#ifdef __linux__
#include <sys/ioctl.h>
#include <sys/param.h>
+#include <sys/syscall.h>
#include <linux/cdrom.h>
#include <linux/fd.h>
#include <linux/fs.h>
typedef struct BDRVRawState {
int fd;
- int lock_fd;
bool use_lock;
int type;
int open_flags;
uint64_t perm;
uint64_t shared_perm;
+ /* The perms bits whose corresponding bytes are already locked in
+ * s->fd. */
+ uint64_t locked_perm;
+ uint64_t locked_shared_perm;
+
#ifdef CONFIG_XFS
bool is_xfs:1;
#endif
bool page_cache_inconsistent:1;
bool has_fallocate;
bool needs_alignment;
+ bool check_cache_dropped;
PRManager *pr_mgr;
} BDRVRawState;
typedef struct BDRVRawReopenState {
int fd;
int open_flags;
+ bool check_cache_dropped;
} BDRVRawReopenState;
static int fd_open(BlockDriverState *bs);
typedef struct RawPosixAIOData {
BlockDriverState *bs;
+ int aio_type;
int aio_fildes;
+
+ off_t aio_offset;
+ uint64_t aio_nbytes;
+
union {
- struct iovec *aio_iov;
- void *aio_ioctl_buf;
+ struct {
+ struct iovec *iov;
+ int niov;
+ } io;
+ struct {
+ uint64_t cmd;
+ void *buf;
+ } ioctl;
+ struct {
+ int aio_fd2;
+ off_t aio_offset2;
+ } copy_range;
+ struct {
+ PreallocMode prealloc;
+ Error **errp;
+ } truncate;
};
- int aio_niov;
- uint64_t aio_nbytes;
-#define aio_ioctl_cmd aio_nbytes /* for QEMU_AIO_IOCTL */
- off_t aio_offset;
- int aio_type;
} RawPosixAIOData;
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
#endif
#if defined(__NetBSD__)
-static int raw_normalize_devicepath(const char **filename)
+static int raw_normalize_devicepath(const char **filename, Error **errp)
{
static char namebuf[PATH_MAX];
const char *dp, *fname;
fname = *filename;
dp = strrchr(fname, '/');
if (lstat(fname, &sb) < 0) {
- fprintf(stderr, "%s: stat failed: %s\n",
- fname, strerror(errno));
+ error_setg_errno(errp, errno, "%s: stat failed", fname);
return -errno;
}
snprintf(namebuf, PATH_MAX, "%.*s/r%s",
(int)(dp - fname), fname, dp + 1);
}
- fprintf(stderr, "%s is a block device", fname);
*filename = namebuf;
- fprintf(stderr, ", using %s\n", *filename);
+ warn_report("%s is a block device, using %s", fname, *filename);
return 0;
}
#else
-static int raw_normalize_devicepath(const char **filename)
+static int raw_normalize_devicepath(const char **filename, Error **errp)
{
return 0;
}
.type = QEMU_OPT_STRING,
.help = "id of persistent reservation manager object (default: none)",
},
+ {
+ .name = "x-check-cache-dropped",
+ .type = QEMU_OPT_BOOL,
+ .help = "check that page cache was dropped on live migration (default: off)"
+ },
{ /* end of list */ }
},
};
static int raw_open_common(BlockDriverState *bs, QDict *options,
- int bdrv_flags, int open_flags, Error **errp)
+ int bdrv_flags, int open_flags,
+ bool device, Error **errp)
{
BDRVRawState *s = bs->opaque;
QemuOpts *opts;
filename = qemu_opt_get(opts, "filename");
- ret = raw_normalize_devicepath(&filename);
+ ret = raw_normalize_devicepath(&filename, errp);
if (ret != 0) {
- error_setg_errno(errp, -ret, "Could not normalize device path");
goto fail;
}
case ON_OFF_AUTO_ON:
s->use_lock = true;
if (!qemu_has_ofd_lock()) {
- fprintf(stderr,
- "File lock requested but OFD locking syscall is "
- "unavailable, falling back to POSIX file locks.\n"
- "Due to the implementation, locks can be lost "
- "unexpectedly.\n");
+ warn_report("File lock requested but OFD locking syscall is "
+ "unavailable, falling back to POSIX file locks");
+ error_printf("Due to the implementation, locks can be lost "
+ "unexpectedly.\n");
}
break;
case ON_OFF_AUTO_OFF:
}
}
+ s->check_cache_dropped = qemu_opt_get_bool(opts, "x-check-cache-dropped",
+ false);
+
s->open_flags = open_flags;
raw_parse_flags(bdrv_flags, &s->open_flags);
s->fd = -1;
fd = qemu_open(filename, s->open_flags, 0644);
- if (fd < 0) {
- ret = -errno;
- error_setg_errno(errp, errno, "Could not open '%s'", filename);
+ ret = fd < 0 ? -errno : 0;
+
+ if (ret == -EACCES || ret == -EROFS) {
+ /* Try to degrade to read-only, but if it doesn't work, still use the
+ * normal error message. */
+ if (bdrv_apply_auto_read_only(bs, NULL, NULL) == 0) {
+ bdrv_flags &= ~BDRV_O_RDWR;
+ raw_parse_flags(bdrv_flags, &s->open_flags);
+ assert(!(s->open_flags & O_CREAT));
+ fd = qemu_open(filename, s->open_flags);
+ ret = fd < 0 ? -errno : 0;
+ }
+ }
+
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not open '%s'", filename);
if (ret == -EROFS) {
ret = -EACCES;
}
}
s->fd = fd;
- s->lock_fd = -1;
- if (s->use_lock) {
- fd = qemu_open(filename, s->open_flags);
- if (fd < 0) {
- ret = -errno;
- error_setg_errno(errp, errno, "Could not open '%s' for locking",
- filename);
- qemu_close(s->fd);
- goto fail;
- }
- s->lock_fd = fd;
- }
s->perm = 0;
s->shared_perm = BLK_PERM_ALL;
#ifdef CONFIG_LINUX_AIO
/* Currently Linux does AIO only for files opened with O_DIRECT */
- if (s->use_linux_aio && !(s->open_flags & O_DIRECT)) {
- error_setg(errp, "aio=native was specified, but it requires "
- "cache.direct=on, which was not specified.");
- ret = -EINVAL;
- goto fail;
+ if (s->use_linux_aio) {
+ if (!(s->open_flags & O_DIRECT)) {
+ error_setg(errp, "aio=native was specified, but it requires "
+ "cache.direct=on, which was not specified.");
+ ret = -EINVAL;
+ goto fail;
+ }
+ if (!aio_setup_linux_aio(bdrv_get_aio_context(bs), errp)) {
+ error_prepend(errp, "Unable to use native AIO: ");
+ goto fail;
+ }
}
#else
if (s->use_linux_aio) {
error_setg_errno(errp, errno, "Could not stat file");
goto fail;
}
- if (S_ISREG(st.st_mode)) {
- s->discard_zeroes = true;
- s->has_fallocate = true;
+
+ if (!device) {
+ if (S_ISBLK(st.st_mode)) {
+ warn_report("Opening a block device as a file using the '%s' "
+ "driver is deprecated", bs->drv->format_name);
+ } else if (S_ISCHR(st.st_mode)) {
+ warn_report("Opening a character device as a file using the '%s' "
+ "driver is deprecated", bs->drv->format_name);
+ } else if (!S_ISREG(st.st_mode)) {
+ error_setg(errp, "A regular file was expected by the '%s' driver, "
+ "but something else was given", bs->drv->format_name);
+ ret = -EINVAL;
+ goto fail;
+ } else {
+ s->discard_zeroes = true;
+ s->has_fallocate = true;
+ }
+ } else {
+ if (!(S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode))) {
+ error_setg(errp, "'%s' driver expects either "
+ "a character or block device", bs->drv->format_name);
+ ret = -EINVAL;
+ goto fail;
+ }
}
+
if (S_ISBLK(st.st_mode)) {
#ifdef BLKDISCARDZEROES
unsigned int arg;
}
#endif
- bs->supported_zero_flags = s->discard_zeroes ? BDRV_REQ_MAY_UNMAP : 0;
+ bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP;
ret = 0;
fail:
if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) {
BDRVRawState *s = bs->opaque;
s->type = FTYPE_FILE;
- return raw_open_common(bs, options, flags, 0, errp);
+ return raw_open_common(bs, options, flags, 0, false, errp);
}
typedef enum {
* file; if @unlock == true, also unlock the unneeded bytes.
