aboutsummaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/commit.c11
-rw-r--r--block/io.c306
-rw-r--r--block/linux-aio.c88
-rw-r--r--block/mirror.c55
-rw-r--r--block/null.c20
-rw-r--r--block/qcow.c14
-rw-r--r--block/qcow2-cluster.c147
-rw-r--r--block/qcow2.c239
-rw-r--r--block/qcow2.h18
-rw-r--r--block/raw-aio.h3
-rw-r--r--block/raw-posix.c62
-rw-r--r--block/rbd.c38
-rw-r--r--block/sheepdog.c13
13 files changed, 589 insertions, 425 deletions
diff --git a/block/commit.c b/block/commit.c
index 8a00e1146c..444333ba65 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -236,6 +236,11 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
return;
}
+ s = block_job_create(&commit_job_driver, bs, speed, cb, opaque, errp);
+ if (!s) {
+ return;
+ }
+
orig_base_flags = bdrv_get_flags(base);
orig_overlay_flags = bdrv_get_flags(overlay_bs);
@@ -252,16 +257,12 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
bdrv_reopen_multiple(reopen_queue, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
+ block_job_unref(&s->common);
return;
}
}
- s = block_job_create(&commit_job_driver, bs, speed, cb, opaque, errp);
- if (!s) {
- return;
- }
-
s->base = blk_new();
blk_insert_bs(s->base, base);
diff --git a/block/io.c b/block/io.c
index fb99a7151c..ebdb9d834c 100644
--- a/block/io.c
+++ b/block/io.c
@@ -289,15 +289,21 @@ void bdrv_drain_all(void)
bool busy = true;
BlockDriverState *bs;
BdrvNextIterator it;
+ BlockJob *job = NULL;
GSList *aio_ctxs = NULL, *ctx;
+ while ((job = block_job_next(job))) {
+ AioContext *aio_context = blk_get_aio_context(job->blk);
+
+ aio_context_acquire(aio_context);
+ block_job_pause(job);
+ aio_context_release(aio_context);
+ }
+
for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
AioContext *aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
- if (bs->job) {
- block_job_pause(bs->job);
- }
bdrv_parent_drained_begin(bs);
bdrv_io_unplugged_begin(bs);
bdrv_drain_recurse(bs);
@@ -340,12 +346,18 @@ void bdrv_drain_all(void)
aio_context_acquire(aio_context);
bdrv_io_unplugged_end(bs);
bdrv_parent_drained_end(bs);
- if (bs->job) {
- block_job_resume(bs->job);
- }
aio_context_release(aio_context);
}
g_slist_free(aio_ctxs);
+
+ job = NULL;
+ while ((job = block_job_next(job))) {
+ AioContext *aio_context = blk_get_aio_context(job->blk);
+
+ aio_context_acquire(aio_context);
+ block_job_resume(job);
+ aio_context_release(aio_context);
+ }
}
/**
@@ -404,12 +416,12 @@ static void mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
}
/**
- * Round a region to cluster boundaries
+ * Round a region to cluster boundaries (sector-based)
*/
-void bdrv_round_to_clusters(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- int64_t *cluster_sector_num,
- int *cluster_nb_sectors)
+void bdrv_round_sectors_to_clusters(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors,
+ int64_t *cluster_sector_num,
+ int *cluster_nb_sectors)
{
BlockDriverInfo bdi;
@@ -424,6 +436,26 @@ void bdrv_round_to_clusters(BlockDriverState *bs,
}
}
+/**
+ * Round a region to cluster boundaries
+ */
+void bdrv_round_to_clusters(BlockDriverState *bs,
+ int64_t offset, unsigned int bytes,
+ int64_t *cluster_offset,
+ unsigned int *cluster_bytes)
+{
+ BlockDriverInfo bdi;
+
+ if (bdrv_get_info(bs, &bdi) < 0 || bdi.cluster_size == 0) {
+ *cluster_offset = offset;
+ *cluster_bytes = bytes;
+ } else {
+ int64_t c = bdi.cluster_size;
+ *cluster_offset = QEMU_ALIGN_DOWN(offset, c);
+ *cluster_bytes = QEMU_ALIGN_UP(offset - *cluster_offset + bytes, c);
+ }
+}
+
static int bdrv_get_cluster_size(BlockDriverState *bs)
{
BlockDriverInfo bdi;
@@ -680,6 +712,18 @@ int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
}
}
+int bdrv_preadv(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov)
+{
+ int ret;
+
+ ret = bdrv_prwv_co(bs, offset, qiov, false, 0);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return qiov->size;
+}
+
int bdrv_pread(BlockDriverState *bs, int64_t offset, void *buf, int bytes)
{
QEMUIOVector qiov;
@@ -687,19 +731,13 @@ int bdrv_pread(BlockDriverState *bs, int64_t offset, void *buf, int bytes)
.iov_base = (void *)buf,
.iov_len = bytes,
};
- int ret;
if (bytes < 0) {
return -EINVAL;
}
qemu_iovec_init_external(&qiov, &iov, 1);
- ret = bdrv_prwv_co(bs, offset, &qiov, false, 0);
- if (ret < 0) {
- return ret;
- }
-
- return bytes;
+ return bdrv_preadv(bs, offset, &qiov);
}
int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov)
@@ -776,6 +814,8 @@ static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
int64_t sector_num;
unsigned int nb_sectors;
+ assert(!(flags & ~BDRV_REQ_MASK));
+
if (drv->bdrv_co_preadv) {
return drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags);
}
@@ -815,6 +855,8 @@ static int coroutine_fn bdrv_driver_pwritev(BlockDriverState *bs,
unsigned int nb_sectors;
int ret;
+ assert(!(flags & ~BDRV_REQ_MASK));
+
if (drv->bdrv_co_pwritev) {
ret = drv->bdrv_co_pwritev(bs, offset, bytes, qiov,
flags & bs->supported_write_flags);
@@ -861,7 +903,7 @@ emulate_flags:
}
static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+ int64_t offset, unsigned int bytes, QEMUIOVector *qiov)
{
/* Perform I/O through a temporary buffer so that users who scribble over
* their read buffer while the operation is in progress do not end up
@@ -873,21 +915,20 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
BlockDriver *drv = bs->drv;
struct iovec iov;
QEMUIOVector bounce_qiov;
- int64_t cluster_sector_num;
- int cluster_nb_sectors;
+ int64_t cluster_offset;
+ unsigned int cluster_bytes;
size_t skip_bytes;
int ret;
/* Cover entire cluster so no additional backing file I/O is required when
* allocating cluster in the image file.
