#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
+/* Maximum bounce buffer for copy-on-read and write zeroes, in bytes */
+#define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS)
+
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes, BdrvRequestFlags flags);
void bdrv_parent_drained_begin(BlockDriverState *bs)
{
- BdrvChild *c;
+ BdrvChild *c, *next;
- QLIST_FOREACH(c, &bs->parents, next_parent) {
+ QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
if (c->role->drained_begin) {
c->role->drained_begin(c);
}
void bdrv_parent_drained_end(BlockDriverState *bs)
{
- BdrvChild *c;
+ BdrvChild *c, *next;
- QLIST_FOREACH(c, &bs->parents, next_parent) {
+ QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
if (c->role->drained_end) {
c->role->drained_end(c);
}
Coroutine *co;
BlockDriverState *bs;
bool done;
+ bool begin;
} BdrvCoDrainData;
static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
BdrvCoDrainData *data = opaque;
BlockDriverState *bs = data->bs;
- bs->drv->bdrv_co_drain(bs);
+ if (data->begin) {
+ bs->drv->bdrv_co_drain_begin(bs);
+ } else {
+ bs->drv->bdrv_co_drain_end(bs);
+ }
/* Set data->done before reading bs->wakeup. */
atomic_mb_set(&data->done, true);
bdrv_wakeup(bs);
}
-static void bdrv_drain_invoke(BlockDriverState *bs)
+static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
{
- BdrvCoDrainData data = { .bs = bs, .done = false };
+ BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin};
- if (!bs->drv || !bs->drv->bdrv_co_drain) {
+ if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) ||
+ (!begin && !bs->drv->bdrv_co_drain_end)) {
return;
}
BDRV_POLL_WHILE(bs, !data.done);
}
-static bool bdrv_drain_recurse(BlockDriverState *bs)
+static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin)
{
BdrvChild *child, *tmp;
bool waited;
- waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0);
-
/* Ensure any pending metadata writes are submitted to bs->file. */
- bdrv_drain_invoke(bs);
+ bdrv_drain_invoke(bs, begin);
+
+ /* Wait for drained requests to finish */
+ waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0);
QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) {
BlockDriverState *bs = child->bs;
*/
bdrv_ref(bs);
}
- waited |= bdrv_drain_recurse(bs);
+ waited |= bdrv_drain_recurse(bs, begin);
if (in_main_loop) {
bdrv_unref(bs);
}
BlockDriverState *bs = data->bs;
bdrv_dec_in_flight(bs);
- bdrv_drained_begin(bs);
+ if (data->begin) {
+ bdrv_drained_begin(bs);
+ } else {
+ bdrv_drained_end(bs);
+ }
+
data->done = true;
aio_co_wake(co);
}
-static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs)
+static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
+ bool begin)
{
BdrvCoDrainData data;
.co = qemu_coroutine_self(),
.bs = bs,
.done = false,
+ .begin = begin,
};
bdrv_inc_in_flight(bs);
aio_bh_schedule_oneshot(bdrv_get_aio_context(bs),
void bdrv_drained_begin(BlockDriverState *bs)
{
if (qemu_in_coroutine()) {
- bdrv_co_yield_to_drain(bs);
+ bdrv_co_yield_to_drain(bs, true);
return;
}
bdrv_parent_drained_begin(bs);
}
- bdrv_drain_recurse(bs);
+ bdrv_drain_recurse(bs, true);
}
void bdrv_drained_end(BlockDriverState *bs)
{
+ if (qemu_in_coroutine()) {
+ bdrv_co_yield_to_drain(bs, false);
+ return;
+ }
assert(bs->quiesce_counter > 0);
if (atomic_fetch_dec(&bs->quiesce_counter) > 1) {
return;
}
bdrv_parent_drained_end(bs);
+ bdrv_drain_recurse(bs, false);
aio_enable_external(bdrv_get_aio_context(bs));
}
aio_context_acquire(aio_context);
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
if (aio_context == bdrv_get_aio_context(bs)) {
- waited |= bdrv_drain_recurse(bs);
+ waited |= bdrv_drain_recurse(bs, true);
}
}
aio_context_release(aio_context);
aio_context_acquire(aio_context);
