#include "block/thread-pool.h"
#include "qemu/iov.h"
#include "raw-aio.h"
+#include "qapi/util.h"
#if defined(__APPLE__) && (__MACH__)
#include <paths.h>
#include <linux/cdrom.h>
#include <linux/fd.h>
#include <linux/fs.h>
+#ifndef FS_NOCOW_FL
+#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
#endif
-#ifdef CONFIG_FIEMAP
-#include <linux/fiemap.h>
#endif
#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
#include <linux/falloc.h>
int fd;
int type;
int open_flags;
+ size_t buf_align;
+
#if defined(__linux__)
/* linux floppy specific */
int64_t fd_open_time;
void *aio_ctx;
#endif
#ifdef CONFIG_XFS
- bool is_xfs : 1;
+ bool is_xfs:1;
#endif
- bool has_discard : 1;
+ bool has_discard:1;
+ bool has_write_zeroes:1;
+ bool discard_zeroes:1;
+ bool needs_alignment;
} BDRVRawState;
typedef struct BDRVRawReopenState {
}
#endif
+static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp)
+{
+ BDRVRawState *s = bs->opaque;
+ char *buf;
+ unsigned int sector_size;
+
+ /* For /dev/sg devices the alignment is not really used.
+ With buffered I/O, we don't have any restrictions. */
+ if (bs->sg || !s->needs_alignment) {
+ bs->request_alignment = 1;
+ s->buf_align = 1;
+ return;
+ }
+
+ /* Try a few ioctls to get the right size */
+ bs->request_alignment = 0;
+ s->buf_align = 0;
+
+#ifdef BLKSSZGET
+ if (ioctl(fd, BLKSSZGET, §or_size) >= 0) {
+ bs->request_alignment = sector_size;
+ }
+#endif
+#ifdef DKIOCGETBLOCKSIZE
+ if (ioctl(fd, DKIOCGETBLOCKSIZE, §or_size) >= 0) {
+ bs->request_alignment = sector_size;
+ }
+#endif
+#ifdef DIOCGSECTORSIZE
+ if (ioctl(fd, DIOCGSECTORSIZE, §or_size) >= 0) {
+ bs->request_alignment = sector_size;
+ }
+#endif
+#ifdef CONFIG_XFS
+ if (s->is_xfs) {
+ struct dioattr da;
+ if (xfsctl(NULL, fd, XFS_IOC_DIOINFO, &da) >= 0) {
+ bs->request_alignment = da.d_miniosz;
+ /* The kernel returns wrong information for d_mem */
+ /* s->buf_align = da.d_mem; */
+ }
+ }
+#endif
+
+ /* If we could not get the sizes so far, we can only guess them */
+ if (!s->buf_align) {
+ size_t align;
+ buf = qemu_memalign(MAX_BLOCKSIZE, 2 * MAX_BLOCKSIZE);
+ for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
+ if (pread(fd, buf + align, MAX_BLOCKSIZE, 0) >= 0) {
+ s->buf_align = align;
+ break;
+ }
+ }
+ qemu_vfree(buf);
+ }
+
+ if (!bs->request_alignment) {
+ size_t align;
+ buf = qemu_memalign(s->buf_align, MAX_BLOCKSIZE);
+ for (align = 512; align <= MAX_BLOCKSIZE; align <<= 1) {
+ if (pread(fd, buf, align, 0) >= 0) {
+ bs->request_alignment = align;
+ break;
+ }
+ }
+ qemu_vfree(buf);
+ }
+
+ if (!s->buf_align || !bs->request_alignment) {
+ error_setg(errp, "Could not find working O_DIRECT alignment. "
+ "Try cache.direct=off.");
+ }
+}
+
static void raw_parse_flags(int bdrv_flags, int *open_flags)
{
assert(open_flags != NULL);
}
}
+static void raw_detach_aio_context(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+
+ if (s->use_aio) {
+ laio_detach_aio_context(s->aio_ctx, bdrv_get_aio_context(bs));
+ }
+#endif
+}
+
+static void raw_attach_aio_context(BlockDriverState *bs,
+ AioContext *new_context)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+
+ if (s->use_aio) {
+ laio_attach_aio_context(s->aio_ctx, new_context);
+ }
+#endif
+}
+
#ifdef CONFIG_LINUX_AIO
static int raw_set_aio(void **aio_ctx, int *use_aio, int bdrv_flags)
{
}
#endif
+static void raw_parse_filename(const char *filename, QDict *options,
+ Error **errp)
+{
+ /* The filename does not have to be prefixed by the protocol name, since
+ * "file" is the default protocol; therefore, the return value of this
+ * function call can be ignored. */
+ strstart(filename, "file:", &filename);
+
+ qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+}
+
static QemuOptsList raw_runtime_opts = {
.name = "raw",
.head = QTAILQ_HEAD_INITIALIZER(raw_runtime_opts.head),
BDRVRawState *s = bs->opaque;
QemuOpts *opts;
Error *local_err = NULL;
- const char *filename;
+ const char *filename = NULL;
int fd, ret;
+ struct stat st;
- opts = qemu_opts_create_nofail(&raw_runtime_opts);
+ opts = qemu_opts_create(&raw_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
- if (error_is_set(&local_err)) {
+ if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail;
if (ret == -EROFS) {
ret = -EACCES;
}
- error_setg_errno(errp, -ret, "Could not open file");
goto fail;
}
s->fd = fd;
}
#endif
- s->has_discard = 1;
+ s->has_discard = true;
+ s->has_write_zeroes = true;
+ if ((bs->open_flags & BDRV_O_NOCACHE) != 0) {
+ s->needs_alignment = true;
+ }
+
+ if (fstat(s->fd, &st) < 0) {
+ error_setg_errno(errp, errno, "Could not stat file");
+ goto fail;
+ }
+ if (S_ISREG(st.st_mode)) {
+ s->discard_zeroes = true;
+ }
+ if (S_ISBLK(st.st_mode)) {
+#ifdef BLKDISCARDZEROES
+ unsigned int arg;
+ if (ioctl(s->fd, BLKDISCARDZEROES, &arg) == 0 && arg) {
+ s->discard_zeroes = true;
+ }
+#endif
+#ifdef __linux__
+ /* On Linux 3.10, BLKDISCARD leaves stale data in the page cache. Do
+ * not rely on the contents of discarded blocks unless using O_DIRECT.
