aboutsummaryrefslogtreecommitdiff
path: root/block/io.c
diff options
context:
space:
mode:
Diffstat (limited to 'block/io.c')
-rw-r--r--block/io.c514
1 files changed, 253 insertions, 261 deletions
diff --git a/block/io.c b/block/io.c
index a7dbf85b19..cd6d71a503 100644
--- a/block/io.c
+++ b/block/io.c
@@ -34,18 +34,6 @@
#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
-static BlockAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque);
-static BlockAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque);
-static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov);
-static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov);
static BlockAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
@@ -62,48 +50,35 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
void bdrv_set_io_limits(BlockDriverState *bs,
ThrottleConfig *cfg)
{
- int i;
-
throttle_group_config(bs, cfg);
-
- for (i = 0; i < 2; i++) {
- qemu_co_enter_next(&bs->throttled_reqs[i]);
- }
}
-/* this function drain all the throttled IOs */
-static bool bdrv_start_throttled_reqs(BlockDriverState *bs)
+void bdrv_no_throttling_begin(BlockDriverState *bs)
{
- bool drained = false;
- bool enabled = bs->io_limits_enabled;
- int i;
-
- bs->io_limits_enabled = false;
-
- for (i = 0; i < 2; i++) {
- while (qemu_co_enter_next(&bs->throttled_reqs[i])) {
- drained = true;
- }
+ if (bs->io_limits_disabled++ == 0) {
+ throttle_group_restart_bs(bs);
}
+}
- bs->io_limits_enabled = enabled;
-
- return drained;
+void bdrv_no_throttling_end(BlockDriverState *bs)
+{
+ assert(bs->io_limits_disabled);
+ --bs->io_limits_disabled;
}
void bdrv_io_limits_disable(BlockDriverState *bs)
{
- bs->io_limits_enabled = false;
- bdrv_start_throttled_reqs(bs);
+ assert(bs->throttle_state);
+ bdrv_no_throttling_begin(bs);
throttle_group_unregister_bs(bs);
+ bdrv_no_throttling_end(bs);
}
/* should be called before bdrv_set_io_limits if a limit is set */
void bdrv_io_limits_enable(BlockDriverState *bs, const char *group)
{
- assert(!bs->io_limits_enabled);
+ assert(!bs->throttle_state);
throttle_group_register_bs(bs, group);
- bs->io_limits_enabled = true;
}
void bdrv_io_limits_update_group(BlockDriverState *bs, const char *group)
@@ -123,24 +98,6 @@ void bdrv_io_limits_update_group(BlockDriverState *bs, const char *group)
bdrv_io_limits_enable(bs, group);
}
-void bdrv_setup_io_funcs(BlockDriver *bdrv)
-{
- /* Block drivers without coroutine functions need emulation */
- if (!bdrv->bdrv_co_readv) {
- bdrv->bdrv_co_readv = bdrv_co_readv_em;
- bdrv->bdrv_co_writev = bdrv_co_writev_em;
-
- /* bdrv_co_readv_em()/brdv_co_writev_em() work in terms of aio, so if
- * the block driver lacks aio we need to emulate that too.
- */
- if (!bdrv->bdrv_aio_readv) {
- /* add AIO emulation layer */
- bdrv->bdrv_aio_readv = bdrv_aio_readv_em;
- bdrv->bdrv_aio_writev = bdrv_aio_writev_em;
- }
- }
-}
-
void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
{
BlockDriver *drv = bs->drv;
@@ -260,18 +217,29 @@ typedef struct {
bool done;
} BdrvCoDrainData;
+static void bdrv_drain_poll(BlockDriverState *bs)
+{
+ bool busy = true;
+
+ while (busy) {
+ /* Keep iterating */
+ busy = bdrv_requests_pending(bs);
+ busy |= aio_poll(bdrv_get_aio_context(bs), busy);
+ }
+}
+
static void bdrv_co_drain_bh_cb(void *opaque)
{
BdrvCoDrainData *data = opaque;
Coroutine *co = data->co;
qemu_bh_delete(data->bh);
- bdrv_drain(data->bs);
+ bdrv_drain_poll(data->bs);
data->done = true;
qemu_coroutine_enter(co, NULL);
}
-void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
+static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs)
{
BdrvCoDrainData data;
@@ -305,21 +273,28 @@ void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
* not depend on events in other AioContexts. In that case, use
* bdrv_drain_all() instead.