aio_enable_external(aio_context);
bdrv_parent_drained_end(bs);
+ bdrv_drain_recurse(bs, false);
aio_context_release(aio_context);
}
* Round a region to cluster boundaries
*/
void bdrv_round_to_clusters(BlockDriverState *bs,
- int64_t offset, unsigned int bytes,
+ int64_t offset, int64_t bytes,
int64_t *cluster_offset,
- unsigned int *cluster_bytes)
+ int64_t *cluster_bytes)
{
BlockDriverInfo bdi;
*/
int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags)
{
- int64_t target_sectors, ret, nb_sectors, sector_num = 0;
+ int ret;
+ int64_t target_size, bytes, offset = 0;
BlockDriverState *bs = child->bs;
- BlockDriverState *file;
- int n;
- target_sectors = bdrv_nb_sectors(bs);
- if (target_sectors < 0) {
- return target_sectors;
+ target_size = bdrv_getlength(bs);
+ if (target_size < 0) {
+ return target_size;
}
for (;;) {
- nb_sectors = MIN(target_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS);
- if (nb_sectors <= 0) {
+ bytes = MIN(target_size - offset, BDRV_REQUEST_MAX_BYTES);
+ if (bytes <= 0) {
return 0;
}
- ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, &file);
+ ret = bdrv_block_status(bs, offset, bytes, &bytes, NULL, NULL);
if (ret < 0) {
- error_report("error getting block status at sector %" PRId64 ": %s",
- sector_num, strerror(-ret));
+ error_report("error getting block status at offset %" PRId64 ": %s",
+ offset, strerror(-ret));
return ret;
}
if (ret & BDRV_BLOCK_ZERO) {
- sector_num += n;
+ offset += bytes;
continue;
}
- ret = bdrv_pwrite_zeroes(child, sector_num << BDRV_SECTOR_BITS,
- n << BDRV_SECTOR_BITS, flags);
+ ret = bdrv_pwrite_zeroes(child, offset, bytes, flags);
if (ret < 0) {
- error_report("error writing zeroes at sector %" PRId64 ": %s",
- sector_num, strerror(-ret));
+ error_report("error writing zeroes at offset %" PRId64 ": %s",
+ offset, strerror(-ret));
return ret;
}
- sector_num += n;
+ offset += bytes;
}
}
assert(!(flags & ~BDRV_REQ_MASK));
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+
if (drv->bdrv_co_preadv) {
return drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags);
}
assert(!(flags & ~BDRV_REQ_MASK));
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+
if (drv->bdrv_co_pwritev) {
ret = drv->bdrv_co_pwritev(bs, offset, bytes, qiov,
flags & bs->supported_write_flags);
{
BlockDriver *drv = bs->drv;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+
if (!drv->bdrv_co_pwritev_compressed) {
return -ENOTSUP;
}
BlockDriver *drv = bs->drv;
struct iovec iov;
- QEMUIOVector bounce_qiov;
+ QEMUIOVector local_qiov;
int64_t cluster_offset;
- unsigned int cluster_bytes;
+ int64_t cluster_bytes;
size_t skip_bytes;
int ret;
+ int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer,
+ BDRV_REQUEST_MAX_BYTES);
+ unsigned int progress = 0;
+
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
/* FIXME We cannot require callers to have write permissions when all they
* are doing is a read request. If we did things right, write permissions
* would be obtained anyway, but internally by the copy-on-read code. As
- * long as it is implemented here rather than in a separat filter driver,
+ * long as it is implemented here rather than in a separate filter driver,
* the copy-on-read code doesn't have its own BdrvChild, however, for which
* it could request permissions. Therefore we have to bypass the permission
* system for the moment. */
// assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
/* Cover entire cluster so no additional backing file I/O is required when
- * allocating cluster in the image file.
+ * allocating cluster in the image file. Note that this value may exceed
+ * BDRV_REQUEST_MAX_BYTES (even when the original read did not), which
+ * is one reason we loop rather than doing it all at once.
