/* Maximum bounce buffer for copy-on-read and write zeroes, in bytes */
#define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS)
-static AioWait drain_all_aio_wait;
-
+static void bdrv_parent_cb_resize(BlockDriverState *bs);
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes, BdrvRequestFlags flags);
if (c == ignore || (ignore_bds_parents && c->role->parent_is_bds)) {
continue;
}
- if (c->role->drained_begin) {
- c->role->drained_begin(c);
- }
+ bdrv_parent_drained_begin_single(c, false);
}
}
}
}
+static bool bdrv_parent_drained_poll_single(BdrvChild *c)
+{
+ if (c->role->drained_poll) {
+ return c->role->drained_poll(c);
+ }
+ return false;
+}
+
static bool bdrv_parent_drained_poll(BlockDriverState *bs, BdrvChild *ignore,
bool ignore_bds_parents)
{
if (c == ignore || (ignore_bds_parents && c->role->parent_is_bds)) {
continue;
}
- if (c->role->drained_poll) {
- busy |= c->role->drained_poll(c);
- }
+ busy |= bdrv_parent_drained_poll_single(c);
}
return busy;
}
+void bdrv_parent_drained_begin_single(BdrvChild *c, bool poll)
+{
+ if (c->role->drained_begin) {
+ c->role->drained_begin(c);
+ }
+ if (poll) {
+ BDRV_POLL_WHILE(c->bs, bdrv_parent_drained_poll_single(c));
+ }
+}
+
static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src)
{
dst->opt_transfer = MAX(dst->opt_transfer, src->opt_transfer);
static bool bdrv_drain_poll_top_level(BlockDriverState *bs, bool recursive,
BdrvChild *ignore_parent)
{
- /* Execute pending BHs first and check everything else only after the BHs
- * have executed. */
- while (aio_poll(bs->aio_context, false));
-
return bdrv_drain_poll(bs, recursive, ignore_parent, false);
}
BlockDriverState *bs = data->bs;
if (bs) {
+ AioContext *ctx = bdrv_get_aio_context(bs);
+ AioContext *co_ctx = qemu_coroutine_get_aio_context(co);
+
+ /*
+ * When the coroutine yielded, the lock for its home context was
+ * released, so we need to re-acquire it here. If it explicitly
+ * acquired a different context, the lock is still held and we don't
+ * want to lock it a second time (or AIO_WAIT_WHILE() would hang).
+ */
+ if (ctx == co_ctx) {
+ aio_context_acquire(ctx);
+ }
bdrv_dec_in_flight(bs);
if (data->begin) {
bdrv_do_drained_begin(bs, data->recursive, data->parent,
bdrv_do_drained_end(bs, data->recursive, data->parent,
data->ignore_bds_parents);
}
+ if (ctx == co_ctx) {
+ aio_context_release(ctx);
+ }
} else {
assert(data->begin);
bdrv_drain_all_begin();
BlockDriverState *bs = NULL;
bool result = false;
- /* Execute pending BHs first (may modify the graph) and check everything
- * else only after the BHs have executed. */
- while (aio_poll(qemu_get_aio_context(), false));
-
/* bdrv_drain_poll() can't make changes to the graph and we are holding the
* main AioContext lock, so iterating bdrv_next_all_states() is safe. */
while ((bs = bdrv_next_all_states(bs))) {
}
/* Now poll the in-flight requests */
- AIO_WAIT_WHILE(&drain_all_aio_wait, NULL, bdrv_drain_all_poll());
+ AIO_WAIT_WHILE(NULL, bdrv_drain_all_poll());
while ((bs = bdrv_next_all_states(bs))) {
bdrv_drain_assert_idle(bs);
static void tracked_request_begin(BdrvTrackedRequest *req,
BlockDriverState *bs,
int64_t offset,
- unsigned int bytes,
+ uint64_t bytes,
enum BdrvTrackedRequestType type)
{
+ assert(bytes <= INT64_MAX && offset <= INT64_MAX - bytes);
+
*req = (BdrvTrackedRequest){
.bs = bs,
.offset = offset,
static void mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
{
int64_t overlap_offset = req->offset & ~(align - 1);
- unsigned int overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
+ uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
- overlap_offset;
if (!req->serialising) {
req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes);
}
+static bool is_request_serialising_and_aligned(BdrvTrackedRequest *req)
+{
+ /*
+ * If the request is serialising, overlap_offset and overlap_bytes are set,
+ * so we can check if the request is aligned. Otherwise, don't care and
+ * return false.