*/
-void bdrv_drain(BlockDriverState *bs)
+void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
{
- bool busy = true;
+ bdrv_no_throttling_begin(bs);
+ bdrv_io_unplugged_begin(bs);
+ bdrv_drain_recurse(bs);
+ bdrv_co_yield_to_drain(bs);
+ bdrv_io_unplugged_end(bs);
+ bdrv_no_throttling_end(bs);
+}
+void bdrv_drain(BlockDriverState *bs)
+{
+ bdrv_no_throttling_begin(bs);
+ bdrv_io_unplugged_begin(bs);
bdrv_drain_recurse(bs);
if (qemu_in_coroutine()) {
- bdrv_co_drain(bs);
- return;
- }
- while (busy) {
- /* Keep iterating */
- bdrv_flush_io_queue(bs);
- busy = bdrv_requests_pending(bs);
- busy |= aio_poll(bdrv_get_aio_context(bs), busy);
+ bdrv_co_yield_to_drain(bs);
+ } else {
+ bdrv_drain_poll(bs);
}
+ bdrv_io_unplugged_end(bs);
+ bdrv_no_throttling_end(bs);
}
/*
@@ -342,6 +317,8 @@ void bdrv_drain_all(void)
if (bs->job) {
block_job_pause(bs->job);
}
+ bdrv_no_throttling_begin(bs);
+ bdrv_io_unplugged_begin(bs);
bdrv_drain_recurse(bs);
aio_context_release(aio_context);
@@ -366,7 +343,6 @@ void bdrv_drain_all(void)
aio_context_acquire(aio_context);
while ((bs = bdrv_next(bs))) {
if (aio_context == bdrv_get_aio_context(bs)) {
- bdrv_flush_io_queue(bs);
if (bdrv_requests_pending(bs)) {
busy = true;
aio_poll(aio_context, busy);
@@ -383,6 +359,8 @@ void bdrv_drain_all(void)
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
+ bdrv_io_unplugged_end(bs);
+ bdrv_no_throttling_end(bs);
if (bs->job) {
block_job_resume(bs->job);
}
@@ -581,13 +559,13 @@ static void coroutine_fn bdrv_rw_co_entry(void *opaque)
RwCo *rwco = opaque;
if (!rwco->is_write) {
- rwco->ret = bdrv_co_do_preadv(rwco->bs, rwco->offset,
- rwco->qiov->size, rwco->qiov,
- rwco->flags);
+ rwco->ret = bdrv_co_preadv(rwco->bs, rwco->offset,
+ rwco->qiov->size, rwco->qiov,
+ rwco->flags);
} else {
- rwco->ret = bdrv_co_do_pwritev(rwco->bs, rwco->offset,
- rwco->qiov->size, rwco->qiov,
- rwco->flags);
+ rwco->ret = bdrv_co_pwritev(rwco->bs, rwco->offset,
+ rwco->qiov->size, rwco->qiov,
+ rwco->flags);
}
}
@@ -608,17 +586,6 @@ static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset,
.flags = flags,
};
- /**
- * In sync call context, when the vcpu is blocked, this throttling timer
- * will not fire; so the I/O throttling function has to be disabled here
- * if it has been enabled.
- */
- if (bs->io_limits_enabled) {
- fprintf(stderr, "Disabling I/O throttling on '%s' due "
- "to synchronous I/O.\n", bdrv_get_device_name(bs));
- bdrv_io_limits_disable(bs);
- }
-
if (qemu_in_coroutine()) {
/* Fast-path if already in coroutine context */
bdrv_rw_co_entry(&rwco);
@@ -685,7 +652,8 @@ int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num,
* Completely zero out a block device with the help of bdrv_write_zeroes.
* The operation is sped up by checking the block status and only writing
* zeroes to the device if they currently do not return zeroes. Optional
- * flags are passed through to bdrv_write_zeroes (e.g. BDRV_REQ_MAY_UNMAP).
+ * flags are passed through to bdrv_write_zeroes (e.g. BDRV_REQ_MAY_UNMAP,
+ * BDRV_REQ_FUA).
*
* Returns < 0 on error, 0 on success. For error codes see bdrv_write().
