The following changes since commit fc3dbb90f2eb069801bfb4cfe9cbc83cf9c5f4a9: Merge remote-tracking branch 'remotes/jnsnow/tags/bitmaps-pull-request' into staging (2019-02-21 13:09:33 +0000) are available in the Git repository at: git://github.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to 9a9f4b74fa547b68edb38fa414999836770a4735: tests/virtio-blk: add test for DISCARD command (2019-02-22 09:42:17 +0000) ---------------------------------------------------------------- Pull request ---------------------------------------------------------------- Stefano Garzarella (10): virtio-blk: add acct_failed param to virtio_blk_handle_rw_error() virtio-blk: add host_features field in VirtIOBlock virtio-blk: add "discard" and "write-zeroes" properties virtio-net: make VirtIOFeature usable for other virtio devices virtio-blk: set config size depending on the features enabled virtio-blk: add DISCARD and WRITE_ZEROES features tests/virtio-blk: change assert on data_size in virtio_blk_request() tests/virtio-blk: add virtio_blk_fix_dwz_hdr() function tests/virtio-blk: add test for WRITE_ZEROES command tests/virtio-blk: add test for DISCARD command Vladimir Sementsov-Ogievskiy (17): block: enhance QEMUIOVector structure block/io: use qemu_iovec_init_buf block/block-backend: use QEMU_IOVEC_INIT_BUF block/backup: use qemu_iovec_init_buf block/commit: use QEMU_IOVEC_INIT_BUF block/stream: use QEMU_IOVEC_INIT_BUF block/parallels: use QEMU_IOVEC_INIT_BUF block/qcow: use qemu_iovec_init_buf block/qcow2: use qemu_iovec_init_buf block/qed: use qemu_iovec_init_buf block/vmdk: use qemu_iovec_init_buf qemu-img: use qemu_iovec_init_buf migration/block: use qemu_iovec_init_buf tests/test-bdrv-drain: use QEMU_IOVEC_INIT_BUF hw/ide: drop iov field from IDEState hw/ide: drop iov field from IDEBufferedRequest hw/ide: drop iov field from IDEDMA include/hw/ide/internal.h | 3 - include/hw/virtio/virtio-blk.h | 6 +- include/hw/virtio/virtio.h | 15 ++ include/qemu/iov.h | 64 ++++++++- block/backup.c | 5 +- block/block-backend.c | 13 +- block/commit.c | 7 +- block/io.c | 89 +++--------- block/parallels.c | 13 +- block/qcow.c | 21 +-- block/qcow2.c | 12 +- block/qed-table.c | 16 +-- block/qed.c | 31 ++--- block/stream.c | 7 +- block/vmdk.c | 7 +- hw/block/virtio-blk.c | 245 ++++++++++++++++++++++++++++++--- hw/core/machine.c | 2 + hw/ide/atapi.c | 14 +- hw/ide/core.c | 19 ++- hw/net/virtio-net.c | 31 +---- hw/virtio/virtio.c | 15 ++ migration/block.c | 10 +- qemu-img.c | 10 +- tests/test-bdrv-drain.c | 29 +--- tests/virtio-blk-test.c | 127 ++++++++++++++++- 25 files changed, 525 insertions(+), 286 deletions(-) -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Add a possibility of embedded iovec, for cases when we need only one local iov. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20190218140926.333779-2-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-2-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/iov.h | 64 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 62 insertions(+), 2 deletions(-) diff --git a/include/qemu/iov.h b/include/qemu/iov.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/iov.h +++ b/include/qemu/iov.h @@ -XXX,XX +XXX,XX @@ size_t iov_discard_back(struct iovec *iov, unsigned int *iov_cnt, typedef struct QEMUIOVector { struct iovec *iov; int niov; - int nalloc; - size_t size; + + /* + * For external @iov (qemu_iovec_init_external()) or allocated @iov + * (qemu_iovec_init()), @size is the cumulative size of iovecs and + * @local_iov is invalid and unused. + * + * For embedded @iov (QEMU_IOVEC_INIT_BUF() or qemu_iovec_init_buf()), + * @iov is equal to &@local_iov, and @size is valid, as it has same + * offset and type as @local_iov.iov_len, which is guaranteed by + * static assertion below. + * + * @nalloc is always valid and is -1 both for embedded and external + * cases. It is included in the union only to ensure the padding prior + * to the @size field will not result in a 0-length array. + */ + union { + struct { + int nalloc; + struct iovec local_iov; + }; + struct { + char __pad[sizeof(int) + offsetof(struct iovec, iov_len)]; + size_t size; + }; + }; } QEMUIOVector; +QEMU_BUILD_BUG_ON(offsetof(QEMUIOVector, size) != + offsetof(QEMUIOVector, local_iov.iov_len)); + +#define QEMU_IOVEC_INIT_BUF(self, buf, len) \ +{ \ + .iov = &(self).local_iov, \ + .niov = 1, \ + .nalloc = -1, \ + .local_iov = { \ + .iov_base = (void *)(buf), /* cast away const */ \ + .iov_len = (len), \ + }, \ +} + +/* + * qemu_iovec_init_buf + * + * Initialize embedded QEMUIOVector. + * + * Note: "const" is used over @buf pointer to make it simple to pass + * const pointers, appearing in read functions. Then this "const" is + * cast away by QEMU_IOVEC_INIT_BUF(). + */ +static inline void qemu_iovec_init_buf(QEMUIOVector *qiov, + const void *buf, size_t len) +{ + *qiov = (QEMUIOVector) QEMU_IOVEC_INIT_BUF(*qiov, buf, len); +} + +static inline void *qemu_iovec_buf(QEMUIOVector *qiov) +{ + /* Only supports embedded iov */ + assert(qiov->nalloc == -1 && qiov->iov == &qiov->local_iov); + + return qiov->local_iov.iov_base; +} + void qemu_iovec_init(QEMUIOVector *qiov, int alloc_hint); void qemu_iovec_init_external(QEMUIOVector *qiov, struct iovec *iov, int niov); void qemu_iovec_add(QEMUIOVector *qiov, void *base, size_t len); -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. While being here, use qemu_try_blockalign0 as well. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-3-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-3-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 89 ++++++++++++------------------------------------------ 1 file changed, 20 insertions(+), 69 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int bdrv_prwv_co(BdrvChild *child, int64_t offset, static int bdrv_rw_co(BdrvChild *child, int64_t sector_num, uint8_t *buf, int nb_sectors, bool is_write, BdrvRequestFlags flags) { - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = (void *)buf, - .iov_len = nb_sectors * BDRV_SECTOR_SIZE, - }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, + nb_sectors * BDRV_SECTOR_SIZE); if (nb_sectors < 0 || nb_sectors > BDRV_REQUEST_MAX_SECTORS) { return -EINVAL; } - qemu_iovec_init_external(&qiov, &iov, 1); return bdrv_prwv_co(child, sector_num << BDRV_SECTOR_BITS, &qiov, is_write, flags); } @@ -XXX,XX +XXX,XX @@ int bdrv_write(BdrvChild *child, int64_t sector_num, int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, int bytes, BdrvRequestFlags flags) { - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = NULL, - .iov_len = bytes, - }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, NULL, bytes); - qemu_iovec_init_external(&qiov, &iov, 1); return bdrv_prwv_co(child, offset, &qiov, true, BDRV_REQ_ZERO_WRITE | flags); } @@ -XXX,XX +XXX,XX @@ int bdrv_preadv(BdrvChild *child, int64_t offset, QEMUIOVector *qiov) int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int bytes) { - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = (void *)buf, - .iov_len = bytes, - }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); if (bytes < 0) { return -EINVAL; } - qemu_iovec_init_external(&qiov, &iov, 1); return bdrv_preadv(child, offset, &qiov); } @@ -XXX,XX +XXX,XX @@ int bdrv_pwritev(BdrvChild *child, int64_t offset, QEMUIOVector *qiov) int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, int bytes) { - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = (void *) buf, - .iov_len = bytes, - }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); if (bytes < 0) { return -EINVAL; } - qemu_iovec_init_external(&qiov, &iov, 1); return bdrv_pwritev(child, offset, &qiov); } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, void *bounce_buffer; BlockDriver *drv = bs->drv; - struct iovec iov; QEMUIOVector local_qiov; int64_t cluster_offset; int64_t cluster_bytes; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, if (ret <= 0) { /* Must copy-on-read; use the bounce buffer */ - iov.iov_base = bounce_buffer; - iov.iov_len = pnum = MIN(pnum, MAX_BOUNCE_BUFFER); - qemu_iovec_init_external(&local_qiov, &iov, 1); + pnum = MIN(pnum, MAX_BOUNCE_BUFFER); + qemu_iovec_init_buf(&local_qiov, bounce_buffer, pnum); ret = bdrv_driver_preadv(bs, cluster_offset, pnum, &local_qiov, 0); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, { BlockDriver *drv = bs->drv; QEMUIOVector qiov; - struct iovec iov = {0}; + void *buf = NULL; int ret = 0; bool need_flush = false; int head = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, need_flush = true; } num = MIN(num, max_transfer); - iov.iov_len = num; - if (iov.iov_base == NULL) { - iov.iov_base = qemu_try_blockalign(bs, num); - if (iov.iov_base == NULL) { + if (buf == NULL) { + buf = qemu_try_blockalign0(bs, num); + if (buf == NULL) { ret = -ENOMEM; goto fail; } - memset(iov.iov_base, 0, num); } - qemu_iovec_init_external(&qiov, &iov, 1); + qemu_iovec_init_buf(&qiov, buf, num); ret = bdrv_driver_pwritev(bs, offset, num, &qiov, write_flags); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, * all future requests. */ if (num < max_transfer) { - qemu_vfree(iov.iov_base); - iov.iov_base = NULL; + qemu_vfree(buf); + buf = NULL; } } @@ -XXX,XX +XXX,XX @@ fail: if (ret == 0 && need_flush) { ret = bdrv_co_flush(bs); } - qemu_vfree(iov.iov_base); + qemu_vfree(buf); return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child, BlockDriverState *bs = child->bs; uint8_t *buf = NULL; QEMUIOVector local_qiov; - struct iovec iov; uint64_t align = bs->bl.request_alignment; unsigned int head_padding_bytes, tail_padding_bytes; int ret = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child, assert(flags & BDRV_REQ_ZERO_WRITE); if (head_padding_bytes || tail_padding_bytes) { buf = qemu_blockalign(bs, align); - iov = (struct iovec) { - .iov_base = buf, - .iov_len = align, - }; - qemu_iovec_init_external(&local_qiov, &iov, 1); + qemu_iovec_init_buf(&local_qiov, buf, align); } if (head_padding_bytes) { uint64_t zero_bytes = MIN(bytes, align - head_padding_bytes); @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child, if (offset & (align - 1)) { QEMUIOVector head_qiov; - struct iovec head_iov; mark_request_serialising(&req, align); wait_serialising_requests(&req); head_buf = qemu_blockalign(bs, align); - head_iov = (struct iovec) { - .iov_base = head_buf, - .iov_len = align, - }; - qemu_iovec_init_external(&head_qiov, &head_iov, 1); + qemu_iovec_init_buf(&head_qiov, head_buf, align); bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD); ret = bdrv_aligned_preadv(child, &req, offset & ~(align - 1), align, @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child, if ((offset + bytes) & (align - 1)) { QEMUIOVector tail_qiov; - struct iovec tail_iov; size_t tail_bytes; bool waited; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child, assert(!waited || !use_local_qiov); tail_buf = qemu_blockalign(bs, align); - tail_iov = (struct iovec) { - .iov_base = tail_buf, - .iov_len = align, - }; - qemu_iovec_init_external(&tail_qiov, &tail_iov, 1); + qemu_iovec_init_buf(&tail_qiov, tail_buf, align); bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL); ret = bdrv_aligned_preadv(child, &req, (offset + bytes) & ~(align - 1), @@ -XXX,XX +XXX,XX @@ bdrv_rw_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos, int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf, int64_t pos, int size) { - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = (void *) buf, - .iov_len = size, - }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size); int ret; - qemu_iovec_init_external(&qiov, &iov, 1); - ret = bdrv_writev_vmstate(bs, &qiov, pos); if (ret < 0) { return ret; @@ -XXX,XX +XXX,XX @@ int bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t 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, - }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, size); int ret; - qemu_iovec_init_external(&qiov, &iov, 1); ret = bdrv_readv_vmstate(bs, &qiov, pos); if (ret < 0) { return ret; -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new QEMU_IOVEC_INIT_BUF() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-4-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-4-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/block-backend.c | 13 ++----------- 1 file changed, 2 insertions(+), 11 deletions(-) diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf, int64_t bytes, CoroutineEntry co_entry, BdrvRequestFlags flags) { - QEMUIOVector qiov; - struct iovec iov; - BlkRwCo rwco; - - iov = (struct iovec) { - .iov_base = buf, - .iov_len = bytes, - }; - qemu_iovec_init_external(&qiov, &iov, 1); - - rwco = (BlkRwCo) { + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); + BlkRwCo rwco = { .blk = blk, .offset = offset, .iobuf = &qiov, -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-5-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-5-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/backup.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_cow_with_bounce_buffer(BackupBlockJob *job, void **bounce_buffer) { int ret; - struct iovec iov; QEMUIOVector qiov; BlockBackend *blk = job->common.blk; int nbytes; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_cow_with_bounce_buffer(BackupBlockJob *job, if (!*bounce_buffer) { *bounce_buffer = blk_blockalign(blk, job->cluster_size); } - iov.iov_base = *bounce_buffer; - iov.iov_len = nbytes; - qemu_iovec_init_external(&qiov, &iov, 1); + qemu_iovec_init_buf(&qiov, *bounce_buffer, nbytes); ret = blk_co_preadv(blk, start, qiov.size, &qiov, read_flags); if (ret < 0) { -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new QEMU_IOVEC_INIT_BUF() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-6-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-6-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/commit.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_populate(BlockBackend *bs, BlockBackend *base, void *buf) { int ret = 0; - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = buf, - .iov_len = bytes, - }; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); assert(bytes < SIZE_MAX); - qemu_iovec_init_external(&qiov, &iov, 1); ret = blk_co_preadv(bs, offset, qiov.size, &qiov, 0); if (ret < 0) { -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new QEMU_IOVEC_INIT_BUF() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-7-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-7-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/stream.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/block/stream.c b/block/stream.c index XXXXXXX..XXXXXXX 100644 --- a/block/stream.c +++ b/block/stream.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn stream_populate(BlockBackend *blk, int64_t offset, uint64_t bytes, void *buf) { - struct iovec iov = { - .iov_base = buf, - .iov_len = bytes, - }; - QEMUIOVector qiov; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes); assert(bytes < SIZE_MAX); - qemu_iovec_init_external(&qiov, &iov, 1); /* Copy-on-read the unallocated clusters */ return blk_co_preadv(blk, offset, qiov.size, &qiov, BDRV_REQ_COPY_ON_READ); -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new QEMU_IOVEC_INIT_BUF() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-8-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-8-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/parallels.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num, if (bs->backing) { int64_t nb_cow_sectors = to_allocate * s->tracks; int64_t nb_cow_bytes = nb_cow_sectors << BDRV_SECTOR_BITS; - QEMUIOVector qiov; - struct iovec iov = { - .iov_len = nb_cow_bytes, - .iov_base = qemu_blockalign(bs, nb_cow_bytes) - }; - qemu_iovec_init_external(&qiov, &iov, 1); + QEMUIOVector qiov = + QEMU_IOVEC_INIT_BUF(qiov, qemu_blockalign(bs, nb_cow_bytes), + nb_cow_bytes); ret = bdrv_co_preadv(bs->backing, idx * s->tracks * BDRV_SECTOR_SIZE, nb_cow_bytes, &qiov, 0); if (ret < 0) { - qemu_vfree(iov.iov_base); + qemu_vfree(qemu_iovec_buf(&qiov)); return ret; } ret = bdrv_co_pwritev(bs->file, s->data_end * BDRV_SECTOR_SIZE, nb_cow_bytes, &qiov, 0); - qemu_vfree(iov.iov_base); + qemu_vfree(qemu_iovec_buf(&qiov)); if (ret < 0) { return ret; } -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-9-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-9-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/qcow.c | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset, int offset_in_cluster; int ret = 0, n; uint64_t cluster_offset; - struct iovec hd_iov; QEMUIOVector hd_qiov; uint8_t *buf; void *orig_buf; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset, if (!cluster_offset) { if (bs->backing) { /* read from the base image */ - hd_iov.iov_base = (void *)buf; - hd_iov.iov_len = n; - qemu_iovec_init_external(&hd_qiov, &hd_iov, 1); + qemu_iovec_init_buf(&hd_qiov, buf, n); qemu_co_mutex_unlock(&s->lock); /* qcow2 emits this on bs->file instead of bs->backing */ BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset, ret = -EIO; break; } - hd_iov.iov_base = (void *)buf; - hd_iov.iov_len = n; - qemu_iovec_init_external(&hd_qiov, &hd_iov, 1); + qemu_iovec_init_buf(&hd_qiov, buf, n); qemu_co_mutex_unlock(&s->lock); BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); ret = bdrv_co_preadv(bs->file, cluster_offset + offset_in_cluster, @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow_co_pwritev(BlockDriverState *bs, uint64_t offset, int offset_in_cluster; uint64_t cluster_offset; int ret = 0, n; - struct iovec hd_iov; QEMUIOVector hd_qiov; uint8_t *buf; void *orig_buf; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow_co_pwritev(BlockDriverState *bs, uint64_t offset, } } - hd_iov.iov_base = (void *)buf; - hd_iov.iov_len = n; - qemu_iovec_init_external(&hd_qiov, &hd_iov, 1); + qemu_iovec_init_buf(&hd_qiov, buf, n); qemu_co_mutex_unlock(&s->lock); BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster, @@ -XXX,XX +XXX,XX @@ qcow_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, { BDRVQcowState *s = bs->opaque; QEMUIOVector hd_qiov; - struct iovec iov; z_stream strm; int ret, out_len; uint8_t *buf, *out_buf; @@ -XXX,XX +XXX,XX @@ qcow_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, } cluster_offset &= s->cluster_offset_mask; - iov = (struct iovec) { - .iov_base = out_buf, - .iov_len = out_len, - }; - qemu_iovec_init_external(&hd_qiov, &iov, 1); + qemu_iovec_init_buf(&hd_qiov, out_buf, out_len); BLKDBG_EVENT(bs->file, BLKDBG_WRITE_COMPRESSED); ret = bdrv_co_pwritev(bs->file, cluster_offset, out_len, &hd_qiov, 0); if (ret < 0) { -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-10-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-10-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/qcow2.