/*
* 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
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
-#include "vl.h"
+#include "config-host.h"
+#include "qemu-common.h"
+#include "monitor.h"
#include "block_int.h"
+#include "module.h"
-#ifdef _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
+#endif
+
+#ifdef _WIN32
+#include <windows.h>
+#endif
#define SECTOR_BITS 9
#define SECTOR_SIZE (1 << SECTOR_BITS)
-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_writev_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_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,
+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 BlockDriverState *bdrv_first;
-static BlockDriver *first_drv;
+BlockDriverState *bdrv_first;
-#ifdef _WIN32
-#define PATH_SEP '\\'
-#else
-#define PATH_SEP '/'
-#endif
+static BlockDriver *first_drv;
int path_is_absolute(const char *path)
{
const char *p;
+#ifdef _WIN32
+ /* specific case for names like: "\\.\d:" */
+ if (*path == '/' || *path == '\\')
+ return 1;
+#endif
p = strchr(path, ':');
if (p)
p++;
else
p = path;
- return (*p == PATH_SEP);
+#ifdef _WIN32
+ return (*p == '/' || *p == '\\');
+#else
+ return (*p == '/');
+#endif
}
/* if filename is absolute, just copy it to dest. Otherwise, build a
p++;
else
p = base_path;
- p1 = strrchr(base_path, PATH_SEP);
+ p1 = strrchr(base_path, '/');
+#ifdef _WIN32
+ {
+ const char *p2;
+ p2 = strrchr(base_path, '\\');
+ if (!p1 || p2 > p1)
+ p1 = p2;
+ }
+#endif
if (p1)
p1++;
else
}
}
-
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);
- } else if (!bdrv->bdrv_read && !bdrv->bdrv_pread) {
+ 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;
}
+
+ if (!bdrv->bdrv_aio_flush)
+ bdrv->bdrv_aio_flush = bdrv_aio_flush_em;
+
bdrv->next = first_drv;
first_drv = bdrv;
}
BlockDriverState **pbs, *bs;
bs = qemu_mallocz(sizeof(BlockDriverState));
- if(!bs)
- return NULL;
pstrcpy(bs->device_name, sizeof(bs->device_name), device_name);
if (device_name[0] != '\0') {
/* insert at the end */
return 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);
}
#ifdef _WIN32
void get_tmp_filename(char *filename, int size)
{
- tmpnam(filename);
+ char temp_dir[MAX_PATH];
+
+ GetTempPath(MAX_PATH, temp_dir);
+ GetTempFileName(temp_dir, "qem", 0, filename);
}
#else
void get_tmp_filename(char *filename, int size)
{
int fd;
+ const char *tmpdir;
/* XXX: race condition possible */
- pstrcpy(filename, size, "/tmp/vl.XXXXXX");
+ tmpdir = getenv("TMPDIR");
+ if (!tmpdir)
+ tmpdir = "/tmp";
+ snprintf(filename, size, "%s/vl.XXXXXX", tmpdir);
fd = mkstemp(filename);
close(fd);
}
(filename[0] >= 'A' && filename[0] <= 'Z')) &&
filename[1] == ':');
}
-
-static int is_windows_drive(const char *filename)
+
+int is_windows_drive(const char *filename)
{
- if (is_windows_drive_prefix(filename) &&
+ if (is_windows_drive_prefix(filename) &&
filename[2] == '\0')
return 1;
if (strstart(filename, "\\\\.\\", NULL) ||
#ifdef _WIN32
if (is_windows_drive(filename) ||
is_windows_drive_prefix(filename))
- return &bdrv_raw;
+ return bdrv_find_format("raw");
#endif
p = strchr(filename, ':');
if (!p)
- return &bdrv_raw;
+ return bdrv_find_format("raw");
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) {
- if (drv1->protocol_name &&
+ if (drv1->protocol_name &&
!strcmp(drv1->protocol_name, protocol))
return drv1;
}
return NULL;
}
-/* XXX: force raw format if block or character device ? It would
- simplify the BSD case */
+/*
+ * 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;
+
+ for (d = first_drv; d; d = d->next) {
+ 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_image_format(const char *filename)