* @shared_perm_lock_bits is the mask of all permissions that are NOT shared.
*/
-static int raw_apply_lock_bytes(BDRVRawState *s,
+static int raw_apply_lock_bytes(BDRVRawState *s, int fd,
uint64_t perm_lock_bits,
uint64_t shared_perm_lock_bits,
bool unlock, Error **errp)
{
int ret;
int i;
+ uint64_t locked_perm, locked_shared_perm;
+
+ if (s) {
+ locked_perm = s->locked_perm;
+ locked_shared_perm = s->locked_shared_perm;
+ } else {
+ /*
+ * We don't have the previous bits, just lock/unlock for each of the
+ * requested bits.
+ */
+ if (unlock) {
+ locked_perm = BLK_PERM_ALL;
+ locked_shared_perm = BLK_PERM_ALL;
+ } else {
+ locked_perm = 0;
+ locked_shared_perm = 0;
+ }
+ }
PERM_FOREACH(i) {
int off = RAW_LOCK_PERM_BASE + i;
- if (perm_lock_bits & (1ULL << i)) {
- ret = qemu_lock_fd(s->lock_fd, off, 1, false);
+ uint64_t bit = (1ULL << i);
+ if ((perm_lock_bits & bit) && !(locked_perm & bit)) {
+ ret = qemu_lock_fd(fd, off, 1, false);
if (ret) {
error_setg(errp, "Failed to lock byte %d", off);
return ret;
+ } else if (s) {
+ s->locked_perm |= bit;
}
- } else if (unlock) {
- ret = qemu_unlock_fd(s->lock_fd, off, 1);
+ } else if (unlock && (locked_perm & bit) && !(perm_lock_bits & bit)) {
+ ret = qemu_unlock_fd(fd, off, 1);
if (ret) {
error_setg(errp, "Failed to unlock byte %d", off);
return ret;
+ } else if (s) {
+ s->locked_perm &= ~bit;
}
}
}
PERM_FOREACH(i) {
int off = RAW_LOCK_SHARED_BASE + i;
- if (shared_perm_lock_bits & (1ULL << i)) {
- ret = qemu_lock_fd(s->lock_fd, off, 1, false);
+ uint64_t bit = (1ULL << i);
+ if ((shared_perm_lock_bits & bit) && !(locked_shared_perm & bit)) {
+ ret = qemu_lock_fd(fd, off, 1, false);
if (ret) {
error_setg(errp, "Failed to lock byte %d", off);
return ret;
+ } else if (s) {
+ s->locked_shared_perm |= bit;
}
- } else if (unlock) {
- ret = qemu_unlock_fd(s->lock_fd, off, 1);
+ } else if (unlock && (locked_shared_perm & bit) &&
+ !(shared_perm_lock_bits & bit)) {
+ ret = qemu_unlock_fd(fd, off, 1);
if (ret) {
error_setg(errp, "Failed to unlock byte %d", off);
return ret;
+ } else if (s) {
+ s->locked_shared_perm &= ~bit;
}
}
}
}
/* Check "unshared" bytes implied by @perm and ~@shared_perm in the file. */
-static int raw_check_lock_bytes(BDRVRawState *s,
- uint64_t perm, uint64_t shared_perm,
+static int raw_check_lock_bytes(int fd, uint64_t perm, uint64_t shared_perm,
Error **errp)
{
int ret;
int off = RAW_LOCK_SHARED_BASE + i;
uint64_t p = 1ULL << i;
if (perm & p) {
- ret = qemu_lock_fd_test(s->lock_fd, off, 1, true);
+ ret = qemu_lock_fd_test(fd, off, 1, true);
if (ret) {
char *perm_name = bdrv_perm_names(p);
error_setg(errp,
"Failed to get \"%s\" lock",
perm_name);
g_free(perm_name);
- error_append_hint(errp,
- "Is another process using the image?\n");
return ret;
}
}
int off = RAW_LOCK_PERM_BASE + i;
uint64_t p = 1ULL << i;
if (!(shared_perm & p)) {
- ret = qemu_lock_fd_test(s->lock_fd, off, 1, true);
+ ret = qemu_lock_fd_test(fd, off, 1, true);
if (ret) {
char *perm_name = bdrv_perm_names(p);
error_setg(errp,
"Failed to get shared \"%s\" lock",
perm_name);
g_free(perm_name);
- error_append_hint(errp,
- "Is another process using the image?\n");
return ret;
}
}
return 0;
}
- assert(s->lock_fd > 0);
-
switch (op) {
case RAW_PL_PREPARE:
- ret = raw_apply_lock_bytes(s, s->perm | new_perm,
+ ret = raw_apply_lock_bytes(s, s->fd, s->perm | new_perm,
~s->shared_perm | ~new_shared,
false, errp);
if (!ret) {
- ret = raw_check_lock_bytes(s, new_perm, new_shared, errp);
+ ret = raw_check_lock_bytes(s->fd, new_perm, new_shared, errp);
if (!ret) {
return 0;
}
+ error_append_hint(errp,
+ "Is another process using the image [%s]?\n",
+ bs->filename);
}
op = RAW_PL_ABORT;
/* fall through to unlock bytes. */
case RAW_PL_ABORT:
- raw_apply_lock_bytes(s, s->perm, ~s->shared_perm, true, &local_err);
+ raw_apply_lock_bytes(s, s->fd, s->perm, ~s->shared_perm,
+ true, &local_err);
if (local_err) {
/* Theoretically the above call only unlocks bytes and it cannot
* fail. Something weird happened, report it.