+ */
+
+ return req->serialising && (req->offset == req->overlap_offset) &&
+ (req->bytes == req->overlap_bytes);
+}
+
/**
* Round a region to cluster boundaries
*/
}
static bool tracked_request_overlaps(BdrvTrackedRequest *req,
- int64_t offset, unsigned int bytes)
+ int64_t offset, uint64_t bytes)
{
/* aaaa bbbb */
if (offset >= req->overlap_offset + req->overlap_bytes) {
void bdrv_wakeup(BlockDriverState *bs)
{
- aio_wait_kick(bdrv_get_aio_wait(bs));
- aio_wait_kick(&drain_all_aio_wait);
+ aio_wait_kick();
}
void bdrv_dec_in_flight(BlockDriverState *bs)
static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
size_t size)
{
- if (size > BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS) {
+ if (size > BDRV_REQUEST_MAX_BYTES) {
return -EIO;
}
rwco->qiov->size, rwco->qiov,
rwco->flags);
}
+ aio_wait_kick();
}
/*
return rwco.ret;
}
-/*
- * Process a synchronous request using coroutines
- */
-static int bdrv_rw_co(BdrvChild *child, int64_t sector_num, uint8_t *buf,
- int nb_sectors, bool is_write, BdrvRequestFlags flags)
-{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *)buf,
- .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
- };
-
- if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
- return -EINVAL;
- }
-
- qemu_iovec_init_external(&qiov, &iov, 1);
- return bdrv_prwv_co(child, sector_num << BDRV_SECTOR_BITS,
- &qiov, is_write, flags);
-}
-
-/* return < 0 if error. See bdrv_write() for the return codes */
-int bdrv_read(BdrvChild *child, int64_t sector_num,
- uint8_t *buf, int nb_sectors)
-{
- return bdrv_rw_co(child, sector_num, buf, nb_sectors, false, 0);
-}
-
-/* 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(BdrvChild *child, int64_t sector_num,
- const uint8_t *buf, int nb_sectors)
-{
- return bdrv_rw_co(child, sector_num, (uint8_t *)buf, nb_sectors, true, 0);
-}
-
int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset,
int bytes, BdrvRequestFlags flags)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = NULL,
- .iov_len = bytes,
- };
+ QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, NULL, bytes);
- qemu_iovec_init_external(&qiov, &iov, 1);
return bdrv_prwv_co(child, offset, &qiov, true,
BDRV_REQ_ZERO_WRITE | flags);
}
}
ret = bdrv_block_status(bs, offset, bytes, &bytes, NULL, NULL);
if (ret < 0) {
- error_report("error getting block status at offset %" PRId64 ": %s",
- offset, strerror(-ret));
return ret;
}
if (ret & BDRV_BLOCK_ZERO) {
}
ret = bdrv_pwrite_zeroes(child, offset, bytes, flags);
if (ret < 0) {
- error_report("error writing zeroes at offset %" PRId64 ": %s",
- offset, strerror(-ret));
return ret;
}
offset += bytes;
return qiov->size;
}
+/* See bdrv_pwrite() for the return codes */
int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int bytes)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *)buf,
- .iov_len = bytes,
- };
+ QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
if (bytes < 0) {
return -EINVAL;
}
- qemu_iovec_init_external(&qiov, &iov, 1);
return bdrv_preadv(child, offset, &qiov);
}
return qiov->size;
}
+/* Return no. of bytes on success or < 0 on error. Important errors are:
+ -EIO generic I/O error (may happen for all errors)
+ -ENOMEDIUM No media inserted.
