From d953169d4840f312d3b9a54952f4a7ccfcb3b311 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Tue, 4 Jun 2019 19:15:03 +0300 Subject: util/iov: introduce qemu_iovec_init_extended Introduce new initialization API, to create requests with padding. Will be used in the following patch. New API uses qemu_iovec_init_buf if resulting io vector has only one element, to avoid extra allocations. So, we need to update qemu_iovec_destroy to support destroying such QIOVs. Signed-off-by: Vladimir Sementsov-Ogievskiy Acked-by: Stefan Hajnoczi Message-id: 20190604161514.262241-2-vsementsov@virtuozzo.com Message-Id: <20190604161514.262241-2-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi --- include/qemu/iov.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/qemu/iov.h b/include/qemu/iov.h index 48b45987b7..f3787a0cf7 100644 --- a/include/qemu/iov.h +++ b/include/qemu/iov.h @@ -199,6 +199,13 @@ static inline void *qemu_iovec_buf(QEMUIOVector *qiov) void qemu_iovec_init(QEMUIOVector *qiov, int alloc_hint); void qemu_iovec_init_external(QEMUIOVector *qiov, struct iovec *iov, int niov); +void qemu_iovec_init_extended( + QEMUIOVector *qiov, + void *head_buf, size_t head_len, + QEMUIOVector *mid_qiov, size_t mid_offset, size_t mid_len, + void *tail_buf, size_t tail_len); +void qemu_iovec_init_slice(QEMUIOVector *qiov, QEMUIOVector *source, + size_t offset, size_t len); void qemu_iovec_add(QEMUIOVector *qiov, void *base, size_t len); void qemu_iovec_concat(QEMUIOVector *dst, QEMUIOVector *src, size_t soffset, size_t sbytes); -- cgit v1.2.3-55-g7522 From f76889e7b947d896db51be8a4d9c941c2f70365a Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Tue, 4 Jun 2019 19:15:04 +0300 Subject: util/iov: improve qemu_iovec_is_zero We'll need to check a part of qiov soon, so implement it now. Optimization with align down to 4 * sizeof(long) is dropped due to: 1. It is strange: it aligns length of the buffer, but where is a guarantee that buffer pointer is aligned itself? 2. buffer_is_zero() is a better place for optimizations and it has them. Signed-off-by: Vladimir Sementsov-Ogievskiy Acked-by: Stefan Hajnoczi Message-id: 20190604161514.262241-3-vsementsov@virtuozzo.com Message-Id: <20190604161514.262241-3-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi --- block/io.c | 2 +- include/qemu/iov.h | 2 +- util/iov.c | 31 +++++++++++++++++++------------ 3 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/block/io.c b/block/io.c index 56bbf195bb..f656fb2dce 100644 --- a/block/io.c +++ b/block/io.c @@ -1722,7 +1722,7 @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child, if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF && !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_pwrite_zeroes && - qemu_iovec_is_zero(qiov)) { + qemu_iovec_is_zero(qiov, 0, qiov->size)) { flags |= BDRV_REQ_ZERO_WRITE; if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) { flags |= BDRV_REQ_MAY_UNMAP; diff --git a/include/qemu/iov.h b/include/qemu/iov.h index f3787a0cf7..29957c8a72 100644 --- a/include/qemu/iov.h +++ b/include/qemu/iov.h @@ -212,7 +212,7 @@ void qemu_iovec_concat(QEMUIOVector *dst, size_t qemu_iovec_concat_iov(QEMUIOVector *dst, struct iovec *src_iov, unsigned int src_cnt, size_t soffset, size_t sbytes); -bool qemu_iovec_is_zero(QEMUIOVector *qiov); +bool qemu_iovec_is_zero(QEMUIOVector *qiov, size_t qiov_offeset, size_t bytes); void qemu_iovec_destroy(QEMUIOVector *qiov); void qemu_iovec_reset(QEMUIOVector *qiov); size_t qemu_iovec_to_buf(QEMUIOVector *qiov, size_t offset, diff --git a/util/iov.c b/util/iov.c index 366ff9cdd1..9ac0261853 100644 --- a/util/iov.c +++ b/util/iov.c @@ -451,23 +451,30 @@ void qemu_iovec_init_extended( } /* - * Check if the contents of the iovecs are all zero + * Check if the contents of subrange of qiov data is all zeroes. */ -bool qemu_iovec_is_zero(QEMUIOVector *qiov) +bool qemu_iovec_is_zero(QEMUIOVector *qiov, size_t offset, size_t bytes) { - int i; - for (i = 0; i < qiov->niov; i++) { - size_t offs = QEMU_ALIGN_DOWN(qiov->iov[i].iov_len, 4 * sizeof(long)); - uint8_t *ptr = qiov->iov[i].iov_base; - if (offs && !buffer_is_zero(qiov->iov[i].iov_base, offs)) { + struct iovec *iov; + size_t current_offset; + + assert(offset + bytes <= qiov->size); + + iov = iov_skip_offset(qiov->iov, offset, ¤t_offset); + + while (bytes) { + uint8_t *base = (uint8_t *)iov->iov_base + current_offset; + size_t len = MIN(iov->iov_len - current_offset, bytes); + + if (!buffer_is_zero(base, len)) { return false; } - for (; offs < qiov->iov[i].iov_len; offs++) { - if (ptr[offs]) { - return false; - } - } + + current_offset = 0; + bytes -= len; + iov++; } + return true; } -- cgit v1.2.3-55-g7522 From ac850bf099f8a356788d487c5205345dfd755fca Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Tue, 4 Jun 2019 19:15:06 +0300 Subject: block: define .*_part io handlers in BlockDriver Add handlers supporting qiov_offset parameter: bdrv_co_preadv_part bdrv_co_pwritev_part bdrv_co_pwritev_compressed_part This is used to reduce need of defining local_qiovs and hd_qiovs in all corners of block layer code. The following patches will increase usage of this new API part by part. Signed-off-by: Vladimir Sementsov-Ogievskiy Acked-by: Stefan Hajnoczi Message-id: 20190604161514.262241-5-vsementsov@virtuozzo.com Message-Id: <20190604161514.262241-5-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi --- block/backup.c | 2 +- block/io.c | 96 +++++++++++++++++++++++++++++++++++++---------- include/block/block_int.h | 15 ++++++++ qemu-img.c | 4 +- 4 files changed, 95 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/block/backup.c b/block/backup.c index 2baf7bed65..03637aeb11 100644 --- a/block/backup.c +++ b/block/backup.c @@ -674,7 +674,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, return NULL; } - if (compress && target->drv->bdrv_co_pwritev_compressed == NULL) { + if (compress && !block_driver_can_compress(target->drv)) { error_setg(errp, "Compression is not supported for this drive %s", bdrv_get_device_name(target)); return NULL; diff --git a/block/io.c b/block/io.c index 04e69400d8..fd2fc7d5ff 100644 --- a/block/io.c +++ b/block/io.c @@ -146,7 +146,8 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp) /* Default alignment based on whether driver has byte interface */ bs->bl.request_alignment = (drv->bdrv_co_preadv || - drv->bdrv_aio_preadv) ? 1 : 512; + drv->bdrv_aio_preadv || + drv->bdrv_co_preadv_part) ? 1 : 512; /* Take some limits from the children as a default */ if (bs->file) { @@ -1044,11 +1045,14 @@ static void bdrv_co_io_em_complete(void *opaque, int ret) static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) + QEMUIOVector *qiov, + size_t qiov_offset, int flags) { BlockDriver *drv = bs->drv; int64_t sector_num; unsigned int nb_sectors; + QEMUIOVector local_qiov; + int ret; assert(!(flags & ~BDRV_REQ_MASK)); assert(!