+ * Same for BLKZEROOUT.
+ */
+ if (!(bs->open_flags & BDRV_O_NOCACHE)) {
+ s->discard_zeroes = false;
+ s->has_write_zeroes = false;
+ }
+#endif
+ }
+#ifdef __FreeBSD__
+ if (S_ISCHR(st.st_mode)) {
+ /*
+ * The file is a char device (disk), which on FreeBSD isn't behind
+ * a pager, so force all requests to be aligned. This is needed
+ * so QEMU makes sure all IO operations on the device are aligned
+ * to sector size, or else FreeBSD will reject them with EINVAL.
+ */
+ s->needs_alignment = true;
+ }
+#endif
+
#ifdef CONFIG_XFS
if (platform_test_xfs_fd(s->fd)) {
- s->is_xfs = 1;
+ s->is_xfs = true;
}
#endif
+ raw_attach_aio_context(bs, bdrv_get_aio_context(bs));
+
ret = 0;
fail:
+ if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) {
+ unlink(filename);
+ }
qemu_opts_del(opts);
return ret;
}
s->type = FTYPE_FILE;
ret = raw_open_common(bs, options, flags, 0, &local_err);
- if (error_is_set(&local_err)) {
+ if (local_err) {
error_propagate(errp, local_err);
}
return ret;
BDRVRawState *s;
BDRVRawReopenState *raw_s;
int ret = 0;
+ Error *local_err = NULL;
assert(state != NULL);
assert(state->bs != NULL);
s = state->bs->opaque;
- state->opaque = g_malloc0(sizeof(BDRVRawReopenState));
+ state->opaque = g_new0(BDRVRawReopenState, 1);
raw_s = state->opaque;
#ifdef CONFIG_LINUX_AIO
ret = -1;
}
}
+
+ /* Fail already reopen_prepare() if we can't get a working O_DIRECT
+ * alignment with the new fd. */
+ if (raw_s->fd != -1) {
+ raw_probe_alignment(state->bs, raw_s->fd, &local_err);
+ if (local_err) {
+ qemu_close(raw_s->fd);
+ raw_s->fd = -1;
+ error_propagate(errp, local_err);
+ ret = -EINVAL;
+ }
+ }
+
return ret;
}
-
static void raw_reopen_commit(BDRVReopenState *state)
{
BDRVRawReopenState *raw_s = state->opaque;
state->opaque = NULL;
}
+static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
+{
+ BDRVRawState *s = bs->opaque;
-/* XXX: use host sector size if necessary with:
-#ifdef DIOCGSECTORSIZE
- {
- unsigned int sectorsize = 512;
- if (!ioctl(fd, DIOCGSECTORSIZE, §orsize) &&
- sectorsize > bufsize)
- bufsize = sectorsize;
- }
-#endif
-#ifdef CONFIG_COCOA
- uint32_t blockSize = 512;
- if ( !ioctl( fd, DKIOCGETBLOCKSIZE, &blockSize ) && blockSize > bufsize) {
- bufsize = blockSize;
- }
-#endif
-*/
+ raw_probe_alignment(bs, s->fd, errp);
+ bs->bl.opt_mem_alignment = s->buf_align;
+}
static ssize_t handle_aiocb_ioctl(RawPosixAIOData *aiocb)
{
}
if (len == -1 && errno == EINTR) {
continue;
+ } else if (len == -1 && errno == EINVAL &&
+ (aiocb->bs->open_flags & BDRV_O_NOCACHE) &&
+ !(aiocb->aio_type & QEMU_AIO_WRITE) &&
+ offset > 0) {
+ /* O_DIRECT pread() may fail with EINVAL when offset is unaligned
+ * after a short read. Assume that O_DIRECT short reads only occur
+ * at EOF. Therefore this is a short read, not an I/O error.
+ */
+ break;
} else if (len == -1) {
offset = -errno;
break;
* Ok, we have to do it the hard way, copy all segments into
* a single aligned buffer.
