diff options
44 files changed, 843 insertions, 652 deletions
diff --git a/block.c b/block.c index f4648e916f..823ff1d7ab 100644 --- a/block.c +++ b/block.c @@ -536,9 +536,10 @@ BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size, return drv; } -static int find_image_format(BlockDriverState *bs, const char *filename, +static int find_image_format(BdrvChild *file, const char *filename, BlockDriver **pdrv, Error **errp) { + BlockDriverState *bs = file->bs; BlockDriver *drv; uint8_t buf[BLOCK_PROBE_BUF_SIZE]; int ret = 0; @@ -549,7 +550,7 @@ static int find_image_format(BlockDriverState *bs, const char *filename, return ret; } - ret = bdrv_pread(bs, 0, buf, sizeof(buf)); + ret = bdrv_pread(file, 0, buf, sizeof(buf)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read image for determining its " "format"); @@ -937,7 +938,6 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file, goto fail_opts; } - bs->request_alignment = drv->bdrv_co_preadv ? 1 : 512; bs->read_only = !(bs->open_flags & BDRV_O_RDWR); if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) { @@ -1017,7 +1017,7 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file, assert(bdrv_opt_mem_align(bs) != 0); assert(bdrv_min_mem_align(bs) != 0); - assert(is_power_of_2(bs->request_alignment) || bdrv_is_sg(bs)); + assert(is_power_of_2(bs->bl.request_alignment)); qemu_opts_del(opts); return 0; @@ -1653,7 +1653,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename, /* Image format probing */ bs->probed = !drv; if (!drv && file) { - ret = find_image_format(file->bs, filename, &drv, &local_err); + ret = find_image_format(file, filename, &drv, &local_err); if (ret < 0) { goto fail; } @@ -2184,9 +2184,9 @@ static void bdrv_close(BlockDriverState *bs) bs->backing_file[0] = '\0'; bs->backing_format[0] = '\0'; bs->total_sectors = 0; - bs->encrypted = 0; - bs->valid_key = 0; - bs->sg = 0; + bs->encrypted = false; + bs->valid_key = false; + bs->sg = false; QDECREF(bs->options); QDECREF(bs->explicit_options); bs->options = NULL; @@ -2323,116 +2323,6 @@ int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix) return bs->drv->bdrv_check(bs, res, fix); } -#define COMMIT_BUF_SECTORS 2048 - -/* commit COW file into the raw image */ -int bdrv_commit(BlockDriverState *bs) -{ - BlockDriver *drv = bs->drv; - int64_t sector, total_sectors, length, backing_length; - int n, ro, open_flags; - int ret = 0; - uint8_t *buf = NULL; - - if (!drv) - return -ENOMEDIUM; - - if (!bs->backing) { - return -ENOTSUP; - } - - if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) || - bdrv_op_is_blocked(bs->backing->bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) { - return -EBUSY; - } - - ro = bs->backing->bs->read_only; - open_flags = bs->backing->bs->open_flags; - - if (ro) { - if (bdrv_reopen(bs->backing->bs, open_flags | BDRV_O_RDWR, NULL)) { - return -EACCES; - } - } - - length = bdrv_getlength(bs); - if (length < 0) { - ret = length; - goto ro_cleanup; - } - - backing_length = bdrv_getlength(bs->backing->bs); - if (backing_length < 0) { - ret = backing_length; - goto ro_cleanup; - } - - /* If our top snapshot is larger than the backing file image, - * grow the backing file image if possible. If not possible, - * we must return an error */ - if (length > backing_length) { - ret = bdrv_truncate(bs->backing->bs, length); - if (ret < 0) { - goto ro_cleanup; - } - } - - total_sectors = length >> BDRV_SECTOR_BITS; - - /* qemu_try_blockalign() for bs will choose an alignment that works for - * bs->backing->bs as well, so no need to compare the alignment manually. */ - buf = qemu_try_blockalign(bs, COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE); - if (buf == NULL) { - ret = -ENOMEM; - goto ro_cleanup; - } - - for (sector = 0; sector < total_sectors; sector += n) { - ret = bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n); - if (ret < 0) { - goto ro_cleanup; - } - if (ret) { - ret = bdrv_read(bs, sector, buf, n); - if (ret < 0) { - goto ro_cleanup; - } - - ret = bdrv_write(bs->backing->bs, sector, buf, n); - if (ret < 0) { - goto ro_cleanup; - } - } - } - - if (drv->bdrv_make_empty) { - ret = drv->bdrv_make_empty(bs); - if (ret < 0) { - goto ro_cleanup; - } - bdrv_flush(bs); - } - - /* - * Make sure all data we wrote to the backing device is actually - * stable on disk. - */ - if (bs->backing) { - bdrv_flush(bs->backing->bs); - } - - ret = 0; -ro_cleanup: - qemu_vfree(buf); - - if (ro) { - /* ignoring error return here */ - bdrv_reopen(bs->backing->bs, open_flags & ~BDRV_O_RDWR, NULL); - } - - return ret; -} - /* * Return values: * 0 - success @@ -2644,30 +2534,30 @@ void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr) *nb_sectors_ptr = nb_sectors < 0 ? 0 : nb_sectors; } -int bdrv_is_read_only(BlockDriverState *bs) +bool bdrv_is_read_only(BlockDriverState *bs) { return bs->read_only; } -int bdrv_is_sg(BlockDriverState *bs) +bool bdrv_is_sg(BlockDriverState *bs) { return bs->sg; } -int bdrv_is_encrypted(BlockDriverState *bs) +bool bdrv_is_encrypted(BlockDriverState *bs) { if (bs->backing && bs->backing->bs->encrypted) { - return 1; + return true; } return bs->encrypted; } -int bdrv_key_required(BlockDriverState *bs) +bool bdrv_key_required(BlockDriverState *bs) { BdrvChild *backing = bs->backing; if (backing && backing->bs->encrypted && !backing->bs->valid_key) { - return 1; + return true; } return (bs->encrypted && !bs->valid_key); } @@ -2689,10 +2579,10 @@ int bdrv_set_key(BlockDriverState *bs, const char *key) } ret = bs->drv->bdrv_set_key(bs, key); if (ret < 0) { - bs->valid_key = 0; + bs->valid_key = false; } else if (!bs->valid_key) { /* call the change callback now, we skipped it on open */ - bs->valid_key = 1; + bs->valid_key = true; bdrv_parent_cb_change_media(bs, true); } return ret; diff --git a/block/Makefile.objs b/block/Makefile.objs index 44a5416225..2593a2f8a6 100644 --- a/block/Makefile.objs +++ b/block/Makefile.objs @@ -9,7 +9,7 @@ block-obj-y += block-backend.o snapshot.o qapi.o block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o block-obj-$(CONFIG_POSIX) += raw-posix.o block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o -block-obj-y += null.o mirror.o io.o +block-obj-y += null.o mirror.o commit.o io.o block-obj-y += throttle-groups.o block-obj-y += nbd.o nbd-client.o sheepdog.o @@ -26,7 +26,6 @@ block-obj-y += write-threshold.o block-obj-y += crypto.o common-obj-y += stream.o -common-obj-y += commit.o common-obj-y += backup.o iscsi.o-cflags := $(LIBISCSI_CFLAGS) diff --git a/block/blkdebug.c b/block/blkdebug.c index 20d25bda67..bbaa33fdd8 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -37,6 +37,7 @@ typedef struct BDRVBlkdebugState { int state; int new_state; + int align; QLIST_HEAD(, BlkdebugRule) rules[BLKDBG__MAX]; QSIMPLEQ_HEAD(, BlkdebugRule) active_rules; @@ -382,10 +383,10 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags, } /* Set request alignment */ - align = qemu_opt_get_size(opts, "align", bs->request_alignment); - if (align > 0 && align < INT_MAX && !(align & (align - 1))) { - bs->request_alignment = align; - } else { + align = qemu_opt_get_size(opts, "align", 0); + if (align < INT_MAX && is_power_of_2(align)) { + s->align = align; + } else if (align) { error_setg(errp, "Invalid alignment"); ret = -EINVAL; goto fail_unref; @@ -456,7 +457,7 @@ static BlockAIOCB *blkdebug_aio_readv(BlockDriverState *bs, return inject_error(bs, cb, opaque, rule); } - return bdrv_aio_readv(bs->file->bs, sector_num, qiov, nb_sectors, + return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque); } @@ -479,7 +480,7 @@ static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs, return inject_error(bs, cb, opaque, rule); } - return bdrv_aio_writev(bs->file->bs, sector_num, qiov, nb_sectors, + return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque); } @@ -720,6 +721,15 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options) bs->full_open_options = opts; } +static void blkdebug_refresh_limits(BlockDriverState *bs, Error **errp) +{ + BDRVBlkdebugState *s = bs->opaque; + + if (s->align) { + bs->bl.request_alignment = s->align; + } +} + static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp) { @@ -738,6 +748,7 @@ static BlockDriver bdrv_blkdebug = { .bdrv_getlength = blkdebug_getlength, .bdrv_truncate = blkdebug_truncate, .bdrv_refresh_filename = blkdebug_refresh_filename, + .bdrv_refresh_limits = blkdebug_refresh_limits, .bdrv_aio_readv = blkdebug_aio_readv, .bdrv_aio_writev = blkdebug_aio_writev, diff --git a/block/blkreplay.c b/block/blkreplay.c index 525c2d54e0..70650e4be1 100755 --- a/block/blkreplay.c +++ b/block/blkreplay.c @@ -81,22 +81,22 @@ static void block_request_create(uint64_t reqid, BlockDriverState *bs, replay_block_event(req->bh, reqid); } -static int coroutine_fn blkreplay_co_readv(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, QEMUIOVector *qiov) +static int coroutine_fn blkreplay_co_preadv(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) { uint64_t reqid = request_id++; - int ret = bdrv_co_readv(bs->file->bs, sector_num, nb_sectors, qiov); + int ret = bdrv_co_preadv(bs->file, offset, bytes, qiov, flags); block_request_create(reqid, bs, qemu_coroutine_self()); qemu_coroutine_yield(); return ret; } -static int coroutine_fn blkreplay_co_writev(BlockDriverState *bs, - int64_t sector_num, int nb_sectors, QEMUIOVector *qiov) +static int coroutine_fn blkreplay_co_pwritev(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) { uint64_t reqid = request_id++; - int ret = bdrv_co_writev(bs->file->bs, sector_num, nb_sectors, qiov); + int ret = bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags); block_request_create(reqid, bs, qemu_coroutine_self()); qemu_coroutine_yield(); @@ -107,7 +107,7 @@ static int coroutine_fn blkreplay_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int count, BdrvRequestFlags flags) { uint64_t reqid = request_id++; - int ret = bdrv_co_pwrite_zeroes(bs->file->bs, offset, count, flags); + int ret = bdrv_co_pwrite_zeroes(bs->file, offset, count, flags); block_request_create(reqid, bs, qemu_coroutine_self()); qemu_coroutine_yield(); @@ -144,8 +144,8 @@ static BlockDriver bdrv_blkreplay = { .bdrv_close = blkreplay_close, .bdrv_getlength = blkreplay_getlength, - .bdrv_co_readv = blkreplay_co_readv, - .bdrv_co_writev = blkreplay_co_writev, + .bdrv_co_preadv = blkreplay_co_preadv, + .bdrv_co_pwritev = blkreplay_co_pwritev, .bdrv_co_pwrite_zeroes = blkreplay_co_pwrite_zeroes, .bdrv_co_discard = blkreplay_co_discard, diff --git a/block/blkverify.c b/block/blkverify.c index 4045396a3d..da62d75969 100644 --- a/block/blkverify.c +++ b/block/blkverify.c @@ -247,9 +247,9 @@ static BlockAIOCB *blkverify_aio_readv(BlockDriverState *bs, qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov); qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf); - bdrv_aio_readv(s->test_file->bs, sector_num, qiov, nb_sectors, + bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors, blkverify_aio_cb, acb); - bdrv_aio_readv(bs->file->bs, sector_num, &acb->raw_qiov, nb_sectors, + bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors, blkverify_aio_cb, acb); return &acb->common; } @@ -262,9 +262,9 @@ static BlockAIOCB *blkverify_aio_writev(BlockDriverState *bs, BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov, nb_sectors, cb, opaque); - bdrv_aio_writev(s->test_file->bs, sector_num, qiov, nb_sectors, + bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors, blkverify_aio_cb, acb); - bdrv_aio_writev(bs->file->bs, sector_num, qiov, nb_sectors, + bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, blkverify_aio_cb, acb); return &acb->common; } diff --git a/block/block-backend.c b/block/block-backend.c index 34500e6080..a862f6577b 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -760,7 +760,7 @@ int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset, throttle_group_co_io_limits_intercept(blk, bytes, false); } - return bdrv_co_preadv(blk_bs(blk), offset, bytes, qiov, flags); + return bdrv_co_preadv(blk->root, offset, bytes, qiov, flags); } int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset, @@ -785,7 +785,7 @@ int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset, flags |= BDRV_REQ_FUA; } - return bdrv_co_pwritev(blk_bs(blk), offset, bytes, qiov, flags); + return bdrv_co_pwritev(blk->root, offset, bytes, qiov, flags); } typedef struct BlkRwCo { @@ -870,6 +870,11 @@ int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, flags | BDRV_REQ_ZERO_WRITE); } +int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags) +{ + return bdrv_make_zero(blk->root, flags); +} + static void error_callback_bh(void *opaque) { struct BlockBackendAIOCB *acb = opaque; @@ -1303,15 +1308,16 @@ int blk_get_flags(BlockBackend *blk) } } -int blk_get_max_transfer_length(BlockBackend *blk) +/* Returns the maximum transfer length, in bytes; guaranteed nonzero */ +uint32_t blk_get_max_transfer(BlockBackend *blk) { BlockDriverState *bs = blk_bs(blk); + uint32_t max = 0; if (bs) { - return bs->bl.max_transfer_length; - } else { - return 0; + max = bs->bl.max_transfer; } + return MIN_NON_ZERO(max, INT_MAX); } int blk_get_max_iov(BlockBackend *blk) diff --git a/block/bochs.c b/block/bochs.c index 6c8d0f3426..8c9652ebeb 100644 --- a/block/bochs.c +++ b/block/bochs.c @@ -104,10 +104,9 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, struct bochs_header bochs; int ret; - bs->read_only = 1; // no write support yet - bs->request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O supported */ + bs->read_only = true; /* no write support yet */ - ret = bdrv_pread(bs->file->bs, 0, &bochs, sizeof(bochs)); + ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs)); if (ret < 0) { return ret; } @@ -141,7 +140,7 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, return -ENOMEM; } - ret = bdrv_pread(bs->file->bs, le32_to_cpu(bochs.header), s->catalog_bitmap, + ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap, s->catalog_size * 4); if (ret < 0) { goto fail; @@ -189,6 +188,11 @@ fail: return ret; } +static void bochs_refresh_limits(BlockDriverState *bs, Error **errp) +{ + bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */ +} + static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num) { BDRVBochsState *s = bs->opaque; @@ -210,7 +214,7 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num) (s->extent_blocks + s->bitmap_blocks)); /* read in bitmap for current extent */ - ret = bdrv_pread(bs->file->bs, bitmap_offset + (extent_offset / 8), + ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8), &bitmap_entry, 1); if (ret < 0) { return ret; @@ -251,7 +255,7 @@ bochs_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_concat(&local_qiov, qiov, bytes_done, 512); if (block_offset > 0) { - ret = bdrv_co_preadv(bs->file->bs, block_offset, 512, + ret = bdrv_co_preadv(bs->file, block_offset, 512, &local_qiov, 0); if (ret < 0) { goto fail; @@ -283,6 +287,7 @@ static BlockDriver bdrv_bochs = { .instance_size = sizeof(BDRVBochsState), .bdrv_probe = bochs_probe, .bdrv_open = bochs_open, + .bdrv_refresh_limits = bochs_refresh_limits, .bdrv_co_preadv = bochs_co_preadv, .bdrv_close = bochs_close, }; diff --git a/block/cloop.c b/block/cloop.c index ea5a92b6d4..7b75f7ef7b 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -66,11 +66,10 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, uint32_t offsets_size, max_compressed_block_size = 1, i; int ret; - bs->read_only = 1; - bs->request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O supported */ + bs->read_only = true; /* read header */ - ret = bdrv_pread(bs->file->bs, 128, &s->block_size, 4); + ret = bdrv_pread(bs->file, 128, &s->block_size, 4); if (ret < 0) { return ret; } @@ -96,7 +95,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = bdrv_pread(bs->file->bs, 128 + 4, &s->n_blocks, 4); + ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4); if (ret < 0) { return ret; } @@ -127,7 +126,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, return -ENOMEM; } - ret = bdrv_pread(bs->file->bs, 128 + 4 + 4, s->offsets, offsets_size); + ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size); if (ret < 0) { goto fail; } @@ -199,6 +198,11 @@ fail: return ret; } +static void cloop_refresh_limits(BlockDriverState *bs, Error **errp) +{ + bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */ +} + static inline int cloop_read_block(BlockDriverState *bs, int block_num) { BDRVCloopState *s = bs->opaque; @@ -207,7 +211,7 @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num) int ret; uint32_t bytes = s->offsets[block_num + 1] - s->offsets[block_num]; - ret = bdrv_pread(bs->file->bs, s->offsets[block_num], + ret = bdrv_pread(bs->file, s->offsets[block_num], s->compressed_block, bytes); if (ret != bytes) { return -1; @@ -280,6 +284,7 @@ static BlockDriver bdrv_cloop = { .instance_size = sizeof(BDRVCloopState), .bdrv_probe = cloop_probe, .bdrv_open = cloop_open, + .bdrv_refresh_limits = cloop_refresh_limits, .bdrv_co_preadv = cloop_co_preadv, .bdrv_close = cloop_close, }; diff --git a/block/commit.c b/block/commit.c index 444333ba65..379efb7c92 100644 --- a/block/commit.c +++ b/block/commit.c @@ -282,3 +282,124 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base, trace_commit_start(bs, base, top, s, s->common.co, opaque); qemu_coroutine_enter(s->common.co, s); } + + +#define COMMIT_BUF_SECTORS 2048 + +/* commit COW file into the raw image */ +int bdrv_commit(BlockDriverState *bs) +{ + BlockBackend *src, *backing; + BlockDriver *drv = bs->drv; + int64_t sector, total_sectors, length, backing_length; + int n, ro, open_flags; + int ret = 0; + uint8_t *buf = NULL; + + if (!drv) + return -ENOMEDIUM; + + if (!bs->backing) { + return -ENOTSUP; + } + + if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) || + bdrv_op_is_blocked(bs->backing->bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) { + return -EBUSY; + } + + ro = bs->backing->bs->read_only; + open_flags = bs->backing->bs->open_flags; + + if (ro) { + if (bdrv_reopen(bs->backing->bs, open_flags | BDRV_O_RDWR, NULL)) { + return -EACCES; + } + } + + src = blk_new(); + blk_insert_bs(src, bs); + + backing = blk_new(); + blk_insert_bs(backing, bs->backing->bs); + + length = blk_getlength(src); + if (length < 0) { + ret = length; + goto ro_cleanup; + } + + backing_length = blk_getlength(backing); + if (backing_length < 0) { + ret = backing_length; + goto ro_cleanup; + } + + /* If our top snapshot is larger than the backing file image, + * grow the backing file image if possible. If not possible, + * we must return an error */ + if (length > backing_length) { + ret = blk_truncate(backing, length); + if (ret < 0) { + goto ro_cleanup; + } + } + + total_sectors = length >> BDRV_SECTOR_BITS; + + /* blk_try_blockalign() for src will choose an alignment that works for + * backing as well, so no need to compare the alignment manually. */ + buf = blk_try_blockalign(src, COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE); + if (buf == NULL) { + ret = -ENOMEM; + goto ro_cleanup; + } + + for (sector = 0; sector < total_sectors; sector += n) { + ret = bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n); + if (ret < 0) { + goto ro_cleanup; + } + if (ret) { + ret = blk_pread(src, sector * BDRV_SECTOR_SIZE, buf, + n * BDRV_SECTOR_SIZE); + if (ret < 0) { + goto ro_cleanup; + } + + ret = blk_pwrite(backing, sector * BDRV_SECTOR_SIZE, buf, + n * BDRV_SECTOR_SIZE, 0); + if (ret < 0) { + goto ro_cleanup; + } + } + } + + if (drv->bdrv_make_empty) { + ret = drv->bdrv_make_empty(bs); + if (ret < 0) { + goto ro_cleanup; + } + blk_flush(src); + } + + /* + * Make sure all data we wrote to the backing device is actually + * stable on disk. + */ + blk_flush(backing); + + ret = 0; +ro_cleanup: + qemu_vfree(buf); + + blk_unref(src); + blk_unref(backing); + + if (ro) { + /* ignoring error return here */ + bdrv_reopen(bs->backing->bs, open_flags & ~BDRV_O_RDWR, NULL); + } + + return ret; +} diff --git a/block/crypto.c b/block/crypto.c index 758e14e032..cb8cbc2cc9 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -64,7 +64,7 @@ static ssize_t block_crypto_read_func(QCryptoBlock *block, BlockDriverState *bs = opaque; ssize_t ret; - ret = bdrv_pread(bs->file->bs, offset, buf, buflen); + ret = bdrv_pread(bs->file, offset, buf, buflen); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read encryption header"); return ret; @@ -322,8 +322,8 @@ static int block_crypto_open_generic(QCryptoBlockFormat format, goto cleanup; } - bs->encrypted = 1; - bs->valid_key = 1; + bs->encrypted = true; + bs->valid_key = true; ret = 0; cleanup: @@ -428,7 +428,7 @@ block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, qemu_iovec_reset(&hd_qiov); qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512); - ret = bdrv_co_readv(bs->file->bs, + ret = bdrv_co_readv(bs->file, payload_offset + sector_num, cur_nr_sectors, &hd_qiov); if (ret < 0) { @@ -507,7 +507,7 @@ block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num, qemu_iovec_reset(&hd_qiov); qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512); - ret = bdrv_co_writev(bs->file->bs, + ret = bdrv_co_writev(bs->file, payload_offset + sector_num, cur_nr_sectors, &hd_qiov); if (ret < 0) { diff --git a/block/dmg.c b/block/dmg.c index 06eb5138f3..b0ed89baa7 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -86,7 +86,7 @@ static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result) uint64_t buffer; int ret; - ret = bdrv_pread(bs->file->bs, offset, &buffer, 8); + ret = bdrv_pread(bs->file, offset, &buffer, 8); if (ret < 0) { return ret; } @@ -100,7 +100,7 @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result) uint32_t buffer; int ret; - ret = bdrv_pread(bs->file->bs, offset, &buffer, 4); + ret = bdrv_pread(bs->file, offset, &buffer, 4); if (ret < 0) { return ret; } @@ -153,8 +153,9 @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk, } } -static int64_t dmg_find_koly_offset(BlockDriverState *file_bs, Error **errp) +static int64_t dmg_find_koly_offset(BdrvChild *file, Error **errp) { + BlockDriverState *file_bs = file->bs; int64_t length; int64_t offset = 0; uint8_t buffer[515]; @@ -178,7 +179,7 @@ static int64_t dmg_find_koly_offset(BlockDriverState *file_bs, Error **errp) offset = length - 511 - 512; } length = length < 515 ? length : 515; - ret = bdrv_pread(file_bs, offset, buffer, length); + ret = bdrv_pread(file, offset, buffer, length); if (ret < 0) { error_setg_errno(errp, -ret, "Failed while reading UDIF trailer"); return ret; @@ -355,7 +356,7 @@ static int dmg_read_resource_fork(BlockDriverState *bs, DmgHeaderState *ds, offset += 4; buffer = g_realloc(buffer, count); - ret = bdrv_pread(bs->file->bs, offset, buffer, count); + ret = bdrv_pread(bs->file, offset, buffer, count); if (ret < 0) { goto fail; } @@ -392,7 +393,7 @@ static int dmg_read_plist_xml(BlockDriverState *bs, DmgHeaderState *ds, buffer = g_malloc(info_length + 1); buffer[info_length] = '\0'; - ret = bdrv_pread(bs->file->bs, info_begin, buffer, info_length); + ret = bdrv_pread(bs->file, info_begin, buffer, info_length); if (ret != info_length) { ret = -EINVAL; goto fail; @@ -438,8 +439,7 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags, int64_t offset; int ret; - bs->read_only = 1; - bs->request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O supported */ + bs->read_only = true; s->n_chunks = 0; s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL; @@ -449,7 +449,7 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags, ds.max_sectors_per_chunk = 1; /* locate the UDIF trailer */ - offset = dmg_find_koly_offset(bs->file->bs, errp); + offset = dmg_find_koly_offset(bs->file, errp); if (offset < 0) { ret = offset; goto fail; @@ -547,6 +547,11 @@ fail: return ret; } +static void dmg_refresh_limits(BlockDriverState *bs, Error **errp) +{ + bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */ +} + static inline int is_sector_in_chunk(BDRVDMGState* s, uint32_t chunk_num, uint64_t sector_num) { @@ -595,7 +600,7 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) case 0x80000005: { /* zlib compressed */ /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file->bs, s->offsets[chunk], + ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, s->lengths[chunk]); if (ret != s->lengths[chunk]) { return -1; @@ -619,7 +624,7 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) case 0x80000006: /* bzip2 compressed */ /* we need to buffer, because only the chunk as whole can be * inflated. */ - ret = bdrv_pread(bs->file->bs, s->offsets[chunk], + ret = bdrv_pread(bs->file, s->offsets[chunk], s->compressed_chunk, s->lengths[chunk]); if (ret != s->lengths[chunk]) { return -1; @@ -644,7 +649,7 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num) break; #endif /* CONFIG_BZIP2 */ case 1: /* copy */ - ret = bdrv_pread(bs->file->bs, s->offsets[chunk], + ret = bdrv_pread(bs->file, s->offsets[chunk], s->uncompressed_chunk, s->lengths[chunk]); if (ret != s->lengths[chunk]) { return -1; @@ -720,6 +725,7 @@ static BlockDriver bdrv_dmg = { .instance_size = sizeof(BDRVDMGState), .bdrv_probe = dmg_probe, .bdrv_open = dmg_open, + .bdrv_refresh_limits = dmg_refresh_limits, .bdrv_co_preadv = dmg_co_preadv, .bdrv_close = dmg_close, }; diff --git a/block/io.c b/block/io.c index 7cf3645ade..708690898f 100644 --- a/block/io.c +++ b/block/io.c @@ -33,7 +33,7 @@ #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */ -static BlockAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs, +static BlockAIOCB *bdrv_co_aio_rw_vector(BdrvChild *child, int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, @@ -67,6 +67,17 @@ static void bdrv_parent_drained_end(BlockDriverState *bs) } } +static void bdrv_merge_limits(BlockLimits *dst, const BlockLimits *src) +{ + dst->opt_transfer = MAX(dst->opt_transfer, src->opt_transfer); + dst->max_transfer = MIN_NON_ZERO(dst->max_transfer, src->max_transfer); + dst->opt_mem_alignment = MAX(dst->opt_mem_alignment, + src->opt_mem_alignment); + dst->min_mem_alignment = MAX(dst->min_mem_alignment, + src->min_mem_alignment); + dst->max_iov = MIN_NON_ZERO(dst->max_iov, src->max_iov); +} + void bdrv_refresh_limits(BlockDriverState *bs, Error **errp) { BlockDriver *drv = bs->drv; @@ -78,6 +89,9 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp) return; } + /* Default alignment based on whether driver has byte interface */ + bs->bl.request_alignment = drv->bdrv_co_preadv ? 1 : 512; + /* Take some limits from the children as a default */ if (bs->file) { bdrv_refresh_limits(bs->file->bs, &local_err); @@ -85,11 +99,7 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp) error_propagate(errp, local_err); return; } - bs->bl.opt_transfer_length = bs->file->bs->bl.opt_transfer_length; - bs->bl.max_transfer_length = bs->file->bs->bl.max_transfer_length; - bs->bl.min_mem_alignment = bs->file->bs->bl.min_mem_alignment; - bs->bl.opt_mem_alignment = bs->file->bs->bl.opt_mem_alignment; - bs->bl.max_iov = bs->file->bs->bl.max_iov; + bdrv_merge_limits(&bs->bl, &bs->file->bs->bl); } else { bs->bl.min_mem_alignment = 512; bs->bl.opt_mem_alignment = getpagesize(); @@ -104,21 +114,7 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp) error_propagate(errp, local_err); return; } - bs->bl.opt_transfer_length = - MAX(bs->bl.opt_transfer_length, - bs->backing->bs->bl.opt_transfer_length); - bs->bl.max_transfer_length = - MIN_NON_ZERO(bs->bl.max_transfer_length, - bs->backing->bs->bl.max_transfer_length); - bs->bl.opt_mem_alignment = - MAX(bs->bl.opt_mem_alignment, - bs->backing->bs->bl.opt_mem_alignment); - bs->bl.min_mem_alignment = - MAX(bs->bl.min_mem_alignment, - bs->backing->bs->bl.min_mem_alignment); - bs->bl.max_iov = - MIN(bs->bl.max_iov, - bs->backing->bs->bl.max_iov); + bdrv_merge_limits(&bs->bl, &bs->backing->bs->bl); } /* Then let the driver override it */ @@ -463,7 +459,7 @@ static int bdrv_get_cluster_size(BlockDriverState *bs) ret = bdrv_get_info(bs, &bdi); if (ret < 0 || bdi.cluster_size == 0) { - return bs->request_alignment; + return bs->bl.request_alignment; } else { return bdi.cluster_size; } @@ -557,7 +553,7 @@ static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num, } typedef struct RwCo { - BlockDriverState *bs; + BdrvChild *child; int64_t offset; QEMUIOVector *qiov; bool is_write; @@ -570,11 +566,11 @@ static void coroutine_fn bdrv_rw_co_entry(void *opaque) RwCo *rwco = opaque; if (!rwco->is_write) { - rwco->ret = bdrv_co_preadv(rwco->bs, rwco->offset, + rwco->ret = bdrv_co_preadv(rwco->child, rwco->offset, rwco->qiov->size, rwco->qiov, rwco->flags); } else { - rwco->ret = bdrv_co_pwritev(rwco->bs, rwco->offset, + rwco->ret = bdrv_co_pwritev(rwco->child, rwco->offset, rwco->qiov->size, rwco->qiov, rwco->flags); } @@ -583,13 +579,13 @@ static void coroutine_fn bdrv_rw_co_entry(void *opaque) /* * Process a vectored synchronous request using coroutines */ -static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset, +static int bdrv_prwv_co(BdrvChild *child, int64_t offset, QEMUIOVector *qiov, bool is_write, BdrvRequestFlags flags) { Coroutine *co; RwCo rwco = { - .bs = bs, + .child = child, .offset = offset, .qiov = qiov, .is_write = is_write, @@ -601,7 +597,7 @@ static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset, /* Fast-path if already in coroutine context */ bdrv_rw_co_entry(&rwco); } else { - AioContext *aio_context = bdrv_get_aio_context(bs); + AioContext *aio_context = bdrv_get_aio_context(child->bs); co = qemu_coroutine_create(bdrv_rw_co_entry); qemu_coroutine_enter(co, &rwco); @@ -615,7 +611,7 @@ static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset, /* * Process a synchronous request using coroutines */ -static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf, +static int bdrv_rw_co(BdrvChild *child, int64_t sector_num, uint8_t *buf, int nb_sectors, bool is_write, BdrvRequestFlags flags) { QEMUIOVector qiov; @@ -629,15 +625,15 @@ static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf, } qemu_iovec_init_external(&qiov, &iov, 1); - return bdrv_prwv_co(bs, sector_num << BDRV_SECTOR_BITS, + return bdrv_prwv_co(child, sector_num << BDRV_SECTOR_BITS, &qiov, is_write, flags); } /* return < 0 if error. See bdrv_write() for the return codes */ -int bdrv_read(BlockDriverState *bs, int64_t sector_num, +int bdrv_read(BdrvChild *child, int64_t sector_num, uint8_t *buf, int nb_sectors) { - return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false, 0); + return bdrv_rw_co(child, sector_num, buf, nb_sectors, false, 0); } /* Return < 0 if error. Important errors are: @@ -646,13 +642,13 @@ int bdrv_read(BlockDriverState *bs, int64_t sector_num, -EINVAL Invalid sector number or nb_sectors -EACCES Trying to write a read-only device */ -int bdrv_write(BlockDriverState *bs, int64_t sector_num, +int bdrv_write(BdrvChild *child, int64_t sector_num, const uint8_t *buf, int nb_sectors) { - return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true, 0); + return bdrv_rw_co(child, sector_num, (uint8_t *)buf, nb_sectors, true, 0); } -int bdrv_pwrite_zeroes(BlockDriverState *bs, int64_t offset, +int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, int count, BdrvRequestFlags flags) { QEMUIOVector qiov; @@ -662,7 +658,7 @@ int bdrv_pwrite_zeroes(BlockDriverState *bs, int64_t offset, }; qemu_iovec_init_external(&qiov, &iov, 1); - return bdrv_prwv_co(bs, offset, &qiov, true, + return bdrv_prwv_co(child, offset, &qiov, true, BDRV_REQ_ZERO_WRITE | flags); } @@ -675,9 +671,10 @@ int bdrv_pwrite_zeroes(BlockDriverState *bs, int64_t offset, * * Returns < 0 on error, 0 on success. For error codes see bdrv_write(). */ -int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags) +int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) { int64_t target_sectors, ret, nb_sectors, sector_num = 0; + BlockDriverState *bs = child->bs; BlockDriverState *file; int n; @@ -701,7 +698,7 @@ int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags) sector_num += n; continue; } - ret = bdrv_pwrite_zeroes(bs, sector_num << BDRV_SECTOR_BITS, + ret = bdrv_pwrite_zeroes(child, sector_num << BDRV_SECTOR_BITS, n << BDRV_SECTOR_BITS, flags); if (ret < 0) { error_report("error writing zeroes at sector %" PRId64 ": %s", @@ -712,11 +709,11 @@ int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags) } } -int bdrv_preadv(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov) +int bdrv_preadv(BdrvChild *child, int64_t offset, QEMUIOVector *qiov) { int ret; - ret = bdrv_prwv_co(bs, offset, qiov, false, 0); + ret = bdrv_prwv_co(child, offset, qiov, false, 0); if (ret < 0) { return ret; } @@ -724,7 +721,7 @@ int bdrv_preadv(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov) return qiov->size; } -int bdrv_pread(BlockDriverState *bs, int64_t offset, void *buf, int bytes) +int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int bytes) { QEMUIOVector qiov; struct iovec iov = { @@ -737,14 +734,14 @@ int bdrv_pread(BlockDriverState *bs, int64_t offset, void *buf, int bytes) } qemu_iovec_init_external(&qiov, &iov, 1); - return bdrv_preadv(bs, offset, &qiov); + return bdrv_preadv(child, offset, &qiov); } -int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov) +int bdrv_pwritev(BdrvChild *child, int64_t offset, QEMUIOVector *qiov) { int ret; - ret = bdrv_prwv_co(bs, offset, qiov, true, 0); + ret = bdrv_prwv_co(child, offset, qiov, true, 0); if (ret < 0) { return ret; } @@ -752,8 +749,7 @@ int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov) return qiov->size; } -int bdrv_pwrite(BlockDriverState *bs, int64_t offset, - const void *buf, int bytes) +int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, int bytes) { QEMUIOVector qiov; struct iovec iov = { @@ -766,7 +762,7 @@ int bdrv_pwrite(BlockDriverState *bs, int64_t offset, } qemu_iovec_init_external(&qiov, &iov, 1); - return bdrv_pwritev(bs, offset, &qiov); + return bdrv_pwritev(child, offset, &qiov); } /* @@ -775,17 +771,17 @@ int bdrv_pwrite(BlockDriverState *bs, int64_t offset, * * Returns 0 on success, -errno in error cases. */ -int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset, - const void *buf, int count) +int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, + const void *buf, int count) { int ret; - ret = bdrv_pwrite(bs, offset, buf, count); + ret = bdrv_pwrite(child, offset, buf, count); if (ret < 0) { return ret; } - ret = bdrv_flush(bs); + ret = bdrv_flush(child->bs); if (ret < 0) { return ret; } @@ -945,6 +941,9 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs, if (drv->bdrv_co_pwrite_zeroes && buffer_is_zero(bounce_buffer, iov.iov_len)) { + /* FIXME: Should we (perhaps conditionally) be setting + * BDRV_REQ_MAY_UNMAP, if it will allow for a sparser copy + * that still correctly reads as zero? */ ret = bdrv_co_do_pwrite_zeroes(bs, cluster_offset, cluster_bytes, 0); } else { /* This does not change the data on the disk, it is not necessary @@ -987,7 +986,12 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs, assert((bytes & (align - 1)) == 0); assert(!qiov || bytes == qiov->size); assert((bs->open_flags & BDRV_O_NO_IO) == 0); - assert(!