{
int ret, score, score_max;
BlockDriver *drv1, *drv;
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)
+ if (drv && strcmp(drv->format_name, "vvfat") == 0)
return drv;
ret = bdrv_file_open(&bs, filename, BDRV_O_RDONLY);
int ret;
bs = bdrv_new("");
- if (!bs)
- return -ENOMEM;
ret = bdrv_open2(bs, filename, flags | BDRV_O_FILE, NULL);
if (ret < 0) {
bdrv_delete(bs);
return ret;
}
+ bs->growable = 1;
*pbs = bs;
return 0;
}
BlockDriver *drv)
{
int ret, open_flags;
- char tmp_filename[1024];
- char backing_filename[1024];
-
+ 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;
+ /* buffer_alignment defaulted to 512, drivers can change this value */
+ bs->buffer_alignment = 512;
if (flags & BDRV_O_SNAPSHOT) {
BlockDriverState *bs1;
int64_t total_size;
-
+ int is_protocol = 0;
+ BlockDriver *bdrv_qcow2;
+ QEMUOptionParameter *options;
+
/* 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("");
- if (!bs1) {
- return -ENOMEM;
- }
- if (bdrv_open(bs1, filename, 0) < 0) {
+ ret = bdrv_open2(bs1, filename, 0, drv);
+ if (ret < 0) {
bdrv_delete(bs1);
- return -1;
+ return ret;
}
total_size = bdrv_getlength(bs1) >> SECTOR_BITS;
+
+ if (bs1->drv && bs1->drv->protocol_name)
+ is_protocol = 1;
+
bdrv_delete(bs1);
-
+
get_tmp_filename(tmp_filename, sizeof(tmp_filename));
- realpath(filename, backing_filename);
- if (bdrv_create(&bdrv_qcow2, tmp_filename,
- total_size, backing_filename, 0) < 0) {
- return -1;
+
+ /* Real path is meaningless for protocols */
+ if (is_protocol)
+ snprintf(backing_filename, sizeof(backing_filename),
+ "%s", filename);
+ else
+ realpath(filename, backing_filename);
+
+ 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_create(bdrv_qcow2, tmp_filename, options);
+ if (ret < 0) {
+ return ret;
}
+
filename = tmp_filename;
+ drv = bdrv_qcow2;
bs->is_temporary = 1;
}
pstrcpy(bs->filename, sizeof(bs->filename), filename);
if (flags & BDRV_O_FILE) {
drv = find_protocol(filename);
- if (!drv)
- return -ENOENT;
- } else {
+ } else if (!drv) {
+ drv = find_hdev_driver(filename);
if (!drv) {
drv = find_image_format(filename);
- if (!drv)
- return -1;
}
}
+ if (!drv) {
+ ret = -ENOENT;
+ goto unlink_and_fail;
+ }
bs->drv = drv;
bs->opaque = qemu_mallocz(drv->instance_size);
- if (bs->opaque == NULL && drv->instance_size > 0)
- return -1;
+
+ /*
+ * 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;
+
/* Note: for compatibility, we open disk image files as RDWR, and
RDONLY as fallback */
if (!(flags & BDRV_O_FILE))
- open_flags = BDRV_O_RDWR;
+ open_flags = BDRV_O_RDWR |
+ (flags & (BDRV_O_CACHE_MASK|BDRV_O_NATIVE_AIO));
else
open_flags = flags & ~(BDRV_O_FILE | BDRV_O_SNAPSHOT);
ret = drv->bdrv_open(bs, filename, open_flags);
- if (ret == -EACCES && !(flags & BDRV_O_FILE)) {
- ret = drv->bdrv_open(bs, filename, BDRV_O_RDONLY);
+ if ((ret == -EACCES || ret == -EPERM) && !(flags & BDRV_O_FILE)) {
+ ret = drv->bdrv_open(bs, filename, open_flags & ~BDRV_O_RDWR);
bs->read_only = 1;
}
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) {
#endif
if (bs->backing_file[0] != '\0') {
/* if there is a backing file, use it */
+ BlockDriver *back_drv = NULL;
bs->backing_hd = bdrv_new("");
- if (!bs->backing_hd) {
- fail:
- bdrv_close(bs);
- return -ENOMEM;
- }
path_combine(backing_filename, sizeof(backing_filename),
filename, bs->backing_file);
- if (bdrv_open(bs->backing_hd, backing_filename, 0) < 0)
- goto fail;
+ 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);
+ if (ret < 0) {
+ bdrv_close(bs);
+ return ret;
+ }
}
- /* call the change callback */
- bs->media_changed = 1;
