summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--block.c53
-rw-r--r--block.h8
-rw-r--r--block_int.h8
-rw-r--r--trace-events1
4 files changed, 64 insertions, 6 deletions
diff --git a/block.c b/block.c
index 3621d11de0..c9fa5c17ff 100644
--- a/block.c
+++ b/block.c
@@ -50,6 +50,7 @@
typedef enum {
BDRV_REQ_COPY_ON_READ = 0x1,
+ BDRV_REQ_ZERO_WRITE = 0x2,
} BdrvRequestFlags;
static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load);
@@ -69,7 +70,8 @@ static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
BdrvRequestFlags flags);
static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
+ BdrvRequestFlags flags);
static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
@@ -1300,7 +1302,7 @@ static void coroutine_fn bdrv_rw_co_entry(void *opaque)
rwco->nb_sectors, rwco->qiov, 0);
} else {
rwco->ret = bdrv_co_do_writev(rwco->bs, rwco->sector_num,
- rwco->nb_sectors, rwco->qiov);
+ rwco->nb_sectors, rwco->qiov, 0);
}
}
@@ -1639,11 +1641,37 @@ int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
BDRV_REQ_COPY_ON_READ);
}
+static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors)
+{
+ BlockDriver *drv = bs->drv;
+ QEMUIOVector qiov;
+ struct iovec iov;
+ int ret;
+
+ /* First try the efficient write zeroes operation */
+ if (drv->bdrv_co_write_zeroes) {
+ return drv->bdrv_co_write_zeroes(bs, sector_num, nb_sectors);
+ }
+
+ /* Fall back to bounce buffer if write zeroes is unsupported */
+ iov.iov_len = nb_sectors * BDRV_SECTOR_SIZE;
+ iov.iov_base = qemu_blockalign(bs, iov.iov_len);
+ memset(iov.iov_base, 0, iov.iov_len);
+ qemu_iovec_init_external(&qiov, &iov, 1);
+
+ ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, &qiov);
+
+ qemu_vfree(iov.iov_base);
+ return ret;
+}
+
/*
* Handle a write request in coroutine context
*/
static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+ int64_t sector_num, int nb_sectors, QEMUIOVector *qiov,
+ BdrvRequestFlags flags)
{
BlockDriver *drv = bs->drv;
BdrvTrackedRequest req;
@@ -1670,7 +1698,11 @@ static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs,
tracked_request_begin(&req, bs, sector_num, nb_sectors, true);
- ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
+ if (flags & BDRV_REQ_ZERO_WRITE) {
+ ret = bdrv_co_do_write_zeroes(bs, sector_num, nb_sectors);
+ } else {
+ ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
+ }
if (bs->dirty_bitmap) {
set_dirty_bitmap(bs, sector_num, nb_sectors, 1);
@@ -1690,7 +1722,16 @@ int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
{
trace_bdrv_co_writev(bs, sector_num, nb_sectors);
- return bdrv_co_do_writev(bs, sector_num, nb_sectors, qiov);
+ return bdrv_co_do_writev(bs, sector_num, nb_sectors, qiov, 0);
+}
+
+int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors)
+{
+ trace_bdrv_co_write_zeroes(bs, sector_num, nb_sectors);
+
+ return bdrv_co_do_writev(bs, sector_num, nb_sectors, NULL,
+ BDRV_REQ_ZERO_WRITE);
}
/**
@@ -3192,7 +3233,7 @@ static void coroutine_fn bdrv_co_do_rw(void *opaque)
acb->req.nb_sectors, acb->req.qiov, 0);
} else {
acb->req.error = bdrv_co_do_writev(bs, acb->req.sector,
- acb->req.nb_sectors, acb->req.qiov);
+ acb->req.nb_sectors, acb->req.qiov, 0);
}
acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
diff --git a/block.h b/block.h
index cae289b2fb..60ea7308c6 100644
--- a/block.h
+++ b/block.h
@@ -146,6 +146,14 @@ int coroutine_fn bdrv_co_copy_on_readv(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov);
+/*
+ * Efficiently zero a region of the disk image. Note that this is a regular
+ * I/O request like read or write and should have a reasonable size. This
+ * function is not suitable for zeroing the entire image in a single request
+ * because it may allocate memory for the entire region.
+ */
+int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
+ int nb_sectors);
int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, int *pnum);
BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
diff --git a/block_int.h b/block_int.h
index 7be2988ca7..7946cf66a1 100644
--- a/block_int.h
+++ b/block_int.h
@@ -131,6 +131,14 @@ struct BlockDriver {
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
+ /*
+ * Efficiently zero a region of the disk image. Typically an image format
+ * would use a compact metadata representation to implement this. This
+ * function pointer may be NULL and .bdrv_co_writev() will be called
+ * instead.
+ */
+ int coroutine_fn (*bdrv_co_write_zeroes)(BlockDriverState *bs,
+ int64_t sector_num, int nb_sectors);
int coroutine_fn (*bdrv_co_discard)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors);
int coroutine_fn (*bdrv_co_is_allocated)(BlockDriverState *bs,
diff --git a/trace-events b/trace-events
index 5d05749643..3372087ed9 100644
--- a/trace-events
+++ b/trace-events
@@ -67,6 +67,7 @@ bdrv_lock_medium(void *bs, bool locked) "bs %p locked %d"
bdrv_co_readv(void *bs, int64_t sector_num, int nb_sector) "bs %p sector_num %"PRId64" nb_sectors %d"
bdrv_co_copy_on_readv(void *bs, int64_t sector_num, int nb_sector) "bs %p sector_num %"PRId64" nb_sectors %d"
bdrv_co_writev(void *bs, int64_t sector_num, int nb_sector) "bs %p sector_num %"PRId64" nb_sectors %d"
+bdrv_co_write_zeroes(void *bs, int64_t sector_num, int nb_sector) "bs %p sector_num %"PRId64" nb_sectors %d"
bdrv_co_io_em(void *bs, int64_t sector_num, int nb_sectors, int is_write, void *acb) "bs %p sector_num %"PRId64" nb_sectors %d is_write %d acb %p"
bdrv_co_do_copy_on_readv(void *bs, int64_t sector_num, int nb_sectors, int64_t cluster_sector_num, int cluster_nb_sectors) "bs %p sector_num %"PRId64" nb_sectors %d cluster_sector_num %"PRId64" cluster_nb_sectors %d"
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-07-17 21:03:07 +0200