*/
@@ -800,6 +768,109 @@ int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
return 0;
}
+typedef struct CoroutineIOCompletion {
+ Coroutine *coroutine;
+ int ret;
+} CoroutineIOCompletion;
+
+static void bdrv_co_io_em_complete(void *opaque, int ret)
+{
+ CoroutineIOCompletion *co = opaque;
+
+ co->ret = ret;
+ qemu_coroutine_enter(co->coroutine, NULL);
+}
+
+static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
+ uint64_t offset, uint64_t bytes,
+ QEMUIOVector *qiov, int flags)
+{
+ BlockDriver *drv = bs->drv;
+ int64_t sector_num;
+ unsigned int nb_sectors;
+
+ if (drv->bdrv_co_preadv) {
+ return drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags);
+ }
+
+ sector_num = offset >> BDRV_SECTOR_BITS;
+ nb_sectors = bytes >> BDRV_SECTOR_BITS;
+
+ assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
+ assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
+ assert((bytes >> BDRV_SECTOR_BITS) <= BDRV_REQUEST_MAX_SECTORS);
+
+ if (drv->bdrv_co_readv) {
+ return drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+ } else {
+ BlockAIOCB *acb;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ acb = bs->drv->bdrv_aio_readv(bs, sector_num, qiov, nb_sectors,
+ bdrv_co_io_em_complete, &co);
+ if (acb == NULL) {
+ return -EIO;
+ } else {
+ qemu_coroutine_yield();
+ return co.ret;
+ }
+ }
+}
+
+static int coroutine_fn bdrv_driver_pwritev(BlockDriverState *bs,
+ uint64_t offset, uint64_t bytes,
+ QEMUIOVector *qiov, int flags)
+{
+ BlockDriver *drv = bs->drv;
+ int64_t sector_num;
+ unsigned int nb_sectors;
+ int ret;
+
+ if (drv->bdrv_co_pwritev) {
+ ret = drv->bdrv_co_pwritev(bs, offset, bytes, qiov, flags);
+ goto emulate_flags;
+ }
+
+ sector_num = offset >> BDRV_SECTOR_BITS;
+ nb_sectors = bytes >> BDRV_SECTOR_BITS;
+
+ assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
+ assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
+ assert((bytes >> BDRV_SECTOR_BITS) <= BDRV_REQUEST_MAX_SECTORS);
+
+ if (drv->bdrv_co_writev_flags) {
+ ret = drv->bdrv_co_writev_flags(bs, sector_num, nb_sectors, qiov,
+ flags & bs->supported_write_flags);
+ flags &= ~bs->supported_write_flags;
+ } else if (drv->bdrv_co_writev) {
+ assert(!bs->supported_write_flags);
+ ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
+ } else {
+ BlockAIOCB *acb;
+ CoroutineIOCompletion co = {
+ .coroutine = qemu_coroutine_self(),
+ };
+
+ acb = bs->drv->bdrv_aio_writev(bs, sector_num, qiov, nb_sectors,
+ bdrv_co_io_em_complete, &co);
+ if (acb == NULL) {
+ ret = -EIO;
+ } else {
+ qemu_coroutine_yield();
+ ret = co.ret;
+ }
+ }
+
+emulate_flags:
+ if (ret == 0 && (flags & BDRV_REQ_FUA)) {
+ ret = bdrv_co_flush(bs);
+ }
+
+ return ret;
+}
+
static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
{
@@ -836,8 +907,9 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
qemu_iovec_init_external(&bounce_qiov, &iov, 1);
- ret = drv->bdrv_co_readv(bs, cluster_sector_num, cluster_nb_sectors,
- &bounce_qiov);
+ ret = bdrv_driver_preadv(bs, cluster_sector_num * BDRV_SECTOR_SIZE,
+ cluster_nb_sectors * BDRV_SECTOR_SIZE,
+ &bounce_qiov, 0);
if (ret < 0) {
goto err;
}
@@ -850,8 +922,9 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
/* This does not change the data on the disk, it is not necessary
* to flush even in cache=writethrough mode.
