* THE SOFTWARE.
*/
#include "config-host.h"
-#ifdef HOST_BSD
-/* include native header before sys-queue.h */
-#include <sys/queue.h>
-#endif
-
#include "qemu-common.h"
#include "monitor.h"
#include "block_int.h"
+#include "module.h"
+#include "qemu-objects.h"
-#ifdef HOST_BSD
+#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
#include <windows.h>
#endif
-#define SECTOR_BITS 9
-#define SECTOR_SIZE (1 << SECTOR_BITS)
-
-static AIOPool vectored_aio_pool;
-
-typedef struct BlockDriverAIOCBSync {
- BlockDriverAIOCB common;
- QEMUBH *bh;
- int ret;
-} BlockDriverAIOCBSync;
-
-static BlockDriverAIOCB *bdrv_aio_read_em(BlockDriverState *bs,
- int64_t sector_num, uint8_t *buf, int nb_sectors,
+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_write_em(BlockDriverState *bs,
- int64_t sector_num, const uint8_t *buf, int nb_sectors,
+static BlockDriverAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque);
+static BlockDriverAIOCB *bdrv_aio_flush_em(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque);
-static void bdrv_aio_cancel_em(BlockDriverAIOCB *acb);
static int bdrv_read_em(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors);
static int bdrv_write_em(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors);
+static BlockDriver *find_protocol(const char *filename);
+
+static QTAILQ_HEAD(, BlockDriverState) bdrv_states =
+ QTAILQ_HEAD_INITIALIZER(bdrv_states);
-BlockDriverState *bdrv_first;
+static QLIST_HEAD(, BlockDriver) bdrv_drivers =
+ QLIST_HEAD_INITIALIZER(bdrv_drivers);
-static BlockDriver *first_drv;
+/* If non-zero, use only whitelisted block drivers */
+static int use_bdrv_whitelist;
int path_is_absolute(const char *path)
{
}
}
-
-static void bdrv_register(BlockDriver *bdrv)
+void bdrv_register(BlockDriver *bdrv)
{
- if (!bdrv->bdrv_aio_read) {
+ if (!bdrv->bdrv_aio_readv) {
/* add AIO emulation layer */
- bdrv->bdrv_aio_read = bdrv_aio_read_em;
- bdrv->bdrv_aio_write = bdrv_aio_write_em;
- bdrv->bdrv_aio_cancel = bdrv_aio_cancel_em;
- bdrv->aiocb_size = sizeof(BlockDriverAIOCBSync);
+ bdrv->bdrv_aio_readv = bdrv_aio_readv_em;
+ bdrv->bdrv_aio_writev = bdrv_aio_writev_em;
} else if (!bdrv->bdrv_read) {
/* add synchronous IO emulation layer */
bdrv->bdrv_read = bdrv_read_em;
bdrv->bdrv_write = bdrv_write_em;
}
- aio_pool_init(&bdrv->aio_pool, bdrv->aiocb_size, bdrv->bdrv_aio_cancel);
- bdrv->next = first_drv;
- first_drv = bdrv;
+
+ if (!bdrv->bdrv_aio_flush)
+ bdrv->bdrv_aio_flush = bdrv_aio_flush_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 **pbs, *bs;
+ BlockDriverState *bs;
bs = qemu_mallocz(sizeof(BlockDriverState));
pstrcpy(bs->device_name, sizeof(bs->device_name), device_name);
if (device_name[0] != '\0') {
- /* insert at the end */
- pbs = &bdrv_first;
- while (*pbs != NULL)
- pbs = &(*pbs)->next;
- *pbs = bs;
+ QTAILQ_INSERT_TAIL(&bdrv_states, bs, list);
}
return bs;
}
BlockDriver *bdrv_find_format(const char *format_name)
{
BlockDriver *drv1;
- for(drv1 = first_drv; drv1 != NULL; drv1 = drv1->next) {
- if (!strcmp(drv1->format_name, format_name))
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
+ if (!strcmp(drv1->format_name, format_name)) {
return drv1;
+ }
}
return NULL;
}
-int bdrv_create2(BlockDriver *drv,
- const char *filename, int64_t size_in_sectors,
- const char *backing_file, const char *backing_format,
- int flags)
+static int bdrv_is_whitelisted(BlockDriver *drv)
{
- if (drv->bdrv_create2)
- return drv->bdrv_create2(filename, size_in_sectors, backing_file,
- backing_format, flags);
- if (drv->bdrv_create)
- return drv->bdrv_create(filename, size_in_sectors, backing_file,
- flags);
- return -ENOTSUP;
+ static const char *whitelist[] = {
+ CONFIG_BDRV_WHITELIST
+ };
+ const char **p;
+
+ if (!whitelist[0])
+ return 1; /* no whitelist, anything goes */
+
+ for (p = whitelist; *p; p++) {
+ if (!strcmp(drv->format_name, *p)) {
+ return 1;
+ }
+ }
+ return 0;
+}
+
+BlockDriver *bdrv_find_whitelisted_format(const char *format_name)
+{
+ BlockDriver *drv = bdrv_find_format(format_name);
+ return drv && bdrv_is_whitelisted(drv) ? drv : NULL;
}
-int bdrv_create(BlockDriver *drv,
- const char *filename, int64_t size_in_sectors,
- const char *backing_file, int flags)
+int bdrv_create(BlockDriver *drv, const char* filename,
+ QEMUOptionParameter *options)
{
if (!drv->bdrv_create)
return -ENOTSUP;
- return drv->bdrv_create(filename, size_in_sectors, backing_file, flags);
+
+ return drv->bdrv_create(filename, options);
+}
+
+int bdrv_create_file(const char* filename, QEMUOptionParameter *options)
+{
+ BlockDriver *drv;
+
+ drv = find_protocol(filename);
+ if (drv == NULL) {
+ drv = bdrv_find_format("file");
+ }
+
+ return bdrv_create(drv, filename, options);
}
#ifdef _WIN32
filename[1] == ':');
}
-static int is_windows_drive(const char *filename)
+int is_windows_drive(const char *filename)
{
if (is_windows_drive_prefix(filename) &&
filename[2] == '\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;
+}
+
static BlockDriver *find_protocol(const char *filename)
{
BlockDriver *drv1;
char protocol[128];
int len;
const char *p;
+ int is_drive;
+
+ /* TODO Drivers without bdrv_file_open must be specified explicitly */
#ifdef _WIN32
- if (is_windows_drive(filename) ||
- is_windows_drive_prefix(filename))
- return &bdrv_raw;
+ is_drive = is_windows_drive(filename) ||
+ is_windows_drive_prefix(filename);
+#else
+ is_drive = 0;
#endif
p = strchr(filename, ':');
- if (!p)
- return &bdrv_raw;
+ if (!p || is_drive) {
+ drv1 = find_hdev_driver(filename);
+ if (!drv1) {
+ drv1 = bdrv_find_format("file");
+ }
+ return drv1;
+ }
len = p - filename;
if (len > sizeof(protocol) - 1)
len = sizeof(protocol) - 1;
memcpy(protocol, filename, len);
protocol[len] = '\0';
- for(drv1 = first_drv; drv1 != NULL; drv1 = drv1->next) {
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
if (drv1->protocol_name &&
- !strcmp(drv1->protocol_name, protocol))
+ !strcmp(drv1->protocol_name, protocol)) {
return drv1;
+ }
}
return NULL;
}
-/* XXX: force raw format if block or character device ? It would
- simplify the BSD case */
static BlockDriver *find_image_format(const char *filename)
{
int ret, score, score_max;
uint8_t buf[2048];
BlockDriverState *bs;
- /* detect host devices. By convention, /dev/cdrom[N] is always
- recognized as a host CDROM */
- if (strstart(filename, "/dev/cdrom", NULL))
- return &bdrv_host_device;
-#ifdef _WIN32
- if (is_windows_drive(filename))
- return &bdrv_host_device;
-#else
- {
- struct stat st;
- if (stat(filename, &st) >= 0 &&
- (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode))) {
- return &bdrv_host_device;
- }
- }
-#endif
-
- drv = find_protocol(filename);
- /* no need to test disk image formats for vvfat */
- if (drv == &bdrv_vvfat)
- return drv;
-
- ret = bdrv_file_open(&bs, filename, BDRV_O_RDONLY);
+ ret = bdrv_file_open(&bs, filename, 0);
if (ret < 0)
return NULL;
+
+ /* Return the raw BlockDriver * to scsi-generic devices */
+ if (bs->sg)
+ return bdrv_find_format("raw");
+
ret = bdrv_pread(bs, 0, buf, sizeof(buf));
bdrv_delete(bs);
if (ret < 0) {
}
score_max = 0;
- for(drv1 = first_drv; drv1 != NULL; drv1 = drv1->next) {
+ drv = NULL;
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
if (drv1->bdrv_probe) {
score = drv1->bdrv_probe(buf, ret, filename);
if (score > score_max) {
return drv;
}
+/**
+ * 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;
+}
+
+/*
+ * Common part for opening disk images and files
+ */
+static int bdrv_open_common(BlockDriverState *bs, const char *filename,
+ int flags, BlockDriver *drv)
+{
+ int ret, open_flags;
+
+ assert(drv != NULL);
+
+ bs->file = NULL;
+ bs->total_sectors = 0;
+ bs->is_temporary = 0;
+ bs->encrypted = 0;
+ bs->valid_key = 0;
+ bs->open_flags = flags;
+ /* buffer_alignment defaulted to 512, drivers can change this value */
+ bs->buffer_alignment = 512;
+
+ pstrcpy(bs->filename, sizeof(bs->filename), filename);
+
+ if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv)) {
+ return -ENOTSUP;
+ }
+
+ bs->drv = drv;
+ bs->opaque = qemu_mallocz(drv->instance_size);
+
+ /*
+ * Yes, BDRV_O_NOCACHE aka O_DIRECT means we have to present a
+ * write cache to the guest. We do need the fdatasync to flush
+ * out transactions for block allocations, and we maybe have a
+ * volatile write cache in our backing device to deal with.