(flags & BDRV_REQ_NO_FALLBACK)); @@ -1057,8 +1061,19 @@ static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs, return -ENOMEDIUM; } + if (drv->bdrv_co_preadv_part) { + return drv->bdrv_co_preadv_part(bs, offset, bytes, qiov, qiov_offset, + flags); + } + + if (qiov_offset > 0 || bytes != qiov->size) { + qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes); + qiov = &local_qiov; + } + if (drv->bdrv_co_preadv) { - return drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags); + ret = drv->bdrv_co_preadv(bs, offset, bytes, qiov, flags); + goto out; } if (drv->bdrv_aio_preadv) { @@ -1070,10 +1085,12 @@ static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs, acb = drv->bdrv_aio_preadv(bs, offset, bytes, qiov, flags, bdrv_co_io_em_complete, &co); if (acb == NULL) { - return -EIO; + ret = -EIO; + goto out; } else { qemu_coroutine_yield(); - return co.ret; + ret = co.ret; + goto out; } } @@ -1085,16 +1102,25 @@ static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs, assert(bytes <= BDRV_REQUEST_MAX_BYTES); assert(drv->bdrv_co_readv); - return drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov); + ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov); + +out: + if (qiov == &local_qiov) { + qemu_iovec_destroy(&local_qiov); + } + + return ret; } static int coroutine_fn bdrv_driver_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, int flags) + QEMUIOVector *qiov, + size_t qiov_offset, int flags) { BlockDriver *drv = bs->drv; int64_t sector_num; unsigned int nb_sectors; + QEMUIOVector local_qiov; int ret; assert(!(flags & ~BDRV_REQ_MASK)); @@ -1104,6 +1130,18 @@ static int coroutine_fn bdrv_driver_pwritev(BlockDriverState *bs, return -ENOMEDIUM; } + if (drv->bdrv_co_pwritev_part) { + ret = drv->bdrv_co_pwritev_part(bs, offset, bytes, qiov, qiov_offset, + flags & bs->supported_write_flags); + flags &= ~bs->supported_write_flags; + goto emulate_flags; + } + + if (qiov_offset > 0 || bytes != qiov->size) { + qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes); + qiov = &local_qiov; + } + if (drv->bdrv_co_pwritev) { ret = drv->bdrv_co_pwritev(bs, offset, bytes, qiov, flags & bs->supported_write_flags); @@ -1147,24 +1185,44 @@ emulate_flags: ret = bdrv_co_flush(bs); } + if (qiov == &local_qiov) { + qemu_iovec_destroy(&local_qiov); + } + return ret; } static int coroutine_fn bdrv_driver_pwritev_compressed(BlockDriverState *bs, uint64_t offset, - uint64_t bytes, QEMUIOVector *qiov) + uint64_t bytes, QEMUIOVector *qiov, + size_t qiov_offset) { BlockDriver *drv = bs->drv; + QEMUIOVector local_qiov; + int ret; if (!drv) { return -ENOMEDIUM; } - if (!drv->bdrv_co_pwritev_compressed) { + if (!block_driver_can_compress(drv)) { return -ENOTSUP; } - return drv->bdrv_co_pwritev_compressed(bs, offset, bytes, qiov); + if (drv->bdrv_co_pwritev_compressed_part) { + return drv->bdrv_co_pwritev_compressed_part(bs, offset, bytes, + qiov, qiov_offset); + } + + if (qiov_offset == 0) { + return drv->bdrv_co_pwritev_compressed(bs, offset, bytes, qiov); + } + + qemu_iovec_init_slice(&local_qiov, qiov, qiov_offset, bytes); + ret = drv->bdrv_co_pwritev_compressed(bs, offset, bytes, &local_qiov); + qemu_iovec_destroy(&local_qiov); + + return ret; } static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, @@ -1249,7 +1307,7 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, qemu_iovec_init_buf(&local_qiov, bounce_buffer, pnum); ret = bdrv_driver_preadv(bs, cluster_offset, pnum, - &local_qiov, 0); + &local_qiov, 0, 0); if (ret < 0) { goto err; } @@ -1267,7 +1325,7 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, * necessary to flush even in cache=writethrough mode. */ ret = bdrv_driver_pwritev(bs, cluster_offset, pnum, - &local_qiov, + &local_qiov, 0, BDRV_REQ_WRITE_UNCHANGED); } @@ -1289,7 +1347,7 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, qemu_iovec_init(&local_qiov, qiov->niov); qemu_iovec_concat(&local_qiov, qiov, progress, pnum - skip_bytes); ret = bdrv_driver_preadv(bs, offset + progress, local_qiov.size, - &local_qiov, 0); + &local_qiov, 0, 0); qemu_iovec_destroy(&local_qiov); if (ret < 0) { goto err; @@ -1380,7 +1438,7 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align); if (bytes <= max_bytes && bytes <= max_transfer) { - ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0); + ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0, 0); goto out; } @@ -1396,7 +1454,7 @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, qemu_iovec_concat(&local_qiov, qiov, bytes - bytes_remaining, num); ret = bdrv_driver_preadv(bs, offset + bytes - bytes_remaining, - num, &local_qiov, 0); + num, &local_qiov, 0, 0); max_bytes -= num; qemu_iovec_destroy(&local_qiov); } else { @@ -1701,7 +1759,7 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, } qemu_iovec_init_buf(&qiov, buf, num); - ret = bdrv_driver_pwritev(bs, offset, num, &qiov, write_flags); + ret = bdrv_driver_pwritev(bs, offset, num, &qiov, 0, write_flags); /* Keep bounce buffer around if it is big enough for all * all future requests. @@ -1857,10 +1915,10 @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child, bdrv_debug_event(bs, BLKDBG_PWRITEV_ZERO); ret = bdrv_co_do_pwrite_zeroes(bs, offset, bytes, flags); } else if (flags & BDRV_REQ_WRITE_COMPRESSED) { - ret = bdrv_driver_pwritev_compressed(bs, offset, bytes, qiov); + ret = bdrv_driver_pwritev_compressed(bs, offset, bytes, qiov, 0); } else if (bytes <= max_transfer) { bdrv_debug_event(bs, BLKDBG_PWRITEV); - ret = bdrv_driver_pwritev(bs, offset, bytes, qiov, flags); + ret = bdrv_driver_pwritev(bs, offset, bytes, qiov, 0, flags); } else { bdrv_debug_event(bs, BLKDBG_PWRITEV); while (bytes_remaining) { @@ -1879,7 +1937,7 @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child, qemu_iovec_concat(&local_qiov, qiov, bytes - bytes_remaining, num); ret = bdrv_driver_pwritev(bs, offset + bytes - bytes_remaining, - num, &local_qiov, local_flags); + num, &local_qiov, 0, local_flags); qemu_iovec_destroy(&local_qiov); if (ret < 0) { break; diff --git a/include/block/block_int.h b/include/block/block_int.h index ceec8c2f56..79a1fdb258 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -210,6 +210,9 @@ struct BlockDriver { */ int coroutine_fn (*bdrv_co_preadv)(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags); + int coroutine_fn (*bdrv_co_preadv_part)(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, size_t qiov_offset, int flags); int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, int flags); /** @@ -229,6 +232,9 @@ struct BlockDriver { */ int coroutine_fn (*bdrv_co_pwritev)(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags); + int coroutine_fn (*bdrv_co_pwritev_part)(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, size_t qiov_offset, int flags); /* * Efficiently zero a region of the disk image. Typically an image format @@ -339,6 +345,9 @@ struct BlockDriver { int coroutine_fn (*bdrv_co_pwritev_compressed)(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov); + int coroutine_fn (*bdrv_co_pwritev_compressed_part)(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, + size_t qiov_offset); int (*bdrv_snapshot_create)(BlockDriverState *bs, QEMUSnapshotInfo *sn_info); @@ -570,6 +579,12 @@ struct BlockDriver { const char *const *strong_runtime_opts; }; +static inline bool block_driver_can_compress(BlockDriver *drv) +{ + return drv->bdrv_co_pwritev_compressed || + drv->bdrv_co_pwritev_compressed_part; +} + typedef struct BlockLimits { /* Alignment requirement, in bytes, for offset/length of I/O * requests. Must be a power of 2 