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, { BDRVQcow2State *s = bs->opaque; QEMUIOVector hd_qiov; - struct iovec iov; int ret; size_t out_len; uint8_t *buf, *out_buf; @@ -XXX,XX +XXX,XX @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, goto fail; } - iov = (struct iovec) { - .iov_base = out_buf, - .iov_len = out_len, - }; - qemu_iovec_init_external(&hd_qiov, &iov, 1); + qemu_iovec_init_buf(&hd_qiov, out_buf, out_len); BLKDBG_EVENT(bs->file, BLKDBG_WRITE_COMPRESSED); ret = bdrv_co_pwritev(bs->file, cluster_offset, out_len, &hd_qiov, 0); @@ -XXX,XX +XXX,XX @@ qcow2_co_preadv_compressed(BlockDriverState *bs, int ret = 0, csize, nb_csectors; uint64_t coffset; uint8_t *buf, *out_buf; - struct iovec iov; QEMUIOVector local_qiov; int offset_in_cluster = offset_into_cluster(s, offset); @@ -XXX,XX +XXX,XX @@ qcow2_co_preadv_compressed(BlockDriverState *bs, if (!buf) { return -ENOMEM; } - iov.iov_base = buf; - iov.iov_len = csize; - qemu_iovec_init_external(&local_qiov, &iov, 1); + qemu_iovec_init_buf(&local_qiov, buf, csize); out_buf = qemu_blockalign(bs, s->cluster_size); -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-11-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-11-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/qed-table.c | 16 +++------------- block/qed.c | 31 +++++++++---------------------- 2 files changed, 12 insertions(+), 35 deletions(-) diff --git a/block/qed-table.c b/block/qed-table.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed-table.c +++ b/block/qed-table.c @@ -XXX,XX +XXX,XX @@ /* Called with table_lock held. */ static int qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table) { - QEMUIOVector qiov; + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF( + qiov, table->offsets, s->header.cluster_size * s->header.table_size); int noffsets; int i, ret; - struct iovec iov = { - .iov_base = table->offsets, - .iov_len = s->header.cluster_size * s->header.table_size, - }; - qemu_iovec_init_external(&qiov, &iov, 1); - trace_qed_read_table(s, offset, table); qemu_co_mutex_unlock(&s->table_lock); @@ -XXX,XX +XXX,XX @@ static int qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1; unsigned int start, end, i; QEDTable *new_table; - struct iovec iov; QEMUIOVector qiov; size_t len_bytes; int ret; @@ -XXX,XX +XXX,XX @@ static int qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, len_bytes = (end - start) * sizeof(uint64_t); new_table = qemu_blockalign(s->bs, len_bytes); - iov = (struct iovec) { - .iov_base = new_table->offsets, - .iov_len = len_bytes, - }; - qemu_iovec_init_external(&qiov, &iov, 1); + qemu_iovec_init_buf(&qiov, new_table->offsets, len_bytes); /* Byteswap table */ for (i = start; i < end; i++) { diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_write_header(BDRVQEDState *s) int nsectors = DIV_ROUND_UP(sizeof(QEDHeader), BDRV_SECTOR_SIZE); size_t len = nsectors * BDRV_SECTOR_SIZE; uint8_t *buf; - struct iovec iov; QEMUIOVector qiov; int ret; assert(s->allocating_acb || s->allocating_write_reqs_plugged); buf = qemu_blockalign(s->bs, len); - iov = (struct iovec) { - .iov_base = buf, - .iov_len = len, - }; - qemu_iovec_init_external(&qiov, &iov, 1); + qemu_iovec_init_buf(&qiov, buf, len); ret = bdrv_co_preadv(s->bs->file, 0, qiov.size, &qiov, 0); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s, { QEMUIOVector qiov; QEMUIOVector *backing_qiov = NULL; - struct iovec iov; int ret; /* Skip copy entirely if there is no work to do */ @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s, return 0; } - iov = (struct iovec) { - .iov_base = qemu_blockalign(s->bs, len), - .iov_len = len, - }; - qemu_iovec_init_external(&qiov, &iov, 1); + qemu_iovec_init_buf(&qiov, qemu_blockalign(s->bs, len), len); ret = qed_read_backing_file(s, pos, &qiov, &backing_qiov); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s, } ret = 0; out: - qemu_vfree(iov.iov_base); + qemu_vfree(qemu_iovec_buf(&qiov)); return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_pwrite_zeroes(BlockDriverState *bs, BdrvRequestFlags flags) { BDRVQEDState *s = bs->opaque; - QEMUIOVector qiov; - struct iovec iov; + + /* + * Zero writes start without an I/O buffer. If a buffer becomes necessary + * then it will be allocated during request processing. + */ + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, NULL, bytes); /* Fall back if the request is not aligned */ if (qed_offset_into_cluster(s, offset) || @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_pwrite_zeroes(BlockDriverState *bs, return -ENOTSUP; } - /* Zero writes start without an I/O buffer. If a buffer becomes necessary - * then it will be allocated during request processing. - */ - iov.iov_base = NULL; - iov.iov_len = bytes; - - qemu_iovec_init_external(&qiov, &iov, 1); return qed_co_request(bs, offset >> BDRV_SECTOR_BITS, &qiov, bytes >> BDRV_SECTOR_BITS, QED_AIOCB_WRITE | QED_AIOCB_ZERO); -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-12-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-12-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/vmdk.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, VmdkGrainMarker *data = NULL; uLongf buf_len; QEMUIOVector local_qiov; - struct iovec iov; int64_t write_offset; int64_t write_end_sector; @@ -XXX,XX +XXX,XX @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, data->size = cpu_to_le32(buf_len); n_bytes = buf_len + sizeof(VmdkGrainMarker); - iov = (struct iovec) { - .iov_base = data, - .iov_len = n_bytes, - }; - qemu_iovec_init_external(&local_qiov, &iov, 1); + qemu_iovec_init_buf(&local_qiov, data, n_bytes); BLKDBG_EVENT(extent->file, BLKDBG_WRITE_COMPRESSED); } else { -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-13-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-13-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qemu-img.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn convert_co_read(ImgConvertState *s, int64_t sector_num, { int n, ret; QEMUIOVector qiov; - struct iovec iov; assert(nb_sectors <= s->buf_sectors); while (nb_sectors > 0) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn convert_co_read(ImgConvertState *s, int64_t sector_num, bs_sectors = s->src_sectors[src_cur]; n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset)); - iov.iov_base = buf; - iov.iov_len = n << BDRV_SECTOR_BITS; - qemu_iovec_init_external(&qiov, &iov, 1); + qemu_iovec_init_buf(&qiov, buf, n << BDRV_SECTOR_BITS); ret = blk_co_preadv( blk, (sector_num - src_cur_offset) << BDRV_SECTOR_BITS, @@ -XXX,XX +XXX,XX @@ static int coroutine_fn convert_co_write(ImgConvertState *s, int64_t sector_num, { int ret; QEMUIOVector qiov; - struct iovec iov; while (nb_sectors > 0) { int n = nb_sectors; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn convert_co_write(ImgConvertState *s, int64_t sector_num, (s->compressed && !buffer_is_zero(buf, n * BDRV_SECTOR_SIZE))) { - iov.iov_base = buf; - iov.iov_len = n << BDRV_SECTOR_BITS; - qemu_iovec_init_external(&qiov, &iov, 1); + qemu_iovec_init_buf(&qiov, buf, n << BDRV_SECTOR_BITS); ret = blk_co_pwritev(s->target, sector_num << BDRV_SECTOR_BITS, n << BDRV_SECTOR_BITS, &qiov, flags); -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new qemu_iovec_init_buf() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-14-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-14-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- migration/block.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/migration/block.c b/migration/block.c index XXXXXXX..XXXXXXX 100644 --- a/migration/block.c +++ b/migration/block.c @@ -XXX,XX +XXX,XX @@ typedef struct BlkMigBlock { BlkMigDevState *bmds; int64_t sector; int nr_sectors; - struct iovec iov; QEMUIOVector qiov; BlockAIOCB *aiocb; @@ -XXX,XX +XXX,XX @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds) blk->sector = cur_sector; blk->nr_sectors = nr_sectors; - blk->iov.iov_base = blk->buf; - blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE; - qemu_iovec_init_external(&blk->qiov, &blk->iov, 1); + qemu_iovec_init_buf(&blk->qiov, blk->buf, nr_sectors * BDRV_SECTOR_SIZE); blk_mig_lock(); block_mig_state.submitted++; @@ -XXX,XX +XXX,XX @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds, blk->nr_sectors = nr_sectors; if (is_async) { - blk->iov.iov_base = blk->buf; - blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE; - qemu_iovec_init_external(&blk->qiov, &blk->iov, 1); + qemu_iovec_init_buf(&blk->qiov, blk->buf, + nr_sectors * BDRV_SECTOR_SIZE); blk->aiocb = blk_aio_preadv(bmds->blk, sector * BDRV_SECTOR_SIZE, -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Use new QEMU_IOVEC_INIT_BUF() instead of qemu_iovec_init_external( ... , 1), which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-15-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-15-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/test-bdrv-drain.c | 29 ++++------------------------- 1 file changed, 4 insertions(+), 25 deletions(-) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_common(enum drain_type drain_type, bool recursive) BlockAIOCB *acb; int aio_ret; - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = NULL, - .iov_len = 0, - }; - qemu_iovec_init_external(&qiov, &iov, 1); + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, NULL, 0); blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, @@ -XXX,XX +XXX,XX @@ static void test_iothread_common(enum drain_type drain_type, int drain_thread) AioContext *ctx_a = iothread_get_aio_context(a); AioContext *ctx_b = iothread_get_aio_context(b); - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = NULL, - .iov_len = 0, - }; - qemu_iovec_init_external(&qiov, &iov, 1); + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, NULL, 0); /* bdrv_drain_all() may only be called from the main loop thread */ if (drain_type == BDRV_DRAIN_ALL && drain_thread != 0) { @@ -XXX,XX +XXX,XX @@ static void coroutine_fn test_co_delete_by_drain(void *opaque) BlockDriverState *bs = blk_bs(blk); BDRVTestTopState *tts = bs->opaque; void *buffer = g_malloc(65536); - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = buffer, - .iov_len = 65536, - }; - - qemu_iovec_init_external(&qiov, &iov, 1); + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buffer, 65536); /* Pretend some internal write operation from parent to child. * Important: We have to read from the child, not from the parent! @@ -XXX,XX +XXX,XX @@ static void test_detach_indirect(bool by_parent_cb) BdrvChild *child_a, *child_b; BlockAIOCB *acb; - QEMUIOVector qiov; - struct iovec iov = { - .iov_base = NULL, - .iov_len = 0, - }; - qemu_iovec_init_external(&qiov, &iov, 1); + QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, NULL, 0); if (!by_parent_cb) { detach_by_driver_cb_role = child_file; -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> @iov is used only to initialize @qiov. Let's use new qemu_iovec_init_buf() instead, which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-16-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-16-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/ide/internal.h | 1 - hw/ide/atapi.c | 9 ++++----- hw/ide/core.c | 8 ++------ 3 files changed, 6 insertions(+), 12 deletions(-) diff --git a/include/hw/ide/internal.h b/include/hw/ide/internal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/ide/internal.h +++ b/include/hw/ide/internal.h @@ -XXX,XX +XXX,XX @@ struct IDEState { int atapi_dma; /* true if dma is requested for the packet cmd */ BlockAcctCookie acct; BlockAIOCB *pio_aiocb; - struct iovec iov; QEMUIOVector qiov; QLIST_HEAD(, IDEBufferedRequest) buffered_requests; /* ATA DMA state */ diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ide/atapi.c +++ b/hw/ide/atapi.c @@ -XXX,XX +XXX,XX @@ static void cd_read_sector_cb(void *opaque, int ret) static int cd_read_sector(IDEState *s) { + void *buf; + if (s->cd_sector_size != 2048 && s->cd_sector_size != 2352) { block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_READ); return -EINVAL; } - s->iov.iov_base = (s->cd_sector_size == 2352) ? - s->io_buffer + 16 : s->io_buffer; - - s->iov.iov_len = ATAPI_SECTOR_SIZE; - qemu_iovec_init_external(&s->qiov, &s->iov, 1); + buf = (s->cd_sector_size == 2352) ? s->io_buffer + 16 : s->io_buffer; + qemu_iovec_init_buf(&s->qiov, buf, ATAPI_SECTOR_SIZE); trace_cd_read_sector(s->lba); diff --git a/hw/ide/core.c b/hw/ide/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -XXX,XX +XXX,XX @@ static void ide_sector_read(IDEState *s) return; } - s->iov.iov_base = s->io_buffer; - s->iov.iov_len = n * BDRV_SECTOR_SIZE; - qemu_iovec_init_external(&s->qiov, &s->iov, 1); + qemu_iovec_init_buf(&s->qiov, s->io_buffer, n * BDRV_SECTOR_SIZE); block_acct_start(blk_get_stats(s->blk), &s->acct, n * BDRV_SECTOR_SIZE, BLOCK_ACCT_READ); @@ -XXX,XX +XXX,XX @@ static void ide_sector_write(IDEState *s) return; } - s->iov.iov_base = s->io_buffer; - s->iov.iov_len = n * BDRV_SECTOR_SIZE; - qemu_iovec_init_external(&s->qiov, &s->iov, 1); + qemu_iovec_init_buf(&s->qiov, s->io_buffer, n * BDRV_SECTOR_SIZE); block_acct_start(blk_get_stats(s->blk), &s->acct, n * BDRV_SECTOR_SIZE, BLOCK_ACCT_WRITE); -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> @iov is used only to initialize @qiov. Let's use new qemu_iovec_init_buf() instead, which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-17-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-17-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/ide/internal.h | 1 - hw/ide/core.c | 11 ++++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/hw/ide/internal.h b/include/hw/ide/internal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/ide/internal.h +++ b/include/hw/ide/internal.h @@ -XXX,XX +XXX,XX @@ extern const char *IDE_DMA_CMD_lookup[IDE_DMA__COUNT]; typedef struct IDEBufferedRequest { QLIST_ENTRY(IDEBufferedRequest) list; - struct iovec iov; QEMUIOVector qiov; QEMUIOVector *original_qiov; BlockCompletionFunc *original_cb; diff --git a/hw/ide/core.c b/hw/ide/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -XXX,XX +XXX,XX @@ static void ide_buffered_readv_cb(void *opaque, int ret) IDEBufferedRequest *req = opaque; if (!req->orphaned) { if (!ret) { - qemu_iovec_from_buf(req->original_qiov, 0, req->iov.iov_base, + assert(req->qiov.size == req->original_qiov->size); + qemu_iovec_from_buf(req->original_qiov, 0, + req->qiov.local_iov.iov_base, req->original_qiov->size); } req->original_cb(req->original_opaque, ret); } QLIST_REMOVE(req, list); - qemu_vfree(req->iov.iov_base); + qemu_vfree(qemu_iovec_buf(&req->qiov)); g_free(req); } @@ -XXX,XX +XXX,XX @@ BlockAIOCB *ide_buffered_readv(IDEState *s, int64_t sector_num, req->original_qiov = iov; req->original_cb = cb; req->original_opaque = opaque; - req->iov.iov_base = qemu_blockalign(blk_bs(s->blk), iov->size); - req->iov.iov_len = iov->size; - qemu_iovec_init_external(&req->qiov, &req->iov, 1); + qemu_iovec_init_buf(&req->qiov, blk_blockalign(s->blk, iov->size), + iov->size); aioreq = blk_aio_preadv(s->blk, sector_num << BDRV_SECTOR_BITS, &req->qiov, 0, ide_buffered_readv_cb, req); -- 2.20.1 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> @iov is used only to initialize @qiov. Let's use new qemu_iovec_init_buf() instead, which simplifies the code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190218140926.333779-18-vsementsov@virtuozzo.com Message-Id: <20190218140926.333779-18-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/ide/internal.h | 1 - hw/ide/atapi.c | 5 ++--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/include/hw/ide/internal.h b/include/hw/ide/internal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/ide/internal.h +++ b/include/hw/ide/internal.h @@ -XXX,XX +XXX,XX @@ struct IDEDMAOps { struct IDEDMA { const struct IDEDMAOps *ops; - struct iovec iov; QEMUIOVector qiov; BlockAIOCB *aiocb; }; diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ide/atapi.c +++ b/hw/ide/atapi.c @@ -XXX,XX +XXX,XX @@ static void ide_atapi_cmd_read_dma_cb(void *opaque, int ret) data_offset = 0; } trace_ide_atapi_cmd_read_dma_cb_aio(s, s->lba, n); - s->bus->dma->iov.iov_base = (void *)(s->io_buffer + data_offset); - s->bus->dma->iov.iov_len = n * ATAPI_SECTOR_SIZE; - qemu_iovec_init_external(&s->bus->dma->qiov, &s->bus->dma->iov, 1); + qemu_iovec_init_buf(&s->bus->dma->qiov, s->io_buffer + data_offset, + n * ATAPI_SECTOR_SIZE); s->bus->dma->aiocb = ide_buffered_readv(s, (int64_t)s->lba << 2, &s->bus->dma->qiov, n * 4, -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> We add acct_failed param in order to use virtio_blk_handle_rw_error() also when is not required to call block_acct_failed(). (eg. a discard operation is failed) Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-2-sgarzare@redhat.com Message-Id: <20190221103314.58500-2-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- hw/block/virtio-blk.