*/
- buf = qemu_blockalign(aiocb->bs, aiocb->aio_nbytes);
+ buf = qemu_try_blockalign(aiocb->bs, aiocb->aio_nbytes);
+ if (buf == NULL) {
+ return -ENOMEM;
+ }
+
if (aiocb->aio_type & QEMU_AIO_WRITE) {
char *p = buf;
int i;
memcpy(p, aiocb->aio_iov[i].iov_base, aiocb->aio_iov[i].iov_len);
p += aiocb->aio_iov[i].iov_len;
}
+ assert(p - buf == aiocb->aio_nbytes);
}
nbytes = handle_aiocb_rw_linear(aiocb, buf);
copy = aiocb->aio_iov[i].iov_len;
}
memcpy(aiocb->aio_iov[i].iov_base, p, copy);
+ assert(count >= copy);
p += copy;
count -= copy;
}
+ assert(count == 0);
}
qemu_vfree(buf);
}
#ifdef CONFIG_XFS
+static int xfs_write_zeroes(BDRVRawState *s, int64_t offset, uint64_t bytes)
+{
+ struct xfs_flock64 fl;
+
+ memset(&fl, 0, sizeof(fl));
+ fl.l_whence = SEEK_SET;
+ fl.l_start = offset;
+ fl.l_len = bytes;
+
+ if (xfsctl(NULL, s->fd, XFS_IOC_ZERO_RANGE, &fl) < 0) {
+ DEBUG_BLOCK_PRINT("cannot write zero range (%s)\n", strerror(errno));
+ return -errno;
+ }
+
+ return 0;
+}
+
static int xfs_discard(BDRVRawState *s, int64_t offset, uint64_t bytes)
{
struct xfs_flock64 fl;
}
#endif
+static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
+{
+ int ret = -EOPNOTSUPP;
+ BDRVRawState *s = aiocb->bs->opaque;
+
+ if (s->has_write_zeroes == 0) {
+ return -ENOTSUP;
+ }
+
+ if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
+#ifdef BLKZEROOUT
+ do {
+ uint64_t range[2] = { aiocb->aio_offset, aiocb->aio_nbytes };
+ if (ioctl(aiocb->aio_fildes, BLKZEROOUT, range) == 0) {
+ return 0;
+ }
+ } while (errno == EINTR);
+
+ ret = -errno;
+#endif
+ } else {
+#ifdef CONFIG_XFS
+ if (s->is_xfs) {
+ return xfs_write_zeroes(s, aiocb->aio_offset, aiocb->aio_nbytes);
+ }
+#endif
+ }
+
+ if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
+ ret == -ENOTTY) {
+ s->has_write_zeroes = false;
+ ret = -ENOTSUP;
+ }
+ return ret;
+}
+
static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
{
int ret = -EOPNOTSUPP;
BDRVRawState *s = aiocb->bs->opaque;
- if (s->has_discard == 0) {
- return 0;
+ if (!s->has_discard) {
+ return -ENOTSUP;
}
if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
ret == -ENOTTY) {
- s->has_discard = 0;
- ret = 0;
+ s->has_discard = false;
+ ret = -ENOTSUP;
}
return ret;
}
case QEMU_AIO_DISCARD:
ret = handle_aiocb_discard(aiocb);
break;
+ case QEMU_AIO_WRITE_ZEROES:
+ ret = handle_aiocb_write_zeroes(aiocb);
+ break;
default:
fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
ret = -EINVAL;
return ret;
}
-static BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
+static int paio_submit_co(BlockDriverState *bs, int fd,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque, int type)
+ int type)
{
RawPosixAIOData *acb = g_slice_new(RawPosixAIOData);
ThreadPool *pool;
acb->aio_type = type;
acb->aio_fildes = fd;
+ acb->aio_nbytes = nb_sectors * BDRV_SECTOR_SIZE;
+ acb->aio_offset = sector_num * BDRV_SECTOR_SIZE;
+
if (qiov) {
acb->aio_iov = qiov->iov;
acb->aio_niov = qiov->niov;
+ assert(qiov->size == acb->aio_nbytes);
+ }
+
+ trace_paio_submit_co(sector_num, nb_sectors, type);
+ pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
+ return thread_pool_submit_co(pool, aio_worker, acb);
+}
+
+static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockCompletionFunc *cb, void *opaque, int type)
+{
+ RawPosixAIOData *acb = g_slice_new(RawPosixAIOData);
+ ThreadPool *pool;
+
+ acb->bs = bs;
+ acb->aio_type = type;
+ acb->aio_fildes = fd;
+
+ acb->aio_nbytes = nb_sectors * BDRV_SECTOR_SIZE;
+ acb->aio_offset = sector_num * BDRV_SECTOR_SIZE;
+
+ if (qiov) {
+ acb->aio_iov = qiov->iov;
+ acb->aio_niov = qiov->niov;
+ assert(qiov->size == acb->aio_nbytes);
}
- acb->aio_nbytes = nb_sectors * 512;
- acb->aio_offset = sector_num * 512;
trace_paio_submit(acb, opaque, sector_num, nb_sectors, type);
pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
}
-static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
+static BlockAIOCB *raw_aio_submit(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque, int type)
+ BlockCompletionFunc *cb, void *opaque, int type)
{
BDRVRawState *s = bs->opaque;
return NULL;
/*
- * If O_DIRECT is used the buffer needs to be aligned on a sector
- * boundary. Check if this is the case or tell the low-level
- * driver that it needs to copy the buffer.
+ * Check if the underlying device requires requests to be aligned,
+ * and if the request we are trying to submit is aligned or not.
+ * If this is the case tell the low-level driver that it needs
+ * to copy the buffer.