less than INT_MAX; defaults to diff --git a/qemu-img.c b/qemu-img.c index 7daa05e51a..4ee436fc94 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -2388,7 +2388,7 @@ static int img_convert(int argc, char **argv) const char *preallocation = qemu_opt_get(opts, BLOCK_OPT_PREALLOC); - if (drv && !drv->bdrv_co_pwritev_compressed) { + if (drv && !block_driver_can_compress(drv)) { error_report("Compression not supported for this file format"); ret = -1; goto out; @@ -2459,7 +2459,7 @@ static int img_convert(int argc, char **argv) } out_bs = blk_bs(s.target); - if (s.compressed && !out_bs->drv->bdrv_co_pwritev_compressed) { + if (s.compressed && !block_driver_can_compress(out_bs->drv)) { error_report("Compression not supported for this file format"); ret = -1; goto out; -- cgit v1.2.3-55-g7522 From 1acc3466a2fbbeb988b91f2ac05bb9cde1fc8e9d Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Tue, 4 Jun 2019 19:15:11 +0300 Subject: block/io: introduce bdrv_co_p{read, write}v_part Introduce extended variants of bdrv_co_preadv and bdrv_co_pwritev with qiov_offset parameter. Signed-off-by: Vladimir Sementsov-Ogievskiy Acked-by: Stefan Hajnoczi Message-id: 20190604161514.262241-10-vsementsov@virtuozzo.com Message-Id: <20190604161514.262241-10-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi --- block/io.c | 29 +++++++++++++++++++++++------ include/block/block_int.h | 6 ++++++ 2 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/block/io.c b/block/io.c index 237d7f40f5..0fa10831ed 100644 --- a/block/io.c +++ b/block/io.c @@ -1614,7 +1614,8 @@ static void bdrv_padding_destroy(BdrvRequestPadding *pad) * * Function always succeeds. */ -static bool bdrv_pad_request(BlockDriverState *bs, QEMUIOVector **qiov, +static bool bdrv_pad_request(BlockDriverState *bs, + QEMUIOVector **qiov, size_t *qiov_offset, int64_t *offset, unsigned int *bytes, BdrvRequestPadding *pad) { @@ -1623,11 +1624,12 @@ static bool bdrv_pad_request(BlockDriverState *bs, QEMUIOVector **qiov, } qemu_iovec_init_extended(&pad->local_qiov, pad->buf, pad->head, - *qiov, 0, *bytes, + *qiov, *qiov_offset, *bytes, pad->buf + pad->buf_len - pad->tail, pad->tail); *bytes += pad->head + pad->tail; *offset -= pad->head; *qiov = &pad->local_qiov; + *qiov_offset = 0; return true; } @@ -1635,6 +1637,14 @@ static bool bdrv_pad_request(BlockDriverState *bs, QEMUIOVector **qiov, int coroutine_fn bdrv_co_preadv(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags) +{ + return bdrv_co_preadv_part(child, offset, bytes, qiov, 0, flags); +} + +int coroutine_fn bdrv_co_preadv_part(BdrvChild *child, + int64_t offset, unsigned int bytes, + QEMUIOVector *qiov, size_t qiov_offset, + BdrvRequestFlags flags) { BlockDriverState *bs = child->bs; BdrvTrackedRequest req; @@ -1655,12 +1665,12 @@ int coroutine_fn bdrv_co_preadv(BdrvChild *child, flags |= BDRV_REQ_COPY_ON_READ; } - bdrv_pad_request(bs, &qiov, &offset, &bytes, &pad); + bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad); tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ); ret = bdrv_aligned_preadv(child, &req, offset, bytes, bs->bl.request_alignment, - qiov, 0, flags); + qiov, qiov_offset, flags); tracked_request_end(&req); bdrv_dec_in_flight(bs); @@ -2023,6 +2033,13 @@ out: int coroutine_fn bdrv_co_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags) +{ + return bdrv_co_pwritev_part(child, offset, bytes, qiov, 0, flags); +} + +int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child, + int64_t offset, unsigned int bytes, QEMUIOVector *qiov, size_t qiov_offset, + BdrvRequestFlags flags) { BlockDriverState *bs = child->bs; BdrvTrackedRequest req; @@ -2054,14 +2071,14 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child, goto out; } - if (bdrv_pad_request(bs, &qiov, &offset, &bytes, &pad)) { + if (bdrv_pad_request(bs, &qiov, &qiov_offset, &offset, &bytes, &pad)) { mark_request_serialising(&req, align); wait_serialising_requests(&req); bdrv_padding_rmw_read(child, &req, &pad, false); } ret = bdrv_aligned_pwritev(child, &req, offset, bytes, align, - qiov, 0, flags); + qiov, qiov_offset, flags); bdrv_padding_destroy(&pad); diff --git a/include/block/block_int.h b/include/block/block_int.h index 79a1fdb258..0422acdf1c 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -959,9 +959,15 @@ extern BlockDriver bdrv_qcow2; int coroutine_fn bdrv_co_preadv(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); +int coroutine_fn bdrv_co_preadv_part(BdrvChild *child, + int64_t offset, unsigned int bytes, + QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags); int coroutine_fn bdrv_co_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); +int coroutine_fn bdrv_co_pwritev_part(BdrvChild *child, + int64_t offset, unsigned int bytes, + QEMUIOVector *qiov, size_t qiov_offset, BdrvRequestFlags flags); static inline int coroutine_fn bdrv_co_pread(BdrvChild *child, int64_t offset, unsigned int bytes, void *buf, BdrvRequestFlags flags) -- cgit v1.2.3-55-g7522 From 5396234b96a2ac743f48644529771498e036e698 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Tue, 4 Jun 2019 19:15:14 +0300 Subject: block/qcow2: implement .bdrv_co_pwritev(_compressed)_part Implement and use new interface to get rid of hd_qiov. Signed-off-by: Vladimir Sementsov-Ogievskiy Acked-by: Stefan Hajnoczi Message-id: 20190604161514.262241-13-vsementsov@virtuozzo.com Message-Id: <20190604161514.262241-13-vsementsov@virtuozzo.com> Signed-off-by: Stefan Hajnoczi --- block/qcow2-cluster.c | 9 +++++--- block/qcow2.c | 60 +++++++++++++++++++++++++-------------------------- block/qcow2.h | 1 + include/qemu/iov.h | 1 + util/iov.c | 10 +++++++++ 5 files changed, 48 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index 0e4524d450..f09cc992af 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -829,7 +829,6 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) assert(start->nb_bytes <= UINT_MAX - end->nb_bytes); assert(start->nb_bytes + end->nb_bytes <= UINT_MAX - data_bytes); assert(start->offset + start->nb_bytes <= end->offset); - assert(!m->data_qiov || m->data_qiov->size == data_bytes); if ((start->nb_bytes == 0 && end->nb_bytes == 0) || m->skip_cow) { return 0; @@ -861,7 +860,11 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) /* The part of the buffer where the end region is located */ end_buffer = start_buffer + buffer_size - end->nb_bytes; - qemu_iovec_init(&qiov, 2 + (m->data_qiov ? m->data_qiov->niov : 0)); + qemu_iovec_init(&qiov, 2 + (m->data_qiov ? + qemu_iovec_subvec_niov(m->data_qiov, + m->data_qiov_offset, + data_bytes) + : 0)); qemu_co_mutex_unlock(&s->lock); /* First we read the existing data from both COW regions. We @@ -904,7 +907,7 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) if (start->nb_bytes) { qemu_iovec_add(&qiov, start_buffer, start->nb_bytes); } - qemu_iovec_concat(&qiov, m->data_qiov, 0, data_bytes); + qemu_iovec_concat(&qiov, m->data_qiov, m->data_qiov_offset, data_bytes); if (end->nb_bytes) { qemu_iovec_add(&qiov, end_buffer, end->nb_bytes); } diff --git a/block/qcow2.c b/block/qcow2.c index ec1fff9dd1..0882ff6e92 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -2103,7 +2103,8 @@ fail: /* Check if it's possible to merge a write request with the