+ */
+ if (flags & (BDRV_O_CACHE_WB|BDRV_O_NOCACHE))
+ bs->enable_write_cache = 1;
+
+ /*
+ * Clear flags that are internal to the block layer before opening the
+ * image.
+ */
+ open_flags = flags & ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
+
+ /*
+ * Snapshots should be writeable.
+ */
+ if (bs->is_temporary) {
+ open_flags |= BDRV_O_RDWR;
+ }
+
+ /* Open the image, either directly or using a protocol */
+ if (drv->bdrv_file_open) {
+ ret = drv->bdrv_file_open(bs, filename, open_flags);
+ } else {
+ ret = bdrv_file_open(&bs->file, filename, open_flags);
+ if (ret >= 0) {
+ ret = drv->bdrv_open(bs, open_flags);
+ }
+ }
+
+ if (ret < 0) {
+ goto free_and_fail;
+ }
+
+ bs->keep_read_only = bs->read_only = !(open_flags & BDRV_O_RDWR);
+
+ ret = refresh_total_sectors(bs, bs->total_sectors);
+ if (ret < 0) {
+ goto free_and_fail;
+ }
+
+#ifndef _WIN32
+ if (bs->is_temporary) {
+ unlink(filename);
+ }
+#endif
+ return 0;
+
+free_and_fail:
+ if (bs->file) {
+ bdrv_delete(bs->file);
+ bs->file = NULL;
+ }
+ qemu_free(bs->opaque);
+ bs->opaque = NULL;
+ bs->drv = NULL;
+ return ret;
+}
+
+/*
+ * Opens a file using a protocol (file, host_device, nbd, ...)
+ */
int bdrv_file_open(BlockDriverState **pbs, const char *filename, int flags)
{
BlockDriverState *bs;
+ BlockDriver *drv;
int ret;
+ drv = find_protocol(filename);
+ if (!drv) {
+ return -ENOENT;
+ }
+
bs = bdrv_new("");
- ret = bdrv_open2(bs, filename, flags | BDRV_O_FILE, NULL);
+ ret = bdrv_open_common(bs, filename, flags, drv);
if (ret < 0) {
bdrv_delete(bs);
return ret;
return 0;
}
-int bdrv_open(BlockDriverState *bs, const char *filename, int flags)
-{
- return bdrv_open2(bs, filename, flags, NULL);
-}
-
-int bdrv_open2(BlockDriverState *bs, const char *filename, int flags,
- BlockDriver *drv)
+/*
+ * Opens a disk image (raw, qcow2, vmdk, ...)
+ */
+int bdrv_open(BlockDriverState *bs, const char *filename, int flags,
+ BlockDriver *drv)
{
- int ret, open_flags;
- char tmp_filename[PATH_MAX];
- char backing_filename[PATH_MAX];
-
- bs->read_only = 0;
- bs->is_temporary = 0;
- bs->encrypted = 0;
- bs->valid_key = 0;
+ int ret;
if (flags & BDRV_O_SNAPSHOT) {
BlockDriverState *bs1;
int64_t total_size;
int is_protocol = 0;
+ BlockDriver *bdrv_qcow2;
+ QEMUOptionParameter *options;
+ char tmp_filename[PATH_MAX];
+ char backing_filename[PATH_MAX];
/* 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_open2(bs1, filename, 0, drv);
+ ret = bdrv_open(bs1, filename, 0, drv);
if (ret < 0) {
bdrv_delete(bs1);
return ret;
}
- total_size = bdrv_getlength(bs1) >> SECTOR_BITS;
+ total_size = bdrv_getlength(bs1) >> BDRV_SECTOR_BITS;
if (bs1->drv && bs1->drv->protocol_name)
is_protocol = 1;
if (is_protocol)
snprintf(backing_filename, sizeof(backing_filename),
"%s", filename);
- else
- realpath(filename, backing_filename);
+ else if (!realpath(filename, backing_filename))
+ return -errno;
+
+ bdrv_qcow2 = bdrv_find_format("qcow2");
+ options = parse_option_parameters("", bdrv_qcow2->create_options, NULL);
+
+ set_option_parameter_int(options, BLOCK_OPT_SIZE, total_size * 512);
+ set_option_parameter(options, BLOCK_OPT_BACKING_FILE, backing_filename);
+ if (drv) {
+ set_option_parameter(options, BLOCK_OPT_BACKING_FMT,
+ drv->format_name);
+ }
- ret = bdrv_create2(&bdrv_qcow2, tmp_filename,
- total_size, backing_filename,
- (drv ? drv->format_name : NULL), 0);
+ ret = bdrv_create(bdrv_qcow2, tmp_filename, options);
+ free_option_parameters(options);
if (ret < 0) {
return ret;
}
+
filename = tmp_filename;
- drv = &bdrv_qcow2;
+ drv = bdrv_qcow2;
bs->is_temporary = 1;
}
- pstrcpy(bs->filename, sizeof(bs->filename), filename);
- if (flags & BDRV_O_FILE) {
- drv = find_protocol(filename);
- } else if (!drv) {
+ /* Find the right image format driver */
+ if (!drv) {
drv = find_image_format(filename);
}
+
if (!drv) {
ret = -ENOENT;
goto unlink_and_fail;
}
- bs->drv = drv;
- bs->opaque = qemu_mallocz(drv->instance_size);
- /* Note: for compatibility, we open disk image files as RDWR, and
- RDONLY as fallback */
- if (!(flags & BDRV_O_FILE))
- open_flags = BDRV_O_RDWR | (flags & BDRV_O_CACHE_MASK);
- else
- open_flags = flags & ~(BDRV_O_FILE | BDRV_O_SNAPSHOT);
- ret = drv->bdrv_open(bs, filename, open_flags);
- if ((ret == -EACCES || ret == -EPERM) && !(flags & BDRV_O_FILE)) {
- ret = drv->bdrv_open(bs, filename, open_flags & ~BDRV_O_RDWR);
- bs->read_only = 1;
- }
+
+ /* Open the image */
+ ret = bdrv_open_common(bs, filename, flags, drv);
if (ret < 0) {
- qemu_free(bs->opaque);
- bs->opaque = NULL;
- bs->drv = NULL;
- unlink_and_fail:
- if (bs->is_temporary)
- unlink(filename);
- return ret;
- }
- if (drv->bdrv_getlength) {
- bs->total_sectors = bdrv_getlength(bs) >> SECTOR_BITS;
- }
-#ifndef _WIN32
- if (bs->is_temporary) {
- unlink(filename);
+ goto unlink_and_fail;
}
-#endif
- if (bs->backing_file[0] != '\0') {
- /* if there is a backing file, use it */
+
+ /* If there is a backing file, use it */
+ if ((flags & BDRV_O_NO_BACKING) == 0 && bs->backing_file[0] != '\0') {
+ char backing_filename[PATH_MAX];
+ int back_flags;
BlockDriver *back_drv = NULL;
+
bs->backing_hd = bdrv_new("");
path_combine(backing_filename, sizeof(backing_filename),
filename, bs->backing_file);
if (bs->backing_format[0] != '\0')