- if (bs->change_cb)
- bs->change_cb(bs->change_opaque);
-
+ if (!bdrv_key_required(bs)) {
+ /* call the change callback */
+ bs->media_changed = 1;
+ if (bs->change_cb)
+ bs->change_cb(bs->change_opaque);
+ }
return 0;
}
void bdrv_delete(BlockDriverState *bs)
{
- /* XXX: remove the driver list */
+ BlockDriverState **pbs;
+
+ pbs = &bdrv_first;
+ while (*pbs != bs && *pbs != NULL)
+ pbs = &(*pbs)->next;
+ if (*pbs == bs)
+ *pbs = bs->next;
+
bdrv_close(bs);
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)
{
return 0;
}
+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 * 512, nb_sectors * 512);
+}
+
/* return < 0 if error. See bdrv_write() for the return codes */
-int bdrv_read(BlockDriverState *bs, int64_t sector_num,
+int bdrv_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
BlockDriver *drv = bs->drv;
if (!drv)
return -ENOMEDIUM;
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return -EIO;
- if (sector_num == 0 && bs->boot_sector_enabled && nb_sectors > 0) {
- memcpy(buf, bs->boot_sector_data, 512);
- sector_num++;
- nb_sectors--;
- buf += 512;
- if (nb_sectors == 0)
- return 0;
- }
- if (drv->bdrv_pread) {
- int ret, len;
- len = nb_sectors * 512;
- ret = drv->bdrv_pread(bs, sector_num * 512, buf, len);
- if (ret < 0)
- return ret;
- else if (ret != len)
- return -EINVAL;
- else
- return 0;
- } else {
- return drv->bdrv_read(bs, sector_num, buf, nb_sectors);
- }
+ return drv->bdrv_read(bs, sector_num, buf, nb_sectors);
}
-/* Return < 0 if error. Important errors are:
+/* 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,
+int bdrv_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BlockDriver *drv = bs->drv;
return -ENOMEDIUM;
if (bs->read_only)
return -EACCES;
- if (sector_num == 0 && bs->boot_sector_enabled && nb_sectors > 0) {
- memcpy(bs->boot_sector_data, buf, 512);
- }
- if (drv->bdrv_pwrite) {
- int ret, len;
- len = nb_sectors * 512;
- ret = drv->bdrv_pwrite(bs, sector_num * 512, buf, len);
- if (ret < 0)
- return ret;
- else if (ret != len)
- return -EIO;
- else
- return 0;
- } else {
- return drv->bdrv_write(bs, sector_num, buf, nb_sectors);
- }
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return -EIO;
+
+ return drv->bdrv_write(bs, sector_num, buf, nb_sectors);
}
-static int bdrv_pread_em(BlockDriverState *bs, int64_t offset,
- uint8_t *buf, int count1)
+int bdrv_pread(BlockDriverState *bs, int64_t offset,
+ void *buf, int count1)
{
uint8_t tmp_buf[SECTOR_SIZE];
int len, nb_sectors, count;
return count1;
}
-static int bdrv_pwrite_em(BlockDriverState *bs, int64_t offset,
- const uint8_t *buf, int count1)
+int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
+ const void *buf, int count1)
{
uint8_t tmp_buf[SECTOR_SIZE];
int len, nb_sectors, count;
return count1;
}
-/**
- * Read with byte offsets (needed only for file protocols)
- */
-int bdrv_pread(BlockDriverState *bs, int64_t offset,
- void *buf1, int count1)
-{
- BlockDriver *drv = bs->drv;
-
- if (!drv)
- return -ENOMEDIUM;
- if (!drv->bdrv_pread)
- return bdrv_pread_em(bs, offset, buf1, count1);
- return drv->bdrv_pread(bs, offset, buf1, count1);
-}
-
-/**
- * Write with byte offsets (needed only for file protocols)
- */
-int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
- const void *buf1, int count1)
-{
- BlockDriver *drv = bs->drv;
-
- if (!drv)
- return -ENOMEDIUM;
- if (!drv->bdrv_pwrite)
- return bdrv_pwrite_em(bs, offset, buf1, count1);
- return drv->bdrv_pwrite(bs, offset, buf1, count1);
-}
-
/**
* Truncate file to 'offset' bytes (needed only for file protocols)
*/
}