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status) } static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error, - bool is_read) + bool is_read, bool acct_failed) { VirtIOBlock *s = req->dev; BlockErrorAction action = blk_get_error_action(s->blk, is_read, error); @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error, s->rq = req; } else if (action == BLOCK_ERROR_ACTION_REPORT) { virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR); - block_acct_failed(blk_get_stats(s->blk), &req->acct); + if (acct_failed) { + block_acct_failed(blk_get_stats(s->blk), &req->acct); + } virtio_blk_free_request(req); } @@ -XXX,XX +XXX,XX @@ static void virtio_blk_rw_complete(void *opaque, int ret) * the memory until the request is completed (which will * happen on the other side of the migration). */ - if (virtio_blk_handle_rw_error(req, -ret, is_read)) { + if (virtio_blk_handle_rw_error(req, -ret, is_read, true)) { continue; } } @@ -XXX,XX +XXX,XX @@ static void virtio_blk_flush_complete(void *opaque, int ret) aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); if (ret) { - if (virtio_blk_handle_rw_error(req, -ret, 0)) { + if (virtio_blk_handle_rw_error(req, -ret, 0, true)) { goto out; } } -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> Since configurable features for virtio-blk are growing, this patch adds host_features field in the struct VirtIOBlock. (as in virtio-net) In this way, we can avoid to add new fields for new properties and we can directly set VIRTIO_BLK_F* flags in the host_features. We update "config-wce" and "scsi" property definition to use the new host_features field without change the behaviour. Suggested-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-3-sgarzare@redhat.com Message-Id: <20190221103314.58500-3-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/virtio/virtio-blk.h | 3 +-- hw/block/virtio-blk.c | 16 +++++++++------- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/virtio/virtio-blk.h +++ b/include/hw/virtio/virtio-blk.h @@ -XXX,XX +XXX,XX @@ struct VirtIOBlkConf BlockConf conf; IOThread *iothread; char *serial; - uint32_t scsi; - uint32_t config_wce; uint32_t request_merging; uint16_t num_queues; uint16_t queue_size; @@ -XXX,XX +XXX,XX @@ typedef struct VirtIOBlock { bool dataplane_disabled; bool dataplane_started; struct VirtIOBlockDataPlane *dataplane; + uint64_t host_features; } VirtIOBlock; typedef struct VirtIOBlockReq { diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_scsi_req(VirtIOBlockReq *req) */ scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base; - if (!blk->conf.scsi) { + if (!virtio_has_feature(blk->host_features, VIRTIO_BLK_F_SCSI)) { status = VIRTIO_BLK_S_UNSUPP; goto fail; } @@ -XXX,XX +XXX,XX @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features, { VirtIOBlock *s = VIRTIO_BLK(vdev); + /* Firstly sync all virtio-blk possible supported features */ + features |= s->host_features; + virtio_add_feature(&features, VIRTIO_BLK_F_SEG_MAX); virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY); virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY); virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE); if (virtio_has_feature(features, VIRTIO_F_VERSION_1)) { - if (s->conf.scsi) { + if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_SCSI)) { error_setg(errp, "Please set scsi=off for virtio-blk devices in order to use virtio 1.0"); return 0; } @@ -XXX,XX +XXX,XX @@ static uint64_t virtio_blk_get_features(VirtIODevice *vdev, uint64_t features, virtio_add_feature(&features, VIRTIO_BLK_F_SCSI); } - if (s->conf.config_wce) { - virtio_add_feature(&features, VIRTIO_BLK_F_CONFIG_WCE); - } if (blk_enable_write_cache(s->blk)) { virtio_add_feature(&features, VIRTIO_BLK_F_WCE); } @@ -XXX,XX +XXX,XX @@ static Property virtio_blk_properties[] = { DEFINE_BLOCK_ERROR_PROPERTIES(VirtIOBlock, conf.conf), DEFINE_BLOCK_CHS_PROPERTIES(VirtIOBlock, conf.conf), DEFINE_PROP_STRING("serial", VirtIOBlock, conf.serial), - DEFINE_PROP_BIT("config-wce", VirtIOBlock, conf.config_wce, 0, true), + DEFINE_PROP_BIT64("config-wce", VirtIOBlock, host_features, + VIRTIO_BLK_F_CONFIG_WCE, true), #ifdef __linux__ - DEFINE_PROP_BIT("scsi", VirtIOBlock, conf.scsi, 0, false), + DEFINE_PROP_BIT64("scsi", VirtIOBlock, host_features, + VIRTIO_BLK_F_SCSI, false), #endif DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0, true), -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> In order to avoid migration issues, we enable DISCARD and WRITE_ZEROES features only for machine type >= 4.0 As discussed with Michael S. Tsirkin and Stefan Hajnoczi on the list [1], DISCARD operation should not have security implications (eg. page cache attacks), so we can enable it by default. [1] https://lists.gnu.org/archive/html/qemu-devel/2019-02/msg00504.html Suggested-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-4-sgarzare@redhat.com Message-Id: <20190221103314.58500-4-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- hw/block/virtio-blk.c | 4 ++++ hw/core/machine.c | 2 ++ 2 files changed, 6 insertions(+) diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static Property virtio_blk_properties[] = { DEFINE_PROP_UINT16("queue-size", VirtIOBlock, conf.queue_size, 128), DEFINE_PROP_LINK("iothread", VirtIOBlock, conf.iothread, TYPE_IOTHREAD, IOThread *), + DEFINE_PROP_BIT64("discard", VirtIOBlock, host_features, + VIRTIO_BLK_F_DISCARD, true), + DEFINE_PROP_BIT64("write-zeroes", VirtIOBlock, host_features, + VIRTIO_BLK_F_WRITE_ZEROES, true), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/core/machine.c b/hw/core/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -XXX,XX +XXX,XX @@ GlobalProperty hw_compat_3_1[] = { { "usb-kbd", "serial", "42" }, { "usb-mouse", "serial", "42" }, { "usb-kbd", "serial", "42" }, + { "virtio-blk-device", "discard", "false" }, + { "virtio-blk-device", "write-zeroes", "false" }, }; const size_t hw_compat_3_1_len = G_N_ELEMENTS(hw_compat_3_1); -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> In order to use VirtIOFeature also in other virtio devices, we move its declaration and the endof() macro (renamed in virtio_endof()) in virtio.h. We add virtio_feature_get_config_size() function to iterate the array of VirtIOFeature and to return the config size depending on the features enabled. (as virtio_net_set_config_size() did) Suggested-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-5-sgarzare@redhat.com Message-Id: <20190221103314.58500-5-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/virtio/virtio.h | 15 +++++++++++++++ hw/net/virtio-net.c | 31 +++++++------------------------ hw/virtio/virtio.c | 15 +++++++++++++++ 3 files changed, 37 insertions(+), 24 deletions(-) diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/virtio/virtio.h +++ b/include/hw/virtio/virtio.h @@ -XXX,XX +XXX,XX @@ static inline hwaddr vring_align(hwaddr addr, return QEMU_ALIGN_UP(addr, align); } +/* + * Calculate the number of bytes up to and including the given 'field' of + * 'container'. + */ +#define virtio_endof(container, field) \ + (offsetof(container, field) + sizeof_field(container, field)) + +typedef struct VirtIOFeature { + uint64_t flags; + size_t end; +} VirtIOFeature; + +size_t virtio_feature_get_config_size(VirtIOFeature *features, + uint64_t host_features); + typedef struct VirtQueue VirtQueue; #define VIRTQUEUE_MAX_SIZE 1024 diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -XXX,XX +XXX,XX @@ static inline __virtio16 *virtio_net_rsc_ext_num_dupacks( #endif -/* - * Calculate the number of bytes up to and including the given 'field' of - * 'container'. - */ -#define endof(container, field) \ - (offsetof(container, field) + sizeof_field(container, field)) - -typedef struct VirtIOFeature { - uint64_t flags; - size_t end; -} VirtIOFeature; - static VirtIOFeature feature_sizes[] = { {.flags = 1ULL << VIRTIO_NET_F_MAC, - .end = endof(struct virtio_net_config, mac)}, + .end = virtio_endof(struct virtio_net_config, mac)}, {.flags = 1ULL << VIRTIO_NET_F_STATUS, - .end = endof(struct virtio_net_config, status)}, + .end = virtio_endof(struct virtio_net_config, status)}, {.flags = 1ULL << VIRTIO_NET_F_MQ, - .end = endof(struct virtio_net_config, max_virtqueue_pairs)}, + .end = virtio_endof(struct virtio_net_config, max_virtqueue_pairs)}, {.flags = 1ULL << VIRTIO_NET_F_MTU, - .end = endof(struct virtio_net_config, mtu)}, + .end = virtio_endof(struct virtio_net_config, mtu)}, {.flags = 1ULL << VIRTIO_NET_F_SPEED_DUPLEX, - .end = endof(struct virtio_net_config, duplex)}, + .end = virtio_endof(struct virtio_net_config, duplex)}, {} }; @@ -XXX,XX +XXX,XX @@ static void virtio_net_guest_notifier_mask(VirtIODevice *vdev, int idx, static void virtio_net_set_config_size(VirtIONet *n, uint64_t host_features) { - int i, config_size = 0; virtio_add_feature(&host_features, VIRTIO_NET_F_MAC); - for (i = 0; feature_sizes[i].flags != 0; i++) { - if (host_features & feature_sizes[i].flags) { - config_size = MAX(feature_sizes[i].end, config_size); - } - } - n->config_size = config_size; + n->config_size = virtio_feature_get_config_size(feature_sizes, + host_features); } void virtio_net_set_netclient_name(VirtIONet *n, const char *name, diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -XXX,XX +XXX,XX @@ int virtio_set_features(VirtIODevice *vdev, uint64_t val) return ret; } +size_t virtio_feature_get_config_size(VirtIOFeature *feature_sizes, + uint64_t host_features) +{ + size_t config_size = 0; + int i; + + for (i = 0; feature_sizes[i].flags != 0; i++) { + if (host_features & feature_sizes[i].flags) { + config_size = MAX(feature_sizes[i].end, config_size); + } + } + + return config_size; +} + int virtio_load(VirtIODevice *vdev, QEMUFile *f, int version_id) { int i, ret; -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> Starting from DISABLE and WRITE_ZEROES features, we use an array of VirtIOFeature (as virtio-net) to properly set the config size depending on the features enabled. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-6-sgarzare@redhat.com Message-Id: <20190221103314.58500-6-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/virtio/virtio-blk.h | 1 + hw/block/virtio-blk.c | 31 +++++++++++++++++++++++++------ 2 files changed, 26 insertions(+), 6 deletions(-) diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/virtio/virtio-blk.h +++ b/include/hw/virtio/virtio-blk.h @@ -XXX,XX +XXX,XX @@ typedef struct VirtIOBlock { bool dataplane_started; struct VirtIOBlockDataPlane *dataplane; uint64_t host_features; + size_t config_size; } VirtIOBlock; typedef struct VirtIOBlockReq { diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ #include "hw/virtio/virtio-bus.h" #include "hw/virtio/virtio-access.h" -/* We don't support discard yet, hide associated config fields. */ +/* Config size before the discard support (hide associated config fields) */ #define VIRTIO_BLK_CFG_SIZE offsetof(struct virtio_blk_config, \ max_discard_sectors) +/* + * Starting from the discard feature, we can use this array to properly + * set the config size depending on the features enabled. + */ +static VirtIOFeature feature_sizes[] = { + {.flags = 1ULL << VIRTIO_BLK_F_DISCARD, + .end = virtio_endof(struct virtio_blk_config, discard_sector_alignment)}, + {.flags = 1ULL << VIRTIO_BLK_F_WRITE_ZEROES, + .end = virtio_endof(struct virtio_blk_config, write_zeroes_may_unmap)}, + {} +}; + +static void virtio_blk_set_config_size(VirtIOBlock *s, uint64_t host_features) +{ + s->config_size = MAX(VIRTIO_BLK_CFG_SIZE, + virtio_feature_get_config_size(feature_sizes, host_features)); + + assert(s->config_size <= sizeof(struct virtio_blk_config)); +} static void virtio_blk_init_request(VirtIOBlock *s, VirtQueue *vq, VirtIOBlockReq *req) @@ -XXX,XX +XXX,XX @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config) blkcfg.alignment_offset = 0; blkcfg.wce = blk_enable_write_cache(s->blk); virtio_stw_p(vdev, &blkcfg.num_queues, s->conf.num_queues); - memcpy(config, &blkcfg, VIRTIO_BLK_CFG_SIZE); - QEMU_BUILD_BUG_ON(VIRTIO_BLK_CFG_SIZE > sizeof(blkcfg)); + memcpy(config, &blkcfg, s->config_size); } static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config) @@ -XXX,XX +XXX,XX @@ static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config) VirtIOBlock *s = VIRTIO_BLK(vdev); struct virtio_blk_config blkcfg; - memcpy(&blkcfg, config, VIRTIO_BLK_CFG_SIZE); - QEMU_BUILD_BUG_ON(VIRTIO_BLK_CFG_SIZE > sizeof(blkcfg)); + memcpy(&blkcfg, config, s->config_size); aio_context_acquire(blk_get_aio_context(s->blk)); blk_set_enable_write_cache(s->blk, blkcfg.wce != 0); @@ -XXX,XX +XXX,XX @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp) return; } - virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK, VIRTIO_BLK_CFG_SIZE); + virtio_blk_set_config_size(s, s->host_features); + + virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK, s->config_size); s->blk = conf->conf.blk; s->rq = NULL; -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> This patch adds the support of DISCARD and WRITE_ZEROES commands, that have been introduced in the virtio-blk protocol to have better performance when using SSD backend. We support only one segment per request since multiple segments are not widely used and there are no userspace APIs that allow applications to submit multiple segments in a single call. Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-7-sgarzare@redhat.com Message-Id: <20190221103314.58500-7-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/virtio/virtio-blk.h | 2 + hw/block/virtio-blk.c | 184 +++++++++++++++++++++++++++++++++ 2 files changed, 186 insertions(+) diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/virtio/virtio-blk.h +++ b/include/hw/virtio/virtio-blk.h @@ -XXX,XX +XXX,XX @@ struct VirtIOBlkConf uint32_t request_merging; uint16_t num_queues; uint16_t queue_size; + uint32_t max_discard_sectors; + uint32_t max_write_zeroes_sectors; }; struct VirtIOBlockDataPlane; diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ out: aio_context_release(blk_get_aio_context(s->conf.conf.blk)); } +static void virtio_blk_discard_write_zeroes_complete(void *opaque, int ret) +{ + VirtIOBlockReq *req = opaque; + VirtIOBlock *s = req->dev; + bool is_write_zeroes = (virtio_ldl_p(VIRTIO_DEVICE(s), &req->out.type) & + ~VIRTIO_BLK_T_BARRIER) == VIRTIO_BLK_T_WRITE_ZEROES; + + aio_context_acquire(blk_get_aio_context(s->conf.conf.blk)); + if (ret) { + if (virtio_blk_handle_rw_error(req, -ret, false, is_write_zeroes)) { + goto out; + } + } + + virtio_blk_req_complete(req, VIRTIO_BLK_S_OK); + if (is_write_zeroes) { + block_acct_done(blk_get_stats(s->blk), &req->acct); + } + virtio_blk_free_request(req); + +out: + aio_context_release(blk_get_aio_context(s->conf.conf.blk)); +} + #ifdef __linux__ typedef struct { @@ -XXX,XX +XXX,XX @@ static bool virtio_blk_sect_range_ok(VirtIOBlock *dev, return true; } +static uint8_t virtio_blk_handle_discard_write_zeroes(VirtIOBlockReq *req, + struct virtio_blk_discard_write_zeroes *dwz_hdr, bool is_write_zeroes) +{ + VirtIOBlock *s = req->dev; + VirtIODevice *vdev = VIRTIO_DEVICE(s); + uint64_t sector; + uint32_t num_sectors, flags, max_sectors; + uint8_t err_status; + int bytes; + + sector = virtio_ldq_p(vdev, &dwz_hdr->sector); + num_sectors = virtio_ldl_p(vdev, &dwz_hdr->num_sectors); + flags = virtio_ldl_p(vdev, &dwz_hdr->flags); + max_sectors = is_write_zeroes ? s->conf.max_write_zeroes_sectors : + s->conf.max_discard_sectors; + + /* + * max_sectors is at most BDRV_REQUEST_MAX_SECTORS, this check + * make us sure that "num_sectors << BDRV_SECTOR_BITS" can fit in + * the integer variable. + */ + if (unlikely(num_sectors > max_sectors)) { + err_status = VIRTIO_BLK_S_IOERR; + goto err; + } + + bytes = num_sectors << BDRV_SECTOR_BITS; + + if (unlikely(!virtio_blk_sect_range_ok(s, sector, bytes))) { + err_status = VIRTIO_BLK_S_IOERR; + goto err; + } + + /* + * The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for discard + * and write zeroes commands if any unknown flag is set. + */ + if (unlikely(flags & ~VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) { + err_status = VIRTIO_BLK_S_UNSUPP; + goto err; + } + + if (is_write_zeroes) { /* VIRTIO_BLK_T_WRITE_ZEROES */ + int blk_aio_flags = 0; + + if (flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP) { + blk_aio_flags |= BDRV_REQ_MAY_UNMAP; + } + + block_acct_start(blk_get_stats(s->blk), &req->acct, bytes, + BLOCK_ACCT_WRITE); + + blk_aio_pwrite_zeroes(s->blk, sector << BDRV_SECTOR_BITS, + bytes, blk_aio_flags, + virtio_blk_discard_write_zeroes_complete, req); + } else { /* VIRTIO_BLK_T_DISCARD */ + /* + * The device MUST set the status byte to VIRTIO_BLK_S_UNSUPP for + * discard commands if the unmap flag is set. + */ + if (unlikely(flags & VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP)) { + err_status = VIRTIO_BLK_S_UNSUPP; + goto err; + } + + blk_aio_pdiscard(s->blk, sector << BDRV_SECTOR_BITS, bytes, + virtio_blk_discard_write_zeroes_complete, req); + } + + return VIRTIO_BLK_S_OK; + +err: + if (is_write_zeroes) { + block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_WRITE); + } + return err_status; +} + static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb) { uint32_t type; @@ -XXX,XX +XXX,XX @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb) virtio_blk_free_request(req); break; } + /* + * VIRTIO_BLK_T_DISCARD and VIRTIO_BLK_T_WRITE_ZEROES are defined with + * VIRTIO_BLK_T_OUT flag set. We masked this flag in the switch statement, + * so we must mask it for these requests, then we will check if it is set. + */ + case VIRTIO_BLK_T_DISCARD & ~VIRTIO_BLK_T_OUT: + case VIRTIO_BLK_T_WRITE_ZEROES & ~VIRTIO_BLK_T_OUT: + { + struct virtio_blk_discard_write_zeroes dwz_hdr; + size_t out_len = iov_size(out_iov, out_num); + bool is_write_zeroes = (type & ~VIRTIO_BLK_T_BARRIER) == + VIRTIO_BLK_T_WRITE_ZEROES; + uint8_t err_status; + + /* + * Unsupported if VIRTIO_BLK_T_OUT is not set or the request contains + * more than one segment. + */ + if (unlikely(!