+ -EINVAL Invalid offset or number of bytes
+ -EACCES Trying to write a read-only device
+*/
int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, int bytes)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *) buf,
- .iov_len = bytes,
- };
+ QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);
if (bytes < 0) {
return -EINVAL;
}
- qemu_iovec_init_external(&qiov, &iov, 1);
return bdrv_pwritev(child, offset, &qiov);
}
unsigned int nb_sectors;
assert(!(flags & ~BDRV_REQ_MASK));
+ assert(!(flags & BDRV_REQ_NO_FALLBACK));
if (!drv) {
return -ENOMEDIUM;
assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes >> BDRV_SECTOR_BITS) <= BDRV_REQUEST_MAX_SECTORS);
+ assert(bytes <= BDRV_REQUEST_MAX_BYTES);
assert(drv->bdrv_co_readv);
return drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
int ret;
assert(!(flags & ~BDRV_REQ_MASK));
+ assert(!(flags & BDRV_REQ_NO_FALLBACK));
if (!drv) {
return -ENOMEDIUM;
assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes >> BDRV_SECTOR_BITS) <= BDRV_REQUEST_MAX_SECTORS);
+ assert(bytes <= BDRV_REQUEST_MAX_BYTES);
assert(drv->bdrv_co_writev);
ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov,
void *bounce_buffer;
BlockDriver *drv = bs->drv;
- struct iovec iov;
QEMUIOVector local_qiov;
int64_t cluster_offset;
int64_t cluster_bytes;
pnum = MIN(cluster_bytes, max_transfer);
}
+ /* Stop at EOF if the image ends in the middle of the cluster */
+ if (ret == 0 && pnum == 0) {
+ assert(progress >= bytes);
+ break;
+ }
+
assert(skip_bytes < pnum);
if (ret <= 0) {
/* Must copy-on-read; use the bounce buffer */
- iov.iov_base = bounce_buffer;
- iov.iov_len = pnum = MIN(pnum, MAX_BOUNCE_BUFFER);
- qemu_iovec_init_external(&local_qiov, &iov, 1);
+ pnum = MIN(pnum, MAX_BOUNCE_BUFFER);
+ qemu_iovec_init_buf(&local_qiov, bounce_buffer, pnum);
ret = bdrv_driver_preadv(bs, cluster_offset, pnum,
&local_qiov, 0);
mark_request_serialising(req, bdrv_get_cluster_size(bs));
}
+ /* BDRV_REQ_SERIALISING is only for write operation */
+ assert(!(flags & BDRV_REQ_SERIALISING));
+
if (!(flags & BDRV_REQ_NO_SERIALISING)) {
wait_serialising_requests(req);
}
return ret;
}
-static int coroutine_fn bdrv_co_do_readv(BdrvChild *child,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
- return -EINVAL;
- }
-
- return bdrv_co_preadv(child, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
-}
-
-int coroutine_fn bdrv_co_readv(BdrvChild *child, int64_t sector_num,
- int nb_sectors, QEMUIOVector *qiov)
-{
- return bdrv_co_do_readv(child, sector_num, nb_sectors, qiov, 0);
-}
-
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes, BdrvRequestFlags flags)
{
BlockDriver *drv = bs->drv;
QEMUIOVector qiov;
- struct iovec iov = {0};
+ void *buf = NULL;
int ret = 0;
bool need_flush = false;
int head = 0;
return -ENOMEDIUM;
}
+ if ((flags & ~bs->supported_zero_flags) & BDRV_REQ_NO_FALLBACK) {
+ return -ENOTSUP;
+ }
+
assert(alignment % bs->bl.request_alignment == 0);
head = offset % alignment;
tail = (offset + bytes) % alignment;
assert(!bs->supported_zero_flags);
}
- if (ret == -ENOTSUP) {
+ if (ret < 0 && !(flags & BDRV_REQ_NO_FALLBACK)) {
/* Fall back to bounce buffer if write zeroes is unsupported */
BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE;
need_flush = true;
}
num = MIN(num, max_transfer);
- iov.iov_len = num;
- if (iov.iov_base == NULL) {
- iov.iov_base = qemu_try_blockalign(bs, num);
- if (iov.iov_base == NULL) {
+ if (buf == NULL) {
+ buf = qemu_try_blockalign0(bs, num);
+ if (buf == NULL) {
ret = -ENOMEM;
goto fail;
}
- memset(iov.iov_base, 0, num);
}
- qemu_iovec_init_external(&qiov, &iov, 1);
+ qemu_iovec_init_buf(&qiov, buf, num);
ret = bdrv_driver_pwritev(bs, offset, num, &qiov, write_flags);
* all future requests.