*/
bdrv_round_to_clusters(bs, offset, bytes, &cluster_offset, &cluster_bytes);
+ skip_bytes = offset - cluster_offset;
trace_bdrv_co_do_copy_on_readv(bs, offset, bytes,
cluster_offset, cluster_bytes);
- iov.iov_len = cluster_bytes;
- iov.iov_base = bounce_buffer = qemu_try_blockalign(bs, iov.iov_len);
+ bounce_buffer = qemu_try_blockalign(bs,
+ MIN(MIN(max_transfer, cluster_bytes),
+ MAX_BOUNCE_BUFFER));
if (bounce_buffer == NULL) {
ret = -ENOMEM;
goto err;
}
- qemu_iovec_init_external(&bounce_qiov, &iov, 1);
+ while (cluster_bytes) {
+ int64_t pnum;
- ret = bdrv_driver_preadv(bs, cluster_offset, cluster_bytes,
- &bounce_qiov, 0);
- if (ret < 0) {
- goto err;
- }
+ ret = bdrv_is_allocated(bs, cluster_offset,
+ MIN(cluster_bytes, max_transfer), &pnum);
+ if (ret < 0) {
+ /* Safe to treat errors in querying allocation as if
+ * unallocated; we'll probably fail again soon on the
+ * read, but at least that will set a decent errno.
+ */
+ pnum = MIN(cluster_bytes, max_transfer);
+ }
- if (drv->bdrv_co_pwrite_zeroes &&
- buffer_is_zero(bounce_buffer, iov.iov_len)) {
- /* FIXME: Should we (perhaps conditionally) be setting
- * BDRV_REQ_MAY_UNMAP, if it will allow for a sparser copy
- * that still correctly reads as zero? */
- ret = bdrv_co_do_pwrite_zeroes(bs, cluster_offset, cluster_bytes, 0);
- } else {
- /* This does not change the data on the disk, it is not necessary
- * to flush even in cache=writethrough mode.
- */
- ret = bdrv_driver_pwritev(bs, cluster_offset, cluster_bytes,
- &bounce_qiov, 0);
- }
+ assert(skip_bytes < pnum);
- if (ret < 0) {
- /* It might be okay to ignore write errors for guest requests. If this
- * is a deliberate copy-on-read then we don't want to ignore the error.
- * Simply report it in all cases.
- */
- goto err;
- }
+ 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);
- skip_bytes = offset - cluster_offset;
- qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes, bytes);
+ ret = bdrv_driver_preadv(bs, cluster_offset, pnum,
+ &local_qiov, 0);
+ if (ret < 0) {
+ goto err;
+ }
+
+ bdrv_debug_event(bs, BLKDBG_COR_WRITE);
+ if (drv->bdrv_co_pwrite_zeroes &&
+ buffer_is_zero(bounce_buffer, pnum)) {
+ /* FIXME: Should we (perhaps conditionally) be setting
+ * BDRV_REQ_MAY_UNMAP, if it will allow for a sparser copy
+ * that still correctly reads as zero? */
+ ret = bdrv_co_do_pwrite_zeroes(bs, cluster_offset, pnum, 0);
+ } else {
+ /* This does not change the data on the disk, it is not
+ * necessary to flush even in cache=writethrough mode.
+ */
+ ret = bdrv_driver_pwritev(bs, cluster_offset, pnum,
+ &local_qiov, 0);
+ }
+
+ if (ret < 0) {
+ /* It might be okay to ignore write errors for guest
+ * requests. If this is a deliberate copy-on-read
+ * then we don't want to ignore the error. Simply
+ * report it in all cases.