back_drv = bdrv_find_format(bs->backing_format);
- ret = bdrv_open2(bs->backing_hd, backing_filename, open_flags,
- back_drv);
+
+ /* backing files always opened read-only */
+ back_flags =
+ flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
+
+ ret = bdrv_open(bs->backing_hd, backing_filename, back_flags, back_drv);
if (ret < 0) {
bdrv_close(bs);
return ret;
}
+ if (bs->is_temporary) {
+ bs->backing_hd->keep_read_only = !(flags & BDRV_O_RDWR);
+ } else {
+ /* base image inherits from "parent" */
+ bs->backing_hd->keep_read_only = bs->keep_read_only;
+ }
}
if (!bdrv_key_required(bs)) {
if (bs->change_cb)
bs->change_cb(bs->change_opaque);
}
+
return 0;
+
+unlink_and_fail:
+ if (bs->is_temporary) {
+ unlink(filename);
+ }
+ return ret;
}
void bdrv_close(BlockDriverState *bs)
{
if (bs->drv) {
- if (bs->backing_hd)
+ if (bs->backing_hd) {
bdrv_delete(bs->backing_hd);
+ bs->backing_hd = NULL;
+ }
bs->drv->bdrv_close(bs);
qemu_free(bs->opaque);
#ifdef _WIN32
bs->opaque = NULL;
bs->drv = NULL;
+ if (bs->file != NULL) {
+ bdrv_close(bs->file);
+ }
+
/* call the change callback */
bs->media_changed = 1;
if (bs->change_cb)
void bdrv_delete(BlockDriverState *bs)
{
- BlockDriverState **pbs;
-
- pbs = &bdrv_first;
- while (*pbs != bs && *pbs != NULL)
- pbs = &(*pbs)->next;
- if (*pbs == bs)
- *pbs = bs->next;
+ /* remove from list, if necessary */
+ if (bs->device_name[0] != '\0') {
+ QTAILQ_REMOVE(&bdrv_states, bs, list);
+ }
bdrv_close(bs);
+ if (bs->file != NULL) {
+ bdrv_delete(bs->file);
+ }
+
qemu_free(bs);
}
+/*
+ * Run consistency checks on an image
+ *
+ * Returns the number of errors or -errno when an internal error occurs
+ */
+int bdrv_check(BlockDriverState *bs)
+{
+ if (bs->drv->bdrv_check == NULL) {
+ return -ENOTSUP;
+ }
+
+ return bs->drv->bdrv_check(bs);
+}
+
/* commit COW file into the raw image */
int bdrv_commit(BlockDriverState *bs)
{
BlockDriver *drv = bs->drv;
int64_t i, total_sectors;
- int n, j;
+ int n, j, ro, open_flags;
+ int ret = 0, rw_ret = 0;
unsigned char sector[512];
+ char filename[1024];
+ BlockDriverState *bs_rw, *bs_ro;
if (!drv)
return -ENOMEDIUM;
-
- if (bs->read_only) {
- return -EACCES;
+
+ if (!bs->backing_hd) {
+ return -ENOTSUP;
}
- if (!bs->backing_hd) {
- return -ENOTSUP;
+ if (bs->backing_hd->keep_read_only) {
+ return -EACCES;
+ }
+
+ ro = bs->backing_hd->read_only;
+ strncpy(filename, bs->backing_hd->filename, sizeof(filename));
+ open_flags = bs->backing_hd->open_flags;
+
+ if (ro) {
+ /* re-open as RW */
+ bdrv_delete(bs->backing_hd);
+ bs->backing_hd = NULL;
+ bs_rw = bdrv_new("");
+ rw_ret = bdrv_open(bs_rw, filename, open_flags | BDRV_O_RDWR, drv);
+ if (rw_ret < 0) {
+ bdrv_delete(bs_rw);
+ /* try to re-open read-only */
+ bs_ro = bdrv_new("");
+ ret = bdrv_open(bs_ro, filename, open_flags & ~BDRV_O_RDWR, drv);
+ if (ret < 0) {
+ bdrv_delete(bs_ro);
+ /* drive not functional anymore */
+ bs->drv = NULL;
+ return ret;
+ }
+ bs->backing_hd = bs_ro;
+ return rw_ret;
+ }
+ bs->backing_hd = bs_rw;
}
- total_sectors = bdrv_getlength(bs) >> SECTOR_BITS;
+ total_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
for (i = 0; i < total_sectors;) {
if (drv->bdrv_is_allocated(bs, i, 65536, &n)) {
for(j = 0; j < n; j++) {
if (bdrv_read(bs, i, sector, 1) != 0) {
- return -EIO;
+ ret = -EIO;
+ goto ro_cleanup;
}
if (bdrv_write(bs->backing_hd, i, sector, 1) != 0) {
- return -EIO;
+ ret = -EIO;
+ goto ro_cleanup;
}
i++;
}
}
}
- if (drv->bdrv_make_empty)
- return drv->bdrv_make_empty(bs);
+ 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);
- return 0;
+ro_cleanup:
+
+ if (ro) {
+ /* re-open as RO */
+ bdrv_delete(bs->backing_hd);
+ bs->backing_hd = NULL;
+ bs_ro = bdrv_new("");
+ ret = bdrv_open(bs_ro, filename, open_flags & ~BDRV_O_RDWR, drv);
+ if (ret < 0) {
+ bdrv_delete(bs_ro);
+ /* drive not functional anymore */
+ bs->drv = NULL;
+ return ret;
+ }
+ bs->backing_hd = bs_ro;
+ bs->backing_hd->keep_read_only = 0;
+ }
+
+ return ret;
+}
+
+/*
+ * 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;
+
+ if (drv->bdrv_change_backing_file != NULL) {
+ return drv->bdrv_change_backing_file(bs, backing_file, backing_fmt);
+ } else {
+ return -ENOTSUP;
+ }
}
static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
len = bdrv_getlength(bs);
- if ((offset + size) > len)
+ if (offset < 0)
+ return -EIO;
+
+ if ((offset > len) || (len - offset < size))
return -EIO;
return 0;
return drv->bdrv_read(bs, sector_num, buf, nb_sectors);
}
+static void set_dirty_bitmap(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, int dirty)
+{
+ int64_t start, end;
+ unsigned long val, idx, bit;
+
+ start = sector_num / BDRV_SECTORS_PER_DIRTY_CHUNK;
+ end = (sector_num + nb_sectors - 1) / BDRV_SECTORS_PER_DIRTY_CHUNK;
+
+ for (; start <= end; start++) {
+ idx = start / (sizeof(unsigned long) * 8);
+ bit = start % (sizeof(unsigned long) * 8);
+ val = bs->dirty_bitmap[idx];
+ if (dirty) {
+ if (!(val & (1 << bit))) {
+ bs->dirty_count++;
+ val |= 1 << bit;
+ }
+ } else {
+ if (val & (1 << bit)) {
+ bs->dirty_count--;
+ val &= ~(1 << bit);
+ }
+ }
+ bs->dirty_bitmap[idx] = val;
+ }
+}
+
/* Return < 0 if error. Important errors are:
-EIO generic I/O error (may happen for all errors)
-ENOMEDIUM No media inserted.
