@@ -211,6 +211,9 @@ struct BlockDriver {
*/
int coroutine_fn (*bdrv_co_preadv)(BlockDriverState *bs,
uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags);
+ int coroutine_fn (*bdrv_co_preadv_part)(BlockDriverState *bs,
+ uint64_t offset, uint64_t bytes,
+ QEMUIOVector *qiov, size_t qiov_offset, int flags);
int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int flags);
/**
@@ -921,6 +924,9 @@ extern BlockDriver bdrv_qcow2;
int coroutine_fn bdrv_co_preadv(BdrvChild *child,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags);
+int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
+ int64_t offset, unsigned int bytes,
+ QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags);
int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags);
@@ -979,11 +979,14 @@ static void bdrv_co_io_em_complete(void *opaque, int ret)
static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
uint64_t offset, uint64_t bytes,
- QEMUIOVector *qiov, int flags)
+ QEMUIOVector *qiov,
+ size_t qiov_offset, int flags)
{
BlockDriver *drv = bs->drv;
int64_t sector_num;
unsigned int nb_sectors;
+ QEMUIOVector local_qiov;
+ int ret;
assert(!(flags & ~BDRV_REQ_MASK));
assert(!(flags & BDRV_REQ_NO_FALLBACK));
@@ -992,8 +995,20 @@ static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
return -ENOMEDIUM;
}
+ if (drv->bdrv_co_preadv_part) {
+ return drv->bdrv_co_preadv_part(bs, offset, bytes, qiov, qiov_offset,
+ flags);
+ }
+
+ if (qiov_offset > 0) {
+ qemu_iovec_init(&local_qiov, qiov->niov);
+ qemu_iovec_concat(&local_qiov, qiov, qiov_offset, bytes);
+ qiov = &local_qiov;
+ }
+
if (drv->bdrv_co_preadv) {
- return drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags);
+ ret = drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags);
+ goto out;
}
if (drv->bdrv_aio_preadv) {
@@ -1005,10 +1020,12 @@ static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
acb = drv->bdrv_aio_preadv(bs, offset, bytes, qiov, flags,
bdrv_co_io_em_complete, &co);
if (acb == NULL) {
- return -EIO;
+ ret = -EIO;
+ goto out;
} else {
qemu_coroutine_yield();
- return co.ret;
+ ret = co.ret;
+ goto out;
}
}
@@ -1020,7 +1037,14 @@ static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
assert((bytes >> BDRV_SECTOR_BITS) <= BDRV_REQUEST_MAX_SECTORS);
assert(drv->bdrv_co_readv);
- return drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+ ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+
+out:
+ if (qiov == &local_qiov) {
+ qemu_iovec_destroy(&local_qiov);
+ }
+
+ return ret;
}
static int coroutine_fn bdrv_driver_pwritev(BlockDriverState *bs,
@@ -1103,7 +1127,8 @@ bdrv_driver_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
}
static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov)
+ int64_t offset, unsigned int bytes,
+ QEMUIOVector *qiov, size_t qiov_offset)
{
BlockDriverState *bs = child->bs;
@@ -1183,7 +1208,7 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
qemu_iovec_init_buf(&local_qiov, bounce_buffer, pnum);
ret = bdrv_driver_preadv(bs, cluster_offset, pnum,
- &local_qiov, 0);
+ &local_qiov, 0, 0);
if (ret < 0) {
goto err;
}
@@ -1214,15 +1239,15 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
goto err;
}
- qemu_iovec_from_buf(qiov, progress, bounce_buffer + skip_bytes,
+ qemu_iovec_from_buf(qiov, qiov_offset + 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);
+ ret = bdrv_driver_preadv(bs, offset + progress,
+ MAX(pnum - skip_bytes,
+ qiov->size - qiov_offset - progress),
+ qiov, qiov_offset + progress, 0);
if (ret < 0) {
goto err;
}
@@ -1247,7 +1272,7 @@ err:
*/
static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
- int64_t align, QEMUIOVector *qiov, int flags)
+ int64_t align, QEMUIOVector *qiov, size_t qiov_offset, int flags)
{
BlockDriverState *bs = child->bs;
int64_t total_bytes, max_bytes;
@@ -1258,7 +1283,6 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