+ */
+ goto err;
+ }
+
+ qemu_iovec_from_buf(qiov, progress, bounce_buffer + skip_bytes,
+ pnum - skip_bytes);
+ } else {
+ /* Read directly into the destination */
+ qemu_iovec_init(&local_qiov, qiov->niov);
+ qemu_iovec_concat(&local_qiov, qiov, progress, pnum - skip_bytes);
+ ret = bdrv_driver_preadv(bs, offset + progress, local_qiov.size,
+ &local_qiov, 0);
+ qemu_iovec_destroy(&local_qiov);
+ if (ret < 0) {
+ goto err;
+ }
+ }
+
+ cluster_offset += pnum;
+ cluster_bytes -= pnum;
+ progress += pnum - skip_bytes;
+ skip_bytes = 0;
+ }
+ ret = 0;
err:
qemu_vfree(bounce_buffer);
}
if (flags & BDRV_REQ_COPY_ON_READ) {
- /* TODO: Simplify further once bdrv_is_allocated no longer
- * requires sector alignment */
- int64_t start = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE);
- int64_t end = QEMU_ALIGN_UP(offset + bytes, BDRV_SECTOR_SIZE);
int64_t pnum;
- ret = bdrv_is_allocated(bs, start, end - start, &pnum);
+ ret = bdrv_is_allocated(bs, offset, bytes, &pnum);
if (ret < 0) {
goto out;
}
- if (!ret || pnum != end - start) {
+ if (!ret || pnum != bytes) {
ret = bdrv_co_do_copy_on_readv(child, offset, bytes, qiov);
goto out;
}
return bdrv_co_do_readv(child, sector_num, nb_sectors, qiov, 0);
}
-/* Maximum buffer for write zeroes fallback, in bytes */
-#define MAX_WRITE_ZEROES_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS)
-
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes, BdrvRequestFlags flags)
{
int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_pwrite_zeroes, INT_MAX);
int alignment = MAX(bs->bl.pwrite_zeroes_alignment,
bs->bl.request_alignment);
- int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer,
- MAX_WRITE_ZEROES_BOUNCE_BUFFER);
+ int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, MAX_BOUNCE_BUFFER);
+
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
assert(alignment % bs->bl.request_alignment == 0);
head = offset % alignment;
bool waited;
int ret;
- int64_t start_sector = offset >> BDRV_SECTOR_BITS;
int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
uint64_t bytes_remaining = bytes;
int max_transfer;
+ if (!drv) {
+ return -ENOMEDIUM;
+ }
+
if (bdrv_has_readonly_bitmaps(bs)) {
return -EPERM;
}
bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE);
atomic_inc(&bs->write_gen);
- bdrv_set_dirty(bs, start_sector, end_sector - start_sector);
+ bdrv_set_dirty(bs, offset, bytes);
stat64_max(&bs->wr_highest_offset, offset + bytes);
}
-typedef struct BdrvCoGetBlockStatusData {
+typedef struct BdrvCoBlockStatusData {
BlockDriverState *bs;
BlockDriverState *base;
+ bool want_zero;
+ int64_t offset;
+ int64_t bytes;
+ int64_t *pnum;
+ int64_t *map;
BlockDriverState **file;
- int64_t sector_num;
- int nb_sectors;
- int *pnum;
- int64_t ret;
+ int ret;
bool done;
-} BdrvCoGetBlockStatusData;
+} BdrvCoBlockStatusData;
int64_t coroutine_fn bdrv_co_get_block_status_from_file(BlockDriverState *bs,
int64_t sector_num,
* Drivers not implementing the functionality are assumed to not support
* backing files, hence all their sectors are reported as allocated.
*
- * If 'sector_num' is beyond the end of the disk image the return value is
- * BDRV_BLOCK_EOF and 'pnum' is set to 0.
+ * If 'want_zero' is true, the caller is querying for mapping purposes,
+ * and the result should include BDRV_BLOCK_OFFSET_VALID and
+ * BDRV_BLOCK_ZERO where possible; otherwise, the result may omit those
+ * bits particularly if it allows for a larger value in 'pnum'.
*
- * 'pnum' is set to the number of sectors (including and immediately following
- * the specified sector) that are known to be in the same
- * allocated/unallocated state.
+ * If 'offset' is beyond the end of the disk image the return value is
+ * BDRV_BLOCK_EOF and 'pnum' is set to 0.
*
- * 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes
+ * 'bytes' is the max value 'pnum' should be set to. If bytes goes
* beyond the end of the disk image it will be clamped; if 'pnum' is set to
* the end of the image, then the returned value will include BDRV_BLOCK_EOF.
*
- * If returned value is positive and BDRV_BLOCK_OFFSET_VALID bit is set, 'file'
- * points to the BDS which the sector range is allocated in.
+ * 'pnum' is set to the number of bytes (including and immediately
+ * following the specified offset) that are easily known to be in the
+ * same allocated/unallocated state. Note that a second call starting
+ * at the original offset plus returned pnum may have the same status.
+ * The returned value is non-zero on success except at end-of-file.