(type & VIRTIO_BLK_T_OUT) || + out_len > sizeof(dwz_hdr))) { + virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP); + virtio_blk_free_request(req); + return 0; + } + + if (unlikely(iov_to_buf(out_iov, out_num, 0, &dwz_hdr, + sizeof(dwz_hdr)) != sizeof(dwz_hdr))) { + virtio_error(vdev, "virtio-blk discard/write_zeroes header" + " too short"); + return -1; + } + + err_status = virtio_blk_handle_discard_write_zeroes(req, &dwz_hdr, + is_write_zeroes); + if (err_status != VIRTIO_BLK_S_OK) { + virtio_blk_req_complete(req, err_status); + virtio_blk_free_request(req); + } + + break; + } default: virtio_blk_req_complete(req, VIRTIO_BLK_S_UNSUPP); virtio_blk_free_request(req); @@ -XXX,XX +XXX,XX @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config) blkcfg.alignment_offset = 0; blkcfg.wce = blk_enable_write_cache(s->blk); virtio_stw_p(vdev, &blkcfg.num_queues, s->conf.num_queues); + if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD)) { + virtio_stl_p(vdev, &blkcfg.max_discard_sectors, + s->conf.max_discard_sectors); + virtio_stl_p(vdev, &blkcfg.discard_sector_alignment, + blk_size >> BDRV_SECTOR_BITS); + /* + * We support only one segment per request since multiple segments + * are not widely used and there are no userspace APIs that allow + * applications to submit multiple segments in a single call. + */ + virtio_stl_p(vdev, &blkcfg.max_discard_seg, 1); + } + if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_WRITE_ZEROES)) { + virtio_stl_p(vdev, &blkcfg.max_write_zeroes_sectors, + s->conf.max_write_zeroes_sectors); + blkcfg.write_zeroes_may_unmap = 1; + virtio_stl_p(vdev, &blkcfg.max_write_zeroes_seg, 1); + } memcpy(config, &blkcfg, s->config_size); } @@ -XXX,XX +XXX,XX @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp) return; } + if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_DISCARD) && + (!conf->max_discard_sectors || + conf->max_discard_sectors > BDRV_REQUEST_MAX_SECTORS)) { + error_setg(errp, "invalid max-discard-sectors property (%" PRIu32 ")" + ", must be between 1 and %d", + conf->max_discard_sectors, (int)BDRV_REQUEST_MAX_SECTORS); + return; + } + + if (virtio_has_feature(s->host_features, VIRTIO_BLK_F_WRITE_ZEROES) && + (!conf->max_write_zeroes_sectors || + conf->max_write_zeroes_sectors > BDRV_REQUEST_MAX_SECTORS)) { + error_setg(errp, "invalid max-write-zeroes-sectors property (%" PRIu32 + "), must be between 1 and %d", + conf->max_write_zeroes_sectors, + (int)BDRV_REQUEST_MAX_SECTORS); + return; + } + virtio_blk_set_config_size(s, s->host_features); virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK, s->config_size); @@ -XXX,XX +XXX,XX @@ static Property virtio_blk_properties[] = { VIRTIO_BLK_F_DISCARD, true), DEFINE_PROP_BIT64("write-zeroes", VirtIOBlock, host_features, VIRTIO_BLK_F_WRITE_ZEROES, true), + DEFINE_PROP_UINT32("max-discard-sectors", VirtIOBlock, + conf.max_discard_sectors, BDRV_REQUEST_MAX_SECTORS), + DEFINE_PROP_UINT32("max-write-zeroes-sectors", VirtIOBlock, + conf.max_write_zeroes_sectors, BDRV_REQUEST_MAX_SECTORS), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> The size of data in the virtio_blk_request must be a multiple of 512 bytes for IN and OUT requests, or a multiple of the size of struct virtio_blk_discard_write_zeroes for DISCARD and WRITE_ZEROES requests. Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-8-sgarzare@redhat.com Message-Id: <20190221103314.58500-8-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/virtio-blk-test.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/tests/virtio-blk-test.c b/tests/virtio-blk-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/virtio-blk-test.c +++ b/tests/virtio-blk-test.c @@ -XXX,XX +XXX,XX @@ static uint64_t virtio_blk_request(QGuestAllocator *alloc, QVirtioDevice *d, uint64_t addr; uint8_t status = 0xFF; - g_assert_cmpuint(data_size % 512, ==, 0); + switch (req->type) { + case VIRTIO_BLK_T_IN: + case VIRTIO_BLK_T_OUT: + g_assert_cmpuint(data_size % 512, ==, 0); + break; + case VIRTIO_BLK_T_DISCARD: + case VIRTIO_BLK_T_WRITE_ZEROES: + g_assert_cmpuint(data_size % + sizeof(struct virtio_blk_discard_write_zeroes), ==, 0); + break; + default: + g_assert_cmpuint(data_size, ==, 0); + } + addr = guest_alloc(alloc, sizeof(*req) + data_size); virtio_blk_fix_request(d, req); -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> This function is useful to fix the endianness of struct virtio_blk_discard_write_zeroes headers. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-9-sgarzare@redhat.com Message-Id: <20190221103314.58500-9-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/virtio-blk-test.c | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/tests/virtio-blk-test.c b/tests/virtio-blk-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/virtio-blk-test.c +++ b/tests/virtio-blk-test.c @@ -XXX,XX +XXX,XX @@ typedef struct QVirtioBlkReq { uint8_t status; } QVirtioBlkReq; +#ifdef HOST_WORDS_BIGENDIAN +const bool host_is_big_endian = true; +#else +const bool host_is_big_endian; /* false */ +#endif + static char *drive_create(void) { int fd, ret; @@ -XXX,XX +XXX,XX @@ static QVirtioPCIDevice *virtio_blk_pci_init(QPCIBus *bus, int slot) static inline void virtio_blk_fix_request(QVirtioDevice *d, QVirtioBlkReq *req) { -#ifdef HOST_WORDS_BIGENDIAN - const bool host_is_big_endian = true; -#else - const bool host_is_big_endian = false; -#endif - if (qvirtio_is_big_endian(d) != host_is_big_endian) { req->type = bswap32(req->type); req->ioprio = bswap32(req->ioprio); @@ -XXX,XX +XXX,XX @@ static inline void virtio_blk_fix_request(QVirtioDevice *d, QVirtioBlkReq *req) } } + +static inline void virtio_blk_fix_dwz_hdr(QVirtioDevice *d, + struct virtio_blk_discard_write_zeroes *dwz_hdr) +{ + if (qvirtio_is_big_endian(d) != host_is_big_endian) { + dwz_hdr->sector = bswap64(dwz_hdr->sector); + dwz_hdr->num_sectors = bswap32(dwz_hdr->num_sectors); + dwz_hdr->flags = bswap32(dwz_hdr->flags); + } +} + static uint64_t virtio_blk_request(QGuestAllocator *alloc, QVirtioDevice *d, QVirtioBlkReq *req, uint64_t data_size) { -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> If the WRITE_ZEROES feature is enabled, we check this command in the test_basic(). Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-10-sgarzare@redhat.com Message-Id: <20190221103314.58500-10-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/virtio-blk-test.c | 62 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) diff --git a/tests/virtio-blk-test.c b/tests/virtio-blk-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/virtio-blk-test.c +++ b/tests/virtio-blk-test.c @@ -XXX,XX +XXX,XX @@ static void test_basic(QVirtioDevice *dev, QGuestAllocator *alloc, guest_free(alloc, req_addr); + if (features & (1u << VIRTIO_BLK_F_WRITE_ZEROES)) { + struct virtio_blk_discard_write_zeroes dwz_hdr; + void *expected; + + /* + * WRITE_ZEROES request on the same sector of previous test where + * we wrote "TEST". + */ + req.type = VIRTIO_BLK_T_WRITE_ZEROES; + req.data = (char *) &dwz_hdr; + dwz_hdr.sector = 0; + dwz_hdr.num_sectors = 1; + dwz_hdr.flags = 0; + + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); + + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); + + free_head = qvirtqueue_add(vq, req_addr, 16, false, true); + qvirtqueue_add(vq, req_addr + 16, sizeof(dwz_hdr), false, true); + qvirtqueue_add(vq, req_addr + 16 + sizeof(dwz_hdr), 1, true, false); + + qvirtqueue_kick(dev, vq, free_head); + + qvirtio_wait_used_elem(dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 16 + sizeof(dwz_hdr)); + g_assert_cmpint(status, ==, 0); + + guest_free(alloc, req_addr); + + /* Read request to check if the sector contains all zeroes */ + req.type = VIRTIO_BLK_T_IN; + req.ioprio = 1; + req.sector = 0; + req.data = g_malloc0(512); + + req_addr = virtio_blk_request(alloc, dev, &req, 512); + + g_free(req.data); + + free_head = qvirtqueue_add(vq, req_addr, 16, false, true); + qvirtqueue_add(vq, req_addr + 16, 512, true, true); + qvirtqueue_add(vq, req_addr + 528, 1, true, false); + + qvirtqueue_kick(dev, vq, free_head); + + qvirtio_wait_used_elem(dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 528); + g_assert_cmpint(status, ==, 0); + + data = g_malloc(512); + expected = g_malloc0(512); + memread(req_addr + 16, data, 512); + g_assert_cmpmem(data, 512, expected, 512); + g_free(expected); + g_free(data); + + guest_free(alloc, req_addr); + } + if (features & (1u << VIRTIO_F_ANY_LAYOUT)) { /* Write and read with 2 descriptor layout */ /* Write request */ -- 2.20.1 From: Stefano Garzarella <sgarzare@redhat.com> If the DISCARD feature is enabled, we try this command in the test_basic(), checking only the status returned by the request. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Message-id: 20190221103314.58500-11-sgarzare@redhat.com Message-Id: <20190221103314.58500-11-sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/virtio-blk-test.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/tests/virtio-blk-test.c b/tests/virtio-blk-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/virtio-blk-test.c +++ b/tests/virtio-blk-test.c @@ -XXX,XX +XXX,XX @@ static void test_basic(QVirtioDevice *dev, QGuestAllocator *alloc, guest_free(alloc, req_addr); } + if (features & (1u << VIRTIO_BLK_F_DISCARD)) { + struct virtio_blk_discard_write_zeroes dwz_hdr; + + req.type = VIRTIO_BLK_T_DISCARD; + req.data = (char *) &dwz_hdr; + dwz_hdr.sector = 0; + dwz_hdr.num_sectors = 1; + dwz_hdr.flags = 0; + + virtio_blk_fix_dwz_hdr(dev, &dwz_hdr); + + req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr)); + + free_head = qvirtqueue_add(vq, req_addr, 16, false, true); + qvirtqueue_add(vq, req_addr + 16, sizeof(dwz_hdr), false, true); + qvirtqueue_add(vq, req_addr + 16 + sizeof(dwz_hdr), 1, true, false); + + qvirtqueue_kick(dev, vq, free_head); + + qvirtio_wait_used_elem(dev, vq, free_head, NULL, + QVIRTIO_BLK_TIMEOUT_US); + status = readb(req_addr + 16 + sizeof(dwz_hdr)); + g_assert_cmpint(status, ==, 0); + + guest_free(alloc, req_addr); + } + if (features & (1u << VIRTIO_F_ANY_LAYOUT)) { /* Write and read with 2 descriptor layout */ /* Write request */ -- 2.20.1 The following changes since commit 928173659d6e5dc368284f73f90ea1d129e1f57d: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20200130' into staging (2020-01-30 16:19:04 +0000) are available in the Git repository at: https://github.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to 8dff69b9415b4287e900358744b732195e1ab2e2: tests/qemu-iotests: use AIOMODE with various tests (2020-01-30 21:01:40 +0000) ---------------------------------------------------------------- Pull request ---------------------------------------------------------------- Aarushi Mehta (15): configure: permit use of io_uring qapi/block-core: add option for io_uring block/block: add BDRV flag for io_uring block/io_uring: implements interfaces for io_uring stubs: add stubs for io_uring interface util/async: add aio interfaces for io_uring blockdev: adds bdrv_parse_aio to use io_uring block/file-posix.c: extend to use io_uring block: add trace events for io_uring block/io_uring: adds userspace completion polling qemu-io: adds option to use aio engine qemu-img: adds option to use aio engine for benchmarking qemu-nbd: adds option for aio engines tests/qemu-iotests: enable testing with aio options tests/qemu-iotests: use AIOMODE with various tests Paolo Bonzini (3): block: eliminate BDRV_REQ_NO_SERIALISING block/io: wait for serialising requests when a request becomes serialising block/io: take bs->reqs_lock in bdrv_mark_request_serialising MAINTAINERS | 9 + block.c | 22 ++ block/Makefile.objs | 3 + block/file-posix.c | 99 ++++++-- block/io.c | 162 +++++++------ block/io_uring.c | 433 ++++++++++++++++++++++++++++++++++ block/trace-events | 12 + blockdev.c | 12 +- configure | 27 +++ docs/interop/qemu-nbd.rst | 4 +- include/block/aio.h | 16 +- include/block/block.h | 14 +- include/block/block_int.h | 3 +- include/block/raw-aio.h | 12 + qapi/block-core.json | 4 +- qemu-img-cmds.hx | 4 +- qemu-img.c | 11 +- qemu-img.texi | 5 +- qemu-io.c | 25 +- qemu-nbd.c | 12 +- stubs/Makefile.objs | 1 + stubs/io_uring.c | 32 +++ tests/qemu-iotests/028 | 2 +- tests/qemu-iotests/058 | 2 +- tests/qemu-iotests/089 | 4 +- tests/qemu-iotests/091 | 4 +- tests/qemu-iotests/109 | 2 +- tests/qemu-iotests/147 | 5 +- tests/qemu-iotests/181 | 8 +- tests/qemu-iotests/183 | 4 +- tests/qemu-iotests/185 | 10 +- tests/qemu-iotests/200 | 2 +- tests/qemu-iotests/201 | 8 +- tests/qemu-iotests/check | 15 +- tests/qemu-iotests/common.rc | 14 ++ tests/qemu-iotests/iotests.py | 12 +- util/async.c | 36 +++ 37 files changed, 878 insertions(+), 172 deletions(-) create mode 100644 block/io_uring.c create mode 100644 stubs/io_uring.c -- 2.24.1 From: Paolo Bonzini <pbonzini@redhat.com> It is unused since commit 00e30f0 ("block/backup: use backup-top instead of write notifiers", 2019-10-01), drop it to simplify the code. While at it, drop redundant assertions on flags. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1578495356-46219-2-git-send-email-pbonzini@redhat.com Message-Id: <1578495356-46219-2-git-send-email-pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 18 ++++-------------- include/block/block.h | 12 ------------ 2 files changed, 4 insertions(+), 26 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, * potential fallback support, if we ever implement any read flags * to pass through to drivers. For now, there aren't any * passthrough flags. */ - assert(!(flags & ~(BDRV_REQ_NO_SERIALISING | BDRV_REQ_COPY_ON_READ | - BDRV_REQ_PREFETCH))); + assert(!(flags & ~(BDRV_REQ_COPY_ON_READ | BDRV_REQ_PREFETCH))); /* Handle Copy on Read and associated serialisation */ if (flags & BDRV_REQ_COPY_ON_READ) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); } - /* BDRV_REQ_SERIALISING is only for write operation */ - assert(!(flags & BDRV_REQ_SERIALISING)); - - if (!(flags & BDRV_REQ_NO_SERIALISING)) { - bdrv_wait_serialising_requests(req); - } + bdrv_wait_serialising_requests(req); if (flags & BDRV_REQ_COPY_ON_READ) { int64_t pnum; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_preadv_part(BdrvChild *child, bdrv_inc_in_flight(bs); /* Don't do copy-on-read if we read data before write operation */ - if (atomic_read(&bs->copy_on_read) && !(flags & BDRV_REQ_NO_SERIALISING)) { + if (atomic_read(&bs->copy_on_read)) { flags |= BDRV_REQ_COPY_ON_READ; } @@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes, return -EPERM; } - /* BDRV_REQ_NO_SERIALISING is only for read operation */ - assert(!(flags & BDRV_REQ_NO_SERIALISING)); assert(!(bs->open_flags & BDRV_O_INACTIVE)); assert((bs->open_flags & BDRV_O_NO_IO) == 0); assert(!(flags & ~BDRV_REQ_MASK)); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_copy_range_internal( /* BDRV_REQ_SERIALISING is only for write operation */ assert(!