*/
- bdrv_round_to_clusters(bs, sector_num, nb_sectors,
- &cluster_sector_num, &cluster_nb_sectors);
+ bdrv_round_to_clusters(bs, offset, bytes, &cluster_offset, &cluster_bytes);
- trace_bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors,
- cluster_sector_num, cluster_nb_sectors);
+ trace_bdrv_co_do_copy_on_readv(bs, offset, bytes,
+ cluster_offset, cluster_bytes);
- iov.iov_len = cluster_nb_sectors * BDRV_SECTOR_SIZE;
+ iov.iov_len = cluster_bytes;
iov.iov_base = bounce_buffer = qemu_try_blockalign(bs, iov.iov_len);
if (bounce_buffer == NULL) {
ret = -ENOMEM;
@@ -896,8 +937,7 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
qemu_iovec_init_external(&bounce_qiov, &iov, 1);
- ret = bdrv_driver_preadv(bs, cluster_sector_num * BDRV_SECTOR_SIZE,
- cluster_nb_sectors * BDRV_SECTOR_SIZE,
+ ret = bdrv_driver_preadv(bs, cluster_offset, cluster_bytes,
&bounce_qiov, 0);
if (ret < 0) {
goto err;
@@ -905,16 +945,12 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
if (drv->bdrv_co_pwrite_zeroes &&
buffer_is_zero(bounce_buffer, iov.iov_len)) {
- ret = bdrv_co_do_pwrite_zeroes(bs,
- cluster_sector_num * BDRV_SECTOR_SIZE,
- cluster_nb_sectors * BDRV_SECTOR_SIZE,
- 0);
+ 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_sector_num * BDRV_SECTOR_SIZE,
- cluster_nb_sectors * BDRV_SECTOR_SIZE,
+ ret = bdrv_driver_pwritev(bs, cluster_offset, cluster_bytes,
&bounce_qiov, 0);
}
@@ -926,9 +962,8 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
goto err;
}
- skip_bytes = (sector_num - cluster_sector_num) * BDRV_SECTOR_SIZE;
- qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes,
- nb_sectors * BDRV_SECTOR_SIZE);
+ skip_bytes = offset - cluster_offset;
+ qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes, bytes);
err:
qemu_vfree(bounce_buffer);
@@ -944,15 +979,15 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
int64_t align, QEMUIOVector *qiov, int flags)
{
+ int64_t total_bytes, max_bytes;
int ret;
- int64_t sector_num = offset >> BDRV_SECTOR_BITS;
- unsigned int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
+ 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);
+ assert(!(flags & ~BDRV_REQ_MASK));
/* Handle Copy on Read and associated serialisation */
if (flags & BDRV_REQ_COPY_ON_READ) {
@@ -969,59 +1004,50 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
}
if (flags & BDRV_REQ_COPY_ON_READ) {
+ int64_t start_sector = offset >> BDRV_SECTOR_BITS;
+ int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
+ unsigned int nb_sectors = end_sector - start_sector;
int pnum;
- ret = bdrv_is_allocated(bs, sector_num, nb_sectors, &pnum);
+ ret = bdrv_is_allocated(bs, start_sector, nb_sectors, &pnum);
if (ret < 0) {
goto out;
}
if (!ret || pnum != nb_sectors) {
- ret = bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors, qiov);
+ ret = bdrv_co_do_copy_on_readv(bs, offset, bytes, qiov);
goto out;
}
}
/* Forward the request to the BlockDriver */
- if (!bs->zero_beyond_eof) {
- ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0);
- } else {
- /* Read zeros after EOF */
- int64_t total_sectors, max_nb_sectors;
-
- total_sectors = bdrv_nb_sectors(bs);
- if (total_sectors < 0) {
- ret = total_sectors;
- goto out;
- }
+ total_bytes = bdrv_getlength(bs);
+ if (total_bytes < 0) {
+ ret = total_bytes;
+ goto out;
+ }
- max_nb_sectors = ROUND_UP(MAX(0, total_sectors - sector_num),
- align >> BDRV_SECTOR_BITS);
- if (nb_sectors < max_nb_sectors) {
- ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0);
- } else if (max_nb_sectors > 0) {
- QEMUIOVector local_qiov;
+ max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align);
+ if (bytes < max_bytes) {
+ ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0);
+ } else if (max_bytes > 0) {
+ QEMUIOVector local_qiov;
- qemu_iovec_init(&local_qiov, qiov->niov);
- qemu_iovec_concat(&local_qiov, qiov, 0,
- max_nb_sectors * BDRV_SECTOR_SIZE);
+ qemu_iovec_init(&local_qiov, qiov->niov);
+ qemu_iovec_concat(&local_qiov, qiov, 0, max_bytes);
- ret = bdrv_driver_preadv(bs, offset,
- max_nb_sectors * BDRV_SECTOR_SIZE,
- &local_qiov, 0);
+ ret = bdrv_driver_preadv(bs, offset, max_bytes, &local_qiov, 0);
- qemu_iovec_destroy(&local_qiov);
- } else {
- ret = 0;
- }
+ qemu_iovec_destroy(&local_qiov);
+ } else {
+ ret = 0;
+ }
- /* Reading beyond end of file is supposed to produce zeroes */
- if (ret == 0 && total_sectors < sector_num + nb_sectors) {
- uint64_t offset = MAX(0, total_sectors - sector_num);
- uint64_t bytes = (sector_num + nb_sectors - offset) *
- BDRV_SECTOR_SIZE;
- qemu_iovec_memset(qiov, offset * BDRV_SECTOR_SIZE, 0, bytes);
- }
+ /* Reading beyond end of file is supposed to produce zeroes */
+ if (ret == 0 && total_bytes < offset + bytes) {
+ uint64_t zero_offset = MAX(0, total_bytes - offset);
+ uint64_t zero_bytes = offset + bytes - zero_offset;
+ qemu_iovec_memset(qiov, zero_offset, 0, zero_bytes);
}
out:
@@ -1038,8 +1064,7 @@ int coroutine_fn bdrv_co_preadv(BlockDriverState *bs,
BlockDriver *drv = bs->drv;
BdrvTrackedRequest req;
- /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
+ uint64_t align = bs->request_alignment;
uint8_t *head_buf = NULL;
uint8_t *tail_buf = NULL;
QEMUIOVector local_qiov;
@@ -1235,13 +1260,12 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
bool waited;
int ret;
- int64_t sector_num = offset >> BDRV_SECTOR_BITS;
- unsigned int nb_sectors = bytes >> BDRV_SECTOR_BITS;
+ int64_t start_sector = offset >> BDRV_SECTOR_BITS;
+ int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
- assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
- assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
assert(!qiov || bytes == qiov->size);
assert((bs->open_flags & BDRV_O_NO_IO) == 0);
+ assert(!(flags & ~BDRV_REQ_MASK));
waited = wait_serialising_requests(req);
assert(!waited || !req->serialising);
@@ -1263,22 +1287,21 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
/* Do nothing, write notifier decided to fail this request */
} else if (flags & BDRV_REQ_ZERO_WRITE) {
bdrv_debug_event(bs, BLKDBG_PWRITEV_ZERO);
- ret = bdrv_co_do_pwrite_zeroes(bs, sector_num << BDRV_SECTOR_BITS,
- nb_sectors << BDRV_SECTOR_BITS, flags);
+ ret = bdrv_co_do_pwrite_zeroes(bs, offset, bytes, flags);
} else {
bdrv_debug_event(bs, BLKDBG_PWRITEV);
ret = bdrv_driver_pwritev(bs, offset, bytes, qiov, flags);
}
bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE);
- bdrv_set_dirty(bs, sector_num, nb_sectors);
+ bdrv_set_dirty(bs, start_sector, end_sector - start_sector);
if (bs->wr_highest_offset < offset + bytes) {
bs->wr_highest_offset = offset + bytes;
}
if (ret >= 0) {
- bs->total_sectors = MAX(bs->total_sectors, sector_num + nb_sectors);
+ bs->total_sectors = MAX(bs->total_sectors, end_sector);
}
return ret;
@@ -1293,7 +1316,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
uint8_t *buf = NULL;
QEMUIOVector local_qiov;
struct iovec iov;
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
+ uint64_t align = bs->request_alignment;
unsigned int head_padding_bytes, tail_padding_bytes;
int ret = 0;
@@ -1380,8 +1403,7 @@ int coroutine_fn bdrv_co_pwritev(BlockDriverState *bs,
BdrvRequestFlags flags)
{
BdrvTrackedRequest req;
- /* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
- uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
+ uint64_t align = bs->request_alignment;
uint8_t *head_buf = NULL;
uint8_t *tail_buf = NULL;
QEMUIOVector local_qiov;
@@ -1824,6 +1846,62 @@ int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
return drv->bdrv_write_compressed(bs, sector_num, buf, nb_sectors);
}
+typedef struct BdrvVmstateCo {
+ BlockDriverState *bs;
+ QEMUIOVector *qiov;
+ int64_t pos;
+ bool is_read;
+ int ret;
+} BdrvVmstateCo;
+
+static int coroutine_fn
+bdrv_co_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
+ bool is_read)
+{
+ BlockDriver *drv = bs->drv;
+
+ if (!drv) {
+ return -ENOMEDIUM;
+ } else if (drv->bdrv_load_vmstate) {
+ return is_read ? drv->bdrv_load_vmstate(bs, qiov, pos)
+ : drv->bdrv_save_vmstate(bs, qiov, pos);
+ } else if (bs->file) {