*/
- if ((bs->open_flags & BDRV_O_NOCACHE)) {
+ if (s->needs_alignment) {
if (!bdrv_qiov_is_aligned(bs, qiov)) {
type |= QEMU_AIO_MISALIGNED;
#ifdef CONFIG_LINUX_AIO
cb, opaque, type);
}
-static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
+static void raw_aio_plug(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+ if (s->use_aio) {
+ laio_io_plug(bs, s->aio_ctx);
+ }
+#endif
+}
+
+static void raw_aio_unplug(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+ if (s->use_aio) {
+ laio_io_unplug(bs, s->aio_ctx, true);
+ }
+#endif
+}
+
+static void raw_aio_flush_io_queue(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+ if (s->use_aio) {
+ laio_io_unplug(bs, s->aio_ctx, false);
+ }
+#endif
+}
+
+static BlockAIOCB *raw_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+ BlockCompletionFunc *cb, void *opaque)
{
return raw_aio_submit(bs, sector_num, qiov, nb_sectors,
cb, opaque, QEMU_AIO_READ);
}
-static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
+static BlockAIOCB *raw_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+ BlockCompletionFunc *cb, void *opaque)
{
return raw_aio_submit(bs, sector_num, qiov, nb_sectors,
cb, opaque, QEMU_AIO_WRITE);
}
-static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
- BlockDriverCompletionFunc *cb, void *opaque)
+static BlockAIOCB *raw_aio_flush(BlockDriverState *bs,
+ BlockCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
static void raw_close(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
+
+ raw_detach_aio_context(bs);
+
+#ifdef CONFIG_LINUX_AIO
+ if (s->use_aio) {
+ laio_cleanup(s->aio_ctx);
+ }
+#endif
if (s->fd >= 0) {
qemu_close(s->fd);
s->fd = -1;
struct stat st;
if (fstat(fd, &st))
- return -1;
+ return -errno;
if (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode)) {
struct disklabel dl;
if (ioctl(fd, DIOCGDINFO, &dl))
- return -1;
+ return -errno;
return (uint64_t)dl.d_secsize *
dl.d_partitions[DISKPART(st.st_rdev)].p_size;
} else
struct stat st;
if (fstat(fd, &st))
- return -1;
+ return -errno;
if (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode)) {
struct dkwedge_info dkw;
struct disklabel dl;
if (ioctl(fd, DIOCGDINFO, &dl))
- return -1;
+ return -errno;
return (uint64_t)dl.d_secsize *
dl.d_partitions[DISKPART(st.st_rdev)].p_size;
}
BDRVRawState *s = bs->opaque;
struct dk_minfo minfo;
int ret;
+ int64_t size;
ret = fd_open(bs);
if (ret < 0) {
* There are reports that lseek on some devices fails, but
* irc discussion said that contingency on contingency was overkill.
*/
- return lseek(s->fd, 0, SEEK_END);
+ size = lseek(s->fd, 0, SEEK_END);
+ if (size < 0) {
+ return -errno;
+ }
+ return size;
}
#elif defined(CONFIG_BSD)
static int64_t raw_getlength(BlockDriverState *bs)
if (size == 0)
#endif
#if defined(__APPLE__) && defined(__MACH__)
- size = LONG_LONG_MAX;
+ size = LLONG_MAX;
#else
size = lseek(fd, 0LL, SEEK_END);
+ if (size < 0) {
+ return -errno;
+ }
#endif
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
switch(s->type) {
#endif
} else {
size = lseek(fd, 0, SEEK_END);
+ if (size < 0) {
+ return -errno;
+ }
}
return size;
}
{
BDRVRawState *s = bs->opaque;
int ret;
+ int64_t size;
ret = fd_open(bs);
if (ret < 0) {
return ret;
}
- return lseek(s->fd, 0, SEEK_END);
+ size = lseek(s->fd, 0, SEEK_END);
+ if (size < 0) {
+ return -errno;
+ }
+ return size;
}
#endif
return (int64_t)st.st_blocks * 512;
}
-static int raw_create(const char *filename, QEMUOptionParameter *options,
- Error **errp)
+static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
{
int fd;
int result = 0;
int64_t total_size = 0;
+ bool nocow = false;
+ PreallocMode prealloc;
+ char *buf = NULL;
+ Error *local_err = NULL;
+
+ strstart(filename, "file:", &filename);
/* Read out options */
- while (options && options->name) {
- if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
- total_size = options->value.n / BDRV_SECTOR_SIZE;
- }
- options++;
+ total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+ BDRV_SECTOR_SIZE);
+ nocow = qemu_opt_get_bool(opts, BLOCK_OPT_NOCOW, false);
+ buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
+ prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
+ PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
+ &local_err);
+ g_free(buf);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ result = -EINVAL;
+ goto out;
}
fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
if (fd < 0) {
result = -errno;
error_setg_errno(errp, -result, "Could not create file");
- } else {
- if (ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
- result = -errno;
- error_setg_errno(errp, -result, "Could not resize file");
+ goto out;
+ }
+
+ if (nocow) {
+#ifdef __linux__
+ /* Set NOCOW flag to solve performance issue on fs like btrfs.
+ * This is an optimisation. The FS_IOC_SETFLAGS ioctl return value
+ * will be ignored since any failure of this operation should not
+ * block the left work.
+ */
+ int attr;
+ if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0) {
+ attr |= FS_NOCOW_FL;
+ ioctl(fd, FS_IOC_SETFLAGS, &attr);
}
- if (qemu_close(fd) != 0) {
- result = -errno;
- error_setg_errno(errp, -result, "Could not close the new file");
+#endif
+ }
+
+ if (ftruncate(fd, total_size) != 0) {
+ result = -errno;
+ error_setg_errno(errp, -result, "Could not resize file");
+ goto out_close;
+ }
+
+ switch (prealloc) {
+#ifdef CONFIG_POSIX_FALLOCATE
+ case PREALLOC_MODE_FALLOC:
+ /* posix_fallocate() doesn't set errno. */
+ result = -posix_fallocate(fd, 0, total_size);
+ if (result != 0) {
+ error_setg_errno(errp, -result,
+ "Could not preallocate data for the new file");
}
+ break;
+#endif
+ case PREALLOC_MODE_FULL:
+ {
+ int64_t num = 0, left = total_size;
+ buf = g_malloc0(65536);
+
+ while (left > 0) {
+ num = MIN(left, 65536);
+ result = write(fd, buf, num);
+ if (result < 0) {
+ result = -errno;
+ error_setg_errno(errp, -result,
+ "Could not write to the new file");
+ break;
+ }
+ left -= result;
+ }
+ if (result >= 0) {
+ result = fsync(fd);
+ if (result < 0) {
+ result = -errno;
+ error_setg_errno(errp, -result,
+ "Could not flush new file to disk");
+ }
+ }
+ g_free(buf);
+ break;
}
+ case PREALLOC_MODE_OFF:
+ break;
+ default:
+ result = -EINVAL;
+ error_setg(errp, "Unsupported preallocation mode: %s",
+ PreallocMode_lookup[prealloc]);
+ break;
+ }
+
+out_close:
+ if (qemu_close(fd) != 0 && result == 0) {
+ result = -errno;
+ error_setg_errno(errp, -result, "Could not close the new file");
+ }
+out:
return result;
}
/*
- * 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.