*/
- error_report_err(local_err);
+ warn_report_err(local_err);
}
break;
case RAW_PL_COMMIT:
- raw_apply_lock_bytes(s, new_perm, ~new_shared, true, &local_err);
+ raw_apply_lock_bytes(s, s->fd, new_perm, ~new_shared,
+ true, &local_err);
if (local_err) {
/* Theoretically the above call only unlocks bytes and it cannot
* fail. Something weird happened, report it.
*/
- error_report_err(local_err);
+ warn_report_err(local_err);
}
break;
}
{
BDRVRawState *s;
BDRVRawReopenState *rs;
+ QemuOpts *opts;
int ret = 0;
Error *local_err = NULL;
state->opaque = g_new0(BDRVRawReopenState, 1);
rs = state->opaque;
+ rs->fd = -1;
+
+ /* Handle options changes */
+ opts = qemu_opts_create(&raw_runtime_opts, NULL, 0, &error_abort);
+ qemu_opts_absorb_qdict(opts, state->options, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ rs->check_cache_dropped =
+ qemu_opt_get_bool_del(opts, "x-check-cache-dropped", false);
+
+ /* This driver's reopen function doesn't currently allow changing
+ * other options, so let's put them back in the original QDict and
+ * bdrv_reopen_prepare() will detect changes and complain. */
+ qemu_opts_to_qdict(opts, state->options);
if (s->type == FTYPE_CD) {
rs->open_flags |= O_NONBLOCK;
raw_parse_flags(state->flags, &rs->open_flags);
- rs->fd = -1;
-
int fcntl_flags = O_APPEND | O_NONBLOCK;
#ifdef O_NOATIME
fcntl_flags |= O_NOATIME;
/* If we cannot use fcntl, or fcntl failed, fall back to qemu_open() */
if (rs->fd == -1) {
const char *normalized_filename = state->bs->filename;
- ret = raw_normalize_devicepath(&normalized_filename);
- if (ret < 0) {
- error_setg_errno(errp, -ret, "Could not normalize device path");
- } else {
+ ret = raw_normalize_devicepath(&normalized_filename, errp);
+ if (ret >= 0) {
assert(!(rs->open_flags & O_CREAT));
rs->fd = qemu_open(normalized_filename, rs->open_flags);
if (rs->fd == -1) {
}
}
+out:
+ qemu_opts_del(opts);
return ret;
}
{
BDRVRawReopenState *rs = state->opaque;
BDRVRawState *s = state->bs->opaque;
+ Error *local_err = NULL;
+ s->check_cache_dropped = rs->check_cache_dropped;
s->open_flags = rs->open_flags;
+ /* Copy locks to the new fd before closing the old one. */
+ raw_apply_lock_bytes(NULL, rs->fd, s->locked_perm,
+ s->locked_shared_perm, false, &local_err);
+ if (local_err) {
+ /* shouldn't fail in a sane host, but report it just in case. */
+ error_report_err(local_err);
+ }
qemu_close(s->fd);
s->fd = rs->fd;
}
#endif
-static ssize_t handle_aiocb_ioctl(RawPosixAIOData *aiocb)
+#if defined(__linux__)
+static int handle_aiocb_ioctl(void *opaque)
{
+ RawPosixAIOData *aiocb = opaque;
int ret;
- ret = ioctl(aiocb->aio_fildes, aiocb->aio_ioctl_cmd, aiocb->aio_ioctl_buf);
+ ret = ioctl(aiocb->aio_fildes, aiocb->ioctl.cmd, aiocb->ioctl.buf);
if (ret == -1) {
return -errno;
}
return 0;
}
+#endif /* linux */
-static ssize_t handle_aiocb_flush(RawPosixAIOData *aiocb)
+static int handle_aiocb_flush(void *opaque)
{
+ RawPosixAIOData *aiocb = opaque;
BDRVRawState *s = aiocb->bs->opaque;
int ret;
do {
if (aiocb->aio_type & QEMU_AIO_WRITE)
len = qemu_pwritev(aiocb->aio_fildes,
- aiocb->aio_iov,
- aiocb->aio_niov,
+ aiocb->io.iov,
+ aiocb->io.niov,
aiocb->aio_offset);
else
len = qemu_preadv(aiocb->aio_fildes,
- aiocb->aio_iov,
- aiocb->aio_niov,
+ aiocb->io.iov,
+ aiocb->io.niov,
aiocb->aio_offset);
} while (len == -1 && errno == EINTR);
return offset;
}
-static ssize_t handle_aiocb_rw(RawPosixAIOData *aiocb)
+static int handle_aiocb_rw(void *opaque)
{
+ RawPosixAIOData *aiocb = opaque;
ssize_t nbytes;
char *buf;
* If there is just a single buffer, and it is properly aligned
* we can just use plain pread/pwrite without any problems.
*/
- if (aiocb->aio_niov == 1) {
- return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);
+ if (aiocb->io.niov == 1) {
+ nbytes = handle_aiocb_rw_linear(aiocb, aiocb->io.iov->iov_base);
+ goto out;
}
/*
* We have more than one iovec, and all are properly aligned.