if (bdrv_check_request(bs, sector_num, nb_sectors))
return -EIO;
+ if (bs->dirty_bitmap) {
+ set_dirty_bitmap(bs, sector_num, nb_sectors, 1);
+ }
+
+ if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
+ bs->wr_highest_sector = sector_num + nb_sectors - 1;
+ }
+
return drv->bdrv_write(bs, sector_num, buf, nb_sectors);
}
int bdrv_pread(BlockDriverState *bs, int64_t offset,
void *buf, int count1)
{
- uint8_t tmp_buf[SECTOR_SIZE];
+ 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 = (SECTOR_SIZE - offset) & (SECTOR_SIZE - 1);
+ len = (BDRV_SECTOR_SIZE - offset) & (BDRV_SECTOR_SIZE - 1);
if (len > count)
len = count;
- sector_num = offset >> SECTOR_BITS;
+ sector_num = offset >> BDRV_SECTOR_BITS;
if (len > 0) {
- if (bdrv_read(bs, sector_num, tmp_buf, 1) < 0)
- return -EIO;
- memcpy(buf, tmp_buf + (offset & (SECTOR_SIZE - 1)), len);
+ 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;
}
/* read the sectors "in place" */
- nb_sectors = count >> SECTOR_BITS;
+ nb_sectors = count >> BDRV_SECTOR_BITS;
if (nb_sectors > 0) {
- if (bdrv_read(bs, sector_num, buf, nb_sectors) < 0)
- return -EIO;
+ if ((ret = bdrv_read(bs, sector_num, buf, nb_sectors)) < 0)
+ return ret;
sector_num += nb_sectors;
- len = nb_sectors << SECTOR_BITS;
+ len = nb_sectors << BDRV_SECTOR_BITS;
buf += len;
count -= len;
}
/* add data from the last sector */
if (count > 0) {
- if (bdrv_read(bs, sector_num, tmp_buf, 1) < 0)
- return -EIO;
+ if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
memcpy(buf, tmp_buf, count);
}
return count1;
int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
const void *buf, int count1)
{
- uint8_t tmp_buf[SECTOR_SIZE];
+ uint8_t tmp_buf[BDRV_SECTOR_SIZE];
int len, nb_sectors, count;
int64_t sector_num;
+ int ret;
count = count1;
/* first write to align to sector start */
- len = (SECTOR_SIZE - offset) & (SECTOR_SIZE - 1);
+ len = (BDRV_SECTOR_SIZE - offset) & (BDRV_SECTOR_SIZE - 1);
if (len > count)
len = count;
- sector_num = offset >> SECTOR_BITS;
+ sector_num = offset >> BDRV_SECTOR_BITS;
if (len > 0) {
- if (bdrv_read(bs, sector_num, tmp_buf, 1) < 0)
- return -EIO;
- memcpy(tmp_buf + (offset & (SECTOR_SIZE - 1)), buf, len);
- if (bdrv_write(bs, sector_num, tmp_buf, 1) < 0)
- return -EIO;
+ if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
+ memcpy(tmp_buf + (offset & (BDRV_SECTOR_SIZE - 1)), buf, len);
+ if ((ret = bdrv_write(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
count -= len;
if (count == 0)
return count1;
}
/* write the sectors "in place" */
- nb_sectors = count >> SECTOR_BITS;
+ nb_sectors = count >> BDRV_SECTOR_BITS;
if (nb_sectors > 0) {
- if (bdrv_write(bs, sector_num, buf, nb_sectors) < 0)
- return -EIO;
+ if ((ret = bdrv_write(bs, sector_num, buf, nb_sectors)) < 0)
+ return ret;
sector_num += nb_sectors;
- len = nb_sectors << SECTOR_BITS;
+ len = nb_sectors << BDRV_SECTOR_BITS;
buf += len;
count -= len;
}
/* add data from the last sector */
if (count > 0) {
- if (bdrv_read(bs, sector_num, tmp_buf, 1) < 0)
- return -EIO;
+ if ((ret = bdrv_read(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
memcpy(tmp_buf, buf, count);
- if (bdrv_write(bs, sector_num, tmp_buf, 1) < 0)
- return -EIO;
+ if ((ret = bdrv_write(bs, sector_num, tmp_buf, 1)) < 0)
+ return ret;
}
return count1;
}
int bdrv_truncate(BlockDriverState *bs, int64_t offset)
{
BlockDriver *drv = bs->drv;
+ int ret;
if (!drv)
return -ENOMEDIUM;
if (!drv->bdrv_truncate)
return -ENOTSUP;
- return drv->bdrv_truncate(bs, offset);
+ if (bs->read_only)
+ return -EACCES;
+ ret = drv->bdrv_truncate(bs, offset);
+ if (ret == 0) {
+ ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
+ }
+ return ret;
}
/**
BlockDriver *drv = bs->drv;
if (!drv)
return -ENOMEDIUM;
- if (!drv->bdrv_getlength) {
- /* legacy mode */
- return bs->total_sectors * SECTOR_SIZE;
+
+ /* Fixed size devices use the total_sectors value for speed instead of
+ issuing a length query (like lseek) on each call. Also, legacy block
+ drivers don't provide a bdrv_getlength function and must use
+ total_sectors. */
+ if (!bs->growable || !drv->bdrv_getlength) {
+ return bs->total_sectors * BDRV_SECTOR_SIZE;
}
return drv->bdrv_getlength(bs);
}
if (length < 0)
length = 0;
else
- length = length >> SECTOR_BITS;
+ length = length >> BDRV_SECTOR_BITS;
*nb_sectors_ptr = length;
}
return bs->sg;
}
+int bdrv_enable_write_cache(BlockDriverState *bs)
+{
+ return bs->enable_write_cache;
+}
+
/* XXX: no longer used */
void bdrv_set_change_cb(BlockDriverState *bs,
void (*change_cb)(void *opaque), void *opaque)
if (!bs->encrypted)
return 0;
}
- if (!bs->encrypted || !bs->drv || !bs->drv->bdrv_set_key)
- return -1;
+ 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;
{
BlockDriver *drv;
- for (drv = first_drv; drv != NULL; drv = drv->next) {
+ QLIST_FOREACH(drv, &bdrv_drivers, list) {
it(opaque, drv->format_name);
}
}
{
BlockDriverState *bs;
- for (bs = bdrv_first; bs != NULL; bs = bs->next) {
- if (!strcmp(name, bs->device_name))
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ if (!strcmp(name, bs->device_name)) {
return bs;
+ }
}
return NULL;
}
{
BlockDriverState *bs;
- for (bs = bdrv_first; bs != NULL; bs = bs->next) {
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
it(opaque, bs);
}
}
void bdrv_flush(BlockDriverState *bs)
{
- if (!bs->drv)
- return;
- if (bs->drv->bdrv_flush)
+ if (bs->drv && bs->drv->bdrv_flush)
bs->drv->bdrv_flush(bs);
- if (bs->backing_hd)
- bdrv_flush(bs->backing_hd);
}
void bdrv_flush_all(void)
{
BlockDriverState *bs;
- for (bs = bdrv_first; bs != NULL; bs = bs->next)
- if (bs->drv && !bdrv_is_read_only(bs) &&
- (!bdrv_is_removable(bs) || bdrv_is_inserted(bs)))
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ if (bs->drv && !bdrv_is_read_only(bs) &&
+ (!bdrv_is_removable(bs) || bdrv_is_inserted(bs))) {
bdrv_flush(bs);
+ }
+ }
+}
+
+int bdrv_has_zero_init(BlockDriverState *bs)
+{
+ assert(bs->drv);
+
+ if (bs->drv->no_zero_init) {
+ return 0;