writing of * the data from the COW regions */ static bool merge_cow(uint64_t offset, unsigned bytes, - QEMUIOVector *hd_qiov, QCowL2Meta *l2meta) + QEMUIOVector *qiov, size_t qiov_offset, + QCowL2Meta *l2meta) { QCowL2Meta *m; @@ -2132,11 +2133,12 @@ static bool merge_cow(uint64_t offset, unsigned bytes, /* Make sure that adding both COW regions to the QEMUIOVector * does not exceed IOV_MAX */ - if (hd_qiov->niov > IOV_MAX - 2) { + if (qemu_iovec_subvec_niov(qiov, qiov_offset, bytes) > IOV_MAX - 2) { continue; } - m->data_qiov = hd_qiov; + m->data_qiov = qiov; + m->data_qiov_offset = qiov_offset; return true; } @@ -2218,24 +2220,22 @@ static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta) return 0; } -static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, - uint64_t bytes, QEMUIOVector *qiov, - int flags) +static coroutine_fn int qcow2_co_pwritev_part( + BlockDriverState *bs, uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, size_t qiov_offset, int flags) { BDRVQcow2State *s = bs->opaque; int offset_in_cluster; int ret; unsigned int cur_bytes; /* number of sectors in current iteration */ uint64_t cluster_offset; - QEMUIOVector hd_qiov; + QEMUIOVector encrypted_qiov; uint64_t bytes_done = 0; uint8_t *cluster_data = NULL; QCowL2Meta *l2meta = NULL; trace_qcow2_writev_start_req(qemu_coroutine_self(), offset, bytes); - qemu_iovec_init(&hd_qiov, qiov->niov); - qemu_co_mutex_lock(&s->lock); while (bytes != 0) { @@ -2268,9 +2268,6 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, qemu_co_mutex_unlock(&s->lock); - qemu_iovec_reset(&hd_qiov); - qemu_iovec_concat(&hd_qiov, qiov, bytes_done, cur_bytes); - if (bs->encrypted) { assert(s->crypto); if (!cluster_data) { @@ -2283,9 +2280,9 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, } } - assert(hd_qiov.size <= - QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size); - qemu_iovec_to_buf(&hd_qiov, 0, cluster_data, hd_qiov.size); + assert(cur_bytes <= QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size); + qemu_iovec_to_buf(qiov, qiov_offset + bytes_done, + cluster_data, cur_bytes); if (qcow2_co_encrypt(bs, cluster_offset, offset, cluster_data, cur_bytes) < 0) { @@ -2293,8 +2290,7 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, goto out_unlocked; } - qemu_iovec_reset(&hd_qiov); - qemu_iovec_add(&hd_qiov, cluster_data, cur_bytes); + qemu_iovec_init_buf(&encrypted_qiov, cluster_data, cur_bytes); } /* Try to efficiently initialize the physical space with zeroes */ @@ -2307,13 +2303,17 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, * writing of the guest data together with that of the COW regions. * If it's not possible (or not necessary) then write the * guest data now. */ - if (!merge_cow(offset, cur_bytes, &hd_qiov, l2meta)) { + if (!merge_cow(offset, cur_bytes, + bs->encrypted ? &encrypted_qiov : qiov, + bs->encrypted ? 0 : qiov_offset + bytes_done, l2meta)) + { BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); trace_qcow2_writev_data(qemu_coroutine_self(), cluster_offset + offset_in_cluster); - ret = bdrv_co_pwritev(s->data_file, - cluster_offset + offset_in_cluster, - cur_bytes, &hd_qiov, 0); + ret = bdrv_co_pwritev_part( + s->data_file, cluster_offset + offset_in_cluster, cur_bytes, + bs->encrypted ? &encrypted_qiov : qiov, + bs->encrypted ? 