+ return bdrv_co_rw_vmstate(bs->file->bs, qiov, pos, is_read);
+ }
+
+ return -ENOTSUP;
+}
+
+static void coroutine_fn bdrv_co_rw_vmstate_entry(void *opaque)
+{
+ BdrvVmstateCo *co = opaque;
+ co->ret = bdrv_co_rw_vmstate(co->bs, co->qiov, co->pos, co->is_read);
+}
+
+static inline int
+bdrv_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos,
+ bool is_read)
+{
+ if (qemu_in_coroutine()) {
+ return bdrv_co_rw_vmstate(bs, qiov, pos, is_read);
+ } else {
+ BdrvVmstateCo data = {
+ .bs = bs,
+ .qiov = qiov,
+ .pos = pos,
+ .is_read = is_read,
+ .ret = -EINPROGRESS,
+ };
+ Coroutine *co = qemu_coroutine_create(bdrv_co_rw_vmstate_entry);
+
+ qemu_coroutine_enter(co, &data);
+ while (data.ret == -EINPROGRESS) {
+ aio_poll(bdrv_get_aio_context(bs), true);
+ }
+ return data.ret;
+ }
+}
+
int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
int64_t pos, int size)
{
@@ -1832,37 +1910,45 @@ int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
.iov_base = (void *) buf,
.iov_len = size,
};
+ int ret;
qemu_iovec_init_external(&qiov, &iov, 1);
- return bdrv_writev_vmstate(bs, &qiov, pos);
+
+ ret = bdrv_writev_vmstate(bs, &qiov, pos);
+ if (ret < 0) {
+ return ret;
+ }
+
+ return size;
}
int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
{
- BlockDriver *drv = bs->drv;
+ return bdrv_rw_vmstate(bs, qiov, pos, false);
+}
- if (!drv) {
- return -ENOMEDIUM;
- } else if (drv->bdrv_save_vmstate) {
- return drv->bdrv_save_vmstate(bs, qiov, pos);
- } else if (bs->file) {
- return bdrv_writev_vmstate(bs->file->bs, qiov, pos);
+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,
+ };
+ int ret;
+
+ qemu_iovec_init_external(&qiov, &iov, 1);
+ ret = bdrv_readv_vmstate(bs, &qiov, pos);
+ if (ret < 0) {
+ return ret;
}
- return -ENOTSUP;
+ return size;
}
-int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
- int64_t pos, int size)
+int bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos)
{
- BlockDriver *drv = bs->drv;
- if (!drv)
- return -ENOMEDIUM;
- if (drv->bdrv_load_vmstate)
- return drv->bdrv_load_vmstate(bs, buf, pos, size);
- if (bs->file)
- return bdrv_load_vmstate(bs->file->bs, buf, pos, size);
- return -ENOTSUP;
+ return bdrv_rw_vmstate(bs, qiov, pos, true);
}
/**************************************************************/
diff --git a/block/linux-aio.c b/block/linux-aio.c
index 90ec98ee23..e468960146 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -11,8 +11,10 @@
#include "qemu-common.h"
#include "block/aio.h"
#include "qemu/queue.h"
+#include "block/block.h"
#include "block/raw-aio.h"
#include "qemu/event_notifier.h"
+#include "qemu/coroutine.h"
#include <libaio.h>
@@ -30,6 +32,7 @@
struct qemu_laiocb {
BlockAIOCB common;
+ Coroutine *co;
LinuxAioState *ctx;
struct iocb iocb;
ssize_t ret;
@@ -88,9 +91,14 @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
}
}
}
- laiocb->common.cb(laiocb->common.opaque, ret);
- qemu_aio_unref(laiocb);
+ laiocb->ret = ret;
+ if (laiocb->co) {
+ qemu_coroutine_enter(laiocb->co, NULL);
+ } else {
+ laiocb->common.cb(laiocb->common.opaque, ret);
+ qemu_aio_unref(laiocb);
+ }
}
/* The completion BH fetches completed I/O requests and invokes their
@@ -141,6 +149,8 @@ static void qemu_laio_completion_bh(void *opaque)
if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
ioq_submit(s);
}
+
+ qemu_bh_cancel(s->completion_bh);
}
static void qemu_laio_completion_cb(EventNotifier *e)
@@ -148,7 +158,7 @@ static void qemu_laio_completion_cb(EventNotifier *e)
LinuxAioState *s = container_of(e, LinuxAioState, e);
if (event_notifier_test_and_clear(&s->e)) {
- qemu_bh_schedule(s->completion_bh);
+ qemu_laio_completion_bh(s);
}
}
@@ -230,22 +240,12 @@ void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s)
}
}
-BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque, int type)
+static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
+ int type)
{
- struct qemu_laiocb *laiocb;
- struct iocb *iocbs;
- off_t offset = sector_num * 512;
-
- laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
- laiocb->nbytes = nb_sectors * 512;
- laiocb->ctx = s;
- laiocb->ret = -EINPROGRESS;
- laiocb->is_read = (type == QEMU_AIO_READ);
- laiocb->qiov = qiov;
-
- iocbs = &laiocb->iocb;
+ LinuxAioState *s = laiocb->ctx;
+ struct iocb *iocbs = &laiocb->iocb;
+ QEMUIOVector *qiov = laiocb->qiov;
switch (type) {
case QEMU_AIO_WRITE:
@@ -258,7 +258,7 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
default:
fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
__func__, type);
- goto out_free_aiocb;
+ return -EIO;
}
io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
@@ -268,11 +268,53 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
(!s->io_q.plugged || s->io_q.n >= MAX_QUEUED_IO)) {
ioq_submit(s);
}
- return &laiocb->common;
-out_free_aiocb:
- qemu_aio_unref(laiocb);
- return NULL;
+ return 0;
+}
+
+int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
+ uint64_t offset, QEMUIOVector *qiov, int type)
+{
+ int ret;
+ struct qemu_laiocb laiocb = {
+ .co = qemu_coroutine_self(),
+ .nbytes = qiov->size,
+ .ctx = s,
+ .is_read = (type == QEMU_AIO_READ),
+ .qiov = qiov,
+ };
+
+ ret = laio_do_submit(fd, &laiocb, offset, type);
+ if (ret < 0) {
+ return ret;
+ }
+
+ qemu_coroutine_yield();
+ return laiocb.ret;
+}
+
+BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
+ int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+ BlockCompletionFunc *cb, void *opaque, int type)
+{
+ struct qemu_laiocb *laiocb;
+ off_t offset = sector_num * BDRV_SECTOR_SIZE;
+ int ret;
+
+ laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
+ laiocb->nbytes = nb_sectors * BDRV_SECTOR_SIZE;
+ laiocb->ctx = s;
+ laiocb->ret = -EINPROGRESS;
+ laiocb->is_read = (type == QEMU_AIO_READ);
+ laiocb->qiov = qiov;
+
+ ret = laio_do_submit(fd, laiocb, offset, type);
+ if (ret < 0) {
+ qemu_aio_unref(laiocb);
+ return NULL;
+ }
+
+ return &laiocb->common;
}
void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context)
diff --git a/block/mirror.c b/block/mirror.c
index 80fd3c7469..075384a9cf 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -44,6 +44,7 @@ typedef struct MirrorBlockJob {
/* Used to block operations on the drive-mirror-replace target */
Error *replace_blocker;
bool is_none_mode;
+ BlockMirrorBackingMode backing_mode;
BlockdevOnError on_source_error, on_target_error;
bool synced;
bool should_complete;
@@ -157,8 +158,7 @@ static void mirror_read_complete(void *opaque, int ret)
return;
}
blk_aio_pwritev(s->target, op->sector_num * BDRV_SECTOR_SIZE, &op->qiov,
- op->nb_sectors * BDRV_SECTOR_SIZE,
- mirror_write_complete, op);
+ 0, mirror_write_complete, op);
}
static inline void mirror_clip_sectors(MirrorBlockJob *s,
@@ -186,8 +186,9 @@ static int mirror_cow_align(MirrorBlockJob *s,
need_cow |= !test_bit((*sector_num + *nb_sectors - 1) / chunk_sectors,
s->cow_bitmap);
if (need_cow) {
- bdrv_round_to_clusters(blk_bs(s->target), *sector_num, *nb_sectors,
- &align_sector_num, &align_nb_sectors);
+ bdrv_round_sectors_to_clusters(blk_bs(s->target), *sector_num,
+ *nb_sectors, &align_sector_num,
+ &align_nb_sectors);
}
if (align_nb_sectors > max_sectors) {
@@ -274,8 +275,7 @@ static int mirror_do_read(MirrorBlockJob *s, int64_t sector_num,
s->sectors_in_flight += nb_sectors;
trace_mirror_one_iteration(s, sector_num, nb_sectors);
- blk_aio_preadv(source, sector_num * BDRV_SECTOR_SIZE, &op->qiov,
- nb_sectors * BDRV_SECTOR_SIZE,
+ blk_aio_preadv(source, sector_num * BDRV_SECTOR_SIZE, &op->qiov, 0,
mirror_read_complete, op);
return ret;
}
@@ -386,8 +386,9 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
} else if (ret >= 0 && !(ret & BDRV_BLOCK_DATA)) {
int64_t target_sector_num;
int target_nb_sectors;
- bdrv_round_to_clusters(blk_bs(s->target), sector_num, io_sectors,
- &target_sector_num, &target_nb_sectors);
+ bdrv_round_sectors_to_clusters(blk_bs(s->target), sector_num,
+ io_sectors, &target_sector_num,
+ &target_nb_sectors);
if (target_sector_num == sector_num &&
target_nb_sectors == io_sectors) {
mirror_method = ret & BDRV_BLOCK_ZERO ?