(flags & ~BDRV_REQ_MASK)); + + /* TODO: We would need a per-BDS .supported_read_flags and + * 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))); /* Handle Copy on Read and associated serialisation */ if (flags & BDRV_REQ_COPY_ON_READ) { @@ -1028,7 +1032,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs, } max_bytes = ROUND_UP(MAX(0, total_bytes - offset), align); - if (bytes < max_bytes) { + if (bytes <= max_bytes) { ret = bdrv_driver_preadv(bs, offset, bytes, qiov, 0); } else if (max_bytes > 0) { QEMUIOVector local_qiov; @@ -1057,14 +1061,15 @@ out: /* * Handle a read request in coroutine context */ -int coroutine_fn bdrv_co_preadv(BlockDriverState *bs, +int coroutine_fn bdrv_co_preadv(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags) { + BlockDriverState *bs = child->bs; BlockDriver *drv = bs->drv; BdrvTrackedRequest req; - uint64_t align = bs->request_alignment; + uint64_t align = bs->bl.request_alignment; uint8_t *head_buf = NULL; uint8_t *tail_buf = NULL; QEMUIOVector local_qiov; @@ -1125,7 +1130,7 @@ int coroutine_fn bdrv_co_preadv(BlockDriverState *bs, return ret; } -static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs, +static int coroutine_fn bdrv_co_do_readv(BdrvChild *child, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, BdrvRequestFlags flags) { @@ -1133,19 +1138,20 @@ static int coroutine_fn bdrv_co_do_readv(BlockDriverState *bs, return -EINVAL; } - return bdrv_co_preadv(bs, sector_num << BDRV_SECTOR_BITS, + return bdrv_co_preadv(child, sector_num << BDRV_SECTOR_BITS, nb_sectors << BDRV_SECTOR_BITS, qiov, flags); } -int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov) +int coroutine_fn bdrv_co_readv(BdrvChild *child, int64_t sector_num, + int nb_sectors, QEMUIOVector *qiov) { - trace_bdrv_co_readv(bs, sector_num, nb_sectors); + trace_bdrv_co_readv(child->bs, sector_num, nb_sectors); - return bdrv_co_do_readv(bs, sector_num, nb_sectors, qiov, 0); + return bdrv_co_do_readv(child, sector_num, nb_sectors, qiov, 0); } -#define MAX_WRITE_ZEROES_BOUNCE_BUFFER 32768 +/* Maximum buffer for write zeroes fallback, in bytes */ +#define MAX_WRITE_ZEROES_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS) static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int count, BdrvRequestFlags flags) @@ -1159,8 +1165,8 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int tail = 0; int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_pwrite_zeroes, INT_MAX); - int alignment = MAX(bs->bl.pwrite_zeroes_alignment ?: 1, - bs->request_alignment); + int alignment = MAX(bs->bl.pwrite_zeroes_alignment, + bs->bl.request_alignment); assert(is_power_of_2(alignment)); head = offset & (alignment - 1); @@ -1203,7 +1209,7 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, if (ret == -ENOTSUP) { /* Fall back to bounce buffer if write zeroes is unsupported */ - int max_xfer_len = MIN_NON_ZERO(bs->bl.max_transfer_length, + int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, MAX_WRITE_ZEROES_BOUNCE_BUFFER); BdrvRequestFlags write_flags = flags & ~BDRV_REQ_ZERO_WRITE; @@ -1214,7 +1220,7 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, write_flags &= ~BDRV_REQ_FUA; need_flush = true; } - num = MIN(num, max_xfer_len << BDRV_SECTOR_BITS); + num = MIN(num, max_transfer); iov.iov_len = num; if (iov.iov_base == NULL) { iov.iov_base = qemu_try_blockalign(bs, num); @@ -1231,7 +1237,7 @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, /* Keep bounce buffer around if it is big enough for all * all future requests. */ - if (num < max_xfer_len << BDRV_SECTOR_BITS) { + if (num < max_transfer) { qemu_vfree(iov.iov_base); iov.iov_base = NULL; } @@ -1254,7 +1260,7 @@ fail: */ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, BdrvTrackedRequest *req, int64_t offset, unsigned int bytes, - QEMUIOVector *qiov, int flags) + int64_t align, QEMUIOVector *qiov, int flags) { BlockDriver *drv = bs->drv; bool waited; @@ -1263,6 +1269,9 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, int64_t start_sector = offset >> BDRV_SECTOR_BITS; int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); + assert(is_power_of_2(align)); + assert((offset & (align - 1)) == 0); + assert((bytes & (align - 1)) == 0); assert(!qiov || bytes == qiov->size); assert((bs->open_flags & BDRV_O_NO_IO) == 0); assert(!(flags & ~BDRV_REQ_MASK)); @@ -1316,7 +1325,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs, uint8_t *buf = NULL; QEMUIOVector local_qiov; struct iovec iov; - uint64_t align = bs->request_alignment; + uint64_t align = bs->bl.request_alignment; unsigned int head_padding_bytes, tail_padding_bytes; int ret = 0; @@ -1349,7 +1358,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs, memset(buf + head_padding_bytes, 0, zero_bytes); ret = bdrv_aligned_pwritev(bs, req, offset & ~(align - 1), align, - &local_qiov, + align, &local_qiov, flags & ~BDRV_REQ_ZERO_WRITE); if (ret < 0) { goto fail; @@ -1362,7 +1371,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs, if (bytes >= align) { /* Write the aligned part in the middle. */ uint64_t aligned_bytes = bytes & ~(align - 1); - ret = bdrv_aligned_pwritev(bs, req, offset, aligned_bytes, + ret = bdrv_aligned_pwritev(bs, req, offset, aligned_bytes, align, NULL, flags); if (ret < 0) { goto fail; @@ -1386,7 +1395,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs, bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL); memset(buf, 0, bytes); - ret = bdrv_aligned_pwritev(bs, req, offset, align, + ret = bdrv_aligned_pwritev(bs, req, offset, align, align, &local_qiov, flags & ~BDRV_REQ_ZERO_WRITE); } fail: @@ -1398,12 +1407,13 @@ fail: /* * Handle a write request in coroutine context */ -int coroutine_fn bdrv_co_pwritev(BlockDriverState *bs, +int coroutine_fn bdrv_co_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags) { + BlockDriverState *bs = child->bs; BdrvTrackedRequest req; - uint64_t align = bs->request_alignment; + uint64_t align = bs->bl.request_alignment; uint8_t *head_buf = NULL; uint8_t *tail_buf = NULL; QEMUIOVector local_qiov; @@ -1511,7 +1521,7 @@ int coroutine_fn bdrv_co_pwritev(BlockDriverState *bs, bytes = ROUND_UP(bytes, align); } - ret = bdrv_aligned_pwritev(bs, &req, offset, bytes, + ret = bdrv_aligned_pwritev(bs, &req, offset, bytes, align, use_local_qiov ? &local_qiov : qiov, flags); @@ -1527,7 +1537,7 @@ out: return ret; } -static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs, +static int coroutine_fn bdrv_co_do_writev(BdrvChild *child, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov, BdrvRequestFlags flags) { @@ -1535,29 +1545,28 @@ static int coroutine_fn bdrv_co_do_writev(BlockDriverState *bs, return -EINVAL; } - return bdrv_co_pwritev(bs, sector_num << BDRV_SECTOR_BITS, + return bdrv_co_pwritev(child, sector_num << BDRV_SECTOR_BITS, nb_sectors << BDRV_SECTOR_BITS, qiov, flags); } -int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num, +int coroutine_fn bdrv_co_writev(BdrvChild *child, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov) { - trace_bdrv_co_writev(bs, sector_num, nb_sectors); + trace_bdrv_co_writev(child->bs, sector_num, nb_sectors); - return bdrv_co_do_writev(bs, sector_num, nb_sectors, qiov, 0); + return bdrv_co_do_writev(child, sector_num, nb_sectors, qiov, 0); } -int coroutine_fn bdrv_co_pwrite_zeroes(BlockDriverState *bs, - int64_t offset, int count, - BdrvRequestFlags flags) +int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset, + int count, BdrvRequestFlags flags) { - trace_bdrv_co_pwrite_zeroes(bs, offset, count, flags); + trace_bdrv_co_pwrite_zeroes(child->bs, offset, count, flags); - if (!(bs->open_flags & BDRV_O_UNMAP)) { + if (!(child->bs->open_flags & BDRV_O_UNMAP)) { flags &= ~BDRV_REQ_MAY_UNMAP; } - return bdrv_co_pwritev(bs, offset, count, NULL, + return bdrv_co_pwritev(child, offset, count, NULL, BDRV_REQ_ZERO_WRITE | flags); } @@ -1954,23 +1963,23 @@ int bdrv_readv_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos) /**************************************************************/ /* async I/Os */ -BlockAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num, +BlockAIOCB *bdrv_aio_readv(BdrvChild *child, int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, BlockCompletionFunc *cb, void *opaque) { - trace_bdrv_aio_readv(bs, sector_num, nb_sectors, opaque); + trace_bdrv_aio_readv(child->bs, sector_num, nb_sectors, opaque); - return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors, 0, + return bdrv_co_aio_rw_vector(child, sector_num, qiov, nb_sectors, 0, cb, opaque, false); } -BlockAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num, +BlockAIOCB *bdrv_aio_writev(BdrvChild *child, int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, BlockCompletionFunc *cb, void *opaque) { - trace_bdrv_aio_writev(bs, sector_num, nb_sectors, opaque); + trace_bdrv_aio_writev(child->bs, sector_num, nb_sectors, opaque); - return bdrv_co_aio_rw_vector(bs, sector_num, qiov, nb_sectors, 0, + return bdrv_co_aio_rw_vector(child, sector_num, qiov, nb_sectors, 0, cb, opaque, true); } @@ -2026,6 +2035,7 @@ typedef struct BlockRequest { typedef struct BlockAIOCBCoroutine { BlockAIOCB common; + BdrvChild *child; BlockRequest req; bool is_write; bool need_bh; @@ -2069,20 +2079,19 @@ static void bdrv_co_maybe_schedule_bh(BlockAIOCBCoroutine *acb) static void coroutine_fn bdrv_co_do_rw(void *opaque) { BlockAIOCBCoroutine *acb = opaque; - BlockDriverState *bs = acb->common.bs; if (!acb->is_write) { - acb->req.error = bdrv_co_do_readv(bs, acb->req.sector, + acb->req.error = bdrv_co_do_readv(acb->child, acb->req.sector, acb->req.nb_sectors, acb->req.qiov, acb->req.flags); } else { - acb->req.error = bdrv_co_do_writev(bs, acb->req.sector, + acb->req.error = bdrv_co_do_writev(acb->child, acb->req.sector, acb->req.nb_sectors, acb->req.qiov, acb->req.flags); } bdrv_co_complete(acb); } -static BlockAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs, +static BlockAIOCB *bdrv_co_aio_rw_vector(BdrvChild *child, int64_t sector_num, QEMUIOVector *qiov, int nb_sectors, @@ -2094,7 +2103,8 @@ static BlockAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs, Coroutine *co; BlockAIOCBCoroutine *acb; - acb = qemu_aio_get(&bdrv_em_co_aiocb_info, bs, cb, opaque); + acb = qemu_aio_get(&bdrv_em_co_aiocb_info, child->bs, cb, opaque); + acb->child = child; acb->need_bh = true; acb->req.error = -EINPROGRESS; acb->req.sector = sector_num; @@ -2200,9 +2210,15 @@ void qemu_aio_unref(void *p) /**************************************************************/ /* Coroutine block device emulation */ +typedef struct FlushCo { + BlockDriverState *bs; + int ret; +} FlushCo; + + static void coroutine_fn bdrv_flush_co_entry(void *opaque) { - RwCo *rwco = opaque; + FlushCo *rwco = opaque; rwco->ret = bdrv_co_flush(rwco->bs); } @@ -2286,25 +2302,25 @@ out: int bdrv_flush(BlockDriverState *bs) { Coroutine *co; - RwCo rwco = { + FlushCo flush_co = { .bs = bs, .ret = NOT_DONE, }; if (qemu_in_coroutine()) { /* Fast-path if already in coroutine context */ - bdrv_flush_co_entry(&rwco); + bdrv_flush_co_entry(&flush_co); } else { AioContext *aio_context = bdrv_get_aio_context(bs); co = qemu_coroutine_create(bdrv_flush_co_entry); - qemu_coroutine_enter(co, &rwco); - while (rwco.ret == NOT_DONE) { + qemu_coroutine_enter(co, &flush_co); + while (flush_co.ret == NOT_DONE) { aio_poll(aio_context, true); } } - return rwco.ret; + return flush_co.ret; } typedef struct DiscardCo { @@ -2355,19 +2371,21 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num, goto out; } - max_discard = MIN_NON_ZERO(bs->bl.max_discard, BDRV_REQUEST_MAX_SECTORS); + max_discard = MIN_NON_ZERO(bs->bl.max_pdiscard >> BDRV_SECTOR_BITS, + BDRV_REQUEST_MAX_SECTORS); while (nb_sectors > 0) { int ret; int num = nb_sectors; + int discard_alignment = bs->bl.pdiscard_alignment >> BDRV_SECTOR_BITS; /* align request */ - if (bs->bl.discard_alignment && - num >= bs->bl.discard_alignment && - sector_num % bs->bl.discard_alignment) { - if (num > bs->bl.discard_alignment) { - num = bs->bl.discard_alignment; + if (discard_alignment && + num >= discard_alignment && + sector_num % discard_alignment) { + if (num > discard_alignment) { + num = discard_alignment; } - num -= sector_num % bs->bl.discard_alignment; + num -= sector_num % discard_alignment; } /* limit request size */ diff --git a/block/iscsi.c b/block/iscsi.c index 9bb5ff6216..24f78a7755 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -473,9 +473,10 @@ iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors, return -EINVAL; } - if (bs->bl.max_transfer_length && nb_sectors > bs->bl.max_transfer_length) { + if (bs->bl.max_transfer && + nb_sectors << BDRV_SECTOR_BITS > bs->bl.max_transfer) { error_report("iSCSI Error: Write of %d sectors exceeds max_xfer_len " - "of %d sectors", nb_sectors, bs->bl.max_transfer_length); + "of %" PRIu32 " bytes", nb_sectors, bs->bl.max_transfer); return -EINVAL; } @@ -650,9 +651,10 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs, return -EINVAL; } - if (bs->bl.max_transfer_length && nb_sectors > bs->bl.max_transfer_length) { + if (bs->bl.max_transfer && + nb_sectors << BDRV_SECTOR_BITS > bs->bl.max_transfer) { error_report("iSCSI Error: Read of %d sectors exceeds max_xfer_len " - "of %d sectors", nb_sectors, bs->bl.max_transfer_length); + "of %" PRIu32 " bytes", nb_sectors, bs->bl.max_transfer); return -EINVAL; } @@ -1589,14 +1591,13 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags, goto out; } bs->total_sectors = sector_lun2qemu(iscsilun->num_blocks, iscsilun); - bs->request_alignment = iscsilun->block_size; /* We don't have any emulation for devices other than disks and CD-ROMs, so * this must be sg ioctl compatible. We force it to be sg, otherwise qemu * will try to read from the device to guess the image format. */ if (iscsilun->type != TYPE_DISK && iscsilun->type != TYPE_ROM) { - bs->sg = 1; + bs->sg = true; } task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1, @@ -1696,34 +1697,33 @@ static void iscsi_close(BlockDriverState *bs) memset(iscsilun, 0, sizeof(IscsiLun)); } -static int sector_limits_lun2qemu(int64_t sector, IscsiLun *iscsilun) -{ - return MIN(sector_lun2qemu(sector, iscsilun), INT_MAX / 2 + 1); -} - static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp) { /* We don't actually refresh here, but just return data queried in * iscsi_open(): iscsi targets don't change their limits. */ IscsiLun *iscsilun = bs->opaque; - uint32_t max_xfer_len = iscsilun->use_16_for_rw ? 0xffffffff : 0xffff; + uint64_t max_xfer_len = iscsilun->use_16_for_rw ? 0xffffffff : 0xffff; + + bs->bl.request_alignment = iscsilun->block_size; if (iscsilun->bl.max_xfer_len) { max_xfer_len = MIN(max_xfer_len, iscsilun->bl.max_xfer_len); } - bs->bl.max_transfer_length = sector_limits_lun2qemu(max_xfer_len, iscsilun); + if (max_xfer_len * iscsilun->block_size < INT_MAX) { + bs->bl.max_transfer = max_xfer_len * iscsilun->block_size; + } if (iscsilun->lbp.lbpu) { - if (iscsilun->bl.max_unmap < 0xffffffff) { - bs->bl.max_discard = - sector_limits_lun2qemu(iscsilun->bl.max_unmap, iscsilun); + if (iscsilun->bl.max_unmap < 0xffffffff / iscsilun->block_size) { + bs->bl.max_pdiscard = + iscsilun->bl.max_unmap * iscsilun->block_size; } - bs->bl.discard_alignment = - sector_limits_lun2qemu(iscsilun->bl.opt_unmap_gran, iscsilun); + bs->bl.pdiscard_alignment = + iscsilun->bl.opt_unmap_gran * iscsilun->block_size; } else { - bs->bl.discard_alignment = iscsilun->block_size >> BDRV_SECTOR_BITS; + bs->bl.pdiscard_alignment = iscsilun->block_size; } if (iscsilun->bl.max_ws_len < 0xffffffff / iscsilun->block_size) { @@ -1736,8 +1736,11 @@ static void iscsi_refresh_limits(BlockDriverState *bs, Error **errp) } else { bs->bl.pwrite_zeroes_alignment = iscsilun->block_size; } - bs->bl.opt_transfer_length = - sector_limits_lun2qemu(iscsilun->bl.opt_xfer_len, iscsilun); + if (iscsilun->bl.opt_xfer_len && + iscsilun->bl.opt_xfer_len < INT_MAX / iscsilun->block_size) { + bs->bl.opt_transfer = pow2floor(iscsilun->bl.opt_xfer_len * + iscsilun->block_size); + } } /* Note that this will not re-establish a connection with an iSCSI target - it diff --git a/block/linux-aio.c b/block/linux-aio.c index e468960146..7df8651581 100644 --- a/block/linux-aio.c +++ b/block/linux-aio.c @@ -87,7 +87,7 @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb) qemu_iovec_memset(laiocb->qiov, ret, 0, laiocb->qiov->size - ret); } else { - ret = -EINVAL; + ret = -ENOSPC; } } } diff --git a/block/nbd-client.c b/block/nbd-client.c index 4d13444409..420bce89f3 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -269,10 +269,6 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num, return -reply.error; } -/* qemu-nbd has a limit of slightly less than 1M per request. Try to - * remain aligned to 4K. */ -#define NBD_MAX_SECTORS 2040 - int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov) { diff --git a/block/nbd.c b/block/nbd.c index 6015e8b537..08e5b67b2f 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -362,8 +362,8 @@ static int nbd_co_flush(BlockDriverState *bs) static void nbd_refresh_limits(BlockDriverState *bs, Error **errp) { - bs->bl.max_discard = UINT32_MAX >> BDRV_SECTOR_BITS; - bs->bl.max_transfer_length = UINT32_MAX >> BDRV_SECTOR_BITS; + bs->bl.max_pdiscard = NBD_MAX_BUFFER_SIZE; + bs->bl.max_transfer = NBD_MAX_BUFFER_SIZE; } static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num, diff --git a/block/parallels.c b/block/parallels.c index d6a1a616b6..807a80169f 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -210,7 +210,7 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num, int ret; space += s->prealloc_size; if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE) { - ret = bdrv_pwrite_zeroes(bs->file->bs, + ret = bdrv_pwrite_zeroes(bs->file, s->data_end << BDRV_SECTOR_BITS, space << BDRV_SECTOR_BITS, 0); } else { @@ -250,7 +250,7 @@ static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs) if (off + to_write > s->header_size) { to_write = s->header_size - off; } - ret = bdrv_pwrite(bs->file->bs, off, (uint8_t *)s->header + off, + ret = bdrv_pwrite(bs->file, off, (uint8_t *)s->header + off, to_write); if (ret < 0) { qemu_co_mutex_unlock(&s->lock); @@ -311,7 +311,7 @@ static coroutine_fn int parallels_co_writev(BlockDriverState *bs, qemu_iovec_reset(&hd_qiov); qemu_iovec_concat(&hd_qiov, qiov, bytes_done, nbytes); - ret = bdrv_co_writev(bs->file->bs, position, n, &hd_qiov); + ret = bdrv_co_writev(bs->file, position, n, &hd_qiov); if (ret < 0) { break; } @@ -351,7 +351,7 @@ static coroutine_fn int parallels_co_readv(BlockDriverState *bs, qemu_iovec_reset(&hd_qiov); qemu_iovec_concat(&hd_qiov, qiov, bytes_done, nbytes); - ret = bdrv_co_readv(bs->file->bs, position, n, &hd_qiov); + ret = bdrv_co_readv(bs->file, position, n, &hd_qiov); if (ret < 0) { break; } @@ -432,7 +432,7 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res, } if (flush_bat) { - ret = bdrv_pwrite_sync(bs->file->bs, 0, s->header, s->header_size); + ret = bdrv_pwrite_sync(bs->file, 0, s->header, s->header_size); if (ret < 0) { res->check_errors++; return ret; @@ -563,7 +563,7 @@ static int parallels_update_header(BlockDriverState *bs) if (size > s->header_size) { size = s->header_size; } - return bdrv_pwrite_sync(bs->file->bs, 0, s->header, size); + return bdrv_pwrite_sync(bs->file, 0, s->header, size); } static int parallels_open(BlockDriverState *bs, QDict *options, int flags, @@ -576,7 +576,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, Error *local_err = NULL; char *buf; - ret = bdrv_pread(bs->file->bs, 0, &ph, sizeof(ph)); + ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph)); if (ret < 0) { goto fail; } @@ -631,7 +631,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, s->header_size = size; } - ret = bdrv_pread(bs->file->bs, 0, s->header, s->header_size); + ret = bdrv_pread(bs->file, 0, s->header, s->header_size); if (ret < 0) { goto fail; } diff --git a/block/qcow.c b/block/qcow.c index 312af52816..ac849bd47c 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -105,7 +105,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, int ret; QCowHeader header; - ret = bdrv_pread(bs->file->bs, 0, &header, sizeof(header)); + ret = bdrv_pread(bs->file, 0, &header, sizeof(header)); if (ret < 0) { goto fail; } @@ -174,7 +174,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - bs->encrypted = 1; + bs->encrypted = true; } s->cluster_bits = header.cluster_bits; s->cluster_size = 1 << s->cluster_bits; @@ -208,7 +208,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file->bs, s->l1_table_offset, s->l1_table, + ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, s->l1_size * sizeof(uint64_t)); if (ret < 0) { goto fail; @@ -239,7 +239,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, ret = -EINVAL; goto fail; } - ret = bdrv_pread(bs->file->bs, header.backing_file_offset, + ret = bdrv_pread(bs->file, header.backing_file_offset, bs->backing_file, len); if (ret < 0) { goto fail; @@ -390,7 +390,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs, /* update the L1 entry */ s->l1_table[l1_index] = l2_offset; tmp = cpu_to_be64(l2_offset); - if (bdrv_pwrite_sync(bs->file->bs, + if (bdrv_pwrite_sync(bs->file, s->l1_table_offset + l1_index * sizeof(tmp), &tmp, sizeof(tmp)) < 0) return 0; @@ -420,11 +420,11 @@ static uint64_t get_cluster_offset(BlockDriverState *bs, l2_table = s->l2_cache + (min_index << s->l2_bits); if (new_l2_table) { memset(l2_table, 0, s->l2_size * sizeof(uint64_t)); - if (bdrv_pwrite_sync(bs->file->bs, l2_offset, l2_table, + if (bdrv_pwrite_sync(bs->file, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) < 0) return 0; } else { - if (bdrv_pread(bs->file->bs, l2_offset, l2_table, + if (bdrv_pread(bs->file, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)) != s->l2_size * sizeof(uint64_t)) return 0; @@ -450,7 +450,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs, cluster_offset = (cluster_offset + s->cluster_size - 1) & ~(s->cluster_size - 1); /* write the cluster content */ - if (bdrv_pwrite(bs->file->bs, cluster_offset, s->cluster_cache, + if (bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache, s->cluster_size) != s->cluster_size) return -1; @@ -480,7 +480,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs, errno = EIO; return -1; } - if (bdrv_pwrite(bs->file->bs, + if (bdrv_pwrite(bs->file, cluster_offset + i * 512, s->cluster_data, 512) != 512) return -1; @@ -495,7 +495,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs, /* update L2 table */ tmp = cpu_to_be64(cluster_offset); l2_table[l2_index] = tmp; - if (bdrv_pwrite_sync(bs->file->bs, l2_offset + l2_index * sizeof(tmp), + if (bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp), &tmp, sizeof(tmp)) < 0) return 0; } @@ -565,7 +565,7 @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset) if (s->cluster_cache_offset != coffset) { csize = cluster_offset >> (63 - s->cluster_bits); csize &= (s->cluster_size - 1); - ret = bdrv_pread(bs->file->bs, coffset, s->cluster_data, csize); + ret = bdrv_pread(bs->file, coffset, s->cluster_data, csize); if (ret != csize) return -1; if (decompress_buffer(s->cluster_cache, s->cluster_size, @@ -619,8 +619,7 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num, hd_iov.iov_len = n * 512; qemu_iovec_init_external(&hd_qiov, &hd_iov, 1); qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_readv(bs->backing->bs, sector_num, - n, &hd_qiov); + ret = bdrv_co_readv(bs->backing, sector_num, n, &hd_qiov); qemu_co_mutex_lock(&s->lock); if (ret < 0) { goto fail; @@ -644,7 +643,7 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num, hd_iov.iov_len = n * 512; qemu_iovec_init_external(&hd_qiov, &hd_iov, 1); qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_readv(bs->file->bs, + ret = bdrv_co_readv(bs->file, (cluster_offset >> 9) + index_in_cluster, n, &hd_qiov); qemu_co_mutex_lock(&s->lock); @@ -746,7 +745,7 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num, hd_iov.iov_len = n * 512; qemu_iovec_init_external(&hd_qiov, &hd_iov, 1); qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_writev(bs->file->bs, + ret = bdrv_co_writev(bs->file, (cluster_offset >> 9) + index_in_cluster, n, &hd_qiov); qemu_co_mutex_lock(&s->lock); @@ -900,7 +899,7 @@ static int qcow_make_empty(BlockDriverState *bs) int ret; memset(s->l1_table, 0, l1_length); - if (bdrv_pwrite_sync(bs->file->bs, s->l1_table_offset, s->l1_table, + if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table, l1_length) < 0) return -1; ret = bdrv_truncate(bs->file->bs, s->l1_table_offset + l1_length); @@ -914,6 +913,49 @@ static int qcow_make_empty(BlockDriverState *bs) return 0; } +typedef struct QcowWriteCo { + BlockDriverState *bs; + int64_t sector_num; + const uint8_t *buf; + int nb_sectors; + int ret; +} QcowWriteCo; + +static void qcow_write_co_entry(void *opaque) +{ + QcowWriteCo *co = opaque; + QEMUIOVector qiov; + + struct iovec iov = (struct iovec) { + .iov_base = (uint8_t*) co->buf, + .iov_len = co->nb_sectors * BDRV_SECTOR_SIZE, + }; + qemu_iovec_init_external(&qiov, &iov, 1); + + co->ret = qcow_co_writev(co->bs, co->sector_num, co->nb_sectors, &qiov); +} + +/* Wrapper for non-coroutine contexts */ +static int qcow_write(BlockDriverState *bs, int64_t sector_num, + const uint8_t *buf, int nb_sectors) +{ + Coroutine *co; + AioContext *aio_context = bdrv_get_aio_context(bs); + QcowWriteCo data = { + .bs = bs, + .sector_num = sector_num, + .buf = buf, + .nb_sectors = nb_sectors, + .ret = -EINPROGRESS, + }; + co = qemu_coroutine_create(qcow_write_co_entry); + qemu_coroutine_enter(co, &data); + while (data.ret == -EINPROGRESS) { + aio_poll(aio_context, true); + } + return data.ret; +} + /* XXX: put compressed sectors first, then all the cluster aligned tables to avoid losing bytes in alignment */ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num, @@ -970,7 +1012,7 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num, if (ret != Z_STREAM_END || out_len >= s->cluster_size) { /* could not compress: write normal cluster */ - ret = bdrv_write(bs, sector_num, buf, s->cluster_sectors); + ret = qcow_write(bs, sector_num, buf, s->cluster_sectors); if (ret < 0) { goto fail; } @@ -983,7 +1025,7 @@ static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num, } cluster_offset &= s->cluster_offset_mask; - ret = bdrv_pwrite(bs->file->bs, cluster_offset, out_buf, out_len); + ret = bdrv_pwrite(bs->file, cluster_offset, out_buf, out_len); if (ret < 0) { goto fail; } diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index 580631c3d8..6eaefeddc4 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -210,7 +210,7 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE); } - ret = bdrv_pwrite(bs->file->bs, c->entries[i].offset, + ret = bdrv_pwrite(bs->file, c->entries[i].offset, qcow2_cache_get_table_addr(bs, c, i), s->cluster_size); if (ret < 0) { return ret; @@ -357,7 +357,7 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD); } - ret = bdrv_pread(bs->file->bs, offset, + ret = bdrv_pread(bs->file, offset, qcow2_cache_get_table_addr(bs, c, i), s->cluster_size); if (ret < 0) { diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index 0fb43566fb..6b92ce9429 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -108,7 +108,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE); for(i = 0; i < s->l1_size; i++) new_l1_table[i] = cpu_to_be64(new_l1_table[i]); - ret = bdrv_pwrite_sync(bs->file->bs, new_l1_table_offset, + ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset, new_l1_table, new_l1_size2); if (ret < 0) goto fail; @@ -117,9 +117,9 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, /* set new table */ BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE); - cpu_to_be32w((uint32_t*)data, new_l1_size); + stl_be_p(data, new_l1_size); stq_be_p(data + 4, new_l1_table_offset); - ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, l1_size), + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size), data, sizeof(data)); if (ret < 0) { goto fail; @@ -185,7 +185,7 @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index) } BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE); - ret = bdrv_pwrite_sync(bs->file->bs, + ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset + 8 * l1_start_index, buf, sizeof(buf)); if (ret < 0) { @@ -446,7 +446,7 @@ static int coroutine_fn do_perform_cow(BlockDriverState *bs, } BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE); - ret = bdrv_co_pwritev(bs->file->bs, cluster_offset + offset_in_cluster, + ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster, bytes, &qiov, 0); if (ret < 0) { goto out; @@ -1408,7 +1408,7 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset) sector_offset = coffset & 511; csize = nb_csectors * 512 - sector_offset; BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED); - ret = bdrv_read(bs->file->bs, coffset >> 9, s->cluster_data, + ret = bdrv_read(bs->file, coffset >> 9, s->cluster_data, nb_csectors); if (ret < 0) { return ret; @@ -1677,7 +1677,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, (void **)&l2_table); } else { /* load inactive L2 tables from disk */ - ret = bdrv_read(bs->file->bs, l2_offset / BDRV_SECTOR_SIZE, + ret = bdrv_read(bs->file, l2_offset / BDRV_SECTOR_SIZE, (void *)l2_table, s->cluster_sectors); } if (ret < 0) { @@ -1752,7 +1752,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } - ret = bdrv_pwrite_zeroes(bs->file->bs, offset, s->cluster_size, 0); + ret = bdrv_pwrite_zeroes(bs->file, offset, s->cluster_size, 0); if (ret < 0) { if (!preallocated) { qcow2_free_clusters(bs, offset, s->cluster_size, @@ -1784,7 +1784,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, goto fail; } - ret = bdrv_write(bs->file->bs, l2_offset / BDRV_SECTOR_SIZE, + ret = bdrv_write(bs->file, l2_offset / BDRV_SECTOR_SIZE, (void *)l2_table, s->cluster_sectors); if (ret < 0) { goto fail; @@ -1859,7 +1859,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs, l1_table = g_realloc(l1_table, l1_sectors * BDRV_SECTOR_SIZE); - ret = bdrv_read(bs->file->bs, + ret = bdrv_read(bs->file, s->snapshots[i].l1_table_offset / BDRV_SECTOR_SIZE, (void *)l1_table, l1_sectors); if (ret < 0) { diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index 3bef410839..49b6ce6bfd 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -104,7 +104,7 @@ int qcow2_refcount_init(BlockDriverState *bs) goto fail; } BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD); - ret = bdrv_pread(bs->file->bs, s->refcount_table_offset, + ret = bdrv_pread(bs->file, s->refcount_table_offset, s->refcount_table, refcount_table_size2); if (ret < 0) { goto fail; @@ -431,7 +431,7 @@ static int alloc_refcount_block(BlockDriverState *bs, if (refcount_table_index < s->refcount_table_size) { uint64_t data64 = cpu_to_be64(new_block); BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_HOOKUP); - ret = bdrv_pwrite_sync(bs->file->bs, + ret = bdrv_pwrite_sync(bs->file, s->refcount_table_offset + refcount_table_index * sizeof(uint64_t), &data64, sizeof(data64)); if (ret < 0) { @@ -533,7 +533,7 @@ static int alloc_refcount_block(BlockDriverState *bs, /* Write refcount blocks to disk */ BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS); - ret = bdrv_pwrite_sync(bs->file->bs, meta_offset, new_blocks, + ret = bdrv_pwrite_sync(bs->file, meta_offset, new_blocks, blocks_clusters * s->cluster_size); g_free(new_blocks); new_blocks = NULL; @@ -547,7 +547,7 @@ static int alloc_refcount_block(BlockDriverState *bs, } BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE); - ret = bdrv_pwrite_sync(bs->file->bs, table_offset, new_table, + ret = bdrv_pwrite_sync(bs->file, table_offset, new_table, table_size * sizeof(uint64_t)); if (ret < 0) { goto fail_table; @@ -562,10 +562,10 @@ static int alloc_refcount_block(BlockDriverState *bs, uint64_t d64; uint32_t d32; } data; - cpu_to_be64w(&data.d64, table_offset); - cpu_to_be32w(&data.d32, table_clusters); + data.d64 = cpu_to_be64(table_offset); + data.d32 = cpu_to_be32(table_clusters); BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE); - ret = bdrv_pwrite_sync(bs->file->bs, + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, refcount_table_offset), &data, sizeof(data)); if (ret < 0) { @@ -1070,7 +1070,7 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs, } l1_allocated = true; - ret = bdrv_pread(bs->file->bs, l1_table_offset, l1_table, l1_size2); + ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2); if (ret < 0) { goto fail; } @@ -1223,7 +1223,7 @@ fail: cpu_to_be64s(&l1_table[i]); } - ret = bdrv_pwrite_sync(bs->file->bs, l1_table_offset, + ret = bdrv_pwrite_sync(bs->file, l1_table_offset, l1_table, l1_size2); for (i = 0; i < l1_size; i++) { @@ -1382,7 +1382,7 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res, l2_size = s->l2_size * sizeof(uint64_t); l2_table = g_malloc(l2_size); - ret = bdrv_pread(bs->file->bs, l2_offset, l2_table, l2_size); + ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size); if (ret < 0) { fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n"); res->check_errors++; @@ -1514,7 +1514,7 @@ static int check_refcounts_l1(BlockDriverState *bs, res->check_errors++; goto fail; } - ret = bdrv_pread(bs->file->bs, l1_table_offset, l1_table, l1_size2); + ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2); if (ret < 0) { fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n"); res->check_errors++; @@ -1612,7 +1612,7 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, } } - ret = bdrv_pread(bs->file->bs, l2_offset, l2_table, + ret = bdrv_pread(bs->file, l2_offset, l2_table, s->l2_size * sizeof(uint64_t)); if (ret < 0) { fprintf(stderr, "ERROR: Could not read L2 table: %s\n", @@ -1664,7 +1664,7 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res, goto fail; } - ret = bdrv_pwrite(bs->file->bs, l2_offset, l2_table, + ret = bdrv_pwrite(bs->file, l2_offset, l2_table, s->cluster_size); if (ret < 0) { fprintf(stderr, "ERROR: Could not write L2 table: %s\n", @@ -2098,7 +2098,7 @@ write_refblocks: on_disk_refblock = (void *)((char *) *refcount_table + refblock_index * s->cluster_size); - ret = bdrv_write(bs->file->bs, refblock_offset / BDRV_SECTOR_SIZE, + ret = bdrv_write(bs->file, refblock_offset / BDRV_SECTOR_SIZE, on_disk_refblock, s->cluster_sectors); if (ret < 0) { fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret)); @@ -2147,7 +2147,7 @@ write_refblocks: } assert(reftable_size < INT_MAX / sizeof(uint64_t)); - ret = bdrv_pwrite(bs->file->bs, reftable_offset, on_disk_reftable, + ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable, reftable_size * sizeof(uint64_t)); if (ret < 0) { fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret)); @@ -2155,12 +2155,11 @@ write_refblocks: } /* Enter new reftable into the image header */ - cpu_to_be64w(&reftable_offset_and_clusters.reftable_offset, - reftable_offset); - cpu_to_be32w(&reftable_offset_and_clusters.reftable_clusters, - size_to_clusters(s, reftable_size * sizeof(uint64_t))); - ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, - refcount_table_offset), + reftable_offset_and_clusters.reftable_offset = cpu_to_be64(reftable_offset); + reftable_offset_and_clusters.reftable_clusters = + cpu_to_be32(size_to_clusters(s, reftable_size * sizeof(uint64_t))); + ret = bdrv_pwrite_sync(bs->file, + offsetof(QCowHeader, refcount_table_offset), &reftable_offset_and_clusters, sizeof(reftable_offset_and_clusters)); if (ret < 0) { @@ -2407,7 +2406,7 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset, return -ENOMEM; } - ret = bdrv_pread(bs->file->bs, l1_ofs, l1, l1_sz2); + ret = bdrv_pread(bs->file, l1_ofs, l1, l1_sz2); if (ret < 0) { g_free(l1); return ret; @@ -2560,7 +2559,7 @@ static int flush_refblock(BlockDriverState *bs, uint64_t **reftable, return ret; } - ret = bdrv_pwrite(bs->file->bs, offset, refblock, s->cluster_size); + ret = bdrv_pwrite(bs->file, offset, refblock, s->cluster_size); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write refblock"); return ret; @@ -2830,7 +2829,7 @@ int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order, cpu_to_be64s(&new_reftable[i]); } - ret = bdrv_pwrite(bs->file->bs, new_reftable_offset, new_reftable, + ret = bdrv_pwrite(bs->file, new_reftable_offset, new_reftable, new_reftable_size * sizeof(uint64_t)); for (i = 0; i < new_reftable_size; i++) { diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c index 242fb21d6e..032424322a 100644 --- a/block/qcow2-snapshot.c +++ b/block/qcow2-snapshot.c @@ -67,7 +67,7 @@ int qcow2_read_snapshots(BlockDriverState *bs) for(i = 0; i < s->nb_snapshots; i++) { /* Read statically sized part of the snapshot header */ offset = align_offset(offset, 8); - ret = bdrv_pread(bs->file->bs, offset, &h, sizeof(h)); + ret = bdrv_pread(bs->file, offset, &h, sizeof(h)); if (ret < 0) { goto fail; } @@ -86,7 +86,7 @@ int qcow2_read_snapshots(BlockDriverState *bs) name_size = be16_to_cpu(h.name_size); /* Read extra data */ - ret = bdrv_pread(bs->file->bs, offset, &extra, + ret = bdrv_pread(bs->file, offset, &extra, MIN(sizeof(extra), extra_data_size)); if (ret < 0) { goto fail; @@ -105,7 +105,7 @@ int qcow2_read_snapshots(BlockDriverState *bs) /* Read snapshot ID */ sn->id_str = g_malloc(id_str_size + 1); - ret = bdrv_pread(bs->file->bs, offset, sn->id_str, id_str_size); + ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size); if (ret < 0) { goto fail; } @@ -114,7 +114,7 @@ int qcow2_read_snapshots(BlockDriverState *bs) /* Read snapshot name */ sn->name = g_malloc(name_size + 1); - ret = bdrv_pread(bs->file->bs, offset, sn->name, name_size); + ret = bdrv_pread(bs->file, offset, sn->name, name_size); if (ret < 0) { goto fail; } @@ -217,25 +217,25 @@ static int qcow2_write_snapshots(BlockDriverState *bs) h.name_size = cpu_to_be16(name_size); offset = align_offset(offset, 8); - ret = bdrv_pwrite(bs->file->bs, offset, &h, sizeof(h)); + ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h)); if (ret < 0) { goto fail; } offset += sizeof(h); - ret = bdrv_pwrite(bs->file->bs, offset, &extra, sizeof(extra)); + ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra)); if (ret < 0) { goto fail; } offset += sizeof(extra); - ret = bdrv_pwrite(bs->file->bs, offset, sn->id_str, id_str_size); + ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size); if (ret < 0) { goto fail; } offset += id_str_size; - ret = bdrv_pwrite(bs->file->bs, offset, sn->name, name_size); + ret = bdrv_pwrite(bs->file, offset, sn->name, name_size); if (ret < 0) { goto fail; } @@ -257,7 +257,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs) header_data.nb_snapshots = cpu_to_be32(s->nb_snapshots); header_data.snapshots_offset = cpu_to_be64(snapshots_offset); - ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, nb_snapshots), + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots), &header_data, sizeof(header_data)); if (ret < 0) { goto fail; @@ -399,7 +399,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info) goto fail; } - ret = bdrv_pwrite(bs->file->bs, sn->l1_table_offset, l1_table, + ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table, s->l1_size * sizeof(uint64_t)); if (ret < 0) { goto fail; @@ -512,7 +512,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) goto fail; } - ret = bdrv_pread(bs->file->bs, sn->l1_table_offset, + ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes); if (ret < 0) { goto fail; @@ -530,7 +530,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id) goto fail; } - ret = bdrv_pwrite_sync(bs->file->bs, s->l1_table_offset, sn_l1_table, + ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table, cur_l1_bytes); if (ret < 0) { goto fail; @@ -716,7 +716,7 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs, return -ENOMEM; } - ret = bdrv_pread(bs->file->bs, sn->l1_table_offset, + ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes); if (ret < 0) { error_setg(errp, "Failed to read l1 table for snapshot"); diff --git a/block/qcow2.c b/block/qcow2.c index 23f666d4ae..a5ea19b0b6 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -107,7 +107,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, printf("attempting to read extended header in offset %lu\n", offset); #endif - ret = bdrv_pread(bs->file->bs, offset, &ext, sizeof(ext)); + ret = bdrv_pread(bs->file, offset, &ext, sizeof(ext)); if (ret < 0) { error_setg_errno(errp, -ret, "qcow2_read_extension: ERROR: " "pread fail from offset %" PRIu64, offset); @@ -135,7 +135,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, sizeof(bs->backing_format)); return 2; } - ret = bdrv_pread(bs->file->bs, offset, bs->backing_format, ext.len); + ret = bdrv_pread(bs->file, offset, bs->backing_format, ext.len); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: ext_backing_format: " "Could not read format name"); @@ -151,7 +151,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, case QCOW2_EXT_MAGIC_FEATURE_TABLE: if (p_feature_table != NULL) { void* feature_table = g_malloc0(ext.len + 2 * sizeof(Qcow2Feature)); - ret = bdrv_pread(bs->file->bs, offset , feature_table, ext.len); + ret = bdrv_pread(bs->file, offset , feature_table, ext.len); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: ext_feature_table: " "Could not read table"); @@ -172,7 +172,7 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset, uext->len = ext.len; QLIST_INSERT_HEAD(&s->unknown_header_ext, uext, next); - ret = bdrv_pread(bs->file->bs, offset , uext->data, uext->len); + ret = bdrv_pread(bs->file, offset , uext->data, uext->len); if (ret < 0) { error_setg_errno(errp, -ret, "ERROR: unknown extension: " "Could not read data"); @@ -249,7 +249,7 @@ int qcow2_mark_dirty(BlockDriverState *bs) } val = cpu_to_be64(s->incompatible_features | QCOW2_INCOMPAT_DIRTY); - ret = bdrv_pwrite(bs->file->bs, offsetof(QCowHeader, incompatible_features), + ret = bdrv_pwrite(bs->file, offsetof(QCowHeader, incompatible_features), &val, sizeof(val)); if (ret < 0) { return ret; @@ -817,7 +817,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, uint64_t ext_end; uint64_t l1_vm_state_index; - ret = bdrv_pread(bs->file->bs, 0, &header, sizeof(header)); + ret = bdrv_pread(bs->file, 0, &header, sizeof(header)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read qcow2 header"); goto fail; @@ -892,7 +892,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, if (header.header_length > sizeof(header)) { s->unknown_header_fields_size = header.header_length - sizeof(header); s->unknown_header_fields = g_malloc(s->unknown_header_fields_size); - ret = bdrv_pread(bs->file->bs, sizeof(header), s->unknown_header_fields, + ret = bdrv_pread(bs->file, sizeof(header), s->unknown_header_fields, s->unknown_header_fields_size); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read unknown qcow2 header " @@ -980,10 +980,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - bs->encrypted = 1; - - /* Encryption works on a sector granularity */ - bs->request_alignment = BDRV_SECTOR_SIZE; + bs->encrypted = true; } s->l2_bits = s->cluster_bits - 3; /* L2 is always one cluster */ @@ -1069,7 +1066,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, ret = -ENOMEM; goto fail; } - ret = bdrv_pread(bs->file->bs, s->l1_table_offset, s->l1_table, + ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table, s->l1_size * sizeof(uint64_t)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read L1 table"); @@ -1125,7 +1122,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, ret = -EINVAL; goto fail; } - ret = bdrv_pread(bs->file->bs, header.backing_file_offset, + ret = bdrv_pread(bs->file, header.backing_file_offset, bs->backing_file, len); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read backing file name"); @@ -1202,6 +1199,10 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp) { BDRVQcow2State *s = bs->opaque; + if (bs->encrypted) { + /* Encryption works on a sector granularity */ + bs->bl.request_alignment = BDRV_SECTOR_SIZE; + } bs->bl.pwrite_zeroes_alignment = s->cluster_size; } @@ -1442,7 +1443,7 @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_preadv(bs->backing->bs, offset, n1, + ret = bdrv_co_preadv(bs->backing, offset, n1, &local_qiov, 0); qemu_co_mutex_lock(&s->lock); @@ -1505,7 +1506,7 @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_preadv(bs->file->bs, + ret = bdrv_co_preadv(bs->file, cluster_offset + offset_in_cluster, cur_bytes, &hd_qiov, 0); qemu_co_mutex_lock(&s->lock); @@ -1636,7 +1637,7 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); trace_qcow2_writev_data(qemu_coroutine_self(), cluster_offset + offset_in_cluster); - ret = bdrv_co_pwritev(bs->file->bs, + ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster, cur_bytes, &hd_qiov, 0); qemu_co_mutex_lock(&s->lock); @@ -1975,7 +1976,7 @@ int qcow2_update_header(BlockDriverState *bs) } /* Write the new header */ - ret = bdrv_pwrite(bs->file->bs, 0, header, s->cluster_size); + ret = bdrv_pwrite(bs->file, 0, header, s->cluster_size); if (ret < 0) { goto fail; } @@ -2058,7 +2059,7 @@ static int preallocate(BlockDriverState *bs) */ if (host_offset != 0) { uint8_t data = 0; - ret = bdrv_pwrite(bs->file->bs, (host_offset + cur_bytes) - 1, + ret = bdrv_pwrite(bs->file, (host_offset + cur_bytes) - 1, &data, 1); if (ret < 0) { return ret; @@ -2522,7 +2523,7 @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset) /* write updated header.size */ offset = cpu_to_be64(offset); - ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, size), + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, size), &offset, sizeof(uint64_t)); if (ret < 0) { return ret; @@ -2532,6 +2533,51 @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset) return 0; } +typedef struct Qcow2WriteCo { + BlockDriverState *bs; + int64_t sector_num; + const uint8_t *buf; + int nb_sectors; + int ret; +} Qcow2WriteCo; + +static void qcow2_write_co_entry(void *opaque) +{ + Qcow2WriteCo *co = opaque; + QEMUIOVector qiov; + uint64_t offset = co->sector_num * BDRV_SECTOR_SIZE; + uint64_t bytes = co->nb_sectors * BDRV_SECTOR_SIZE; + + struct iovec iov = (struct iovec) { + .iov_base = (uint8_t*) co->buf, + .iov_len = bytes, + }; + qemu_iovec_init_external(&qiov, &iov, 1); + + co->ret = qcow2_co_pwritev(co->bs, offset, bytes, &qiov, 0); +} + +/* Wrapper for non-coroutine contexts */ +static int qcow2_write(BlockDriverState *bs, int64_t sector_num, + const uint8_t *buf, int nb_sectors) +{ + Coroutine *co; + AioContext *aio_context = bdrv_get_aio_context(bs); + Qcow2WriteCo data = { + .bs = bs, + .sector_num = sector_num, + .buf = buf, + .nb_sectors = nb_sectors, + .ret = -EINPROGRESS, + }; + co = qemu_coroutine_create(qcow2_write_co_entry); + qemu_coroutine_enter(co, &data); + while (data.ret == -EINPROGRESS) { + aio_poll(aio_context, true); + } + return data.ret; +} + /* XXX: put compressed sectors first, then all the cluster aligned tables to avoid losing bytes in alignment */ static int qcow2_write_compressed(BlockDriverState *bs, int64_t sector_num, @@ -2595,7 +2641,7 @@ static int qcow2_write_compressed(BlockDriverState *bs, int64_t sector_num, if (ret != Z_STREAM_END || out_len >= s->cluster_size) { /* could not compress: write normal cluster */ - ret = bdrv_write(bs, sector_num, buf, s->cluster_sectors); + ret = qcow2_write(bs, sector_num, buf, s->cluster_sectors); if (ret < 0) { goto fail; } @@ -2614,7 +2660,7 @@ static int qcow2_write_compressed(BlockDriverState *bs, int64_t sector_num, } BLKDBG_EVENT(bs->file, BLKDBG_WRITE_COMPRESSED); - ret = bdrv_pwrite(bs->file->bs, cluster_offset, out_buf, out_len); + ret = bdrv_pwrite(bs->file, cluster_offset, out_buf, out_len); if (ret < 0) { goto fail; } @@ -2663,7 +2709,7 @@ static int make_completely_empty(BlockDriverState *bs) /* After this call, neither the in-memory nor the on-disk refcount * information accurately describe the actual references */ - ret = bdrv_pwrite_zeroes(bs->file->bs, s->l1_table_offset, + ret = bdrv_pwrite_zeroes(bs->file, s->l1_table_offset, l1_clusters * s->cluster_size, 0); if (ret < 0) { goto fail_broken_refcounts; @@ -2677,7 +2723,7 @@ static int make_completely_empty(BlockDriverState *bs) * overwrite parts of the existing refcount and L1 table, which is not * an issue because the dirty flag is set, complete data loss is in fact * desired and partial data loss is consequently fine as well */ - ret = bdrv_pwrite_zeroes(bs->file->bs, s->cluster_size, + ret = bdrv_pwrite_zeroes(bs->file, s->cluster_size, (2 + l1_clusters) * s->cluster_size, 0); /* This call (even if it failed overall) may have overwritten on-disk * refcount structures; in that case, the in-memory refcount information @@ -2693,10 +2739,10 @@ static int make_completely_empty(BlockDriverState *bs) /* "Create" an empty reftable (one cluster) directly after the image * header and an empty L1 table three clusters after the image header; * the cluster between those two will be used as the first refblock */ - cpu_to_be64w(&l1_ofs_rt_ofs_cls.l1_offset, 3 * s->cluster_size); - cpu_to_be64w(&l1_ofs_rt_ofs_cls.reftable_offset, s->cluster_size); - cpu_to_be32w(&l1_ofs_rt_ofs_cls.reftable_clusters, 1); - ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, l1_table_offset), + l1_ofs_rt_ofs_cls.l1_offset = cpu_to_be64(3 * s->cluster_size); + l1_ofs_rt_ofs_cls.reftable_offset = cpu_to_be64(s->cluster_size); + l1_ofs_rt_ofs_cls.reftable_clusters = cpu_to_be32(1); + ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_table_offset), &l1_ofs_rt_ofs_cls, sizeof(l1_ofs_rt_ofs_cls)); if (ret < 0) { goto fail_broken_refcounts; @@ -2727,7 +2773,7 @@ static int make_completely_empty(BlockDriverState *bs) /* Enter the first refblock into the reftable */ rt_entry = cpu_to_be64(2 * s->cluster_size); - ret = bdrv_pwrite_sync(bs->file->bs, s->cluster_size, + ret = bdrv_pwrite_sync(bs->file, s->cluster_size, &rt_entry, sizeof(rt_entry)); if (ret < 0) { goto fail_broken_refcounts; diff --git a/block/qed-table.c b/block/qed-table.c index c841ad10fe..1a731dff51 100644 --- a/block/qed-table.c +++ b/block/qed-table.c @@ -65,7 +65,7 @@ static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, read_table_cb->iov.iov_len = s->header.cluster_size * s->header.table_size, qemu_iovec_init_external(qiov, &read_table_cb->iov, 1); - bdrv_aio_readv(s->bs->file->bs, offset / BDRV_SECTOR_SIZE, qiov, + bdrv_aio_readv(s->bs->file, offset / BDRV_SECTOR_SIZE, qiov, qiov->size / BDRV_SECTOR_SIZE, qed_read_table_cb, read_table_cb); } @@ -154,7 +154,7 @@ static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table, /* Adjust for offset into table */ offset += start * sizeof(uint64_t); - bdrv_aio_writev(s->bs->file->bs, offset / BDRV_SECTOR_SIZE, + bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE, &write_table_cb->qiov, write_table_cb->qiov.size / BDRV_SECTOR_SIZE, qed_write_table_cb, write_table_cb); diff --git a/block/qed.c b/block/qed.c index 12068061ac..f619d82c6e 100644 --- a/block/qed.c +++ b/block/qed.c @@ -86,7 +86,7 @@ int qed_write_header_sync(BDRVQEDState *s) int ret; qed_header_cpu_to_le(&s->header, &le); - ret = bdrv_pwrite(s->bs->file->bs, 0, &le, sizeof(le)); + ret = bdrv_pwrite(s->bs->file, 0, &le, sizeof(le)); if (ret != sizeof(le)) { return ret; } @@ -123,7 +123,7 @@ static void qed_write_header_read_cb(void *opaque, int ret) /* Update header */ qed_header_cpu_to_le(&s->header, (QEDHeader *)write_header_cb->buf); - bdrv_aio_writev(s->bs->file->bs, 0, &write_header_cb->qiov, + bdrv_aio_writev(s->bs->file, 0, &write_header_cb->qiov, write_header_cb->nsectors, qed_write_header_cb, write_header_cb); } @@ -155,7 +155,7 @@ static void qed_write_header(BDRVQEDState *s, BlockCompletionFunc cb, write_header_cb->iov.iov_len = len; qemu_iovec_init_external(&write_header_cb->qiov, &write_header_cb->iov, 1); - bdrv_aio_readv(s->bs->file->bs, 0, &write_header_cb->qiov, nsectors, + bdrv_aio_readv(s->bs->file, 0, &write_header_cb->qiov, nsectors, qed_write_header_read_cb, write_header_cb); } @@ -218,7 +218,7 @@ static bool qed_is_image_size_valid(uint64_t image_size, uint32_t cluster_size, * * The string is NUL-terminated. */ -static int qed_read_string(BlockDriverState *file, uint64_t offset, size_t n, +static int qed_read_string(BdrvChild *file, uint64_t offset, size_t n, char *buf, size_t buflen) { int ret; @@ -389,7 +389,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags, s->bs = bs; QSIMPLEQ_INIT(&s->allocating_write_reqs); - ret = bdrv_pread(bs->file->bs, 0, &le_header, sizeof(le_header)); + ret = bdrv_pread(bs->file, 0, &le_header, sizeof(le_header)); if (ret < 0) { return ret; } @@ -446,7 +446,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags, return -EINVAL; } - ret = qed_read_string(bs->file->bs, s->header.backing_filename_offset, + ret = qed_read_string(bs->file, s->header.backing_filename_offset, s->header.backing_filename_size, bs->backing_file, sizeof(bs->backing_file)); if (ret < 0) { @@ -800,7 +800,7 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos, qemu_iovec_concat(*backing_qiov, qiov, 0, size); BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO); - bdrv_aio_readv(s->bs->backing->bs, pos / BDRV_SECTOR_SIZE, + bdrv_aio_readv(s->bs->backing, pos / BDRV_SECTOR_SIZE, *backing_qiov, size / BDRV_SECTOR_SIZE, cb, opaque); } @@ -837,7 +837,7 @@ static void qed_copy_from_backing_file_write(void *opaque, int ret) } BLKDBG_EVENT(s->bs->file, BLKDBG_COW_WRITE); - bdrv_aio_writev(s->bs->file->bs, copy_cb->offset / BDRV_SECTOR_SIZE, + bdrv_aio_writev(s->bs->file, copy_cb->offset / BDRV_SECTOR_SIZE, ©_cb->qiov, copy_cb->qiov.size / BDRV_SECTOR_SIZE, qed_copy_from_backing_file_cb, copy_cb); } @@ -1087,7 +1087,7 @@ static void qed_aio_write_main(void *opaque, int ret) } BLKDBG_EVENT(s->bs->file, BLKDBG_WRITE_AIO); - bdrv_aio_writev(s->bs->file->bs, offset / BDRV_SECTOR_SIZE, + bdrv_aio_writev(s->bs->file, offset / BDRV_SECTOR_SIZE, &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE, next_fn, acb); } @@ -1319,7 +1319,7 @@ static void qed_aio_read_data(void *opaque, int ret, } BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); - bdrv_aio_readv(bs->file->bs, offset / BDRV_SECTOR_SIZE, + bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE, &acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE, qed_aio_next_io, acb); return; @@ -1575,7 +1575,7 @@ static int bdrv_qed_change_backing_file(BlockDriverState *bs, } /* Write new header */ - ret = bdrv_pwrite_sync(bs->file->bs, 0, buffer, buffer_len); + ret = bdrv_pwrite_sync(bs->file, 0, buffer, buffer_len); g_free(buffer); if (ret == 0) { memcpy(&s->header, &new_header, sizeof(new_header)); diff --git a/block/quorum.c b/block/quorum.c index 331b726f97..9cf876fb34 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -383,7 +383,7 @@ static bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb, continue; } QLIST_FOREACH(item, &version->items, next) { - bdrv_aio_writev(s->children[item->index]->bs, acb->sector_num, + bdrv_aio_writev(s->children[item->index], acb->sector_num, acb->qiov, acb->nb_sectors, quorum_rewrite_aio_cb, acb); } @@ -660,7 +660,7 @@ static BlockAIOCB *read_quorum_children(QuorumAIOCB *acb) } for (i = 0; i < s->num_children; i++) { - acb->qcrs[i].aiocb = bdrv_aio_readv(s->children[i]->bs, acb->sector_num, + acb->qcrs[i].aiocb = bdrv_aio_readv(s->children[i], acb->sector_num, &acb->qcrs[i].qiov, acb->nb_sectors, quorum_aio_cb, &acb->qcrs[i]); } @@ -678,7 +678,7 @@ static BlockAIOCB *read_fifo_child(QuorumAIOCB *acb) qemu_iovec_clone(&acb->qcrs[acb->child_iter].qiov, acb->qiov, acb->qcrs[acb->child_iter].buf); acb->qcrs[acb->child_iter].aiocb = - bdrv_aio_readv(s->children[acb->child_iter]->bs, acb->sector_num, + bdrv_aio_readv(s->children[acb->child_iter], acb->sector_num, &acb->qcrs[acb->child_iter].qiov, acb->nb_sectors, quorum_aio_cb, &acb->qcrs[acb->child_iter]); @@ -719,7 +719,7 @@ static BlockAIOCB *quorum_aio_writev(BlockDriverState *bs, int i; for (i = 0; i < s->num_children; i++) { - acb->qcrs[i].aiocb = bdrv_aio_writev(s->children[i]->bs, sector_num, + acb->qcrs[i].aiocb = bdrv_aio_writev(s->children[i], sector_num, qiov, nb_sectors, &quorum_aio_cb, &acb->qcrs[i]); } diff --git a/block/raw-posix.c b/block/raw-posix.c index bef7a671a6..c979ac3fd1 100644 --- a/block/raw-posix.c +++ b/block/raw-posix.c @@ -302,22 +302,22 @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp) /* For SCSI generic devices the alignment is not really used. With buffered I/O, we don't have any restrictions. */ if (bdrv_is_sg(bs) || !s->needs_alignment) { - bs->request_alignment = 1; + bs->bl.request_alignment = 1; s->buf_align = 1; return; } - bs->request_alignment = 0; + bs->bl.request_alignment = 0; s->buf_align = 0; /* Let's try to use the logical blocksize for the alignment. */ - if (probe_logical_blocksize(fd, &bs->request_alignment) < 0) { - bs->request_alignment = 0; + if (probe_logical_blocksize(fd, &bs->bl.request_alignment) < 0) { + bs->bl.request_alignment = 0; } #ifdef CONFIG_XFS if (s->is_xfs) { struct dioattr da; if (xfsctl(NULL, fd, XFS_IOC_DIOINFO, &da) >= 0) { - bs->request_alignment = da.d_miniosz; + bs->bl.request_alignment = da.d_miniosz; /* The kernel returns wrong information for d_mem */ /* s->buf_align = da.d_mem; */ } @@ -337,21 +337,21 @@ static void raw_probe_alignment(BlockDriverState *bs, int fd, Error **errp) qemu_vfree(buf); } - if (!bs->request_alignment) { + if (!bs->bl.request_alignment) { size_t align; buf = qemu_memalign(s->buf_align, max_align); for (align = 512; align <= max_align; align <<= 1) { if (raw_is_io_aligned(fd, buf, align)) { - bs->request_alignment = align; + bs->bl.request_alignment = align; break; } } qemu_vfree(buf); } - if (!s->buf_align || !bs->request_alignment) { - error_setg(errp, "Could not find working O_DIRECT alignment. " - "Try cache.direct=off."); + if (!s->buf_align || !bs->bl.request_alignment) { + error_setg(errp, "Could not find working O_DIRECT alignment"); + error_append_hint(errp, "Try cache.direct=off\n"); } } @@ -745,8 +745,8 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) if (!fstat(s->fd, &st)) { if (S_ISBLK(st.st_mode)) { int ret = hdev_get_max_transfer_length(s->fd); - if (ret >= 0) { - bs->bl.max_transfer_length = ret; + if (ret > 0 && ret <= BDRV_REQUEST_MAX_SECTORS) { + bs->bl.max_transfer = pow2floor(ret << BDRV_SECTOR_BITS); } } } diff --git a/block/raw-win32.c b/block/raw-win32.c index fd23891534..62edb1a6cc 100644 --- a/block/raw-win32.c +++ b/block/raw-win32.c @@ -222,7 +222,7 @@ static void raw_attach_aio_context(BlockDriverState *bs, } } -static void raw_probe_alignment(BlockDriverState *bs) +static void raw_probe_alignment(BlockDriverState *bs, Error **errp) { BDRVRawState *s = bs->opaque; DWORD sectorsPerCluster, freeClusters, totalClusters, count; @@ -230,14 +230,14 @@ static void raw_probe_alignment(BlockDriverState *bs) BOOL status; if (s->type == FTYPE_CD) { - bs->request_alignment = 2048; + bs->bl.request_alignment = 2048; return; } if (s->type == FTYPE_HARDDISK) { status = DeviceIoControl(s->hfile, IOCTL_DISK_GET_DRIVE_GEOMETRY_EX, NULL, 0, &dg, sizeof(dg), &count, NULL); if (status != 0) { - bs->request_alignment = dg.Geometry.BytesPerSector; + bs->bl.request_alignment = dg.Geometry.BytesPerSector; return; } /* try GetDiskFreeSpace too */ @@ -247,7 +247,7 @@ static void raw_probe_alignment(BlockDriverState *bs) GetDiskFreeSpace(s->drive_path, §orsPerCluster, &dg.Geometry.BytesPerSector, &freeClusters, &totalClusters); - bs->request_alignment = dg.Geometry.BytesPerSector; + bs->bl.request_alignment = dg.Geometry.BytesPerSector; } } @@ -365,7 +365,6 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, win32_aio_attach_aio_context(s->aio, bdrv_get_aio_context(bs)); } - raw_probe_alignment(bs); ret = 0; fail: qemu_opts_del(opts); @@ -550,6 +549,7 @@ BlockDriver bdrv_file = { .bdrv_needs_filename = true, .bdrv_parse_filename = raw_parse_filename, .bdrv_file_open = raw_open, + .bdrv_refresh_limits = raw_probe_alignment, .bdrv_close = raw_close, .bdrv_create = raw_create, .bdrv_has_zero_init = bdrv_has_zero_init_1, diff --git a/block/raw_bsd.c b/block/raw_bsd.c index 7f637914b7..5f9dd299a6 100644 --- a/block/raw_bsd.c +++ b/block/raw_bsd.c @@ -1,6 +1,6 @@ /* BlockDriver implementation for "raw" * - * Copyright (C) 2010, 2013, Red Hat, Inc. + * Copyright (C) 2010-2016 Red Hat, Inc. * Copyright (C) 2010, Blue Swirl <blauwirbel@gmail.com> * Copyright (C) 2009, Anthony Liguori <aliguori@us.ibm.com> * @@ -54,7 +54,7 @@ static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num, int nb_sectors, QEMUIOVector *qiov) { BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO); - return bdrv_co_readv(bs->file->bs, sector_num, nb_sectors, qiov); + return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov); } static int coroutine_fn @@ -105,7 +105,7 @@ raw_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors, } BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); - ret = bdrv_co_pwritev(bs->file->bs, sector_num * BDRV_SECTOR_SIZE, + ret = bdrv_co_pwritev(bs->file, sector_num * BDRV_SECTOR_SIZE, nb_sectors * BDRV_SECTOR_SIZE, qiov, flags); fail: @@ -131,7 +131,7 @@ static int coroutine_fn raw_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int count, BdrvRequestFlags flags) { - return bdrv_co_pwrite_zeroes(bs->file->bs, offset, count, flags); + return bdrv_co_pwrite_zeroes(bs->file, offset, count, flags); } static int coroutine_fn raw_co_discard(BlockDriverState *bs, @@ -150,11 +150,6 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi) return bdrv_get_info(bs->file->bs, bdi); } -static void raw_refresh_limits(BlockDriverState *bs, Error **errp) -{ - bs->bl = bs->file->bs->bl; -} - static int raw_truncate(BlockDriverState *bs, int64_t offset) { return bdrv_truncate(bs->file->bs, offset); @@ -252,7 +247,6 @@ BlockDriver bdrv_raw = { .bdrv_getlength = &raw_getlength, .has_variable_length = true, .bdrv_get_info = &raw_get_info, - .bdrv_refresh_limits = &raw_refresh_limits, .bdrv_probe_blocksizes = &raw_probe_blocksizes, .bdrv_probe_geometry = &raw_probe_geometry, .bdrv_media_changed = &raw_media_changed, diff --git a/block/vdi.c b/block/vdi.c index 7d9ab9cc17..8a1cf97928 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -403,7 +403,7 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, logout("\n"); - ret = bdrv_read(bs->file->bs, 0, (uint8_t *)&header, 1); + ret = bdrv_read(bs->file, 0, (uint8_t *)&header, 1); if (ret < 0) { goto fail; } @@ -500,7 +500,7 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_read(bs->file->bs, s->bmap_sector, (uint8_t *)s->bmap, + ret = bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size); if (ret < 0) { goto fail_free_bmap; @@ -597,7 +597,7 @@ vdi_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_reset(&local_qiov); qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes); - ret = bdrv_co_preadv(bs->file->bs, data_offset, n_bytes, + ret = bdrv_co_preadv(bs->file, data_offset, n_bytes, &local_qiov, 0); } logout("%u bytes read\n", n_bytes); @@ -670,7 +670,7 @@ vdi_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, * acquire the lock and thus the padded cluster is written before * the other coroutines can write to the affected area. */ qemu_co_mutex_lock(&s->write_lock); - ret = bdrv_pwrite(bs->file->bs, data_offset, block, s->block_size); + ret = bdrv_pwrite(bs->file, data_offset, block, s->block_size); qemu_co_mutex_unlock(&s->write_lock); } else { uint64_t data_offset = s->header.offset_data + @@ -690,7 +690,7 @@ vdi_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_reset(&local_qiov); qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes); - ret = bdrv_co_pwritev(bs->file->bs, data_offset, n_bytes, + ret = bdrv_co_pwritev(bs->file, data_offset, n_bytes, &local_qiov, 0); } @@ -719,7 +719,7 @@ vdi_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, assert(VDI_IS_ALLOCATED(bmap_first)); *header = s->header; vdi_header_to_le(header); - ret = bdrv_write(bs->file->bs, 0, block, 1); + ret = bdrv_write(bs->file, 0, block, 1); g_free(block); block = NULL; @@ -737,7 +737,7 @@ vdi_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, base = ((uint8_t *)&s->bmap[0]) + bmap_first * SECTOR_SIZE; logout("will write %u block map sectors starting from entry %u\n", n_sectors, bmap_first); - ret = bdrv_write(bs->file->bs, offset, base, n_sectors); + ret = bdrv_write(bs->file, offset, base, n_sectors); } return ret; diff --git a/block/vhdx-log.c b/block/vhdx-log.c index 8ab7d22d9a..02eb104310 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -84,7 +84,7 @@ static int vhdx_log_peek_hdr(BlockDriverState *bs, VHDXLogEntries *log, offset = log->offset + read; - ret = bdrv_pread(bs->file->bs, offset, hdr, sizeof(VHDXLogEntryHeader)); + ret = bdrv_pread(bs->file, offset, hdr, sizeof(VHDXLogEntryHeader)); if (ret < 0) { goto exit; } @@ -144,7 +144,7 @@ static int vhdx_log_read_sectors(BlockDriverState *bs, VHDXLogEntries *log, } offset = log->offset + read; - ret = bdrv_pread(bs->file->bs, offset, buffer, VHDX_LOG_SECTOR_SIZE); + ret = bdrv_pread(bs->file, offset, buffer, VHDX_LOG_SECTOR_SIZE); if (ret < 0) { goto exit; } @@ -194,7 +194,7 @@ static int vhdx_log_write_sectors(BlockDriverState *bs, VHDXLogEntries *log, /* full */ break; } - ret = bdrv_pwrite(bs->file->bs, offset, buffer_tmp, + ret = bdrv_pwrite(bs->file, offset, buffer_tmp, VHDX_LOG_SECTOR_SIZE); if (ret < 0) { goto exit; @@ -466,7 +466,7 @@ static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc, /* count is only > 1 if we are writing zeroes */ for (i = 0; i < count; i++) { - ret = bdrv_pwrite_sync(bs->file->bs, file_offset, buffer, + ret = bdrv_pwrite_sync(bs->file, file_offset, buffer, VHDX_LOG_SECTOR_SIZE); if (ret < 0) { goto exit; @@ -945,7 +945,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s, if (i == 0 && leading_length) { /* partial sector at the front of the buffer */ - ret = bdrv_pread(bs->file->bs, file_offset, merged_sector, + ret = bdrv_pread(bs->file, file_offset, merged_sector, VHDX_LOG_SECTOR_SIZE); if (ret < 0) { goto exit; @@ -955,7 +955,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s, sector_write = merged_sector; } else if (i == sectors - 1 && trailing_length) { /* partial sector at the end of the buffer */ - ret = bdrv_pread(bs->file->bs, + ret = bdrv_pread(bs->file, file_offset, merged_sector + trailing_length, VHDX_LOG_SECTOR_SIZE - trailing_length); diff --git a/block/vhdx.c b/block/vhdx.c index f5605a2ff4..75ef2b1c2d 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -298,9 +298,10 @@ static int vhdx_probe(const uint8_t *buf, int buf_size, const char *filename) * and then update the header checksum. Header is converted to proper * endianness before being written to the specified file offset */ -static int vhdx_write_header(BlockDriverState *bs_file, VHDXHeader *hdr, +static int vhdx_write_header(BdrvChild *file, VHDXHeader *hdr, uint64_t offset, bool read) { + BlockDriverState *bs_file = file->bs; uint8_t *buffer = NULL; int ret; VHDXHeader *header_le; @@ -315,7 +316,7 @@ static int vhdx_write_header(BlockDriverState *bs_file, VHDXHeader *hdr, buffer = qemu_blockalign(bs_file, VHDX_HEADER_SIZE); if (read) { /* if true, we can't assume the extra reserved bytes are 0 */ - ret = bdrv_pread(bs_file, offset, buffer, VHDX_HEADER_SIZE); + ret = bdrv_pread(file, offset, buffer, VHDX_HEADER_SIZE); if (ret < 0) { goto exit; } @@ -329,7 +330,7 @@ static int vhdx_write_header(BlockDriverState *bs_file, VHDXHeader *hdr, vhdx_header_le_export(hdr, header_le); vhdx_update_checksum(buffer, VHDX_HEADER_SIZE, offsetof(VHDXHeader, checksum)); - ret = bdrv_pwrite_sync(bs_file, offset, header_le, sizeof(VHDXHeader)); + ret = bdrv_pwrite_sync(file, offset, header_le, sizeof(VHDXHeader)); exit: qemu_vfree(buffer); @@ -378,7 +379,7 @@ static int vhdx_update_header(BlockDriverState *bs, BDRVVHDXState *s, inactive_header->log_guid = *log_guid; } - ret = vhdx_write_header(bs->file->bs, inactive_header, header_offset, true); + ret = vhdx_write_header(bs->file, inactive_header, header_offset, true); if (ret < 0) { goto exit; } @@ -430,7 +431,7 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s, /* We have to read the whole VHDX_HEADER_SIZE instead of * sizeof(VHDXHeader), because the checksum is over the whole * region */ - ret = bdrv_pread(bs->file->bs, VHDX_HEADER1_OFFSET, buffer, + ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer, VHDX_HEADER_SIZE); if (ret < 0) { goto fail; @@ -447,7 +448,7 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s, } } - ret = bdrv_pread(bs->file->bs, VHDX_HEADER2_OFFSET, buffer, + ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE); if (ret < 0) { goto fail; @@ -521,7 +522,7 @@ static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s) * whole block */ buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE); - ret = bdrv_pread(bs->file->bs, VHDX_REGION_TABLE_OFFSET, buffer, + ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer, VHDX_HEADER_BLOCK_SIZE); if (ret < 0) { goto fail; @@ -634,7 +635,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE); - ret = bdrv_pread(bs->file->bs, s->metadata_rt.file_offset, buffer, + ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer, VHDX_METADATA_TABLE_MAX_SIZE); if (ret < 0) { goto exit; @@ -737,7 +738,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) goto exit; } - ret = bdrv_pread(bs->file->bs, + ret = bdrv_pread(bs->file, s->metadata_entries.file_parameters_entry.offset + s->metadata_rt.file_offset, &s->params, @@ -772,7 +773,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) /* determine virtual disk size, logical sector size, * and phys sector size */ - ret = bdrv_pread(bs->file->bs, + ret = bdrv_pread(bs->file, s->metadata_entries.virtual_disk_size_entry.offset + s->metadata_rt.file_offset, &s->virtual_disk_size, @@ -780,7 +781,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) if (ret < 0) { goto exit; } - ret = bdrv_pread(bs->file->bs, + ret = bdrv_pread(bs->file, s->metadata_entries.logical_sector_size_entry.offset + s->metadata_rt.file_offset, &s->logical_sector_size, @@ -788,7 +789,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s) if (ret < 0) { goto exit; } - ret = bdrv_pread(bs->file->bs, + ret = bdrv_pread(bs->file, s->metadata_entries.phys_sector_size_entry.offset + s->metadata_rt.file_offset, &s->physical_sector_size, @@ -905,7 +906,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, QLIST_INIT(&s->regions); /* validate the file signature */ - ret = bdrv_pread(bs->file->bs, 0, &signature, sizeof(uint64_t)); + ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t)); if (ret < 0) { goto fail; } @@ -964,7 +965,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file->bs, s->bat_offset, s->bat, s->bat_rt.length); + ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length); if (ret < 0) { goto fail; } @@ -1117,7 +1118,7 @@ static coroutine_fn int vhdx_co_readv(BlockDriverState *bs, int64_t sector_num, break; case PAYLOAD_BLOCK_FULLY_PRESENT: qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_readv(bs->file->bs, + ret = bdrv_co_readv(bs->file, sinfo.file_offset >> BDRV_SECTOR_BITS, sinfo.sectors_avail, &hd_qiov); qemu_co_mutex_lock(&s->lock); @@ -1326,7 +1327,7 @@ static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num, } /* block exists, so we can just overwrite it */ qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_writev(bs->file->bs, + ret = bdrv_co_writev(bs->file, sinfo.file_offset >> BDRV_SECTOR_BITS, sectors_to_write, &hd_qiov); qemu_co_mutex_lock(&s->lock); @@ -1387,9 +1388,11 @@ exit: * There are 2 headers, and the highest sequence number will represent * the active header */ -static int vhdx_create_new_headers(BlockDriverState *bs, uint64_t image_size, +static int vhdx_create_new_headers(BlockBackend *blk, uint64_t image_size, uint32_t log_size) { + BlockDriverState *bs = blk_bs(blk); + BdrvChild *child; int ret = 0; VHDXHeader *hdr = NULL; @@ -1404,12 +1407,18 @@ static int vhdx_create_new_headers(BlockDriverState *bs, uint64_t image_size, vhdx_guid_generate(&hdr->file_write_guid); vhdx_guid_generate(&hdr->data_write_guid); - ret = vhdx_write_header(bs, hdr, VHDX_HEADER1_OFFSET, false); + /* XXX Ugly way to get blk->root, but that's a feature, not a bug. This + * hack makes it obvious that vhdx_write_header() bypasses the BlockBackend + * here, which it really shouldn't be doing. */ + child = QLIST_FIRST(&bs->parents); + assert(!QLIST_NEXT(child, next_parent)); + + ret = vhdx_write_header(child, hdr, VHDX_HEADER1_OFFSET, false); if (ret < 0) { goto exit; } hdr->sequence_number++; - ret = vhdx_write_header(bs, hdr, VHDX_HEADER2_OFFSET, false); + ret = vhdx_write_header(child, hdr, VHDX_HEADER2_OFFSET, false); if (ret < 0) { goto exit; } @@ -1442,7 +1451,7 @@ exit: * The first 64KB of the Metadata section is reserved for the metadata * header and entries; beyond that, the metadata items themselves reside. */ -static int vhdx_create_new_metadata(BlockDriverState *bs, +static int vhdx_create_new_metadata(BlockBackend *blk, uint64_t image_size, uint32_t block_size, uint32_t sector_size, @@ -1538,13 +1547,13 @@ static int vhdx_create_new_metadata(BlockDriverState *bs, VHDX_META_FLAGS_IS_VIRTUAL_DISK; vhdx_metadata_entry_le_export(&md_table_entry[4]); - ret = bdrv_pwrite(bs, metadata_offset, buffer, VHDX_HEADER_BLOCK_SIZE); + ret = blk_pwrite(blk, metadata_offset, buffer, VHDX_HEADER_BLOCK_SIZE, 0); if (ret < 0) { goto exit; } - ret = bdrv_pwrite(bs, metadata_offset + (64 * KiB), entry_buffer, - VHDX_METADATA_ENTRY_BUFFER_SIZE); + ret = blk_pwrite(blk, metadata_offset + (64 * KiB), entry_buffer, + VHDX_METADATA_ENTRY_BUFFER_SIZE, 0); if (ret < 0) { goto exit; } @@ -1564,7 +1573,7 @@ exit: * Fixed images: default state of the BAT is fully populated, with * file offsets and state PAYLOAD_BLOCK_FULLY_PRESENT. */ -static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s, +static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s, uint64_t image_size, VHDXImageType type, bool use_zero_blocks, uint64_t file_offset, uint32_t length) @@ -1588,12 +1597,12 @@ static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s, if (type == VHDX_TYPE_DYNAMIC) { /* All zeroes, so we can just extend the file - the end of the BAT * is the furthest thing we have written yet */ - ret = bdrv_truncate(bs, data_file_offset); + ret = blk_truncate(blk, data_file_offset); if (ret < 0) { goto exit; } } else if (type == VHDX_TYPE_FIXED) { - ret = bdrv_truncate(bs, data_file_offset + image_size); + ret = blk_truncate(blk, data_file_offset + image_size); if (ret < 0) { goto exit; } @@ -1604,7 +1613,7 @@ static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s, if (type == VHDX_TYPE_FIXED || use_zero_blocks || - bdrv_has_zero_init(bs) == 0) { + bdrv_has_zero_init(blk_bs(blk)) == 0) { /* for a fixed file, the default BAT entry is not zero */ s->bat = g_try_malloc0(length); if (length && s->bat == NULL) { @@ -1620,12 +1629,12 @@ static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s, sinfo.file_offset = data_file_offset + (sector_num << s->logical_sector_size_bits); sinfo.file_offset = ROUND_UP(sinfo.file_offset, MiB); - vhdx_update_bat_table_entry(bs, s, &sinfo, &unused, &unused, + vhdx_update_bat_table_entry(blk_bs(blk), s, &sinfo, &unused, &unused, block_state); cpu_to_le64s(&s->bat[sinfo.bat_idx]); sector_num += s->sectors_per_block; } - ret = bdrv_pwrite(bs, file_offset, s->bat, length); + ret = blk_pwrite(blk, file_offset, s->bat, length, 0); if (ret < 0) { goto exit; } @@ -1645,7 +1654,7 @@ exit: * to create the BAT itself, we will also cause the BAT to be * created. */ -static int vhdx_create_new_region_table(BlockDriverState *bs, +static int vhdx_create_new_region_table(BlockBackend *blk, uint64_t image_size, uint32_t block_size, uint32_t sector_size, @@ -1720,21 +1729,21 @@ static int vhdx_create_new_region_table(BlockDriverState *bs, /* The region table gives us the data we need to create the BAT, * so do that now */ - ret = vhdx_create_bat(bs, s, image_size, type, use_zero_blocks, + ret = vhdx_create_bat(blk, s, image_size, type, use_zero_blocks, bat_file_offset, bat_length); if (ret < 0) { goto exit; } /* Now write out the region headers to disk */ - ret = bdrv_pwrite(bs, VHDX_REGION_TABLE_OFFSET, buffer, - VHDX_HEADER_BLOCK_SIZE); + ret = blk_pwrite(blk, VHDX_REGION_TABLE_OFFSET, buffer, + VHDX_HEADER_BLOCK_SIZE, 0); if (ret < 0) { goto exit; } - ret = bdrv_pwrite(bs, VHDX_REGION_TABLE2_OFFSET, buffer, - VHDX_HEADER_BLOCK_SIZE); + ret = blk_pwrite(blk, VHDX_REGION_TABLE2_OFFSET, buffer, + VHDX_HEADER_BLOCK_SIZE, 0); if (ret < 0) { goto exit; } @@ -1871,13 +1880,13 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp) /* Creates (B),(C) */ - ret = vhdx_create_new_headers(blk_bs(blk), image_size, log_size); + ret = vhdx_create_new_headers(blk, image_size, log_size); if (ret < 0) { goto delete_and_exit; } /* Creates (D),(E),(G) explicitly. (F) created as by-product */ - ret = vhdx_create_new_region_table(blk_bs(blk), image_size, block_size, 512, + ret = vhdx_create_new_region_table(blk, image_size, block_size, 512, log_size, use_zero_blocks, image_type, &metadata_offset); if (ret < 0) { @@ -1885,7 +1894,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp) } /* Creates (H) */ - ret = vhdx_create_new_metadata(blk_bs(blk), image_size, block_size, 512, + ret = vhdx_create_new_metadata(blk, image_size, block_size, 512, metadata_offset, image_type); if (ret < 0) { goto delete_and_exit; diff --git a/block/vmdk.c b/block/vmdk.c index 2901692700..d73f4314ba 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -252,7 +252,7 @@ static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent) int ret; desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); if (ret < 0) { g_free(desc); return 0; @@ -286,7 +286,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) desc = g_malloc0(DESC_SIZE); tmp_desc = g_malloc0(DESC_SIZE); - ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); if (ret < 0) { goto out; } @@ -306,7 +306,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid) pstrcat(desc, DESC_SIZE, tmp_desc); } - ret = bdrv_pwrite_sync(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE); out: g_free(desc); @@ -350,7 +350,7 @@ static int vmdk_parent_open(BlockDriverState *bs) int ret; desc = g_malloc0(DESC_SIZE + 1); - ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE); + ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE); if (ret < 0) { goto out; } @@ -454,7 +454,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, return -ENOMEM; } - ret = bdrv_pread(extent->file->bs, + ret = bdrv_pread(extent->file, extent->l1_table_offset, extent->l1_table, l1_size); @@ -474,7 +474,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, ret = -ENOMEM; goto fail_l1; } - ret = bdrv_pread(extent->file->bs, + ret = bdrv_pread(extent->file, extent->l1_backup_table_offset, extent->l1_backup_table, l1_size); @@ -508,7 +508,7 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs, VMDK3Header header; VmdkExtent *extent; - ret = bdrv_pread(file->bs, sizeof(magic), &header, sizeof(header)); + ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read header from file '%s'", @@ -538,14 +538,13 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs, static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf, QDict *options, Error **errp); -static char *vmdk_read_desc(BlockDriverState *file, uint64_t desc_offset, - Error **errp) +static char *vmdk_read_desc(BdrvChild *file, uint64_t desc_offset, Error **errp) { int64_t size; char *buf; int ret; - size = bdrv_getlength(file); + size = bdrv_getlength(file->bs); if (size < 0) { error_setg_errno(errp, -size, "Could not access file"); return NULL; @@ -586,7 +585,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs, int64_t l1_backup_offset = 0; bool compressed; - ret = bdrv_pread(file->bs, sizeof(magic), &header, sizeof(header)); + ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header)); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read header from file '%s'", @@ -596,7 +595,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs, if (header.capacity == 0) { uint64_t desc_offset = le64_to_cpu(header.desc_offset); if (desc_offset) { - char *buf = vmdk_read_desc(file->bs, desc_offset << 9, errp); + char *buf = vmdk_read_desc(file, desc_offset << 9, errp); if (!buf) { return -EINVAL; } @@ -636,7 +635,7 @@ static int vmdk_open_vmdk4(BlockDriverState *bs, } QEMU_PACKED eos_marker; } QEMU_PACKED footer; - ret = bdrv_pread(file->bs, + ret = bdrv_pread(file, bs->file->bs->total_sectors * 512 - 1536, &footer, sizeof(footer)); if (ret < 0) { @@ -874,7 +873,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, extent->flat_start_offset = flat_offset << 9; } else if (!strcmp(type, "SPARSE") || !strcmp(type, "VMFSSPARSE")) { /* SPARSE extent and VMFSSPARSE extent are both "COWD" sparse file*/ - char *buf = vmdk_read_desc(extent_file->bs, 0, errp); + char *buf = vmdk_read_desc(extent_file, 0, errp); if (!buf) { ret = -EINVAL; } else { @@ -943,7 +942,7 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags, BDRVVmdkState *s = bs->opaque; uint32_t magic; - buf = vmdk_read_desc(bs->file->bs, 0, errp); + buf = vmdk_read_desc(bs->file, 0, errp); if (!buf) { return -EINVAL; } @@ -1046,14 +1045,14 @@ static int get_whole_cluster(BlockDriverState *bs, /* Read backing data before skip range */ if (skip_start_bytes > 0) { if (bs->backing) { - ret = bdrv_pread(bs->backing->bs, offset, whole_grain, + ret = bdrv_pread(bs->backing, offset, whole_grain, skip_start_bytes); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } - ret = bdrv_pwrite(extent->file->bs, cluster_offset, whole_grain, + ret = bdrv_pwrite(extent->file, cluster_offset, whole_grain, skip_start_bytes); if (ret < 0) { ret = VMDK_ERROR; @@ -1063,7 +1062,7 @@ static int get_whole_cluster(BlockDriverState *bs, /* Read backing data after skip range */ if (skip_end_bytes < cluster_bytes) { if (bs->backing) { - ret = bdrv_pread(bs->backing->bs, offset + skip_end_bytes, + ret = bdrv_pread(bs->backing, offset + skip_end_bytes, whole_grain + skip_end_bytes, cluster_bytes - skip_end_bytes); if (ret < 0) { @@ -1071,7 +1070,7 @@ static int get_whole_cluster(BlockDriverState *bs, goto exit; } } - ret = bdrv_pwrite(extent->file->bs, cluster_offset + skip_end_bytes, + ret = bdrv_pwrite(extent->file, cluster_offset + skip_end_bytes, whole_grain + skip_end_bytes, cluster_bytes - skip_end_bytes); if (ret < 0) { @@ -1091,8 +1090,7 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, { offset = cpu_to_le32(offset); /* update L2 table */ - if (bdrv_pwrite_sync( - extent->file->bs, + if (bdrv_pwrite_sync(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), &offset, sizeof(offset)) < 0) { @@ -1101,8 +1099,7 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, /* update backup L2 table */ if (extent->l1_backup_table_offset != 0) { m_data->l2_offset = extent->l1_backup_table[m_data->l1_index]; - if (bdrv_pwrite_sync( - extent->file->bs, + if (bdrv_pwrite_sync(extent->file, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(offset)), &offset, sizeof(offset)) < 0) { @@ -1191,8 +1188,7 @@ static int get_cluster_offset(BlockDriverState *bs, } } l2_table = extent->l2_cache + (min_index * extent->l2_size); - if (bdrv_pread( - extent->file->bs, + if (bdrv_pread(extent->file, (int64_t)l2_offset * 512, l2_table, extent->l2_size * sizeof(uint32_t) @@ -1373,7 +1369,7 @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, } write_offset = cluster_offset + offset_in_cluster, - ret = bdrv_co_pwritev(extent->file->bs, write_offset, n_bytes, + ret = bdrv_co_pwritev(extent->file, write_offset, n_bytes, &local_qiov, 0); write_end_sector = DIV_ROUND_UP(write_offset + n_bytes, BDRV_SECTOR_SIZE); @@ -1411,7 +1407,7 @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, if (!extent->compressed) { - ret = bdrv_co_preadv(extent->file->bs, + ret = bdrv_co_preadv(extent->file, cluster_offset + offset_in_cluster, bytes, qiov, 0); if (ret < 0) { @@ -1424,7 +1420,7 @@ static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, buf_bytes = cluster_bytes * 2; cluster_buf = g_malloc(buf_bytes); uncomp_buf = g_malloc(cluster_bytes); - ret = bdrv_pread(extent->file->bs, + ret = bdrv_pread(extent->file, cluster_offset, cluster_buf, buf_bytes); if (ret < 0) { @@ -1501,7 +1497,7 @@ vmdk_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_reset(&local_qiov); qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes); - ret = bdrv_co_preadv(bs->backing->bs, offset, n_bytes, + ret = bdrv_co_preadv(bs->backing, offset, n_bytes, &local_qiov, 0); if (ret < 0) { goto fail; diff --git a/block/vpc.c b/block/vpc.c index 076a7ce399..43707ed22c 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -237,7 +237,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - ret = bdrv_pread(bs->file->bs, 0, s->footer_buf, HEADER_SIZE); + ret = bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE); if (ret < 0) { error_setg(errp, "Unable to read VHD header"); goto fail; @@ -257,7 +257,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, } /* If a fixed disk, the footer is found only at the end of the file */ - ret = bdrv_pread(bs->file->bs, offset-HEADER_SIZE, s->footer_buf, + ret = bdrv_pread(bs->file, offset-HEADER_SIZE, s->footer_buf, HEADER_SIZE); if (ret < 0) { goto fail; @@ -328,7 +328,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, } if (disk_type == VHD_DYNAMIC) { - ret = bdrv_pread(bs->file->bs, be64_to_cpu(footer->data_offset), buf, + ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf, HEADER_SIZE); if (ret < 0) { error_setg(errp, "Error reading dynamic VHD header"); @@ -385,7 +385,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, s->bat_offset = be64_to_cpu(dyndisk_header->table_offset); - ret = bdrv_pread(bs->file->bs, s->bat_offset, s->pagetable, + ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable, pagetable_size); if (ret < 0) { error_setg(errp, "Error reading pagetable"); @@ -481,7 +481,7 @@ static inline int64_t get_image_offset(BlockDriverState *bs, uint64_t offset, s->last_bitmap_offset = bitmap_offset; memset(bitmap, 0xff, s->bitmap_size); - bdrv_pwrite_sync(bs->file->bs, bitmap_offset, bitmap, s->bitmap_size); + bdrv_pwrite_sync(bs->file, bitmap_offset, bitmap, s->bitmap_size); } return block_offset; @@ -505,7 +505,7 @@ static int rewrite_footer(BlockDriverState* bs) BDRVVPCState *s = bs->opaque; int64_t offset = s->free_data_block_offset; - ret = bdrv_pwrite_sync(bs->file->bs, offset, s->footer_buf, HEADER_SIZE); + ret = bdrv_pwrite_sync(bs->file, offset, s->footer_buf, HEADER_SIZE); if (ret < 0) return ret; @@ -539,7 +539,7 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t offset) /* Initialize the block's bitmap */ memset(bitmap, 0xff, s->bitmap_size); - ret = bdrv_pwrite_sync(bs->file->bs, s->free_data_block_offset, bitmap, + ret = bdrv_pwrite_sync(bs->file, s->free_data_block_offset, bitmap, s->bitmap_size); if (ret < 0) { return ret; @@ -554,7 +554,7 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t offset) /* Write BAT entry to disk */ bat_offset = s->bat_offset + (4 * index); bat_value = cpu_to_be32(s->pagetable[index]); - ret = bdrv_pwrite_sync(bs->file->bs, bat_offset, &bat_value, 4); + ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4); if (ret < 0) goto fail; @@ -591,7 +591,7 @@ vpc_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector local_qiov; if (be32_to_cpu(footer->type) == VHD_FIXED) { - return bdrv_co_preadv(bs->file->bs, offset, bytes, qiov, 0); + return bdrv_co_preadv(bs->file, offset, bytes, qiov, 0); } qemu_co_mutex_lock(&s->lock); @@ -607,7 +607,7 @@ vpc_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_reset(&local_qiov); qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes); - ret = bdrv_co_preadv(bs->file->bs, image_offset, n_bytes, + ret = bdrv_co_preadv(bs->file, image_offset, n_bytes, &local_qiov, 0); if (ret < 0) { goto fail; @@ -640,7 +640,7 @@ vpc_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector local_qiov; if (be32_to_cpu(footer->type) == VHD_FIXED) { - return bdrv_co_pwritev(bs->file->bs, offset, bytes, qiov, 0); + return bdrv_co_pwritev(bs->file, offset, bytes, qiov, 0); } qemu_co_mutex_lock(&s->lock); @@ -661,7 +661,7 @@ vpc_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_reset(&local_qiov); qemu_iovec_concat(&local_qiov, qiov, bytes_done, n_bytes); - ret = bdrv_co_pwritev(bs->file->bs, image_offset, n_bytes, + ret = bdrv_co_pwritev(bs->file, image_offset, n_bytes, &local_qiov, 0); if (ret < 0) { goto fail; diff --git a/block/vvfat.c b/block/vvfat.c index 5569450616..c3f24c6eb0 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -341,9 +341,8 @@ typedef struct BDRVVVFATState { unsigned int current_cluster; /* write support */ - BlockDriverState* write_target; char* qcow_filename; - BlockDriverState* qcow; + BdrvChild* qcow; void* fat2; char* used_clusters; array_t commits; @@ -981,7 +980,7 @@ static int init_directories(BDRVVVFATState* s, static BDRVVVFATState *vvv = NULL; #endif -static int enable_write_target(BDRVVVFATState *s, Error **errp); +static int enable_write_target(BlockDriverState *bs, Error **errp); static int is_consistent(BDRVVVFATState *s); static QemuOptsList runtime_opts = { @@ -1158,8 +1157,8 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags, s->current_cluster=0xffffffff; /* read only is the default for safety */ - bs->read_only = 1; - s->qcow = s->write_target = NULL; + bs->read_only = true; + s->qcow = NULL; s->qcow_filename = NULL; s->fat2 = NULL; s->downcase_short_names = 1; @@ -1170,14 +1169,13 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags, s->sector_count = cyls * heads * secs - (s->first_sectors_number - 1); if (qemu_opt_get_bool(opts, "rw", false)) { - ret = enable_write_target(s, errp); + ret = enable_write_target(bs, errp); if (ret < 0) { goto fail; } - bs->read_only = 0; + bs->read_only = false; } - bs->request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O supported */ bs->total_sectors = cyls * heads * secs; if (init_directories(s, dirname, heads, secs, errp)) { @@ -1209,6 +1207,11 @@ fail: return ret; } +static void vvfat_refresh_limits(BlockDriverState *bs, Error **errp) +{ + bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */ +} + static inline void vvfat_close_current_file(BDRVVVFATState *s) { if(s->current_mapping) { @@ -1387,9 +1390,10 @@ static int vvfat_read(BlockDriverState *bs, int64_t sector_num, return -1; if (s->qcow) { int n; - if (bdrv_is_allocated(s->qcow, sector_num, nb_sectors-i, &n)) { -DLOG(fprintf(stderr, "sectors %d+%d allocated\n", (int)sector_num, n)); - if (bdrv_read(s->qcow, sector_num, buf + i*0x200, n)) { + if (bdrv_is_allocated(s->qcow->bs, sector_num, nb_sectors-i, &n)) { + DLOG(fprintf(stderr, "sectors %d+%d allocated\n", + (int)sector_num, n)); + if (bdrv_read(s->qcow, sector_num, buf + i * 0x200, n)) { return -1; } i += n - 1; @@ -1665,12 +1669,15 @@ static inline int cluster_was_modified(BDRVVVFATState* s, uint32_t cluster_num) int was_modified = 0; int i, dummy; - if (s->qcow == NULL) - return 0; + if (s->qcow == NULL) { + return 0; + } - for (i = 0; !was_modified && i < s->sectors_per_cluster; i++) - was_modified = bdrv_is_allocated(s->qcow, - cluster2sector(s, cluster_num) + i, 1, &dummy); + for (i = 0; !was_modified && i < s->sectors_per_cluster; i++) { + was_modified = bdrv_is_allocated(s->qcow->bs, + cluster2sector(s, cluster_num) + i, + 1, &dummy); + } return was_modified; } @@ -1819,11 +1826,16 @@ static uint32_t get_cluster_count_for_direntry(BDRVVVFATState* s, vvfat_close_current_file(s); for (i = 0; i < s->sectors_per_cluster; i++) { - if (!bdrv_is_allocated(s->qcow, offset + i, 1, &dummy)) { - if (vvfat_read(s->bs, offset, s->cluster_buffer, 1)) { + int res; + + res = bdrv_is_allocated(s->qcow->bs, offset + i, 1, &dummy); + if (!res) { + res = vvfat_read(s->bs, offset, s->cluster_buffer, 1); + if (res) { return -1; } - if (bdrv_write(s->qcow, offset, s->cluster_buffer, 1)) { + res = bdrv_write(s->qcow, offset, s->cluster_buffer, 1); + if (res) { return -2; } } @@ -2779,8 +2791,8 @@ static int do_commit(BDRVVVFATState* s) return ret; } - if (s->qcow->drv->bdrv_make_empty) { - s->qcow->drv->bdrv_make_empty(s->qcow); + if (s->qcow->bs->drv->bdrv_make_empty) { + s->qcow->bs->drv->bdrv_make_empty(s->qcow->bs); } memset(s->used_clusters, 0, sector2cluster(s, s->sector_count)); @@ -2946,7 +2958,7 @@ write_target_commit(BlockDriverState *bs, uint64_t offset, uint64_t bytes, static void write_target_close(BlockDriverState *bs) { BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque); - bdrv_unref(s->qcow); + bdrv_unref_child(s->bs, s->qcow); g_free(s->qcow_filename); } @@ -2956,8 +2968,19 @@ static BlockDriver vvfat_write_target = { .bdrv_close = write_target_close, }; -static int enable_write_target(BDRVVVFATState *s, Error **errp) +static void vvfat_qcow_options(int *child_flags, QDict *child_options, + int parent_flags, QDict *parent_options) { + *child_flags = BDRV_O_RDWR | BDRV_O_NO_FLUSH; +} + +static const BdrvChildRole child_vvfat_qcow = { + .inherit_options = vvfat_qcow_options, +}; + +static int enable_write_target(BlockDriverState *bs, Error **errp) +{ + BDRVVVFATState *s = bs->opaque; BlockDriver *bdrv_qcow = NULL; BlockDriverState *backing; QemuOpts *opts = NULL; @@ -2996,8 +3019,8 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp) options = qdict_new(); qdict_put(options, "driver", qstring_from_str("qcow")); - s->qcow = bdrv_open(s->qcow_filename, NULL, options, - BDRV_O_RDWR | BDRV_O_NO_FLUSH, errp); + s->qcow = bdrv_open_child(s->qcow_filename, options, "write-target", bs, + &child_vvfat_qcow, false, errp); if (!s->qcow) { ret = -EINVAL; goto err; @@ -3046,6 +3069,7 @@ static BlockDriver bdrv_vvfat = { .bdrv_parse_filename = vvfat_parse_filename, .bdrv_file_open = vvfat_open, + .bdrv_refresh_limits = vvfat_refresh_limits, .bdrv_close = vvfat_close, .bdrv_co_preadv = vvfat_co_preadv, diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index fb43bbaa46..ae86e944ea 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -384,7 +384,7 @@ static int multireq_compare(const void *a, const void *b) void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb) { int i = 0, start = 0, num_reqs = 0, niov = 0, nb_sectors = 0; - int max_xfer_len = 0; + uint32_t max_transfer; int64_t sector_num = 0; if (mrb->num_reqs == 1) { @@ -393,8 +393,7 @@ void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb) return; } - max_xfer_len = blk_get_max_transfer_length(mrb->reqs[0]->dev->blk); - max_xfer_len = MIN_NON_ZERO(max_xfer_len, BDRV_REQUEST_MAX_SECTORS); + max_transfer = blk_get_max_transfer(mrb->reqs[0]->dev->blk); qsort(mrb->reqs, mrb->num_reqs, sizeof(*mrb->reqs), &multireq_compare); @@ -410,8 +409,9 @@ void virtio_blk_submit_multireq(BlockBackend *blk, MultiReqBuffer *mrb) */ if (sector_num + nb_sectors != req->sector_num || niov > blk_get_max_iov(blk) - req->qiov.niov || - req->qiov.size / BDRV_SECTOR_SIZE > max_xfer_len || - nb_sectors > max_xfer_len - req->qiov.size / BDRV_SECTOR_SIZE) { + req->qiov.size > max_transfer || + nb_sectors > (max_transfer - + req->qiov.size) / BDRV_SECTOR_SIZE) { submit_requests(blk, mrb, start, num_reqs, niov); num_reqs = 0; } diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c index 891219ae05..df38b8a03b 100644 --- a/hw/core/qdev-properties-system.c +++ b/hw/core/qdev-properties-system.c @@ -82,7 +82,7 @@ static void parse_drive(DeviceState *dev, const char *str, void **ptr, if (blk_attach_dev(blk, dev) < 0) { DriveInfo *dinfo = blk_legacy_dinfo(blk); - if (dinfo->type != IF_NONE) { + if (dinfo && dinfo->type != IF_NONE) { error_setg(errp, "Drive '%s' is already in use because " "it has been automatically connected to another " "device (did you need 'if=none' in the drive options?)", diff --git a/hw/scsi/scsi-generic.c b/hw/scsi/scsi-generic.c index 6a2d89afba..7a588a7ad4 100644 --- a/hw/scsi/scsi-generic.c +++ b/hw/scsi/scsi-generic.c @@ -225,13 +225,14 @@ static void scsi_read_complete(void * opaque, int ret) if (s->type == TYPE_DISK && r->req.cmd.buf[0] == INQUIRY && r->req.cmd.buf[2] == 0xb0) { - uint32_t max_xfer_len = blk_get_max_transfer_length(s->conf.blk); - if (max_xfer_len) { - stl_be_p(&r->buf[8], max_xfer_len); - /* Also take care of the opt xfer len. */ - if (ldl_be_p(&r->buf[12]) > max_xfer_len) { - stl_be_p(&r->buf[12], max_xfer_len); - } + uint32_t max_transfer = + blk_get_max_transfer(s->conf.blk) / s->blocksize; + + assert(max_transfer); + stl_be_p(&r->buf[8], max_transfer); + /* Also take care of the opt xfer len. */ + if (ldl_be_p(&r->buf[12]) > max_transfer) { + stl_be_p(&r->buf[12], max_transfer); } } scsi_req_data(&r->req, len); diff --git a/include/block/block.h b/include/block/block.h index 733a8ec2ec..616d8b9f12 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -226,33 +226,31 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp); void bdrv_reopen_commit(BDRVReopenState *reopen_state); void bdrv_reopen_abort(BDRVReopenState *reopen_state); -int bdrv_read(BlockDriverState *bs, int64_t sector_num, +int bdrv_read(BdrvChild *child, int64_t sector_num, uint8_t *buf, int nb_sectors); -int bdrv_write(BlockDriverState *bs, int64_t sector_num, +int bdrv_write(BdrvChild *child, int64_t sector_num, const uint8_t *buf, int nb_sectors); -int bdrv_pwrite_zeroes(BlockDriverState *bs, int64_t offset, +int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, int count, BdrvRequestFlags flags); -int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags); -int bdrv_pread(BlockDriverState *bs, int64_t offset, - void *buf, int count); -int bdrv_preadv(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov); -int bdrv_pwrite(BlockDriverState *bs, int64_t offset, - const void *buf, int count); -int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov); -int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset, - const void *buf, int count); -int coroutine_fn bdrv_co_readv(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov); -int coroutine_fn bdrv_co_writev(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, QEMUIOVector *qiov); +int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags); +int bdrv_pread(BdrvChild *child, int64_t offset, void *buf, int bytes); +int bdrv_preadv(BdrvChild *child, int64_t offset, QEMUIOVector *qiov); +int bdrv_pwrite(BdrvChild *child, int64_t offset, const void *buf, int bytes); +int bdrv_pwritev(BdrvChild *child, int64_t offset, QEMUIOVector *qiov); +int bdrv_pwrite_sync(BdrvChild *child, int64_t offset, + const void *buf, int count); +int coroutine_fn bdrv_co_readv(BdrvChild *child, int64_t sector_num, + int nb_sectors, QEMUIOVector *qiov); +int coroutine_fn bdrv_co_writev(BdrvChild *child, int64_t sector_num, + int nb_sectors, QEMUIOVector *qiov); /* * Efficiently zero a region of the disk image. Note that this is a regular * I/O request like read or write and should have a reasonable size. This * function is not suitable for zeroing the entire image in a single request * because it may allocate memory for the entire region. */ -int coroutine_fn bdrv_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, - int count, BdrvRequestFlags flags); +int coroutine_fn bdrv_co_pwrite_zeroes(BdrvChild *child, int64_t offset, + int count, BdrvRequestFlags flags); BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs, const char *backing_file); int bdrv_get_backing_file_depth(BlockDriverState *bs); @@ -310,10 +308,10 @@ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp); /* async block I/O */ -BlockAIOCB *bdrv_aio_readv(BlockDriverState *bs, int64_t sector_num, +BlockAIOCB *bdrv_aio_readv(BdrvChild *child, int64_t sector_num, QEMUIOVector *iov, int nb_sectors, BlockCompletionFunc *cb, void *opaque); -BlockAIOCB *bdrv_aio_writev(BlockDriverState *bs, int64_t sector_num, +BlockAIOCB *bdrv_aio_writev(BdrvChild *child, int64_t sector_num, QEMUIOVector *iov, int nb_sectors, BlockCompletionFunc *cb, void *opaque); BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs, @@ -362,8 +360,8 @@ int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, int64_t sector_num, int nb_sectors, int *pnum); -int bdrv_is_read_only(BlockDriverState *bs); -int bdrv_is_sg(BlockDriverState *bs); +bool bdrv_is_read_only(BlockDriverState *bs); +bool bdrv_is_sg(BlockDriverState *bs); bool bdrv_is_inserted(BlockDriverState *bs); int bdrv_media_changed(BlockDriverState *bs); void bdrv_lock_medium(BlockDriverState *bs, bool locked); @@ -390,8 +388,8 @@ BlockDriverState *bdrv_first(BdrvNextIterator *it); BlockDriverState *bdrv_next(BdrvNextIterator *it); BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs); -int bdrv_is_encrypted(BlockDriverState *bs); -int bdrv_key_required(BlockDriverState *bs); +bool bdrv_is_encrypted(BlockDriverState *bs); +bool bdrv_key_required(BlockDriverState *bs); int bdrv_set_key(BlockDriverState *bs, const char *key); void bdrv_add_key(BlockDriverState *bs, const char *key, Error **errp); int bdrv_query_missing_keys(void); diff --git a/include/block/block_int.h b/include/block/block_int.h index 205715600b..47b9aac71b 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -324,30 +324,48 @@ struct BlockDriver { }; typedef struct BlockLimits { - /* maximum number of sectors that can be discarded at once */ - int max_discard; - - /* optimal alignment for discard requests in sectors */ - int64_t discard_alignment; + /* Alignment requirement, in bytes, for offset/length of I/O + * requests. Must be a power of 2 less than INT_MAX; defaults to + * 1 for drivers with modern byte interfaces, and to 512 + * otherwise. */ + uint32_t request_alignment; + + /* maximum number of bytes that can be discarded at once (since it + * is signed, it must be < 2G, if set), should be multiple of + * pdiscard_alignment, but need not be power of 2. May be 0 if no + * inherent 32-bit limit */ + int32_t max_pdiscard; + + /* optimal alignment for discard requests in bytes, must be power + * of 2, less than max_pdiscard if that is set, and multiple of + * bl.request_alignment. May be 0 if bl.request_alignment is good + * enough */ + uint32_t pdiscard_alignment; /* maximum number of bytes that can zeroized at once (since it is - * signed, it must be < 2G, if set) */ + * signed, it must be < 2G, if set), should be multiple of + * pwrite_zeroes_alignment. May be 0 if no inherent 32-bit limit */ int32_t max_pwrite_zeroes; /* optimal alignment for write zeroes requests in bytes, must be - * power of 2, and less than max_pwrite_zeroes if that is set */ + * power of 2, less than max_pwrite_zeroes if that is set, and + * multiple of bl.request_alignment. May be 0 if + * bl.request_alignment is good enough */ uint32_t pwrite_zeroes_alignment; - /* optimal transfer length in sectors */ - int opt_transfer_length; + /* optimal transfer length in bytes (must be power of 2, and + * multiple of bl.request_alignment), or 0 if no preferred size */ + uint32_t opt_transfer; - /* maximal transfer length in sectors */ - int max_transfer_length; + /* maximal transfer length in bytes (need not be power of 2, but + * should be multiple of opt_transfer), or 0 for no 32-bit limit. + * For now, anything larger than INT_MAX is clamped down. */ + uint32_t max_transfer; - /* memory alignment so that no bounce buffer is needed */ + /* memory alignment, in bytes so that no bounce buffer is needed */ size_t min_mem_alignment; - /* memory alignment for bounce buffer */ + /* memory alignment, in bytes, for bounce buffer */ size_t opt_mem_alignment; /* maximum number of iovec elements */ @@ -411,14 +429,15 @@ struct BdrvChild { struct BlockDriverState { int64_t total_sectors; /* if we are reading a disk image, give its size in sectors */ - int read_only; /* if true, the media is read only */ int open_flags; /* flags used to open the file, re-used for re-open */ - int encrypted; /* if true, the media is encrypted */ - int valid_key; /* if true, a valid encryption key has been set */ - int sg; /* if true, the device is a /dev/sg* */ - int copy_on_read; /* if true, copy read backing sectors into image + bool read_only; /* if true, the media is read only */ + bool encrypted; /* if true, the media is encrypted */ + bool valid_key; /* if true, a valid encryption key has been set */ + bool sg; /* if true, the device is a /dev/sg* */ + bool probed; /* if true, format was probed rather than specified */ + + int copy_on_read; /* if nonzero, copy read backing sectors into image. note this is a reference count */ - bool probed; BlockDriver *drv; /* NULL means no media */ void *opaque; @@ -453,8 +472,6 @@ struct BlockDriverState { /* I/O Limits */ BlockLimits bl; - /* Alignment requirement for offset/length of I/O requests */ - unsigned int request_alignment; /* Flags honored during pwrite (so far: BDRV_REQ_FUA) */ unsigned int supported_write_flags; /* Flags honored during pwrite_zeroes (so far: BDRV_REQ_FUA, @@ -546,10 +563,10 @@ extern BlockDriver bdrv_qcow2; */ void bdrv_setup_io_funcs(BlockDriver *bdrv); -int coroutine_fn bdrv_co_preadv(BlockDriverState *bs, +int coroutine_fn bdrv_co_preadv(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); -int coroutine_fn bdrv_co_pwritev(BlockDriverState *bs, +int coroutine_fn bdrv_co_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); diff --git a/include/block/nbd.h b/include/block/nbd.h index df1f804338..eeda3ebdf7 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -77,6 +77,8 @@ enum { /* Maximum size of a single READ/WRITE data buffer */ #define NBD_MAX_BUFFER_SIZE (32 * 1024 * 1024) +#define NBD_MAX_SECTORS (NBD_MAX_BUFFER_SIZE / BDRV_SECTOR_SIZE) + /* Maximum size of an export name. The NBD spec requires 256 and * suggests that servers support up to 4096, but we stick to only the * required size so that we can stack-allocate the names, and because diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index c04af8ea46..3c3e82f05d 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -124,6 +124,7 @@ int blk_pwrite_zeroes(BlockBackend *blk, int64_t offset, BlockAIOCB *blk_aio_pwrite_zeroes(BlockBackend *blk, int64_t offset, int count, BdrvRequestFlags flags, BlockCompletionFunc *cb, void *opaque); +int blk_make_zero(BlockBackend *blk, BdrvRequestFlags flags); int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count); int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count, BdrvRequestFlags flags); @@ -170,7 +171,7 @@ bool blk_is_available(BlockBackend *blk); void blk_lock_medium(BlockBackend *blk, bool locked); void blk_eject(BlockBackend *blk, bool eject_flag); int blk_get_flags(BlockBackend *blk); -int blk_get_max_transfer_length(BlockBackend *blk); +uint32_t blk_get_max_transfer(BlockBackend *blk); int blk_get_max_iov(BlockBackend *blk); void blk_set_guest_block_size(BlockBackend *blk, int align); void *blk_try_blockalign(BlockBackend *blk, size_t size); diff --git a/qapi/block-core.json b/qapi/block-core.json index 98a20d22f4..ac8f5f61d4 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -1961,7 +1961,8 @@ # # @config: #optional filename of the configuration file # -# @align: #optional required alignment for requests in bytes +# @align: #optional required alignment for requests in bytes, +# must be power of 2, or 0 for default # # @inject-error: #optional array of error injection descriptions # diff --git a/qemu-img.c b/qemu-img.c index 3322a1e5fc..2e04e281aa 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -1648,7 +1648,7 @@ static int convert_do_copy(ImgConvertState *s) if (!s->has_zero_init && !s->target_has_backing && bdrv_can_write_zeroes_with_unmap(blk_bs(s->target))) { - ret = bdrv_make_zero(blk_bs(s->target), BDRV_REQ_MAY_UNMAP); + ret = blk_make_zero(s->target, BDRV_REQ_MAY_UNMAP); if (ret == 0) { s->has_zero_init = true; } @@ -2085,13 +2085,14 @@ static int img_convert(int argc, char **argv) } out_bs = blk_bs(out_blk); - /* increase bufsectors from the default 4096 (2M) if opt_transfer_length + /* increase bufsectors from the default 4096 (2M) if opt_transfer * or discard_alignment of the out_bs is greater. Limit to 32768 (16MB) * as maximum. */ bufsectors = MIN(32768, - MAX(bufsectors, MAX(out_bs->bl.opt_transfer_length, - out_bs->bl.discard_alignment)) - ); + MAX(bufsectors, + MAX(out_bs->bl.opt_transfer >> BDRV_SECTOR_BITS, + out_bs->bl.pdiscard_alignment >> + BDRV_SECTOR_BITS))); if (skip_create) { int64_t output_sectors = blk_nb_sectors(out_blk); @@ -3866,7 +3867,7 @@ int main(int argc, char **argv) return 0; } argv += optind; - optind = 1; + optind = 0; if (!trace_init_backends()) { exit(1); |