+ } else if (bs->file) {
+ return bdrv_has_zero_init(bs->file);
+ }
+
+ return 1;
}
/*
return bs->drv->bdrv_is_allocated(bs, sector_num, nb_sectors, pnum);
}
-void bdrv_info(Monitor *mon)
+void bdrv_mon_event(const BlockDriverState *bdrv,
+ BlockMonEventAction action, int 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(QEVENT_BLOCK_IO_ERROR, data);
+
+ qobject_decref(data);
+}
+
+static void bdrv_print_dict(QObject *obj, void *opaque)
+{
+ QDict *bs_dict;
+ Monitor *mon = opaque;
+
+ bs_dict = qobject_to_qdict(obj);
+
+ monitor_printf(mon, "%s: type=%s removable=%d",
+ qdict_get_str(bs_dict, "device"),
+ qdict_get_str(bs_dict, "type"),
+ qdict_get_bool(bs_dict, "removable"));
+
+ if (qdict_get_bool(bs_dict, "removable")) {
+ monitor_printf(mon, " locked=%d", qdict_get_bool(bs_dict, "locked"));
+ }
+
+ if (qdict_haskey(bs_dict, "inserted")) {
+ QDict *qdict = qobject_to_qdict(qdict_get(bs_dict, "inserted"));
+
+ monitor_printf(mon, " file=");
+ monitor_print_filename(mon, qdict_get_str(qdict, "file"));
+ if (qdict_haskey(qdict, "backing_file")) {
+ monitor_printf(mon, " backing_file=");
+ monitor_print_filename(mon, qdict_get_str(qdict, "backing_file"));
+ }
+ monitor_printf(mon, " ro=%d drv=%s encrypted=%d",
+ qdict_get_bool(qdict, "ro"),
+ qdict_get_str(qdict, "drv"),
+ qdict_get_bool(qdict, "encrypted"));
+ } else {
+ monitor_printf(mon, " [not inserted]");
+ }
+
+ monitor_printf(mon, "\n");
+}
+
+void bdrv_info_print(Monitor *mon, const QObject *data)
+{
+ qlist_iter(qobject_to_qlist(data), bdrv_print_dict, mon);
+}
+
+/**
+ * bdrv_info(): Block devices information
+ *
+ * Each block device information is stored in a QDict and the
+ * returned QObject is a QList of all devices.
+ *
+ * The QDict contains the following:
+ *
+ * - "device": device name
+ * - "type": device type
+ * - "removable": true if the device is removable, false otherwise
+ * - "locked": true if the device is locked, false otherwise
+ * - "inserted": only present if the device is inserted, it is a QDict
+ * containing the following:
+ * - "file": device file name
+ * - "ro": true if read-only, false otherwise
+ * - "drv": driver format name
+ * - "backing_file": backing file name if one is used
+ * - "encrypted": true if encrypted, false otherwise
+ *
+ * Example:
+ *
+ * [ { "device": "ide0-hd0", "type": "hd", "removable": false, "locked": false,
+ * "inserted": { "file": "/tmp/foobar", "ro": false, "drv": "qcow2" } },
+ * { "device": "floppy0", "type": "floppy", "removable": true,
+ * "locked": false } ]
+ */
+void bdrv_info(Monitor *mon, QObject **ret_data)
{
+ QList *bs_list;
BlockDriverState *bs;
- for (bs = bdrv_first; bs != NULL; bs = bs->next) {
- monitor_printf(mon, "%s:", bs->device_name);
- monitor_printf(mon, " type=");
+ bs_list = qlist_new();
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ QObject *bs_obj;
+ const char *type = "unknown";
+
switch(bs->type) {
case BDRV_TYPE_HD:
- monitor_printf(mon, "hd");
+ type = "hd";
break;
case BDRV_TYPE_CDROM:
- monitor_printf(mon, "cdrom");
+ type = "cdrom";
break;
case BDRV_TYPE_FLOPPY:
- monitor_printf(mon, "floppy");
+ type = "floppy";
break;
}
- monitor_printf(mon, " removable=%d", bs->removable);
- if (bs->removable) {
- monitor_printf(mon, " locked=%d", bs->locked);
- }
+
+ bs_obj = qobject_from_jsonf("{ 'device': %s, 'type': %s, "
+ "'removable': %i, 'locked': %i }",
+ bs->device_name, type, bs->removable,
+ bs->locked);
+
if (bs->drv) {
- monitor_printf(mon, " file=");
- monitor_print_filename(mon, bs->filename);
+ QObject *obj;
+ QDict *bs_dict = qobject_to_qdict(bs_obj);
+
+ obj = qobject_from_jsonf("{ 'file': %s, 'ro': %i, 'drv': %s, "
+ "'encrypted': %i }",
+ bs->filename, bs->read_only,
+ bs->drv->format_name,
+ bdrv_is_encrypted(bs));
if (bs->backing_file[0] != '\0') {
- monitor_printf(mon, " backing_file=");
- monitor_print_filename(mon, bs->backing_file);
+ QDict *qdict = qobject_to_qdict(obj);
+ qdict_put(qdict, "backing_file",
+ qstring_from_str(bs->backing_file));
}
- monitor_printf(mon, " ro=%d", bs->read_only);
- monitor_printf(mon, " drv=%s", bs->drv->format_name);
- monitor_printf(mon, " encrypted=%d", bdrv_is_encrypted(bs));
- } else {
- monitor_printf(mon, " [not inserted]");
+
+ qdict_put_obj(bs_dict, "inserted", obj);
}
- monitor_printf(mon, "\n");
+ qlist_append_obj(bs_list, bs_obj);
+ }
+
+ *ret_data = QOBJECT(bs_list);
+}
+
+static void bdrv_stats_iter(QObject *data, void *opaque)
+{
+ QDict *qdict;
+ Monitor *mon = opaque;
+
+ qdict = qobject_to_qdict(data);
+ monitor_printf(mon, "%s:", qdict_get_str(qdict, "device"));
+
+ qdict = qobject_to_qdict(qdict_get(qdict, "stats"));
+ monitor_printf(mon, " rd_bytes=%" PRId64
+ " wr_bytes=%" PRId64
+ " rd_operations=%" PRId64
+ " wr_operations=%" PRId64
+ "\n",
+ qdict_get_int(qdict, "rd_bytes"),
+ qdict_get_int(qdict, "wr_bytes"),
+ qdict_get_int(qdict, "rd_operations"),
+ qdict_get_int(qdict, "wr_operations"));
+}
+
+void bdrv_stats_print(Monitor *mon, const QObject *data)
+{
+ qlist_iter(qobject_to_qlist(data), bdrv_stats_iter, mon);
+}
+
+static QObject* bdrv_info_stats_bs(BlockDriverState *bs)
+{
+ QObject *res;
+ QDict *dict;
+
+ res = qobject_from_jsonf("{ 'stats': {"
+ "'rd_bytes': %" PRId64 ","
+ "'wr_bytes': %" PRId64 ","
+ "'rd_operations': %" PRId64 ","
+ "'wr_operations': %" PRId64 ","
+ "'wr_highest_offset': %" PRId64
+ "} }",
+ bs->rd_bytes, bs->wr_bytes,
+ bs->rd_ops, bs->wr_ops,
+ bs->wr_highest_sector * 512);
+ dict = qobject_to_qdict(res);
+
+ if (*bs->device_name) {
+ qdict_put(dict, "device", qstring_from_str(bs->device_name));
+ }
+
+ if (bs->file) {
+ QObject *parent = bdrv_info_stats_bs(bs->file);
+ qdict_put_obj(dict, "parent", parent);
}
+
+ return res;
}
-/* The "info blockstats" command. */
-void bdrv_info_stats(Monitor *mon)
+/**
+ * bdrv_info_stats(): show block device statistics
+ *
+ * Each device statistic information is stored in a QDict and
+ * the returned QObject is a QList of all devices.