@@ -742,20 +743,26 @@ static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
static void mirror_complete(BlockJob *job, Error **errp)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
- Error *local_err = NULL;
- int ret;
+ BlockDriverState *src, *target;
+
+ src = blk_bs(job->blk);
+ target = blk_bs(s->target);
- ret = bdrv_open_backing_file(blk_bs(s->target), NULL, "backing",
- &local_err);
- if (ret < 0) {
- error_propagate(errp, local_err);
- return;
- }
if (!s->synced) {
error_setg(errp, QERR_BLOCK_JOB_NOT_READY, job->id);
return;
}
+ if (s->backing_mode == MIRROR_OPEN_BACKING_CHAIN) {
+ int ret;
+
+ assert(!target->backing);
+ ret = bdrv_open_backing_file(target, NULL, "backing", errp);
+ if (ret < 0) {
+ return;
+ }
+ }
+
/* check the target bs is not blocked and block all operations on it */
if (s->replaces) {
AioContext *replace_aio_context;
@@ -777,6 +784,13 @@ static void mirror_complete(BlockJob *job, Error **errp)
aio_context_release(replace_aio_context);
}
+ if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
+ BlockDriverState *backing = s->is_none_mode ? src : s->base;
+ if (backing_bs(target) != backing) {
+ bdrv_set_backing_hd(target, backing);
+ }
+ }
+
s->should_complete = true;
block_job_enter(&s->common);
}
@@ -799,6 +813,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
const char *replaces,
int64_t speed, uint32_t granularity,
int64_t buf_size,
+ BlockMirrorBackingMode backing_mode,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
bool unmap,
@@ -836,6 +851,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
s->on_source_error = on_source_error;
s->on_target_error = on_target_error;
s->is_none_mode = is_none_mode;
+ s->backing_mode = backing_mode;
s->base = base;
s->granularity = granularity;
s->buf_size = ROUND_UP(buf_size, granularity);
@@ -859,7 +875,8 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
void mirror_start(BlockDriverState *bs, BlockDriverState *target,
const char *replaces,
int64_t speed, uint32_t granularity, int64_t buf_size,
- MirrorSyncMode mode, BlockdevOnError on_source_error,
+ MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
+ BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
bool unmap,
BlockCompletionFunc *cb,
@@ -875,7 +892,7 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
base = mode == MIRROR_SYNC_MODE_TOP ? backing_bs(bs) : NULL;
mirror_start_job(bs, target, replaces,
- speed, granularity, buf_size,
+ speed, granularity, buf_size, backing_mode,
on_source_error, on_target_error, unmap, cb, opaque, errp,
&mirror_job_driver, is_none_mode, base);
}
@@ -922,7 +939,7 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
}
}
- mirror_start_job(bs, base, NULL, speed, 0, 0,
+ mirror_start_job(bs, base, NULL, speed, 0, 0, MIRROR_LEAVE_BACKING_CHAIN,
on_error, on_error, false, cb, opaque, &local_err,
&commit_active_job_driver, false, base);
if (local_err) {
diff --git a/block/null.c b/block/null.c
index 396500babd..b511010ba5 100644
--- a/block/null.c
+++ b/block/null.c
@@ -12,6 +12,8 @@
#include "qemu/osdep.h"
#include "qapi/error.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qstring.h"
#include "block/block_int.h"
#define NULL_OPT_LATENCY "latency-ns"
@@ -223,6 +225,20 @@ static int64_t coroutine_fn null_co_get_block_status(BlockDriverState *bs,
}
}
+static void null_refresh_filename(BlockDriverState *bs, QDict *opts)
+{
+ QINCREF(opts);
+ qdict_del(opts, "filename");
+
+ if (!qdict_size(opts)) {
+ snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s://",
+ bs->drv->format_name);
+ }
+
+ qdict_put(opts, "driver", qstring_from_str(bs->drv->format_name));
+ bs->full_open_options = opts;
+}
+
static BlockDriver bdrv_null_co = {
.format_name = "null-co",
.protocol_name = "null-co",
@@ -238,6 +254,8 @@ static BlockDriver bdrv_null_co = {
.bdrv_reopen_prepare = null_reopen_prepare,
.bdrv_co_get_block_status = null_co_get_block_status,
+
+ .bdrv_refresh_filename = null_refresh_filename,
};
static BlockDriver bdrv_null_aio = {
@@ -255,6 +273,8 @@ static BlockDriver bdrv_null_aio = {
.bdrv_reopen_prepare = null_reopen_prepare,
.bdrv_co_get_block_status = null_co_get_block_status,
+
+ .bdrv_refresh_filename = null_refresh_filename,
};
static void bdrv_null_init(void)
diff --git a/block/qcow.c b/block/qcow.c
index c5cf813469..312af52816 100644
--- a/block/qcow.c
+++ b/block/qcow.c
@@ -162,10 +162,16 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
if (s->crypt_method_header) {
if (bdrv_uses_whitelist() &&
s->crypt_method_header == QCOW_CRYPT_AES) {
- error_report("qcow built-in AES encryption is deprecated");
- error_printf("Support for it will be removed in a future release.\n"
- "You can use 'qemu-img convert' to switch to an\n"
- "unencrypted qcow image, or a LUKS raw image.\n");
+ error_setg(errp,
+ "Use of AES-CBC encrypted qcow images is no longer "
+ "supported in system emulators");
+ error_append_hint(errp,
+ "You can use 'qemu-img convert' to convert your "
+ "image to an alternative supported format, such "
+ "as unencrypted qcow, or raw with the LUKS "
+ "format instead.\n");
+ ret = -ENOSYS;
+ goto fail;
}
bs->encrypted = 1;
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index b04bfafd65..893ddf6798 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -390,22 +390,18 @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
return 0;
}
-static int coroutine_fn copy_sectors(BlockDriverState *bs,
- uint64_t start_sect,
- uint64_t cluster_offset,
- int n_start, int n_end)
+static int coroutine_fn do_perform_cow(BlockDriverState *bs,
+ uint64_t src_cluster_offset,
+ uint64_t cluster_offset,
+ int offset_in_cluster,
+ int bytes)
{
BDRVQcow2State *s = bs->opaque;
QEMUIOVector qiov;
struct iovec iov;
- int n, ret;
-
- n = n_end - n_start;
- if (n <= 0) {
- return 0;
- }
+ int ret;
- iov.iov_len = n * BDRV_SECTOR_SIZE;
+ iov.iov_len = bytes;
iov.iov_base = qemu_try_blockalign(bs, iov.iov_len);
if (iov.iov_base == NULL) {
return -ENOMEM;
@@ -424,17 +420,21 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
* interface. This avoids double I/O throttling and request tracking,
* which can lead to deadlock when block layer copy-on-read is enabled.
*/
- ret = bs->drv->bdrv_co_readv(bs, start_sect + n_start, n, &qiov);
+ ret = bs->drv->bdrv_co_preadv(bs, src_cluster_offset + offset_in_cluster,
+ bytes, &qiov, 0);
if (ret < 0) {
goto out;
}
if (bs->encrypted) {
Error *err = NULL;
+ int64_t sector = (cluster_offset + offset_in_cluster)
+ >> BDRV_SECTOR_BITS;
assert(s->cipher);
- if (qcow2_encrypt_sectors(s, start_sect + n_start,
- iov.iov_base, iov.iov_base, n,
- true, &err) < 0) {
+ assert((offset_in_cluster & ~BDRV_SECTOR_MASK) == 0);
+ assert((bytes & ~BDRV_SECTOR_MASK) == 0);
+ if (qcow2_encrypt_sectors(s, sector, iov.iov_base, iov.iov_base,
+ bytes >> BDRV_SECTOR_BITS, true, &err) < 0) {
ret = -EIO;
error_free(err);
goto out;
@@ -442,14 +442,14 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
}
ret = qcow2_pre_write_overlap_check(bs, 0,
- cluster_offset + n_start * BDRV_SECTOR_SIZE, n * BDRV_SECTOR_SIZE);
+ cluster_offset + offset_in_cluster, bytes);
if (ret < 0) {
goto out;
}
BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE);
- ret = bdrv_co_writev(bs->file->bs, (cluster_offset >> 9) + n_start, n,
- &qiov);
+ ret = bdrv_co_pwritev(bs->file->bs, cluster_offset + offset_in_cluster,
+ bytes, &qiov, 0);
if (ret < 0) {
goto out;
}
@@ -464,47 +464,44 @@ out:
/*
* get_cluster_offset
*
- * For a given offset of the disk image, find the cluster offset in
- * qcow2 file. The offset is stored in *cluster_offset.
+ * For a given offset of the virtual disk, find the cluster type and offset in
+ * the qcow2 file. The offset is stored in *cluster_offset.
*
- * on entry, *num is the number of contiguous sectors we'd like to
- * access following offset.
+ * On entry, *bytes is the maximum number of contiguous bytes starting at
+ * offset that we are interested in.
*
- * on exit, *num is the number of contiguous sectors we can read.
+ * On exit, *bytes is the number of bytes starting at offset that have the same
+ * cluster type and (if applicable) are stored contiguously in the image file.
+ * Compressed clusters are always returned one by one.
*
* Returns the cluster type (QCOW2_CLUSTER_*) on success, -errno in error
* cases.