nbytes = handle_aiocb_rw_vector(aiocb);
if (nbytes == aiocb->aio_nbytes ||
(nbytes < 0 && nbytes != -ENOSYS)) {
- return nbytes;
+ goto out;
}
preadv_present = false;
}
*/
buf = qemu_try_blockalign(aiocb->bs, aiocb->aio_nbytes);
if (buf == NULL) {
- return -ENOMEM;
+ nbytes = -ENOMEM;
+ goto out;
}
if (aiocb->aio_type & QEMU_AIO_WRITE) {
char *p = buf;
int i;
- for (i = 0; i < aiocb->aio_niov; ++i) {
- memcpy(p, aiocb->aio_iov[i].iov_base, aiocb->aio_iov[i].iov_len);
- p += aiocb->aio_iov[i].iov_len;
+ for (i = 0; i < aiocb->io.niov; ++i) {
+ memcpy(p, aiocb->io.iov[i].iov_base, aiocb->io.iov[i].iov_len);
+ p += aiocb->io.iov[i].iov_len;
}
assert(p - buf == aiocb->aio_nbytes);
}
size_t count = aiocb->aio_nbytes, copy;
int i;
- for (i = 0; i < aiocb->aio_niov && count; ++i) {
+ for (i = 0; i < aiocb->io.niov && count; ++i) {
copy = count;
- if (copy > aiocb->aio_iov[i].iov_len) {
- copy = aiocb->aio_iov[i].iov_len;
+ if (copy > aiocb->io.iov[i].iov_len) {
+ copy = aiocb->io.iov[i].iov_len;
}
- memcpy(aiocb->aio_iov[i].iov_base, p, copy);
+ memcpy(aiocb->io.iov[i].iov_base, p, copy);
assert(count >= copy);
p += copy;
count -= copy;
}
qemu_vfree(buf);
- return nbytes;
+out:
+ if (nbytes == aiocb->aio_nbytes) {
+ return 0;
+ } else if (nbytes >= 0 && nbytes < aiocb->aio_nbytes) {
+ if (aiocb->aio_type & QEMU_AIO_WRITE) {
+ return -EINVAL;
+ } else {
+ iov_memset(aiocb->io.iov, aiocb->io.niov, nbytes,
+ 0, aiocb->aio_nbytes - nbytes);
+ return 0;
+ }
+ } else {
+ assert(nbytes < 0);
+ return nbytes;
+ }
}
#ifdef CONFIG_XFS
return ret;
}
-static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
+static int handle_aiocb_write_zeroes(void *opaque)
{
+ RawPosixAIOData *aiocb = opaque;
#if defined(CONFIG_FALLOCATE) || defined(CONFIG_XFS)
BDRVRawState *s = aiocb->bs->opaque;
#endif
return -ENOTSUP;
}
-static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
+static int handle_aiocb_write_zeroes_unmap(void *opaque)
+{
+ RawPosixAIOData *aiocb = opaque;
+ BDRVRawState *s G_GNUC_UNUSED = aiocb->bs->opaque;
+ int ret;
+
+ /* First try to write zeros and unmap at the same time */
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+ ret = do_fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+ aiocb->aio_offset, aiocb->aio_nbytes);
+ if (ret != -ENOTSUP) {
+ return ret;
+ }
+#endif
+
+#ifdef CONFIG_XFS
+ if (s->is_xfs) {
+ /* xfs_discard() guarantees that the discarded area reads as all-zero
+ * afterwards, so we can use it here. */
+ return xfs_discard(s, aiocb->aio_offset, aiocb->aio_nbytes);
+ }
+#endif
+
+ /* If we couldn't manage to unmap while guaranteed that the area reads as
+ * all-zero afterwards, just write zeroes without unmapping */
+ ret = handle_aiocb_write_zeroes(aiocb);
+ return ret;
+}
+
+#ifndef HAVE_COPY_FILE_RANGE
+static off_t copy_file_range(int in_fd, off_t *in_off, int out_fd,
+ off_t *out_off, size_t len, unsigned int flags)
+{
+#ifdef __NR_copy_file_range
+ return syscall(__NR_copy_file_range, in_fd, in_off, out_fd,
+ out_off, len, flags);
+#else
+ errno = ENOSYS;
+ return -1;
+#endif
+}
+#endif
+
+static int handle_aiocb_copy_range(void *opaque)
+{
+ RawPosixAIOData *aiocb = opaque;
+ uint64_t bytes = aiocb->aio_nbytes;
+ off_t in_off = aiocb->aio_offset;
+ off_t out_off = aiocb->copy_range.aio_offset2;
+
+ while (bytes) {
+ ssize_t ret = copy_file_range(aiocb->aio_fildes, &in_off,
+ aiocb->copy_range.aio_fd2, &out_off,
+ bytes, 0);
+ trace_file_copy_file_range(aiocb->bs, aiocb->aio_fildes, in_off,
+ aiocb->copy_range.aio_fd2, out_off, bytes,
+ 0, ret);
+ if (ret == 0) {
+ /* No progress (e.g. when beyond EOF), let the caller fall back to
+ * buffer I/O. */
+ return -ENOSPC;
+ }
+ if (ret < 0) {
+ switch (errno) {
+ case ENOSYS:
+ return -ENOTSUP;
+ case EINTR:
+ continue;
+ default:
+ return -errno;
+ }
+ }
+ bytes -= ret;
+ }
+ return 0;
+}
+
+static int handle_aiocb_discard(void *opaque)
{
+ RawPosixAIOData *aiocb = opaque;
int ret = -EOPNOTSUPP;
BDRVRawState *s = aiocb->bs->opaque;
return ret;
}
-static int aio_worker(void *arg)
-{
- RawPosixAIOData *aiocb = arg;
- ssize_t ret = 0;
-
- switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
- case QEMU_AIO_READ:
- ret = handle_aiocb_rw(aiocb);
- if (ret >= 0 && ret < aiocb->aio_nbytes) {
- iov_memset(aiocb->aio_iov, aiocb->aio_niov, ret,
- 0, aiocb->aio_nbytes - ret);
-
- ret = aiocb->aio_nbytes;
- }
- if (ret == aiocb->aio_nbytes) {
- ret = 0;
- } else if (ret >= 0 && ret < aiocb->aio_nbytes) {
- ret = -EINVAL;
- }
- break;
- case QEMU_AIO_WRITE:
- ret = handle_aiocb_rw(aiocb);
- if (ret == aiocb->aio_nbytes) {
- ret = 0;
- } else if (ret >= 0 && ret < aiocb->aio_nbytes) {
- ret = -EINVAL;
- }
- break;
- case QEMU_AIO_FLUSH:
- ret = handle_aiocb_flush(aiocb);
- break;
- case QEMU_AIO_IOCTL:
- ret = handle_aiocb_ioctl(aiocb);
- break;
- 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;
- break;
- }
-
- g_free(aiocb);
- return ret;
-}
-
-static int paio_submit_co(BlockDriverState *bs, int fd,
- int64_t offset, QEMUIOVector *qiov,
- int bytes, int type)
-{
- RawPosixAIOData *acb = g_new(RawPosixAIOData, 1);
- ThreadPool *pool;
-
- acb->bs = bs;
- acb->aio_type = type;
- acb->aio_fildes = fd;
-
- acb->aio_nbytes = bytes;
- acb->aio_offset = offset;
-
- if (qiov) {
- acb->aio_iov = qiov->iov;
- acb->aio_niov = qiov->niov;
- assert(qiov->size == bytes);
- }
-
- trace_paio_submit_co(offset, bytes, 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 offset, QEMUIOVector *qiov, int bytes,
- BlockCompletionFunc *cb, void *opaque, int type)
-{
- RawPosixAIOData *acb = g_new(RawPosixAIOData, 1);
- ThreadPool *pool;
-
- acb->bs = bs;
- acb->aio_type = type;
- acb->aio_fildes = fd;
-
- acb->aio_nbytes = bytes;
- acb->aio_offset = offset;
-
- if (qiov) {
- acb->aio_iov = qiov->iov;
- acb->aio_niov = qiov->niov;
- assert(qiov->size == acb->aio_nbytes);
- }
-
- trace_paio_submit(acb, opaque, offset, bytes, type);
- pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
- return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
-}
-
-static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
- uint64_t bytes, QEMUIOVector *qiov, int type)
-{
- BDRVRawState *s = bs->opaque;
-