(read_flags & BDRV_REQ_SERIALISING)); - if (!(read_flags & BDRV_REQ_NO_SERIALISING)) { - bdrv_wait_serialising_requests(&req); - } + bdrv_wait_serialising_requests(&req); ret = src->bs->drv->bdrv_co_copy_range_from(src->bs, src, src_offset, diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ typedef enum { */ BDRV_REQ_MAY_UNMAP = 0x4, - /* - * The BDRV_REQ_NO_SERIALISING flag is only valid for reads and means that - * we don't want wait_serialising_requests() during the read operation. - * - * This flag is used for backup copy-on-write operations, when we need to - * read old data before write (write notifier triggered). It is okay since - * we already waited for other serializing requests in the initiating write - * (see bdrv_aligned_pwritev), and it is necessary if the initiating write - * is already serializing (without the flag, the read would deadlock - * waiting for the serialising write to complete). - */ - BDRV_REQ_NO_SERIALISING = 0x8, BDRV_REQ_FUA = 0x10, BDRV_REQ_WRITE_COMPRESSED = 0x20, -- 2.24.1 From: Paolo Bonzini <pbonzini@redhat.com> Marking without waiting would not result in actual serialising behavior. Thus, make a call bdrv_mark_request_serialising sufficient for serialisation to happen. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1578495356-46219-3-git-send-email-pbonzini@redhat.com Message-Id: <1578495356-46219-3-git-send-email-pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/file-posix.c | 1 - block/io.c | 40 +++++++++++++++++---------------------- include/block/block_int.h | 3 +-- 3 files changed, 18 insertions(+), 26 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, req->overlap_bytes = req->bytes; bdrv_mark_request_serialising(req, bs->bl.request_alignment); - bdrv_wait_serialising_requests(req); } #endif diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ #define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS) static void bdrv_parent_cb_resize(BlockDriverState *bs); +static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self); static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags); @@ -XXX,XX +XXX,XX @@ static void tracked_request_begin(BdrvTrackedRequest *req, qemu_co_mutex_unlock(&bs->reqs_lock); } -void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) +bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) { int64_t overlap_offset = req->offset & ~(align - 1); uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align) @@ -XXX,XX +XXX,XX @@ void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) req->overlap_offset = MIN(req->overlap_offset, overlap_offset); req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes); -} - -static bool is_request_serialising_and_aligned(BdrvTrackedRequest *req) -{ - /* - * If the request is serialising, overlap_offset and overlap_bytes are set, - * so we can check if the request is aligned. Otherwise, don't care and - * return false. - */ - - return req->serialising && (req->offset == req->overlap_offset) && - (req->bytes == req->overlap_bytes); + return bdrv_wait_serialising_requests(req); } /** @@ -XXX,XX +XXX,XX @@ void bdrv_dec_in_flight(BlockDriverState *bs) bdrv_wakeup(bs); } -bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self) +static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self) { BlockDriverState *bs = self->bs; BdrvTrackedRequest *req; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, * it ensures that the CoR read and write operations are atomic and * guest writes cannot interleave between them. */ bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); + } else { + bdrv_wait_serialising_requests(req); } - bdrv_wait_serialising_requests(req); - if (flags & BDRV_REQ_COPY_ON_READ) { int64_t pnum; @@ -XXX,XX +XXX,XX @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, uint64_t bytes, assert(!(flags & ~BDRV_REQ_MASK)); if (flags & BDRV_REQ_SERIALISING) { - bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); + waited = bdrv_mark_request_serialising(req, bdrv_get_cluster_size(bs)); + /* + * For a misaligned request we should have already waited earlier, + * because we come after bdrv_padding_rmw_read which must be called + * with the request already marked as serialising. + */ + assert(!waited || + (req->offset == req->overlap_offset && + req->bytes == req->overlap_bytes)); + } else { + bdrv_wait_serialising_requests(req); } - waited = bdrv_wait_serialising_requests(req); - - assert(!waited || !req->serialising || - is_request_serialising_and_aligned(req)); assert(req->overlap_offset <= offset); assert(offset + bytes <= req->overlap_offset + req->overlap_bytes); assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child, padding = bdrv_init_padding(bs, offset, bytes, &pad); if (padding) { bdrv_mark_request_serialising(req, align); - bdrv_wait_serialising_requests(req); bdrv_padding_rmw_read(child, req, &pad, true); @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child, if (bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad)) { bdrv_mark_request_serialising(&req, align); - bdrv_wait_serialising_requests(&req); bdrv_padding_rmw_read(child, &req, &pad, false); } diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ extern unsigned int bdrv_drain_all_count; void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent); void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent); -bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self); -void bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align); +bool coroutine_fn bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align); BdrvTrackedRequest *coroutine_fn bdrv_co_get_self_request(BlockDriverState *bs); int get_tmp_filename(char *filename, int size); -- 2.24.1 From: Paolo Bonzini <pbonzini@redhat.com> bdrv_mark_request_serialising is writing the overlap_offset and overlap_bytes fields of BdrvTrackedRequest. Take bs->reqs_lock for the whole duration of it, and not just when waiting for serialising requests, so that tracked_request_overlaps does not look at a half-updated request. The new code does not unlock/relock around retries. This is unnecessary because a retry is always preceded by a CoQueue wait, which already releases and reacquires bs->reqs_lock. Reported-by: Peter Lieven <pl@kamp.de> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1578495356-46219-4-git-send-email-pbonzini@redhat.com Message-Id: <1578495356-46219-4-git-send-email-pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 112 ++++++++++++++++++++++++++++++----------------------- 1 file changed, 63 insertions(+), 49 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ #define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS) static void bdrv_parent_cb_resize(BlockDriverState *bs); -static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self); static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags); @@ -XXX,XX +XXX,XX @@ static void tracked_request_begin(BdrvTrackedRequest *req, qemu_co_mutex_unlock(&bs->reqs_lock); } +static bool tracked_request_overlaps(BdrvTrackedRequest *req, + int64_t offset, uint64_t bytes) +{ + /* aaaa bbbb */ + if (offset >= req->overlap_offset + req->overlap_bytes) { + return false; + } + /* bbbb aaaa */ + if (req->overlap_offset >= offset + bytes) { + return false; + } + return true; +} + +static bool coroutine_fn +bdrv_wait_serialising_requests_locked(BlockDriverState *bs, + BdrvTrackedRequest *self) +{ + BdrvTrackedRequest *req; + bool retry; + bool waited = false; + + do { + retry = false; + QLIST_FOREACH(req, &bs->tracked_requests, list) { + if (req == self || (!req->serialising && !self->serialising)) { + continue; + } + if (tracked_request_overlaps(req, self->overlap_offset, + self->overlap_bytes)) + { + /* Hitting this means there was a reentrant request, for + * example, a block driver issuing nested requests. This must + * never happen since it means deadlock. + */ + assert(qemu_coroutine_self() != req->co); + + /* If the request is already (indirectly) waiting for us, or + * will wait for us as soon as it wakes up, then just go on + * (instead of producing a deadlock in the former case). */ + if (!req->waiting_for) { + self->waiting_for = req; + qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock); + self->waiting_for = NULL; + retry = true; + waited = true; + break; + } + } + } + } while (retry); + return waited; +} + bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) { + BlockDriverState *bs = req->bs; int64_t overlap_offset = req->offset & ~(align - 1); uint64_t overlap_bytes = ROUND_UP(req->offset + req->bytes, align) - overlap_offset; + bool waited; + qemu_co_mutex_lock(&bs->reqs_lock); if (!req->serialising) { atomic_inc(&req->bs->serialising_in_flight); req->serialising = true; @@ -XXX,XX +XXX,XX @@ bool bdrv_mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) req->overlap_offset = MIN(req->overlap_offset, overlap_offset); req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes); - return bdrv_wait_serialising_requests(req); + waited = bdrv_wait_serialising_requests_locked(bs, req); + qemu_co_mutex_unlock(&bs->reqs_lock); + return waited; } /** @@ -XXX,XX +XXX,XX @@ static int bdrv_get_cluster_size(BlockDriverState *bs) } } -static bool tracked_request_overlaps(BdrvTrackedRequest *req, - int64_t offset, uint64_t bytes) -{ - /* aaaa bbbb */ - if (offset >= req->overlap_offset + req->overlap_bytes) { - return false; - } - /* bbbb aaaa */ - if (req->overlap_offset >= offset + bytes) { - return false; - } - return true; -} - void bdrv_inc_in_flight(BlockDriverState *bs) { atomic_inc(&bs->in_flight); @@ -XXX,XX +XXX,XX @@ void bdrv_dec_in_flight(BlockDriverState *bs) static bool coroutine_fn bdrv_wait_serialising_requests(BdrvTrackedRequest *self) { BlockDriverState *bs = self->bs; - BdrvTrackedRequest *req; - bool retry; bool waited = false; if (!atomic_read(&bs->serialising_in_flight)) { return false; } - do { - retry = false; - qemu_co_mutex_lock(&bs->reqs_lock); - QLIST_FOREACH(req, &bs->tracked_requests, list) { - if (req == self || (!req->serialising && !self->serialising)) { - continue; - } - if (tracked_request_overlaps(req, self->overlap_offset, - self->overlap_bytes)) - { - /* Hitting this means there was a reentrant request, for - * example, a block driver issuing nested requests. This must - * never happen since it means deadlock. - */ - assert(qemu_coroutine_self() != req->co); - - /* If the request is already (indirectly) waiting for us, or - * will wait for us as soon as it wakes up, then just go on - * (instead of producing a deadlock in the former case). */ - if (!req->waiting_for) { - self->waiting_for = req; - qemu_co_queue_wait(&req->wait_queue, &bs->reqs_lock); - self->waiting_for = NULL; - retry = true; - waited = true; - break; - } - } - } - qemu_co_mutex_unlock(&bs->reqs_lock); - } while (retry); + qemu_co_mutex_lock(&bs->reqs_lock); + waited = bdrv_wait_serialising_requests_locked(bs, self); + qemu_co_mutex_unlock(&bs->reqs_lock); return waited; } -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Reviewed-by: Maxim Levitsky <maximlevitsky@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-2-stefanha@redhat.com Message-Id: <20200120141858.587874-2-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- configure | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ xen="" xen_ctrl_version="" xen_pci_passthrough="" linux_aio="" +linux_io_uring="" cap_ng="" attr="" libattr="" @@ -XXX,XX +XXX,XX @@ for opt do ;; --enable-linux-aio) linux_aio="yes" ;; + --disable-linux-io-uring) linux_io_uring="no" + ;; + --enable-linux-io-uring) linux_io_uring="yes" + ;; --disable-attr) attr="no" ;; --enable-attr) attr="yes" @@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available: vde support for vde network netmap support for netmap network linux-aio Linux AIO support + linux-io-uring Linux io_uring support cap-ng libcap-ng support attr attr and xattr support vhost-net vhost-net kernel acceleration support @@ -XXX,XX +XXX,XX @@ EOF linux_aio=no fi fi +########################################## +# linux-io-uring probe + +if test "$linux_io_uring" != "no" ; then + if $pkg_config liburing; then + linux_io_uring_cflags=$($pkg_config --cflags liburing) + linux_io_uring_libs=$($pkg_config --libs liburing) + linux_io_uring=yes + else + if test "$linux_io_uring" = "yes" ; then + feature_not_found "linux io_uring" "Install liburing devel" + fi + linux_io_uring=no + fi +fi ########################################## # TPM emulation is only on POSIX @@ -XXX,XX +XXX,XX @@ echo "PIE $pie" echo "vde support $vde" echo "netmap support $netmap" echo "Linux AIO support $linux_aio" +echo "Linux io_uring support $linux_io_uring" echo "ATTR/XATTR support $attr" echo "Install blobs $blobs" echo "KVM support $kvm" @@ -XXX,XX +XXX,XX @@ fi if test "$linux_aio" = "yes" ; then echo "CONFIG_LINUX_AIO=y" >> $config_host_mak fi +if test "$linux_io_uring" = "yes" ; then + echo "CONFIG_LINUX_IO_URING=y" >> $config_host_mak + echo "LINUX_IO_URING_CFLAGS=$linux_io_uring_cflags" >> $config_host_mak + echo "LINUX_IO_URING_LIBS=$linux_io_uring_libs" >> $config_host_mak +fi if test "$attr" = "yes" ; then echo "CONFIG_ATTR=y" >> $config_host_mak fi -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Since io_uring is the actual name of the Linux API, we use it as enum value even though the QAPI schema conventions would prefer io-uring. Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Markus Armbruster <armbru@redhat.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-3-stefanha@redhat.com Message-Id: <20200120141858.587874-3-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qapi/block-core.json | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # # @threads: Use qemu's thread pool # @native: Use native AIO backend (only Linux and Windows) +# @io_uring: Use linux io_uring (since 5.0) # # Since: 2.9 ## { 'enum': 'BlockdevAioOptions', - 'data': [ 'threads', 'native' ] } + 'data': [ 'threads', 'native', + { 'name': 'io_uring', 'if': 'defined(CONFIG_LINUX_IO_URING)' } ] } ## # @BlockdevCacheOptions: -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Reviewed-by: Maxim Levitsky <maximlevitsky@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-4-stefanha@redhat.com Message-Id: <20200120141858.587874-4-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/block.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ typedef struct HDGeometry { ignoring the format layer */ #define BDRV_O_NO_IO 0x10000 /* don't initialize for I/O */ #define BDRV_O_AUTO_RDONLY 0x20000 /* degrade to read-only if opening read-write fails */ +#define BDRV_O_IO_URING 0x40000 /* use io_uring instead of the thread pool */ #define BDRV_O_CACHE_MASK (BDRV_O_NOCACHE | BDRV_O_NO_FLUSH) -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Aborts when sqe fails to be set as sqes cannot be returned to the ring. Adds slow path for short reads for older kernels Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-5-stefanha@redhat.com Message-Id: <20200120141858.587874-5-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 8 + block/Makefile.objs | 3 + block/io_uring.c | 401 ++++++++++++++++++++++++++++++++++++++++ include/block/aio.h | 16 +- include/block/raw-aio.h | 12 ++ 5 files changed, 439 insertions(+), 1 deletion(-) create mode 100644 block/io_uring.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: block/file-posix.c F: block/file-win32.c F: block/win32-aio.c +Linux io_uring +M: Aarushi Mehta <mehta.aaru20@gmail.com> +M: Julia Suvorova <jusual@redhat.com> +M: Stefan Hajnoczi <stefanha@redhat.com> +L: qemu-block@nongnu.org +S: Maintained +F: block/io_uring.c + qcow2 M: Kevin Wolf <kwolf@redhat.com> M: Max Reitz <mreitz@redhat.com> diff --git a/block/Makefile.objs b/block/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/block/Makefile.objs +++ b/block/Makefile.objs @@ -XXX,XX +XXX,XX @@ block-obj-y += block-backend.o snapshot.o qapi.o block-obj-$(CONFIG_WIN32) += file-win32.o win32-aio.o block-obj-$(CONFIG_POSIX) += file-posix.o block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o +block-obj-$(CONFIG_LINUX_IO_URING) += io_uring.o block-obj-y += null.o mirror.o commit.o io.o create.o block-obj-y += throttle-groups.o block-obj-$(CONFIG_LINUX) += nvme.o @@ -XXX,XX +XXX,XX @@ block-obj-$(if $(CONFIG_LZFSE),m,n) += dmg-lzfse.o dmg-lzfse.o-libs := $(LZFSE_LIBS) qcow.o-libs := -lz linux-aio.o-libs := -laio +io_uring.o-cflags := $(LINUX_IO_URING_CFLAGS) +io_uring.o-libs := $(LINUX_IO_URING_LIBS) parallels.o-cflags := $(LIBXML2_CFLAGS) parallels.o-libs := $(LIBXML2_LIBS) diff --git a/block/io_uring.c b/block/io_uring.