*/
- ret = drv->bdrv_co_writev(bs, cluster_sector_num, cluster_nb_sectors,
- &bounce_qiov);
+ ret = bdrv_driver_pwritev(bs, cluster_sector_num * BDRV_SECTOR_SIZE,
+ cluster_nb_sectors * BDRV_SECTOR_SIZE,
+ &bounce_qiov, 0);
}
if (ret < 0) {
@@ -880,7 +953,6 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
int64_t align, QEMUIOVector *qiov, int flags)
{
- BlockDriver *drv = bs->drv;
int ret;
int64_t sector_num = offset >> BDRV_SECTOR_BITS;
@@ -921,7 +993,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
/* Forward the request to the BlockDriver */
if (!bs->zero_beyond_eof) {
- ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+ ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0);
} else {
/* Read zeros after EOF */
int64_t total_sectors, max_nb_sectors;
@@ -935,7 +1007,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
max_nb_sectors = ROUND_UP(MAX(0, total_sectors - sector_num),
align >> BDRV_SECTOR_BITS);
if (nb_sectors < max_nb_sectors) {
- ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
+ ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0);
} else if (max_nb_sectors > 0) {
QEMUIOVector local_qiov;
@@ -943,8 +1015,9 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
qemu_iovec_concat(&local_qiov, qiov, 0,
max_nb_sectors * BDRV_SECTOR_SIZE);
- ret = drv->bdrv_co_readv(bs, sector_num, max_nb_sectors,
- &local_qiov);
+ ret = bdrv_driver_preadv(bs, offset,
+ max_nb_sectors * BDRV_SECTOR_SIZE,
+ &local_qiov, 0);
qemu_iovec_destroy(&local_qiov);
} else {
@@ -967,7 +1040,7 @@ out:
/*
* Handle a read request in coroutine context
*/
-int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
+int coroutine_fn bdrv_co_preadv(BlockDriverState *bs,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
@@ -997,7 +1070,7 @@ int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
}
/* throttling disk I/O */
- if (bs->io_limits_enabled) {
+ if (bs->throttle_state) {
throttle_group_co_io_limits_intercept(bs, bytes, false);
}
@@ -1049,8 +1122,8 @@ static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
return -EINVAL;
}
- return bdrv_co_do_preadv(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
+ return bdrv_co_preadv(bs, sector_num << BDRV_SECTOR_BITS,
+ nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
}
int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num,
@@ -1088,6 +1161,7 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
QEMUIOVector qiov;
struct iovec iov = {0};
int ret = 0;
+ bool need_flush = false;
int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_write_zeroes,
BDRV_REQUEST_MAX_SECTORS);
@@ -1120,13 +1194,29 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
ret = -ENOTSUP;
/* First try the efficient write zeroes operation */
if (drv->bdrv_co_write_zeroes) {
- ret = drv->bdrv_co_write_zeroes(bs, sector_num, num, flags);
+ ret = drv->bdrv_co_write_zeroes(bs, sector_num, num,
+ flags & bs->supported_zero_flags);
+ if (ret != -ENOTSUP && (flags & BDRV_REQ_FUA) &&
+ !(bs->supported_zero_flags & BDRV_REQ_FUA)) {
+ need_flush = true;
+ }
+ } else {
+ assert(!bs->supported_zero_flags);
}
if (ret == -ENOTSUP) {
/* Fall back to bounce buffer if write zeroes is unsupported */
int max_xfer_len = MIN_NON_ZERO(bs->bl.max_transfer_length,
MAX_WRITE_ZEROES_BOUNCE_BUFFER);
+ BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE;
+
+ if ((flags & BDRV_REQ_FUA) &&
+ !(bs->supported_write_flags & BDRV_REQ_FUA)) {
+ /* No need for bdrv_driver_pwrite() to do a fallback
+ * flush on each chunk; use just one at the end */
+ write_flags &= ~BDRV_REQ_FUA;
+ need_flush = true;
+ }
num = MIN(num, max_xfer_len);
iov.iov_len = num * BDRV_SECTOR_SIZE;
if (iov.iov_base == NULL) {
@@ -1139,7 +1229,9 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
}
qemu_iovec_init_external(&qiov, &iov, 1);
- ret = drv->bdrv_co_writev(bs, sector_num, num, &qiov);
+ ret = bdrv_driver_pwritev(bs, sector_num * BDRV_SECTOR_SIZE,
+ num * BDRV_SECTOR_SIZE, &qiov,
+ write_flags);
/* Keep bounce buffer around if it is big enough for all
* all future requests.