*/
int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
- int *num, uint64_t *cluster_offset)
+ unsigned int *bytes, uint64_t *cluster_offset)
{
BDRVQcow2State *s = bs->opaque;
unsigned int l2_index;
uint64_t l1_index, l2_offset, *l2_table;
int l1_bits, c;
- unsigned int index_in_cluster, nb_clusters;
- uint64_t nb_available, nb_needed;
+ unsigned int offset_in_cluster, nb_clusters;
+ uint64_t bytes_available, bytes_needed;
int ret;
- index_in_cluster = (offset >> 9) & (s->cluster_sectors - 1);
- nb_needed = *num + index_in_cluster;
+ offset_in_cluster = offset_into_cluster(s, offset);
+ bytes_needed = (uint64_t) *bytes + offset_in_cluster;
l1_bits = s->l2_bits + s->cluster_bits;
- /* compute how many bytes there are between the offset and
- * the end of the l1 entry
- */
-
- nb_available = (1ULL << l1_bits) - (offset & ((1ULL << l1_bits) - 1));
+ /* compute how many bytes there are between the start of the cluster
+ * containing offset and the end of the l1 entry */
+ bytes_available = (1ULL << l1_bits) - (offset & ((1ULL << l1_bits) - 1))
+ + offset_in_cluster;
- /* compute the number of available sectors */
-
- nb_available = (nb_available >> 9) + index_in_cluster;
-
- if (nb_needed > nb_available) {
- nb_needed = nb_available;
+ if (bytes_needed > bytes_available) {
+ bytes_needed = bytes_available;
}
- assert(nb_needed <= INT_MAX);
+ assert(bytes_needed <= INT_MAX);
*cluster_offset = 0;
@@ -542,7 +539,7 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
*cluster_offset = be64_to_cpu(l2_table[l2_index]);
/* nb_needed <= INT_MAX, thus nb_clusters <= INT_MAX, too */
- nb_clusters = size_to_clusters(s, nb_needed << 9);
+ nb_clusters = size_to_clusters(s, bytes_needed);
ret = qcow2_get_cluster_type(*cluster_offset);
switch (ret) {
@@ -589,13 +586,14 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
- nb_available = (c * s->cluster_sectors);
+ bytes_available = (c * s->cluster_size);
out:
- if (nb_available > nb_needed)
- nb_available = nb_needed;
+ if (bytes_available > bytes_needed) {
+ bytes_available = bytes_needed;
+ }
- *num = nb_available - index_in_cluster;
+ *bytes = bytes_available - offset_in_cluster;
return ret;
@@ -741,14 +739,12 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
BDRVQcow2State *s = bs->opaque;
int ret;
- if (r->nb_sectors == 0) {
+ if (r->nb_bytes == 0) {
return 0;
}
qemu_co_mutex_unlock(&s->lock);
- ret = copy_sectors(bs, m->offset / BDRV_SECTOR_SIZE, m->alloc_offset,
- r->offset / BDRV_SECTOR_SIZE,
- r->offset / BDRV_SECTOR_SIZE + r->nb_sectors);
+ ret = do_perform_cow(bs, m->offset, m->alloc_offset, r->offset, r->nb_bytes);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
@@ -810,13 +806,14 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
assert(l2_index + m->nb_clusters <= s->l2_size);
for (i = 0; i < m->nb_clusters; i++) {
/* if two concurrent writes happen to the same unallocated cluster
- * each write allocates separate cluster and writes data concurrently.
- * The first one to complete updates l2 table with pointer to its
- * cluster the second one has to do RMW (which is done above by
- * copy_sectors()), update l2 table with its cluster pointer and free
- * old cluster. This is what this loop does */
- if(l2_table[l2_index + i] != 0)
+ * each write allocates separate cluster and writes data concurrently.
+ * The first one to complete updates l2 table with pointer to its
+ * cluster the second one has to do RMW (which is done above by
+ * perform_cow()), update l2 table with its cluster pointer and free
+ * old cluster. This is what this loop does */
+ if (l2_table[l2_index + i] != 0) {
old_cluster[j++] = l2_table[l2_index + i];
+ }
l2_table[l2_index + i] = cpu_to_be64((cluster_offset +
(i << s->cluster_bits)) | QCOW_OFLAG_COPIED);
@@ -1198,25 +1195,20 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
/*
* Save info needed for meta data update.
*
- * requested_sectors: Number of sectors from the start of the first
+ * requested_bytes: Number of bytes from the start of the first
* newly allocated cluster to the end of the (possibly shortened
* before) write request.
*
- * avail_sectors: Number of sectors from the start of the first
+ * avail_bytes: Number of bytes from the start of the first
* newly allocated to the end of the last newly allocated cluster.
*
- * nb_sectors: The number of sectors from the start of the first
+ * nb_bytes: The number of bytes from the start of the first
* newly allocated cluster to the end of the area that the write
* request actually writes to (excluding COW at the end)
*/
- int requested_sectors =
- (*bytes + offset_into_cluster(s, guest_offset))
- >> BDRV_SECTOR_BITS;
- int avail_sectors = nb_clusters
- << (s->cluster_bits - BDRV_SECTOR_BITS);
- int alloc_n_start = offset_into_cluster(s, guest_offset)
- >> BDRV_SECTOR_BITS;
- int nb_sectors = MIN(requested_sectors, avail_sectors);
+ uint64_t requested_bytes = *bytes + offset_into_cluster(s, guest_offset);
+ int avail_bytes = MIN(INT_MAX, nb_clusters << s->cluster_bits);
+ int nb_bytes = MIN(requested_bytes, avail_bytes);
QCowL2Meta *old_m = *m;
*m = g_malloc0(sizeof(**m));
@@ -1227,23 +1219,21 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
.alloc_offset = alloc_cluster_offset,
.offset = start_of_cluster(s, guest_offset),
.nb_clusters = nb_clusters,
- .nb_available = nb_sectors,
.cow_start = {
.offset = 0,
- .nb_sectors = alloc_n_start,
+ .nb_bytes = offset_into_cluster(s, guest_offset),
},
.cow_end = {
- .offset = nb_sectors * BDRV_SECTOR_SIZE,
- .nb_sectors = avail_sectors - nb_sectors,
+ .offset = nb_bytes,
+ .nb_bytes = avail_bytes - nb_bytes,
},
};
qemu_co_queue_init(&(*m)->dependent_requests);
QLIST_INSERT_HEAD(&s->cluster_allocs, *m, next_in_flight);
*host_offset = alloc_cluster_offset + offset_into_cluster(s, guest_offset);
- *bytes = MIN(*bytes, (nb_sectors * BDRV_SECTOR_SIZE)
- - offset_into_cluster(s, guest_offset));
+ *bytes = MIN(*bytes, nb_bytes - offset_into_cluster(s, guest_offset));
assert(*bytes != 0);
return 1;
@@ -1275,7 +1265,8 @@ fail:
* Return 0 on success and -errno in error cases
*/
int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
- int *num, uint64_t *host_offset, QCowL2Meta **m)
+ unsigned int *bytes, uint64_t *host_offset,
+ QCowL2Meta **m)
{
BDRVQcow2State *s = bs->opaque;
uint64_t start, remaining;
@@ -1283,13 +1274,11 @@ int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
uint64_t cur_bytes;
int ret;
- trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset, *num);
-
- assert((offset & ~BDRV_SECTOR_MASK) == 0);
+ trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset, *bytes);
again:
start = offset;
- remaining = (uint64_t)*num << BDRV_SECTOR_BITS;
+ remaining = *bytes;
cluster_offset = 0;
*host_offset = 0;
cur_bytes = 0;
@@ -1375,8 +1364,8 @@ again:
}
}
- *num -= remaining >> BDRV_SECTOR_BITS;
- assert(*num > 0);
+ *bytes -= remaining;
+ assert(*bytes > 0);
assert(*host_offset != 0);
return 0;
diff --git a/block/qcow2.c b/block/qcow2.c
index 6f5fb810e4..4718f8250e 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -968,13 +968,22 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
if (s->crypt_method_header) {
if (bdrv_uses_whitelist() &&
s->crypt_method_header == QCOW_CRYPT_AES) {
- error_report("qcow2 built-in AES encryption is deprecated");
- error_printf("Support for it will be removed in a future release.\n"
- "You can use 'qemu-img convert' to switch to an\n"
- "unencrypted qcow2 image, or a LUKS raw image.\n");
+ error_setg(errp,
+ "Use of AES-CBC encrypted qcow2 images is no longer "
+ "supported in system emulators");
+ error_append_hint(errp,
+ "You can use 'qemu-img convert' to convert your "
