (e.g. monitor command block_resize)
+ */
+ void (*resize_cb)(void *opaque);
+} BlockDevOps;
+
+#define BDRV_O_RDWR 0x0002
+#define BDRV_O_SNAPSHOT 0x0008 /* open the file read only and save writes in a snapshot */
+#define BDRV_O_NOCACHE 0x0020 /* do not use the host page cache */
+#define BDRV_O_CACHE_WB 0x0040 /* use write-back caching */
+#define BDRV_O_NATIVE_AIO 0x0080 /* use native AIO instead of the thread pool */
+#define BDRV_O_NO_BACKING 0x0100 /* don't open the backing file */
+#define BDRV_O_NO_FLUSH 0x0200 /* disable flushing on this disk */
+#define BDRV_O_COPY_ON_READ 0x0400 /* copy read backing sectors into image */
+#define BDRV_O_INCOMING 0x0800 /* consistency hint for incoming migration */
+#define BDRV_O_CHECK 0x1000 /* open solely for consistency check */
+#define BDRV_O_ALLOW_RDWR 0x2000 /* allow reopen to change from r/o to r/w */
+#define BDRV_O_UNMAP 0x4000 /* execute guest UNMAP/TRIM operations */
+
+#define BDRV_O_CACHE_MASK (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
+
+#define BDRV_SECTOR_BITS 9
+#define BDRV_SECTOR_SIZE (1ULL << BDRV_SECTOR_BITS)
+#define BDRV_SECTOR_MASK ~(BDRV_SECTOR_SIZE - 1)
+
+typedef enum {
+ BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+} BlockErrorAction;
+
+typedef QSIMPLEQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue;
+
+typedef struct BDRVReopenState {
+ BlockDriverState *bs;
+ int flags;
+ void *opaque;
+} BDRVReopenState;
+
+
+void bdrv_iostatus_enable(BlockDriverState *bs);
+void bdrv_iostatus_reset(BlockDriverState *bs);
+void bdrv_iostatus_disable(BlockDriverState *bs);
+bool bdrv_iostatus_is_enabled(const BlockDriverState *bs);
+void bdrv_iostatus_set_err(BlockDriverState *bs, int error);
+void bdrv_info_print(Monitor *mon, const QObject *data);
+void bdrv_info(Monitor *mon, QObject **ret_data);
+void bdrv_stats_print(Monitor *mon, const QObject *data);
+void bdrv_info_stats(Monitor *mon, QObject **ret_data);
+
+/* disk I/O throttling */
+void bdrv_io_limits_enable(BlockDriverState *bs);
+void bdrv_io_limits_disable(BlockDriverState *bs);
+bool bdrv_io_limits_enabled(BlockDriverState *bs);
+
+void bdrv_init(void);
+void bdrv_init_with_whitelist(void);
+BlockDriver *bdrv_find_protocol(const char *filename,
+ bool allow_protocol_prefix);
+BlockDriver *bdrv_find_format(const char *format_name);
+BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
+ bool readonly);
+int bdrv_create(BlockDriver *drv, const char* filename,
+ QEMUOptionParameter *options);
+int bdrv_create_file(const char* filename, QEMUOptionParameter *options);
+BlockDriverState *bdrv_new(const char *device_name);
+void bdrv_make_anon(BlockDriverState *bs);
+void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old);
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
+void bdrv_delete(BlockDriverState *bs);
+int bdrv_parse_cache_flags(const char *mode, int *flags);
+int bdrv_parse_discard_flags(const char *mode, int *flags);
+int bdrv_file_open(BlockDriverState **pbs, const char *filename,
+ QDict *options, int flags);
+int bdrv_open_backing_file(BlockDriverState *bs, QDict *options);
+int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
+ int flags, BlockDriver *drv);
+BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
+ BlockDriverState *bs, int flags);
+int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
+int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp);
+int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
+ BlockReopenQueue *queue, Error **errp);
+void bdrv_reopen_commit(BDRVReopenState *reopen_state);
+void bdrv_reopen_abort(BDRVReopenState *reopen_state);
+void bdrv_close(BlockDriverState *bs);
+void bdrv_add_close_notifier(BlockDriverState *bs, Notifier *notify);
+int bdrv_attach_dev(BlockDriverState *bs, void *dev);
+void bdrv_attach_dev_nofail(BlockDriverState *bs, void *dev);
+void bdrv_detach_dev(BlockDriverState *bs, void *dev);
+void *bdrv_get_attached_dev(BlockDriverState *bs);
+void bdrv_set_dev_ops(BlockDriverState *bs, const BlockDevOps *ops,
+ void *opaque);
+void bdrv_dev_eject_request(BlockDriverState *bs, bool force);
+bool bdrv_dev_has_removable_media(BlockDriverState *bs);
+bool bdrv_dev_is_tray_open(BlockDriverState *bs);
+bool bdrv_dev_is_medium_locked(BlockDriverState *bs);
+int bdrv_read(BlockDriverState *bs, int64_t sector_num,
+ uint8_t *buf, int nb_sectors);
+int bdrv_read_unthrottled(BlockDriverState *bs, int64_t sector_num,
+ uint8_t *buf, int nb_sectors);
+int bdrv_write(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors);
+int bdrv_writev(BlockDriverState *bs, int64_t sector_num, QEMUIOVector *qiov);
+int bdrv_pread(BlockDriverState *bs, int64_t offset,
+ void *buf, int count);
+int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
+ const void *buf, int count);
+int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov);
+int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
+ const void *buf, int count);
+int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov);
+int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, QEMUIOVector *qiov);
+/*
+ * Efficiently zero a region of the disk image. Note that this is a regular
+ * I/O request like read or write and should have a reasonable size. This
+ * function is not suitable for zeroing the entire image in a single request
+ * because it may allocate memory for the entire region.
+ */
+int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors);
+int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, int *pnum);
+int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *top,
+ BlockDriverState *base,
+ int64_t sector_num,
+ int nb_sectors, int *pnum);
+BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
+ const char *backing_file);
+int bdrv_get_backing_file_depth(BlockDriverState *bs);
+int bdrv_truncate(BlockDriverState *bs, int64_t offset);
+int64_t bdrv_getlength(BlockDriverState *bs);
+int64_t bdrv_get_allocated_file_size(BlockDriverState *bs);
+void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr);
+int bdrv_commit(BlockDriverState *bs);
+int bdrv_commit_all(void);
+int bdrv_change_backing_file(BlockDriverState *bs,
+ const char *backing_file, const char *backing_fmt);
+void bdrv_register(BlockDriver *bdrv);
+int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
+ BlockDriverState *base);
+BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
+ BlockDriverState *bs);
+BlockDriverState *bdrv_find_base(BlockDriverState *bs);
+
+
+typedef struct BdrvCheckResult {
+ int corruptions;
+ int leaks;
+ int check_errors;
+ int corruptions_fixed;
+ int leaks_fixed;
+ int64_t image_end_offset;
+ BlockFragInfo bfi;
+} BdrvCheckResult;
+
+typedef enum {
+ BDRV_FIX_LEAKS = 1,
+ BDRV_FIX_ERRORS = 2,
+} BdrvCheckMode;
+
+int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix);
+
+/* async block I/O */
+typedef void BlockDriverDirtyHandler(BlockDriverState *bs, int64_t sector,
+ int sector_num);
+BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *iov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *iov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque);
+BlockDriverAIOCB *bdrv_aio_discard(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+void bdrv_aio_cancel(BlockDriverAIOCB *acb);
+
+typedef struct BlockRequest {
+ /* Fields to be filled by multiwrite caller */
+ int64_t sector;
+ int nb_sectors;
+ QEMUIOVector *qiov;
+ BlockDriverCompletionFunc *cb;
+ void *opaque;
+
+ /* Filled by multiwrite implementation */
+ int error;
+} BlockRequest;
+
+int bdrv_aio_multiwrite(BlockDriverState *bs, BlockRequest *reqs,
+ int num_reqs);
+
+/* sg packet commands */
+int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf);
+BlockDriverAIOCB *bdrv_aio_ioctl(BlockDriverState *bs,
+ unsigned long int req, void *buf,
+ BlockDriverCompletionFunc *cb, void *opaque);
+
+/* Invalidate any cached metadata used by image formats */
+void bdrv_invalidate_cache(BlockDriverState *bs);
+void bdrv_invalidate_cache_all(void);
+
+void bdrv_clear_incoming_migration_all(void);
+
+/* Ensure contents are flushed to disk. */
+int bdrv_flush(BlockDriverState *bs);
+int coroutine_fn bdrv_co_flush(BlockDriverState *bs);
+int bdrv_flush_all(void);
+void bdrv_close_all(void);
+void bdrv_drain_all(void);
+
+int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors);
+int bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors);
+int bdrv_has_zero_init_1(BlockDriverState *bs);
+int bdrv_has_zero_init(BlockDriverState *bs);
+int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+ int *pnum);
+int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
+ int64_t sector_num, int nb_sectors, int *pnum);
+
+void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
+ BlockdevOnError on_write_error);
+BlockdevOnError bdrv_get_on_error(BlockDriverState *bs, bool is_read);
+BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int error);
+void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
+ bool is_read, int error);
+int bdrv_is_read_only(BlockDriverState *bs);
+int bdrv_is_sg(BlockDriverState *bs);
+int bdrv_enable_write_cache(BlockDriverState *bs);
+void bdrv_set_enable_write_cache(BlockDriverState *bs, bool wce);
+int bdrv_is_inserted(BlockDriverState *bs);
+int bdrv_media_changed(BlockDriverState *bs);
+void bdrv_lock_medium(BlockDriverState *bs, bool locked);
+void bdrv_eject(BlockDriverState *bs, bool eject_flag);
+const char *bdrv_get_format_name(BlockDriverState *bs);
+BlockDriverState *bdrv_find(const char *name);
+BlockDriverState *bdrv_next(BlockDriverState *bs);
+void bdrv_iterate(void (*it)(void *opaque, BlockDriverState *bs),
+ void *opaque);
+int bdrv_is_encrypted(BlockDriverState *bs);
+int bdrv_key_required(BlockDriverState *bs);
+int bdrv_set_key(BlockDriverState *bs, const char *key);
+int bdrv_query_missing_keys(void);
+void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
+ void *opaque);
+const char *bdrv_get_device_name(BlockDriverState *bs);
+int bdrv_get_flags(BlockDriverState *bs);
+int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors);
+int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
+void bdrv_round_to_clusters(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ int64_t *cluster_sector_num,
+ int *cluster_nb_sectors);
+
+const char *bdrv_get_encrypted_filename(BlockDriverState *bs);
+void bdrv_get_backing_filename(BlockDriverState *bs,
+ char *filename, int filename_size);
+void bdrv_get_full_backing_filename(BlockDriverState *bs,
+ char *dest, size_t sz);
+int bdrv_is_snapshot(BlockDriverState *bs);
+
+int path_is_absolute(const char *path);
+void path_combine(char *dest, int dest_size,
+ const char *base_path,
+ const char *filename);
+
+int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos);
+int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
+ int64_t pos, int size);
+
+int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
+ int64_t pos, int size);
+
+void bdrv_img_create(const char *filename, const char *fmt,
+ const char *base_filename, const char *base_fmt,
+ char *options, uint64_t img_size, int flags,
+ Error **errp, bool quiet);
+
+void bdrv_set_buffer_alignment(BlockDriverState *bs, int align);
+void *qemu_blockalign(BlockDriverState *bs, size_t size);
+bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov);
+
+struct HBitmapIter;
+void bdrv_set_dirty_tracking(BlockDriverState *bs, int granularity);
+int bdrv_get_dirty(BlockDriverState *bs, int64_t sector);
+void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
+void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
+void bdrv_dirty_iter_init(BlockDriverState *bs, struct HBitmapIter *hbi);
+int64_t bdrv_get_dirty_count(BlockDriverState *bs);
+
+void bdrv_enable_copy_on_read(BlockDriverState *bs);
+void bdrv_disable_copy_on_read(BlockDriverState *bs);
+
+void bdrv_set_in_use(BlockDriverState *bs, int in_use);
+int bdrv_in_use(BlockDriverState *bs);
+
+#ifdef CONFIG_LINUX_AIO
+int raw_get_aio_fd(BlockDriverState *bs);
+#else
+static inline int raw_get_aio_fd(BlockDriverState *bs)
+{
+ return -ENOTSUP;
+}
+#endif
+
+enum BlockAcctType {
+ BDRV_ACCT_READ,
+ BDRV_ACCT_WRITE,
+ BDRV_ACCT_FLUSH,
+ BDRV_MAX_IOTYPE,
+};
+
+typedef struct BlockAcctCookie {
+ int64_t bytes;
+ int64_t start_time_ns;
+ enum BlockAcctType type;
+} BlockAcctCookie;
+
+void bdrv_acct_start(BlockDriverState *bs, BlockAcctCookie *cookie,
+ int64_t bytes, enum BlockAcctType type);
+void bdrv_acct_done(BlockDriverState *bs, BlockAcctCookie *cookie);
+
+typedef enum {
+ BLKDBG_L1_UPDATE,
+
+ BLKDBG_L1_GROW_ALLOC_TABLE,
+ BLKDBG_L1_GROW_WRITE_TABLE,
+ BLKDBG_L1_GROW_ACTIVATE_TABLE,
+
+ BLKDBG_L2_LOAD,
+ BLKDBG_L2_UPDATE,
+ BLKDBG_L2_UPDATE_COMPRESSED,
+ BLKDBG_L2_ALLOC_COW_READ,
+ BLKDBG_L2_ALLOC_WRITE,
+
+ BLKDBG_READ_AIO,
+ BLKDBG_READ_BACKING_AIO,
+ BLKDBG_READ_COMPRESSED,
+
+ BLKDBG_WRITE_AIO,
+ BLKDBG_WRITE_COMPRESSED,
+
+ BLKDBG_VMSTATE_LOAD,
+ BLKDBG_VMSTATE_SAVE,
+
+ BLKDBG_COW_READ,
+ BLKDBG_COW_WRITE,
+
+ BLKDBG_REFTABLE_LOAD,
+ BLKDBG_REFTABLE_GROW,
+
+ BLKDBG_REFBLOCK_LOAD,
+ BLKDBG_REFBLOCK_UPDATE,
+ BLKDBG_REFBLOCK_UPDATE_PART,
+ BLKDBG_REFBLOCK_ALLOC,
+ BLKDBG_REFBLOCK_ALLOC_HOOKUP,
+ BLKDBG_REFBLOCK_ALLOC_WRITE,
+ BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS,
+ BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE,
+ BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE,
+
+ BLKDBG_CLUSTER_ALLOC,
+ BLKDBG_CLUSTER_ALLOC_BYTES,
+ BLKDBG_CLUSTER_FREE,
+
+ BLKDBG_FLUSH_TO_OS,
+ BLKDBG_FLUSH_TO_DISK,
+
+ BLKDBG_EVENT_MAX,
+} BlkDebugEvent;
+
+#define BLKDBG_EVENT(bs, evt) bdrv_debug_event(bs, evt)
+void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event);
+
+int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
+ const char *tag);
+int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
+bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
+
+#endif
diff --git a/contrib/qemu/include/block/block_int.h b/contrib/qemu/include/block/block_int.h
new file mode 100644
index 00000000000..c6ac871e210
--- /dev/null
+++ b/contrib/qemu/include/block/block_int.h
@@ -0,0 +1,421 @@
+/*
+ * QEMU System Emulator block driver
+ *
+ * Copyright (c) 2003 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef BLOCK_INT_H
+#define BLOCK_INT_H
+
+#include "block/block.h"
+#include "qemu/option.h"
+#include "qemu/queue.h"
+#include "block/coroutine.h"
+#include "qemu/timer.h"
+#include "qapi-types.h"
+#include "qapi/qmp/qerror.h"
+#include "monitor/monitor.h"
+#include "qemu/hbitmap.h"
+#include "block/snapshot.h"
+
+#define BLOCK_FLAG_ENCRYPT 1
+#define BLOCK_FLAG_COMPAT6 4
+#define BLOCK_FLAG_LAZY_REFCOUNTS 8
+
+#define BLOCK_IO_LIMIT_READ 0
+#define BLOCK_IO_LIMIT_WRITE 1
+#define BLOCK_IO_LIMIT_TOTAL 2
+
+#define BLOCK_IO_SLICE_TIME 100000000
+#define NANOSECONDS_PER_SECOND 1000000000.0
+
+#define BLOCK_OPT_SIZE "size"
+#define BLOCK_OPT_ENCRYPT "encryption"
+#define BLOCK_OPT_COMPAT6 "compat6"
+#define BLOCK_OPT_BACKING_FILE "backing_file"
+#define BLOCK_OPT_BACKING_FMT "backing_fmt"
+#define BLOCK_OPT_CLUSTER_SIZE "cluster_size"
+#define BLOCK_OPT_TABLE_SIZE "table_size"
+#define BLOCK_OPT_PREALLOC "preallocation"
+#define BLOCK_OPT_SUBFMT "subformat"
+#define BLOCK_OPT_COMPAT_LEVEL "compat"
+#define BLOCK_OPT_LAZY_REFCOUNTS "lazy_refcounts"
+#define BLOCK_OPT_ADAPTER_TYPE "adapter_type"
+
+typedef struct BdrvTrackedRequest {
+ BlockDriverState *bs;
+ int64_t sector_num;
+ int nb_sectors;
+ bool is_write;
+ QLIST_ENTRY(BdrvTrackedRequest) list;
+ Coroutine *co; /* owner, used for deadlock detection */
+ CoQueue wait_queue; /* coroutines blocked on this request */
+} BdrvTrackedRequest;
+
+
+typedef struct BlockIOLimit {
+ int64_t bps[3];
+ int64_t iops[3];
+} BlockIOLimit;
+
+typedef struct BlockIOBaseValue {
+ uint64_t bytes[2];
+ uint64_t ios[2];
+} BlockIOBaseValue;
+
+struct BlockDriver {
+ const char *format_name;
+ int instance_size;
+ int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
+ int (*bdrv_probe_device)(const char *filename);
+
+ /* Any driver implementing this callback is expected to be able to handle
+ * NULL file names in its .bdrv_open() implementation */
+ void (*bdrv_parse_filename)(const char *filename, QDict *options, Error **errp);
+
+ /* For handling image reopen for split or non-split files */
+ int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state,
+ BlockReopenQueue *queue, Error **errp);
+ void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state);
+ void (*bdrv_reopen_abort)(BDRVReopenState *reopen_state);
+
+ int (*bdrv_open)(BlockDriverState *bs, QDict *options, int flags);
+ int (*bdrv_file_open)(BlockDriverState *bs, QDict *options, int flags);
+ int (*bdrv_read)(BlockDriverState *bs, int64_t sector_num,
+ uint8_t *buf, int nb_sectors);
+ int (*bdrv_write)(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors);
+ void (*bdrv_close)(BlockDriverState *bs);
+ void (*bdrv_rebind)(BlockDriverState *bs);
+ int (*bdrv_create)(const char *filename, QEMUOptionParameter *options);
+ int (*bdrv_set_key)(BlockDriverState *bs, const char *key);
+ int (*bdrv_make_empty)(BlockDriverState *bs);
+ /* aio */
+ BlockDriverAIOCB *(*bdrv_aio_readv)(BlockDriverState *bs,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+ BlockDriverAIOCB *(*bdrv_aio_writev)(BlockDriverState *bs,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+ BlockDriverAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque);
+ BlockDriverAIOCB *(*bdrv_aio_discard)(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+
+ int coroutine_fn (*bdrv_co_readv)(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+ int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+ /*
+ * Efficiently zero a region of the disk image. Typically an image format
+ * would use a compact metadata representation to implement this. This
+ * function pointer may be NULL and .bdrv_co_writev() will be called
+ * instead.
+ */
+ int coroutine_fn (*bdrv_co_write_zeroes)(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors);
+ int coroutine_fn (*bdrv_co_discard)(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors);
+ int coroutine_fn (*bdrv_co_is_allocated)(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, int *pnum);
+
+ /*
+ * Invalidate any cached meta-data.
+ */
+ void (*bdrv_invalidate_cache)(BlockDriverState *bs);
+
+ /*
+ * Flushes all data that was already written to the OS all the way down to
+ * the disk (for example raw-posix calls fsync()).
+ */
+ int coroutine_fn (*bdrv_co_flush_to_disk)(BlockDriverState *bs);
+
+ /*
+ * Flushes all internal caches to the OS. The data may still sit in a
+ * writeback cache of the host OS, but it will survive a crash of the qemu
+ * process.
+ */
+ int coroutine_fn (*bdrv_co_flush_to_os)(BlockDriverState *bs);
+
+ const char *protocol_name;
+ int (*bdrv_truncate)(BlockDriverState *bs, int64_t offset);
+ int64_t (*bdrv_getlength)(BlockDriverState *bs);
+ int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
+ int (*bdrv_write_compressed)(BlockDriverState *bs, int64_t sector_num,
+ const uint8_t *buf, int nb_sectors);
+
+ int (*bdrv_snapshot_create)(BlockDriverState *bs,
+ QEMUSnapshotInfo *sn_info);
+ int (*bdrv_snapshot_goto)(BlockDriverState *bs,
+ const char *snapshot_id);
+ int (*bdrv_snapshot_delete)(BlockDriverState *bs, const char *snapshot_id);
+ int (*bdrv_snapshot_list)(BlockDriverState *bs,
+ QEMUSnapshotInfo **psn_info);
+ int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
+ const char *snapshot_name);
+ int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
+
+ int (*bdrv_save_vmstate)(BlockDriverState *bs, QEMUIOVector *qiov,
+ int64_t pos);
+ int (*bdrv_load_vmstate)(BlockDriverState *bs, uint8_t *buf,
+ int64_t pos, int size);
+
+ int (*bdrv_change_backing_file)(BlockDriverState *bs,
+ const char *backing_file, const char *backing_fmt);
+
+ /* removable device specific */
+ int (*bdrv_is_inserted)(BlockDriverState *bs);
+ int (*bdrv_media_changed)(BlockDriverState *bs);
+ void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag);
+ void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
+
+ /* to control generic scsi devices */
+ int (*bdrv_ioctl)(BlockDriverState *bs, unsigned long int req, void *buf);
+ BlockDriverAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
+ unsigned long int req, void *buf,
+ BlockDriverCompletionFunc *cb, void *opaque);
+
+ /* List of options for creating images, terminated by name == NULL */
+ QEMUOptionParameter *create_options;
+
+
+ /*
+ * Returns 0 for completed check, -errno for internal errors.
+ * The check results are stored in result.
+ */
+ int (*bdrv_check)(BlockDriverState* bs, BdrvCheckResult *result,
+ BdrvCheckMode fix);
+
+ void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
+
+ /* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
+ int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
+ const char *tag);
+ int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
+ bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
+
+ /*
+ * Returns 1 if newly created images are guaranteed to contain only
+ * zeros, 0 otherwise.
+ */
+ int (*bdrv_has_zero_init)(BlockDriverState *bs);
+
+ QLIST_ENTRY(BlockDriver) list;
+};
+
+/*
+ * Note: the function bdrv_append() copies and swaps contents of
+ * BlockDriverStates, so if you add new fields to this struct, please
+ * inspect bdrv_append() to determine if the new fields need to be
+ * copied as well.
+ */
+struct BlockDriverState {
+ int64_t total_sectors; /* if we are reading a disk image, give its
+ size in sectors */
+ int read_only; /* if true, the media is read only */
+ int open_flags; /* flags used to open the file, re-used for re-open */
+ int encrypted; /* if true, the media is encrypted */
+ int valid_key; /* if true, a valid encryption key has been set */
+ int sg; /* if true, the device is a /dev/sg* */
+ int copy_on_read; /* if true, copy read backing sectors into image
+ note this is a reference count */
+
+ BlockDriver *drv; /* NULL means no media */
+ void *opaque;
+
+ void *dev; /* attached device model, if any */
+ /* TODO change to DeviceState when all users are qdevified */
+ const BlockDevOps *dev_ops;
+ void *dev_opaque;
+
+ char filename[1024];
+ char backing_file[1024]; /* if non zero, the image is a diff of
+ this file image */
+ char backing_format[16]; /* if non-zero and backing_file exists */
+ int is_temporary;
+
+ BlockDriverState *backing_hd;
+ BlockDriverState *file;
+
+ NotifierList close_notifiers;
+
+ /* Callback before write request is processed */
+ NotifierWithReturnList before_write_notifiers;
+
+ /* number of in-flight copy-on-read requests */
+ unsigned int copy_on_read_in_flight;
+
+ /* the time for latest disk I/O */
+ int64_t slice_start;
+ int64_t slice_end;
+ BlockIOLimit io_limits;
+ BlockIOBaseValue slice_submitted;
+ CoQueue throttled_reqs;
+ QEMUTimer *block_timer;
+ bool io_limits_enabled;
+
+ /* I/O stats (display with "info blockstats"). */
+ uint64_t nr_bytes[BDRV_MAX_IOTYPE];
+ uint64_t nr_ops[BDRV_MAX_IOTYPE];
+ uint64_t total_time_ns[BDRV_MAX_IOTYPE];
+ uint64_t wr_highest_sector;
+
+ /* Whether the disk can expand beyond total_sectors */
+ int growable;
+
+ /* the memory alignment required for the buffers handled by this driver */
+ int buffer_alignment;
+
+ /* do we need to tell the quest if we have a volatile write cache? */
+ int enable_write_cache;
+
+ /* NOTE: the following infos are only hints for real hardware
+ drivers. They are not used by the block driver */
+ BlockdevOnError on_read_error, on_write_error;
+ bool iostatus_enabled;
+ BlockDeviceIoStatus iostatus;
+ char device_name[32];
+ HBitmap *dirty_bitmap;
+ int in_use; /* users other than guest access, eg. block migration */
+ QTAILQ_ENTRY(BlockDriverState) list;
+
+ QLIST_HEAD(, BdrvTrackedRequest) tracked_requests;
+
+ /* long-running background operation */
+ BlockJob *job;
+
+ QDict *options;
+};
+
+int get_tmp_filename(char *filename, int size);
+
+void bdrv_set_io_limits(BlockDriverState *bs,
+ BlockIOLimit *io_limits);
+
+/**
+ * bdrv_add_before_write_notifier:
+ *
+ * Register a callback that is invoked before write requests are processed but
+ * after any throttling or waiting for overlapping requests.
+ */
+void bdrv_add_before_write_notifier(BlockDriverState *bs,
+ NotifierWithReturn *notifier);
+
+/**
+ * bdrv_get_aio_context:
+ *
+ * Returns: the currently bound #AioContext
+ */
+AioContext *bdrv_get_aio_context(BlockDriverState *bs);
+
+#ifdef _WIN32
+int is_windows_drive(const char *filename);
+#endif
+void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
+ enum MonitorEvent ev,
+ BlockErrorAction action, bool is_read);
+
+/**
+ * stream_start:
+ * @bs: Block device to operate on.
+ * @base: Block device that will become the new base, or %NULL to
+ * flatten the whole backing file chain onto @bs.
+ * @base_id: The file name that will be written to @bs as the new
+ * backing file if the job completes. Ignored if @base is %NULL.
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @on_error: The action to take upon error.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @errp: Error object.
+ *
+ * Start a streaming operation on @bs. Clusters that are unallocated
+ * in @bs, but allocated in any image between @base and @bs (both
+ * exclusive) will be written to @bs. At the end of a successful
+ * streaming job, the backing file of @bs will be changed to
+ * @base_id in the written image and to @base in the live BlockDriverState.
+ */
+void stream_start(BlockDriverState *bs, BlockDriverState *base,
+ const char *base_id, int64_t speed, BlockdevOnError on_error,
+ BlockDriverCompletionFunc *cb,
+ void *opaque, Error **errp);
+
+/**
+ * commit_start:
+ * @bs: Top Block device
+ * @base: Block device that will be written into, and become the new top
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @on_error: The action to take upon error.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @errp: Error object.
+ *
+ */
+void commit_start(BlockDriverState *bs, BlockDriverState *base,
+ BlockDriverState *top, int64_t speed,
+ BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
+ void *opaque, Error **errp);
+
+/*
+ * mirror_start:
+ * @bs: Block device to operate on.
+ * @target: Block device to write to.
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @granularity: The chosen granularity for the dirty bitmap.
+ * @buf_size: The amount of data that can be in flight at one time.
+ * @mode: Whether to collapse all images in the chain to the target.
+ * @on_source_error: The action to take upon error reading from the source.
+ * @on_target_error: The action to take upon error writing to the target.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @errp: Error object.
+ *
+ * Start a mirroring operation on @bs. Clusters that are allocated
+ * in @bs will be written to @bs until the job is cancelled or
+ * manually completed. At the end of a successful mirroring job,
+ * @bs will be switched to read from @target.
+ */
+void mirror_start(BlockDriverState *bs, BlockDriverState *target,
+ int64_t speed, int64_t granularity, int64_t buf_size,
+ MirrorSyncMode mode, BlockdevOnError on_source_error,
+ BlockdevOnError on_target_error,
+ BlockDriverCompletionFunc *cb,
+ void *opaque, Error **errp);
+
+/*
+ * backup_start:
+ * @bs: Block device to operate on.
+ * @target: Block device to write to.
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @on_source_error: The action to take upon error reading from the source.
+ * @on_target_error: The action to take upon error writing to the target.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ *
+ * Start a backup operation on @bs. Clusters in @bs are written to @target
+ * until the job is cancelled or manually completed.
+ */
+void backup_start(BlockDriverState *bs, BlockDriverState *target,
+ int64_t speed, BlockdevOnError on_source_error,
+ BlockdevOnError on_target_error,
+ BlockDriverCompletionFunc *cb, void *opaque,
+ Error **errp);
+
+#endif /* BLOCK_INT_H */
diff --git a/contrib/qemu/include/block/blockjob.h b/contrib/qemu/include/block/blockjob.h
new file mode 100644
index 00000000000..c290d07bba0
--- /dev/null
+++ b/contrib/qemu/include/block/blockjob.h
@@ -0,0 +1,278 @@
+/*
+ * Declarations for long-running block device operations
+ *
+ * Copyright (c) 2011 IBM Corp.
+ * Copyright (c) 2012 Red Hat, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef BLOCKJOB_H
+#define BLOCKJOB_H 1
+
+#include "block/block.h"
+
+/**
+ * BlockJobType:
+ *
+ * A class type for block job objects.
+ */
+typedef struct BlockJobType {
+ /** Derived BlockJob struct size */
+ size_t instance_size;
+
+ /** String describing the operation, part of query-block-jobs QMP API */
+ const char *job_type;
+
+ /** Optional callback for job types that support setting a speed limit */
+ void (*set_speed)(BlockJob *job, int64_t speed, Error **errp);
+
+ /** Optional callback for job types that need to forward I/O status reset */
+ void (*iostatus_reset)(BlockJob *job);
+
+ /**
+ * Optional callback for job types whose completion must be triggered
+ * manually.
+ */
+ void (*complete)(BlockJob *job, Error **errp);
+} BlockJobType;
+
+/**
+ * BlockJob:
+ *
+ * Long-running operation on a BlockDriverState.
+ */
+struct BlockJob {
+ /** The job type, including the job vtable. */
+ const BlockJobType *job_type;
+
+ /** The block device on which the job is operating. */
+ BlockDriverState *bs;
+
+ /**
+ * The coroutine that executes the job. If not NULL, it is
+ * reentered when busy is false and the job is cancelled.
+ */
+ Coroutine *co;
+
+ /**
+ * Set to true if the job should cancel itself. The flag must
+ * always be tested just before toggling the busy flag from false
+ * to true. After a job has been cancelled, it should only yield
+ * if #qemu_aio_wait will ("sooner or later") reenter the coroutine.
+ */
+ bool cancelled;
+
+ /**
+ * Set to true if the job is either paused, or will pause itself
+ * as soon as possible (if busy == true).
+ */
+ bool paused;
+
+ /**
+ * Set to false by the job while it is in a quiescent state, where
+ * no I/O is pending and the job has yielded on any condition
+ * that is not detected by #qemu_aio_wait, such as a timer.
+ */
+ bool busy;
+
+ /** Status that is published by the query-block-jobs QMP API */
+ BlockDeviceIoStatus iostatus;
+
+ /** Offset that is published by the query-block-jobs QMP API */
+ int64_t offset;
+
+ /** Length that is published by the query-block-jobs QMP API */
+ int64_t len;
+
+ /** Speed that was set with @block_job_set_speed. */
+ int64_t speed;
+
+ /** The completion function that will be called when the job completes. */
+ BlockDriverCompletionFunc *cb;
+
+ /** The opaque value that is passed to the completion function. */
+ void *opaque;
+};
+
+/**
+ * block_job_create:
+ * @job_type: The class object for the newly-created job.
+ * @bs: The block
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @errp: Error object.
+ *
+ * Create a new long-running block device job and return it. The job
+ * will call @cb asynchronously when the job completes. Note that
+ * @bs may have been closed at the time the @cb it is called. If
+ * this is the case, the job may be reported as either cancelled or
+ * completed.
+ *
+ * This function is not part of the public job interface; it should be
+ * called from a wrapper that is specific to the job type.
+ */
+void *block_job_create(const BlockJobType *job_type, BlockDriverState *bs,
+ int64_t speed, BlockDriverCompletionFunc *cb,
+ void *opaque, Error **errp);
+
+/**
+ * block_job_sleep_ns:
+ * @job: The job that calls the function.
+ * @clock: The clock to sleep on.
+ * @ns: How many nanoseconds to stop for.
+ *
+ * Put the job to sleep (assuming that it wasn't canceled) for @ns
+ * nanoseconds. Canceling the job will interrupt the wait immediately.
+ */
+void block_job_sleep_ns(BlockJob *job, QEMUClock *clock, int64_t ns);
+
+/**
+ * block_job_completed:
+ * @job: The job being completed.
+ * @ret: The status code.
+ *
+ * Call the completion function that was registered at creation time, and
+ * free @job.
+ */
+void block_job_completed(BlockJob *job, int ret);
+
+/**
+ * block_job_set_speed:
+ * @job: The job to set the speed for.
+ * @speed: The new value
+ * @errp: Error object.
+ *
+ * Set a rate-limiting parameter for the job; the actual meaning may
+ * vary depending on the job type.
+ */
+void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp);
+
+/**
+ * block_job_cancel:
+ * @job: The job to be canceled.
+ *
+ * Asynchronously cancel the specified job.
+ */
+void block_job_cancel(BlockJob *job);
+
+/**
+ * block_job_complete:
+ * @job: The job to be completed.
+ * @errp: Error object.
+ *
+ * Asynchronously complete the specified job.
+ */
+void block_job_complete(BlockJob *job, Error **errp);
+
+/**
+ * block_job_is_cancelled:
+ * @job: The job being queried.
+ *
+ * Returns whether the job is scheduled for cancellation.
+ */
+bool block_job_is_cancelled(BlockJob *job);
+
+/**
+ * block_job_query:
+ * @job: The job to get information about.
+ *
+ * Return information about a job.
+ */
+BlockJobInfo *block_job_query(BlockJob *job);
+
+/**
+ * block_job_pause:
+ * @job: The job to be paused.
+ *
+ * Asynchronously pause the specified job.
+ */
+void block_job_pause(BlockJob *job);
+
+/**
+ * block_job_resume:
+ * @job: The job to be resumed.
+ *
+ * Resume the specified job.
+ */
+void block_job_resume(BlockJob *job);
+
+/**
+ * qobject_from_block_job:
+ * @job: The job whose information is requested.
+ *
+ * Return a QDict corresponding to @job's query-block-jobs entry.
+ */
+QObject *qobject_from_block_job(BlockJob *job);
+
+/**
+ * block_job_ready:
+ * @job: The job which is now ready to complete.
+ *
+ * Send a BLOCK_JOB_READY event for the specified job.
+ */
+void block_job_ready(BlockJob *job);
+
+/**
+ * block_job_is_paused:
+ * @job: The job being queried.
+ *
+ * Returns whether the job is currently paused, or will pause
+ * as soon as it reaches a sleeping point.
+ */
+bool block_job_is_paused(BlockJob *job);
+
+/**
+ * block_job_cancel_sync:
+ * @job: The job to be canceled.
+ *
+ * Synchronously cancel the job. The completion callback is called
+ * before the function returns. The job may actually complete
+ * instead of canceling itself; the circumstances under which this
+ * happens depend on the kind of job that is active.
+ *
+ * Returns the return value from the job if the job actually completed
+ * during the call, or -ECANCELED if it was canceled.
+ */
+int block_job_cancel_sync(BlockJob *job);
+
+/**
+ * block_job_iostatus_reset:
+ * @job: The job whose I/O status should be reset.
+ *
+ * Reset I/O status on @job and on BlockDriverState objects it uses,
+ * other than job->bs.
+ */
+void block_job_iostatus_reset(BlockJob *job);
+
+/**
+ * block_job_error_action:
+ * @job: The job to signal an error for.
+ * @bs: The block device on which to set an I/O error.
+ * @on_err: The error action setting.
+ * @is_read: Whether the operation was a read.
+ * @error: The error that was reported.
+ *
+ * Report an I/O error for a block job and possibly stop the VM. Return the
+ * action that was selected based on @on_err and @error.
+ */
+BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
+ BlockdevOnError on_err,
+ int is_read, int error);
+#endif
diff --git a/contrib/qemu/include/block/coroutine.h b/contrib/qemu/include/block/coroutine.h
new file mode 100644
index 00000000000..377805a3b08
--- /dev/null
+++ b/contrib/qemu/include/block/coroutine.h
@@ -0,0 +1,218 @@
+/*
+ * QEMU coroutine implementation
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Kevin Wolf <kwolf@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_COROUTINE_H
+#define QEMU_COROUTINE_H
+
+#include <stdbool.h>
+#include "qemu/queue.h"
+#include "qemu/timer.h"
+
+/**
+ * Coroutines are a mechanism for stack switching and can be used for
+ * cooperative userspace threading. These functions provide a simple but
+ * useful flavor of coroutines that is suitable for writing sequential code,
+ * rather than callbacks, for operations that need to give up control while
+ * waiting for events to complete.
+ *
+ * These functions are re-entrant and may be used outside the global mutex.
+ */
+
+/**
+ * Mark a function that executes in coroutine context
+ *
+ * Functions that execute in coroutine context cannot be called directly from
+ * normal functions. In the future it would be nice to enable compiler or
+ * static checker support for catching such errors. This annotation might make
+ * it possible and in the meantime it serves as documentation.
+ *
+ * For example:
+ *
+ * static void coroutine_fn foo(void) {
+ * ....
+ * }
+ */
+#define coroutine_fn
+
+typedef struct Coroutine Coroutine;
+
+/**
+ * Coroutine entry point
+ *
+ * When the coroutine is entered for the first time, opaque is passed in as an
+ * argument.
+ *
+ * When this function returns, the coroutine is destroyed automatically and
+ * execution continues in the caller who last entered the coroutine.
+ */
+typedef void coroutine_fn CoroutineEntry(void *opaque);
+
+/**
+ * Create a new coroutine
+ *
+ * Use qemu_coroutine_enter() to actually transfer control to the coroutine.
+ */
+Coroutine *qemu_coroutine_create(CoroutineEntry *entry);
+
+/**
+ * Transfer control to a coroutine
+ *
+ * The opaque argument is passed as the argument to the entry point when
+ * entering the coroutine for the first time. It is subsequently ignored.
+ */
+void qemu_coroutine_enter(Coroutine *coroutine, void *opaque);
+
+/**
+ * Transfer control back to a coroutine's caller
+ *
+ * This function does not return until the coroutine is re-entered using
+ * qemu_coroutine_enter().
+ */
+void coroutine_fn qemu_coroutine_yield(void);
+
+/**
+ * Get the currently executing coroutine
+ */
+Coroutine *coroutine_fn qemu_coroutine_self(void);
+
+/**
+ * Return whether or not currently inside a coroutine
+ *
+ * This can be used to write functions that work both when in coroutine context
+ * and when not in coroutine context. Note that such functions cannot use the
+ * coroutine_fn annotation since they work outside coroutine context.
+ */
+bool qemu_in_coroutine(void);
+
+
+
+/**
+ * CoQueues are a mechanism to queue coroutines in order to continue executing
+ * them later. They provide the fundamental primitives on which coroutine locks
+ * are built.
+ */
+typedef struct CoQueue {
+ QTAILQ_HEAD(, Coroutine) entries;
+ AioContext *ctx;
+} CoQueue;
+
+/**
+ * Initialise a CoQueue. This must be called before any other operation is used
+ * on the CoQueue.
+ */
+void qemu_co_queue_init(CoQueue *queue);
+
+/**
+ * Adds the current coroutine to the CoQueue and transfers control to the
+ * caller of the coroutine.
+ */
+void coroutine_fn qemu_co_queue_wait(CoQueue *queue);
+
+/**
+ * Adds the current coroutine to the head of the CoQueue and transfers control to the
+ * caller of the coroutine.
+ */
+void coroutine_fn qemu_co_queue_wait_insert_head(CoQueue *queue);
+
+/**
+ * Restarts the next coroutine in the CoQueue and removes it from the queue.
+ *
+ * Returns true if a coroutine was restarted, false if the queue is empty.
+ */
+bool qemu_co_queue_next(CoQueue *queue);
+
+/**
+ * Restarts all coroutines in the CoQueue and leaves the queue empty.
+ */
+void qemu_co_queue_restart_all(CoQueue *queue);
+
+/**
+ * Checks if the CoQueue is empty.
+ */
+bool qemu_co_queue_empty(CoQueue *queue);
+
+
+/**
+ * Provides a mutex that can be used to synchronise coroutines
+ */
+typedef struct CoMutex {
+ bool locked;
+ CoQueue queue;
+} CoMutex;
+
+/**
+ * Initialises a CoMutex. This must be called before any other operation is used
+ * on the CoMutex.
+ */
+void qemu_co_mutex_init(CoMutex *mutex);
+
+/**
+ * Locks the mutex. If the lock cannot be taken immediately, control is
+ * transferred to the caller of the current coroutine.
+ */
+void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex);
+
+/**
+ * Unlocks the mutex and schedules the next coroutine that was waiting for this
+ * lock to be run.
+ */
+void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex);
+
+typedef struct CoRwlock {
+ bool writer;
+ int reader;
+ CoQueue queue;
+} CoRwlock;
+
+/**
+ * Initialises a CoRwlock. This must be called before any other operation
+ * is used on the CoRwlock
+ */
+void qemu_co_rwlock_init(CoRwlock *lock);
+
+/**
+ * Read locks the CoRwlock. If the lock cannot be taken immediately because
+ * of a parallel writer, control is transferred to the caller of the current
+ * coroutine.
+ */
+void qemu_co_rwlock_rdlock(CoRwlock *lock);
+
+/**
+ * Write Locks the mutex. If the lock cannot be taken immediately because
+ * of a parallel reader, control is transferred to the caller of the current
+ * coroutine.
+ */
+void qemu_co_rwlock_wrlock(CoRwlock *lock);
+
+/**
+ * Unlocks the read/write lock and schedules the next coroutine that was
+ * waiting for this lock to be run.
+ */
+void qemu_co_rwlock_unlock(CoRwlock *lock);
+
+/**
+ * Yield the coroutine for a given duration
+ *
+ * Note this function uses timers and hence only works when a main loop is in
+ * use. See main-loop.h and do not use from qemu-tool programs.
+ */
+void coroutine_fn co_sleep_ns(QEMUClock *clock, int64_t ns);
+
+/**
+ * Yield until a file descriptor becomes readable
+ *
+ * Note that this function clobbers the handlers for the file descriptor.
+ */
+void coroutine_fn yield_until_fd_readable(int fd);
+#endif /* QEMU_COROUTINE_H */
diff --git a/contrib/qemu/include/block/coroutine_int.h b/contrib/qemu/include/block/coroutine_int.h
new file mode 100644
index 00000000000..f133d65af86
--- /dev/null
+++ b/contrib/qemu/include/block/coroutine_int.h
@@ -0,0 +1,53 @@
+/*
+ * Coroutine internals
+ *
+ * Copyright (c) 2011 Kevin Wolf <kwolf@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef QEMU_COROUTINE_INT_H
+#define QEMU_COROUTINE_INT_H
+
+#include "qemu/queue.h"
+#include "block/coroutine.h"
+
+typedef enum {
+ COROUTINE_YIELD = 1,
+ COROUTINE_TERMINATE = 2,
+} CoroutineAction;
+
+struct Coroutine {
+ CoroutineEntry *entry;
+ void *entry_arg;
+ Coroutine *caller;
+ QSLIST_ENTRY(Coroutine) pool_next;
+
+ /* Coroutines that should be woken up when we yield or terminate */
+ QTAILQ_HEAD(, Coroutine) co_queue_wakeup;
+ QTAILQ_ENTRY(Coroutine) co_queue_next;
+};
+
+Coroutine *qemu_coroutine_new(void);
+void qemu_coroutine_delete(Coroutine *co);
+CoroutineAction qemu_coroutine_switch(Coroutine *from, Coroutine *to,
+ CoroutineAction action);
+void coroutine_fn qemu_co_queue_run_restart(Coroutine *co);
+
+#endif
diff --git a/contrib/qemu/include/block/snapshot.h b/contrib/qemu/include/block/snapshot.h
new file mode 100644
index 00000000000..eaf61f0326e
--- /dev/null
+++ b/contrib/qemu/include/block/snapshot.h
@@ -0,0 +1,53 @@
+/*
+ * Block layer snapshot related functions
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef SNAPSHOT_H
+#define SNAPSHOT_H
+
+#include "qemu-common.h"
+
+typedef struct QEMUSnapshotInfo {
+ char id_str[128]; /* unique snapshot id */
+ /* the following fields are informative. They are not needed for
+ the consistency of the snapshot */
+ char name[256]; /* user chosen name */
+ uint64_t vm_state_size; /* VM state info size */
+ uint32_t date_sec; /* UTC date of the snapshot */
+ uint32_t date_nsec;
+ uint64_t vm_clock_nsec; /* VM clock relative to boot */
+} QEMUSnapshotInfo;
+
+int bdrv_snapshot_find(BlockDriverState *bs, QEMUSnapshotInfo *sn_info,
+ const char *name);
+int bdrv_can_snapshot(BlockDriverState *bs);
+int bdrv_snapshot_create(BlockDriverState *bs,
+ QEMUSnapshotInfo *sn_info);
+int bdrv_snapshot_goto(BlockDriverState *bs,
+ const char *snapshot_id);
+int bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id);
+int bdrv_snapshot_list(BlockDriverState *bs,
+ QEMUSnapshotInfo **psn_info);
+int bdrv_snapshot_load_tmp(BlockDriverState *bs,
+ const char *snapshot_name);
+#endif
diff --git a/contrib/qemu/include/config.h b/contrib/qemu/include/config.h
new file mode 100644
index 00000000000..e20f78696a1
--- /dev/null
+++ b/contrib/qemu/include/config.h
@@ -0,0 +1,2 @@
+#include "config-host.h"
+#include "config-target.h"
diff --git a/contrib/qemu/include/exec/cpu-common.h b/contrib/qemu/include/exec/cpu-common.h
new file mode 100644
index 00000000000..e4996e19c32
--- /dev/null
+++ b/contrib/qemu/include/exec/cpu-common.h
@@ -0,0 +1,124 @@
+#ifndef CPU_COMMON_H
+#define CPU_COMMON_H 1
+
+/* CPU interfaces that are target independent. */
+
+#ifndef CONFIG_USER_ONLY
+#include "exec/hwaddr.h"
+#endif
+
+#ifndef NEED_CPU_H
+#include "exec/poison.h"
+#endif
+
+#include "qemu/bswap.h"
+#include "qemu/queue.h"
+
+/**
+ * CPUListState:
+ * @cpu_fprintf: Print function.
+ * @file: File to print to using @cpu_fprint.
+ *
+ * State commonly used for iterating over CPU models.
+ */
+typedef struct CPUListState {
+ fprintf_function cpu_fprintf;
+ FILE *file;
+} CPUListState;
+
+#if !defined(CONFIG_USER_ONLY)
+
+enum device_endian {
+ DEVICE_NATIVE_ENDIAN,
+ DEVICE_BIG_ENDIAN,
+ DEVICE_LITTLE_ENDIAN,
+};
+
+/* address in the RAM (different from a physical address) */
+#if defined(CONFIG_XEN_BACKEND)
+typedef uint64_t ram_addr_t;
+# define RAM_ADDR_MAX UINT64_MAX
+# define RAM_ADDR_FMT "%" PRIx64
+#else
+typedef uintptr_t ram_addr_t;
+# define RAM_ADDR_MAX UINTPTR_MAX
+# define RAM_ADDR_FMT "%" PRIxPTR
+#endif
+
+/* memory API */
+
+typedef void CPUWriteMemoryFunc(void *opaque, hwaddr addr, uint32_t value);
+typedef uint32_t CPUReadMemoryFunc(void *opaque, hwaddr addr);
+
+void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
+/* This should not be used by devices. */
+MemoryRegion *qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr);
+void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev);
+
+void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf,
+ int len, int is_write);
+static inline void cpu_physical_memory_read(hwaddr addr,
+ void *buf, int len)
+{
+ cpu_physical_memory_rw(addr, buf, len, 0);
+}
+static inline void cpu_physical_memory_write(hwaddr addr,
+ const void *buf, int len)
+{
+ cpu_physical_memory_rw(addr, (void *)buf, len, 1);
+}
+void *cpu_physical_memory_map(hwaddr addr,
+ hwaddr *plen,
+ int is_write);
+void cpu_physical_memory_unmap(void *buffer, hwaddr len,
+ int is_write, hwaddr access_len);
+void *cpu_register_map_client(void *opaque, void (*callback)(void *opaque));
+
+bool cpu_physical_memory_is_io(hwaddr phys_addr);
+
+/* Coalesced MMIO regions are areas where write operations can be reordered.
+ * This usually implies that write operations are side-effect free. This allows
+ * batching which can make a major impact on performance when using
+ * virtualization.
+ */
+void qemu_flush_coalesced_mmio_buffer(void);
+
+uint32_t ldub_phys(hwaddr addr);
+uint32_t lduw_le_phys(hwaddr addr);
+uint32_t lduw_be_phys(hwaddr addr);
+uint32_t ldl_le_phys(hwaddr addr);
+uint32_t ldl_be_phys(hwaddr addr);
+uint64_t ldq_le_phys(hwaddr addr);
+uint64_t ldq_be_phys(hwaddr addr);
+void stb_phys(hwaddr addr, uint32_t val);
+void stw_le_phys(hwaddr addr, uint32_t val);
+void stw_be_phys(hwaddr addr, uint32_t val);
+void stl_le_phys(hwaddr addr, uint32_t val);
+void stl_be_phys(hwaddr addr, uint32_t val);
+void stq_le_phys(hwaddr addr, uint64_t val);
+void stq_be_phys(hwaddr addr, uint64_t val);
+
+#ifdef NEED_CPU_H
+uint32_t lduw_phys(hwaddr addr);
+uint32_t ldl_phys(hwaddr addr);
+uint64_t ldq_phys(hwaddr addr);
+void stl_phys_notdirty(hwaddr addr, uint32_t val);
+void stw_phys(hwaddr addr, uint32_t val);
+void stl_phys(hwaddr addr, uint32_t val);
+void stq_phys(hwaddr addr, uint64_t val);
+#endif
+
+void cpu_physical_memory_write_rom(hwaddr addr,
+ const uint8_t *buf, int len);
+
+extern struct MemoryRegion io_mem_rom;
+extern struct MemoryRegion io_mem_notdirty;
+
+typedef void (RAMBlockIterFunc)(void *host_addr,
+ ram_addr_t offset, ram_addr_t length, void *opaque);
+
+void qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque);
+
+#endif
+
+#endif /* !CPU_COMMON_H */
diff --git a/contrib/qemu/include/exec/hwaddr.h b/contrib/qemu/include/exec/hwaddr.h
new file mode 100644
index 00000000000..c9eb78fba18
--- /dev/null
+++ b/contrib/qemu/include/exec/hwaddr.h
@@ -0,0 +1,20 @@
+/* Define hwaddr if it exists. */
+
+#ifndef HWADDR_H
+#define HWADDR_H
+
+#define HWADDR_BITS 64
+/* hwaddr is the type of a physical address (its size can
+ be different from 'target_ulong'). */
+
+typedef uint64_t hwaddr;
+#define HWADDR_MAX UINT64_MAX
+#define TARGET_FMT_plx "%016" PRIx64
+#define HWADDR_PRId PRId64
+#define HWADDR_PRIi PRIi64
+#define HWADDR_PRIo PRIo64
+#define HWADDR_PRIu PRIu64
+#define HWADDR_PRIx PRIx64
+#define HWADDR_PRIX PRIX64
+
+#endif
diff --git a/contrib/qemu/include/exec/poison.h b/contrib/qemu/include/exec/poison.h
new file mode 100644
index 00000000000..2341a750413
--- /dev/null
+++ b/contrib/qemu/include/exec/poison.h
@@ -0,0 +1,63 @@
+/* Poison identifiers that should not be used when building
+ target independent device code. */
+
+#ifndef HW_POISON_H
+#define HW_POISON_H
+#ifdef __GNUC__
+
+#pragma GCC poison TARGET_I386
+#pragma GCC poison TARGET_X86_64
+#pragma GCC poison TARGET_ALPHA
+#pragma GCC poison TARGET_ARM
+#pragma GCC poison TARGET_CRIS
+#pragma GCC poison TARGET_LM32
+#pragma GCC poison TARGET_M68K
+#pragma GCC poison TARGET_MIPS
+#pragma GCC poison TARGET_MIPS64
+#pragma GCC poison TARGET_OPENRISC
+#pragma GCC poison TARGET_PPC
+#pragma GCC poison TARGET_PPCEMB
+#pragma GCC poison TARGET_PPC64
+#pragma GCC poison TARGET_ABI32
+#pragma GCC poison TARGET_SH4
+#pragma GCC poison TARGET_SPARC
+#pragma GCC poison TARGET_SPARC64
+
+#pragma GCC poison TARGET_WORDS_BIGENDIAN
+#pragma GCC poison BSWAP_NEEDED
+
+#pragma GCC poison TARGET_LONG_BITS
+#pragma GCC poison TARGET_FMT_lx
+#pragma GCC poison TARGET_FMT_ld
+
+#pragma GCC poison TARGET_PAGE_SIZE
+#pragma GCC poison TARGET_PAGE_MASK
+#pragma GCC poison TARGET_PAGE_BITS
+#pragma GCC poison TARGET_PAGE_ALIGN
+
+#pragma GCC poison CPUArchState
+#pragma GCC poison env
+
+#pragma GCC poison lduw_phys
+#pragma GCC poison ldl_phys
+#pragma GCC poison ldq_phys
+#pragma GCC poison stl_phys_notdirty
+#pragma GCC poison stw_phys
+#pragma GCC poison stl_phys
+#pragma GCC poison stq_phys
+
+#pragma GCC poison CPU_INTERRUPT_HARD
+#pragma GCC poison CPU_INTERRUPT_EXITTB
+#pragma GCC poison CPU_INTERRUPT_HALT
+#pragma GCC poison CPU_INTERRUPT_DEBUG
+#pragma GCC poison CPU_INTERRUPT_TGT_EXT_0
+#pragma GCC poison CPU_INTERRUPT_TGT_EXT_1
+#pragma GCC poison CPU_INTERRUPT_TGT_EXT_2
+#pragma GCC poison CPU_INTERRUPT_TGT_EXT_3
+#pragma GCC poison CPU_INTERRUPT_TGT_EXT_4
+#pragma GCC poison CPU_INTERRUPT_TGT_INT_0
+#pragma GCC poison CPU_INTERRUPT_TGT_INT_1
+#pragma GCC poison CPU_INTERRUPT_TGT_INT_2
+
+#endif
+#endif
diff --git a/contrib/qemu/include/fpu/softfloat.h b/contrib/qemu/include/fpu/softfloat.h
new file mode 100644
index 00000000000..f3927e2419f
--- /dev/null
+++ b/contrib/qemu/include/fpu/softfloat.h
@@ -0,0 +1,641 @@
+/*
+ * QEMU float support
+ *
+ * Derived from SoftFloat.
+ */
+
+/*============================================================================
+
+This C header file is part of the SoftFloat IEC/IEEE Floating-point Arithmetic
+Package, Release 2b.
+
+Written by John R. Hauser. This work was made possible in part by the
+International Computer Science Institute, located at Suite 600, 1947 Center
+Street, Berkeley, California 94704. Funding was partially provided by the
+National Science Foundation under grant MIP-9311980. The original version
+of this code was written as part of a project to build a fixed-point vector
+processor in collaboration with the University of California at Berkeley,
+overseen by Profs. Nelson Morgan and John Wawrzynek. More information
+is available through the Web page `http://www.cs.berkeley.edu/~jhauser/
+arithmetic/SoftFloat.html'.
+
+THIS SOFTWARE IS DISTRIBUTED AS IS, FOR FREE. Although reasonable effort has
+been made to avoid it, THIS SOFTWARE MAY CONTAIN FAULTS THAT WILL AT TIMES
+RESULT IN INCORRECT BEHAVIOR. USE OF THIS SOFTWARE IS RESTRICTED TO PERSONS
+AND ORGANIZATIONS WHO CAN AND WILL TAKE FULL RESPONSIBILITY FOR ALL LOSSES,
+COSTS, OR OTHER PROBLEMS THEY INCUR DUE TO THE SOFTWARE, AND WHO FURTHERMORE
+EFFECTIVELY INDEMNIFY JOHN HAUSER AND THE INTERNATIONAL COMPUTER SCIENCE
+INSTITUTE (possibly via similar legal warning) AGAINST ALL LOSSES, COSTS, OR
+OTHER PROBLEMS INCURRED BY THEIR CUSTOMERS AND CLIENTS DUE TO THE SOFTWARE.
+
+Derivative works are acceptable, even for commercial purposes, so long as
+(1) the source code for the derivative work includes prominent notice that
+the work is derivative, and (2) the source code includes prominent notice with
+these four paragraphs for those parts of this code that are retained.
+
+=============================================================================*/
+
+#ifndef SOFTFLOAT_H
+#define SOFTFLOAT_H
+
+#if defined(CONFIG_SOLARIS) && defined(CONFIG_NEEDS_LIBSUNMATH)
+#include <sunmath.h>
+#endif
+
+#include <inttypes.h>
+#include "config-host.h"
+#include "qemu/osdep.h"
+
+/*----------------------------------------------------------------------------
+| Each of the following `typedef's defines the most convenient type that holds
+| integers of at least as many bits as specified. For example, `uint8' should
+| be the most convenient type that can hold unsigned integers of as many as
+| 8 bits. The `flag' type must be able to hold either a 0 or 1. For most
+| implementations of C, `flag', `uint8', and `int8' should all be `typedef'ed
+| to the same as `int'.
+*----------------------------------------------------------------------------*/
+typedef uint8_t flag;
+typedef uint8_t uint8;
+typedef int8_t int8;
+typedef unsigned int uint32;
+typedef signed int int32;
+typedef uint64_t uint64;
+typedef int64_t int64;
+
+#define LIT64( a ) a##LL
+#define INLINE static inline
+
+#define STATUS_PARAM , float_status *status
+#define STATUS(field) status->field
+#define STATUS_VAR , status
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE floating-point ordering relations
+*----------------------------------------------------------------------------*/
+enum {
+ float_relation_less = -1,
+ float_relation_equal = 0,
+ float_relation_greater = 1,
+ float_relation_unordered = 2
+};
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE floating-point types.
+*----------------------------------------------------------------------------*/
+/* Use structures for soft-float types. This prevents accidentally mixing
+ them with native int/float types. A sufficiently clever compiler and
+ sane ABI should be able to see though these structs. However
+ x86/gcc 3.x seems to struggle a bit, so leave them disabled by default. */
+//#define USE_SOFTFLOAT_STRUCT_TYPES
+#ifdef USE_SOFTFLOAT_STRUCT_TYPES
+typedef struct {
+ uint16_t v;
+} float16;
+#define float16_val(x) (((float16)(x)).v)
+#define make_float16(x) __extension__ ({ float16 f16_val = {x}; f16_val; })
+#define const_float16(x) { x }
+typedef struct {
+ uint32_t v;
+} float32;
+/* The cast ensures an error if the wrong type is passed. */
+#define float32_val(x) (((float32)(x)).v)
+#define make_float32(x) __extension__ ({ float32 f32_val = {x}; f32_val; })
+#define const_float32(x) { x }
+typedef struct {
+ uint64_t v;
+} float64;
+#define float64_val(x) (((float64)(x)).v)
+#define make_float64(x) __extension__ ({ float64 f64_val = {x}; f64_val; })
+#define const_float64(x) { x }
+#else
+typedef uint16_t float16;
+typedef uint32_t float32;
+typedef uint64_t float64;
+#define float16_val(x) (x)
+#define float32_val(x) (x)
+#define float64_val(x) (x)
+#define make_float16(x) (x)
+#define make_float32(x) (x)
+#define make_float64(x) (x)
+#define const_float16(x) (x)
+#define const_float32(x) (x)
+#define const_float64(x) (x)
+#endif
+typedef struct {
+ uint64_t low;
+ uint16_t high;
+} floatx80;
+#define make_floatx80(exp, mant) ((floatx80) { mant, exp })
+#define make_floatx80_init(exp, mant) { .low = mant, .high = exp }
+typedef struct {
+#ifdef HOST_WORDS_BIGENDIAN
+ uint64_t high, low;
+#else
+ uint64_t low, high;
+#endif
+} float128;
+#define make_float128(high_, low_) ((float128) { .high = high_, .low = low_ })
+#define make_float128_init(high_, low_) { .high = high_, .low = low_ }
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE floating-point underflow tininess-detection mode.
+*----------------------------------------------------------------------------*/
+enum {
+ float_tininess_after_rounding = 0,
+ float_tininess_before_rounding = 1
+};
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE floating-point rounding mode.
+*----------------------------------------------------------------------------*/
+enum {
+ float_round_nearest_even = 0,
+ float_round_down = 1,
+ float_round_up = 2,
+ float_round_to_zero = 3
+};
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE floating-point exception flags.
+*----------------------------------------------------------------------------*/
+enum {
+ float_flag_invalid = 1,
+ float_flag_divbyzero = 4,
+ float_flag_overflow = 8,
+ float_flag_underflow = 16,
+ float_flag_inexact = 32,
+ float_flag_input_denormal = 64,
+ float_flag_output_denormal = 128
+};
+
+typedef struct float_status {
+ signed char float_detect_tininess;
+ signed char float_rounding_mode;
+ signed char float_exception_flags;
+ signed char floatx80_rounding_precision;
+ /* should denormalised results go to zero and set the inexact flag? */
+ flag flush_to_zero;
+ /* should denormalised inputs go to zero and set the input_denormal flag? */
+ flag flush_inputs_to_zero;
+ flag default_nan_mode;
+} float_status;
+
+void set_float_rounding_mode(int val STATUS_PARAM);
+void set_float_exception_flags(int val STATUS_PARAM);
+INLINE void set_float_detect_tininess(int val STATUS_PARAM)
+{
+ STATUS(float_detect_tininess) = val;
+}
+INLINE void set_flush_to_zero(flag val STATUS_PARAM)
+{
+ STATUS(flush_to_zero) = val;
+}
+INLINE void set_flush_inputs_to_zero(flag val STATUS_PARAM)
+{
+ STATUS(flush_inputs_to_zero) = val;
+}
+INLINE void set_default_nan_mode(flag val STATUS_PARAM)
+{
+ STATUS(default_nan_mode) = val;
+}
+INLINE int get_float_exception_flags(float_status *status)
+{
+ return STATUS(float_exception_flags);
+}
+void set_floatx80_rounding_precision(int val STATUS_PARAM);
+
+/*----------------------------------------------------------------------------
+| Routine to raise any or all of the software IEC/IEEE floating-point
+| exception flags.
+*----------------------------------------------------------------------------*/
+void float_raise( int8 flags STATUS_PARAM);
+
+/*----------------------------------------------------------------------------
+| Options to indicate which negations to perform in float*_muladd()
+| Using these differs from negating an input or output before calling
+| the muladd function in that this means that a NaN doesn't have its
+| sign bit inverted before it is propagated.
+*----------------------------------------------------------------------------*/
+enum {
+ float_muladd_negate_c = 1,
+ float_muladd_negate_product = 2,
+ float_muladd_negate_result = 4,
+};
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE integer-to-floating-point conversion routines.
+*----------------------------------------------------------------------------*/
+float32 int32_to_float32( int32 STATUS_PARAM );
+float64 int32_to_float64( int32 STATUS_PARAM );
+float32 uint32_to_float32( uint32 STATUS_PARAM );
+float64 uint32_to_float64( uint32 STATUS_PARAM );
+floatx80 int32_to_floatx80( int32 STATUS_PARAM );
+float128 int32_to_float128( int32 STATUS_PARAM );
+float32 int64_to_float32( int64 STATUS_PARAM );
+float32 uint64_to_float32( uint64 STATUS_PARAM );
+float64 int64_to_float64( int64 STATUS_PARAM );
+float64 uint64_to_float64( uint64 STATUS_PARAM );
+floatx80 int64_to_floatx80( int64 STATUS_PARAM );
+float128 int64_to_float128( int64 STATUS_PARAM );
+float128 uint64_to_float128( uint64 STATUS_PARAM );
+
+/*----------------------------------------------------------------------------
+| Software half-precision conversion routines.
+*----------------------------------------------------------------------------*/
+float16 float32_to_float16( float32, flag STATUS_PARAM );
+float32 float16_to_float32( float16, flag STATUS_PARAM );
+
+/*----------------------------------------------------------------------------
+| Software half-precision operations.
+*----------------------------------------------------------------------------*/
+int float16_is_quiet_nan( float16 );
+int float16_is_signaling_nan( float16 );
+float16 float16_maybe_silence_nan( float16 );
+
+INLINE int float16_is_any_nan(float16 a)
+{
+ return ((float16_val(a) & ~0x8000) > 0x7c00);
+}
+
+/*----------------------------------------------------------------------------
+| The pattern for a default generated half-precision NaN.
+*----------------------------------------------------------------------------*/
+extern const float16 float16_default_nan;
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE single-precision conversion routines.
+*----------------------------------------------------------------------------*/
+int_fast16_t float32_to_int16_round_to_zero(float32 STATUS_PARAM);
+uint_fast16_t float32_to_uint16_round_to_zero(float32 STATUS_PARAM);
+int32 float32_to_int32( float32 STATUS_PARAM );
+int32 float32_to_int32_round_to_zero( float32 STATUS_PARAM );
+uint32 float32_to_uint32( float32 STATUS_PARAM );
+uint32 float32_to_uint32_round_to_zero( float32 STATUS_PARAM );
+int64 float32_to_int64( float32 STATUS_PARAM );
+int64 float32_to_int64_round_to_zero( float32 STATUS_PARAM );
+float64 float32_to_float64( float32 STATUS_PARAM );
+floatx80 float32_to_floatx80( float32 STATUS_PARAM );
+float128 float32_to_float128( float32 STATUS_PARAM );
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE single-precision operations.
+*----------------------------------------------------------------------------*/
+float32 float32_round_to_int( float32 STATUS_PARAM );
+float32 float32_add( float32, float32 STATUS_PARAM );
+float32 float32_sub( float32, float32 STATUS_PARAM );
+float32 float32_mul( float32, float32 STATUS_PARAM );
+float32 float32_div( float32, float32 STATUS_PARAM );
+float32 float32_rem( float32, float32 STATUS_PARAM );
+float32 float32_muladd(float32, float32, float32, int STATUS_PARAM);
+float32 float32_sqrt( float32 STATUS_PARAM );
+float32 float32_exp2( float32 STATUS_PARAM );
+float32 float32_log2( float32 STATUS_PARAM );
+int float32_eq( float32, float32 STATUS_PARAM );
+int float32_le( float32, float32 STATUS_PARAM );
+int float32_lt( float32, float32 STATUS_PARAM );
+int float32_unordered( float32, float32 STATUS_PARAM );
+int float32_eq_quiet( float32, float32 STATUS_PARAM );
+int float32_le_quiet( float32, float32 STATUS_PARAM );
+int float32_lt_quiet( float32, float32 STATUS_PARAM );
+int float32_unordered_quiet( float32, float32 STATUS_PARAM );
+int float32_compare( float32, float32 STATUS_PARAM );
+int float32_compare_quiet( float32, float32 STATUS_PARAM );
+float32 float32_min(float32, float32 STATUS_PARAM);
+float32 float32_max(float32, float32 STATUS_PARAM);
+int float32_is_quiet_nan( float32 );
+int float32_is_signaling_nan( float32 );
+float32 float32_maybe_silence_nan( float32 );
+float32 float32_scalbn( float32, int STATUS_PARAM );
+
+INLINE float32 float32_abs(float32 a)
+{
+ /* Note that abs does *not* handle NaN specially, nor does
+ * it flush denormal inputs to zero.
+ */
+ return make_float32(float32_val(a) & 0x7fffffff);
+}
+
+INLINE float32 float32_chs(float32 a)
+{
+ /* Note that chs does *not* handle NaN specially, nor does
+ * it flush denormal inputs to zero.
+ */
+ return make_float32(float32_val(a) ^ 0x80000000);
+}
+
+INLINE int float32_is_infinity(float32 a)
+{
+ return (float32_val(a) & 0x7fffffff) == 0x7f800000;
+}
+
+INLINE int float32_is_neg(float32 a)
+{
+ return float32_val(a) >> 31;
+}
+
+INLINE int float32_is_zero(float32 a)
+{
+ return (float32_val(a) & 0x7fffffff) == 0;
+}
+
+INLINE int float32_is_any_nan(float32 a)
+{
+ return ((float32_val(a) & ~(1 << 31)) > 0x7f800000UL);
+}
+
+INLINE int float32_is_zero_or_denormal(float32 a)
+{
+ return (float32_val(a) & 0x7f800000) == 0;
+}
+
+INLINE float32 float32_set_sign(float32 a, int sign)
+{
+ return make_float32((float32_val(a) & 0x7fffffff) | (sign << 31));
+}
+
+#define float32_zero make_float32(0)
+#define float32_one make_float32(0x3f800000)
+#define float32_ln2 make_float32(0x3f317218)
+#define float32_pi make_float32(0x40490fdb)
+#define float32_half make_float32(0x3f000000)
+#define float32_infinity make_float32(0x7f800000)
+
+
+/*----------------------------------------------------------------------------
+| The pattern for a default generated single-precision NaN.
+*----------------------------------------------------------------------------*/
+extern const float32 float32_default_nan;
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE double-precision conversion routines.
+*----------------------------------------------------------------------------*/
+int_fast16_t float64_to_int16_round_to_zero(float64 STATUS_PARAM);
+uint_fast16_t float64_to_uint16_round_to_zero(float64 STATUS_PARAM);
+int32 float64_to_int32( float64 STATUS_PARAM );
+int32 float64_to_int32_round_to_zero( float64 STATUS_PARAM );
+uint32 float64_to_uint32( float64 STATUS_PARAM );
+uint32 float64_to_uint32_round_to_zero( float64 STATUS_PARAM );
+int64 float64_to_int64( float64 STATUS_PARAM );
+int64 float64_to_int64_round_to_zero( float64 STATUS_PARAM );
+uint64 float64_to_uint64 (float64 a STATUS_PARAM);
+uint64 float64_to_uint64_round_to_zero (float64 a STATUS_PARAM);
+float32 float64_to_float32( float64 STATUS_PARAM );
+floatx80 float64_to_floatx80( float64 STATUS_PARAM );
+float128 float64_to_float128( float64 STATUS_PARAM );
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE double-precision operations.
+*----------------------------------------------------------------------------*/
+float64 float64_round_to_int( float64 STATUS_PARAM );
+float64 float64_trunc_to_int( float64 STATUS_PARAM );
+float64 float64_add( float64, float64 STATUS_PARAM );
+float64 float64_sub( float64, float64 STATUS_PARAM );
+float64 float64_mul( float64, float64 STATUS_PARAM );
+float64 float64_div( float64, float64 STATUS_PARAM );
+float64 float64_rem( float64, float64 STATUS_PARAM );
+float64 float64_muladd(float64, float64, float64, int STATUS_PARAM);
+float64 float64_sqrt( float64 STATUS_PARAM );
+float64 float64_log2( float64 STATUS_PARAM );
+int float64_eq( float64, float64 STATUS_PARAM );
+int float64_le( float64, float64 STATUS_PARAM );
+int float64_lt( float64, float64 STATUS_PARAM );
+int float64_unordered( float64, float64 STATUS_PARAM );
+int float64_eq_quiet( float64, float64 STATUS_PARAM );
+int float64_le_quiet( float64, float64 STATUS_PARAM );
+int float64_lt_quiet( float64, float64 STATUS_PARAM );
+int float64_unordered_quiet( float64, float64 STATUS_PARAM );
+int float64_compare( float64, float64 STATUS_PARAM );
+int float64_compare_quiet( float64, float64 STATUS_PARAM );
+float64 float64_min(float64, float64 STATUS_PARAM);
+float64 float64_max(float64, float64 STATUS_PARAM);
+int float64_is_quiet_nan( float64 a );
+int float64_is_signaling_nan( float64 );
+float64 float64_maybe_silence_nan( float64 );
+float64 float64_scalbn( float64, int STATUS_PARAM );
+
+INLINE float64 float64_abs(float64 a)
+{
+ /* Note that abs does *not* handle NaN specially, nor does
+ * it flush denormal inputs to zero.
+ */
+ return make_float64(float64_val(a) & 0x7fffffffffffffffLL);
+}
+
+INLINE float64 float64_chs(float64 a)
+{
+ /* Note that chs does *not* handle NaN specially, nor does
+ * it flush denormal inputs to zero.
+ */
+ return make_float64(float64_val(a) ^ 0x8000000000000000LL);
+}
+
+INLINE int float64_is_infinity(float64 a)
+{
+ return (float64_val(a) & 0x7fffffffffffffffLL ) == 0x7ff0000000000000LL;
+}
+
+INLINE int float64_is_neg(float64 a)
+{
+ return float64_val(a) >> 63;
+}
+
+INLINE int float64_is_zero(float64 a)
+{
+ return (float64_val(a) & 0x7fffffffffffffffLL) == 0;
+}
+
+INLINE int float64_is_any_nan(float64 a)
+{
+ return ((float64_val(a) & ~(1ULL << 63)) > 0x7ff0000000000000ULL);
+}
+
+INLINE int float64_is_zero_or_denormal(float64 a)
+{
+ return (float64_val(a) & 0x7ff0000000000000LL) == 0;
+}
+
+INLINE float64 float64_set_sign(float64 a, int sign)
+{
+ return make_float64((float64_val(a) & 0x7fffffffffffffffULL)
+ | ((int64_t)sign << 63));
+}
+
+#define float64_zero make_float64(0)
+#define float64_one make_float64(0x3ff0000000000000LL)
+#define float64_ln2 make_float64(0x3fe62e42fefa39efLL)
+#define float64_pi make_float64(0x400921fb54442d18LL)
+#define float64_half make_float64(0x3fe0000000000000LL)
+#define float64_infinity make_float64(0x7ff0000000000000LL)
+
+/*----------------------------------------------------------------------------
+| The pattern for a default generated double-precision NaN.
+*----------------------------------------------------------------------------*/
+extern const float64 float64_default_nan;
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE extended double-precision conversion routines.
+*----------------------------------------------------------------------------*/
+int32 floatx80_to_int32( floatx80 STATUS_PARAM );
+int32 floatx80_to_int32_round_to_zero( floatx80 STATUS_PARAM );
+int64 floatx80_to_int64( floatx80 STATUS_PARAM );
+int64 floatx80_to_int64_round_to_zero( floatx80 STATUS_PARAM );
+float32 floatx80_to_float32( floatx80 STATUS_PARAM );
+float64 floatx80_to_float64( floatx80 STATUS_PARAM );
+float128 floatx80_to_float128( floatx80 STATUS_PARAM );
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE extended double-precision operations.
+*----------------------------------------------------------------------------*/
+floatx80 floatx80_round_to_int( floatx80 STATUS_PARAM );
+floatx80 floatx80_add( floatx80, floatx80 STATUS_PARAM );
+floatx80 floatx80_sub( floatx80, floatx80 STATUS_PARAM );
+floatx80 floatx80_mul( floatx80, floatx80 STATUS_PARAM );
+floatx80 floatx80_div( floatx80, floatx80 STATUS_PARAM );
+floatx80 floatx80_rem( floatx80, floatx80 STATUS_PARAM );
+floatx80 floatx80_sqrt( floatx80 STATUS_PARAM );
+int floatx80_eq( floatx80, floatx80 STATUS_PARAM );
+int floatx80_le( floatx80, floatx80 STATUS_PARAM );
+int floatx80_lt( floatx80, floatx80 STATUS_PARAM );
+int floatx80_unordered( floatx80, floatx80 STATUS_PARAM );
+int floatx80_eq_quiet( floatx80, floatx80 STATUS_PARAM );
+int floatx80_le_quiet( floatx80, floatx80 STATUS_PARAM );
+int floatx80_lt_quiet( floatx80, floatx80 STATUS_PARAM );
+int floatx80_unordered_quiet( floatx80, floatx80 STATUS_PARAM );
+int floatx80_compare( floatx80, floatx80 STATUS_PARAM );
+int floatx80_compare_quiet( floatx80, floatx80 STATUS_PARAM );
+int floatx80_is_quiet_nan( floatx80 );
+int floatx80_is_signaling_nan( floatx80 );
+floatx80 floatx80_maybe_silence_nan( floatx80 );
+floatx80 floatx80_scalbn( floatx80, int STATUS_PARAM );
+
+INLINE floatx80 floatx80_abs(floatx80 a)
+{
+ a.high &= 0x7fff;
+ return a;
+}
+
+INLINE floatx80 floatx80_chs(floatx80 a)
+{
+ a.high ^= 0x8000;
+ return a;
+}
+
+INLINE int floatx80_is_infinity(floatx80 a)
+{
+ return (a.high & 0x7fff) == 0x7fff && a.low == 0x8000000000000000LL;
+}
+
+INLINE int floatx80_is_neg(floatx80 a)
+{
+ return a.high >> 15;
+}
+
+INLINE int floatx80_is_zero(floatx80 a)
+{
+ return (a.high & 0x7fff) == 0 && a.low == 0;
+}
+
+INLINE int floatx80_is_zero_or_denormal(floatx80 a)
+{
+ return (a.high & 0x7fff) == 0;
+}
+
+INLINE int floatx80_is_any_nan(floatx80 a)
+{
+ return ((a.high & 0x7fff) == 0x7fff) && (a.low<<1);
+}
+
+#define floatx80_zero make_floatx80(0x0000, 0x0000000000000000LL)
+#define floatx80_one make_floatx80(0x3fff, 0x8000000000000000LL)
+#define floatx80_ln2 make_floatx80(0x3ffe, 0xb17217f7d1cf79acLL)
+#define floatx80_pi make_floatx80(0x4000, 0xc90fdaa22168c235LL)
+#define floatx80_half make_floatx80(0x3ffe, 0x8000000000000000LL)
+#define floatx80_infinity make_floatx80(0x7fff, 0x8000000000000000LL)
+
+/*----------------------------------------------------------------------------
+| The pattern for a default generated extended double-precision NaN.
+*----------------------------------------------------------------------------*/
+extern const floatx80 floatx80_default_nan;
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE quadruple-precision conversion routines.
+*----------------------------------------------------------------------------*/
+int32 float128_to_int32( float128 STATUS_PARAM );
+int32 float128_to_int32_round_to_zero( float128 STATUS_PARAM );
+int64 float128_to_int64( float128 STATUS_PARAM );
+int64 float128_to_int64_round_to_zero( float128 STATUS_PARAM );
+float32 float128_to_float32( float128 STATUS_PARAM );
+float64 float128_to_float64( float128 STATUS_PARAM );
+floatx80 float128_to_floatx80( float128 STATUS_PARAM );
+
+/*----------------------------------------------------------------------------
+| Software IEC/IEEE quadruple-precision operations.
+*----------------------------------------------------------------------------*/
+float128 float128_round_to_int( float128 STATUS_PARAM );
+float128 float128_add( float128, float128 STATUS_PARAM );
+float128 float128_sub( float128, float128 STATUS_PARAM );
+float128 float128_mul( float128, float128 STATUS_PARAM );
+float128 float128_div( float128, float128 STATUS_PARAM );
+float128 float128_rem( float128, float128 STATUS_PARAM );
+float128 float128_sqrt( float128 STATUS_PARAM );
+int float128_eq( float128, float128 STATUS_PARAM );
+int float128_le( float128, float128 STATUS_PARAM );
+int float128_lt( float128, float128 STATUS_PARAM );
+int float128_unordered( float128, float128 STATUS_PARAM );
+int float128_eq_quiet( float128, float128 STATUS_PARAM );
+int float128_le_quiet( float128, float128 STATUS_PARAM );
+int float128_lt_quiet( float128, float128 STATUS_PARAM );
+int float128_unordered_quiet( float128, float128 STATUS_PARAM );
+int float128_compare( float128, float128 STATUS_PARAM );
+int float128_compare_quiet( float128, float128 STATUS_PARAM );
+int float128_is_quiet_nan( float128 );
+int float128_is_signaling_nan( float128 );
+float128 float128_maybe_silence_nan( float128 );
+float128 float128_scalbn( float128, int STATUS_PARAM );
+
+INLINE float128 float128_abs(float128 a)
+{
+ a.high &= 0x7fffffffffffffffLL;
+ return a;
+}
+
+INLINE float128 float128_chs(float128 a)
+{
+ a.high ^= 0x8000000000000000LL;
+ return a;
+}
+
+INLINE int float128_is_infinity(float128 a)
+{
+ return (a.high & 0x7fffffffffffffffLL) == 0x7fff000000000000LL && a.low == 0;
+}
+
+INLINE int float128_is_neg(float128 a)
+{
+ return a.high >> 63;
+}
+
+INLINE int float128_is_zero(float128 a)
+{
+ return (a.high & 0x7fffffffffffffffLL) == 0 && a.low == 0;
+}
+
+INLINE int float128_is_zero_or_denormal(float128 a)
+{
+ return (a.high & 0x7fff000000000000LL) == 0;
+}
+
+INLINE int float128_is_any_nan(float128 a)
+{
+ return ((a.high >> 48) & 0x7fff) == 0x7fff &&
+ ((a.low != 0) || ((a.high & 0xffffffffffffLL) != 0));
+}
+
+#define float128_zero make_float128(0, 0)
+
+/*----------------------------------------------------------------------------
+| The pattern for a default generated quadruple-precision NaN.
+*----------------------------------------------------------------------------*/
+extern const float128 float128_default_nan;
+
+#endif /* !SOFTFLOAT_H */
diff --git a/contrib/qemu/include/glib-compat.h b/contrib/qemu/include/glib-compat.h
new file mode 100644
index 00000000000..8aa77afd626
--- /dev/null
+++ b/contrib/qemu/include/glib-compat.h
@@ -0,0 +1,27 @@
+/*
+ * GLIB Compatibility Functions
+ *
+ * Copyright IBM, Corp. 2013
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_GLIB_COMPAT_H
+#define QEMU_GLIB_COMPAT_H
+
+#include <glib.h>
+
+#if !GLIB_CHECK_VERSION(2, 14, 0)
+static inline guint g_timeout_add_seconds(guint interval, GSourceFunc function,
+ gpointer data)
+{
+ return g_timeout_add(interval * 1000, function, data);
+}
+#endif
+
+#endif
diff --git a/contrib/qemu/include/migration/migration.h b/contrib/qemu/include/migration/migration.h
new file mode 100644
index 00000000000..bc9fde0b2ab
--- /dev/null
+++ b/contrib/qemu/include/migration/migration.h
@@ -0,0 +1,157 @@
+/*
+ * QEMU live migration
+ *
+ * Copyright IBM, Corp. 2008
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_MIGRATION_H
+#define QEMU_MIGRATION_H
+
+#include "qapi/qmp/qdict.h"
+#include "qemu-common.h"
+#include "qemu/thread.h"
+#include "qemu/notify.h"
+#include "qapi/error.h"
+#include "migration/vmstate.h"
+#include "qapi-types.h"
+#include "exec/cpu-common.h"
+
+struct MigrationParams {
+ bool blk;
+ bool shared;
+};
+
+typedef struct MigrationState MigrationState;
+
+struct MigrationState
+{
+ int64_t bandwidth_limit;
+ size_t bytes_xfer;
+ size_t xfer_limit;
+ QemuThread thread;
+ QEMUBH *cleanup_bh;
+ QEMUFile *file;
+
+ int state;
+ MigrationParams params;
+ double mbps;
+ int64_t total_time;
+ int64_t downtime;
+ int64_t expected_downtime;
+ int64_t dirty_pages_rate;
+ int64_t dirty_bytes_rate;
+ bool enabled_capabilities[MIGRATION_CAPABILITY_MAX];
+ int64_t xbzrle_cache_size;
+};
+
+void process_incoming_migration(QEMUFile *f);
+
+void qemu_start_incoming_migration(const char *uri, Error **errp);
+
+uint64_t migrate_max_downtime(void);
+
+void do_info_migrate_print(Monitor *mon, const QObject *data);
+
+void do_info_migrate(Monitor *mon, QObject **ret_data);
+
+void exec_start_incoming_migration(const char *host_port, Error **errp);
+
+void exec_start_outgoing_migration(MigrationState *s, const char *host_port, Error **errp);
+
+void tcp_start_incoming_migration(const char *host_port, Error **errp);
+
+void tcp_start_outgoing_migration(MigrationState *s, const char *host_port, Error **errp);
+
+void unix_start_incoming_migration(const char *path, Error **errp);
+
+void unix_start_outgoing_migration(MigrationState *s, const char *path, Error **errp);
+
+void fd_start_incoming_migration(const char *path, Error **errp);
+
+void fd_start_outgoing_migration(MigrationState *s, const char *fdname, Error **errp);
+
+void migrate_fd_error(MigrationState *s);
+
+void migrate_fd_connect(MigrationState *s);
+
+int migrate_fd_close(MigrationState *s);
+
+void add_migration_state_change_notifier(Notifier *notify);
+void remove_migration_state_change_notifier(Notifier *notify);
+bool migration_is_active(MigrationState *);
+bool migration_has_finished(MigrationState *);
+bool migration_has_failed(MigrationState *);
+MigrationState *migrate_get_current(void);
+
+uint64_t ram_bytes_remaining(void);
+uint64_t ram_bytes_transferred(void);
+uint64_t ram_bytes_total(void);
+
+void acct_update_position(QEMUFile *f, size_t size, bool zero);
+
+extern SaveVMHandlers savevm_ram_handlers;
+
+uint64_t dup_mig_bytes_transferred(void);
+uint64_t dup_mig_pages_transferred(void);
+uint64_t skipped_mig_bytes_transferred(void);
+uint64_t skipped_mig_pages_transferred(void);
+uint64_t norm_mig_bytes_transferred(void);
+uint64_t norm_mig_pages_transferred(void);
+uint64_t xbzrle_mig_bytes_transferred(void);
+uint64_t xbzrle_mig_pages_transferred(void);
+uint64_t xbzrle_mig_pages_overflow(void);
+uint64_t xbzrle_mig_pages_cache_miss(void);
+
+/**
+ * @migrate_add_blocker - prevent migration from proceeding
+ *
+ * @reason - an error to be returned whenever migration is attempted
+ */
+void migrate_add_blocker(Error *reason);
+
+/**
+ * @migrate_del_blocker - remove a blocking error from migration
+ *
+ * @reason - the error blocking migration
+ */
+void migrate_del_blocker(Error *reason);
+
+bool migrate_rdma_pin_all(void);
+
+bool migrate_auto_converge(void);
+
+int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen,
+ uint8_t *dst, int dlen);
+int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen);
+
+int migrate_use_xbzrle(void);
+int64_t migrate_xbzrle_cache_size(void);
+
+int64_t xbzrle_cache_resize(int64_t new_size);
+
+void ram_control_before_iterate(QEMUFile *f, uint64_t flags);
+void ram_control_after_iterate(QEMUFile *f, uint64_t flags);
+void ram_control_load_hook(QEMUFile *f, uint64_t flags);
+
+/* Whenever this is found in the data stream, the flags
+ * will be passed to ram_control_load_hook in the incoming-migration
+ * side. This lets before_ram_iterate/after_ram_iterate add
+ * transport-specific sections to the RAM migration data.
+ */
+#define RAM_SAVE_FLAG_HOOK 0x80
+
+#define RAM_SAVE_CONTROL_NOT_SUPP -1000
+#define RAM_SAVE_CONTROL_DELAYED -2000
+
+size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset,
+ ram_addr_t offset, size_t size,
+ int *bytes_sent);
+
+#endif
diff --git a/contrib/qemu/include/migration/qemu-file.h b/contrib/qemu/include/migration/qemu-file.h
new file mode 100644
index 00000000000..0f757fbeb63
--- /dev/null
+++ b/contrib/qemu/include/migration/qemu-file.h
@@ -0,0 +1,266 @@
+/*
+ * QEMU System Emulator
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef QEMU_FILE_H
+#define QEMU_FILE_H 1
+#include "exec/cpu-common.h"
+
+/* This function writes a chunk of data to a file at the given position.
+ * The pos argument can be ignored if the file is only being used for
+ * streaming. The handler should try to write all of the data it can.
+ */
+typedef int (QEMUFilePutBufferFunc)(void *opaque, const uint8_t *buf,
+ int64_t pos, int size);
+
+/* Read a chunk of data from a file at the given position. The pos argument
+ * can be ignored if the file is only be used for streaming. The number of
+ * bytes actually read should be returned.
+ */
+typedef int (QEMUFileGetBufferFunc)(void *opaque, uint8_t *buf,
+ int64_t pos, int size);
+
+/* Close a file
+ *
+ * Return negative error number on error, 0 or positive value on success.
+ *
+ * The meaning of return value on success depends on the specific back-end being
+ * used.
+ */
+typedef int (QEMUFileCloseFunc)(void *opaque);
+
+/* Called to return the OS file descriptor associated to the QEMUFile.
+ */
+typedef int (QEMUFileGetFD)(void *opaque);
+
+/*
+ * This function writes an iovec to file.
+ */
+typedef ssize_t (QEMUFileWritevBufferFunc)(void *opaque, struct iovec *iov,
+ int iovcnt, int64_t pos);
+
+/*
+ * This function provides hooks around different
+ * stages of RAM migration.
+ */
+typedef int (QEMURamHookFunc)(QEMUFile *f, void *opaque, uint64_t flags);
+
+/*
+ * Constants used by ram_control_* hooks
+ */
+#define RAM_CONTROL_SETUP 0
+#define RAM_CONTROL_ROUND 1
+#define RAM_CONTROL_HOOK 2
+#define RAM_CONTROL_FINISH 3
+
+/*
+ * This function allows override of where the RAM page
+ * is saved (such as RDMA, for example.)
+ */
+typedef size_t (QEMURamSaveFunc)(QEMUFile *f, void *opaque,
+ ram_addr_t block_offset,
+ ram_addr_t offset,
+ size_t size,
+ int *bytes_sent);
+
+typedef struct QEMUFileOps {
+ QEMUFilePutBufferFunc *put_buffer;
+ QEMUFileGetBufferFunc *get_buffer;
+ QEMUFileCloseFunc *close;
+ QEMUFileGetFD *get_fd;
+ QEMUFileWritevBufferFunc *writev_buffer;
+ QEMURamHookFunc *before_ram_iterate;
+ QEMURamHookFunc *after_ram_iterate;
+ QEMURamHookFunc *hook_ram_load;
+ QEMURamSaveFunc *save_page;
+} QEMUFileOps;
+
+QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops);
+QEMUFile *qemu_fopen(const char *filename, const char *mode);
+QEMUFile *qemu_fdopen(int fd, const char *mode);
+QEMUFile *qemu_fopen_socket(int fd, const char *mode);
+QEMUFile *qemu_popen_cmd(const char *command, const char *mode);
+int qemu_get_fd(QEMUFile *f);
+int qemu_fclose(QEMUFile *f);
+int64_t qemu_ftell(QEMUFile *f);
+void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, int size);
+void qemu_put_byte(QEMUFile *f, int v);
+/*
+ * put_buffer without copying the buffer.
+ * The buffer should be available till it is sent asynchronously.
+ */
+void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, int size);
+bool qemu_file_mode_is_not_valid(const char *mode);
+
+static inline void qemu_put_ubyte(QEMUFile *f, unsigned int v)
+{
+ qemu_put_byte(f, (int)v);
+}
+
+#define qemu_put_sbyte qemu_put_byte
+
+void qemu_put_be16(QEMUFile *f, unsigned int v);
+void qemu_put_be32(QEMUFile *f, unsigned int v);
+void qemu_put_be64(QEMUFile *f, uint64_t v);
+int qemu_get_buffer(QEMUFile *f, uint8_t *buf, int size);
+int qemu_get_byte(QEMUFile *f);
+void qemu_update_position(QEMUFile *f, size_t size);
+
+static inline unsigned int qemu_get_ubyte(QEMUFile *f)
+{
+ return (unsigned int)qemu_get_byte(f);
+}
+
+#define qemu_get_sbyte qemu_get_byte
+
+unsigned int qemu_get_be16(QEMUFile *f);
+unsigned int qemu_get_be32(QEMUFile *f);
+uint64_t qemu_get_be64(QEMUFile *f);
+
+int qemu_file_rate_limit(QEMUFile *f);
+void qemu_file_reset_rate_limit(QEMUFile *f);
+void qemu_file_set_rate_limit(QEMUFile *f, int64_t new_rate);
+int64_t qemu_file_get_rate_limit(QEMUFile *f);
+int qemu_file_get_error(QEMUFile *f);
+void qemu_fflush(QEMUFile *f);
+
+static inline void qemu_put_be64s(QEMUFile *f, const uint64_t *pv)
+{
+ qemu_put_be64(f, *pv);
+}
+
+static inline void qemu_put_be32s(QEMUFile *f, const uint32_t *pv)
+{
+ qemu_put_be32(f, *pv);
+}
+
+static inline void qemu_put_be16s(QEMUFile *f, const uint16_t *pv)
+{
+ qemu_put_be16(f, *pv);
+}
+
+static inline void qemu_put_8s(QEMUFile *f, const uint8_t *pv)
+{
+ qemu_put_byte(f, *pv);
+}
+
+static inline void qemu_get_be64s(QEMUFile *f, uint64_t *pv)
+{
+ *pv = qemu_get_be64(f);
+}
+
+static inline void qemu_get_be32s(QEMUFile *f, uint32_t *pv)
+{
+ *pv = qemu_get_be32(f);
+}
+
+static inline void qemu_get_be16s(QEMUFile *f, uint16_t *pv)
+{
+ *pv = qemu_get_be16(f);
+}
+
+static inline void qemu_get_8s(QEMUFile *f, uint8_t *pv)
+{
+ *pv = qemu_get_byte(f);
+}
+
+// Signed versions for type safety
+static inline void qemu_put_sbuffer(QEMUFile *f, const int8_t *buf, int size)
+{
+ qemu_put_buffer(f, (const uint8_t *)buf, size);
+}
+
+static inline void qemu_put_sbe16(QEMUFile *f, int v)
+{
+ qemu_put_be16(f, (unsigned int)v);
+}
+
+static inline void qemu_put_sbe32(QEMUFile *f, int v)
+{
+ qemu_put_be32(f, (unsigned int)v);
+}
+
+static inline void qemu_put_sbe64(QEMUFile *f, int64_t v)
+{
+ qemu_put_be64(f, (uint64_t)v);
+}
+
+static inline size_t qemu_get_sbuffer(QEMUFile *f, int8_t *buf, int size)
+{
+ return qemu_get_buffer(f, (uint8_t *)buf, size);
+}
+
+static inline int qemu_get_sbe16(QEMUFile *f)
+{
+ return (int)qemu_get_be16(f);
+}
+
+static inline int qemu_get_sbe32(QEMUFile *f)
+{
+ return (int)qemu_get_be32(f);
+}
+
+static inline int64_t qemu_get_sbe64(QEMUFile *f)
+{
+ return (int64_t)qemu_get_be64(f);
+}
+
+static inline void qemu_put_s8s(QEMUFile *f, const int8_t *pv)
+{
+ qemu_put_8s(f, (const uint8_t *)pv);
+}
+
+static inline void qemu_put_sbe16s(QEMUFile *f, const int16_t *pv)
+{
+ qemu_put_be16s(f, (const uint16_t *)pv);
+}
+
+static inline void qemu_put_sbe32s(QEMUFile *f, const int32_t *pv)
+{
+ qemu_put_be32s(f, (const uint32_t *)pv);
+}
+
+static inline void qemu_put_sbe64s(QEMUFile *f, const int64_t *pv)
+{
+ qemu_put_be64s(f, (const uint64_t *)pv);
+}
+
+static inline void qemu_get_s8s(QEMUFile *f, int8_t *pv)
+{
+ qemu_get_8s(f, (uint8_t *)pv);
+}
+
+static inline void qemu_get_sbe16s(QEMUFile *f, int16_t *pv)
+{
+ qemu_get_be16s(f, (uint16_t *)pv);
+}
+
+static inline void qemu_get_sbe32s(QEMUFile *f, int32_t *pv)
+{
+ qemu_get_be32s(f, (uint32_t *)pv);
+}
+
+static inline void qemu_get_sbe64s(QEMUFile *f, int64_t *pv)
+{
+ qemu_get_be64s(f, (uint64_t *)pv);
+}
+#endif
diff --git a/contrib/qemu/include/migration/vmstate.h b/contrib/qemu/include/migration/vmstate.h
new file mode 100644
index 00000000000..1c31b5d6fb5
--- /dev/null
+++ b/contrib/qemu/include/migration/vmstate.h
@@ -0,0 +1,740 @@
+/*
+ * QEMU migration/snapshot declarations
+ *
+ * Copyright (c) 2009-2011 Red Hat, Inc.
+ *
+ * Original author: Juan Quintela <quintela@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef QEMU_VMSTATE_H
+#define QEMU_VMSTATE_H 1
+
+#ifndef CONFIG_USER_ONLY
+#include <migration/qemu-file.h>
+#endif
+
+typedef void SaveStateHandler(QEMUFile *f, void *opaque);
+typedef int LoadStateHandler(QEMUFile *f, void *opaque, int version_id);
+
+typedef struct SaveVMHandlers {
+ /* This runs inside the iothread lock. */
+ void (*set_params)(const MigrationParams *params, void * opaque);
+ SaveStateHandler *save_state;
+
+ void (*cancel)(void *opaque);
+ int (*save_live_complete)(QEMUFile *f, void *opaque);
+
+ /* This runs both outside and inside the iothread lock. */
+ bool (*is_active)(void *opaque);
+
+ /* This runs outside the iothread lock in the migration case, and
+ * within the lock in the savevm case. The callback had better only
+ * use data that is local to the migration thread or protected
+ * by other locks.