+ * Find allocation range in @bs around offset @start.
+ * May change underlying file descriptor's file offset.
+ * If @start is not in a hole, store @start in @data, and the
+ * beginning of the next hole in @hole, and return 0.
+ * If @start is in a non-trailing hole, store @start in @hole and the
+ * beginning of the next non-hole in @data, and return 0.
+ * If @start is in a trailing hole or beyond EOF, return -ENXIO.
+ * If we can't find out, return a negative errno other than -ENXIO.
+ */
+static int find_allocation(BlockDriverState *bs, off_t start,
+ off_t *data, off_t *hole)
+{
+#if defined SEEK_HOLE && defined SEEK_DATA
+ BDRVRawState *s = bs->opaque;
+ off_t offs;
+
+ /*
+ * SEEK_DATA cases:
+ * D1. offs == start: start is in data
+ * D2. offs > start: start is in a hole, next data at offs
+ * D3. offs < 0, errno = ENXIO: either start is in a trailing hole
+ * or start is beyond EOF
+ * If the latter happens, the file has been truncated behind
+ * our back since we opened it. All bets are off then.
+ * Treating like a trailing hole is simplest.
+ * D4. offs < 0, errno != ENXIO: we learned nothing
+ */
+ offs = lseek(s->fd, start, SEEK_DATA);
+ if (offs < 0) {
+ return -errno; /* D3 or D4 */
+ }
+ assert(offs >= start);
+
+ if (offs > start) {
+ /* D2: in hole, next data at offs */
+ *hole = start;
+ *data = offs;
+ return 0;
+ }
+
+ /* D1: in data, end not yet known */
+
+ /*
+ * SEEK_HOLE cases:
+ * H1. offs == start: start is in a hole
+ * If this happens here, a hole has been dug behind our back
+ * since the previous lseek().
+ * H2. offs > start: either start is in data, next hole at offs,
+ * or start is in trailing hole, EOF at offs
+ * Linux treats trailing holes like any other hole: offs ==
+ * start. Solaris seeks to EOF instead: offs > start (blech).
+ * If that happens here, a hole has been dug behind our back
+ * since the previous lseek().
+ * H3. offs < 0, errno = ENXIO: start is beyond EOF
+ * If this happens, the file has been truncated behind our
+ * back since we opened it. Treat it like a trailing hole.
+ * H4. offs < 0, errno != ENXIO: we learned nothing
+ * Pretend we know nothing at all, i.e. "forget" about D1.
+ */
+ offs = lseek(s->fd, start, SEEK_HOLE);
+ if (offs < 0) {
+ return -errno; /* D1 and (H3 or H4) */
+ }
+ assert(offs >= start);
+
+ if (offs > start) {
+ /*
+ * D1 and H2: either in data, next hole at offs, or it was in
+ * data but is now in a trailing hole. In the latter case,
+ * all bets are off. Treating it as if it there was data all
+ * the way to EOF is safe, so simply do that.
+ */
+ *data = start;
+ *hole = offs;
+ return 0;
+ }
+
+ /* D1 and H1 */
+ return -EBUSY;
+#else
+ return -ENOTSUP;
+#endif
+}
+
+/*
+ * Returns the allocation status of the specified sectors.
*
* If 'sector_num' is beyond the end of the disk image the return value is 0
* and 'pnum' is set to 0.
* beyond the end of the disk image it will be clamped.
*/
static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
- int64_t sector_num,
- int nb_sectors, int *pnum)
+ int64_t sector_num,
+ int nb_sectors, int *pnum)
{
- off_t start, data, hole;
- int64_t ret;
+ off_t start, data = 0, hole = 0;
+ int64_t total_size;
+ int ret;
ret = fd_open(bs);
if (ret < 0) {
}
start = sector_num * BDRV_SECTOR_SIZE;
- ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
-
-#ifdef CONFIG_FIEMAP
-
- BDRVRawState *s = bs->opaque;
- struct {
- struct fiemap fm;
- struct fiemap_extent fe;
- } f;
-
- f.fm.fm_start = start;
- f.fm.fm_length = (int64_t)nb_sectors * BDRV_SECTOR_SIZE;
- f.fm.fm_flags = 0;
- f.fm.fm_extent_count = 1;
- f.fm.fm_reserved = 0;
- if (ioctl(s->fd, FS_IOC_FIEMAP, &f) == -1) {
- /* Assume everything is allocated. */
- *pnum = nb_sectors;
- return ret;
- }
-
- if (f.fm.fm_mapped_extents == 0) {
- /* No extents found, data is beyond f.fm.fm_start + f.fm.fm_length.
- * f.fm.fm_start + f.fm.fm_length must be clamped to the file size!
- */
- off_t length = lseek(s->fd, 0, SEEK_END);
- hole = f.fm.fm_start;
- data = MIN(f.fm.fm_start + f.fm.fm_length, length);
- } else {
- data = f.fe.fe_logical;
- hole = f.fe.fe_logical + f.fe.fe_length;
- if (f.fe.fe_flags & FIEMAP_EXTENT_UNWRITTEN) {
- ret |= BDRV_BLOCK_ZERO;
- }
+ total_size = bdrv_getlength(bs);
+ if (total_size < 0) {
+ return total_size;
+ } else if (start >= total_size) {
+ *pnum = 0;
+ return 0;
+ } else if (start + nb_sectors * BDRV_SECTOR_SIZE > total_size) {
+ nb_sectors = DIV_ROUND_UP(total_size - start, BDRV_SECTOR_SIZE);
}
-#elif defined SEEK_HOLE && defined SEEK_DATA
-
- BDRVRawState *s = bs->opaque;
-
- hole = lseek(s->fd, start, SEEK_HOLE);
- if (hole == -1) {
- /* -ENXIO indicates that sector_num was past the end of the file.