+ "image to an alternative supported format, such "
+ "as unencrypted qcow2, or raw with the LUKS "
+ "format instead.\n");
+ ret = -ENOSYS;
+ goto fail;
}
bs->encrypted = 1;
+
+ /* Encryption works on a sector granularity */
+ bs->request_alignment = BDRV_SECTOR_SIZE;
}
s->l2_bits = s->cluster_bits - 3; /* L2 is always one cluster */
@@ -1331,16 +1340,20 @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs,
BDRVQcow2State *s = bs->opaque;
uint64_t cluster_offset;
int index_in_cluster, ret;
+ unsigned int bytes;
int64_t status = 0;
- *pnum = nb_sectors;
+ bytes = MIN(INT_MAX, nb_sectors * BDRV_SECTOR_SIZE);
qemu_co_mutex_lock(&s->lock);
- ret = qcow2_get_cluster_offset(bs, sector_num << 9, pnum, &cluster_offset);
+ ret = qcow2_get_cluster_offset(bs, sector_num << 9, &bytes,
+ &cluster_offset);
qemu_co_mutex_unlock(&s->lock);
if (ret < 0) {
return ret;
}
+ *pnum = bytes >> BDRV_SECTOR_BITS;
+
if (cluster_offset != 0 && ret != QCOW2_CLUSTER_COMPRESSED &&
!s->cipher) {
index_in_cluster = sector_num & (s->cluster_sectors - 1);
@@ -1358,28 +1371,34 @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs,
/* handle reading after the end of the backing file */
int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
- int64_t sector_num, int nb_sectors)
+ int64_t offset, int bytes)
{
+ uint64_t bs_size = bs->total_sectors * BDRV_SECTOR_SIZE;
int n1;
- if ((sector_num + nb_sectors) <= bs->total_sectors)
- return nb_sectors;
- if (sector_num >= bs->total_sectors)
+
+ if ((offset + bytes) <= bs_size) {
+ return bytes;
+ }
+
+ if (offset >= bs_size) {
n1 = 0;
- else
- n1 = bs->total_sectors - sector_num;
+ } else {
+ n1 = bs_size - offset;
+ }
- qemu_iovec_memset(qiov, 512 * n1, 0, 512 * (nb_sectors - n1));
+ qemu_iovec_memset(qiov, n1, 0, bytes - n1);
return n1;
}
-static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
- int remaining_sectors, QEMUIOVector *qiov)
+static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, QEMUIOVector *qiov,
+ int flags)
{
BDRVQcow2State *s = bs->opaque;
- int index_in_cluster, n1;
+ int offset_in_cluster, n1;
int ret;
- int cur_nr_sectors; /* number of sectors in current iteration */
+ unsigned int cur_bytes; /* number of bytes in current iteration */
uint64_t cluster_offset = 0;
uint64_t bytes_done = 0;
QEMUIOVector hd_qiov;
@@ -1389,26 +1408,24 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
qemu_co_mutex_lock(&s->lock);
- while (remaining_sectors != 0) {
+ while (bytes != 0) {
/* prepare next request */
- cur_nr_sectors = remaining_sectors;
+ cur_bytes = MIN(bytes, INT_MAX);
if (s->cipher) {
- cur_nr_sectors = MIN(cur_nr_sectors,
- QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors);
+ cur_bytes = MIN(cur_bytes,
+ QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
}
- ret = qcow2_get_cluster_offset(bs, sector_num << 9,
- &cur_nr_sectors, &cluster_offset);
+ ret = qcow2_get_cluster_offset(bs, offset, &cur_bytes, &cluster_offset);
if (ret < 0) {
goto fail;
}
- index_in_cluster = sector_num & (s->cluster_sectors - 1);
+ offset_in_cluster = offset_into_cluster(s, offset);
qemu_iovec_reset(&hd_qiov);
- qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
- cur_nr_sectors * 512);
+ qemu_iovec_concat(&hd_qiov, qiov, bytes_done, cur_bytes);
switch (ret) {
case QCOW2_CLUSTER_UNALLOCATED:
@@ -1416,18 +1433,17 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
if (bs->backing) {
/* read from the base image */
n1 = qcow2_backing_read1(bs->backing->bs, &hd_qiov,
- sector_num, cur_nr_sectors);
+ offset, cur_bytes);
if (n1 > 0) {
QEMUIOVector local_qiov;
qemu_iovec_init(&local_qiov, hd_qiov.niov);
- qemu_iovec_concat(&local_qiov, &hd_qiov, 0,
- n1 * BDRV_SECTOR_SIZE);
+ qemu_iovec_concat(&local_qiov, &hd_qiov, 0, n1);
BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
qemu_co_mutex_unlock(&s->lock);
- ret = bdrv_co_readv(bs->backing->bs, sector_num,
- n1, &local_qiov);
+ ret = bdrv_co_preadv(bs->backing->bs, offset, n1,
+ &local_qiov, 0);
qemu_co_mutex_lock(&s->lock);
qemu_iovec_destroy(&local_qiov);
@@ -1438,12 +1454,12 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
}
} else {
/* Note: in this case, no need to wait */
- qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+ qemu_iovec_memset(&hd_qiov, 0, 0, cur_bytes);
}
break;
case QCOW2_CLUSTER_ZERO:
- qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+ qemu_iovec_memset(&hd_qiov, 0, 0, cur_bytes);
break;
case QCOW2_CLUSTER_COMPRESSED:
@@ -1454,8 +1470,8 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
}
qemu_iovec_from_buf(&hd_qiov, 0,
- s->cluster_cache + index_in_cluster * 512,
- 512 * cur_nr_sectors);
+ s->cluster_cache + offset_in_cluster,
+ cur_bytes);
break;
case QCOW2_CLUSTER_NORMAL:
@@ -1482,34 +1498,34 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
}
}
- assert(cur_nr_sectors <=
- QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors);
+ assert(cur_bytes <= QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
qemu_iovec_reset(&hd_qiov);
- qemu_iovec_add(&hd_qiov, cluster_data,
- 512 * cur_nr_sectors);
+ qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes);
}
BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
qemu_co_mutex_unlock(&s->lock);
- ret = bdrv_co_readv(bs->file->bs,
- (cluster_offset >> 9) + index_in_cluster,
- cur_nr_sectors, &hd_qiov);
+ ret = bdrv_co_preadv(bs->file->bs,
+ cluster_offset + offset_in_cluster,
+ cur_bytes, &hd_qiov, 0);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
goto fail;
}
if (bs->encrypted) {
assert(s->cipher);
+ assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
+ assert((cur_bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
Error *err = NULL;
- if (qcow2_encrypt_sectors(s, sector_num, cluster_data,
- cluster_data, cur_nr_sectors, false,
- &err) < 0) {
+ if (qcow2_encrypt_sectors(s, offset >> BDRV_SECTOR_BITS,
+ cluster_data, cluster_data,
+ cur_bytes >> BDRV_SECTOR_BITS,
+ false, &err) < 0) {
error_free(err);
ret = -EIO;
goto fail;
}
- qemu_iovec_from_buf(qiov, bytes_done,
- cluster_data, 512 * cur_nr_sectors);
+ qemu_iovec_from_buf(qiov, bytes_done, cluster_data, cur_bytes);
}
break;
@@ -1519,9 +1535,9 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
goto fail;
}
- remaining_sectors -= cur_nr_sectors;
- sector_num += cur_nr_sectors;
- bytes_done += cur_nr_sectors * 512;
+ bytes -= cur_bytes;
+ offset += cur_bytes;
+ bytes_done += cur_bytes;
}
ret = 0;
@@ -1534,23 +1550,21 @@ fail:
return ret;
}
-static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
- int64_t sector_num,
- int remaining_sectors,
- QEMUIOVector *qiov)
+static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, QEMUIOVector *qiov,
+ int flags)
{
BDRVQcow2State *s = bs->opaque;
- int index_in_cluster;
+ int offset_in_cluster;
int ret;
- int cur_nr_sectors; /* number of sectors in current iteration */
+ unsigned int cur_bytes; /* number of sectors in current iteration */
uint64_t cluster_offset;
QEMUIOVector hd_qiov;
uint64_t bytes_done = 0;
uint8_t *cluster_data = NULL;
QCowL2Meta *l2meta = NULL;
- trace_qcow2_writev_start_req(qemu_coroutine_self(), sector_num,
- remaining_sectors);
+ trace_qcow2_writev_start_req(qemu_coroutine_self(), offset, bytes);
qemu_iovec_init(&hd_qiov, qiov->niov);
@@ -1558,22 +1572,21 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
qemu_co_mutex_lock(&s->lock);
- while (remaining_sectors != 0) {
+ while (bytes != 0) {
l2meta = NULL;
trace_qcow2_writev_start_part(qemu_coroutine_self());
- index_in_cluster = sector_num & (s->cluster_sectors - 1);
- cur_nr_sectors = remaining_sectors;
- if (bs->encrypted &&
- cur_nr_sectors >
- QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors - index_in_cluster) {
- cur_nr_sectors =