+ */
+ int (*save_live_iterate)(QEMUFile *f, void *opaque);
+
+ /* This runs outside the iothread lock! */
+ int (*save_live_setup)(QEMUFile *f, void *opaque);
+ uint64_t (*save_live_pending)(QEMUFile *f, void *opaque, uint64_t max_size);
+
+ LoadStateHandler *load_state;
+} SaveVMHandlers;
+
+int register_savevm(DeviceState *dev,
+ const char *idstr,
+ int instance_id,
+ int version_id,
+ SaveStateHandler *save_state,
+ LoadStateHandler *load_state,
+ void *opaque);
+
+int register_savevm_live(DeviceState *dev,
+ const char *idstr,
+ int instance_id,
+ int version_id,
+ SaveVMHandlers *ops,
+ void *opaque);
+
+void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque);
+void register_device_unmigratable(DeviceState *dev, const char *idstr,
+ void *opaque);
+
+
+typedef struct VMStateInfo VMStateInfo;
+typedef struct VMStateDescription VMStateDescription;
+
+struct VMStateInfo {
+ const char *name;
+ int (*get)(QEMUFile *f, void *pv, size_t size);
+ void (*put)(QEMUFile *f, void *pv, size_t size);
+};
+
+enum VMStateFlags {
+ VMS_SINGLE = 0x001,
+ VMS_POINTER = 0x002,
+ VMS_ARRAY = 0x004,
+ VMS_STRUCT = 0x008,
+ VMS_VARRAY_INT32 = 0x010, /* Array with size in int32_t field*/
+ VMS_BUFFER = 0x020, /* static sized buffer */
+ VMS_ARRAY_OF_POINTER = 0x040,
+ VMS_VARRAY_UINT16 = 0x080, /* Array with size in uint16_t field */
+ VMS_VBUFFER = 0x100, /* Buffer with size in int32_t field */
+ VMS_MULTIPLY = 0x200, /* multiply "size" field by field_size */
+ VMS_VARRAY_UINT8 = 0x400, /* Array with size in uint8_t field*/
+ VMS_VARRAY_UINT32 = 0x800, /* Array with size in uint32_t field*/
+};
+
+typedef struct {
+ const char *name;
+ size_t offset;
+ size_t size;
+ size_t start;
+ int num;
+ size_t num_offset;
+ size_t size_offset;
+ const VMStateInfo *info;
+ enum VMStateFlags flags;
+ const VMStateDescription *vmsd;
+ int version_id;
+ bool (*field_exists)(void *opaque, int version_id);
+} VMStateField;
+
+typedef struct VMStateSubsection {
+ const VMStateDescription *vmsd;
+ bool (*needed)(void *opaque);
+} VMStateSubsection;
+
+struct VMStateDescription {
+ const char *name;
+ int unmigratable;
+ int version_id;
+ int minimum_version_id;
+ int minimum_version_id_old;
+ LoadStateHandler *load_state_old;
+ int (*pre_load)(void *opaque);
+ int (*post_load)(void *opaque, int version_id);
+ void (*pre_save)(void *opaque);
+ VMStateField *fields;
+ const VMStateSubsection *subsections;
+};
+
+#ifdef CONFIG_USER_ONLY
+extern const VMStateDescription vmstate_dummy;
+#endif
+
+extern const VMStateInfo vmstate_info_bool;
+
+extern const VMStateInfo vmstate_info_int8;
+extern const VMStateInfo vmstate_info_int16;
+extern const VMStateInfo vmstate_info_int32;
+extern const VMStateInfo vmstate_info_int64;
+
+extern const VMStateInfo vmstate_info_uint8_equal;
+extern const VMStateInfo vmstate_info_uint16_equal;
+extern const VMStateInfo vmstate_info_int32_equal;
+extern const VMStateInfo vmstate_info_uint32_equal;
+extern const VMStateInfo vmstate_info_uint64_equal;
+extern const VMStateInfo vmstate_info_int32_le;
+
+extern const VMStateInfo vmstate_info_uint8;
+extern const VMStateInfo vmstate_info_uint16;
+extern const VMStateInfo vmstate_info_uint32;
+extern const VMStateInfo vmstate_info_uint64;
+
+extern const VMStateInfo vmstate_info_float64;
+
+extern const VMStateInfo vmstate_info_timer;
+extern const VMStateInfo vmstate_info_buffer;
+extern const VMStateInfo vmstate_info_unused_buffer;
+extern const VMStateInfo vmstate_info_bitmap;
+
+#define type_check_2darray(t1,t2,n,m) ((t1(*)[n][m])0 - (t2*)0)
+#define type_check_array(t1,t2,n) ((t1(*)[n])0 - (t2*)0)
+#define type_check_pointer(t1,t2) ((t1**)0 - (t2*)0)
+
+#define vmstate_offset_value(_state, _field, _type) \
+ (offsetof(_state, _field) + \
+ type_check(_type, typeof_field(_state, _field)))
+
+#define vmstate_offset_pointer(_state, _field, _type) \
+ (offsetof(_state, _field) + \
+ type_check_pointer(_type, typeof_field(_state, _field)))
+
+#define vmstate_offset_array(_state, _field, _type, _num) \
+ (offsetof(_state, _field) + \
+ type_check_array(_type, typeof_field(_state, _field), _num))
+
+#define vmstate_offset_2darray(_state, _field, _type, _n1, _n2) \
+ (offsetof(_state, _field) + \
+ type_check_2darray(_type, typeof_field(_state, _field), _n1, _n2))
+
+#define vmstate_offset_sub_array(_state, _field, _type, _start) \
+ (offsetof(_state, _field[_start]))
+
+#define vmstate_offset_buffer(_state, _field) \
+ vmstate_offset_array(_state, _field, uint8_t, \
+ sizeof(typeof_field(_state, _field)))
+
+#define VMSTATE_SINGLE_TEST(_field, _state, _test, _version, _info, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .field_exists = (_test), \
+ .size = sizeof(_type), \
+ .info = &(_info), \
+ .flags = VMS_SINGLE, \
+ .offset = vmstate_offset_value(_state, _field, _type), \
+}
+
+#define VMSTATE_POINTER(_field, _state, _version, _info, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_SINGLE|VMS_POINTER, \
+ .offset = vmstate_offset_value(_state, _field, _type), \
+}
+
+#define VMSTATE_POINTER_TEST(_field, _state, _test, _info, _type) { \
+ .name = (stringify(_field)), \
+ .info = &(_info), \
+ .field_exists = (_test), \
+ .size = sizeof(_type), \
+ .flags = VMS_SINGLE|VMS_POINTER, \
+ .offset = vmstate_offset_value(_state, _field, _type), \
+}
+
+#define VMSTATE_ARRAY(_field, _state, _num, _version, _info, _type) {\
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .num = (_num), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_ARRAY, \
+ .offset = vmstate_offset_array(_state, _field, _type, _num), \
+}
+
+#define VMSTATE_2DARRAY(_field, _state, _n1, _n2, _version, _info, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .num = (_n1) * (_n2), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_ARRAY, \
+ .offset = vmstate_offset_2darray(_state, _field, _type, _n1, _n2), \
+}
+
+#define VMSTATE_ARRAY_TEST(_field, _state, _num, _test, _info, _type) {\
+ .name = (stringify(_field)), \
+ .field_exists = (_test), \
+ .num = (_num), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_ARRAY, \
+ .offset = vmstate_offset_array(_state, _field, _type, _num),\
+}
+
+#define VMSTATE_SUB_ARRAY(_field, _state, _start, _num, _version, _info, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .num = (_num), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_ARRAY, \
+ .offset = vmstate_offset_sub_array(_state, _field, _type, _start), \
+}
+
+#define VMSTATE_ARRAY_INT32_UNSAFE(_field, _state, _field_num, _info, _type) {\
+ .name = (stringify(_field)), \
+ .num_offset = vmstate_offset_value(_state, _field_num, int32_t), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_VARRAY_INT32, \
+ .offset = offsetof(_state, _field), \
+}
+
+#define VMSTATE_VARRAY_INT32(_field, _state, _field_num, _version, _info, _type) {\
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .num_offset = vmstate_offset_value(_state, _field_num, int32_t), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_VARRAY_INT32|VMS_POINTER, \
+ .offset = vmstate_offset_pointer(_state, _field, _type), \
+}
+
+#define VMSTATE_VARRAY_UINT32(_field, _state, _field_num, _version, _info, _type) {\
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .num_offset = vmstate_offset_value(_state, _field_num, uint32_t),\
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_VARRAY_UINT32|VMS_POINTER, \
+ .offset = vmstate_offset_pointer(_state, _field, _type), \
+}
+
+#define VMSTATE_VARRAY_UINT16_UNSAFE(_field, _state, _field_num, _version, _info, _type) {\
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .num_offset = vmstate_offset_value(_state, _field_num, uint16_t),\
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_VARRAY_UINT16, \
+ .offset = offsetof(_state, _field), \
+}
+
+#define VMSTATE_STRUCT_TEST(_field, _state, _test, _version, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .field_exists = (_test), \
+ .vmsd = &(_vmsd), \
+ .size = sizeof(_type), \
+ .flags = VMS_STRUCT, \
+ .offset = vmstate_offset_value(_state, _field, _type), \
+}
+
+#define VMSTATE_STRUCT_POINTER_TEST(_field, _state, _test, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .field_exists = (_test), \
+ .vmsd = &(_vmsd), \
+ .size = sizeof(_type), \
+ .flags = VMS_STRUCT|VMS_POINTER, \
+ .offset = vmstate_offset_value(_state, _field, _type), \
+}
+
+#define VMSTATE_ARRAY_OF_POINTER(_field, _state, _num, _version, _info, _type) {\
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .num = (_num), \
+ .info = &(_info), \
+ .size = sizeof(_type), \
+ .flags = VMS_ARRAY|VMS_ARRAY_OF_POINTER, \
+ .offset = vmstate_offset_array(_state, _field, _type, _num), \
+}
+
+#define VMSTATE_STRUCT_ARRAY_TEST(_field, _state, _num, _test, _version, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .num = (_num), \
+ .field_exists = (_test), \
+ .version_id = (_version), \
+ .vmsd = &(_vmsd), \
+ .size = sizeof(_type), \
+ .flags = VMS_STRUCT|VMS_ARRAY, \
+ .offset = vmstate_offset_array(_state, _field, _type, _num),\
+}
+
+#define VMSTATE_STRUCT_VARRAY_UINT8(_field, _state, _field_num, _version, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .num_offset = vmstate_offset_value(_state, _field_num, uint8_t), \
+ .version_id = (_version), \
+ .vmsd = &(_vmsd), \
+ .size = sizeof(_type), \
+ .flags = VMS_STRUCT|VMS_VARRAY_UINT8, \
+ .offset = offsetof(_state, _field), \
+}
+
+#define VMSTATE_STRUCT_VARRAY_POINTER_INT32(_field, _state, _field_num, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = 0, \
+ .num_offset = vmstate_offset_value(_state, _field_num, int32_t), \
+ .size = sizeof(_type), \
+ .vmsd = &(_vmsd), \
+ .flags = VMS_POINTER | VMS_VARRAY_INT32 | VMS_STRUCT, \
+ .offset = vmstate_offset_pointer(_state, _field, _type), \
+}
+
+#define VMSTATE_STRUCT_VARRAY_POINTER_UINT32(_field, _state, _field_num, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = 0, \
+ .num_offset = vmstate_offset_value(_state, _field_num, uint32_t),\
+ .size = sizeof(_type), \
+ .vmsd = &(_vmsd), \
+ .flags = VMS_POINTER | VMS_VARRAY_INT32 | VMS_STRUCT, \
+ .offset = vmstate_offset_pointer(_state, _field, _type), \
+}
+
+#define VMSTATE_STRUCT_VARRAY_POINTER_UINT16(_field, _state, _field_num, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .version_id = 0, \
+ .num_offset = vmstate_offset_value(_state, _field_num, uint16_t),\
+ .size = sizeof(_type), \
+ .vmsd = &(_vmsd), \
+ .flags = VMS_POINTER | VMS_VARRAY_UINT16 | VMS_STRUCT, \
+ .offset = vmstate_offset_pointer(_state, _field, _type), \
+}
+
+#define VMSTATE_STRUCT_VARRAY_INT32(_field, _state, _field_num, _version, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .num_offset = vmstate_offset_value(_state, _field_num, int32_t), \
+ .version_id = (_version), \
+ .vmsd = &(_vmsd), \
+ .size = sizeof(_type), \
+ .flags = VMS_STRUCT|VMS_VARRAY_INT32, \
+ .offset = offsetof(_state, _field), \
+}
+
+#define VMSTATE_STRUCT_VARRAY_UINT32(_field, _state, _field_num, _version, _vmsd, _type) { \
+ .name = (stringify(_field)), \
+ .num_offset = vmstate_offset_value(_state, _field_num, uint32_t), \
+ .version_id = (_version), \
+ .vmsd = &(_vmsd), \
+ .size = sizeof(_type), \
+ .flags = VMS_STRUCT|VMS_VARRAY_UINT32, \
+ .offset = offsetof(_state, _field), \
+}
+
+#define VMSTATE_STATIC_BUFFER(_field, _state, _version, _test, _start, _size) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .field_exists = (_test), \
+ .size = (_size - _start), \
+ .info = &vmstate_info_buffer, \
+ .flags = VMS_BUFFER, \
+ .offset = vmstate_offset_buffer(_state, _field) + _start, \
+}
+
+#define VMSTATE_VBUFFER_MULTIPLY(_field, _state, _version, _test, _start, _field_size, _multiply) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .field_exists = (_test), \
+ .size_offset = vmstate_offset_value(_state, _field_size, uint32_t),\
+ .size = (_multiply), \
+ .info = &vmstate_info_buffer, \
+ .flags = VMS_VBUFFER|VMS_POINTER|VMS_MULTIPLY, \
+ .offset = offsetof(_state, _field), \
+ .start = (_start), \
+}
+
+#define VMSTATE_VBUFFER(_field, _state, _version, _test, _start, _field_size) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .field_exists = (_test), \
+ .size_offset = vmstate_offset_value(_state, _field_size, int32_t),\
+ .info = &vmstate_info_buffer, \
+ .flags = VMS_VBUFFER|VMS_POINTER, \
+ .offset = offsetof(_state, _field), \
+ .start = (_start), \
+}
+
+#define VMSTATE_VBUFFER_UINT32(_field, _state, _version, _test, _start, _field_size) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .field_exists = (_test), \
+ .size_offset = vmstate_offset_value(_state, _field_size, uint32_t),\
+ .info = &vmstate_info_buffer, \
+ .flags = VMS_VBUFFER|VMS_POINTER, \
+ .offset = offsetof(_state, _field), \
+ .start = (_start), \
+}
+
+#define VMSTATE_BUFFER_UNSAFE_INFO(_field, _state, _version, _info, _size) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .size = (_size), \
+ .info = &(_info), \
+ .flags = VMS_BUFFER, \
+ .offset = offsetof(_state, _field), \
+}
+
+#define VMSTATE_BUFFER_POINTER_UNSAFE(_field, _state, _version, _size) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .size = (_size), \
+ .info = &vmstate_info_buffer, \
+ .flags = VMS_BUFFER|VMS_POINTER, \
+ .offset = offsetof(_state, _field), \
+}
+
+#define VMSTATE_UNUSED_BUFFER(_test, _version, _size) { \
+ .name = "unused", \
+ .field_exists = (_test), \
+ .version_id = (_version), \
+ .size = (_size), \
+ .info = &vmstate_info_unused_buffer, \
+ .flags = VMS_BUFFER, \
+}
+
+/* _field_size should be a int32_t field in the _state struct giving the
+ * size of the bitmap _field in bits.
+ */
+#define VMSTATE_BITMAP(_field, _state, _version, _field_size) { \
+ .name = (stringify(_field)), \
+ .version_id = (_version), \
+ .size_offset = vmstate_offset_value(_state, _field_size, int32_t),\
+ .info = &vmstate_info_bitmap, \
+ .flags = VMS_VBUFFER|VMS_POINTER, \
+ .offset = offsetof(_state, _field), \
+}
+
+/* _f : field name
+ _f_n : num of elements field_name
+ _n : num of elements
+ _s : struct state name
+ _v : version
+*/
+
+#define VMSTATE_SINGLE(_field, _state, _version, _info, _type) \
+ VMSTATE_SINGLE_TEST(_field, _state, NULL, _version, _info, _type)
+
+#define VMSTATE_STRUCT(_field, _state, _version, _vmsd, _type) \
+ VMSTATE_STRUCT_TEST(_field, _state, NULL, _version, _vmsd, _type)
+
+#define VMSTATE_STRUCT_POINTER(_field, _state, _vmsd, _type) \
+ VMSTATE_STRUCT_POINTER_TEST(_field, _state, NULL, _vmsd, _type)
+
+#define VMSTATE_STRUCT_ARRAY(_field, _state, _num, _version, _vmsd, _type) \
+ VMSTATE_STRUCT_ARRAY_TEST(_field, _state, _num, NULL, _version, \
+ _vmsd, _type)
+
+#define VMSTATE_BOOL_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_bool, bool)
+
+#define VMSTATE_INT8_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_int8, int8_t)
+#define VMSTATE_INT16_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_int16, int16_t)
+#define VMSTATE_INT32_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_int32, int32_t)
+#define VMSTATE_INT64_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_int64, int64_t)
+
+#define VMSTATE_UINT8_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint8, uint8_t)
+#define VMSTATE_UINT16_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint16, uint16_t)
+#define VMSTATE_UINT32_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint32, uint32_t)
+#define VMSTATE_UINT64_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint64, uint64_t)
+
+#define VMSTATE_BOOL(_f, _s) \
+ VMSTATE_BOOL_V(_f, _s, 0)
+
+#define VMSTATE_INT8(_f, _s) \
+ VMSTATE_INT8_V(_f, _s, 0)
+#define VMSTATE_INT16(_f, _s) \
+ VMSTATE_INT16_V(_f, _s, 0)
+#define VMSTATE_INT32(_f, _s) \
+ VMSTATE_INT32_V(_f, _s, 0)
+#define VMSTATE_INT64(_f, _s) \
+ VMSTATE_INT64_V(_f, _s, 0)
+
+#define VMSTATE_UINT8(_f, _s) \
+ VMSTATE_UINT8_V(_f, _s, 0)
+#define VMSTATE_UINT16(_f, _s) \
+ VMSTATE_UINT16_V(_f, _s, 0)
+#define VMSTATE_UINT32(_f, _s) \
+ VMSTATE_UINT32_V(_f, _s, 0)
+#define VMSTATE_UINT64(_f, _s) \
+ VMSTATE_UINT64_V(_f, _s, 0)
+
+#define VMSTATE_UINT8_EQUAL(_f, _s) \
+ VMSTATE_SINGLE(_f, _s, 0, vmstate_info_uint8_equal, uint8_t)
+
+#define VMSTATE_UINT16_EQUAL(_f, _s) \
+ VMSTATE_SINGLE(_f, _s, 0, vmstate_info_uint16_equal, uint16_t)
+
+#define VMSTATE_UINT16_EQUAL_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint16_equal, uint16_t)
+
+#define VMSTATE_INT32_EQUAL(_f, _s) \
+ VMSTATE_SINGLE(_f, _s, 0, vmstate_info_int32_equal, int32_t)
+
+#define VMSTATE_UINT32_EQUAL_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint32_equal, uint32_t)
+
+#define VMSTATE_UINT32_EQUAL(_f, _s) \
+ VMSTATE_UINT32_EQUAL_V(_f, _s, 0)
+
+#define VMSTATE_UINT64_EQUAL_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_uint64_equal, uint64_t)
+
+#define VMSTATE_UINT64_EQUAL(_f, _s) \
+ VMSTATE_UINT64_EQUAL_V(_f, _s, 0)
+
+#define VMSTATE_INT32_LE(_f, _s) \
+ VMSTATE_SINGLE(_f, _s, 0, vmstate_info_int32_le, int32_t)
+
+#define VMSTATE_UINT8_TEST(_f, _s, _t) \
+ VMSTATE_SINGLE_TEST(_f, _s, _t, 0, vmstate_info_uint8, uint8_t)
+
+#define VMSTATE_UINT16_TEST(_f, _s, _t) \
+ VMSTATE_SINGLE_TEST(_f, _s, _t, 0, vmstate_info_uint16, uint16_t)
+
+#define VMSTATE_UINT32_TEST(_f, _s, _t) \
+ VMSTATE_SINGLE_TEST(_f, _s, _t, 0, vmstate_info_uint32, uint32_t)
+
+
+#define VMSTATE_FLOAT64_V(_f, _s, _v) \
+ VMSTATE_SINGLE(_f, _s, _v, vmstate_info_float64, float64)
+
+#define VMSTATE_FLOAT64(_f, _s) \
+ VMSTATE_FLOAT64_V(_f, _s, 0)
+
+#define VMSTATE_TIMER_TEST(_f, _s, _test) \
+ VMSTATE_POINTER_TEST(_f, _s, _test, vmstate_info_timer, QEMUTimer *)
+
+#define VMSTATE_TIMER_V(_f, _s, _v) \
+ VMSTATE_POINTER(_f, _s, _v, vmstate_info_timer, QEMUTimer *)
+
+#define VMSTATE_TIMER(_f, _s) \
+ VMSTATE_TIMER_V(_f, _s, 0)
+
+#define VMSTATE_TIMER_ARRAY(_f, _s, _n) \
+ VMSTATE_ARRAY_OF_POINTER(_f, _s, _n, 0, vmstate_info_timer, QEMUTimer *)
+
+#define VMSTATE_BOOL_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_bool, bool)
+
+#define VMSTATE_BOOL_ARRAY(_f, _s, _n) \
+ VMSTATE_BOOL_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_UINT16_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_uint16, uint16_t)
+
+#define VMSTATE_UINT16_2DARRAY_V(_f, _s, _n1, _n2, _v) \
+ VMSTATE_2DARRAY(_f, _s, _n1, _n2, _v, vmstate_info_uint16, uint16_t)
+
+#define VMSTATE_UINT16_ARRAY(_f, _s, _n) \
+ VMSTATE_UINT16_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_UINT16_2DARRAY(_f, _s, _n1, _n2) \
+ VMSTATE_UINT16_2DARRAY_V(_f, _s, _n1, _n2, 0)
+
+#define VMSTATE_UINT8_2DARRAY_V(_f, _s, _n1, _n2, _v) \
+ VMSTATE_2DARRAY(_f, _s, _n1, _n2, _v, vmstate_info_uint8, uint8_t)
+
+#define VMSTATE_UINT8_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_uint8, uint8_t)
+
+#define VMSTATE_UINT8_ARRAY(_f, _s, _n) \
+ VMSTATE_UINT8_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_UINT8_2DARRAY(_f, _s, _n1, _n2) \
+ VMSTATE_UINT8_2DARRAY_V(_f, _s, _n1, _n2, 0)
+
+#define VMSTATE_UINT32_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_uint32, uint32_t)
+
+#define VMSTATE_UINT32_ARRAY(_f, _s, _n) \
+ VMSTATE_UINT32_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_UINT64_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_uint64, uint64_t)
+
+#define VMSTATE_UINT64_ARRAY(_f, _s, _n) \
+ VMSTATE_UINT64_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_INT16_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_int16, int16_t)
+
+#define VMSTATE_INT16_ARRAY(_f, _s, _n) \
+ VMSTATE_INT16_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_INT32_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_int32, int32_t)
+
+#define VMSTATE_INT32_ARRAY(_f, _s, _n) \
+ VMSTATE_INT32_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_UINT32_SUB_ARRAY(_f, _s, _start, _num) \
+ VMSTATE_SUB_ARRAY(_f, _s, _start, _num, 0, vmstate_info_uint32, uint32_t)
+
+#define VMSTATE_UINT32_ARRAY(_f, _s, _n) \
+ VMSTATE_UINT32_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_INT64_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_int64, int64_t)
+
+#define VMSTATE_INT64_ARRAY(_f, _s, _n) \
+ VMSTATE_INT64_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_FLOAT64_ARRAY_V(_f, _s, _n, _v) \
+ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_float64, float64)
+
+#define VMSTATE_FLOAT64_ARRAY(_f, _s, _n) \
+ VMSTATE_FLOAT64_ARRAY_V(_f, _s, _n, 0)
+
+#define VMSTATE_BUFFER_V(_f, _s, _v) \
+ VMSTATE_STATIC_BUFFER(_f, _s, _v, NULL, 0, sizeof(typeof_field(_s, _f)))
+
+#define VMSTATE_BUFFER(_f, _s) \
+ VMSTATE_BUFFER_V(_f, _s, 0)
+
+#define VMSTATE_PARTIAL_BUFFER(_f, _s, _size) \
+ VMSTATE_STATIC_BUFFER(_f, _s, 0, NULL, 0, _size)
+
+#define VMSTATE_BUFFER_START_MIDDLE(_f, _s, _start) \
+ VMSTATE_STATIC_BUFFER(_f, _s, 0, NULL, _start, sizeof(typeof_field(_s, _f)))
+
+#define VMSTATE_PARTIAL_VBUFFER(_f, _s, _size) \
+ VMSTATE_VBUFFER(_f, _s, 0, NULL, 0, _size)
+
+#define VMSTATE_PARTIAL_VBUFFER_UINT32(_f, _s, _size) \
+ VMSTATE_VBUFFER_UINT32(_f, _s, 0, NULL, 0, _size)
+
+#define VMSTATE_SUB_VBUFFER(_f, _s, _start, _size) \
+ VMSTATE_VBUFFER(_f, _s, 0, NULL, _start, _size)
+
+#define VMSTATE_BUFFER_TEST(_f, _s, _test) \
+ VMSTATE_STATIC_BUFFER(_f, _s, 0, _test, 0, sizeof(typeof_field(_s, _f)))
+
+#define VMSTATE_BUFFER_UNSAFE(_field, _state, _version, _size) \
+ VMSTATE_BUFFER_UNSAFE_INFO(_field, _state, _version, vmstate_info_buffer, _size)
+
+#define VMSTATE_UNUSED_V(_v, _size) \
+ VMSTATE_UNUSED_BUFFER(NULL, _v, _size)
+
+#define VMSTATE_UNUSED(_size) \
+ VMSTATE_UNUSED_V(0, _size)
+
+#define VMSTATE_UNUSED_TEST(_test, _size) \
+ VMSTATE_UNUSED_BUFFER(_test, 0, _size)
+
+#define VMSTATE_END_OF_LIST() \
+ {}
+
+int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd,
+ void *opaque, int version_id);
+void vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd,
+ void *opaque);
+
+int vmstate_register_with_alias_id(DeviceState *dev, int instance_id,
+ const VMStateDescription *vmsd,
+ void *base, int alias_id,
+ int required_for_version);
+
+static inline int vmstate_register(DeviceState *dev, int instance_id,
+ const VMStateDescription *vmsd,
+ void *opaque)
+{
+ return vmstate_register_with_alias_id(dev, instance_id, vmsd,
+ opaque, -1, 0);
+}
+
+void vmstate_unregister(DeviceState *dev, const VMStateDescription *vmsd,
+ void *opaque);
+
+struct MemoryRegion;
+void vmstate_register_ram(struct MemoryRegion *memory, DeviceState *dev);
+void vmstate_unregister_ram(struct MemoryRegion *memory, DeviceState *dev);
+void vmstate_register_ram_global(struct MemoryRegion *memory);
+
+#endif
diff --git a/contrib/qemu/include/monitor/monitor.h b/contrib/qemu/include/monitor/monitor.h
new file mode 100644
index 00000000000..1942cc42fe2
--- /dev/null
+++ b/contrib/qemu/include/monitor/monitor.h
@@ -0,0 +1,104 @@
+#ifndef MONITOR_H
+#define MONITOR_H
+
+#include "qemu-common.h"
+#include "qapi/qmp/qerror.h"
+#include "qapi/qmp/qdict.h"
+#include "block/block.h"
+#include "monitor/readline.h"
+
+extern Monitor *cur_mon;
+extern Monitor *default_mon;
+
+/* flags for monitor_init */
+#define MONITOR_IS_DEFAULT 0x01
+#define MONITOR_USE_READLINE 0x02
+#define MONITOR_USE_CONTROL 0x04
+#define MONITOR_USE_PRETTY 0x08
+
+/* flags for monitor commands */
+#define MONITOR_CMD_ASYNC 0x0001
+
+/* QMP events */
+typedef enum MonitorEvent {
+ QEVENT_SHUTDOWN,
+ QEVENT_RESET,
+ QEVENT_POWERDOWN,
+ QEVENT_STOP,
+ QEVENT_RESUME,
+ QEVENT_VNC_CONNECTED,
+ QEVENT_VNC_INITIALIZED,
+ QEVENT_VNC_DISCONNECTED,
+ QEVENT_BLOCK_IO_ERROR,
+ QEVENT_RTC_CHANGE,
+ QEVENT_WATCHDOG,
+ QEVENT_SPICE_CONNECTED,
+ QEVENT_SPICE_INITIALIZED,
+ QEVENT_SPICE_DISCONNECTED,
+ QEVENT_BLOCK_JOB_COMPLETED,
+ QEVENT_BLOCK_JOB_CANCELLED,
+ QEVENT_BLOCK_JOB_ERROR,
+ QEVENT_BLOCK_JOB_READY,
+ QEVENT_DEVICE_DELETED,
+ QEVENT_DEVICE_TRAY_MOVED,
+ QEVENT_NIC_RX_FILTER_CHANGED,
+ QEVENT_SUSPEND,
+ QEVENT_SUSPEND_DISK,
+ QEVENT_WAKEUP,
+ QEVENT_BALLOON_CHANGE,
+ QEVENT_SPICE_MIGRATE_COMPLETED,
+ QEVENT_GUEST_PANICKED,
+
+ /* Add to 'monitor_event_names' array in monitor.c when
+ * defining new events here */
+
+ QEVENT_MAX,
+} MonitorEvent;
+
+int monitor_cur_is_qmp(void);
+
+void monitor_protocol_event(MonitorEvent event, QObject *data);
+void monitor_init(CharDriverState *chr, int flags);
+
+int monitor_suspend(Monitor *mon);
+void monitor_resume(Monitor *mon);
+
+int monitor_read_bdrv_key_start(Monitor *mon, BlockDriverState *bs,
+ BlockDriverCompletionFunc *completion_cb,
+ void *opaque);
+int monitor_read_block_device_key(Monitor *mon, const char *device,
+ BlockDriverCompletionFunc *completion_cb,
+ void *opaque);
+
+int monitor_get_fd(Monitor *mon, const char *fdname, Error **errp);
+int monitor_handle_fd_param(Monitor *mon, const char *fdname);
+
+void monitor_vprintf(Monitor *mon, const char *fmt, va_list ap)
+ GCC_FMT_ATTR(2, 0);
+void monitor_printf(Monitor *mon, const char *fmt, ...) GCC_FMT_ATTR(2, 3);
+void monitor_print_filename(Monitor *mon, const char *filename);
+void monitor_flush(Monitor *mon);
+int monitor_set_cpu(int cpu_index);
+int monitor_get_cpu_index(void);
+
+typedef void (MonitorCompletion)(void *opaque, QObject *ret_data);
+
+void monitor_set_error(Monitor *mon, QError *qerror);
+void monitor_read_command(Monitor *mon, int show_prompt);
+ReadLineState *monitor_get_rs(Monitor *mon);
+int monitor_read_password(Monitor *mon, ReadLineFunc *readline_func,
+ void *opaque);
+
+int qmp_qom_set(Monitor *mon, const QDict *qdict, QObject **ret);
+
+int qmp_qom_get(Monitor *mon, const QDict *qdict, QObject **ret);
+
+AddfdInfo *monitor_fdset_add_fd(int fd, bool has_fdset_id, int64_t fdset_id,
+ bool has_opaque, const char *opaque,
+ Error **errp);
+int monitor_fdset_get_fd(int64_t fdset_id, int flags);
+int monitor_fdset_dup_fd_add(int64_t fdset_id, int dup_fd);
+int monitor_fdset_dup_fd_remove(int dup_fd);
+int monitor_fdset_dup_fd_find(int dup_fd);
+
+#endif /* !MONITOR_H */
diff --git a/contrib/qemu/include/monitor/readline.h b/contrib/qemu/include/monitor/readline.h
new file mode 100644
index 00000000000..fc9806ecf1a
--- /dev/null
+++ b/contrib/qemu/include/monitor/readline.h
@@ -0,0 +1,55 @@
+#ifndef READLINE_H
+#define READLINE_H
+
+#include "qemu-common.h"
+
+#define READLINE_CMD_BUF_SIZE 4095
+#define READLINE_MAX_CMDS 64
+#define READLINE_MAX_COMPLETIONS 256
+
+typedef void ReadLineFunc(Monitor *mon, const char *str, void *opaque);
+typedef void ReadLineCompletionFunc(const char *cmdline);
+
+typedef struct ReadLineState {
+ char cmd_buf[READLINE_CMD_BUF_SIZE + 1];
+ int cmd_buf_index;
+ int cmd_buf_size;
+
+ char last_cmd_buf[READLINE_CMD_BUF_SIZE + 1];
+ int last_cmd_buf_index;
+ int last_cmd_buf_size;
+
+ int esc_state;
+ int esc_param;
+
+ char *history[READLINE_MAX_CMDS];
+ int hist_entry;
+
+ ReadLineCompletionFunc *completion_finder;
+ char *completions[READLINE_MAX_COMPLETIONS];
+ int nb_completions;
+ int completion_index;
+
+ ReadLineFunc *readline_func;
+ void *readline_opaque;
+ int read_password;
+ char prompt[256];
+ Monitor *mon;
+} ReadLineState;
+
+void readline_add_completion(ReadLineState *rs, const char *str);
+void readline_set_completion_index(ReadLineState *rs, int completion_index);
+
+const char *readline_get_history(ReadLineState *rs, unsigned int index);
+
+void readline_handle_byte(ReadLineState *rs, int ch);
+
+void readline_start(ReadLineState *rs, const char *prompt, int read_password,
+ ReadLineFunc *readline_func, void *opaque);
+void readline_restart(ReadLineState *rs);
+void readline_show_prompt(ReadLineState *rs);
+
+ReadLineState *readline_init(Monitor *mon,
+ ReadLineCompletionFunc *completion_finder);
+
+#endif /* !READLINE_H */
diff --git a/contrib/qemu/include/qapi/error.h b/contrib/qemu/include/qapi/error.h
new file mode 100644
index 00000000000..ffd1cea4772
--- /dev/null
+++ b/contrib/qemu/include/qapi/error.h
@@ -0,0 +1,85 @@
+/*
+ * QEMU Error Objects
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2. See
+ * the COPYING.LIB file in the top-level directory.
+ */
+#ifndef ERROR_H
+#define ERROR_H
+
+#include "qemu/compiler.h"
+#include "qapi-types.h"
+#include <stdbool.h>
+
+/**
+ * A class representing internal errors within QEMU. An error has a ErrorClass
+ * code and a human message.
+ */
+typedef struct Error Error;
+
+/**
+ * Set an indirect pointer to an error given a ErrorClass value and a
+ * printf-style human message. This function is not meant to be used outside
+ * of QEMU.
+ */
+void error_set(Error **err, ErrorClass err_class, const char *fmt, ...) GCC_FMT_ATTR(3, 4);
+
+/**
+ * Set an indirect pointer to an error given a ErrorClass value and a
+ * printf-style human message, followed by a strerror() string if
+ * @os_error is not zero.
+ */
+void error_set_errno(Error **err, int os_error, ErrorClass err_class, const char *fmt, ...) GCC_FMT_ATTR(4, 5);
+
+/**
+ * Same as error_set(), but sets a generic error
+ */
+#define error_setg(err, fmt, ...) \
+ error_set(err, ERROR_CLASS_GENERIC_ERROR, fmt, ## __VA_ARGS__)
+#define error_setg_errno(err, os_error, fmt, ...) \
+ error_set_errno(err, os_error, ERROR_CLASS_GENERIC_ERROR, fmt, ## __VA_ARGS__)
+
+/**
+ * Helper for open() errors
+ */
+void error_setg_file_open(Error **errp, int os_errno, const char *filename);
+
+/**
+ * Returns true if an indirect pointer to an error is pointing to a valid
+ * error object.
+ */
+bool error_is_set(Error **err);
+
+/*
+ * Get the error class of an error object.
+ */
+ErrorClass error_get_class(const Error *err);
+
+/**
+ * Returns an exact copy of the error passed as an argument.
+ */
+Error *error_copy(const Error *err);
+
+/**
+ * Get a human readable representation of an error object.
+ */
+const char *error_get_pretty(Error *err);
+
+/**
+ * Propagate an error to an indirect pointer to an error. This function will
+ * always transfer ownership of the error reference and handles the case where
+ * dst_err is NULL correctly. Errors after the first are discarded.
+ */
+void error_propagate(Error **dst_err, Error *local_err);
+
+/**
+ * Free an error object.
+ */
+void error_free(Error *err);
+
+#endif
diff --git a/contrib/qemu/include/qapi/qmp/json-lexer.h b/contrib/qemu/include/qapi/qmp/json-lexer.h
new file mode 100644
index 00000000000..cdff0460a83
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/json-lexer.h
@@ -0,0 +1,51 @@
+/*
+ * JSON lexer
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_JSON_LEXER_H
+#define QEMU_JSON_LEXER_H
+
+#include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qlist.h"
+
+typedef enum json_token_type {
+ JSON_OPERATOR = 100,
+ JSON_INTEGER,
+ JSON_FLOAT,
+ JSON_KEYWORD,
+ JSON_STRING,
+ JSON_ESCAPE,
+ JSON_SKIP,
+ JSON_ERROR,
+} JSONTokenType;
+
+typedef struct JSONLexer JSONLexer;
+
+typedef void (JSONLexerEmitter)(JSONLexer *, QString *, JSONTokenType, int x, int y);
+
+struct JSONLexer
+{
+ JSONLexerEmitter *emit;
+ int state;
+ QString *token;
+ int x, y;
+};
+
+void json_lexer_init(JSONLexer *lexer, JSONLexerEmitter func);
+
+int json_lexer_feed(JSONLexer *lexer, const char *buffer, size_t size);
+
+int json_lexer_flush(JSONLexer *lexer);
+
+void json_lexer_destroy(JSONLexer *lexer);
+
+#endif
diff --git a/contrib/qemu/include/qapi/qmp/json-parser.h b/contrib/qemu/include/qapi/qmp/json-parser.h
new file mode 100644
index 00000000000..44d88f34685
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/json-parser.h
@@ -0,0 +1,24 @@
+/*
+ * JSON Parser
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_JSON_PARSER_H
+#define QEMU_JSON_PARSER_H
+
+#include "qemu-common.h"
+#include "qapi/qmp/qlist.h"
+#include "qapi/error.h"
+
+QObject *json_parser_parse(QList *tokens, va_list *ap);
+QObject *json_parser_parse_err(QList *tokens, va_list *ap, Error **errp);
+
+#endif
diff --git a/contrib/qemu/include/qapi/qmp/json-streamer.h b/contrib/qemu/include/qapi/qmp/json-streamer.h
new file mode 100644
index 00000000000..823f7d7fa42
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/json-streamer.h
@@ -0,0 +1,40 @@
+/*
+ * JSON streaming support
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_JSON_STREAMER_H
+#define QEMU_JSON_STREAMER_H
+
+#include "qapi/qmp/qlist.h"
+#include "qapi/qmp/json-lexer.h"
+
+typedef struct JSONMessageParser
+{
+ void (*emit)(struct JSONMessageParser *parser, QList *tokens);
+ JSONLexer lexer;
+ int brace_count;
+ int bracket_count;
+ QList *tokens;
+ uint64_t token_size;
+} JSONMessageParser;
+
+void json_message_parser_init(JSONMessageParser *parser,
+ void (*func)(JSONMessageParser *, QList *));
+
+int json_message_parser_feed(JSONMessageParser *parser,
+ const char *buffer, size_t size);
+
+int json_message_parser_flush(JSONMessageParser *parser);
+
+void json_message_parser_destroy(JSONMessageParser *parser);
+
+#endif
diff --git a/contrib/qemu/include/qapi/qmp/qbool.h b/contrib/qemu/include/qapi/qmp/qbool.h
new file mode 100644
index 00000000000..c4eaab9bb9f
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qbool.h
@@ -0,0 +1,29 @@
+/*
+ * QBool Module
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QBOOL_H
+#define QBOOL_H
+
+#include <stdint.h>
+#include "qapi/qmp/qobject.h"
+
+typedef struct QBool {
+ QObject_HEAD;
+ int value;
+} QBool;
+
+QBool *qbool_from_int(int value);
+int qbool_get_int(const QBool *qb);
+QBool *qobject_to_qbool(const QObject *obj);
+
+#endif /* QBOOL_H */
diff --git a/contrib/qemu/include/qapi/qmp/qdict.h b/contrib/qemu/include/qapi/qmp/qdict.h
new file mode 100644
index 00000000000..685b2e3fcbb
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qdict.h
@@ -0,0 +1,69 @@
+/*
+ * QDict Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef QDICT_H
+#define QDICT_H
+
+#include "qapi/qmp/qobject.h"
+#include "qapi/qmp/qlist.h"
+#include "qemu/queue.h"
+#include <stdint.h>
+
+#define QDICT_BUCKET_MAX 512
+
+typedef struct QDictEntry {
+ char *key;
+ QObject *value;
+ QLIST_ENTRY(QDictEntry) next;
+} QDictEntry;
+
+typedef struct QDict {
+ QObject_HEAD;
+ size_t size;
+ QLIST_HEAD(,QDictEntry) table[QDICT_BUCKET_MAX];
+} QDict;
+
+/* Object API */
+QDict *qdict_new(void);
+const char *qdict_entry_key(const QDictEntry *entry);
+QObject *qdict_entry_value(const QDictEntry *entry);
+size_t qdict_size(const QDict *qdict);
+void qdict_put_obj(QDict *qdict, const char *key, QObject *value);
+void qdict_del(QDict *qdict, const char *key);
+int qdict_haskey(const QDict *qdict, const char *key);
+QObject *qdict_get(const QDict *qdict, const char *key);
+QDict *qobject_to_qdict(const QObject *obj);
+void qdict_iter(const QDict *qdict,
+ void (*iter)(const char *key, QObject *obj, void *opaque),
+ void *opaque);
+const QDictEntry *qdict_first(const QDict *qdict);
+const QDictEntry *qdict_next(const QDict *qdict, const QDictEntry *entry);
+
+/* Helper to qdict_put_obj(), accepts any object */
+#define qdict_put(qdict, key, obj) \
+ qdict_put_obj(qdict, key, QOBJECT(obj))
+
+/* High level helpers */
+double qdict_get_double(const QDict *qdict, const char *key);
+int64_t qdict_get_int(const QDict *qdict, const char *key);
+int qdict_get_bool(const QDict *qdict, const char *key);
+QList *qdict_get_qlist(const QDict *qdict, const char *key);
+QDict *qdict_get_qdict(const QDict *qdict, const char *key);
+const char *qdict_get_str(const QDict *qdict, const char *key);
+int64_t qdict_get_try_int(const QDict *qdict, const char *key,
+ int64_t def_value);
+int qdict_get_try_bool(const QDict *qdict, const char *key, int def_value);
+const char *qdict_get_try_str(const QDict *qdict, const char *key);
+
+QDict *qdict_clone_shallow(const QDict *src);
+
+#endif /* QDICT_H */
diff --git a/contrib/qemu/include/qapi/qmp/qerror.h b/contrib/qemu/include/qapi/qmp/qerror.h
new file mode 100644
index 00000000000..c30c2f6d7a3
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qerror.h
@@ -0,0 +1,249 @@
+/*
+ * QError Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+#ifndef QERROR_H
+#define QERROR_H
+
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qstring.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+#include "qapi-types.h"
+#include <stdarg.h>
+
+typedef struct QError {
+ QObject_HEAD;
+ Location loc;
+ char *err_msg;
+ ErrorClass err_class;
+} QError;
+
+QString *qerror_human(const QError *qerror);
+void qerror_report(ErrorClass err_class, const char *fmt, ...) GCC_FMT_ATTR(2, 3);
+void qerror_report_err(Error *err);
+void assert_no_error(Error *err);
+
+/*
+ * QError class list
+ * Please keep the definitions in alphabetical order.
+ * Use scripts/check-qerror.sh to check.
+ */
+#define QERR_ADD_CLIENT_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Could not add client"
+
+#define QERR_AMBIGUOUS_PATH \
+ ERROR_CLASS_GENERIC_ERROR, "Path '%s' does not uniquely identify an object"
+
+#define QERR_BAD_BUS_FOR_DEVICE \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' can't go on a %s bus"
+
+#define QERR_BASE_NOT_FOUND \
+ ERROR_CLASS_GENERIC_ERROR, "Base '%s' not found"
+
+#define QERR_BLOCK_JOB_NOT_ACTIVE \
+ ERROR_CLASS_DEVICE_NOT_ACTIVE, "No active block job on device '%s'"
+
+#define QERR_BLOCK_JOB_PAUSED \
+ ERROR_CLASS_GENERIC_ERROR, "The block job for device '%s' is currently paused"
+
+#define QERR_BLOCK_JOB_NOT_READY \
+ ERROR_CLASS_GENERIC_ERROR, "The active block job for device '%s' cannot be completed"
+
+#define QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED \
+ ERROR_CLASS_GENERIC_ERROR, "Block format '%s' used by device '%s' does not support feature '%s'"
+
+#define QERR_BUFFER_OVERRUN \
+ ERROR_CLASS_GENERIC_ERROR, "An internal buffer overran"
+
+#define QERR_BUS_NO_HOTPLUG \
+ ERROR_CLASS_GENERIC_ERROR, "Bus '%s' does not support hotplugging"
+
+#define QERR_BUS_NOT_FOUND \
+ ERROR_CLASS_GENERIC_ERROR, "Bus '%s' not found"
+
+#define QERR_COMMAND_DISABLED \
+ ERROR_CLASS_GENERIC_ERROR, "The command %s has been disabled for this instance"
+
+#define QERR_COMMAND_NOT_FOUND \
+ ERROR_CLASS_COMMAND_NOT_FOUND, "The command %s has not been found"
+
+#define QERR_DEVICE_ENCRYPTED \
+ ERROR_CLASS_DEVICE_ENCRYPTED, "'%s' (%s) is encrypted"
+
+#define QERR_DEVICE_FEATURE_BLOCKS_MIGRATION \
+ ERROR_CLASS_GENERIC_ERROR, "Migration is disabled when using feature '%s' in device '%s'"
+
+#define QERR_DEVICE_HAS_NO_MEDIUM \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' has no medium"
+
+#define QERR_DEVICE_INIT_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' could not be initialized"
+
+#define QERR_DEVICE_IN_USE \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' is in use"
+
+#define QERR_DEVICE_IS_READ_ONLY \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' is read only"
+
+#define QERR_DEVICE_LOCKED \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' is locked"
+
+#define QERR_DEVICE_MULTIPLE_BUSSES \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' has multiple child busses"
+
+#define QERR_DEVICE_NO_BUS \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' has no child bus"
+
+#define QERR_DEVICE_NO_HOTPLUG \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' does not support hotplugging"
+
+#define QERR_DEVICE_NOT_ACTIVE \
+ ERROR_CLASS_DEVICE_NOT_ACTIVE, "Device '%s' has not been activated"
+
+#define QERR_DEVICE_NOT_ENCRYPTED \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' is not encrypted"
+
+#define QERR_DEVICE_NOT_FOUND \
+ ERROR_CLASS_DEVICE_NOT_FOUND, "Device '%s' not found"
+
+#define QERR_DEVICE_NOT_REMOVABLE \
+ ERROR_CLASS_GENERIC_ERROR, "Device '%s' is not removable"
+
+#define QERR_DUPLICATE_ID \
+ ERROR_CLASS_GENERIC_ERROR, "Duplicate ID '%s' for %s"
+
+#define QERR_FD_NOT_FOUND \
+ ERROR_CLASS_GENERIC_ERROR, "File descriptor named '%s' not found"
+
+#define QERR_FD_NOT_SUPPLIED \
+ ERROR_CLASS_GENERIC_ERROR, "No file descriptor supplied via SCM_RIGHTS"
+
+#define QERR_FEATURE_DISABLED \
+ ERROR_CLASS_GENERIC_ERROR, "The feature '%s' is not enabled"
+
+#define QERR_INVALID_BLOCK_FORMAT \
+ ERROR_CLASS_GENERIC_ERROR, "Invalid block format '%s'"
+
+#define QERR_INVALID_OPTION_GROUP \
+ ERROR_CLASS_GENERIC_ERROR, "There is no option group '%s'"
+
+#define QERR_INVALID_PARAMETER \
+ ERROR_CLASS_GENERIC_ERROR, "Invalid parameter '%s'"
+
+#define QERR_INVALID_PARAMETER_COMBINATION \
+ ERROR_CLASS_GENERIC_ERROR, "Invalid parameter combination"
+
+#define QERR_INVALID_PARAMETER_TYPE \
+ ERROR_CLASS_GENERIC_ERROR, "Invalid parameter type for '%s', expected: %s"
+
+#define QERR_INVALID_PARAMETER_VALUE \
+ ERROR_CLASS_GENERIC_ERROR, "Parameter '%s' expects %s"
+
+#define QERR_INVALID_PASSWORD \
+ ERROR_CLASS_GENERIC_ERROR, "Password incorrect"
+
+#define QERR_IO_ERROR \
+ ERROR_CLASS_GENERIC_ERROR, "An IO error has occurred"
+
+#define QERR_JSON_PARSE_ERROR \
+ ERROR_CLASS_GENERIC_ERROR, "JSON parse error, %s"
+
+#define QERR_JSON_PARSING \
+ ERROR_CLASS_GENERIC_ERROR, "Invalid JSON syntax"
+
+#define QERR_KVM_MISSING_CAP \
+ ERROR_CLASS_K_V_M_MISSING_CAP, "Using KVM without %s, %s unavailable"
+
+#define QERR_MIGRATION_ACTIVE \
+ ERROR_CLASS_GENERIC_ERROR, "There's a migration process in progress"
+
+#define QERR_MIGRATION_NOT_SUPPORTED \
+ ERROR_CLASS_GENERIC_ERROR, "State blocked by non-migratable device '%s'"
+
+#define QERR_MISSING_PARAMETER \
+ ERROR_CLASS_GENERIC_ERROR, "Parameter '%s' is missing"
+
+#define QERR_NO_BUS_FOR_DEVICE \
+ ERROR_CLASS_GENERIC_ERROR, "No '%s' bus found for device '%s'"
+
+#define QERR_NOT_SUPPORTED \
+ ERROR_CLASS_GENERIC_ERROR, "Not supported"
+
+#define QERR_PERMISSION_DENIED \
+ ERROR_CLASS_GENERIC_ERROR, "Insufficient permission to perform this operation"
+
+#define QERR_PROPERTY_NOT_FOUND \
+ ERROR_CLASS_GENERIC_ERROR, "Property '%s.%s' not found"
+
+#define QERR_PROPERTY_VALUE_BAD \
+ ERROR_CLASS_GENERIC_ERROR, "Property '%s.%s' doesn't take value '%s'"
+
+#define QERR_PROPERTY_VALUE_IN_USE \
+ ERROR_CLASS_GENERIC_ERROR, "Property '%s.%s' can't take value '%s', it's in use"
+
+#define QERR_PROPERTY_VALUE_NOT_FOUND \
+ ERROR_CLASS_GENERIC_ERROR, "Property '%s.%s' can't find value '%s'"
+
+#define QERR_PROPERTY_VALUE_NOT_POWER_OF_2 \
+ ERROR_CLASS_GENERIC_ERROR, "Property %s.%s doesn't take value '%" PRId64 "', it's not a power of 2"
+
+#define QERR_PROPERTY_VALUE_OUT_OF_RANGE \
+ ERROR_CLASS_GENERIC_ERROR, "Property %s.%s doesn't take value %" PRId64 " (minimum: %" PRId64 ", maximum: %" PRId64 ")"
+
+#define QERR_QGA_COMMAND_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Guest agent command failed, error was '%s'"
+
+#define QERR_QGA_LOGGING_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Guest agent failed to log non-optional log statement"
+
+#define QERR_QMP_BAD_INPUT_OBJECT \
+ ERROR_CLASS_GENERIC_ERROR, "Expected '%s' in QMP input"
+
+#define QERR_QMP_BAD_INPUT_OBJECT_MEMBER \
+ ERROR_CLASS_GENERIC_ERROR, "QMP input object member '%s' expects '%s'"
+
+#define QERR_QMP_EXTRA_MEMBER \
+ ERROR_CLASS_GENERIC_ERROR, "QMP input object member '%s' is unexpected"
+
+#define QERR_RESET_REQUIRED \
+ ERROR_CLASS_GENERIC_ERROR, "Resetting the Virtual Machine is required"
+
+#define QERR_SET_PASSWD_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Could not set password"
+
+#define QERR_TOO_MANY_FILES \
+ ERROR_CLASS_GENERIC_ERROR, "Too many open files"
+
+#define QERR_UNDEFINED_ERROR \
+ ERROR_CLASS_GENERIC_ERROR, "An undefined error has occurred"
+
+#define QERR_UNKNOWN_BLOCK_FORMAT_FEATURE \
+ ERROR_CLASS_GENERIC_ERROR, "'%s' uses a %s feature which is not supported by this qemu version: %s"
+
+#define QERR_UNSUPPORTED \
+ ERROR_CLASS_GENERIC_ERROR, "this feature or command is not currently supported"
+
+#define QERR_VIRTFS_FEATURE_BLOCKS_MIGRATION \
+ ERROR_CLASS_GENERIC_ERROR, "Migration is disabled when VirtFS export path '%s' is mounted in the guest using mount_tag '%s'"
+
+#define QERR_SOCKET_CONNECT_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Failed to connect to socket"
+
+#define QERR_SOCKET_LISTEN_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Failed to set socket to listening mode"
+
+#define QERR_SOCKET_BIND_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Failed to bind socket"
+
+#define QERR_SOCKET_CREATE_FAILED \
+ ERROR_CLASS_GENERIC_ERROR, "Failed to create socket"
+
+#endif /* QERROR_H */
diff --git a/contrib/qemu/include/qapi/qmp/qfloat.h b/contrib/qemu/include/qapi/qmp/qfloat.h
new file mode 100644
index 00000000000..a8658443dc2
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qfloat.h
@@ -0,0 +1,29 @@
+/*
+ * QFloat Module
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QFLOAT_H
+#define QFLOAT_H
+
+#include <stdint.h>
+#include "qapi/qmp/qobject.h"
+
+typedef struct QFloat {
+ QObject_HEAD;
+ double value;
+} QFloat;
+
+QFloat *qfloat_from_double(double value);
+double qfloat_get_double(const QFloat *qi);
+QFloat *qobject_to_qfloat(const QObject *obj);
+
+#endif /* QFLOAT_H */
diff --git a/contrib/qemu/include/qapi/qmp/qint.h b/contrib/qemu/include/qapi/qmp/qint.h
new file mode 100644
index 00000000000..48a41b0f2ae
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qint.h
@@ -0,0 +1,28 @@
+/*
+ * QInt Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef QINT_H
+#define QINT_H
+
+#include <stdint.h>
+#include "qapi/qmp/qobject.h"
+
+typedef struct QInt {
+ QObject_HEAD;
+ int64_t value;
+} QInt;
+
+QInt *qint_from_int(int64_t value);
+int64_t qint_get_int(const QInt *qi);
+QInt *qobject_to_qint(const QObject *obj);
+
+#endif /* QINT_H */
diff --git a/contrib/qemu/include/qapi/qmp/qjson.h b/contrib/qemu/include/qapi/qmp/qjson.h
new file mode 100644
index 00000000000..73351ed6d68
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qjson.h
@@ -0,0 +1,29 @@
+/*
+ * QObject JSON integration
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QJSON_H
+#define QJSON_H
+
+#include <stdarg.h>
+#include "qemu/compiler.h"
+#include "qapi/qmp/qobject.h"
+#include "qapi/qmp/qstring.h"
+
+QObject *qobject_from_json(const char *string) GCC_FMT_ATTR(1, 0);
+QObject *qobject_from_jsonf(const char *string, ...) GCC_FMT_ATTR(1, 2);
+QObject *qobject_from_jsonv(const char *string, va_list *ap) GCC_FMT_ATTR(1, 0);
+
+QString *qobject_to_json(const QObject *obj);
+QString *qobject_to_json_pretty(const QObject *obj);
+
+#endif /* QJSON_H */
diff --git a/contrib/qemu/include/qapi/qmp/qlist.h b/contrib/qemu/include/qapi/qmp/qlist.h
new file mode 100644
index 00000000000..6cc4831df3e
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qlist.h
@@ -0,0 +1,63 @@
+/*
+ * QList Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef QLIST_H
+#define QLIST_H
+
+#include "qapi/qmp/qobject.h"
+#include "qemu/queue.h"
+
+typedef struct QListEntry {
+ QObject *value;
+ QTAILQ_ENTRY(QListEntry) next;
+} QListEntry;
+
+typedef struct QList {
+ QObject_HEAD;
+ QTAILQ_HEAD(,QListEntry) head;
+} QList;
+
+#define qlist_append(qlist, obj) \
+ qlist_append_obj(qlist, QOBJECT(obj))
+
+#define QLIST_FOREACH_ENTRY(qlist, var) \
+ for ((var) = ((qlist)->head.tqh_first); \
+ (var); \
+ (var) = ((var)->next.tqe_next))
+
+static inline QObject *qlist_entry_obj(const QListEntry *entry)
+{
+ return entry->value;
+}
+
+QList *qlist_new(void);
+QList *qlist_copy(QList *src);
+void qlist_append_obj(QList *qlist, QObject *obj);
+void qlist_iter(const QList *qlist,
+ void (*iter)(QObject *obj, void *opaque), void *opaque);
+QObject *qlist_pop(QList *qlist);
+QObject *qlist_peek(QList *qlist);
+int qlist_empty(const QList *qlist);
+size_t qlist_size(const QList *qlist);
+QList *qobject_to_qlist(const QObject *obj);
+
+static inline const QListEntry *qlist_first(const QList *qlist)
+{
+ return QTAILQ_FIRST(&qlist->head);
+}
+
+static inline const QListEntry *qlist_next(const QListEntry *entry)
+{
+ return QTAILQ_NEXT(entry, next);
+}
+
+#endif /* QLIST_H */
diff --git a/contrib/qemu/include/qapi/qmp/qobject.h b/contrib/qemu/include/qapi/qmp/qobject.h
new file mode 100644
index 00000000000..9124649ed20
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qobject.h
@@ -0,0 +1,112 @@
+/*
+ * QEMU Object Model.
+ *
+ * Based on ideas by Avi Kivity <avi@redhat.com>
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ * QObject Reference Counts Terminology
+ * ------------------------------------
+ *
+ * - Returning references: A function that returns an object may
+ * return it as either a weak or a strong reference. If the reference
+ * is strong, you are responsible for calling QDECREF() on the reference
+ * when you are done.
+ *
+ * If the reference is weak, the owner of the reference may free it at
+ * any time in the future. Before storing the reference anywhere, you
+ * should call QINCREF() to make the reference strong.
+ *
+ * - Transferring ownership: when you transfer ownership of a reference
+ * by calling a function, you are no longer responsible for calling
+ * QDECREF() when the reference is no longer needed. In other words,
+ * when the function returns you must behave as if the reference to the
+ * passed object was weak.
+ */
+#ifndef QOBJECT_H
+#define QOBJECT_H
+
+#include <stddef.h>
+#include <assert.h>
+
+typedef enum {
+ QTYPE_NONE,
+ QTYPE_QINT,
+ QTYPE_QSTRING,
+ QTYPE_QDICT,
+ QTYPE_QLIST,
+ QTYPE_QFLOAT,
+ QTYPE_QBOOL,
+ QTYPE_QERROR,
+} qtype_code;
+
+struct QObject;
+
+typedef struct QType {
+ qtype_code code;
+ void (*destroy)(struct QObject *);
+} QType;
+
+typedef struct QObject {
+ const QType *type;
+ size_t refcnt;
+} QObject;
+
+/* Objects definitions must include this */
+#define QObject_HEAD \
+ QObject base
+
+/* Get the 'base' part of an object */
+#define QOBJECT(obj) (&(obj)->base)
+
+/* High-level interface for qobject_incref() */
+#define QINCREF(obj) \
+ qobject_incref(QOBJECT(obj))
+
+/* High-level interface for qobject_decref() */
+#define QDECREF(obj) \
+ qobject_decref(obj ? QOBJECT(obj) : NULL)
+
+/* Initialize an object to default values */
+#define QOBJECT_INIT(obj, qtype_type) \
+ obj->base.refcnt = 1; \
+ obj->base.type = qtype_type
+
+/**
+ * qobject_incref(): Increment QObject's reference count
+ */
+static inline void qobject_incref(QObject *obj)
+{
+ if (obj)
+ obj->refcnt++;
+}
+
+/**
+ * qobject_decref(): Decrement QObject's reference count, deallocate
+ * when it reaches zero
+ */
+static inline void qobject_decref(QObject *obj)
+{
+ if (obj && --obj->refcnt == 0) {
+ assert(obj->type != NULL);
+ assert(obj->type->destroy != NULL);
+ obj->type->destroy(obj);
+ }
+}
+
+/**
+ * qobject_type(): Return the QObject's type
+ */
+static inline qtype_code qobject_type(const QObject *obj)
+{
+ assert(obj->type != NULL);
+ return obj->type->code;
+}
+
+#endif /* QOBJECT_H */
diff --git a/contrib/qemu/include/qapi/qmp/qstring.h b/contrib/qemu/include/qapi/qmp/qstring.h
new file mode 100644
index 00000000000..1bc3666107c
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/qstring.h
@@ -0,0 +1,36 @@
+/*
+ * QString Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef QSTRING_H
+#define QSTRING_H
+
+#include <stdint.h>
+#include "qapi/qmp/qobject.h"
+
+typedef struct QString {
+ QObject_HEAD;
+ char *string;
+ size_t length;
+ size_t capacity;
+} QString;
+
+QString *qstring_new(void);
+QString *qstring_from_str(const char *str);
+QString *qstring_from_substr(const char *str, int start, int end);
+size_t qstring_get_length(const QString *qstring);
+const char *qstring_get_str(const QString *qstring);
+void qstring_append_int(QString *qstring, int64_t value);
+void qstring_append(QString *qstring, const char *str);
+void qstring_append_chr(QString *qstring, int c);
+QString *qobject_to_qstring(const QObject *obj);
+
+#endif /* QSTRING_H */
diff --git a/contrib/qemu/include/qapi/qmp/types.h b/contrib/qemu/include/qapi/qmp/types.h
new file mode 100644
index 00000000000..7782ec5a602
--- /dev/null
+++ b/contrib/qemu/include/qapi/qmp/types.h
@@ -0,0 +1,25 @@
+/*
+ * Include all QEMU objects.
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef QEMU_OBJECTS_H
+#define QEMU_OBJECTS_H
+
+#include "qapi/qmp/qobject.h"
+#include "qapi/qmp/qint.h"
+#include "qapi/qmp/qfloat.h"
+#include "qapi/qmp/qbool.h"
+#include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qlist.h"
+#include "qapi/qmp/qjson.h"
+
+#endif /* QEMU_OBJECTS_H */
diff --git a/contrib/qemu/include/qemu-common.h b/contrib/qemu/include/qemu-common.h
new file mode 100644
index 00000000000..6948bb91774
--- /dev/null
+++ b/contrib/qemu/include/qemu-common.h
@@ -0,0 +1,478 @@
+
+/* Common header file that is included by all of QEMU.
+ *
+ * This file is supposed to be included only by .c files. No header file should
+ * depend on qemu-common.h, as this would easily lead to circular header
+ * dependencies.
+ *
+ * If a header file uses a definition from qemu-common.h, that definition
+ * must be moved to a separate header file, and the header that uses it
+ * must include that header.
+ */
+#ifndef QEMU_COMMON_H
+#define QEMU_COMMON_H
+
+#include "qemu/compiler.h"
+#include "config-host.h"
+#include "qemu/typedefs.h"
+
+#if defined(__arm__) || defined(__sparc__) || defined(__mips__) || defined(__hppa__) || defined(__ia64__)
+#define WORDS_ALIGNED
+#endif
+
+#define TFR(expr) do { if ((expr) != -1) break; } while (errno == EINTR)
+
+/* we put basic includes here to avoid repeating them in device drivers */
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <string.h>
+#include <strings.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <time.h>
+#include <ctype.h>
+#include <errno.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <assert.h>
+#include <signal.h>
+#include "glib-compat.h"
+
+#ifdef _WIN32
+#include "sysemu/os-win32.h"
+#endif
+
+#ifdef CONFIG_POSIX
+#include "sysemu/os-posix.h"
+#endif
+
+#ifndef O_LARGEFILE
+#define O_LARGEFILE 0
+#endif
+#ifndef O_BINARY
+#define O_BINARY 0
+#endif
+#ifndef MAP_ANONYMOUS
+#define MAP_ANONYMOUS MAP_ANON
+#endif
+#ifndef ENOMEDIUM
+#define ENOMEDIUM ENODEV
+#endif
+#if !defined(ENOTSUP)
+#define ENOTSUP 4096
+#endif
+#if !defined(ECANCELED)
+#define ECANCELED 4097
+#endif
+#if !defined(EMEDIUMTYPE)
+#define EMEDIUMTYPE 4098
+#endif
+#ifndef TIME_MAX
+#define TIME_MAX LONG_MAX
+#endif
+
+/* HOST_LONG_BITS is the size of a native pointer in bits. */
+#if UINTPTR_MAX == UINT32_MAX
+# define HOST_LONG_BITS 32
+#elif UINTPTR_MAX == UINT64_MAX
+# define HOST_LONG_BITS 64
+#else
+# error Unknown pointer size
+#endif
+
+typedef int (*fprintf_function)(FILE *f, const char *fmt, ...)
+ GCC_FMT_ATTR(2, 3);
+
+#ifdef _WIN32
+#define fsync _commit
+#if !defined(lseek)
+# define lseek _lseeki64
+#endif
+int qemu_ftruncate64(int, int64_t);
+#if !defined(ftruncate)
+# define ftruncate qemu_ftruncate64
+#endif
+
+static inline char *realpath(const char *path, char *resolved_path)
+{
+ _fullpath(resolved_path, path, _MAX_PATH);
+ return resolved_path;
+}
+#endif
+
+/* icount */
+void configure_icount(const char *option);
+extern int use_icount;
+
+#include "qemu/osdep.h"
+#include "qemu/bswap.h"
+
+/* FIXME: Remove NEED_CPU_H. */
+#ifdef NEED_CPU_H
+#include "cpu.h"
+#endif /* !defined(NEED_CPU_H) */
+
+/* main function, renamed */
+#if defined(CONFIG_COCOA)
+int qemu_main(int argc, char **argv, char **envp);
+#endif
+
+void qemu_get_timedate(struct tm *tm, int offset);
+int qemu_timedate_diff(struct tm *tm);
+
+#if !GLIB_CHECK_VERSION(2, 20, 0)
+/*
+ * Glib before 2.20.0 doesn't implement g_poll, so wrap it to compile properly
+ * on older systems.
+ */
+static inline gint g_poll(GPollFD *fds, guint nfds, gint timeout)
+{
+ GMainContext *ctx = g_main_context_default();
+ return g_main_context_get_poll_func(ctx)(fds, nfds, timeout);
+}
+#endif
+
+/**
+ * is_help_option:
+ * @s: string to test
+ *
+ * Check whether @s is one of the standard strings which indicate
+ * that the user is asking for a list of the valid values for a
+ * command option like -cpu or -M. The current accepted strings
+ * are 'help' and '?'. '?' is deprecated (it is a shell wildcard
+ * which makes it annoying to use in a reliable way) but provided
+ * for backwards compatibility.
+ *
+ * Returns: true if @s is a request for a list.
+ */
+static inline bool is_help_option(const char *s)
+{
+ return !strcmp(s, "?") || !strcmp(s, "help");
+}
+
+/* cutils.c */
+void pstrcpy(char *buf, int buf_size, const char *str);
+void strpadcpy(char *buf, int buf_size, const char *str, char pad);
+char *pstrcat(char *buf, int buf_size, const char *s);
+int strstart(const char *str, const char *val, const char **ptr);
+int stristart(const char *str, const char *val, const char **ptr);
+int qemu_strnlen(const char *s, int max_len);
+char *qemu_strsep(char **input, const char *delim);
+time_t mktimegm(struct tm *tm);
+int qemu_fls(int i);
+int qemu_fdatasync(int fd);
+int fcntl_setfl(int fd, int flag);
+int qemu_parse_fd(const char *param);
+
+int parse_uint(const char *s, unsigned long long *value, char **endptr,
+ int base);
+int parse_uint_full(const char *s, unsigned long long *value, int base);
+
+/*
+ * strtosz() suffixes used to specify the default treatment of an
+ * argument passed to strtosz() without an explicit suffix.
+ * These should be defined using upper case characters in the range
+ * A-Z, as strtosz() will use qemu_toupper() on the given argument
+ * prior to comparison.
+ */
+#define STRTOSZ_DEFSUFFIX_EB 'E'
+#define STRTOSZ_DEFSUFFIX_PB 'P'
+#define STRTOSZ_DEFSUFFIX_TB 'T'
+#define STRTOSZ_DEFSUFFIX_GB 'G'
+#define STRTOSZ_DEFSUFFIX_MB 'M'
+#define STRTOSZ_DEFSUFFIX_KB 'K'
+#define STRTOSZ_DEFSUFFIX_B 'B'
+int64_t strtosz(const char *nptr, char **end);
+int64_t strtosz_suffix(const char *nptr, char **end, const char default_suffix);
+int64_t strtosz_suffix_unit(const char *nptr, char **end,
+ const char default_suffix, int64_t unit);
+
+/* path.c */
+void init_paths(const char *prefix);
+const char *path(const char *pathname);
+
+#define qemu_isalnum(c) isalnum((unsigned char)(c))
+#define qemu_isalpha(c) isalpha((unsigned char)(c))
+#define qemu_iscntrl(c) iscntrl((unsigned char)(c))
+#define qemu_isdigit(c) isdigit((unsigned char)(c))
+#define qemu_isgraph(c) isgraph((unsigned char)(c))
+#define qemu_islower(c) islower((unsigned char)(c))
+#define qemu_isprint(c) isprint((unsigned char)(c))
+#define qemu_ispunct(c) ispunct((unsigned char)(c))
+#define qemu_isspace(c) isspace((unsigned char)(c))
+#define qemu_isupper(c) isupper((unsigned char)(c))
+#define qemu_isxdigit(c) isxdigit((unsigned char)(c))
+#define qemu_tolower(c) tolower((unsigned char)(c))
+#define qemu_toupper(c) toupper((unsigned char)(c))
+#define qemu_isascii(c) isascii((unsigned char)(c))
+#define qemu_toascii(c) toascii((unsigned char)(c))
+
+void *qemu_oom_check(void *ptr);
+
+ssize_t qemu_write_full(int fd, const void *buf, size_t count)
+ QEMU_WARN_UNUSED_RESULT;
+ssize_t qemu_send_full(int fd, const void *buf, size_t count, int flags)
+ QEMU_WARN_UNUSED_RESULT;
+ssize_t qemu_recv_full(int fd, void *buf, size_t count, int flags)
+ QEMU_WARN_UNUSED_RESULT;
+
+#ifndef _WIN32
+int qemu_pipe(int pipefd[2]);
+/* like openpty() but also makes it raw; return master fd */
+int qemu_openpty_raw(int *aslave, char *pty_name);
+#endif
+
+#ifdef _WIN32
+/* MinGW needs type casts for the 'buf' and 'optval' arguments. */
+#define qemu_getsockopt(sockfd, level, optname, optval, optlen) \
+ getsockopt(sockfd, level, optname, (void *)optval, optlen)
+#define qemu_setsockopt(sockfd, level, optname, optval, optlen) \
+ setsockopt(sockfd, level, optname, (const void *)optval, optlen)
+#define qemu_recv(sockfd, buf, len, flags) recv(sockfd, (void *)buf, len, flags)
+#define qemu_sendto(sockfd, buf, len, flags, destaddr, addrlen) \
+ sendto(sockfd, (const void *)buf, len, flags, destaddr, addrlen)
+#else
+#define qemu_getsockopt(sockfd, level, optname, optval, optlen) \
+ getsockopt(sockfd, level, optname, optval, optlen)
+#define qemu_setsockopt(sockfd, level, optname, optval, optlen) \
+ setsockopt(sockfd, level, optname, optval, optlen)
+#define qemu_recv(sockfd, buf, len, flags) recv(sockfd, buf, len, flags)
+#define qemu_sendto(sockfd, buf, len, flags, destaddr, addrlen) \
+ sendto(sockfd, buf, len, flags, destaddr, addrlen)
+#endif
+
+/* Error handling. */
+
+void QEMU_NORETURN hw_error(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
+
+struct ParallelIOArg {
+ void *buffer;
+ int count;
+};
+
+typedef int (*DMA_transfer_handler) (void *opaque, int nchan, int pos, int size);
+
+typedef uint64_t pcibus_t;
+
+typedef enum LostTickPolicy {
+ LOST_TICK_DISCARD,
+ LOST_TICK_DELAY,
+ LOST_TICK_MERGE,
+ LOST_TICK_SLEW,
+ LOST_TICK_MAX
+} LostTickPolicy;
+
+typedef struct PCIHostDeviceAddress {
+ unsigned int domain;
+ unsigned int bus;
+ unsigned int slot;
+ unsigned int function;
+} PCIHostDeviceAddress;
+
+void tcg_exec_init(unsigned long tb_size);
+bool tcg_enabled(void);
+
+void cpu_exec_init_all(void);
+
+/* CPU save/load. */
+#ifdef CPU_SAVE_VERSION
+void cpu_save(QEMUFile *f, void *opaque);
+int cpu_load(QEMUFile *f, void *opaque, int version_id);
+#endif
+
+/* Unblock cpu */
+void qemu_cpu_kick_self(void);
+
+/* work queue */
+struct qemu_work_item {
+ struct qemu_work_item *next;
+ void (*func)(void *data);
+ void *data;
+ int done;
+ bool free;
+};
+
+
+/**
+ * Sends a (part of) iovec down a socket, yielding when the socket is full, or
+ * Receives data into a (part of) iovec from a socket,
+ * yielding when there is no data in the socket.
+ * The same interface as qemu_sendv_recvv(), with added yielding.
+ * XXX should mark these as coroutine_fn
+ */
+ssize_t qemu_co_sendv_recvv(int sockfd, struct iovec *iov, unsigned iov_cnt,
+ size_t offset, size_t bytes, bool do_send);
+#define qemu_co_recvv(sockfd, iov, iov_cnt, offset, bytes) \
+ qemu_co_sendv_recvv(sockfd, iov, iov_cnt, offset, bytes, false)
+#define qemu_co_sendv(sockfd, iov, iov_cnt, offset, bytes) \
+ qemu_co_sendv_recvv(sockfd, iov, iov_cnt, offset, bytes, true)
+
+/**
+ * The same as above, but with just a single buffer
+ */
+ssize_t qemu_co_send_recv(int sockfd, void *buf, size_t bytes, bool do_send);
+#define qemu_co_recv(sockfd, buf, bytes) \
+ qemu_co_send_recv(sockfd, buf, bytes, false)
+#define qemu_co_send(sockfd, buf, bytes) \
+ qemu_co_send_recv(sockfd, buf, bytes, true)
+
+typedef struct QEMUIOVector {
+ struct iovec *iov;
+ int niov;
+ int nalloc;
+ size_t size;
+} QEMUIOVector;
+
+void qemu_iovec_init(QEMUIOVector *qiov, int alloc_hint);
+void qemu_iovec_init_external(QEMUIOVector *qiov, struct iovec *iov, int niov);
+void qemu_iovec_add(QEMUIOVector *qiov, void *base, size_t len);
+void qemu_iovec_concat(QEMUIOVector *dst,
+ QEMUIOVector *src, size_t soffset, size_t sbytes);
+void qemu_iovec_concat_iov(QEMUIOVector *dst,
+ struct iovec *src_iov, unsigned int src_cnt,
+ size_t soffset, size_t sbytes);
+void qemu_iovec_destroy(QEMUIOVector *qiov);
+void qemu_iovec_reset(QEMUIOVector *qiov);
+size_t qemu_iovec_to_buf(QEMUIOVector *qiov, size_t offset,
+ void *buf, size_t bytes);
+size_t qemu_iovec_from_buf(QEMUIOVector *qiov, size_t offset,
+ const void *buf, size_t bytes);
+size_t qemu_iovec_memset(QEMUIOVector *qiov, size_t offset,
+ int fillc, size_t bytes);
+
+bool buffer_is_zero(const void *buf, size_t len);
+
+void qemu_progress_init(int enabled, float min_skip);
+void qemu_progress_end(void);
+void qemu_progress_print(float delta, int max);
+const char *qemu_get_vm_name(void);
+
+#define QEMU_FILE_TYPE_BIOS 0
+#define QEMU_FILE_TYPE_KEYMAP 1
+char *qemu_find_file(int type, const char *name);
+
+/* OS specific functions */
+void os_setup_early_signal_handling(void);
+char *os_find_datadir(const char *argv0);
+void os_parse_cmd_args(int index, const char *optarg);
+void os_pidfile_error(void);
+
+/* Convert a byte between binary and BCD. */
+static inline uint8_t to_bcd(uint8_t val)
+{
+ return ((val / 10) << 4) | (val % 10);
+}
+
+static inline uint8_t from_bcd(uint8_t val)
+{
+ return ((val >> 4) * 10) + (val & 0x0f);
+}
+
+/* compute with 96 bit intermediate result: (a*b)/c */
+static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c)
+{
+ union {
+ uint64_t ll;
+ struct {
+#ifdef HOST_WORDS_BIGENDIAN
+ uint32_t high, low;
+#else
+ uint32_t low, high;
+#endif
+ } l;
+ } u, res;
+ uint64_t rl, rh;
+
+ u.ll = a;
+ rl = (uint64_t)u.l.low * (uint64_t)b;
+ rh = (uint64_t)u.l.high * (uint64_t)b;
+ rh += (rl >> 32);
+ res.l.high = rh / c;
+ res.l.low = (((rh % c) << 32) + (rl & 0xffffffff)) / c;
+ return res.ll;
+}
+
+/* Round number down to multiple */
+#define QEMU_ALIGN_DOWN(n, m) ((n) / (m) * (m))
+
+/* Round number up to multiple */
+#define QEMU_ALIGN_UP(n, m) QEMU_ALIGN_DOWN((n) + (m) - 1, (m))
+
+static inline bool is_power_of_2(uint64_t value)
+{
+ if (!value) {
+ return 0;
+ }
+
+ return !(value & (value - 1));
+}
+
+/* round down to the nearest power of 2*/
+int64_t pow2floor(int64_t value);
+
+#include "qemu/module.h"
+
+/*
+ * Implementation of ULEB128 (http://en.wikipedia.org/wiki/LEB128)
+ * Input is limited to 14-bit numbers
+ */
+
+int uleb128_encode_small(uint8_t *out, uint32_t n);
+int uleb128_decode_small(const uint8_t *in, uint32_t *n);
+
+/* unicode.c */
+int mod_utf8_codepoint(const char *s, size_t n, char **end);
+
+/*
+ * Hexdump a buffer to a file. An optional string prefix is added to every line
+ */
+
+void qemu_hexdump(const char *buf, FILE *fp, const char *prefix, size_t size);
+
+/* vector definitions */
+#ifdef __ALTIVEC__
+#include <altivec.h>
+/* The altivec.h header says we're allowed to undef these for
+ * C++ compatibility. Here we don't care about C++, but we
+ * undef them anyway to avoid namespace pollution.
+ */
+#undef vector
+#undef pixel
+#undef bool
+#define VECTYPE __vector unsigned char
+#define SPLAT(p) vec_splat(vec_ld(0, p), 0)
+#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
+/* altivec.h may redefine the bool macro as vector type.
+ * Reset it to POSIX semantics. */
+#define bool _Bool
+#elif defined __SSE2__
+#include <emmintrin.h>
+#define VECTYPE __m128i
+#define SPLAT(p) _mm_set1_epi8(*(p))
+#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
+#else
+#define VECTYPE unsigned long
+#define SPLAT(p) (*(p) * (~0UL / 255))
+#define ALL_EQ(v1, v2) ((v1) == (v2))
+#endif
+
+#define BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR 8
+static inline bool
+can_use_buffer_find_nonzero_offset(const void *buf, size_t len)
+{
+ return (len % (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR
+ * sizeof(VECTYPE)) == 0
+ && ((uintptr_t) buf) % sizeof(VECTYPE) == 0);
+}
+size_t buffer_find_nonzero_offset(const void *buf, size_t len);
+
+/*
+ * helper to parse debug environment variables
+ */
+int parse_debug_env(const char *name, int max, int initial);
+
+#endif
diff --git a/contrib/qemu/include/qemu/aes.h b/contrib/qemu/include/qemu/aes.h
new file mode 100644
index 00000000000..e79c707436f
--- /dev/null
+++ b/contrib/qemu/include/qemu/aes.h
@@ -0,0 +1,45 @@
+#ifndef QEMU_AES_H
+#define QEMU_AES_H
+
+#define AES_MAXNR 14
+#define AES_BLOCK_SIZE 16
+
+struct aes_key_st {
+ uint32_t rd_key[4 *(AES_MAXNR + 1)];
+ int rounds;
+};
+typedef struct aes_key_st AES_KEY;
+
+int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
+ AES_KEY *key);
+int AES_set_decrypt_key(const unsigned char *userKey, const int bits,
+ AES_KEY *key);
+
+void AES_encrypt(const unsigned char *in, unsigned char *out,
+ const AES_KEY *key);
+void AES_decrypt(const unsigned char *in, unsigned char *out,
+ const AES_KEY *key);
+void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
+ const unsigned long length, const AES_KEY *key,
+ unsigned char *ivec, const int enc);
+
+/*
+AES_Te0[x] = S [x].[02, 01, 01, 03];
+AES_Te1[x] = S [x].[03, 02, 01, 01];
+AES_Te2[x] = S [x].[01, 03, 02, 01];
+AES_Te3[x] = S [x].[01, 01, 03, 02];
+AES_Te4[x] = S [x].[01, 01, 01, 01];
+
+AES_Td0[x] = Si[x].[0e, 09, 0d, 0b];
+AES_Td1[x] = Si[x].[0b, 0e, 09, 0d];
+AES_Td2[x] = Si[x].[0d, 0b, 0e, 09];
+AES_Td3[x] = Si[x].[09, 0d, 0b, 0e];
+AES_Td4[x] = Si[x].[01, 01, 01, 01];
+*/
+
+extern const uint32_t AES_Te0[256], AES_Te1[256], AES_Te2[256],
+ AES_Te3[256], AES_Te4[256];
+extern const uint32_t AES_Td0[256], AES_Td1[256], AES_Td2[256],
+ AES_Td3[256], AES_Td4[256];
+
+#endif
diff --git a/contrib/qemu/include/qemu/atomic.h b/contrib/qemu/include/qemu/atomic.h
new file mode 100644
index 00000000000..0aa89133018
--- /dev/null
+++ b/contrib/qemu/include/qemu/atomic.h
@@ -0,0 +1,202 @@
+/*
+ * Simple interface for atomic operations.
+ *
+ * Copyright (C) 2013 Red Hat, Inc.
+ *
+ * Author: Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef __QEMU_ATOMIC_H
+#define __QEMU_ATOMIC_H 1
+
+#include "qemu/compiler.h"
+
+/* For C11 atomic ops */
+
+/* Compiler barrier */
+#define barrier() ({ asm volatile("" ::: "memory"); (void)0; })
+
+#ifndef __ATOMIC_RELAXED
+
+/*
+ * We use GCC builtin if it's available, as that can use mfence on
+ * 32-bit as well, e.g. if built with -march=pentium-m. However, on
+ * i386 the spec is buggy, and the implementation followed it until
+ * 4.3 (http://gcc.gnu.org/bugzilla/show_bug.cgi?id=36793).
+ */
+#if defined(__i386__) || defined(__x86_64__)
+#if !QEMU_GNUC_PREREQ(4, 4)
+#if defined __x86_64__
+#define smp_mb() ({ asm volatile("mfence" ::: "memory"); (void)0; })
+#else
+#define smp_mb() ({ asm volatile("lock; addl $0,0(%%esp) " ::: "memory"); (void)0; })
+#endif
+#endif
+#endif
+
+
+#ifdef __alpha__
+#define smp_read_barrier_depends() asm volatile("mb":::"memory")
+#endif
+
+#if defined(__i386__) || defined(__x86_64__) || defined(__s390x__)
+
+/*
+ * Because of the strongly ordered storage model, wmb() and rmb() are nops
+ * here (a compiler barrier only). QEMU doesn't do accesses to write-combining
+ * qemu memory or non-temporal load/stores from C code.
+ */
+#define smp_wmb() barrier()
+#define smp_rmb() barrier()
+
+/*
+ * __sync_lock_test_and_set() is documented to be an acquire barrier only,
+ * but it is a full barrier at the hardware level. Add a compiler barrier
+ * to make it a full barrier also at the compiler level.
+ */
+#define atomic_xchg(ptr, i) (barrier(), __sync_lock_test_and_set(ptr, i))
+
+/*
+ * Load/store with Java volatile semantics.
+ */
+#define atomic_mb_set(ptr, i) ((void)atomic_xchg(ptr, i))
+
+#elif defined(_ARCH_PPC)
+
+/*
+ * We use an eieio() for wmb() on powerpc. This assumes we don't
+ * need to order cacheable and non-cacheable stores with respect to
+ * each other.
+ *
+ * smp_mb has the same problem as on x86 for not-very-new GCC
+ * (http://patchwork.ozlabs.org/patch/126184/, Nov 2011).
+ */
+#define smp_wmb() ({ asm volatile("eieio" ::: "memory"); (void)0; })
+#if defined(__powerpc64__)
+#define smp_rmb() ({ asm volatile("lwsync" ::: "memory"); (void)0; })
+#else
+#define smp_rmb() ({ asm volatile("sync" ::: "memory"); (void)0; })
+#endif
+#define smp_mb() ({ asm volatile("sync" ::: "memory"); (void)0; })
+
+#endif /* _ARCH_PPC */
+
+#endif /* C11 atomics */
+
+/*
+ * For (host) platforms we don't have explicit barrier definitions
+ * for, we use the gcc __sync_synchronize() primitive to generate a
+ * full barrier. This should be safe on all platforms, though it may
+ * be overkill for smp_wmb() and smp_rmb().
+ */
+#ifndef smp_mb
+#define smp_mb() __sync_synchronize()
+#endif
+
+#ifndef smp_wmb
+#ifdef __ATOMIC_RELEASE
+#define smp_wmb() __atomic_thread_fence(__ATOMIC_RELEASE)
+#else
+#define smp_wmb() __sync_synchronize()
+#endif
+#endif
+
+#ifndef smp_rmb
+#ifdef __ATOMIC_ACQUIRE
+#define smp_rmb() __atomic_thread_fence(__ATOMIC_ACQUIRE)
+#else
+#define smp_rmb() __sync_synchronize()
+#endif
+#endif
+
+#ifndef smp_read_barrier_depends
+#ifdef __ATOMIC_CONSUME
+#define smp_read_barrier_depends() __atomic_thread_fence(__ATOMIC_CONSUME)
+#else
+#define smp_read_barrier_depends() barrier()
+#endif
+#endif
+
+#ifndef atomic_read
+#define atomic_read(ptr) (*(__typeof__(*ptr) *volatile) (ptr))
+#endif
+
+#ifndef atomic_set
+#define atomic_set(ptr, i) ((*(__typeof__(*ptr) *volatile) (ptr)) = (i))
+#endif
+
+/* These have the same semantics as Java volatile variables.
+ * See http://gee.cs.oswego.edu/dl/jmm/cookbook.html:
+ * "1. Issue a StoreStore barrier (wmb) before each volatile store."
+ * 2. Issue a StoreLoad barrier after each volatile store.
+ * Note that you could instead issue one before each volatile load, but
+ * this would be slower for typical programs using volatiles in which
+ * reads greatly outnumber writes. Alternatively, if available, you
+ * can implement volatile store as an atomic instruction (for example
+ * XCHG on x86) and omit the barrier. This may be more efficient if
+ * atomic instructions are cheaper than StoreLoad barriers.
+ * 3. Issue LoadLoad and LoadStore barriers after each volatile load."
+ *
+ * If you prefer to think in terms of "pairing" of memory barriers,
+ * an atomic_mb_read pairs with an atomic_mb_set.
+ *
+ * And for the few ia64 lovers that exist, an atomic_mb_read is a ld.acq,
+ * while an atomic_mb_set is a st.rel followed by a memory barrier.
+ *
+ * These are a bit weaker than __atomic_load/store with __ATOMIC_SEQ_CST
+ * (see docs/atomics.txt), and I'm not sure that __ATOMIC_ACQ_REL is enough.
+ * Just always use the barriers manually by the rules above.
+ */
+#ifndef atomic_mb_read
+#define atomic_mb_read(ptr) ({ \
+ typeof(*ptr) _val = atomic_read(ptr); \
+ smp_rmb(); \
+ _val; \
+})
+#endif
+
+#ifndef atomic_mb_set
+#define atomic_mb_set(ptr, i) do { \
+ smp_wmb(); \
+ atomic_set(ptr, i); \
+ smp_mb(); \
+} while (0)
+#endif
+
+#ifndef atomic_xchg
+#ifdef __ATOMIC_SEQ_CST
+#define atomic_xchg(ptr, i) ({ \
+ typeof(*ptr) _new = (i), _old; \
+ __atomic_exchange(ptr, &_new, &_old, __ATOMIC_SEQ_CST); \
+ _old; \
+})
+#elif defined __clang__
+#define atomic_xchg(ptr, i) __sync_exchange(ptr, i)
+#else
+/* __sync_lock_test_and_set() is documented to be an acquire barrier only. */
+#define atomic_xchg(ptr, i) (smp_mb(), __sync_lock_test_and_set(ptr, i))
+#endif
+#endif
+
+/* Provide shorter names for GCC atomic builtins. */
+#define atomic_fetch_inc(ptr) __sync_fetch_and_add(ptr, 1)
+#define atomic_fetch_dec(ptr) __sync_fetch_and_add(ptr, -1)
+#define atomic_fetch_add __sync_fetch_and_add
+#define atomic_fetch_sub __sync_fetch_and_sub
+#define atomic_fetch_and __sync_fetch_and_and
+#define atomic_fetch_or __sync_fetch_and_or
+#define atomic_cmpxchg __sync_val_compare_and_swap
+
+/* And even shorter names that return void. */
+#define atomic_inc(ptr) ((void) __sync_fetch_and_add(ptr, 1))
+#define atomic_dec(ptr) ((void) __sync_fetch_and_add(ptr, -1))
+#define atomic_add(ptr, n) ((void) __sync_fetch_and_add(ptr, n))
+#define atomic_sub(ptr, n) ((void) __sync_fetch_and_sub(ptr, n))
+#define atomic_and(ptr, n) ((void) __sync_fetch_and_and(ptr, n))
+#define atomic_or(ptr, n) ((void) __sync_fetch_and_or(ptr, n))
+
+#endif
diff --git a/contrib/qemu/include/qemu/bitmap.h b/contrib/qemu/include/qemu/bitmap.h
new file mode 100644
index 00000000000..308bbb71e9b
--- /dev/null
+++ b/contrib/qemu/include/qemu/bitmap.h
@@ -0,0 +1,222 @@
+/*
+ * Bitmap Module
+ *
+ * Copyright (C) 2010 Corentin Chary <corentin.chary@gmail.com>
+ *
+ * Mostly inspired by (stolen from) linux/bitmap.h and linux/bitops.h
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef BITMAP_H
+#define BITMAP_H
+
+#include "qemu-common.h"
+#include "qemu/bitops.h"
+
+/*
+ * The available bitmap operations and their rough meaning in the
+ * case that the bitmap is a single unsigned long are thus:
+ *
+ * Note that nbits should be always a compile time evaluable constant.
+ * Otherwise many inlines will generate horrible code.
+ *
+ * bitmap_zero(dst, nbits) *dst = 0UL
+ * bitmap_fill(dst, nbits) *dst = ~0UL
+ * bitmap_copy(dst, src, nbits) *dst = *src
+ * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2
+ * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2
+ * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2
+ * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2)
+ * bitmap_complement(dst, src, nbits) *dst = ~(*src)
+ * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal?
+ * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap?
+ * bitmap_empty(src, nbits) Are all bits zero in *src?
+ * bitmap_full(src, nbits) Are all bits set in *src?
+ * bitmap_set(dst, pos, nbits) Set specified bit area
+ * bitmap_clear(dst, pos, nbits) Clear specified bit area
+ * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area
+ */
+
+/*
+ * Also the following operations apply to bitmaps.
+ *
+ * set_bit(bit, addr) *addr |= bit
+ * clear_bit(bit, addr) *addr &= ~bit
+ * change_bit(bit, addr) *addr ^= bit
+ * test_bit(bit, addr) Is bit set in *addr?
+ * test_and_set_bit(bit, addr) Set bit and return old value
+ * test_and_clear_bit(bit, addr) Clear bit and return old value
+ * test_and_change_bit(bit, addr) Change bit and return old value
+ * find_first_zero_bit(addr, nbits) Position first zero bit in *addr
+ * find_first_bit(addr, nbits) Position first set bit in *addr
+ * find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit
+ * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit
+ */
+
+#define BITMAP_LAST_WORD_MASK(nbits) \
+ ( \
+ ((nbits) % BITS_PER_LONG) ? \
+ (1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL \
+ )
+
+#define DECLARE_BITMAP(name,bits) \
+ unsigned long name[BITS_TO_LONGS(bits)]
+
+#define small_nbits(nbits) \
+ ((nbits) <= BITS_PER_LONG)
+
+int slow_bitmap_empty(const unsigned long *bitmap, int bits);
+int slow_bitmap_full(const unsigned long *bitmap, int bits);
+int slow_bitmap_equal(const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits);
+void slow_bitmap_complement(unsigned long *dst, const unsigned long *src,
+ int bits);
+void slow_bitmap_shift_right(unsigned long *dst,
+ const unsigned long *src, int shift, int bits);
+void slow_bitmap_shift_left(unsigned long *dst,
+ const unsigned long *src, int shift, int bits);
+int slow_bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits);
+void slow_bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits);
+void slow_bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits);
+int slow_bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits);
+int slow_bitmap_intersects(const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits);
+
+static inline unsigned long *bitmap_new(int nbits)
+{
+ int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ return g_malloc0(len);
+}
+
+static inline void bitmap_zero(unsigned long *dst, int nbits)
+{
+ if (small_nbits(nbits)) {
+ *dst = 0UL;
+ } else {
+ int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ memset(dst, 0, len);
+ }
+}
+
+static inline void bitmap_fill(unsigned long *dst, int nbits)
+{
+ size_t nlongs = BITS_TO_LONGS(nbits);
+ if (!small_nbits(nbits)) {
+ int len = (nlongs - 1) * sizeof(unsigned long);
+ memset(dst, 0xff, len);
+ }
+ dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
+}
+
+static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
+ int nbits)
+{
+ if (small_nbits(nbits)) {
+ *dst = *src;
+ } else {
+ int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+ memcpy(dst, src, len);
+ }
+}
+
+static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
+ const unsigned long *src2, int nbits)
+{
+ if (small_nbits(nbits)) {
+ return (*dst = *src1 & *src2) != 0;
+ }
+ return slow_bitmap_and(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
+ const unsigned long *src2, int nbits)
+{
+ if (small_nbits(nbits)) {
+ *dst = *src1 | *src2;
+ } else {
+ slow_bitmap_or(dst, src1, src2, nbits);
+ }
+}
+
+static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
+ const unsigned long *src2, int nbits)
+{
+ if (small_nbits(nbits)) {
+ *dst = *src1 ^ *src2;
+ } else {
+ slow_bitmap_xor(dst, src1, src2, nbits);
+ }
+}
+
+static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+ const unsigned long *src2, int nbits)
+{
+ if (small_nbits(nbits)) {
+ return (*dst = *src1 & ~(*src2)) != 0;
+ }
+ return slow_bitmap_andnot(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
+ int nbits)
+{
+ if (small_nbits(nbits)) {
+ *dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits);
+ } else {
+ slow_bitmap_complement(dst, src, nbits);
+ }
+}
+
+static inline int bitmap_equal(const unsigned long *src1,
+ const unsigned long *src2, int nbits)
+{
+ if (small_nbits(nbits)) {
+ return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
+ } else {
+ return slow_bitmap_equal(src1, src2, nbits);
+ }
+}
+
+static inline int bitmap_empty(const unsigned long *src, int nbits)
+{
+ if (small_nbits(nbits)) {
+ return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
+ } else {
+ return slow_bitmap_empty(src, nbits);
+ }
+}
+
+static inline int bitmap_full(const unsigned long *src, int nbits)
+{
+ if (small_nbits(nbits)) {
+ return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
+ } else {
+ return slow_bitmap_full(src, nbits);
+ }
+}
+
+static inline int bitmap_intersects(const unsigned long *src1,
+ const unsigned long *src2, int nbits)
+{
+ if (small_nbits(nbits)) {
+ return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+ } else {
+ return slow_bitmap_intersects(src1, src2, nbits);
+ }
+}
+
+void bitmap_set(unsigned long *map, int i, int len);
+void bitmap_clear(unsigned long *map, int start, int nr);
+unsigned long bitmap_find_next_zero_area(unsigned long *map,
+ unsigned long size,
+ unsigned long start,
+ unsigned int nr,
+ unsigned long align_mask);
+
+#endif /* BITMAP_H */
diff --git a/contrib/qemu/include/qemu/bitops.h b/contrib/qemu/include/qemu/bitops.h
new file mode 100644
index 00000000000..affcc969dcf
--- /dev/null
+++ b/contrib/qemu/include/qemu/bitops.h
@@ -0,0 +1,276 @@
+/*
+ * Bitops Module
+ *
+ * Copyright (C) 2010 Corentin Chary <corentin.chary@gmail.com>
+ *
+ * Mostly inspired by (stolen from) linux/bitmap.h and linux/bitops.h
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#ifndef BITOPS_H
+#define BITOPS_H
+
+#include "qemu-common.h"
+#include "host-utils.h"
+
+#define BITS_PER_BYTE CHAR_BIT
+#define BITS_PER_LONG (sizeof (unsigned long) * BITS_PER_BYTE)
+
+#define BIT(nr) (1UL << (nr))
+#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
+#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+
+/**
+ * set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ */
+static inline void set_bit(int nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = addr + BIT_WORD(nr);
+
+ *p |= mask;
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ */
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = addr + BIT_WORD(nr);
+
+ *p &= ~mask;
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ */
+static inline void change_bit(int nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = addr + BIT_WORD(nr);
+
+ *p ^= mask;
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+static inline int test_and_set_bit(int nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = addr + BIT_WORD(nr);
+ unsigned long old = *p;
+
+ *p = old | mask;
+ return (old & mask) != 0;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ */
+static inline int test_and_clear_bit(int nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = addr + BIT_WORD(nr);
+ unsigned long old = *p;
+
+ *p = old & ~mask;
+ return (old & mask) != 0;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ */
+static inline int test_and_change_bit(int nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ unsigned long *p = addr + BIT_WORD(nr);
+ unsigned long old = *p;
+
+ *p = old ^ mask;
+ return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const unsigned long *addr)
+{
+ return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+/**
+ * find_last_bit - find the last set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit, or size.
+ */
+unsigned long find_last_bit(const unsigned long *addr,
+ unsigned long size);
+
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+unsigned long find_next_bit(const unsigned long *addr,
+ unsigned long size, unsigned long offset);
+
+/**
+ * find_next_zero_bit - find the next cleared bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The bitmap size in bits
+ */
+
+unsigned long find_next_zero_bit(const unsigned long *addr,
+ unsigned long size,
+ unsigned long offset);
+
+/**
+ * find_first_bit - find the first set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit.
+ */
+static inline unsigned long find_first_bit(const unsigned long *addr,
+ unsigned long size)
+{
+ return find_next_bit(addr, size, 0);
+}
+
+/**
+ * find_first_zero_bit - find the first cleared bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first cleared bit.