- * There is a virtual hole there. */
- assert(errno != -ENXIO);
-
- /* Most likely EINVAL. Assume everything is allocated. */
+ ret = find_allocation(bs, start, &data, &hole);
+ if (ret == -ENXIO) {
+ /* Trailing hole */
*pnum = nb_sectors;
- return ret;
- }
-
- if (hole > start) {
- data = start;
- } else {
- /* On a hole. We need another syscall to find its end. */
- data = lseek(s->fd, start, SEEK_DATA);
- if (data == -1) {
- data = lseek(s->fd, 0, SEEK_END);
- }
- }
-#else
- data = 0;
- hole = start + nb_sectors * BDRV_SECTOR_SIZE;
-#endif
-
- if (data <= start) {
+ ret = BDRV_BLOCK_ZERO;
+ } else if (ret < 0) {
+ /* No info available, so pretend there are no holes */
+ *pnum = nb_sectors;
+ ret = BDRV_BLOCK_DATA;
+ } else if (data == start) {
/* On a data extent, compute sectors to the end of the extent. */
*pnum = MIN(nb_sectors, (hole - start) / BDRV_SECTOR_SIZE);
+ ret = BDRV_BLOCK_DATA;
} else {
/* On a hole, compute sectors to the beginning of the next extent. */
+ assert(hole == start);
*pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
- ret &= ~BDRV_BLOCK_DATA;
- ret |= BDRV_BLOCK_ZERO;
+ ret = BDRV_BLOCK_ZERO;
}
-
- return ret;
+ return ret | BDRV_BLOCK_OFFSET_VALID | start;
}
-static coroutine_fn BlockDriverAIOCB *raw_aio_discard(BlockDriverState *bs,
+static coroutine_fn BlockAIOCB *raw_aio_discard(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+ BlockCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
cb, opaque, QEMU_AIO_DISCARD);
}
-static QEMUOptionParameter raw_create_options[] = {
- {
- .name = BLOCK_OPT_SIZE,
- .type = OPT_SIZE,
- .help = "Virtual disk size"
- },
- { NULL }
+static int coroutine_fn raw_co_write_zeroes(
+ BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors, BdrvRequestFlags flags)
+{
+ BDRVRawState *s = bs->opaque;
+
+ if (!(flags & BDRV_REQ_MAY_UNMAP)) {
+ return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
+ QEMU_AIO_WRITE_ZEROES);
+ } else if (s->discard_zeroes) {
+ return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
+ QEMU_AIO_DISCARD);
+ }
+ return -ENOTSUP;
+}
+
+static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
+{
+ BDRVRawState *s = bs->opaque;
+
+ bdi->unallocated_blocks_are_zero = s->discard_zeroes;
+ bdi->can_write_zeroes_with_unmap = s->discard_zeroes;
+ return 0;
+}
+
+static QemuOptsList raw_create_opts = {
+ .name = "raw-create-opts",
+ .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
+ .desc = {
+ {
+ .name = BLOCK_OPT_SIZE,
+ .type = QEMU_OPT_SIZE,
+ .help = "Virtual disk size"
+ },
+ {
+ .name = BLOCK_OPT_NOCOW,
+ .type = QEMU_OPT_BOOL,
+ .help = "Turn off copy-on-write (valid only on btrfs)"
+ },
+ {
+ .name = BLOCK_OPT_PREALLOC,
+ .type = QEMU_OPT_STRING,
+ .help = "Preallocation mode (allowed values: off, falloc, full)"
+ },
+ { /* end of list */ }
+ }
};
-static BlockDriver bdrv_file = {
+BlockDriver bdrv_file = {
.format_name = "file",
.protocol_name = "file",
.instance_size = sizeof(BDRVRawState),
.bdrv_needs_filename = true,
.bdrv_probe = NULL, /* no probe for protocols */
+ .bdrv_parse_filename = raw_parse_filename,
.bdrv_file_open = raw_open,
.bdrv_reopen_prepare = raw_reopen_prepare,
.bdrv_reopen_commit = raw_reopen_commit,
.bdrv_create = raw_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_co_get_block_status = raw_co_get_block_status,
+ .bdrv_co_write_zeroes = raw_co_write_zeroes,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_aio_discard = raw_aio_discard,
+ .bdrv_refresh_limits = raw_refresh_limits,
+ .bdrv_io_plug = raw_aio_plug,
+ .bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_flush_io_queue = raw_aio_flush_io_queue,
.bdrv_truncate = raw_truncate,
.bdrv_getlength = raw_getlength,
+ .bdrv_get_info = raw_get_info,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
- .create_options = raw_create_options,
+ .bdrv_detach_aio_context = raw_detach_aio_context,
+ .bdrv_attach_aio_context = raw_attach_aio_context,
+
+ .create_opts = &raw_create_opts,
};
/***********************************************/
return 0;
}
+static void hdev_parse_filename(const char *filename, QDict *options,
+ Error **errp)
+{
+ /* The prefix is optional, just as for "file". */
+ strstart(filename, "host_device:", &filename);
+
+ qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+}
+
static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
ret = raw_open_common(bs, options, flags, 0, &local_err);
if (ret < 0) {
- if (error_is_set(&local_err)) {
+ if (local_err) {
error_propagate(errp, local_err);
}
return ret;
return 0;
last_media_present = (s->fd >= 0);
if (s->fd >= 0 &&
- (get_clock() - s->fd_open_time) >= FD_OPEN_TIMEOUT) {
+ (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - s->fd_open_time) >= FD_OPEN_TIMEOUT) {
qemu_close(s->fd);
s->fd = -1;
#ifdef DEBUG_FLOPPY
}
if (s->fd < 0) {
if (s->fd_got_error &&
- (get_clock() - s->fd_error_time) < FD_OPEN_TIMEOUT) {