- if (fd_open(bs) < 0)
- return -EIO;
-
- /*
- * 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 (s->needs_alignment) {
- if (!bdrv_qiov_is_aligned(bs, qiov)) {
- type |= QEMU_AIO_MISALIGNED;
-#ifdef CONFIG_LINUX_AIO
- } else if (s->use_linux_aio) {
- LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
- assert(qiov->size == bytes);
- return laio_co_submit(bs, aio, s->fd, offset, qiov, type);
-#endif
- }
- }
-
- return paio_submit_co(bs, s->fd, offset, qiov, bytes, type);
-}
-
-static int coroutine_fn raw_co_preadv(BlockDriverState *bs, uint64_t offset,
- uint64_t bytes, QEMUIOVector *qiov,
- int flags)
-{
- return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_READ);
-}
-
-static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
- uint64_t bytes, QEMUIOVector *qiov,
- int flags)
-{
- assert(flags == 0);
- return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_WRITE);
-}
-
-static void raw_aio_plug(BlockDriverState *bs)
-{
-#ifdef CONFIG_LINUX_AIO
- BDRVRawState *s = bs->opaque;
- if (s->use_linux_aio) {
- LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
- laio_io_plug(bs, aio);
- }
-#endif
-}
-
-static void raw_aio_unplug(BlockDriverState *bs)
-{
-#ifdef CONFIG_LINUX_AIO
- BDRVRawState *s = bs->opaque;
- if (s->use_linux_aio) {
- LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
- laio_io_unplug(bs, aio);
- }
-#endif
-}
-
-static BlockAIOCB *raw_aio_flush(BlockDriverState *bs,
- BlockCompletionFunc *cb, void *opaque)
-{
- BDRVRawState *s = bs->opaque;
-
- if (fd_open(bs) < 0)
- return NULL;
-
- return paio_submit(bs, s->fd, 0, NULL, 0, cb, opaque, QEMU_AIO_FLUSH);
-}
-
-static void raw_close(BlockDriverState *bs)
-{
- BDRVRawState *s = bs->opaque;
-
- if (s->fd >= 0) {
- qemu_close(s->fd);
- s->fd = -1;
- }
- if (s->lock_fd >= 0) {
- qemu_close(s->lock_fd);
- s->lock_fd = -1;
- }
-}
-
-/**
- * Truncates the given regular file @fd to @offset and, when growing, fills the
- * new space according to @prealloc.
- *
- * Returns: 0 on success, -errno on failure.
- */
-static int raw_regular_truncate(int fd, int64_t offset, PreallocMode prealloc,
- Error **errp)
+static int handle_aiocb_truncate(void *opaque)
{
+ RawPosixAIOData *aiocb = opaque;
int result = 0;
int64_t current_length = 0;
char *buf = NULL;
struct stat st;
+ int fd = aiocb->aio_fildes;
+ int64_t offset = aiocb->aio_offset;
+ PreallocMode prealloc = aiocb->truncate.prealloc;
+ Error **errp = aiocb->truncate.errp;
if (fstat(fd, &st) < 0) {
result = -errno;
* block is allocated before allocating it, so don't do that here.
*/
if (offset != current_length) {
- result = -posix_fallocate(fd, current_length, offset - current_length);
+ result = -posix_fallocate(fd, current_length,
+ offset - current_length);
if (result != 0) {
/* posix_fallocate() doesn't set errno. */
error_setg_errno(errp, -result,
num = MIN(left, 65536);
result = write(fd, buf, num);
if (result < 0) {
+ if (errno == EINTR) {
+ continue;
+ }
result = -errno;
error_setg_errno(errp, -result,
"Could not write zeros for preallocation");
return result;
}
-static int raw_truncate(BlockDriverState *bs, int64_t offset,
- PreallocMode prealloc, Error **errp)
+static int coroutine_fn raw_thread_pool_submit(BlockDriverState *bs,
+ ThreadPoolFunc func, void *arg)
+{
+ /* @bs can be NULL, bdrv_get_aio_context() returns the main context then */
+ ThreadPool *pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
+ return thread_pool_submit_co(pool, func, arg);
+}
+
+static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, QEMUIOVector *qiov, int type)
+{
+ BDRVRawState *s = bs->opaque;
+ RawPosixAIOData acb;
+
+ if (fd_open(bs) < 0)
+ return -EIO;
+
+ /*
+ * 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 (s->needs_alignment) {
+ if (!bdrv_qiov_is_aligned(bs, qiov)) {
+ type |= QEMU_AIO_MISALIGNED;
+#ifdef CONFIG_LINUX_AIO
+ } else if (s->use_linux_aio) {
+ LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
+ assert(qiov->size == bytes);
+ return laio_co_submit(bs, aio, s->fd, offset, qiov, type);
+#endif
+ }
+ }
+
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_fildes = s->fd,
+ .aio_type = type,
+ .aio_offset = offset,
+ .aio_nbytes = bytes,
+ .io = {
+ .iov = qiov->iov,
+ .niov = qiov->niov,
+ },
+ };
+
+ assert(qiov->size == bytes);
+ return raw_thread_pool_submit(bs, handle_aiocb_rw, &acb);
+}
+
+static int coroutine_fn raw_co_preadv(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, QEMUIOVector *qiov,
+ int flags)
+{
+ return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_READ);
+}
+
+static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, QEMUIOVector *qiov,
+ int flags)
+{
+ assert(flags == 0);
+ return raw_co_prw(bs, offset, bytes, qiov, QEMU_AIO_WRITE);
+}
+
+static void raw_aio_plug(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+ if (s->use_linux_aio) {
+ LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
+ laio_io_plug(bs, aio);
+ }
+#endif
+}
+
+static void raw_aio_unplug(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+ if (s->use_linux_aio) {
+ LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs));
+ laio_io_unplug(bs, aio);
+ }
+#endif
+}
+
+static int raw_co_flush_to_disk(BlockDriverState *bs)
+{
+ BDRVRawState *s = bs->opaque;
+ RawPosixAIOData acb;
+ int ret;
+
+ ret = fd_open(bs);
+ if (ret < 0) {
+ return ret;
+ }
+
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_fildes = s->fd,
+ .aio_type = QEMU_AIO_FLUSH,
+ };
+
+ return raw_thread_pool_submit(bs, handle_aiocb_flush, &acb);
+}
+
+static void raw_aio_attach_aio_context(BlockDriverState *bs,
+ AioContext *new_context)
+{
+#ifdef CONFIG_LINUX_AIO
+ BDRVRawState *s = bs->opaque;
+ if (s->use_linux_aio) {
+ Error *local_err;
+ if (!aio_setup_linux_aio(new_context, &local_err)) {
+ error_reportf_err(local_err, "Unable to use native AIO, "
+ "falling back to thread pool: ");
+ s->use_linux_aio = false;
+ }
+ }
+#endif
+}
+
+static void raw_close(BlockDriverState *bs)
+{
+ BDRVRawState *s = bs->opaque;
+
+ if (s->fd >= 0) {
+ qemu_close(s->fd);
+ s->fd = -1;
+ }
+}
+
+/**
+ * Truncates the given regular file @fd to @offset and, when growing, fills the
+ * new space according to @prealloc.