+ *
+ * The QDict contains the following:
+ *
+ * - "device": device name
+ * - "stats": A QDict with the statistics information, it contains:
+ * - "rd_bytes": bytes read
+ * - "wr_bytes": bytes written
+ * - "rd_operations": read operations
+ * - "wr_operations": write operations
+ * - "wr_highest_offset": Highest offset of a sector written since the
+ * BlockDriverState has been opened
+ * - "parent": A QDict recursively holding the statistics of the underlying
+ * protocol (e.g. the host file for a qcow2 image). If there is no
+ * underlying protocol, this field is omitted.
+ *
+ * Example:
+ *
+ * [ { "device": "ide0-hd0",
+ * "stats": { "rd_bytes": 512,
+ * "wr_bytes": 0,
+ * "rd_operations": 1,
+ * "wr_operations": 0,
+ * "wr_highest_offset": 0 },
+ * "parent": {
+ * "stats": { "rd_bytes": 1024,
+ * "wr_bytes": 0,
+ * "rd_operations": 2,
+ * "wr_operations": 0,
+ * "wr_highest_offset": 0,
+ * } } },
+ * { "device": "ide1-cd0",
+ * "stats": { "rd_bytes": 0,
+ * "wr_bytes": 0,
+ * "rd_operations": 0,
+ * "wr_operations": 0,
+ * "wr_highest_offset": 0 } },
+ */
+void bdrv_info_stats(Monitor *mon, QObject **ret_data)
{
+ QObject *obj;
+ QList *devices;
BlockDriverState *bs;
- for (bs = bdrv_first; bs != NULL; bs = bs->next) {
- monitor_printf(mon, "%s:"
- " rd_bytes=%" PRIu64
- " wr_bytes=%" PRIu64
- " rd_operations=%" PRIu64
- " wr_operations=%" PRIu64
- "\n",
- bs->device_name,
- bs->rd_bytes, bs->wr_bytes,
- bs->rd_ops, bs->wr_ops);
+ devices = qlist_new();
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ obj = bdrv_info_stats_bs(bs);
+ qlist_append_obj(devices, obj);
}
+
+ *ret_data = QOBJECT(devices);
}
const char *bdrv_get_encrypted_filename(BlockDriverState *bs)
void bdrv_get_backing_filename(BlockDriverState *bs,
char *filename, int filename_size)
{
- if (!bs->backing_hd) {
+ if (!bs->backing_file) {
pstrcpy(filename, filename_size, "");
} else {
pstrcpy(filename, filename_size, bs->backing_file);
return -ENOMEDIUM;
if (!drv->bdrv_write_compressed)
return -ENOTSUP;
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return -EIO;
+
+ if (bs->dirty_bitmap) {
+ set_dirty_bitmap(bs, sector_num, nb_sectors, 1);
+ }
+
return drv->bdrv_write_compressed(bs, sector_num, buf, nb_sectors);
}
return drv->bdrv_get_info(bs, bdi);
}
-int bdrv_put_buffer(BlockDriverState *bs, const uint8_t *buf, int64_t pos, int size)
+int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
+ int64_t pos, int size)
{
BlockDriver *drv = bs->drv;
if (!drv)
return -ENOMEDIUM;
- if (!drv->bdrv_put_buffer)
+ if (!drv->bdrv_save_vmstate)
return -ENOTSUP;
- return drv->bdrv_put_buffer(bs, buf, pos, size);
+ return drv->bdrv_save_vmstate(bs, buf, pos, size);
}
-int bdrv_get_buffer(BlockDriverState *bs, uint8_t *buf, int64_t pos, int size)
+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_get_buffer)
+ if (!drv->bdrv_load_vmstate)
return -ENOTSUP;
- return drv->bdrv_get_buffer(bs, buf, pos, size);
+ return drv->bdrv_load_vmstate(bs, buf, pos, size);
+}
+
+void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (!drv || !drv->bdrv_debug_event) {
+ return;
+ }
+
+ return drv->bdrv_debug_event(bs, event);
+
}
/**************************************************************/
/**************************************************************/
/* async I/Os */
-typedef struct VectorTranslationAIOCB {
- BlockDriverAIOCB common;
- QEMUIOVector *iov;
- uint8_t *bounce;
- int is_write;
- BlockDriverAIOCB *aiocb;
-} VectorTranslationAIOCB;
-
-static void bdrv_aio_cancel_vector(BlockDriverAIOCB *_acb)
+BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
{
- VectorTranslationAIOCB *acb
- = container_of(_acb, VectorTranslationAIOCB, common);
+ BlockDriver *drv = bs->drv;
+ BlockDriverAIOCB *ret;
+
+ if (!drv)
+ return NULL;
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return NULL;
+
+ ret = drv->bdrv_aio_readv(bs, sector_num, qiov, nb_sectors,
+ cb, opaque);
+
+ if (ret) {
+ /* Update stats even though technically transfer has not happened. */
+ bs->rd_bytes += (unsigned) nb_sectors * BDRV_SECTOR_SIZE;
+ bs->rd_ops ++;
+ }
- bdrv_aio_cancel(acb->aiocb);
+ return ret;
}
-static void bdrv_aio_rw_vector_cb(void *opaque, int ret)
+BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
{
- VectorTranslationAIOCB *s = (VectorTranslationAIOCB *)opaque;
+ BlockDriver *drv = bs->drv;
+ BlockDriverAIOCB *ret;
+
+ if (!drv)
+ return NULL;
+ if (bs->read_only)
+ return NULL;
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return NULL;
+
+ if (bs->dirty_bitmap) {
+ set_dirty_bitmap(bs, sector_num, nb_sectors, 1);
+ }
+
+ ret = drv->bdrv_aio_writev(bs, sector_num, qiov, nb_sectors,
+ cb, opaque);
- if (!s->is_write) {
- qemu_iovec_from_buffer(s->iov, s->bounce, s->iov->size);
+ if (ret) {
+ /* Update stats even though technically transfer has not happened. */
+ bs->wr_bytes += (unsigned) nb_sectors * BDRV_SECTOR_SIZE;
+ bs->wr_ops ++;
+ if (bs->wr_highest_sector < sector_num + nb_sectors - 1) {
+ bs->wr_highest_sector = sector_num + nb_sectors - 1;
+ }
}
- qemu_vfree(s->bounce);
- s->common.cb(s->common.opaque, ret);
- qemu_aio_release(s);
+
+ return ret;
}
-static BlockDriverAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
- int64_t sector_num,
- QEMUIOVector *iov,
- int nb_sectors,
- BlockDriverCompletionFunc *cb,
- void *opaque,
- int is_write)
+typedef struct MultiwriteCB {
+ int error;
+ int num_requests;
+ int num_callbacks;
+ struct {
+ BlockDriverCompletionFunc *cb;
+ void *opaque;