assert(is_power_of_2(align));
assert((offset & (align - 1)) == 0);
assert((bytes & (align - 1)) == 0);
- assert(!qiov || bytes == qiov->size);
assert((bs->open_flags & BDRV_O_NO_IO) == 0);
max_transfer = QEMU_ALIGN_DOWN(MIN_NON_ZERO(bs->bl.max_transfer, INT_MAX),
align);
@@ -1295,7 +1319,8 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
}
if (!ret || pnum != bytes) {
- ret = bdrv_co_do_copy_on_readv(child, offset, bytes, qiov);
+ ret = bdrv_co_do_copy_on_readv(child, offset, bytes,
+ qiov, qiov_offset);
goto out;
}
}
@@ -1309,7 +1334,7 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align);
if (bytes <= max_bytes && bytes <= max_transfer) {
- ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0);
+ ret = bdrv_driver_preadv(bs, offset, bytes, qiov, qiov_offset, 0);
goto out;
}
@@ -1317,17 +1342,12 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
int num;
if (max_bytes) {
- QEMUIOVector local_qiov;
-
num = MIN(bytes_remaining, MIN(max_bytes, max_transfer));
assert(num);
- qemu_iovec_init(&local_qiov, qiov->niov);
- qemu_iovec_concat(&local_qiov, qiov, bytes - bytes_remaining, num);
ret = bdrv_driver_preadv(bs, offset + bytes - bytes_remaining,
- num, &local_qiov, 0);
+ num, qiov, bytes - bytes_remaining, 0);
max_bytes -= num;
- qemu_iovec_destroy(&local_qiov);
} else {
num = bytes_remaining;
ret = qemu_iovec_memset(qiov, bytes - bytes_remaining, 0,
@@ -1346,8 +1366,9 @@ out:
/*
* Handle a read request in coroutine context
*/
-int coroutine_fn bdrv_co_preadv(BdrvChild *child,
- int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
+int coroutine_fn bdrv_co_preadv_part(BdrvChild *child,
+ int64_t offset, unsigned int bytes,
+ QEMUIOVector *qiov, size_t qiov_offset,
BdrvRequestFlags flags)
{
BlockDriverState *bs = child->bs;
@@ -1407,6 +1428,7 @@ int coroutine_fn bdrv_co_preadv(BdrvChild *child,
tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ);
ret = bdrv_aligned_preadv(child, &req, offset, bytes, align,
use_local_qiov ? &local_qiov : qiov,
+ use_local_qiov ? 0 : qiov_offset,
flags);
tracked_request_end(&req);
bdrv_dec_in_flight(bs);
@@ -1420,6 +1442,13 @@ int coroutine_fn bdrv_co_preadv(BdrvChild *child,
return ret;
}
+int coroutine_fn bdrv_co_preadv(BdrvChild *child,
+ int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
+ BdrvRequestFlags flags)
+{
+ return bdrv_co_preadv_part(child, offset, bytes, qiov, 0, flags);
+}
+
static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int bytes, BdrvRequestFlags flags)
{
@@ -1734,7 +1763,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
wait_serialising_requests(req);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
ret = bdrv_aligned_preadv(child, req, offset & ~(align - 1), align,
- align, &local_qiov, 0);
+ align, &local_qiov, 0, 0);
if (ret < 0) {
goto fail;
}
@@ -1772,7 +1801,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
wait_serialising_requests(req);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
ret = bdrv_aligned_preadv(child, req, offset, align,
- align, &local_qiov, 0);
+ align, &local_qiov, 0, 0);
if (ret < 0) {
goto fail;
}
@@ -1839,7 +1868,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
ret = bdrv_aligned_preadv(child, &req, offset & ~(align - 1), align,
- align, &head_qiov, 0);
+ align, &head_qiov, 0, 0);
if (ret < 0) {
goto fail;
}
@@ -1876,7 +1905,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
ret = bdrv_aligned_preadv(child, &req, (offset + bytes) & ~(align - 1),
- align, align, &tail_qiov, 0);
+ align, align, &tail_qiov, 0, 0);
if (ret < 0) {
goto fail;
}
Introduce extended variant of bdrv_co_preadv with qiov_offset parameter, to finally get rid of (most of) local_qiov workarounds. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> --- include/block/block_int.h | 6 +++ block/io.c | 87 ++++++++++++++++++++++++++------------- 2 files changed, 64 insertions(+), 29 deletions(-)