+ */
+static inline unsigned long find_first_zero_bit(const unsigned long *addr,
+ unsigned long size)
+{
+ return find_next_zero_bit(addr, size, 0);
+}
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+ unsigned long count;
+
+ for (count = 0; w; w >>= 1) {
+ count += w & 1;
+ }
+ return count;
+}
+
+/**
+ * extract32:
+ * @value: the value to extract the bit field from
+ * @start: the lowest bit in the bit field (numbered from 0)
+ * @length: the length of the bit field
+ *
+ * Extract from the 32 bit input @value the bit field specified by the
+ * @start and @length parameters, and return it. The bit field must
+ * lie entirely within the 32 bit word. It is valid to request that
+ * all 32 bits are returned (ie @length 32 and @start 0).
+ *
+ * Returns: the value of the bit field extracted from the input value.
+ */
+static inline uint32_t extract32(uint32_t value, int start, int length)
+{
+ assert(start >= 0 && length > 0 && length <= 32 - start);
+ return (value >> start) & (~0U >> (32 - length));
+}
+
+/**
+ * extract64:
+ * @value: the value to extract the bit field from
+ * @start: the lowest bit in the bit field (numbered from 0)
+ * @length: the length of the bit field
+ *
+ * Extract from the 64 bit input @value the bit field specified by the
+ * @start and @length parameters, and return it. The bit field must
+ * lie entirely within the 64 bit word. It is valid to request that
+ * all 64 bits are returned (ie @length 64 and @start 0).
+ *
+ * Returns: the value of the bit field extracted from the input value.
+ */
+static inline uint64_t extract64(uint64_t value, int start, int length)
+{
+ assert(start >= 0 && length > 0 && length <= 64 - start);
+ return (value >> start) & (~0ULL >> (64 - length));
+}
+
+/**
+ * deposit32:
+ * @value: initial value to insert bit field into
+ * @start: the lowest bit in the bit field (numbered from 0)
+ * @length: the length of the bit field
+ * @fieldval: the value to insert into the bit field
+ *
+ * Deposit @fieldval into the 32 bit @value at the bit field specified
+ * by the @start and @length parameters, and return the modified
+ * @value. Bits of @value outside the bit field are not modified.
+ * Bits of @fieldval above the least significant @length bits are
+ * ignored. The bit field must lie entirely within the 32 bit word.
+ * It is valid to request that all 32 bits are modified (ie @length
+ * 32 and @start 0).
+ *
+ * Returns: the modified @value.
+ */
+static inline uint32_t deposit32(uint32_t value, int start, int length,
+ uint32_t fieldval)
+{
+ uint32_t mask;
+ assert(start >= 0 && length > 0 && length <= 32 - start);
+ mask = (~0U >> (32 - length)) << start;
+ return (value & ~mask) | ((fieldval << start) & mask);
+}
+
+/**
+ * deposit64:
+ * @value: initial value to insert bit field into
+ * @start: the lowest bit in the bit field (numbered from 0)
+ * @length: the length of the bit field
+ * @fieldval: the value to insert into the bit field
+ *
+ * Deposit @fieldval into the 64 bit @value at the bit field specified
+ * by the @start and @length parameters, and return the modified
+ * @value. Bits of @value outside the bit field are not modified.
+ * Bits of @fieldval above the least significant @length bits are
+ * ignored. The bit field must lie entirely within the 64 bit word.
+ * It is valid to request that all 64 bits are modified (ie @length
+ * 64 and @start 0).
+ *
+ * Returns: the modified @value.
+ */
+static inline uint64_t deposit64(uint64_t value, int start, int length,
+ uint64_t fieldval)
+{
+ uint64_t mask;
+ assert(start >= 0 && length > 0 && length <= 64 - start);
+ mask = (~0ULL >> (64 - length)) << start;
+ return (value & ~mask) | ((fieldval << start) & mask);
+}
+
+#endif
diff --git a/contrib/qemu/include/qemu/bswap.h b/contrib/qemu/include/qemu/bswap.h
new file mode 100644
index 00000000000..14a5f657ce5
--- /dev/null
+++ b/contrib/qemu/include/qemu/bswap.h
@@ -0,0 +1,478 @@
+#ifndef BSWAP_H
+#define BSWAP_H
+
+#include "config-host.h"
+#include <inttypes.h>
+#include <limits.h>
+#include <string.h>
+#include "fpu/softfloat.h"
+
+#ifdef CONFIG_MACHINE_BSWAP_H
+# include <sys/endian.h>
+# include <sys/types.h>
+# include <machine/bswap.h>
+#elif defined(CONFIG_BYTESWAP_H)
+# include <byteswap.h>
+
+static inline uint16_t bswap16(uint16_t x)
+{
+ return bswap_16(x);
+}
+
+static inline uint32_t bswap32(uint32_t x)
+{
+ return bswap_32(x);
+}
+
+static inline uint64_t bswap64(uint64_t x)
+{
+ return bswap_64(x);
+}
+# else
+static inline uint16_t bswap16(uint16_t x)
+{
+ return (((x & 0x00ff) << 8) |
+ ((x & 0xff00) >> 8));
+}
+
+static inline uint32_t bswap32(uint32_t x)
+{
+ return (((x & 0x000000ffU) << 24) |
+ ((x & 0x0000ff00U) << 8) |
+ ((x & 0x00ff0000U) >> 8) |
+ ((x & 0xff000000U) >> 24));
+}
+
+static inline uint64_t bswap64(uint64_t x)
+{
+ return (((x & 0x00000000000000ffULL) << 56) |
+ ((x & 0x000000000000ff00ULL) << 40) |
+ ((x & 0x0000000000ff0000ULL) << 24) |
+ ((x & 0x00000000ff000000ULL) << 8) |
+ ((x & 0x000000ff00000000ULL) >> 8) |
+ ((x & 0x0000ff0000000000ULL) >> 24) |
+ ((x & 0x00ff000000000000ULL) >> 40) |
+ ((x & 0xff00000000000000ULL) >> 56));
+}
+#endif /* ! CONFIG_MACHINE_BSWAP_H */
+
+static inline void bswap16s(uint16_t *s)
+{
+ *s = bswap16(*s);
+}
+
+static inline void bswap32s(uint32_t *s)
+{
+ *s = bswap32(*s);
+}
+
+static inline void bswap64s(uint64_t *s)
+{
+ *s = bswap64(*s);
+}
+
+#if defined(HOST_WORDS_BIGENDIAN)
+#define be_bswap(v, size) (v)
+#define le_bswap(v, size) glue(bswap, size)(v)
+#define be_bswaps(v, size)
+#define le_bswaps(p, size) do { *p = glue(bswap, size)(*p); } while(0)
+#else
+#define le_bswap(v, size) (v)
+#define be_bswap(v, size) glue(bswap, size)(v)
+#define le_bswaps(v, size)
+#define be_bswaps(p, size) do { *p = glue(bswap, size)(*p); } while(0)
+#endif
+
+#define CPU_CONVERT(endian, size, type)\
+static inline type endian ## size ## _to_cpu(type v)\
+{\
+ return glue(endian, _bswap)(v, size);\
+}\
+\
+static inline type cpu_to_ ## endian ## size(type v)\
+{\
+ return glue(endian, _bswap)(v, size);\
+}\
+\
+static inline void endian ## size ## _to_cpus(type *p)\
+{\
+ glue(endian, _bswaps)(p, size);\
+}\
+\
+static inline void cpu_to_ ## endian ## size ## s(type *p)\
+{\
+ glue(endian, _bswaps)(p, size);\
+}\
+\
+static inline type endian ## size ## _to_cpup(const type *p)\
+{\
+ return glue(glue(endian, size), _to_cpu)(*p);\
+}\
+\
+static inline void cpu_to_ ## endian ## size ## w(type *p, type v)\
+{\
+ *p = glue(glue(cpu_to_, endian), size)(v);\
+}
+
+CPU_CONVERT(be, 16, uint16_t)
+CPU_CONVERT(be, 32, uint32_t)
+CPU_CONVERT(be, 64, uint64_t)
+
+CPU_CONVERT(le, 16, uint16_t)
+CPU_CONVERT(le, 32, uint32_t)
+CPU_CONVERT(le, 64, uint64_t)
+
+/* len must be one of 1, 2, 4 */
+static inline uint32_t qemu_bswap_len(uint32_t value, int len)
+{
+ return bswap32(value) >> (32 - 8 * len);
+}
+
+/* Unions for reinterpreting between floats and integers. */
+
+typedef union {
+ float32 f;
+ uint32_t l;
+} CPU_FloatU;
+
+typedef union {
+ float64 d;
+#if defined(HOST_WORDS_BIGENDIAN)
+ struct {
+ uint32_t upper;
+ uint32_t lower;
+ } l;
+#else
+ struct {
+ uint32_t lower;
+ uint32_t upper;
+ } l;
+#endif
+ uint64_t ll;
+} CPU_DoubleU;
+
+typedef union {
+ floatx80 d;
+ struct {
+ uint64_t lower;
+ uint16_t upper;
+ } l;
+} CPU_LDoubleU;
+
+typedef union {
+ float128 q;
+#if defined(HOST_WORDS_BIGENDIAN)
+ struct {
+ uint32_t upmost;
+ uint32_t upper;
+ uint32_t lower;
+ uint32_t lowest;
+ } l;
+ struct {
+ uint64_t upper;
+ uint64_t lower;
+ } ll;
+#else
+ struct {
+ uint32_t lowest;
+ uint32_t lower;
+ uint32_t upper;
+ uint32_t upmost;
+ } l;
+ struct {
+ uint64_t lower;
+ uint64_t upper;
+ } ll;
+#endif
+} CPU_QuadU;
+
+/* unaligned/endian-independent pointer access */
+
+/*
+ * the generic syntax is:
+ *
+ * load: ld{type}{sign}{size}{endian}_p(ptr)
+ *
+ * store: st{type}{size}{endian}_p(ptr, val)
+ *
+ * Note there are small differences with the softmmu access API!
+ *
+ * type is:
+ * (empty): integer access
+ * f : float access
+ *
+ * sign is:
+ * (empty): for floats or 32 bit size
+ * u : unsigned
+ * s : signed
+ *
+ * size is:
+ * b: 8 bits
+ * w: 16 bits
+ * l: 32 bits
+ * q: 64 bits
+ *
+ * endian is:
+ * (empty): host endian
+ * be : big endian
+ * le : little endian
+ */
+
+static inline int ldub_p(const void *ptr)
+{
+ return *(uint8_t *)ptr;
+}
+
+static inline int ldsb_p(const void *ptr)
+{
+ return *(int8_t *)ptr;
+}
+
+static inline void stb_p(void *ptr, int v)
+{
+ *(uint8_t *)ptr = v;
+}
+
+/* Any compiler worth its salt will turn these memcpy into native unaligned
+ operations. Thus we don't need to play games with packed attributes, or
+ inline byte-by-byte stores. */
+
+static inline int lduw_p(const void *ptr)
+{
+ uint16_t r;
+ memcpy(&r, ptr, sizeof(r));
+ return r;
+}
+
+static inline int ldsw_p(const void *ptr)
+{
+ int16_t r;
+ memcpy(&r, ptr, sizeof(r));
+ return r;
+}
+
+static inline void stw_p(void *ptr, uint16_t v)
+{
+ memcpy(ptr, &v, sizeof(v));
+}
+
+static inline int ldl_p(const void *ptr)
+{
+ int32_t r;
+ memcpy(&r, ptr, sizeof(r));
+ return r;
+}
+
+static inline void stl_p(void *ptr, uint32_t v)
+{
+ memcpy(ptr, &v, sizeof(v));
+}
+
+static inline uint64_t ldq_p(const void *ptr)
+{
+ uint64_t r;
+ memcpy(&r, ptr, sizeof(r));
+ return r;
+}
+
+static inline void stq_p(void *ptr, uint64_t v)
+{
+ memcpy(ptr, &v, sizeof(v));
+}
+
+static inline int lduw_le_p(const void *ptr)
+{
+ return (uint16_t)le_bswap(lduw_p(ptr), 16);
+}
+
+static inline int ldsw_le_p(const void *ptr)
+{
+ return (int16_t)le_bswap(lduw_p(ptr), 16);
+}
+
+static inline int ldl_le_p(const void *ptr)
+{
+ return le_bswap(ldl_p(ptr), 32);
+}
+
+static inline uint64_t ldq_le_p(const void *ptr)
+{
+ return le_bswap(ldq_p(ptr), 64);
+}
+
+static inline void stw_le_p(void *ptr, int v)
+{
+ stw_p(ptr, le_bswap(v, 16));
+}
+
+static inline void stl_le_p(void *ptr, int v)
+{
+ stl_p(ptr, le_bswap(v, 32));
+}
+
+static inline void stq_le_p(void *ptr, uint64_t v)
+{
+ stq_p(ptr, le_bswap(v, 64));
+}
+
+/* float access */
+
+static inline float32 ldfl_le_p(const void *ptr)
+{
+ CPU_FloatU u;
+ u.l = ldl_le_p(ptr);
+ return u.f;
+}
+
+static inline void stfl_le_p(void *ptr, float32 v)
+{
+ CPU_FloatU u;
+ u.f = v;
+ stl_le_p(ptr, u.l);
+}
+
+static inline float64 ldfq_le_p(const void *ptr)
+{
+ CPU_DoubleU u;
+ u.ll = ldq_le_p(ptr);
+ return u.d;
+}
+
+static inline void stfq_le_p(void *ptr, float64 v)
+{
+ CPU_DoubleU u;
+ u.d = v;
+ stq_le_p(ptr, u.ll);
+}
+
+static inline int lduw_be_p(const void *ptr)
+{
+ return (uint16_t)be_bswap(lduw_p(ptr), 16);
+}
+
+static inline int ldsw_be_p(const void *ptr)
+{
+ return (int16_t)be_bswap(lduw_p(ptr), 16);
+}
+
+static inline int ldl_be_p(const void *ptr)
+{
+ return be_bswap(ldl_p(ptr), 32);
+}
+
+static inline uint64_t ldq_be_p(const void *ptr)
+{
+ return be_bswap(ldq_p(ptr), 64);
+}
+
+static inline void stw_be_p(void *ptr, int v)
+{
+ stw_p(ptr, be_bswap(v, 16));
+}
+
+static inline void stl_be_p(void *ptr, int v)
+{
+ stl_p(ptr, be_bswap(v, 32));
+}
+
+static inline void stq_be_p(void *ptr, uint64_t v)
+{
+ stq_p(ptr, be_bswap(v, 64));
+}
+
+/* float access */
+
+static inline float32 ldfl_be_p(const void *ptr)
+{
+ CPU_FloatU u;
+ u.l = ldl_be_p(ptr);
+ return u.f;
+}
+
+static inline void stfl_be_p(void *ptr, float32 v)
+{
+ CPU_FloatU u;
+ u.f = v;
+ stl_be_p(ptr, u.l);
+}
+
+static inline float64 ldfq_be_p(const void *ptr)
+{
+ CPU_DoubleU u;
+ u.ll = ldq_be_p(ptr);
+ return u.d;
+}
+
+static inline void stfq_be_p(void *ptr, float64 v)
+{
+ CPU_DoubleU u;
+ u.d = v;
+ stq_be_p(ptr, u.ll);
+}
+
+/* Legacy unaligned versions. Note that we never had a complete set. */
+
+static inline void cpu_to_le16wu(uint16_t *p, uint16_t v)
+{
+ stw_le_p(p, v);
+}
+
+static inline void cpu_to_le32wu(uint32_t *p, uint32_t v)
+{
+ stl_le_p(p, v);
+}
+
+static inline uint16_t le16_to_cpupu(const uint16_t *p)
+{
+ return lduw_le_p(p);
+}
+
+static inline uint32_t le32_to_cpupu(const uint32_t *p)
+{
+ return ldl_le_p(p);
+}
+
+static inline uint32_t be32_to_cpupu(const uint32_t *p)
+{
+ return ldl_be_p(p);
+}
+
+static inline void cpu_to_be16wu(uint16_t *p, uint16_t v)
+{
+ stw_be_p(p, v);
+}
+
+static inline void cpu_to_be32wu(uint32_t *p, uint32_t v)
+{
+ stl_be_p(p, v);
+}
+
+static inline void cpu_to_be64wu(uint64_t *p, uint64_t v)
+{
+ stq_be_p(p, v);
+}
+
+static inline void cpu_to_32wu(uint32_t *p, uint32_t v)
+{
+ stl_p(p, v);
+}
+
+static inline unsigned long leul_to_cpu(unsigned long v)
+{
+ /* In order to break an include loop between here and
+ qemu-common.h, don't rely on HOST_LONG_BITS. */
+#if ULONG_MAX == UINT32_MAX
+ return le_bswap(v, 32);
+#elif ULONG_MAX == UINT64_MAX
+ return le_bswap(v, 64);
+#else
+# error Unknown sizeof long
+#endif
+}
+
+#undef le_bswap
+#undef be_bswap
+#undef le_bswaps
+#undef be_bswaps
+
+#endif /* BSWAP_H */
diff --git a/contrib/qemu/include/qemu/compiler.h b/contrib/qemu/include/qemu/compiler.h
new file mode 100644
index 00000000000..155b358964a
--- /dev/null
+++ b/contrib/qemu/include/qemu/compiler.h
@@ -0,0 +1,55 @@
+/* public domain */
+
+#ifndef COMPILER_H
+#define COMPILER_H
+
+#include "config-host.h"
+
+/*----------------------------------------------------------------------------
+| The macro QEMU_GNUC_PREREQ tests for minimum version of the GNU C compiler.
+| The code is a copy of SOFTFLOAT_GNUC_PREREQ, see softfloat-macros.h.
+*----------------------------------------------------------------------------*/
+#if defined(__GNUC__) && defined(__GNUC_MINOR__)
+# define QEMU_GNUC_PREREQ(maj, min) \
+ ((__GNUC__ << 16) + __GNUC_MINOR__ >= ((maj) << 16) + (min))
+#else
+# define QEMU_GNUC_PREREQ(maj, min) 0
+#endif
+
+#define QEMU_NORETURN __attribute__ ((__noreturn__))
+
+#if QEMU_GNUC_PREREQ(3, 4)
+#define QEMU_WARN_UNUSED_RESULT __attribute__((warn_unused_result))
+#else
+#define QEMU_WARN_UNUSED_RESULT
+#endif
+
+#if defined(_WIN32)
+# define QEMU_PACKED __attribute__((gcc_struct, packed))
+#else
+# define QEMU_PACKED __attribute__((packed))
+#endif
+
+#define cat(x,y) x ## y
+#define cat2(x,y) cat(x,y)
+#define QEMU_BUILD_BUG_ON(x) \
+ typedef char cat2(qemu_build_bug_on__,__LINE__)[(x)?-1:1] __attribute__((unused));
+
+#if defined __GNUC__
+# if !QEMU_GNUC_PREREQ(4, 4)
+ /* gcc versions before 4.4.x don't support gnu_printf, so use printf. */
+# define GCC_FMT_ATTR(n, m) __attribute__((format(printf, n, m)))
+# else
+ /* Use gnu_printf when supported (qemu uses standard format strings). */
+# define GCC_FMT_ATTR(n, m) __attribute__((format(gnu_printf, n, m)))
+# if defined(_WIN32)
+ /* Map __printf__ to __gnu_printf__ because we want standard format strings
+ * even when MinGW or GLib include files use __printf__. */
+# define __printf__ __gnu_printf__
+# endif
+# endif
+#else
+#define GCC_FMT_ATTR(n, m)
+#endif
+
+#endif /* COMPILER_H */
diff --git a/contrib/qemu/include/qemu/error-report.h b/contrib/qemu/include/qemu/error-report.h
new file mode 100644
index 00000000000..3b098a91730
--- /dev/null
+++ b/contrib/qemu/include/qemu/error-report.h
@@ -0,0 +1,46 @@
+/*
+ * Error reporting
+ *
+ * Copyright (C) 2010 Red Hat Inc.
+ *
+ * Authors:
+ * Markus Armbruster <armbru@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_ERROR_H
+#define QEMU_ERROR_H
+
+#include <stdarg.h>
+#include <stdbool.h>
+#include "qemu/compiler.h"
+
+typedef struct Location {
+ /* all members are private to qemu-error.c */
+ enum { LOC_NONE, LOC_CMDLINE, LOC_FILE } kind;
+ int num;
+ const void *ptr;
+ struct Location *prev;
+} Location;
+
+Location *loc_push_restore(Location *loc);
+Location *loc_push_none(Location *loc);
+Location *loc_pop(Location *loc);
+Location *loc_save(Location *loc);
+void loc_restore(Location *loc);
+void loc_set_none(void);
+void loc_set_cmdline(char **argv, int idx, int cnt);
+void loc_set_file(const char *fname, int lno);
+
+void error_vprintf(const char *fmt, va_list ap) GCC_FMT_ATTR(1, 0);
+void error_printf(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
+void error_printf_unless_qmp(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
+void error_print_loc(void);
+void error_set_progname(const char *argv0);
+void error_report(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
+const char *error_get_progname(void);
+extern bool enable_timestamp_msg;
+
+#endif
diff --git a/contrib/qemu/include/qemu/event_notifier.h b/contrib/qemu/include/qemu/event_notifier.h
new file mode 100644
index 00000000000..88b57af7ce8
--- /dev/null
+++ b/contrib/qemu/include/qemu/event_notifier.h
@@ -0,0 +1,46 @@
+/*
+ * event notifier support
+ *
+ * Copyright Red Hat, Inc. 2010
+ *
+ * Authors:
+ * Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#ifndef QEMU_EVENT_NOTIFIER_H
+#define QEMU_EVENT_NOTIFIER_H
+
+#include "qemu-common.h"
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
+
+struct EventNotifier {
+#ifdef _WIN32
+ HANDLE event;
+#else
+ int rfd;
+ int wfd;
+#endif
+};
+
+typedef void EventNotifierHandler(EventNotifier *);
+
+int event_notifier_init(EventNotifier *, int active);
+void event_notifier_cleanup(EventNotifier *);
+int event_notifier_set(EventNotifier *);
+int event_notifier_test_and_clear(EventNotifier *);
+int event_notifier_set_handler(EventNotifier *, EventNotifierHandler *);
+
+#ifdef CONFIG_POSIX
+void event_notifier_init_fd(EventNotifier *, int fd);
+int event_notifier_get_fd(EventNotifier *);
+#else
+HANDLE event_notifier_get_handle(EventNotifier *);
+#endif
+
+#endif
diff --git a/contrib/qemu/include/qemu/hbitmap.h b/contrib/qemu/include/qemu/hbitmap.h
new file mode 100644
index 00000000000..550d7ce2c39
--- /dev/null
+++ b/contrib/qemu/include/qemu/hbitmap.h
@@ -0,0 +1,209 @@
+/*
+ * Hierarchical Bitmap Data Type
+ *
+ * Copyright Red Hat, Inc., 2012
+ *
+ * Author: Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later. See the COPYING file in the top-level directory.
+ */
+
+#ifndef HBITMAP_H
+#define HBITMAP_H 1
+
+#include <limits.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include "bitops.h"
+#include "host-utils.h"
+
+typedef struct HBitmap HBitmap;
+typedef struct HBitmapIter HBitmapIter;
+
+#define BITS_PER_LEVEL (BITS_PER_LONG == 32 ? 5 : 6)
+
+/* For 32-bit, the largest that fits in a 4 GiB address space.
+ * For 64-bit, the number of sectors in 1 PiB. Good luck, in
+ * either case... :)
+ */
+#define HBITMAP_LOG_MAX_SIZE (BITS_PER_LONG == 32 ? 34 : 41)
+
+/* We need to place a sentinel in level 0 to speed up iteration. Thus,
+ * we do this instead of HBITMAP_LOG_MAX_SIZE / BITS_PER_LEVEL. The
+ * difference is that it allocates an extra level when HBITMAP_LOG_MAX_SIZE
+ * is an exact multiple of BITS_PER_LEVEL.
+ */
+#define HBITMAP_LEVELS ((HBITMAP_LOG_MAX_SIZE / BITS_PER_LEVEL) + 1)
+
+struct HBitmapIter {
+ const HBitmap *hb;
+
+ /* Copied from hb for access in the inline functions (hb is opaque). */
+ int granularity;
+
+ /* Entry offset into the last-level array of longs. */
+ size_t pos;
+
+ /* The currently-active path in the tree. Each item of cur[i] stores
+ * the bits (i.e. the subtrees) yet to be processed under that node.
+ */
+ unsigned long cur[HBITMAP_LEVELS];
+};
+
+/**
+ * hbitmap_alloc:
+ * @size: Number of bits in the bitmap.
+ * @granularity: Granularity of the bitmap. Aligned groups of 2^@granularity
+ * bits will be represented by a single bit. Each operation on a
+ * range of bits first rounds the bits to determine which group they land
+ * in, and then affect the entire set; iteration will only visit the first
+ * bit of each group.
+ *
+ * Allocate a new HBitmap.
+ */
+HBitmap *hbitmap_alloc(uint64_t size, int granularity);
+
+/**
+ * hbitmap_empty:
+ * @hb: HBitmap to operate on.
+ *
+ * Return whether the bitmap is empty.
+ */
+bool hbitmap_empty(const HBitmap *hb);
+
+/**
+ * hbitmap_granularity:
+ * @hb: HBitmap to operate on.
+ *
+ * Return the granularity of the HBitmap.
+ */
+int hbitmap_granularity(const HBitmap *hb);
+
+/**
+ * hbitmap_count:
+ * @hb: HBitmap to operate on.
+ *
+ * Return the number of bits set in the HBitmap.
+ */
+uint64_t hbitmap_count(const HBitmap *hb);
+
+/**
+ * hbitmap_set:
+ * @hb: HBitmap to operate on.
+ * @start: First bit to set (0-based).
+ * @count: Number of bits to set.
+ *
+ * Set a consecutive range of bits in an HBitmap.
+ */
+void hbitmap_set(HBitmap *hb, uint64_t start, uint64_t count);
+
+/**
+ * hbitmap_reset:
+ * @hb: HBitmap to operate on.
+ * @start: First bit to reset (0-based).
+ * @count: Number of bits to reset.
+ *
+ * Reset a consecutive range of bits in an HBitmap.
+ */
+void hbitmap_reset(HBitmap *hb, uint64_t start, uint64_t count);
+
+/**
+ * hbitmap_get:
+ * @hb: HBitmap to operate on.
+ * @item: Bit to query (0-based).
+ *
+ * Return whether the @item-th bit in an HBitmap is set.
+ */
+bool hbitmap_get(const HBitmap *hb, uint64_t item);
+
+/**
+ * hbitmap_free:
+ * @hb: HBitmap to operate on.
+ *
+ * Free an HBitmap and all of its associated memory.
+ */
+void hbitmap_free(HBitmap *hb);
+
+/**
+ * hbitmap_iter_init:
+ * @hbi: HBitmapIter to initialize.
+ * @hb: HBitmap to iterate on.
+ * @first: First bit to visit (0-based, must be strictly less than the
+ * size of the bitmap).
+ *
+ * Set up @hbi to iterate on the HBitmap @hb. hbitmap_iter_next will return
+ * the lowest-numbered bit that is set in @hb, starting at @first.
+ *
+ * Concurrent setting of bits is acceptable, and will at worst cause the
+ * iteration to miss some of those bits. Resetting bits before the current
+ * position of the iterator is also okay. However, concurrent resetting of
+ * bits can lead to unexpected behavior if the iterator has not yet reached
+ * those bits.
+ */
+void hbitmap_iter_init(HBitmapIter *hbi, const HBitmap *hb, uint64_t first);
+
+/* hbitmap_iter_skip_words:
+ * @hbi: HBitmapIter to operate on.
+ *
+ * Internal function used by hbitmap_iter_next and hbitmap_iter_next_word.
+ */
+unsigned long hbitmap_iter_skip_words(HBitmapIter *hbi);
+
+/**
+ * hbitmap_iter_next:
+ * @hbi: HBitmapIter to operate on.
+ *
+ * Return the next bit that is set in @hbi's associated HBitmap,
+ * or -1 if all remaining bits are zero.
+ */
+static inline int64_t hbitmap_iter_next(HBitmapIter *hbi)
+{
+ unsigned long cur = hbi->cur[HBITMAP_LEVELS - 1];
+ int64_t item;
+
+ if (cur == 0) {
+ cur = hbitmap_iter_skip_words(hbi);
+ if (cur == 0) {
+ return -1;
+ }
+ }
+
+ /* The next call will resume work from the next bit. */
+ hbi->cur[HBITMAP_LEVELS - 1] = cur & (cur - 1);
+ item = ((uint64_t)hbi->pos << BITS_PER_LEVEL) + ctzl(cur);
+
+ return item << hbi->granularity;
+}
+
+/**
+ * hbitmap_iter_next_word:
+ * @hbi: HBitmapIter to operate on.
+ * @p_cur: Location where to store the next non-zero word.
+ *
+ * Return the index of the next nonzero word that is set in @hbi's
+ * associated HBitmap, and set *p_cur to the content of that word
+ * (bits before the index that was passed to hbitmap_iter_init are
+ * trimmed on the first call). Return -1, and set *p_cur to zero,
+ * if all remaining words are zero.
+ */
+static inline size_t hbitmap_iter_next_word(HBitmapIter *hbi, unsigned long *p_cur)
+{
+ unsigned long cur = hbi->cur[HBITMAP_LEVELS - 1];
+
+ if (cur == 0) {
+ cur = hbitmap_iter_skip_words(hbi);
+ if (cur == 0) {
+ *p_cur = 0;
+ return -1;
+ }
+ }
+
+ /* The next call will resume work from the next word. */
+ hbi->cur[HBITMAP_LEVELS - 1] = 0;
+ *p_cur = cur;
+ return hbi->pos;
+}
+
+
+#endif
diff --git a/contrib/qemu/include/qemu/host-utils.h b/contrib/qemu/include/qemu/host-utils.h
new file mode 100644
index 00000000000..0f688c1c00a
--- /dev/null
+++ b/contrib/qemu/include/qemu/host-utils.h
@@ -0,0 +1,322 @@
+/*
+ * Utility compute operations used by translated code.
+ *
+ * Copyright (c) 2007 Thiemo Seufer
+ * Copyright (c) 2007 Jocelyn Mayer
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef HOST_UTILS_H
+#define HOST_UTILS_H 1
+
+#include "qemu/compiler.h" /* QEMU_GNUC_PREREQ */
+#include <limits.h>
+
+#ifdef CONFIG_INT128
+static inline void mulu64(uint64_t *plow, uint64_t *phigh,
+ uint64_t a, uint64_t b)
+{
+ __uint128_t r = (__uint128_t)a * b;
+ *plow = r;
+ *phigh = r >> 64;
+}
+
+static inline void muls64(uint64_t *plow, uint64_t *phigh,
+ int64_t a, int64_t b)
+{
+ __int128_t r = (__int128_t)a * b;
+ *plow = r;
+ *phigh = r >> 64;
+}
+#else
+void muls64(uint64_t *phigh, uint64_t *plow, int64_t a, int64_t b);
+void mulu64(uint64_t *phigh, uint64_t *plow, uint64_t a, uint64_t b);
+#endif
+
+/**
+ * clz32 - count leading zeros in a 32-bit value.
+ * @val: The value to search
+ *
+ * Returns 32 if the value is zero. Note that the GCC builtin is
+ * undefined if the value is zero.
+ */
+static inline int clz32(uint32_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return val ? __builtin_clz(val) : 32;
+#else
+ /* Binary search for the leading one bit. */
+ int cnt = 0;
+
+ if (!(val & 0xFFFF0000U)) {
+ cnt += 16;
+ val <<= 16;
+ }
+ if (!(val & 0xFF000000U)) {
+ cnt += 8;
+ val <<= 8;
+ }
+ if (!(val & 0xF0000000U)) {
+ cnt += 4;
+ val <<= 4;
+ }
+ if (!(val & 0xC0000000U)) {
+ cnt += 2;
+ val <<= 2;
+ }
+ if (!(val & 0x80000000U)) {
+ cnt++;
+ val <<= 1;
+ }
+ if (!(val & 0x80000000U)) {
+ cnt++;
+ }
+ return cnt;
+#endif
+}
+
+/**
+ * clo32 - count leading ones in a 32-bit value.
+ * @val: The value to search
+ *
+ * Returns 32 if the value is -1.
+ */
+static inline int clo32(uint32_t val)
+{
+ return clz32(~val);
+}
+
+/**
+ * clz64 - count leading zeros in a 64-bit value.
+ * @val: The value to search
+ *
+ * Returns 64 if the value is zero. Note that the GCC builtin is
+ * undefined if the value is zero.
+ */
+static inline int clz64(uint64_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return val ? __builtin_clzll(val) : 64;
+#else
+ int cnt = 0;
+
+ if (!(val >> 32)) {
+ cnt += 32;
+ } else {
+ val >>= 32;
+ }
+
+ return cnt + clz32(val);
+#endif
+}
+
+/**
+ * clo64 - count leading ones in a 64-bit value.
+ * @val: The value to search
+ *
+ * Returns 64 if the value is -1.
+ */
+static inline int clo64(uint64_t val)
+{
+ return clz64(~val);
+}
+
+/**
+ * ctz32 - count trailing zeros in a 32-bit value.
+ * @val: The value to search
+ *
+ * Returns 32 if the value is zero. Note that the GCC builtin is
+ * undefined if the value is zero.
+ */
+static inline int ctz32(uint32_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return val ? __builtin_ctz(val) : 32;
+#else
+ /* Binary search for the trailing one bit. */
+ int cnt;
+
+ cnt = 0;
+ if (!(val & 0x0000FFFFUL)) {
+ cnt += 16;
+ val >>= 16;
+ }
+ if (!(val & 0x000000FFUL)) {
+ cnt += 8;
+ val >>= 8;
+ }
+ if (!(val & 0x0000000FUL)) {
+ cnt += 4;
+ val >>= 4;
+ }
+ if (!(val & 0x00000003UL)) {
+ cnt += 2;
+ val >>= 2;
+ }
+ if (!(val & 0x00000001UL)) {
+ cnt++;
+ val >>= 1;
+ }
+ if (!(val & 0x00000001UL)) {
+ cnt++;
+ }
+
+ return cnt;
+#endif
+}
+
+/**
+ * cto32 - count trailing ones in a 32-bit value.
+ * @val: The value to search
+ *
+ * Returns 32 if the value is -1.
+ */
+static inline int cto32(uint32_t val)
+{
+ return ctz32(~val);
+}
+
+/**
+ * ctz64 - count trailing zeros in a 64-bit value.
+ * @val: The value to search
+ *
+ * Returns 64 if the value is zero. Note that the GCC builtin is
+ * undefined if the value is zero.
+ */
+static inline int ctz64(uint64_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return val ? __builtin_ctzll(val) : 64;
+#else
+ int cnt;
+
+ cnt = 0;
+ if (!((uint32_t)val)) {
+ cnt += 32;
+ val >>= 32;
+ }
+
+ return cnt + ctz32(val);
+#endif
+}
+
+/**
+ * ctz64 - count trailing ones in a 64-bit value.
+ * @val: The value to search
+ *
+ * Returns 64 if the value is -1.
+ */
+static inline int cto64(uint64_t val)
+{
+ return ctz64(~val);
+}
+
+/**
+ * ctpop8 - count the population of one bits in an 8-bit value.
+ * @val: The value to search
+ */
+static inline int ctpop8(uint8_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return __builtin_popcount(val);
+#else
+ val = (val & 0x55) + ((val >> 1) & 0x55);
+ val = (val & 0x33) + ((val >> 2) & 0x33);
+ val = (val & 0x0f) + ((val >> 4) & 0x0f);
+
+ return val;
+#endif
+}
+
+/**
+ * ctpop16 - count the population of one bits in a 16-bit value.
+ * @val: The value to search
+ */
+static inline int ctpop16(uint16_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return __builtin_popcount(val);
+#else
+ val = (val & 0x5555) + ((val >> 1) & 0x5555);
+ val = (val & 0x3333) + ((val >> 2) & 0x3333);
+ val = (val & 0x0f0f) + ((val >> 4) & 0x0f0f);
+ val = (val & 0x00ff) + ((val >> 8) & 0x00ff);
+
+ return val;
+#endif
+}
+
+/**
+ * ctpop32 - count the population of one bits in a 32-bit value.
+ * @val: The value to search
+ */
+static inline int ctpop32(uint32_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return __builtin_popcount(val);
+#else
+ val = (val & 0x55555555) + ((val >> 1) & 0x55555555);
+ val = (val & 0x33333333) + ((val >> 2) & 0x33333333);
+ val = (val & 0x0f0f0f0f) + ((val >> 4) & 0x0f0f0f0f);
+ val = (val & 0x00ff00ff) + ((val >> 8) & 0x00ff00ff);
+ val = (val & 0x0000ffff) + ((val >> 16) & 0x0000ffff);
+
+ return val;
+#endif
+}
+
+/**
+ * ctpop64 - count the population of one bits in a 64-bit value.
+ * @val: The value to search
+ */
+static inline int ctpop64(uint64_t val)
+{
+#if QEMU_GNUC_PREREQ(3, 4)
+ return __builtin_popcountll(val);
+#else
+ val = (val & 0x5555555555555555ULL) + ((val >> 1) & 0x5555555555555555ULL);
+ val = (val & 0x3333333333333333ULL) + ((val >> 2) & 0x3333333333333333ULL);
+ val = (val & 0x0f0f0f0f0f0f0f0fULL) + ((val >> 4) & 0x0f0f0f0f0f0f0f0fULL);
+ val = (val & 0x00ff00ff00ff00ffULL) + ((val >> 8) & 0x00ff00ff00ff00ffULL);
+ val = (val & 0x0000ffff0000ffffULL) + ((val >> 16) & 0x0000ffff0000ffffULL);
+ val = (val & 0x00000000ffffffffULL) + ((val >> 32) & 0x00000000ffffffffULL);
+
+ return val;
+#endif
+}
+
+/* Host type specific sizes of these routines. */
+
+#if ULONG_MAX == UINT32_MAX
+# define clzl clz32
+# define ctzl ctz32
+# define clol clo32
+# define ctol cto32
+# define ctpopl ctpop32
+#elif ULONG_MAX == UINT64_MAX
+# define clzl clz64
+# define ctzl ctz64
+# define clol clo64
+# define ctol cto64
+# define ctpopl ctpop64
+#else
+# error Unknown sizeof long
+#endif
+
+#endif
diff --git a/contrib/qemu/include/qemu/iov.h b/contrib/qemu/include/qemu/iov.h
new file mode 100644
index 00000000000..68d25f29b76
--- /dev/null
+++ b/contrib/qemu/include/qemu/iov.h
@@ -0,0 +1,115 @@
+/*
+ * Helpers for using (partial) iovecs.
+ *
+ * Copyright (C) 2010 Red Hat, Inc.
+ *
+ * Author(s):
+ * Amit Shah <amit.shah@redhat.com>
+ * Michael Tokarev <mjt@tls.msk.ru>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ */
+
+#ifndef IOV_H
+#define IOV_H
+
+#include "qemu-common.h"
+
+/**
+ * count and return data size, in bytes, of an iovec
+ * starting at `iov' of `iov_cnt' number of elements.
+ */
+size_t iov_size(const struct iovec *iov, const unsigned int iov_cnt);
+
+/**
+ * Copy from single continuous buffer to scatter-gather vector of buffers
+ * (iovec) and back like memcpy() between two continuous memory regions.
+ * Data in single continuous buffer starting at address `buf' and
+ * `bytes' bytes long will be copied to/from an iovec `iov' with
+ * `iov_cnt' number of elements, starting at byte position `offset'
+ * within the iovec. If the iovec does not contain enough space,
+ * only part of data will be copied, up to the end of the iovec.
+ * Number of bytes actually copied will be returned, which is
+ * min(bytes, iov_size(iov)-offset)
+ * `Offset' must point to the inside of iovec.
+ * It is okay to use very large value for `bytes' since we're
+ * limited by the size of the iovec anyway, provided that the
+ * buffer pointed to by buf has enough space. One possible
+ * such "large" value is -1 (sinice size_t is unsigned),
+ * so specifying `-1' as `bytes' means 'up to the end of iovec'.
+ */
+size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
+ size_t offset, const void *buf, size_t bytes);
+size_t iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
+ size_t offset, void *buf, size_t bytes);
+
+/**
+ * Set data bytes pointed out by iovec `iov' of size `iov_cnt' elements,
+ * starting at byte offset `start', to value `fillc', repeating it
+ * `bytes' number of times. `Offset' must point to the inside of iovec.
+ * If `bytes' is large enough, only last bytes portion of iovec,
+ * up to the end of it, will be filled with the specified value.
+ * Function return actual number of bytes processed, which is
+ * min(size, iov_size(iov) - offset).
+ * Again, it is okay to use large value for `bytes' to mean "up to the end".
+ */
+size_t iov_memset(const struct iovec *iov, const unsigned int iov_cnt,
+ size_t offset, int fillc, size_t bytes);
+
+/*
+ * Send/recv data from/to iovec buffers directly
+ *
+ * `offset' bytes in the beginning of iovec buffer are skipped and
+ * next `bytes' bytes are used, which must be within data of iovec.
+ *
+ * r = iov_send_recv(sockfd, iov, iovcnt, offset, bytes, true);
+ *
+ * is logically equivalent to
+ *
+ * char *buf = malloc(bytes);
+ * iov_to_buf(iov, iovcnt, offset, buf, bytes);
+ * r = send(sockfd, buf, bytes, 0);
+ * free(buf);
+ *
+ * For iov_send_recv() _whole_ area being sent or received
+ * should be within the iovec, not only beginning of it.
+ */
+ssize_t iov_send_recv(int sockfd, struct iovec *iov, unsigned iov_cnt,
+ size_t offset, size_t bytes, bool do_send);
+#define iov_recv(sockfd, iov, iov_cnt, offset, bytes) \
+ iov_send_recv(sockfd, iov, iov_cnt, offset, bytes, false)
+#define iov_send(sockfd, iov, iov_cnt, offset, bytes) \
+ iov_send_recv(sockfd, iov, iov_cnt, offset, bytes, true)
+
+/**
+ * Produce a text hexdump of iovec `iov' with `iov_cnt' number of elements
+ * in file `fp', prefixing each line with `prefix' and processing not more
+ * than `limit' data bytes.
+ */
+void iov_hexdump(const struct iovec *iov, const unsigned int iov_cnt,
+ FILE *fp, const char *prefix, size_t limit);
+
+/*
+ * Partial copy of vector from iov to dst_iov (data is not copied).
+ * dst_iov overlaps iov at a specified offset.
+ * size of dst_iov is at most bytes. dst vector count is returned.
+ */
+unsigned iov_copy(struct iovec *dst_iov, unsigned int dst_iov_cnt,
+ const struct iovec *iov, unsigned int iov_cnt,
+ size_t offset, size_t bytes);
+
+/*
+ * Remove a given number of bytes from the front or back of a vector.
+ * This may update iov and/or iov_cnt to exclude iovec elements that are
+ * no longer required.
+ *
+ * The number of bytes actually discarded is returned. This number may be
+ * smaller than requested if the vector is too small.
+ */
+size_t iov_discard_front(struct iovec **iov, unsigned int *iov_cnt,
+ size_t bytes);
+size_t iov_discard_back(struct iovec *iov, unsigned int *iov_cnt,
+ size_t bytes);
+
+#endif
diff --git a/contrib/qemu/include/qemu/main-loop.h b/contrib/qemu/include/qemu/main-loop.h
new file mode 100644
index 00000000000..6f0200a7acc
--- /dev/null
+++ b/contrib/qemu/include/qemu/main-loop.h
@@ -0,0 +1,311 @@
+/*
+ * QEMU System Emulator
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef QEMU_MAIN_LOOP_H
+#define QEMU_MAIN_LOOP_H 1
+
+#include "block/aio.h"
+
+#define SIG_IPI SIGUSR1
+
+/**
+ * qemu_init_main_loop: Set up the process so that it can run the main loop.
+ *
+ * This includes setting up signal handlers. It should be called before
+ * any other threads are created. In addition, threads other than the
+ * main one should block signals that are trapped by the main loop.
+ * For simplicity, you can consider these signals to be safe: SIGUSR1,
+ * SIGUSR2, thread signals (SIGFPE, SIGILL, SIGSEGV, SIGBUS) and real-time
+ * signals if available. Remember that Windows in practice does not have
+ * signals, though.
+ *
+ * In the case of QEMU tools, this will also start/initialize timers.
+ */
+int qemu_init_main_loop(void);
+
+/**
+ * main_loop_wait: Run one iteration of the main loop.
+ *
+ * If @nonblocking is true, poll for events, otherwise suspend until
+ * one actually occurs. The main loop usually consists of a loop that
+ * repeatedly calls main_loop_wait(false).
+ *
+ * Main loop services include file descriptor callbacks, bottom halves
+ * and timers (defined in qemu-timer.h). Bottom halves are similar to timers
+ * that execute immediately, but have a lower overhead and scheduling them
+ * is wait-free, thread-safe and signal-safe.
+ *
+ * It is sometimes useful to put a whole program in a coroutine. In this
+ * case, the coroutine actually should be started from within the main loop,
+ * so that the main loop can run whenever the coroutine yields. To do this,
+ * you can use a bottom half to enter the coroutine as soon as the main loop
+ * starts:
+ *
+ * void enter_co_bh(void *opaque) {
+ * QEMUCoroutine *co = opaque;
+ * qemu_coroutine_enter(co, NULL);
+ * }
+ *
+ * ...
+ * QEMUCoroutine *co = qemu_coroutine_create(coroutine_entry);
+ * QEMUBH *start_bh = qemu_bh_new(enter_co_bh, co);
+ * qemu_bh_schedule(start_bh);
+ * while (...) {
+ * main_loop_wait(false);
+ * }
+ *
+ * (In the future we may provide a wrapper for this).
+ *
+ * @nonblocking: Whether the caller should block until an event occurs.
+ */
+int main_loop_wait(int nonblocking);
+
+/**
+ * qemu_get_aio_context: Return the main loop's AioContext
+ */
+AioContext *qemu_get_aio_context(void);
+
+/**
+ * qemu_notify_event: Force processing of pending events.
+ *
+ * Similar to signaling a condition variable, qemu_notify_event forces
+ * main_loop_wait to look at pending events and exit. The caller of
+ * main_loop_wait will usually call it again very soon, so qemu_notify_event
+ * also has the side effect of recalculating the sets of file descriptors
+ * that the main loop waits for.
+ *
+ * Calling qemu_notify_event is rarely necessary, because main loop
+ * services (bottom halves and timers) call it themselves. One notable
+ * exception occurs when using qemu_set_fd_handler2 (see below).
+ */
+void qemu_notify_event(void);
+
+#ifdef _WIN32
+/* return TRUE if no sleep should be done afterwards */
+typedef int PollingFunc(void *opaque);
+
+/**
+ * qemu_add_polling_cb: Register a Windows-specific polling callback
+ *
+ * Currently, under Windows some events are polled rather than waited for.
+ * Polling callbacks do not ensure that @func is called timely, because
+ * the main loop might wait for an arbitrarily long time. If possible,
+ * you should instead create a separate thread that does a blocking poll
+ * and set a Win32 event object. The event can then be passed to
+ * qemu_add_wait_object.
+ *
+ * Polling callbacks really have nothing Windows specific in them, but
+ * as they are a hack and are currently not necessary under POSIX systems,
+ * they are only available when QEMU is running under Windows.
+ *
+ * @func: The function that does the polling, and returns 1 to force
+ * immediate completion of main_loop_wait.
+ * @opaque: A pointer-size value that is passed to @func.
+ */
+int qemu_add_polling_cb(PollingFunc *func, void *opaque);
+
+/**
+ * qemu_del_polling_cb: Unregister a Windows-specific polling callback
+ *
+ * This function removes a callback that was registered with
+ * qemu_add_polling_cb.
+ *
+ * @func: The function that was passed to qemu_add_polling_cb.
+ * @opaque: A pointer-size value that was passed to qemu_add_polling_cb.
+ */
+void qemu_del_polling_cb(PollingFunc *func, void *opaque);
+
+/* Wait objects handling */
+typedef void WaitObjectFunc(void *opaque);
+
+/**
+ * qemu_add_wait_object: Register a callback for a Windows handle
+ *
+ * Under Windows, the iohandler mechanism can only be used with sockets.
+ * QEMU must use the WaitForMultipleObjects API to wait on other handles.
+ * This function registers a #HANDLE with QEMU, so that it will be included
+ * in the main loop's calls to WaitForMultipleObjects. When the handle
+ * is in a signaled state, QEMU will call @func.
+ *
+ * @handle: The Windows handle to be observed.
+ * @func: A function to be called when @handle is in a signaled state.
+ * @opaque: A pointer-size value that is passed to @func.
+ */
+int qemu_add_wait_object(HANDLE handle, WaitObjectFunc *func, void *opaque);
+
+/**
+ * qemu_del_wait_object: Unregister a callback for a Windows handle
+ *
+ * This function removes a callback that was registered with
+ * qemu_add_wait_object.
+ *
+ * @func: The function that was passed to qemu_add_wait_object.
+ * @opaque: A pointer-size value that was passed to qemu_add_wait_object.
+ */
+void qemu_del_wait_object(HANDLE handle, WaitObjectFunc *func, void *opaque);
+#endif
+
+/* async I/O support */
+
+typedef void IOReadHandler(void *opaque, const uint8_t *buf, int size);
+typedef int IOCanReadHandler(void *opaque);
+
+/**
+ * qemu_set_fd_handler2: Register a file descriptor with the main loop
+ *
+ * This function tells the main loop to wake up whenever one of the
+ * following conditions is true:
+ *
+ * 1) if @fd_write is not %NULL, when the file descriptor is writable;
+ *
+ * 2) if @fd_read is not %NULL, when the file descriptor is readable.
+ *
+ * @fd_read_poll can be used to disable the @fd_read callback temporarily.
+ * This is useful to avoid calling qemu_set_fd_handler2 every time the
+ * client becomes interested in reading (or dually, stops being interested).
+ * A typical example is when @fd is a listening socket and you want to bound
+ * the number of active clients. Remember to call qemu_notify_event whenever
+ * the condition may change from %false to %true.
+ *
+ * The callbacks that are set up by qemu_set_fd_handler2 are level-triggered.
+ * If @fd_read does not read from @fd, or @fd_write does not write to @fd
+ * until its buffers are full, they will be called again on the next
+ * iteration.
+ *
+ * @fd: The file descriptor to be observed. Under Windows it must be
+ * a #SOCKET.
+ *
+ * @fd_read_poll: A function that returns 1 if the @fd_read callback
+ * should be fired. If the function returns 0, the main loop will not
+ * end its iteration even if @fd becomes readable.
+ *
+ * @fd_read: A level-triggered callback that is fired if @fd is readable
+ * at the beginning of a main loop iteration, or if it becomes readable
+ * during one.
+ *
+ * @fd_write: A level-triggered callback that is fired when @fd is writable
+ * at the beginning of a main loop iteration, or if it becomes writable
+ * during one.
+ *
+ * @opaque: A pointer-sized value that is passed to @fd_read_poll,
+ * @fd_read and @fd_write.
+ */
+int qemu_set_fd_handler2(int fd,
+ IOCanReadHandler *fd_read_poll,
+ IOHandler *fd_read,
+ IOHandler *fd_write,
+ void *opaque);
+
+/**
+ * qemu_set_fd_handler: Register a file descriptor with the main loop
+ *
+ * This function tells the main loop to wake up whenever one of the
+ * following conditions is true:
+ *
+ * 1) if @fd_write is not %NULL, when the file descriptor is writable;
+ *
+ * 2) if @fd_read is not %NULL, when the file descriptor is readable.
+ *
+ * The callbacks that are set up by qemu_set_fd_handler are level-triggered.
+ * If @fd_read does not read from @fd, or @fd_write does not write to @fd
+ * until its buffers are full, they will be called again on the next
+ * iteration.
+ *
+ * @fd: The file descriptor to be observed. Under Windows it must be
+ * a #SOCKET.
+ *
+ * @fd_read: A level-triggered callback that is fired if @fd is readable
+ * at the beginning of a main loop iteration, or if it becomes readable
+ * during one.
+ *
+ * @fd_write: A level-triggered callback that is fired when @fd is writable
+ * at the beginning of a main loop iteration, or if it becomes writable
+ * during one.
+ *
+ * @opaque: A pointer-sized value that is passed to @fd_read and @fd_write.
+ */
+int qemu_set_fd_handler(int fd,
+ IOHandler *fd_read,
+ IOHandler *fd_write,
+ void *opaque);
+
+#ifdef CONFIG_POSIX
+/**
+ * qemu_add_child_watch: Register a child process for reaping.
+ *
+ * Under POSIX systems, a parent process must read the exit status of
+ * its child processes using waitpid, or the operating system will not
+ * free some of the resources attached to that process.
+ *
+ * This function directs the QEMU main loop to observe a child process
+ * and call waitpid as soon as it exits; the watch is then removed
+ * automatically. It is useful whenever QEMU forks a child process
+ * but will find out about its termination by other means such as a
+ * "broken pipe".
+ *
+ * @pid: The pid that QEMU should observe.
+ */
+int qemu_add_child_watch(pid_t pid);
+#endif
+
+/**
+ * qemu_mutex_lock_iothread: Lock the main loop mutex.
+ *
+ * This function locks the main loop mutex. The mutex is taken by
+ * qemu_init_main_loop and always taken except while waiting on
+ * external events (such as with select). The mutex should be taken
+ * by threads other than the main loop thread when calling
+ * qemu_bh_new(), qemu_set_fd_handler() and basically all other
+ * functions documented in this file.
+ *
+ * NOTE: tools currently are single-threaded and qemu_mutex_lock_iothread
+ * is a no-op there.
+ */
+void qemu_mutex_lock_iothread(void);
+
+/**
+ * qemu_mutex_unlock_iothread: Unlock the main loop mutex.
+ *
+ * This function unlocks the main loop mutex. The mutex is taken by
+ * qemu_init_main_loop and always taken except while waiting on
+ * external events (such as with select). The mutex should be unlocked
+ * as soon as possible by threads other than the main loop thread,
+ * because it prevents the main loop from processing callbacks,
+ * including timers and bottom halves.
+ *
+ * NOTE: tools currently are single-threaded and qemu_mutex_unlock_iothread
+ * is a no-op there.
+ */
+void qemu_mutex_unlock_iothread(void);
+
+/* internal interfaces */
+
+void qemu_fd_register(int fd);
+void qemu_iohandler_fill(GArray *pollfds);
+void qemu_iohandler_poll(GArray *pollfds, int rc);
+
+QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque);
+void qemu_bh_schedule_idle(QEMUBH *bh);
+
+#endif
diff --git a/contrib/qemu/include/qemu/module.h b/contrib/qemu/include/qemu/module.h
new file mode 100644
index 00000000000..c4ccd571664
--- /dev/null
+++ b/contrib/qemu/include/qemu/module.h
@@ -0,0 +1,40 @@
+/*
+ * QEMU Module Infrastructure
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_MODULE_H
+#define QEMU_MODULE_H
+
+/* This should not be used directly. Use block_init etc. instead. */
+#define module_init(function, type) \
+static void __attribute__((constructor)) do_qemu_init_ ## function(void) { \
+ register_module_init(function, type); \
+}
+
+typedef enum {
+ MODULE_INIT_BLOCK,
+ MODULE_INIT_MACHINE,
+ MODULE_INIT_QAPI,
+ MODULE_INIT_QOM,
+ MODULE_INIT_MAX
+} module_init_type;
+
+#define block_init(function) module_init(function, MODULE_INIT_BLOCK)
+#define machine_init(function) module_init(function, MODULE_INIT_MACHINE)
+#define qapi_init(function) module_init(function, MODULE_INIT_QAPI)
+#define type_init(function) module_init(function, MODULE_INIT_QOM)
+
+void register_module_init(void (*fn)(void), module_init_type type);
+
+void module_call_init(module_init_type type);
+
+#endif
diff --git a/contrib/qemu/include/qemu/notify.h b/contrib/qemu/include/qemu/notify.h
new file mode 100644
index 00000000000..a3d73e4bc76
--- /dev/null
+++ b/contrib/qemu/include/qemu/notify.h
@@ -0,0 +1,72 @@
+/*
+ * Notifier lists
+ *
+ * Copyright IBM, Corp. 2010
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_NOTIFY_H
+#define QEMU_NOTIFY_H
+
+#include "qemu/queue.h"
+
+typedef struct Notifier Notifier;
+
+struct Notifier
+{
+ void (*notify)(Notifier *notifier, void *data);
+ QLIST_ENTRY(Notifier) node;
+};
+
+typedef struct NotifierList
+{
+ QLIST_HEAD(, Notifier) notifiers;
+} NotifierList;
+
+#define NOTIFIER_LIST_INITIALIZER(head) \
+ { QLIST_HEAD_INITIALIZER((head).notifiers) }
+
+void notifier_list_init(NotifierList *list);
+
+void notifier_list_add(NotifierList *list, Notifier *notifier);
+
+void notifier_remove(Notifier *notifier);
+
+void notifier_list_notify(NotifierList *list, void *data);
+
+/* Same as Notifier but allows .notify() to return errors */
+typedef struct NotifierWithReturn NotifierWithReturn;
+
+struct NotifierWithReturn {
+ /**
+ * Return 0 on success (next notifier will be invoked), otherwise
+ * notifier_with_return_list_notify() will stop and return the value.
+ */
+ int (*notify)(NotifierWithReturn *notifier, void *data);
+ QLIST_ENTRY(NotifierWithReturn) node;
+};
+
+typedef struct NotifierWithReturnList {
+ QLIST_HEAD(, NotifierWithReturn) notifiers;
+} NotifierWithReturnList;
+
+#define NOTIFIER_WITH_RETURN_LIST_INITIALIZER(head) \
+ { QLIST_HEAD_INITIALIZER((head).notifiers) }
+
+void notifier_with_return_list_init(NotifierWithReturnList *list);
+
+void notifier_with_return_list_add(NotifierWithReturnList *list,
+ NotifierWithReturn *notifier);
+
+void notifier_with_return_remove(NotifierWithReturn *notifier);
+
+int notifier_with_return_list_notify(NotifierWithReturnList *list,
+ void *data);
+
+#endif
diff --git a/contrib/qemu/include/qemu/option.h b/contrib/qemu/include/qemu/option.h
new file mode 100644
index 00000000000..a83c700323e
--- /dev/null
+++ b/contrib/qemu/include/qemu/option.h
@@ -0,0 +1,157 @@
+/*
+ * Commandline option parsing functions
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ * Copyright (c) 2009 Kevin Wolf <kwolf@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef QEMU_OPTIONS_H
+#define QEMU_OPTIONS_H
+
+#include <stdint.h>
+#include "qemu/queue.h"
+#include "qapi/error.h"
+#include "qapi/qmp/qdict.h"
+
+enum QEMUOptionParType {
+ OPT_FLAG,
+ OPT_NUMBER,
+ OPT_SIZE,
+ OPT_STRING,
+};
+
+typedef struct QEMUOptionParameter {
+ const char *name;
+ enum QEMUOptionParType type;
+ union {
+ uint64_t n;
+ char* s;
+ } value;
+ const char *help;
+} QEMUOptionParameter;
+
+
+const char *get_opt_name(char *buf, int buf_size, const char *p, char delim);
+const char *get_opt_value(char *buf, int buf_size, const char *p);
+int get_next_param_value(char *buf, int buf_size,
+ const char *tag, const char **pstr);
+int get_param_value(char *buf, int buf_size,
+ const char *tag, const char *str);
+
+
+/*
+ * The following functions take a parameter list as input. This is a pointer to
+ * the first element of a QEMUOptionParameter array which is terminated by an
+ * entry with entry->name == NULL.
+ */
+
+QEMUOptionParameter *get_option_parameter(QEMUOptionParameter *list,
+ const char *name);
+int set_option_parameter(QEMUOptionParameter *list, const char *name,
+ const char *value);
+int set_option_parameter_int(QEMUOptionParameter *list, const char *name,
+ uint64_t value);
+QEMUOptionParameter *append_option_parameters(QEMUOptionParameter *dest,
+ QEMUOptionParameter *list);
+QEMUOptionParameter *parse_option_parameters(const char *param,
+ QEMUOptionParameter *list, QEMUOptionParameter *dest);
+void free_option_parameters(QEMUOptionParameter *list);
+void print_option_parameters(QEMUOptionParameter *list);
+void print_option_help(QEMUOptionParameter *list);
+
+/* ------------------------------------------------------------------ */
+
+typedef struct QemuOpt QemuOpt;
+typedef struct QemuOpts QemuOpts;
+typedef struct QemuOptsList QemuOptsList;
+
+enum QemuOptType {
+ QEMU_OPT_STRING = 0, /* no parsing (use string as-is) */
+ QEMU_OPT_BOOL, /* on/off */
+ QEMU_OPT_NUMBER, /* simple number */
+ QEMU_OPT_SIZE, /* size, accepts (K)ilo, (M)ega, (G)iga, (T)era postfix */
+};
+
+typedef struct QemuOptDesc {
+ const char *name;
+ enum QemuOptType type;
+ const char *help;
+} QemuOptDesc;
+
+struct QemuOptsList {
+ const char *name;
+ const char *implied_opt_name;
+ bool merge_lists; /* Merge multiple uses of option into a single list? */
+ QTAILQ_HEAD(, QemuOpts) head;
+ QemuOptDesc desc[];
+};
+
+const char *qemu_opt_get(QemuOpts *opts, const char *name);
+/**
+ * qemu_opt_has_help_opt:
+ * @opts: options to search for a help request
+ *
+ * Check whether the options specified by @opts include one of the
+ * standard strings which indicate that the user is asking for a
+ * list of the valid values for a command line option (as defined
+ * by is_help_option()).
+ *
+ * Returns: true if @opts includes 'help' or equivalent.
+ */
+bool qemu_opt_has_help_opt(QemuOpts *opts);
+bool qemu_opt_get_bool(QemuOpts *opts, const char *name, bool defval);
+uint64_t qemu_opt_get_number(QemuOpts *opts, const char *name, uint64_t defval);
+uint64_t qemu_opt_get_size(QemuOpts *opts, const char *name, uint64_t defval);
+int qemu_opt_set(QemuOpts *opts, const char *name, const char *value);
+void qemu_opt_set_err(QemuOpts *opts, const char *name, const char *value,
+ Error **errp);
+int qemu_opt_set_bool(QemuOpts *opts, const char *name, bool val);
+int qemu_opt_set_number(QemuOpts *opts, const char *name, int64_t val);
+typedef int (*qemu_opt_loopfunc)(const char *name, const char *value, void *opaque);
+int qemu_opt_foreach(QemuOpts *opts, qemu_opt_loopfunc func, void *opaque,
+ int abort_on_failure);
+
+QemuOpts *qemu_opts_find(QemuOptsList *list, const char *id);
+QemuOpts *qemu_opts_create(QemuOptsList *list, const char *id,
+ int fail_if_exists, Error **errp);
+QemuOpts *qemu_opts_create_nofail(QemuOptsList *list);
+void qemu_opts_reset(QemuOptsList *list);
+void qemu_opts_loc_restore(QemuOpts *opts);
+int qemu_opts_set(QemuOptsList *list, const char *id,
+ const char *name, const char *value);
+const char *qemu_opts_id(QemuOpts *opts);
+void qemu_opts_del(QemuOpts *opts);
+void qemu_opts_validate(QemuOpts *opts, const QemuOptDesc *desc, Error **errp);
+int qemu_opts_do_parse(QemuOpts *opts, const char *params, const char *firstname);
+QemuOpts *qemu_opts_parse(QemuOptsList *list, const char *params, int permit_abbrev);
+void qemu_opts_set_defaults(QemuOptsList *list, const char *params,
+ int permit_abbrev);
+QemuOpts *qemu_opts_from_qdict(QemuOptsList *list, const QDict *qdict,
+ Error **errp);
+QDict *qemu_opts_to_qdict(QemuOpts *opts, QDict *qdict);
+void qemu_opts_absorb_qdict(QemuOpts *opts, QDict *qdict, Error **errp);
+
+typedef int (*qemu_opts_loopfunc)(QemuOpts *opts, void *opaque);
+int qemu_opts_print(QemuOpts *opts, void *dummy);
+int qemu_opts_foreach(QemuOptsList *list, qemu_opts_loopfunc func, void *opaque,
+ int abort_on_failure);
+
+#endif
diff --git a/contrib/qemu/include/qemu/option_int.h b/contrib/qemu/include/qemu/option_int.h
new file mode 100644
index 00000000000..8212fa4a485
--- /dev/null
+++ b/contrib/qemu/include/qemu/option_int.h
@@ -0,0 +1,54 @@
+/*
+ * Commandline option parsing functions
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ * Copyright (c) 2009 Kevin Wolf <kwolf@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef QEMU_OPTIONS_INTERNAL_H
+#define QEMU_OPTIONS_INTERNAL_H
+
+#include "qemu/option.h"
+#include "qemu/error-report.h"
+
+struct QemuOpt {
+ const char *name;
+ const char *str;
+
+ const QemuOptDesc *desc;
+ union {
+ bool boolean;
+ uint64_t uint;
+ } value;
+
+ QemuOpts *opts;
+ QTAILQ_ENTRY(QemuOpt) next;
+};
+
+struct QemuOpts {
+ char *id;
+ QemuOptsList *list;
+ Location loc;
+ QTAILQ_HEAD(QemuOptHead, QemuOpt) head;
+ QTAILQ_ENTRY(QemuOpts) next;
+};
+
+#endif
diff --git a/contrib/qemu/include/qemu/osdep.h b/contrib/qemu/include/qemu/osdep.h
new file mode 100644
index 00000000000..26136f16ecd
--- /dev/null
+++ b/contrib/qemu/include/qemu/osdep.h
@@ -0,0 +1,218 @@
+#ifndef QEMU_OSDEP_H
+#define QEMU_OSDEP_H
+
+#include "config-host.h"
+#include <stdarg.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#ifdef __OpenBSD__
+#include <sys/signal.h>
+#endif
+
+#ifndef _WIN32
+#include <sys/wait.h>
+#else
+#define WIFEXITED(x) 1
+#define WEXITSTATUS(x) (x)
+#endif
+
+#include <sys/time.h>
+
+#if defined(CONFIG_SOLARIS) && CONFIG_SOLARIS_VERSION < 10
+/* [u]int_fast*_t not in <sys/int_types.h> */
+typedef unsigned char uint_fast8_t;
+typedef unsigned int uint_fast16_t;
+typedef signed int int_fast16_t;
+#endif
+
+#ifndef glue
+#define xglue(x, y) x ## y
+#define glue(x, y) xglue(x, y)
+#define stringify(s) tostring(s)
+#define tostring(s) #s
+#endif
+
+#ifndef likely
+#if __GNUC__ < 3
+#define __builtin_expect(x, n) (x)
+#endif
+
+#define likely(x) __builtin_expect(!!(x), 1)
+#define unlikely(x) __builtin_expect(!!(x), 0)
+#endif
+
+#ifndef container_of
+#define container_of(ptr, type, member) ({ \
+ const typeof(((type *) 0)->member) *__mptr = (ptr); \
+ (type *) ((char *) __mptr - offsetof(type, member));})
+#endif
+
+/* Convert from a base type to a parent type, with compile time checking. */
+#ifdef __GNUC__
+#define DO_UPCAST(type, field, dev) ( __extension__ ( { \
+ char __attribute__((unused)) offset_must_be_zero[ \
+ -offsetof(type, field)]; \
+ container_of(dev, type, field);}))
+#else
+#define DO_UPCAST(type, field, dev) container_of(dev, type, field)
+#endif
+
+#define typeof_field(type, field) typeof(((type *)0)->field)
+#define type_check(t1,t2) ((t1*)0 - (t2*)0)
+
+#ifndef MIN
+#define MIN(a, b) (((a) < (b)) ? (a) : (b))
+#endif
+#ifndef MAX
+#define MAX(a, b) (((a) > (b)) ? (a) : (b))
+#endif
+
+#ifndef ROUND_UP
+#define ROUND_UP(n,d) (((n) + (d) - 1) & -(d))
+#endif
+
+#ifndef DIV_ROUND_UP
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+#endif
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+#ifndef always_inline
+#if !((__GNUC__ < 3) || defined(__APPLE__))
+#ifdef __OPTIMIZE__
+#undef inline
+#define inline __attribute__ (( always_inline )) __inline__
+#endif
+#endif
+#else
+#undef inline
+#define inline always_inline
+#endif
+
+#define qemu_printf printf
+
+int qemu_daemon(int nochdir, int noclose);
+void *qemu_memalign(size_t alignment, size_t size);
+void *qemu_anon_ram_alloc(size_t size);
+void qemu_vfree(void *ptr);
+void qemu_anon_ram_free(void *ptr, size_t size);
+
+#define QEMU_MADV_INVALID -1
+
+#if defined(CONFIG_MADVISE)
+
+#define QEMU_MADV_WILLNEED MADV_WILLNEED
+#define QEMU_MADV_DONTNEED MADV_DONTNEED
+#ifdef MADV_DONTFORK
+#define QEMU_MADV_DONTFORK MADV_DONTFORK
+#else
+#define QEMU_MADV_DONTFORK QEMU_MADV_INVALID
+#endif
+#ifdef MADV_MERGEABLE
+#define QEMU_MADV_MERGEABLE MADV_MERGEABLE
+#else
+#define QEMU_MADV_MERGEABLE QEMU_MADV_INVALID
+#endif
+#ifdef MADV_DONTDUMP
+#define QEMU_MADV_DONTDUMP MADV_DONTDUMP
+#else
+#define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID
+#endif
+#ifdef MADV_HUGEPAGE
+#define QEMU_MADV_HUGEPAGE MADV_HUGEPAGE
+#else
+#define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID
+#endif
+
+#elif defined(CONFIG_POSIX_MADVISE)
+
+#define QEMU_MADV_WILLNEED POSIX_MADV_WILLNEED
+#define QEMU_MADV_DONTNEED POSIX_MADV_DONTNEED
+#define QEMU_MADV_DONTFORK QEMU_MADV_INVALID
+#define QEMU_MADV_MERGEABLE QEMU_MADV_INVALID
+#define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID
+#define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID
+
+#else /* no-op */
+
+#define QEMU_MADV_WILLNEED QEMU_MADV_INVALID
+#define QEMU_MADV_DONTNEED QEMU_MADV_INVALID
+#define QEMU_MADV_DONTFORK QEMU_MADV_INVALID
+#define QEMU_MADV_MERGEABLE QEMU_MADV_INVALID
+#define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID
+#define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID
+
+#endif
+
+int qemu_madvise(void *addr, size_t len, int advice);
+
+int qemu_open(const char *name, int flags, ...);
+int qemu_close(int fd);
+
+#if defined(__HAIKU__) && defined(__i386__)
+#define FMT_pid "%ld"
+#elif defined(WIN64)
+#define FMT_pid "%" PRId64
+#else
+#define FMT_pid "%d"
+#endif
+
+int qemu_create_pidfile(const char *filename);
+int qemu_get_thread_id(void);
+
+#ifndef CONFIG_IOVEC
+struct iovec {
+ void *iov_base;
+ size_t iov_len;
+};
+/*
+ * Use the same value as Linux for now.
+ */
+#define IOV_MAX 1024
+
+ssize_t readv(int fd, const struct iovec *iov, int iov_cnt);
+ssize_t writev(int fd, const struct iovec *iov, int iov_cnt);
+#else
+#include <sys/uio.h>
+#endif
+
+#ifdef _WIN32
+static inline void qemu_timersub(const struct timeval *val1,
+ const struct timeval *val2,
+ struct timeval *res)
+{
+ res->tv_sec = val1->tv_sec - val2->tv_sec;
+ if (val1->tv_usec < val2->tv_usec) {
+ res->tv_sec--;
+ res->tv_usec = val1->tv_usec - val2->tv_usec + 1000 * 1000;
+ } else {
+ res->tv_usec = val1->tv_usec - val2->tv_usec;
+ }
+}
+#else
+#define qemu_timersub timersub
+#endif
+
+void qemu_set_cloexec(int fd);
+
+void qemu_set_version(const char *);
+const char *qemu_get_version(void);
+
+void fips_set_state(bool requested);
+bool fips_get_state(void);
+
+/* Return a dynamically allocated pathname denoting a file or directory that is
+ * appropriate for storing local state.
+ *
+ * @relative_pathname need not start with a directory separator; one will be
+ * added automatically.
+ *
+ * The caller is responsible for releasing the value returned with g_free()
+ * after use.
+ */
+char *qemu_get_local_state_pathname(const char *relative_pathname);
+
+#endif
diff --git a/contrib/qemu/include/qemu/queue.h b/contrib/qemu/include/qemu/queue.h
new file mode 100644
index 00000000000..d433b9017ce
--- /dev/null
+++ b/contrib/qemu/include/qemu/queue.h
@@ -0,0 +1,414 @@
+/* $NetBSD: queue.h,v 1.52 2009/04/20 09:56:08 mschuett Exp $ */
+
+/*
+ * QEMU version: Copy from netbsd, removed debug code, removed some of
+ * the implementations. Left in singly-linked lists, lists, simple
+ * queues, and tail queues.
+ */
+
+/*
+ * Copyright (c) 1991, 1993
+ * The Regents of the University of California. All rights reserved.
+ *
+ * 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 the University 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 REGENTS 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 THE REGENTS 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.
+ *
+ * @(#)queue.h 8.5 (Berkeley) 8/20/94
+ */
+
+#ifndef QEMU_SYS_QUEUE_H_
+#define QEMU_SYS_QUEUE_H_
+
+/*
+ * This file defines four types of data structures: singly-linked lists,
+ * lists, simple queues, and tail queues.
+ *
+ * A singly-linked list is headed by a single forward pointer. The
+ * elements are singly linked for minimum space and pointer manipulation
+ * overhead at the expense of O(n) removal for arbitrary elements. New
+ * elements can be added to the list after an existing element or at the
+ * head of the list. Elements being removed from the head of the list
+ * should use the explicit macro for this purpose for optimum
+ * efficiency. A singly-linked list may only be traversed in the forward
+ * direction. Singly-linked lists are ideal for applications with large
+ * datasets and few or no removals or for implementing a LIFO queue.
+ *
+ * A list is headed by a single forward pointer (or an array of forward
+ * pointers for a hash table header). The elements are doubly linked
+ * so that an arbitrary element can be removed without a need to
+ * traverse the list. New elements can be added to the list before
+ * or after an existing element or at the head of the list. A list
+ * may only be traversed in the forward direction.
+ *
+ * A simple queue is headed by a pair of pointers, one the head of the
+ * list and the other to the tail of the list. The elements are singly
+ * linked to save space, so elements can only be removed from the
+ * head of the list. New elements can be added to the list after
+ * an existing element, at the head of the list, or at the end of the
+ * list. A simple queue may only be traversed in the forward direction.
+ *
+ * A tail queue is headed by a pair of pointers, one to the head of the
+ * list and the other to the tail of the list. The elements are doubly
+ * linked so that an arbitrary element can be removed without a need to
+ * traverse the list. New elements can be added to the list before or
+ * after an existing element, at the head of the list, or at the end of
+ * the list. A tail queue may be traversed in either direction.
+ *
+ * For details on the use of these macros, see the queue(3) manual page.
+ */
+
+#include "qemu/atomic.h" /* for smp_wmb() */
+
+/*
+ * List definitions.
+ */
+#define QLIST_HEAD(name, type) \
+struct name { \
+ struct type *lh_first; /* first element */ \
+}
+
+#define QLIST_HEAD_INITIALIZER(head) \
+ { NULL }
+
+#define QLIST_ENTRY(type) \
+struct { \
+ struct type *le_next; /* next element */ \
+ struct type **le_prev; /* address of previous next element */ \
+}
+
+/*
+ * List functions.
+ */
+#define QLIST_INIT(head) do { \
+ (head)->lh_first = NULL; \
+} while (/*CONSTCOND*/0)
+
+#define QLIST_INSERT_AFTER(listelm, elm, field) do { \
+ if (((elm)->field.le_next = (listelm)->field.le_next) != NULL) \
+ (listelm)->field.le_next->field.le_prev = \
+ &(elm)->field.le_next; \
+ (listelm)->field.le_next = (elm); \
+ (elm)->field.le_prev = &(listelm)->field.le_next; \
+} while (/*CONSTCOND*/0)
+
+#define QLIST_INSERT_BEFORE(listelm, elm, field) do { \
+ (elm)->field.le_prev = (listelm)->field.le_prev; \
+ (elm)->field.le_next = (listelm); \
+ *(listelm)->field.le_prev = (elm); \
+ (listelm)->field.le_prev = &(elm)->field.le_next; \
+} while (/*CONSTCOND*/0)
+
+#define QLIST_INSERT_HEAD(head, elm, field) do { \
+ if (((elm)->field.le_next = (head)->lh_first) != NULL) \
+ (head)->lh_first->field.le_prev = &(elm)->field.le_next;\
+ (head)->lh_first = (elm); \
+ (elm)->field.le_prev = &(head)->lh_first; \
+} while (/*CONSTCOND*/0)
+
+#define QLIST_INSERT_HEAD_RCU(head, elm, field) do { \
+ (elm)->field.le_prev = &(head)->lh_first; \
+ (elm)->field.le_next = (head)->lh_first; \
+ smp_wmb(); /* fill elm before linking it */ \
+ if ((head)->lh_first != NULL) { \
+ (head)->lh_first->field.le_prev = &(elm)->field.le_next; \
+ } \
+ (head)->lh_first = (elm); \
+ smp_wmb(); \
+} while (/* CONSTCOND*/0)
+
+#define QLIST_REMOVE(elm, field) do { \
+ if ((elm)->field.le_next != NULL) \
+ (elm)->field.le_next->field.le_prev = \
+ (elm)->field.le_prev; \
+ *(elm)->field.le_prev = (elm)->field.le_next; \
+} while (/*CONSTCOND*/0)
+
+#define QLIST_FOREACH(var, head, field) \
+ for ((var) = ((head)->lh_first); \
+ (var); \
+ (var) = ((var)->field.le_next))
+
+#define QLIST_FOREACH_SAFE(var, head, field, next_var) \
+ for ((var) = ((head)->lh_first); \
+ (var) && ((next_var) = ((var)->field.le_next), 1); \
+ (var) = (next_var))
+
+/*
+ * List access methods.
+ */
+#define QLIST_EMPTY(head) ((head)->lh_first == NULL)
+#define QLIST_FIRST(head) ((head)->lh_first)
+#define QLIST_NEXT(elm, field) ((elm)->field.le_next)
+
+
+/*
+ * Singly-linked List definitions.
+ */
+#define QSLIST_HEAD(name, type) \
+struct name { \
+ struct type *slh_first; /* first element */ \
+}
+
+#define QSLIST_HEAD_INITIALIZER(head) \
+ { NULL }
+
+#define QSLIST_ENTRY(type) \
+struct { \
+ struct type *sle_next; /* next element */ \
+}
+
+/*
+ * Singly-linked List functions.
+ */
+#define QSLIST_INIT(head) do { \
+ (head)->slh_first = NULL; \
+} while (/*CONSTCOND*/0)
+
+#define QSLIST_INSERT_AFTER(slistelm, elm, field) do { \
+ (elm)->field.sle_next = (slistelm)->field.sle_next; \
+ (slistelm)->field.sle_next = (elm); \
+} while (/*CONSTCOND*/0)
+
+#define QSLIST_INSERT_HEAD(head, elm, field) do { \
+ (elm)->field.sle_next = (head)->slh_first; \
+ (head)->slh_first = (elm); \
+} while (/*CONSTCOND*/0)
+
+#define QSLIST_REMOVE_HEAD(head, field) do { \
+ (head)->slh_first = (head)->slh_first->field.sle_next; \
+} while (/*CONSTCOND*/0)
+
+#define QSLIST_REMOVE_AFTER(slistelm, field) do { \
+ (slistelm)->field.sle_next = \
+ QSLIST_NEXT(QSLIST_NEXT((slistelm), field), field); \
+} while (/*CONSTCOND*/0)
+
+#define QSLIST_FOREACH(var, head, field) \
+ for((var) = (head)->slh_first; (var); (var) = (var)->field.sle_next)
+
+#define QSLIST_FOREACH_SAFE(var, head, field, tvar) \
+ for ((var) = QSLIST_FIRST((head)); \
+ (var) && ((tvar) = QSLIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+/*
+ * Singly-linked List access methods.
+ */
+#define QSLIST_EMPTY(head) ((head)->slh_first == NULL)
+#define QSLIST_FIRST(head) ((head)->slh_first)
+#define QSLIST_NEXT(elm, field) ((elm)->field.sle_next)
+
+
+/*
+ * Simple queue definitions.
+ */
+#define QSIMPLEQ_HEAD(name, type) \
+struct name { \
+ struct type *sqh_first; /* first element */ \
+ struct type **sqh_last; /* addr of last next element */ \
+}
+
+#define QSIMPLEQ_HEAD_INITIALIZER(head) \
+ { NULL, &(head).sqh_first }
+
+#define QSIMPLEQ_ENTRY(type) \
+struct { \
+ struct type *sqe_next; /* next element */ \
+}
+
+/*
+ * Simple queue functions.
+ */
+#define QSIMPLEQ_INIT(head) do { \
+ (head)->sqh_first = NULL; \
+ (head)->sqh_last = &(head)->sqh_first; \
+} while (/*CONSTCOND*/0)
+
+#define QSIMPLEQ_INSERT_HEAD(head, elm, field) do { \
+ if (((elm)->field.sqe_next = (head)->sqh_first) == NULL) \
+ (head)->sqh_last = &(elm)->field.sqe_next; \
+ (head)->sqh_first = (elm); \
+} while (/*CONSTCOND*/0)
+
+#define QSIMPLEQ_INSERT_TAIL(head, elm, field) do { \
+ (elm)->field.sqe_next = NULL; \
+ *(head)->sqh_last = (elm); \
+ (head)->sqh_last = &(elm)->field.sqe_next; \
+} while (/*CONSTCOND*/0)
+
+#define QSIMPLEQ_INSERT_AFTER(head, listelm, elm, field) do { \
+ if (((elm)->field.sqe_next = (listelm)->field.sqe_next) == NULL) \
+ (head)->sqh_last = &(elm)->field.sqe_next; \
+ (listelm)->field.sqe_next = (elm); \
+} while (/*CONSTCOND*/0)
+
+#define QSIMPLEQ_REMOVE_HEAD(head, field) do { \
+ if (((head)->sqh_first = (head)->sqh_first->field.sqe_next) == NULL)\
+ (head)->sqh_last = &(head)->sqh_first; \
+} while (/*CONSTCOND*/0)
+
+#define QSIMPLEQ_REMOVE(head, elm, type, field) do { \
+ if ((head)->sqh_first == (elm)) { \
+ QSIMPLEQ_REMOVE_HEAD((head), field); \
+ } else { \
+ struct type *curelm = (head)->sqh_first; \
+ while (curelm->field.sqe_next != (elm)) \
+ curelm = curelm->field.sqe_next; \
+ if ((curelm->field.sqe_next = \
+ curelm->field.sqe_next->field.sqe_next) == NULL) \
+ (head)->sqh_last = &(curelm)->field.sqe_next; \
+ } \
+} while (/*CONSTCOND*/0)
+
+#define QSIMPLEQ_FOREACH(var, head, field) \
+ for ((var) = ((head)->sqh_first); \
+ (var); \
+ (var) = ((var)->field.sqe_next))
+
+#define QSIMPLEQ_FOREACH_SAFE(var, head, field, next) \
+ for ((var) = ((head)->sqh_first); \
+ (var) && ((next = ((var)->field.sqe_next)), 1); \
+ (var) = (next))
+
+#define QSIMPLEQ_CONCAT(head1, head2) do { \
+ if (!QSIMPLEQ_EMPTY((head2))) { \
+ *(head1)->sqh_last = (head2)->sqh_first; \
+ (head1)->sqh_last = (head2)->sqh_last; \
+ QSIMPLEQ_INIT((head2)); \
+ } \
+} while (/*CONSTCOND*/0)
+
+#define QSIMPLEQ_LAST(head, type, field) \
+ (QSIMPLEQ_EMPTY((head)) ? \
+ NULL : \
+ ((struct type *)(void *) \
+ ((char *)((head)->sqh_last) - offsetof(struct type, field))))
+
+/*
+ * Simple queue access methods.
+ */
+#define QSIMPLEQ_EMPTY(head) ((head)->sqh_first == NULL)
+#define QSIMPLEQ_FIRST(head) ((head)->sqh_first)
+#define QSIMPLEQ_NEXT(elm, field) ((elm)->field.sqe_next)
+
+
+/*
+ * Tail queue definitions.
+ */
+#define Q_TAILQ_HEAD(name, type, qual) \
+struct name { \
+ qual type *tqh_first; /* first element */ \
+ qual type *qual *tqh_last; /* addr of last next element */ \
+}
+#define QTAILQ_HEAD(name, type) Q_TAILQ_HEAD(name, struct type,)
+
+#define QTAILQ_HEAD_INITIALIZER(head) \
+ { NULL, &(head).tqh_first }
+
+#define Q_TAILQ_ENTRY(type, qual) \
+struct { \
+ qual type *tqe_next; /* next element */ \
+ qual type *qual *tqe_prev; /* address of previous next element */\
+}
+#define QTAILQ_ENTRY(type) Q_TAILQ_ENTRY(struct type,)
+
+/*
+ * Tail queue functions.
+ */
+#define QTAILQ_INIT(head) do { \
+ (head)->tqh_first = NULL; \
+ (head)->tqh_last = &(head)->tqh_first; \
+} while (/*CONSTCOND*/0)
+
+#define QTAILQ_INSERT_HEAD(head, elm, field) do { \
+ if (((elm)->field.tqe_next = (head)->tqh_first) != NULL) \
+ (head)->tqh_first->field.tqe_prev = \
+ &(elm)->field.tqe_next; \
+ else \
+ (head)->tqh_last = &(elm)->field.tqe_next; \
+ (head)->tqh_first = (elm); \
+ (elm)->field.tqe_prev = &(head)->tqh_first; \
+} while (/*CONSTCOND*/0)
+
+#define QTAILQ_INSERT_TAIL(head, elm, field) do { \
+ (elm)->field.tqe_next = NULL; \
+ (elm)->field.tqe_prev = (head)->tqh_last; \
+ *(head)->tqh_last = (elm); \
+ (head)->tqh_last = &(elm)->field.tqe_next; \
+} while (/*CONSTCOND*/0)
+
+#define QTAILQ_INSERT_AFTER(head, listelm, elm, field) do { \
+ if (((elm)->field.tqe_next = (listelm)->field.tqe_next) != NULL)\
+ (elm)->field.tqe_next->field.tqe_prev = \
+ &(elm)->field.tqe_next; \
+ else \
+ (head)->tqh_last = &(elm)->field.tqe_next; \
+ (listelm)->field.tqe_next = (elm); \
+ (elm)->field.tqe_prev = &(listelm)->field.tqe_next; \
+} while (/*CONSTCOND*/0)
+
+#define QTAILQ_INSERT_BEFORE(listelm, elm, field) do { \
+ (elm)->field.tqe_prev = (listelm)->field.tqe_prev; \
+ (elm)->field.tqe_next = (listelm); \
+ *(listelm)->field.tqe_prev = (elm); \
+ (listelm)->field.tqe_prev = &(elm)->field.tqe_next; \
+} while (/*CONSTCOND*/0)
+
+#define QTAILQ_REMOVE(head, elm, field) do { \
+ if (((elm)->field.tqe_next) != NULL) \
+ (elm)->field.tqe_next->field.tqe_prev = \
+ (elm)->field.tqe_prev; \
+ else \
+ (head)->tqh_last = (elm)->field.tqe_prev; \
+ *(elm)->field.tqe_prev = (elm)->field.tqe_next; \
+} while (/*CONSTCOND*/0)
+
+#define QTAILQ_FOREACH(var, head, field) \
+ for ((var) = ((head)->tqh_first); \
+ (var); \
+ (var) = ((var)->field.tqe_next))
+
+#define QTAILQ_FOREACH_SAFE(var, head, field, next_var) \
+ for ((var) = ((head)->tqh_first); \
+ (var) && ((next_var) = ((var)->field.tqe_next), 1); \
+ (var) = (next_var))
+
+#define QTAILQ_FOREACH_REVERSE(var, head, headname, field) \
+ for ((var) = (*(((struct headname *)((head)->tqh_last))->tqh_last)); \
+ (var); \
+ (var) = (*(((struct headname *)((var)->field.tqe_prev))->tqh_last)))
+
+/*
+ * Tail queue access methods.
+ */
+#define QTAILQ_EMPTY(head) ((head)->tqh_first == NULL)
+#define QTAILQ_FIRST(head) ((head)->tqh_first)
+#define QTAILQ_NEXT(elm, field) ((elm)->field.tqe_next)
+
+#define QTAILQ_LAST(head, headname) \
+ (*(((struct headname *)((head)->tqh_last))->tqh_last))
+#define QTAILQ_PREV(elm, headname, field) \
+ (*(((struct headname *)((elm)->field.tqe_prev))->tqh_last))
+
+#endif /* !QEMU_SYS_QUEUE_H_ */
diff --git a/contrib/qemu/include/qemu/sockets.h b/contrib/qemu/include/qemu/sockets.h
new file mode 100644
index 00000000000..c5174d76a70
--- /dev/null
+++ b/contrib/qemu/include/qemu/sockets.h
@@ -0,0 +1,83 @@
+/* headers to use the BSD sockets */
+#ifndef QEMU_SOCKET_H
+#define QEMU_SOCKET_H
+
+#ifdef _WIN32
+#include <windows.h>
+#include <winsock2.h>
+#include <ws2tcpip.h>
+
+#define socket_error() WSAGetLastError()
+
+int inet_aton(const char *cp, struct in_addr *ia);
+
+#else
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <arpa/inet.h>
+#include <netdb.h>
+#include <sys/un.h>
+
+#define socket_error() errno
+#define closesocket(s) close(s)
+
+#endif /* !_WIN32 */
+
+#include "qemu/option.h"
+#include "qapi/error.h"
+#include "qapi/qmp/qerror.h"
+
+extern QemuOptsList socket_optslist;
+
+/* misc helpers */
+int qemu_socket(int domain, int type, int protocol);
+int qemu_accept(int s, struct sockaddr *addr, socklen_t *addrlen);
+int socket_set_cork(int fd, int v);
+int socket_set_nodelay(int fd);
+void qemu_set_block(int fd);
+void qemu_set_nonblock(int fd);
+int send_all(int fd, const void *buf, int len1);
+int recv_all(int fd, void *buf, int len1, bool single_read);
+
+/* callback function for nonblocking connect
+ * valid fd on success, negative error code on failure
+ */
+typedef void NonBlockingConnectHandler(int fd, void *opaque);
+
+InetSocketAddress *inet_parse(const char *str, Error **errp);
+int inet_listen_opts(QemuOpts *opts, int port_offset, Error **errp);
+int inet_listen(const char *str, char *ostr, int olen,
+ int socktype, int port_offset, Error **errp);
+int inet_connect_opts(QemuOpts *opts, Error **errp,
+ NonBlockingConnectHandler *callback, void *opaque);
+int inet_connect(const char *str, Error **errp);
+int inet_nonblocking_connect(const char *str,
+ NonBlockingConnectHandler *callback,
+ void *opaque, Error **errp);
+
+int inet_dgram_opts(QemuOpts *opts, Error **errp);
+const char *inet_strfamily(int family);
+
+int unix_listen_opts(QemuOpts *opts, Error **errp);
+int unix_listen(const char *path, char *ostr, int olen, Error **errp);
+int unix_connect_opts(QemuOpts *opts, Error **errp,
+ NonBlockingConnectHandler *callback, void *opaque);
+int unix_connect(const char *path, Error **errp);
+int unix_nonblocking_connect(const char *str,
+ NonBlockingConnectHandler *callback,
+ void *opaque, Error **errp);
+
+SocketAddress *socket_parse(const char *str, Error **errp);
+int socket_connect(SocketAddress *addr, Error **errp,
+ NonBlockingConnectHandler *callback, void *opaque);
+int socket_listen(SocketAddress *addr, Error **errp);
+int socket_dgram(SocketAddress *remote, SocketAddress *local, Error **errp);
+
+/* Old, ipv4 only bits. Don't use for new code. */
+int parse_host_port(struct sockaddr_in *saddr, const char *str);
+int socket_init(void);
+
+#endif /* QEMU_SOCKET_H */
diff --git a/contrib/qemu/include/qemu/thread-posix.h b/contrib/qemu/include/qemu/thread-posix.h
new file mode 100644
index 00000000000..0f30dccb53c
--- /dev/null
+++ b/contrib/qemu/include/qemu/thread-posix.h
@@ -0,0 +1,28 @@
+#ifndef __QEMU_THREAD_POSIX_H
+#define __QEMU_THREAD_POSIX_H 1
+#include "pthread.h"
+#include <semaphore.h>
+
+struct QemuMutex {
+ pthread_mutex_t lock;
+};
+
+struct QemuCond {
+ pthread_cond_t cond;
+};
+
+struct QemuSemaphore {
+#if defined(__APPLE__) || defined(__NetBSD__)
+ pthread_mutex_t lock;
+ pthread_cond_t cond;
+ int count;
+#else
+ sem_t sem;
+#endif
+};
+
+struct QemuThread {
+ pthread_t thread;
+};
+
+#endif
diff --git a/contrib/qemu/include/qemu/thread.h b/contrib/qemu/include/qemu/thread.h
new file mode 100644
index 00000000000..c02404b9fbf
--- /dev/null
+++ b/contrib/qemu/include/qemu/thread.h
@@ -0,0 +1,56 @@
+#ifndef __QEMU_THREAD_H
+#define __QEMU_THREAD_H 1
+
+#include <inttypes.h>
+#include <stdbool.h>
+
+typedef struct QemuMutex QemuMutex;
+typedef struct QemuCond QemuCond;
+typedef struct QemuSemaphore QemuSemaphore;
+typedef struct QemuThread QemuThread;
+
+#ifdef _WIN32
+#include "qemu/thread-win32.h"
+#else
+#include "qemu/thread-posix.h"
+#endif
+
+#define QEMU_THREAD_JOINABLE 0
+#define QEMU_THREAD_DETACHED 1
+
+void qemu_mutex_init(QemuMutex *mutex);
+void qemu_mutex_destroy(QemuMutex *mutex);
+void qemu_mutex_lock(QemuMutex *mutex);
+int qemu_mutex_trylock(QemuMutex *mutex);
+void qemu_mutex_unlock(QemuMutex *mutex);
+
+#define rcu_read_lock() do { } while (0)
+#define rcu_read_unlock() do { } while (0)
+
+void qemu_cond_init(QemuCond *cond);
+void qemu_cond_destroy(QemuCond *cond);
+
+/*
+ * IMPORTANT: The implementation does not guarantee that pthread_cond_signal
+ * and pthread_cond_broadcast can be called except while the same mutex is
+ * held as in the corresponding pthread_cond_wait calls!
+ */
+void qemu_cond_signal(QemuCond *cond);
+void qemu_cond_broadcast(QemuCond *cond);
+void qemu_cond_wait(QemuCond *cond, QemuMutex *mutex);
+
+void qemu_sem_init(QemuSemaphore *sem, int init);
+void qemu_sem_post(QemuSemaphore *sem);
+void qemu_sem_wait(QemuSemaphore *sem);
+int qemu_sem_timedwait(QemuSemaphore *sem, int ms);
+void qemu_sem_destroy(QemuSemaphore *sem);
+
+void qemu_thread_create(QemuThread *thread,
+ void *(*start_routine)(void *),
+ void *arg, int mode);
+void *qemu_thread_join(QemuThread *thread);
+void qemu_thread_get_self(QemuThread *thread);
+bool qemu_thread_is_self(QemuThread *thread);
+void qemu_thread_exit(void *retval);
+
+#endif
diff --git a/contrib/qemu/include/qemu/timer.h b/contrib/qemu/include/qemu/timer.h
new file mode 100644
index 00000000000..9dd206ce7f4
--- /dev/null
+++ b/contrib/qemu/include/qemu/timer.h
@@ -0,0 +1,305 @@
+#ifndef QEMU_TIMER_H
+#define QEMU_TIMER_H
+
+#include "qemu-common.h"
+#include "qemu/main-loop.h"
+#include "qemu/notify.h"
+
+/* timers */
+
+#define SCALE_MS 1000000
+#define SCALE_US 1000
+#define SCALE_NS 1
+
+typedef struct QEMUClock QEMUClock;
+typedef void QEMUTimerCB(void *opaque);
+
+/* The real time clock should be used only for stuff which does not
+ change the virtual machine state, as it is run even if the virtual
+ machine is stopped. The real time clock has a frequency of 1000
+ Hz. */
+extern QEMUClock *rt_clock;
+
+/* The virtual clock is only run during the emulation. It is stopped
+ when the virtual machine is stopped. Virtual timers use a high
+ precision clock, usually cpu cycles (use ticks_per_sec). */
+extern QEMUClock *vm_clock;
+
+/* The host clock should be use for device models that emulate accurate
+ real time sources. It will continue to run when the virtual machine
+ is suspended, and it will reflect system time changes the host may
+ undergo (e.g. due to NTP). The host clock has the same precision as
+ the virtual clock. */
+extern QEMUClock *host_clock;
+
+int64_t qemu_get_clock_ns(QEMUClock *clock);
+int64_t qemu_clock_has_timers(QEMUClock *clock);
+int64_t qemu_clock_expired(QEMUClock *clock);
+int64_t qemu_clock_deadline(QEMUClock *clock);
+void qemu_clock_enable(QEMUClock *clock, bool enabled);
+void qemu_clock_warp(QEMUClock *clock);
+
+void qemu_register_clock_reset_notifier(QEMUClock *clock, Notifier *notifier);
+void qemu_unregister_clock_reset_notifier(QEMUClock *clock,
+ Notifier *notifier);
+
+QEMUTimer *qemu_new_timer(QEMUClock *clock, int scale,
+ QEMUTimerCB *cb, void *opaque);
+void qemu_free_timer(QEMUTimer *ts);
+void qemu_del_timer(QEMUTimer *ts);
+void qemu_mod_timer_ns(QEMUTimer *ts, int64_t expire_time);
+void qemu_mod_timer(QEMUTimer *ts, int64_t expire_time);
+bool qemu_timer_pending(QEMUTimer *ts);
+bool qemu_timer_expired(QEMUTimer *timer_head, int64_t current_time);
+uint64_t qemu_timer_expire_time_ns(QEMUTimer *ts);
+
+void qemu_run_timers(QEMUClock *clock);
+void qemu_run_all_timers(void);
+void configure_alarms(char const *opt);
+void init_clocks(void);
+int init_timer_alarm(void);
+
+int64_t cpu_get_ticks(void);
+void cpu_enable_ticks(void);
+void cpu_disable_ticks(void);
+
+static inline QEMUTimer *qemu_new_timer_ns(QEMUClock *clock, QEMUTimerCB *cb,
+ void *opaque)
+{
+ return qemu_new_timer(clock, SCALE_NS, cb, opaque);
+}
+
+static inline QEMUTimer *qemu_new_timer_ms(QEMUClock *clock, QEMUTimerCB *cb,
+ void *opaque)
+{
+ return qemu_new_timer(clock, SCALE_MS, cb, opaque);
+}
+
+static inline int64_t qemu_get_clock_ms(QEMUClock *clock)
+{
+ return qemu_get_clock_ns(clock) / SCALE_MS;
+}
+
+static inline int64_t get_ticks_per_sec(void)
+{
+ return 1000000000LL;
+}
+
+/* real time host monotonic timer */
+static inline int64_t get_clock_realtime(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return tv.tv_sec * 1000000000LL + (tv.tv_usec * 1000);
+}
+
+/* Warning: don't insert tracepoints into these functions, they are
+ also used by simpletrace backend and tracepoints would cause
+ an infinite recursion! */
+#ifdef _WIN32
+extern int64_t clock_freq;
+
+static inline int64_t get_clock(void)
+{
+ LARGE_INTEGER ti;
+ QueryPerformanceCounter(&ti);
+ return muldiv64(ti.QuadPart, get_ticks_per_sec(), clock_freq);
+}
+
+#else
+
+extern int use_rt_clock;
+
+static inline int64_t get_clock(void)
+{
+#ifdef CLOCK_MONOTONIC
+ if (use_rt_clock) {
+ struct timespec ts;
+ clock_gettime(CLOCK_MONOTONIC, &ts);
+ return ts.tv_sec * 1000000000LL + ts.tv_nsec;
+ } else
+#endif
+ {
+ /* XXX: using gettimeofday leads to problems if the date
+ changes, so it should be avoided. */
+ return get_clock_realtime();
+ }
+}
+#endif
+
+void qemu_get_timer(QEMUFile *f, QEMUTimer *ts);
+void qemu_put_timer(QEMUFile *f, QEMUTimer *ts);
+
+/* icount */
+int64_t cpu_get_icount(void);
+int64_t cpu_get_clock(void);
+
+/*******************************************/
+/* host CPU ticks (if available) */
+
+#if defined(_ARCH_PPC)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ int64_t retval;
+#ifdef _ARCH_PPC64
+ /* This reads timebase in one 64bit go and includes Cell workaround from:
+ http://ozlabs.org/pipermail/linuxppc-dev/2006-October/027052.html
+ */
+ __asm__ __volatile__ ("mftb %0\n\t"
+ "cmpwi %0,0\n\t"
+ "beq- $-8"
+ : "=r" (retval));
+#else
+ /* http://ozlabs.org/pipermail/linuxppc-dev/1999-October/003889.html */
+ unsigned long junk;
+ __asm__ __volatile__ ("mfspr %1,269\n\t" /* mftbu */
+ "mfspr %L0,268\n\t" /* mftb */
+ "mfspr %0,269\n\t" /* mftbu */
+ "cmpw %0,%1\n\t"
+ "bne $-16"
+ : "=r" (retval), "=r" (junk));
+#endif
+ return retval;
+}
+
+#elif defined(__i386__)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ int64_t val;
+ asm volatile ("rdtsc" : "=A" (val));
+ return val;
+}
+
+#elif defined(__x86_64__)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ uint32_t low,high;
+ int64_t val;
+ asm volatile("rdtsc" : "=a" (low), "=d" (high));
+ val = high;
+ val <<= 32;
+ val |= low;
+ return val;
+}
+
+#elif defined(__hppa__)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ int val;
+ asm volatile ("mfctl %%cr16, %0" : "=r"(val));
+ return val;
+}
+
+#elif defined(__ia64)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ int64_t val;
+ asm volatile ("mov %0 = ar.itc" : "=r"(val) :: "memory");
+ return val;
+}
+
+#elif defined(__s390__)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ int64_t val;
+ asm volatile("stck 0(%1)" : "=m" (val) : "a" (&val) : "cc");
+ return val;
+}
+
+#elif defined(__sparc__)
+
+static inline int64_t cpu_get_real_ticks (void)
+{
+#if defined(_LP64)
+ uint64_t rval;
+ asm volatile("rd %%tick,%0" : "=r"(rval));
+ return rval;
+#else
+ /* We need an %o or %g register for this. For recent enough gcc
+ there is an "h" constraint for that. Don't bother with that. */
+ union {
+ uint64_t i64;
+ struct {
+ uint32_t high;
+ uint32_t low;
+ } i32;
+ } rval;
+ asm volatile("rd %%tick,%%g1; srlx %%g1,32,%0; mov %%g1,%1"
+ : "=r"(rval.i32.high), "=r"(rval.i32.low) : : "g1");
+ return rval.i64;
+#endif
+}
+
+#elif defined(__mips__) && \
+ ((defined(__mips_isa_rev) && __mips_isa_rev >= 2) || defined(__linux__))
+/*
+ * binutils wants to use rdhwr only on mips32r2
+ * but as linux kernel emulate it, it's fine
+ * to use it.