+ *
+ * Returns negative errno on failure. Otherwise, if the
+ * BDRV_BLOCK_OFFSET_VALID bit is set, 'map' and 'file' (if non-NULL) are
+ * set to the host mapping and BDS corresponding to the guest offset.
*/
-static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
- int64_t sector_num,
- int nb_sectors, int *pnum,
- BlockDriverState **file)
-{
- int64_t total_sectors;
- int64_t n;
- int64_t ret, ret2;
+static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs,
+ bool want_zero,
+ int64_t offset, int64_t bytes,
+ int64_t *pnum, int64_t *map,
+ BlockDriverState **file)
+{
+ int64_t total_size;
+ int64_t n; /* bytes */
+ int ret;
+ int64_t local_map = 0;
+ BlockDriverState *local_file = NULL;
+ int64_t aligned_offset, aligned_bytes;
+ uint32_t align;
- *file = NULL;
- total_sectors = bdrv_nb_sectors(bs);
- if (total_sectors < 0) {
- return total_sectors;
+ assert(pnum);
+ *pnum = 0;
+ total_size = bdrv_getlength(bs);
+ if (total_size < 0) {
+ ret = total_size;
+ goto early_out;
}
- if (sector_num >= total_sectors) {
- *pnum = 0;
- return BDRV_BLOCK_EOF;
+ if (offset >= total_size) {
+ ret = BDRV_BLOCK_EOF;
+ goto early_out;
+ }
+ if (!bytes) {
+ ret = 0;
+ goto early_out;
}
- n = total_sectors - sector_num;
- if (n < nb_sectors) {
- nb_sectors = n;
+ n = total_size - offset;
+ if (n < bytes) {
+ bytes = n;
}
+ /* Must be non-NULL or bdrv_getlength() would have failed */
+ assert(bs->drv);
if (!bs->drv->bdrv_co_get_block_status) {
- *pnum = nb_sectors;
+ *pnum = bytes;
ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED;
- if (sector_num + nb_sectors == total_sectors) {
+ if (offset + bytes == total_size) {
ret |= BDRV_BLOCK_EOF;
}
if (bs->drv->protocol_name) {
- ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE);
- *file = bs;
+ ret |= BDRV_BLOCK_OFFSET_VALID;
+ local_map = offset;
+ local_file = bs;
}
- return ret;
+ goto early_out;
}
bdrv_inc_in_flight(bs);
- ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum,
- file);
- if (ret < 0) {
- *pnum = 0;
- goto out;
+
+ /* Round out to request_alignment boundaries */
+ /* TODO: until we have a byte-based driver callback, we also have to
+ * round out to sectors, even if that is bigger than request_alignment */
+ align = MAX(bs->bl.request_alignment, BDRV_SECTOR_SIZE);
+ aligned_offset = QEMU_ALIGN_DOWN(offset, align);
+ aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset;
+
+ {
+ int count; /* sectors */
+ int64_t longret;
+
+ assert(QEMU_IS_ALIGNED(aligned_offset | aligned_bytes,
+ BDRV_SECTOR_SIZE));
+ /*
+ * The contract allows us to return pnum smaller than bytes, even
+ * if the next query would see the same status; we truncate the
+ * request to avoid overflowing the driver's 32-bit interface.
+ */
+ longret = bs->drv->bdrv_co_get_block_status(
+ bs, aligned_offset >> BDRV_SECTOR_BITS,
+ MIN(INT_MAX, aligned_bytes) >> BDRV_SECTOR_BITS, &count,
+ &local_file);
+ if (longret < 0) {
+ assert(INT_MIN <= longret);
+ ret = longret;
+ goto out;
+ }
+ if (longret & BDRV_BLOCK_OFFSET_VALID) {
+ local_map = longret & BDRV_BLOCK_OFFSET_MASK;
+ }
+ ret = longret & ~BDRV_BLOCK_OFFSET_MASK;
+ *pnum = count * BDRV_SECTOR_SIZE;
+ }
+
+ /*
+ * The driver's result must be a multiple of request_alignment.
+ * Clamp pnum and adjust map to original request.