@@ -1155,6 +1247,9 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
}
fail:
+ if (ret == 0 && need_flush) {
+ ret = bdrv_co_flush(bs);
+ }
qemu_vfree(iov.iov_base);
return ret;
}
@@ -1199,23 +1294,12 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
} else if (flags & BDRV_REQ_ZERO_WRITE) {
bdrv_debug_event(bs, BLKDBG_PWRITEV_ZERO);
ret = bdrv_co_do_write_zeroes(bs, sector_num, nb_sectors, flags);
- } else if (drv->bdrv_co_writev_flags) {
- bdrv_debug_event(bs, BLKDBG_PWRITEV);
- ret = drv->bdrv_co_writev_flags(bs, sector_num, nb_sectors, qiov,
- flags);
} else {
- assert(drv->supported_write_flags == 0);
bdrv_debug_event(bs, BLKDBG_PWRITEV);
- ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
+ ret = bdrv_driver_pwritev(bs, offset, bytes, qiov, flags);
}
bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE);
- if (ret == 0 && (flags & BDRV_REQ_FUA) &&
- !(drv->supported_write_flags & BDRV_REQ_FUA))
- {
- ret = bdrv_co_flush(bs);
- }
-
bdrv_set_dirty(bs, sector_num, nb_sectors);
if (bs->wr_highest_offset < offset + bytes) {
@@ -1320,7 +1404,7 @@ fail:
/*
* Handle a write request in coroutine context
*/
-int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
+int coroutine_fn bdrv_co_pwritev(BlockDriverState *bs,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
@@ -1347,7 +1431,7 @@ int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
}
/* throttling disk I/O */
- if (bs->io_limits_enabled) {
+ if (bs->throttle_state) {
throttle_group_co_io_limits_intercept(bs, bytes, true);
}
@@ -1455,8 +1539,8 @@ static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
return -EINVAL;
}
- return bdrv_co_do_pwritev(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
+ return bdrv_co_pwritev(bs, sector_num << BDRV_SECTOR_BITS,
+ nb_sectors << BDRV_SECTOR_BITS, qiov, flags);
}
int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
@@ -2064,80 +2148,6 @@ void bdrv_aio_cancel_async(BlockAIOCB *acb)
/**************************************************************/
/* async block device emulation */
-typedef struct BlockAIOCBSync {
- BlockAIOCB common;
- QEMUBH *bh;
- int ret;
- /* vector translation state */
- QEMUIOVector *qiov;
- uint8_t *bounce;
- int is_write;
-} BlockAIOCBSync;
-
-static const AIOCBInfo bdrv_em_aiocb_info = {
- .aiocb_size = sizeof(BlockAIOCBSync),
-};
-
-static void bdrv_aio_bh_cb(void *opaque)
-{
- BlockAIOCBSync *acb = opaque;
-
- if (!acb->is_write && acb->ret >= 0) {
- qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
- }
- qemu_vfree(acb->bounce);
- acb->common.cb(acb->common.opaque, acb->ret);
- qemu_bh_delete(acb->bh);
- acb->bh = NULL;
- qemu_aio_unref(acb);
-}
-
-static BlockAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
- int64_t sector_num,
- QEMUIOVector *qiov,
- int nb_sectors,
- BlockCompletionFunc *cb,
- void *opaque,
- int is_write)
-
-{
- BlockAIOCBSync *acb;
-
- acb = qemu_aio_get(&bdrv_em_aiocb_info, bs, cb, opaque);
- acb->is_write = is_write;
- acb->qiov = qiov;
- acb->bounce = qemu_try_blockalign(bs, qiov->size);
- acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_aio_bh_cb, acb);
-
- if (acb->bounce == NULL) {
- acb->ret = -ENOMEM;
- } else if (is_write) {
- qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
- acb->ret = bs->drv->bdrv_write(bs, sector_num, acb->bounce, nb_sectors);
- } else {
- acb->ret = bs->drv->bdrv_read(bs, sector_num, acb->bounce, nb_sectors);
- }
-
- qemu_bh_schedule(acb->bh);
-
- return &acb->common;
-}
-
-static BlockAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque)
-{
- return bdrv_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
-}
-