/* return 0 as number of sectors if no device present or error */
-void bdrv_get_geometry(BlockDriverState *bs, int64_t *nb_sectors_ptr)
+void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
{
int64_t length;
length = bdrv_getlength(bs);
*nb_sectors_ptr = length;
}
-/* force a given boot sector. */
-void bdrv_set_boot_sector(BlockDriverState *bs, const uint8_t *data, int size)
+struct partition {
+ uint8_t boot_ind; /* 0x80 - active */
+ uint8_t head; /* starting head */
+ uint8_t sector; /* starting sector */
+ uint8_t cyl; /* starting cylinder */
+ uint8_t sys_ind; /* What partition type */
+ uint8_t end_head; /* end head */
+ uint8_t end_sector; /* end sector */
+ uint8_t end_cyl; /* end cylinder */
+ uint32_t start_sect; /* starting sector counting from 0 */
+ uint32_t nr_sects; /* nr of sectors in partition */
+} __attribute__((packed));
+
+/* try to guess the disk logical geometry from the MSDOS partition table. Return 0 if OK, -1 if could not guess */
+static int guess_disk_lchs(BlockDriverState *bs,
+ int *pcylinders, int *pheads, int *psectors)
+{
+ uint8_t buf[512];
+ int ret, i, heads, sectors, cylinders;
+ struct partition *p;
+ uint32_t nr_sects;
+ uint64_t nb_sectors;
+
+ bdrv_get_geometry(bs, &nb_sectors);
+
+ ret = bdrv_read(bs, 0, buf, 1);
+ if (ret < 0)
+ return -1;
+ /* test msdos magic */
+ if (buf[510] != 0x55 || buf[511] != 0xaa)
+ return -1;
+ for(i = 0; i < 4; i++) {
+ p = ((struct partition *)(buf + 0x1be)) + i;
+ nr_sects = le32_to_cpu(p->nr_sects);
+ if (nr_sects && p->end_head) {
+ /* We make the assumption that the partition terminates on
+ a cylinder boundary */
+ heads = p->end_head + 1;
+ sectors = p->end_sector & 63;
+ if (sectors == 0)
+ continue;
+ cylinders = nb_sectors / (heads * sectors);
+ if (cylinders < 1 || cylinders > 16383)
+ continue;
+ *pheads = heads;
+ *psectors = sectors;
+ *pcylinders = cylinders;
+#if 0
+ printf("guessed geometry: LCHS=%d %d %d\n",
+ cylinders, heads, sectors);
+#endif
+ return 0;
+ }
+ }
+ return -1;
+}
+
+void bdrv_guess_geometry(BlockDriverState *bs, int *pcyls, int *pheads, int *psecs)
{
- bs->boot_sector_enabled = 1;
- if (size > 512)
- size = 512;
- memcpy(bs->boot_sector_data, data, size);
- memset(bs->boot_sector_data + size, 0, 512 - size);
+ int translation, lba_detected = 0;
+ int cylinders, heads, secs;
+ uint64_t nb_sectors;
+
+ /* if a geometry hint is available, use it */
+ bdrv_get_geometry(bs, &nb_sectors);
+ bdrv_get_geometry_hint(bs, &cylinders, &heads, &secs);
+ translation = bdrv_get_translation_hint(bs);
+ if (cylinders != 0) {
+ *pcyls = cylinders;
+ *pheads = heads;
+ *psecs = secs;
+ } else {
+ if (guess_disk_lchs(bs, &cylinders, &heads, &secs) == 0) {
+ if (heads > 16) {
+ /* if heads > 16, it means that a BIOS LBA
+ translation was active, so the default
+ hardware geometry is OK */
+ lba_detected = 1;
+ goto default_geometry;
+ } else {
+ *pcyls = cylinders;
+ *pheads = heads;
+ *psecs = secs;
+ /* disable any translation to be in sync with
+ the logical geometry */
+ if (translation == BIOS_ATA_TRANSLATION_AUTO) {
+ bdrv_set_translation_hint(bs,
+ BIOS_ATA_TRANSLATION_NONE);
+ }
+ }
+ } else {
+ default_geometry:
+ /* if no geometry, use a standard physical disk geometry */
+ cylinders = nb_sectors / (16 * 63);
+
+ if (cylinders > 16383)
+ cylinders = 16383;
+ else if (cylinders < 2)
+ cylinders = 2;
+ *pcyls = cylinders;
+ *pheads = 16;
+ *psecs = 63;
+ if ((lba_detected == 1) && (translation == BIOS_ATA_TRANSLATION_AUTO)) {
+ if ((*pcyls * *pheads) <= 131072) {
+ bdrv_set_translation_hint(bs,
+ BIOS_ATA_TRANSLATION_LARGE);
+ } else {