+ */
+ assert(QEMU_IS_ALIGNED(*pnum, align) && align > offset - aligned_offset);
+ *pnum -= offset - aligned_offset;
+ if (*pnum > bytes) {
+ *pnum = bytes;
+ }
+ if (ret & BDRV_BLOCK_OFFSET_VALID) {
+ local_map += offset - aligned_offset;
}
if (ret & BDRV_BLOCK_RAW) {
- assert(ret & BDRV_BLOCK_OFFSET_VALID && *file);
- ret = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS,
- *pnum, pnum, file);
+ assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file);
+ ret = bdrv_co_block_status(local_file, want_zero, local_map,
+ *pnum, pnum, &local_map, &local_file);
goto out;
}
if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
ret |= BDRV_BLOCK_ALLOCATED;
- } else {
+ } else if (want_zero) {
if (bdrv_unallocated_blocks_are_zero(bs)) {
ret |= BDRV_BLOCK_ZERO;
} else if (bs->backing) {
BlockDriverState *bs2 = bs->backing->bs;
- int64_t nb_sectors2 = bdrv_nb_sectors(bs2);
- if (nb_sectors2 >= 0 && sector_num >= nb_sectors2) {
+ int64_t size2 = bdrv_getlength(bs2);
+
+ if (size2 >= 0 && offset >= size2) {
ret |= BDRV_BLOCK_ZERO;
}
}
}
- if (*file && *file != bs &&
+ if (want_zero && local_file && local_file != bs &&
(ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) &&
(ret & BDRV_BLOCK_OFFSET_VALID)) {
- BlockDriverState *file2;
- int file_pnum;
+ int64_t file_pnum;
+ int ret2;
- ret2 = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS,
- *pnum, &file_pnum, &file2);
+ ret2 = bdrv_co_block_status(local_file, want_zero, local_map,
+ *pnum, &file_pnum, NULL, NULL);
if (ret2 >= 0) {
/* Ignore errors. This is just providing extra information, it
* is useful but not necessary.
out:
bdrv_dec_in_flight(bs);
- if (ret >= 0 && sector_num + *pnum == total_sectors) {
+ if (ret >= 0 && offset + *pnum == total_size) {
ret |= BDRV_BLOCK_EOF;
}
+early_out:
+ if (file) {
+ *file = local_file;
+ }
+ if (map) {
+ *map = local_map;
+ }
return ret;
}
-static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs,
- BlockDriverState *base,
- int64_t sector_num,
- int nb_sectors,
- int *pnum,
- BlockDriverState **file)
+static int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs,
+ BlockDriverState *base,
+ bool want_zero,
+ int64_t offset,
+ int64_t bytes,
+ int64_t *pnum,
+ int64_t *map,
+ BlockDriverState **file)
{
BlockDriverState *p;
- int64_t ret = 0;
+ int ret = 0;
bool first = true;
assert(bs != base);
for (p = bs; p != base; p = backing_bs(p)) {
- ret = bdrv_co_get_block_status(p, sector_num, nb_sectors, pnum, file);
+ ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map,
+ file);
if (ret < 0) {
break;
}
* unallocated length we learned from an earlier
* iteration.
*/
- *pnum = nb_sectors;
+ *pnum = bytes;
}
if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) {
break;
}
- /* [sector_num, pnum] unallocated on this layer, which could be only
- * the first part of [sector_num, nb_sectors]. */
- nb_sectors = MIN(nb_sectors, *pnum);
+ /* [offset, pnum] unallocated on this layer, which could be only
+ * the first part of [offset, bytes]. */
+ bytes = MIN(bytes, *pnum);
first = false;
}
return ret;
}
-/* Coroutine wrapper for bdrv_get_block_status_above() */
-static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque)
+/* Coroutine wrapper for bdrv_block_status_above() */
+static void coroutine_fn bdrv_block_status_above_co_entry(void *opaque)
{
- BdrvCoGetBlockStatusData *data = opaque;
+ BdrvCoBlockStatusData *data = opaque;
- data->ret = bdrv_co_get_block_status_above(data->bs, data->base,
- data->sector_num,
- data->nb_sectors,
- data->pnum,
- data->file);
+ data->ret = bdrv_co_block_status_above(data->bs, data->base,
+ data->want_zero,
+ data->offset, data->bytes,
+ data->pnum, data->map, data->file);
data->done = true;
}
/*
- * Synchronous wrapper around bdrv_co_get_block_status_above().