+ *
+ * Returns: 0 on success, -errno on failure.
+ */
+static int coroutine_fn
+raw_regular_truncate(BlockDriverState *bs, int fd, int64_t offset,
+ PreallocMode prealloc, Error **errp)
+{
+ RawPosixAIOData acb;
+
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_fildes = fd,
+ .aio_type = QEMU_AIO_TRUNCATE,
+ .aio_offset = offset,
+ .truncate = {
+ .prealloc = prealloc,
+ .errp = errp,
+ },
+ };
+
+ return raw_thread_pool_submit(bs, handle_aiocb_truncate, &acb);
+}
+
+static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset,
+ PreallocMode prealloc, Error **errp)
{
BDRVRawState *s = bs->opaque;
struct stat st;
}
if (S_ISREG(st.st_mode)) {
- return raw_regular_truncate(s->fd, offset, prealloc, errp);
+ return raw_regular_truncate(bs, s->fd, offset, prealloc, errp);
}
if (prealloc != PREALLOC_MODE_OFF) {
#endif
if (!fstat(fd, &sb) && (S_IFCHR & sb.st_mode)) {
#ifdef DIOCGMEDIASIZE
- if (ioctl(fd, DIOCGMEDIASIZE, (off_t *)&size))
+ if (ioctl(fd, DIOCGMEDIASIZE, (off_t *)&size))
#elif defined(DIOCGPART)
{
struct partinfo pi;
return (int64_t)st.st_blocks * 512;
}
-static int raw_co_create(BlockdevCreateOptions *options, Error **errp)
+static int coroutine_fn
+raw_co_create(BlockdevCreateOptions *options, Error **errp)
{
BlockdevCreateOptionsFile *file_opts;
+ Error *local_err = NULL;
int fd;
+ uint64_t perm, shared;
int result = 0;
/* Validate options and set default values */
}
/* Create file */
- fd = qemu_open(file_opts->filename, O_RDWR | O_CREAT | O_TRUNC | O_BINARY,
- 0644);
+ fd = qemu_open(file_opts->filename, O_RDWR | O_CREAT | O_BINARY, 0644);
if (fd < 0) {
result = -errno;
error_setg_errno(errp, -result, "Could not create file");
goto out;
}
+ /* Take permissions: We want to discard everything, so we need
+ * BLK_PERM_WRITE; and truncation to the desired size requires
+ * BLK_PERM_RESIZE.
+ * On the other hand, we cannot share the RESIZE permission
+ * because we promise that after this function, the file has the
+ * size given in the options. If someone else were to resize it
+ * concurrently, we could not guarantee that.
+ * Note that after this function, we can no longer guarantee that
+ * the file is not touched by a third party, so it may be resized
+ * then. */
+ perm = BLK_PERM_WRITE | BLK_PERM_RESIZE;
+ shared = BLK_PERM_ALL & ~BLK_PERM_RESIZE;
+
+ /* Step one: Take locks */
+ result = raw_apply_lock_bytes(NULL, fd, perm, ~shared, false, errp);
+ if (result < 0) {
+ goto out_close;
+ }
+
+ /* Step two: Check that nobody else has taken conflicting locks */
+ result = raw_check_lock_bytes(fd, perm, shared, errp);
+ if (result < 0) {
+ error_append_hint(errp,
+ "Is another process using the image [%s]?\n",
+ file_opts->filename);
+ goto out_unlock;
+ }
+
+ /* Clear the file by truncating it to 0 */
+ result = raw_regular_truncate(NULL, fd, 0, PREALLOC_MODE_OFF, errp);
+ if (result < 0) {
+ goto out_unlock;
+ }
+
if (file_opts->nocow) {
#ifdef __linux__
/* Set NOCOW flag to solve performance issue on fs like btrfs.
#endif
}
- result = raw_regular_truncate(fd, file_opts->size, file_opts->preallocation,
- errp);
+ /* Resize and potentially preallocate the file to the desired
+ * final size */
+ result = raw_regular_truncate(NULL, fd, file_opts->size,
+ file_opts->preallocation, errp);
if (result < 0) {
- goto out_close;
+ goto out_unlock;
+ }
+
+out_unlock:
+ raw_apply_lock_bytes(NULL, fd, 0, 0, true, &local_err);
+ if (local_err) {
+ /* The above call should not fail, and if it does, that does
+ * not mean the whole creation operation has failed. So
+ * report it the user for their convenience, but do not report
+ * it to the caller. */
+ warn_report_err(local_err);
}
out_close:
return ret | BDRV_BLOCK_OFFSET_VALID;
}
-static coroutine_fn BlockAIOCB *raw_aio_pdiscard(BlockDriverState *bs,
- int64_t offset, int bytes,
- BlockCompletionFunc *cb, void *opaque)
+#if defined(__linux__)
+/* Verify that the file is not in the page cache */
+static void check_cache_dropped(BlockDriverState *bs, Error **errp)
{
+ const size_t window_size = 128 * 1024 * 1024;
BDRVRawState *s = bs->opaque;
+ void *window = NULL;
+ size_t length = 0;
+ unsigned char *vec;
+ size_t page_size;
+ off_t offset;
+ off_t end;
+
+ /* mincore(2) page status information requires 1 byte per page */
+ page_size = sysconf(_SC_PAGESIZE);
+ vec = g_malloc(DIV_ROUND_UP(window_size, page_size));
+
+ end = raw_getlength(bs);
+
+ for (offset = 0; offset < end; offset += window_size) {
+ void *new_window;
+ size_t new_length;
+ size_t vec_end;
+ size_t i;
+ int ret;
+
+ /* Unmap previous window if size has changed */
+ new_length = MIN(end - offset, window_size);
+ if (new_length != length) {
+ munmap(window, length);
+ window = NULL;
+ length = 0;
+ }
+
+ new_window = mmap(window, new_length, PROT_NONE, MAP_PRIVATE,
+ s->fd, offset);
+ if (new_window == MAP_FAILED) {
+ error_setg_errno(errp, errno, "mmap failed");
+ break;
+ }
+
+ window = new_window;
+ length = new_length;
+
+ ret = mincore(window, length, vec);
+ if (ret < 0) {
+ error_setg_errno(errp, errno, "mincore failed");
+ break;
+ }
+
+ vec_end = DIV_ROUND_UP(length, page_size);
+ for (i = 0; i < vec_end; i++) {
+ if (vec[i] & 0x1) {
+ error_setg(errp, "page cache still in use!");
+ break;
+ }
+ }
+ }
- return paio_submit(bs, s->fd, offset, NULL, bytes,
- cb, opaque, QEMU_AIO_DISCARD);
+ if (window) {
+ munmap(window, length);
+ }
+
+ g_free(vec);
}
+#endif /* __linux__ */
-static int coroutine_fn raw_co_pwrite_zeroes(
- BlockDriverState *bs, int64_t offset,
- int bytes, BdrvRequestFlags flags)
+static void coroutine_fn raw_co_invalidate_cache(BlockDriverState *bs,
+ Error **errp)
{
BDRVRawState *s = bs->opaque;
+ int ret;
- if (!(flags & BDRV_REQ_MAY_UNMAP)) {
- return paio_submit_co(bs, s->fd, offset, NULL, bytes,
- QEMU_AIO_WRITE_ZEROES);
- } else if (s->discard_zeroes) {
- return paio_submit_co(bs, s->fd, offset, NULL, bytes,
- QEMU_AIO_DISCARD);
+ ret = fd_open(bs);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "The file descriptor is not open");
+ return;
}
- return -ENOTSUP;
+
+ if (s->open_flags & O_DIRECT) {
+ return; /* No host kernel page cache */
+ }
+
+#if defined(__linux__)
+ /* This sets the scene for the next syscall... */
+ ret = bdrv_co_flush(bs);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "flush failed");
+ return;
+ }
+
+ /* Linux does not invalidate pages that are dirty, locked, or mmapped by a
+ * process. These limitations are okay because we just fsynced the file,
+ * we don't use mmap, and the file should not be in use by other processes.