*/
if (num < max_transfer) {
- qemu_vfree(iov.iov_base);
- iov.iov_base = NULL;
+ qemu_vfree(buf);
+ buf = NULL;
}
}
if (ret == 0 && need_flush) {
ret = bdrv_co_flush(bs);
}
- qemu_vfree(iov.iov_base);
+ qemu_vfree(buf);
return ret;
}
+static inline int coroutine_fn
+bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes,
+ BdrvTrackedRequest *req, int flags)
+{
+ BlockDriverState *bs = child->bs;
+ bool waited;
+ int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
+
+ if (bs->read_only) {
+ return -EPERM;
+ }
+
+ /* BDRV_REQ_NO_SERIALISING is only for read operation */
+ assert(!(flags & BDRV_REQ_NO_SERIALISING));
+ assert(!(bs->open_flags & BDRV_O_INACTIVE));
+ assert((bs->open_flags & BDRV_O_NO_IO) == 0);
+ assert(!(flags & ~BDRV_REQ_MASK));
+
+ if (flags & BDRV_REQ_SERIALISING) {
+ mark_request_serialising(req, bdrv_get_cluster_size(bs));
+ }
+
+ waited = wait_serialising_requests(req);
+
+ assert(!waited || !req->serialising ||
+ is_request_serialising_and_aligned(req));
+ assert(req->overlap_offset <= offset);
+ assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
+ assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
+
+ switch (req->type) {
+ case BDRV_TRACKED_WRITE:
+ case BDRV_TRACKED_DISCARD:
+ if (flags & BDRV_REQ_WRITE_UNCHANGED) {
+ assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
+ } else {
+ assert(child->perm & BLK_PERM_WRITE);
+ }
+ return notifier_with_return_list_notify(&bs->before_write_notifiers,
+ req);
+ case BDRV_TRACKED_TRUNCATE:
+ assert(child->perm & BLK_PERM_RESIZE);
+ return 0;
+ default:
+ abort();
+ }
+}
+
+static inline void coroutine_fn
+bdrv_co_write_req_finish(BdrvChild *child, int64_t offset, uint64_t bytes,
+ BdrvTrackedRequest *req, int ret)
+{
+ int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
+ BlockDriverState *bs = child->bs;
+
+ atomic_inc(&bs->write_gen);
+
+ /*
+ * Discard cannot extend the image, but in error handling cases, such as
+ * when reverting a qcow2 cluster allocation, the discarded range can pass
+ * the end of image file, so we cannot assert about BDRV_TRACKED_DISCARD
+ * here. Instead, just skip it, since semantically a discard request
+ * beyond EOF cannot expand the image anyway.
+ */
+ if (ret == 0 &&
+ (req->type == BDRV_TRACKED_TRUNCATE ||
+ end_sector > bs->total_sectors) &&
+ req->type != BDRV_TRACKED_DISCARD) {
+ bs->total_sectors = end_sector;
+ bdrv_parent_cb_resize(bs);
+ bdrv_dirty_bitmap_truncate(bs, end_sector << BDRV_SECTOR_BITS);
+ }
+ if (req->bytes) {
+ switch (req->type) {
+ case BDRV_TRACKED_WRITE:
+ stat64_max(&bs->wr_highest_offset, offset + bytes);
+ /* fall through, to set dirty bits */
+ case BDRV_TRACKED_DISCARD:
+ bdrv_set_dirty(bs, offset, bytes);
+ break;
+ default:
+ break;
+ }
+ }
+}
+
/*
* Forwards an already correctly aligned write request to the BlockDriver,
* after possibly fragmenting it.