+ bdrv_set_translation_hint(bs,
+ BIOS_ATA_TRANSLATION_LBA);
+ }
+ }
+ }
+ bdrv_set_geometry_hint(bs, *pcyls, *pheads, *psecs);
+ }
}
-void bdrv_set_geometry_hint(BlockDriverState *bs,
+void bdrv_set_geometry_hint(BlockDriverState *bs,
int cyls, int heads, int secs)
{
bs->cyls = cyls;
bs->translation = translation;
}
-void bdrv_get_geometry_hint(BlockDriverState *bs,
+void bdrv_get_geometry_hint(BlockDriverState *bs,
int *pcyls, int *pheads, int *psecs)
{
*pcyls = bs->cyls;
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;
+}
+
/* XXX: no longer used */
-void bdrv_set_change_cb(BlockDriverState *bs,
+void bdrv_set_change_cb(BlockDriverState *bs,
void (*change_cb)(void *opaque), void *opaque)
{
bs->change_cb = change_cb;
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->encrypted || !bs->drv || !bs->drv->bdrv_set_key)
return -1;
- return bs->drv->bdrv_set_key(bs, key);
+ 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 */
+ bs->media_changed = 1;
+ if (bs->change_cb)
+ bs->change_cb(bs->change_opaque);
+ }
+ return ret;
}
void bdrv_get_format(BlockDriverState *bs, char *buf, int buf_size)
}
}
-void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
+void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
void *opaque)
{
BlockDriver *drv;
return NULL;
}
-void bdrv_iterate(void (*it)(void *opaque, const char *name), void *opaque)
+void bdrv_iterate(void (*it)(void *opaque, BlockDriverState *bs), void *opaque)
{
BlockDriverState *bs;
for (bs = bdrv_first; bs != NULL; bs = bs->next) {
- it(opaque, bs->device_name);
+ it(opaque, bs);
}
}
void bdrv_flush(BlockDriverState *bs)
{
+ if (!bs->drv)
+ return;
if (bs->drv->bdrv_flush)
bs->drv->bdrv_flush(bs);
if (bs->backing_hd)
bdrv_flush(bs->backing_hd);
}
-void bdrv_info(void)
+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)))
+ bdrv_flush(bs);
+}
+
+/*
+ * 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.
+ *
+ * '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.
+ */
+int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+ int *pnum)
+{
+ int64_t n;
+ if (!bs->drv->bdrv_is_allocated) {
+ if (sector_num >= bs->total_sectors) {
+ *pnum = 0;
+ return 0;
+ }
+ n = bs->total_sectors - sector_num;
+ *pnum = (n < nb_sectors) ? (n) : (nb_sectors);
+ return 1;
+ }
+ return bs->drv->bdrv_is_allocated(bs, sector_num, nb_sectors, pnum);
+}
+
+void bdrv_info(Monitor *mon)
{
BlockDriverState *bs;
for (bs = bdrv_first; bs != NULL; bs = bs->next) {
- term_printf("%s:", bs->device_name);
- term_printf(" type=");
+ monitor_printf(mon, "%s:", bs->device_name);
+ monitor_printf(mon, " type=");
switch(bs->type) {
case BDRV_TYPE_HD:
- term_printf("hd");
+ monitor_printf(mon, "hd");
break;
case BDRV_TYPE_CDROM:
- term_printf("cdrom");
+ monitor_printf(mon, "cdrom");
break;
case BDRV_TYPE_FLOPPY:
- term_printf("floppy");
+ monitor_printf(mon, "floppy");
break;
}
- term_printf(" removable=%d", bs->removable);
+ monitor_printf(mon, " removable=%d", bs->removable);
if (bs->removable) {
- term_printf(" locked=%d", bs->locked);
+ monitor_printf(mon, " locked=%d", bs->locked);
}
if (bs->drv) {
- term_printf(" file=");
- term_print_filename(bs->filename);
+ monitor_printf(mon, " file=");
+ monitor_print_filename(mon, bs->filename);
if (bs->backing_file[0] != '\0') {
- term_printf(" backing_file=");
- term_print_filename(bs->backing_file);
- }
- term_printf(" ro=%d", bs->read_only);
- term_printf(" drv=%s", bs->drv->format_name);
- if (bs->encrypted)
- term_printf(" encrypted");
+ monitor_printf(mon, " backing_file=");
+ monitor_print_filename(mon, 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 {