+ (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - s->fd_error_time) < FD_OPEN_TIMEOUT) {
#ifdef DEBUG_FLOPPY
printf("No floppy (open delayed)\n");
#endif
}
s->fd = qemu_open(bs->filename, s->open_flags & ~O_NONBLOCK);
if (s->fd < 0) {
- s->fd_error_time = get_clock();
+ s->fd_error_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
s->fd_got_error = 1;
if (last_media_present)
s->fd_media_changed = 1;
}
if (!last_media_present)
s->fd_media_changed = 1;
- s->fd_open_time = get_clock();
+ s->fd_open_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
s->fd_got_error = 0;
return 0;
}
return ioctl(s->fd, req, buf);
}
-static BlockDriverAIOCB *hdev_aio_ioctl(BlockDriverState *bs,
+static BlockAIOCB *hdev_aio_ioctl(BlockDriverState *bs,
unsigned long int req, void *buf,
- BlockDriverCompletionFunc *cb, void *opaque)
+ BlockCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
RawPosixAIOData *acb;
#endif /* !linux && !FreeBSD */
-static coroutine_fn BlockDriverAIOCB *hdev_aio_discard(BlockDriverState *bs,
+static coroutine_fn BlockAIOCB *hdev_aio_discard(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
- BlockDriverCompletionFunc *cb, void *opaque)
+ BlockCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
cb, opaque, QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);
}
-static int hdev_create(const char *filename, QEMUOptionParameter *options,
+static coroutine_fn int hdev_co_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
+{
+ BDRVRawState *s = bs->opaque;
+ int rc;
+
+ rc = fd_open(bs);
+ if (rc < 0) {
+ return rc;
+ }
+ if (!(flags & BDRV_REQ_MAY_UNMAP)) {
+ return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
+ QEMU_AIO_WRITE_ZEROES|QEMU_AIO_BLKDEV);
+ } else if (s->discard_zeroes) {
+ return paio_submit_co(bs, s->fd, sector_num, NULL, nb_sectors,
+ QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);
+ }
+ return -ENOTSUP;
+}
+
+static int hdev_create(const char *filename, QemuOpts *opts,
Error **errp)
{
int fd;
int ret = 0;
struct stat stat_buf;
int64_t total_size = 0;
+ bool has_prefix;
+
+ /* This function is used by all three protocol block drivers and therefore
+ * any of these three prefixes may be given.
+ * The return value has to be stored somewhere, otherwise this is an error
+ * due to -Werror=unused-value. */
+ has_prefix =
+ strstart(filename, "host_device:", &filename) ||
+ strstart(filename, "host_cdrom:" , &filename) ||
+ strstart(filename, "host_floppy:", &filename);
+
+ (void)has_prefix;
/* Read out options */
- while (options && options->name) {
- if (!strcmp(options->name, "size")) {
- total_size = options->value.n / BDRV_SECTOR_SIZE;
- }
- options++;
- }
+ total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+ BDRV_SECTOR_SIZE);
fd = qemu_open(filename, O_WRONLY | O_BINARY);
if (fd < 0) {
error_setg(errp,
"The given file is neither a block nor a character device");
ret = -ENODEV;
- } else if (lseek(fd, 0, SEEK_END) < total_size * BDRV_SECTOR_SIZE) {
+ } else if (lseek(fd, 0, SEEK_END) < total_size) {
error_setg(errp, "Device is too small");
ret = -ENOSPC;
}
.instance_size = sizeof(BDRVRawState),
.bdrv_needs_filename = true,
.bdrv_probe_device = hdev_probe_device,
+ .bdrv_parse_filename = hdev_parse_filename,
.bdrv_file_open = hdev_open,
.bdrv_close = raw_close,
.bdrv_reopen_prepare = raw_reopen_prepare,
.bdrv_reopen_commit = raw_reopen_commit,
.bdrv_reopen_abort = raw_reopen_abort,
- .bdrv_create = hdev_create,
- .create_options = raw_create_options,
+ .bdrv_create = hdev_create,
+ .create_opts = &raw_create_opts,
+ .bdrv_co_write_zeroes = hdev_co_write_zeroes,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_aio_discard = hdev_aio_discard,
+ .bdrv_refresh_limits = raw_refresh_limits,
+ .bdrv_io_plug = raw_aio_plug,
+ .bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_flush_io_queue = raw_aio_flush_io_queue,
.bdrv_truncate = raw_truncate,
.bdrv_getlength = raw_getlength,
+ .bdrv_get_info = raw_get_info,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
+ .bdrv_detach_aio_context = raw_detach_aio_context,
+ .bdrv_attach_aio_context = raw_attach_aio_context,
+
/* generic scsi device */
#ifdef __linux__
.bdrv_ioctl = hdev_ioctl,
};
#ifdef __linux__
+static void floppy_parse_filename(const char *filename, QDict *options,
+ Error **errp)
+{
+ /* The prefix is optional, just as for "file". */
+ strstart(filename, "host_floppy:", &filename);
+
+ qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+}
+
static int floppy_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
/* open will not fail even if no floppy is inserted, so add O_NONBLOCK */
ret = raw_open_common(bs, options, flags, O_NONBLOCK, &local_err);
if (ret) {
- if (error_is_set(&local_err)) {
+ if (local_err) {
error_propagate(errp, local_err);
}
return ret;
.instance_size = sizeof(BDRVRawState),
.bdrv_needs_filename = true,
.bdrv_probe_device = floppy_probe_device,