+ */
+ ret = posix_fadvise(s->fd, 0, 0, POSIX_FADV_DONTNEED);
+ if (ret != 0) { /* the return value is a positive errno */
+ error_setg_errno(errp, ret, "fadvise failed");
+ return;
+ }
+
+ if (s->check_cache_dropped) {
+ check_cache_dropped(bs, errp);
+ }
+#else /* __linux__ */
+ /* Do nothing. Live migration to a remote host with cache.direct=off is
+ * unsupported on other host operating systems. Cache consistency issues
+ * may occur but no error is reported here, partly because that's the
+ * historical behavior and partly because it's hard to differentiate valid
+ * configurations that should not cause errors.
+ */
+#endif /* !__linux__ */
+}
+
+static coroutine_fn int
+raw_do_pdiscard(BlockDriverState *bs, int64_t offset, int bytes, bool blkdev)
+{
+ BDRVRawState *s = bs->opaque;
+ RawPosixAIOData acb;
+
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_fildes = s->fd,
+ .aio_type = QEMU_AIO_DISCARD,
+ .aio_offset = offset,
+ .aio_nbytes = bytes,
+ };
+
+ if (blkdev) {
+ acb.aio_type |= QEMU_AIO_BLKDEV;
+ }
+
+ return raw_thread_pool_submit(bs, handle_aiocb_discard, &acb);
+}
+
+static coroutine_fn int
+raw_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
+{
+ return raw_do_pdiscard(bs, offset, bytes, false);
+}
+
+static int coroutine_fn
+raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
+ BdrvRequestFlags flags, bool blkdev)
+{
+ BDRVRawState *s = bs->opaque;
+ RawPosixAIOData acb;
+ ThreadPoolFunc *handler;
+
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_fildes = s->fd,
+ .aio_type = QEMU_AIO_WRITE_ZEROES,
+ .aio_offset = offset,
+ .aio_nbytes = bytes,
+ };
+
+ if (blkdev) {
+ acb.aio_type |= QEMU_AIO_BLKDEV;
+ }
+
+ if (flags & BDRV_REQ_MAY_UNMAP) {
+ acb.aio_type |= QEMU_AIO_DISCARD;
+ handler = handle_aiocb_write_zeroes_unmap;
+ } else {
+ handler = handle_aiocb_write_zeroes;
+ }
+
+ return raw_thread_pool_submit(bs, handler, &acb);
+}
+
+static int coroutine_fn raw_co_pwrite_zeroes(
+ BlockDriverState *bs, int64_t offset,
+ int bytes, BdrvRequestFlags flags)
+{
+ return raw_do_pwrite_zeroes(bs, offset, bytes, flags, false);
}
static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
raw_handle_perm_lock(bs, RAW_PL_ABORT, 0, 0, NULL);
}
+static int coroutine_fn raw_co_copy_range_from(
+ BlockDriverState *bs, BdrvChild *src, uint64_t src_offset,
+ BdrvChild *dst, uint64_t dst_offset, uint64_t bytes,
+ BdrvRequestFlags read_flags, BdrvRequestFlags write_flags)
+{
+ return bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes,
+ read_flags, write_flags);
+}
+
+static int coroutine_fn raw_co_copy_range_to(BlockDriverState *bs,
+ BdrvChild *src,
+ uint64_t src_offset,
+ BdrvChild *dst,
+ uint64_t dst_offset,
+ uint64_t bytes,
+ BdrvRequestFlags read_flags,
+ BdrvRequestFlags write_flags)
+{
+ RawPosixAIOData acb;
+ BDRVRawState *s = bs->opaque;
+ BDRVRawState *src_s;
+
+ assert(dst->bs == bs);
+ if (src->bs->drv->bdrv_co_copy_range_to != raw_co_copy_range_to) {
+ return -ENOTSUP;
+ }
+
+ src_s = src->bs->opaque;
+ if (fd_open(src->bs) < 0 || fd_open(dst->bs) < 0) {
+ return -EIO;
+ }
+
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_type = QEMU_AIO_COPY_RANGE,
+ .aio_fildes = src_s->fd,
+ .aio_offset = src_offset,
+ .aio_nbytes = bytes,
+ .copy_range = {
+ .aio_fd2 = s->fd,
+ .aio_offset2 = dst_offset,
+ },
+ };
+
+ return raw_thread_pool_submit(bs, handle_aiocb_copy_range, &acb);
+}
+
BlockDriver bdrv_file = {
.format_name = "file",
.protocol_name = "file",
.bdrv_co_create_opts = raw_co_create_opts,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_co_block_status = raw_co_block_status,
+ .bdrv_co_invalidate_cache = raw_co_invalidate_cache,
.bdrv_co_pwrite_zeroes = raw_co_pwrite_zeroes,
.bdrv_co_preadv = raw_co_preadv,
.bdrv_co_pwritev = raw_co_pwritev,
- .bdrv_aio_flush = raw_aio_flush,
- .bdrv_aio_pdiscard = raw_aio_pdiscard,
+ .bdrv_co_flush_to_disk = raw_co_flush_to_disk,
+ .bdrv_co_pdiscard = raw_co_pdiscard,
+ .bdrv_co_copy_range_from = raw_co_copy_range_from,
+ .bdrv_co_copy_range_to = raw_co_copy_range_to,
.bdrv_refresh_limits = raw_refresh_limits,
.bdrv_io_plug = raw_aio_plug,
.bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_attach_aio_context = raw_aio_attach_aio_context,
- .bdrv_truncate = raw_truncate,
+ .bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_info = raw_get_info,
.bdrv_get_allocated_file_size
s->type = FTYPE_FILE;
- ret = raw_open_common(bs, options, flags, 0, &local_err);
+ ret = raw_open_common(bs, options, flags, 0, true, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
#if defined(__APPLE__) && defined(__MACH__)
}
#if defined(__linux__)
-
-static BlockAIOCB *hdev_aio_ioctl(BlockDriverState *bs,
- unsigned long int req, void *buf,
- BlockCompletionFunc *cb, void *opaque)
+static int coroutine_fn
+hdev_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
{
BDRVRawState *s = bs->opaque;
- RawPosixAIOData *acb;
- ThreadPool *pool;
+ RawPosixAIOData acb;
+ int ret;
- if (fd_open(bs) < 0)
- return NULL;
+ ret = fd_open(bs);