+ *
+ */
+#define MIPS_RDHWR(rd, value) { \
+ __asm__ __volatile__ (".set push\n\t" \
+ ".set mips32r2\n\t" \
+ "rdhwr %0, "rd"\n\t" \
+ ".set pop" \
+ : "=r" (value)); \
+ }
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ /* On kernels >= 2.6.25 rdhwr <reg>, $2 and $3 are emulated */
+ uint32_t count;
+ static uint32_t cyc_per_count = 0;
+
+ if (!cyc_per_count) {
+ MIPS_RDHWR("$3", cyc_per_count);
+ }
+
+ MIPS_RDHWR("$2", count);
+ return (int64_t)(count * cyc_per_count);
+}
+
+#elif defined(__alpha__)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+ uint64_t cc;
+ uint32_t cur, ofs;
+
+ asm volatile("rpcc %0" : "=r"(cc));
+ cur = cc;
+ ofs = cc >> 32;
+ return cur - ofs;
+}
+
+#else
+/* The host CPU doesn't have an easily accessible cycle counter.
+ Just return a monotonically increasing value. This will be
+ totally wrong, but hopefully better than nothing. */
+static inline int64_t cpu_get_real_ticks (void)
+{
+ static int64_t ticks = 0;
+ return ticks++;
+}
+#endif
+
+#ifdef CONFIG_PROFILER
+static inline int64_t profile_getclock(void)
+{
+ return cpu_get_real_ticks();
+}
+
+extern int64_t qemu_time, qemu_time_start;
+extern int64_t tlb_flush_time;
+extern int64_t dev_time;
+#endif
+
+#endif
diff --git a/contrib/qemu/include/qemu/typedefs.h b/contrib/qemu/include/qemu/typedefs.h
new file mode 100644
index 00000000000..ac9f8d41a35
--- /dev/null
+++ b/contrib/qemu/include/qemu/typedefs.h
@@ -0,0 +1,69 @@
+#ifndef QEMU_TYPEDEFS_H
+#define QEMU_TYPEDEFS_H
+
+/* A load of opaque types so that device init declarations don't have to
+ pull in all the real definitions. */
+typedef struct QEMUTimer QEMUTimer;
+typedef struct QEMUFile QEMUFile;
+typedef struct QEMUBH QEMUBH;
+
+struct Monitor;
+typedef struct Monitor Monitor;
+typedef struct MigrationParams MigrationParams;
+
+typedef struct Property Property;
+typedef struct PropertyInfo PropertyInfo;
+typedef struct CompatProperty CompatProperty;
+typedef struct DeviceState DeviceState;
+typedef struct BusState BusState;
+typedef struct BusClass BusClass;
+
+typedef struct AddressSpace AddressSpace;
+typedef struct MemoryRegion MemoryRegion;
+typedef struct MemoryRegionSection MemoryRegionSection;
+
+typedef struct MemoryMappingList MemoryMappingList;
+
+typedef struct NICInfo NICInfo;
+typedef struct HCIInfo HCIInfo;
+typedef struct AudioState AudioState;
+typedef struct BlockDriverState BlockDriverState;
+typedef struct DriveInfo DriveInfo;
+typedef struct DisplayState DisplayState;
+typedef struct DisplayChangeListener DisplayChangeListener;
+typedef struct DisplaySurface DisplaySurface;
+typedef struct PixelFormat PixelFormat;
+typedef struct QemuConsole QemuConsole;
+typedef struct CharDriverState CharDriverState;
+typedef struct MACAddr MACAddr;
+typedef struct NetClientState NetClientState;
+typedef struct i2c_bus i2c_bus;
+typedef struct ISABus ISABus;
+typedef struct ISADevice ISADevice;
+typedef struct SMBusDevice SMBusDevice;
+typedef struct PCIHostState PCIHostState;
+typedef struct PCIExpressHost PCIExpressHost;
+typedef struct PCIBus PCIBus;
+typedef struct PCIDevice PCIDevice;
+typedef struct PCIExpressDevice PCIExpressDevice;
+typedef struct PCIBridge PCIBridge;
+typedef struct PCIEAERMsg PCIEAERMsg;
+typedef struct PCIEAERLog PCIEAERLog;
+typedef struct PCIEAERErr PCIEAERErr;
+typedef struct PCIEPort PCIEPort;
+typedef struct PCIESlot PCIESlot;
+typedef struct MSIMessage MSIMessage;
+typedef struct SerialState SerialState;
+typedef struct PCMCIACardState PCMCIACardState;
+typedef struct MouseTransformInfo MouseTransformInfo;
+typedef struct uWireSlave uWireSlave;
+typedef struct I2SCodec I2SCodec;
+typedef struct SSIBus SSIBus;
+typedef struct EventNotifier EventNotifier;
+typedef struct VirtIODevice VirtIODevice;
+typedef struct QEMUSGList QEMUSGList;
+typedef struct SHPCDevice SHPCDevice;
+typedef struct FWCfgState FWCfgState;
+typedef struct PcGuestInfo PcGuestInfo;
+
+#endif /* QEMU_TYPEDEFS_H */
diff --git a/contrib/qemu/include/sysemu/os-posix.h b/contrib/qemu/include/sysemu/os-posix.h
new file mode 100644
index 00000000000..25d0b2a73f6
--- /dev/null
+++ b/contrib/qemu/include/sysemu/os-posix.h
@@ -0,0 +1,52 @@
+/*
+ * posix specific declarations
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ * Copyright (c) 2010 Jes Sorensen <Jes.Sorensen@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef QEMU_OS_POSIX_H
+#define QEMU_OS_POSIX_H
+
+void os_set_line_buffering(void);
+void os_set_proc_name(const char *s);
+void os_setup_signal_handling(void);
+void os_daemonize(void);
+void os_setup_post(void);
+int os_mlock(void);
+
+typedef struct timeval qemu_timeval;
+#define qemu_gettimeofday(tp) gettimeofday(tp, NULL)
+
+#ifndef CONFIG_UTIMENSAT
+#ifndef UTIME_NOW
+# define UTIME_NOW ((1l << 30) - 1l)
+#endif
+#ifndef UTIME_OMIT
+# define UTIME_OMIT ((1l << 30) - 2l)
+#endif
+#endif
+typedef struct timespec qemu_timespec;
+int qemu_utimens(const char *path, const qemu_timespec *times);
+
+bool is_daemonized(void);
+
+#endif
diff --git a/contrib/qemu/include/sysemu/sysemu.h b/contrib/qemu/include/sysemu/sysemu.h
new file mode 100644
index 00000000000..3caeb66eb2f
--- /dev/null
+++ b/contrib/qemu/include/sysemu/sysemu.h
@@ -0,0 +1,200 @@
+#ifndef SYSEMU_H
+#define SYSEMU_H
+/* Misc. things related to the system emulator. */
+
+#include "qemu/typedefs.h"
+#include "qemu/option.h"
+#include "qemu/queue.h"
+#include "qemu/timer.h"
+#include "qapi-types.h"
+#include "qemu/notify.h"
+#include "qemu/main-loop.h"
+
+/* vl.c */
+
+extern const char *bios_name;
+
+extern const char *qemu_name;
+extern uint8_t qemu_uuid[];
+int qemu_uuid_parse(const char *str, uint8_t *uuid);
+#define UUID_FMT "%02hhx%02hhx%02hhx%02hhx-%02hhx%02hhx-%02hhx%02hhx-%02hhx%02hhx-%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx"
+
+bool runstate_check(RunState state);
+void runstate_set(RunState new_state);
+int runstate_is_running(void);
+bool runstate_needs_reset(void);
+typedef struct vm_change_state_entry VMChangeStateEntry;
+typedef void VMChangeStateHandler(void *opaque, int running, RunState state);
+
+VMChangeStateEntry *qemu_add_vm_change_state_handler(VMChangeStateHandler *cb,
+ void *opaque);
+void qemu_del_vm_change_state_handler(VMChangeStateEntry *e);
+void vm_state_notify(int running, RunState state);
+
+#define VMRESET_SILENT false
+#define VMRESET_REPORT true
+
+void vm_start(void);
+int vm_stop(RunState state);
+int vm_stop_force_state(RunState state);
+
+typedef enum WakeupReason {
+ QEMU_WAKEUP_REASON_OTHER = 0,
+ QEMU_WAKEUP_REASON_RTC,
+ QEMU_WAKEUP_REASON_PMTIMER,
+} WakeupReason;
+
+void qemu_system_reset_request(void);
+void qemu_system_suspend_request(void);
+void qemu_register_suspend_notifier(Notifier *notifier);
+void qemu_system_wakeup_request(WakeupReason reason);
+void qemu_system_wakeup_enable(WakeupReason reason, bool enabled);
+void qemu_register_wakeup_notifier(Notifier *notifier);
+void qemu_system_shutdown_request(void);
+void qemu_system_powerdown_request(void);
+void qemu_register_powerdown_notifier(Notifier *notifier);
+void qemu_system_debug_request(void);
+void qemu_system_vmstop_request(RunState reason);
+int qemu_shutdown_requested_get(void);
+int qemu_reset_requested_get(void);
+void qemu_system_killed(int signal, pid_t pid);
+void qemu_devices_reset(void);
+void qemu_system_reset(bool report);
+
+void qemu_add_exit_notifier(Notifier *notify);
+void qemu_remove_exit_notifier(Notifier *notify);
+
+void qemu_add_machine_init_done_notifier(Notifier *notify);
+
+void do_savevm(Monitor *mon, const QDict *qdict);
+int load_vmstate(const char *name);
+void do_delvm(Monitor *mon, const QDict *qdict);
+void do_info_snapshots(Monitor *mon, const QDict *qdict);
+
+void qemu_announce_self(void);
+
+bool qemu_savevm_state_blocked(Error **errp);
+void qemu_savevm_state_begin(QEMUFile *f,
+ const MigrationParams *params);
+int qemu_savevm_state_iterate(QEMUFile *f);
+void qemu_savevm_state_complete(QEMUFile *f);
+void qemu_savevm_state_cancel(void);
+uint64_t qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size);
+int qemu_loadvm_state(QEMUFile *f);
+
+/* SLIRP */
+void do_info_slirp(Monitor *mon);
+
+typedef enum DisplayType
+{
+ DT_DEFAULT,
+ DT_CURSES,
+ DT_SDL,
+ DT_GTK,
+ DT_NOGRAPHIC,
+ DT_NONE,
+} DisplayType;
+
+extern int autostart;
+
+typedef enum {
+ VGA_NONE, VGA_STD, VGA_CIRRUS, VGA_VMWARE, VGA_XENFB, VGA_QXL,
+} VGAInterfaceType;
+
+extern int vga_interface_type;
+#define xenfb_enabled (vga_interface_type == VGA_XENFB)
+#define qxl_enabled (vga_interface_type == VGA_QXL)
+
+extern int graphic_width;
+extern int graphic_height;
+extern int graphic_depth;
+extern DisplayType display_type;
+extern const char *keyboard_layout;
+extern int win2k_install_hack;
+extern int alt_grab;
+extern int ctrl_grab;
+extern int smp_cpus;
+extern int max_cpus;
+extern int cursor_hide;
+extern int graphic_rotate;
+extern int no_quit;
+extern int no_shutdown;
+extern int semihosting_enabled;
+extern int old_param;
+extern int boot_menu;
+extern uint8_t *boot_splash_filedata;
+extern size_t boot_splash_filedata_size;
+extern uint8_t qemu_extra_params_fw[2];
+extern QEMUClock *rtc_clock;
+
+#define MAX_NODES 64
+#define MAX_CPUMASK_BITS 255
+extern int nb_numa_nodes;
+extern uint64_t node_mem[MAX_NODES];
+extern unsigned long *node_cpumask[MAX_NODES];
+
+#define MAX_OPTION_ROMS 16
+typedef struct QEMUOptionRom {
+ const char *name;
+ int32_t bootindex;
+} QEMUOptionRom;
+extern QEMUOptionRom option_rom[MAX_OPTION_ROMS];
+extern int nb_option_roms;
+
+#define MAX_PROM_ENVS 128
+extern const char *prom_envs[MAX_PROM_ENVS];
+extern unsigned int nb_prom_envs;
+
+/* pci-hotplug */
+void pci_device_hot_add(Monitor *mon, const QDict *qdict);
+int pci_drive_hot_add(Monitor *mon, const QDict *qdict, DriveInfo *dinfo);
+void do_pci_device_hot_remove(Monitor *mon, const QDict *qdict);
+
+/* generic hotplug */
+void drive_hot_add(Monitor *mon, const QDict *qdict);
+
+/* CPU hotplug */
+void qemu_register_cpu_added_notifier(Notifier *notifier);
+
+/* pcie aer error injection */
+void pcie_aer_inject_error_print(Monitor *mon, const QObject *data);
+int do_pcie_aer_inject_error(Monitor *mon,
+ const QDict *qdict, QObject **ret_data);
+
+/* serial ports */
+
+#define MAX_SERIAL_PORTS 4
+
+extern CharDriverState *serial_hds[MAX_SERIAL_PORTS];
+
+/* parallel ports */
+
+#define MAX_PARALLEL_PORTS 3
+
+extern CharDriverState *parallel_hds[MAX_PARALLEL_PORTS];
+
+void do_usb_add(Monitor *mon, const QDict *qdict);
+void do_usb_del(Monitor *mon, const QDict *qdict);
+void usb_info(Monitor *mon, const QDict *qdict);
+
+void rtc_change_mon_event(struct tm *tm);
+
+void add_boot_device_path(int32_t bootindex, DeviceState *dev,
+ const char *suffix);
+char *get_boot_devices_list(size_t *size);
+
+DeviceState *get_boot_device(uint32_t position);
+
+QemuOpts *qemu_get_machine_opts(void);
+
+bool usb_enabled(bool default_usb);
+
+extern QemuOptsList qemu_drive_opts;
+extern QemuOptsList qemu_chardev_opts;
+extern QemuOptsList qemu_device_opts;
+extern QemuOptsList qemu_netdev_opts;
+extern QemuOptsList qemu_net_opts;
+extern QemuOptsList qemu_global_opts;
+extern QemuOptsList qemu_mon_opts;
+
+#endif
diff --git a/contrib/qemu/include/trace.h b/contrib/qemu/include/trace.h
new file mode 100644
index 00000000000..c15f4981280
--- /dev/null
+++ b/contrib/qemu/include/trace.h
@@ -0,0 +1,6 @@
+#ifndef TRACE_H
+#define TRACE_H
+
+#include "trace/generated-tracers.h"
+
+#endif /* TRACE_H */
diff --git a/contrib/qemu/qapi-types.h b/contrib/qemu/qapi-types.h
new file mode 100644
index 00000000000..082b06d1c2b
--- /dev/null
+++ b/contrib/qemu/qapi-types.h
@@ -0,0 +1,2746 @@
+/* AUTOMATICALLY GENERATED, DO NOT MODIFY */
+
+/*
+ * schema-defined QAPI types
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QAPI_TYPES_H
+#define QAPI_TYPES_H
+
+#include <stdbool.h>
+#include <stdint.h>
+
+
+#ifndef QAPI_TYPES_BUILTIN_STRUCT_DECL_H
+#define QAPI_TYPES_BUILTIN_STRUCT_DECL_H
+
+
+typedef struct strList
+{
+ union {
+ char * value;
+ uint64_t padding;
+ };
+ struct strList *next;
+} strList;
+
+typedef struct intList
+{
+ union {
+ int64_t value;
+ uint64_t padding;
+ };
+ struct intList *next;
+} intList;
+
+typedef struct numberList
+{
+ union {
+ double value;
+ uint64_t padding;
+ };
+ struct numberList *next;
+} numberList;
+
+typedef struct boolList
+{
+ union {
+ bool value;
+ uint64_t padding;
+ };
+ struct boolList *next;
+} boolList;
+
+typedef struct int8List
+{
+ union {
+ int8_t value;
+ uint64_t padding;
+ };
+ struct int8List *next;
+} int8List;
+
+typedef struct int16List
+{
+ union {
+ int16_t value;
+ uint64_t padding;
+ };
+ struct int16List *next;
+} int16List;
+
+typedef struct int32List
+{
+ union {
+ int32_t value;
+ uint64_t padding;
+ };
+ struct int32List *next;
+} int32List;
+
+typedef struct int64List
+{
+ union {
+ int64_t value;
+ uint64_t padding;
+ };
+ struct int64List *next;
+} int64List;
+
+typedef struct uint8List
+{
+ union {
+ uint8_t value;
+ uint64_t padding;
+ };
+ struct uint8List *next;
+} uint8List;
+
+typedef struct uint16List
+{
+ union {
+ uint16_t value;
+ uint64_t padding;
+ };
+ struct uint16List *next;
+} uint16List;
+
+typedef struct uint32List
+{
+ union {
+ uint32_t value;
+ uint64_t padding;
+ };
+ struct uint32List *next;
+} uint32List;
+
+typedef struct uint64List
+{
+ union {
+ uint64_t value;
+ uint64_t padding;
+ };
+ struct uint64List *next;
+} uint64List;
+
+#endif /* QAPI_TYPES_BUILTIN_STRUCT_DECL_H */
+
+
+extern const char *ErrorClass_lookup[];
+typedef enum ErrorClass
+{
+ ERROR_CLASS_GENERIC_ERROR = 0,
+ ERROR_CLASS_COMMAND_NOT_FOUND = 1,
+ ERROR_CLASS_DEVICE_ENCRYPTED = 2,
+ ERROR_CLASS_DEVICE_NOT_ACTIVE = 3,
+ ERROR_CLASS_DEVICE_NOT_FOUND = 4,
+ ERROR_CLASS_K_V_M_MISSING_CAP = 5,
+ ERROR_CLASS_MAX = 6,
+} ErrorClass;
+
+typedef struct ErrorClassList
+{
+ ErrorClass value;
+ struct ErrorClassList *next;
+} ErrorClassList;
+
+
+typedef struct NameInfo NameInfo;
+
+typedef struct NameInfoList
+{
+ union {
+ NameInfo *value;
+ uint64_t padding;
+ };
+ struct NameInfoList *next;
+} NameInfoList;
+
+
+typedef struct VersionInfo VersionInfo;
+
+typedef struct VersionInfoList
+{
+ union {
+ VersionInfo *value;
+ uint64_t padding;
+ };
+ struct VersionInfoList *next;
+} VersionInfoList;
+
+
+typedef struct KvmInfo KvmInfo;
+
+typedef struct KvmInfoList
+{
+ union {
+ KvmInfo *value;
+ uint64_t padding;
+ };
+ struct KvmInfoList *next;
+} KvmInfoList;
+
+extern const char *RunState_lookup[];
+typedef enum RunState
+{
+ RUN_STATE_DEBUG = 0,
+ RUN_STATE_INMIGRATE = 1,
+ RUN_STATE_INTERNAL_ERROR = 2,
+ RUN_STATE_IO_ERROR = 3,
+ RUN_STATE_PAUSED = 4,
+ RUN_STATE_POSTMIGRATE = 5,
+ RUN_STATE_PRELAUNCH = 6,
+ RUN_STATE_FINISH_MIGRATE = 7,
+ RUN_STATE_RESTORE_VM = 8,
+ RUN_STATE_RUNNING = 9,
+ RUN_STATE_SAVE_VM = 10,
+ RUN_STATE_SHUTDOWN = 11,
+ RUN_STATE_SUSPENDED = 12,
+ RUN_STATE_WATCHDOG = 13,
+ RUN_STATE_GUEST_PANICKED = 14,
+ RUN_STATE_MAX = 15,
+} RunState;
+
+typedef struct RunStateList
+{
+ RunState value;
+ struct RunStateList *next;
+} RunStateList;
+
+
+typedef struct SnapshotInfo SnapshotInfo;
+
+typedef struct SnapshotInfoList
+{
+ union {
+ SnapshotInfo *value;
+ uint64_t padding;
+ };
+ struct SnapshotInfoList *next;
+} SnapshotInfoList;
+
+
+typedef struct ImageInfo ImageInfo;
+
+typedef struct ImageInfoList
+{
+ union {
+ ImageInfo *value;
+ uint64_t padding;
+ };
+ struct ImageInfoList *next;
+} ImageInfoList;
+
+
+typedef struct ImageCheck ImageCheck;
+
+typedef struct ImageCheckList
+{
+ union {
+ ImageCheck *value;
+ uint64_t padding;
+ };
+ struct ImageCheckList *next;
+} ImageCheckList;
+
+
+typedef struct StatusInfo StatusInfo;
+
+typedef struct StatusInfoList
+{
+ union {
+ StatusInfo *value;
+ uint64_t padding;
+ };
+ struct StatusInfoList *next;
+} StatusInfoList;
+
+
+typedef struct UuidInfo UuidInfo;
+
+typedef struct UuidInfoList
+{
+ union {
+ UuidInfo *value;
+ uint64_t padding;
+ };
+ struct UuidInfoList *next;
+} UuidInfoList;
+
+
+typedef struct ChardevInfo ChardevInfo;
+
+typedef struct ChardevInfoList
+{
+ union {
+ ChardevInfo *value;
+ uint64_t padding;
+ };
+ struct ChardevInfoList *next;
+} ChardevInfoList;
+
+extern const char *DataFormat_lookup[];
+typedef enum DataFormat
+{
+ DATA_FORMAT_UTF8 = 0,
+ DATA_FORMAT_BASE64 = 1,
+ DATA_FORMAT_MAX = 2,
+} DataFormat;
+
+typedef struct DataFormatList
+{
+ DataFormat value;
+ struct DataFormatList *next;
+} DataFormatList;
+
+
+typedef struct CommandInfo CommandInfo;
+
+typedef struct CommandInfoList
+{
+ union {
+ CommandInfo *value;
+ uint64_t padding;
+ };
+ struct CommandInfoList *next;
+} CommandInfoList;
+
+
+typedef struct EventInfo EventInfo;
+
+typedef struct EventInfoList
+{
+ union {
+ EventInfo *value;
+ uint64_t padding;
+ };
+ struct EventInfoList *next;
+} EventInfoList;
+
+
+typedef struct MigrationStats MigrationStats;
+
+typedef struct MigrationStatsList
+{
+ union {
+ MigrationStats *value;
+ uint64_t padding;
+ };
+ struct MigrationStatsList *next;
+} MigrationStatsList;
+
+
+typedef struct XBZRLECacheStats XBZRLECacheStats;
+
+typedef struct XBZRLECacheStatsList
+{
+ union {
+ XBZRLECacheStats *value;
+ uint64_t padding;
+ };
+ struct XBZRLECacheStatsList *next;
+} XBZRLECacheStatsList;
+
+
+typedef struct MigrationInfo MigrationInfo;
+
+typedef struct MigrationInfoList
+{
+ union {
+ MigrationInfo *value;
+ uint64_t padding;
+ };
+ struct MigrationInfoList *next;
+} MigrationInfoList;
+
+extern const char *MigrationCapability_lookup[];
+typedef enum MigrationCapability
+{
+ MIGRATION_CAPABILITY_XBZRLE = 0,
+ MIGRATION_CAPABILITY_X_RDMA_PIN_ALL = 1,
+ MIGRATION_CAPABILITY_AUTO_CONVERGE = 2,
+ MIGRATION_CAPABILITY_MAX = 3,
+} MigrationCapability;
+
+typedef struct MigrationCapabilityList
+{
+ MigrationCapability value;
+ struct MigrationCapabilityList *next;
+} MigrationCapabilityList;
+
+
+typedef struct MigrationCapabilityStatus MigrationCapabilityStatus;
+
+typedef struct MigrationCapabilityStatusList
+{
+ union {
+ MigrationCapabilityStatus *value;
+ uint64_t padding;
+ };
+ struct MigrationCapabilityStatusList *next;
+} MigrationCapabilityStatusList;
+
+
+typedef struct MouseInfo MouseInfo;
+
+typedef struct MouseInfoList
+{
+ union {
+ MouseInfo *value;
+ uint64_t padding;
+ };
+ struct MouseInfoList *next;
+} MouseInfoList;
+
+
+typedef struct CpuInfo CpuInfo;
+
+typedef struct CpuInfoList
+{
+ union {
+ CpuInfo *value;
+ uint64_t padding;
+ };
+ struct CpuInfoList *next;
+} CpuInfoList;
+
+
+typedef struct BlockDeviceInfo BlockDeviceInfo;
+
+typedef struct BlockDeviceInfoList
+{
+ union {
+ BlockDeviceInfo *value;
+ uint64_t padding;
+ };
+ struct BlockDeviceInfoList *next;
+} BlockDeviceInfoList;
+
+extern const char *BlockDeviceIoStatus_lookup[];
+typedef enum BlockDeviceIoStatus
+{
+ BLOCK_DEVICE_IO_STATUS_OK = 0,
+ BLOCK_DEVICE_IO_STATUS_FAILED = 1,
+ BLOCK_DEVICE_IO_STATUS_NOSPACE = 2,
+ BLOCK_DEVICE_IO_STATUS_MAX = 3,
+} BlockDeviceIoStatus;
+
+typedef struct BlockDeviceIoStatusList
+{
+ BlockDeviceIoStatus value;
+ struct BlockDeviceIoStatusList *next;
+} BlockDeviceIoStatusList;
+
+
+typedef struct BlockDirtyInfo BlockDirtyInfo;
+
+typedef struct BlockDirtyInfoList
+{
+ union {
+ BlockDirtyInfo *value;
+ uint64_t padding;
+ };
+ struct BlockDirtyInfoList *next;
+} BlockDirtyInfoList;
+
+
+typedef struct BlockInfo BlockInfo;
+
+typedef struct BlockInfoList
+{
+ union {
+ BlockInfo *value;
+ uint64_t padding;
+ };
+ struct BlockInfoList *next;
+} BlockInfoList;
+
+
+typedef struct BlockDeviceStats BlockDeviceStats;
+
+typedef struct BlockDeviceStatsList
+{
+ union {
+ BlockDeviceStats *value;
+ uint64_t padding;
+ };
+ struct BlockDeviceStatsList *next;
+} BlockDeviceStatsList;
+
+
+typedef struct BlockStats BlockStats;
+
+typedef struct BlockStatsList
+{
+ union {
+ BlockStats *value;
+ uint64_t padding;
+ };
+ struct BlockStatsList *next;
+} BlockStatsList;
+
+
+typedef struct VncClientInfo VncClientInfo;
+
+typedef struct VncClientInfoList
+{
+ union {
+ VncClientInfo *value;
+ uint64_t padding;
+ };
+ struct VncClientInfoList *next;
+} VncClientInfoList;
+
+
+typedef struct VncInfo VncInfo;
+
+typedef struct VncInfoList
+{
+ union {
+ VncInfo *value;
+ uint64_t padding;
+ };
+ struct VncInfoList *next;
+} VncInfoList;
+
+
+typedef struct SpiceChannel SpiceChannel;
+
+typedef struct SpiceChannelList
+{
+ union {
+ SpiceChannel *value;
+ uint64_t padding;
+ };
+ struct SpiceChannelList *next;
+} SpiceChannelList;
+
+extern const char *SpiceQueryMouseMode_lookup[];
+typedef enum SpiceQueryMouseMode
+{
+ SPICE_QUERY_MOUSE_MODE_CLIENT = 0,
+ SPICE_QUERY_MOUSE_MODE_SERVER = 1,
+ SPICE_QUERY_MOUSE_MODE_UNKNOWN = 2,
+ SPICE_QUERY_MOUSE_MODE_MAX = 3,
+} SpiceQueryMouseMode;
+
+typedef struct SpiceQueryMouseModeList
+{
+ SpiceQueryMouseMode value;
+ struct SpiceQueryMouseModeList *next;
+} SpiceQueryMouseModeList;
+
+
+typedef struct SpiceInfo SpiceInfo;
+
+typedef struct SpiceInfoList
+{
+ union {
+ SpiceInfo *value;
+ uint64_t padding;
+ };
+ struct SpiceInfoList *next;
+} SpiceInfoList;
+
+
+typedef struct BalloonInfo BalloonInfo;
+
+typedef struct BalloonInfoList
+{
+ union {
+ BalloonInfo *value;
+ uint64_t padding;
+ };
+ struct BalloonInfoList *next;
+} BalloonInfoList;
+
+
+typedef struct PciMemoryRange PciMemoryRange;
+
+typedef struct PciMemoryRangeList
+{
+ union {
+ PciMemoryRange *value;
+ uint64_t padding;
+ };
+ struct PciMemoryRangeList *next;
+} PciMemoryRangeList;
+
+
+typedef struct PciMemoryRegion PciMemoryRegion;
+
+typedef struct PciMemoryRegionList
+{
+ union {
+ PciMemoryRegion *value;
+ uint64_t padding;
+ };
+ struct PciMemoryRegionList *next;
+} PciMemoryRegionList;
+
+
+typedef struct PciBridgeInfo PciBridgeInfo;
+
+typedef struct PciBridgeInfoList
+{
+ union {
+ PciBridgeInfo *value;
+ uint64_t padding;
+ };
+ struct PciBridgeInfoList *next;
+} PciBridgeInfoList;
+
+
+typedef struct PciDeviceInfo PciDeviceInfo;
+
+typedef struct PciDeviceInfoList
+{
+ union {
+ PciDeviceInfo *value;
+ uint64_t padding;
+ };
+ struct PciDeviceInfoList *next;
+} PciDeviceInfoList;
+
+
+typedef struct PciInfo PciInfo;
+
+typedef struct PciInfoList
+{
+ union {
+ PciInfo *value;
+ uint64_t padding;
+ };
+ struct PciInfoList *next;
+} PciInfoList;
+
+extern const char *BlockdevOnError_lookup[];
+typedef enum BlockdevOnError
+{
+ BLOCKDEV_ON_ERROR_REPORT = 0,
+ BLOCKDEV_ON_ERROR_IGNORE = 1,
+ BLOCKDEV_ON_ERROR_ENOSPC = 2,
+ BLOCKDEV_ON_ERROR_STOP = 3,
+ BLOCKDEV_ON_ERROR_MAX = 4,
+} BlockdevOnError;
+
+typedef struct BlockdevOnErrorList
+{
+ BlockdevOnError value;
+ struct BlockdevOnErrorList *next;
+} BlockdevOnErrorList;
+
+extern const char *MirrorSyncMode_lookup[];
+typedef enum MirrorSyncMode
+{
+ MIRROR_SYNC_MODE_TOP = 0,
+ MIRROR_SYNC_MODE_FULL = 1,
+ MIRROR_SYNC_MODE_NONE = 2,
+ MIRROR_SYNC_MODE_MAX = 3,
+} MirrorSyncMode;
+
+typedef struct MirrorSyncModeList
+{
+ MirrorSyncMode value;
+ struct MirrorSyncModeList *next;
+} MirrorSyncModeList;
+
+
+typedef struct BlockJobInfo BlockJobInfo;
+
+typedef struct BlockJobInfoList
+{
+ union {
+ BlockJobInfo *value;
+ uint64_t padding;
+ };
+ struct BlockJobInfoList *next;
+} BlockJobInfoList;
+
+extern const char *NewImageMode_lookup[];
+typedef enum NewImageMode
+{
+ NEW_IMAGE_MODE_EXISTING = 0,
+ NEW_IMAGE_MODE_ABSOLUTE_PATHS = 1,
+ NEW_IMAGE_MODE_MAX = 2,
+} NewImageMode;
+
+typedef struct NewImageModeList
+{
+ NewImageMode value;
+ struct NewImageModeList *next;
+} NewImageModeList;
+
+
+typedef struct BlockdevSnapshot BlockdevSnapshot;
+
+typedef struct BlockdevSnapshotList
+{
+ union {
+ BlockdevSnapshot *value;
+ uint64_t padding;
+ };
+ struct BlockdevSnapshotList *next;
+} BlockdevSnapshotList;
+
+
+typedef struct DriveBackup DriveBackup;
+
+typedef struct DriveBackupList
+{
+ union {
+ DriveBackup *value;
+ uint64_t padding;
+ };
+ struct DriveBackupList *next;
+} DriveBackupList;
+
+
+typedef struct Abort Abort;
+
+typedef struct AbortList
+{
+ union {
+ Abort *value;
+ uint64_t padding;
+ };
+ struct AbortList *next;
+} AbortList;
+
+
+typedef struct TransactionAction TransactionAction;
+
+typedef struct TransactionActionList
+{
+ union {
+ TransactionAction *value;
+ uint64_t padding;
+ };
+ struct TransactionActionList *next;
+} TransactionActionList;
+
+extern const char *TransactionActionKind_lookup[];
+typedef enum TransactionActionKind
+{
+ TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC = 0,
+ TRANSACTION_ACTION_KIND_DRIVE_BACKUP = 1,
+ TRANSACTION_ACTION_KIND_ABORT = 2,
+ TRANSACTION_ACTION_KIND_MAX = 3,
+} TransactionActionKind;
+
+
+typedef struct ObjectPropertyInfo ObjectPropertyInfo;
+
+typedef struct ObjectPropertyInfoList
+{
+ union {
+ ObjectPropertyInfo *value;
+ uint64_t padding;
+ };
+ struct ObjectPropertyInfoList *next;
+} ObjectPropertyInfoList;
+
+
+typedef struct ObjectTypeInfo ObjectTypeInfo;
+
+typedef struct ObjectTypeInfoList
+{
+ union {
+ ObjectTypeInfo *value;
+ uint64_t padding;
+ };
+ struct ObjectTypeInfoList *next;
+} ObjectTypeInfoList;
+
+
+typedef struct DevicePropertyInfo DevicePropertyInfo;
+
+typedef struct DevicePropertyInfoList
+{
+ union {
+ DevicePropertyInfo *value;
+ uint64_t padding;
+ };
+ struct DevicePropertyInfoList *next;
+} DevicePropertyInfoList;
+
+
+typedef struct NetdevNoneOptions NetdevNoneOptions;
+
+typedef struct NetdevNoneOptionsList
+{
+ union {
+ NetdevNoneOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevNoneOptionsList *next;
+} NetdevNoneOptionsList;
+
+
+typedef struct NetLegacyNicOptions NetLegacyNicOptions;
+
+typedef struct NetLegacyNicOptionsList
+{
+ union {
+ NetLegacyNicOptions *value;
+ uint64_t padding;
+ };
+ struct NetLegacyNicOptionsList *next;
+} NetLegacyNicOptionsList;
+
+
+typedef struct String String;
+
+typedef struct StringList
+{
+ union {
+ String *value;
+ uint64_t padding;
+ };
+ struct StringList *next;
+} StringList;
+
+
+typedef struct NetdevUserOptions NetdevUserOptions;
+
+typedef struct NetdevUserOptionsList
+{
+ union {
+ NetdevUserOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevUserOptionsList *next;
+} NetdevUserOptionsList;
+
+
+typedef struct NetdevTapOptions NetdevTapOptions;
+
+typedef struct NetdevTapOptionsList
+{
+ union {
+ NetdevTapOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevTapOptionsList *next;
+} NetdevTapOptionsList;
+
+
+typedef struct NetdevSocketOptions NetdevSocketOptions;
+
+typedef struct NetdevSocketOptionsList
+{
+ union {
+ NetdevSocketOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevSocketOptionsList *next;
+} NetdevSocketOptionsList;
+
+
+typedef struct NetdevVdeOptions NetdevVdeOptions;
+
+typedef struct NetdevVdeOptionsList
+{
+ union {
+ NetdevVdeOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevVdeOptionsList *next;
+} NetdevVdeOptionsList;
+
+
+typedef struct NetdevDumpOptions NetdevDumpOptions;
+
+typedef struct NetdevDumpOptionsList
+{
+ union {
+ NetdevDumpOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevDumpOptionsList *next;
+} NetdevDumpOptionsList;
+
+
+typedef struct NetdevBridgeOptions NetdevBridgeOptions;
+
+typedef struct NetdevBridgeOptionsList
+{
+ union {
+ NetdevBridgeOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevBridgeOptionsList *next;
+} NetdevBridgeOptionsList;
+
+
+typedef struct NetdevHubPortOptions NetdevHubPortOptions;
+
+typedef struct NetdevHubPortOptionsList
+{
+ union {
+ NetdevHubPortOptions *value;
+ uint64_t padding;
+ };
+ struct NetdevHubPortOptionsList *next;
+} NetdevHubPortOptionsList;
+
+
+typedef struct NetClientOptions NetClientOptions;
+
+typedef struct NetClientOptionsList
+{
+ union {
+ NetClientOptions *value;
+ uint64_t padding;
+ };
+ struct NetClientOptionsList *next;
+} NetClientOptionsList;
+
+extern const char *NetClientOptionsKind_lookup[];
+typedef enum NetClientOptionsKind
+{
+ NET_CLIENT_OPTIONS_KIND_NONE = 0,
+ NET_CLIENT_OPTIONS_KIND_NIC = 1,
+ NET_CLIENT_OPTIONS_KIND_USER = 2,
+ NET_CLIENT_OPTIONS_KIND_TAP = 3,
+ NET_CLIENT_OPTIONS_KIND_SOCKET = 4,
+ NET_CLIENT_OPTIONS_KIND_VDE = 5,
+ NET_CLIENT_OPTIONS_KIND_DUMP = 6,
+ NET_CLIENT_OPTIONS_KIND_BRIDGE = 7,
+ NET_CLIENT_OPTIONS_KIND_HUBPORT = 8,
+ NET_CLIENT_OPTIONS_KIND_MAX = 9,
+} NetClientOptionsKind;
+
+
+typedef struct NetLegacy NetLegacy;
+
+typedef struct NetLegacyList
+{
+ union {
+ NetLegacy *value;
+ uint64_t padding;
+ };
+ struct NetLegacyList *next;
+} NetLegacyList;
+
+
+typedef struct Netdev Netdev;
+
+typedef struct NetdevList
+{
+ union {
+ Netdev *value;
+ uint64_t padding;
+ };
+ struct NetdevList *next;
+} NetdevList;
+
+
+typedef struct InetSocketAddress InetSocketAddress;
+
+typedef struct InetSocketAddressList
+{
+ union {
+ InetSocketAddress *value;
+ uint64_t padding;
+ };
+ struct InetSocketAddressList *next;
+} InetSocketAddressList;
+
+
+typedef struct UnixSocketAddress UnixSocketAddress;
+
+typedef struct UnixSocketAddressList
+{
+ union {
+ UnixSocketAddress *value;
+ uint64_t padding;
+ };
+ struct UnixSocketAddressList *next;
+} UnixSocketAddressList;
+
+
+typedef struct SocketAddress SocketAddress;
+
+typedef struct SocketAddressList
+{
+ union {
+ SocketAddress *value;
+ uint64_t padding;
+ };
+ struct SocketAddressList *next;
+} SocketAddressList;
+
+extern const char *SocketAddressKind_lookup[];
+typedef enum SocketAddressKind
+{
+ SOCKET_ADDRESS_KIND_INET = 0,
+ SOCKET_ADDRESS_KIND_UNIX = 1,
+ SOCKET_ADDRESS_KIND_FD = 2,
+ SOCKET_ADDRESS_KIND_MAX = 3,
+} SocketAddressKind;
+
+
+typedef struct MachineInfo MachineInfo;
+
+typedef struct MachineInfoList
+{
+ union {
+ MachineInfo *value;
+ uint64_t padding;
+ };
+ struct MachineInfoList *next;
+} MachineInfoList;
+
+
+typedef struct CpuDefinitionInfo CpuDefinitionInfo;
+
+typedef struct CpuDefinitionInfoList
+{
+ union {
+ CpuDefinitionInfo *value;
+ uint64_t padding;
+ };
+ struct CpuDefinitionInfoList *next;
+} CpuDefinitionInfoList;
+
+
+typedef struct AddfdInfo AddfdInfo;
+
+typedef struct AddfdInfoList
+{
+ union {
+ AddfdInfo *value;
+ uint64_t padding;
+ };
+ struct AddfdInfoList *next;
+} AddfdInfoList;
+
+
+typedef struct FdsetFdInfo FdsetFdInfo;
+
+typedef struct FdsetFdInfoList
+{
+ union {
+ FdsetFdInfo *value;
+ uint64_t padding;
+ };
+ struct FdsetFdInfoList *next;
+} FdsetFdInfoList;
+
+
+typedef struct FdsetInfo FdsetInfo;
+
+typedef struct FdsetInfoList
+{
+ union {
+ FdsetInfo *value;
+ uint64_t padding;
+ };
+ struct FdsetInfoList *next;
+} FdsetInfoList;
+
+
+typedef struct TargetInfo TargetInfo;
+
+typedef struct TargetInfoList
+{
+ union {
+ TargetInfo *value;
+ uint64_t padding;
+ };
+ struct TargetInfoList *next;
+} TargetInfoList;
+
+extern const char *QKeyCode_lookup[];
+typedef enum QKeyCode
+{
+ Q_KEY_CODE_SHIFT = 0,
+ Q_KEY_CODE_SHIFT_R = 1,
+ Q_KEY_CODE_ALT = 2,
+ Q_KEY_CODE_ALT_R = 3,
+ Q_KEY_CODE_ALTGR = 4,
+ Q_KEY_CODE_ALTGR_R = 5,
+ Q_KEY_CODE_CTRL = 6,
+ Q_KEY_CODE_CTRL_R = 7,
+ Q_KEY_CODE_MENU = 8,
+ Q_KEY_CODE_ESC = 9,
+ Q_KEY_CODE_1 = 10,
+ Q_KEY_CODE_2 = 11,
+ Q_KEY_CODE_3 = 12,
+ Q_KEY_CODE_4 = 13,
+ Q_KEY_CODE_5 = 14,
+ Q_KEY_CODE_6 = 15,
+ Q_KEY_CODE_7 = 16,
+ Q_KEY_CODE_8 = 17,
+ Q_KEY_CODE_9 = 18,
+ Q_KEY_CODE_0 = 19,
+ Q_KEY_CODE_MINUS = 20,
+ Q_KEY_CODE_EQUAL = 21,
+ Q_KEY_CODE_BACKSPACE = 22,
+ Q_KEY_CODE_TAB = 23,
+ Q_KEY_CODE_Q = 24,
+ Q_KEY_CODE_W = 25,
+ Q_KEY_CODE_E = 26,
+ Q_KEY_CODE_R = 27,
+ Q_KEY_CODE_T = 28,
+ Q_KEY_CODE_Y = 29,
+ Q_KEY_CODE_U = 30,
+ Q_KEY_CODE_I = 31,
+ Q_KEY_CODE_O = 32,
+ Q_KEY_CODE_P = 33,
+ Q_KEY_CODE_BRACKET_LEFT = 34,
+ Q_KEY_CODE_BRACKET_RIGHT = 35,
+ Q_KEY_CODE_RET = 36,
+ Q_KEY_CODE_A = 37,
+ Q_KEY_CODE_S = 38,
+ Q_KEY_CODE_D = 39,
+ Q_KEY_CODE_F = 40,
+ Q_KEY_CODE_G = 41,
+ Q_KEY_CODE_H = 42,
+ Q_KEY_CODE_J = 43,
+ Q_KEY_CODE_K = 44,
+ Q_KEY_CODE_L = 45,
+ Q_KEY_CODE_SEMICOLON = 46,
+ Q_KEY_CODE_APOSTROPHE = 47,
+ Q_KEY_CODE_GRAVE_ACCENT = 48,
+ Q_KEY_CODE_BACKSLASH = 49,
+ Q_KEY_CODE_Z = 50,
+ Q_KEY_CODE_X = 51,
+ Q_KEY_CODE_C = 52,
+ Q_KEY_CODE_V = 53,
+ Q_KEY_CODE_B = 54,
+ Q_KEY_CODE_N = 55,
+ Q_KEY_CODE_M = 56,
+ Q_KEY_CODE_COMMA = 57,
+ Q_KEY_CODE_DOT = 58,
+ Q_KEY_CODE_SLASH = 59,
+ Q_KEY_CODE_ASTERISK = 60,
+ Q_KEY_CODE_SPC = 61,
+ Q_KEY_CODE_CAPS_LOCK = 62,
+ Q_KEY_CODE_F1 = 63,
+ Q_KEY_CODE_F2 = 64,
+ Q_KEY_CODE_F3 = 65,
+ Q_KEY_CODE_F4 = 66,
+ Q_KEY_CODE_F5 = 67,
+ Q_KEY_CODE_F6 = 68,
+ Q_KEY_CODE_F7 = 69,
+ Q_KEY_CODE_F8 = 70,
+ Q_KEY_CODE_F9 = 71,
+ Q_KEY_CODE_F10 = 72,
+ Q_KEY_CODE_NUM_LOCK = 73,
+ Q_KEY_CODE_SCROLL_LOCK = 74,
+ Q_KEY_CODE_KP_DIVIDE = 75,
+ Q_KEY_CODE_KP_MULTIPLY = 76,
+ Q_KEY_CODE_KP_SUBTRACT = 77,
+ Q_KEY_CODE_KP_ADD = 78,
+ Q_KEY_CODE_KP_ENTER = 79,
+ Q_KEY_CODE_KP_DECIMAL = 80,
+ Q_KEY_CODE_SYSRQ = 81,
+ Q_KEY_CODE_KP_0 = 82,
+ Q_KEY_CODE_KP_1 = 83,
+ Q_KEY_CODE_KP_2 = 84,
+ Q_KEY_CODE_KP_3 = 85,
+ Q_KEY_CODE_KP_4 = 86,
+ Q_KEY_CODE_KP_5 = 87,
+ Q_KEY_CODE_KP_6 = 88,
+ Q_KEY_CODE_KP_7 = 89,
+ Q_KEY_CODE_KP_8 = 90,
+ Q_KEY_CODE_KP_9 = 91,
+ Q_KEY_CODE_LESS = 92,
+ Q_KEY_CODE_F11 = 93,
+ Q_KEY_CODE_F12 = 94,
+ Q_KEY_CODE_PRINT = 95,
+ Q_KEY_CODE_HOME = 96,
+ Q_KEY_CODE_PGUP = 97,
+ Q_KEY_CODE_PGDN = 98,
+ Q_KEY_CODE_END = 99,
+ Q_KEY_CODE_LEFT = 100,
+ Q_KEY_CODE_UP = 101,
+ Q_KEY_CODE_DOWN = 102,
+ Q_KEY_CODE_RIGHT = 103,
+ Q_KEY_CODE_INSERT = 104,
+ Q_KEY_CODE_DELETE = 105,
+ Q_KEY_CODE_STOP = 106,
+ Q_KEY_CODE_AGAIN = 107,
+ Q_KEY_CODE_PROPS = 108,
+ Q_KEY_CODE_UNDO = 109,
+ Q_KEY_CODE_FRONT = 110,
+ Q_KEY_CODE_COPY = 111,
+ Q_KEY_CODE_OPEN = 112,
+ Q_KEY_CODE_PASTE = 113,
+ Q_KEY_CODE_FIND = 114,
+ Q_KEY_CODE_CUT = 115,
+ Q_KEY_CODE_LF = 116,
+ Q_KEY_CODE_HELP = 117,
+ Q_KEY_CODE_META_L = 118,
+ Q_KEY_CODE_META_R = 119,
+ Q_KEY_CODE_COMPOSE = 120,
+ Q_KEY_CODE_MAX = 121,
+} QKeyCode;
+
+typedef struct QKeyCodeList
+{
+ QKeyCode value;
+ struct QKeyCodeList *next;
+} QKeyCodeList;
+
+
+typedef struct KeyValue KeyValue;
+
+typedef struct KeyValueList
+{
+ union {
+ KeyValue *value;
+ uint64_t padding;
+ };
+ struct KeyValueList *next;
+} KeyValueList;
+
+extern const char *KeyValueKind_lookup[];
+typedef enum KeyValueKind
+{
+ KEY_VALUE_KIND_NUMBER = 0,
+ KEY_VALUE_KIND_QCODE = 1,
+ KEY_VALUE_KIND_MAX = 2,
+} KeyValueKind;
+
+
+typedef struct ChardevFile ChardevFile;
+
+typedef struct ChardevFileList
+{
+ union {
+ ChardevFile *value;
+ uint64_t padding;
+ };
+ struct ChardevFileList *next;
+} ChardevFileList;
+
+
+typedef struct ChardevHostdev ChardevHostdev;
+
+typedef struct ChardevHostdevList
+{
+ union {
+ ChardevHostdev *value;
+ uint64_t padding;
+ };
+ struct ChardevHostdevList *next;
+} ChardevHostdevList;
+
+
+typedef struct ChardevSocket ChardevSocket;
+
+typedef struct ChardevSocketList
+{
+ union {
+ ChardevSocket *value;
+ uint64_t padding;
+ };
+ struct ChardevSocketList *next;
+} ChardevSocketList;
+
+
+typedef struct ChardevUdp ChardevUdp;
+
+typedef struct ChardevUdpList
+{
+ union {
+ ChardevUdp *value;
+ uint64_t padding;
+ };
+ struct ChardevUdpList *next;
+} ChardevUdpList;
+
+
+typedef struct ChardevMux ChardevMux;
+
+typedef struct ChardevMuxList
+{
+ union {
+ ChardevMux *value;
+ uint64_t padding;
+ };
+ struct ChardevMuxList *next;
+} ChardevMuxList;
+
+
+typedef struct ChardevStdio ChardevStdio;
+
+typedef struct ChardevStdioList
+{
+ union {
+ ChardevStdio *value;
+ uint64_t padding;
+ };
+ struct ChardevStdioList *next;
+} ChardevStdioList;
+
+
+typedef struct ChardevSpiceChannel ChardevSpiceChannel;
+
+typedef struct ChardevSpiceChannelList
+{
+ union {
+ ChardevSpiceChannel *value;
+ uint64_t padding;
+ };
+ struct ChardevSpiceChannelList *next;
+} ChardevSpiceChannelList;
+
+
+typedef struct ChardevSpicePort ChardevSpicePort;
+
+typedef struct ChardevSpicePortList
+{
+ union {
+ ChardevSpicePort *value;
+ uint64_t padding;
+ };
+ struct ChardevSpicePortList *next;
+} ChardevSpicePortList;
+
+
+typedef struct ChardevVC ChardevVC;
+
+typedef struct ChardevVCList
+{
+ union {
+ ChardevVC *value;
+ uint64_t padding;
+ };
+ struct ChardevVCList *next;
+} ChardevVCList;
+
+
+typedef struct ChardevMemory ChardevMemory;
+
+typedef struct ChardevMemoryList
+{
+ union {
+ ChardevMemory *value;
+ uint64_t padding;
+ };
+ struct ChardevMemoryList *next;
+} ChardevMemoryList;
+
+
+typedef struct ChardevDummy ChardevDummy;
+
+typedef struct ChardevDummyList
+{
+ union {
+ ChardevDummy *value;
+ uint64_t padding;
+ };
+ struct ChardevDummyList *next;
+} ChardevDummyList;
+
+
+typedef struct ChardevBackend ChardevBackend;
+
+typedef struct ChardevBackendList
+{
+ union {
+ ChardevBackend *value;
+ uint64_t padding;
+ };
+ struct ChardevBackendList *next;
+} ChardevBackendList;
+
+extern const char *ChardevBackendKind_lookup[];
+typedef enum ChardevBackendKind
+{
+ CHARDEV_BACKEND_KIND_FILE = 0,
+ CHARDEV_BACKEND_KIND_SERIAL = 1,
+ CHARDEV_BACKEND_KIND_PARALLEL = 2,
+ CHARDEV_BACKEND_KIND_PIPE = 3,
+ CHARDEV_BACKEND_KIND_SOCKET = 4,
+ CHARDEV_BACKEND_KIND_UDP = 5,
+ CHARDEV_BACKEND_KIND_PTY = 6,
+ CHARDEV_BACKEND_KIND_NULL = 7,
+ CHARDEV_BACKEND_KIND_MUX = 8,
+ CHARDEV_BACKEND_KIND_MSMOUSE = 9,
+ CHARDEV_BACKEND_KIND_BRAILLE = 10,
+ CHARDEV_BACKEND_KIND_STDIO = 11,
+ CHARDEV_BACKEND_KIND_CONSOLE = 12,
+ CHARDEV_BACKEND_KIND_SPICEVMC = 13,
+ CHARDEV_BACKEND_KIND_SPICEPORT = 14,
+ CHARDEV_BACKEND_KIND_VC = 15,
+ CHARDEV_BACKEND_KIND_MEMORY = 16,
+ CHARDEV_BACKEND_KIND_MAX = 17,
+} ChardevBackendKind;
+
+
+typedef struct ChardevReturn ChardevReturn;
+
+typedef struct ChardevReturnList
+{
+ union {
+ ChardevReturn *value;
+ uint64_t padding;
+ };
+ struct ChardevReturnList *next;
+} ChardevReturnList;
+
+extern const char *TpmModel_lookup[];
+typedef enum TpmModel
+{
+ TPM_MODEL_TPM_TIS = 0,
+ TPM_MODEL_MAX = 1,
+} TpmModel;
+
+typedef struct TpmModelList
+{
+ TpmModel value;
+ struct TpmModelList *next;
+} TpmModelList;
+
+extern const char *TpmType_lookup[];
+typedef enum TpmType
+{
+ TPM_TYPE_PASSTHROUGH = 0,
+ TPM_TYPE_MAX = 1,
+} TpmType;
+
+typedef struct TpmTypeList
+{
+ TpmType value;
+ struct TpmTypeList *next;
+} TpmTypeList;
+
+
+typedef struct TPMPassthroughOptions TPMPassthroughOptions;
+
+typedef struct TPMPassthroughOptionsList
+{
+ union {
+ TPMPassthroughOptions *value;
+ uint64_t padding;
+ };
+ struct TPMPassthroughOptionsList *next;
+} TPMPassthroughOptionsList;
+
+
+typedef struct TpmTypeOptions TpmTypeOptions;
+
+typedef struct TpmTypeOptionsList
+{
+ union {
+ TpmTypeOptions *value;
+ uint64_t padding;
+ };
+ struct TpmTypeOptionsList *next;
+} TpmTypeOptionsList;
+
+extern const char *TpmTypeOptionsKind_lookup[];
+typedef enum TpmTypeOptionsKind
+{
+ TPM_TYPE_OPTIONS_KIND_PASSTHROUGH = 0,
+ TPM_TYPE_OPTIONS_KIND_MAX = 1,
+} TpmTypeOptionsKind;
+
+
+typedef struct TPMInfo TPMInfo;
+
+typedef struct TPMInfoList
+{
+ union {
+ TPMInfo *value;
+ uint64_t padding;
+ };
+ struct TPMInfoList *next;
+} TPMInfoList;
+
+
+typedef struct AcpiTableOptions AcpiTableOptions;
+
+typedef struct AcpiTableOptionsList
+{
+ union {
+ AcpiTableOptions *value;
+ uint64_t padding;
+ };
+ struct AcpiTableOptionsList *next;
+} AcpiTableOptionsList;
+
+extern const char *CommandLineParameterType_lookup[];
+typedef enum CommandLineParameterType
+{
+ COMMAND_LINE_PARAMETER_TYPE_STRING = 0,
+ COMMAND_LINE_PARAMETER_TYPE_BOOLEAN = 1,
+ COMMAND_LINE_PARAMETER_TYPE_NUMBER = 2,
+ COMMAND_LINE_PARAMETER_TYPE_SIZE = 3,
+ COMMAND_LINE_PARAMETER_TYPE_MAX = 4,
+} CommandLineParameterType;
+
+typedef struct CommandLineParameterTypeList
+{
+ CommandLineParameterType value;
+ struct CommandLineParameterTypeList *next;
+} CommandLineParameterTypeList;
+
+
+typedef struct CommandLineParameterInfo CommandLineParameterInfo;
+
+typedef struct CommandLineParameterInfoList
+{
+ union {
+ CommandLineParameterInfo *value;
+ uint64_t padding;
+ };
+ struct CommandLineParameterInfoList *next;
+} CommandLineParameterInfoList;
+
+
+typedef struct CommandLineOptionInfo CommandLineOptionInfo;
+
+typedef struct CommandLineOptionInfoList
+{
+ union {
+ CommandLineOptionInfo *value;
+ uint64_t padding;
+ };
+ struct CommandLineOptionInfoList *next;
+} CommandLineOptionInfoList;
+
+extern const char *X86CPURegister32_lookup[];
+typedef enum X86CPURegister32
+{
+ X86_C_P_U_REGISTER32_EAX = 0,
+ X86_C_P_U_REGISTER32_EBX = 1,
+ X86_C_P_U_REGISTER32_ECX = 2,
+ X86_C_P_U_REGISTER32_EDX = 3,
+ X86_C_P_U_REGISTER32_ESP = 4,
+ X86_C_P_U_REGISTER32_EBP = 5,
+ X86_C_P_U_REGISTER32_ESI = 6,
+ X86_C_P_U_REGISTER32_EDI = 7,
+ X86_C_P_U_REGISTER32_MAX = 8,
+} X86CPURegister32;
+
+typedef struct X86CPURegister32List
+{
+ X86CPURegister32 value;
+ struct X86CPURegister32List *next;
+} X86CPURegister32List;
+
+
+typedef struct X86CPUFeatureWordInfo X86CPUFeatureWordInfo;
+
+typedef struct X86CPUFeatureWordInfoList
+{
+ union {
+ X86CPUFeatureWordInfo *value;
+ uint64_t padding;
+ };
+ struct X86CPUFeatureWordInfoList *next;
+} X86CPUFeatureWordInfoList;
+
+extern const char *RxState_lookup[];
+typedef enum RxState
+{
+ RX_STATE_NORMAL = 0,
+ RX_STATE_NONE = 1,
+ RX_STATE_ALL = 2,
+ RX_STATE_MAX = 3,
+} RxState;
+
+typedef struct RxStateList
+{
+ RxState value;
+ struct RxStateList *next;
+} RxStateList;
+
+
+typedef struct RxFilterInfo RxFilterInfo;
+
+typedef struct RxFilterInfoList
+{
+ union {
+ RxFilterInfo *value;
+ uint64_t padding;
+ };
+ struct RxFilterInfoList *next;
+} RxFilterInfoList;
+
+#ifndef QAPI_TYPES_BUILTIN_CLEANUP_DECL_H
+#define QAPI_TYPES_BUILTIN_CLEANUP_DECL_H
+
+void qapi_free_strList(strList * obj);
+void qapi_free_intList(intList * obj);
+void qapi_free_numberList(numberList * obj);
+void qapi_free_boolList(boolList * obj);
+void qapi_free_int8List(int8List * obj);
+void qapi_free_int16List(int16List * obj);
+void qapi_free_int32List(int32List * obj);
+void qapi_free_int64List(int64List * obj);
+void qapi_free_uint8List(uint8List * obj);
+void qapi_free_uint16List(uint16List * obj);
+void qapi_free_uint32List(uint32List * obj);
+void qapi_free_uint64List(uint64List * obj);
+
+#endif /* QAPI_TYPES_BUILTIN_CLEANUP_DECL_H */
+
+
+void qapi_free_ErrorClassList(ErrorClassList * obj);
+
+struct NameInfo
+{
+ bool has_name;
+ char * name;
+};
+
+void qapi_free_NameInfoList(NameInfoList * obj);
+void qapi_free_NameInfo(NameInfo * obj);
+
+struct VersionInfo
+{
+ struct
+ {
+ int64_t major;
+ int64_t minor;
+ int64_t micro;
+ } qemu;
+ char * package;
+};
+
+void qapi_free_VersionInfoList(VersionInfoList * obj);
+void qapi_free_VersionInfo(VersionInfo * obj);
+
+struct KvmInfo
+{
+ bool enabled;
+ bool present;
+};
+
+void qapi_free_KvmInfoList(KvmInfoList * obj);
+void qapi_free_KvmInfo(KvmInfo * obj);
+
+void qapi_free_RunStateList(RunStateList * obj);
+
+struct SnapshotInfo
+{
+ char * id;
+ char * name;
+ int64_t vm_state_size;
+ int64_t date_sec;
+ int64_t date_nsec;
+ int64_t vm_clock_sec;
+ int64_t vm_clock_nsec;
+};
+
+void qapi_free_SnapshotInfoList(SnapshotInfoList * obj);
+void qapi_free_SnapshotInfo(SnapshotInfo * obj);
+
+struct ImageInfo
+{
+ char * filename;
+ char * format;
+ bool has_dirty_flag;
+ bool dirty_flag;
+ bool has_actual_size;
+ int64_t actual_size;
+ int64_t virtual_size;
+ bool has_cluster_size;
+ int64_t cluster_size;
+ bool has_encrypted;
+ bool encrypted;
+ bool has_backing_filename;
+ char * backing_filename;
+ bool has_full_backing_filename;
+ char * full_backing_filename;
+ bool has_backing_filename_format;
+ char * backing_filename_format;
+ bool has_snapshots;
+ SnapshotInfoList * snapshots;
+ bool has_backing_image;
+ ImageInfo * backing_image;
+};
+
+void qapi_free_ImageInfoList(ImageInfoList * obj);
+void qapi_free_ImageInfo(ImageInfo * obj);
+
+struct ImageCheck
+{
+ char * filename;
+ char * format;
+ int64_t check_errors;
+ bool has_image_end_offset;
+ int64_t image_end_offset;
+ bool has_corruptions;
+ int64_t corruptions;
+ bool has_leaks;
+ int64_t leaks;
+ bool has_corruptions_fixed;
+ int64_t corruptions_fixed;
+ bool has_leaks_fixed;
+ int64_t leaks_fixed;
+ bool has_total_clusters;
+ int64_t total_clusters;
+ bool has_allocated_clusters;
+ int64_t allocated_clusters;
+ bool has_fragmented_clusters;
+ int64_t fragmented_clusters;
+ bool has_compressed_clusters;
+ int64_t compressed_clusters;
+};
+
+void qapi_free_ImageCheckList(ImageCheckList * obj);
+void qapi_free_ImageCheck(ImageCheck * obj);
+
+struct StatusInfo
+{
+ bool running;
+ bool singlestep;
+ RunState status;
+};
+
+void qapi_free_StatusInfoList(StatusInfoList * obj);
+void qapi_free_StatusInfo(StatusInfo * obj);
+
+struct UuidInfo
+{
+ char * UUID;
+};
+
+void qapi_free_UuidInfoList(UuidInfoList * obj);
+void qapi_free_UuidInfo(UuidInfo * obj);
+
+struct ChardevInfo
+{
+ char * label;
+ char * filename;
+};
+
+void qapi_free_ChardevInfoList(ChardevInfoList * obj);
+void qapi_free_ChardevInfo(ChardevInfo * obj);
+
+void qapi_free_DataFormatList(DataFormatList * obj);
+
+struct CommandInfo
+{
+ char * name;
+};
+
+void qapi_free_CommandInfoList(CommandInfoList * obj);
+void qapi_free_CommandInfo(CommandInfo * obj);
+
+struct EventInfo
+{
+ char * name;
+};
+
+void qapi_free_EventInfoList(EventInfoList * obj);
+void qapi_free_EventInfo(EventInfo * obj);
+
+struct MigrationStats
+{
+ int64_t transferred;
+ int64_t remaining;
+ int64_t total;
+ int64_t duplicate;
+ int64_t skipped;
+ int64_t normal;
+ int64_t normal_bytes;
+ int64_t dirty_pages_rate;
+ double mbps;
+};
+
+void qapi_free_MigrationStatsList(MigrationStatsList * obj);
+void qapi_free_MigrationStats(MigrationStats * obj);
+
+struct XBZRLECacheStats
+{
+ int64_t cache_size;
+ int64_t bytes;
+ int64_t pages;
+ int64_t cache_miss;
+ int64_t overflow;
+};
+
+void qapi_free_XBZRLECacheStatsList(XBZRLECacheStatsList * obj);
+void qapi_free_XBZRLECacheStats(XBZRLECacheStats * obj);
+
+struct MigrationInfo
+{
+ bool has_status;
+ char * status;
+ bool has_ram;
+ MigrationStats * ram;
+ bool has_disk;
+ MigrationStats * disk;
+ bool has_xbzrle_cache;
+ XBZRLECacheStats * xbzrle_cache;
+ bool has_total_time;
+ int64_t total_time;
+ bool has_expected_downtime;
+ int64_t expected_downtime;
+ bool has_downtime;
+ int64_t downtime;
+};
+
+void qapi_free_MigrationInfoList(MigrationInfoList * obj);
+void qapi_free_MigrationInfo(MigrationInfo * obj);
+
+void qapi_free_MigrationCapabilityList(MigrationCapabilityList * obj);
+
+struct MigrationCapabilityStatus
+{
+ MigrationCapability capability;
+ bool state;
+};
+
+void qapi_free_MigrationCapabilityStatusList(MigrationCapabilityStatusList * obj);
+void qapi_free_MigrationCapabilityStatus(MigrationCapabilityStatus * obj);
+
+struct MouseInfo
+{
+ char * name;
+ int64_t index;
+ bool current;
+ bool absolute;
+};
+
+void qapi_free_MouseInfoList(MouseInfoList * obj);
+void qapi_free_MouseInfo(MouseInfo * obj);
+
+struct CpuInfo
+{
+ int64_t CPU;
+ bool current;
+ bool halted;
+ bool has_pc;
+ int64_t pc;
+ bool has_nip;
+ int64_t nip;
+ bool has_npc;
+ int64_t npc;
+ bool has_PC;
+ int64_t PC;
+ int64_t thread_id;
+};
+
+void qapi_free_CpuInfoList(CpuInfoList * obj);
+void qapi_free_CpuInfo(CpuInfo * obj);
+
+struct BlockDeviceInfo
+{
+ char * file;
+ bool ro;
+ char * drv;
+ bool has_backing_file;
+ char * backing_file;
+ int64_t backing_file_depth;
+ bool encrypted;
+ bool encryption_key_missing;
+ int64_t bps;
+ int64_t bps_rd;
+ int64_t bps_wr;
+ int64_t iops;
+ int64_t iops_rd;
+ int64_t iops_wr;
+ ImageInfo * image;
+};
+
+void qapi_free_BlockDeviceInfoList(BlockDeviceInfoList * obj);
+void qapi_free_BlockDeviceInfo(BlockDeviceInfo * obj);
+
+void qapi_free_BlockDeviceIoStatusList(BlockDeviceIoStatusList * obj);
+
+struct BlockDirtyInfo
+{
+ int64_t count;
+ int64_t granularity;
+};
+
+void qapi_free_BlockDirtyInfoList(BlockDirtyInfoList * obj);
+void qapi_free_BlockDirtyInfo(BlockDirtyInfo * obj);
+
+struct BlockInfo
+{
+ char * device;
+ char * type;
+ bool removable;
+ bool locked;
+ bool has_inserted;
+ BlockDeviceInfo * inserted;
+ bool has_tray_open;
+ bool tray_open;
+ bool has_io_status;
+ BlockDeviceIoStatus io_status;
+ bool has_dirty;
+ BlockDirtyInfo * dirty;
+};
+
+void qapi_free_BlockInfoList(BlockInfoList * obj);
+void qapi_free_BlockInfo(BlockInfo * obj);
+
+struct BlockDeviceStats
+{
+ int64_t rd_bytes;
+ int64_t wr_bytes;
+ int64_t rd_operations;
+ int64_t wr_operations;
+ int64_t flush_operations;
+ int64_t flush_total_time_ns;
+ int64_t wr_total_time_ns;
+ int64_t rd_total_time_ns;
+ int64_t wr_highest_offset;
+};
+
+void qapi_free_BlockDeviceStatsList(BlockDeviceStatsList * obj);
+void qapi_free_BlockDeviceStats(BlockDeviceStats * obj);
+
+struct BlockStats
+{
+ bool has_device;
+ char * device;
+ BlockDeviceStats * stats;
+ bool has_parent;
+ BlockStats * parent;
+};
+
+void qapi_free_BlockStatsList(BlockStatsList * obj);
+void qapi_free_BlockStats(BlockStats * obj);
+
+struct VncClientInfo
+{
+ char * host;
+ char * family;
+ char * service;
+ bool has_x509_dname;
+ char * x509_dname;
+ bool has_sasl_username;
+ char * sasl_username;
+};
+
+void qapi_free_VncClientInfoList(VncClientInfoList * obj);
+void qapi_free_VncClientInfo(VncClientInfo * obj);
+
+struct VncInfo
+{
+ bool enabled;
+ bool has_host;
+ char * host;
+ bool has_family;
+ char * family;
+ bool has_service;
+ char * service;
+ bool has_auth;
+ char * auth;
+ bool has_clients;
+ VncClientInfoList * clients;
+};
+
+void qapi_free_VncInfoList(VncInfoList * obj);
+void qapi_free_VncInfo(VncInfo * obj);
+
+struct SpiceChannel
+{
+ char * host;
+ char * family;
+ char * port;
+ int64_t connection_id;
+ int64_t channel_type;
+ int64_t channel_id;
+ bool tls;
+};
+
+void qapi_free_SpiceChannelList(SpiceChannelList * obj);
+void qapi_free_SpiceChannel(SpiceChannel * obj);
+
+void qapi_free_SpiceQueryMouseModeList(SpiceQueryMouseModeList * obj);
+
+struct SpiceInfo
+{
+ bool enabled;
+ bool migrated;
+ bool has_host;
+ char * host;
+ bool has_port;
+ int64_t port;
+ bool has_tls_port;
+ int64_t tls_port;
+ bool has_auth;
+ char * auth;
+ bool has_compiled_version;
+ char * compiled_version;
+ SpiceQueryMouseMode mouse_mode;
+ bool has_channels;
+ SpiceChannelList * channels;
+};
+
+void qapi_free_SpiceInfoList(SpiceInfoList * obj);
+void qapi_free_SpiceInfo(SpiceInfo * obj);
+
+struct BalloonInfo
+{
+ int64_t actual;
+};
+
+void qapi_free_BalloonInfoList(BalloonInfoList * obj);
+void qapi_free_BalloonInfo(BalloonInfo * obj);
+
+struct PciMemoryRange
+{
+ int64_t base;
+ int64_t limit;
+};
+
+void qapi_free_PciMemoryRangeList(PciMemoryRangeList * obj);
+void qapi_free_PciMemoryRange(PciMemoryRange * obj);
+
+struct PciMemoryRegion
+{
+ int64_t bar;
+ char * type;
+ int64_t address;
+ int64_t size;
+ bool has_prefetch;
+ bool prefetch;
+ bool has_mem_type_64;
+ bool mem_type_64;
+};
+
+void qapi_free_PciMemoryRegionList(PciMemoryRegionList * obj);
+void qapi_free_PciMemoryRegion(PciMemoryRegion * obj);
+
+struct PciBridgeInfo
+{
+ struct
+ {
+ int64_t number;
+ int64_t secondary;
+ int64_t subordinate;
+ PciMemoryRange * io_range;
+ PciMemoryRange * memory_range;
+ PciMemoryRange * prefetchable_range;
+ } bus;
+ bool has_devices;
+ PciDeviceInfoList * devices;
+};
+
+void qapi_free_PciBridgeInfoList(PciBridgeInfoList * obj);
+void qapi_free_PciBridgeInfo(PciBridgeInfo * obj);
+
+struct PciDeviceInfo
+{
+ int64_t bus;
+ int64_t slot;
+ int64_t function;
+ struct
+ {
+ bool has_desc;
+ char * desc;
+ int64_t class;
+ } class_info;
+ struct
+ {
+ int64_t device;
+ int64_t vendor;
+ } id;
+ bool has_irq;
+ int64_t irq;
+ char * qdev_id;
+ bool has_pci_bridge;
+ PciBridgeInfo * pci_bridge;
+ PciMemoryRegionList * regions;
+};
+
+void qapi_free_PciDeviceInfoList(PciDeviceInfoList * obj);
+void qapi_free_PciDeviceInfo(PciDeviceInfo * obj);
+
+struct PciInfo
+{
+ int64_t bus;
+ PciDeviceInfoList * devices;
+};
+
+void qapi_free_PciInfoList(PciInfoList * obj);
+void qapi_free_PciInfo(PciInfo * obj);
+
+void qapi_free_BlockdevOnErrorList(BlockdevOnErrorList * obj);
+
+void qapi_free_MirrorSyncModeList(MirrorSyncModeList * obj);
+
+struct BlockJobInfo
+{
+ char * type;
+ char * device;
+ int64_t len;
+ int64_t offset;
+ bool busy;
+ bool paused;
+ int64_t speed;
+ BlockDeviceIoStatus io_status;
+};
+
+void qapi_free_BlockJobInfoList(BlockJobInfoList * obj);
+void qapi_free_BlockJobInfo(BlockJobInfo * obj);
+
+void qapi_free_NewImageModeList(NewImageModeList * obj);
+
+struct BlockdevSnapshot
+{
+ char * device;
+ char * snapshot_file;
+ bool has_format;
+ char * format;
+ bool has_mode;
+ NewImageMode mode;
+};
+
+void qapi_free_BlockdevSnapshotList(BlockdevSnapshotList * obj);
+void qapi_free_BlockdevSnapshot(BlockdevSnapshot * obj);
+
+struct DriveBackup
+{
+ char * device;
+ char * target;
+ bool has_format;
+ char * format;
+ MirrorSyncMode sync;
+ bool has_mode;
+ NewImageMode mode;
+ bool has_speed;
+ int64_t speed;
+ bool has_on_source_error;
+ BlockdevOnError on_source_error;
+ bool has_on_target_error;
+ BlockdevOnError on_target_error;
+};
+
+void qapi_free_DriveBackupList(DriveBackupList * obj);
+void qapi_free_DriveBackup(DriveBackup * obj);
+
+struct Abort
+{
+};
+
+void qapi_free_AbortList(AbortList * obj);
+void qapi_free_Abort(Abort * obj);
+
+struct TransactionAction
+{
+ TransactionActionKind kind;
+ union {
+ void *data;
+ BlockdevSnapshot * blockdev_snapshot_sync;
+ DriveBackup * drive_backup;
+ Abort * abort;
+ };
+};
+void qapi_free_TransactionActionList(TransactionActionList * obj);
+void qapi_free_TransactionAction(TransactionAction * obj);
+
+struct ObjectPropertyInfo
+{
+ char * name;
+ char * type;
+};
+
+void qapi_free_ObjectPropertyInfoList(ObjectPropertyInfoList * obj);
+void qapi_free_ObjectPropertyInfo(ObjectPropertyInfo * obj);
+
+struct ObjectTypeInfo
+{
+ char * name;
+};
+
+void qapi_free_ObjectTypeInfoList(ObjectTypeInfoList * obj);
+void qapi_free_ObjectTypeInfo(ObjectTypeInfo * obj);
+
+struct DevicePropertyInfo
+{
+ char * name;
+ char * type;
+};
+
+void qapi_free_DevicePropertyInfoList(DevicePropertyInfoList * obj);
+void qapi_free_DevicePropertyInfo(DevicePropertyInfo * obj);
+
+struct NetdevNoneOptions
+{
+};
+
+void qapi_free_NetdevNoneOptionsList(NetdevNoneOptionsList * obj);
+void qapi_free_NetdevNoneOptions(NetdevNoneOptions * obj);
+
+struct NetLegacyNicOptions
+{
+ bool has_netdev;
+ char * netdev;
+ bool has_macaddr;
+ char * macaddr;
+ bool has_model;
+ char * model;
+ bool has_addr;
+ char * addr;
+ bool has_vectors;
+ uint32_t vectors;
+};
+
+void qapi_free_NetLegacyNicOptionsList(NetLegacyNicOptionsList * obj);
+void qapi_free_NetLegacyNicOptions(NetLegacyNicOptions * obj);
+
+struct String
+{
+ char * str;
+};
+
+void qapi_free_StringList(StringList * obj);
+void qapi_free_String(String * obj);
+
+struct NetdevUserOptions
+{
+ bool has_hostname;
+ char * hostname;
+ bool has_q_restrict;
+ bool q_restrict;
+ bool has_ip;
+ char * ip;
+ bool has_net;
+ char * net;
+ bool has_host;
+ char * host;
+ bool has_tftp;
+ char * tftp;
+ bool has_bootfile;
+ char * bootfile;
+ bool has_dhcpstart;
+ char * dhcpstart;
+ bool has_dns;
+ char * dns;
+ bool has_dnssearch;
+ StringList * dnssearch;
+ bool has_smb;
+ char * smb;
+ bool has_smbserver;
+ char * smbserver;
+ bool has_hostfwd;
+ StringList * hostfwd;
+ bool has_guestfwd;
+ StringList * guestfwd;
+};
+
+void qapi_free_NetdevUserOptionsList(NetdevUserOptionsList * obj);
+void qapi_free_NetdevUserOptions(NetdevUserOptions * obj);
+
+struct NetdevTapOptions
+{
+ bool has_ifname;
+ char * ifname;
+ bool has_fd;
+ char * fd;
+ bool has_fds;
+ char * fds;
+ bool has_script;
+ char * script;
+ bool has_downscript;
+ char * downscript;
+ bool has_helper;
+ char * helper;
+ bool has_sndbuf;
+ uint64_t sndbuf;
+ bool has_vnet_hdr;
+ bool vnet_hdr;
+ bool has_vhost;
+ bool vhost;
+ bool has_vhostfd;
+ char * vhostfd;
+ bool has_vhostfds;
+ char * vhostfds;
+ bool has_vhostforce;
+ bool vhostforce;
+ bool has_queues;
+ uint32_t queues;
+};
+
+void qapi_free_NetdevTapOptionsList(NetdevTapOptionsList * obj);
+void qapi_free_NetdevTapOptions(NetdevTapOptions * obj);
+
+struct NetdevSocketOptions
+{
+ bool has_fd;
+ char * fd;
+ bool has_listen;
+ char * listen;
+ bool has_connect;
+ char * connect;
+ bool has_mcast;
+ char * mcast;
+ bool has_localaddr;
+ char * localaddr;
+ bool has_udp;
+ char * udp;
+};
+
+void qapi_free_NetdevSocketOptionsList(NetdevSocketOptionsList * obj);
+void qapi_free_NetdevSocketOptions(NetdevSocketOptions * obj);
+
+struct NetdevVdeOptions
+{
+ bool has_sock;
+ char * sock;
+ bool has_port;
+ uint16_t port;
+ bool has_group;
+ char * group;
+ bool has_mode;
+ uint16_t mode;
+};
+
+void qapi_free_NetdevVdeOptionsList(NetdevVdeOptionsList * obj);
+void qapi_free_NetdevVdeOptions(NetdevVdeOptions * obj);
+
+struct NetdevDumpOptions
+{
+ bool has_len;
+ uint64_t len;
+ bool has_file;
+ char * file;
+};
+
+void qapi_free_NetdevDumpOptionsList(NetdevDumpOptionsList * obj);
+void qapi_free_NetdevDumpOptions(NetdevDumpOptions * obj);
+
+struct NetdevBridgeOptions
+{
+ bool has_br;
+ char * br;
+ bool has_helper;
+ char * helper;
+};
+
+void qapi_free_NetdevBridgeOptionsList(NetdevBridgeOptionsList * obj);
+void qapi_free_NetdevBridgeOptions(NetdevBridgeOptions * obj);
+
+struct NetdevHubPortOptions
+{
+ int32_t hubid;
+};
+
+void qapi_free_NetdevHubPortOptionsList(NetdevHubPortOptionsList * obj);
+void qapi_free_NetdevHubPortOptions(NetdevHubPortOptions * obj);
+
+struct NetClientOptions
+{
+ NetClientOptionsKind kind;
+ union {
+ void *data;
+ NetdevNoneOptions * none;
+ NetLegacyNicOptions * nic;
+ NetdevUserOptions * user;
+ NetdevTapOptions * tap;
+ NetdevSocketOptions * socket;
+ NetdevVdeOptions * vde;
+ NetdevDumpOptions * dump;
+ NetdevBridgeOptions * bridge;
+ NetdevHubPortOptions * hubport;
+ };
+};
+void qapi_free_NetClientOptionsList(NetClientOptionsList * obj);
+void qapi_free_NetClientOptions(NetClientOptions * obj);
+
+struct NetLegacy
+{
+ bool has_vlan;
+ int32_t vlan;
+ bool has_id;
+ char * id;
+ bool has_name;
+ char * name;
+ NetClientOptions * opts;
+};
+
+void qapi_free_NetLegacyList(NetLegacyList * obj);
+void qapi_free_NetLegacy(NetLegacy * obj);
+
+struct Netdev
+{
+ char * id;
+ NetClientOptions * opts;
+};
+
+void qapi_free_NetdevList(NetdevList * obj);
+void qapi_free_Netdev(Netdev * obj);
+
+struct InetSocketAddress
+{
+ char * host;
+ char * port;
+ bool has_to;
+ uint16_t to;
+ bool has_ipv4;
+ bool ipv4;
+ bool has_ipv6;
+ bool ipv6;
+};
+
+void qapi_free_InetSocketAddressList(InetSocketAddressList * obj);
+void qapi_free_InetSocketAddress(InetSocketAddress * obj);
+
+struct UnixSocketAddress
+{
+ char * path;
+};
+
+void qapi_free_UnixSocketAddressList(UnixSocketAddressList * obj);
+void qapi_free_UnixSocketAddress(UnixSocketAddress * obj);
+
+struct SocketAddress
+{
+ SocketAddressKind kind;
+ union {
+ void *data;
+ InetSocketAddress * inet;
+ UnixSocketAddress * q_unix;
+ String * fd;
+ };
+};
+void qapi_free_SocketAddressList(SocketAddressList * obj);
+void qapi_free_SocketAddress(SocketAddress * obj);
+
+struct MachineInfo
+{
+ char * name;
+ bool has_alias;
+ char * alias;
+ bool has_is_default;
+ bool is_default;
+ int64_t cpu_max;
+};
+
+void qapi_free_MachineInfoList(MachineInfoList * obj);
+void qapi_free_MachineInfo(MachineInfo * obj);
+
+struct CpuDefinitionInfo
+{
+ char * name;
+};
+
+void qapi_free_CpuDefinitionInfoList(CpuDefinitionInfoList * obj);
+void qapi_free_CpuDefinitionInfo(CpuDefinitionInfo * obj);
+
+struct AddfdInfo
+{
+ int64_t fdset_id;
+ int64_t fd;
+};
+
+void qapi_free_AddfdInfoList(AddfdInfoList * obj);
+void qapi_free_AddfdInfo(AddfdInfo * obj);
+
+struct FdsetFdInfo
+{
+ int64_t fd;
+ bool has_opaque;
+ char * opaque;
+};
+
+void qapi_free_FdsetFdInfoList(FdsetFdInfoList * obj);
+void qapi_free_FdsetFdInfo(FdsetFdInfo * obj);
+
+struct FdsetInfo
+{
+ int64_t fdset_id;
+ FdsetFdInfoList * fds;
+};
+
+void qapi_free_FdsetInfoList(FdsetInfoList * obj);
+void qapi_free_FdsetInfo(FdsetInfo * obj);
+
+struct TargetInfo
+{
+ char * arch;
+};
+
+void qapi_free_TargetInfoList(TargetInfoList * obj);
+void qapi_free_TargetInfo(TargetInfo * obj);
+
+void qapi_free_QKeyCodeList(QKeyCodeList * obj);
+
+struct KeyValue
+{
+ KeyValueKind kind;
+ union {
+ void *data;
+ int64_t number;
+ QKeyCode qcode;
+ };
+};
+void qapi_free_KeyValueList(KeyValueList * obj);
+void qapi_free_KeyValue(KeyValue * obj);
+
+struct ChardevFile
+{
+ bool has_in;
+ char * in;
+ char * out;
+};
+
+void qapi_free_ChardevFileList(ChardevFileList * obj);
+void qapi_free_ChardevFile(ChardevFile * obj);
+
+struct ChardevHostdev
+{
+ char * device;
+};
+
+void qapi_free_ChardevHostdevList(ChardevHostdevList * obj);
+void qapi_free_ChardevHostdev(ChardevHostdev * obj);
+
+struct ChardevSocket
+{
+ SocketAddress * addr;
+ bool has_server;
+ bool server;
+ bool has_wait;
+ bool wait;
+ bool has_nodelay;
+ bool nodelay;
+ bool has_telnet;
+ bool telnet;
+};
+
+void qapi_free_ChardevSocketList(ChardevSocketList * obj);
+void qapi_free_ChardevSocket(ChardevSocket * obj);
+
+struct ChardevUdp
+{
+ SocketAddress * remote;
+ bool has_local;
+ SocketAddress * local;
+};
+
+void qapi_free_ChardevUdpList(ChardevUdpList * obj);
+void qapi_free_ChardevUdp(ChardevUdp * obj);
+
+struct ChardevMux
+{
+ char * chardev;
+};
+
+void qapi_free_ChardevMuxList(ChardevMuxList * obj);
+void qapi_free_ChardevMux(ChardevMux * obj);
+
+struct ChardevStdio
+{
+ bool has_signal;
+ bool signal;
+};
+
+void qapi_free_ChardevStdioList(ChardevStdioList * obj);
+void qapi_free_ChardevStdio(ChardevStdio * obj);
+
+struct ChardevSpiceChannel
+{
+ char * type;
+};
+
+void qapi_free_ChardevSpiceChannelList(ChardevSpiceChannelList * obj);
+void qapi_free_ChardevSpiceChannel(ChardevSpiceChannel * obj);
+
+struct ChardevSpicePort
+{
+ char * fqdn;
+};
+
+void qapi_free_ChardevSpicePortList(ChardevSpicePortList * obj);
+void qapi_free_ChardevSpicePort(ChardevSpicePort * obj);
+
+struct ChardevVC
+{
+ bool has_width;
+ int64_t width;
+ bool has_height;
+ int64_t height;
+ bool has_cols;
+ int64_t cols;
+ bool has_rows;
+ int64_t rows;
+};
+
+void qapi_free_ChardevVCList(ChardevVCList * obj);
+void qapi_free_ChardevVC(ChardevVC * obj);
+
+struct ChardevMemory
+{
+ bool has_size;
+ int64_t size;
+};
+
+void qapi_free_ChardevMemoryList(ChardevMemoryList * obj);
+void qapi_free_ChardevMemory(ChardevMemory * obj);
+
+struct ChardevDummy
+{
+};
+
+void qapi_free_ChardevDummyList(ChardevDummyList * obj);
+void qapi_free_ChardevDummy(ChardevDummy * obj);
+
+struct ChardevBackend
+{
+ ChardevBackendKind kind;
+ union {
+ void *data;
+ ChardevFile * file;
+ ChardevHostdev * serial;
+ ChardevHostdev * parallel;
+ ChardevHostdev * pipe;
+ ChardevSocket * socket;
+ ChardevUdp * udp;
+ ChardevDummy * pty;
+ ChardevDummy * null;
+ ChardevMux * mux;
+ ChardevDummy * msmouse;
+ ChardevDummy * braille;
+ ChardevStdio * stdio;
+ ChardevDummy * console;
+ ChardevSpiceChannel * spicevmc;
+ ChardevSpicePort * spiceport;
+ ChardevVC * vc;
+ ChardevMemory * memory;
+ };
+};
+void qapi_free_ChardevBackendList(ChardevBackendList * obj);
+void qapi_free_ChardevBackend(ChardevBackend * obj);
+
+struct ChardevReturn
+{
+ bool has_pty;
+ char * pty;
+};
+
+void qapi_free_ChardevReturnList(ChardevReturnList * obj);
+void qapi_free_ChardevReturn(ChardevReturn * obj);
+
+void qapi_free_TpmModelList(TpmModelList * obj);
+
+void qapi_free_TpmTypeList(TpmTypeList * obj);
+
+struct TPMPassthroughOptions
+{
+ bool has_path;
+ char * path;
+ bool has_cancel_path;
+ char * cancel_path;
+};
+
+void qapi_free_TPMPassthroughOptionsList(TPMPassthroughOptionsList * obj);
+void qapi_free_TPMPassthroughOptions(TPMPassthroughOptions * obj);
+
+struct TpmTypeOptions
+{
+ TpmTypeOptionsKind kind;
+ union {
+ void *data;
+ TPMPassthroughOptions * passthrough;
+ };
+};
+void qapi_free_TpmTypeOptionsList(TpmTypeOptionsList * obj);
+void qapi_free_TpmTypeOptions(TpmTypeOptions * obj);
+
+struct TPMInfo
+{
+ char * id;
+ TpmModel model;
+ TpmTypeOptions * options;
+};
+
+void qapi_free_TPMInfoList(TPMInfoList * obj);
+void qapi_free_TPMInfo(TPMInfo * obj);
+
+struct AcpiTableOptions
+{
+ bool has_sig;
+ char * sig;
+ bool has_rev;
+ uint8_t rev;
+ bool has_oem_id;
+ char * oem_id;
+ bool has_oem_table_id;
+ char * oem_table_id;
+ bool has_oem_rev;
+ uint32_t oem_rev;
+ bool has_asl_compiler_id;
+ char * asl_compiler_id;
+ bool has_asl_compiler_rev;
+ uint32_t asl_compiler_rev;
+ bool has_file;
+ char * file;
+ bool has_data;
+ char * data;
+};
+
+void qapi_free_AcpiTableOptionsList(AcpiTableOptionsList * obj);
+void qapi_free_AcpiTableOptions(AcpiTableOptions * obj);
+
+void qapi_free_CommandLineParameterTypeList(CommandLineParameterTypeList * obj);
+
+struct CommandLineParameterInfo
+{
+ char * name;
+ CommandLineParameterType type;
+ bool has_help;
+ char * help;
+};
+
+void qapi_free_CommandLineParameterInfoList(CommandLineParameterInfoList * obj);
+void qapi_free_CommandLineParameterInfo(CommandLineParameterInfo * obj);
+
+struct CommandLineOptionInfo
+{
+ char * option;
+ CommandLineParameterInfoList * parameters;
+};
+
+void qapi_free_CommandLineOptionInfoList(CommandLineOptionInfoList * obj);
+void qapi_free_CommandLineOptionInfo(CommandLineOptionInfo * obj);
+
+void qapi_free_X86CPURegister32List(X86CPURegister32List * obj);
+
+struct X86CPUFeatureWordInfo
+{
+ int64_t cpuid_input_eax;
+ bool has_cpuid_input_ecx;
+ int64_t cpuid_input_ecx;
+ X86CPURegister32 cpuid_register;
+ int64_t features;
+};
+
+void qapi_free_X86CPUFeatureWordInfoList(X86CPUFeatureWordInfoList * obj);
+void qapi_free_X86CPUFeatureWordInfo(X86CPUFeatureWordInfo * obj);
+
+void qapi_free_RxStateList(RxStateList * obj);
+
+struct RxFilterInfo
+{
+ char * name;
+ bool promiscuous;
+ RxState multicast;
+ RxState unicast;
+ bool broadcast_allowed;
+ bool multicast_overflow;
+ bool unicast_overflow;
+ char * main_mac;
+ intList * vlan_table;
+ strList * unicast_table;
+ strList * multicast_table;
+};
+
+void qapi_free_RxFilterInfoList(RxFilterInfoList * obj);
+void qapi_free_RxFilterInfo(RxFilterInfo * obj);
+
+#endif
diff --git a/contrib/qemu/qemu-coroutine-lock.c b/contrib/qemu/qemu-coroutine-lock.c
new file mode 100644
index 00000000000..d9fea4989d4
--- /dev/null
+++ b/contrib/qemu/qemu-coroutine-lock.c
@@ -0,0 +1,178 @@
+/*
+ * coroutine queues and locks
+ *
+ * Copyright (c) 2011 Kevin Wolf <kwolf@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu-common.h"
+#include "block/coroutine.h"
+#include "block/coroutine_int.h"
+#include "qemu/queue.h"
+#include "trace.h"
+
+void qemu_co_queue_init(CoQueue *queue)
+{
+ QTAILQ_INIT(&queue->entries);
+}
+
+void coroutine_fn qemu_co_queue_wait(CoQueue *queue)
+{
+ Coroutine *self = qemu_coroutine_self();
+ QTAILQ_INSERT_TAIL(&queue->entries, self, co_queue_next);
+ qemu_coroutine_yield();
+ assert(qemu_in_coroutine());
+}
+
+void coroutine_fn qemu_co_queue_wait_insert_head(CoQueue *queue)
+{
+ Coroutine *self = qemu_coroutine_self();
+ QTAILQ_INSERT_HEAD(&queue->entries, self, co_queue_next);
+ qemu_coroutine_yield();
+ assert(qemu_in_coroutine());
+}
+
+/**
+ * qemu_co_queue_run_restart:
+ *
+ * Enter each coroutine that was previously marked for restart by
+ * qemu_co_queue_next() or qemu_co_queue_restart_all(). This function is
+ * invoked by the core coroutine code when the current coroutine yields or
+ * terminates.