+ QEMUIOVector *free_qiov;
+ void *free_buf;
+ } callbacks[];
+} MultiwriteCB;
+
+static void multiwrite_user_cb(MultiwriteCB *mcb)
{
- VectorTranslationAIOCB *s = qemu_aio_get_pool(&vectored_aio_pool, bs,
- cb, opaque);
+ int i;
- s->iov = iov;
- s->bounce = qemu_memalign(512, nb_sectors * 512);
- s->is_write = is_write;
- if (is_write) {
- qemu_iovec_to_buffer(s->iov, s->bounce);
- s->aiocb = bdrv_aio_write(bs, sector_num, s->bounce, nb_sectors,
- bdrv_aio_rw_vector_cb, s);
- } else {
- s->aiocb = bdrv_aio_read(bs, sector_num, s->bounce, nb_sectors,
- bdrv_aio_rw_vector_cb, s);
- }
- if (!s->aiocb) {
- qemu_vfree(s->bounce);
- qemu_aio_release(s);
- return NULL;
+ 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);
+ }
+ qemu_free(mcb->callbacks[i].free_qiov);
+ qemu_vfree(mcb->callbacks[i].free_buf);
}
- return &s->common;
}
-BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
- QEMUIOVector *iov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+static void multiwrite_cb(void *opaque, int ret)
{
- if (bdrv_check_request(bs, sector_num, nb_sectors))
- return NULL;
+ MultiwriteCB *mcb = opaque;
+
+ if (ret < 0 && !mcb->error) {
+ mcb->error = ret;
+ multiwrite_user_cb(mcb);
+ }
- return bdrv_aio_rw_vector(bs, sector_num, iov, nb_sectors,
- cb, opaque, 0);
+ mcb->num_requests--;
+ if (mcb->num_requests == 0) {
+ if (mcb->error == 0) {
+ multiwrite_user_cb(mcb);
+ }
+ qemu_free(mcb);
+ }
}
-BlockDriverAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num,
- QEMUIOVector *iov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+static int multiwrite_req_compare(const void *a, const void *b)
{
- if (bdrv_check_request(bs, sector_num, nb_sectors))
- return NULL;
+ const BlockRequest *req1 = a, *req2 = b;
- return bdrv_aio_rw_vector(bs, sector_num, iov, nb_sectors,
- cb, opaque, 1);
+ /*
+ * 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;
+ }
}
-BlockDriverAIOCB *bdrv_aio_read(BlockDriverState *bs, int64_t sector_num,
- uint8_t *buf, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+/*
+ * 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)
{
- BlockDriver *drv = bs->drv;
- BlockDriverAIOCB *ret;
+ int i, outidx;
- if (!drv)
- return NULL;
- if (bdrv_check_request(bs, sector_num, nb_sectors))
- return NULL;
+ // Sort requests by start sector
+ qsort(reqs, num_reqs, sizeof(*reqs), &multiwrite_req_compare);
- ret = drv->bdrv_aio_read(bs, sector_num, buf, nb_sectors, cb, opaque);
+ // 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;
- if (ret) {
- /* Update stats even though technically transfer has not happened. */
- bs->rd_bytes += (unsigned) nb_sectors * SECTOR_SIZE;
- bs->rd_ops ++;
+ // This handles the cases that are valid for all block drivers, namely
+ // exactly sequential writes and overlapping writes.
+ if (reqs[i].sector <= oldreq_last) {
+ merge = 1;
+ }
+
+ // The block driver may decide that it makes sense to combine requests
+ // even if there is a gap of some sectors between them. In this case,
+ // the gap is filled with zeros (therefore only applicable for yet
+ // unused space in format like qcow2).
+ if (!merge && bs->drv->bdrv_merge_requests) {
+ merge = bs->drv->bdrv_merge_requests(bs, &reqs[outidx], &reqs[i]);
+ }
+
+ if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 > IOV_MAX) {
+ merge = 0;
+ }
+
+ if (merge) {
+ size_t size;
+ QEMUIOVector *qiov = qemu_mallocz(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, size);
+
+ // We might need to add some zeros between the two requests
+ if (reqs[i].sector > oldreq_last) {
+ size_t zero_bytes = (reqs[i].sector - oldreq_last) << 9;
+ uint8_t *buf = qemu_blockalign(bs, zero_bytes);
+ memset(buf, 0, zero_bytes);
+ qemu_iovec_add(qiov, buf, zero_bytes);
+ mcb->callbacks[i].free_buf = buf;
+ }
+
+ // Add the second request
+ qemu_iovec_concat(qiov, reqs[i].qiov, reqs[i].qiov->size);
+
+ reqs[outidx].nb_sectors += reqs[i].nb_sectors;
+ 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 ret;
+ return outidx + 1;
}
-BlockDriverAIOCB *bdrv_aio_write(BlockDriverState *bs, int64_t sector_num,
- const uint8_t *buf, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+/*
+ * 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)
{
- BlockDriver *drv = bs->drv;
- BlockDriverAIOCB *ret;
+ BlockDriverAIOCB *acb;
+ MultiwriteCB *mcb;
+ int i;
- if (!drv)
- return NULL;
- if (bs->read_only)
- return NULL;
- if (bdrv_check_request(bs, sector_num, nb_sectors))
- return NULL;
+ if (num_reqs == 0) {
+ return 0;
+ }
- ret = drv->bdrv_aio_write(bs, sector_num, buf, nb_sectors, cb, opaque);
+ // Create MultiwriteCB structure
+ mcb = qemu_mallocz(sizeof(*mcb) + num_reqs * sizeof(*mcb->callbacks));
+ mcb->num_requests = 0;
+ mcb->num_callbacks = num_reqs;
- if (ret) {
- /* Update stats even though technically transfer has not happened. */
- bs->wr_bytes += (unsigned) nb_sectors * SECTOR_SIZE;
- bs->wr_ops ++;
+ for (i = 0; i < num_reqs; i++) {
+ mcb->callbacks[i].cb = reqs[i].cb;
+ mcb->callbacks[i].opaque = reqs[i].opaque;
}
- return ret;
+ // Check for mergable requests
+ num_reqs = multiwrite_merge(bs, reqs, num_reqs, mcb);
+
+ // Run the aio requests
+ for (i = 0; i < num_reqs; i++) {
+ acb = bdrv_aio_writev(bs, reqs[i].sector, reqs[i].qiov,
+ reqs[i].nb_sectors, multiwrite_cb, mcb);
+
+ if (acb == NULL) {
+ // We can only fail the whole thing if no request has been
+ // submitted yet. Otherwise we'll wait for the submitted AIOs to
+ // complete and report the error in the callback.