+ .bdrv_parse_filename = floppy_parse_filename,
.bdrv_file_open = floppy_open,
.bdrv_close = raw_close,
.bdrv_reopen_prepare = raw_reopen_prepare,
.bdrv_reopen_commit = raw_reopen_commit,
.bdrv_reopen_abort = raw_reopen_abort,
- .bdrv_create = hdev_create,
- .create_options = raw_create_options,
+ .bdrv_create = hdev_create,
+ .create_opts = &raw_create_opts,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
+ .bdrv_refresh_limits = raw_refresh_limits,
+ .bdrv_io_plug = raw_aio_plug,
+ .bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_flush_io_queue = raw_aio_flush_io_queue,
.bdrv_truncate = raw_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
+ .bdrv_detach_aio_context = raw_detach_aio_context,
+ .bdrv_attach_aio_context = raw_attach_aio_context,
+
/* removable device support */
.bdrv_is_inserted = floppy_is_inserted,
.bdrv_media_changed = floppy_media_changed,
.bdrv_eject = floppy_eject,
};
+#endif
+#if defined(__linux__) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
+static void cdrom_parse_filename(const char *filename, QDict *options,
+ Error **errp)
+{
+ /* The prefix is optional, just as for "file". */
+ strstart(filename, "host_cdrom:", &filename);
+
+ qdict_put_obj(options, "filename", QOBJECT(qstring_from_str(filename)));
+}
+#endif
+
+#ifdef __linux__
static int cdrom_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
/* open will not fail even if no CD is inserted, so add O_NONBLOCK */
ret = raw_open_common(bs, options, flags, O_NONBLOCK, &local_err);
- if (error_is_set(&local_err)) {
+ if (local_err) {
error_propagate(errp, local_err);
}
return ret;
.instance_size = sizeof(BDRVRawState),
.bdrv_needs_filename = true,
.bdrv_probe_device = cdrom_probe_device,
+ .bdrv_parse_filename = cdrom_parse_filename,
.bdrv_file_open = cdrom_open,
.bdrv_close = raw_close,
.bdrv_reopen_prepare = raw_reopen_prepare,
.bdrv_reopen_commit = raw_reopen_commit,
.bdrv_reopen_abort = raw_reopen_abort,
- .bdrv_create = hdev_create,
- .create_options = raw_create_options,
+ .bdrv_create = hdev_create,
+ .create_opts = &raw_create_opts,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
+ .bdrv_refresh_limits = raw_refresh_limits,
+ .bdrv_io_plug = raw_aio_plug,
+ .bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_flush_io_queue = raw_aio_flush_io_queue,
.bdrv_truncate = raw_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
+ .bdrv_detach_aio_context = raw_detach_aio_context,
+ .bdrv_attach_aio_context = raw_attach_aio_context,
+
/* removable device support */
.bdrv_is_inserted = cdrom_is_inserted,
.bdrv_eject = cdrom_eject,
#endif /* __linux__ */
#if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
-static int cdrom_open(BlockDriverState *bs, QDict *options, int flags)
+static int cdrom_open(BlockDriverState *bs, QDict *options, int flags,
+ Error **errp)
{
BDRVRawState *s = bs->opaque;
Error *local_err = NULL;
ret = raw_open_common(bs, options, flags, 0, &local_err);
if (ret) {
- if (error_is_set(&local_err)) {
+ if (local_err) {
error_propagate(errp, local_err);
}
return ret;
.instance_size = sizeof(BDRVRawState),
.bdrv_needs_filename = true,
.bdrv_probe_device = cdrom_probe_device,
+ .bdrv_parse_filename = cdrom_parse_filename,
.bdrv_file_open = cdrom_open,
.bdrv_close = raw_close,
.bdrv_reopen_prepare = raw_reopen_prepare,
.bdrv_reopen_commit = raw_reopen_commit,
.bdrv_reopen_abort = raw_reopen_abort,
.bdrv_create = hdev_create,
- .create_options = raw_create_options,
+ .create_opts = &raw_create_opts,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
+ .bdrv_refresh_limits = raw_refresh_limits,
+ .bdrv_io_plug = raw_aio_plug,
+ .bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_flush_io_queue = raw_aio_flush_io_queue,
.bdrv_truncate = raw_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
+ .bdrv_detach_aio_context = raw_detach_aio_context,
+ .bdrv_attach_aio_context = raw_attach_aio_context,
+
/* removable device support */
.bdrv_is_inserted = cdrom_is_inserted,
.bdrv_eject = cdrom_eject,
};
#endif /* __FreeBSD__ */
-#ifdef CONFIG_LINUX_AIO
-/**
- * Return the file descriptor for Linux AIO
- *
- * This function is a layering violation and should be removed when it becomes
- * possible to call the block layer outside the global mutex. It allows the
- * caller to hijack the file descriptor so I/O can be performed outside the
- * block layer.
- */
-int raw_get_aio_fd(BlockDriverState *bs)
-{
- BDRVRawState *s;
-
- if (!bs->drv) {
- return -ENOMEDIUM;
- }
-
- if (bs->drv == bdrv_find_format("raw")) {
- bs = bs->file;
- }
-
- /* raw-posix has several protocols so just check for raw_aio_readv */
- if (bs->drv->bdrv_aio_readv != raw_aio_readv) {
- return -ENOTSUP;
- }
-
- s = bs->opaque;
- if (!s->use_aio) {
- return -ENOTSUP;
- }
- return s->fd;
-}
-#endif /* CONFIG_LINUX_AIO */
-
static void bdrv_file_init(void)
{
/*
projects / qemu.git / blobdiff