+ */
+void qemu_co_queue_run_restart(Coroutine *co)
+{
+ Coroutine *next;
+
+ trace_qemu_co_queue_run_restart(co);
+ while ((next = QTAILQ_FIRST(&co->co_queue_wakeup))) {
+ QTAILQ_REMOVE(&co->co_queue_wakeup, next, co_queue_next);
+ qemu_coroutine_enter(next, NULL);
+ }
+}
+
+static bool qemu_co_queue_do_restart(CoQueue *queue, bool single)
+{
+ Coroutine *self = qemu_coroutine_self();
+ Coroutine *next;
+
+ if (QTAILQ_EMPTY(&queue->entries)) {
+ return false;
+ }
+
+ while ((next = QTAILQ_FIRST(&queue->entries)) != NULL) {
+ QTAILQ_REMOVE(&queue->entries, next, co_queue_next);
+ QTAILQ_INSERT_TAIL(&self->co_queue_wakeup, next, co_queue_next);
+ trace_qemu_co_queue_next(next);
+ if (single) {
+ break;
+ }
+ }
+ return true;
+}
+
+bool qemu_co_queue_next(CoQueue *queue)
+{
+ return qemu_co_queue_do_restart(queue, true);
+}
+
+void qemu_co_queue_restart_all(CoQueue *queue)
+{
+ qemu_co_queue_do_restart(queue, false);
+}
+
+bool qemu_co_queue_empty(CoQueue *queue)
+{
+ return (QTAILQ_FIRST(&queue->entries) == NULL);
+}
+
+void qemu_co_mutex_init(CoMutex *mutex)
+{
+ memset(mutex, 0, sizeof(*mutex));
+ qemu_co_queue_init(&mutex->queue);
+}
+
+void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex)
+{
+ Coroutine *self = qemu_coroutine_self();
+
+ trace_qemu_co_mutex_lock_entry(mutex, self);
+
+ while (mutex->locked) {
+ qemu_co_queue_wait(&mutex->queue);
+ }
+
+ mutex->locked = true;
+
+ trace_qemu_co_mutex_lock_return(mutex, self);
+}
+
+void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex)
+{
+ Coroutine *self = qemu_coroutine_self();
+
+ trace_qemu_co_mutex_unlock_entry(mutex, self);
+
+ assert(mutex->locked == true);
+ assert(qemu_in_coroutine());
+
+ mutex->locked = false;
+ qemu_co_queue_next(&mutex->queue);
+
+ trace_qemu_co_mutex_unlock_return(mutex, self);
+}
+
+void qemu_co_rwlock_init(CoRwlock *lock)
+{
+ memset(lock, 0, sizeof(*lock));
+ qemu_co_queue_init(&lock->queue);
+}
+
+void qemu_co_rwlock_rdlock(CoRwlock *lock)
+{
+ while (lock->writer) {
+ qemu_co_queue_wait(&lock->queue);
+ }
+ lock->reader++;
+}
+
+void qemu_co_rwlock_unlock(CoRwlock *lock)
+{
+ assert(qemu_in_coroutine());
+ if (lock->writer) {
+ lock->writer = false;
+ qemu_co_queue_restart_all(&lock->queue);
+ } else {
+ lock->reader--;
+ assert(lock->reader >= 0);
+ /* Wakeup only one waiting writer */
+ if (!lock->reader) {
+ qemu_co_queue_next(&lock->queue);
+ }
+ }
+}
+
+void qemu_co_rwlock_wrlock(CoRwlock *lock)
+{
+ while (lock->writer || lock->reader) {
+ qemu_co_queue_wait(&lock->queue);
+ }
+ lock->writer = true;
+}
diff --git a/contrib/qemu/qemu-coroutine-sleep.c b/contrib/qemu/qemu-coroutine-sleep.c
new file mode 100644
index 00000000000..169ce5ccc92
--- /dev/null
+++ b/contrib/qemu/qemu-coroutine-sleep.c
@@ -0,0 +1,39 @@
+/*
+ * QEMU coroutine sleep
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "block/coroutine.h"
+#include "qemu/timer.h"
+
+typedef struct CoSleepCB {
+ QEMUTimer *ts;
+ Coroutine *co;
+} CoSleepCB;
+
+static void co_sleep_cb(void *opaque)
+{
+ CoSleepCB *sleep_cb = opaque;
+
+ qemu_coroutine_enter(sleep_cb->co, NULL);
+}
+
+void coroutine_fn co_sleep_ns(QEMUClock *clock, int64_t ns)
+{
+ CoSleepCB sleep_cb = {
+ .co = qemu_coroutine_self(),
+ };
+ sleep_cb.ts = qemu_new_timer(clock, SCALE_NS, co_sleep_cb, &sleep_cb);
+ qemu_mod_timer(sleep_cb.ts, qemu_get_clock_ns(clock) + ns);
+ qemu_coroutine_yield();
+ qemu_del_timer(sleep_cb.ts);
+ qemu_free_timer(sleep_cb.ts);
+}
diff --git a/contrib/qemu/qemu-coroutine.c b/contrib/qemu/qemu-coroutine.c
new file mode 100644
index 00000000000..423430d3a03
--- /dev/null
+++ b/contrib/qemu/qemu-coroutine.c
@@ -0,0 +1,135 @@
+/*
+ * QEMU coroutines
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Kevin Wolf <kwolf@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "trace.h"
+#include "qemu-common.h"
+#include "qemu/thread.h"
+#include "block/coroutine.h"
+#include "block/coroutine_int.h"
+
+enum {
+ /* Maximum free pool size prevents holding too many freed coroutines */
+ POOL_MAX_SIZE = 64,
+};
+
+/** Free list to speed up creation */
+static QemuMutex pool_lock;
+static QSLIST_HEAD(, Coroutine) pool = QSLIST_HEAD_INITIALIZER(pool);
+static unsigned int pool_size;
+
+Coroutine *qemu_coroutine_create(CoroutineEntry *entry)
+{
+ Coroutine *co;
+
+ qemu_mutex_lock(&pool_lock);
+ co = QSLIST_FIRST(&pool);
+ if (co) {
+ QSLIST_REMOVE_HEAD(&pool, pool_next);
+ pool_size--;
+ }
+ qemu_mutex_unlock(&pool_lock);
+
+ if (!co) {
+ co = qemu_coroutine_new();
+ }
+
+ co->entry = entry;
+ QTAILQ_INIT(&co->co_queue_wakeup);
+ return co;
+}
+
+static void coroutine_delete(Coroutine *co)
+{
+ qemu_mutex_lock(&pool_lock);
+ if (pool_size < POOL_MAX_SIZE) {
+ QSLIST_INSERT_HEAD(&pool, co, pool_next);
+ co->caller = NULL;
+ pool_size++;
+ qemu_mutex_unlock(&pool_lock);
+ return;
+ }
+ qemu_mutex_unlock(&pool_lock);
+
+ qemu_coroutine_delete(co);
+}
+
+static void __attribute__((constructor)) coroutine_pool_init(void)
+{
+ qemu_mutex_init(&pool_lock);
+}
+
+static void __attribute__((destructor)) coroutine_pool_cleanup(void)
+{
+ Coroutine *co;
+ Coroutine *tmp;
+
+ QSLIST_FOREACH_SAFE(co, &pool, pool_next, tmp) {
+ QSLIST_REMOVE_HEAD(&pool, pool_next);
+ qemu_coroutine_delete(co);
+ }
+
+ qemu_mutex_destroy(&pool_lock);
+}
+
+static void coroutine_swap(Coroutine *from, Coroutine *to)
+{
+ CoroutineAction ret;
+
+ ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
+
+ qemu_co_queue_run_restart(to);
+
+ switch (ret) {
+ case COROUTINE_YIELD:
+ return;
+ case COROUTINE_TERMINATE:
+ trace_qemu_coroutine_terminate(to);
+ coroutine_delete(to);
+ return;
+ default:
+ abort();
+ }
+}
+
+void qemu_coroutine_enter(Coroutine *co, void *opaque)
+{
+ Coroutine *self = qemu_coroutine_self();
+
+ trace_qemu_coroutine_enter(self, co, opaque);
+
+ if (co->caller) {
+ fprintf(stderr, "Co-routine re-entered recursively\n");
+ abort();
+ }
+
+ co->caller = self;
+ co->entry_arg = opaque;
+ coroutine_swap(self, co);
+}
+
+void coroutine_fn qemu_coroutine_yield(void)
+{
+ Coroutine *self = qemu_coroutine_self();
+ Coroutine *to = self->caller;
+
+ trace_qemu_coroutine_yield(self, to);
+
+ if (!to) {
+ fprintf(stderr, "Co-routine is yielding to no one\n");
+ abort();
+ }
+
+ self->caller = NULL;
+ coroutine_swap(self, to);
+}
diff --git a/contrib/qemu/qmp-commands.h b/contrib/qemu/qmp-commands.h
new file mode 100644
index 00000000000..fcc0ff0f7f0
--- /dev/null
+++ b/contrib/qemu/qmp-commands.h
@@ -0,0 +1,204 @@
+/* THIS FILE IS AUTOMATICALLY GENERATED, DO NOT MODIFY */
+
+/*
+ * schema-defined QAPI function prototypes
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef QMP_COMMANDS_H
+#define QMP_COMMANDS_H
+
+#include "qapi-types.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/error.h"
+
+void qmp_add_client(const char * protocol, const char * fdname, bool has_skipauth, bool skipauth, bool has_tls, bool tls, Error **errp);
+int qmp_marshal_input_add_client(Monitor *mon, const QDict *qdict, QObject **ret);
+NameInfo * qmp_query_name(Error **errp);
+int qmp_marshal_input_query_name(Monitor *mon, const QDict *qdict, QObject **ret);
+VersionInfo * qmp_query_version(Error **errp);
+int qmp_marshal_input_query_version(Monitor *mon, const QDict *qdict, QObject **ret);
+KvmInfo * qmp_query_kvm(Error **errp);
+int qmp_marshal_input_query_kvm(Monitor *mon, const QDict *qdict, QObject **ret);
+StatusInfo * qmp_query_status(Error **errp);
+int qmp_marshal_input_query_status(Monitor *mon, const QDict *qdict, QObject **ret);
+UuidInfo * qmp_query_uuid(Error **errp);
+int qmp_marshal_input_query_uuid(Monitor *mon, const QDict *qdict, QObject **ret);
+ChardevInfoList * qmp_query_chardev(Error **errp);
+int qmp_marshal_input_query_chardev(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_ringbuf_write(const char * device, const char * data, bool has_format, DataFormat format, Error **errp);
+int qmp_marshal_input_ringbuf_write(Monitor *mon, const QDict *qdict, QObject **ret);
+char * qmp_ringbuf_read(const char * device, int64_t size, bool has_format, DataFormat format, Error **errp);
+int qmp_marshal_input_ringbuf_read(Monitor *mon, const QDict *qdict, QObject **ret);
+CommandInfoList * qmp_query_commands(Error **errp);
+int qmp_marshal_input_query_commands(Monitor *mon, const QDict *qdict, QObject **ret);
+EventInfoList * qmp_query_events(Error **errp);
+int qmp_marshal_input_query_events(Monitor *mon, const QDict *qdict, QObject **ret);
+MigrationInfo * qmp_query_migrate(Error **errp);
+int qmp_marshal_input_query_migrate(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_migrate_set_capabilities(MigrationCapabilityStatusList * capabilities, Error **errp);
+int qmp_marshal_input_migrate_set_capabilities(Monitor *mon, const QDict *qdict, QObject **ret);
+MigrationCapabilityStatusList * qmp_query_migrate_capabilities(Error **errp);
+int qmp_marshal_input_query_migrate_capabilities(Monitor *mon, const QDict *qdict, QObject **ret);
+MouseInfoList * qmp_query_mice(Error **errp);
+int qmp_marshal_input_query_mice(Monitor *mon, const QDict *qdict, QObject **ret);
+CpuInfoList * qmp_query_cpus(Error **errp);
+int qmp_marshal_input_query_cpus(Monitor *mon, const QDict *qdict, QObject **ret);
+BlockInfoList * qmp_query_block(Error **errp);
+int qmp_marshal_input_query_block(Monitor *mon, const QDict *qdict, QObject **ret);
+BlockStatsList * qmp_query_blockstats(Error **errp);
+int qmp_marshal_input_query_blockstats(Monitor *mon, const QDict *qdict, QObject **ret);
+VncInfo * qmp_query_vnc(Error **errp);
+int qmp_marshal_input_query_vnc(Monitor *mon, const QDict *qdict, QObject **ret);
+SpiceInfo * qmp_query_spice(Error **errp);
+int qmp_marshal_input_query_spice(Monitor *mon, const QDict *qdict, QObject **ret);
+BalloonInfo * qmp_query_balloon(Error **errp);
+int qmp_marshal_input_query_balloon(Monitor *mon, const QDict *qdict, QObject **ret);
+PciInfoList * qmp_query_pci(Error **errp);
+int qmp_marshal_input_query_pci(Monitor *mon, const QDict *qdict, QObject **ret);
+BlockJobInfoList * qmp_query_block_jobs(Error **errp);
+int qmp_marshal_input_query_block_jobs(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_quit(Error **errp);
+int qmp_marshal_input_quit(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_stop(Error **errp);
+int qmp_marshal_input_stop(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_system_reset(Error **errp);
+int qmp_marshal_input_system_reset(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_system_powerdown(Error **errp);
+int qmp_marshal_input_system_powerdown(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_cpu(int64_t index, Error **errp);
+int qmp_marshal_input_cpu(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_cpu_add(int64_t id, Error **errp);
+int qmp_marshal_input_cpu_add(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_memsave(int64_t val, int64_t size, const char * filename, bool has_cpu_index, int64_t cpu_index, Error **errp);
+int qmp_marshal_input_memsave(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_pmemsave(int64_t val, int64_t size, const char * filename, Error **errp);
+int qmp_marshal_input_pmemsave(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_cont(Error **errp);
+int qmp_marshal_input_cont(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_system_wakeup(Error **errp);
+int qmp_marshal_input_system_wakeup(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_inject_nmi(Error **errp);
+int qmp_marshal_input_inject_nmi(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_set_link(const char * name, bool up, Error **errp);
+int qmp_marshal_input_set_link(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_passwd(const char * device, const char * password, Error **errp);
+int qmp_marshal_input_block_passwd(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_balloon(int64_t value, Error **errp);
+int qmp_marshal_input_balloon(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_resize(const char * device, int64_t size, Error **errp);
+int qmp_marshal_input_block_resize(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_transaction(TransactionActionList * actions, Error **errp);
+int qmp_marshal_input_transaction(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_blockdev_snapshot_sync(const char * device, const char * snapshot_file, bool has_format, const char * format, bool has_mode, NewImageMode mode, Error **errp);
+int qmp_marshal_input_blockdev_snapshot_sync(Monitor *mon, const QDict *qdict, QObject **ret);
+char * qmp_human_monitor_command(const char * command_line, bool has_cpu_index, int64_t cpu_index, Error **errp);
+int qmp_marshal_input_human_monitor_command(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_commit(const char * device, bool has_base, const char * base, const char * top, bool has_speed, int64_t speed, Error **errp);
+int qmp_marshal_input_block_commit(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_drive_backup(const char * device, const char * target, bool has_format, const char * format, MirrorSyncMode sync, bool has_mode, NewImageMode mode, bool has_speed, int64_t speed, bool has_on_source_error, BlockdevOnError on_source_error, bool has_on_target_error, BlockdevOnError on_target_error, Error **errp);
+int qmp_marshal_input_drive_backup(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_drive_mirror(const char * device, const char * target, bool has_format, const char * format, MirrorSyncMode sync, bool has_mode, NewImageMode mode, bool has_speed, int64_t speed, bool has_granularity, uint32_t granularity, bool has_buf_size, int64_t buf_size, bool has_on_source_error, BlockdevOnError on_source_error, bool has_on_target_error, BlockdevOnError on_target_error, Error **errp);
+int qmp_marshal_input_drive_mirror(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_migrate_cancel(Error **errp);
+int qmp_marshal_input_migrate_cancel(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_migrate_set_downtime(double value, Error **errp);
+int qmp_marshal_input_migrate_set_downtime(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_migrate_set_speed(int64_t value, Error **errp);
+int qmp_marshal_input_migrate_set_speed(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_migrate_set_cache_size(int64_t value, Error **errp);
+int qmp_marshal_input_migrate_set_cache_size(Monitor *mon, const QDict *qdict, QObject **ret);
+int64_t qmp_query_migrate_cache_size(Error **errp);
+int qmp_marshal_input_query_migrate_cache_size(Monitor *mon, const QDict *qdict, QObject **ret);
+ObjectPropertyInfoList * qmp_qom_list(const char * path, Error **errp);
+int qmp_marshal_input_qom_list(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_set_password(const char * protocol, const char * password, bool has_connected, const char * connected, Error **errp);
+int qmp_marshal_input_set_password(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_expire_password(const char * protocol, const char * time, Error **errp);
+int qmp_marshal_input_expire_password(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_eject(const char * device, bool has_force, bool force, Error **errp);
+int qmp_marshal_input_eject(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_change_vnc_password(const char * password, Error **errp);
+int qmp_marshal_input_change_vnc_password(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_change(const char * device, const char * target, bool has_arg, const char * arg, Error **errp);
+int qmp_marshal_input_change(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_set_io_throttle(const char * device, int64_t bps, int64_t bps_rd, int64_t bps_wr, int64_t iops, int64_t iops_rd, int64_t iops_wr, Error **errp);
+int qmp_marshal_input_block_set_io_throttle(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_stream(const char * device, bool has_base, const char * base, bool has_speed, int64_t speed, bool has_on_error, BlockdevOnError on_error, Error **errp);
+int qmp_marshal_input_block_stream(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_job_set_speed(const char * device, int64_t speed, Error **errp);
+int qmp_marshal_input_block_job_set_speed(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_job_cancel(const char * device, bool has_force, bool force, Error **errp);
+int qmp_marshal_input_block_job_cancel(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_job_pause(const char * device, Error **errp);
+int qmp_marshal_input_block_job_pause(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_job_resume(const char * device, Error **errp);
+int qmp_marshal_input_block_job_resume(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_block_job_complete(const char * device, Error **errp);
+int qmp_marshal_input_block_job_complete(Monitor *mon, const QDict *qdict, QObject **ret);
+ObjectTypeInfoList * qmp_qom_list_types(bool has_implements, const char * implements, bool has_abstract, bool abstract, Error **errp);
+int qmp_marshal_input_qom_list_types(Monitor *mon, const QDict *qdict, QObject **ret);
+DevicePropertyInfoList * qmp_device_list_properties(const char * typename, Error **errp);
+int qmp_marshal_input_device_list_properties(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_migrate(const char * uri, bool has_blk, bool blk, bool has_inc, bool inc, bool has_detach, bool detach, Error **errp);
+int qmp_marshal_input_migrate(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_xen_save_devices_state(const char * filename, Error **errp);
+int qmp_marshal_input_xen_save_devices_state(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_xen_set_global_dirty_log(bool enable, Error **errp);
+int qmp_marshal_input_xen_set_global_dirty_log(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_device_del(const char * id, Error **errp);
+int qmp_marshal_input_device_del(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_dump_guest_memory(bool paging, const char * protocol, bool has_begin, int64_t begin, bool has_length, int64_t length, Error **errp);
+int qmp_marshal_input_dump_guest_memory(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_netdev_del(const char * id, Error **errp);
+int qmp_marshal_input_netdev_del(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_getfd(const char * fdname, Error **errp);
+int qmp_marshal_input_getfd(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_closefd(const char * fdname, Error **errp);
+int qmp_marshal_input_closefd(Monitor *mon, const QDict *qdict, QObject **ret);
+MachineInfoList * qmp_query_machines(Error **errp);
+int qmp_marshal_input_query_machines(Monitor *mon, const QDict *qdict, QObject **ret);
+CpuDefinitionInfoList * qmp_query_cpu_definitions(Error **errp);
+int qmp_marshal_input_query_cpu_definitions(Monitor *mon, const QDict *qdict, QObject **ret);
+AddfdInfo * qmp_add_fd(bool has_fdset_id, int64_t fdset_id, bool has_opaque, const char * opaque, Error **errp);
+int qmp_marshal_input_add_fd(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_remove_fd(int64_t fdset_id, bool has_fd, int64_t fd, Error **errp);
+int qmp_marshal_input_remove_fd(Monitor *mon, const QDict *qdict, QObject **ret);
+FdsetInfoList * qmp_query_fdsets(Error **errp);
+int qmp_marshal_input_query_fdsets(Monitor *mon, const QDict *qdict, QObject **ret);
+TargetInfo * qmp_query_target(Error **errp);
+int qmp_marshal_input_query_target(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_send_key(KeyValueList * keys, bool has_hold_time, int64_t hold_time, Error **errp);
+int qmp_marshal_input_send_key(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_screendump(const char * filename, Error **errp);
+int qmp_marshal_input_screendump(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_nbd_server_start(SocketAddress * addr, Error **errp);
+int qmp_marshal_input_nbd_server_start(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_nbd_server_add(const char * device, bool has_writable, bool writable, Error **errp);
+int qmp_marshal_input_nbd_server_add(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_nbd_server_stop(Error **errp);
+int qmp_marshal_input_nbd_server_stop(Monitor *mon, const QDict *qdict, QObject **ret);
+ChardevReturn * qmp_chardev_add(const char * id, ChardevBackend * backend, Error **errp);
+int qmp_marshal_input_chardev_add(Monitor *mon, const QDict *qdict, QObject **ret);
+void qmp_chardev_remove(const char * id, Error **errp);
+int qmp_marshal_input_chardev_remove(Monitor *mon, const QDict *qdict, QObject **ret);
+TpmModelList * qmp_query_tpm_models(Error **errp);
+int qmp_marshal_input_query_tpm_models(Monitor *mon, const QDict *qdict, QObject **ret);
+TpmTypeList * qmp_query_tpm_types(Error **errp);
+int qmp_marshal_input_query_tpm_types(Monitor *mon, const QDict *qdict, QObject **ret);
+TPMInfoList * qmp_query_tpm(Error **errp);
+int qmp_marshal_input_query_tpm(Monitor *mon, const QDict *qdict, QObject **ret);
+CommandLineOptionInfoList * qmp_query_command_line_options(bool has_option, const char * option, Error **errp);
+int qmp_marshal_input_query_command_line_options(Monitor *mon, const QDict *qdict, QObject **ret);
+RxFilterInfoList * qmp_query_rx_filter(bool has_name, const char * name, Error **errp);
+int qmp_marshal_input_query_rx_filter(Monitor *mon, const QDict *qdict, QObject **ret);
+
+#endif
diff --git a/contrib/qemu/qobject/json-lexer.c b/contrib/qemu/qobject/json-lexer.c
new file mode 100644
index 00000000000..440df60392b
--- /dev/null
+++ b/contrib/qemu/qobject/json-lexer.c
@@ -0,0 +1,373 @@
+/*
+ * JSON lexer
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qlist.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qint.h"
+#include "qemu-common.h"
+#include "qapi/qmp/json-lexer.h"
+
+#define MAX_TOKEN_SIZE (64ULL << 20)
+
+/*
+ * \"([^\\\"]|(\\\"\\'\\\\\\/\\b\\f\\n\\r\\t\\u[0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F]))*\"
+ * '([^\\']|(\\\"\\'\\\\\\/\\b\\f\\n\\r\\t\\u[0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F]))*'
+ * 0|([1-9][0-9]*(.[0-9]+)?([eE]([-+])?[0-9]+))
+ * [{}\[\],:]
+ * [a-z]+
+ *
+ */
+
+enum json_lexer_state {
+ IN_ERROR = 0,
+ IN_DQ_UCODE3,
+ IN_DQ_UCODE2,
+ IN_DQ_UCODE1,
+ IN_DQ_UCODE0,
+ IN_DQ_STRING_ESCAPE,
+ IN_DQ_STRING,
+ IN_SQ_UCODE3,
+ IN_SQ_UCODE2,
+ IN_SQ_UCODE1,
+ IN_SQ_UCODE0,
+ IN_SQ_STRING_ESCAPE,
+ IN_SQ_STRING,
+ IN_ZERO,
+ IN_DIGITS,
+ IN_DIGIT,
+ IN_EXP_E,
+ IN_MANTISSA,
+ IN_MANTISSA_DIGITS,
+ IN_NONZERO_NUMBER,
+ IN_NEG_NONZERO_NUMBER,
+ IN_KEYWORD,
+ IN_ESCAPE,
+ IN_ESCAPE_L,
+ IN_ESCAPE_LL,
+ IN_ESCAPE_I,
+ IN_ESCAPE_I6,
+ IN_ESCAPE_I64,
+ IN_WHITESPACE,
+ IN_START,
+};
+
+#define TERMINAL(state) [0 ... 0x7F] = (state)
+
+/* Return whether TERMINAL is a terminal state and the transition to it
+ from OLD_STATE required lookahead. This happens whenever the table
+ below uses the TERMINAL macro. */
+#define TERMINAL_NEEDED_LOOKAHEAD(old_state, terminal) \
+ (json_lexer[(old_state)][0] == (terminal))
+
+static const uint8_t json_lexer[][256] = {
+ /* double quote string */
+ [IN_DQ_UCODE3] = {
+ ['0' ... '9'] = IN_DQ_STRING,
+ ['a' ... 'f'] = IN_DQ_STRING,
+ ['A' ... 'F'] = IN_DQ_STRING,
+ },
+ [IN_DQ_UCODE2] = {
+ ['0' ... '9'] = IN_DQ_UCODE3,
+ ['a' ... 'f'] = IN_DQ_UCODE3,
+ ['A' ... 'F'] = IN_DQ_UCODE3,
+ },
+ [IN_DQ_UCODE1] = {
+ ['0' ... '9'] = IN_DQ_UCODE2,
+ ['a' ... 'f'] = IN_DQ_UCODE2,
+ ['A' ... 'F'] = IN_DQ_UCODE2,
+ },
+ [IN_DQ_UCODE0] = {
+ ['0' ... '9'] = IN_DQ_UCODE1,
+ ['a' ... 'f'] = IN_DQ_UCODE1,
+ ['A' ... 'F'] = IN_DQ_UCODE1,
+ },
+ [IN_DQ_STRING_ESCAPE] = {
+ ['b'] = IN_DQ_STRING,
+ ['f'] = IN_DQ_STRING,
+ ['n'] = IN_DQ_STRING,
+ ['r'] = IN_DQ_STRING,
+ ['t'] = IN_DQ_STRING,
+ ['/'] = IN_DQ_STRING,
+ ['\\'] = IN_DQ_STRING,
+ ['\''] = IN_DQ_STRING,
+ ['\"'] = IN_DQ_STRING,
+ ['u'] = IN_DQ_UCODE0,
+ },
+ [IN_DQ_STRING] = {
+ [1 ... 0xBF] = IN_DQ_STRING,
+ [0xC2 ... 0xF4] = IN_DQ_STRING,
+ ['\\'] = IN_DQ_STRING_ESCAPE,
+ ['"'] = JSON_STRING,
+ },
+
+ /* single quote string */
+ [IN_SQ_UCODE3] = {
+ ['0' ... '9'] = IN_SQ_STRING,
+ ['a' ... 'f'] = IN_SQ_STRING,
+ ['A' ... 'F'] = IN_SQ_STRING,
+ },
+ [IN_SQ_UCODE2] = {
+ ['0' ... '9'] = IN_SQ_UCODE3,
+ ['a' ... 'f'] = IN_SQ_UCODE3,
+ ['A' ... 'F'] = IN_SQ_UCODE3,
+ },
+ [IN_SQ_UCODE1] = {
+ ['0' ... '9'] = IN_SQ_UCODE2,
+ ['a' ... 'f'] = IN_SQ_UCODE2,
+ ['A' ... 'F'] = IN_SQ_UCODE2,
+ },
+ [IN_SQ_UCODE0] = {
+ ['0' ... '9'] = IN_SQ_UCODE1,
+ ['a' ... 'f'] = IN_SQ_UCODE1,
+ ['A' ... 'F'] = IN_SQ_UCODE1,
+ },
+ [IN_SQ_STRING_ESCAPE] = {
+ ['b'] = IN_SQ_STRING,
+ ['f'] = IN_SQ_STRING,
+ ['n'] = IN_SQ_STRING,
+ ['r'] = IN_SQ_STRING,
+ ['t'] = IN_SQ_STRING,
+ ['/'] = IN_DQ_STRING,
+ ['\\'] = IN_DQ_STRING,
+ ['\''] = IN_SQ_STRING,
+ ['\"'] = IN_SQ_STRING,
+ ['u'] = IN_SQ_UCODE0,
+ },
+ [IN_SQ_STRING] = {
+ [1 ... 0xBF] = IN_SQ_STRING,
+ [0xC2 ... 0xF4] = IN_SQ_STRING,
+ ['\\'] = IN_SQ_STRING_ESCAPE,
+ ['\''] = JSON_STRING,
+ },
+
+ /* Zero */
+ [IN_ZERO] = {
+ TERMINAL(JSON_INTEGER),
+ ['0' ... '9'] = IN_ERROR,
+ ['.'] = IN_MANTISSA,
+ },
+
+ /* Float */
+ [IN_DIGITS] = {
+ TERMINAL(JSON_FLOAT),
+ ['0' ... '9'] = IN_DIGITS,
+ },
+
+ [IN_DIGIT] = {
+ ['0' ... '9'] = IN_DIGITS,
+ },
+
+ [IN_EXP_E] = {
+ ['-'] = IN_DIGIT,
+ ['+'] = IN_DIGIT,
+ ['0' ... '9'] = IN_DIGITS,
+ },
+
+ [IN_MANTISSA_DIGITS] = {
+ TERMINAL(JSON_FLOAT),
+ ['0' ... '9'] = IN_MANTISSA_DIGITS,
+ ['e'] = IN_EXP_E,
+ ['E'] = IN_EXP_E,
+ },
+
+ [IN_MANTISSA] = {
+ ['0' ... '9'] = IN_MANTISSA_DIGITS,
+ },
+
+ /* Number */
+ [IN_NONZERO_NUMBER] = {
+ TERMINAL(JSON_INTEGER),
+ ['0' ... '9'] = IN_NONZERO_NUMBER,
+ ['e'] = IN_EXP_E,
+ ['E'] = IN_EXP_E,
+ ['.'] = IN_MANTISSA,
+ },
+
+ [IN_NEG_NONZERO_NUMBER] = {
+ ['0'] = IN_ZERO,
+ ['1' ... '9'] = IN_NONZERO_NUMBER,
+ },
+
+ /* keywords */
+ [IN_KEYWORD] = {
+ TERMINAL(JSON_KEYWORD),
+ ['a' ... 'z'] = IN_KEYWORD,
+ },
+
+ /* whitespace */
+ [IN_WHITESPACE] = {
+ TERMINAL(JSON_SKIP),
+ [' '] = IN_WHITESPACE,
+ ['\t'] = IN_WHITESPACE,
+ ['\r'] = IN_WHITESPACE,
+ ['\n'] = IN_WHITESPACE,
+ },
+
+ /* escape */
+ [IN_ESCAPE_LL] = {
+ ['d'] = JSON_ESCAPE,
+ },
+
+ [IN_ESCAPE_L] = {
+ ['d'] = JSON_ESCAPE,
+ ['l'] = IN_ESCAPE_LL,
+ },
+
+ [IN_ESCAPE_I64] = {
+ ['d'] = JSON_ESCAPE,
+ },
+
+ [IN_ESCAPE_I6] = {
+ ['4'] = IN_ESCAPE_I64,
+ },
+
+ [IN_ESCAPE_I] = {
+ ['6'] = IN_ESCAPE_I6,
+ },
+
+ [IN_ESCAPE] = {
+ ['d'] = JSON_ESCAPE,
+ ['i'] = JSON_ESCAPE,
+ ['p'] = JSON_ESCAPE,
+ ['s'] = JSON_ESCAPE,
+ ['f'] = JSON_ESCAPE,
+ ['l'] = IN_ESCAPE_L,
+ ['I'] = IN_ESCAPE_I,
+ },
+
+ /* top level rule */
+ [IN_START] = {
+ ['"'] = IN_DQ_STRING,
+ ['\''] = IN_SQ_STRING,
+ ['0'] = IN_ZERO,
+ ['1' ... '9'] = IN_NONZERO_NUMBER,
+ ['-'] = IN_NEG_NONZERO_NUMBER,
+ ['{'] = JSON_OPERATOR,
+ ['}'] = JSON_OPERATOR,
+ ['['] = JSON_OPERATOR,
+ [']'] = JSON_OPERATOR,
+ [','] = JSON_OPERATOR,
+ [':'] = JSON_OPERATOR,
+ ['a' ... 'z'] = IN_KEYWORD,
+ ['%'] = IN_ESCAPE,
+ [' '] = IN_WHITESPACE,
+ ['\t'] = IN_WHITESPACE,
+ ['\r'] = IN_WHITESPACE,
+ ['\n'] = IN_WHITESPACE,
+ },
+};
+
+void json_lexer_init(JSONLexer *lexer, JSONLexerEmitter func)
+{
+ lexer->emit = func;
+ lexer->state = IN_START;
+ lexer->token = qstring_new();
+ lexer->x = lexer->y = 0;
+}
+
+static int json_lexer_feed_char(JSONLexer *lexer, char ch, bool flush)
+{
+ int char_consumed, new_state;
+
+ lexer->x++;
+ if (ch == '\n') {
+ lexer->x = 0;
+ lexer->y++;
+ }
+
+ do {
+ new_state = json_lexer[lexer->state][(uint8_t)ch];
+ char_consumed = !TERMINAL_NEEDED_LOOKAHEAD(lexer->state, new_state);
+ if (char_consumed) {
+ qstring_append_chr(lexer->token, ch);
+ }
+
+ switch (new_state) {
+ case JSON_OPERATOR:
+ case JSON_ESCAPE:
+ case JSON_INTEGER:
+ case JSON_FLOAT:
+ case JSON_KEYWORD:
+ case JSON_STRING:
+ lexer->emit(lexer, lexer->token, new_state, lexer->x, lexer->y);
+ /* fall through */
+ case JSON_SKIP:
+ QDECREF(lexer->token);
+ lexer->token = qstring_new();
+ new_state = IN_START;
+ break;
+ case IN_ERROR:
+ /* XXX: To avoid having previous bad input leaving the parser in an
+ * unresponsive state where we consume unpredictable amounts of
+ * subsequent "good" input, percolate this error state up to the
+ * tokenizer/parser by forcing a NULL object to be emitted, then
+ * reset state.
+ *
+ * Also note that this handling is required for reliable channel
+ * negotiation between QMP and the guest agent, since chr(0xFF)
+ * is placed at the beginning of certain events to ensure proper
+ * delivery when the channel is in an unknown state. chr(0xFF) is
+ * never a valid ASCII/UTF-8 sequence, so this should reliably
+ * induce an error/flush state.
+ */
+ lexer->emit(lexer, lexer->token, JSON_ERROR, lexer->x, lexer->y);
+ QDECREF(lexer->token);
+ lexer->token = qstring_new();
+ new_state = IN_START;
+ lexer->state = new_state;
+ return 0;
+ default:
+ break;
+ }
+ lexer->state = new_state;
+ } while (!char_consumed && !flush);
+
+ /* Do not let a single token grow to an arbitrarily large size,
+ * this is a security consideration.
+ */
+ if (lexer->token->length > MAX_TOKEN_SIZE) {
+ lexer->emit(lexer, lexer->token, lexer->state, lexer->x, lexer->y);
+ QDECREF(lexer->token);
+ lexer->token = qstring_new();
+ lexer->state = IN_START;
+ }
+
+ return 0;
+}
+
+int json_lexer_feed(JSONLexer *lexer, const char *buffer, size_t size)
+{
+ size_t i;
+
+ for (i = 0; i < size; i++) {
+ int err;
+
+ err = json_lexer_feed_char(lexer, buffer[i], false);
+ if (err < 0) {
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+int json_lexer_flush(JSONLexer *lexer)
+{
+ return lexer->state == IN_START ? 0 : json_lexer_feed_char(lexer, 0, true);
+}
+
+void json_lexer_destroy(JSONLexer *lexer)
+{
+ QDECREF(lexer->token);
+}
diff --git a/contrib/qemu/qobject/json-parser.c b/contrib/qemu/qobject/json-parser.c
new file mode 100644
index 00000000000..e7947b340c1
--- /dev/null
+++ b/contrib/qemu/qobject/json-parser.c
@@ -0,0 +1,724 @@
+/*
+ * JSON Parser
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include <stdarg.h>
+
+#include "qemu-common.h"
+#include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qint.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qlist.h"
+#include "qapi/qmp/qfloat.h"
+#include "qapi/qmp/qbool.h"
+#include "qapi/qmp/json-parser.h"
+#include "qapi/qmp/json-lexer.h"
+#include "qapi/qmp/qerror.h"
+
+typedef struct JSONParserContext
+{
+ Error *err;
+ struct {
+ QObject **buf;
+ size_t pos;
+ size_t count;
+ } tokens;
+} JSONParserContext;
+
+#define BUG_ON(cond) assert(!(cond))
+
+/**
+ * TODO
+ *
+ * 0) make errors meaningful again
+ * 1) add geometry information to tokens
+ * 3) should we return a parsed size?
+ * 4) deal with premature EOI
+ */
+
+static QObject *parse_value(JSONParserContext *ctxt, va_list *ap);
+
+/**
+ * Token manipulators
+ *
+ * tokens are dictionaries that contain a type, a string value, and geometry information
+ * about a token identified by the lexer. These are routines that make working with
+ * these objects a bit easier.
+ */
+static const char *token_get_value(QObject *obj)
+{
+ return qdict_get_str(qobject_to_qdict(obj), "token");
+}
+
+static JSONTokenType token_get_type(QObject *obj)
+{
+ return qdict_get_int(qobject_to_qdict(obj), "type");
+}
+
+static int token_is_operator(QObject *obj, char op)
+{
+ const char *val;
+
+ if (token_get_type(obj) != JSON_OPERATOR) {
+ return 0;
+ }
+
+ val = token_get_value(obj);
+
+ return (val[0] == op) && (val[1] == 0);
+}
+
+static int token_is_keyword(QObject *obj, const char *value)
+{
+ if (token_get_type(obj) != JSON_KEYWORD) {
+ return 0;
+ }
+
+ return strcmp(token_get_value(obj), value) == 0;
+}
+
+static int token_is_escape(QObject *obj, const char *value)
+{
+ if (token_get_type(obj) != JSON_ESCAPE) {
+ return 0;
+ }
+
+ return (strcmp(token_get_value(obj), value) == 0);
+}
+
+/**
+ * Error handler
+ */
+static void GCC_FMT_ATTR(3, 4) parse_error(JSONParserContext *ctxt,
+ QObject *token, const char *msg, ...)
+{
+ va_list ap;
+ char message[1024];
+ va_start(ap, msg);
+ vsnprintf(message, sizeof(message), msg, ap);
+ va_end(ap);
+ if (ctxt->err) {
+ error_free(ctxt->err);
+ ctxt->err = NULL;
+ }
+ error_set(&ctxt->err, QERR_JSON_PARSE_ERROR, message);
+}
+
+/**
+ * String helpers
+ *
+ * These helpers are used to unescape strings.
+ */
+static void wchar_to_utf8(uint16_t wchar, char *buffer, size_t buffer_length)
+{
+ if (wchar <= 0x007F) {
+ BUG_ON(buffer_length < 2);
+
+ buffer[0] = wchar & 0x7F;
+ buffer[1] = 0;
+ } else if (wchar <= 0x07FF) {
+ BUG_ON(buffer_length < 3);
+
+ buffer[0] = 0xC0 | ((wchar >> 6) & 0x1F);
+ buffer[1] = 0x80 | (wchar & 0x3F);
+ buffer[2] = 0;
+ } else {
+ BUG_ON(buffer_length < 4);
+
+ buffer[0] = 0xE0 | ((wchar >> 12) & 0x0F);
+ buffer[1] = 0x80 | ((wchar >> 6) & 0x3F);
+ buffer[2] = 0x80 | (wchar & 0x3F);
+ buffer[3] = 0;
+ }
+}
+
+static int hex2decimal(char ch)
+{
+ if (ch >= '0' && ch <= '9') {
+ return (ch - '0');
+ } else if (ch >= 'a' && ch <= 'f') {
+ return 10 + (ch - 'a');
+ } else if (ch >= 'A' && ch <= 'F') {
+ return 10 + (ch - 'A');
+ }
+
+ return -1;
+}
+
+/**
+ * parse_string(): Parse a json string and return a QObject
+ *
+ * string
+ * ""
+ * " chars "
+ * chars
+ * char
+ * char chars
+ * char
+ * any-Unicode-character-
+ * except-"-or-\-or-
+ * control-character
+ * \"
+ * \\
+ * \/
+ * \b
+ * \f
+ * \n
+ * \r
+ * \t
+ * \u four-hex-digits
+ */
+static QString *qstring_from_escaped_str(JSONParserContext *ctxt, QObject *token)
+{
+ const char *ptr = token_get_value(token);
+ QString *str;
+ int double_quote = 1;
+
+ if (*ptr == '"') {
+ double_quote = 1;
+ } else {
+ double_quote = 0;
+ }
+ ptr++;
+
+ str = qstring_new();
+ while (*ptr &&
+ ((double_quote && *ptr != '"') || (!double_quote && *ptr != '\''))) {
+ if (*ptr == '\\') {
+ ptr++;
+
+ switch (*ptr) {
+ case '"':
+ qstring_append(str, "\"");
+ ptr++;
+ break;
+ case '\'':
+ qstring_append(str, "'");
+ ptr++;
+ break;
+ case '\\':
+ qstring_append(str, "\\");
+ ptr++;
+ break;
+ case '/':
+ qstring_append(str, "/");
+ ptr++;
+ break;
+ case 'b':
+ qstring_append(str, "\b");
+ ptr++;
+ break;
+ case 'f':
+ qstring_append(str, "\f");
+ ptr++;
+ break;
+ case 'n':
+ qstring_append(str, "\n");
+ ptr++;
+ break;
+ case 'r':
+ qstring_append(str, "\r");
+ ptr++;
+ break;
+ case 't':
+ qstring_append(str, "\t");
+ ptr++;
+ break;
+ case 'u': {
+ uint16_t unicode_char = 0;
+ char utf8_char[4];
+ int i = 0;
+
+ ptr++;
+
+ for (i = 0; i < 4; i++) {
+ if (qemu_isxdigit(*ptr)) {
+ unicode_char |= hex2decimal(*ptr) << ((3 - i) * 4);
+ } else {
+ parse_error(ctxt, token,
+ "invalid hex escape sequence in string");
+ goto out;
+ }
+ ptr++;
+ }
+
+ wchar_to_utf8(unicode_char, utf8_char, sizeof(utf8_char));
+ qstring_append(str, utf8_char);
+ } break;
+ default:
+ parse_error(ctxt, token, "invalid escape sequence in string");
+ goto out;
+ }
+ } else {
+ char dummy[2];
+
+ dummy[0] = *ptr++;
+ dummy[1] = 0;
+
+ qstring_append(str, dummy);
+ }
+ }
+
+ return str;
+
+out:
+ QDECREF(str);
+ return NULL;
+}
+
+static QObject *parser_context_pop_token(JSONParserContext *ctxt)
+{
+ QObject *token;
+ g_assert(ctxt->tokens.pos < ctxt->tokens.count);
+ token = ctxt->tokens.buf[ctxt->tokens.pos];
+ ctxt->tokens.pos++;
+ return token;
+}
+
+/* Note: parser_context_{peek|pop}_token do not increment the
+ * token object's refcount. In both cases the references will continue
+ * to be tracked and cleaned up in parser_context_free(), so do not
+ * attempt to free the token object.
+ */
+static QObject *parser_context_peek_token(JSONParserContext *ctxt)
+{
+ QObject *token;
+ g_assert(ctxt->tokens.pos < ctxt->tokens.count);
+ token = ctxt->tokens.buf[ctxt->tokens.pos];
+ return token;
+}
+
+static JSONParserContext parser_context_save(JSONParserContext *ctxt)
+{
+ JSONParserContext saved_ctxt = {0};
+ saved_ctxt.tokens.pos = ctxt->tokens.pos;
+ saved_ctxt.tokens.count = ctxt->tokens.count;
+ saved_ctxt.tokens.buf = ctxt->tokens.buf;
+ return saved_ctxt;
+}
+
+static void parser_context_restore(JSONParserContext *ctxt,
+ JSONParserContext saved_ctxt)
+{
+ ctxt->tokens.pos = saved_ctxt.tokens.pos;
+ ctxt->tokens.count = saved_ctxt.tokens.count;
+ ctxt->tokens.buf = saved_ctxt.tokens.buf;
+}
+
+static void tokens_append_from_iter(QObject *obj, void *opaque)
+{
+ JSONParserContext *ctxt = opaque;
+ g_assert(ctxt->tokens.pos < ctxt->tokens.count);
+ ctxt->tokens.buf[ctxt->tokens.pos++] = obj;
+ qobject_incref(obj);
+}
+
+static JSONParserContext *parser_context_new(QList *tokens)
+{
+ JSONParserContext *ctxt;
+ size_t count;
+
+ if (!tokens) {
+ return NULL;
+ }
+
+ count = qlist_size(tokens);
+ if (count == 0) {
+ return NULL;
+ }
+
+ ctxt = g_malloc0(sizeof(JSONParserContext));
+ ctxt->tokens.pos = 0;
+ ctxt->tokens.count = count;
+ ctxt->tokens.buf = g_malloc(count * sizeof(QObject *));
+ qlist_iter(tokens, tokens_append_from_iter, ctxt);
+ ctxt->tokens.pos = 0;
+
+ return ctxt;
+}
+
+/* to support error propagation, ctxt->err must be freed separately */
+static void parser_context_free(JSONParserContext *ctxt)
+{
+ int i;
+ if (ctxt) {
+ for (i = 0; i < ctxt->tokens.count; i++) {
+ qobject_decref(ctxt->tokens.buf[i]);
+ }
+ g_free(ctxt->tokens.buf);
+ g_free(ctxt);
+ }
+}
+
+/**
+ * Parsing rules
+ */
+static int parse_pair(JSONParserContext *ctxt, QDict *dict, va_list *ap)
+{
+ QObject *key = NULL, *token = NULL, *value, *peek;
+ JSONParserContext saved_ctxt = parser_context_save(ctxt);
+
+ peek = parser_context_peek_token(ctxt);
+ if (peek == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+
+ key = parse_value(ctxt, ap);
+ if (!key || qobject_type(key) != QTYPE_QSTRING) {
+ parse_error(ctxt, peek, "key is not a string in object");
+ goto out;
+ }
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+
+ if (!token_is_operator(token, ':')) {
+ parse_error(ctxt, token, "missing : in object pair");
+ goto out;
+ }
+
+ value = parse_value(ctxt, ap);
+ if (value == NULL) {
+ parse_error(ctxt, token, "Missing value in dict");
+ goto out;
+ }
+
+ qdict_put_obj(dict, qstring_get_str(qobject_to_qstring(key)), value);
+
+ qobject_decref(key);
+
+ return 0;
+
+out:
+ parser_context_restore(ctxt, saved_ctxt);
+ qobject_decref(key);
+
+ return -1;
+}
+
+static QObject *parse_object(JSONParserContext *ctxt, va_list *ap)
+{
+ QDict *dict = NULL;
+ QObject *token, *peek;
+ JSONParserContext saved_ctxt = parser_context_save(ctxt);
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ goto out;
+ }
+
+ if (!token_is_operator(token, '{')) {
+ goto out;
+ }
+ token = NULL;
+
+ dict = qdict_new();
+
+ peek = parser_context_peek_token(ctxt);
+ if (peek == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+
+ if (!token_is_operator(peek, '}')) {
+ if (parse_pair(ctxt, dict, ap) == -1) {
+ goto out;
+ }
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+
+ while (!token_is_operator(token, '}')) {
+ if (!token_is_operator(token, ',')) {
+ parse_error(ctxt, token, "expected separator in dict");
+ goto out;
+ }
+ token = NULL;
+
+ if (parse_pair(ctxt, dict, ap) == -1) {
+ goto out;
+ }
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+ }
+ token = NULL;
+ } else {
+ token = parser_context_pop_token(ctxt);
+ token = NULL;
+ }
+
+ return QOBJECT(dict);
+
+out:
+ parser_context_restore(ctxt, saved_ctxt);
+ QDECREF(dict);
+ return NULL;
+}
+
+static QObject *parse_array(JSONParserContext *ctxt, va_list *ap)
+{
+ QList *list = NULL;
+ QObject *token, *peek;
+ JSONParserContext saved_ctxt = parser_context_save(ctxt);
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ goto out;
+ }
+
+ if (!token_is_operator(token, '[')) {
+ token = NULL;
+ goto out;
+ }
+ token = NULL;
+
+ list = qlist_new();
+
+ peek = parser_context_peek_token(ctxt);
+ if (peek == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+
+ if (!token_is_operator(peek, ']')) {
+ QObject *obj;
+
+ obj = parse_value(ctxt, ap);
+ if (obj == NULL) {
+ parse_error(ctxt, token, "expecting value");
+ goto out;
+ }
+
+ qlist_append_obj(list, obj);
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+
+ while (!token_is_operator(token, ']')) {
+ if (!token_is_operator(token, ',')) {
+ parse_error(ctxt, token, "expected separator in list");
+ goto out;
+ }
+
+ token = NULL;
+
+ obj = parse_value(ctxt, ap);
+ if (obj == NULL) {
+ parse_error(ctxt, token, "expecting value");
+ goto out;
+ }
+
+ qlist_append_obj(list, obj);
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ parse_error(ctxt, NULL, "premature EOI");
+ goto out;
+ }
+ }
+
+ token = NULL;
+ } else {
+ token = parser_context_pop_token(ctxt);
+ token = NULL;
+ }
+
+ return QOBJECT(list);
+
+out:
+ parser_context_restore(ctxt, saved_ctxt);
+ QDECREF(list);
+ return NULL;
+}
+
+static QObject *parse_keyword(JSONParserContext *ctxt)
+{
+ QObject *token, *ret;
+ JSONParserContext saved_ctxt = parser_context_save(ctxt);
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ goto out;
+ }
+
+ if (token_get_type(token) != JSON_KEYWORD) {
+ goto out;
+ }
+
+ if (token_is_keyword(token, "true")) {
+ ret = QOBJECT(qbool_from_int(true));
+ } else if (token_is_keyword(token, "false")) {
+ ret = QOBJECT(qbool_from_int(false));
+ } else {
+ parse_error(ctxt, token, "invalid keyword `%s'", token_get_value(token));
+ goto out;
+ }
+
+ return ret;
+
+out:
+ parser_context_restore(ctxt, saved_ctxt);
+
+ return NULL;
+}
+
+static QObject *parse_escape(JSONParserContext *ctxt, va_list *ap)
+{
+ QObject *token = NULL, *obj;
+ JSONParserContext saved_ctxt = parser_context_save(ctxt);
+
+ if (ap == NULL) {
+ goto out;
+ }
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ goto out;
+ }
+
+ if (token_is_escape(token, "%p")) {
+ obj = va_arg(*ap, QObject *);
+ } else if (token_is_escape(token, "%i")) {
+ obj = QOBJECT(qbool_from_int(va_arg(*ap, int)));
+ } else if (token_is_escape(token, "%d")) {
+ obj = QOBJECT(qint_from_int(va_arg(*ap, int)));
+ } else if (token_is_escape(token, "%ld")) {
+ obj = QOBJECT(qint_from_int(va_arg(*ap, long)));
+ } else if (token_is_escape(token, "%lld") ||
+ token_is_escape(token, "%I64d")) {
+ obj = QOBJECT(qint_from_int(va_arg(*ap, long long)));
+ } else if (token_is_escape(token, "%s")) {
+ obj = QOBJECT(qstring_from_str(va_arg(*ap, const char *)));
+ } else if (token_is_escape(token, "%f")) {
+ obj = QOBJECT(qfloat_from_double(va_arg(*ap, double)));
+ } else {
+ goto out;
+ }
+
+ return obj;
+
+out:
+ parser_context_restore(ctxt, saved_ctxt);
+
+ return NULL;
+}
+
+static QObject *parse_literal(JSONParserContext *ctxt)
+{
+ QObject *token, *obj;
+ JSONParserContext saved_ctxt = parser_context_save(ctxt);
+
+ token = parser_context_pop_token(ctxt);
+ if (token == NULL) {
+ goto out;
+ }
+
+ switch (token_get_type(token)) {
+ case JSON_STRING:
+ obj = QOBJECT(qstring_from_escaped_str(ctxt, token));
+ break;
+ case JSON_INTEGER: {
+ /* A possibility exists that this is a whole-valued float where the
+ * fractional part was left out due to being 0 (.0). It's not a big
+ * deal to treat these as ints in the parser, so long as users of the
+ * resulting QObject know to expect a QInt in place of a QFloat in
+ * cases like these.
+ *
+ * However, in some cases these values will overflow/underflow a
+ * QInt/int64 container, thus we should assume these are to be handled
+ * as QFloats/doubles rather than silently changing their values.
+ *
+ * strtoll() indicates these instances by setting errno to ERANGE
+ */
+ int64_t value;
+
+ errno = 0; /* strtoll doesn't set errno on success */
+ value = strtoll(token_get_value(token), NULL, 10);
+ if (errno != ERANGE) {
+ obj = QOBJECT(qint_from_int(value));
+ break;
+ }
+ /* fall through to JSON_FLOAT */
+ }
+ case JSON_FLOAT:
+ /* FIXME dependent on locale */
+ obj = QOBJECT(qfloat_from_double(strtod(token_get_value(token), NULL)));
+ break;
+ default:
+ goto out;
+ }
+
+ return obj;
+
+out:
+ parser_context_restore(ctxt, saved_ctxt);
+
+ return NULL;
+}
+
+static QObject *parse_value(JSONParserContext *ctxt, va_list *ap)
+{
+ QObject *obj;
+
+ obj = parse_object(ctxt, ap);
+ if (obj == NULL) {
+ obj = parse_array(ctxt, ap);
+ }
+ if (obj == NULL) {
+ obj = parse_escape(ctxt, ap);
+ }
+ if (obj == NULL) {
+ obj = parse_keyword(ctxt);
+ }
+ if (obj == NULL) {
+ obj = parse_literal(ctxt);
+ }
+
+ return obj;
+}
+
+QObject *json_parser_parse(QList *tokens, va_list *ap)
+{
+ return json_parser_parse_err(tokens, ap, NULL);
+}
+
+QObject *json_parser_parse_err(QList *tokens, va_list *ap, Error **errp)
+{
+ JSONParserContext *ctxt = parser_context_new(tokens);
+ QObject *result;
+
+ if (!ctxt) {
+ return NULL;
+ }
+
+ result = parse_value(ctxt, ap);
+
+ error_propagate(errp, ctxt->err);
+
+ parser_context_free(ctxt);
+
+ return result;
+}
diff --git a/contrib/qemu/qobject/json-streamer.c b/contrib/qemu/qobject/json-streamer.c
new file mode 100644
index 00000000000..1b2f9b1d107
--- /dev/null
+++ b/contrib/qemu/qobject/json-streamer.c
@@ -0,0 +1,122 @@
+/*
+ * JSON streaming support
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qapi/qmp/qlist.h"
+#include "qapi/qmp/qint.h"
+#include "qapi/qmp/qdict.h"
+#include "qemu-common.h"
+#include "qapi/qmp/json-lexer.h"
+#include "qapi/qmp/json-streamer.h"
+
+#define MAX_TOKEN_SIZE (64ULL << 20)
+#define MAX_NESTING (1ULL << 10)
+
+static void json_message_process_token(JSONLexer *lexer, QString *token, JSONTokenType type, int x, int y)
+{
+ JSONMessageParser *parser = container_of(lexer, JSONMessageParser, lexer);
+ QDict *dict;
+
+ if (type == JSON_OPERATOR) {
+ switch (qstring_get_str(token)[0]) {
+ case '{':
+ parser->brace_count++;
+ break;
+ case '}':
+ parser->brace_count--;
+ break;
+ case '[':
+ parser->bracket_count++;
+ break;
+ case ']':
+ parser->bracket_count--;
+ break;
+ default:
+ break;
+ }
+ }
+
+ dict = qdict_new();
+ qdict_put(dict, "type", qint_from_int(type));
+ QINCREF(token);
+ qdict_put(dict, "token", token);
+ qdict_put(dict, "x", qint_from_int(x));
+ qdict_put(dict, "y", qint_from_int(y));
+
+ parser->token_size += token->length;
+
+ qlist_append(parser->tokens, dict);
+
+ if (type == JSON_ERROR) {
+ goto out_emit_bad;
+ } else if (parser->brace_count < 0 ||
+ parser->bracket_count < 0 ||
+ (parser->brace_count == 0 &&
+ parser->bracket_count == 0)) {
+ goto out_emit;
+ } else if (parser->token_size > MAX_TOKEN_SIZE ||
+ parser->bracket_count > MAX_NESTING ||
+ parser->brace_count > MAX_NESTING) {
+ /* Security consideration, we limit total memory allocated per object
+ * and the maximum recursion depth that a message can force.
+ */
+ goto out_emit;
+ }
+
+ return;
+
+out_emit_bad:
+ /* clear out token list and tell the parser to emit and error
+ * indication by passing it a NULL list
+ */
+ QDECREF(parser->tokens);
+ parser->tokens = NULL;
+out_emit:
+ /* send current list of tokens to parser and reset tokenizer */
+ parser->brace_count = 0;
+ parser->bracket_count = 0;
+ parser->emit(parser, parser->tokens);
+ if (parser->tokens) {
+ QDECREF(parser->tokens);
+ }
+ parser->tokens = qlist_new();
+ parser->token_size = 0;
+}
+
+void json_message_parser_init(JSONMessageParser *parser,
+ void (*func)(JSONMessageParser *, QList *))
+{
+ parser->emit = func;
+ parser->brace_count = 0;
+ parser->bracket_count = 0;
+ parser->tokens = qlist_new();
+ parser->token_size = 0;
+
+ json_lexer_init(&parser->lexer, json_message_process_token);
+}
+
+int json_message_parser_feed(JSONMessageParser *parser,
+ const char *buffer, size_t size)
+{
+ return json_lexer_feed(&parser->lexer, buffer, size);
+}
+
+int json_message_parser_flush(JSONMessageParser *parser)
+{
+ return json_lexer_flush(&parser->lexer);
+}
+
+void json_message_parser_destroy(JSONMessageParser *parser)
+{
+ json_lexer_destroy(&parser->lexer);
+ QDECREF(parser->tokens);
+}
diff --git a/contrib/qemu/qobject/qbool.c b/contrib/qemu/qobject/qbool.c
new file mode 100644
index 00000000000..a3d2afa827f
--- /dev/null
+++ b/contrib/qemu/qobject/qbool.c
@@ -0,0 +1,68 @@
+/*
+ * QBool Module
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qapi/qmp/qbool.h"
+#include "qapi/qmp/qobject.h"
+#include "qemu-common.h"
+
+static void qbool_destroy_obj(QObject *obj);
+
+static const QType qbool_type = {
+ .code = QTYPE_QBOOL,
+ .destroy = qbool_destroy_obj,
+};
+
+/**
+ * qbool_from_int(): Create a new QBool from an int
+ *
+ * Return strong reference.
+ */
+QBool *qbool_from_int(int value)
+{
+ QBool *qb;
+
+ qb = g_malloc(sizeof(*qb));
+ qb->value = value;
+ QOBJECT_INIT(qb, &qbool_type);
+
+ return qb;
+}
+
+/**
+ * qbool_get_int(): Get the stored int
+ */
+int qbool_get_int(const QBool *qb)
+{
+ return qb->value;
+}
+
+/**
+ * qobject_to_qbool(): Convert a QObject into a QBool
+ */
+QBool *qobject_to_qbool(const QObject *obj)
+{
+ if (qobject_type(obj) != QTYPE_QBOOL)
+ return NULL;
+
+ return container_of(obj, QBool, base);
+}
+
+/**
+ * qbool_destroy_obj(): Free all memory allocated by a
+ * QBool object
+ */
+static void qbool_destroy_obj(QObject *obj)
+{
+ assert(obj != NULL);
+ g_free(qobject_to_qbool(obj));
+}
diff --git a/contrib/qemu/qobject/qdict.c b/contrib/qemu/qobject/qdict.c
new file mode 100644
index 00000000000..ed381f9a507
--- /dev/null
+++ b/contrib/qemu/qobject/qdict.c
@@ -0,0 +1,478 @@
+/*
+ * QDict Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#include "qapi/qmp/qint.h"
+#include "qapi/qmp/qfloat.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qbool.h"
+#include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qobject.h"
+#include "qemu/queue.h"
+#include "qemu-common.h"
+
+static void qdict_destroy_obj(QObject *obj);
+
+static const QType qdict_type = {
+ .code = QTYPE_QDICT,
+ .destroy = qdict_destroy_obj,
+};
+
+/**
+ * qdict_new(): Create a new QDict
+ *
+ * Return strong reference.
+ */
+QDict *qdict_new(void)
+{
+ QDict *qdict;
+
+ qdict = g_malloc0(sizeof(*qdict));
+ QOBJECT_INIT(qdict, &qdict_type);
+
+ return qdict;
+}
+
+/**
+ * qobject_to_qdict(): Convert a QObject into a QDict
+ */
+QDict *qobject_to_qdict(const QObject *obj)
+{
+ if (qobject_type(obj) != QTYPE_QDICT)
+ return NULL;
+
+ return container_of(obj, QDict, base);
+}
+
+/**
+ * tdb_hash(): based on the hash agorithm from gdbm, via tdb
+ * (from module-init-tools)
+ */
+static unsigned int tdb_hash(const char *name)
+{
+ unsigned value; /* Used to compute the hash value. */
+ unsigned i; /* Used to cycle through random values. */
+
+ /* Set the initial value from the key size. */
+ for (value = 0x238F13AF * strlen(name), i=0; name[i]; i++)
+ value = (value + (((const unsigned char *)name)[i] << (i*5 % 24)));
+
+ return (1103515243 * value + 12345);
+}
+
+/**
+ * alloc_entry(): allocate a new QDictEntry
+ */
+static QDictEntry *alloc_entry(const char *key, QObject *value)
+{
+ QDictEntry *entry;
+
+ entry = g_malloc0(sizeof(*entry));
+ entry->key = g_strdup(key);
+ entry->value = value;
+
+ return entry;
+}
+
+/**
+ * qdict_entry_value(): Return qdict entry value
+ *
+ * Return weak reference.
+ */
+QObject *qdict_entry_value(const QDictEntry *entry)
+{
+ return entry->value;
+}
+
+/**
+ * qdict_entry_key(): Return qdict entry key
+ *
+ * Return a *pointer* to the string, it has to be duplicated before being
+ * stored.
+ */
+const char *qdict_entry_key(const QDictEntry *entry)
+{
+ return entry->key;
+}
+
+/**
+ * qdict_find(): List lookup function
+ */
+static QDictEntry *qdict_find(const QDict *qdict,
+ const char *key, unsigned int bucket)
+{
+ QDictEntry *entry;
+
+ QLIST_FOREACH(entry, &qdict->table[bucket], next)
+ if (!strcmp(entry->key, key))
+ return entry;
+
+ return NULL;
+}
+
+/**
+ * qdict_put_obj(): Put a new QObject into the dictionary
+ *
+ * Insert the pair 'key:value' into 'qdict', if 'key' already exists
+ * its 'value' will be replaced.
+ *
+ * This is done by freeing the reference to the stored QObject and
+ * storing the new one in the same entry.
+ *
+ * NOTE: ownership of 'value' is transferred to the QDict
+ */
+void qdict_put_obj(QDict *qdict, const char *key, QObject *value)
+{
+ unsigned int bucket;
+ QDictEntry *entry;
+
+ bucket = tdb_hash(key) % QDICT_BUCKET_MAX;
+ entry = qdict_find(qdict, key, bucket);
+ if (entry) {
+ /* replace key's value */
+ qobject_decref(entry->value);
+ entry->value = value;
+ } else {
+ /* allocate a new entry */
+ entry = alloc_entry(key, value);
+ QLIST_INSERT_HEAD(&qdict->table[bucket], entry, next);
+ qdict->size++;
+ }
+}
+
+/**
+ * qdict_get(): Lookup for a given 'key'
+ *
+ * Return a weak reference to the QObject associated with 'key' if
+ * 'key' is present in the dictionary, NULL otherwise.
+ */
+QObject *qdict_get(const QDict *qdict, const char *key)
+{
+ QDictEntry *entry;
+
+ entry = qdict_find(qdict, key, tdb_hash(key) % QDICT_BUCKET_MAX);
+ return (entry == NULL ? NULL : entry->value);
+}
+
+/**
+ * qdict_haskey(): Check if 'key' exists
+ *
+ * Return 1 if 'key' exists in the dict, 0 otherwise
+ */
+int qdict_haskey(const QDict *qdict, const char *key)
+{
+ unsigned int bucket = tdb_hash(key) % QDICT_BUCKET_MAX;
+ return (qdict_find(qdict, key, bucket) == NULL ? 0 : 1);
+}
+
+/**
+ * qdict_size(): Return the size of the dictionary
+ */
+size_t qdict_size(const QDict *qdict)
+{
+ return qdict->size;
+}
+
+/**
+ * qdict_get_obj(): Get a QObject of a specific type
+ */
+static QObject *qdict_get_obj(const QDict *qdict, const char *key,
+ qtype_code type)
+{
+ QObject *obj;
+
+ obj = qdict_get(qdict, key);
+ assert(obj != NULL);
+ assert(qobject_type(obj) == type);
+
+ return obj;
+}
+
+/**
+ * qdict_get_double(): Get an number mapped by 'key'
+ *
+ * This function assumes that 'key' exists and it stores a
+ * QFloat or QInt object.
+ *
+ * Return number mapped by 'key'.
+ */
+double qdict_get_double(const QDict *qdict, const char *key)
+{
+ QObject *obj = qdict_get(qdict, key);
+
+ assert(obj);
+ switch (qobject_type(obj)) {
+ case QTYPE_QFLOAT:
+ return qfloat_get_double(qobject_to_qfloat(obj));
+ case QTYPE_QINT:
+ return qint_get_int(qobject_to_qint(obj));
+ default:
+ abort();
+ }
+}
+
+/**
+ * qdict_get_int(): Get an integer mapped by 'key'
+ *
+ * This function assumes that 'key' exists and it stores a
+ * QInt object.
+ *
+ * Return integer mapped by 'key'.
+ */
+int64_t qdict_get_int(const QDict *qdict, const char *key)
+{
+ QObject *obj = qdict_get_obj(qdict, key, QTYPE_QINT);
+ return qint_get_int(qobject_to_qint(obj));
+}
+
+/**
+ * qdict_get_bool(): Get a bool mapped by 'key'
+ *
+ * This function assumes that 'key' exists and it stores a
+ * QBool object.
+ *
+ * Return bool mapped by 'key'.
+ */
+int qdict_get_bool(const QDict *qdict, const char *key)
+{
+ QObject *obj = qdict_get_obj(qdict, key, QTYPE_QBOOL);
+ return qbool_get_int(qobject_to_qbool(obj));
+}
+
+/**
+ * qdict_get_qlist(): Get the QList mapped by 'key'
+ *
+ * This function assumes that 'key' exists and it stores a
+ * QList object.
+ *
+ * Return QList mapped by 'key'.
+ */
+QList *qdict_get_qlist(const QDict *qdict, const char *key)
+{
+ return qobject_to_qlist(qdict_get_obj(qdict, key, QTYPE_QLIST));
+}
+
+/**
+ * qdict_get_qdict(): Get the QDict mapped by 'key'
+ *
+ * This function assumes that 'key' exists and it stores a
+ * QDict object.
+ *
+ * Return QDict mapped by 'key'.
+ */
+QDict *qdict_get_qdict(const QDict *qdict, const char *key)
+{
+ return qobject_to_qdict(qdict_get_obj(qdict, key, QTYPE_QDICT));
+}
+
+/**
+ * qdict_get_str(): Get a pointer to the stored string mapped
+ * by 'key'
+ *
+ * This function assumes that 'key' exists and it stores a
+ * QString object.
+ *
+ * Return pointer to the string mapped by 'key'.
+ */
+const char *qdict_get_str(const QDict *qdict, const char *key)
+{
+ QObject *obj = qdict_get_obj(qdict, key, QTYPE_QSTRING);
+ return qstring_get_str(qobject_to_qstring(obj));
+}
+
+/**
+ * qdict_get_try_int(): Try to get integer mapped by 'key'
+ *
+ * Return integer mapped by 'key', if it is not present in
+ * the dictionary or if the stored object is not of QInt type
+ * 'def_value' will be returned.
+ */
+int64_t qdict_get_try_int(const QDict *qdict, const char *key,
+ int64_t def_value)
+{
+ QObject *obj;
+
+ obj = qdict_get(qdict, key);
+ if (!obj || qobject_type(obj) != QTYPE_QINT)
+ return def_value;
+
+ return qint_get_int(qobject_to_qint(obj));
+}
+
+/**
+ * qdict_get_try_bool(): Try to get a bool mapped by 'key'
+ *
+ * Return bool mapped by 'key', if it is not present in the
+ * dictionary or if the stored object is not of QBool type
+ * 'def_value' will be returned.
+ */
+int qdict_get_try_bool(const QDict *qdict, const char *key, int def_value)
+{
+ QObject *obj;
+
+ obj = qdict_get(qdict, key);
+ if (!obj || qobject_type(obj) != QTYPE_QBOOL)
+ return def_value;
+
+ return qbool_get_int(qobject_to_qbool(obj));
+}
+
+/**
+ * qdict_get_try_str(): Try to get a pointer to the stored string
+ * mapped by 'key'
+ *
+ * Return a pointer to the string mapped by 'key', if it is not present
+ * in the dictionary or if the stored object is not of QString type
+ * NULL will be returned.
+ */
+const char *qdict_get_try_str(const QDict *qdict, const char *key)
+{
+ QObject *obj;
+
+ obj = qdict_get(qdict, key);
+ if (!obj || qobject_type(obj) != QTYPE_QSTRING)
+ return NULL;
+
+ return qstring_get_str(qobject_to_qstring(obj));
+}
+
+/**
+ * qdict_iter(): Iterate over all the dictionary's stored values.
+ *
+ * This function allows the user to provide an iterator, which will be
+ * called for each stored value in the dictionary.
+ */
+void qdict_iter(const QDict *qdict,
+ void (*iter)(const char *key, QObject *obj, void *opaque),
+ void *opaque)
+{
+ int i;
+ QDictEntry *entry;
+
+ for (i = 0; i < QDICT_BUCKET_MAX; i++) {
+ QLIST_FOREACH(entry, &qdict->table[i], next)
+ iter(entry->key, entry->value, opaque);
+ }
+}
+
+static QDictEntry *qdict_next_entry(const QDict *qdict, int first_bucket)
+{
+ int i;
+
+ for (i = first_bucket; i < QDICT_BUCKET_MAX; i++) {
+ if (!QLIST_EMPTY(&qdict->table[i])) {
+ return QLIST_FIRST(&qdict->table[i]);
+ }
+ }
+
+ return NULL;
+}
+
+/**
+ * qdict_first(): Return first qdict entry for iteration.
+ */
+const QDictEntry *qdict_first(const QDict *qdict)
+{
+ return qdict_next_entry(qdict, 0);
+}
+
+/**
+ * qdict_next(): Return next qdict entry in an iteration.
+ */
+const QDictEntry *qdict_next(const QDict *qdict, const QDictEntry *entry)
+{
+ QDictEntry *ret;
+
+ ret = QLIST_NEXT(entry, next);
+ if (!ret) {
+ unsigned int bucket = tdb_hash(entry->key) % QDICT_BUCKET_MAX;
+ ret = qdict_next_entry(qdict, bucket + 1);
+ }
+
+ return ret;
+}
+
+/**
+ * qdict_clone_shallow(): Clones a given QDict. Its entries are not copied, but
+ * another reference is added.
+ */
+QDict *qdict_clone_shallow(const QDict *src)
+{
+ QDict *dest;
+ QDictEntry *entry;
+ int i;
+
+ dest = qdict_new();
+
+ for (i = 0; i < QDICT_BUCKET_MAX; i++) {
+ QLIST_FOREACH(entry, &src->table[i], next) {
+ qobject_incref(entry->value);
+ qdict_put_obj(dest, entry->key, entry->value);
+ }
+ }
+
+ return dest;
+}
+
+/**
+ * qentry_destroy(): Free all the memory allocated by a QDictEntry
+ */
+static void qentry_destroy(QDictEntry *e)
+{
+ assert(e != NULL);
+ assert(e->key != NULL);
+ assert(e->value != NULL);
+
+ qobject_decref(e->value);
+ g_free(e->key);
+ g_free(e);
+}
+
+/**
+ * qdict_del(): Delete a 'key:value' pair from the dictionary
+ *
+ * This will destroy all data allocated by this entry.
+ */
+void qdict_del(QDict *qdict, const char *key)
+{
+ QDictEntry *entry;
+
+ entry = qdict_find(qdict, key, tdb_hash(key) % QDICT_BUCKET_MAX);
+ if (entry) {
+ QLIST_REMOVE(entry, next);
+ qentry_destroy(entry);
+ qdict->size--;
+ }
+}
+
+/**
+ * qdict_destroy_obj(): Free all the memory allocated by a QDict
+ */
+static void qdict_destroy_obj(QObject *obj)
+{
+ int i;
+ QDict *qdict;
+
+ assert(obj != NULL);
+ qdict = qobject_to_qdict(obj);
+
+ for (i = 0; i < QDICT_BUCKET_MAX; i++) {
+ QDictEntry *entry = QLIST_FIRST(&qdict->table[i]);
+ while (entry) {
+ QDictEntry *tmp = QLIST_NEXT(entry, next);
+ QLIST_REMOVE(entry, next);
+ qentry_destroy(entry);
+ entry = tmp;
+ }
+ }
+
+ g_free(qdict);
+}
diff --git a/contrib/qemu/qobject/qerror.c b/contrib/qemu/qobject/qerror.c
new file mode 100644
index 00000000000..3aee1cf6a69
--- /dev/null
+++ b/contrib/qemu/qobject/qerror.c
@@ -0,0 +1,156 @@
+/*
+ * QError Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#include "monitor/monitor.h"
+#include "qapi/qmp/qjson.h"
+#include "qapi/qmp/qerror.h"
+#include "qemu-common.h"
+
+static void qerror_destroy_obj(QObject *obj);
+
+static const QType qerror_type = {
+ .code = QTYPE_QERROR,
+ .destroy = qerror_destroy_obj,
+};
+
+/**
+ * qerror_new(): Create a new QError
+ *
+ * Return strong reference.
+ */
+static QError *qerror_new(void)
+{
+ QError *qerr;
+
+ qerr = g_malloc0(sizeof(*qerr));
+ QOBJECT_INIT(qerr, &qerror_type);
+
+ return qerr;
+}
+
+/**
+ * qerror_from_info(): Create a new QError from error information
+ *
+ * Return strong reference.
+ */
+static QError *qerror_from_info(ErrorClass err_class, const char *fmt,
+ va_list *va)
+{
+ QError *qerr;
+
+ qerr = qerror_new();
+ loc_save(&qerr->loc);
+
+ qerr->err_msg = g_strdup_vprintf(fmt, *va);
+ qerr->err_class = err_class;
+
+ return qerr;
+}
+
+/**
+ * qerror_human(): Format QError data into human-readable string.
+ */
+QString *qerror_human(const QError *qerror)
+{
+ return qstring_from_str(qerror->err_msg);
+}
+
+/**
+ * qerror_print(): Print QError data
+ *
+ * This function will print the member 'desc' of the specified QError object,
+ * it uses error_report() for this, so that the output is routed to the right
+ * place (ie. stderr or Monitor's device).
+ */
+static void qerror_print(QError *qerror)
+{
+ QString *qstring = qerror_human(qerror);
+ loc_push_restore(&qerror->loc);
+ error_report("%s", qstring_get_str(qstring));
+ loc_pop(&qerror->loc);
+ QDECREF(qstring);
+}
+
+void qerror_report(ErrorClass eclass, const char *fmt, ...)
+{
+ va_list va;
+ QError *qerror;
+
+ va_start(va, fmt);
+ qerror = qerror_from_info(eclass, fmt, &va);
+ va_end(va);
+
+ if (monitor_cur_is_qmp()) {
+ monitor_set_error(cur_mon, qerror);
+ } else {
+ qerror_print(qerror);
+ QDECREF(qerror);
+ }
+}
+
+/* Evil... */
+struct Error
+{
+ char *msg;
+ ErrorClass err_class;
+};
+
+void qerror_report_err(Error *err)
+{
+ QError *qerr;
+
+ qerr = qerror_new();
+ loc_save(&qerr->loc);
+ qerr->err_msg = g_strdup(err->msg);
+ qerr->err_class = err->err_class;
+
+ if (monitor_cur_is_qmp()) {
+ monitor_set_error(cur_mon, qerr);
+ } else {
+ qerror_print(qerr);
+ QDECREF(qerr);
+ }
+}
+
+void assert_no_error(Error *err)
+{
+ if (err) {
+ qerror_report_err(err);
+ abort();
+ }
+}
+
+/**
+ * qobject_to_qerror(): Convert a QObject into a QError
+ */
+static QError *qobject_to_qerror(const QObject *obj)
+{
+ if (qobject_type(obj) != QTYPE_QERROR) {
+ return NULL;
+ }
+
+ return container_of(obj, QError, base);
+}
+
+/**
+ * qerror_destroy_obj(): Free all memory allocated by a QError
+ */
+static void qerror_destroy_obj(QObject *obj)
+{
+ QError *qerr;
+
+ assert(obj != NULL);
+ qerr = qobject_to_qerror(obj);
+
+ g_free(qerr->err_msg);
+ g_free(qerr);
+}
diff --git a/contrib/qemu/qobject/qfloat.c b/contrib/qemu/qobject/qfloat.c
new file mode 100644
index 00000000000..7de0992dba7
--- /dev/null
+++ b/contrib/qemu/qobject/qfloat.c
@@ -0,0 +1,68 @@
+/*
+ * QFloat Module
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qapi/qmp/qfloat.h"
+#include "qapi/qmp/qobject.h"
+#include "qemu-common.h"
+
+static void qfloat_destroy_obj(QObject *obj);
+
+static const QType qfloat_type = {
+ .code = QTYPE_QFLOAT,
+ .destroy = qfloat_destroy_obj,
+};
+
+/**
+ * qfloat_from_int(): Create a new QFloat from a float
+ *
+ * Return strong reference.
+ */
+QFloat *qfloat_from_double(double value)
+{
+ QFloat *qf;
+
+ qf = g_malloc(sizeof(*qf));
+ qf->value = value;
+ QOBJECT_INIT(qf, &qfloat_type);
+
+ return qf;
+}
+
+/**
+ * qfloat_get_double(): Get the stored float
+ */
+double qfloat_get_double(const QFloat *qf)
+{
+ return qf->value;
+}
+
+/**
+ * qobject_to_qfloat(): Convert a QObject into a QFloat
+ */
+QFloat *qobject_to_qfloat(const QObject *obj)
+{
+ if (qobject_type(obj) != QTYPE_QFLOAT)
+ return NULL;
+
+ return container_of(obj, QFloat, base);
+}
+
+/**
+ * qfloat_destroy_obj(): Free all memory allocated by a
+ * QFloat object
+ */
+static void qfloat_destroy_obj(QObject *obj)
+{
+ assert(obj != NULL);
+ g_free(qobject_to_qfloat(obj));
+}
diff --git a/contrib/qemu/qobject/qint.c b/contrib/qemu/qobject/qint.c
new file mode 100644
index 00000000000..86b9b04f0b6
--- /dev/null
+++ b/contrib/qemu/qobject/qint.c
@@ -0,0 +1,67 @@
+/*
+ * QInt Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#include "qapi/qmp/qint.h"
+#include "qapi/qmp/qobject.h"
+#include "qemu-common.h"
+
+static void qint_destroy_obj(QObject *obj);
+
+static const QType qint_type = {
+ .code = QTYPE_QINT,
+ .destroy = qint_destroy_obj,
+};
+
+/**
+ * qint_from_int(): Create a new QInt from an int64_t
+ *
+ * Return strong reference.
+ */
+QInt *qint_from_int(int64_t value)
+{
+ QInt *qi;
+
+ qi = g_malloc(sizeof(*qi));
+ qi->value = value;
+ QOBJECT_INIT(qi, &qint_type);
+
+ return qi;
+}
+
+/**
+ * qint_get_int(): Get the stored integer
+ */
+int64_t qint_get_int(const QInt *qi)
+{
+ return qi->value;
+}
+
+/**
+ * qobject_to_qint(): Convert a QObject into a QInt
+ */
+QInt *qobject_to_qint(const QObject *obj)
+{
+ if (qobject_type(obj) != QTYPE_QINT)
+ return NULL;
+
+ return container_of(obj, QInt, base);
+}
+
+/**
+ * qint_destroy_obj(): Free all memory allocated by a
+ * QInt object
+ */
+static void qint_destroy_obj(QObject *obj)
+{
+ assert(obj != NULL);
+ g_free(qobject_to_qint(obj));
+}
diff --git a/contrib/qemu/qobject/qjson.c b/contrib/qemu/qobject/qjson.c
new file mode 100644
index 00000000000..19085a1bb7f
--- /dev/null
+++ b/contrib/qemu/qobject/qjson.c
@@ -0,0 +1,282 @@
+/*
+ * QObject JSON integration
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qapi/qmp/json-lexer.h"
+#include "qapi/qmp/json-parser.h"
+#include "qapi/qmp/json-streamer.h"
+#include "qapi/qmp/qjson.h"
+#include "qapi/qmp/qint.h"
+#include "qapi/qmp/qlist.h"
+#include "qapi/qmp/qbool.h"
+#include "qapi/qmp/qfloat.h"
+#include "qapi/qmp/qdict.h"
+
+typedef struct JSONParsingState
+{
+ JSONMessageParser parser;
+ va_list *ap;
+ QObject *result;
+} JSONParsingState;
+
+static void parse_json(JSONMessageParser *parser, QList *tokens)
+{
+ JSONParsingState *s = container_of(parser, JSONParsingState, parser);
+ s->result = json_parser_parse(tokens, s->ap);
+}
+
+QObject *qobject_from_jsonv(const char *string, va_list *ap)
+{
+ JSONParsingState state = {};
+
+ state.ap = ap;
+
+ json_message_parser_init(&state.parser, parse_json);
+ json_message_parser_feed(&state.parser, string, strlen(string));
+ json_message_parser_flush(&state.parser);
+ json_message_parser_destroy(&state.parser);
+
+ return state.result;
+}
+
+QObject *qobject_from_json(const char *string)
+{
+ return qobject_from_jsonv(string, NULL);
+}
+
+/*
+ * IMPORTANT: This function aborts on error, thus it must not
+ * be used with untrusted arguments.
+ */
+QObject *qobject_from_jsonf(const char *string, ...)
+{
+ QObject *obj;
+ va_list ap;
+
+ va_start(ap, string);
+ obj = qobject_from_jsonv(string, &ap);
+ va_end(ap);
+
+ assert(obj != NULL);
+ return obj;
+}
+
+typedef struct ToJsonIterState
+{
+ int indent;
+ int pretty;
+ int count;
+ QString *str;
+} ToJsonIterState;
+
+static void to_json(const QObject *obj, QString *str, int pretty, int indent);
+
+static void to_json_dict_iter(const char *key, QObject *obj, void *opaque)
+{
+ ToJsonIterState *s = opaque;
+ QString *qkey;
+ int j;
+
+ if (s->count)
+ qstring_append(s->str, ", ");
+
+ if (s->pretty) {
+ qstring_append(s->str, "\n");
+ for (j = 0 ; j < s->indent ; j++)
+ qstring_append(s->str, " ");
+ }
+
+ qkey = qstring_from_str(key);
+ to_json(QOBJECT(qkey), s->str, s->pretty, s->indent);
+ QDECREF(qkey);
+
+ qstring_append(s->str, ": ");
+ to_json(obj, s->str, s->pretty, s->indent);
+ s->count++;
+}
+
+static void to_json_list_iter(QObject *obj, void *opaque)
+{
+ ToJsonIterState *s = opaque;
+ int j;
+
+ if (s->count)
+ qstring_append(s->str, ", ");
+
+ if (s->pretty) {
+ qstring_append(s->str, "\n");
+ for (j = 0 ; j < s->indent ; j++)
+ qstring_append(s->str, " ");
+ }
+
+ to_json(obj, s->str, s->pretty, s->indent);
+ s->count++;
+}
+
+static void to_json(const QObject *obj, QString *str, int pretty, int indent)
+{
+ switch (qobject_type(obj)) {
+ case QTYPE_QINT: {
+ QInt *val = qobject_to_qint(obj);
+ char buffer[1024];
+
+ snprintf(buffer, sizeof(buffer), "%" PRId64, qint_get_int(val));
+ qstring_append(str, buffer);
+ break;
+ }
+ case QTYPE_QSTRING: {
+ QString *val = qobject_to_qstring(obj);
+ const char *ptr;
+ int cp;
+ char buf[16];
+ char *end;
+
+ ptr = qstring_get_str(val);
+ qstring_append(str, "\"");
+
+ for (; *ptr; ptr = end) {
+ cp = mod_utf8_codepoint(ptr, 6, &end);
+ switch (cp) {
+ case '\"':
+ qstring_append(str, "\\\"");
+ break;
+ case '\\':
+ qstring_append(str, "\\\\");
+ break;
+ case '\b':
+ qstring_append(str, "\\b");
+ break;
+ case '\f':
+ qstring_append(str, "\\f");
+ break;
+ case '\n':
+ qstring_append(str, "\\n");
+ break;
+ case '\r':
+ qstring_append(str, "\\r");
+ break;
+ case '\t':
+ qstring_append(str, "\\t");
+ break;
+ default:
+ if (cp < 0) {
+ cp = 0xFFFD; /* replacement character */
+ }
+ if (cp > 0xFFFF) {
+ /* beyond BMP; need a surrogate pair */
+ snprintf(buf, sizeof(buf), "\\u%04X\\u%04X",
+ 0xD800 + ((cp - 0x10000) >> 10),
+ 0xDC00 + ((cp - 0x10000) & 0x3FF));
+ } else if (cp < 0x20 || cp >= 0x7F) {
+ snprintf(buf, sizeof(buf), "\\u%04X", cp);
+ } else {
+ buf[0] = cp;
+ buf[1] = 0;
+ }
+ qstring_append(str, buf);
+ }
+ };
+
+ qstring_append(str, "\"");
+ break;
+ }
+ case QTYPE_QDICT: {
+ ToJsonIterState s;
+ QDict *val = qobject_to_qdict(obj);
+
+ s.count = 0;
+ s.str = str;
+ s.indent = indent + 1;
+ s.pretty = pretty;
+ qstring_append(str, "{");
+ qdict_iter(val, to_json_dict_iter, &s);
+ if (pretty) {
+ int j;
+ qstring_append(str, "\n");
+ for (j = 0 ; j < indent ; j++)
+ qstring_append(str, " ");
+ }
+ qstring_append(str, "}");
+ break;
+ }
+ case QTYPE_QLIST: {
+ ToJsonIterState s;
+ QList *val = qobject_to_qlist(obj);
+
+ s.count = 0;
+ s.str = str;
+ s.indent = indent + 1;
+ s.pretty = pretty;
+ qstring_append(str, "[");
+ qlist_iter(val, (void *)to_json_list_iter, &s);
+ if (pretty) {
+ int j;
+ qstring_append(str, "\n");
+ for (j = 0 ; j < indent ; j++)
+ qstring_append(str, " ");
+ }
+ qstring_append(str, "]");
+ break;
+ }
+ case QTYPE_QFLOAT: {
+ QFloat *val = qobject_to_qfloat(obj);
+ char buffer[1024];
+ int len;
+
+ len = snprintf(buffer, sizeof(buffer), "%f", qfloat_get_double(val));
+ while (len > 0 && buffer[len - 1] == '0') {
+ len--;
+ }
+
+ if (len && buffer[len - 1] == '.') {
+ buffer[len - 1] = 0;
+ } else {
+ buffer[len] = 0;
+ }
+
+ qstring_append(str, buffer);
+ break;
+ }
+ case QTYPE_QBOOL: {
+ QBool *val = qobject_to_qbool(obj);
+
+ if (qbool_get_int(val)) {
+ qstring_append(str, "true");
+ } else {
+ qstring_append(str, "false");
+ }
+ break;
+ }
+ case QTYPE_QERROR:
+ /* XXX: should QError be emitted? */
+ case QTYPE_NONE:
+ break;
+ }
+}
+
+QString *qobject_to_json(const QObject *obj)
+{
+ QString *str = qstring_new();
+
+ to_json(obj, str, 0, 0);
+
+ return str;
+}
+
+QString *qobject_to_json_pretty(const QObject *obj)
+{
+ QString *str = qstring_new();
+
+ to_json(obj, str, 1, 0);
+
+ return str;
+}
diff --git a/contrib/qemu/qobject/qlist.c b/contrib/qemu/qobject/qlist.c
new file mode 100644
index 00000000000..1ced0de58e2
--- /dev/null
+++ b/contrib/qemu/qobject/qlist.c
@@ -0,0 +1,170 @@
+/*
+ * QList Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#include "qapi/qmp/qlist.h"
+#include "qapi/qmp/qobject.h"
+#include "qemu/queue.h"
+#include "qemu-common.h"
+
+static void qlist_destroy_obj(QObject *obj);
+
+static const QType qlist_type = {
+ .code = QTYPE_QLIST,
+ .destroy = qlist_destroy_obj,
+};
+
+/**
+ * qlist_new(): Create a new QList
+ *
+ * Return strong reference.
+ */
+QList *qlist_new(void)
+{
+ QList *qlist;
+
+ qlist = g_malloc(sizeof(*qlist));
+ QTAILQ_INIT(&qlist->head);
+ QOBJECT_INIT(qlist, &qlist_type);
+
+ return qlist;
+}
+
+static void qlist_copy_elem(QObject *obj, void *opaque)
+{
+ QList *dst = opaque;
+
+ qobject_incref(obj);
+ qlist_append_obj(dst, obj);
+}
+
+QList *qlist_copy(QList *src)
+{
+ QList *dst = qlist_new();
+
+ qlist_iter(src, qlist_copy_elem, dst);
+
+ return dst;
+}
+
+/**
+ * qlist_append_obj(): Append an QObject into QList
+ *
+ * NOTE: ownership of 'value' is transferred to the QList
+ */
+void qlist_append_obj(QList *qlist, QObject *value)
+{
+ QListEntry *entry;
+
+ entry = g_malloc(sizeof(*entry));
+ entry->value = value;
+
+ QTAILQ_INSERT_TAIL(&qlist->head, entry, next);
+}
+
+/**
+ * qlist_iter(): Iterate over all the list's stored values.
+ *
+ * This function allows the user to provide an iterator, which will be
+ * called for each stored value in the list.
+ */
+void qlist_iter(const QList *qlist,
+ void (*iter)(QObject *obj, void *opaque), void *opaque)
+{
+ QListEntry *entry;
+
+ QTAILQ_FOREACH(entry, &qlist->head, next)
+ iter(entry->value, opaque);
+}
+
+QObject *qlist_pop(QList *qlist)
+{
+ QListEntry *entry;
+ QObject *ret;
+
+ if (qlist == NULL || QTAILQ_EMPTY(&qlist->head)) {
+ return NULL;
+ }
+
+ entry = QTAILQ_FIRST(&qlist->head);
+ QTAILQ_REMOVE(&qlist->head, entry, next);
+
+ ret = entry->value;
+ g_free(entry);
+
+ return ret;
+}
+
+QObject *qlist_peek(QList *qlist)
+{
+ QListEntry *entry;
+ QObject *ret;
+
+ if (qlist == NULL || QTAILQ_EMPTY(&qlist->head)) {
+ return NULL;
+ }
+
+ entry = QTAILQ_FIRST(&qlist->head);
+
+ ret = entry->value;
+
+ return ret;
+}
+
+int qlist_empty(const QList *qlist)
+{
+ return QTAILQ_EMPTY(&qlist->head);
+}
+
+static void qlist_size_iter(QObject *obj, void *opaque)
+{
+ size_t *count = opaque;
+ (*count)++;
+}
+
+size_t qlist_size(const QList *qlist)
+{
+ size_t count = 0;
+ qlist_iter(qlist, qlist_size_iter, &count);
+ return count;
+}
+
+/**
+ * qobject_to_qlist(): Convert a QObject into a QList
+ */
+QList *qobject_to_qlist(const QObject *obj)
+{
+ if (qobject_type(obj) != QTYPE_QLIST) {
+ return NULL;
+ }
+
+ return container_of(obj, QList, base);
+}
+
+/**
+ * qlist_destroy_obj(): Free all the memory allocated by a QList
+ */
+static void qlist_destroy_obj(QObject *obj)
+{
+ QList *qlist;
+ QListEntry *entry, *next_entry;
+
+ assert(obj != NULL);
+ qlist = qobject_to_qlist(obj);
+
+ QTAILQ_FOREACH_SAFE(entry, &qlist->head, next, next_entry) {
+ QTAILQ_REMOVE(&qlist->head, entry, next);
+ qobject_decref(entry->value);
+ g_free(entry);
+ }
+
+ g_free(qlist);
+}
diff --git a/contrib/qemu/qobject/qstring.c b/contrib/qemu/qobject/qstring.c
new file mode 100644
index 00000000000..607b7a142c6
--- /dev/null
+++ b/contrib/qemu/qobject/qstring.c
@@ -0,0 +1,149 @@
+/*
+ * QString Module
+ *
+ * Copyright (C) 2009 Red Hat Inc.
+ *
+ * Authors:
+ * Luiz Capitulino <lcapitulino@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2.1 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ */
+
+#include "qapi/qmp/qobject.h"
+#include "qapi/qmp/qstring.h"
+#include "qemu-common.h"
+
+static void qstring_destroy_obj(QObject *obj);
+
+static const QType qstring_type = {
+ .code = QTYPE_QSTRING,
+ .destroy = qstring_destroy_obj,
+};
+
+/**
+ * qstring_new(): Create a new empty QString
+ *
+ * Return strong reference.
+ */
+QString *qstring_new(void)
+{
+ return qstring_from_str("");
+}
+
+/**
+ * qstring_get_length(): Get the length of a QString
+ */
+size_t qstring_get_length(const QString *qstring)
+{
+ return qstring->length;
+}
+
+/**
+ * qstring_from_substr(): Create a new QString from a C string substring
+ *
+ * Return string reference
+ */
+QString *qstring_from_substr(const char *str, int start, int end)
+{
+ QString *qstring;
+
+ qstring = g_malloc(sizeof(*qstring));
+
+ qstring->length = end - start + 1;
+ qstring->capacity = qstring->length;
+
+ qstring->string = g_malloc(qstring->capacity + 1);
+ memcpy(qstring->string, str + start, qstring->length);
+ qstring->string[qstring->length] = 0;
+
+ QOBJECT_INIT(qstring, &qstring_type);
+
+ return qstring;
+}
+
+/**
+ * qstring_from_str(): Create a new QString from a regular C string
+ *
+ * Return strong reference.
+ */
+QString *qstring_from_str(const char *str)
+{
+ return qstring_from_substr(str, 0, strlen(str) - 1);
+}
+
+static void capacity_increase(QString *qstring, size_t len)
+{
+ if (qstring->capacity < (qstring->length + len)) {
+ qstring->capacity += len;
+ qstring->capacity *= 2; /* use exponential growth */
+
+ qstring->string = g_realloc(qstring->string, qstring->capacity + 1);
+ }
+}
+
+/* qstring_append(): Append a C string to a QString
+ */
+void qstring_append(QString *qstring, const char *str)
+{
+ size_t len = strlen(str);
+
+ capacity_increase(qstring, len);
+ memcpy(qstring->string + qstring->length, str, len);
+ qstring->length += len;
+ qstring->string[qstring->length] = 0;
+}
+
+void qstring_append_int(QString *qstring, int64_t value)
+{
+ char num[32];
+
+ snprintf(num, sizeof(num), "%" PRId64, value);
+ qstring_append(qstring, num);
+}
+
+/**
+ * qstring_append_chr(): Append a C char to a QString
+ */
+void qstring_append_chr(QString *qstring, int c)
+{
+ capacity_increase(qstring, 1);
+ qstring->string[qstring->length++] = c;
+ qstring->string[qstring->length] = 0;
+}
+
+/**
+ * qobject_to_qstring(): Convert a QObject to a QString
+ */
+QString *qobject_to_qstring(const QObject *obj)
+{
+ if (qobject_type(obj) != QTYPE_QSTRING)
+ return NULL;
+
+ return container_of(obj, QString, base);
+}
+
+/**
+ * qstring_get_str(): Return a pointer to the stored string
+ *
+ * NOTE: Should be used with caution, if the object is deallocated
+ * this pointer becomes invalid.