0 : qiov_offset + bytes_done, 0); if (ret < 0) { goto out_unlocked; } @@ -2342,7 +2342,6 @@ out_locked: qemu_co_mutex_unlock(&s->lock); - qemu_iovec_destroy(&hd_qiov); qemu_vfree(cluster_data); trace_qcow2_writev_done_req(qemu_coroutine_self(), ret); @@ -4007,8 +4006,9 @@ fail: /* XXX: put compressed sectors first, then all the cluster aligned tables to avoid losing bytes in alignment */ static coroutine_fn int -qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, - uint64_t bytes, QEMUIOVector *qiov) +qcow2_co_pwritev_compressed_part(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, size_t qiov_offset) { BDRVQcow2State *s = bs->opaque; int ret; @@ -4045,7 +4045,7 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, /* Zero-pad last write if image size is not cluster aligned */ memset(buf + bytes, 0, s->cluster_size - bytes); } - qemu_iovec_to_buf(qiov, 0, buf, bytes); + qemu_iovec_to_buf(qiov, qiov_offset, buf, bytes); out_buf = g_malloc(s->cluster_size); @@ -4053,7 +4053,7 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, buf, s->cluster_size); if (out_len == -ENOMEM) { /* could not compress: write normal cluster */ - ret = qcow2_co_pwritev(bs, offset, bytes, qiov, 0); + ret = qcow2_co_pwritev_part(bs, offset, bytes, qiov, qiov_offset, 0); if (ret < 0) { goto fail; } @@ -4664,8 +4664,8 @@ static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, BDRVQcow2State *s = bs->opaque; BLKDBG_EVENT(bs->file, BLKDBG_VMSTATE_SAVE); - return bs->drv->bdrv_co_pwritev(bs, qcow2_vm_state_offset(s) + pos, - qiov->size, qiov, 0); + return bs->drv->bdrv_co_pwritev_part(bs, qcow2_vm_state_offset(s) + pos, + qiov->size, qiov, 0, 0); } static int qcow2_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, @@ -5218,7 +5218,7 @@ BlockDriver bdrv_qcow2 = { .bdrv_co_block_status = qcow2_co_block_status, .bdrv_co_preadv_part = qcow2_co_preadv_part, - .bdrv_co_pwritev = qcow2_co_pwritev, + .bdrv_co_pwritev_part = qcow2_co_pwritev_part, .bdrv_co_flush_to_os = qcow2_co_flush_to_os, .bdrv_co_pwrite_zeroes = qcow2_co_pwrite_zeroes, @@ -5226,7 +5226,7 @@ BlockDriver bdrv_qcow2 = { .bdrv_co_copy_range_from = qcow2_co_copy_range_from, .bdrv_co_copy_range_to = qcow2_co_copy_range_to, .bdrv_co_truncate = qcow2_co_truncate, - .bdrv_co_pwritev_compressed = qcow2_co_pwritev_compressed, + .bdrv_co_pwritev_compressed_part = qcow2_co_pwritev_compressed_part, .bdrv_make_empty = qcow2_make_empty, .bdrv_snapshot_create = qcow2_snapshot_create, diff --git a/block/qcow2.h b/block/qcow2.h index fc1b0d3c1e..998bcdaef1 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -420,6 +420,7 @@ typedef struct QCowL2Meta * from @cow_start and @cow_end into one single write operation. */ QEMUIOVector *data_qiov; + size_t data_qiov_offset; /** Pointer to next L2Meta of the same write request */ struct QCowL2Meta *next; diff --git a/include/qemu/iov.h b/include/qemu/iov.h index 29957c8a72..bffc151282 100644 --- a/include/qemu/iov.h +++ b/include/qemu/iov.h @@ -206,6 +206,7 @@ void qemu_iovec_init_extended( void *tail_buf, size_t tail_len); void qemu_iovec_init_slice(QEMUIOVector *qiov, QEMUIOVector *source, size_t offset, size_t len); +int qemu_iovec_subvec_niov(QEMUIOVector *qiov, size_t offset, size_t len); void qemu_iovec_add(QEMUIOVector *qiov, void *base, size_t len); void qemu_iovec_concat(QEMUIOVector *dst, QEMUIOVector *src, size_t soffset, size_t sbytes); diff --git a/util/iov.c b/util/iov.c index 9ac0261853..5059e10431 100644 --- a/util/iov.c +++ b/util/iov.c @@ -401,6 +401,16 @@ static struct iovec *qiov_slice(QEMUIOVector *qiov, return iov; } +int qemu_iovec_subvec_niov(QEMUIOVector *qiov, size_t offset, size_t len) +{ + size_t head, tail; + int niov; + + qiov_slice(qiov, offset, len, &head, &tail, &niov); + + return niov; +} + /* * Compile new iovec, combining @head_buf buffer, sub-qiov of @mid_qiov, * and @tail_buf buffer into new qiov. -- cgit v1.2.3-55-g7522