+ * Synchronous wrapper around bdrv_co_block_status_above().
*
- * See bdrv_co_get_block_status_above() for details.
+ * See bdrv_co_block_status_above() for details.
*/
-int64_t bdrv_get_block_status_above(BlockDriverState *bs,
- BlockDriverState *base,
- int64_t sector_num,
- int nb_sectors, int *pnum,
- BlockDriverState **file)
+static int bdrv_common_block_status_above(BlockDriverState *bs,
+ BlockDriverState *base,
+ bool want_zero, int64_t offset,
+ int64_t bytes, int64_t *pnum,
+ int64_t *map,
+ BlockDriverState **file)
{
Coroutine *co;
- BdrvCoGetBlockStatusData data = {
+ BdrvCoBlockStatusData data = {
.bs = bs,
.base = base,
- .file = file,
- .sector_num = sector_num,
- .nb_sectors = nb_sectors,
+ .want_zero = want_zero,
+ .offset = offset,
+ .bytes = bytes,
.pnum = pnum,
+ .map = map,
+ .file = file,
.done = false,
};
if (qemu_in_coroutine()) {
/* Fast-path if already in coroutine context */
- bdrv_get_block_status_above_co_entry(&data);
+ bdrv_block_status_above_co_entry(&data);
} else {
- co = qemu_coroutine_create(bdrv_get_block_status_above_co_entry,
- &data);
+ co = qemu_coroutine_create(bdrv_block_status_above_co_entry, &data);
bdrv_coroutine_enter(bs, co);
BDRV_POLL_WHILE(bs, !data.done);
}
return data.ret;
}
-int64_t bdrv_get_block_status(BlockDriverState *bs,
- int64_t sector_num,
- int nb_sectors, int *pnum,
- BlockDriverState **file)
+int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base,
+ int64_t offset, int64_t bytes, int64_t *pnum,
+ int64_t *map, BlockDriverState **file)
{
- return bdrv_get_block_status_above(bs, backing_bs(bs),
- sector_num, nb_sectors, pnum, file);
+ return bdrv_common_block_status_above(bs, base, true, offset, bytes,
+ pnum, map, file);
+}
+
+int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes,
+ int64_t *pnum, int64_t *map, BlockDriverState **file)
+{
+ return bdrv_block_status_above(bs, backing_bs(bs),
+ offset, bytes, pnum, map, file);
}
int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset,
int64_t bytes, int64_t *pnum)
{
- BlockDriverState *file;
- int64_t sector_num = offset >> BDRV_SECTOR_BITS;
- int nb_sectors = bytes >> BDRV_SECTOR_BITS;
- int64_t ret;
- int psectors;
+ int ret;
+ int64_t dummy;
- assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE));
- assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE) && bytes < INT_MAX);
- ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &psectors,
- &file);
+ ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, offset,
+ bytes, pnum ? pnum : &dummy, NULL,
+ NULL);
if (ret < 0) {
return ret;
}
- if (pnum) {
- *pnum = psectors * BDRV_SECTOR_SIZE;
- }
return !!(ret & BDRV_BLOCK_ALLOCATED);
}
}
BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_DISK);
+ if (!bs->drv) {
+ /* bs->drv->bdrv_co_flush() might have ejected the BDS
+ * (even in case of apparent success) */
+ ret = -ENOMEDIUM;
+ goto out;
+ }
if (bs->drv->bdrv_co_flush_to_disk) {
ret = bs->drv->bdrv_co_flush_to_disk(bs);
} else if (bs->drv->bdrv_aio_flush) {
num = max_pdiscard;
}
+ if (!bs->drv) {
+ ret = -ENOMEDIUM;
+ goto out;
+ }
if (bs->drv->bdrv_co_pdiscard) {
ret = bs->drv->bdrv_co_pdiscard(bs, offset, num);
} else {
ret = 0;
out:
atomic_inc(&bs->write_gen);
- bdrv_set_dirty(bs, req.offset >> BDRV_SECTOR_BITS,
- req.bytes >> BDRV_SECTOR_BITS);
+ bdrv_set_dirty(bs, req.offset, req.bytes);
tracked_request_end(&req);
bdrv_dec_in_flight(bs);
return ret;
projects / mirror_qemu.git / blobdiff