- term_printf(" [not inserted]");
+ monitor_printf(mon, " [not inserted]");
}
- term_printf("\n");
+ monitor_printf(mon, "\n");
}
}
-void bdrv_get_backing_filename(BlockDriverState *bs,
+/* The "info blockstats" command. */
+void bdrv_info_stats(Monitor *mon)
+{
+ 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);
+ }
+}
+
+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)
{
if (!bs->backing_hd) {
}
}
-int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
+int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BlockDriver *drv = bs->drv;
return -ENOMEDIUM;
if (!drv->bdrv_write_compressed)
return -ENOTSUP;
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return -EIO;
return drv->bdrv_write_compressed(bs, sector_num, buf, nb_sectors);
}
-
+
int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
BlockDriver *drv = bs->drv;
return drv->bdrv_get_info(bs, bdi);
}
+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_save_vmstate)
+ return -ENOTSUP;
+ return drv->bdrv_save_vmstate(bs, buf, pos, 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_load_vmstate)
+ return -ENOTSUP;
+ return drv->bdrv_load_vmstate(bs, buf, pos, size);
+}
+
/**************************************************************/
/* handling of snapshots */
-int bdrv_snapshot_create(BlockDriverState *bs,
+int bdrv_snapshot_create(BlockDriverState *bs,
QEMUSnapshotInfo *sn_info)
{
BlockDriver *drv = bs->drv;
return drv->bdrv_snapshot_create(bs, sn_info);
}
-int bdrv_snapshot_goto(BlockDriverState *bs,
+int bdrv_snapshot_goto(BlockDriverState *bs,
const char *snapshot_id)
{
BlockDriver *drv = bs->drv;
return drv->bdrv_snapshot_delete(bs, snapshot_id);
}
-int bdrv_snapshot_list(BlockDriverState *bs,
+int bdrv_snapshot_list(BlockDriverState *bs,
QEMUSnapshotInfo **psn_info)
{
BlockDriver *drv = bs->drv;
base = 1024;
for(i = 0; i < NB_SUFFIXES; i++) {
if (size < (10 * base)) {
- snprintf(buf, buf_size, "%0.1f%c",
+ snprintf(buf, buf_size, "%0.1f%c",
(double)size / base,
suffixes[i]);
break;
} else if (size < (1000 * base) || i == (NB_SUFFIXES - 1)) {
- snprintf(buf, buf_size, "%" PRId64 "%c",
+ snprintf(buf, buf_size, "%" PRId64 "%c",
((size + (base >> 1)) / base),
suffixes[i]);
break;
char *bdrv_snapshot_dump(char *buf, int buf_size, QEMUSnapshotInfo *sn)
{
char buf1[128], date_buf[128], clock_buf[128];
+#ifdef _WIN32
+ struct tm *ptm;
+#else
struct tm tm;
+#endif
time_t ti;
int64_t secs;
if (!sn) {
- snprintf(buf, buf_size,
- "%-10s%-20s%7s%20s%15s",
+ snprintf(buf, buf_size,
+ "%-10s%-20s%7s%20s%15s",
"ID", "TAG", "VM SIZE", "DATE", "VM CLOCK");
} else {
ti = sn->date_sec;
-#ifndef _WIN32
+#ifdef _WIN32
+ ptm = localtime(&ti);
+ strftime(date_buf, sizeof(date_buf),
+ "%Y-%m-%d %H:%M:%S", ptm);
+#else
localtime_r(&ti, &tm);
-#endif
strftime(date_buf, sizeof(date_buf),
"%Y-%m-%d %H:%M:%S", &tm);
+#endif
secs = sn->vm_clock_nsec / 1000000000;
snprintf(clock_buf, sizeof(clock_buf),
"%02d:%02d:%02d.%03d",
(int)(secs / 3600),
(int)((secs / 60) % 60),
- (int)(secs % 60),
+ (int)(secs % 60),
(int)((sn->vm_clock_nsec / 1000000) % 1000));
snprintf(buf, buf_size,
- "%-10s%-20s%7s%20s%15s",
+ "%-10s%-20s%7s%20s%15s",
sn->id_str, sn->name,
get_human_readable_size(buf1, sizeof(buf1), sn->vm_state_size),
date_buf,
/**************************************************************/
/* async I/Os */
-BlockDriverAIOCB *bdrv_aio_read(BlockDriverState *bs, int64_t sector_num,
- uint8_t *buf, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+BlockDriverAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num,
+ QEMUIOVector *qiov, int nb_sectors,