{
BlockDriverState *bs = child->bs;
BlockDriver *drv = bs->drv;
- bool waited;
int ret;
- int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
uint64_t bytes_remaining = bytes;
int max_transfer;
assert((offset & (align - 1)) == 0);
assert((bytes & (align - 1)) == 0);
assert(!qiov || bytes == qiov->size);
- assert((bs->open_flags & BDRV_O_NO_IO) == 0);
- assert(!(flags & ~BDRV_REQ_MASK));
max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX),
align);
- waited = wait_serialising_requests(req);
- assert(!waited || !req->serialising);
- assert(req->overlap_offset <= offset);
- assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
- if (flags & BDRV_REQ_WRITE_UNCHANGED) {
- assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
- } else {
- assert(child->perm & BLK_PERM_WRITE);
- }
- assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
-
- ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
+ ret = bdrv_co_write_req_prepare(child, offset, bytes, req, flags);
if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF &&
!(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_pwrite_zeroes &&
}
bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE);
- atomic_inc(&bs->write_gen);
- bdrv_set_dirty(bs, offset, bytes);
-
- stat64_max(&bs->wr_highest_offset, offset + bytes);
-
if (ret >= 0) {
- bs->total_sectors = MAX(bs->total_sectors, end_sector);
ret = 0;
}
+ bdrv_co_write_req_finish(child, offset, bytes, req, ret);
return ret;
}
BlockDriverState *bs = child->bs;
uint8_t *buf = NULL;
QEMUIOVector local_qiov;
- struct iovec iov;
uint64_t align = bs->bl.request_alignment;
unsigned int head_padding_bytes, tail_padding_bytes;
int ret = 0;
assert(flags & BDRV_REQ_ZERO_WRITE);
if (head_padding_bytes || tail_padding_bytes) {
buf = qemu_blockalign(bs, align);
- iov = (struct iovec) {
- .iov_base = buf,
- .iov_len = align,
- };
- qemu_iovec_init_external(&local_qiov, &iov, 1);
+ qemu_iovec_init_buf(&local_qiov, buf, align);
}
if (head_padding_bytes) {
uint64_t zero_bytes = MIN(bytes, align - head_padding_bytes);
if (!bs->drv) {
return -ENOMEDIUM;
}
- if (bs->read_only) {
- return -EPERM;
- }
- assert(!(bs->open_flags & BDRV_O_INACTIVE));
ret = bdrv_check_byte_request(bs, offset, bytes);
if (ret < 0) {
if (offset & (align - 1)) {
QEMUIOVector head_qiov;
- struct iovec head_iov;
mark_request_serialising(&req, align);
wait_serialising_requests(&req);
head_buf = qemu_blockalign(bs, align);
- head_iov = (struct iovec) {
- .iov_base = head_buf,
- .iov_len = align,
- };
- qemu_iovec_init_external(&head_qiov, &head_iov, 1);
+ qemu_iovec_init_buf(&head_qiov, head_buf, align);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
ret = bdrv_aligned_preadv(child, &req, offset & ~(align - 1), align,
if ((offset + bytes) & (align - 1)) {
QEMUIOVector tail_qiov;
- struct iovec tail_iov;
size_t tail_bytes;
bool waited;
assert(!waited || !use_local_qiov);
tail_buf = qemu_blockalign(bs, align);
- tail_iov = (struct iovec) {
- .iov_base = tail_buf,
- .iov_len = align,
- };
- qemu_iovec_init_external(&tail_qiov, &tail_iov, 1);
+ qemu_iovec_init_buf(&tail_qiov, tail_buf, align);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
ret = bdrv_aligned_preadv(child, &req, (offset + bytes) & ~(align - 1),
return ret;
}
-static int coroutine_fn bdrv_co_do_writev(BdrvChild *child,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
- BdrvRequestFlags flags)
-{
- if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) {
- return -EINVAL;
- }
-
- return bdrv_co_pwritev(child, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
-}
-
-int coroutine_fn bdrv_co_writev(BdrvChild *child, int64_t sector_num,
- int nb_sectors, QEMUIOVector *qiov)
-{