+ if (mcb->num_requests == 0) {
+ reqs[i].error = -EIO;
+ goto fail;
+ } else {
+ mcb->num_requests++;
+ multiwrite_cb(mcb, -EIO);
+ break;
+ }
+ } else {
+ mcb->num_requests++;
+ }
+ }
+
+ return 0;
+
+fail:
+ qemu_free(mcb);
+ return -1;
+}
+
+BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (!drv)
+ return NULL;
+ return drv->bdrv_aio_flush(bs, cb, opaque);
}
void bdrv_aio_cancel(BlockDriverAIOCB *acb)
/**************************************************************/
/* 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 AIOPool bdrv_em_aio_pool = {
+ .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_buffer(acb->qiov, 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_read_em(BlockDriverState *bs,
- int64_t sector_num, uint8_t *buf, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+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;
- int ret;
- acb = qemu_aio_get(bs, cb, opaque);
+ acb = qemu_aio_get(&bdrv_em_aio_pool, bs, cb, opaque);
+ acb->is_write = is_write;
+ acb->qiov = qiov;
+ acb->bounce = qemu_blockalign(bs, qiov->size);
+
if (!acb->bh)
acb->bh = qemu_bh_new(bdrv_aio_bh_cb, acb);
- ret = bdrv_read(bs, sector_num, buf, nb_sectors);
- acb->ret = ret;
+
+ if (is_write) {
+ qemu_iovec_to_buffer(acb->qiov, acb->bounce);
+ acb->ret = bdrv_write(bs, sector_num, acb->bounce, nb_sectors);
+ } else {
+ acb->ret = bdrv_read(bs, sector_num, acb->bounce, nb_sectors);
+ }
+
qemu_bh_schedule(acb->bh);
+
return &acb->common;
}
-static BlockDriverAIOCB *bdrv_aio_write_em(BlockDriverState *bs,
- int64_t sector_num, const uint8_t *buf, int nb_sectors,
+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);
+}
+
+static BlockDriverAIOCB *bdrv_aio_flush_em(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque)
{
BlockDriverAIOCBSync *acb;
- int ret;
- acb = qemu_aio_get(bs, cb, opaque);
+ acb = qemu_aio_get(&bdrv_em_aio_pool, bs, cb, opaque);
+ acb->is_write = 1; /* don't bounce in the completion hadler */
+ acb->qiov = NULL;
+ acb->bounce = NULL;
+ acb->ret = 0;
+
if (!acb->bh)
acb->bh = qemu_bh_new(bdrv_aio_bh_cb, acb);
- ret = bdrv_write(bs, sector_num, buf, nb_sectors);
- acb->ret = ret;
+
+ bdrv_flush(bs);
qemu_bh_schedule(acb->bh);
return &acb->common;
}
-static void bdrv_aio_cancel_em(BlockDriverAIOCB *blockacb)
-{
- BlockDriverAIOCBSync *acb = (BlockDriverAIOCBSync *)blockacb;
- qemu_bh_cancel(acb->bh);
- qemu_aio_release(acb);
-}
-
/**************************************************************/
/* sync block device emulation */
{
int async_ret;
BlockDriverAIOCB *acb;
+ struct iovec iov;
+ QEMUIOVector qiov;
+
+ async_context_push();
async_ret = NOT_DONE;
- acb = bdrv_aio_read(bs, sector_num, buf, nb_sectors,
- bdrv_rw_em_cb, &async_ret);
- if (acb == NULL)
- return -1;
+ iov.iov_base = (void *)buf;
+ iov.iov_len = nb_sectors * 512;
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ acb = bdrv_aio_readv(bs, sector_num, &qiov, nb_sectors,
+ bdrv_rw_em_cb, &async_ret);
+ if (acb == NULL) {
+ async_ret = -1;
+ goto fail;
+ }
while (async_ret == NOT_DONE) {
qemu_aio_wait();
}
+
+fail:
+ async_context_pop();
return async_ret;
}
{
int async_ret;
BlockDriverAIOCB *acb;
+ struct iovec iov;
+ QEMUIOVector qiov;
+
+ async_context_push();
async_ret = NOT_DONE;
- acb = bdrv_aio_write(bs, sector_num, buf, nb_sectors,
- bdrv_rw_em_cb, &async_ret);
- if (acb == NULL)
- return -1;
+ iov.iov_base = (void *)buf;
+ iov.iov_len = nb_sectors * 512;
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ acb = bdrv_aio_writev(bs, sector_num, &qiov, nb_sectors,
+ bdrv_rw_em_cb, &async_ret);
+ if (acb == NULL) {
+ async_ret = -1;
+ goto fail;
+ }
while (async_ret == NOT_DONE) {
qemu_aio_wait();
}
+
+fail:
+ async_context_pop();
return async_ret;
}
void bdrv_init(void)
{
- aio_pool_init(&vectored_aio_pool, sizeof(VectorTranslationAIOCB),
- bdrv_aio_cancel_vector);
-
- bdrv_register(&bdrv_raw);
- bdrv_register(&bdrv_host_device);
-#ifndef _WIN32
- bdrv_register(&bdrv_cow);
-#endif
- bdrv_register(&bdrv_qcow);
- bdrv_register(&bdrv_vmdk);
- bdrv_register(&bdrv_cloop);
- bdrv_register(&bdrv_dmg);
- bdrv_register(&bdrv_bochs);
- bdrv_register(&bdrv_vpc);
- bdrv_register(&bdrv_vvfat);
- bdrv_register(&bdrv_qcow2);
- bdrv_register(&bdrv_parallels);
- bdrv_register(&bdrv_nbd);
+ module_call_init(MODULE_INIT_BLOCK);
}
-void aio_pool_init(AIOPool *pool, int aiocb_size,
- void (*cancel)(BlockDriverAIOCB *acb))
+void bdrv_init_with_whitelist(void)
{
- pool->aiocb_size = aiocb_size;
- pool->cancel = cancel;
- pool->free_aiocb = NULL;
+ use_bdrv_whitelist = 1;
+ bdrv_init();
}
-void *qemu_aio_get_pool(AIOPool *pool, BlockDriverState *bs,
- BlockDriverCompletionFunc *cb, void *opaque)
+void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque)
{
BlockDriverAIOCB *acb;
return acb;
}
-void *qemu_aio_get(BlockDriverState *bs, BlockDriverCompletionFunc *cb,
- void *opaque)
-{
- return qemu_aio_get_pool(&bs->drv->aio_pool, bs, cb, opaque);
-}
-
void qemu_aio_release(void *p)
{
BlockDriverAIOCB *acb = (BlockDriverAIOCB *)p;
/**
* If eject_flag is TRUE, eject the media. Otherwise, close the tray
*/
-void bdrv_eject(BlockDriverState *bs, int eject_flag)
+int bdrv_eject(BlockDriverState *bs, int eject_flag)
{
BlockDriver *drv = bs->drv;
int ret;
+ if (bs->locked) {
+ return -EBUSY;
+ }
+
if (!drv || !drv->bdrv_eject) {
ret = -ENOTSUP;
} else {
if (ret == -ENOTSUP) {
if (eject_flag)
bdrv_close(bs);
+ ret = 0;
}
+
+ return ret;
}
int bdrv_is_locked(BlockDriverState *bs)
return drv->bdrv_aio_ioctl(bs, req, buf, cb, opaque);
return NULL;
}
+
+
+
+void *qemu_blockalign(BlockDriverState *bs, size_t size)
+{
+ return qemu_memalign((bs && bs->buffer_alignment) ? bs->buffer_alignment : 512, size);
+}
+
+void bdrv_set_dirty_tracking(BlockDriverState *bs, int enable)
+{
+ int64_t bitmap_size;
+
+ bs->dirty_count = 0;
+ if (enable) {
+ if (!bs->dirty_bitmap) {
+ bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS) +
+ BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
+ bitmap_size /= BDRV_SECTORS_PER_DIRTY_CHUNK * 8;
+
+ bs->dirty_bitmap = qemu_mallocz(bitmap_size);
+ }
+ } else {
+ if (bs->dirty_bitmap) {
+ qemu_free(bs->dirty_bitmap);
+ bs->dirty_bitmap = NULL;
+ }
+ }
+}
+
+int bdrv_get_dirty(BlockDriverState *bs, int64_t sector)
+{
+ int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
+
+ if (bs->dirty_bitmap &&
+ (sector << BDRV_SECTOR_BITS) < bdrv_getlength(bs)) {
+ return bs->dirty_bitmap[chunk / (sizeof(unsigned long) * 8)] &
+ (1 << (chunk % (sizeof(unsigned long) * 8)));
+ } else {
+ return 0;
+ }
+}
+
+void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
+ int nr_sectors)
+{
+ set_dirty_bitmap(bs, cur_sector, nr_sectors, 0);
+}
+
+int64_t bdrv_get_dirty_count(BlockDriverState *bs)
+{
+ return bs->dirty_count;
+}
projects / qemu.git / blobdiff