+ BlockDriverCompletionFunc *cb, void *opaque)
{
BlockDriver *drv = bs->drv;
+ BlockDriverAIOCB *ret;
if (!drv)
return NULL;
-
- /* XXX: we assume that nb_sectors == 0 is suppored by the async read */
- if (sector_num == 0 && bs->boot_sector_enabled && nb_sectors > 0) {
- memcpy(buf, bs->boot_sector_data, 512);
- sector_num++;
- nb_sectors--;
- buf += 512;
+ 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 * SECTOR_SIZE;
+ bs->rd_ops ++;
}
- return drv->bdrv_aio_read(bs, sector_num, buf, nb_sectors, cb, opaque);
+ return ret;
}
-BlockDriverAIOCB *bdrv_aio_write(BlockDriverState *bs, int64_t sector_num,
- const uint8_t *buf, 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)
{
BlockDriver *drv = bs->drv;
+ BlockDriverAIOCB *ret;
if (!drv)
return NULL;
if (bs->read_only)
return NULL;
- if (sector_num == 0 && bs->boot_sector_enabled && nb_sectors > 0) {
- memcpy(bs->boot_sector_data, buf, 512);
+ if (bdrv_check_request(bs, sector_num, nb_sectors))
+ return NULL;
+
+ ret = drv->bdrv_aio_writev(bs, sector_num, qiov, nb_sectors,
+ cb, opaque);
+
+ if (ret) {
+ /* Update stats even though technically transfer has not happened. */
+ bs->wr_bytes += (unsigned) nb_sectors * SECTOR_SIZE;
+ bs->wr_ops ++;
}
- return drv->bdrv_aio_write(bs, sector_num, buf, nb_sectors, cb, opaque);
+ return ret;
}
-void bdrv_aio_cancel(BlockDriverAIOCB *acb)
+
+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)
{
- BlockDriver *drv = acb->bs->drv;
+ int i;
- drv->bdrv_aio_cancel(acb);
+ for (i = 0; i < mcb->num_callbacks; i++) {
+ mcb->callbacks[i].cb(mcb->callbacks[i].opaque, mcb->error);
+ qemu_free(mcb->callbacks[i].free_qiov);
+ qemu_free(mcb->callbacks[i].free_buf);
+ }
}
+static void multiwrite_cb(void *opaque, int ret)
+{
+ MultiwriteCB *mcb = opaque;
-/**************************************************************/
-/* async block device emulation */
+ if (ret < 0) {
+ mcb->error = ret;
+ multiwrite_user_cb(mcb);
+ }
-#ifdef QEMU_TOOL
-static BlockDriverAIOCB *bdrv_aio_read_em(BlockDriverState *bs,
- int64_t sector_num, uint8_t *buf, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+ mcb->num_requests--;
+ if (mcb->num_requests == 0) {
+ if (mcb->error == 0) {
+ multiwrite_user_cb(mcb);
+ }
+ qemu_free(mcb);
+ }
+}
+
+static int multiwrite_req_compare(const void *a, const void *b)
{
- int ret;
- ret = bdrv_read(bs, sector_num, buf, nb_sectors);
- cb(opaque, ret);
- return NULL;
+ return (((BlockRequest*) a)->sector - ((BlockRequest*) b)->sector);
}
-static BlockDriverAIOCB *bdrv_aio_write_em(BlockDriverState *bs,
- int64_t sector_num, const uint8_t *buf, int nb_sectors,
+/*
+ * 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;
+
+ // 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 (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 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)
+{
+ BlockDriverAIOCB *acb;
+ MultiwriteCB *mcb;
+ int i;
+
+ if (num_reqs == 0) {
+ return 0;
+ }
+
+ // Create MultiwriteCB structure
+ mcb = qemu_mallocz(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);
+
+ // 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->error = EIO;
+ break;
+ }
+ } else {
+ mcb->num_requests++;
+ }
+ }
+
+ return 0;
+
+fail:
+ free(mcb);
+ return -1;
+}
+
+BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque)
{
- int ret;
- ret = bdrv_write(bs, sector_num, buf, nb_sectors);
- cb(opaque, ret);
- return NULL;
+ BlockDriver *drv = bs->drv;
+
+ if (!drv)
+ return NULL;
+
+ /*
+ * Note that unlike bdrv_flush the driver is reponsible for flushing a
+ * backing image if it exists.