- return bdrv_co_do_writev(child, sector_num, nb_sectors, qiov, 0);
-}
-
int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset,
int bytes, BdrvRequestFlags flags)
{
data->offset, data->bytes,
data->pnum, data->map, data->file);
data->done = true;
+ aio_wait_kick();
}
/*
{
BdrvVmstateCo *co = opaque;
co->ret = bdrv_co_rw_vmstate(co->bs, co->qiov, co->pos, co->is_read);
+ aio_wait_kick();
}
static inline int
int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
int64_t pos, int size)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = (void *) buf,
- .iov_len = size,
- };
+ QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size);
int ret;
- qemu_iovec_init_external(&qiov, &iov, 1);
-
ret = bdrv_writev_vmstate(bs, &qiov, pos);
if (ret < 0) {
return ret;
int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
int64_t pos, int size)
{
- QEMUIOVector qiov;
- struct iovec iov = {
- .iov_base = buf,
- .iov_len = size,
- };
+ QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size);
int ret;
- qemu_iovec_init_external(&qiov, &iov, 1);
ret = bdrv_readv_vmstate(bs, &qiov, pos);
if (ret < 0) {
return ret;
FlushCo *rwco = opaque;
rwco->ret = bdrv_co_flush(rwco->bs);
+ aio_wait_kick();
}
int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
}
typedef struct DiscardCo {
- BlockDriverState *bs;
+ BdrvChild *child;
int64_t offset;
int bytes;
int ret;
{
DiscardCo *rwco = opaque;
- rwco->ret = bdrv_co_pdiscard(rwco->bs, rwco->offset, rwco->bytes);
+ rwco->ret = bdrv_co_pdiscard(rwco->child, rwco->offset, rwco->bytes);
+ aio_wait_kick();
}
-int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset,
- int bytes)
+int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int bytes)
{
BdrvTrackedRequest req;
int max_pdiscard, ret;
int head, tail, align;
+ BlockDriverState *bs = child->bs;
- if (!bs->drv) {
+ if (!bs || !bs->drv) {
return -ENOMEDIUM;
}
ret = bdrv_check_byte_request(bs, offset, bytes);
if (ret < 0) {
return ret;
- } else if (bs->read_only) {
- return -EPERM;
}
- assert(!(bs->open_flags & BDRV_O_INACTIVE));
/* Do nothing if disabled. */
if (!(bs->open_flags & BDRV_O_UNMAP)) {
bdrv_inc_in_flight(bs);
tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_DISCARD);
- ret = notifier_with_return_list_notify(&bs->before_write_notifiers, &req);
+ ret = bdrv_co_write_req_prepare(child, offset, bytes, &req, 0);
if (ret < 0) {
goto out;
}
}
ret = 0;
out:
- atomic_inc(&bs->write_gen);
- bdrv_set_dirty(bs, req.offset, req.bytes);
+ bdrv_co_write_req_finish(child, req.offset, req.bytes, &req, ret);
tracked_request_end(&req);
bdrv_dec_in_flight(bs);
return ret;
}
-int bdrv_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
+int bdrv_pdiscard(BdrvChild *child, int64_t offset, int bytes)
{
Coroutine *co;
DiscardCo rwco = {
- .bs = bs,
+ .child = child,
.offset = offset,
.bytes = bytes,
.ret = NOT_DONE,
bdrv_pdiscard_co_entry(&rwco);
} else {
co = qemu_coroutine_create(bdrv_pdiscard_co_entry, &rwco);
- bdrv_coroutine_enter(bs, co);
- BDRV_POLL_WHILE(bs, rwco.ret == NOT_DONE);
+ bdrv_coroutine_enter(child->bs, co);
+ BDRV_POLL_WHILE(child->bs, rwco.ret == NOT_DONE);
}
return rwco.ret;
}
}
-static int coroutine_fn bdrv_co_copy_range_internal(BdrvChild *src,
- uint64_t src_offset,
- BdrvChild *dst,
- uint64_t dst_offset,
- uint64_t bytes,
- BdrvRequestFlags flags,
- bool recurse_src)
+static int coroutine_fn bdrv_co_copy_range_internal(
+ BdrvChild *src, uint64_t src_offset, BdrvChild *dst,
+ uint64_t dst_offset, uint64_t bytes,
+ BdrvRequestFlags read_flags, BdrvRequestFlags write_flags,
+ bool recurse_src)
{
+ BdrvTrackedRequest req;
int ret;
- if (!src || !dst || !src->bs || !dst->bs) {
+ /* TODO We can support BDRV_REQ_NO_FALLBACK here */
+ assert(!(read_flags & BDRV_REQ_NO_FALLBACK));