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/block/io_uring.c @@ -XXX,XX +XXX,XX @@ +/* + * Linux io_uring support. + * + * Copyright (C) 2009 IBM, Corp. + * Copyright (C) 2009 Red Hat, Inc. + * Copyright (C) 2019 Aarushi Mehta + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include <liburing.h> +#include "qemu-common.h" +#include "block/aio.h" +#include "qemu/queue.h" +#include "block/block.h" +#include "block/raw-aio.h" +#include "qemu/coroutine.h" +#include "qapi/error.h" + +/* io_uring ring size */ +#define MAX_ENTRIES 128 + +typedef struct LuringAIOCB { + Coroutine *co; + struct io_uring_sqe sqeq; + ssize_t ret; + QEMUIOVector *qiov; + bool is_read; + QSIMPLEQ_ENTRY(LuringAIOCB) next; + + /* + * Buffered reads may require resubmission, see + * luring_resubmit_short_read(). + */ + int total_read; + QEMUIOVector resubmit_qiov; +} LuringAIOCB; + +typedef struct LuringQueue { + int plugged; + unsigned int in_queue; + unsigned int in_flight; + bool blocked; + QSIMPLEQ_HEAD(, LuringAIOCB) submit_queue; +} LuringQueue; + +typedef struct LuringState { + AioContext *aio_context; + + struct io_uring ring; + + /* io queue for submit at batch. Protected by AioContext lock. */ + LuringQueue io_q; + + /* I/O completion processing. Only runs in I/O thread. */ + QEMUBH *completion_bh; +} LuringState; + +/** + * luring_resubmit: + * + * Resubmit a request by appending it to submit_queue. The caller must ensure + * that ioq_submit() is called later so that submit_queue requests are started. + */ +static void luring_resubmit(LuringState *s, LuringAIOCB *luringcb) +{ + QSIMPLEQ_INSERT_TAIL(&s->io_q.submit_queue, luringcb, next); + s->io_q.in_queue++; +} + +/** + * luring_resubmit_short_read: + * + * Before Linux commit 9d93a3f5a0c ("io_uring: punt short reads to async + * context") a buffered I/O request with the start of the file range in the + * page cache could result in a short read. Applications need to resubmit the + * remaining read request. + * + * This is a slow path but recent kernels never take it. + */ +static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb, + int nread) +{ + QEMUIOVector *resubmit_qiov; + size_t remaining; + + /* Update read position */ + luringcb->total_read = nread; + remaining = luringcb->qiov->size - luringcb->total_read; + + /* Shorten qiov */ + resubmit_qiov = &luringcb->resubmit_qiov; + if (resubmit_qiov->iov == NULL) { + qemu_iovec_init(resubmit_qiov, luringcb->qiov->niov); + } else { + qemu_iovec_reset(resubmit_qiov); + } + qemu_iovec_concat(resubmit_qiov, luringcb->qiov, luringcb->total_read, + remaining); + + /* Update sqe */ + luringcb->sqeq.off = nread; + luringcb->sqeq.addr = (__u64)(uintptr_t)luringcb->resubmit_qiov.iov; + luringcb->sqeq.len = luringcb->resubmit_qiov.niov; + + luring_resubmit(s, luringcb); +} + +/** + * luring_process_completions: + * @s: AIO state + * + * Fetches completed I/O requests, consumes cqes and invokes their callbacks + * The function is somewhat tricky because it supports nested event loops, for + * example when a request callback invokes aio_poll(). + * + * Function schedules BH completion so it can be called again in a nested + * event loop. When there are no events left to complete the BH is being + * canceled. + * + */ +static void luring_process_completions(LuringState *s) +{ + struct io_uring_cqe *cqes; + int total_bytes; + /* + * Request completion callbacks can run the nested event loop. + * Schedule ourselves so the nested event loop will "see" remaining + * completed requests and process them. Without this, completion + * callbacks that wait for other requests using a nested event loop + * would hang forever. + * + * This workaround is needed because io_uring uses poll_wait, which + * is woken up when new events are added to the uring, thus polling on + * the same uring fd will block unless more events are received. + * + * Other leaf block drivers (drivers that access the data themselves) + * are networking based, so they poll sockets for data and run the + * correct coroutine. + */ + qemu_bh_schedule(s->completion_bh); + + while (io_uring_peek_cqe(&s->ring, &cqes) == 0) { + LuringAIOCB *luringcb; + int ret; + + if (!cqes) { + break; + } + + luringcb = io_uring_cqe_get_data(cqes); + ret = cqes->res; + io_uring_cqe_seen(&s->ring, cqes); + cqes = NULL; + + /* Change counters one-by-one because we can be nested. */ + s->io_q.in_flight--; + + /* total_read is non-zero only for resubmitted read requests */ + total_bytes = ret + luringcb->total_read; + + if (ret < 0) { + if (ret == -EINTR) { + luring_resubmit(s, luringcb); + continue; + } + } else if (!luringcb->qiov) { + goto end; + } else if (total_bytes == luringcb->qiov->size) { + ret = 0; + /* Only read/write */ + } else { + /* Short Read/Write */ + if (luringcb->is_read) { + if (ret > 0) { + luring_resubmit_short_read(s, luringcb, ret); + continue; + } else { + /* Pad with zeroes */ + qemu_iovec_memset(luringcb->qiov, total_bytes, 0, + luringcb->qiov->size - total_bytes); + ret = 0; + } + } else { + ret = -ENOSPC;; + } + } +end: + luringcb->ret = ret; + qemu_iovec_destroy(&luringcb->resubmit_qiov); + + /* + * If the coroutine is already entered it must be in ioq_submit() + * and will notice luringcb->ret has been filled in when it + * eventually runs later. Coroutines cannot be entered recursively + * so avoid doing that! + */ + if (!qemu_coroutine_entered(luringcb->co)) { + aio_co_wake(luringcb->co); + } + } + qemu_bh_cancel(s->completion_bh); +} + +static int ioq_submit(LuringState *s) +{ + int ret = 0; + LuringAIOCB *luringcb, *luringcb_next; + + while (s->io_q.in_queue > 0) { + /* + * Try to fetch sqes from the ring for requests waiting in + * the overflow queue + */ + QSIMPLEQ_FOREACH_SAFE(luringcb, &s->io_q.submit_queue, next, + luringcb_next) { + struct io_uring_sqe *sqes = io_uring_get_sqe(&s->ring); + if (!sqes) { + break; + } + /* Prep sqe for submission */ + *sqes = luringcb->sqeq; + QSIMPLEQ_REMOVE_HEAD(&s->io_q.submit_queue, next); + } + ret = io_uring_submit(&s->ring); + /* Prevent infinite loop if submission is refused */ + if (ret <= 0) { + if (ret == -EAGAIN) { + continue; + } + break; + } + s->io_q.in_flight += ret; + s->io_q.in_queue -= ret; + } + s->io_q.blocked = (s->io_q.in_queue > 0); + + if (s->io_q.in_flight) { + /* + * We can try to complete something just right away if there are + * still requests in-flight. + */ + luring_process_completions(s); + } + return ret; +} + +static void luring_process_completions_and_submit(LuringState *s) +{ + aio_context_acquire(s->aio_context); + luring_process_completions(s); + + if (!s->io_q.plugged && s->io_q.in_queue > 0) { + ioq_submit(s); + } + aio_context_release(s->aio_context); +} + +static void qemu_luring_completion_bh(void *opaque) +{ + LuringState *s = opaque; + luring_process_completions_and_submit(s); +} + +static void qemu_luring_completion_cb(void *opaque) +{ + LuringState *s = opaque; + luring_process_completions_and_submit(s); +} + +static void ioq_init(LuringQueue *io_q) +{ + QSIMPLEQ_INIT(&io_q->submit_queue); + io_q->plugged = 0; + io_q->in_queue = 0; + io_q->in_flight = 0; + io_q->blocked = false; +} + +void luring_io_plug(BlockDriverState *bs, LuringState *s) +{ + s->io_q.plugged++; +} + +void luring_io_unplug(BlockDriverState *bs, LuringState *s) +{ + assert(s->io_q.plugged); + if (--s->io_q.plugged == 0 && + !s->io_q.blocked && s->io_q.in_queue > 0) { + ioq_submit(s); + } +} + +/** + * luring_do_submit: + * @fd: file descriptor for I/O + * @luringcb: AIO control block + * @s: AIO state + * @offset: offset for request + * @type: type of request + * + * Fetches sqes from ring, adds to pending queue and preps them + * + */ +static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s, + uint64_t offset, int type) +{ + struct io_uring_sqe *sqes = &luringcb->sqeq; + + switch (type) { + case QEMU_AIO_WRITE: + io_uring_prep_writev(sqes, fd, luringcb->qiov->iov, + luringcb->qiov->niov, offset); + break; + case QEMU_AIO_READ: + io_uring_prep_readv(sqes, fd, luringcb->qiov->iov, + luringcb->qiov->niov, offset); + break; + case QEMU_AIO_FLUSH: + io_uring_prep_fsync(sqes, fd, IORING_FSYNC_DATASYNC); + break; + default: + fprintf(stderr, "%s: invalid AIO request type, aborting 0x%x.\n", + __func__, type); + abort(); + } + io_uring_sqe_set_data(sqes, luringcb); + + QSIMPLEQ_INSERT_TAIL(&s->io_q.submit_queue, luringcb, next); + s->io_q.in_queue++; + + if (!s->io_q.blocked && + (!s->io_q.plugged || + s->io_q.in_flight + s->io_q.in_queue >= MAX_ENTRIES)) { + return ioq_submit(s); + } + return 0; +} + +int coroutine_fn luring_co_submit(BlockDriverState *bs, LuringState *s, int fd, + uint64_t offset, QEMUIOVector *qiov, int type) +{ + int ret; + LuringAIOCB luringcb = { + .co = qemu_coroutine_self(), + .ret = -EINPROGRESS, + .qiov = qiov, + .is_read = (type == QEMU_AIO_READ), + }; + + ret = luring_do_submit(fd, &luringcb, s, offset, type); + if (ret < 0) { + return ret; + } + + if (luringcb.ret == -EINPROGRESS) { + qemu_coroutine_yield(); + } + return luringcb.ret; +} + +void luring_detach_aio_context(LuringState *s, AioContext *old_context) +{ + aio_set_fd_handler(old_context, s->ring.ring_fd, false, NULL, NULL, NULL, + s); + qemu_bh_delete(s->completion_bh); + s->aio_context = NULL; +} + +void luring_attach_aio_context(LuringState *s, AioContext *new_context) +{ + s->aio_context = new_context; + s->completion_bh = aio_bh_new(new_context, qemu_luring_completion_bh, s); + aio_set_fd_handler(s->aio_context, s->ring.ring_fd, false, + qemu_luring_completion_cb, NULL, NULL, s); +} + +LuringState *luring_init(Error **errp) +{ + int rc; + LuringState *s = g_new0(LuringState, 1); + struct io_uring *ring = &s->ring; + + rc = io_uring_queue_init(MAX_ENTRIES, ring, 0); + if (rc < 0) { + error_setg_errno(errp, errno, "failed to init linux io_uring ring"); + g_free(s); + return NULL; + } + + ioq_init(&s->io_q); + return s; + +} + +void luring_cleanup(LuringState *s) +{ + io_uring_queue_exit(&s->ring); + g_free(s); +} diff --git a/include/block/aio.h b/include/block/aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -XXX,XX +XXX,XX @@ typedef void IOHandler(void *opaque); struct Coroutine; struct ThreadPool; struct LinuxAioState; +struct LuringState; struct AioContext { GSource source; @@ -XXX,XX +XXX,XX @@ struct AioContext { struct ThreadPool *thread_pool; #ifdef CONFIG_LINUX_AIO - /* State for native Linux AIO. Uses aio_context_acquire/release for + /* + * State for native Linux AIO. Uses aio_context_acquire/release for * locking. */ struct LinuxAioState *linux_aio; #endif +#ifdef CONFIG_LINUX_IO_URING + /* + * State for Linux io_uring. Uses aio_context_acquire/release for + * locking. + */ + struct LuringState *linux_io_uring; +#endif /* TimerLists for calling timers - one per clock type. Has its own * locking. @@ -XXX,XX +XXX,XX @@ struct LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp); /* Return the LinuxAioState bound to this AioContext */ struct LinuxAioState *aio_get_linux_aio(AioContext *ctx); +/* Setup the LuringState bound to this AioContext */ +struct LuringState *aio_setup_linux_io_uring(AioContext *ctx, Error **errp); + +/* Return the LuringState bound to this AioContext */ +struct LuringState *aio_get_linux_io_uring(AioContext *ctx); /** * aio_timer_new_with_attrs: * @ctx: the aio context diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/raw-aio.h +++ b/include/block/raw-aio.h @@ -XXX,XX +XXX,XX @@ void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context); void laio_io_plug(BlockDriverState *bs, LinuxAioState *s); void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s); #endif +/* io_uring.c - Linux io_uring implementation */ +#ifdef CONFIG_LINUX_IO_URING +typedef struct LuringState LuringState; +LuringState *luring_init(Error **errp); +void luring_cleanup(LuringState *s); +int coroutine_fn luring_co_submit(BlockDriverState *bs, LuringState *s, int fd, + uint64_t offset, QEMUIOVector *qiov, int type); +void luring_detach_aio_context(LuringState *s, AioContext *old_context); +void luring_attach_aio_context(LuringState *s, AioContext *new_context); +void luring_io_plug(BlockDriverState *bs, LuringState *s); +void luring_io_unplug(BlockDriverState *bs, LuringState *s); +#endif #ifdef _WIN32 typedef struct QEMUWin32AIOState QEMUWin32AIOState; -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Follow linux-aio.o and stub out the block/io_uring.o APIs that will be missing when a binary is linked with obj-util-y but without block-util-y (e.g. vhost-user-gpu). For example, the stubs are necessary so that a binary using util/async.o from obj-util-y for qemu_bh_new() links successfully. In this case block/io_uring.o from block-util-y isn't needed and we can avoid dragging in the block layer by linking the stubs instead. The stub functions never get called. Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-6-stefanha@redhat.com Message-Id: <20200120141858.587874-6-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + stubs/Makefile.objs | 1 + stubs/io_uring.c | 32 ++++++++++++++++++++++++++++++++ 3 files changed, 34 insertions(+) create mode 100644 stubs/io_uring.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Stefan Hajnoczi <stefanha@redhat.com> L: qemu-block@nongnu.org S: Maintained F: block/io_uring.c +F: stubs/io_uring.c qcow2 M: Kevin Wolf <kwolf@redhat.com> diff --git a/stubs/Makefile.objs b/stubs/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/stubs/Makefile.objs +++ b/stubs/Makefile.objs @@ -XXX,XX +XXX,XX @@ stub-obj-y += iothread.o stub-obj-y += iothread-lock.o stub-obj-y += is-daemonized.o stub-obj-$(CONFIG_LINUX_AIO) += linux-aio.o +stub-obj-$(CONFIG_LINUX_IO_URING) += io_uring.o stub-obj-y += machine-init-done.o stub-obj-y += migr-blocker.o stub-obj-y += change-state-handler.o diff --git a/stubs/io_uring.c b/stubs/io_uring.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/stubs/io_uring.c @@ -XXX,XX +XXX,XX @@ +/* + * Linux io_uring support. + * + * Copyright (C) 2009 IBM, Corp. + * Copyright (C) 2009 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#include "qemu/osdep.h" +#include "block/aio.h" +#include "block/raw-aio.h" + +void luring_detach_aio_context(LuringState *s, AioContext *old_context) +{ + abort(); +} + +void luring_attach_aio_context(LuringState *s, AioContext *new_context) +{ + abort(); +} + +LuringState *luring_init(Error **errp) +{ + abort(); +} + +void luring_cleanup(LuringState *s) +{ + abort(); +} -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-7-stefanha@redhat.com Message-Id: <20200120141858.587874-7-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/async.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ aio_ctx_finalize(GSource *source) } #endif +#ifdef CONFIG_LINUX_IO_URING + if (ctx->linux_io_uring) { + luring_detach_aio_context(ctx->linux_io_uring, ctx); + luring_cleanup(ctx->linux_io_uring); + ctx->linux_io_uring = NULL; + } +#endif + assert(QSLIST_EMPTY(&ctx->scheduled_coroutines)); qemu_bh_delete(ctx->co_schedule_bh); @@ -XXX,XX +XXX,XX @@ LinuxAioState *aio_get_linux_aio(AioContext *ctx) } #endif +#ifdef CONFIG_LINUX_IO_URING +LuringState *aio_setup_linux_io_uring(AioContext *ctx, Error **errp) +{ + if (ctx->linux_io_uring) { + return ctx->linux_io_uring; + } + + ctx->linux_io_uring = luring_init(errp); + if (!ctx->linux_io_uring) { + return NULL; + } + + luring_attach_aio_context(ctx->linux_io_uring, ctx); + return ctx->linux_io_uring; +} + +LuringState *aio_get_linux_io_uring(AioContext *ctx) +{ + assert(ctx->linux_io_uring); + return ctx->linux_io_uring; +} +#endif + void aio_notify(AioContext *ctx) { /* Write e.g. bh->scheduled before reading ctx->notify_me. Pairs @@ -XXX,XX +XXX,XX @@ AioContext *aio_context_new(Error **errp) #ifdef CONFIG_LINUX_AIO ctx->linux_aio = NULL; #endif + +#ifdef CONFIG_LINUX_IO_URING + ctx->linux_io_uring = NULL; +#endif + ctx->thread_pool = NULL; qemu_rec_mutex_init(&ctx->lock); timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx); -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-8-stefanha@redhat.com Message-Id: <20200120141858.587874-8-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block.c | 22 ++++++++++++++++++++++ blockdev.c | 12 ++++-------- include/block/block.h | 1 + 3 files changed, 27 insertions(+), 8 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static BlockdevDetectZeroesOptions bdrv_parse_detect_zeroes(QemuOpts *opts, return detect_zeroes; } +/** + * Set open flags for aio engine + * + * Return 0 on success, -1 if the engine specified is invalid + */ +int bdrv_parse_aio(const char *mode, int *flags) +{ + if (!strcmp(mode, "threads")) { + /* do nothing, default */ + } else if (!strcmp(mode, "native")) { + *flags |= BDRV_O_NATIVE_AIO; +#ifdef CONFIG_LINUX_IO_URING + } else if (!strcmp(mode, "io_uring")) { + *flags |= BDRV_O_IO_URING; +#endif + } else { + return -1; + } + + return 0; +} + /** * Set open flags for a given discard mode * diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags, } if ((aio = qemu_opt_get(opts, "aio")) != NULL) { - if (!strcmp(aio, "native")) { - *bdrv_flags |= BDRV_O_NATIVE_AIO; - } else if (!strcmp(aio, "threads")) { - /* this is the default */ - } else { - error_setg(errp, "invalid aio option"); - return; + if (bdrv_parse_aio(aio, bdrv_flags) < 0) { + error_setg(errp, "invalid aio option"); + return; } } } @@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_common_drive_opts = { },{ .name = "aio", .type = QEMU_OPT_STRING, - .help = "host AIO implementation (threads, native)", + .help = "host AIO implementation (threads, native, io_uring)", },{ .name = BDRV_OPT_CACHE_WB, .type = QEMU_OPT_BOOL, diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top, void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, Error **errp); +int bdrv_parse_aio(const char *mode, int *flags); int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough); int bdrv_parse_discard_flags(const char *mode, int *flags); BdrvChild *bdrv_open_child(const char *filename, -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Reviewed-by: Maxim Levitsky <maximlevitsky@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-9-stefanha@redhat.com Message-Id: <20200120141858.587874-9-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/file-posix.c | 98 +++++++++++++++++++++++++++++++++++++--------- 1 file changed, 79 insertions(+), 19 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ typedef struct BDRVRawState { bool has_write_zeroes:1; bool discard_zeroes:1; bool use_linux_aio:1; + bool use_linux_io_uring:1; bool page_cache_inconsistent:1; bool has_fallocate; bool needs_alignment; @@ -XXX,XX +XXX,XX @@ static QemuOptsList raw_runtime_opts = { { .name = "aio", .type = QEMU_OPT_STRING, - .help = "host AIO implementation (threads, native)", + .help = "host AIO implementation (threads, native, io_uring)", }, { .name = "locking", @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, goto fail; } - aio_default = (bdrv_flags & BDRV_O_NATIVE_AIO) - ? BLOCKDEV_AIO_OPTIONS_NATIVE - : BLOCKDEV_AIO_OPTIONS_THREADS; + if (bdrv_flags & BDRV_O_NATIVE_AIO) { + aio_default = BLOCKDEV_AIO_OPTIONS_NATIVE; +#ifdef CONFIG_LINUX_IO_URING + } else if (bdrv_flags & BDRV_O_IO_URING) { + aio_default = BLOCKDEV_AIO_OPTIONS_IO_URING; +#endif + } else { + aio_default = BLOCKDEV_AIO_OPTIONS_THREADS; + } + aio = qapi_enum_parse(&BlockdevAioOptions_lookup, qemu_opt_get(opts, "aio"), aio_default, &local_err); @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, ret = -EINVAL; goto fail; } + s->use_linux_aio = (aio == BLOCKDEV_AIO_OPTIONS_NATIVE); +#ifdef CONFIG_LINUX_IO_URING + s->use_linux_io_uring = (aio == BLOCKDEV_AIO_OPTIONS_IO_URING); +#endif locking = qapi_enum_parse(&OnOffAuto_lookup, qemu_opt_get(opts, "locking"), @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, } #endif /* !defined(CONFIG_LINUX_AIO) */ +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + if (!aio_setup_linux_io_uring(bdrv_get_aio_context(bs), errp)) { + error_prepend(errp, "Unable to use io_uring: "); + goto fail; + } + } +#else + if (s->use_linux_io_uring) { + error_setg(errp, "aio=io_uring was specified, but is not supported " + "in this build."); + ret = -EINVAL; + goto fail; + } +#endif /* !defined(CONFIG_LINUX_IO_URING) */ + s->has_discard = true; s->has_write_zeroes = true; if ((bs->open_flags & BDRV_O_NOCACHE) != 0) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_prw(BlockDriverState *bs, uint64_t offset, return -EIO; /* - * Check if the underlying device requires requests to be aligned, - * and if the request we are trying to submit is aligned or not. - * If this is the case tell the low-level driver that it needs - * to copy the buffer. + * When using O_DIRECT, the request must be aligned to be able to use + * either libaio or io_uring interface. If not fail back to regular thread + * pool read/write code which emulates this for us if we + * set QEMU_AIO_MISALIGNED. */ - if (s->needs_alignment) { - if (!bdrv_qiov_is_aligned(bs, qiov)) { - type |= QEMU_AIO_MISALIGNED; + if (s->needs_alignment && !bdrv_qiov_is_aligned(bs, qiov)) { + type |= QEMU_AIO_MISALIGNED; +#ifdef CONFIG_LINUX_IO_URING + } else if (s->use_linux_io_uring) { + LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs)); + assert(qiov->size == bytes); + return luring_co_submit(bs, aio, s->fd, offset, qiov, type); +#endif #ifdef CONFIG_LINUX_AIO - } else if (s->use_linux_aio) { - LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs)); - assert(qiov->size == bytes); - return laio_co_submit(bs, aio, s->fd, offset, qiov, type); + } else if (s->use_linux_aio) { + LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs)); + assert(qiov->size == bytes); + return laio_co_submit(bs, aio, s->fd, offset, qiov, type); #endif - } } acb = (RawPosixAIOData) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset, static void raw_aio_plug(BlockDriverState *bs) { + BDRVRawState __attribute__((unused)) *s = bs->opaque; #ifdef CONFIG_LINUX_AIO - BDRVRawState *s = bs->opaque; if (s->use_linux_aio) { LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs)); laio_io_plug(bs, aio); } #endif +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs)); + luring_io_plug(bs, aio); + } +#endif } static void raw_aio_unplug(BlockDriverState *bs) { + BDRVRawState __attribute__((unused)) *s = bs->opaque; #ifdef CONFIG_LINUX_AIO - BDRVRawState *s = bs->opaque; if (s->use_linux_aio) { LinuxAioState *aio = aio_get_linux_aio(bdrv_get_aio_context(bs)); laio_io_unplug(bs, aio); } #endif +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs)); + luring_io_unplug(bs, aio); + } +#endif } static int raw_co_flush_to_disk(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static int raw_co_flush_to_disk(BlockDriverState *bs) .aio_type = QEMU_AIO_FLUSH, }; +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + LuringState *aio = aio_get_linux_io_uring(bdrv_get_aio_context(bs)); + return luring_co_submit(bs, aio, s->fd, 0, NULL, QEMU_AIO_FLUSH); + } +#endif return raw_thread_pool_submit(bs, handle_aiocb_flush, &acb); } static void raw_aio_attach_aio_context(BlockDriverState *bs, AioContext *new_context) { + BDRVRawState __attribute__((unused)) *s = bs->opaque; #ifdef CONFIG_LINUX_AIO - BDRVRawState *s = bs->opaque; if (s->use_linux_aio) { Error *local_err = NULL; if (!aio_setup_linux_aio(new_context, &local_err)) { @@ -XXX,XX +XXX,XX @@ static void raw_aio_attach_aio_context(BlockDriverState *bs, } } #endif +#ifdef CONFIG_LINUX_IO_URING + if (s->use_linux_io_uring) { + Error *local_err; + if (!aio_setup_linux_io_uring(new_context, &local_err)) { + error_reportf_err(local_err, "Unable to use linux io_uring, " + "falling back to thread pool: "); + s->use_linux_io_uring = false; + } + } +#endif } static void raw_close(BlockDriverState *bs) -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-10-stefanha@redhat.com Message-Id: <20200120141858.587874-10-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io_uring.c | 23 ++++++++++++++++++++--- block/trace-events | 12 ++++++++++++ 2 files changed, 32 insertions(+), 3 deletions(-) diff --git a/block/io_uring.c b/block/io_uring.c index XXXXXXX..XXXXXXX 100644 --- a/block/io_uring.c +++ b/block/io_uring.c @@ -XXX,XX +XXX,XX @@ #include "block/raw-aio.h" #include "qemu/coroutine.h" #include "qapi/error.h" +#include "trace.h" /* io_uring ring size */ #define MAX_ENTRIES 128 @@ -XXX,XX +XXX,XX @@ static void luring_resubmit_short_read(LuringState *s, LuringAIOCB *luringcb, QEMUIOVector *resubmit_qiov; size_t remaining; + trace_luring_resubmit_short_read(s, luringcb, nread); + /* Update read position */ luringcb->total_read = nread; remaining = luringcb->qiov->size - luringcb->total_read; @@ -XXX,XX +XXX,XX @@ static void luring_process_completions(LuringState *s) /* Change counters one-by-one because we can be nested. */ s->io_q.in_flight--; + trace_luring_process_completion(s, luringcb, ret); /* total_read is non-zero only for resubmitted read requests */ total_bytes = ret + luringcb->total_read; @@ -XXX,XX +XXX,XX @@ static int ioq_submit(LuringState *s) QSIMPLEQ_REMOVE_HEAD(&s->io_q.submit_queue, next); } ret = io_uring_submit(&s->ring); + trace_luring_io_uring_submit(s, ret); /* Prevent infinite loop if submission is refused */ if (ret <= 0) { if (ret == -EAGAIN) { @@ -XXX,XX +XXX,XX @@ static void ioq_init(LuringQueue *io_q) void luring_io_plug(BlockDriverState *bs, LuringState *s) { + trace_luring_io_plug(s); s->io_q.plugged++; } void luring_io_unplug(BlockDriverState *bs, LuringState *s) { assert(s->io_q.plugged); + trace_luring_io_unplug(s, s->io_q.blocked, s->io_q.plugged, + s->io_q.in_queue, s->io_q.in_flight); if (--s->io_q.plugged == 0 && !s->io_q.blocked && s->io_q.in_queue > 0) { ioq_submit(s); @@ -XXX,XX +XXX,XX @@ void luring_io_unplug(BlockDriverState *bs, LuringState *s) static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s, uint64_t offset, int type) { + int ret; struct io_uring_sqe *sqes = &luringcb->sqeq; switch (type) { @@ -XXX,XX +XXX,XX @@ static int luring_do_submit(int fd, LuringAIOCB *luringcb, LuringState *s, QSIMPLEQ_INSERT_TAIL(&s->io_q.submit_queue, luringcb, next); s->io_q.in_queue++; - + trace_luring_do_submit(s, s->io_q.blocked, s->io_q.plugged, + s->io_q.in_queue, s->io_q.in_flight); if (!s->io_q.blocked && (!s->io_q.plugged || s->io_q.in_flight + s->io_q.in_queue >= MAX_ENTRIES)) { - return ioq_submit(s); + ret = ioq_submit(s); + trace_luring_do_submit_done(s, ret); + return ret; } return 0; } @@ -XXX,XX +XXX,XX @@ int coroutine_fn luring_co_submit(BlockDriverState *bs, LuringState *s, int fd, .qiov = qiov, .is_read = (type == QEMU_AIO_READ), }; - + trace_luring_co_submit(bs, s, &luringcb, fd, offset, qiov ? qiov->size : 0, + type); ret = luring_do_submit(fd, &luringcb, s, offset, type); + if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ LuringState *luring_init(Error **errp) LuringState *s = g_new0(LuringState, 1); struct io_uring *ring = &s->ring; + trace_luring_init_state(s, sizeof(*s)); + rc = io_uring_queue_init(MAX_ENTRIES, ring, 0); if (rc < 0) { error_setg_errno(errp, errno, "failed to init linux io_uring ring"); @@ -XXX,XX +XXX,XX @@ void luring_cleanup(LuringState *s) { io_uring_queue_exit(&s->ring); g_free(s); + trace_luring_cleanup_state(s); } diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ qmp_block_stream(void *bs) "bs %p" file_paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "acb %p opaque %p offset %"PRId64" count %d type %d" file_copy_file_range(void *bs, int src, int64_t src_off, int dst, int64_t dst_off, int64_t bytes, int flags, int64_t ret) "bs %p src_fd %d offset %"PRIu64" dst_fd %d offset %"PRIu64" bytes %"PRIu64" flags %d ret %"PRId64 +#io_uring.c +luring_init_state(void *s, size_t size) "s %p size %zu" +luring_cleanup_state(void *s) "%p freed" +luring_io_plug(void *s) "LuringState %p plug" +luring_io_unplug(void *s, int blocked, int plugged, int queued, int inflight) "LuringState %p blocked %d plugged %d queued %d inflight %d" +luring_do_submit(void *s, int blocked, int plugged, int queued, int inflight) "LuringState %p blocked %d plugged %d queued %d inflight %d" +luring_do_submit_done(void *s, int ret) "LuringState %p submitted to kernel %d" +luring_co_submit(void *bs, void *s, void *luringcb, int fd, uint64_t offset, size_t nbytes, int type) "bs %p s %p luringcb %p fd %d offset %" PRId64 " nbytes %zd type %d" +luring_process_completion(void *s, void *aiocb, int ret) "LuringState %p luringcb %p ret %d" +luring_io_uring_submit(void *s, int ret) "LuringState %p ret %d" +luring_resubmit_short_read(void *s, void *luringcb, int nread) "LuringState %p luringcb %p nread %d" + # qcow2.c qcow2_add_task(void *co, void *bs, void *pool, const char *action, int cluster_type, uint64_t file_cluster_offset, uint64_t offset, uint64_t bytes, void *qiov, size_t qiov_offset) "co %p bs %p pool %p: %s: cluster_type %d file_cluster_offset %" PRIu64 " offset %" PRIu64 " bytes %" PRIu64 " qiov %p qiov_offset %zu" qcow2_writev_start_req(void *co, int64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d" -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-11-stefanha@redhat.com Message-Id: <20200120141858.587874-11-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io_uring.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/block/io_uring.c b/block/io_uring.c index XXXXXXX..XXXXXXX 100644 --- a/block/io_uring.c +++ b/block/io_uring.c @@ -XXX,XX +XXX,XX @@ static void qemu_luring_completion_cb(void *opaque) luring_process_completions_and_submit(s); } +static bool qemu_luring_poll_cb(void *opaque) +{ + LuringState *s = opaque; + struct io_uring_cqe *cqes; + + if (io_uring_peek_cqe(&s->ring, &cqes) == 0) { + if (cqes) { + luring_process_completions_and_submit(s); + return true; + } + } + + return false; +} + static void ioq_init(LuringQueue *io_q) { QSIMPLEQ_INIT(&io_q->submit_queue); @@ -XXX,XX +XXX,XX @@ void luring_attach_aio_context(LuringState *s, AioContext *new_context) s->aio_context = new_context; s->completion_bh = aio_bh_new(new_context, qemu_luring_completion_bh, s); aio_set_fd_handler(s->aio_context, s->ring.ring_fd, false, - qemu_luring_completion_cb, NULL, NULL, s); + qemu_luring_completion_cb, NULL, qemu_luring_poll_cb, s); } LuringState *luring_init(Error **errp) -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-12-stefanha@redhat.com Message-Id: <20200120141858.587874-12-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qemu-io.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/qemu-io.c b/qemu-io.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io.c +++ b/qemu-io.c @@ -XXX,XX +XXX,XX @@ static void open_help(void) " -C, -- use copy-on-read\n" " -n, -- disable host cache, short for -t none\n" " -U, -- force shared permissions\n" -" -k, -- use kernel AIO implementation (on Linux only)\n" +" -k, -- use kernel AIO implementation (Linux only, prefer use of -i)\n" +" -i, -- use AIO mode (threads, native or io_uring)\n" " -t, -- use the given cache mode for the image\n" " -d, -- use the given discard mode for the image\n" " -o, -- options to be given to the block driver" @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) QDict *opts; bool force_share = false; - while ((c = getopt(argc, argv, "snCro:kt:d:U")) != -1) { + while ((c = getopt(argc, argv, "snCro:ki:t:d:U")) != -1) { switch (c) { case 's': flags |= BDRV_O_SNAPSHOT; @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) return -EINVAL; } break; + case 'i': + if (bdrv_parse_aio(optarg, &flags) < 0) { + error_report("Invalid aio option: %s", optarg); + qemu_opts_reset(&empty_opts); + return -EINVAL; + } + break; case 'o': if (imageOpts) { printf("--image-opts and 'open -o' are mutually exclusive\n"); @@ -XXX,XX +XXX,XX @@ static void usage(const char *name) " -n, --nocache disable host cache, short for -t none\n" " -C, --copy-on-read enable copy-on-read\n" " -m, --misalign misalign allocations for O_DIRECT\n" -" -k, --native-aio use kernel AIO implementation (on Linux only)\n" +" -k, --native-aio use kernel AIO implementation\n" +" (Linux only, prefer use of -i)\n" +" -i, --aio=MODE use AIO mode (threads, native or io_uring)\n" " -t, --cache=MODE use the given cache mode for the image\n" " -d, --discard=MODE use the given discard mode for the image\n" " -T, --trace [[enable=]<pattern>][,events=<file>][,file=<file>]\n" @@ -XXX,XX +XXX,XX @@ static QemuOptsList file_opts = { int main(int argc, char **argv) { int readonly = 0; - const char *sopt = "hVc:d:f:rsnCmkt:T:U"; + const char *sopt = "hVc:d:f:rsnCmki:t:T:U"; const struct option lopt[] = { { "help", no_argument, NULL, 'h' }, { "version", no_argument, NULL, 'V' }, @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) { "copy-on-read", no_argument, NULL, 'C' }, { "misalign", no_argument, NULL, 'm' }, { "native-aio", no_argument, NULL, 'k' }, + { "aio", required_argument, NULL, 'i' }, { "discard", required_argument, NULL, 'd' }, { "cache", required_argument, NULL, 't' }, { "trace", required_argument, NULL, 'T' }, @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) case 'k': flags |= BDRV_O_NATIVE_AIO; break; + case 'i': + if (bdrv_parse_aio(optarg, &flags) < 0) { + error_report("Invalid aio option: %s", optarg); + exit(1); + } + break; case 't': if (bdrv_parse_cache_mode(optarg, &flags, &writethrough) < 0) { error_report("Invalid cache option: %s", optarg); -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-13-stefanha@redhat.com Message-Id: <20200120141858.587874-13-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- qemu-img-cmds.hx | 4 ++-- qemu-img.c | 11 ++++++++++- qemu-img.texi | 5 ++++- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-img-cmds.hx +++ b/qemu-img-cmds.hx @@ -XXX,XX +XXX,XX @@ STEXI ETEXI DEF("bench", img_bench, - "bench [-c count] [-d depth] [-f fmt] [--flush-interval=flush_interval] [-n] [--no-drain] [-o offset] [--pattern=pattern] [-q] [-s buffer_size] [-S step_size] [-t cache] [-w] [-U] filename") + "bench [-c count] [-d depth] [-f fmt] [--flush-interval=flush_interval] [-n] [--no-drain] [-o offset] [--pattern=pattern] [-q] [-s buffer_size] [-S step_size] [-t cache] [-i aio] [-w] [-U] filename") STEXI -@item bench [-c @var{count}] [-d @var{depth}] [-f @var{fmt}] [--flush-interval=@var{flush_interval}] [-n] [--no-drain] [-o @var{offset}] [--pattern=@var{pattern}] [-q] [-s @var{buffer_size}] [-S @var{step_size}] [-t @var{cache}] [-w] [-U] @var{filename} +@item bench [-c @var{count}] [-d @var{depth}] [-f @var{fmt}] [--flush-interval=@var{flush_interval}] [-n] [--no-drain] [-o @var{offset}] [--pattern=@var{pattern}] [-q] [-s @var{buffer_size}] [-S @var{step_size}] [-t @var{cache}] [-i @var{aio}] [-w] [-U] @var{filename} ETEXI DEF("check", img_check, diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_bench(int argc, char **argv) {"force-share", no_argument, 0, 'U'}, {0, 0, 0, 0} }; - c = getopt_long(argc, argv, ":hc:d:f:no:qs:S:t:wU", long_options, NULL); + c = getopt_long(argc, argv, ":hc:d:f:ni:o:qs:S:t:wU", long_options, + NULL); if (c == -1) { break; } @@ -XXX,XX +XXX,XX @@ static int img_bench(int argc, char **argv) case 'n': flags |= BDRV_O_NATIVE_AIO; break; + case 'i': + ret = bdrv_parse_aio(optarg, &flags); + if (ret < 0) { + error_report("Invalid aio option: %s", optarg); + ret = -1; + goto out; + } + break; case 'o': { offset = cvtnum(optarg); diff --git a/qemu-img.texi b/qemu-img.