-static BlockAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque)
-{
- return bdrv_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
-}
-
-
typedef struct BlockAIOCBCoroutine {
BlockAIOCB common;
BlockRequest req;
@@ -2314,59 +2324,6 @@ void qemu_aio_unref(void *p)
/**************************************************************/
/* Coroutine block device emulation */
-typedef struct CoroutineIOCompletion {
- Coroutine *coroutine;
- int ret;
-} CoroutineIOCompletion;
-
-static void bdrv_co_io_em_complete(void *opaque, int ret)
-{
- CoroutineIOCompletion *co = opaque;
-
- co->ret = ret;
- qemu_coroutine_enter(co->coroutine, NULL);
-}
-
-static int coroutine_fn bdrv_co_io_em(BlockDriverState *bs, int64_t sector_num,
- int nb_sectors, QEMUIOVector *iov,
- bool is_write)
-{
- CoroutineIOCompletion co = {
- .coroutine = qemu_coroutine_self(),
- };
- BlockAIOCB *acb;
-
- if (is_write) {
- acb = bs->drv->bdrv_aio_writev(bs, sector_num, iov, nb_sectors,
- bdrv_co_io_em_complete, &co);
- } else {
- acb = bs->drv->bdrv_aio_readv(bs, sector_num, iov, nb_sectors,
- bdrv_co_io_em_complete, &co);
- }
-
- trace_bdrv_co_io_em(bs, sector_num, nb_sectors, is_write, acb);
- if (!acb) {
- return -EIO;
- }
- qemu_coroutine_yield();
-
- return co.ret;
-}
-
-static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov)
-{
- return bdrv_co_io_em(bs, sector_num, nb_sectors, iov, false);
-}
-
-static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov)
-{
- return bdrv_co_io_em(bs, sector_num, nb_sectors, iov, true);
-}
-
static void coroutine_fn bdrv_flush_co_entry(void *opaque)
{
RwCo *rwco = opaque;
@@ -2763,33 +2720,68 @@ void bdrv_add_before_write_notifier(BlockDriverState *bs,
void bdrv_io_plug(BlockDriverState *bs)
{
- BlockDriver *drv = bs->drv;
- if (drv && drv->bdrv_io_plug) {
- drv->bdrv_io_plug(bs);
- } else if (bs->file) {
- bdrv_io_plug(bs->file->bs);
+ BdrvChild *child;
+
+ QLIST_FOREACH(child, &bs->children, next) {
+ bdrv_io_plug(child->bs);
+ }
+
+ if (bs->io_plugged++ == 0 && bs->io_plug_disabled == 0) {
+ BlockDriver *drv = bs->drv;
+ if (drv && drv->bdrv_io_plug) {
+ drv->bdrv_io_plug(bs);
+ }
}
}
void bdrv_io_unplug(BlockDriverState *bs)
{
- BlockDriver *drv = bs->drv;
- if (drv && drv->bdrv_io_unplug) {
- drv->bdrv_io_unplug(bs);
- } else if (bs->file) {
- bdrv_io_unplug(bs->file->bs);
+ BdrvChild *child;
+
+ assert(bs->io_plugged);
+ if (--bs->io_plugged == 0 && bs->io_plug_disabled == 0) {
+ BlockDriver *drv = bs->drv;
+ if (drv && drv->bdrv_io_unplug) {
+ drv->bdrv_io_unplug(bs);
+ }
+ }
+
+ QLIST_FOREACH(child, &bs->children, next) {
+ bdrv_io_unplug(child->bs);
}
}
-void bdrv_flush_io_queue(BlockDriverState *bs)
+void bdrv_io_unplugged_begin(BlockDriverState *bs)
{
- BlockDriver *drv = bs->drv;
- if (drv && drv->bdrv_flush_io_queue) {
- drv->bdrv_flush_io_queue(bs);
- } else if (bs->file) {
- bdrv_flush_io_queue(bs->file->bs);
+ BdrvChild *child;
+
+ if (bs->io_plug_disabled++ == 0 && bs->io_plugged > 0) {
+ BlockDriver *drv = bs->drv;
+ if (drv && drv->bdrv_io_unplug) {
+ drv->bdrv_io_unplug(bs);
+ }
+ }
+
+ QLIST_FOREACH(child, &bs->children, next) {
+ bdrv_io_unplugged_begin(child->bs);
+ }
+}
+
+void bdrv_io_unplugged_end(BlockDriverState *bs)
+{
+ BdrvChild *child;
+
+ assert(bs->io_plug_disabled);
+ QLIST_FOREACH(child, &bs->children, next) {
+ bdrv_io_unplugged_end(child->bs);
+ }
+
+ if (--bs->io_plug_disabled == 0 && bs->io_plugged > 0) {
+ BlockDriver *drv = bs->drv;
+ if (drv && drv->bdrv_io_plug) {
+ drv->bdrv_io_plug(bs);
+ }
}
- bdrv_start_throttled_reqs(bs);
}
void bdrv_drained_begin(BlockDriverState *bs)
generated by cgit v1.2.3 (git 2.26.2) at 2024-12-17 07:43:58 +0000