+ assert(!(write_flags & BDRV_REQ_NO_FALLBACK));
+
+ if (!dst || !dst->bs) {
return -ENOMEDIUM;
}
- ret = bdrv_check_byte_request(src->bs, src_offset, bytes);
+ ret = bdrv_check_byte_request(dst->bs, dst_offset, bytes);
if (ret) {
return ret;
}
+ if (write_flags & BDRV_REQ_ZERO_WRITE) {
+ return bdrv_co_pwrite_zeroes(dst, dst_offset, bytes, write_flags);
+ }
- ret = bdrv_check_byte_request(dst->bs, dst_offset, bytes);
+ if (!src || !src->bs) {
+ return -ENOMEDIUM;
+ }
+ ret = bdrv_check_byte_request(src->bs, src_offset, bytes);
if (ret) {
return ret;
}
- if (flags & BDRV_REQ_ZERO_WRITE) {
- return bdrv_co_pwrite_zeroes(dst, dst_offset, bytes, flags);
- }
if (!src->bs->drv->bdrv_co_copy_range_from
|| !dst->bs->drv->bdrv_co_copy_range_to
|| src->bs->encrypted || dst->bs->encrypted) {
return -ENOTSUP;
}
+
if (recurse_src) {
- return src->bs->drv->bdrv_co_copy_range_from(src->bs,
- src, src_offset,
- dst, dst_offset,
- bytes, flags);
+ bdrv_inc_in_flight(src->bs);
+ tracked_request_begin(&req, src->bs, src_offset, bytes,
+ BDRV_TRACKED_READ);
+
+ /* BDRV_REQ_SERIALISING is only for write operation */
+ assert(!(read_flags & BDRV_REQ_SERIALISING));
+ if (!(read_flags & BDRV_REQ_NO_SERIALISING)) {
+ wait_serialising_requests(&req);
+ }
+
+ ret = src->bs->drv->bdrv_co_copy_range_from(src->bs,
+ src, src_offset,
+ dst, dst_offset,
+ bytes,
+ read_flags, write_flags);
+
+ tracked_request_end(&req);
+ bdrv_dec_in_flight(src->bs);
} else {
- return dst->bs->drv->bdrv_co_copy_range_to(dst->bs,
- src, src_offset,
- dst, dst_offset,
- bytes, flags);
+ bdrv_inc_in_flight(dst->bs);
+ tracked_request_begin(&req, dst->bs, dst_offset, bytes,
+ BDRV_TRACKED_WRITE);
+ ret = bdrv_co_write_req_prepare(dst, dst_offset, bytes, &req,
+ write_flags);
+ if (!ret) {
+ ret = dst->bs->drv->bdrv_co_copy_range_to(dst->bs,
+ src, src_offset,
+ dst, dst_offset,
+ bytes,
+ read_flags, write_flags);
+ }
+ bdrv_co_write_req_finish(dst, dst_offset, bytes, &req, ret);
+ tracked_request_end(&req);
+ bdrv_dec_in_flight(dst->bs);
}
+
+ return ret;
}
/* Copy range from @src to @dst.
* semantics. */
int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
- uint64_t bytes, BdrvRequestFlags flags)
+ uint64_t bytes,
+ BdrvRequestFlags read_flags,
+ BdrvRequestFlags write_flags)
{
+ trace_bdrv_co_copy_range_from(src, src_offset, dst, dst_offset, bytes,
+ read_flags, write_flags);
return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
- bytes, flags, true);
+ bytes, read_flags, write_flags, true);
}
/* Copy range from @src to @dst.
* semantics. */
int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
- uint64_t bytes, BdrvRequestFlags flags)
+ uint64_t bytes,
+ BdrvRequestFlags read_flags,
+ BdrvRequestFlags write_flags)
{
+ trace_bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes,
+ read_flags, write_flags);
return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
- bytes, flags, false);
+ bytes, read_flags, write_flags, false);
}
int coroutine_fn bdrv_co_copy_range(BdrvChild *src, uint64_t src_offset,
BdrvChild *dst, uint64_t dst_offset,
- uint64_t bytes, BdrvRequestFlags flags)
+ uint64_t bytes, BdrvRequestFlags read_flags,
+ BdrvRequestFlags write_flags)
+{
+ return bdrv_co_copy_range_from(src, src_offset,
+ dst, dst_offset,
+ bytes, read_flags, write_flags);
+}
+
+static void bdrv_parent_cb_resize(BlockDriverState *bs)
+{
+ BdrvChild *c;
+ QLIST_FOREACH(c, &bs->parents, next_parent) {
+ if (c->role->resize) {
+ c->role->resize(c);
+ }
+ }
+}
+
+/**
+ * Truncate file to 'offset' bytes (needed only for file protocols)
+ */
+int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset,
+ PreallocMode prealloc, Error **errp)
{
- BdrvTrackedRequest src_req, dst_req;