+ */
+const char *qstring_get_str(const QString *qstring)
+{
+ return qstring->string;
+}
+
+/**
+ * qstring_destroy_obj(): Free all memory allocated by a QString
+ * object
+ */
+static void qstring_destroy_obj(QObject *obj)
+{
+ QString *qs;
+
+ assert(obj != NULL);
+ qs = qobject_to_qstring(obj);
+ g_free(qs->string);
+ g_free(qs);
+}
diff --git a/contrib/qemu/trace/generated-tracers.h b/contrib/qemu/trace/generated-tracers.h
new file mode 100644
index 00000000000..b512660f358
--- /dev/null
+++ b/contrib/qemu/trace/generated-tracers.h
@@ -0,0 +1,3759 @@
+/* This file is autogenerated by tracetool, do not edit. */
+
+#ifndef TRACE__GENERATED_TRACERS_H
+#define TRACE__GENERATED_TRACERS_H
+
+#include "qemu-common.h"
+
+static inline void trace_qxl_interface_set_mm_time(int qid, uint32_t mm_time)
+{
+}
+
+static inline void trace_qxl_io_write_vga(int qid, const char * mode, uint32_t addr, uint32_t val)
+{
+}
+
+static inline void trace_g_malloc(size_t size, void * ptr)
+{
+}
+
+static inline void trace_g_realloc(void * ptr, size_t size, void * newptr)
+{
+}
+
+static inline void trace_g_free(void * ptr)
+{
+}
+
+static inline void trace_qemu_memalign(size_t alignment, size_t size, void * ptr)
+{
+}
+
+static inline void trace_qemu_anon_ram_alloc(size_t size, void * ptr)
+{
+}
+
+static inline void trace_qemu_vfree(void * ptr)
+{
+}
+
+static inline void trace_qemu_anon_ram_free(void * ptr, size_t size)
+{
+}
+
+static inline void trace_virtqueue_fill(void * vq, const void * elem, unsigned int len, unsigned int idx)
+{
+}
+
+static inline void trace_virtqueue_flush(void * vq, unsigned int count)
+{
+}
+
+static inline void trace_virtqueue_pop(void * vq, void * elem, unsigned int in_num, unsigned int out_num)
+{
+}
+
+static inline void trace_virtio_queue_notify(void * vdev, int n, void * vq)
+{
+}
+
+static inline void trace_virtio_irq(void * vq)
+{
+}
+
+static inline void trace_virtio_notify(void * vdev, void * vq)
+{
+}
+
+static inline void trace_virtio_set_status(void * vdev, uint8_t val)
+{
+}
+
+static inline void trace_virtio_serial_send_control_event(unsigned int port, uint16_t event, uint16_t value)
+{
+}
+
+static inline void trace_virtio_serial_throttle_port(unsigned int port, bool throttle)
+{
+}
+
+static inline void trace_virtio_serial_handle_control_message(uint16_t event, uint16_t value)
+{
+}
+
+static inline void trace_virtio_serial_handle_control_message_port(unsigned int port)
+{
+}
+
+static inline void trace_virtio_console_flush_buf(unsigned int port, size_t len, ssize_t ret)
+{
+}
+
+static inline void trace_virtio_console_chr_read(unsigned int port, int size)
+{
+}
+
+static inline void trace_virtio_console_chr_event(unsigned int port, int event)
+{
+}
+
+static inline void trace_bdrv_open_common(void * bs, const char * filename, int flags, const char * format_name)
+{
+}
+
+static inline void trace_multiwrite_cb(void * mcb, int ret)
+{
+}
+
+static inline void trace_bdrv_aio_multiwrite(void * mcb, int num_callbacks, int num_reqs)
+{
+}
+
+static inline void trace_bdrv_aio_discard(void * bs, int64_t sector_num, int nb_sectors, void * opaque)
+{
+}
+
+static inline void trace_bdrv_aio_flush(void * bs, void * opaque)
+{
+}
+
+static inline void trace_bdrv_aio_readv(void * bs, int64_t sector_num, int nb_sectors, void * opaque)
+{
+}
+
+static inline void trace_bdrv_aio_writev(void * bs, int64_t sector_num, int nb_sectors, void * opaque)
+{
+}
+
+static inline void trace_bdrv_lock_medium(void * bs, bool locked)
+{
+}
+
+static inline void trace_bdrv_co_readv(void * bs, int64_t sector_num, int nb_sector)
+{
+}
+
+static inline void trace_bdrv_co_copy_on_readv(void * bs, int64_t sector_num, int nb_sector)
+{
+}
+
+static inline void trace_bdrv_co_writev(void * bs, int64_t sector_num, int nb_sector)
+{
+}
+
+static inline void trace_bdrv_co_write_zeroes(void * bs, int64_t sector_num, int nb_sector)
+{
+}
+
+static inline void trace_bdrv_co_io_em(void * bs, int64_t sector_num, int nb_sectors, int is_write, void * acb)
+{
+}
+
+static inline void trace_bdrv_co_do_copy_on_readv(void * bs, int64_t sector_num, int nb_sectors, int64_t cluster_sector_num, int cluster_nb_sectors)
+{
+}
+
+static inline void trace_stream_one_iteration(void * s, int64_t sector_num, int nb_sectors, int is_allocated)
+{
+}
+
+static inline void trace_stream_start(void * bs, void * base, void * s, void * co, void * opaque)
+{
+}
+
+static inline void trace_commit_one_iteration(void * s, int64_t sector_num, int nb_sectors, int is_allocated)
+{
+}
+
+static inline void trace_commit_start(void * bs, void * base, void * top, void * s, void * co, void * opaque)
+{
+}
+
+static inline void trace_mirror_start(void * bs, void * s, void * co, void * opaque)
+{
+}
+
+static inline void trace_mirror_restart_iter(void * s, int64_t cnt)
+{
+}
+
+static inline void trace_mirror_before_flush(void * s)
+{
+}
+
+static inline void trace_mirror_before_drain(void * s, int64_t cnt)
+{
+}
+
+static inline void trace_mirror_before_sleep(void * s, int64_t cnt, int synced)
+{
+}
+
+static inline void trace_mirror_one_iteration(void * s, int64_t sector_num, int nb_sectors)
+{
+}
+
+static inline void trace_mirror_cow(void * s, int64_t sector_num)
+{
+}
+
+static inline void trace_mirror_iteration_done(void * s, int64_t sector_num, int nb_sectors, int ret)
+{
+}
+
+static inline void trace_mirror_yield(void * s, int64_t cnt, int buf_free_count, int in_flight)
+{
+}
+
+static inline void trace_mirror_yield_in_flight(void * s, int64_t sector_num, int in_flight)
+{
+}
+
+static inline void trace_mirror_yield_buf_busy(void * s, int nb_chunks, int in_flight)
+{
+}
+
+static inline void trace_mirror_break_buf_busy(void * s, int nb_chunks, int in_flight)
+{
+}
+
+static inline void trace_backup_do_cow_enter(void * job, int64_t start, int64_t sector_num, int nb_sectors)
+{
+}
+
+static inline void trace_backup_do_cow_return(void * job, int64_t sector_num, int nb_sectors, int ret)
+{
+}
+
+static inline void trace_backup_do_cow_skip(void * job, int64_t start)
+{
+}
+
+static inline void trace_backup_do_cow_process(void * job, int64_t start)
+{
+}
+
+static inline void trace_backup_do_cow_read_fail(void * job, int64_t start, int ret)
+{
+}
+
+static inline void trace_backup_do_cow_write_fail(void * job, int64_t start, int ret)
+{
+}
+
+static inline void trace_qmp_block_job_cancel(void * job)
+{
+}
+
+static inline void trace_qmp_block_job_pause(void * job)
+{
+}
+
+static inline void trace_qmp_block_job_resume(void * job)
+{
+}
+
+static inline void trace_qmp_block_job_complete(void * job)
+{
+}
+
+static inline void trace_block_job_cb(void * bs, void * job, int ret)
+{
+}
+
+static inline void trace_qmp_block_stream(void * bs, void * job)
+{
+}
+
+static inline void trace_virtio_blk_req_complete(void * req, int status)
+{
+}
+
+static inline void trace_virtio_blk_rw_complete(void * req, int ret)
+{
+}
+
+static inline void trace_virtio_blk_handle_write(void * req, uint64_t sector, size_t nsectors)
+{
+}
+
+static inline void trace_virtio_blk_handle_read(void * req, uint64_t sector, size_t nsectors)
+{
+}
+
+static inline void trace_virtio_blk_data_plane_start(void * s)
+{
+}
+
+static inline void trace_virtio_blk_data_plane_stop(void * s)
+{
+}
+
+static inline void trace_virtio_blk_data_plane_process_request(void * s, unsigned int out_num, unsigned int in_num, unsigned int head)
+{
+}
+
+static inline void trace_virtio_blk_data_plane_complete_request(void * s, unsigned int head, int ret)
+{
+}
+
+static inline void trace_vring_setup(uint64_t physical, void * desc, void * avail, void * used)
+{
+}
+
+static inline void trace_thread_pool_submit(void * pool, void * req, void * opaque)
+{
+}
+
+static inline void trace_thread_pool_complete(void * pool, void * req, void * opaque, int ret)
+{
+}
+
+static inline void trace_thread_pool_cancel(void * req, void * opaque)
+{
+}
+
+static inline void trace_paio_submit(void * acb, void * opaque, int64_t sector_num, int nb_sectors, int type)
+{
+}
+
+static inline void trace_paio_complete(void * acb, void * opaque, int ret)
+{
+}
+
+static inline void trace_paio_cancel(void * acb, void * opaque)
+{
+}
+
+static inline void trace_cpu_in(unsigned int addr, unsigned int val)
+{
+}
+
+static inline void trace_cpu_out(unsigned int addr, unsigned int val)
+{
+}
+
+static inline void trace_balloon_event(void * opaque, unsigned long addr)
+{
+}
+
+static inline void trace_apic_local_deliver(int vector, uint32_t lvt)
+{
+}
+
+static inline void trace_apic_deliver_irq(uint8_t dest, uint8_t dest_mode, uint8_t delivery_mode, uint8_t vector_num, uint8_t trigger_mode)
+{
+}
+
+static inline void trace_cpu_set_apic_base(uint64_t val)
+{
+}
+
+static inline void trace_cpu_get_apic_base(uint64_t val)
+{
+}
+
+static inline void trace_apic_mem_readl(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_apic_mem_writel(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_apic_report_irq_delivered(int apic_irq_delivered)
+{
+}
+
+static inline void trace_apic_reset_irq_delivered(int apic_irq_delivered)
+{
+}
+
+static inline void trace_apic_get_irq_delivered(int apic_irq_delivered)
+{
+}
+
+static inline void trace_cs4231_mem_readl_dreg(uint32_t reg, uint32_t ret)
+{
+}
+
+static inline void trace_cs4231_mem_readl_reg(uint32_t reg, uint32_t ret)
+{
+}
+
+static inline void trace_cs4231_mem_writel_reg(uint32_t reg, uint32_t old, uint32_t val)
+{
+}
+
+static inline void trace_cs4231_mem_writel_dreg(uint32_t reg, uint32_t old, uint32_t val)
+{
+}
+
+static inline void trace_nvram_read(uint32_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_nvram_write(uint32_t addr, uint32_t old, uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_writel_mer(uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_writel_mdr(uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_writel_mfsr(uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_writel_vcr(uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_writel_dr(uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_writel_ecr0(uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_writel_ecr1(uint32_t val)
+{
+}
+
+static inline void trace_ecc_mem_readl_mer(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_mdr(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_mfsr(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_vcr(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_mfar0(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_mfar1(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_dr(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_ecr0(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_mem_readl_ecr1(uint32_t ret)
+{
+}
+
+static inline void trace_ecc_diag_mem_writeb(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_ecc_diag_mem_readb(uint64_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_fw_cfg_write(void * s, uint8_t value)
+{
+}
+
+static inline void trace_fw_cfg_select(void * s, uint16_t key, int ret)
+{
+}
+
+static inline void trace_fw_cfg_read(void * s, uint8_t ret)
+{
+}
+
+static inline void trace_fw_cfg_add_file_dupe(void * s, char * name)
+{
+}
+
+static inline void trace_fw_cfg_add_file(void * s, int index, char * name, size_t len)
+{
+}
+
+static inline void trace_hd_geometry_lchs_guess(void * bs, int cyls, int heads, int secs)
+{
+}
+
+static inline void trace_hd_geometry_guess(void * bs, uint32_t cyls, uint32_t heads, uint32_t secs, int trans)
+{
+}
+
+static inline void trace_jazz_led_read(uint64_t addr, uint8_t val)
+{
+}
+
+static inline void trace_jazz_led_write(uint64_t addr, uint8_t new)
+{
+}
+
+static inline void trace_lance_mem_readw(uint64_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_lance_mem_writew(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_slavio_intctl_mem_readl(uint32_t cpu, uint64_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_slavio_intctl_mem_writel(uint32_t cpu, uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_slavio_intctl_mem_writel_clear(uint32_t cpu, uint32_t val, uint32_t intreg_pending)
+{
+}
+
+static inline void trace_slavio_intctl_mem_writel_set(uint32_t cpu, uint32_t val, uint32_t intreg_pending)
+{
+}
+
+static inline void trace_slavio_intctlm_mem_readl(uint64_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_slavio_intctlm_mem_writel(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_slavio_intctlm_mem_writel_enable(uint32_t val, uint32_t intregm_disabled)
+{
+}
+
+static inline void trace_slavio_intctlm_mem_writel_disable(uint32_t val, uint32_t intregm_disabled)
+{
+}
+
+static inline void trace_slavio_intctlm_mem_writel_target(uint32_t cpu)
+{
+}
+
+static inline void trace_slavio_check_interrupts(uint32_t pending, uint32_t intregm_disabled)
+{
+}
+
+static inline void trace_slavio_set_irq(uint32_t target_cpu, int irq, uint32_t pil, int level)
+{
+}
+
+static inline void trace_slavio_set_timer_irq_cpu(int cpu, int level)
+{
+}
+
+static inline void trace_slavio_misc_update_irq_raise(void)
+{
+}
+
+static inline void trace_slavio_misc_update_irq_lower(void)
+{
+}
+
+static inline void trace_slavio_set_power_fail(int power_failing, uint8_t config)
+{
+}
+
+static inline void trace_slavio_cfg_mem_writeb(uint32_t val)
+{
+}
+
+static inline void trace_slavio_cfg_mem_readb(uint32_t ret)
+{
+}
+
+static inline void trace_slavio_diag_mem_writeb(uint32_t val)
+{
+}
+
+static inline void trace_slavio_diag_mem_readb(uint32_t ret)
+{
+}
+
+static inline void trace_slavio_mdm_mem_writeb(uint32_t val)
+{
+}
+
+static inline void trace_slavio_mdm_mem_readb(uint32_t ret)
+{
+}
+
+static inline void trace_slavio_aux1_mem_writeb(uint32_t val)
+{
+}
+
+static inline void trace_slavio_aux1_mem_readb(uint32_t ret)
+{
+}
+
+static inline void trace_slavio_aux2_mem_writeb(uint32_t val)
+{
+}
+
+static inline void trace_slavio_aux2_mem_readb(uint32_t ret)
+{
+}
+
+static inline void trace_apc_mem_writeb(uint32_t val)
+{
+}
+
+static inline void trace_apc_mem_readb(uint32_t ret)
+{
+}
+
+static inline void trace_slavio_sysctrl_mem_writel(uint32_t val)
+{
+}
+
+static inline void trace_slavio_sysctrl_mem_readl(uint32_t ret)
+{
+}
+
+static inline void trace_slavio_led_mem_writew(uint32_t val)
+{
+}
+
+static inline void trace_slavio_led_mem_readw(uint32_t ret)
+{
+}
+
+static inline void trace_slavio_timer_get_out(uint64_t limit, uint32_t counthigh, uint32_t count)
+{
+}
+
+static inline void trace_slavio_timer_irq(uint32_t counthigh, uint32_t count)
+{
+}
+
+static inline void trace_slavio_timer_mem_readl_invalid(uint64_t addr)
+{
+}
+
+static inline void trace_slavio_timer_mem_readl(uint64_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_limit(unsigned int timer_index, uint64_t count)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_counter_invalid(void)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_status_start(unsigned int timer_index)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_status_stop(unsigned int timer_index)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_mode_user(unsigned int timer_index)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_mode_counter(unsigned int timer_index)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_mode_invalid(void)
+{
+}
+
+static inline void trace_slavio_timer_mem_writel_invalid(uint64_t addr)
+{
+}
+
+static inline void trace_ledma_memory_read(uint64_t addr)
+{
+}
+
+static inline void trace_ledma_memory_write(uint64_t addr)
+{
+}
+
+static inline void trace_sparc32_dma_set_irq_raise(void)
+{
+}
+
+static inline void trace_sparc32_dma_set_irq_lower(void)
+{
+}
+
+static inline void trace_espdma_memory_read(uint32_t addr)
+{
+}
+
+static inline void trace_espdma_memory_write(uint32_t addr)
+{
+}
+
+static inline void trace_sparc32_dma_mem_readl(uint64_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_sparc32_dma_mem_writel(uint64_t addr, uint32_t old, uint32_t val)
+{
+}
+
+static inline void trace_sparc32_dma_enable_raise(void)
+{
+}
+
+static inline void trace_sparc32_dma_enable_lower(void)
+{
+}
+
+static inline void trace_sun4m_cpu_interrupt(unsigned int level)
+{
+}
+
+static inline void trace_sun4m_cpu_reset_interrupt(unsigned int level)
+{
+}
+
+static inline void trace_sun4m_cpu_set_irq_raise(int level)
+{
+}
+
+static inline void trace_sun4m_cpu_set_irq_lower(int level)
+{
+}
+
+static inline void trace_sun4m_iommu_mem_readl(uint64_t addr, uint32_t ret)
+{
+}
+
+static inline void trace_sun4m_iommu_mem_writel(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_sun4m_iommu_mem_writel_ctrl(uint64_t iostart)
+{
+}
+
+static inline void trace_sun4m_iommu_mem_writel_tlbflush(uint32_t val)
+{
+}
+
+static inline void trace_sun4m_iommu_mem_writel_pgflush(uint32_t val)
+{
+}
+
+static inline void trace_sun4m_iommu_page_get_flags(uint64_t pa, uint64_t iopte, uint32_t ret)
+{
+}
+
+static inline void trace_sun4m_iommu_translate_pa(uint64_t addr, uint64_t pa, uint32_t iopte)
+{
+}
+
+static inline void trace_sun4m_iommu_bad_addr(uint64_t addr)
+{
+}
+
+static inline void trace_usb_packet_state_change(int bus, const char * port, int ep, void * p, const char * o, const char * n)
+{
+}
+
+static inline void trace_usb_packet_state_fault(int bus, const char * port, int ep, void * p, const char * o, const char * n)
+{
+}
+
+static inline void trace_usb_port_claim(int bus, const char * port)
+{
+}
+
+static inline void trace_usb_port_attach(int bus, const char * port, const char * devspeed, const char * portspeed)
+{
+}
+
+static inline void trace_usb_port_detach(int bus, const char * port)
+{
+}
+
+static inline void trace_usb_port_release(int bus, const char * port)
+{
+}
+
+static inline void trace_usb_ehci_reset(void)
+{
+}
+
+static inline void trace_usb_ehci_opreg_read(uint32_t addr, const char * str, uint32_t val)
+{
+}
+
+static inline void trace_usb_ehci_opreg_write(uint32_t addr, const char * str, uint32_t val)
+{
+}
+
+static inline void trace_usb_ehci_opreg_change(uint32_t addr, const char * str, uint32_t new, uint32_t old)
+{
+}
+
+static inline void trace_usb_ehci_portsc_read(uint32_t addr, uint32_t port, uint32_t val)
+{
+}
+
+static inline void trace_usb_ehci_portsc_write(uint32_t addr, uint32_t port, uint32_t val)
+{
+}
+
+static inline void trace_usb_ehci_portsc_change(uint32_t addr, uint32_t port, uint32_t new, uint32_t old)
+{
+}
+
+static inline void trace_usb_ehci_usbsts(const char * sts, int state)
+{
+}
+
+static inline void trace_usb_ehci_state(const char * schedule, const char * state)
+{
+}
+
+static inline void trace_usb_ehci_qh_ptrs(void * q, uint32_t addr, uint32_t nxt, uint32_t c_qtd, uint32_t n_qtd, uint32_t a_qtd)
+{
+}
+
+static inline void trace_usb_ehci_qh_fields(uint32_t addr, int rl, int mplen, int eps, int ep, int devaddr)
+{
+}
+
+static inline void trace_usb_ehci_qh_bits(uint32_t addr, int c, int h, int dtc, int i)
+{
+}
+
+static inline void trace_usb_ehci_qtd_ptrs(void * q, uint32_t addr, uint32_t nxt, uint32_t altnext)
+{
+}
+
+static inline void trace_usb_ehci_qtd_fields(uint32_t addr, int tbytes, int cpage, int cerr, int pid)
+{
+}
+
+static inline void trace_usb_ehci_qtd_bits(uint32_t addr, int ioc, int active, int halt, int babble, int xacterr)
+{
+}
+
+static inline void trace_usb_ehci_itd(uint32_t addr, uint32_t nxt, uint32_t mplen, uint32_t mult, uint32_t ep, uint32_t devaddr)
+{
+}
+
+static inline void trace_usb_ehci_sitd(uint32_t addr, uint32_t nxt, uint32_t active)
+{
+}
+
+static inline void trace_usb_ehci_port_attach(uint32_t port, const char * owner, const char * device)
+{
+}
+
+static inline void trace_usb_ehci_port_detach(uint32_t port, const char * owner)
+{
+}
+
+static inline void trace_usb_ehci_port_reset(uint32_t port, int enable)
+{
+}
+
+static inline void trace_usb_ehci_data(int rw, uint32_t cpage, uint32_t offset, uint32_t addr, uint32_t len, uint32_t bufpos)
+{
+}
+
+static inline void trace_usb_ehci_queue_action(void * q, const char * action)
+{
+}
+
+static inline void trace_usb_ehci_packet_action(void * q, void * p, const char * action)
+{
+}
+
+static inline void trace_usb_ehci_irq(uint32_t level, uint32_t frindex, uint32_t sts, uint32_t mask)
+{
+}
+
+static inline void trace_usb_ehci_guest_bug(const char * reason)
+{
+}
+
+static inline void trace_usb_ehci_doorbell_ring(void)
+{
+}
+
+static inline void trace_usb_ehci_doorbell_ack(void)
+{
+}
+
+static inline void trace_usb_ehci_dma_error(void)
+{
+}
+
+static inline void trace_usb_uhci_reset(void)
+{
+}
+
+static inline void trace_usb_uhci_schedule_start(void)
+{
+}
+
+static inline void trace_usb_uhci_schedule_stop(void)
+{
+}
+
+static inline void trace_usb_uhci_frame_start(uint32_t num)
+{
+}
+
+static inline void trace_usb_uhci_frame_stop_bandwidth(void)
+{
+}
+
+static inline void trace_usb_uhci_frame_loop_stop_idle(void)
+{
+}
+
+static inline void trace_usb_uhci_frame_loop_continue(void)
+{
+}
+
+static inline void trace_usb_uhci_mmio_readw(uint32_t addr, uint32_t val)
+{
+}
+
+static inline void trace_usb_uhci_mmio_writew(uint32_t addr, uint32_t val)
+{
+}
+
+static inline void trace_usb_uhci_queue_add(uint32_t token)
+{
+}
+
+static inline void trace_usb_uhci_queue_del(uint32_t token, const char * reason)
+{
+}
+
+static inline void trace_usb_uhci_packet_add(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_link_async(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_unlink_async(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_cancel(uint32_t token, uint32_t addr, int done)
+{
+}
+
+static inline void trace_usb_uhci_packet_complete_success(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_complete_shortxfer(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_complete_stall(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_complete_babble(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_complete_error(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_packet_del(uint32_t token, uint32_t addr)
+{
+}
+
+static inline void trace_usb_uhci_qh_load(uint32_t qh)
+{
+}
+
+static inline void trace_usb_uhci_td_load(uint32_t qh, uint32_t td, uint32_t ctrl, uint32_t token)
+{
+}
+
+static inline void trace_usb_uhci_td_queue(uint32_t td, uint32_t ctrl, uint32_t token)
+{
+}
+
+static inline void trace_usb_uhci_td_nextqh(uint32_t qh, uint32_t td)
+{
+}
+
+static inline void trace_usb_uhci_td_async(uint32_t qh, uint32_t td)
+{
+}
+
+static inline void trace_usb_uhci_td_complete(uint32_t qh, uint32_t td)
+{
+}
+
+static inline void trace_usb_xhci_reset(void)
+{
+}
+
+static inline void trace_usb_xhci_run(void)
+{
+}
+
+static inline void trace_usb_xhci_stop(void)
+{
+}
+
+static inline void trace_usb_xhci_cap_read(uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_oper_read(uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_port_read(uint32_t port, uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_runtime_read(uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_doorbell_read(uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_oper_write(uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_port_write(uint32_t port, uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_runtime_write(uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_doorbell_write(uint32_t off, uint32_t val)
+{
+}
+
+static inline void trace_usb_xhci_irq_intx(uint32_t level)
+{
+}
+
+static inline void trace_usb_xhci_irq_msi(uint32_t nr)
+{
+}
+
+static inline void trace_usb_xhci_irq_msix(uint32_t nr)
+{
+}
+
+static inline void trace_usb_xhci_irq_msix_use(uint32_t nr)
+{
+}
+
+static inline void trace_usb_xhci_irq_msix_unuse(uint32_t nr)
+{
+}
+
+static inline void trace_usb_xhci_queue_event(uint32_t vector, uint32_t idx, const char * trb, const char * evt, uint64_t param, uint32_t status, uint32_t control)
+{
+}
+
+static inline void trace_usb_xhci_fetch_trb(uint64_t addr, const char * name, uint64_t param, uint32_t status, uint32_t control)
+{
+}
+
+static inline void trace_usb_xhci_port_reset(uint32_t port)
+{
+}
+
+static inline void trace_usb_xhci_port_link(uint32_t port, uint32_t pls)
+{
+}
+
+static inline void trace_usb_xhci_port_notify(uint32_t port, uint32_t pls)
+{
+}
+
+static inline void trace_usb_xhci_slot_enable(uint32_t slotid)
+{
+}
+
+static inline void trace_usb_xhci_slot_disable(uint32_t slotid)
+{
+}
+
+static inline void trace_usb_xhci_slot_address(uint32_t slotid)
+{
+}
+
+static inline void trace_usb_xhci_slot_configure(uint32_t slotid)
+{
+}
+
+static inline void trace_usb_xhci_slot_evaluate(uint32_t slotid)
+{
+}
+
+static inline void trace_usb_xhci_slot_reset(uint32_t slotid)
+{
+}
+
+static inline void trace_usb_xhci_ep_enable(uint32_t slotid, uint32_t epid)
+{
+}
+
+static inline void trace_usb_xhci_ep_disable(uint32_t slotid, uint32_t epid)
+{
+}
+
+static inline void trace_usb_xhci_ep_set_dequeue(uint32_t slotid, uint32_t epid, uint32_t streamid, uint64_t param)
+{
+}
+
+static inline void trace_usb_xhci_ep_kick(uint32_t slotid, uint32_t epid, uint32_t streamid)
+{
+}
+
+static inline void trace_usb_xhci_ep_stop(uint32_t slotid, uint32_t epid)
+{
+}
+
+static inline void trace_usb_xhci_ep_reset(uint32_t slotid, uint32_t epid)
+{
+}
+
+static inline void trace_usb_xhci_xfer_start(void * xfer, uint32_t slotid, uint32_t epid, uint32_t streamid)
+{
+}
+
+static inline void trace_usb_xhci_xfer_async(void * xfer)
+{
+}
+
+static inline void trace_usb_xhci_xfer_nak(void * xfer)
+{
+}
+
+static inline void trace_usb_xhci_xfer_retry(void * xfer)
+{
+}
+
+static inline void trace_usb_xhci_xfer_success(void * xfer, uint32_t bytes)
+{
+}
+
+static inline void trace_usb_xhci_xfer_error(void * xfer, uint32_t ret)
+{
+}
+
+static inline void trace_usb_xhci_unimplemented(const char * item, int nr)
+{
+}
+
+static inline void trace_usb_desc_device(int addr, int len, int ret)
+{
+}
+
+static inline void trace_usb_desc_device_qualifier(int addr, int len, int ret)
+{
+}
+
+static inline void trace_usb_desc_config(int addr, int index, int len, int ret)
+{
+}
+
+static inline void trace_usb_desc_other_speed_config(int addr, int index, int len, int ret)
+{
+}
+
+static inline void trace_usb_desc_string(int addr, int index, int len, int ret)
+{
+}
+
+static inline void trace_usb_desc_bos(int addr, int len, int ret)
+{
+}
+
+static inline void trace_usb_set_addr(int addr)
+{
+}
+
+static inline void trace_usb_set_config(int addr, int config, int ret)
+{
+}
+
+static inline void trace_usb_set_interface(int addr, int iface, int alt, int ret)
+{
+}
+
+static inline void trace_usb_clear_device_feature(int addr, int feature, int ret)
+{
+}
+
+static inline void trace_usb_set_device_feature(int addr, int feature, int ret)
+{
+}
+
+static inline void trace_usb_hub_reset(int addr)
+{
+}
+
+static inline void trace_usb_hub_control(int addr, int request, int value, int index, int length)
+{
+}
+
+static inline void trace_usb_hub_get_port_status(int addr, int nr, int status, int changed)
+{
+}
+
+static inline void trace_usb_hub_set_port_feature(int addr, int nr, const char * f)
+{
+}
+
+static inline void trace_usb_hub_clear_port_feature(int addr, int nr, const char * f)
+{
+}
+
+static inline void trace_usb_hub_attach(int addr, int nr)
+{
+}
+
+static inline void trace_usb_hub_detach(int addr, int nr)
+{
+}
+
+static inline void trace_usb_uas_reset(int addr)
+{
+}
+
+static inline void trace_usb_uas_command(int addr, uint16_t tag, int lun, uint32_t lun64_1, uint32_t lun64_2)
+{
+}
+
+static inline void trace_usb_uas_response(int addr, uint16_t tag, uint8_t code)
+{
+}
+
+static inline void trace_usb_uas_sense(int addr, uint16_t tag, uint8_t status)
+{
+}
+
+static inline void trace_usb_uas_read_ready(int addr, uint16_t tag)
+{
+}
+
+static inline void trace_usb_uas_write_ready(int addr, uint16_t tag)
+{
+}
+
+static inline void trace_usb_uas_xfer_data(int addr, uint16_t tag, uint32_t copy, uint32_t uoff, uint32_t usize, uint32_t soff, uint32_t ssize)
+{
+}
+
+static inline void trace_usb_uas_scsi_data(int addr, uint16_t tag, uint32_t bytes)
+{
+}
+
+static inline void trace_usb_uas_scsi_complete(int addr, uint16_t tag, uint32_t status, uint32_t resid)
+{
+}
+
+static inline void trace_usb_uas_tmf_abort_task(int addr, uint16_t tag, uint16_t task_tag)
+{
+}
+
+static inline void trace_usb_uas_tmf_logical_unit_reset(int addr, uint16_t tag, int lun)
+{
+}
+
+static inline void trace_usb_uas_tmf_unsupported(int addr, uint16_t tag, uint32_t function)
+{
+}
+
+static inline void trace_usb_host_open_started(int bus, int addr)
+{
+}
+
+static inline void trace_usb_host_open_success(int bus, int addr)
+{
+}
+
+static inline void trace_usb_host_open_failure(int bus, int addr)
+{
+}
+
+static inline void trace_usb_host_disconnect(int bus, int addr)
+{
+}
+
+static inline void trace_usb_host_close(int bus, int addr)
+{
+}
+
+static inline void trace_usb_host_attach_kernel(int bus, int addr, int interface)
+{
+}
+
+static inline void trace_usb_host_detach_kernel(int bus, int addr, int interface)
+{
+}
+
+static inline void trace_usb_host_set_address(int bus, int addr, int config)
+{
+}
+
+static inline void trace_usb_host_set_config(int bus, int addr, int config)
+{
+}
+
+static inline void trace_usb_host_set_interface(int bus, int addr, int interface, int alt)
+{
+}
+
+static inline void trace_usb_host_claim_interfaces(int bus, int addr, int config, int nif)
+{
+}
+
+static inline void trace_usb_host_claim_interface(int bus, int addr, int config, int interface)
+{
+}
+
+static inline void trace_usb_host_release_interfaces(int bus, int addr)
+{
+}
+
+static inline void trace_usb_host_release_interface(int bus, int addr, int interface)
+{
+}
+
+static inline void trace_usb_host_req_control(int bus, int addr, void * p, int req, int value, int index)
+{
+}
+
+static inline void trace_usb_host_req_data(int bus, int addr, void * p, int in, int ep, int size)
+{
+}
+
+static inline void trace_usb_host_req_complete(int bus, int addr, void * p, int status, int length)
+{
+}
+
+static inline void trace_usb_host_req_emulated(int bus, int addr, void * p, int status)
+{
+}
+
+static inline void trace_usb_host_req_canceled(int bus, int addr, void * p)
+{
+}
+
+static inline void trace_usb_host_urb_submit(int bus, int addr, void * aurb, int length, int more)
+{
+}
+
+static inline void trace_usb_host_urb_complete(int bus, int addr, void * aurb, int status, int length, int more)
+{
+}
+
+static inline void trace_usb_host_urb_canceled(int bus, int addr, void * aurb)
+{
+}
+
+static inline void trace_usb_host_ep_set_halt(int bus, int addr, int ep)
+{
+}
+
+static inline void trace_usb_host_ep_clear_halt(int bus, int addr, int ep)
+{
+}
+
+static inline void trace_usb_host_iso_start(int bus, int addr, int ep)
+{
+}
+
+static inline void trace_usb_host_iso_stop(int bus, int addr, int ep)
+{
+}
+
+static inline void trace_usb_host_iso_out_of_bufs(int bus, int addr, int ep)
+{
+}
+
+static inline void trace_usb_host_iso_many_urbs(int bus, int addr, int count)
+{
+}
+
+static inline void trace_usb_host_reset(int bus, int addr)
+{
+}
+
+static inline void trace_usb_host_auto_scan_enabled(void)
+{
+}
+
+static inline void trace_usb_host_auto_scan_disabled(void)
+{
+}
+
+static inline void trace_usb_host_claim_port(int bus, int hub, int port)
+{
+}
+
+static inline void trace_usb_host_parse_device(int bus, int addr, int vendor, int product)
+{
+}
+
+static inline void trace_usb_host_parse_config(int bus, int addr, int value, int active)
+{
+}
+
+static inline void trace_usb_host_parse_interface(int bus, int addr, int num, int alt, int active)
+{
+}
+
+static inline void trace_usb_host_parse_endpoint(int bus, int addr, int ep, const char * dir, const char * type, int active)
+{
+}
+
+static inline void trace_usb_host_parse_unknown(int bus, int addr, int len, int type)
+{
+}
+
+static inline void trace_usb_host_parse_error(int bus, int addr, const char * errmsg)
+{
+}
+
+static inline void trace_scsi_req_alloc(int target, int lun, int tag)
+{
+}
+
+static inline void trace_scsi_req_cancel(int target, int lun, int tag)
+{
+}
+
+static inline void trace_scsi_req_data(int target, int lun, int tag, int len)
+{
+}
+
+static inline void trace_scsi_req_data_canceled(int target, int lun, int tag, int len)
+{
+}
+
+static inline void trace_scsi_req_dequeue(int target, int lun, int tag)
+{
+}
+
+static inline void trace_scsi_req_continue(int target, int lun, int tag)
+{
+}
+
+static inline void trace_scsi_req_continue_canceled(int target, int lun, int tag)
+{
+}
+
+static inline void trace_scsi_req_parsed(int target, int lun, int tag, int cmd, int mode, int xfer)
+{
+}
+
+static inline void trace_scsi_req_parsed_lba(int target, int lun, int tag, int cmd, uint64_t lba)
+{
+}
+
+static inline void trace_scsi_req_parse_bad(int target, int lun, int tag, int cmd)
+{
+}
+
+static inline void trace_scsi_req_build_sense(int target, int lun, int tag, int key, int asc, int ascq)
+{
+}
+
+static inline void trace_scsi_device_set_ua(int target, int lun, int key, int asc, int ascq)
+{
+}
+
+static inline void trace_scsi_report_luns(int target, int lun, int tag)
+{
+}
+
+static inline void trace_scsi_inquiry(int target, int lun, int tag, int cdb1, int cdb2)
+{
+}
+
+static inline void trace_scsi_test_unit_ready(int target, int lun, int tag)
+{
+}
+
+static inline void trace_scsi_request_sense(int target, int lun, int tag)
+{
+}
+
+static inline void trace_vm_state_notify(int running, int reason)
+{
+}
+
+static inline void trace_load_file(const char * name, const char * path)
+{
+}
+
+static inline void trace_runstate_set(int new_state)
+{
+}
+
+static inline void trace_qcow2_writev_start_req(void * co, int64_t sector, int nb_sectors)
+{
+}
+
+static inline void trace_qcow2_writev_done_req(void * co, int ret)
+{
+}
+
+static inline void trace_qcow2_writev_start_part(void * co)
+{
+}
+
+static inline void trace_qcow2_writev_done_part(void * co, int cur_nr_sectors)
+{
+}
+
+static inline void trace_qcow2_writev_data(void * co, uint64_t offset)
+{
+}
+
+static inline void trace_qcow2_alloc_clusters_offset(void * co, uint64_t offset, int n_start, int n_end)
+{
+}
+
+static inline void trace_qcow2_handle_copied(void * co, uint64_t guest_offset, uint64_t host_offset, uint64_t bytes)
+{
+}
+
+static inline void trace_qcow2_handle_alloc(void * co, uint64_t guest_offset, uint64_t host_offset, uint64_t bytes)
+{
+}
+
+static inline void trace_qcow2_do_alloc_clusters_offset(void * co, uint64_t guest_offset, uint64_t host_offset, int nb_clusters)
+{
+}
+
+static inline void trace_qcow2_cluster_alloc_phys(void * co)
+{
+}
+
+static inline void trace_qcow2_cluster_link_l2(void * co, int nb_clusters)
+{
+}
+
+static inline void trace_qcow2_l2_allocate(void * bs, int l1_index)
+{
+}
+
+static inline void trace_qcow2_l2_allocate_get_empty(void * bs, int l1_index)
+{
+}
+
+static inline void trace_qcow2_l2_allocate_write_l2(void * bs, int l1_index)
+{
+}
+
+static inline void trace_qcow2_l2_allocate_write_l1(void * bs, int l1_index)
+{
+}
+
+static inline void trace_qcow2_l2_allocate_done(void * bs, int l1_index, int ret)
+{
+}
+
+static inline void trace_qcow2_cache_get(void * co, int c, uint64_t offset, bool read_from_disk)
+{
+}
+
+static inline void trace_qcow2_cache_get_replace_entry(void * co, int c, int i)
+{
+}
+
+static inline void trace_qcow2_cache_get_read(void * co, int c, int i)
+{
+}
+
+static inline void trace_qcow2_cache_get_done(void * co, int c, int i)
+{
+}
+
+static inline void trace_qcow2_cache_flush(void * co, int c)
+{
+}
+
+static inline void trace_qcow2_cache_entry_flush(void * co, int c, int i)
+{
+}
+
+static inline void trace_qed_alloc_l2_cache_entry(void * l2_cache, void * entry)
+{
+}
+
+static inline void trace_qed_unref_l2_cache_entry(void * entry, int ref)
+{
+}
+
+static inline void trace_qed_find_l2_cache_entry(void * l2_cache, void * entry, uint64_t offset, int ref)
+{
+}
+
+static inline void trace_qed_read_table(void * s, uint64_t offset, void * table)
+{
+}
+
+static inline void trace_qed_read_table_cb(void * s, void * table, int ret)
+{
+}
+
+static inline void trace_qed_write_table(void * s, uint64_t offset, void * table, unsigned int index, unsigned int n)
+{
+}
+
+static inline void trace_qed_write_table_cb(void * s, void * table, int flush, int ret)
+{
+}
+
+static inline void trace_qed_need_check_timer_cb(void * s)
+{
+}
+
+static inline void trace_qed_start_need_check_timer(void * s)
+{
+}
+
+static inline void trace_qed_cancel_need_check_timer(void * s)
+{
+}
+
+static inline void trace_qed_aio_complete(void * s, void * acb, int ret)
+{
+}
+
+static inline void trace_qed_aio_setup(void * s, void * acb, int64_t sector_num, int nb_sectors, void * opaque, int flags)
+{
+}
+
+static inline void trace_qed_aio_next_io(void * s, void * acb, int ret, uint64_t cur_pos)
+{
+}
+
+static inline void trace_qed_aio_read_data(void * s, void * acb, int ret, uint64_t offset, size_t len)
+{
+}
+
+static inline void trace_qed_aio_write_data(void * s, void * acb, int ret, uint64_t offset, size_t len)
+{
+}
+
+static inline void trace_qed_aio_write_prefill(void * s, void * acb, uint64_t start, size_t len, uint64_t offset)
+{
+}
+
+static inline void trace_qed_aio_write_postfill(void * s, void * acb, uint64_t start, size_t len, uint64_t offset)
+{
+}
+
+static inline void trace_qed_aio_write_main(void * s, void * acb, int ret, uint64_t offset, size_t len)
+{
+}
+
+static inline void trace_g364fb_read(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_g364fb_write(uint64_t addr, uint32_t new)
+{
+}
+
+static inline void trace_grlib_gptimer_enable(int id, uint32_t count)
+{
+}
+
+static inline void trace_grlib_gptimer_disabled(int id, uint32_t config)
+{
+}
+
+static inline void trace_grlib_gptimer_restart(int id, uint32_t reload)
+{
+}
+
+static inline void trace_grlib_gptimer_set_scaler(uint32_t scaler, uint32_t freq)
+{
+}
+
+static inline void trace_grlib_gptimer_hit(int id)
+{
+}
+
+static inline void trace_grlib_gptimer_readl(int id, uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_grlib_gptimer_writel(int id, uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_grlib_irqmp_check_irqs(uint32_t pend, uint32_t force, uint32_t mask, uint32_t lvl1, uint32_t lvl2)
+{
+}
+
+static inline void trace_grlib_irqmp_ack(int intno)
+{
+}
+
+static inline void trace_grlib_irqmp_set_irq(int irq)
+{
+}
+
+static inline void trace_grlib_irqmp_readl_unknown(uint64_t addr)
+{
+}
+
+static inline void trace_grlib_irqmp_writel_unknown(uint64_t addr, uint32_t value)
+{
+}
+
+static inline void trace_grlib_apbuart_event(int event)
+{
+}
+
+static inline void trace_grlib_apbuart_writel_unknown(uint64_t addr, uint32_t value)
+{
+}
+
+static inline void trace_grlib_apbuart_readl_unknown(uint64_t addr)
+{
+}
+
+static inline void trace_leon3_set_irq(int intno)
+{
+}
+
+static inline void trace_leon3_reset_irq(int intno)
+{
+}
+
+static inline void trace_spice_vmc_write(ssize_t out, int len)
+{
+}
+
+static inline void trace_spice_vmc_read(int bytes, int len)
+{
+}
+
+static inline void trace_spice_vmc_register_interface(void * scd)
+{
+}
+
+static inline void trace_spice_vmc_unregister_interface(void * scd)
+{
+}
+
+static inline void trace_spice_vmc_event(int event)
+{
+}
+
+static inline void trace_lm32_pic_raise_irq(void)
+{
+}
+
+static inline void trace_lm32_pic_lower_irq(void)
+{
+}
+
+static inline void trace_lm32_pic_interrupt(int irq, int level)
+{
+}
+
+static inline void trace_lm32_pic_set_im(uint32_t im)
+{
+}
+
+static inline void trace_lm32_pic_set_ip(uint32_t ip)
+{
+}
+
+static inline void trace_lm32_pic_get_im(uint32_t im)
+{
+}
+
+static inline void trace_lm32_pic_get_ip(uint32_t ip)
+{
+}
+
+static inline void trace_lm32_juart_get_jtx(uint32_t value)
+{
+}
+
+static inline void trace_lm32_juart_set_jtx(uint32_t value)
+{
+}
+
+static inline void trace_lm32_juart_get_jrx(uint32_t value)
+{
+}
+
+static inline void trace_lm32_juart_set_jrx(uint32_t value)
+{
+}
+
+static inline void trace_lm32_timer_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_lm32_timer_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_lm32_timer_hit(void)
+{
+}
+
+static inline void trace_lm32_timer_irq_state(int level)
+{
+}
+
+static inline void trace_lm32_uart_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_lm32_uart_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_lm32_uart_irq_state(int level)
+{
+}
+
+static inline void trace_lm32_sys_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_megasas_init_firmware(uint64_t pa)
+{
+}
+
+static inline void trace_megasas_init_queue(uint64_t queue_pa, int queue_len, uint64_t head, uint64_t tail, uint32_t flags)
+{
+}
+
+static inline void trace_megasas_initq_map_failed(int frame)
+{
+}
+
+static inline void trace_megasas_initq_mismatch(int queue_len, int fw_cmds)
+{
+}
+
+static inline void trace_megasas_qf_found(unsigned int index, uint64_t pa)
+{
+}
+
+static inline void trace_megasas_qf_new(unsigned int index, void * cmd)
+{
+}
+
+static inline void trace_megasas_qf_failed(unsigned long pa)
+{
+}
+
+static inline void trace_megasas_qf_enqueue(unsigned int index, unsigned int count, uint64_t context, unsigned int tail, int busy)
+{
+}
+
+static inline void trace_megasas_qf_update(unsigned int head, unsigned int busy)
+{
+}
+
+static inline void trace_megasas_qf_dequeue(unsigned int index)
+{
+}
+
+static inline void trace_megasas_qf_map_failed(int cmd, unsigned long frame)
+{
+}
+
+static inline void trace_megasas_qf_complete_noirq(uint64_t context)
+{
+}
+
+static inline void trace_megasas_qf_complete(uint64_t context, unsigned int tail, unsigned int offset, int busy, unsigned int doorbell)
+{
+}
+
+static inline void trace_megasas_handle_frame(const char * cmd, uint64_t addr, uint64_t context, uint32_t count)
+{
+}
+
+static inline void trace_megasas_frame_busy(uint64_t addr)
+{
+}
+
+static inline void trace_megasas_unhandled_frame_cmd(int cmd, uint8_t frame_cmd)
+{
+}
+
+static inline void trace_megasas_handle_scsi(const char * frame, int bus, int dev, int lun, void * sdev, unsigned long size)
+{
+}
+
+static inline void trace_megasas_scsi_target_not_present(const char * frame, int bus, int dev, int lun)
+{
+}
+
+static inline void trace_megasas_scsi_invalid_cdb_len(const char * frame, int bus, int dev, int lun, int len)
+{
+}
+
+static inline void trace_megasas_iov_read_overflow(int cmd, int bytes, int len)
+{
+}
+
+static inline void trace_megasas_iov_write_overflow(int cmd, int bytes, int len)
+{
+}
+
+static inline void trace_megasas_iov_read_underflow(int cmd, int bytes, int len)
+{
+}
+
+static inline void trace_megasas_iov_write_underflow(int cmd, int bytes, int len)
+{
+}
+
+static inline void trace_megasas_scsi_req_alloc_failed(const char * frame, int dev, int lun)
+{
+}
+
+static inline void trace_megasas_scsi_read_start(int cmd, int len)
+{
+}
+
+static inline void trace_megasas_scsi_write_start(int cmd, int len)
+{
+}
+
+static inline void trace_megasas_scsi_nodata(int cmd)
+{
+}
+
+static inline void trace_megasas_scsi_complete(int cmd, uint32_t status, int len, int xfer)
+{
+}
+
+static inline void trace_megasas_command_complete(int cmd, uint32_t status, uint32_t resid)
+{
+}
+
+static inline void trace_megasas_handle_io(int cmd, const char * frame, int dev, int lun, unsigned long lba, unsigned long count)
+{
+}
+
+static inline void trace_megasas_io_target_not_present(int cmd, const char * frame, int dev, int lun)
+{
+}
+
+static inline void trace_megasas_io_read_start(int cmd, unsigned long lba, unsigned long count, unsigned long len)
+{
+}
+
+static inline void trace_megasas_io_write_start(int cmd, unsigned long lba, unsigned long count, unsigned long len)
+{
+}
+
+static inline void trace_megasas_io_complete(int cmd, uint32_t len)
+{
+}
+
+static inline void trace_megasas_io_read(int cmd, int bytes, int len, unsigned long offset)
+{
+}
+
+static inline void trace_megasas_io_write(int cmd, int bytes, int len, unsigned long offset)
+{
+}
+
+static inline void trace_megasas_io_continue(int cmd, int bytes)
+{
+}
+
+static inline void trace_megasas_iovec_map_failed(int cmd, int index, unsigned long iov_size)
+{
+}
+
+static inline void trace_megasas_iovec_sgl_overflow(int cmd, int index, int limit)
+{
+}
+
+static inline void trace_megasas_iovec_sgl_underflow(int cmd, int index)
+{
+}
+
+static inline void trace_megasas_iovec_sgl_invalid(int cmd, int index, uint64_t pa, uint32_t len)
+{
+}
+
+static inline void trace_megasas_iovec_overflow(int cmd, int len, int limit)
+{
+}
+
+static inline void trace_megasas_iovec_underflow(int cmd, int len, int limit)
+{
+}
+
+static inline void trace_megasas_handle_dcmd(int cmd, int opcode)
+{
+}
+
+static inline void trace_megasas_finish_dcmd(int cmd, int size)
+{
+}
+
+static inline void trace_megasas_dcmd_req_alloc_failed(int cmd, const char * desc)
+{
+}
+
+static inline void trace_megasas_dcmd_internal_submit(int cmd, const char * desc, int dev)
+{
+}
+
+static inline void trace_megasas_dcmd_internal_finish(int cmd, int opcode, int lun)
+{
+}
+
+static inline void trace_megasas_dcmd_internal_invalid(int cmd, int opcode)
+{
+}
+
+static inline void trace_megasas_dcmd_unhandled(int cmd, int opcode, int len)
+{
+}
+
+static inline void trace_megasas_dcmd_zero_sge(int cmd)
+{
+}
+
+static inline void trace_megasas_dcmd_invalid_sge(int cmd, int count)
+{
+}
+
+static inline void trace_megasas_dcmd_map_failed(int cmd)
+{
+}
+
+static inline void trace_megasas_dcmd_invalid_xfer_len(int cmd, unsigned long size, unsigned long max)
+{
+}
+
+static inline void trace_megasas_dcmd_enter(int cmd, const char * dcmd, int len)
+{
+}
+
+static inline void trace_megasas_dcmd_dummy(int cmd, unsigned long size)
+{
+}
+
+static inline void trace_megasas_dcmd_set_fw_time(int cmd, unsigned long time)
+{
+}
+
+static inline void trace_megasas_dcmd_pd_get_list(int cmd, int num, int max, int offset)
+{
+}
+
+static inline void trace_megasas_dcmd_ld_get_list(int cmd, int num, int max)
+{
+}
+
+static inline void trace_megasas_dcmd_ld_get_info(int cmd, int ld_id)
+{
+}
+
+static inline void trace_megasas_dcmd_pd_get_info(int cmd, int pd_id)
+{
+}
+
+static inline void trace_megasas_dcmd_pd_list_query(int cmd, int flags)
+{
+}
+
+static inline void trace_megasas_dcmd_unsupported(int cmd, unsigned long size)
+{
+}
+
+static inline void trace_megasas_abort_frame(int cmd, int abort_cmd)
+{
+}
+
+static inline void trace_megasas_abort_no_cmd(int cmd, uint64_t context)
+{
+}
+
+static inline void trace_megasas_abort_invalid_context(int cmd, uint64_t context, int abort_cmd)
+{
+}
+
+static inline void trace_megasas_reset(void)
+{
+}
+
+static inline void trace_megasas_init(int sges, int cmds, const char * intr, const char * mode)
+{
+}
+
+static inline void trace_megasas_msix_raise(int vector)
+{
+}
+
+static inline void trace_megasas_irq_lower(void)
+{
+}
+
+static inline void trace_megasas_irq_raise(void)
+{
+}
+
+static inline void trace_megasas_intr_enabled(void)
+{
+}
+
+static inline void trace_megasas_intr_disabled(void)
+{
+}
+
+static inline void trace_megasas_mmio_readl(unsigned long addr, uint32_t val)
+{
+}
+
+static inline void trace_megasas_mmio_invalid_readl(unsigned long addr)
+{
+}
+
+static inline void trace_megasas_mmio_writel(uint32_t addr, uint32_t val)
+{
+}
+
+static inline void trace_megasas_mmio_invalid_writel(uint32_t addr, uint32_t val)
+{
+}
+
+static inline void trace_milkymist_ac97_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_ac97_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_ac97_pulse_irq_crrequest(void)
+{
+}
+
+static inline void trace_milkymist_ac97_pulse_irq_crreply(void)
+{
+}
+
+static inline void trace_milkymist_ac97_pulse_irq_dmaw(void)
+{
+}
+
+static inline void trace_milkymist_ac97_pulse_irq_dmar(void)
+{
+}
+
+static inline void trace_milkymist_ac97_in_cb(int avail, uint32_t remaining)
+{
+}
+
+static inline void trace_milkymist_ac97_in_cb_transferred(int transferred)
+{
+}
+
+static inline void trace_milkymist_ac97_out_cb(int free, uint32_t remaining)
+{
+}
+
+static inline void trace_milkymist_ac97_out_cb_transferred(int transferred)
+{
+}
+
+static inline void trace_milkymist_hpdmc_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_hpdmc_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_memcard_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_memcard_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_minimac2_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_minimac2_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_minimac2_mdio_write(uint8_t phy_addr, uint8_t addr, uint16_t value)
+{
+}
+
+static inline void trace_milkymist_minimac2_mdio_read(uint8_t phy_addr, uint8_t addr, uint16_t value)
+{
+}
+
+static inline void trace_milkymist_minimac2_tx_frame(uint32_t length)
+{
+}
+
+static inline void trace_milkymist_minimac2_rx_frame(const void * buf, uint32_t length)
+{
+}
+
+static inline void trace_milkymist_minimac2_drop_rx_frame(const void * buf)
+{
+}
+
+static inline void trace_milkymist_minimac2_rx_transfer(const void * buf, uint32_t length)
+{
+}
+
+static inline void trace_milkymist_minimac2_raise_irq_rx(void)
+{
+}
+
+static inline void trace_milkymist_minimac2_lower_irq_rx(void)
+{
+}
+
+static inline void trace_milkymist_minimac2_pulse_irq_tx(void)
+{
+}
+
+static inline void trace_milkymist_pfpu_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_pfpu_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_pfpu_vectout(uint32_t a, uint32_t b, uint32_t dma_ptr)
+{
+}
+
+static inline void trace_milkymist_pfpu_pulse_irq(void)
+{
+}
+
+static inline void trace_milkymist_softusb_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_softusb_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_softusb_mevt(uint8_t m)
+{
+}
+
+static inline void trace_milkymist_softusb_kevt(uint8_t m)
+{
+}
+
+static inline void trace_milkymist_softusb_mouse_event(int dx, int dy, int dz, int bs)
+{
+}
+
+static inline void trace_milkymist_softusb_pulse_irq(void)
+{
+}
+
+static inline void trace_milkymist_sysctl_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_sysctl_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_sysctl_icap_write(uint32_t value)
+{
+}
+
+static inline void trace_milkymist_sysctl_start_timer0(void)
+{
+}
+
+static inline void trace_milkymist_sysctl_stop_timer0(void)
+{
+}
+
+static inline void trace_milkymist_sysctl_start_timer1(void)
+{
+}
+
+static inline void trace_milkymist_sysctl_stop_timer1(void)
+{
+}
+
+static inline void trace_milkymist_sysctl_pulse_irq_timer0(void)
+{
+}
+
+static inline void trace_milkymist_sysctl_pulse_irq_timer1(void)
+{
+}
+
+static inline void trace_milkymist_tmu2_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_tmu2_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_tmu2_start(void)
+{
+}
+
+static inline void trace_milkymist_tmu2_pulse_irq(void)
+{
+}
+
+static inline void trace_milkymist_uart_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_uart_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_uart_raise_irq(void)
+{
+}
+
+static inline void trace_milkymist_uart_lower_irq(void)
+{
+}
+
+static inline void trace_milkymist_vgafb_memory_read(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_milkymist_vgafb_memory_write(uint32_t addr, uint32_t value)
+{
+}
+
+static inline void trace_mipsnet_send(uint32_t size)
+{
+}
+
+static inline void trace_mipsnet_receive(uint32_t size)
+{
+}
+
+static inline void trace_mipsnet_read(uint64_t addr, uint32_t val)
+{
+}
+
+static inline void trace_mipsnet_write(uint64_t addr, uint64_t val)
+{
+}
+
+static inline void trace_mipsnet_irq(uint32_t isr, uint32_t intctl)
+{
+}
+
+static inline void trace_pc87312_io_read(uint32_t addr, uint32_t val)
+{
+}
+
+static inline void trace_pc87312_io_write(uint32_t addr, uint32_t val)
+{
+}
+
+static inline void trace_pc87312_info_floppy(uint32_t base)
+{
+}
+
+static inline void trace_pc87312_info_ide(uint32_t base)
+{
+}
+
+static inline void trace_pc87312_info_parallel(uint32_t base, uint32_t irq)
+{
+}
+
+static inline void trace_pc87312_info_serial(int n, uint32_t base, uint32_t irq)
+{
+}
+
+static inline void trace_pvscsi_ring_init_data(uint32_t txr_len_log2, uint32_t rxr_len_log2)
+{
+}
+
+static inline void trace_pvscsi_ring_init_msg(uint32_t len_log2)
+{
+}
+
+static inline void trace_pvscsi_ring_flush_cmp(uint64_t filled_cmp_ptr)
+{
+}
+
+static inline void trace_pvscsi_ring_flush_msg(uint64_t filled_cmp_ptr)
+{
+}
+
+static inline void trace_pvscsi_update_irq_level(bool raise, uint64_t mask, uint64_t status)
+{
+}
+
+static inline void trace_pvscsi_update_irq_msi(void)
+{
+}
+
+static inline void trace_pvscsi_cmp_ring_put(unsigned long addr)
+{
+}
+
+static inline void trace_pvscsi_msg_ring_put(unsigned long addr)
+{
+}
+
+static inline void trace_pvscsi_complete_request(uint64_t context, uint64_t len, uint8_t sense_key)
+{
+}
+
+static inline void trace_pvscsi_get_sg_list(int nsg, size_t size)
+{
+}
+
+static inline void trace_pvscsi_get_next_sg_elem(uint32_t flags)
+{
+}
+
+static inline void trace_pvscsi_command_complete_not_found(uint32_t tag)
+{
+}
+
+static inline void trace_pvscsi_command_complete_data_run(void)
+{
+}
+
+static inline void trace_pvscsi_command_complete_sense_len(int len)
+{
+}
+
+static inline void trace_pvscsi_convert_sglist(uint64_t context, unsigned long addr, uint32_t resid)
+{
+}
+
+static inline void trace_pvscsi_process_req_descr(uint8_t cmd, uint64_t ctx)
+{
+}
+
+static inline void trace_pvscsi_process_req_descr_unknown_device(void)
+{
+}
+
+static inline void trace_pvscsi_process_req_descr_invalid_dir(void)
+{
+}
+
+static inline void trace_pvscsi_process_io(unsigned long addr)
+{
+}
+
+static inline void trace_pvscsi_on_cmd_noimpl(const char* cmd)
+{
+}
+
+static inline void trace_pvscsi_on_cmd_reset_dev(uint32_t tgt, int lun, void* dev)
+{
+}
+
+static inline void trace_pvscsi_on_cmd_arrived(const char* cmd)
+{
+}
+
+static inline void trace_pvscsi_on_cmd_abort(uint64_t ctx, uint32_t tgt)
+{
+}
+
+static inline void trace_pvscsi_on_cmd_unknown(uint64_t cmd_id)
+{
+}
+
+static inline void trace_pvscsi_on_cmd_unknown_data(uint32_t data)
+{
+}
+
+static inline void trace_pvscsi_io_write(const char* cmd, uint64_t val)
+{
+}
+
+static inline void trace_pvscsi_io_write_unknown(unsigned long addr, unsigned sz, uint64_t val)
+{
+}
+
+static inline void trace_pvscsi_io_read(const char* cmd, uint64_t status)
+{
+}
+
+static inline void trace_pvscsi_io_read_unknown(unsigned long addr, unsigned sz)
+{
+}
+
+static inline void trace_pvscsi_init_msi_fail(int res)
+{
+}
+
+static inline void trace_pvscsi_state(const char* state)
+{
+}
+
+static inline void trace_pvscsi_tx_rings_ppn(const char* label, uint64_t ppn)
+{
+}
+
+static inline void trace_pvscsi_tx_rings_num_pages(const char* label, uint32_t num)
+{
+}
+
+static inline void trace_xen_ram_alloc(unsigned long ram_addr, unsigned long size)
+{
+}
+
+static inline void trace_xen_client_set_memory(uint64_t start_addr, unsigned long size, bool log_dirty)
+{
+}
+
+static inline void trace_xen_map_cache(uint64_t phys_addr)
+{
+}
+
+static inline void trace_xen_remap_bucket(uint64_t index)
+{
+}
+
+static inline void trace_xen_map_cache_return(void* ptr)
+{
+}
+
+static inline void trace_xen_map_block(uint64_t phys_addr, uint64_t size)
+{
+}
+
+static inline void trace_xen_unmap_block(void* addr, unsigned long size)
+{
+}
+
+static inline void trace_xen_platform_log(char * s)
+{
+}
+
+static inline void trace_qemu_coroutine_enter(void * from, void * to, void * opaque)
+{
+}
+
+static inline void trace_qemu_coroutine_yield(void * from, void * to)
+{
+}
+
+static inline void trace_qemu_coroutine_terminate(void * co)
+{
+}
+
+static inline void trace_qemu_co_queue_run_restart(void * co)
+{
+}
+
+static inline void trace_qemu_co_queue_next(void * nxt)
+{
+}
+
+static inline void trace_qemu_co_mutex_lock_entry(void * mutex, void * self)
+{
+}
+
+static inline void trace_qemu_co_mutex_lock_return(void * mutex, void * self)
+{
+}
+
+static inline void trace_qemu_co_mutex_unlock_entry(void * mutex, void * self)
+{
+}
+
+static inline void trace_qemu_co_mutex_unlock_return(void * mutex, void * self)
+{
+}
+
+static inline void trace_escc_put_queue(char channel, int b)
+{
+}
+
+static inline void trace_escc_get_queue(char channel, int val)
+{
+}
+
+static inline void trace_escc_update_irq(int irq)
+{
+}
+
+static inline void trace_escc_update_parameters(char channel, int speed, int parity, int data_bits, int stop_bits)
+{
+}
+
+static inline void trace_escc_mem_writeb_ctrl(char channel, uint32_t reg, uint32_t val)
+{
+}
+
+static inline void trace_escc_mem_writeb_data(char channel, uint32_t val)
+{
+}
+
+static inline void trace_escc_mem_readb_ctrl(char channel, uint32_t reg, uint8_t val)
+{
+}
+
+static inline void trace_escc_mem_readb_data(char channel, uint32_t ret)
+{
+}
+
+static inline void trace_escc_serial_receive_byte(char channel, int ch)
+{
+}
+
+static inline void trace_escc_sunkbd_event_in(int ch)
+{
+}
+
+static inline void trace_escc_sunkbd_event_out(int ch)
+{
+}
+
+static inline void trace_escc_kbd_command(int val)
+{
+}
+
+static inline void trace_escc_sunmouse_event(int dx, int dy, int buttons_state)
+{
+}
+
+static inline void trace_iscsi_aio_write16_cb(void * iscsi, int status, void * acb, int canceled)
+{
+}
+
+static inline void trace_iscsi_aio_writev(void * iscsi, int64_t sector_num, int nb_sectors, void * opaque, void * acb)
+{
+}
+
+static inline void trace_iscsi_aio_read16_cb(void * iscsi, int status, void * acb, int canceled)
+{
+}
+
+static inline void trace_iscsi_aio_readv(void * iscsi, int64_t sector_num, int nb_sectors, void * opaque, void * acb)
+{
+}
+
+static inline void trace_esp_error_fifo_overrun(void)
+{
+}
+
+static inline void trace_esp_error_unhandled_command(uint32_t val)
+{
+}
+
+static inline void trace_esp_error_invalid_write(uint32_t val, uint32_t addr)
+{
+}
+
+static inline void trace_esp_raise_irq(void)
+{
+}
+
+static inline void trace_esp_lower_irq(void)
+{
+}
+
+static inline void trace_esp_dma_enable(void)
+{
+}
+
+static inline void trace_esp_dma_disable(void)
+{
+}
+
+static inline void trace_esp_get_cmd(uint32_t dmalen, int target)
+{
+}
+
+static inline void trace_esp_do_busid_cmd(uint8_t busid)
+{
+}
+
+static inline void trace_esp_handle_satn_stop(uint32_t cmdlen)
+{
+}
+
+static inline void trace_esp_write_response(uint32_t status)
+{
+}
+
+static inline void trace_esp_do_dma(uint32_t cmdlen, uint32_t len)
+{
+}
+
+static inline void trace_esp_command_complete(void)
+{
+}
+
+static inline void trace_esp_command_complete_unexpected(void)
+{
+}
+
+static inline void trace_esp_command_complete_fail(void)
+{
+}
+
+static inline void trace_esp_transfer_data(uint32_t dma_left, int32_t ti_size)
+{
+}
+
+static inline void trace_esp_handle_ti(uint32_t minlen)
+{
+}
+
+static inline void trace_esp_handle_ti_cmd(uint32_t cmdlen)
+{
+}
+
+static inline void trace_esp_mem_readb(uint32_t saddr, uint8_t reg)
+{
+}
+
+static inline void trace_esp_mem_writeb(uint32_t saddr, uint8_t reg, uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_nop(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_flush(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_reset(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_bus_reset(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_iccs(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_msgacc(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_pad(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_satn(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_rstatn(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_sel(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_selatn(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_selatns(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_ensel(uint32_t val)
+{
+}
+
+static inline void trace_esp_mem_writeb_cmd_dissel(uint32_t val)
+{
+}
+
+static inline void trace_esp_pci_error_invalid_dma_direction(void)
+{
+}
+
+static inline void trace_esp_pci_error_invalid_read(uint32_t reg)
+{
+}
+
+static inline void trace_esp_pci_error_invalid_write(uint32_t reg)
+{
+}
+
+static inline void trace_esp_pci_error_invalid_write_dma(uint32_t val, uint32_t addr)
+{
+}
+
+static inline void trace_esp_pci_dma_read(uint32_t saddr, uint32_t reg)
+{
+}
+
+static inline void trace_esp_pci_dma_write(uint32_t saddr, uint32_t reg, uint32_t val)
+{
+}
+
+static inline void trace_esp_pci_dma_idle(uint32_t val)
+{
+}
+
+static inline void trace_esp_pci_dma_blast(uint32_t val)
+{
+}
+
+static inline void trace_esp_pci_dma_abort(uint32_t val)
+{
+}
+
+static inline void trace_esp_pci_dma_start(uint32_t val)
+{
+}
+
+static inline void trace_esp_pci_sbac_read(uint32_t reg)
+{
+}
+
+static inline void trace_esp_pci_sbac_write(uint32_t reg, uint32_t val)
+{
+}
+
+static inline void trace_handle_qmp_command(void * mon, const char * cmd_name)
+{
+}
+
+static inline void trace_monitor_protocol_emitter(void * mon)
+{
+}
+
+static inline void trace_monitor_protocol_event(uint32_t event, const char * evname, void * data)
+{
+}
+
+static inline void trace_monitor_protocol_event_handler(uint32_t event, void * data, uint64_t last, uint64_t now)
+{
+}
+
+static inline void trace_monitor_protocol_event_emit(uint32_t event, void * data)
+{
+}
+
+static inline void trace_monitor_protocol_event_queue(uint32_t event, void * data, uint64_t rate, uint64_t last, uint64_t now)
+{
+}
+
+static inline void trace_monitor_protocol_event_throttle(uint32_t event, uint64_t rate)
+{
+}
+
+static inline void trace_open_eth_mii_write(unsigned idx, uint16_t v)
+{
+}
+
+static inline void trace_open_eth_mii_read(unsigned idx, uint16_t v)
+{
+}
+
+static inline void trace_open_eth_update_irq(uint32_t v)
+{
+}
+
+static inline void trace_open_eth_receive(unsigned len)
+{
+}
+
+static inline void trace_open_eth_receive_mcast(unsigned idx, uint32_t h0, uint32_t h1)
+{
+}
+
+static inline void trace_open_eth_receive_reject(void)
+{
+}
+
+static inline void trace_open_eth_receive_desc(uint32_t addr, uint32_t len_flags)
+{
+}
+
+static inline void trace_open_eth_start_xmit(uint32_t addr, unsigned len, unsigned tx_len)
+{
+}
+
+static inline void trace_open_eth_reg_read(uint32_t addr, uint32_t v)
+{
+}
+
+static inline void trace_open_eth_reg_write(uint32_t addr, uint32_t v)
+{
+}
+
+static inline void trace_open_eth_desc_read(uint32_t addr, uint32_t v)
+{
+}
+
+static inline void trace_open_eth_desc_write(uint32_t addr, uint32_t v)
+{
+}
+
+static inline void trace_v9fs_rerror(uint16_t tag, uint8_t id, int err)
+{
+}
+
+static inline void trace_v9fs_version(uint16_t tag, uint8_t id, int32_t msize, char* version)
+{
+}
+
+static inline void trace_v9fs_version_return(uint16_t tag, uint8_t id, int32_t msize, char* version)
+{
+}
+
+static inline void trace_v9fs_attach(uint16_t tag, uint8_t id, int32_t fid, int32_t afid, char* uname, char* aname)
+{
+}
+
+static inline void trace_v9fs_attach_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path)
+{
+}
+
+static inline void trace_v9fs_stat(uint16_t tag, uint8_t id, int32_t fid)
+{
+}
+
+static inline void trace_v9fs_stat_return(uint16_t tag, uint8_t id, int32_t mode, int32_t atime, int32_t mtime, int64_t length)
+{
+}
+
+static inline void trace_v9fs_getattr(uint16_t tag, uint8_t id, int32_t fid, uint64_t request_mask)
+{
+}
+
+static inline void trace_v9fs_getattr_return(uint16_t tag, uint8_t id, uint64_t result_mask, uint32_t mode, uint32_t uid, uint32_t gid)
+{
+}
+
+static inline void trace_v9fs_walk(uint16_t tag, uint8_t id, int32_t fid, int32_t newfid, uint16_t nwnames)
+{
+}
+
+static inline void trace_v9fs_walk_return(uint16_t tag, uint8_t id, uint16_t nwnames, void* qids)
+{
+}
+
+static inline void trace_v9fs_open(uint16_t tag, uint8_t id, int32_t fid, int32_t mode)
+{
+}
+
+static inline void trace_v9fs_open_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path, int iounit)
+{
+}
+
+static inline void trace_v9fs_lcreate(uint16_t tag, uint8_t id, int32_t dfid, int32_t flags, int32_t mode, uint32_t gid)
+{
+}
+
+static inline void trace_v9fs_lcreate_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path, int32_t iounit)
+{
+}
+
+static inline void trace_v9fs_fsync(uint16_t tag, uint8_t id, int32_t fid, int datasync)
+{
+}
+
+static inline void trace_v9fs_clunk(uint16_t tag, uint8_t id, int32_t fid)
+{
+}
+
+static inline void trace_v9fs_read(uint16_t tag, uint8_t id, int32_t fid, uint64_t off, uint32_t max_count)
+{
+}
+
+static inline void trace_v9fs_read_return(uint16_t tag, uint8_t id, int32_t count, ssize_t err)
+{
+}
+
+static inline void trace_v9fs_readdir(uint16_t tag, uint8_t id, int32_t fid, uint64_t offset, uint32_t max_count)
+{
+}
+
+static inline void trace_v9fs_readdir_return(uint16_t tag, uint8_t id, uint32_t count, ssize_t retval)
+{
+}
+
+static inline void trace_v9fs_write(uint16_t tag, uint8_t id, int32_t fid, uint64_t off, uint32_t count, int cnt)
+{
+}
+
+static inline void trace_v9fs_write_return(uint16_t tag, uint8_t id, int32_t total, ssize_t err)
+{
+}
+
+static inline void trace_v9fs_create(uint16_t tag, uint8_t id, int32_t fid, char* name, int32_t perm, int8_t mode)
+{
+}
+
+static inline void trace_v9fs_create_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path, int iounit)
+{
+}
+
+static inline void trace_v9fs_symlink(uint16_t tag, uint8_t id, int32_t fid, char* name, char* symname, uint32_t gid)
+{
+}
+
+static inline void trace_v9fs_symlink_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path)
+{
+}
+
+static inline void trace_v9fs_flush(uint16_t tag, uint8_t id, int16_t flush_tag)
+{
+}
+
+static inline void trace_v9fs_link(uint16_t tag, uint8_t id, int32_t dfid, int32_t oldfid, char* name)
+{
+}
+
+static inline void trace_v9fs_remove(uint16_t tag, uint8_t id, int32_t fid)
+{
+}
+
+static inline void trace_v9fs_wstat(uint16_t tag, uint8_t id, int32_t fid, int32_t mode, int32_t atime, int32_t mtime)
+{
+}
+
+static inline void trace_v9fs_mknod(uint16_t tag, uint8_t id, int32_t fid, int mode, int major, int minor)
+{
+}
+
+static inline void trace_v9fs_mknod_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path)
+{
+}
+
+static inline void trace_v9fs_lock(uint16_t tag, uint8_t id, int32_t fid, uint8_t type, uint64_t start, uint64_t length)
+{
+}
+
+static inline void trace_v9fs_lock_return(uint16_t tag, uint8_t id, int8_t status)
+{
+}
+
+static inline void trace_v9fs_getlock(uint16_t tag, uint8_t id, int32_t fid, uint8_t type, uint64_t start, uint64_t length)
+{
+}
+
+static inline void trace_v9fs_getlock_return(uint16_t tag, uint8_t id, uint8_t type, uint64_t start, uint64_t length, uint32_t proc_id)
+{
+}
+
+static inline void trace_v9fs_mkdir(uint16_t tag, uint8_t id, int32_t fid, char* name, int mode, uint32_t gid)
+{
+}
+
+static inline void trace_v9fs_mkdir_return(uint16_t tag, uint8_t id, int8_t type, int32_t version, int64_t path, int err)
+{
+}
+
+static inline void trace_v9fs_xattrwalk(uint16_t tag, uint8_t id, int32_t fid, int32_t newfid, char* name)
+{
+}
+
+static inline void trace_v9fs_xattrwalk_return(uint16_t tag, uint8_t id, int64_t size)
+{
+}
+
+static inline void trace_v9fs_xattrcreate(uint16_t tag, uint8_t id, int32_t fid, char* name, int64_t size, int flags)
+{
+}
+
+static inline void trace_v9fs_readlink(uint16_t tag, uint8_t id, int32_t fid)
+{
+}
+
+static inline void trace_v9fs_readlink_return(uint16_t tag, uint8_t id, char* target)
+{
+}
+
+static inline void trace_mmu_helper_dfault(uint64_t address, uint64_t context, int mmu_idx, uint32_t tl)
+{
+}
+
+static inline void trace_mmu_helper_dprot(uint64_t address, uint64_t context, int mmu_idx, uint32_t tl)
+{
+}
+
+static inline void trace_mmu_helper_dmiss(uint64_t address, uint64_t context)
+{
+}
+
+static inline void trace_mmu_helper_tfault(uint64_t address, uint64_t context)
+{
+}
+
+static inline void trace_mmu_helper_tmiss(uint64_t address, uint64_t context)
+{
+}
+
+static inline void trace_mmu_helper_get_phys_addr_code(uint32_t tl, int mmu_idx, uint64_t prim_context, uint64_t sec_context, uint64_t address)
+{
+}
+
+static inline void trace_mmu_helper_get_phys_addr_data(uint32_t tl, int mmu_idx, uint64_t prim_context, uint64_t sec_context, uint64_t address)
+{
+}
+
+static inline void trace_mmu_helper_mmu_fault(uint64_t address, uint64_t paddr, int mmu_idx, uint32_t tl, uint64_t prim_context, uint64_t sec_context)
+{
+}
+
+static inline void trace_int_helper_set_softint(uint32_t softint)
+{
+}
+
+static inline void trace_int_helper_clear_softint(uint32_t softint)
+{
+}
+
+static inline void trace_int_helper_write_softint(uint32_t softint)
+{
+}
+
+static inline void trace_int_helper_icache_freeze(void)
+{
+}
+
+static inline void trace_int_helper_dcache_freeze(void)
+{
+}
+
+static inline void trace_win_helper_gregset_error(uint32_t pstate)
+{
+}
+
+static inline void trace_win_helper_switch_pstate(uint32_t pstate_regs, uint32_t new_pstate_regs)
+{
+}
+
+static inline void trace_win_helper_no_switch_pstate(uint32_t new_pstate_regs)
+{
+}
+
+static inline void trace_win_helper_wrpil(uint32_t psrpil, uint32_t new_pil)
+{
+}
+
+static inline void trace_win_helper_done(uint32_t tl)
+{
+}
+
+static inline void trace_win_helper_retry(uint32_t tl)
+{
+}
+
+static inline void trace_dma_bdrv_io(void * dbs, void * bs, int64_t sector_num, bool to_dev)
+{
+}
+
+static inline void trace_dma_aio_cancel(void * dbs)
+{
+}
+
+static inline void trace_dma_complete(void * dbs, int ret, void * cb)
+{
+}
+
+static inline void trace_dma_bdrv_cb(void * dbs, int ret)
+{
+}
+
+static inline void trace_dma_map_wait(void * dbs)
+{
+}
+
+static inline void trace_console_gfx_new(void)
+{
+}
+
+static inline void trace_console_txt_new(int w, int h)
+{
+}
+
+static inline void trace_console_select(int nr)
+{
+}
+
+static inline void trace_console_refresh(int interval)
+{
+}
+
+static inline void trace_displaysurface_create(void * display_surface, int w, int h)
+{
+}
+
+static inline void trace_displaysurface_create_from(void * display_surface, int w, int h, int bpp, int swap)
+{
+}
+
+static inline void trace_displaysurface_free(void * display_surface)
+{
+}
+
+static inline void trace_displaychangelistener_register(void * dcl, const char * name)
+{
+}
+
+static inline void trace_displaychangelistener_unregister(void * dcl, const char * name)
+{
+}
+
+static inline void trace_ppm_save(const char * filename, void * display_surface)
+{
+}
+
+static inline void trace_vmware_value_read(uint32_t index, uint32_t value)
+{
+}
+
+static inline void trace_vmware_value_write(uint32_t index, uint32_t value)
+{
+}
+
+static inline void trace_vmware_palette_read(uint32_t index, uint32_t value)
+{
+}
+
+static inline void trace_vmware_palette_write(uint32_t index, uint32_t value)
+{
+}
+
+static inline void trace_vmware_scratch_read(uint32_t index, uint32_t value)
+{
+}
+
+static inline void trace_vmware_scratch_write(uint32_t index, uint32_t value)
+{
+}
+
+static inline void trace_vmware_setmode(uint32_t w, uint32_t h, uint32_t bpp)
+{
+}
+
+static inline void trace_savevm_section_start(void)
+{
+}
+
+static inline void trace_savevm_section_end(unsigned int section_id)
+{
+}
+
+static inline void trace_migration_bitmap_sync_start(void)
+{
+}
+
+static inline void trace_migration_bitmap_sync_end(uint64_t dirty_pages)
+{
+}
+
+static inline void trace_migration_throttle(void)
+{
+}
+
+static inline void trace_qxl_create_guest_primary(int qid, uint32_t width, uint32_t height, uint64_t mem, uint32_t format, uint32_t position)
+{
+}
+
+static inline void trace_qxl_create_guest_primary_rest(int qid, int32_t stride, uint32_t type, uint32_t flags)
+{
+}
+
+static inline void trace_qxl_destroy_primary(int qid)
+{
+}
+
+static inline void trace_qxl_enter_vga_mode(int qid)
+{
+}
+
+static inline void trace_qxl_exit_vga_mode(int qid)
+{
+}
+
+static inline void trace_qxl_hard_reset(int qid, int64_t loadvm)
+{
+}
+
+static inline void trace_qxl_interface_async_complete_io(int qid, uint32_t current_async, void * cookie)
+{
+}
+
+static inline void trace_qxl_interface_attach_worker(int qid)
+{
+}
+
+static inline void trace_qxl_interface_get_init_info(int qid)
+{
+}
+
+static inline void trace_qxl_interface_set_compression_level(int qid, int64_t level)
+{
+}
+
+static inline void trace_qxl_interface_update_area_complete(int qid, uint32_t surface_id, uint32_t dirty_left, uint32_t dirty_right, uint32_t dirty_top, uint32_t dirty_bottom)
+{
+}
+
+static inline void trace_qxl_interface_update_area_complete_rest(int qid, uint32_t num_updated_rects)
+{
+}
+
+static inline void trace_qxl_interface_update_area_complete_overflow(int qid, int max)
+{
+}
+
+static inline void trace_qxl_interface_update_area_complete_schedule_bh(int qid, uint32_t num_dirty)
+{
+}
+
+static inline void trace_qxl_io_destroy_primary_ignored(int qid, const char * mode)
+{
+}
+
+static inline void trace_qxl_io_log(int qid, const uint8_t * log_buf)
+{
+}
+
+static inline void trace_qxl_io_read_unexpected(int qid)
+{
+}
+
+static inline void trace_qxl_io_unexpected_vga_mode(int qid, uint64_t addr, uint64_t val, const char * desc)
+{
+}
+
+static inline void trace_qxl_io_write(int qid, const char * mode, uint64_t addr, uint64_t val, unsigned size, int async)
+{
+}
+
+static inline void trace_qxl_memslot_add_guest(int qid, uint32_t slot_id, uint64_t guest_start, uint64_t guest_end)
+{
+}
+
+static inline void trace_qxl_post_load(int qid, const char * mode)
+{
+}
+
+static inline void trace_qxl_pre_load(int qid)
+{
+}
+
+static inline void trace_qxl_pre_save(int qid)
+{
+}
+
+static inline void trace_qxl_reset_surfaces(int qid)
+{
+}
+
+static inline void trace_qxl_ring_command_check(int qid, const char * mode)
+{
+}
+
+static inline void trace_qxl_ring_command_get(int qid, const char * mode)
+{
+}
+
+static inline void trace_qxl_ring_command_req_notification(int qid)
+{
+}
+
+static inline void trace_qxl_ring_cursor_check(int qid, const char * mode)
+{
+}
+
+static inline void trace_qxl_ring_cursor_get(int qid, const char * mode)
+{
+}
+
+static inline void trace_qxl_ring_cursor_req_notification(int qid)
+{
+}
+
+static inline void trace_qxl_ring_res_push(int qid, const char * mode, uint32_t surface_count, uint32_t free_res, void * last_release, const char * notify)
+{
+}
+
+static inline void trace_qxl_ring_res_push_rest(int qid, uint32_t ring_has, uint32_t ring_size, uint32_t prod, uint32_t cons)
+{
+}
+
+static inline void trace_qxl_ring_res_put(int qid, uint32_t free_res)
+{
+}
+
+static inline void trace_qxl_set_mode(int qid, int modenr, uint32_t x_res, uint32_t y_res, uint32_t bits, uint64_t devmem)
+{
+}
+
+static inline void trace_qxl_soft_reset(int qid)
+{
+}
+
+static inline void trace_qemu_spice_add_memslot(int qid, uint32_t slot_id, unsigned long virt_start, unsigned long virt_end, int async)
+{
+}
+
+static inline void trace_qemu_spice_del_memslot(int qid, uint32_t gid, uint32_t slot_id)
+{
+}
+
+static inline void trace_qemu_spice_create_primary_surface(int qid, uint32_t sid, void * surface, int async)
+{
+}
+
+static inline void trace_qemu_spice_destroy_primary_surface(int qid, uint32_t sid, int async)
+{
+}
+
+static inline void trace_qemu_spice_wakeup(uint32_t qid)
+{
+}
+
+static inline void trace_qemu_spice_start(uint32_t qid)
+{
+}
+
+static inline void trace_qemu_spice_stop(uint32_t qid)
+{
+}
+
+static inline void trace_qemu_spice_create_update(uint32_t left, uint32_t right, uint32_t top, uint32_t bottom)
+{
+}
+
+static inline void trace_qxl_spice_destroy_surfaces_complete(int qid)
+{
+}
+
+static inline void trace_qxl_spice_destroy_surfaces(int qid, int async)
+{
+}
+
+static inline void trace_qxl_spice_destroy_surface_wait_complete(int qid, uint32_t id)
+{
+}
+
+static inline void trace_qxl_spice_destroy_surface_wait(int qid, uint32_t id, int async)
+{
+}
+
+static inline void trace_qxl_spice_flush_surfaces_async(int qid, uint32_t surface_count, uint32_t num_free_res)
+{
+}
+
+static inline void trace_qxl_spice_monitors_config(int qid)
+{
+}
+
+static inline void trace_qxl_spice_loadvm_commands(int qid, void * ext, uint32_t count)
+{
+}
+
+static inline void trace_qxl_spice_oom(int qid)
+{
+}
+
+static inline void trace_qxl_spice_reset_cursor(int qid)
+{
+}
+
+static inline void trace_qxl_spice_reset_image_cache(int qid)
+{
+}
+
+static inline void trace_qxl_spice_reset_memslots(int qid)
+{
+}
+
+static inline void trace_qxl_spice_update_area(int qid, uint32_t surface_id, uint32_t left, uint32_t right, uint32_t top, uint32_t bottom)
+{
+}
+
+static inline void trace_qxl_spice_update_area_rest(int qid, uint32_t num_dirty_rects, uint32_t clear_dirty_region)
+{
+}
+
+static inline void trace_qxl_surfaces_dirty(int qid, int surface, int offset, int size)
+{
+}
+
+static inline void trace_qxl_send_events(int qid, uint32_t events)
+{
+}
+
+static inline void trace_qxl_send_events_vm_stopped(int qid, uint32_t events)
+{
+}
+
+static inline void trace_qxl_set_guest_bug(int qid)
+{
+}
+
+static inline void trace_qxl_interrupt_client_monitors_config(int qid, int num_heads, void * heads)
+{
+}
+
+static inline void trace_qxl_client_monitors_config_unsupported_by_guest(int qid, uint32_t int_mask, void * client_monitors_config)
+{
+}
+
+static inline void trace_qxl_client_monitors_config_unsupported_by_device(int qid, int revision)
+{
+}
+
+static inline void trace_qxl_client_monitors_config_capped(int qid, int requested, int limit)
+{
+}
+
+static inline void trace_qxl_client_monitors_config_crc(int qid, unsigned size, uint32_t crc32)
+{
+}
+
+static inline void trace_qxl_set_client_capabilities_unsupported_by_revision(int qid, int revision)
+{
+}
+
+static inline void trace_qxl_render_blit_guest_primary_initialized(void)
+{
+}
+
+static inline void trace_qxl_render_blit(int32_t stride, int32_t left, int32_t right, int32_t top, int32_t bottom)
+{
+}
+
+static inline void trace_qxl_render_guest_primary_resized(int32_t width, int32_t height, int32_t stride, int32_t bytes_pp, int32_t bits_pp)
+{
+}
+
+static inline void trace_qxl_render_update_area_done(void * cookie)
+{
+}
+
+static inline void trace_spapr_pci_msi(const char * msg, uint32_t n, uint32_t ca)
+{
+}
+
+static inline void trace_spapr_pci_msi_setup(const char * name, unsigned vector, uint64_t addr)
+{
+}
+
+static inline void trace_spapr_pci_rtas_ibm_change_msi(unsigned func, unsigned req)
+{
+}
+
+static inline void trace_spapr_pci_rtas_ibm_query_interrupt_source_number(unsigned ioa, unsigned intr)
+{
+}
+
+static inline void trace_spapr_pci_msi_write(uint64_t addr, uint64_t data, uint32_t dt_irq)
+{
+}
+
+static inline void trace_spapr_pci_lsi_set(const char * busname, int pin, uint32_t irq)
+{
+}
+
+static inline void trace_xics_icp_check_ipi(int server, uint8_t mfrr)
+{
+}
+
+static inline void trace_xics_icp_accept(uint32_t old_xirr, uint32_t new_xirr)
+{
+}
+
+static inline void trace_xics_icp_eoi(int server, uint32_t xirr, uint32_t new_xirr)
+{
+}
+
+static inline void trace_xics_icp_irq(int server, int nr, uint8_t priority)
+{
+}
+
+static inline void trace_xics_icp_raise(uint32_t xirr, uint8_t pending_priority)
+{
+}
+
+static inline void trace_xics_set_irq_msi(int srcno, int nr)
+{
+}
+
+static inline void trace_xics_masked_pending(void)
+{
+}
+
+static inline void trace_xics_set_irq_lsi(int srcno, int nr)
+{
+}
+
+static inline void trace_xics_ics_write_xive(int nr, int srcno, int server, uint8_t priority)
+{
+}
+
+static inline void trace_xics_ics_reject(int nr, int srcno)
+{
+}
+
+static inline void trace_xics_ics_eoi(int nr)
+{
+}
+
+static inline void trace_hbitmap_iter_skip_words(const void * hb, void * hbi, uint64_t pos, unsigned long cur)
+{
+}
+
+static inline void trace_hbitmap_reset(void * hb, uint64_t start, uint64_t count, uint64_t sbit, uint64_t ebit)
+{
+}
+
+static inline void trace_hbitmap_set(void * hb, uint64_t start, uint64_t count, uint64_t sbit, uint64_t ebit)
+{
+}
+
+static inline void trace_ioinst(const char * insn)
+{
+}
+
+static inline void trace_ioinst_sch_id(const char * insn, int cssid, int ssid, int schid)
+{
+}
+
+static inline void trace_ioinst_chp_id(const char * insn, int cssid, int chpid)
+{
+}
+
+static inline void trace_ioinst_chsc_cmd(uint16_t cmd, uint16_t len)
+{
+}
+
+static inline void trace_css_enable_facility(const char * facility)
+{
+}
+
+static inline void trace_css_crw(uint8_t rsc, uint8_t erc, uint16_t rsid, const char * chained)
+{
+}
+
+static inline void trace_css_chpid_add(uint8_t cssid, uint8_t chpid, uint8_t type)
+{
+}
+
+static inline void trace_css_new_image(uint8_t cssid, const char * default_cssid)
+{
+}
+
+static inline void trace_css_assign_subch(const char * do_assign, uint8_t cssid, uint8_t ssid, uint16_t schid, uint16_t devno)
+{
+}
+
+static inline void trace_css_io_interrupt(int cssid, int ssid, int schid, uint32_t intparm, uint8_t isc, const char * conditional)
+{
+}
+
+static inline void trace_virtio_ccw_interpret_ccw(int cssid, int ssid, int schid, int cmd_code)
+{
+}
+
+static inline void trace_virtio_ccw_new_device(int cssid, int ssid, int schid, int devno, const char * devno_mode)
+{
+}
+
+static inline void trace_migrate_set_state(int new_state)
+{
+}
+
+static inline void trace_kvm_ioctl(int type, void * arg)
+{
+}
+
+static inline void trace_kvm_vm_ioctl(int type, void * arg)
+{
+}
+
+static inline void trace_kvm_vcpu_ioctl(int cpu_index, int type, void * arg)
+{
+}
+
+static inline void trace_kvm_run_exit(int cpu_index, uint32_t reason)
+{
+}
+
+static inline void trace_object_dynamic_cast_assert(const char * type, const char * target, const char * file, int line, const char * func)
+{
+}
+
+static inline void trace_object_class_dynamic_cast_assert(const char * type, const char * target, const char * file, int line, const char * func)
+{
+}
+#endif /* TRACE__GENERATED_TRACERS_H */
diff --git a/contrib/qemu/util/aes.c b/contrib/qemu/util/aes.c
new file mode 100644
index 00000000000..91e97fa6e7f
--- /dev/null
+++ b/contrib/qemu/util/aes.c
@@ -0,0 +1,1314 @@
+/**
+ *
+ * aes.c - integrated in QEMU by Fabrice Bellard from the OpenSSL project.