- QCOW_MAX_CRYPT_CLUSTERS * s->cluster_sectors - index_in_cluster;
+ offset_in_cluster = offset_into_cluster(s, offset);
+ cur_bytes = MIN(bytes, INT_MAX);
+ if (bs->encrypted) {
+ cur_bytes = MIN(cur_bytes,
+ QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size
+ - offset_in_cluster);
}
- ret = qcow2_alloc_cluster_offset(bs, sector_num << 9,
- &cur_nr_sectors, &cluster_offset, &l2meta);
+ ret = qcow2_alloc_cluster_offset(bs, offset, &cur_bytes,
+ &cluster_offset, &l2meta);
if (ret < 0) {
goto fail;
}
@@ -1581,8 +1594,7 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
assert((cluster_offset & 511) == 0);
qemu_iovec_reset(&hd_qiov);
- qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
- cur_nr_sectors * 512);
+ qemu_iovec_concat(&hd_qiov, qiov, bytes_done, cur_bytes);
if (bs->encrypted) {
Error *err = NULL;
@@ -1601,8 +1613,9 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
qemu_iovec_to_buf(&hd_qiov, 0, cluster_data, hd_qiov.size);
- if (qcow2_encrypt_sectors(s, sector_num, cluster_data,
- cluster_data, cur_nr_sectors,
+ if (qcow2_encrypt_sectors(s, offset >> BDRV_SECTOR_BITS,
+ cluster_data, cluster_data,
+ cur_bytes >>BDRV_SECTOR_BITS,
true, &err) < 0) {
error_free(err);
ret = -EIO;
@@ -1610,13 +1623,11 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
}
qemu_iovec_reset(&hd_qiov);
- qemu_iovec_add(&hd_qiov, cluster_data,
- cur_nr_sectors * 512);
+ qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes);
}
ret = qcow2_pre_write_overlap_check(bs, 0,
- cluster_offset + index_in_cluster * BDRV_SECTOR_SIZE,
- cur_nr_sectors * BDRV_SECTOR_SIZE);
+ cluster_offset + offset_in_cluster, cur_bytes);
if (ret < 0) {
goto fail;
}
@@ -1624,10 +1635,10 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
qemu_co_mutex_unlock(&s->lock);
BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
trace_qcow2_writev_data(qemu_coroutine_self(),
- (cluster_offset >> 9) + index_in_cluster);
- ret = bdrv_co_writev(bs->file->bs,
- (cluster_offset >> 9) + index_in_cluster,
- cur_nr_sectors, &hd_qiov);
+ cluster_offset + offset_in_cluster);
+ ret = bdrv_co_pwritev(bs->file->bs,
+ cluster_offset + offset_in_cluster,
+ cur_bytes, &hd_qiov, 0);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
goto fail;
@@ -1653,10 +1664,10 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
l2meta = next;
}
- remaining_sectors -= cur_nr_sectors;
- sector_num += cur_nr_sectors;
- bytes_done += cur_nr_sectors * 512;
- trace_qcow2_writev_done_part(qemu_coroutine_self(), cur_nr_sectors);
+ bytes -= cur_bytes;
+ offset += cur_bytes;
+ bytes_done += cur_bytes;
+ trace_qcow2_writev_done_part(qemu_coroutine_self(), cur_bytes);
}
ret = 0;
@@ -1998,19 +2009,19 @@ static int qcow2_change_backing_file(BlockDriverState *bs,
static int preallocate(BlockDriverState *bs)
{
- uint64_t nb_sectors;
+ uint64_t bytes;
uint64_t offset;
uint64_t host_offset = 0;
- int num;
+ unsigned int cur_bytes;
int ret;
QCowL2Meta *meta;
- nb_sectors = bdrv_nb_sectors(bs);
+ bytes = bdrv_getlength(bs);
offset = 0;
- while (nb_sectors) {
- num = MIN(nb_sectors, INT_MAX >> BDRV_SECTOR_BITS);
- ret = qcow2_alloc_cluster_offset(bs, offset, &num,
+ while (bytes) {
+ cur_bytes = MIN(bytes, INT_MAX);
+ ret = qcow2_alloc_cluster_offset(bs, offset, &cur_bytes,
&host_offset, &meta);
if (ret < 0) {
return ret;
@@ -2036,8 +2047,8 @@ static int preallocate(BlockDriverState *bs)
/* TODO Preallocate data if requested */
- nb_sectors -= num;
- offset += num << BDRV_SECTOR_BITS;
+ bytes -= cur_bytes;
+ offset += cur_bytes;
}
/*
@@ -2046,11 +2057,9 @@ static int preallocate(BlockDriverState *bs)
* EOF). Extend the image to the last allocated sector.
*/
if (host_offset != 0) {
- uint8_t buf[BDRV_SECTOR_SIZE];
- memset(buf, 0, BDRV_SECTOR_SIZE);
- ret = bdrv_write(bs->file->bs,
- (host_offset >> BDRV_SECTOR_BITS) + num - 1,
- buf, 1);
+ uint8_t data = 0;
+ ret = bdrv_pwrite(bs->file->bs, (host_offset + cur_bytes) - 1,
+ &data, 1);
if (ret < 0) {
return ret;
}
@@ -2435,7 +2444,7 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
if (head || tail) {
int64_t cl_start = (offset - head) >> BDRV_SECTOR_BITS;
uint64_t off;
- int nr;
+ unsigned int nr;
assert(head + count <= s->cluster_size);
@@ -2452,7 +2461,7 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
/* We can have new write after previous check */
offset = cl_start << BDRV_SECTOR_BITS;
count = s->cluster_size;
- nr = s->cluster_sectors;
+ nr = s->cluster_size;
ret = qcow2_get_cluster_offset(bs, offset, &nr, &off);
if (ret != QCOW2_CLUSTER_UNALLOCATED && ret != QCOW2_CLUSTER_ZERO) {
qemu_co_mutex_unlock(&s->lock);
@@ -2900,36 +2909,20 @@ static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
int64_t pos)
{
BDRVQcow2State *s = bs->opaque;
- int64_t total_sectors = bs->total_sectors;
- bool zero_beyond_eof = bs->zero_beyond_eof;
- int ret;
BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_SAVE);
- bs->zero_beyond_eof = false;
- ret = bdrv_pwritev(bs, qcow2_vm_state_offset(s) + pos, qiov);
- bs->zero_beyond_eof = zero_beyond_eof;
-
- /* bdrv_co_do_writev will have increased the total_sectors value to include
- * the VM state - the VM state is however not an actual part of the block
- * device, therefore, we need to restore the old value. */
- bs->total_sectors = total_sectors;
-
- return ret;
+ return bs->drv->bdrv_co_pwritev(bs, qcow2_vm_state_offset(s) + pos,
+ qiov->size, qiov, 0);
}
-static int qcow2_load_vmstate(BlockDriverState *bs, uint8_t *buf,
- int64_t pos, int size)
+static int qcow2_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
+ int64_t pos)
{
BDRVQcow2State *s = bs->opaque;
- bool zero_beyond_eof = bs->zero_beyond_eof;
- int ret;
BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_LOAD);
- bs->zero_beyond_eof = false;
- ret = bdrv_pread(bs, qcow2_vm_state_offset(s) + pos, buf, size);
- bs->zero_beyond_eof = zero_beyond_eof;
-
- return ret;
+ return bs->drv->bdrv_co_preadv(bs, qcow2_vm_state_offset(s) + pos,
+ qiov->size, qiov, 0);
}
/*
@@ -3368,8 +3361,8 @@ BlockDriver bdrv_qcow2 = {
.bdrv_co_get_block_status = qcow2_co_get_block_status,
.bdrv_set_key = qcow2_set_key,
- .bdrv_co_readv = qcow2_co_readv,
- .bdrv_co_writev = qcow2_co_writev,
+ .bdrv_co_preadv = qcow2_co_preadv,
+ .bdrv_co_pwritev = qcow2_co_pwritev,
.bdrv_co_flush_to_os = qcow2_co_flush_to_os,
.bdrv_co_pwrite_zeroes = qcow2_co_pwrite_zeroes,
diff --git a/block/qcow2.h b/block/qcow2.h
index 7db9795d44..b36a7bf8ad 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -302,8 +302,8 @@ typedef struct Qcow2COWRegion {
*/
uint64_t offset;
- /** Number of sectors to copy */
- int nb_sectors;
+ /** Number of bytes to copy */
+ int nb_bytes;
} Qcow2COWRegion;
/**
@@ -318,12 +318,6 @@ typedef struct QCowL2Meta
/** Host offset of the first newly allocated cluster */
uint64_t alloc_offset;
- /**
- * Number of sectors from the start of the first allocated cluster to
- * the end of the (possibly shortened) request
- */
- int nb_available;
-
/** Number of newly allocated clusters */
int nb_clusters;
@@ -471,8 +465,7 @@ static inline uint64_t l2meta_cow_start(QCowL2Meta *m)
static inline uint64_t l2meta_cow_end(QCowL2Meta *m)
{
- return m->offset + m->cow_end.offset
- + (m->cow_end.nb_sectors << BDRV_SECTOR_BITS);
+ return m->offset + m->cow_end.offset + m->cow_end.nb_bytes;
}
static inline uint64_t refcount_diff(uint64_t r1, uint64_t r2)
@@ -544,9 +537,10 @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
int nb_sectors, bool enc, Error **errp);
int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
- int *num, uint64_t *cluster_offset);
+ unsigned int *bytes, uint64_t *cluster_offset);
int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