- BlockDriverState *src_bs = src->bs;
- BlockDriverState *dst_bs = dst->bs;
+ BlockDriverState *bs = child->bs;
+ BlockDriver *drv = bs->drv;
+ BdrvTrackedRequest req;
+ int64_t old_size, new_bytes;
int ret;
- bdrv_inc_in_flight(src_bs);
- bdrv_inc_in_flight(dst_bs);
- tracked_request_begin(&src_req, src_bs, src_offset,
- bytes, BDRV_TRACKED_READ);
- tracked_request_begin(&dst_req, dst_bs, dst_offset,
- bytes, BDRV_TRACKED_WRITE);
-
- wait_serialising_requests(&src_req);
- wait_serialising_requests(&dst_req);
- ret = bdrv_co_copy_range_from(src, src_offset,
- dst, dst_offset,
- bytes, flags);
-
- tracked_request_end(&src_req);
- tracked_request_end(&dst_req);
- bdrv_dec_in_flight(src_bs);
- bdrv_dec_in_flight(dst_bs);
+
+ /* if bs->drv == NULL, bs is closed, so there's nothing to do here */
+ if (!drv) {
+ error_setg(errp, "No medium inserted");
+ return -ENOMEDIUM;
+ }
+ if (offset < 0) {
+ error_setg(errp, "Image size cannot be negative");
+ return -EINVAL;
+ }
+
+ old_size = bdrv_getlength(bs);
+ if (old_size < 0) {
+ error_setg_errno(errp, -old_size, "Failed to get old image size");
+ return old_size;
+ }
+
+ if (offset > old_size) {
+ new_bytes = offset - old_size;
+ } else {
+ new_bytes = 0;
+ }
+
+ bdrv_inc_in_flight(bs);
+ tracked_request_begin(&req, bs, offset - new_bytes, new_bytes,
+ BDRV_TRACKED_TRUNCATE);
+
+ /* If we are growing the image and potentially using preallocation for the
+ * new area, we need to make sure that no write requests are made to it
+ * concurrently or they might be overwritten by preallocation. */
+ if (new_bytes) {
+ mark_request_serialising(&req, 1);
+ }
+ if (bs->read_only) {
+ error_setg(errp, "Image is read-only");
+ ret = -EACCES;
+ goto out;
+ }
+ ret = bdrv_co_write_req_prepare(child, offset - new_bytes, new_bytes, &req,
+ 0);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret,
+ "Failed to prepare request for truncation");
+ goto out;
+ }
+
+ if (!drv->bdrv_co_truncate) {
+ if (bs->file && drv->is_filter) {
+ ret = bdrv_co_truncate(bs->file, offset, prealloc, errp);
+ goto out;
+ }
+ error_setg(errp, "Image format driver does not support resize");
+ ret = -ENOTSUP;
+ goto out;
+ }
+
+ ret = drv->bdrv_co_truncate(bs, offset, prealloc, errp);
+ if (ret < 0) {
+ goto out;
+ }
+ ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "Could not refresh total sector count");
+ } else {
+ offset = bs->total_sectors * BDRV_SECTOR_SIZE;
+ }
+ /* It's possible that truncation succeeded but refresh_total_sectors
+ * failed, but the latter doesn't affect how we should finish the request.
+ * Pass 0 as the last parameter so that dirty bitmaps etc. are handled. */
+ bdrv_co_write_req_finish(child, offset - new_bytes, new_bytes, &req, 0);
+
+out:
+ tracked_request_end(&req);
+ bdrv_dec_in_flight(bs);
+
return ret;
}
+
+typedef struct TruncateCo {
+ BdrvChild *child;
+ int64_t offset;
+ PreallocMode prealloc;
+ Error **errp;
+ int ret;
+} TruncateCo;
+
+static void coroutine_fn bdrv_truncate_co_entry(void *opaque)
+{
+ TruncateCo *tco = opaque;
+ tco->ret = bdrv_co_truncate(tco->child, tco->offset, tco->prealloc,
+ tco->errp);
+ aio_wait_kick();
+}
+
+int bdrv_truncate(BdrvChild *child, int64_t offset, PreallocMode prealloc,
+ Error **errp)
+{
+ Coroutine *co;
+ TruncateCo tco = {
+ .child = child,
+ .offset = offset,
+ .prealloc = prealloc,
+ .errp = errp,
+ .ret = NOT_DONE,
+ };
+
+ if (qemu_in_coroutine()) {
+ /* Fast-path if already in coroutine context */
+ bdrv_truncate_co_entry(&tco);
+ } else {
+ co = qemu_coroutine_create(bdrv_truncate_co_entry, &tco);
+ bdrv_coroutine_enter(child->bs, co);
+ BDRV_POLL_WHILE(child->bs, tco.ret == NOT_DONE);
+ }
+
+ return tco.ret;
+}
projects / qemu.git / blobdiff