+ */
+/*
+ * rijndael-alg-fst.c
+ *
+ * @version 3.0 (December 2000)
+ *
+ * Optimised ANSI C code for the Rijndael cipher (now AES)
+ *
+ * @author Vincent Rijmen <vincent.rijmen@esat.kuleuven.ac.be>
+ * @author Antoon Bosselaers <antoon.bosselaers@esat.kuleuven.ac.be>
+ * @author Paulo Barreto <paulo.barreto@terra.com.br>
+ *
+ * This code is hereby placed in the public domain.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHORS ''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 THE AUTHORS 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 "qemu-common.h"
+#include "qemu/aes.h"
+
+#ifndef NDEBUG
+#define NDEBUG
+#endif
+
+typedef uint32_t u32;
+typedef uint16_t u16;
+typedef uint8_t u8;
+
+/* This controls loop-unrolling in aes_core.c */
+#undef FULL_UNROLL
+# define GETU32(pt) (((u32)(pt)[0] << 24) ^ ((u32)(pt)[1] << 16) ^ ((u32)(pt)[2] << 8) ^ ((u32)(pt)[3]))
+# define PUTU32(ct, st) { (ct)[0] = (u8)((st) >> 24); (ct)[1] = (u8)((st) >> 16); (ct)[2] = (u8)((st) >> 8); (ct)[3] = (u8)(st); }
+
+/*
+AES_Te0[x] = S [x].[02, 01, 01, 03];
+AES_Te1[x] = S [x].[03, 02, 01, 01];
+AES_Te2[x] = S [x].[01, 03, 02, 01];
+AES_Te3[x] = S [x].[01, 01, 03, 02];
+AES_Te4[x] = S [x].[01, 01, 01, 01];
+
+AES_Td0[x] = Si[x].[0e, 09, 0d, 0b];
+AES_Td1[x] = Si[x].[0b, 0e, 09, 0d];
+AES_Td2[x] = Si[x].[0d, 0b, 0e, 09];
+AES_Td3[x] = Si[x].[09, 0d, 0b, 0e];
+AES_Td4[x] = Si[x].[01, 01, 01, 01];
+*/
+
+const uint32_t AES_Te0[256] = {
+ 0xc66363a5U, 0xf87c7c84U, 0xee777799U, 0xf67b7b8dU,
+ 0xfff2f20dU, 0xd66b6bbdU, 0xde6f6fb1U, 0x91c5c554U,
+ 0x60303050U, 0x02010103U, 0xce6767a9U, 0x562b2b7dU,
+ 0xe7fefe19U, 0xb5d7d762U, 0x4dababe6U, 0xec76769aU,
+ 0x8fcaca45U, 0x1f82829dU, 0x89c9c940U, 0xfa7d7d87U,
+ 0xeffafa15U, 0xb25959ebU, 0x8e4747c9U, 0xfbf0f00bU,
+ 0x41adadecU, 0xb3d4d467U, 0x5fa2a2fdU, 0x45afafeaU,
+ 0x239c9cbfU, 0x53a4a4f7U, 0xe4727296U, 0x9bc0c05bU,
+ 0x75b7b7c2U, 0xe1fdfd1cU, 0x3d9393aeU, 0x4c26266aU,
+ 0x6c36365aU, 0x7e3f3f41U, 0xf5f7f702U, 0x83cccc4fU,
+ 0x6834345cU, 0x51a5a5f4U, 0xd1e5e534U, 0xf9f1f108U,
+ 0xe2717193U, 0xabd8d873U, 0x62313153U, 0x2a15153fU,
+ 0x0804040cU, 0x95c7c752U, 0x46232365U, 0x9dc3c35eU,
+ 0x30181828U, 0x379696a1U, 0x0a05050fU, 0x2f9a9ab5U,
+ 0x0e070709U, 0x24121236U, 0x1b80809bU, 0xdfe2e23dU,
+ 0xcdebeb26U, 0x4e272769U, 0x7fb2b2cdU, 0xea75759fU,
+ 0x1209091bU, 0x1d83839eU, 0x582c2c74U, 0x341a1a2eU,
+ 0x361b1b2dU, 0xdc6e6eb2U, 0xb45a5aeeU, 0x5ba0a0fbU,
+ 0xa45252f6U, 0x763b3b4dU, 0xb7d6d661U, 0x7db3b3ceU,
+ 0x5229297bU, 0xdde3e33eU, 0x5e2f2f71U, 0x13848497U,
+ 0xa65353f5U, 0xb9d1d168U, 0x00000000U, 0xc1eded2cU,
+ 0x40202060U, 0xe3fcfc1fU, 0x79b1b1c8U, 0xb65b5bedU,
+ 0xd46a6abeU, 0x8dcbcb46U, 0x67bebed9U, 0x7239394bU,
+ 0x944a4adeU, 0x984c4cd4U, 0xb05858e8U, 0x85cfcf4aU,
+ 0xbbd0d06bU, 0xc5efef2aU, 0x4faaaae5U, 0xedfbfb16U,
+ 0x864343c5U, 0x9a4d4dd7U, 0x66333355U, 0x11858594U,
+ 0x8a4545cfU, 0xe9f9f910U, 0x04020206U, 0xfe7f7f81U,
+ 0xa05050f0U, 0x783c3c44U, 0x259f9fbaU, 0x4ba8a8e3U,
+ 0xa25151f3U, 0x5da3a3feU, 0x804040c0U, 0x058f8f8aU,
+ 0x3f9292adU, 0x219d9dbcU, 0x70383848U, 0xf1f5f504U,
+ 0x63bcbcdfU, 0x77b6b6c1U, 0xafdada75U, 0x42212163U,
+ 0x20101030U, 0xe5ffff1aU, 0xfdf3f30eU, 0xbfd2d26dU,
+ 0x81cdcd4cU, 0x180c0c14U, 0x26131335U, 0xc3ecec2fU,
+ 0xbe5f5fe1U, 0x359797a2U, 0x884444ccU, 0x2e171739U,
+ 0x93c4c457U, 0x55a7a7f2U, 0xfc7e7e82U, 0x7a3d3d47U,
+ 0xc86464acU, 0xba5d5de7U, 0x3219192bU, 0xe6737395U,
+ 0xc06060a0U, 0x19818198U, 0x9e4f4fd1U, 0xa3dcdc7fU,
+ 0x44222266U, 0x542a2a7eU, 0x3b9090abU, 0x0b888883U,
+ 0x8c4646caU, 0xc7eeee29U, 0x6bb8b8d3U, 0x2814143cU,
+ 0xa7dede79U, 0xbc5e5ee2U, 0x160b0b1dU, 0xaddbdb76U,
+ 0xdbe0e03bU, 0x64323256U, 0x743a3a4eU, 0x140a0a1eU,
+ 0x924949dbU, 0x0c06060aU, 0x4824246cU, 0xb85c5ce4U,
+ 0x9fc2c25dU, 0xbdd3d36eU, 0x43acacefU, 0xc46262a6U,
+ 0x399191a8U, 0x319595a4U, 0xd3e4e437U, 0xf279798bU,
+ 0xd5e7e732U, 0x8bc8c843U, 0x6e373759U, 0xda6d6db7U,
+ 0x018d8d8cU, 0xb1d5d564U, 0x9c4e4ed2U, 0x49a9a9e0U,
+ 0xd86c6cb4U, 0xac5656faU, 0xf3f4f407U, 0xcfeaea25U,
+ 0xca6565afU, 0xf47a7a8eU, 0x47aeaee9U, 0x10080818U,
+ 0x6fbabad5U, 0xf0787888U, 0x4a25256fU, 0x5c2e2e72U,
+ 0x381c1c24U, 0x57a6a6f1U, 0x73b4b4c7U, 0x97c6c651U,
+ 0xcbe8e823U, 0xa1dddd7cU, 0xe874749cU, 0x3e1f1f21U,
+ 0x964b4bddU, 0x61bdbddcU, 0x0d8b8b86U, 0x0f8a8a85U,
+ 0xe0707090U, 0x7c3e3e42U, 0x71b5b5c4U, 0xcc6666aaU,
+ 0x904848d8U, 0x06030305U, 0xf7f6f601U, 0x1c0e0e12U,
+ 0xc26161a3U, 0x6a35355fU, 0xae5757f9U, 0x69b9b9d0U,
+ 0x17868691U, 0x99c1c158U, 0x3a1d1d27U, 0x279e9eb9U,
+ 0xd9e1e138U, 0xebf8f813U, 0x2b9898b3U, 0x22111133U,
+ 0xd26969bbU, 0xa9d9d970U, 0x078e8e89U, 0x339494a7U,
+ 0x2d9b9bb6U, 0x3c1e1e22U, 0x15878792U, 0xc9e9e920U,
+ 0x87cece49U, 0xaa5555ffU, 0x50282878U, 0xa5dfdf7aU,
+ 0x038c8c8fU, 0x59a1a1f8U, 0x09898980U, 0x1a0d0d17U,
+ 0x65bfbfdaU, 0xd7e6e631U, 0x844242c6U, 0xd06868b8U,
+ 0x824141c3U, 0x299999b0U, 0x5a2d2d77U, 0x1e0f0f11U,
+ 0x7bb0b0cbU, 0xa85454fcU, 0x6dbbbbd6U, 0x2c16163aU,
+};
+const uint32_t AES_Te1[256] = {
+ 0xa5c66363U, 0x84f87c7cU, 0x99ee7777U, 0x8df67b7bU,
+ 0x0dfff2f2U, 0xbdd66b6bU, 0xb1de6f6fU, 0x5491c5c5U,
+ 0x50603030U, 0x03020101U, 0xa9ce6767U, 0x7d562b2bU,
+ 0x19e7fefeU, 0x62b5d7d7U, 0xe64dababU, 0x9aec7676U,
+ 0x458fcacaU, 0x9d1f8282U, 0x4089c9c9U, 0x87fa7d7dU,
+ 0x15effafaU, 0xebb25959U, 0xc98e4747U, 0x0bfbf0f0U,
+ 0xec41adadU, 0x67b3d4d4U, 0xfd5fa2a2U, 0xea45afafU,
+ 0xbf239c9cU, 0xf753a4a4U, 0x96e47272U, 0x5b9bc0c0U,
+ 0xc275b7b7U, 0x1ce1fdfdU, 0xae3d9393U, 0x6a4c2626U,
+ 0x5a6c3636U, 0x417e3f3fU, 0x02f5f7f7U, 0x4f83ccccU,
+ 0x5c683434U, 0xf451a5a5U, 0x34d1e5e5U, 0x08f9f1f1U,
+ 0x93e27171U, 0x73abd8d8U, 0x53623131U, 0x3f2a1515U,
+ 0x0c080404U, 0x5295c7c7U, 0x65462323U, 0x5e9dc3c3U,
+ 0x28301818U, 0xa1379696U, 0x0f0a0505U, 0xb52f9a9aU,
+ 0x090e0707U, 0x36241212U, 0x9b1b8080U, 0x3ddfe2e2U,
+ 0x26cdebebU, 0x694e2727U, 0xcd7fb2b2U, 0x9fea7575U,
+ 0x1b120909U, 0x9e1d8383U, 0x74582c2cU, 0x2e341a1aU,
+ 0x2d361b1bU, 0xb2dc6e6eU, 0xeeb45a5aU, 0xfb5ba0a0U,
+ 0xf6a45252U, 0x4d763b3bU, 0x61b7d6d6U, 0xce7db3b3U,
+ 0x7b522929U, 0x3edde3e3U, 0x715e2f2fU, 0x97138484U,
+ 0xf5a65353U, 0x68b9d1d1U, 0x00000000U, 0x2cc1ededU,
+ 0x60402020U, 0x1fe3fcfcU, 0xc879b1b1U, 0xedb65b5bU,
+ 0xbed46a6aU, 0x468dcbcbU, 0xd967bebeU, 0x4b723939U,
+ 0xde944a4aU, 0xd4984c4cU, 0xe8b05858U, 0x4a85cfcfU,
+ 0x6bbbd0d0U, 0x2ac5efefU, 0xe54faaaaU, 0x16edfbfbU,
+ 0xc5864343U, 0xd79a4d4dU, 0x55663333U, 0x94118585U,
+ 0xcf8a4545U, 0x10e9f9f9U, 0x06040202U, 0x81fe7f7fU,
+ 0xf0a05050U, 0x44783c3cU, 0xba259f9fU, 0xe34ba8a8U,
+ 0xf3a25151U, 0xfe5da3a3U, 0xc0804040U, 0x8a058f8fU,
+ 0xad3f9292U, 0xbc219d9dU, 0x48703838U, 0x04f1f5f5U,
+ 0xdf63bcbcU, 0xc177b6b6U, 0x75afdadaU, 0x63422121U,
+ 0x30201010U, 0x1ae5ffffU, 0x0efdf3f3U, 0x6dbfd2d2U,
+ 0x4c81cdcdU, 0x14180c0cU, 0x35261313U, 0x2fc3ececU,
+ 0xe1be5f5fU, 0xa2359797U, 0xcc884444U, 0x392e1717U,
+ 0x5793c4c4U, 0xf255a7a7U, 0x82fc7e7eU, 0x477a3d3dU,
+ 0xacc86464U, 0xe7ba5d5dU, 0x2b321919U, 0x95e67373U,
+ 0xa0c06060U, 0x98198181U, 0xd19e4f4fU, 0x7fa3dcdcU,
+ 0x66442222U, 0x7e542a2aU, 0xab3b9090U, 0x830b8888U,
+ 0xca8c4646U, 0x29c7eeeeU, 0xd36bb8b8U, 0x3c281414U,
+ 0x79a7dedeU, 0xe2bc5e5eU, 0x1d160b0bU, 0x76addbdbU,
+ 0x3bdbe0e0U, 0x56643232U, 0x4e743a3aU, 0x1e140a0aU,
+ 0xdb924949U, 0x0a0c0606U, 0x6c482424U, 0xe4b85c5cU,
+ 0x5d9fc2c2U, 0x6ebdd3d3U, 0xef43acacU, 0xa6c46262U,
+ 0xa8399191U, 0xa4319595U, 0x37d3e4e4U, 0x8bf27979U,
+ 0x32d5e7e7U, 0x438bc8c8U, 0x596e3737U, 0xb7da6d6dU,
+ 0x8c018d8dU, 0x64b1d5d5U, 0xd29c4e4eU, 0xe049a9a9U,
+ 0xb4d86c6cU, 0xfaac5656U, 0x07f3f4f4U, 0x25cfeaeaU,
+ 0xafca6565U, 0x8ef47a7aU, 0xe947aeaeU, 0x18100808U,
+ 0xd56fbabaU, 0x88f07878U, 0x6f4a2525U, 0x725c2e2eU,
+ 0x24381c1cU, 0xf157a6a6U, 0xc773b4b4U, 0x5197c6c6U,
+ 0x23cbe8e8U, 0x7ca1ddddU, 0x9ce87474U, 0x213e1f1fU,
+ 0xdd964b4bU, 0xdc61bdbdU, 0x860d8b8bU, 0x850f8a8aU,
+ 0x90e07070U, 0x427c3e3eU, 0xc471b5b5U, 0xaacc6666U,
+ 0xd8904848U, 0x05060303U, 0x01f7f6f6U, 0x121c0e0eU,
+ 0xa3c26161U, 0x5f6a3535U, 0xf9ae5757U, 0xd069b9b9U,
+ 0x91178686U, 0x5899c1c1U, 0x273a1d1dU, 0xb9279e9eU,
+ 0x38d9e1e1U, 0x13ebf8f8U, 0xb32b9898U, 0x33221111U,
+ 0xbbd26969U, 0x70a9d9d9U, 0x89078e8eU, 0xa7339494U,
+ 0xb62d9b9bU, 0x223c1e1eU, 0x92158787U, 0x20c9e9e9U,
+ 0x4987ceceU, 0xffaa5555U, 0x78502828U, 0x7aa5dfdfU,
+ 0x8f038c8cU, 0xf859a1a1U, 0x80098989U, 0x171a0d0dU,
+ 0xda65bfbfU, 0x31d7e6e6U, 0xc6844242U, 0xb8d06868U,
+ 0xc3824141U, 0xb0299999U, 0x775a2d2dU, 0x111e0f0fU,
+ 0xcb7bb0b0U, 0xfca85454U, 0xd66dbbbbU, 0x3a2c1616U,
+};
+const uint32_t AES_Te2[256] = {
+ 0x63a5c663U, 0x7c84f87cU, 0x7799ee77U, 0x7b8df67bU,
+ 0xf20dfff2U, 0x6bbdd66bU, 0x6fb1de6fU, 0xc55491c5U,
+ 0x30506030U, 0x01030201U, 0x67a9ce67U, 0x2b7d562bU,
+ 0xfe19e7feU, 0xd762b5d7U, 0xabe64dabU, 0x769aec76U,
+ 0xca458fcaU, 0x829d1f82U, 0xc94089c9U, 0x7d87fa7dU,
+ 0xfa15effaU, 0x59ebb259U, 0x47c98e47U, 0xf00bfbf0U,
+ 0xadec41adU, 0xd467b3d4U, 0xa2fd5fa2U, 0xafea45afU,
+ 0x9cbf239cU, 0xa4f753a4U, 0x7296e472U, 0xc05b9bc0U,
+ 0xb7c275b7U, 0xfd1ce1fdU, 0x93ae3d93U, 0x266a4c26U,
+ 0x365a6c36U, 0x3f417e3fU, 0xf702f5f7U, 0xcc4f83ccU,
+ 0x345c6834U, 0xa5f451a5U, 0xe534d1e5U, 0xf108f9f1U,
+ 0x7193e271U, 0xd873abd8U, 0x31536231U, 0x153f2a15U,
+ 0x040c0804U, 0xc75295c7U, 0x23654623U, 0xc35e9dc3U,
+ 0x18283018U, 0x96a13796U, 0x050f0a05U, 0x9ab52f9aU,
+ 0x07090e07U, 0x12362412U, 0x809b1b80U, 0xe23ddfe2U,
+ 0xeb26cdebU, 0x27694e27U, 0xb2cd7fb2U, 0x759fea75U,
+ 0x091b1209U, 0x839e1d83U, 0x2c74582cU, 0x1a2e341aU,
+ 0x1b2d361bU, 0x6eb2dc6eU, 0x5aeeb45aU, 0xa0fb5ba0U,
+ 0x52f6a452U, 0x3b4d763bU, 0xd661b7d6U, 0xb3ce7db3U,
+ 0x297b5229U, 0xe33edde3U, 0x2f715e2fU, 0x84971384U,
+ 0x53f5a653U, 0xd168b9d1U, 0x00000000U, 0xed2cc1edU,
+ 0x20604020U, 0xfc1fe3fcU, 0xb1c879b1U, 0x5bedb65bU,
+ 0x6abed46aU, 0xcb468dcbU, 0xbed967beU, 0x394b7239U,
+ 0x4ade944aU, 0x4cd4984cU, 0x58e8b058U, 0xcf4a85cfU,
+ 0xd06bbbd0U, 0xef2ac5efU, 0xaae54faaU, 0xfb16edfbU,
+ 0x43c58643U, 0x4dd79a4dU, 0x33556633U, 0x85941185U,
+ 0x45cf8a45U, 0xf910e9f9U, 0x02060402U, 0x7f81fe7fU,
+ 0x50f0a050U, 0x3c44783cU, 0x9fba259fU, 0xa8e34ba8U,
+ 0x51f3a251U, 0xa3fe5da3U, 0x40c08040U, 0x8f8a058fU,
+ 0x92ad3f92U, 0x9dbc219dU, 0x38487038U, 0xf504f1f5U,
+ 0xbcdf63bcU, 0xb6c177b6U, 0xda75afdaU, 0x21634221U,
+ 0x10302010U, 0xff1ae5ffU, 0xf30efdf3U, 0xd26dbfd2U,
+ 0xcd4c81cdU, 0x0c14180cU, 0x13352613U, 0xec2fc3ecU,
+ 0x5fe1be5fU, 0x97a23597U, 0x44cc8844U, 0x17392e17U,
+ 0xc45793c4U, 0xa7f255a7U, 0x7e82fc7eU, 0x3d477a3dU,
+ 0x64acc864U, 0x5de7ba5dU, 0x192b3219U, 0x7395e673U,
+ 0x60a0c060U, 0x81981981U, 0x4fd19e4fU, 0xdc7fa3dcU,
+ 0x22664422U, 0x2a7e542aU, 0x90ab3b90U, 0x88830b88U,
+ 0x46ca8c46U, 0xee29c7eeU, 0xb8d36bb8U, 0x143c2814U,
+ 0xde79a7deU, 0x5ee2bc5eU, 0x0b1d160bU, 0xdb76addbU,
+ 0xe03bdbe0U, 0x32566432U, 0x3a4e743aU, 0x0a1e140aU,
+ 0x49db9249U, 0x060a0c06U, 0x246c4824U, 0x5ce4b85cU,
+ 0xc25d9fc2U, 0xd36ebdd3U, 0xacef43acU, 0x62a6c462U,
+ 0x91a83991U, 0x95a43195U, 0xe437d3e4U, 0x798bf279U,
+ 0xe732d5e7U, 0xc8438bc8U, 0x37596e37U, 0x6db7da6dU,
+ 0x8d8c018dU, 0xd564b1d5U, 0x4ed29c4eU, 0xa9e049a9U,
+ 0x6cb4d86cU, 0x56faac56U, 0xf407f3f4U, 0xea25cfeaU,
+ 0x65afca65U, 0x7a8ef47aU, 0xaee947aeU, 0x08181008U,
+ 0xbad56fbaU, 0x7888f078U, 0x256f4a25U, 0x2e725c2eU,
+ 0x1c24381cU, 0xa6f157a6U, 0xb4c773b4U, 0xc65197c6U,
+ 0xe823cbe8U, 0xdd7ca1ddU, 0x749ce874U, 0x1f213e1fU,
+ 0x4bdd964bU, 0xbddc61bdU, 0x8b860d8bU, 0x8a850f8aU,
+ 0x7090e070U, 0x3e427c3eU, 0xb5c471b5U, 0x66aacc66U,
+ 0x48d89048U, 0x03050603U, 0xf601f7f6U, 0x0e121c0eU,
+ 0x61a3c261U, 0x355f6a35U, 0x57f9ae57U, 0xb9d069b9U,
+ 0x86911786U, 0xc15899c1U, 0x1d273a1dU, 0x9eb9279eU,
+ 0xe138d9e1U, 0xf813ebf8U, 0x98b32b98U, 0x11332211U,
+ 0x69bbd269U, 0xd970a9d9U, 0x8e89078eU, 0x94a73394U,
+ 0x9bb62d9bU, 0x1e223c1eU, 0x87921587U, 0xe920c9e9U,
+ 0xce4987ceU, 0x55ffaa55U, 0x28785028U, 0xdf7aa5dfU,
+ 0x8c8f038cU, 0xa1f859a1U, 0x89800989U, 0x0d171a0dU,
+ 0xbfda65bfU, 0xe631d7e6U, 0x42c68442U, 0x68b8d068U,
+ 0x41c38241U, 0x99b02999U, 0x2d775a2dU, 0x0f111e0fU,
+ 0xb0cb7bb0U, 0x54fca854U, 0xbbd66dbbU, 0x163a2c16U,
+};
+const uint32_t AES_Te3[256] = {
+
+ 0x6363a5c6U, 0x7c7c84f8U, 0x777799eeU, 0x7b7b8df6U,
+ 0xf2f20dffU, 0x6b6bbdd6U, 0x6f6fb1deU, 0xc5c55491U,
+ 0x30305060U, 0x01010302U, 0x6767a9ceU, 0x2b2b7d56U,
+ 0xfefe19e7U, 0xd7d762b5U, 0xababe64dU, 0x76769aecU,
+ 0xcaca458fU, 0x82829d1fU, 0xc9c94089U, 0x7d7d87faU,
+ 0xfafa15efU, 0x5959ebb2U, 0x4747c98eU, 0xf0f00bfbU,
+ 0xadadec41U, 0xd4d467b3U, 0xa2a2fd5fU, 0xafafea45U,
+ 0x9c9cbf23U, 0xa4a4f753U, 0x727296e4U, 0xc0c05b9bU,
+ 0xb7b7c275U, 0xfdfd1ce1U, 0x9393ae3dU, 0x26266a4cU,
+ 0x36365a6cU, 0x3f3f417eU, 0xf7f702f5U, 0xcccc4f83U,
+ 0x34345c68U, 0xa5a5f451U, 0xe5e534d1U, 0xf1f108f9U,
+ 0x717193e2U, 0xd8d873abU, 0x31315362U, 0x15153f2aU,
+ 0x04040c08U, 0xc7c75295U, 0x23236546U, 0xc3c35e9dU,
+ 0x18182830U, 0x9696a137U, 0x05050f0aU, 0x9a9ab52fU,
+ 0x0707090eU, 0x12123624U, 0x80809b1bU, 0xe2e23ddfU,
+ 0xebeb26cdU, 0x2727694eU, 0xb2b2cd7fU, 0x75759feaU,
+ 0x09091b12U, 0x83839e1dU, 0x2c2c7458U, 0x1a1a2e34U,
+ 0x1b1b2d36U, 0x6e6eb2dcU, 0x5a5aeeb4U, 0xa0a0fb5bU,
+ 0x5252f6a4U, 0x3b3b4d76U, 0xd6d661b7U, 0xb3b3ce7dU,
+ 0x29297b52U, 0xe3e33eddU, 0x2f2f715eU, 0x84849713U,
+ 0x5353f5a6U, 0xd1d168b9U, 0x00000000U, 0xeded2cc1U,
+ 0x20206040U, 0xfcfc1fe3U, 0xb1b1c879U, 0x5b5bedb6U,
+ 0x6a6abed4U, 0xcbcb468dU, 0xbebed967U, 0x39394b72U,
+ 0x4a4ade94U, 0x4c4cd498U, 0x5858e8b0U, 0xcfcf4a85U,
+ 0xd0d06bbbU, 0xefef2ac5U, 0xaaaae54fU, 0xfbfb16edU,
+ 0x4343c586U, 0x4d4dd79aU, 0x33335566U, 0x85859411U,
+ 0x4545cf8aU, 0xf9f910e9U, 0x02020604U, 0x7f7f81feU,
+ 0x5050f0a0U, 0x3c3c4478U, 0x9f9fba25U, 0xa8a8e34bU,
+ 0x5151f3a2U, 0xa3a3fe5dU, 0x4040c080U, 0x8f8f8a05U,
+ 0x9292ad3fU, 0x9d9dbc21U, 0x38384870U, 0xf5f504f1U,
+ 0xbcbcdf63U, 0xb6b6c177U, 0xdada75afU, 0x21216342U,
+ 0x10103020U, 0xffff1ae5U, 0xf3f30efdU, 0xd2d26dbfU,
+ 0xcdcd4c81U, 0x0c0c1418U, 0x13133526U, 0xecec2fc3U,
+ 0x5f5fe1beU, 0x9797a235U, 0x4444cc88U, 0x1717392eU,
+ 0xc4c45793U, 0xa7a7f255U, 0x7e7e82fcU, 0x3d3d477aU,
+ 0x6464acc8U, 0x5d5de7baU, 0x19192b32U, 0x737395e6U,
+ 0x6060a0c0U, 0x81819819U, 0x4f4fd19eU, 0xdcdc7fa3U,
+ 0x22226644U, 0x2a2a7e54U, 0x9090ab3bU, 0x8888830bU,
+ 0x4646ca8cU, 0xeeee29c7U, 0xb8b8d36bU, 0x14143c28U,
+ 0xdede79a7U, 0x5e5ee2bcU, 0x0b0b1d16U, 0xdbdb76adU,
+ 0xe0e03bdbU, 0x32325664U, 0x3a3a4e74U, 0x0a0a1e14U,
+ 0x4949db92U, 0x06060a0cU, 0x24246c48U, 0x5c5ce4b8U,
+ 0xc2c25d9fU, 0xd3d36ebdU, 0xacacef43U, 0x6262a6c4U,
+ 0x9191a839U, 0x9595a431U, 0xe4e437d3U, 0x79798bf2U,
+ 0xe7e732d5U, 0xc8c8438bU, 0x3737596eU, 0x6d6db7daU,
+ 0x8d8d8c01U, 0xd5d564b1U, 0x4e4ed29cU, 0xa9a9e049U,
+ 0x6c6cb4d8U, 0x5656faacU, 0xf4f407f3U, 0xeaea25cfU,
+ 0x6565afcaU, 0x7a7a8ef4U, 0xaeaee947U, 0x08081810U,
+ 0xbabad56fU, 0x787888f0U, 0x25256f4aU, 0x2e2e725cU,
+ 0x1c1c2438U, 0xa6a6f157U, 0xb4b4c773U, 0xc6c65197U,
+ 0xe8e823cbU, 0xdddd7ca1U, 0x74749ce8U, 0x1f1f213eU,
+ 0x4b4bdd96U, 0xbdbddc61U, 0x8b8b860dU, 0x8a8a850fU,
+ 0x707090e0U, 0x3e3e427cU, 0xb5b5c471U, 0x6666aaccU,
+ 0x4848d890U, 0x03030506U, 0xf6f601f7U, 0x0e0e121cU,
+ 0x6161a3c2U, 0x35355f6aU, 0x5757f9aeU, 0xb9b9d069U,
+ 0x86869117U, 0xc1c15899U, 0x1d1d273aU, 0x9e9eb927U,
+ 0xe1e138d9U, 0xf8f813ebU, 0x9898b32bU, 0x11113322U,
+ 0x6969bbd2U, 0xd9d970a9U, 0x8e8e8907U, 0x9494a733U,
+ 0x9b9bb62dU, 0x1e1e223cU, 0x87879215U, 0xe9e920c9U,
+ 0xcece4987U, 0x5555ffaaU, 0x28287850U, 0xdfdf7aa5U,
+ 0x8c8c8f03U, 0xa1a1f859U, 0x89898009U, 0x0d0d171aU,
+ 0xbfbfda65U, 0xe6e631d7U, 0x4242c684U, 0x6868b8d0U,
+ 0x4141c382U, 0x9999b029U, 0x2d2d775aU, 0x0f0f111eU,
+ 0xb0b0cb7bU, 0x5454fca8U, 0xbbbbd66dU, 0x16163a2cU,
+};
+const uint32_t AES_Te4[256] = {
+ 0x63636363U, 0x7c7c7c7cU, 0x77777777U, 0x7b7b7b7bU,
+ 0xf2f2f2f2U, 0x6b6b6b6bU, 0x6f6f6f6fU, 0xc5c5c5c5U,
+ 0x30303030U, 0x01010101U, 0x67676767U, 0x2b2b2b2bU,
+ 0xfefefefeU, 0xd7d7d7d7U, 0xababababU, 0x76767676U,
+ 0xcacacacaU, 0x82828282U, 0xc9c9c9c9U, 0x7d7d7d7dU,
+ 0xfafafafaU, 0x59595959U, 0x47474747U, 0xf0f0f0f0U,
+ 0xadadadadU, 0xd4d4d4d4U, 0xa2a2a2a2U, 0xafafafafU,
+ 0x9c9c9c9cU, 0xa4a4a4a4U, 0x72727272U, 0xc0c0c0c0U,
+ 0xb7b7b7b7U, 0xfdfdfdfdU, 0x93939393U, 0x26262626U,
+ 0x36363636U, 0x3f3f3f3fU, 0xf7f7f7f7U, 0xccccccccU,
+ 0x34343434U, 0xa5a5a5a5U, 0xe5e5e5e5U, 0xf1f1f1f1U,
+ 0x71717171U, 0xd8d8d8d8U, 0x31313131U, 0x15151515U,
+ 0x04040404U, 0xc7c7c7c7U, 0x23232323U, 0xc3c3c3c3U,
+ 0x18181818U, 0x96969696U, 0x05050505U, 0x9a9a9a9aU,
+ 0x07070707U, 0x12121212U, 0x80808080U, 0xe2e2e2e2U,
+ 0xebebebebU, 0x27272727U, 0xb2b2b2b2U, 0x75757575U,
+ 0x09090909U, 0x83838383U, 0x2c2c2c2cU, 0x1a1a1a1aU,
+ 0x1b1b1b1bU, 0x6e6e6e6eU, 0x5a5a5a5aU, 0xa0a0a0a0U,
+ 0x52525252U, 0x3b3b3b3bU, 0xd6d6d6d6U, 0xb3b3b3b3U,
+ 0x29292929U, 0xe3e3e3e3U, 0x2f2f2f2fU, 0x84848484U,
+ 0x53535353U, 0xd1d1d1d1U, 0x00000000U, 0xededededU,
+ 0x20202020U, 0xfcfcfcfcU, 0xb1b1b1b1U, 0x5b5b5b5bU,
+ 0x6a6a6a6aU, 0xcbcbcbcbU, 0xbebebebeU, 0x39393939U,
+ 0x4a4a4a4aU, 0x4c4c4c4cU, 0x58585858U, 0xcfcfcfcfU,
+ 0xd0d0d0d0U, 0xefefefefU, 0xaaaaaaaaU, 0xfbfbfbfbU,
+ 0x43434343U, 0x4d4d4d4dU, 0x33333333U, 0x85858585U,
+ 0x45454545U, 0xf9f9f9f9U, 0x02020202U, 0x7f7f7f7fU,
+ 0x50505050U, 0x3c3c3c3cU, 0x9f9f9f9fU, 0xa8a8a8a8U,
+ 0x51515151U, 0xa3a3a3a3U, 0x40404040U, 0x8f8f8f8fU,
+ 0x92929292U, 0x9d9d9d9dU, 0x38383838U, 0xf5f5f5f5U,
+ 0xbcbcbcbcU, 0xb6b6b6b6U, 0xdadadadaU, 0x21212121U,
+ 0x10101010U, 0xffffffffU, 0xf3f3f3f3U, 0xd2d2d2d2U,
+ 0xcdcdcdcdU, 0x0c0c0c0cU, 0x13131313U, 0xececececU,
+ 0x5f5f5f5fU, 0x97979797U, 0x44444444U, 0x17171717U,
+ 0xc4c4c4c4U, 0xa7a7a7a7U, 0x7e7e7e7eU, 0x3d3d3d3dU,
+ 0x64646464U, 0x5d5d5d5dU, 0x19191919U, 0x73737373U,
+ 0x60606060U, 0x81818181U, 0x4f4f4f4fU, 0xdcdcdcdcU,
+ 0x22222222U, 0x2a2a2a2aU, 0x90909090U, 0x88888888U,
+ 0x46464646U, 0xeeeeeeeeU, 0xb8b8b8b8U, 0x14141414U,
+ 0xdedededeU, 0x5e5e5e5eU, 0x0b0b0b0bU, 0xdbdbdbdbU,
+ 0xe0e0e0e0U, 0x32323232U, 0x3a3a3a3aU, 0x0a0a0a0aU,
+ 0x49494949U, 0x06060606U, 0x24242424U, 0x5c5c5c5cU,
+ 0xc2c2c2c2U, 0xd3d3d3d3U, 0xacacacacU, 0x62626262U,
+ 0x91919191U, 0x95959595U, 0xe4e4e4e4U, 0x79797979U,
+ 0xe7e7e7e7U, 0xc8c8c8c8U, 0x37373737U, 0x6d6d6d6dU,
+ 0x8d8d8d8dU, 0xd5d5d5d5U, 0x4e4e4e4eU, 0xa9a9a9a9U,
+ 0x6c6c6c6cU, 0x56565656U, 0xf4f4f4f4U, 0xeaeaeaeaU,
+ 0x65656565U, 0x7a7a7a7aU, 0xaeaeaeaeU, 0x08080808U,
+ 0xbabababaU, 0x78787878U, 0x25252525U, 0x2e2e2e2eU,
+ 0x1c1c1c1cU, 0xa6a6a6a6U, 0xb4b4b4b4U, 0xc6c6c6c6U,
+ 0xe8e8e8e8U, 0xddddddddU, 0x74747474U, 0x1f1f1f1fU,
+ 0x4b4b4b4bU, 0xbdbdbdbdU, 0x8b8b8b8bU, 0x8a8a8a8aU,
+ 0x70707070U, 0x3e3e3e3eU, 0xb5b5b5b5U, 0x66666666U,
+ 0x48484848U, 0x03030303U, 0xf6f6f6f6U, 0x0e0e0e0eU,
+ 0x61616161U, 0x35353535U, 0x57575757U, 0xb9b9b9b9U,
+ 0x86868686U, 0xc1c1c1c1U, 0x1d1d1d1dU, 0x9e9e9e9eU,
+ 0xe1e1e1e1U, 0xf8f8f8f8U, 0x98989898U, 0x11111111U,
+ 0x69696969U, 0xd9d9d9d9U, 0x8e8e8e8eU, 0x94949494U,
+ 0x9b9b9b9bU, 0x1e1e1e1eU, 0x87878787U, 0xe9e9e9e9U,
+ 0xcecececeU, 0x55555555U, 0x28282828U, 0xdfdfdfdfU,
+ 0x8c8c8c8cU, 0xa1a1a1a1U, 0x89898989U, 0x0d0d0d0dU,
+ 0xbfbfbfbfU, 0xe6e6e6e6U, 0x42424242U, 0x68686868U,
+ 0x41414141U, 0x99999999U, 0x2d2d2d2dU, 0x0f0f0f0fU,
+ 0xb0b0b0b0U, 0x54545454U, 0xbbbbbbbbU, 0x16161616U,
+};
+const uint32_t AES_Td0[256] = {
+ 0x51f4a750U, 0x7e416553U, 0x1a17a4c3U, 0x3a275e96U,
+ 0x3bab6bcbU, 0x1f9d45f1U, 0xacfa58abU, 0x4be30393U,
+ 0x2030fa55U, 0xad766df6U, 0x88cc7691U, 0xf5024c25U,
+ 0x4fe5d7fcU, 0xc52acbd7U, 0x26354480U, 0xb562a38fU,
+ 0xdeb15a49U, 0x25ba1b67U, 0x45ea0e98U, 0x5dfec0e1U,
+ 0xc32f7502U, 0x814cf012U, 0x8d4697a3U, 0x6bd3f9c6U,
+ 0x038f5fe7U, 0x15929c95U, 0xbf6d7aebU, 0x955259daU,
+ 0xd4be832dU, 0x587421d3U, 0x49e06929U, 0x8ec9c844U,
+ 0x75c2896aU, 0xf48e7978U, 0x99583e6bU, 0x27b971ddU,
+ 0xbee14fb6U, 0xf088ad17U, 0xc920ac66U, 0x7dce3ab4U,
+ 0x63df4a18U, 0xe51a3182U, 0x97513360U, 0x62537f45U,
+ 0xb16477e0U, 0xbb6bae84U, 0xfe81a01cU, 0xf9082b94U,
+ 0x70486858U, 0x8f45fd19U, 0x94de6c87U, 0x527bf8b7U,
+ 0xab73d323U, 0x724b02e2U, 0xe31f8f57U, 0x6655ab2aU,
+ 0xb2eb2807U, 0x2fb5c203U, 0x86c57b9aU, 0xd33708a5U,
+ 0x302887f2U, 0x23bfa5b2U, 0x02036abaU, 0xed16825cU,
+ 0x8acf1c2bU, 0xa779b492U, 0xf307f2f0U, 0x4e69e2a1U,
+ 0x65daf4cdU, 0x0605bed5U, 0xd134621fU, 0xc4a6fe8aU,
+ 0x342e539dU, 0xa2f355a0U, 0x058ae132U, 0xa4f6eb75U,
+ 0x0b83ec39U, 0x4060efaaU, 0x5e719f06U, 0xbd6e1051U,
+ 0x3e218af9U, 0x96dd063dU, 0xdd3e05aeU, 0x4de6bd46U,
+ 0x91548db5U, 0x71c45d05U, 0x0406d46fU, 0x605015ffU,
+ 0x1998fb24U, 0xd6bde997U, 0x894043ccU, 0x67d99e77U,
+ 0xb0e842bdU, 0x07898b88U, 0xe7195b38U, 0x79c8eedbU,
+ 0xa17c0a47U, 0x7c420fe9U, 0xf8841ec9U, 0x00000000U,
+ 0x09808683U, 0x322bed48U, 0x1e1170acU, 0x6c5a724eU,
+ 0xfd0efffbU, 0x0f853856U, 0x3daed51eU, 0x362d3927U,
+ 0x0a0fd964U, 0x685ca621U, 0x9b5b54d1U, 0x24362e3aU,
+ 0x0c0a67b1U, 0x9357e70fU, 0xb4ee96d2U, 0x1b9b919eU,
+ 0x80c0c54fU, 0x61dc20a2U, 0x5a774b69U, 0x1c121a16U,
+ 0xe293ba0aU, 0xc0a02ae5U, 0x3c22e043U, 0x121b171dU,
+ 0x0e090d0bU, 0xf28bc7adU, 0x2db6a8b9U, 0x141ea9c8U,
+ 0x57f11985U, 0xaf75074cU, 0xee99ddbbU, 0xa37f60fdU,
+ 0xf701269fU, 0x5c72f5bcU, 0x44663bc5U, 0x5bfb7e34U,
+ 0x8b432976U, 0xcb23c6dcU, 0xb6edfc68U, 0xb8e4f163U,
+ 0xd731dccaU, 0x42638510U, 0x13972240U, 0x84c61120U,
+ 0x854a247dU, 0xd2bb3df8U, 0xaef93211U, 0xc729a16dU,
+ 0x1d9e2f4bU, 0xdcb230f3U, 0x0d8652ecU, 0x77c1e3d0U,
+ 0x2bb3166cU, 0xa970b999U, 0x119448faU, 0x47e96422U,
+ 0xa8fc8cc4U, 0xa0f03f1aU, 0x567d2cd8U, 0x223390efU,
+ 0x87494ec7U, 0xd938d1c1U, 0x8ccaa2feU, 0x98d40b36U,
+ 0xa6f581cfU, 0xa57ade28U, 0xdab78e26U, 0x3fadbfa4U,
+ 0x2c3a9de4U, 0x5078920dU, 0x6a5fcc9bU, 0x547e4662U,
+ 0xf68d13c2U, 0x90d8b8e8U, 0x2e39f75eU, 0x82c3aff5U,
+ 0x9f5d80beU, 0x69d0937cU, 0x6fd52da9U, 0xcf2512b3U,
+ 0xc8ac993bU, 0x10187da7U, 0xe89c636eU, 0xdb3bbb7bU,
+ 0xcd267809U, 0x6e5918f4U, 0xec9ab701U, 0x834f9aa8U,
+ 0xe6956e65U, 0xaaffe67eU, 0x21bccf08U, 0xef15e8e6U,
+ 0xbae79bd9U, 0x4a6f36ceU, 0xea9f09d4U, 0x29b07cd6U,
+ 0x31a4b2afU, 0x2a3f2331U, 0xc6a59430U, 0x35a266c0U,
+ 0x744ebc37U, 0xfc82caa6U, 0xe090d0b0U, 0x33a7d815U,
+ 0xf104984aU, 0x41ecdaf7U, 0x7fcd500eU, 0x1791f62fU,
+ 0x764dd68dU, 0x43efb04dU, 0xccaa4d54U, 0xe49604dfU,
+ 0x9ed1b5e3U, 0x4c6a881bU, 0xc12c1fb8U, 0x4665517fU,
+ 0x9d5eea04U, 0x018c355dU, 0xfa877473U, 0xfb0b412eU,
+ 0xb3671d5aU, 0x92dbd252U, 0xe9105633U, 0x6dd64713U,
+ 0x9ad7618cU, 0x37a10c7aU, 0x59f8148eU, 0xeb133c89U,
+ 0xcea927eeU, 0xb761c935U, 0xe11ce5edU, 0x7a47b13cU,
+ 0x9cd2df59U, 0x55f2733fU, 0x1814ce79U, 0x73c737bfU,
+ 0x53f7cdeaU, 0x5ffdaa5bU, 0xdf3d6f14U, 0x7844db86U,
+ 0xcaaff381U, 0xb968c43eU, 0x3824342cU, 0xc2a3405fU,
+ 0x161dc372U, 0xbce2250cU, 0x283c498bU, 0xff0d9541U,
+ 0x39a80171U, 0x080cb3deU, 0xd8b4e49cU, 0x6456c190U,
+ 0x7bcb8461U, 0xd532b670U, 0x486c5c74U, 0xd0b85742U,
+};
+const uint32_t AES_Td1[256] = {
+ 0x5051f4a7U, 0x537e4165U, 0xc31a17a4U, 0x963a275eU,
+ 0xcb3bab6bU, 0xf11f9d45U, 0xabacfa58U, 0x934be303U,
+ 0x552030faU, 0xf6ad766dU, 0x9188cc76U, 0x25f5024cU,
+ 0xfc4fe5d7U, 0xd7c52acbU, 0x80263544U, 0x8fb562a3U,
+ 0x49deb15aU, 0x6725ba1bU, 0x9845ea0eU, 0xe15dfec0U,
+ 0x02c32f75U, 0x12814cf0U, 0xa38d4697U, 0xc66bd3f9U,
+ 0xe7038f5fU, 0x9515929cU, 0xebbf6d7aU, 0xda955259U,
+ 0x2dd4be83U, 0xd3587421U, 0x2949e069U, 0x448ec9c8U,
+ 0x6a75c289U, 0x78f48e79U, 0x6b99583eU, 0xdd27b971U,
+ 0xb6bee14fU, 0x17f088adU, 0x66c920acU, 0xb47dce3aU,
+ 0x1863df4aU, 0x82e51a31U, 0x60975133U, 0x4562537fU,
+ 0xe0b16477U, 0x84bb6baeU, 0x1cfe81a0U, 0x94f9082bU,
+ 0x58704868U, 0x198f45fdU, 0x8794de6cU, 0xb7527bf8U,
+ 0x23ab73d3U, 0xe2724b02U, 0x57e31f8fU, 0x2a6655abU,
+ 0x07b2eb28U, 0x032fb5c2U, 0x9a86c57bU, 0xa5d33708U,
+ 0xf2302887U, 0xb223bfa5U, 0xba02036aU, 0x5ced1682U,
+ 0x2b8acf1cU, 0x92a779b4U, 0xf0f307f2U, 0xa14e69e2U,
+ 0xcd65daf4U, 0xd50605beU, 0x1fd13462U, 0x8ac4a6feU,
+ 0x9d342e53U, 0xa0a2f355U, 0x32058ae1U, 0x75a4f6ebU,
+ 0x390b83ecU, 0xaa4060efU, 0x065e719fU, 0x51bd6e10U,
+ 0xf93e218aU, 0x3d96dd06U, 0xaedd3e05U, 0x464de6bdU,
+ 0xb591548dU, 0x0571c45dU, 0x6f0406d4U, 0xff605015U,
+ 0x241998fbU, 0x97d6bde9U, 0xcc894043U, 0x7767d99eU,
+ 0xbdb0e842U, 0x8807898bU, 0x38e7195bU, 0xdb79c8eeU,
+ 0x47a17c0aU, 0xe97c420fU, 0xc9f8841eU, 0x00000000U,
+ 0x83098086U, 0x48322bedU, 0xac1e1170U, 0x4e6c5a72U,
+ 0xfbfd0effU, 0x560f8538U, 0x1e3daed5U, 0x27362d39U,
+ 0x640a0fd9U, 0x21685ca6U, 0xd19b5b54U, 0x3a24362eU,
+ 0xb10c0a67U, 0x0f9357e7U, 0xd2b4ee96U, 0x9e1b9b91U,
+ 0x4f80c0c5U, 0xa261dc20U, 0x695a774bU, 0x161c121aU,
+ 0x0ae293baU, 0xe5c0a02aU, 0x433c22e0U, 0x1d121b17U,
+ 0x0b0e090dU, 0xadf28bc7U, 0xb92db6a8U, 0xc8141ea9U,
+ 0x8557f119U, 0x4caf7507U, 0xbbee99ddU, 0xfda37f60U,
+ 0x9ff70126U, 0xbc5c72f5U, 0xc544663bU, 0x345bfb7eU,
+ 0x768b4329U, 0xdccb23c6U, 0x68b6edfcU, 0x63b8e4f1U,
+ 0xcad731dcU, 0x10426385U, 0x40139722U, 0x2084c611U,
+ 0x7d854a24U, 0xf8d2bb3dU, 0x11aef932U, 0x6dc729a1U,
+ 0x4b1d9e2fU, 0xf3dcb230U, 0xec0d8652U, 0xd077c1e3U,
+ 0x6c2bb316U, 0x99a970b9U, 0xfa119448U, 0x2247e964U,
+ 0xc4a8fc8cU, 0x1aa0f03fU, 0xd8567d2cU, 0xef223390U,
+ 0xc787494eU, 0xc1d938d1U, 0xfe8ccaa2U, 0x3698d40bU,
+ 0xcfa6f581U, 0x28a57adeU, 0x26dab78eU, 0xa43fadbfU,
+ 0xe42c3a9dU, 0x0d507892U, 0x9b6a5fccU, 0x62547e46U,
+ 0xc2f68d13U, 0xe890d8b8U, 0x5e2e39f7U, 0xf582c3afU,
+ 0xbe9f5d80U, 0x7c69d093U, 0xa96fd52dU, 0xb3cf2512U,
+ 0x3bc8ac99U, 0xa710187dU, 0x6ee89c63U, 0x7bdb3bbbU,
+ 0x09cd2678U, 0xf46e5918U, 0x01ec9ab7U, 0xa8834f9aU,
+ 0x65e6956eU, 0x7eaaffe6U, 0x0821bccfU, 0xe6ef15e8U,
+ 0xd9bae79bU, 0xce4a6f36U, 0xd4ea9f09U, 0xd629b07cU,
+ 0xaf31a4b2U, 0x312a3f23U, 0x30c6a594U, 0xc035a266U,
+ 0x37744ebcU, 0xa6fc82caU, 0xb0e090d0U, 0x1533a7d8U,
+ 0x4af10498U, 0xf741ecdaU, 0x0e7fcd50U, 0x2f1791f6U,
+ 0x8d764dd6U, 0x4d43efb0U, 0x54ccaa4dU, 0xdfe49604U,
+ 0xe39ed1b5U, 0x1b4c6a88U, 0xb8c12c1fU, 0x7f466551U,
+ 0x049d5eeaU, 0x5d018c35U, 0x73fa8774U, 0x2efb0b41U,
+ 0x5ab3671dU, 0x5292dbd2U, 0x33e91056U, 0x136dd647U,
+ 0x8c9ad761U, 0x7a37a10cU, 0x8e59f814U, 0x89eb133cU,
+ 0xeecea927U, 0x35b761c9U, 0xede11ce5U, 0x3c7a47b1U,
+ 0x599cd2dfU, 0x3f55f273U, 0x791814ceU, 0xbf73c737U,
+ 0xea53f7cdU, 0x5b5ffdaaU, 0x14df3d6fU, 0x867844dbU,
+ 0x81caaff3U, 0x3eb968c4U, 0x2c382434U, 0x5fc2a340U,
+ 0x72161dc3U, 0x0cbce225U, 0x8b283c49U, 0x41ff0d95U,
+ 0x7139a801U, 0xde080cb3U, 0x9cd8b4e4U, 0x906456c1U,
+ 0x617bcb84U, 0x70d532b6U, 0x74486c5cU, 0x42d0b857U,
+};
+const uint32_t AES_Td2[256] = {
+ 0xa75051f4U, 0x65537e41U, 0xa4c31a17U, 0x5e963a27U,
+ 0x6bcb3babU, 0x45f11f9dU, 0x58abacfaU, 0x03934be3U,
+ 0xfa552030U, 0x6df6ad76U, 0x769188ccU, 0x4c25f502U,
+ 0xd7fc4fe5U, 0xcbd7c52aU, 0x44802635U, 0xa38fb562U,
+ 0x5a49deb1U, 0x1b6725baU, 0x0e9845eaU, 0xc0e15dfeU,
+ 0x7502c32fU, 0xf012814cU, 0x97a38d46U, 0xf9c66bd3U,
+ 0x5fe7038fU, 0x9c951592U, 0x7aebbf6dU, 0x59da9552U,
+ 0x832dd4beU, 0x21d35874U, 0x692949e0U, 0xc8448ec9U,
+ 0x896a75c2U, 0x7978f48eU, 0x3e6b9958U, 0x71dd27b9U,
+ 0x4fb6bee1U, 0xad17f088U, 0xac66c920U, 0x3ab47dceU,
+ 0x4a1863dfU, 0x3182e51aU, 0x33609751U, 0x7f456253U,
+ 0x77e0b164U, 0xae84bb6bU, 0xa01cfe81U, 0x2b94f908U,
+ 0x68587048U, 0xfd198f45U, 0x6c8794deU, 0xf8b7527bU,
+ 0xd323ab73U, 0x02e2724bU, 0x8f57e31fU, 0xab2a6655U,
+ 0x2807b2ebU, 0xc2032fb5U, 0x7b9a86c5U, 0x08a5d337U,
+ 0x87f23028U, 0xa5b223bfU, 0x6aba0203U, 0x825ced16U,
+ 0x1c2b8acfU, 0xb492a779U, 0xf2f0f307U, 0xe2a14e69U,
+ 0xf4cd65daU, 0xbed50605U, 0x621fd134U, 0xfe8ac4a6U,
+ 0x539d342eU, 0x55a0a2f3U, 0xe132058aU, 0xeb75a4f6U,
+ 0xec390b83U, 0xefaa4060U, 0x9f065e71U, 0x1051bd6eU,
+
+ 0x8af93e21U, 0x063d96ddU, 0x05aedd3eU, 0xbd464de6U,
+ 0x8db59154U, 0x5d0571c4U, 0xd46f0406U, 0x15ff6050U,
+ 0xfb241998U, 0xe997d6bdU, 0x43cc8940U, 0x9e7767d9U,
+ 0x42bdb0e8U, 0x8b880789U, 0x5b38e719U, 0xeedb79c8U,
+ 0x0a47a17cU, 0x0fe97c42U, 0x1ec9f884U, 0x00000000U,
+ 0x86830980U, 0xed48322bU, 0x70ac1e11U, 0x724e6c5aU,
+ 0xfffbfd0eU, 0x38560f85U, 0xd51e3daeU, 0x3927362dU,
+ 0xd9640a0fU, 0xa621685cU, 0x54d19b5bU, 0x2e3a2436U,
+ 0x67b10c0aU, 0xe70f9357U, 0x96d2b4eeU, 0x919e1b9bU,
+ 0xc54f80c0U, 0x20a261dcU, 0x4b695a77U, 0x1a161c12U,
+ 0xba0ae293U, 0x2ae5c0a0U, 0xe0433c22U, 0x171d121bU,
+ 0x0d0b0e09U, 0xc7adf28bU, 0xa8b92db6U, 0xa9c8141eU,
+ 0x198557f1U, 0x074caf75U, 0xddbbee99U, 0x60fda37fU,
+ 0x269ff701U, 0xf5bc5c72U, 0x3bc54466U, 0x7e345bfbU,
+ 0x29768b43U, 0xc6dccb23U, 0xfc68b6edU, 0xf163b8e4U,
+ 0xdccad731U, 0x85104263U, 0x22401397U, 0x112084c6U,
+ 0x247d854aU, 0x3df8d2bbU, 0x3211aef9U, 0xa16dc729U,
+ 0x2f4b1d9eU, 0x30f3dcb2U, 0x52ec0d86U, 0xe3d077c1U,
+ 0x166c2bb3U, 0xb999a970U, 0x48fa1194U, 0x642247e9U,
+ 0x8cc4a8fcU, 0x3f1aa0f0U, 0x2cd8567dU, 0x90ef2233U,
+ 0x4ec78749U, 0xd1c1d938U, 0xa2fe8ccaU, 0x0b3698d4U,
+ 0x81cfa6f5U, 0xde28a57aU, 0x8e26dab7U, 0xbfa43fadU,
+ 0x9de42c3aU, 0x920d5078U, 0xcc9b6a5fU, 0x4662547eU,
+ 0x13c2f68dU, 0xb8e890d8U, 0xf75e2e39U, 0xaff582c3U,
+ 0x80be9f5dU, 0x937c69d0U, 0x2da96fd5U, 0x12b3cf25U,
+ 0x993bc8acU, 0x7da71018U, 0x636ee89cU, 0xbb7bdb3bU,
+ 0x7809cd26U, 0x18f46e59U, 0xb701ec9aU, 0x9aa8834fU,
+ 0x6e65e695U, 0xe67eaaffU, 0xcf0821bcU, 0xe8e6ef15U,
+ 0x9bd9bae7U, 0x36ce4a6fU, 0x09d4ea9fU, 0x7cd629b0U,
+ 0xb2af31a4U, 0x23312a3fU, 0x9430c6a5U, 0x66c035a2U,
+ 0xbc37744eU, 0xcaa6fc82U, 0xd0b0e090U, 0xd81533a7U,
+ 0x984af104U, 0xdaf741ecU, 0x500e7fcdU, 0xf62f1791U,
+ 0xd68d764dU, 0xb04d43efU, 0x4d54ccaaU, 0x04dfe496U,
+ 0xb5e39ed1U, 0x881b4c6aU, 0x1fb8c12cU, 0x517f4665U,
+ 0xea049d5eU, 0x355d018cU, 0x7473fa87U, 0x412efb0bU,
+ 0x1d5ab367U, 0xd25292dbU, 0x5633e910U, 0x47136dd6U,
+ 0x618c9ad7U, 0x0c7a37a1U, 0x148e59f8U, 0x3c89eb13U,
+ 0x27eecea9U, 0xc935b761U, 0xe5ede11cU, 0xb13c7a47U,
+ 0xdf599cd2U, 0x733f55f2U, 0xce791814U, 0x37bf73c7U,
+ 0xcdea53f7U, 0xaa5b5ffdU, 0x6f14df3dU, 0xdb867844U,
+ 0xf381caafU, 0xc43eb968U, 0x342c3824U, 0x405fc2a3U,
+ 0xc372161dU, 0x250cbce2U, 0x498b283cU, 0x9541ff0dU,
+ 0x017139a8U, 0xb3de080cU, 0xe49cd8b4U, 0xc1906456U,
+ 0x84617bcbU, 0xb670d532U, 0x5c74486cU, 0x5742d0b8U,
+};
+const uint32_t AES_Td3[256] = {
+ 0xf4a75051U, 0x4165537eU, 0x17a4c31aU, 0x275e963aU,
+ 0xab6bcb3bU, 0x9d45f11fU, 0xfa58abacU, 0xe303934bU,
+ 0x30fa5520U, 0x766df6adU, 0xcc769188U, 0x024c25f5U,
+ 0xe5d7fc4fU, 0x2acbd7c5U, 0x35448026U, 0x62a38fb5U,
+ 0xb15a49deU, 0xba1b6725U, 0xea0e9845U, 0xfec0e15dU,
+ 0x2f7502c3U, 0x4cf01281U, 0x4697a38dU, 0xd3f9c66bU,
+ 0x8f5fe703U, 0x929c9515U, 0x6d7aebbfU, 0x5259da95U,
+ 0xbe832dd4U, 0x7421d358U, 0xe0692949U, 0xc9c8448eU,
+ 0xc2896a75U, 0x8e7978f4U, 0x583e6b99U, 0xb971dd27U,
+ 0xe14fb6beU, 0x88ad17f0U, 0x20ac66c9U, 0xce3ab47dU,
+ 0xdf4a1863U, 0x1a3182e5U, 0x51336097U, 0x537f4562U,
+ 0x6477e0b1U, 0x6bae84bbU, 0x81a01cfeU, 0x082b94f9U,
+ 0x48685870U, 0x45fd198fU, 0xde6c8794U, 0x7bf8b752U,
+ 0x73d323abU, 0x4b02e272U, 0x1f8f57e3U, 0x55ab2a66U,
+ 0xeb2807b2U, 0xb5c2032fU, 0xc57b9a86U, 0x3708a5d3U,
+ 0x2887f230U, 0xbfa5b223U, 0x036aba02U, 0x16825cedU,
+ 0xcf1c2b8aU, 0x79b492a7U, 0x07f2f0f3U, 0x69e2a14eU,
+ 0xdaf4cd65U, 0x05bed506U, 0x34621fd1U, 0xa6fe8ac4U,
+ 0x2e539d34U, 0xf355a0a2U, 0x8ae13205U, 0xf6eb75a4U,
+ 0x83ec390bU, 0x60efaa40U, 0x719f065eU, 0x6e1051bdU,
+ 0x218af93eU, 0xdd063d96U, 0x3e05aeddU, 0xe6bd464dU,
+ 0x548db591U, 0xc45d0571U, 0x06d46f04U, 0x5015ff60U,
+ 0x98fb2419U, 0xbde997d6U, 0x4043cc89U, 0xd99e7767U,
+ 0xe842bdb0U, 0x898b8807U, 0x195b38e7U, 0xc8eedb79U,
+ 0x7c0a47a1U, 0x420fe97cU, 0x841ec9f8U, 0x00000000U,
+ 0x80868309U, 0x2bed4832U, 0x1170ac1eU, 0x5a724e6cU,
+ 0x0efffbfdU, 0x8538560fU, 0xaed51e3dU, 0x2d392736U,
+ 0x0fd9640aU, 0x5ca62168U, 0x5b54d19bU, 0x362e3a24U,
+ 0x0a67b10cU, 0x57e70f93U, 0xee96d2b4U, 0x9b919e1bU,
+ 0xc0c54f80U, 0xdc20a261U, 0x774b695aU, 0x121a161cU,
+ 0x93ba0ae2U, 0xa02ae5c0U, 0x22e0433cU, 0x1b171d12U,
+ 0x090d0b0eU, 0x8bc7adf2U, 0xb6a8b92dU, 0x1ea9c814U,
+ 0xf1198557U, 0x75074cafU, 0x99ddbbeeU, 0x7f60fda3U,
+ 0x01269ff7U, 0x72f5bc5cU, 0x663bc544U, 0xfb7e345bU,
+ 0x4329768bU, 0x23c6dccbU, 0xedfc68b6U, 0xe4f163b8U,
+ 0x31dccad7U, 0x63851042U, 0x97224013U, 0xc6112084U,
+ 0x4a247d85U, 0xbb3df8d2U, 0xf93211aeU, 0x29a16dc7U,
+ 0x9e2f4b1dU, 0xb230f3dcU, 0x8652ec0dU, 0xc1e3d077U,
+ 0xb3166c2bU, 0x70b999a9U, 0x9448fa11U, 0xe9642247U,
+ 0xfc8cc4a8U, 0xf03f1aa0U, 0x7d2cd856U, 0x3390ef22U,
+ 0x494ec787U, 0x38d1c1d9U, 0xcaa2fe8cU, 0xd40b3698U,
+ 0xf581cfa6U, 0x7ade28a5U, 0xb78e26daU, 0xadbfa43fU,
+ 0x3a9de42cU, 0x78920d50U, 0x5fcc9b6aU, 0x7e466254U,
+ 0x8d13c2f6U, 0xd8b8e890U, 0x39f75e2eU, 0xc3aff582U,
+ 0x5d80be9fU, 0xd0937c69U, 0xd52da96fU, 0x2512b3cfU,
+ 0xac993bc8U, 0x187da710U, 0x9c636ee8U, 0x3bbb7bdbU,
+ 0x267809cdU, 0x5918f46eU, 0x9ab701ecU, 0x4f9aa883U,
+ 0x956e65e6U, 0xffe67eaaU, 0xbccf0821U, 0x15e8e6efU,
+ 0xe79bd9baU, 0x6f36ce4aU, 0x9f09d4eaU, 0xb07cd629U,
+ 0xa4b2af31U, 0x3f23312aU, 0xa59430c6U, 0xa266c035U,
+ 0x4ebc3774U, 0x82caa6fcU, 0x90d0b0e0U, 0xa7d81533U,
+ 0x04984af1U, 0xecdaf741U, 0xcd500e7fU, 0x91f62f17U,
+ 0x4dd68d76U, 0xefb04d43U, 0xaa4d54ccU, 0x9604dfe4U,
+ 0xd1b5e39eU, 0x6a881b4cU, 0x2c1fb8c1U, 0x65517f46U,
+ 0x5eea049dU, 0x8c355d01U, 0x877473faU, 0x0b412efbU,
+ 0x671d5ab3U, 0xdbd25292U, 0x105633e9U, 0xd647136dU,
+ 0xd7618c9aU, 0xa10c7a37U, 0xf8148e59U, 0x133c89ebU,
+ 0xa927eeceU, 0x61c935b7U, 0x1ce5ede1U, 0x47b13c7aU,
+ 0xd2df599cU, 0xf2733f55U, 0x14ce7918U, 0xc737bf73U,
+ 0xf7cdea53U, 0xfdaa5b5fU, 0x3d6f14dfU, 0x44db8678U,
+ 0xaff381caU, 0x68c43eb9U, 0x24342c38U, 0xa3405fc2U,
+ 0x1dc37216U, 0xe2250cbcU, 0x3c498b28U, 0x0d9541ffU,
+ 0xa8017139U, 0x0cb3de08U, 0xb4e49cd8U, 0x56c19064U,
+ 0xcb84617bU, 0x32b670d5U, 0x6c5c7448U, 0xb85742d0U,
+};
+const uint32_t AES_Td4[256] = {
+ 0x52525252U, 0x09090909U, 0x6a6a6a6aU, 0xd5d5d5d5U,
+ 0x30303030U, 0x36363636U, 0xa5a5a5a5U, 0x38383838U,
+ 0xbfbfbfbfU, 0x40404040U, 0xa3a3a3a3U, 0x9e9e9e9eU,
+ 0x81818181U, 0xf3f3f3f3U, 0xd7d7d7d7U, 0xfbfbfbfbU,
+ 0x7c7c7c7cU, 0xe3e3e3e3U, 0x39393939U, 0x82828282U,
+ 0x9b9b9b9bU, 0x2f2f2f2fU, 0xffffffffU, 0x87878787U,
+ 0x34343434U, 0x8e8e8e8eU, 0x43434343U, 0x44444444U,
+ 0xc4c4c4c4U, 0xdedededeU, 0xe9e9e9e9U, 0xcbcbcbcbU,
+ 0x54545454U, 0x7b7b7b7bU, 0x94949494U, 0x32323232U,
+ 0xa6a6a6a6U, 0xc2c2c2c2U, 0x23232323U, 0x3d3d3d3dU,
+ 0xeeeeeeeeU, 0x4c4c4c4cU, 0x95959595U, 0x0b0b0b0bU,
+ 0x42424242U, 0xfafafafaU, 0xc3c3c3c3U, 0x4e4e4e4eU,
+ 0x08080808U, 0x2e2e2e2eU, 0xa1a1a1a1U, 0x66666666U,
+ 0x28282828U, 0xd9d9d9d9U, 0x24242424U, 0xb2b2b2b2U,
+ 0x76767676U, 0x5b5b5b5bU, 0xa2a2a2a2U, 0x49494949U,
+ 0x6d6d6d6dU, 0x8b8b8b8bU, 0xd1d1d1d1U, 0x25252525U,
+ 0x72727272U, 0xf8f8f8f8U, 0xf6f6f6f6U, 0x64646464U,
+ 0x86868686U, 0x68686868U, 0x98989898U, 0x16161616U,
+ 0xd4d4d4d4U, 0xa4a4a4a4U, 0x5c5c5c5cU, 0xccccccccU,
+ 0x5d5d5d5dU, 0x65656565U, 0xb6b6b6b6U, 0x92929292U,
+ 0x6c6c6c6cU, 0x70707070U, 0x48484848U, 0x50505050U,
+ 0xfdfdfdfdU, 0xededededU, 0xb9b9b9b9U, 0xdadadadaU,
+ 0x5e5e5e5eU, 0x15151515U, 0x46464646U, 0x57575757U,
+ 0xa7a7a7a7U, 0x8d8d8d8dU, 0x9d9d9d9dU, 0x84848484U,
+ 0x90909090U, 0xd8d8d8d8U, 0xababababU, 0x00000000U,
+ 0x8c8c8c8cU, 0xbcbcbcbcU, 0xd3d3d3d3U, 0x0a0a0a0aU,
+ 0xf7f7f7f7U, 0xe4e4e4e4U, 0x58585858U, 0x05050505U,
+ 0xb8b8b8b8U, 0xb3b3b3b3U, 0x45454545U, 0x06060606U,
+ 0xd0d0d0d0U, 0x2c2c2c2cU, 0x1e1e1e1eU, 0x8f8f8f8fU,
+ 0xcacacacaU, 0x3f3f3f3fU, 0x0f0f0f0fU, 0x02020202U,
+ 0xc1c1c1c1U, 0xafafafafU, 0xbdbdbdbdU, 0x03030303U,
+ 0x01010101U, 0x13131313U, 0x8a8a8a8aU, 0x6b6b6b6bU,
+ 0x3a3a3a3aU, 0x91919191U, 0x11111111U, 0x41414141U,
+ 0x4f4f4f4fU, 0x67676767U, 0xdcdcdcdcU, 0xeaeaeaeaU,
+ 0x97979797U, 0xf2f2f2f2U, 0xcfcfcfcfU, 0xcecececeU,
+ 0xf0f0f0f0U, 0xb4b4b4b4U, 0xe6e6e6e6U, 0x73737373U,
+ 0x96969696U, 0xacacacacU, 0x74747474U, 0x22222222U,
+ 0xe7e7e7e7U, 0xadadadadU, 0x35353535U, 0x85858585U,
+ 0xe2e2e2e2U, 0xf9f9f9f9U, 0x37373737U, 0xe8e8e8e8U,
+ 0x1c1c1c1cU, 0x75757575U, 0xdfdfdfdfU, 0x6e6e6e6eU,
+ 0x47474747U, 0xf1f1f1f1U, 0x1a1a1a1aU, 0x71717171U,
+ 0x1d1d1d1dU, 0x29292929U, 0xc5c5c5c5U, 0x89898989U,
+ 0x6f6f6f6fU, 0xb7b7b7b7U, 0x62626262U, 0x0e0e0e0eU,
+ 0xaaaaaaaaU, 0x18181818U, 0xbebebebeU, 0x1b1b1b1bU,
+ 0xfcfcfcfcU, 0x56565656U, 0x3e3e3e3eU, 0x4b4b4b4bU,
+ 0xc6c6c6c6U, 0xd2d2d2d2U, 0x79797979U, 0x20202020U,
+ 0x9a9a9a9aU, 0xdbdbdbdbU, 0xc0c0c0c0U, 0xfefefefeU,
+ 0x78787878U, 0xcdcdcdcdU, 0x5a5a5a5aU, 0xf4f4f4f4U,
+ 0x1f1f1f1fU, 0xddddddddU, 0xa8a8a8a8U, 0x33333333U,
+ 0x88888888U, 0x07070707U, 0xc7c7c7c7U, 0x31313131U,
+ 0xb1b1b1b1U, 0x12121212U, 0x10101010U, 0x59595959U,
+ 0x27272727U, 0x80808080U, 0xececececU, 0x5f5f5f5fU,
+ 0x60606060U, 0x51515151U, 0x7f7f7f7fU, 0xa9a9a9a9U,
+ 0x19191919U, 0xb5b5b5b5U, 0x4a4a4a4aU, 0x0d0d0d0dU,
+ 0x2d2d2d2dU, 0xe5e5e5e5U, 0x7a7a7a7aU, 0x9f9f9f9fU,
+ 0x93939393U, 0xc9c9c9c9U, 0x9c9c9c9cU, 0xefefefefU,
+ 0xa0a0a0a0U, 0xe0e0e0e0U, 0x3b3b3b3bU, 0x4d4d4d4dU,
+ 0xaeaeaeaeU, 0x2a2a2a2aU, 0xf5f5f5f5U, 0xb0b0b0b0U,
+ 0xc8c8c8c8U, 0xebebebebU, 0xbbbbbbbbU, 0x3c3c3c3cU,
+ 0x83838383U, 0x53535353U, 0x99999999U, 0x61616161U,
+ 0x17171717U, 0x2b2b2b2bU, 0x04040404U, 0x7e7e7e7eU,
+ 0xbabababaU, 0x77777777U, 0xd6d6d6d6U, 0x26262626U,
+ 0xe1e1e1e1U, 0x69696969U, 0x14141414U, 0x63636363U,
+ 0x55555555U, 0x21212121U, 0x0c0c0c0cU, 0x7d7d7d7dU,
+};
+static const u32 rcon[] = {
+ 0x01000000, 0x02000000, 0x04000000, 0x08000000,
+ 0x10000000, 0x20000000, 0x40000000, 0x80000000,
+ 0x1B000000, 0x36000000, /* for 128-bit blocks, Rijndael never uses more than 10 rcon values */
+};
+
+/**
+ * Expand the cipher key into the encryption key schedule.
+ */
+int AES_set_encrypt_key(const unsigned char *userKey, const int bits,
+ AES_KEY *key) {
+
+ u32 *rk;
+ int i = 0;
+ u32 temp;
+
+ if (!userKey || !key)
+ return -1;
+ if (bits != 128 && bits != 192 && bits != 256)
+ return -2;
+
+ rk = key->rd_key;
+
+ if (bits==128)
+ key->rounds = 10;
+ else if (bits==192)
+ key->rounds = 12;
+ else
+ key->rounds = 14;
+
+ rk[0] = GETU32(userKey );
+ rk[1] = GETU32(userKey + 4);
+ rk[2] = GETU32(userKey + 8);
+ rk[3] = GETU32(userKey + 12);
+ if (bits == 128) {
+ while (1) {
+ temp = rk[3];
+ rk[4] = rk[0] ^
+ (AES_Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+ (AES_Te4[(temp >> 8) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(temp ) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(temp >> 24) ] & 0x000000ff) ^
+ rcon[i];
+ rk[5] = rk[1] ^ rk[4];
+ rk[6] = rk[2] ^ rk[5];
+ rk[7] = rk[3] ^ rk[6];
+ if (++i == 10) {
+ return 0;
+ }
+ rk += 4;
+ }
+ }
+ rk[4] = GETU32(userKey + 16);
+ rk[5] = GETU32(userKey + 20);
+ if (bits == 192) {
+ while (1) {
+ temp = rk[ 5];
+ rk[ 6] = rk[ 0] ^
+ (AES_Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+ (AES_Te4[(temp >> 8) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(temp ) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(temp >> 24) ] & 0x000000ff) ^
+ rcon[i];
+ rk[ 7] = rk[ 1] ^ rk[ 6];
+ rk[ 8] = rk[ 2] ^ rk[ 7];
+ rk[ 9] = rk[ 3] ^ rk[ 8];
+ if (++i == 8) {
+ return 0;
+ }
+ rk[10] = rk[ 4] ^ rk[ 9];
+ rk[11] = rk[ 5] ^ rk[10];
+ rk += 6;
+ }
+ }
+ rk[6] = GETU32(userKey + 24);
+ rk[7] = GETU32(userKey + 28);
+ if (bits == 256) {
+ while (1) {
+ temp = rk[ 7];
+ rk[ 8] = rk[ 0] ^
+ (AES_Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+ (AES_Te4[(temp >> 8) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(temp ) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(temp >> 24) ] & 0x000000ff) ^
+ rcon[i];
+ rk[ 9] = rk[ 1] ^ rk[ 8];
+ rk[10] = rk[ 2] ^ rk[ 9];
+ rk[11] = rk[ 3] ^ rk[10];
+ if (++i == 7) {
+ return 0;
+ }
+ temp = rk[11];
+ rk[12] = rk[ 4] ^
+ (AES_Te4[(temp >> 24) ] & 0xff000000) ^
+ (AES_Te4[(temp >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(temp >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(temp ) & 0xff] & 0x000000ff);
+ rk[13] = rk[ 5] ^ rk[12];
+ rk[14] = rk[ 6] ^ rk[13];
+ rk[15] = rk[ 7] ^ rk[14];
+
+ rk += 8;
+ }
+ }
+ return 0;
+}
+
+/**
+ * Expand the cipher key into the decryption key schedule.
+ */
+int AES_set_decrypt_key(const unsigned char *userKey, const int bits,
+ AES_KEY *key) {
+
+ u32 *rk;
+ int i, j, status;
+ u32 temp;
+
+ /* first, start with an encryption schedule */
+ status = AES_set_encrypt_key(userKey, bits, key);
+ if (status < 0)
+ return status;
+
+ rk = key->rd_key;
+
+ /* invert the order of the round keys: */
+ for (i = 0, j = 4*(key->rounds); i < j; i += 4, j -= 4) {
+ temp = rk[i ]; rk[i ] = rk[j ]; rk[j ] = temp;
+ temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp;
+ temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp;
+ temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp;
+ }
+ /* apply the inverse MixColumn transform to all round keys but the first and the last: */
+ for (i = 1; i < (key->rounds); i++) {
+ rk += 4;
+ rk[0] =
+ AES_Td0[AES_Te4[(rk[0] >> 24) ] & 0xff] ^
+ AES_Td1[AES_Te4[(rk[0] >> 16) & 0xff] & 0xff] ^
+ AES_Td2[AES_Te4[(rk[0] >> 8) & 0xff] & 0xff] ^
+ AES_Td3[AES_Te4[(rk[0] ) & 0xff] & 0xff];
+ rk[1] =
+ AES_Td0[AES_Te4[(rk[1] >> 24) ] & 0xff] ^
+ AES_Td1[AES_Te4[(rk[1] >> 16) & 0xff] & 0xff] ^
+ AES_Td2[AES_Te4[(rk[1] >> 8) & 0xff] & 0xff] ^
+ AES_Td3[AES_Te4[(rk[1] ) & 0xff] & 0xff];
+ rk[2] =
+ AES_Td0[AES_Te4[(rk[2] >> 24) ] & 0xff] ^
+ AES_Td1[AES_Te4[(rk[2] >> 16) & 0xff] & 0xff] ^
+ AES_Td2[AES_Te4[(rk[2] >> 8) & 0xff] & 0xff] ^
+ AES_Td3[AES_Te4[(rk[2] ) & 0xff] & 0xff];
+ rk[3] =
+ AES_Td0[AES_Te4[(rk[3] >> 24) ] & 0xff] ^
+ AES_Td1[AES_Te4[(rk[3] >> 16) & 0xff] & 0xff] ^
+ AES_Td2[AES_Te4[(rk[3] >> 8) & 0xff] & 0xff] ^
+ AES_Td3[AES_Te4[(rk[3] ) & 0xff] & 0xff];
+ }
+ return 0;
+}
+
+#ifndef AES_ASM
+/*
+ * Encrypt a single block
+ * in and out can overlap
+ */
+void AES_encrypt(const unsigned char *in, unsigned char *out,
+ const AES_KEY *key) {
+
+ const u32 *rk;
+ u32 s0, s1, s2, s3, t0, t1, t2, t3;
+#ifndef FULL_UNROLL
+ int r;
+#endif /* ?FULL_UNROLL */
+
+ assert(in && out && key);
+ rk = key->rd_key;
+
+ /*
+ * map byte array block to cipher state
+ * and add initial round key:
+ */
+ s0 = GETU32(in ) ^ rk[0];
+ s1 = GETU32(in + 4) ^ rk[1];
+ s2 = GETU32(in + 8) ^ rk[2];
+ s3 = GETU32(in + 12) ^ rk[3];
+#ifdef FULL_UNROLL
+ /* round 1: */
+ t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >> 8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[ 4];
+ t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >> 8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[ 5];
+ t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >> 8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[ 6];
+ t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >> 8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[ 7];
+ /* round 2: */
+ s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >> 8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[ 8];
+ s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >> 8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[ 9];
+ s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >> 8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[10];
+ s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >> 8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[11];
+ /* round 3: */
+ t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >> 8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[12];
+ t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >> 8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[13];
+ t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >> 8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[14];
+ t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >> 8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[15];
+ /* round 4: */
+ s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >> 8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[16];
+ s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >> 8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[17];
+ s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >> 8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[18];
+ s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >> 8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[19];
+ /* round 5: */
+ t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >> 8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[20];
+ t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >> 8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[21];
+ t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >> 8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[22];
+ t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >> 8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[23];
+ /* round 6: */
+ s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >> 8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[24];
+ s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >> 8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[25];
+ s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >> 8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[26];
+ s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >> 8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[27];
+ /* round 7: */
+ t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >> 8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[28];
+ t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >> 8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[29];
+ t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >> 8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[30];
+ t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >> 8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[31];
+ /* round 8: */
+ s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >> 8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[32];
+ s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >> 8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[33];
+ s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >> 8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[34];
+ s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >> 8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[35];
+ /* round 9: */
+ t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >> 8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[36];
+ t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >> 8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[37];
+ t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >> 8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[38];
+ t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >> 8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[39];
+ if (key->rounds > 10) {
+ /* round 10: */
+ s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >> 8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[40];
+ s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >> 8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[41];
+ s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >> 8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[42];
+ s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >> 8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[43];
+ /* round 11: */
+ t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >> 8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[44];
+ t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >> 8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[45];
+ t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >> 8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[46];
+ t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >> 8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[47];
+ if (key->rounds > 12) {
+ /* round 12: */
+ s0 = AES_Te0[t0 >> 24] ^ AES_Te1[(t1 >> 16) & 0xff] ^ AES_Te2[(t2 >> 8) & 0xff] ^ AES_Te3[t3 & 0xff] ^ rk[48];
+ s1 = AES_Te0[t1 >> 24] ^ AES_Te1[(t2 >> 16) & 0xff] ^ AES_Te2[(t3 >> 8) & 0xff] ^ AES_Te3[t0 & 0xff] ^ rk[49];
+ s2 = AES_Te0[t2 >> 24] ^ AES_Te1[(t3 >> 16) & 0xff] ^ AES_Te2[(t0 >> 8) & 0xff] ^ AES_Te3[t1 & 0xff] ^ rk[50];
+ s3 = AES_Te0[t3 >> 24] ^ AES_Te1[(t0 >> 16) & 0xff] ^ AES_Te2[(t1 >> 8) & 0xff] ^ AES_Te3[t2 & 0xff] ^ rk[51];
+ /* round 13: */
+ t0 = AES_Te0[s0 >> 24] ^ AES_Te1[(s1 >> 16) & 0xff] ^ AES_Te2[(s2 >> 8) & 0xff] ^ AES_Te3[s3 & 0xff] ^ rk[52];
+ t1 = AES_Te0[s1 >> 24] ^ AES_Te1[(s2 >> 16) & 0xff] ^ AES_Te2[(s3 >> 8) & 0xff] ^ AES_Te3[s0 & 0xff] ^ rk[53];
+ t2 = AES_Te0[s2 >> 24] ^ AES_Te1[(s3 >> 16) & 0xff] ^ AES_Te2[(s0 >> 8) & 0xff] ^ AES_Te3[s1 & 0xff] ^ rk[54];
+ t3 = AES_Te0[s3 >> 24] ^ AES_Te1[(s0 >> 16) & 0xff] ^ AES_Te2[(s1 >> 8) & 0xff] ^ AES_Te3[s2 & 0xff] ^ rk[55];
+ }
+ }
+ rk += key->rounds << 2;
+#else /* !FULL_UNROLL */
+ /*
+ * Nr - 1 full rounds:
+ */
+ r = key->rounds >> 1;
+ for (;;) {
+ t0 =
+ AES_Te0[(s0 >> 24) ] ^
+ AES_Te1[(s1 >> 16) & 0xff] ^
+ AES_Te2[(s2 >> 8) & 0xff] ^
+ AES_Te3[(s3 ) & 0xff] ^
+ rk[4];
+ t1 =
+ AES_Te0[(s1 >> 24) ] ^
+ AES_Te1[(s2 >> 16) & 0xff] ^
+ AES_Te2[(s3 >> 8) & 0xff] ^
+ AES_Te3[(s0 ) & 0xff] ^
+ rk[5];
+ t2 =
+ AES_Te0[(s2 >> 24) ] ^
+ AES_Te1[(s3 >> 16) & 0xff] ^
+ AES_Te2[(s0 >> 8) & 0xff] ^
+ AES_Te3[(s1 ) & 0xff] ^
+ rk[6];
+ t3 =
+ AES_Te0[(s3 >> 24) ] ^
+ AES_Te1[(s0 >> 16) & 0xff] ^
+ AES_Te2[(s1 >> 8) & 0xff] ^
+ AES_Te3[(s2 ) & 0xff] ^
+ rk[7];
+
+ rk += 8;
+ if (--r == 0) {
+ break;
+ }
+
+ s0 =
+ AES_Te0[(t0 >> 24) ] ^
+ AES_Te1[(t1 >> 16) & 0xff] ^
+ AES_Te2[(t2 >> 8) & 0xff] ^
+ AES_Te3[(t3 ) & 0xff] ^
+ rk[0];
+ s1 =
+ AES_Te0[(t1 >> 24) ] ^
+ AES_Te1[(t2 >> 16) & 0xff] ^
+ AES_Te2[(t3 >> 8) & 0xff] ^
+ AES_Te3[(t0 ) & 0xff] ^
+ rk[1];
+ s2 =
+ AES_Te0[(t2 >> 24) ] ^
+ AES_Te1[(t3 >> 16) & 0xff] ^
+ AES_Te2[(t0 >> 8) & 0xff] ^
+ AES_Te3[(t1 ) & 0xff] ^
+ rk[2];
+ s3 =
+ AES_Te0[(t3 >> 24) ] ^
+ AES_Te1[(t0 >> 16) & 0xff] ^
+ AES_Te2[(t1 >> 8) & 0xff] ^
+ AES_Te3[(t2 ) & 0xff] ^
+ rk[3];
+ }
+#endif /* ?FULL_UNROLL */
+ /*
+ * apply last round and
+ * map cipher state to byte array block:
+ */
+ s0 =
+ (AES_Te4[(t0 >> 24) ] & 0xff000000) ^
+ (AES_Te4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(t2 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(t3 ) & 0xff] & 0x000000ff) ^
+ rk[0];
+ PUTU32(out , s0);
+ s1 =
+ (AES_Te4[(t1 >> 24) ] & 0xff000000) ^
+ (AES_Te4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(t3 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(t0 ) & 0xff] & 0x000000ff) ^
+ rk[1];
+ PUTU32(out + 4, s1);
+ s2 =
+ (AES_Te4[(t2 >> 24) ] & 0xff000000) ^
+ (AES_Te4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(t0 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(t1 ) & 0xff] & 0x000000ff) ^
+ rk[2];
+ PUTU32(out + 8, s2);
+ s3 =
+ (AES_Te4[(t3 >> 24) ] & 0xff000000) ^
+ (AES_Te4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Te4[(t1 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Te4[(t2 ) & 0xff] & 0x000000ff) ^
+ rk[3];
+ PUTU32(out + 12, s3);
+}
+
+/*
+ * Decrypt a single block
+ * in and out can overlap
+ */
+void AES_decrypt(const unsigned char *in, unsigned char *out,
+ const AES_KEY *key) {
+
+ const u32 *rk;
+ u32 s0, s1, s2, s3, t0, t1, t2, t3;
+#ifndef FULL_UNROLL
+ int r;
+#endif /* ?FULL_UNROLL */
+
+ assert(in && out && key);
+ rk = key->rd_key;
+
+ /*
+ * map byte array block to cipher state
+ * and add initial round key:
+ */
+ s0 = GETU32(in ) ^ rk[0];
+ s1 = GETU32(in + 4) ^ rk[1];
+ s2 = GETU32(in + 8) ^ rk[2];
+ s3 = GETU32(in + 12) ^ rk[3];
+#ifdef FULL_UNROLL
+ /* round 1: */
+ t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >> 8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[ 4];
+ t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >> 8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[ 5];
+ t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >> 8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[ 6];
+ t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >> 8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[ 7];
+ /* round 2: */
+ s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >> 8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[ 8];
+ s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >> 8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[ 9];
+ s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >> 8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[10];
+ s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >> 8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[11];
+ /* round 3: */
+ t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >> 8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[12];
+ t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >> 8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[13];
+ t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >> 8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[14];
+ t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >> 8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[15];
+ /* round 4: */
+ s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >> 8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[16];
+ s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >> 8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[17];
+ s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >> 8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[18];
+ s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >> 8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[19];
+ /* round 5: */
+ t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >> 8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[20];
+ t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >> 8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[21];
+ t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >> 8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[22];
+ t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >> 8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[23];
+ /* round 6: */
+ s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >> 8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[24];
+ s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >> 8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[25];
+ s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >> 8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[26];
+ s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >> 8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[27];
+ /* round 7: */
+ t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >> 8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[28];
+ t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >> 8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[29];
+ t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >> 8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[30];
+ t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >> 8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[31];
+ /* round 8: */
+ s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >> 8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[32];
+ s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >> 8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[33];
+ s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >> 8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[34];
+ s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >> 8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[35];
+ /* round 9: */
+ t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >> 8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[36];
+ t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >> 8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[37];
+ t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >> 8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[38];
+ t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >> 8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[39];
+ if (key->rounds > 10) {
+ /* round 10: */
+ s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >> 8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[40];
+ s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >> 8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[41];
+ s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >> 8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[42];
+ s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >> 8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[43];
+ /* round 11: */
+ t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >> 8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[44];
+ t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >> 8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[45];
+ t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >> 8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[46];
+ t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >> 8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[47];
+ if (key->rounds > 12) {
+ /* round 12: */
+ s0 = AES_Td0[t0 >> 24] ^ AES_Td1[(t3 >> 16) & 0xff] ^ AES_Td2[(t2 >> 8) & 0xff] ^ AES_Td3[t1 & 0xff] ^ rk[48];
+ s1 = AES_Td0[t1 >> 24] ^ AES_Td1[(t0 >> 16) & 0xff] ^ AES_Td2[(t3 >> 8) & 0xff] ^ AES_Td3[t2 & 0xff] ^ rk[49];
+ s2 = AES_Td0[t2 >> 24] ^ AES_Td1[(t1 >> 16) & 0xff] ^ AES_Td2[(t0 >> 8) & 0xff] ^ AES_Td3[t3 & 0xff] ^ rk[50];
+ s3 = AES_Td0[t3 >> 24] ^ AES_Td1[(t2 >> 16) & 0xff] ^ AES_Td2[(t1 >> 8) & 0xff] ^ AES_Td3[t0 & 0xff] ^ rk[51];
+ /* round 13: */
+ t0 = AES_Td0[s0 >> 24] ^ AES_Td1[(s3 >> 16) & 0xff] ^ AES_Td2[(s2 >> 8) & 0xff] ^ AES_Td3[s1 & 0xff] ^ rk[52];
+ t1 = AES_Td0[s1 >> 24] ^ AES_Td1[(s0 >> 16) & 0xff] ^ AES_Td2[(s3 >> 8) & 0xff] ^ AES_Td3[s2 & 0xff] ^ rk[53];
+ t2 = AES_Td0[s2 >> 24] ^ AES_Td1[(s1 >> 16) & 0xff] ^ AES_Td2[(s0 >> 8) & 0xff] ^ AES_Td3[s3 & 0xff] ^ rk[54];
+ t3 = AES_Td0[s3 >> 24] ^ AES_Td1[(s2 >> 16) & 0xff] ^ AES_Td2[(s1 >> 8) & 0xff] ^ AES_Td3[s0 & 0xff] ^ rk[55];
+ }
+ }
+ rk += key->rounds << 2;
+#else /* !FULL_UNROLL */
+ /*
+ * Nr - 1 full rounds:
+ */
+ r = key->rounds >> 1;
+ for (;;) {
+ t0 =
+ AES_Td0[(s0 >> 24) ] ^
+ AES_Td1[(s3 >> 16) & 0xff] ^
+ AES_Td2[(s2 >> 8) & 0xff] ^
+ AES_Td3[(s1 ) & 0xff] ^
+ rk[4];
+ t1 =
+ AES_Td0[(s1 >> 24) ] ^
+ AES_Td1[(s0 >> 16) & 0xff] ^
+ AES_Td2[(s3 >> 8) & 0xff] ^
+ AES_Td3[(s2 ) & 0xff] ^
+ rk[5];
+ t2 =
+ AES_Td0[(s2 >> 24) ] ^
+ AES_Td1[(s1 >> 16) & 0xff] ^
+ AES_Td2[(s0 >> 8) & 0xff] ^
+ AES_Td3[(s3 ) & 0xff] ^
+ rk[6];
+ t3 =
+ AES_Td0[(s3 >> 24) ] ^
+ AES_Td1[(s2 >> 16) & 0xff] ^
+ AES_Td2[(s1 >> 8) & 0xff] ^
+ AES_Td3[(s0 ) & 0xff] ^
+ rk[7];
+
+ rk += 8;
+ if (--r == 0) {
+ break;
+ }
+
+ s0 =
+ AES_Td0[(t0 >> 24) ] ^
+ AES_Td1[(t3 >> 16) & 0xff] ^
+ AES_Td2[(t2 >> 8) & 0xff] ^
+ AES_Td3[(t1 ) & 0xff] ^
+ rk[0];
+ s1 =
+ AES_Td0[(t1 >> 24) ] ^
+ AES_Td1[(t0 >> 16) & 0xff] ^
+ AES_Td2[(t3 >> 8) & 0xff] ^
+ AES_Td3[(t2 ) & 0xff] ^
+ rk[1];
+ s2 =
+ AES_Td0[(t2 >> 24) ] ^
+ AES_Td1[(t1 >> 16) & 0xff] ^
+ AES_Td2[(t0 >> 8) & 0xff] ^
+ AES_Td3[(t3 ) & 0xff] ^
+ rk[2];
+ s3 =
+ AES_Td0[(t3 >> 24) ] ^
+ AES_Td1[(t2 >> 16) & 0xff] ^
+ AES_Td2[(t1 >> 8) & 0xff] ^
+ AES_Td3[(t0 ) & 0xff] ^
+ rk[3];
+ }
+#endif /* ?FULL_UNROLL */
+ /*
+ * apply last round and
+ * map cipher state to byte array block:
+ */
+ s0 =
+ (AES_Td4[(t0 >> 24) ] & 0xff000000) ^
+ (AES_Td4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Td4[(t2 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Td4[(t1 ) & 0xff] & 0x000000ff) ^
+ rk[0];
+ PUTU32(out , s0);
+ s1 =
+ (AES_Td4[(t1 >> 24) ] & 0xff000000) ^
+ (AES_Td4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Td4[(t3 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Td4[(t2 ) & 0xff] & 0x000000ff) ^
+ rk[1];
+ PUTU32(out + 4, s1);
+ s2 =
+ (AES_Td4[(t2 >> 24) ] & 0xff000000) ^
+ (AES_Td4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Td4[(t0 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Td4[(t3 ) & 0xff] & 0x000000ff) ^
+ rk[2];
+ PUTU32(out + 8, s2);
+ s3 =
+ (AES_Td4[(t3 >> 24) ] & 0xff000000) ^
+ (AES_Td4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
+ (AES_Td4[(t1 >> 8) & 0xff] & 0x0000ff00) ^
+ (AES_Td4[(t0 ) & 0xff] & 0x000000ff) ^
+ rk[3];
+ PUTU32(out + 12, s3);
+}
+
+#endif /* AES_ASM */
+
+void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
+ const unsigned long length, const AES_KEY *key,
+ unsigned char *ivec, const int enc)
+{
+
+ unsigned long n;
+ unsigned long len = length;
+ unsigned char tmp[AES_BLOCK_SIZE];
+
+ assert(in && out && key && ivec);
+
+ if (enc) {
+ while (len >= AES_BLOCK_SIZE) {
+ for(n=0; n < AES_BLOCK_SIZE; ++n)
+ tmp[n] = in[n] ^ ivec[n];
+ AES_encrypt(tmp, out, key);
+ memcpy(ivec, out, AES_BLOCK_SIZE);
+ len -= AES_BLOCK_SIZE;
+ in += AES_BLOCK_SIZE;
+ out += AES_BLOCK_SIZE;
+ }
+ if (len) {
+ for(n=0; n < len; ++n)
+ tmp[n] = in[n] ^ ivec[n];
+ for(n=len; n < AES_BLOCK_SIZE; ++n)
+ tmp[n] = ivec[n];
+ AES_encrypt(tmp, tmp, key);
+ memcpy(out, tmp, AES_BLOCK_SIZE);
+ memcpy(ivec, tmp, AES_BLOCK_SIZE);
+ }
+ } else {
+ while (len >= AES_BLOCK_SIZE) {
+ memcpy(tmp, in, AES_BLOCK_SIZE);
+ AES_decrypt(in, out, key);
+ for(n=0; n < AES_BLOCK_SIZE; ++n)
+ out[n] ^= ivec[n];
+ memcpy(ivec, tmp, AES_BLOCK_SIZE);
+ len -= AES_BLOCK_SIZE;
+ in += AES_BLOCK_SIZE;
+ out += AES_BLOCK_SIZE;
+ }
+ if (len) {
+ memcpy(tmp, in, AES_BLOCK_SIZE);
+ AES_decrypt(tmp, tmp, key);
+ for(n=0; n < len; ++n)
+ out[n] = tmp[n] ^ ivec[n];
+ memcpy(ivec, tmp, AES_BLOCK_SIZE);
+ }
+ }
+}
diff --git a/contrib/qemu/util/bitmap.c b/contrib/qemu/util/bitmap.c
new file mode 100644
index 00000000000..687841dcec0
--- /dev/null
+++ b/contrib/qemu/util/bitmap.c
@@ -0,0 +1,256 @@
+/*
+ * Bitmap Module
+ *
+ * Stolen from linux/src/lib/bitmap.c
+ *
+ * Copyright (C) 2010 Corentin Chary
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.
+ */
+
+#include "qemu/bitops.h"
+#include "qemu/bitmap.h"
+
+/*
+ * bitmaps provide an array of bits, implemented using an an
+ * array of unsigned longs. The number of valid bits in a
+ * given bitmap does _not_ need to be an exact multiple of
+ * BITS_PER_LONG.
+ *
+ * The possible unused bits in the last, partially used word
+ * of a bitmap are 'don't care'. The implementation makes
+ * no particular effort to keep them zero. It ensures that
+ * their value will not affect the results of any operation.
+ * The bitmap operations that return Boolean (bitmap_empty,
+ * for example) or scalar (bitmap_weight, for example) results
+ * carefully filter out these unused bits from impacting their
+ * results.
+ *
+ * These operations actually hold to a slightly stronger rule:
+ * if you don't input any bitmaps to these ops that have some
+ * unused bits set, then they won't output any set unused bits
+ * in output bitmaps.
+ *
+ * The byte ordering of bitmaps is more natural on little
+ * endian architectures.
+ */
+
+int slow_bitmap_empty(const unsigned long *bitmap, int bits)
+{
+ int k, lim = bits/BITS_PER_LONG;
+
+ for (k = 0; k < lim; ++k) {
+ if (bitmap[k]) {
+ return 0;
+ }
+ }
+ if (bits % BITS_PER_LONG) {
+ if (bitmap[k] & BITMAP_LAST_WORD_MASK(bits)) {
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+int slow_bitmap_full(const unsigned long *bitmap, int bits)
+{
+ int k, lim = bits/BITS_PER_LONG;
+
+ for (k = 0; k < lim; ++k) {
+ if (~bitmap[k]) {
+ return 0;
+ }
+ }
+
+ if (bits % BITS_PER_LONG) {
+ if (~bitmap[k] & BITMAP_LAST_WORD_MASK(bits)) {
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+int slow_bitmap_equal(const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits)
+{
+ int k, lim = bits/BITS_PER_LONG;
+
+ for (k = 0; k < lim; ++k) {
+ if (bitmap1[k] != bitmap2[k]) {
+ return 0;
+ }
+ }
+
+ if (bits % BITS_PER_LONG) {
+ if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) {
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+void slow_bitmap_complement(unsigned long *dst, const unsigned long *src,
+ int bits)
+{
+ int k, lim = bits/BITS_PER_LONG;
+
+ for (k = 0; k < lim; ++k) {
+ dst[k] = ~src[k];
+ }
+
+ if (bits % BITS_PER_LONG) {
+ dst[k] = ~src[k] & BITMAP_LAST_WORD_MASK(bits);
+ }
+}
+
+int slow_bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits)
+{
+ int k;
+ int nr = BITS_TO_LONGS(bits);
+ unsigned long result = 0;
+
+ for (k = 0; k < nr; k++) {
+ result |= (dst[k] = bitmap1[k] & bitmap2[k]);
+ }
+ return result != 0;
+}
+
+void slow_bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits)
+{
+ int k;
+ int nr = BITS_TO_LONGS(bits);
+
+ for (k = 0; k < nr; k++) {
+ dst[k] = bitmap1[k] | bitmap2[k];
+ }
+}
+
+void slow_bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits)
+{
+ int k;
+ int nr = BITS_TO_LONGS(bits);
+
+ for (k = 0; k < nr; k++) {
+ dst[k] = bitmap1[k] ^ bitmap2[k];
+ }
+}
+
+int slow_bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits)
+{
+ int k;
+ int nr = BITS_TO_LONGS(bits);
+ unsigned long result = 0;
+
+ for (k = 0; k < nr; k++) {
+ result |= (dst[k] = bitmap1[k] & ~bitmap2[k]);
+ }
+ return result != 0;
+}
+
+#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
+
+void bitmap_set(unsigned long *map, int start, int nr)
+{
+ unsigned long *p = map + BIT_WORD(start);
+ const int size = start + nr;
+ int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+ unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+ while (nr - bits_to_set >= 0) {
+ *p |= mask_to_set;
+ nr -= bits_to_set;
+ bits_to_set = BITS_PER_LONG;
+ mask_to_set = ~0UL;
+ p++;
+ }
+ if (nr) {
+ mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+ *p |= mask_to_set;
+ }
+}
+
+void bitmap_clear(unsigned long *map, int start, int nr)
+{
+ unsigned long *p = map + BIT_WORD(start);
+ const int size = start + nr;
+ int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+ unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+ while (nr - bits_to_clear >= 0) {
+ *p &= ~mask_to_clear;
+ nr -= bits_to_clear;
+ bits_to_clear = BITS_PER_LONG;
+ mask_to_clear = ~0UL;
+ p++;
+ }
+ if (nr) {
+ mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+ *p &= ~mask_to_clear;
+ }
+}
+
+#define ALIGN_MASK(x,mask) (((x)+(mask))&~(mask))
+
+/**
+ * bitmap_find_next_zero_area - find a contiguous aligned zero area
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @align_mask: Alignment mask for zero area
+ *
+ * The @align_mask should be one less than a power of 2; the effect is that
+ * the bit offset of all zero areas this function finds is multiples of that
+ * power of 2. A @align_mask of 0 means no alignment is required.
+ */
+unsigned long bitmap_find_next_zero_area(unsigned long *map,
+ unsigned long size,
+ unsigned long start,
+ unsigned int nr,
+ unsigned long align_mask)
+{
+ unsigned long index, end, i;
+again:
+ index = find_next_zero_bit(map, size, start);
+
+ /* Align allocation */
+ index = ALIGN_MASK(index, align_mask);
+
+ end = index + nr;
+ if (end > size) {
+ return end;
+ }
+ i = find_next_bit(map, end, index);
+ if (i < end) {
+ start = i + 1;
+ goto again;
+ }
+ return index;
+}
+
+int slow_bitmap_intersects(const unsigned long *bitmap1,
+ const unsigned long *bitmap2, int bits)
+{
+ int k, lim = bits/BITS_PER_LONG;
+
+ for (k = 0; k < lim; ++k) {
+ if (bitmap1[k] & bitmap2[k]) {
+ return 1;
+ }
+ }
+
+ if (bits % BITS_PER_LONG) {
+ if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) {
+ return 1;
+ }
+ }
+ return 0;
+}
diff --git a/contrib/qemu/util/bitops.c b/contrib/qemu/util/bitops.c
new file mode 100644
index 00000000000..227c38b883d
--- /dev/null
+++ b/contrib/qemu/util/bitops.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ * Copyright (C) 2008 IBM Corporation
+ * Written by Rusty Russell <rusty@rustcorp.com.au>
+ * (Inspired by David Howell's find_next_bit implementation)
+ *
+ * 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.
+ */
+
+#include "qemu/bitops.h"
+
+#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
+
+/*
+ * Find the next set bit in a memory region.
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ const unsigned long *p = addr + BITOP_WORD(offset);
+ unsigned long result = offset & ~(BITS_PER_LONG-1);
+ unsigned long tmp;
+
+ if (offset >= size) {
+ return size;
+ }
+ size -= result;
+ offset %= BITS_PER_LONG;
+ if (offset) {
+ tmp = *(p++);
+ tmp &= (~0UL << offset);
+ if (size < BITS_PER_LONG) {
+ goto found_first;
+ }
+ if (tmp) {
+ goto found_middle;
+ }
+ size -= BITS_PER_LONG;
+ result += BITS_PER_LONG;
+ }
+ while (size >= 4*BITS_PER_LONG) {
+ unsigned long d1, d2, d3;
+ tmp = *p;
+ d1 = *(p+1);
+ d2 = *(p+2);
+ d3 = *(p+3);
+ if (tmp) {
+ goto found_middle;
+ }
+ if (d1 | d2 | d3) {
+ break;
+ }
+ p += 4;
+ result += 4*BITS_PER_LONG;
+ size -= 4*BITS_PER_LONG;
+ }
+ while (size >= BITS_PER_LONG) {
+ if ((tmp = *(p++))) {
+ goto found_middle;
+ }
+ result += BITS_PER_LONG;
+ size -= BITS_PER_LONG;
+ }
+ if (!size) {
+ return result;
+ }
+ tmp = *p;
+
+found_first:
+ tmp &= (~0UL >> (BITS_PER_LONG - size));
+ if (tmp == 0UL) { /* Are any bits set? */
+ return result + size; /* Nope. */
+ }
+found_middle:
+ return result + ctzl(tmp);
+}
+
+/*
+ * This implementation of find_{first,next}_zero_bit was stolen from
+ * Linus' asm-alpha/bitops.h.
+ */
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+ unsigned long offset)
+{
+ const unsigned long *p = addr + BITOP_WORD(offset);
+ unsigned long result = offset & ~(BITS_PER_LONG-1);
+ unsigned long tmp;
+
+ if (offset >= size) {
+ return size;
+ }
+ size -= result;
+ offset %= BITS_PER_LONG;
+ if (offset) {
+ tmp = *(p++);
+ tmp |= ~0UL >> (BITS_PER_LONG - offset);
+ if (size < BITS_PER_LONG) {
+ goto found_first;
+ }
+ if (~tmp) {
+ goto found_middle;
+ }
+ size -= BITS_PER_LONG;
+ result += BITS_PER_LONG;
+ }
+ while (size & ~(BITS_PER_LONG-1)) {
+ if (~(tmp = *(p++))) {
+ goto found_middle;
+ }
+ result += BITS_PER_LONG;
+ size -= BITS_PER_LONG;
+ }
+ if (!size) {
+ return result;
+ }
+ tmp = *p;
+
+found_first:
+ tmp |= ~0UL << size;
+ if (tmp == ~0UL) { /* Are any bits zero? */
+ return result + size; /* Nope. */
+ }
+found_middle:
+ return result + ctzl(~tmp);
+}
+
+unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+{
+ unsigned long words;
+ unsigned long tmp;
+
+ /* Start at final word. */
+ words = size / BITS_PER_LONG;
+
+ /* Partial final word? */
+ if (size & (BITS_PER_LONG-1)) {
+ tmp = (addr[words] & (~0UL >> (BITS_PER_LONG
+ - (size & (BITS_PER_LONG-1)))));
+ if (tmp) {
+ goto found;
+ }
+ }
+
+ while (words) {
+ tmp = addr[--words];
+ if (tmp) {
+ found:
+ return words * BITS_PER_LONG + BITS_PER_LONG - 1 - clzl(tmp);
+ }
+ }
+
+ /* Not found */
+ return size;
+}
diff --git a/contrib/qemu/util/cutils.c b/contrib/qemu/util/cutils.c
new file mode 100644
index 00000000000..0116fcde74f
--- /dev/null
+++ b/contrib/qemu/util/cutils.c
@@ -0,0 +1,532 @@
+/*
+ * Simple C functions to supplement the C library
+ *
+ * Copyright (c) 2006 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "qemu-common.h"
+#include "qemu/host-utils.h"
+#include <math.h>
+
+#include "qemu/sockets.h"
+#include "qemu/iov.h"
+
+void strpadcpy(char *buf, int buf_size, const char *str, char pad)
+{
+ int len = qemu_strnlen(str, buf_size);
+ memcpy(buf, str, len);
+ memset(buf + len, pad, buf_size - len);
+}
+
+void pstrcpy(char *buf, int buf_size, const char *str)
+{
+ int c;
+ char *q = buf;
+
+ if (buf_size <= 0)
+ return;
+
+ for(;;) {
+ c = *str++;
+ if (c == 0 || q >= buf + buf_size - 1)
+ break;
+ *q++ = c;
+ }
+ *q = '\0';
+}
+
+/* strcat and truncate. */
+char *pstrcat(char *buf, int buf_size, const char *s)
+{
+ int len;
+ len = strlen(buf);
+ if (len < buf_size)
+ pstrcpy(buf + len, buf_size - len, s);
+ return buf;
+}
+
+int strstart(const char *str, const char *val, const char **ptr)
+{
+ const char *p, *q;
+ p = str;
+ q = val;
+ while (*q != '\0') {
+ if (*p != *q)
+ return 0;
+ p++;
+ q++;
+ }
+ if (ptr)
+ *ptr = p;
+ return 1;
+}
+
+int stristart(const char *str, const char *val, const char **ptr)
+{
+ const char *p, *q;
+ p = str;
+ q = val;
+ while (*q != '\0') {
+ if (qemu_toupper(*p) != qemu_toupper(*q))
+ return 0;
+ p++;
+ q++;
+ }
+ if (ptr)
+ *ptr = p;
+ return 1;
+}
+
+/* XXX: use host strnlen if available ? */
+int qemu_strnlen(const char *s, int max_len)
+{
+ int i;
+
+ for(i = 0; i < max_len; i++) {
+ if (s[i] == '\0') {
+ break;
+ }
+ }
+ return i;
+}
+
+char *qemu_strsep(char **input, const char *delim)
+{
+ char *result = *input;
+ if (result != NULL) {
+ char *p;
+
+ for (p = result; *p != '\0'; p++) {
+ if (strchr(delim, *p)) {
+ break;
+ }
+ }
+ if (*p == '\0') {
+ *input = NULL;
+ } else {
+ *p = '\0';
+ *input = p + 1;
+ }
+ }
+ return result;
+}
+
+time_t mktimegm(struct tm *tm)
+{
+ time_t t;
+ int y = tm->tm_year + 1900, m = tm->tm_mon + 1, d = tm->tm_mday;
+ if (m < 3) {
+ m += 12;
+ y--;
+ }
+ t = 86400ULL * (d + (153 * m - 457) / 5 + 365 * y + y / 4 - y / 100 +
+ y / 400 - 719469);
+ t += 3600 * tm->tm_hour + 60 * tm->tm_min + tm->tm_sec;
+ return t;
+}
+
+int qemu_fls(int i)
+{
+ return 32 - clz32(i);
+}
+
+/*
+ * Make sure data goes on disk, but if possible do not bother to
+ * write out the inode just for timestamp updates.
+ *
+ * Unfortunately even in 2009 many operating systems do not support
+ * fdatasync and have to fall back to fsync.
+ */
+int qemu_fdatasync(int fd)
+{
+#ifdef CONFIG_FDATASYNC
+ return fdatasync(fd);
+#else
+ return fsync(fd);
+#endif
+}
+
+/*
+ * Searches for an area with non-zero content in a buffer
+ *
+ * Attention! The len must be a multiple of
+ * BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR * sizeof(VECTYPE)
+ * and addr must be a multiple of sizeof(VECTYPE) due to
+ * restriction of optimizations in this function.
+ *
+ * can_use_buffer_find_nonzero_offset() can be used to check
+ * these requirements.
+ *
+ * The return value is the offset of the non-zero area rounded
+ * down to a multiple of sizeof(VECTYPE) for the first
+ * BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR chunks and down to
+ * BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR * sizeof(VECTYPE)
+ * afterwards.
+ *
+ * If the buffer is all zero the return value is equal to len.