- int *num, uint64_t *host_offset, QCowL2Meta **m);
+ unsigned int *bytes, uint64_t *host_offset,
+ QCowL2Meta **m);
uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
uint64_t offset,
int compressed_size);
diff --git a/block/raw-aio.h b/block/raw-aio.h
index 714714e016..a4cdbbf1b7 100644
--- a/block/raw-aio.h
+++ b/block/raw-aio.h
@@ -15,6 +15,7 @@
#ifndef QEMU_RAW_AIO_H
#define QEMU_RAW_AIO_H
+#include "qemu/coroutine.h"
#include "qemu/iov.h"
/* AIO request types */
@@ -38,6 +39,8 @@
typedef struct LinuxAioState LinuxAioState;
LinuxAioState *laio_init(void);
void laio_cleanup(LinuxAioState *s);
+int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
+ uint64_t offset, QEMUIOVector *qiov, int type);
BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque, int type);
diff --git a/block/raw-posix.c b/block/raw-posix.c
index ce2e20f203..aacf13203f 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -1325,14 +1325,13 @@ static BlockAIOCB *paio_submit(BlockDriverState *bs, int fd,
return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
}
-static BlockAIOCB *raw_aio_submit(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque, int type)
+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 NULL;
+ return -EIO;
/*
* Check if the underlying device requires requests to be aligned,
@@ -1345,14 +1344,28 @@ static BlockAIOCB *raw_aio_submit(BlockDriverState *bs,
type |= QEMU_AIO_MISALIGNED;
#ifdef CONFIG_LINUX_AIO
} else if (s->use_aio) {
- return laio_submit(bs, s->aio_ctx, s->fd, sector_num, qiov,
- nb_sectors, cb, opaque, type);
+ assert(qiov->size == bytes);
+ return laio_co_submit(bs, s->aio_ctx, s->fd, offset, qiov, type);
#endif
}
}
- return paio_submit(bs, s->fd, sector_num, qiov, nb_sectors,
- cb, opaque, type);
+ 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)
@@ -1375,22 +1388,6 @@ static void raw_aio_unplug(BlockDriverState *bs)
#endif
}
-static BlockAIOCB *raw_aio_readv(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque)
-{
- return raw_aio_submit(bs, sector_num, qiov, nb_sectors,
- cb, opaque, QEMU_AIO_READ);
-}
-
-static BlockAIOCB *raw_aio_writev(BlockDriverState *bs,
- int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
- BlockCompletionFunc *cb, void *opaque)
-{
- return raw_aio_submit(bs, sector_num, qiov, nb_sectors,
- cb, opaque, QEMU_AIO_WRITE);
-}
-
static BlockAIOCB *raw_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque)
{
@@ -1957,8 +1954,8 @@ BlockDriver bdrv_file = {
.bdrv_co_get_block_status = raw_co_get_block_status,
.bdrv_co_pwrite_zeroes = raw_co_pwrite_zeroes,
- .bdrv_aio_readv = raw_aio_readv,
- .bdrv_aio_writev = raw_aio_writev,
+ .bdrv_co_preadv = raw_co_preadv,
+ .bdrv_co_pwritev = raw_co_pwritev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_aio_discard = raw_aio_discard,
.bdrv_refresh_limits = raw_refresh_limits,
@@ -2405,8 +2402,8 @@ static BlockDriver bdrv_host_device = {
.create_opts = &raw_create_opts,
.bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes,
- .bdrv_aio_readv = raw_aio_readv,
- .bdrv_aio_writev = raw_aio_writev,
+ .bdrv_co_preadv = raw_co_preadv,
+ .bdrv_co_pwritev = raw_co_pwritev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_aio_discard = hdev_aio_discard,
.bdrv_refresh_limits = raw_refresh_limits,
@@ -2535,8 +2532,9 @@ static BlockDriver bdrv_host_cdrom = {
.bdrv_create = hdev_create,
.create_opts = &raw_create_opts,
- .bdrv_aio_readv = raw_aio_readv,
- .bdrv_aio_writev = raw_aio_writev,
+
+ .bdrv_co_preadv = raw_co_preadv,
+ .bdrv_co_pwritev = raw_co_pwritev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_refresh_limits = raw_refresh_limits,
.bdrv_io_plug = raw_aio_plug,
@@ -2670,8 +2668,8 @@ static BlockDriver bdrv_host_cdrom = {
.bdrv_create = hdev_create,
.create_opts = &raw_create_opts,
- .bdrv_aio_readv = raw_aio_readv,
- .bdrv_aio_writev = raw_aio_writev,
+ .bdrv_co_preadv = raw_co_preadv,
+ .bdrv_co_pwritev = raw_co_pwritev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_refresh_limits = raw_refresh_limits,
.bdrv_io_plug = raw_aio_plug,
diff --git a/block/rbd.c b/block/rbd.c
index 5bc5b32530..5226b6fef8 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -290,7 +290,8 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
if (only_read_conf_file) {
ret = rados_conf_read_file(cluster, value);
if (ret < 0) {
- error_setg(errp, "error reading conf file %s", value);
+ error_setg_errno(errp, -ret, "error reading conf file %s",
+ value);
break;
}
}
@@ -299,7 +300,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
} else if (!only_read_conf_file) {
ret = rados_conf_set(cluster, name, value);
if (ret < 0) {
- error_setg(errp, "invalid conf option %s", name);
+ error_setg_errno(errp, -ret, "invalid conf option %s", name);
ret = -EINVAL;
break;
}
@@ -354,9 +355,10 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
}
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
- if (rados_create(&cluster, clientname) < 0) {
- error_setg(errp, "error initializing");
- return -EIO;
+ ret = rados_create(&cluster, clientname);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error initializing");
+ return ret;
}
if (strstr(conf, "conf=") == NULL) {
@@ -381,21 +383,27 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
return -EIO;
}
- if (rados_connect(cluster) < 0) {
- error_setg(errp, "error connecting");
+ ret = rados_connect(cluster);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error connecting");
rados_shutdown(cluster);
- return -EIO;
+ return ret;
}
- if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
- error_setg(errp, "error opening pool %s", pool);
+ ret = rados_ioctx_create(cluster, pool, &io_ctx);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error opening pool %s", pool);
rados_shutdown(cluster);
- return -EIO;
+ return ret;
}
ret = rbd_create(io_ctx, name, bytes, &obj_order);
rados_ioctx_destroy(io_ctx);
rados_shutdown(cluster);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "error rbd create");
+ return ret;
+ }
return ret;
}
@@ -500,7 +508,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
r = rados_create(&s->cluster, clientname);
if (r < 0) {
- error_setg(errp, "error initializing");
+ error_setg_errno(errp, -r, "error initializing");
goto failed_opts;
}
@@ -546,19 +554,19 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
r = rados_connect(s->cluster);
if (r < 0) {
- error_setg(errp, "error connecting");
+ error_setg_errno(errp, -r, "error connecting");
goto failed_shutdown;
}
r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
if (r < 0) {
- error_setg(errp, "error opening pool %s", pool);
+ error_setg_errno(errp, -r, "error opening pool %s", pool);
goto failed_shutdown;
}
r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
if (r < 0) {
- error_setg(errp, "error reading header from %s", s->name);
+ error_setg_errno(errp, -r, "error reading header from %s", s->name);
goto failed_open;
}
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 23fbace1f9..ef5d044ab9 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -2784,12 +2784,19 @@ static int sd_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
return ret;
}
-static int sd_load_vmstate(BlockDriverState *bs, uint8_t *data,
- int64_t pos, int size)
+static int sd_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
+ int64_t pos)
{
BDRVSheepdogState *s = bs->opaque;
+ void *buf;
+ int ret;
- return do_load_save_vmstate(s, data, pos, size, 1);
+ buf = qemu_blockalign(bs, qiov->size);
+ ret = do_load_save_vmstate(s, buf, pos, qiov->size, 1);
+ qemu_iovec_from_buf(qiov, 0, buf, qiov->size);
+ qemu_vfree(buf);
+
+ return ret;
}
generated by cgit v1.2.3 (git 2.26.2) at 2025-01-13 08:12:32 +0000