+ if (ret < 0) {
+ return ret;
+ }
if (req == SG_IO && s->pr_mgr) {
struct sg_io_hdr *io_hdr = buf;
if (io_hdr->cmdp[0] == PERSISTENT_RESERVE_OUT ||
io_hdr->cmdp[0] == PERSISTENT_RESERVE_IN) {
return pr_manager_execute(s->pr_mgr, bdrv_get_aio_context(bs),
- s->fd, io_hdr, cb, opaque);
+ s->fd, io_hdr);
}
}
- acb = g_new(RawPosixAIOData, 1);
- acb->bs = bs;
- acb->aio_type = QEMU_AIO_IOCTL;
- acb->aio_fildes = s->fd;
- acb->aio_offset = 0;
- acb->aio_ioctl_buf = buf;
- acb->aio_ioctl_cmd = req;
- pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
- return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
+ acb = (RawPosixAIOData) {
+ .bs = bs,
+ .aio_type = QEMU_AIO_IOCTL,
+ .aio_fildes = s->fd,
+ .aio_offset = 0,
+ .ioctl = {
+ .buf = buf,
+ .cmd = req,
+ },
+ };
+
+ return raw_thread_pool_submit(bs, handle_aiocb_ioctl, &acb);
}
#endif /* linux */
return -EIO;
}
-static coroutine_fn BlockAIOCB *hdev_aio_pdiscard(BlockDriverState *bs,
- int64_t offset, int bytes,
- BlockCompletionFunc *cb, void *opaque)
+static coroutine_fn int
+hdev_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
{
- BDRVRawState *s = bs->opaque;
+ int ret;
- if (fd_open(bs) < 0) {
- return NULL;
+ ret = fd_open(bs);
+ if (ret < 0) {
+ return ret;
}
- return paio_submit(bs, s->fd, offset, NULL, bytes,
- cb, opaque, QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);
+ return raw_do_pdiscard(bs, offset, bytes, true);
}
static coroutine_fn int hdev_co_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes, 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, offset, NULL, bytes,
- QEMU_AIO_WRITE_ZEROES|QEMU_AIO_BLKDEV);
- } else if (s->discard_zeroes) {
- return paio_submit_co(bs, s->fd, offset, NULL, bytes,
- QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);
- }
- return -ENOTSUP;
+
+ return raw_do_pwrite_zeroes(bs, offset, bytes, flags, true);
}
static int coroutine_fn hdev_co_create_opts(const char *filename, QemuOpts *opts,
(void)has_prefix;
- ret = raw_normalize_devicepath(&filename);
+ ret = raw_normalize_devicepath(&filename, errp);
if (ret < 0) {
- error_setg_errno(errp, -ret, "Could not normalize device path");
return ret;
}
.bdrv_reopen_abort = raw_reopen_abort,
.bdrv_co_create_opts = hdev_co_create_opts,
.create_opts = &raw_create_opts,
+ .bdrv_co_invalidate_cache = raw_co_invalidate_cache,
.bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes,
.bdrv_co_preadv = raw_co_preadv,
.bdrv_co_pwritev = raw_co_pwritev,
- .bdrv_aio_flush = raw_aio_flush,
- .bdrv_aio_pdiscard = hdev_aio_pdiscard,
+ .bdrv_co_flush_to_disk = raw_co_flush_to_disk,
+ .bdrv_co_pdiscard = hdev_co_pdiscard,
+ .bdrv_co_copy_range_from = raw_co_copy_range_from,
+ .bdrv_co_copy_range_to = raw_co_copy_range_to,
.bdrv_refresh_limits = raw_refresh_limits,
.bdrv_io_plug = raw_aio_plug,
.bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_attach_aio_context = raw_aio_attach_aio_context,
- .bdrv_truncate = raw_truncate,
+ .bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.bdrv_get_info = raw_get_info,
.bdrv_get_allocated_file_size
/* generic scsi device */
#ifdef __linux__
- .bdrv_aio_ioctl = hdev_aio_ioctl,
+ .bdrv_co_ioctl = hdev_co_ioctl,
#endif
};
s->type = FTYPE_CD;
/* open will not fail even if no CD is inserted, so add O_NONBLOCK */
- return raw_open_common(bs, options, flags, O_NONBLOCK, errp);
+ return raw_open_common(bs, options, flags, O_NONBLOCK, true, errp);
}
static int cdrom_probe_device(const char *filename)
.bdrv_reopen_abort = raw_reopen_abort,
.bdrv_co_create_opts = hdev_co_create_opts,
.create_opts = &raw_create_opts,
+ .bdrv_co_invalidate_cache = raw_co_invalidate_cache,
.bdrv_co_preadv = raw_co_preadv,
.bdrv_co_pwritev = raw_co_pwritev,
- .bdrv_aio_flush = raw_aio_flush,
+ .bdrv_co_flush_to_disk = raw_co_flush_to_disk,
.bdrv_refresh_limits = raw_refresh_limits,
.bdrv_io_plug = raw_aio_plug,
.bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_attach_aio_context = raw_aio_attach_aio_context,
- .bdrv_truncate = raw_truncate,
+ .bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.has_variable_length = true,
.bdrv_get_allocated_file_size
.bdrv_lock_medium = cdrom_lock_medium,
/* generic scsi device */
- .bdrv_aio_ioctl = hdev_aio_ioctl,
+ .bdrv_co_ioctl = hdev_co_ioctl,
};
#endif /* __linux__ */
s->type = FTYPE_CD;
- ret = raw_open_common(bs, options, flags, 0, &local_err);
+ ret = raw_open_common(bs, options, flags, 0, true, &local_err);
if (ret) {
error_propagate(errp, local_err);
return ret;
.bdrv_co_preadv = raw_co_preadv,
.bdrv_co_pwritev = raw_co_pwritev,
- .bdrv_aio_flush = raw_aio_flush,
+ .bdrv_co_flush_to_disk = raw_co_flush_to_disk,
.bdrv_refresh_limits = raw_refresh_limits,
.bdrv_io_plug = raw_aio_plug,
.bdrv_io_unplug = raw_aio_unplug,
+ .bdrv_attach_aio_context = raw_aio_attach_aio_context,
- .bdrv_truncate = raw_truncate,
+ .bdrv_co_truncate = raw_co_truncate,
.bdrv_getlength = raw_getlength,
.has_variable_length = true,
.bdrv_get_allocated_file_size
projects / qemu.git / blobdiff