+ */
+
+size_t buffer_find_nonzero_offset(const void *buf, size_t len)
+{
+ const VECTYPE *p = buf;
+ const VECTYPE zero = (VECTYPE){0};
+ size_t i;
+
+ assert(can_use_buffer_find_nonzero_offset(buf, len));
+
+ if (!len) {
+ return 0;
+ }
+
+ for (i = 0; i < BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR; i++) {
+ if (!ALL_EQ(p[i], zero)) {
+ return i * sizeof(VECTYPE);
+ }
+ }
+
+ for (i = BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR;
+ i < len / sizeof(VECTYPE);
+ i += BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR) {
+ VECTYPE tmp0 = p[i + 0] | p[i + 1];
+ VECTYPE tmp1 = p[i + 2] | p[i + 3];
+ VECTYPE tmp2 = p[i + 4] | p[i + 5];
+ VECTYPE tmp3 = p[i + 6] | p[i + 7];
+ VECTYPE tmp01 = tmp0 | tmp1;
+ VECTYPE tmp23 = tmp2 | tmp3;
+ if (!ALL_EQ(tmp01 | tmp23, zero)) {
+ break;
+ }
+ }
+
+ return i * sizeof(VECTYPE);
+}
+
+/*
+ * Checks if a buffer is all zeroes
+ *
+ * Attention! The len must be a multiple of 4 * sizeof(long) due to
+ * restriction of optimizations in this function.
+ */
+bool buffer_is_zero(const void *buf, size_t len)
+{
+ /*
+ * Use long as the biggest available internal data type that fits into the
+ * CPU register and unroll the loop to smooth out the effect of memory
+ * latency.
+ */
+
+ size_t i;
+ long d0, d1, d2, d3;
+ const long * const data = buf;
+
+ /* use vector optimized zero check if possible */
+ if (can_use_buffer_find_nonzero_offset(buf, len)) {
+ return buffer_find_nonzero_offset(buf, len) == len;
+ }
+
+ assert(len % (4 * sizeof(long)) == 0);
+ len /= sizeof(long);
+
+ for (i = 0; i < len; i += 4) {
+ d0 = data[i + 0];
+ d1 = data[i + 1];
+ d2 = data[i + 2];
+ d3 = data[i + 3];
+
+ if (d0 || d1 || d2 || d3) {
+ return false;
+ }
+ }
+
+ return true;
+}
+
+#ifndef _WIN32
+/* Sets a specific flag */
+int fcntl_setfl(int fd, int flag)
+{
+ int flags;
+
+ flags = fcntl(fd, F_GETFL);
+ if (flags == -1)
+ return -errno;
+
+ if (fcntl(fd, F_SETFL, flags | flag) == -1)
+ return -errno;
+
+ return 0;
+}
+#endif
+
+static int64_t suffix_mul(char suffix, int64_t unit)
+{
+ switch (qemu_toupper(suffix)) {
+ case STRTOSZ_DEFSUFFIX_B:
+ return 1;
+ case STRTOSZ_DEFSUFFIX_KB:
+ return unit;
+ case STRTOSZ_DEFSUFFIX_MB:
+ return unit * unit;
+ case STRTOSZ_DEFSUFFIX_GB:
+ return unit * unit * unit;
+ case STRTOSZ_DEFSUFFIX_TB:
+ return unit * unit * unit * unit;
+ case STRTOSZ_DEFSUFFIX_PB:
+ return unit * unit * unit * unit * unit;
+ case STRTOSZ_DEFSUFFIX_EB:
+ return unit * unit * unit * unit * unit * unit;
+ }
+ return -1;
+}
+
+/*
+ * Convert string to bytes, allowing either B/b for bytes, K/k for KB,
+ * M/m for MB, G/g for GB or T/t for TB. End pointer will be returned
+ * in *end, if not NULL. Return -ERANGE on overflow, Return -EINVAL on
+ * other error.
+ */
+int64_t strtosz_suffix_unit(const char *nptr, char **end,
+ const char default_suffix, int64_t unit)
+{
+ int64_t retval = -EINVAL;
+ char *endptr;
+ unsigned char c;
+ int mul_required = 0;
+ double val, mul, integral, fraction;
+
+ errno = 0;
+ val = strtod(nptr, &endptr);
+ if (isnan(val) || endptr == nptr || errno != 0) {
+ goto fail;
+ }
+ fraction = modf(val, &integral);
+ if (fraction != 0) {
+ mul_required = 1;
+ }
+ c = *endptr;
+ mul = suffix_mul(c, unit);
+ if (mul >= 0) {
+ endptr++;
+ } else {
+ mul = suffix_mul(default_suffix, unit);
+ assert(mul >= 0);
+ }
+ if (mul == 1 && mul_required) {
+ goto fail;
+ }
+ if ((val * mul >= INT64_MAX) || val < 0) {
+ retval = -ERANGE;
+ goto fail;
+ }
+ retval = val * mul;
+
+fail:
+ if (end) {
+ *end = endptr;
+ }
+
+ return retval;
+}
+
+int64_t strtosz_suffix(const char *nptr, char **end, const char default_suffix)
+{
+ return strtosz_suffix_unit(nptr, end, default_suffix, 1024);
+}
+
+int64_t strtosz(const char *nptr, char **end)
+{
+ return strtosz_suffix(nptr, end, STRTOSZ_DEFSUFFIX_MB);
+}
+
+/**
+ * parse_uint:
+ *
+ * @s: String to parse
+ * @value: Destination for parsed integer value
+ * @endptr: Destination for pointer to first character not consumed
+ * @base: integer base, between 2 and 36 inclusive, or 0
+ *
+ * Parse unsigned integer
+ *
+ * Parsed syntax is like strtoull()'s: arbitrary whitespace, a single optional
+ * '+' or '-', an optional "0x" if @base is 0 or 16, one or more digits.
+ *
+ * If @s is null, or @base is invalid, or @s doesn't start with an
+ * integer in the syntax above, set *@value to 0, *@endptr to @s, and
+ * return -EINVAL.
+ *
+ * Set *@endptr to point right beyond the parsed integer (even if the integer
+ * overflows or is negative, all digits will be parsed and *@endptr will
+ * point right beyond them).
+ *
+ * If the integer is negative, set *@value to 0, and return -ERANGE.
+ *
+ * If the integer overflows unsigned long long, set *@value to
+ * ULLONG_MAX, and return -ERANGE.
+ *
+ * Else, set *@value to the parsed integer, and return 0.
+ */
+int parse_uint(const char *s, unsigned long long *value, char **endptr,
+ int base)
+{
+ int r = 0;
+ char *endp = (char *)s;
+ unsigned long long val = 0;
+
+ if (!s) {
+ r = -EINVAL;
+ goto out;
+ }
+
+ errno = 0;
+ val = strtoull(s, &endp, base);
+ if (errno) {
+ r = -errno;
+ goto out;
+ }
+
+ if (endp == s) {
+ r = -EINVAL;
+ goto out;
+ }
+
+ /* make sure we reject negative numbers: */
+ while (isspace((unsigned char)*s)) {
+ s++;
+ }
+ if (*s == '-') {
+ val = 0;
+ r = -ERANGE;
+ goto out;
+ }
+
+out:
+ *value = val;
+ *endptr = endp;
+ return r;
+}
+
+/**
+ * parse_uint_full:
+ *
+ * @s: String to parse
+ * @value: Destination for parsed integer value
+ * @base: integer base, between 2 and 36 inclusive, or 0
+ *
+ * Parse unsigned integer from entire string
+ *
+ * Have the same behavior of parse_uint(), but with an additional check
+ * for additional data after the parsed number. If extra characters are present
+ * after the parsed number, the function will return -EINVAL, and *@v will
+ * be set to 0.
+ */
+int parse_uint_full(const char *s, unsigned long long *value, int base)
+{
+ char *endp;
+ int r;
+
+ r = parse_uint(s, value, &endp, base);
+ if (r < 0) {
+ return r;
+ }
+ if (*endp) {
+ *value = 0;
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int qemu_parse_fd(const char *param)
+{
+ int fd;
+ char *endptr = NULL;
+
+ fd = strtol(param, &endptr, 10);
+ if (*endptr || (fd == 0 && param == endptr)) {
+ return -1;
+ }
+ return fd;
+}
+
+/* round down to the nearest power of 2*/
+int64_t pow2floor(int64_t value)
+{
+ if (!is_power_of_2(value)) {
+ value = 0x8000000000000000ULL >> clz64(value);
+ }
+ return value;
+}
+
+/*
+ * Implementation of ULEB128 (http://en.wikipedia.org/wiki/LEB128)
+ * Input is limited to 14-bit numbers
+ */
+int uleb128_encode_small(uint8_t *out, uint32_t n)
+{
+ g_assert(n <= 0x3fff);
+ if (n < 0x80) {
+ *out++ = n;
+ return 1;
+ } else {
+ *out++ = (n & 0x7f) | 0x80;
+ *out++ = n >> 7;
+ return 2;
+ }
+}
+
+int uleb128_decode_small(const uint8_t *in, uint32_t *n)
+{
+ if (!(*in & 0x80)) {
+ *n = *in++;
+ return 1;
+ } else {
+ *n = *in++ & 0x7f;
+ /* we exceed 14 bit number */
+ if (*in & 0x80) {
+ return -1;
+ }
+ *n |= *in++ << 7;
+ return 2;
+ }
+}
+
+/*
+ * helper to parse debug environment variables
+ */
+int parse_debug_env(const char *name, int max, int initial)
+{
+ char *debug_env = getenv(name);
+ char *inv = NULL;
+ int debug;
+
+ if (!debug_env) {
+ return initial;
+ }
+ debug = strtol(debug_env, &inv, 10);
+ if (inv == debug_env) {
+ return initial;
+ }
+ if (debug < 0 || debug > max) {
+ fprintf(stderr, "warning: %s not in [0, %d]", name, max);
+ return initial;
+ }
+ return debug;
+}
diff --git a/contrib/qemu/util/error.c b/contrib/qemu/util/error.c
new file mode 100644
index 00000000000..53b04354aef
--- /dev/null
+++ b/contrib/qemu/util/error.c
@@ -0,0 +1,120 @@
+/*
+ * QEMU Error Objects
+ *
+ * Copyright IBM, Corp. 2011
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2. See
+ * the COPYING.LIB file in the top-level directory.
+ */
+
+#include "qemu-common.h"
+#include "qapi/error.h"
+#include "qapi/qmp/qjson.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi-types.h"
+#include "qapi/qmp/qerror.h"
+
+struct Error
+{
+ char *msg;
+ ErrorClass err_class;
+};
+
+void error_set(Error **errp, ErrorClass err_class, const char *fmt, ...)
+{
+ Error *err;
+ va_list ap;
+
+ if (errp == NULL) {
+ return;
+ }
+ assert(*errp == NULL);
+
+ err = g_malloc0(sizeof(*err));
+
+ va_start(ap, fmt);
+ err->msg = g_strdup_vprintf(fmt, ap);
+ va_end(ap);
+ err->err_class = err_class;
+
+ *errp = err;
+}
+
+void error_set_errno(Error **errp, int os_errno, ErrorClass err_class,
+ const char *fmt, ...)
+{
+ Error *err;
+ char *msg1;
+ va_list ap;
+
+ if (errp == NULL) {
+ return;
+ }
+ assert(*errp == NULL);
+
+ err = g_malloc0(sizeof(*err));
+
+ va_start(ap, fmt);
+ msg1 = g_strdup_vprintf(fmt, ap);
+ if (os_errno != 0) {
+ err->msg = g_strdup_printf("%s: %s", msg1, strerror(os_errno));
+ g_free(msg1);
+ } else {
+ err->msg = msg1;
+ }
+ va_end(ap);
+ err->err_class = err_class;
+
+ *errp = err;
+}
+
+void error_setg_file_open(Error **errp, int os_errno, const char *filename)
+{
+ error_setg_errno(errp, os_errno, "Could not open '%s'", filename);
+}
+
+Error *error_copy(const Error *err)
+{
+ Error *err_new;
+
+ err_new = g_malloc0(sizeof(*err));
+ err_new->msg = g_strdup(err->msg);
+ err_new->err_class = err->err_class;
+
+ return err_new;
+}
+
+bool error_is_set(Error **errp)
+{
+ return (errp && *errp);
+}
+
+ErrorClass error_get_class(const Error *err)
+{
+ return err->err_class;
+}
+
+const char *error_get_pretty(Error *err)
+{
+ return err->msg;
+}
+
+void error_free(Error *err)
+{
+ if (err) {
+ g_free(err->msg);
+ g_free(err);
+ }
+}
+
+void error_propagate(Error **dst_err, Error *local_err)
+{
+ if (dst_err && !*dst_err) {
+ *dst_err = local_err;
+ } else if (local_err) {
+ error_free(local_err);
+ }
+}
diff --git a/contrib/qemu/util/hbitmap.c b/contrib/qemu/util/hbitmap.c
new file mode 100644
index 00000000000..d93683128bd
--- /dev/null
+++ b/contrib/qemu/util/hbitmap.c
@@ -0,0 +1,402 @@
+/*
+ * Hierarchical Bitmap Data Type
+ *
+ * Copyright Red Hat, Inc., 2012
+ *
+ * Author: Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later. See the COPYING file in the top-level directory.
+ */
+
+#include <string.h>
+#include <glib.h>
+#include <assert.h>
+#include "qemu/osdep.h"
+#include "qemu/hbitmap.h"
+#include "qemu/host-utils.h"
+#include "trace.h"
+
+/* HBitmaps provides an array of bits. The bits are stored as usual in an
+ * array of unsigned longs, but HBitmap is also optimized to provide fast
+ * iteration over set bits; going from one bit to the next is O(logB n)
+ * worst case, with B = sizeof(long) * CHAR_BIT: the result is low enough
+ * that the number of levels is in fact fixed.
+ *
+ * In order to do this, it stacks multiple bitmaps with progressively coarser
+ * granularity; in all levels except the last, bit N is set iff the N-th
+ * unsigned long is nonzero in the immediately next level. When iteration
+ * completes on the last level it can examine the 2nd-last level to quickly
+ * skip entire words, and even do so recursively to skip blocks of 64 words or
+ * powers thereof (32 on 32-bit machines).
+ *
+ * Given an index in the bitmap, it can be split in group of bits like
+ * this (for the 64-bit case):
+ *
+ * bits 0-57 => word in the last bitmap | bits 58-63 => bit in the word
+ * bits 0-51 => word in the 2nd-last bitmap | bits 52-57 => bit in the word
+ * bits 0-45 => word in the 3rd-last bitmap | bits 46-51 => bit in the word
+ *
+ * So it is easy to move up simply by shifting the index right by
+ * log2(BITS_PER_LONG) bits. To move down, you shift the index left
+ * similarly, and add the word index within the group. Iteration uses
+ * ffs (find first set bit) to find the next word to examine; this
+ * operation can be done in constant time in most current architectures.
+ *
+ * Setting or clearing a range of m bits on all levels, the work to perform
+ * is O(m + m/W + m/W^2 + ...), which is O(m) like on a regular bitmap.
+ *
+ * When iterating on a bitmap, each bit (on any level) is only visited
+ * once. Hence, The total cost of visiting a bitmap with m bits in it is
+ * the number of bits that are set in all bitmaps. Unless the bitmap is
+ * extremely sparse, this is also O(m + m/W + m/W^2 + ...), so the amortized
+ * cost of advancing from one bit to the next is usually constant (worst case
+ * O(logB n) as in the non-amortized complexity).
+ */
+
+struct HBitmap {
+ /* Number of total bits in the bottom level. */
+ uint64_t size;
+
+ /* Number of set bits in the bottom level. */
+ uint64_t count;
+
+ /* A scaling factor. Given a granularity of G, each bit in the bitmap will
+ * will actually represent a group of 2^G elements. Each operation on a
+ * range of bits first rounds the bits to determine which group they land
+ * in, and then affect the entire page; iteration will only visit the first
+ * bit of each group. Here is an example of operations in a size-16,
+ * granularity-1 HBitmap:
+ *
+ * initial state 00000000
+ * set(start=0, count=9) 11111000 (iter: 0, 2, 4, 6, 8)
+ * reset(start=1, count=3) 00111000 (iter: 4, 6, 8)
+ * set(start=9, count=2) 00111100 (iter: 4, 6, 8, 10)
+ * reset(start=5, count=5) 00000000
+ *
+ * From an implementation point of view, when setting or resetting bits,
+ * the bitmap will scale bit numbers right by this amount of bits. When
+ * iterating, the bitmap will scale bit numbers left by this amount of
+ * bits.
+ */
+ int granularity;
+
+ /* A number of progressively less coarse bitmaps (i.e. level 0 is the
+ * coarsest). Each bit in level N represents a word in level N+1 that
+ * has a set bit, except the last level where each bit represents the
+ * actual bitmap.
+ *
+ * Note that all bitmaps have the same number of levels. Even a 1-bit
+ * bitmap will still allocate HBITMAP_LEVELS arrays.
+ */
+ unsigned long *levels[HBITMAP_LEVELS];
+};
+
+static inline int popcountl(unsigned long l)
+{
+ return BITS_PER_LONG == 32 ? ctpop32(l) : ctpop64(l);
+}
+
+/* Advance hbi to the next nonzero word and return it. hbi->pos
+ * is updated. Returns zero if we reach the end of the bitmap.
+ */
+unsigned long hbitmap_iter_skip_words(HBitmapIter *hbi)
+{
+ size_t pos = hbi->pos;
+ const HBitmap *hb = hbi->hb;
+ unsigned i = HBITMAP_LEVELS - 1;
+
+ unsigned long cur;
+ do {
+ cur = hbi->cur[--i];
+ pos >>= BITS_PER_LEVEL;
+ } while (cur == 0);
+
+ /* Check for end of iteration. We always use fewer than BITS_PER_LONG
+ * bits in the level 0 bitmap; thus we can repurpose the most significant
+ * bit as a sentinel. The sentinel is set in hbitmap_alloc and ensures
+ * that the above loop ends even without an explicit check on i.
+ */
+
+ if (i == 0 && cur == (1UL << (BITS_PER_LONG - 1))) {
+ return 0;
+ }
+ for (; i < HBITMAP_LEVELS - 1; i++) {
+ /* Shift back pos to the left, matching the right shifts above.
+ * The index of this word's least significant set bit provides
+ * the low-order bits.
+ */
+ assert(cur);
+ pos = (pos << BITS_PER_LEVEL) + ctzl(cur);
+ hbi->cur[i] = cur & (cur - 1);
+
+ /* Set up next level for iteration. */
+ cur = hb->levels[i + 1][pos];
+ }
+
+ hbi->pos = pos;
+ trace_hbitmap_iter_skip_words(hbi->hb, hbi, pos, cur);
+
+ assert(cur);
+ return cur;
+}
+
+void hbitmap_iter_init(HBitmapIter *hbi, const HBitmap *hb, uint64_t first)
+{
+ unsigned i, bit;
+ uint64_t pos;
+
+ hbi->hb = hb;
+ pos = first >> hb->granularity;
+ assert(pos < hb->size);
+ hbi->pos = pos >> BITS_PER_LEVEL;
+ hbi->granularity = hb->granularity;
+
+ for (i = HBITMAP_LEVELS; i-- > 0; ) {
+ bit = pos & (BITS_PER_LONG - 1);
+ pos >>= BITS_PER_LEVEL;
+
+ /* Drop bits representing items before first. */
+ hbi->cur[i] = hb->levels[i][pos] & ~((1UL << bit) - 1);
+
+ /* We have already added level i+1, so the lowest set bit has
+ * been processed. Clear it.
+ */
+ if (i != HBITMAP_LEVELS - 1) {
+ hbi->cur[i] &= ~(1UL << bit);
+ }
+ }
+}
+
+bool hbitmap_empty(const HBitmap *hb)
+{
+ return hb->count == 0;
+}
+
+int hbitmap_granularity(const HBitmap *hb)
+{
+ return hb->granularity;
+}
+
+uint64_t hbitmap_count(const HBitmap *hb)
+{
+ return hb->count << hb->granularity;
+}
+
+/* Count the number of set bits between start and end, not accounting for
+ * the granularity. Also an example of how to use hbitmap_iter_next_word.
+ */
+static uint64_t hb_count_between(HBitmap *hb, uint64_t start, uint64_t last)
+{
+ HBitmapIter hbi;
+ uint64_t count = 0;
+ uint64_t end = last + 1;
+ unsigned long cur;
+ size_t pos;
+
+ hbitmap_iter_init(&hbi, hb, start << hb->granularity);
+ for (;;) {
+ pos = hbitmap_iter_next_word(&hbi, &cur);
+ if (pos >= (end >> BITS_PER_LEVEL)) {
+ break;
+ }
+ count += popcountl(cur);
+ }
+
+ if (pos == (end >> BITS_PER_LEVEL)) {
+ /* Drop bits representing the END-th and subsequent items. */
+ int bit = end & (BITS_PER_LONG - 1);
+ cur &= (1UL << bit) - 1;
+ count += popcountl(cur);
+ }
+
+ return count;
+}
+
+/* Setting starts at the last layer and propagates up if an element
+ * changes from zero to non-zero.
+ */
+static inline bool hb_set_elem(unsigned long *elem, uint64_t start, uint64_t last)
+{
+ unsigned long mask;
+ bool changed;
+
+ assert((last >> BITS_PER_LEVEL) == (start >> BITS_PER_LEVEL));
+ assert(start <= last);
+
+ mask = 2UL << (last & (BITS_PER_LONG - 1));
+ mask -= 1UL << (start & (BITS_PER_LONG - 1));
+ changed = (*elem == 0);
+ *elem |= mask;
+ return changed;
+}
+
+/* The recursive workhorse (the depth is limited to HBITMAP_LEVELS)... */
+static void hb_set_between(HBitmap *hb, int level, uint64_t start, uint64_t last)
+{
+ size_t pos = start >> BITS_PER_LEVEL;
+ size_t lastpos = last >> BITS_PER_LEVEL;
+ bool changed = false;
+ size_t i;
+
+ i = pos;
+ if (i < lastpos) {
+ uint64_t next = (start | (BITS_PER_LONG - 1)) + 1;
+ changed |= hb_set_elem(&hb->levels[level][i], start, next - 1);
+ for (;;) {
+ start = next;
+ next += BITS_PER_LONG;
+ if (++i == lastpos) {
+ break;
+ }
+ changed |= (hb->levels[level][i] == 0);
+ hb->levels[level][i] = ~0UL;
+ }
+ }
+ changed |= hb_set_elem(&hb->levels[level][i], start, last);
+
+ /* If there was any change in this layer, we may have to update
+ * the one above.
+ */
+ if (level > 0 && changed) {
+ hb_set_between(hb, level - 1, pos, lastpos);
+ }
+}
+
+void hbitmap_set(HBitmap *hb, uint64_t start, uint64_t count)
+{
+ /* Compute range in the last layer. */
+ uint64_t last = start + count - 1;
+
+ trace_hbitmap_set(hb, start, count,
+ start >> hb->granularity, last >> hb->granularity);
+
+ start >>= hb->granularity;
+ last >>= hb->granularity;
+ count = last - start + 1;
+
+ hb->count += count - hb_count_between(hb, start, last);
+ hb_set_between(hb, HBITMAP_LEVELS - 1, start, last);
+}
+
+/* Resetting works the other way round: propagate up if the new
+ * value is zero.
+ */
+static inline bool hb_reset_elem(unsigned long *elem, uint64_t start, uint64_t last)
+{
+ unsigned long mask;
+ bool blanked;
+
+ assert((last >> BITS_PER_LEVEL) == (start >> BITS_PER_LEVEL));
+ assert(start <= last);
+
+ mask = 2UL << (last & (BITS_PER_LONG - 1));
+ mask -= 1UL << (start & (BITS_PER_LONG - 1));
+ blanked = *elem != 0 && ((*elem & ~mask) == 0);
+ *elem &= ~mask;
+ return blanked;
+}
+
+/* The recursive workhorse (the depth is limited to HBITMAP_LEVELS)... */
+static void hb_reset_between(HBitmap *hb, int level, uint64_t start, uint64_t last)
+{
+ size_t pos = start >> BITS_PER_LEVEL;
+ size_t lastpos = last >> BITS_PER_LEVEL;
+ bool changed = false;
+ size_t i;
+
+ i = pos;
+ if (i < lastpos) {
+ uint64_t next = (start | (BITS_PER_LONG - 1)) + 1;
+
+ /* Here we need a more complex test than when setting bits. Even if
+ * something was changed, we must not blank bits in the upper level
+ * unless the lower-level word became entirely zero. So, remove pos
+ * from the upper-level range if bits remain set.
+ */
+ if (hb_reset_elem(&hb->levels[level][i], start, next - 1)) {
+ changed = true;
+ } else {
+ pos++;
+ }
+
+ for (;;) {
+ start = next;
+ next += BITS_PER_LONG;
+ if (++i == lastpos) {
+ break;
+ }
+ changed |= (hb->levels[level][i] != 0);
+ hb->levels[level][i] = 0UL;
+ }
+ }
+
+ /* Same as above, this time for lastpos. */
+ if (hb_reset_elem(&hb->levels[level][i], start, last)) {
+ changed = true;
+ } else {
+ lastpos--;
+ }
+
+ if (level > 0 && changed) {
+ hb_reset_between(hb, level - 1, pos, lastpos);
+ }
+}
+
+void hbitmap_reset(HBitmap *hb, uint64_t start, uint64_t count)
+{
+ /* Compute range in the last layer. */
+ uint64_t last = start + count - 1;
+
+ trace_hbitmap_reset(hb, start, count,
+ start >> hb->granularity, last >> hb->granularity);
+
+ start >>= hb->granularity;
+ last >>= hb->granularity;
+
+ hb->count -= hb_count_between(hb, start, last);
+ hb_reset_between(hb, HBITMAP_LEVELS - 1, start, last);
+}
+
+bool hbitmap_get(const HBitmap *hb, uint64_t item)
+{
+ /* Compute position and bit in the last layer. */
+ uint64_t pos = item >> hb->granularity;
+ unsigned long bit = 1UL << (pos & (BITS_PER_LONG - 1));
+
+ return (hb->levels[HBITMAP_LEVELS - 1][pos >> BITS_PER_LEVEL] & bit) != 0;
+}
+
+void hbitmap_free(HBitmap *hb)
+{
+ unsigned i;
+ for (i = HBITMAP_LEVELS; i-- > 0; ) {
+ g_free(hb->levels[i]);
+ }
+ g_free(hb);
+}
+
+HBitmap *hbitmap_alloc(uint64_t size, int granularity)
+{
+ HBitmap *hb = g_malloc0(sizeof (struct HBitmap));
+ unsigned i;
+
+ assert(granularity >= 0 && granularity < 64);
+ size = (size + (1ULL << granularity) - 1) >> granularity;
+ assert(size <= ((uint64_t)1 << HBITMAP_LOG_MAX_SIZE));
+
+ hb->size = size;
+ hb->granularity = granularity;
+ for (i = HBITMAP_LEVELS; i-- > 0; ) {
+ size = MAX((size + BITS_PER_LONG - 1) >> BITS_PER_LEVEL, 1);
+ hb->levels[i] = g_malloc0(size * sizeof(unsigned long));
+ }
+
+ /* We necessarily have free bits in level 0 due to the definition
+ * of HBITMAP_LEVELS, so use one for a sentinel. This speeds up
+ * hbitmap_iter_skip_words.
+ */
+ assert(size == 1);
+ hb->levels[0][0] |= 1UL << (BITS_PER_LONG - 1);
+ return hb;
+}
diff --git a/contrib/qemu/util/hexdump.c b/contrib/qemu/util/hexdump.c
new file mode 100644
index 00000000000..969b3406c07
--- /dev/null
+++ b/contrib/qemu/util/hexdump.c
@@ -0,0 +1,37 @@
+/*
+ * Helper to hexdump a buffer
+ *
+ * Copyright (c) 2013 Red Hat, Inc.
+ * Copyright (c) 2013 Gerd Hoffmann <kraxel@redhat.com>
+ * Copyright (c) 2013 Peter Crosthwaite <peter.crosthwaite@xilinx.com>
+ * Copyright (c) 2013 Xilinx, Inc
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu-common.h"
+
+void qemu_hexdump(const char *buf, FILE *fp, const char *prefix, size_t size)
+{
+ unsigned int b;
+
+ for (b = 0; b < size; b++) {
+ if ((b % 16) == 0) {
+ fprintf(fp, "%s: %04x:", prefix, b);
+ }
+ if ((b % 4) == 0) {
+ fprintf(fp, " ");
+ }
+ fprintf(fp, " %02x", (unsigned char)buf[b]);
+ if ((b % 16) == 15) {
+ fprintf(fp, "\n");
+ }
+ }
+ if ((b % 16) != 0) {
+ fprintf(fp, "\n");
+ }
+}
diff --git a/contrib/qemu/util/iov.c b/contrib/qemu/util/iov.c
new file mode 100644
index 00000000000..cc6e837c836
--- /dev/null
+++ b/contrib/qemu/util/iov.c
@@ -0,0 +1,426 @@
+/*
+ * Helpers for getting linearized buffers from iov / filling buffers into iovs
+ *
+ * Copyright IBM, Corp. 2007, 2008
+ * Copyright (C) 2010 Red Hat, Inc.
+ *
+ * Author(s):
+ * Anthony Liguori <aliguori@us.ibm.com>
+ * Amit Shah <amit.shah@redhat.com>
+ * Michael Tokarev <mjt@tls.msk.ru>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu/iov.h"
+
+#ifdef _WIN32
+# include <windows.h>
+# include <winsock2.h>
+#else
+# include <sys/types.h>
+# include <sys/socket.h>
+#endif
+
+size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt,
+ size_t offset, const void *buf, size_t bytes)
+{
+ size_t done;
+ unsigned int i;
+ for (i = 0, done = 0; (offset || done < bytes) && i < iov_cnt; i++) {
+ if (offset < iov[i].iov_len) {
+ size_t len = MIN(iov[i].iov_len - offset, bytes - done);
+ memcpy(iov[i].iov_base + offset, buf + done, len);
+ done += len;
+ offset = 0;
+ } else {
+ offset -= iov[i].iov_len;
+ }
+ }
+ assert(offset == 0);
+ return done;
+}
+
+size_t iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt,
+ size_t offset, void *buf, size_t bytes)
+{
+ size_t done;
+ unsigned int i;
+ for (i = 0, done = 0; (offset || done < bytes) && i < iov_cnt; i++) {
+ if (offset < iov[i].iov_len) {
+ size_t len = MIN(iov[i].iov_len - offset, bytes - done);
+ memcpy(buf + done, iov[i].iov_base + offset, len);
+ done += len;
+ offset = 0;
+ } else {
+ offset -= iov[i].iov_len;
+ }
+ }
+ assert(offset == 0);
+ return done;
+}
+
+size_t iov_memset(const struct iovec *iov, const unsigned int iov_cnt,
+ size_t offset, int fillc, size_t bytes)
+{
+ size_t done;
+ unsigned int i;
+ for (i = 0, done = 0; (offset || done < bytes) && i < iov_cnt; i++) {
+ if (offset < iov[i].iov_len) {
+ size_t len = MIN(iov[i].iov_len - offset, bytes - done);
+ memset(iov[i].iov_base + offset, fillc, len);
+ done += len;
+ offset = 0;
+ } else {
+ offset -= iov[i].iov_len;
+ }
+ }
+ assert(offset == 0);
+ return done;
+}
+
+size_t iov_size(const struct iovec *iov, const unsigned int iov_cnt)
+{
+ size_t len;
+ unsigned int i;
+
+ len = 0;
+ for (i = 0; i < iov_cnt; i++) {
+ len += iov[i].iov_len;
+ }
+ return len;
+}
+
+/* helper function for iov_send_recv() */
+static ssize_t
+do_send_recv(int sockfd, struct iovec *iov, unsigned iov_cnt, bool do_send)
+{
+#ifdef CONFIG_POSIX
+ ssize_t ret;
+ struct msghdr msg;
+ memset(&msg, 0, sizeof(msg));
+ msg.msg_iov = iov;
+ msg.msg_iovlen = iov_cnt;
+ do {
+ ret = do_send
+ ? sendmsg(sockfd, &msg, 0)
+ : recvmsg(sockfd, &msg, 0);
+ } while (ret < 0 && errno == EINTR);
+ return ret;
+#else
+ /* else send piece-by-piece */
+ /*XXX Note: windows has WSASend() and WSARecv() */
+ unsigned i = 0;
+ ssize_t ret = 0;
+ while (i < iov_cnt) {
+ ssize_t r = do_send
+ ? send(sockfd, iov[i].iov_base, iov[i].iov_len, 0)
+ : recv(sockfd, iov[i].iov_base, iov[i].iov_len, 0);
+ if (r > 0) {
+ ret += r;
+ } else if (!r) {
+ break;
+ } else if (errno == EINTR) {
+ continue;
+ } else {
+ /* else it is some "other" error,
+ * only return if there was no data processed. */
+ if (ret == 0) {
+ ret = -1;
+ }
+ break;
+ }
+ i++;
+ }
+ return ret;
+#endif
+}
+
+ssize_t iov_send_recv(int sockfd, struct iovec *iov, unsigned iov_cnt,
+ size_t offset, size_t bytes,
+ bool do_send)
+{
+ ssize_t total = 0;
+ ssize_t ret;
+ size_t orig_len, tail;
+ unsigned niov;
+
+ while (bytes > 0) {
+ /* Find the start position, skipping `offset' bytes:
+ * first, skip all full-sized vector elements, */
+ for (niov = 0; niov < iov_cnt && offset >= iov[niov].iov_len; ++niov) {
+ offset -= iov[niov].iov_len;
+ }
+
+ /* niov == iov_cnt would only be valid if bytes == 0, which
+ * we already ruled out in the loop condition. */
+ assert(niov < iov_cnt);
+ iov += niov;
+ iov_cnt -= niov;
+
+ if (offset) {
+ /* second, skip `offset' bytes from the (now) first element,
+ * undo it on exit */
+ iov[0].iov_base += offset;
+ iov[0].iov_len -= offset;
+ }
+ /* Find the end position skipping `bytes' bytes: */
+ /* first, skip all full-sized elements */
+ tail = bytes;
+ for (niov = 0; niov < iov_cnt && iov[niov].iov_len <= tail; ++niov) {
+ tail -= iov[niov].iov_len;
+ }
+ if (tail) {
+ /* second, fixup the last element, and remember the original
+ * length */
+ assert(niov < iov_cnt);
+ assert(iov[niov].iov_len > tail);
+ orig_len = iov[niov].iov_len;
+ iov[niov++].iov_len = tail;
+ }
+
+ ret = do_send_recv(sockfd, iov, niov, do_send);
+
+ /* Undo the changes above before checking for errors */
+ if (tail) {
+ iov[niov-1].iov_len = orig_len;
+ }
+ if (offset) {
+ iov[0].iov_base -= offset;
+ iov[0].iov_len += offset;
+ }
+
+ if (ret < 0) {
+ assert(errno != EINTR);
+ if (errno == EAGAIN && total > 0) {
+ return total;
+ }
+ return -1;
+ }
+
+ /* Prepare for the next iteration */
+ offset += ret;
+ total += ret;
+ bytes -= ret;
+ }
+
+ return total;
+}
+
+
+void iov_hexdump(const struct iovec *iov, const unsigned int iov_cnt,
+ FILE *fp, const char *prefix, size_t limit)
+{
+ int v;
+ size_t size = 0;
+ char *buf;
+
+ for (v = 0; v < iov_cnt; v++) {
+ size += iov[v].iov_len;
+ }
+ size = size > limit ? limit : size;
+ buf = g_malloc(size);
+ iov_to_buf(iov, iov_cnt, 0, buf, size);
+ qemu_hexdump(buf, fp, prefix, size);
+ g_free(buf);
+}
+
+unsigned iov_copy(struct iovec *dst_iov, unsigned int dst_iov_cnt,
+ const struct iovec *iov, unsigned int iov_cnt,
+ size_t offset, size_t bytes)
+{
+ size_t len;
+ unsigned int i, j;
+ for (i = 0, j = 0; i < iov_cnt && j < dst_iov_cnt && bytes; i++) {
+ if (offset >= iov[i].iov_len) {
+ offset -= iov[i].iov_len;
+ continue;
+ }
+ len = MIN(bytes, iov[i].iov_len - offset);
+
+ dst_iov[j].iov_base = iov[i].iov_base + offset;
+ dst_iov[j].iov_len = len;
+ j++;
+ bytes -= len;
+ offset = 0;
+ }
+ assert(offset == 0);
+ return j;
+}
+
+/* io vectors */
+
+void qemu_iovec_init(QEMUIOVector *qiov, int alloc_hint)
+{
+ qiov->iov = g_malloc(alloc_hint * sizeof(struct iovec));
+ qiov->niov = 0;
+ qiov->nalloc = alloc_hint;
+ qiov->size = 0;
+}
+
+void qemu_iovec_init_external(QEMUIOVector *qiov, struct iovec *iov, int niov)
+{
+ int i;
+
+ qiov->iov = iov;
+ qiov->niov = niov;
+ qiov->nalloc = -1;
+ qiov->size = 0;
+ for (i = 0; i < niov; i++)
+ qiov->size += iov[i].iov_len;
+}
+
+void qemu_iovec_add(QEMUIOVector *qiov, void *base, size_t len)
+{
+ assert(qiov->nalloc != -1);
+
+ if (qiov->niov == qiov->nalloc) {
+ qiov->nalloc = 2 * qiov->nalloc + 1;
+ qiov->iov = g_realloc(qiov->iov, qiov->nalloc * sizeof(struct iovec));
+ }
+ qiov->iov[qiov->niov].iov_base = base;
+ qiov->iov[qiov->niov].iov_len = len;
+ qiov->size += len;
+ ++qiov->niov;
+}
+
+/*
+ * Concatenates (partial) iovecs from src_iov to the end of dst.
+ * It starts copying after skipping `soffset' bytes at the
+ * beginning of src and adds individual vectors from src to
+ * dst copies up to `sbytes' bytes total, or up to the end
+ * of src_iov if it comes first. This way, it is okay to specify
+ * very large value for `sbytes' to indicate "up to the end
+ * of src".
+ * Only vector pointers are processed, not the actual data buffers.
+ */
+void qemu_iovec_concat_iov(QEMUIOVector *dst,
+ struct iovec *src_iov, unsigned int src_cnt,
+ size_t soffset, size_t sbytes)
+{
+ int i;
+ size_t done;
+
+ if (!sbytes) {
+ return;
+ }
+ assert(dst->nalloc != -1);
+ for (i = 0, done = 0; done < sbytes && i < src_cnt; i++) {
+ if (soffset < src_iov[i].iov_len) {
+ size_t len = MIN(src_iov[i].iov_len - soffset, sbytes - done);
+ qemu_iovec_add(dst, src_iov[i].iov_base + soffset, len);
+ done += len;
+ soffset = 0;
+ } else {
+ soffset -= src_iov[i].iov_len;
+ }
+ }
+ assert(soffset == 0); /* offset beyond end of src */
+}
+
+/*
+ * Concatenates (partial) iovecs from src to the end of dst.
+ * It starts copying after skipping `soffset' bytes at the
+ * beginning of src and adds individual vectors from src to
+ * dst copies up to `sbytes' bytes total, or up to the end
+ * of src if it comes first. This way, it is okay to specify
+ * very large value for `sbytes' to indicate "up to the end
+ * of src".
+ * Only vector pointers are processed, not the actual data buffers.
+ */
+void qemu_iovec_concat(QEMUIOVector *dst,
+ QEMUIOVector *src, size_t soffset, size_t sbytes)
+{
+ qemu_iovec_concat_iov(dst, src->iov, src->niov, soffset, sbytes);
+}
+
+void qemu_iovec_destroy(QEMUIOVector *qiov)
+{
+ assert(qiov->nalloc != -1);
+
+ qemu_iovec_reset(qiov);
+ g_free(qiov->iov);
+ qiov->nalloc = 0;
+ qiov->iov = NULL;
+}
+
+void qemu_iovec_reset(QEMUIOVector *qiov)
+{
+ assert(qiov->nalloc != -1);
+
+ qiov->niov = 0;
+ qiov->size = 0;
+}
+
+size_t qemu_iovec_to_buf(QEMUIOVector *qiov, size_t offset,
+ void *buf, size_t bytes)
+{
+ return iov_to_buf(qiov->iov, qiov->niov, offset, buf, bytes);
+}
+
+size_t qemu_iovec_from_buf(QEMUIOVector *qiov, size_t offset,
+ const void *buf, size_t bytes)
+{
+ return iov_from_buf(qiov->iov, qiov->niov, offset, buf, bytes);
+}
+
+size_t qemu_iovec_memset(QEMUIOVector *qiov, size_t offset,
+ int fillc, size_t bytes)
+{
+ return iov_memset(qiov->iov, qiov->niov, offset, fillc, bytes);
+}
+
+size_t iov_discard_front(struct iovec **iov, unsigned int *iov_cnt,
+ size_t bytes)
+{
+ size_t total = 0;
+ struct iovec *cur;
+
+ for (cur = *iov; *iov_cnt > 0; cur++) {
+ if (cur->iov_len > bytes) {
+ cur->iov_base += bytes;
+ cur->iov_len -= bytes;
+ total += bytes;
+ break;
+ }
+
+ bytes -= cur->iov_len;
+ total += cur->iov_len;
+ *iov_cnt -= 1;
+ }
+
+ *iov = cur;
+ return total;
+}
+
+size_t iov_discard_back(struct iovec *iov, unsigned int *iov_cnt,
+ size_t bytes)
+{
+ size_t total = 0;
+ struct iovec *cur;
+
+ if (*iov_cnt == 0) {
+ return 0;
+ }
+
+ cur = iov + (*iov_cnt - 1);
+
+ while (*iov_cnt > 0) {
+ if (cur->iov_len > bytes) {
+ cur->iov_len -= bytes;
+ total += bytes;
+ break;
+ }
+
+ bytes -= cur->iov_len;
+ total += cur->iov_len;
+ cur--;
+ *iov_cnt -= 1;
+ }
+
+ return total;
+}
diff --git a/contrib/qemu/util/module.c b/contrib/qemu/util/module.c
new file mode 100644
index 00000000000..7acc33d076a
--- /dev/null
+++ b/contrib/qemu/util/module.c
@@ -0,0 +1,81 @@
+/*
+ * QEMU Module Infrastructure
+ *
+ * Copyright IBM, Corp. 2009
+ *
+ * Authors:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu-common.h"
+#include "qemu/queue.h"
+#include "qemu/module.h"
+
+typedef struct ModuleEntry
+{
+ void (*init)(void);
+ QTAILQ_ENTRY(ModuleEntry) node;
+} ModuleEntry;
+
+typedef QTAILQ_HEAD(, ModuleEntry) ModuleTypeList;
+
+static ModuleTypeList init_type_list[MODULE_INIT_MAX];
+
+static void init_types(void)
+{
+ static int inited;
+ int i;
+
+ if (inited) {
+ return;
+ }
+
+ for (i = 0; i < MODULE_INIT_MAX; i++) {
+ QTAILQ_INIT(&init_type_list[i]);
+ }
+
+ inited = 1;
+}
+
+
+static ModuleTypeList *find_type(module_init_type type)
+{
+ ModuleTypeList *l;
+
+ init_types();
+
+ l = &init_type_list[type];
+
+ return l;
+}
+
+void register_module_init(void (*fn)(void), module_init_type type)
+{
+ ModuleEntry *e;
+ ModuleTypeList *l;
+
+ e = g_malloc0(sizeof(*e));
+ e->init = fn;
+
+ l = find_type(type);
+
+ QTAILQ_INSERT_TAIL(l, e, node);
+}
+
+void module_call_init(module_init_type type)
+{
+ ModuleTypeList *l;
+ ModuleEntry *e;
+
+ l = find_type(type);
+
+ QTAILQ_FOREACH(e, l, node) {
+ e->init();
+ }
+}
diff --git a/contrib/qemu/util/oslib-posix.c b/contrib/qemu/util/oslib-posix.c
new file mode 100644
index 00000000000..3dc8b1b0743
--- /dev/null
+++ b/contrib/qemu/util/oslib-posix.c
@@ -0,0 +1,243 @@
+/*
+ * os-posix-lib.c
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ * Copyright (c) 2010 Red Hat, Inc.
+ *
+ * QEMU library functions on POSIX which are shared between QEMU and
+ * the QEMU tools.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+/* The following block of code temporarily renames the daemon() function so the
+ compiler does not see the warning associated with it in stdlib.h on OSX */
+#ifdef __APPLE__
+#define daemon qemu_fake_daemon_function
+#include <stdlib.h>
+#undef daemon
+extern int daemon(int, int);
+#endif
+
+#if defined(__linux__) && (defined(__x86_64__) || defined(__arm__))
+ /* Use 2 MiB alignment so transparent hugepages can be used by KVM.
+ Valgrind does not support alignments larger than 1 MiB,
+ therefore we need special code which handles running on Valgrind. */
+# define QEMU_VMALLOC_ALIGN (512 * 4096)
+#elif defined(__linux__) && defined(__s390x__)
+ /* Use 1 MiB (segment size) alignment so gmap can be used by KVM. */
+# define QEMU_VMALLOC_ALIGN (256 * 4096)
+#else
+# define QEMU_VMALLOC_ALIGN getpagesize()
+#endif
+
+#include <glib/gprintf.h>
+
+#include "config-host.h"
+#include "sysemu/sysemu.h"
+#include "trace.h"
+#include "qemu/sockets.h"
+#include <sys/mman.h>
+
+#ifdef CONFIG_LINUX
+#include <sys/syscall.h>
+#endif
+
+int qemu_get_thread_id(void)
+{
+#if defined(__linux__)
+ return syscall(SYS_gettid);
+#else
+ return getpid();
+#endif
+}
+
+int qemu_daemon(int nochdir, int noclose)
+{
+ return daemon(nochdir, noclose);
+}
+
+void *qemu_oom_check(void *ptr)
+{
+ if (ptr == NULL) {
+ fprintf(stderr, "Failed to allocate memory: %s\n", strerror(errno));
+ abort();
+ }
+ return ptr;
+}
+
+void *qemu_memalign(size_t alignment, size_t size)
+{
+ void *ptr;
+#if defined(_POSIX_C_SOURCE) && !defined(__sun__)
+ int ret;
+ ret = posix_memalign(&ptr, alignment, size);
+ if (ret != 0) {
+ fprintf(stderr, "Failed to allocate %zu B: %s\n",
+ size, strerror(ret));
+ abort();
+ }
+#elif defined(CONFIG_BSD)
+ ptr = qemu_oom_check(valloc(size));
+#else
+ ptr = qemu_oom_check(memalign(alignment, size));
+#endif
+ trace_qemu_memalign(alignment, size, ptr);
+ return ptr;
+}
+
+/* alloc shared memory pages */
+void *qemu_anon_ram_alloc(size_t size)
+{
+ size_t align = QEMU_VMALLOC_ALIGN;
+ size_t total = size + align - getpagesize();
+ void *ptr = mmap(0, total, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;
+
+ if (ptr == MAP_FAILED) {
+ fprintf(stderr, "Failed to allocate %zu B: %s\n",
+ size, strerror(errno));
+ abort();
+ }
+
+ ptr += offset;
+ total -= offset;
+
+ if (offset > 0) {
+ munmap(ptr - offset, offset);
+ }
+ if (total > size) {
+ munmap(ptr + size, total - size);
+ }
+
+ trace_qemu_anon_ram_alloc(size, ptr);
+ return ptr;
+}
+
+void qemu_vfree(void *ptr)
+{
+ trace_qemu_vfree(ptr);
+ free(ptr);
+}
+
+void qemu_anon_ram_free(void *ptr, size_t size)
+{
+ trace_qemu_anon_ram_free(ptr, size);
+ if (ptr) {
+ munmap(ptr, size);
+ }
+}
+
+void qemu_set_block(int fd)
+{
+ int f;
+ f = fcntl(fd, F_GETFL);
+ fcntl(fd, F_SETFL, f & ~O_NONBLOCK);
+}
+
+void qemu_set_nonblock(int fd)
+{
+ int f;
+ f = fcntl(fd, F_GETFL);
+ fcntl(fd, F_SETFL, f | O_NONBLOCK);
+}
+
+void qemu_set_cloexec(int fd)
+{
+ int f;
+ f = fcntl(fd, F_GETFD);
+ fcntl(fd, F_SETFD, f | FD_CLOEXEC);
+}
+
+/*
+ * Creates a pipe with FD_CLOEXEC set on both file descriptors
+ */
+int qemu_pipe(int pipefd[2])
+{
+ int ret;
+
+#ifdef CONFIG_PIPE2
+ ret = pipe2(pipefd, O_CLOEXEC);
+ if (ret != -1 || errno != ENOSYS) {
+ return ret;
+ }
+#endif
+ ret = pipe(pipefd);
+ if (ret == 0) {
+ qemu_set_cloexec(pipefd[0]);
+ qemu_set_cloexec(pipefd[1]);
+ }
+
+ return ret;
+}
+
+int qemu_utimens(const char *path, const struct timespec *times)
+{
+ struct timeval tv[2], tv_now;
+ struct stat st;
+ int i;
+#ifdef CONFIG_UTIMENSAT
+ int ret;
+
+ ret = utimensat(AT_FDCWD, path, times, AT_SYMLINK_NOFOLLOW);
+ if (ret != -1 || errno != ENOSYS) {
+ return ret;
+ }
+#endif
+ /* Fallback: use utimes() instead of utimensat() */
+
+ /* happy if special cases */
+ if (times[0].tv_nsec == UTIME_OMIT && times[1].tv_nsec == UTIME_OMIT) {
+ return 0;
+ }
+ if (times[0].tv_nsec == UTIME_NOW && times[1].tv_nsec == UTIME_NOW) {
+ return utimes(path, NULL);
+ }
+
+ /* prepare for hard cases */
+ if (times[0].tv_nsec == UTIME_NOW || times[1].tv_nsec == UTIME_NOW) {
+ gettimeofday(&tv_now, NULL);
+ }
+ if (times[0].tv_nsec == UTIME_OMIT || times[1].tv_nsec == UTIME_OMIT) {
+ stat(path, &st);
+ }
+
+ for (i = 0; i < 2; i++) {
+ if (times[i].tv_nsec == UTIME_NOW) {
+ tv[i].tv_sec = tv_now.tv_sec;
+ tv[i].tv_usec = tv_now.tv_usec;
+ } else if (times[i].tv_nsec == UTIME_OMIT) {
+ tv[i].tv_sec = (i == 0) ? st.st_atime : st.st_mtime;
+ tv[i].tv_usec = 0;
+ } else {
+ tv[i].tv_sec = times[i].tv_sec;
+ tv[i].tv_usec = times[i].tv_nsec / 1000;
+ }
+ }
+
+ return utimes(path, &tv[0]);
+}
+
+char *
+qemu_get_local_state_pathname(const char *relative_pathname)
+{
+ return g_strdup_printf("%s/%s", CONFIG_QEMU_LOCALSTATEDIR,
+ relative_pathname);
+}
diff --git a/contrib/qemu/util/qemu-error.c b/contrib/qemu/util/qemu-error.c
new file mode 100644
index 00000000000..fec02c60754
--- /dev/null
+++ b/contrib/qemu/util/qemu-error.c
@@ -0,0 +1,225 @@
+/*
+ * Error reporting
+ *
+ * Copyright (C) 2010 Red Hat Inc.
+ *
+ * Authors:
+ * Markus Armbruster <armbru@redhat.com>,
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include <stdio.h>
+#include "monitor/monitor.h"
+
+/*
+ * Print to current monitor if we have one, else to stderr.
+ * TODO should return int, so callers can calculate width, but that
+ * requires surgery to monitor_vprintf(). Left for another day.
+ */
+void error_vprintf(const char *fmt, va_list ap)
+{
+ if (cur_mon) {
+ monitor_vprintf(cur_mon, fmt, ap);
+ } else {
+ vfprintf(stderr, fmt, ap);
+ }
+}
+
+/*
+ * Print to current monitor if we have one, else to stderr.
+ * TODO just like error_vprintf()
+ */
+void error_printf(const char *fmt, ...)
+{
+ va_list ap;
+
+ va_start(ap, fmt);
+ error_vprintf(fmt, ap);
+ va_end(ap);
+}
+
+void error_printf_unless_qmp(const char *fmt, ...)
+{
+ va_list ap;
+
+ if (!monitor_cur_is_qmp()) {
+ va_start(ap, fmt);
+ error_vprintf(fmt, ap);
+ va_end(ap);
+ }
+}
+
+static Location std_loc = {
+ .kind = LOC_NONE
+};
+static Location *cur_loc = &std_loc;
+
+/*
+ * Push location saved in LOC onto the location stack, return it.
+ * The top of that stack is the current location.
+ * Needs a matching loc_pop().
+ */
+Location *loc_push_restore(Location *loc)
+{
+ assert(!loc->prev);
+ loc->prev = cur_loc;
+ cur_loc = loc;
+ return loc;
+}
+
+/*
+ * Initialize *LOC to "nowhere", push it onto the location stack.
+ * The top of that stack is the current location.
+ * Needs a matching loc_pop().
+ * Return LOC.
+ */
+Location *loc_push_none(Location *loc)
+{
+ loc->kind = LOC_NONE;
+ loc->prev = NULL;
+ return loc_push_restore(loc);
+}
+
+/*
+ * Pop the location stack.
+ * LOC must be the current location, i.e. the top of the stack.
+ */
+Location *loc_pop(Location *loc)
+{
+ assert(cur_loc == loc && loc->prev);
+ cur_loc = loc->prev;
+ loc->prev = NULL;
+ return loc;
+}
+
+/*
+ * Save the current location in LOC, return LOC.
+ */
+Location *loc_save(Location *loc)
+{
+ *loc = *cur_loc;
+ loc->prev = NULL;
+ return loc;
+}
+
+/*
+ * Change the current location to the one saved in LOC.
+ */
+void loc_restore(Location *loc)
+{
+ Location *prev = cur_loc->prev;
+ assert(!loc->prev);
+ *cur_loc = *loc;
+ cur_loc->prev = prev;
+}
+
+/*
+ * Change the current location to "nowhere in particular".
+ */
+void loc_set_none(void)
+{
+ cur_loc->kind = LOC_NONE;
+}
+
+/*
+ * Change the current location to argument ARGV[IDX..IDX+CNT-1].
+ */
+void loc_set_cmdline(char **argv, int idx, int cnt)
+{
+ cur_loc->kind = LOC_CMDLINE;
+ cur_loc->num = cnt;
+ cur_loc->ptr = argv + idx;
+}
+
+/*
+ * Change the current location to file FNAME, line LNO.
+ */
+void loc_set_file(const char *fname, int lno)
+{
+ assert (fname || cur_loc->kind == LOC_FILE);
+ cur_loc->kind = LOC_FILE;
+ cur_loc->num = lno;
+ if (fname) {
+ cur_loc->ptr = fname;
+ }
+}
+
+static const char *progname;
+
+/*
+ * Set the program name for error_print_loc().
+ */
+void error_set_progname(const char *argv0)
+{
+ const char *p = strrchr(argv0, '/');
+ progname = p ? p + 1 : argv0;
+}
+
+const char *error_get_progname(void)
+{
+ return progname;
+}
+
+/*
+ * Print current location to current monitor if we have one, else to stderr.
+ */
+void error_print_loc(void)
+{
+ const char *sep = "";
+ int i;
+ const char *const *argp;
+
+ if (!cur_mon && progname) {
+ fprintf(stderr, "%s:", progname);
+ sep = " ";
+ }
+ switch (cur_loc->kind) {
+ case LOC_CMDLINE:
+ argp = cur_loc->ptr;
+ for (i = 0; i < cur_loc->num; i++) {
+ error_printf("%s%s", sep, argp[i]);
+ sep = " ";
+ }
+ error_printf(": ");
+ break;
+ case LOC_FILE:
+ error_printf("%s:", (const char *)cur_loc->ptr);
+ if (cur_loc->num) {
+ error_printf("%d:", cur_loc->num);
+ }
+ error_printf(" ");
+ break;
+ default:
+ error_printf("%s", sep);
+ }
+}
+
+bool enable_timestamp_msg;
+/*
+ * Print an error message to current monitor if we have one, else to stderr.
+ * Format arguments like sprintf(). The result should not contain
+ * newlines.
+ * Prepend the current location and append a newline.
+ * It's wrong to call this in a QMP monitor. Use qerror_report() there.
+ */
+void error_report(const char *fmt, ...)
+{
+ va_list ap;
+ GTimeVal tv;
+ gchar *timestr;
+
+ if (enable_timestamp_msg) {
+ g_get_current_time(&tv);
+ timestr = g_time_val_to_iso8601(&tv);
+ error_printf("%s ", timestr);
+ g_free(timestr);
+ }
+
+ error_print_loc();
+ va_start(ap, fmt);
+ error_vprintf(fmt, ap);
+ va_end(ap);
+ error_printf("\n");
+}
diff --git a/contrib/qemu/util/qemu-option.c b/contrib/qemu/util/qemu-option.c
new file mode 100644
index 00000000000..e0ef426daa0
--- /dev/null
+++ b/contrib/qemu/util/qemu-option.c
@@ -0,0 +1,1126 @@
+/*
+ * Commandline option parsing functions
+ *
+ * Copyright (c) 2003-2008 Fabrice Bellard
+ * Copyright (c) 2009 Kevin Wolf <kwolf@redhat.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "qemu-common.h"
+#include "qemu/error-report.h"
+#include "qapi/qmp/types.h"
+#include "qapi/error.h"
+#include "qapi/qmp/qerror.h"
+#include "qemu/option_int.h"
+
+/*
+ * Extracts the name of an option from the parameter string (p points at the
+ * first byte of the option name)
+ *
+ * The option name is delimited by delim (usually , or =) or the string end
+ * and is copied into buf. If the option name is longer than buf_size, it is
+ * truncated. buf is always zero terminated.
+ *
+ * The return value is the position of the delimiter/zero byte after the option
+ * name in p.
+ */
+const char *get_opt_name(char *buf, int buf_size, const char *p, char delim)
+{
+ char *q;
+
+ q = buf;
+ while (*p != '\0' && *p != delim) {
+ if (q && (q - buf) < buf_size - 1)
+ *q++ = *p;
+ p++;
+ }
+ if (q)
+ *q = '\0';
+
+ return p;
+}
+
+/*
+ * Extracts the value of an option from the parameter string p (p points at the
+ * first byte of the option value)
+ *
+ * This function is comparable to get_opt_name with the difference that the
+ * delimiter is fixed to be comma which starts a new option. To specify an
+ * option value that contains commas, double each comma.
+ */
+const char *get_opt_value(char *buf, int buf_size, const char *p)
+{
+ char *q;
+
+ q = buf;
+ while (*p != '\0') {
+ if (*p == ',') {
+ if (*(p + 1) != ',')
+ break;
+ p++;
+ }
+ if (q && (q - buf) < buf_size - 1)
+ *q++ = *p;
+ p++;
+ }
+ if (q)
+ *q = '\0';
+
+ return p;
+}
+
+int get_next_param_value(char *buf, int buf_size,
+ const char *tag, const char **pstr)
+{
+ const char *p;
+ char option[128];
+
+ p = *pstr;
+ for(;;) {
+ p = get_opt_name(option, sizeof(option), p, '=');
+ if (*p != '=')
+ break;
+ p++;
+ if (!strcmp(tag, option)) {
+ *pstr = get_opt_value(buf, buf_size, p);
+ if (**pstr == ',') {
+ (*pstr)++;
+ }
+ return strlen(buf);
+ } else {
+ p = get_opt_value(NULL, 0, p);
+ }
+ if (*p != ',')
+ break;
+ p++;
+ }
+ return 0;
+}
+
+int get_param_value(char *buf, int buf_size,
+ const char *tag, const char *str)
+{
+ return get_next_param_value(buf, buf_size, tag, &str);
+}
+
+/*
+ * Searches an option list for an option with the given name
+ */
+QEMUOptionParameter *get_option_parameter(QEMUOptionParameter *list,
+ const char *name)
+{
+ while (list && list->name) {
+ if (!strcmp(list->name, name)) {
+ return list;
+ }
+ list++;
+ }
+
+ return NULL;
+}
+
+static void parse_option_bool(const char *name, const char *value, bool *ret,
+ Error **errp)
+{
+ if (value != NULL) {
+ if (!strcmp(value, "on")) {
+ *ret = 1;
+ } else if (!strcmp(value, "off")) {
+ *ret = 0;
+ } else {
+ error_set(errp,QERR_INVALID_PARAMETER_VALUE, name, "'on' or 'off'");
+ }
+ } else {
+ *ret = 1;
+ }
+}
+
+static void parse_option_number(const char *name, const char *value,
+ uint64_t *ret, Error **errp)
+{
+ char *postfix;
+ uint64_t number;
+
+ if (value != NULL) {
+ number = strtoull(value, &postfix, 0);
+ if (*postfix != '\0') {
+ error_set(errp, QERR_INVALID_PARAMETER_VALUE, name, "a number");
+ return;
+ }
+ *ret = number;
+ } else {
+ error_set(errp, QERR_INVALID_PARAMETER_VALUE, name, "a number");
+ }
+}
+
+static void parse_option_size(const char *name, const char *value,
+ uint64_t *ret, Error **errp)
+{
+ char *postfix;
+ double sizef;
+
+ if (value != NULL) {
+ sizef = strtod(value, &postfix);
+ switch (*postfix) {
+ case 'T':
+ sizef *= 1024;
+ /* fall through */
+ case 'G':
+ sizef *= 1024;
+ /* fall through */
+ case 'M':
+ sizef *= 1024;
+ /* fall through */
+ case 'K':
+ case 'k':
+ sizef *= 1024;
+ /* fall through */
+ case 'b':
+ case '\0':
+ *ret = (uint64_t) sizef;
+ break;
+ default:
+ error_set(errp, QERR_INVALID_PARAMETER_VALUE, name, "a size");
+#if 0 /* conversion from qerror_report() to error_set() broke this: */
+ error_printf_unless_qmp("You may use k, M, G or T suffixes for "
+ "kilobytes, megabytes, gigabytes and terabytes.\n");
+#endif
+ return;
+ }
+ } else {
+ error_set(errp, QERR_INVALID_PARAMETER_VALUE, name, "a size");
+ }
+}
+
+/*
+ * Sets the value of a parameter in a given option list. The parsing of the
+ * value depends on the type of option:
+ *
+ * OPT_FLAG (uses value.n):
+ * If no value is given, the flag is set to 1.
+ * Otherwise the value must be "on" (set to 1) or "off" (set to 0)
+ *
+ * OPT_STRING (uses value.s):
+ * value is strdup()ed and assigned as option value
+ *
+ * OPT_SIZE (uses value.n):
+ * The value is converted to an integer. Suffixes for kilobytes etc. are
+ * allowed (powers of 1024).
+ *
+ * Returns 0 on succes, -1 in error cases
+ */
+int set_option_parameter(QEMUOptionParameter *list, const char *name,
+ const char *value)
+{
+ bool flag;
+ Error *local_err = NULL;
+
+ // Find a matching parameter
+ list = get_option_parameter(list, name);
+ if (list == NULL) {
+ fprintf(stderr, "Unknown option '%s'\n", name);
+ return -1;
+ }
+
+ // Process parameter
+ switch (list->type) {
+ case OPT_FLAG:
+ parse_option_bool(name, value, &flag, &local_err);
+ if (!error_is_set(&local_err)) {
+ list->value.n = flag;
+ }
+ break;
+
+ case OPT_STRING:
+ if (value != NULL) {
+ list->value.s = g_strdup(value);
+ } else {
+ fprintf(stderr, "Option '%s' needs a parameter\n", name);
+ return -1;
+ }
+ break;
+
+ case OPT_SIZE:
+ parse_option_size(name, value, &list->value.n, &local_err);
+ break;
+
+ default:
+ fprintf(stderr, "Bug: Option '%s' has an unknown type\n", name);
+ return -1;
+ }
+
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * Sets the given parameter to an integer instead of a string.
+ * This function cannot be used to set string options.
+ *
+ * Returns 0 on success, -1 in error cases
+ */
+int set_option_parameter_int(QEMUOptionParameter *list, const char *name,
+ uint64_t value)
+{
+ // Find a matching parameter
+ list = get_option_parameter(list, name);
+ if (list == NULL) {
+ fprintf(stderr, "Unknown option '%s'\n", name);
+ return -1;
+ }
+
+ // Process parameter
+ switch (list->type) {
+ case OPT_FLAG:
+ case OPT_NUMBER:
+ case OPT_SIZE:
+ list->value.n = value;
+ break;
+
+ default:
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * Frees a option list. If it contains strings, the strings are freed as well.
+ */
+void free_option_parameters(QEMUOptionParameter *list)
+{
+ QEMUOptionParameter *cur = list;
+
+ while (cur && cur->name) {
+ if (cur->type == OPT_STRING) {
+ g_free(cur->value.s);
+ }
+ cur++;
+ }
+
+ g_free(list);
+}
+
+/*
+ * Count valid options in list
+ */
+static size_t count_option_parameters(QEMUOptionParameter *list)
+{
+ size_t num_options = 0;
+
+ while (list && list->name) {
+ num_options++;
+ list++;
+ }
+
+ return num_options;
+}
+
+/*
+ * Append an option list (list) to an option list (dest).
+ *
+ * If dest is NULL, a new copy of list is created.
+ *
+ * Returns a pointer to the first element of dest (or the newly allocated copy)
+ */
+QEMUOptionParameter *append_option_parameters(QEMUOptionParameter *dest,
+ QEMUOptionParameter *list)
+{
+ size_t num_options, num_dest_options;
+
+ num_options = count_option_parameters(dest);
+ num_dest_options = num_options;
+
+ num_options += count_option_parameters(list);
+
+ dest = g_realloc(dest, (num_options + 1) * sizeof(QEMUOptionParameter));
+ dest[num_dest_options].name = NULL;
+
+ while (list && list->name) {
+ if (get_option_parameter(dest, list->name) == NULL) {
+ dest[num_dest_options++] = *list;
+ dest[num_dest_options].name = NULL;
+ }
+ list++;
+ }
+
+ return dest;
+}
+
+/*
+ * Parses a parameter string (param) into an option list (dest).
+ *
+ * list is the template option list. If dest is NULL, a new copy of list is
+ * created. If list is NULL, this function fails.
+ *
+ * A parameter string consists of one or more parameters, separated by commas.
+ * Each parameter consists of its name and possibly of a value. In the latter
+ * case, the value is delimited by an = character. To specify a value which
+ * contains commas, double each comma so it won't be recognized as the end of
+ * the parameter.
+ *
+ * For more details of the parsing see above.
+ *
+ * Returns a pointer to the first element of dest (or the newly allocated copy)
+ * or NULL in error cases
+ */
+QEMUOptionParameter *parse_option_parameters(const char *param,
+ QEMUOptionParameter *list, QEMUOptionParameter *dest)
+{
+ QEMUOptionParameter *allocated = NULL;
+ char name[256];
+ char value[256];
+ char *param_delim, *value_delim;
+ char next_delim;
+
+ if (list == NULL) {
+ return NULL;
+ }
+
+ if (dest == NULL) {
+ dest = allocated = append_option_parameters(NULL, list);
+ }
+
+ while (*param) {
+
+ // Find parameter name and value in the string
+ param_delim = strchr(param, ',');
+ value_delim = strchr(param, '=');
+
+ if (value_delim && (value_delim < param_delim || !param_delim)) {
+ next_delim = '=';
+ } else {
+ next_delim = ',';
+ value_delim = NULL;
+ }
+
+ param = get_opt_name(name, sizeof(name), param, next_delim);
+ if (value_delim) {
+ param = get_opt_value(value, sizeof(value), param + 1);
+ }
+ if (*param != '\0') {
+ param++;
+ }
+
+ // Set the parameter
+ if (set_option_parameter(dest, name, value_delim ? value : NULL)) {
+ goto fail;
+ }
+ }
+
+ return dest;
+
+fail:
+ // Only free the list if it was newly allocated
+ free_option_parameters(allocated);
+ return NULL;
+}
+
+/*
+ * Prints all options of a list that have a value to stdout
+ */
+void print_option_parameters(QEMUOptionParameter *list)
+{
+ while (list && list->name) {
+ switch (list->type) {
+ case OPT_STRING:
+ if (list->value.s != NULL) {
+ printf("%s='%s' ", list->name, list->value.s);
+ }
+ break;
+ case OPT_FLAG:
+ printf("%s=%s ", list->name, list->value.n ? "on" : "off");
+ break;
+ case OPT_SIZE:
+ case OPT_NUMBER:
+ printf("%s=%" PRId64 " ", list->name, list->value.n);
+ break;
+ default:
+ printf("%s=(unknown type) ", list->name);
+ break;
+ }
+ list++;
+ }
+}
+
+/*
+ * Prints an overview of all available options
+ */
+void print_option_help(QEMUOptionParameter *list)
+{
+ printf("Supported options:\n");
+ while (list && list->name) {
+ printf("%-16s %s\n", list->name,
+ list->help ? list->help : "No description available");
+ list++;
+ }
+}
+
+/* ------------------------------------------------------------------ */
+
+static QemuOpt *qemu_opt_find(QemuOpts *opts, const char *name)
+{
+ QemuOpt *opt;
+
+ QTAILQ_FOREACH_REVERSE(opt, &opts->head, QemuOptHead, next) {
+ if (strcmp(opt->name, name) != 0)
+ continue;
+ return opt;
+ }
+ return NULL;
+}
+
+const char *qemu_opt_get(QemuOpts *opts, const char *name)
+{
+ QemuOpt *opt = qemu_opt_find(opts, name);
+ return opt ? opt->str : NULL;
+}
+
+bool qemu_opt_has_help_opt(QemuOpts *opts)
+{
+ QemuOpt *opt;
+
+ QTAILQ_FOREACH_REVERSE(opt, &opts->head, QemuOptHead, next) {
+ if (is_help_option(opt->name)) {
+ return true;
+ }
+ }
+ return false;
+}
+
+bool qemu_opt_get_bool(QemuOpts *opts, const char *name, bool defval)
+{
+ QemuOpt *opt = qemu_opt_find(opts, name);
+
+ if (opt == NULL)
+ return defval;
+ assert(opt->desc && opt->desc->type == QEMU_OPT_BOOL);
+ return opt->value.boolean;
+}
+
+uint64_t qemu_opt_get_number(QemuOpts *opts, const char *name, uint64_t defval)
+{
+ QemuOpt *opt = qemu_opt_find(opts, name);
+
+ if (opt == NULL)
+ return defval;
+ assert(opt->desc && opt->desc->type == QEMU_OPT_NUMBER);
+ return opt->value.uint;
+}
+
+uint64_t qemu_opt_get_size(QemuOpts *opts, const char *name, uint64_t defval)
+{
+ QemuOpt *opt = qemu_opt_find(opts, name);
+
+ if (opt == NULL)
+ return defval;
+ assert(opt->desc && opt->desc->type == QEMU_OPT_SIZE);
+ return opt->value.uint;
+}
+
+static void qemu_opt_parse(QemuOpt *opt, Error **errp)
+{
+ if (opt->desc == NULL)
+ return;
+
+ switch (opt->desc->type) {
+ case QEMU_OPT_STRING:
+ /* nothing */
+ return;
+ case QEMU_OPT_BOOL:
+ parse_option_bool(opt->name, opt->str, &opt->value.boolean, errp);
+ break;
+ case QEMU_OPT_NUMBER:
+ parse_option_number(opt->name, opt->str, &opt->value.uint, errp);
+ break;
+ case QEMU_OPT_SIZE:
+ parse_option_size(opt->name, opt->str, &opt->value.uint, errp);
+ break;
+ default:
+ abort();
+ }
+}
+
+static void qemu_opt_del(QemuOpt *opt)
+{
+ QTAILQ_REMOVE(&opt->opts->head, opt, next);
+ g_free((/* !const */ char*)opt->name);
+ g_free((/* !const */ char*)opt->str);
+ g_free(opt);
+}
+
+static bool opts_accepts_any(const QemuOpts *opts)
+{
+ return opts->list->desc[0].name == NULL;
+}
+
+static const QemuOptDesc *find_desc_by_name(const QemuOptDesc *desc,
+ const char *name)
+{
+ int i;
+
+ for (i = 0; desc[i].name != NULL; i++) {
+ if (strcmp(desc[i].name, name) == 0) {
+ return &desc[i];
+ }
+ }
+
+ return NULL;
+}
+
+static void opt_set(QemuOpts *opts, const char *name, const char *value,
+ bool prepend, Error **errp)
+{
+ QemuOpt *opt;
+ const QemuOptDesc *desc;
+ Error *local_err = NULL;
+
+ desc = find_desc_by_name(opts->list->desc, name);
+ if (!desc && !opts_accepts_any(opts)) {
+ error_set(errp, QERR_INVALID_PARAMETER, name);
+ return;
+ }
+
+ opt = g_malloc0(sizeof(*opt));
+ opt->name = g_strdup(name);
+ opt->opts = opts;
+ if (prepend) {
+ QTAILQ_INSERT_HEAD(&opts->head, opt, next);
+ } else {
+ QTAILQ_INSERT_TAIL(&opts->head, opt, next);
+ }
+ opt->desc = desc;
+ opt->str = g_strdup(value);
+ qemu_opt_parse(opt, &local_err);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ qemu_opt_del(opt);
+ }
+}
+
+int qemu_opt_set(QemuOpts *opts, const char *name, const char *value)
+{
+ Error *local_err = NULL;
+
+ opt_set(opts, name, value, false, &local_err);
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ return -1;
+ }
+
+ return 0;
+}
+
+void qemu_opt_set_err(QemuOpts *opts, const char *name, const char *value,
+ Error **errp)
+{
+ opt_set(opts, name, value, false, errp);
+}
+
+int qemu_opt_set_bool(QemuOpts *opts, const char *name, bool val)
+{
+ QemuOpt *opt;
+ const QemuOptDesc *desc = opts->list->desc;
+
+ opt = g_malloc0(sizeof(*opt));
+ opt->desc = find_desc_by_name(desc, name);
+ if (!opt->desc && !opts_accepts_any(opts)) {
+ qerror_report(QERR_INVALID_PARAMETER, name);
+ g_free(opt);
+ return -1;
+ }
+
+ opt->name = g_strdup(name);
+ opt->opts = opts;
+ opt->value.boolean = !!val;
+ opt->str = g_strdup(val ? "on" : "off");
+ QTAILQ_INSERT_TAIL(&opts->head, opt, next);
+
+ return 0;
+}
+
+int qemu_opt_set_number(QemuOpts *opts, const char *name, int64_t val)
+{
+ QemuOpt *opt;
+ const QemuOptDesc *desc = opts->list->desc;
+
+ opt = g_malloc0(sizeof(*opt));
+ opt->desc = find_desc_by_name(desc, name);
+ if (!opt->desc && !opts_accepts_any(opts)) {
+ qerror_report(QERR_INVALID_PARAMETER, name);
+ g_free(opt);
+ return -1;
+ }
+
+ opt->name = g_strdup(name);
+ opt->opts = opts;
+ opt->value.uint = val;
+ opt->str = g_strdup_printf("%" PRId64, val);
+ QTAILQ_INSERT_TAIL(&opts->head, opt, next);
+
+ return 0;
+}
+
+int qemu_opt_foreach(QemuOpts *opts, qemu_opt_loopfunc func, void *opaque,
+ int abort_on_failure)
+{
+ QemuOpt *opt;
+ int rc = 0;
+
+ QTAILQ_FOREACH(opt, &opts->head, next) {
+ rc = func(opt->name, opt->str, opaque);
+ if (abort_on_failure && rc != 0)
+ break;
+ }
+ return rc;
+}
+
+QemuOpts *qemu_opts_find(QemuOptsList *list, const char *id)
+{
+ QemuOpts *opts;
+
+ QTAILQ_FOREACH(opts, &list->head, next) {
+ if (!opts->id && !id) {
+ return opts;
+ }
+ if (opts->id && id && !strcmp(opts->id, id)) {
+ return opts;
+ }
+ }
+ return NULL;
+}
+
+static int id_wellformed(const char *id)
+{
+ int i;
+
+ if (!qemu_isalpha(id[0])) {
+ return 0;
+ }
+ for (i = 1; id[i]; i++) {
+ if (!qemu_isalnum(id[i]) && !strchr("-._", id[i])) {
+ return 0;
+ }
+ }
+ return 1;
+}
+
+QemuOpts *qemu_opts_create(QemuOptsList *list, const char *id,
+ int fail_if_exists, Error **errp)
+{
+ QemuOpts *opts = NULL;
+
+ if (id) {
+ if (!id_wellformed(id)) {
+ error_set(errp,QERR_INVALID_PARAMETER_VALUE, "id", "an identifier");
+#if 0 /* conversion from qerror_report() to error_set() broke this: */
+ error_printf_unless_qmp("Identifiers consist of letters, digits, '-', '.', '_', starting with a letter.\n");
+#endif
+ return NULL;
+ }
+ opts = qemu_opts_find(list, id);
+ if (opts != NULL) {
+ if (fail_if_exists && !list->merge_lists) {
+ error_set(errp, QERR_DUPLICATE_ID, id, list->name);
+ return NULL;
+ } else {
+ return opts;
+ }
+ }
+ } else if (list->merge_lists) {
+ opts = qemu_opts_find(list, NULL);
+ if (opts) {
+ return opts;
+ }
+ }
+ opts = g_malloc0(sizeof(*opts));
+ opts->id = g_strdup(id);
+ opts->list = list;
+ loc_save(&opts->loc);
+ QTAILQ_INIT(&opts->head);
+ QTAILQ_INSERT_TAIL(&list->head, opts, next);
+ return opts;
+}
+
+QemuOpts *qemu_opts_create_nofail(QemuOptsList *list)
+{
+ QemuOpts *opts;
+ Error *errp = NULL;
+ opts = qemu_opts_create(list, NULL, 0, &errp);
+ assert_no_error(errp);
+ return opts;
+}
+
+void qemu_opts_reset(QemuOptsList *list)
+{
+ QemuOpts *opts, *next_opts;
+
+ QTAILQ_FOREACH_SAFE(opts, &list->head, next, next_opts) {
+ qemu_opts_del(opts);
+ }
+}
+
+void qemu_opts_loc_restore(QemuOpts *opts)
+{
+ loc_restore(&opts->loc);
+}
+
+int qemu_opts_set(QemuOptsList *list, const char *id,
+ const char *name, const char *value)
+{
+ QemuOpts *opts;
+ Error *local_err = NULL;
+
+ opts = qemu_opts_create(list, id, 1, &local_err);
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ return -1;
+ }
+ return qemu_opt_set(opts, name, value);
+}
+
+const char *qemu_opts_id(QemuOpts *opts)
+{
+ return opts->id;
+}
+
+void qemu_opts_del(QemuOpts *opts)
+{
+ QemuOpt *opt;
+
+ for (;;) {
+ opt = QTAILQ_FIRST(&opts->head);
+ if (opt == NULL)
+ break;
+ qemu_opt_del(opt);
+ }
+ QTAILQ_REMOVE(&opts->list->head, opts, next);
+ g_free(opts->id);
+ g_free(opts);
+}
+
+int qemu_opts_print(QemuOpts *opts, void *dummy)
+{
+ QemuOpt *opt;
+
+ fprintf(stderr, "%s: %s:", opts->list->name,
+ opts->id ? opts->id : "<noid>");
+ QTAILQ_FOREACH(opt, &opts->head, next) {
+ fprintf(stderr, " %s=\"%s\"", opt->name, opt->str);
+ }
+ fprintf(stderr, "\n");
+ return 0;
+}
+
+static int opts_do_parse(QemuOpts *opts, const char *params,
+ const char *firstname, bool prepend)
+{
+ char option[128], value[1024];
+ const char *p,*pe,*pc;
+ Error *local_err = NULL;
+
+ for (p = params; *p != '\0'; p++) {
+ pe = strchr(p, '=');
+ pc = strchr(p, ',');
+ if (!pe || (pc && pc < pe)) {
+ /* found "foo,more" */
+ if (p == params && firstname) {
+ /* implicitly named first option */
+ pstrcpy(option, sizeof(option), firstname);
+ p = get_opt_value(value, sizeof(value), p);
+ } else {
+ /* option without value, probably a flag */
+ p = get_opt_name(option, sizeof(option), p, ',');
+ if (strncmp(option, "no", 2) == 0) {
+ memmove(option, option+2, strlen(option+2)+1);
+ pstrcpy(value, sizeof(value), "off");
+ } else {
+ pstrcpy(value, sizeof(value), "on");
+ }
+ }
+ } else {
+ /* found "foo=bar,more" */
+ p = get_opt_name(option, sizeof(option), p, '=');
+ if (*p != '=') {
+ break;
+ }
+ p++;
+ p = get_opt_value(value, sizeof(value), p);
+ }
+ if (strcmp(option, "id") != 0) {
+ /* store and parse */
+ opt_set(opts, option, value, prepend, &local_err);
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ return -1;
+ }
+ }
+ if (*p != ',') {
+ break;
+ }
+ }
+ return 0;
+}
+
+int qemu_opts_do_parse(QemuOpts *opts, const char *params, const char *firstname)
+{
+ return opts_do_parse(opts, params, firstname, false);
+}
+
+static QemuOpts *opts_parse(QemuOptsList *list, const char *params,
+ int permit_abbrev, bool defaults)
+{
+ const char *firstname;
+ char value[1024], *id = NULL;
+ const char *p;
+ QemuOpts *opts;
+ Error *local_err = NULL;
+
+ assert(!permit_abbrev || list->implied_opt_name);
+ firstname = permit_abbrev ? list->implied_opt_name : NULL;
+
+ if (strncmp(params, "id=", 3) == 0) {
+ get_opt_value(value, sizeof(value), params+3);
+ id = value;
+ } else if ((p = strstr(params, ",id=")) != NULL) {
+ get_opt_value(value, sizeof(value), p+4);
+ id = value;
+ }
+ opts = qemu_opts_create(list, id, !defaults, &local_err);
+ if (opts == NULL) {
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ }
+ return NULL;
+ }
+
+ if (opts_do_parse(opts, params, firstname, defaults) != 0) {
+ qemu_opts_del(opts);
+ return NULL;
+ }
+
+ return opts;
+}
+
+QemuOpts *qemu_opts_parse(QemuOptsList *list, const char *params,
+ int permit_abbrev)
+{
+ return opts_parse(list, params, permit_abbrev, false);
+}
+
+void qemu_opts_set_defaults(QemuOptsList *list, const char *params,
+ int permit_abbrev)
+{
+ QemuOpts *opts;
+
+ opts = opts_parse(list, params, permit_abbrev, true);
+ assert(opts);
+}
+
+typedef struct OptsFromQDictState {
+ QemuOpts *opts;
+ Error **errp;
+} OptsFromQDictState;
+
+static void qemu_opts_from_qdict_1(const char *key, QObject *obj, void *opaque)
+{
+ OptsFromQDictState *state = opaque;
+ char buf[32];
+ const char *value;
+ int n;
+
+ if (!strcmp(key, "id") || error_is_set(state->errp)) {
+ return;
+ }
+
+ switch (qobject_type(obj)) {
+ case QTYPE_QSTRING:
+ value = qstring_get_str(qobject_to_qstring(obj));
+ break;
+ case QTYPE_QINT:
+ n = snprintf(buf, sizeof(buf), "%" PRId64,
+ qint_get_int(qobject_to_qint(obj)));
+ assert(n < sizeof(buf));
+ value = buf;
+ break;
+ case QTYPE_QFLOAT:
+ n = snprintf(buf, sizeof(buf), "%.17g",
+ qfloat_get_double(qobject_to_qfloat(obj)));
+ assert(n < sizeof(buf));
+ value = buf;
+ break;
+ case QTYPE_QBOOL:
+ pstrcpy(buf, sizeof(buf),
+ qbool_get_int(qobject_to_qbool(obj)) ? "on" : "off");
+ value = buf;
+ break;
+ default:
+ return;
+ }
+
+ qemu_opt_set_err(state->opts, key, value, state->errp);
+}
+
+/*
+ * Create QemuOpts from a QDict.
+ * Use value of key "id" as ID if it exists and is a QString.
+ * Only QStrings, QInts, QFloats and QBools are copied. Entries with
+ * other types are silently ignored.
+ */
+QemuOpts *qemu_opts_from_qdict(QemuOptsList *list, const QDict *qdict,
+ Error **errp)
+{
+ OptsFromQDictState state;
+ Error *local_err = NULL;
+ QemuOpts *opts;
+
+ opts = qemu_opts_create(list, qdict_get_try_str(qdict, "id"), 1,
+ &local_err);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ return NULL;
+ }
+
+ assert(opts != NULL);
+
+ state.errp = &local_err;
+ state.opts = opts;
+ qdict_iter(qdict, qemu_opts_from_qdict_1, &state);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ qemu_opts_del(opts);
+ return NULL;
+ }
+
+ return opts;
+}
+
+/*
+ * Adds all QDict entries to the QemuOpts that can be added and removes them
+ * from the QDict. When this function returns, the QDict contains only those
+ * entries that couldn't be added to the QemuOpts.
+ */
+void qemu_opts_absorb_qdict(QemuOpts *opts, QDict *qdict, Error **errp)
+{
+ const QDictEntry *entry, *next;
+
+ entry = qdict_first(qdict);
+
+ while (entry != NULL) {
+ Error *local_err = NULL;
+ OptsFromQDictState state = {
+ .errp = &local_err,
+ .opts = opts,
+ };
+
+ next = qdict_next(qdict, entry);
+
+ if (find_desc_by_name(opts->list->desc, entry->key)) {
+ qemu_opts_from_qdict_1(entry->key, entry->value, &state);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ return;
+ } else {
+ qdict_del(qdict, entry->key);
+ }
+ }
+
+ entry = next;
+ }
+}
+
+/*
+ * Convert from QemuOpts to QDict.
+ * The QDict values are of type QString.
+ * TODO We'll want to use types appropriate for opt->desc->type, but
+ * this is enough for now.
+ */
+QDict *qemu_opts_to_qdict(QemuOpts *opts, QDict *qdict)
+{
+ QemuOpt *opt;
+ QObject *val;
+
+ if (!qdict) {
+ qdict = qdict_new();
+ }
+ if (opts->id) {
+ qdict_put(qdict, "id", qstring_from_str(opts->id));
+ }
+ QTAILQ_FOREACH(opt, &opts->head, next) {
+ val = QOBJECT(qstring_from_str(opt->str));
+ qdict_put_obj(qdict, opt->name, val);
+ }
+ return qdict;
+}
+
+/* Validate parsed opts against descriptions where no
+ * descriptions were provided in the QemuOptsList.
+ */
+void qemu_opts_validate(QemuOpts *opts, const QemuOptDesc *desc, Error **errp)
+{
+ QemuOpt *opt;
+ Error *local_err = NULL;
+
+ assert(opts_accepts_any(opts));
+
+ QTAILQ_FOREACH(opt, &opts->head, next) {
+ opt->desc = find_desc_by_name(desc, opt->name);
+ if (!opt->desc) {
+ error_set(errp, QERR_INVALID_PARAMETER, opt->name);
+ return;
+ }
+
+ qemu_opt_parse(opt, &local_err);
+ if (error_is_set(&local_err)) {
+ error_propagate(errp, local_err);
+ return;
+ }
+ }
+}
+
+int qemu_opts_foreach(QemuOptsList *list, qemu_opts_loopfunc func, void *opaque,
+ int abort_on_failure)
+{
+ Location loc;
+ QemuOpts *opts;
+ int rc = 0;
+
+ loc_push_none(&loc);
+ QTAILQ_FOREACH(opts, &list->head, next) {
+ loc_restore(&opts->loc);
+ rc |= func(opts, opaque);
+ if (abort_on_failure && rc != 0)
+ break;
+ }
+ loc_pop(&loc);
+ return rc;
+}
diff --git a/contrib/qemu/util/qemu-thread-posix.c b/contrib/qemu/util/qemu-thread-posix.c
new file mode 100644
index 00000000000..4489abf1d85
--- /dev/null
+++ b/contrib/qemu/util/qemu-thread-posix.c
@@ -0,0 +1,327 @@
+/*
+ * Wrappers around mutex/cond/thread functions
+ *
+ * Copyright Red Hat, Inc. 2009
+ *
+ * Author:
+ * Marcelo Tosatti <mtosatti@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <time.h>
+#include <signal.h>
+#include <stdint.h>
+#include <string.h>
+#include <limits.h>
+#include <unistd.h>
+#include <sys/time.h>
+#include "qemu/thread.h"
+
+static void error_exit(int err, const char *msg)
+{
+ fprintf(stderr, "qemu: %s: %s\n", msg, strerror(err));
+ abort();
+}
+
+void qemu_mutex_init(QemuMutex *mutex)
+{
+ int err;
+ pthread_mutexattr_t mutexattr;
+
+ pthread_mutexattr_init(&mutexattr);
+ pthread_mutexattr_settype(&mutexattr, PTHREAD_MUTEX_ERRORCHECK);
+ err = pthread_mutex_init(&mutex->lock, &mutexattr);
+ pthread_mutexattr_destroy(&mutexattr);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_mutex_destroy(QemuMutex *mutex)
+{
+ int err;
+
+ err = pthread_mutex_destroy(&mutex->lock);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_mutex_lock(QemuMutex *mutex)
+{
+ int err;
+
+ err = pthread_mutex_lock(&mutex->lock);
+ if (err)
+ error_exit(err, __func__);
+}
+
+int qemu_mutex_trylock(QemuMutex *mutex)
+{
+ return pthread_mutex_trylock(&mutex->lock);
+}
+
+void qemu_mutex_unlock(QemuMutex *mutex)
+{
+ int err;
+
+ err = pthread_mutex_unlock(&mutex->lock);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_cond_init(QemuCond *cond)
+{
+ int err;
+
+ err = pthread_cond_init(&cond->cond, NULL);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_cond_destroy(QemuCond *cond)
+{
+ int err;
+
+ err = pthread_cond_destroy(&cond->cond);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_cond_signal(QemuCond *cond)
+{
+ int err;
+
+ err = pthread_cond_signal(&cond->cond);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_cond_broadcast(QemuCond *cond)
+{
+ int err;
+
+ err = pthread_cond_broadcast(&cond->cond);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_cond_wait(QemuCond *cond, QemuMutex *mutex)
+{
+ int err;
+
+ err = pthread_cond_wait(&cond->cond, &mutex->lock);
+ if (err)
+ error_exit(err, __func__);
+}
+
+void qemu_sem_init(QemuSemaphore *sem, int init)
+{
+ int rc;
+
+#if defined(__APPLE__) || defined(__NetBSD__)
+ rc = pthread_mutex_init(&sem->lock, NULL);
+ if (rc != 0) {
+ error_exit(rc, __func__);
+ }
+ rc = pthread_cond_init(&sem->cond, NULL);
+ if (rc != 0) {
+ error_exit(rc, __func__);
+ }
+ if (init < 0) {
+ error_exit(EINVAL, __func__);
+ }
+ sem->count = init;
+#else
+ rc = sem_init(&sem->sem, 0, init);
+ if (rc < 0) {
+ error_exit(errno, __func__);
+ }
+#endif
+}
+
+void qemu_sem_destroy(QemuSemaphore *sem)
+{
+ int rc;
+
+#if defined(__APPLE__) || defined(__NetBSD__)
+ rc = pthread_cond_destroy(&sem->cond);
+ if (rc < 0) {
+ error_exit(rc, __func__);
+ }
+ rc = pthread_mutex_destroy(&sem->lock);
+ if (rc < 0) {
+ error_exit(rc, __func__);
+ }
+#else
+ rc = sem_destroy(&sem->sem);
+ if (rc < 0) {
+ error_exit(errno, __func__);
+ }
+#endif
+}
+
+void qemu_sem_post(QemuSemaphore *sem)
+{
+ int rc;
+
+#if defined(__APPLE__) || defined(__NetBSD__)
+ pthread_mutex_lock(&sem->lock);
+ if (sem->count == INT_MAX) {
+ rc = EINVAL;
+ } else if (sem->count++ < 0) {
+ rc = pthread_cond_signal(&sem->cond);
+ } else {
+ rc = 0;
+ }
+ pthread_mutex_unlock(&sem->lock);
+ if (rc != 0) {
+ error_exit(rc, __func__);
+ }
+#else
+ rc = sem_post(&sem->sem);
+ if (rc < 0) {
+ error_exit(errno, __func__);
+ }
+#endif
+}
+
+static void compute_abs_deadline(struct timespec *ts, int ms)
+{
+ struct timeval tv;
+ gettimeofday(&tv, NULL);
+ ts->tv_nsec = tv.tv_usec * 1000 + (ms % 1000) * 1000000;
+ ts->tv_sec = tv.tv_sec + ms / 1000;
+ if (ts->tv_nsec >= 1000000000) {
+ ts->tv_sec++;
+ ts->tv_nsec -= 1000000000;
+ }
+}
+
+int qemu_sem_timedwait(QemuSemaphore *sem, int ms)
+{
+ int rc;
+ struct timespec ts;
+
+#if defined(__APPLE__) || defined(__NetBSD__)
+ compute_abs_deadline(&ts, ms);
+ pthread_mutex_lock(&sem->lock);
+ --sem->count;
+ while (sem->count < 0) {
+ rc = pthread_cond_timedwait(&sem->cond, &sem->lock, &ts);
+ if (rc == ETIMEDOUT) {
+ ++sem->count;
+ break;
+ }
+ if (rc != 0) {
+ error_exit(rc, __func__);
+ }
+ }
+ pthread_mutex_unlock(&sem->lock);
+ return (rc == ETIMEDOUT ? -1 : 0);
+#else
+ if (ms <= 0) {
+ /* This is cheaper than sem_timedwait. */
+ do {
+ rc = sem_trywait(&sem->sem);
+ } while (rc == -1 && errno == EINTR);
+ if (rc == -1 && errno == EAGAIN) {
+ return -1;
+ }
+ } else {
+ compute_abs_deadline(&ts, ms);
+ do {
+ rc = sem_timedwait(&sem->sem, &ts);
+ } while (rc == -1 && errno == EINTR);
+ if (rc == -1 && errno == ETIMEDOUT) {
+ return -1;
+ }
+ }
+ if (rc < 0) {
+ error_exit(errno, __func__);
+ }
+ return 0;
+#endif
+}
+
+void qemu_sem_wait(QemuSemaphore *sem)
+{
+#if defined(__APPLE__) || defined(__NetBSD__)
+ pthread_mutex_lock(&sem->lock);
+ --sem->count;
+ while (sem->count < 0) {
+ pthread_cond_wait(&sem->cond, &sem->lock);
+ }
+ pthread_mutex_unlock(&sem->lock);
+#else
+ int rc;
+
+ do {
+ rc = sem_wait(&sem->sem);
+ } while (rc == -1 && errno == EINTR);
+ if (rc < 0) {
+ error_exit(errno, __func__);
+ }
+#endif
+}
+
+void qemu_thread_create(QemuThread *thread,
+ void *(*start_routine)(void*),
+ void *arg, int mode)
+{
+ sigset_t set, oldset;
+ int err;
+ pthread_attr_t attr;
+
+ err = pthread_attr_init(&attr);
+ if (err) {
+ error_exit(err, __func__);
+ }
+ if (mode == QEMU_THREAD_DETACHED) {
+ err = pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
+ if (err) {
+ error_exit(err, __func__);
+ }
+ }
+
+ /* Leave signal handling to the iothread. */
+ sigfillset(&set);
+ pthread_sigmask(SIG_SETMASK, &set, &oldset);
+ err = pthread_create(&thread->thread, &attr, start_routine, arg);
+ if (err)
+ error_exit(err, __func__);
+
+ pthread_sigmask(SIG_SETMASK, &oldset, NULL);
+
+ pthread_attr_destroy(&attr);
+}
+
+void qemu_thread_get_self(QemuThread *thread)
+{
+ thread->thread = pthread_self();
+}
+
+bool qemu_thread_is_self(QemuThread *thread)
+{
+ return pthread_equal(pthread_self(), thread->thread);
+}
+
+void qemu_thread_exit(void *retval)
+{
+ pthread_exit(retval);
+}
+
+void *qemu_thread_join(QemuThread *thread)
+{
+ int err;
+ void *ret;
+
+ err = pthread_join(thread->thread, &ret);
+ if (err) {
+ error_exit(err, __func__);
+ }
+ return ret;
+}
diff --git a/contrib/qemu/util/unicode.c b/contrib/qemu/util/unicode.c
new file mode 100644
index 00000000000..d1c86588505
--- /dev/null
+++ b/contrib/qemu/util/unicode.c
@@ -0,0 +1,100 @@
+/*
+ * Dealing with Unicode
+ *
+ * Copyright (C) 2013 Red Hat, Inc.
+ *
+ * Authors:
+ * Markus Armbruster <armbru@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later. See the COPYING file in the top-level directory.
+ */
+
+#include "qemu-common.h"
+
+/**
+ * mod_utf8_codepoint:
+ * @s: string encoded in modified UTF-8
+ * @n: maximum number of bytes to read from @s, if less than 6
+ * @end: set to end of sequence on return
+ *
+ * Convert the modified UTF-8 sequence at the start of @s. Modified
+ * UTF-8 is exactly like UTF-8, except U+0000 is encoded as
+ * "\xC0\x80".
+ *
+ * If @n is zero or @s points to a zero byte, the sequence is invalid,
+ * and @end is set to @s.
+ *
+ * If @s points to an impossible byte (0xFE or 0xFF) or a continuation
+ * byte, the sequence is invalid, and @end is set to @s + 1
+ *
+ * Else, the first byte determines how many continuation bytes are
+ * expected. If there are fewer, the sequence is invalid, and @end is
+ * set to @s + 1 + actual number of continuation bytes. Else, the
+ * sequence is well-formed, and @end is set to @s + 1 + expected
+ * number of continuation bytes.
+ *
+ * A well-formed sequence is valid unless it encodes a codepoint
+ * outside the Unicode range U+0000..U+10FFFF, one of Unicode's 66
+ * noncharacters, a surrogate codepoint, or is overlong. Except the
+ * overlong sequence "\xC0\x80" is valid.
+ *
+ * Conversion succeeds if and only if the sequence is valid.
+ *
+ * Returns: the Unicode codepoint on success, -1 on failure.
+ */
+int mod_utf8_codepoint(const char *s, size_t n, char **end)
+{
+ static int min_cp[5] = { 0x80, 0x800, 0x10000, 0x200000, 0x4000000 };
+ const unsigned char *p;
+ unsigned byte, mask, len, i;
+ int cp;
+
+ if (n == 0 || *s == 0) {
+ /* empty sequence */
+ *end = (char *)s;
+ return -1;
+ }
+
+ p = (const unsigned char *)s;
+ byte = *p++;
+ if (byte < 0x80) {
+ cp = byte; /* one byte sequence */
+ } else if (byte >= 0xFE) {
+ cp = -1; /* impossible bytes 0xFE, 0xFF */
+ } else if ((byte & 0x40) == 0) {
+ cp = -1; /* unexpected continuation byte */
+ } else {
+ /* multi-byte sequence */
+ len = 0;
+ for (mask = 0x80; byte & mask; mask >>= 1) {
+ len++;
+ }
+ assert(len > 1 && len < 7);
+ cp = byte & (mask - 1);
+ for (i = 1; i < len; i++) {
+ byte = i < n ? *p : 0;
+ if ((byte & 0xC0) != 0x80) {
+ cp = -1; /* continuation byte missing */
+ goto out;
+ }
+ p++;
+ cp <<= 6;
+ cp |= byte & 0x3F;
+ }
+ if (cp > 0x10FFFF) {
+ cp = -1; /* beyond Unicode range */
+ } else if ((cp >= 0xFDD0 && cp <= 0xFDEF)
+ || (cp & 0xFFFE) == 0xFFFE) {
+ cp = -1; /* noncharacter */
+ } else if (cp >= 0xD800 && cp <= 0xDFFF) {
+ cp = -1; /* surrogate code point */
+ } else if (cp < min_cp[len - 2] && !(cp == 0 && len == 2)) {
+ cp = -1; /* overlong, not \xC0\x80 */
+ }
+ }
+
+out:
+ *end = (char *)p;
+ return cp;
+}