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.texi +++ b/qemu-img.texi @@ -XXX,XX +XXX,XX @@ Command description: Amends the image format specific @var{options} for the image file @var{filename}. Not all file formats support this operation. -@item bench [-c @var{count}] [-d @var{depth}] [-f @var{fmt}] [--flush-interval=@var{flush_interval}] [-n] [--no-drain] [-o @var{offset}] [--pattern=@var{pattern}] [-q] [-s @var{buffer_size}] [-S @var{step_size}] [-t @var{cache}] [-w] [-U] @var{filename} +@item bench [-c @var{count}] [-d @var{depth}] [-f @var{fmt}] [--flush-interval=@var{flush_interval}] [-n] [-i @var{aio}] [--no-drain] [-o @var{offset}] [--pattern=@var{pattern}] [-q] [-s @var{buffer_size}] [-S @var{step_size}] [-t @var{cache}] [-w] [-U] @var{filename} Run a simple sequential I/O benchmark on the specified image. If @code{-w} is specified, a write test is performed, otherwise a read test is performed. @@ -XXX,XX +XXX,XX @@ If @code{-n} is specified, the native AIO backend is used if possible. On Linux, this option only works if @code{-t none} or @code{-t directsync} is specified as well. +If @code{-i} is specified, aio option can be used to specify different AIO +backends: @var{threads}, @var{native} or @var{io_uring}. + For write tests, by default a buffer filled with zeros is written. This can be overridden with a pattern byte specified by @var{pattern}. -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Eric Blake <eblake@redhat.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-14-stefanha@redhat.com Message-Id: <20200120141858.587874-14-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- docs/interop/qemu-nbd.rst | 4 ++-- qemu-nbd.c | 12 ++++-------- 2 files changed, 6 insertions(+), 10 deletions(-) diff --git a/docs/interop/qemu-nbd.rst b/docs/interop/qemu-nbd.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/interop/qemu-nbd.rst +++ b/docs/interop/qemu-nbd.rst @@ -XXX,XX +XXX,XX @@ driver options if ``--image-opts`` is specified. .. option:: --aio=AIO - Set the asynchronous I/O mode between ``threads`` (the default) - and ``native`` (Linux only). + Set the asynchronous I/O mode between ``threads`` (the default), + ``native`` (Linux only), and ``io_uring`` (Linux 5.1+). .. option:: --discard=DISCARD diff --git a/qemu-nbd.c b/qemu-nbd.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-nbd.c +++ b/qemu-nbd.c @@ -XXX,XX +XXX,XX @@ static void usage(const char *name) " '[ID_OR_NAME]'\n" " -n, --nocache disable host cache\n" " --cache=MODE set cache mode (none, writeback, ...)\n" -" --aio=MODE set AIO mode (native or threads)\n" +" --aio=MODE set AIO mode (native, io_uring or threads)\n" " --discard=MODE set discard mode (ignore, unmap)\n" " --detect-zeroes=MODE set detect-zeroes mode (off, on, unmap)\n" " --image-opts treat FILE as a full set of image options\n" @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } seen_aio = true; - if (!strcmp(optarg, "native")) { - flags |= BDRV_O_NATIVE_AIO; - } else if (!strcmp(optarg, "threads")) { - /* this is the default */ - } else { - error_report("invalid aio mode `%s'", optarg); - exit(EXIT_FAILURE); + if (bdrv_parse_aio(optarg, &flags) < 0) { + error_report("Invalid aio mode '%s'", optarg); + exit(EXIT_FAILURE); } break; case QEMU_NBD_OPT_DISCARD: -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-15-stefanha@redhat.com Message-Id: <20200120141858.587874-15-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qemu-iotests/check | 15 ++++++++++++++- tests/qemu-iotests/common.rc | 14 ++++++++++++++ tests/qemu-iotests/iotests.py | 12 ++++++++++-- 3 files changed, 38 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ sortme=false expunge=true have_test_arg=false cachemode=false +aiomode=false tmp="${TEST_DIR}"/$$ rm -f $tmp.list $tmp.tmp $tmp.sed @@ -XXX,XX +XXX,XX @@ export IMGFMT_GENERIC=true export IMGPROTO=file export IMGOPTS="" export CACHEMODE="writeback" +export AIOMODE="threads" export QEMU_IO_OPTIONS="" export QEMU_IO_OPTIONS_NO_FMT="" export CACHEMODE_IS_DEFAULT=true @@ -XXX,XX +XXX,XX @@ s/ .*//p CACHEMODE_IS_DEFAULT=false cachemode=false continue + elif $aiomode + then + AIOMODE="$r" + aiomode=false + continue fi xpand=true @@ -XXX,XX +XXX,XX @@ other options -n show me, do not run tests -o options -o options to pass to qemu-img create/convert -c mode cache mode + -i mode AIO mode -makecheck pretty print output for make check testlist options @@ -XXX,XX +XXX,XX @@ testlist options cachemode=true xpand=false ;; + -i) + aiomode=true + xpand=false + ;; -T) # deprecated timestamp option xpand=false ;; - -v) verbose=true xpand=false @@ -XXX,XX +XXX,XX @@ done # Set qemu-io cache mode with $CACHEMODE we have QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS --cache $CACHEMODE" +# Set qemu-io aio mode with $AIOMODE we have +QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS --aio $AIOMODE" QEMU_IO_OPTIONS_NO_FMT="$QEMU_IO_OPTIONS" if [ "$IMGOPTSSYNTAX" != "true" ]; then diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _default_cache_mode() return fi } +_supported_aio_modes() +{ + for mode; do + if [ "$mode" = "$AIOMODE" ]; then + return + fi + done + _notrun "not suitable for aio mode: $AIOMODE" +} +_default_aio_mode() +{ + AIOMODE="$1" + QEMU_IO="$QEMU_IO --aio $1" +} _unsupported_imgopts() { diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ test_dir = os.environ.get('TEST_DIR') sock_dir = os.environ.get('SOCK_DIR') output_dir = os.environ.get('OUTPUT_DIR', '.') cachemode = os.environ.get('CACHEMODE') +aiomode = os.environ.get('AIOMODE') qemu_default_machine = os.environ.get('QEMU_DEFAULT_MACHINE') socket_scm_helper = os.environ.get('SOCKET_SCM_HELPER', 'socket_scm_helper') @@ -XXX,XX +XXX,XX @@ class VM(qtest.QEMUQtestMachine): options.append('file=%s' % path) options.append('format=%s' % format) options.append('cache=%s' % cachemode) + options.append('aio=%s' % aiomode) if opts: options.append(opts) @@ -XXX,XX +XXX,XX @@ def verify_cache_mode(supported_cache_modes=[]): if supported_cache_modes and (cachemode not in supported_cache_modes): notrun('not suitable for this cache mode: %s' % cachemode) +def verify_aio_mode(supported_aio_modes=[]): + if supported_aio_modes and (aiomode not in supported_aio_modes): + notrun('not suitable for this aio mode: %s' % aiomode) + def supports_quorum(): return 'quorum' in qemu_img_pipe('--help') @@ -XXX,XX +XXX,XX @@ def execute_unittest(output, verbosity, debug): def execute_test(test_function=None, supported_fmts=[], supported_oses=['linux'], - supported_cache_modes=[], unsupported_fmts=[], - supported_protocols=[], unsupported_protocols=[]): + supported_cache_modes=[], supported_aio_modes={}, + unsupported_fmts=[], supported_protocols=[], + unsupported_protocols=[]): """Run either unittest or script-style tests.""" # We are using TEST_DIR and QEMU_DEFAULT_MACHINE as proxies to @@ -XXX,XX +XXX,XX @@ def execute_test(test_function=None, verify_protocol(supported_protocols, unsupported_protocols) verify_platform(supported_oses) verify_cache_mode(supported_cache_modes) + verify_aio_mode(supported_aio_modes) if debug: output = sys.stdout -- 2.24.1 From: Aarushi Mehta <mehta.aaru20@gmail.com> Signed-off-by: Aarushi Mehta <mehta.aaru20@gmail.com> Acked-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200120141858.587874-16-stefanha@redhat.com Message-Id: <20200120141858.587874-16-stefanha@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qemu-iotests/028 | 2 +- tests/qemu-iotests/058 | 2 +- tests/qemu-iotests/089 | 4 ++-- tests/qemu-iotests/091 | 4 ++-- tests/qemu-iotests/109 | 2 +- tests/qemu-iotests/147 | 5 +++-- tests/qemu-iotests/181 | 8 ++++---- tests/qemu-iotests/183 | 4 ++-- tests/qemu-iotests/185 | 10 +++++----- tests/qemu-iotests/200 | 2 +- tests/qemu-iotests/201 | 8 ++++---- 11 files changed, 26 insertions(+), 25 deletions(-) diff --git a/tests/qemu-iotests/028 b/tests/qemu-iotests/028 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/028 +++ b/tests/qemu-iotests/028 @@ -XXX,XX +XXX,XX @@ echo block-backup echo qemu_comm_method="monitor" -_launch_qemu -drive file="${TEST_IMG}",cache=${CACHEMODE},id=disk +_launch_qemu -drive file="${TEST_IMG}",cache=${CACHEMODE},aio=${AIOMODE},id=disk h=$QEMU_HANDLE if [ "${VALGRIND_QEMU}" == "y" ]; then QEMU_COMM_TIMEOUT=7 diff --git a/tests/qemu-iotests/058 b/tests/qemu-iotests/058 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/058 +++ b/tests/qemu-iotests/058 @@ -XXX,XX +XXX,XX @@ nbd_snapshot_img="nbd:unix:$nbd_unix_socket" converted_image=$TEST_IMG.converted # Use -f raw instead of -f $IMGFMT for the NBD connection -QEMU_IO_NBD="$QEMU_IO -f raw --cache=$CACHEMODE" +QEMU_IO_NBD="$QEMU_IO -f raw --cache=$CACHEMODE --aio=$AIOMODE" echo echo "== preparing image ==" diff --git a/tests/qemu-iotests/089 b/tests/qemu-iotests/089 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/089 +++ b/tests/qemu-iotests/089 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'write -P 42 0 512' -c 'write -P 23 512 512' \ $QEMU_IMG convert -f raw -O $IMGFMT "$TEST_IMG.base" "$TEST_IMG" -$QEMU_IO_PROG --cache $CACHEMODE \ +$QEMU_IO_PROG --cache $CACHEMODE --aio $AIOMODE \ -c 'read -P 42 0 512' -c 'read -P 23 512 512' \ -c 'read -P 66 1024 512' "json:{ \"driver\": \"$IMGFMT\", @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'write -P 42 0x38000 512' "$TEST_IMG" | _filter_qemu_io # The "image.filename" part tests whether "a": { "b": "c" } and "a.b": "c" do # the same (which they should). -$QEMU_IO_PROG --cache $CACHEMODE \ +$QEMU_IO_PROG --cache $CACHEMODE --aio $AIOMODE \ -c 'read -P 42 0x38000 512' "json:{ \"driver\": \"$IMGFMT\", \"file\": { diff --git a/tests/qemu-iotests/091 b/tests/qemu-iotests/091 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/091 +++ b/tests/qemu-iotests/091 @@ -XXX,XX +XXX,XX @@ echo === Starting QEMU VM1 === echo qemu_comm_method="monitor" -_launch_qemu -drive file="${TEST_IMG}",cache=${CACHEMODE},id=disk +_launch_qemu -drive file="${TEST_IMG}",cache=${CACHEMODE},aio=${AIOMODE},id=disk h1=$QEMU_HANDLE echo echo === Starting QEMU VM2 === echo -_launch_qemu -drive file="${TEST_IMG}",cache=${CACHEMODE},id=disk \ +_launch_qemu -drive file="${TEST_IMG}",cache=${CACHEMODE},aio=${AIOMODE},id=disk \ -incoming "exec: cat '${MIG_FIFO}'" h2=$QEMU_HANDLE diff --git a/tests/qemu-iotests/109 b/tests/qemu-iotests/109 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/109 +++ b/tests/qemu-iotests/109 @@ -XXX,XX +XXX,XX @@ run_qemu() local qmp_format="$3" local qmp_event="$4" - _launch_qemu -drive file="${source_img}",format=raw,cache=${CACHEMODE},id=src + _launch_qemu -drive file="${source_img}",format=raw,cache=${CACHEMODE},aio=${AIOMODE},id=src _send_qemu_cmd $QEMU_HANDLE "{ 'execute': 'qmp_capabilities' }" "return" _send_qemu_cmd $QEMU_HANDLE \ diff --git a/tests/qemu-iotests/147 b/tests/qemu-iotests/147 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/147 +++ b/tests/qemu-iotests/147 @@ -XXX,XX +XXX,XX @@ import socket import stat import time import iotests -from iotests import cachemode, imgfmt, qemu_img, qemu_nbd, qemu_nbd_early_pipe +from iotests import cachemode, aiomode, imgfmt, qemu_img, qemu_nbd, qemu_nbd_early_pipe NBD_PORT_START = 32768 NBD_PORT_END = NBD_PORT_START + 1024 @@ -XXX,XX +XXX,XX @@ class BuiltinNBD(NBDBlockdevAddBase): self.server.add_drive_raw('if=none,id=nbd-export,' + 'file=%s,' % test_img + 'format=%s,' % imgfmt + - 'cache=%s' % cachemode) + 'cache=%s' % cachemode + + 'aio=%s' % aiomode) self.server.launch() def tearDown(self): diff --git a/tests/qemu-iotests/181 b/tests/qemu-iotests/181 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/181 +++ b/tests/qemu-iotests/181 @@ -XXX,XX +XXX,XX @@ qemu_comm_method="monitor" if [ "$IMGOPTSSYNTAX" = "true" ]; then _launch_qemu \ - -drive "${TEST_IMG}",cache=${CACHEMODE},id=disk + -drive "${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,id=disk else _launch_qemu \ - -drive file="${TEST_IMG}",cache=${CACHEMODE},driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,driver=$IMGFMT,id=disk fi src=$QEMU_HANDLE if [ "$IMGOPTSSYNTAX" = "true" ]; then _launch_qemu \ - -drive "${TEST_IMG}",cache=${CACHEMODE},id=disk \ + -drive "${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,id=disk \ -incoming "unix:${MIG_SOCKET}" else _launch_qemu \ - -drive file="${TEST_IMG}",cache=${CACHEMODE},driver=$IMGFMT,id=disk \ + -drive file="${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,driver=$IMGFMT,id=disk \ -incoming "unix:${MIG_SOCKET}" fi dest=$QEMU_HANDLE diff --git a/tests/qemu-iotests/183 b/tests/qemu-iotests/183 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/183 +++ b/tests/qemu-iotests/183 @@ -XXX,XX +XXX,XX @@ echo qemu_comm_method="qmp" _launch_qemu \ - -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}",cache=$CACHEMODE,aio=$AIOMODE,driver=$IMGFMT,id=disk src=$QEMU_HANDLE _send_qemu_cmd $src "{ 'execute': 'qmp_capabilities' }" 'return' _launch_qemu \ - -drive file="${TEST_IMG}.dest",cache=$CACHEMODE,driver=$IMGFMT,id=disk \ + -drive file="${TEST_IMG}.dest",cache=$CACHEMODE,aio=$AIOMODE,driver=$IMGFMT,id=disk \ -incoming "unix:${MIG_SOCKET}" dest=$QEMU_HANDLE _send_qemu_cmd $dest "{ 'execute': 'qmp_capabilities' }" 'return' diff --git a/tests/qemu-iotests/185 b/tests/qemu-iotests/185 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/185 +++ b/tests/qemu-iotests/185 @@ -XXX,XX +XXX,XX @@ echo qemu_comm_method="qmp" _launch_qemu \ - -drive file="${TEST_IMG}.base",cache=$CACHEMODE,driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}.base",cache=$CACHEMODE,aio=$AIOMODE,driver=$IMGFMT,id=disk h=$QEMU_HANDLE _send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' @@ -XXX,XX +XXX,XX @@ echo === Start active commit job and exit qemu === echo _launch_qemu \ - -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}",cache=$CACHEMODE,aio=$AIOMODE,driver=$IMGFMT,id=disk h=$QEMU_HANDLE _send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' @@ -XXX,XX +XXX,XX @@ echo === Start mirror job and exit qemu === echo _launch_qemu \ - -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}",cache=$CACHEMODE,aio=$AIOMODE,driver=$IMGFMT,id=disk h=$QEMU_HANDLE _send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' @@ -XXX,XX +XXX,XX @@ echo === Start backup job and exit qemu === echo _launch_qemu \ - -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}",cache=$CACHEMODE,aio=$AIOMODE,driver=$IMGFMT,id=disk h=$QEMU_HANDLE _send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' @@ -XXX,XX +XXX,XX @@ echo === Start streaming job and exit qemu === echo _launch_qemu \ - -drive file="${TEST_IMG}",cache=$CACHEMODE,driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}",cache=$CACHEMODE,aio=$AIOMODE,driver=$IMGFMT,id=disk h=$QEMU_HANDLE _send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" 'return' diff --git a/tests/qemu-iotests/200 b/tests/qemu-iotests/200 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/200 +++ b/tests/qemu-iotests/200 @@ -XXX,XX +XXX,XX @@ echo === Starting QEMU VM === echo qemu_comm_method="qmp" _launch_qemu -object iothread,id=iothread0 $virtio_scsi \ - -drive file="${TEST_IMG}",media=disk,if=none,cache=$CACHEMODE,id=drive_sysdisk,format=$IMGFMT \ + -drive file="${TEST_IMG}",media=disk,if=none,cache=$CACHEMODE,aio=$AIOMODE,id=drive_sysdisk,format=$IMGFMT \ -device scsi-hd,drive=drive_sysdisk,bus=scsi0.0,id=sysdisk,bootindex=0 h1=$QEMU_HANDLE diff --git a/tests/qemu-iotests/201 b/tests/qemu-iotests/201 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/201 +++ b/tests/qemu-iotests/201 @@ -XXX,XX +XXX,XX @@ qemu_comm_method="monitor" if [ "$IMGOPTSSYNTAX" = "true" ]; then _launch_qemu \ - -drive "${TEST_IMG}",cache=${CACHEMODE},id=disk + -drive "${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,id=disk else _launch_qemu \ - -drive file="${TEST_IMG}",cache=${CACHEMODE},driver=$IMGFMT,id=disk + -drive file="${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,driver=$IMGFMT,id=disk fi src=$QEMU_HANDLE if [ "$IMGOPTSSYNTAX" = "true" ]; then _launch_qemu \ - -drive "${TEST_IMG}",cache=${CACHEMODE},id=disk \ + -drive "${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,id=disk \ -incoming "unix:${MIG_SOCKET}" else _launch_qemu \ - -drive file="${TEST_IMG}",cache=${CACHEMODE},driver=$IMGFMT,id=disk \ + -drive file="${TEST_IMG}",cache=${CACHEMODE},aio=$AIOMODE,driver=$IMGFMT,id=disk \ -incoming "unix:${MIG_SOCKET}" fi dest=$QEMU_HANDLE -- 2.24.1