+ */
+ return drv->bdrv_aio_flush(bs, cb, opaque);
}
-static void bdrv_aio_cancel_em(BlockDriverAIOCB *acb)
+void bdrv_aio_cancel(BlockDriverAIOCB *acb)
{
+ acb->pool->cancel(acb);
}
-#else
+
+
+/**************************************************************/
+/* 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 = (BlockDriverAIOCBSync *)blockacb;
+ 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);
-}
-#endif /* !QEMU_TOOL */
-
/**************************************************************/
/* sync block device emulation */
#define NOT_DONE 0x7fffffff
-static int bdrv_read_em(BlockDriverState *bs, int64_t sector_num,
+static int bdrv_read_em(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
int async_ret;
BlockDriverAIOCB *acb;
+ struct iovec iov;
+ QEMUIOVector qiov;
async_ret = NOT_DONE;
- qemu_aio_wait_start();
- acb = bdrv_aio_read(bs, sector_num, buf, nb_sectors,
- bdrv_rw_em_cb, &async_ret);
- if (acb == NULL) {
- qemu_aio_wait_end();
+ 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)
return -1;
- }
+
while (async_ret == NOT_DONE) {
qemu_aio_wait();
}
- qemu_aio_wait_end();
+
return async_ret;
}
{
int async_ret;
BlockDriverAIOCB *acb;
+ struct iovec iov;
+ QEMUIOVector qiov;
async_ret = NOT_DONE;
- qemu_aio_wait_start();
- acb = bdrv_aio_write(bs, sector_num, buf, nb_sectors,
- bdrv_rw_em_cb, &async_ret);
- if (acb == NULL) {
- qemu_aio_wait_end();
+ 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)
return -1;
- }
while (async_ret == NOT_DONE) {
qemu_aio_wait();
}
- qemu_aio_wait_end();
return async_ret;
}
void bdrv_init(void)
{
- 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);
+ module_call_init(MODULE_INIT_BLOCK);
}
-void *qemu_aio_get(BlockDriverState *bs, BlockDriverCompletionFunc *cb,
- void *opaque)
+void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
+ BlockDriverCompletionFunc *cb, void *opaque)
{
- BlockDriver *drv;
BlockDriverAIOCB *acb;
- drv = bs->drv;
- if (drv->free_aiocb) {
- acb = drv->free_aiocb;
- drv->free_aiocb = acb->next;
+ if (pool->free_aiocb) {
+ acb = pool->free_aiocb;
+ pool->free_aiocb = acb->next;
} else {
- acb = qemu_mallocz(drv->aiocb_size);
- if (!acb)
- return NULL;
+ acb = qemu_mallocz(pool->aiocb_size);
+ acb->pool = pool;
}
acb->bs = bs;
acb->cb = cb;
void qemu_aio_release(void *p)
{
- BlockDriverAIOCB *acb = p;
- BlockDriver *drv = acb->bs->drv;
- acb->next = drv->free_aiocb;
- drv->free_aiocb = acb;
+ BlockDriverAIOCB *acb = (BlockDriverAIOCB *)p;
+ AIOPool *pool = acb->pool;
+ acb->next = pool->free_aiocb;
+ pool->free_aiocb = acb;
}
/**************************************************************/
/**
* Return TRUE if the media changed since the last call to this
- * function. It is currently only used for floppy disks
+ * function. It is currently only used for floppy disks
*/
int bdrv_media_changed(BlockDriverState *bs)
{
/**
* 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)
drv->bdrv_set_locked(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 *qemu_blockalign(BlockDriverState *bs, size_t size)
+{
+ return qemu_memalign((bs && bs->buffer_alignment) ? bs->buffer_alignment : 512, size);
+}
projects / qemu.git / blobdiff