The following changes since commit ae49fbbcd8e4e9d8bf7131add34773f579e1aff7: Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20171025' into staging (2017-10-25 16:38:57 +0100) are available in the git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to 4254d01ce4eec9a3ccf320d14e2da132b8ad4a51: Merge remote-tracking branch 'mreitz/tags/pull-block-2017-10-26' into queue-block (2017-10-26 15:02:40 +0200) ---------------------------------------------------------------- Block layer patches ---------------------------------------------------------------- Alberto Garcia (1): qcow2: Use BDRV_SECTOR_BITS instead of its literal value Eric Blake (24): block: Allow NULL file for bdrv_get_block_status() block: Add flag to avoid wasted work in bdrv_is_allocated() block: Make bdrv_round_to_clusters() signature more useful qcow2: Switch is_zero_sectors() to byte-based block: Switch bdrv_make_zero() to byte-based qemu-img: Switch get_block_status() to byte-based block: Convert bdrv_get_block_status() to bytes block: Switch bdrv_co_get_block_status() to byte-based block: Switch BdrvCoGetBlockStatusData to byte-based block: Switch bdrv_common_block_status_above() to byte-based block: Switch bdrv_co_get_block_status_above() to byte-based block: Convert bdrv_get_block_status_above() to bytes qemu-img: Simplify logic in img_compare() qemu-img: Speed up compare on pre-allocated larger file qemu-img: Add find_nonzero() qemu-img: Drop redundant error message in compare qemu-img: Change check_empty_sectors() to byte-based qemu-img: Change compare_sectors() to be byte-based qemu-img: Change img_rebase() to be byte-based qemu-img: Change img_compare() to be byte-based block: Align block status requests block: Reduce bdrv_aligned_preadv() rounding qcow2: Reduce is_zero() rounding qemu-io: Relax 'alloc' now that block-status doesn't assert Kevin Wolf (2): qemu-iotests: Test backing_fmt with backing node reference Merge remote-tracking branch 'mreitz/tags/pull-block-2017-10-26' into queue-block Max Reitz (8): qemu-img.1: Image invalidation on qemu-img commit iotests: Add test for dataplane mirroring iotests: Pull _filter_actual_image_size from 67/87 iotests: Filter actual image size in 184 and 191 qcow2: Emit errp when truncating the image tail qcow2: Fix unaligned preallocated truncation qcow2: Always execute preallocate() in a coroutine iotests: Add cluster_size=64k to 125 Peter Krempa (1): block: don't add 'driver' to options when referring to backing via node name include/block/block.h | 29 ++- include/block/block_int.h | 11 +- block.c | 3 +- block/blkdebug.c | 13 +- block/io.c | 334 ++++++++++++++++----------- block/mirror.c | 26 +-- block/qcow2-cluster.c | 2 +- block/qcow2.c | 116 ++++++---- qemu-img.c | 381 ++++++++++++++----------------- qemu-io-cmds.c | 13 -- block/trace-events | 2 +- qemu-img.texi | 9 +- tests/qemu-iotests/067 | 2 +- tests/qemu-iotests/074.out | 2 - tests/qemu-iotests/087 | 2 +- tests/qemu-iotests/125 | 7 +- tests/qemu-iotests/125.out | 480 +++++++++++++++++++++++++++++++++++---- tests/qemu-iotests/127 | 97 ++++++++ tests/qemu-iotests/127.out | 14 ++ tests/qemu-iotests/177 | 12 +- tests/qemu-iotests/177.out | 19 +- tests/qemu-iotests/184 | 3 +- tests/qemu-iotests/184.out | 6 +- tests/qemu-iotests/191 | 7 +- tests/qemu-iotests/191.out | 48 ++-- tests/qemu-iotests/common.filter | 6 + tests/qemu-iotests/group | 1 + 27 files changed, 1102 insertions(+), 543 deletions(-) create mode 100755 tests/qemu-iotests/127 create mode 100644 tests/qemu-iotests/127.out From: Peter Krempa <pkrempa@redhat.com> When referring to a backing file of an image via node name bdrv_open_backing_file would add the 'driver' option to the option list filling it with the backing format driver. This breaks construction of the backing chain via -blockdev, as bdrv_open_inherit reports an error if both 'reference' and 'options' are provided. $ qemu-img create -f raw /tmp/backing.raw 64M $ qemu-img create -f qcow2 -F raw -b /tmp/backing.raw /tmp/test.qcow2 $ qemu-system-x86_64 \ -blockdev driver=file,filename=/tmp/backing.raw,node-name=backing \ -blockdev driver=qcow2,file.driver=file,file.filename=/tmp/test.qcow2,node-name=root,backing=backing qemu-system-x86_64: -blockdev driver=qcow2,file.driver=file,file.filename=/tmp/test.qcow2,node-name=root,backing=backing: Could not open backing file: Cannot reference an existing block device with additional options or a new filename Signed-off-by: Peter Krempa <pkrempa@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options, goto free_exit; } - if (bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) { + if (!reference && + bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) { qdict_put_str(options, "driver", bs->backing_format); } -- 2.13.6 This changes test case 191 to include a backing image that has backing_fmt set in the image file, but is referenced by node name in the qemu command line. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- tests/qemu-iotests/191 | 3 ++- tests/qemu-iotests/191.out | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/191 +++ b/tests/qemu-iotests/191 @@ -XXX,XX +XXX,XX @@ echo === Preparing and starting VM === echo TEST_IMG="${TEST_IMG}.base" _make_test_img $size -TEST_IMG="${TEST_IMG}.mid" _make_test_img -b "${TEST_IMG}.base" +IMGOPTS=$(_optstr_add "$IMGOPTS" "backing_fmt=$IMGFMT") \ + TEST_IMG="${TEST_IMG}.mid" _make_test_img -b "${TEST_IMG}.base" _make_test_img -b "${TEST_IMG}.mid" TEST_IMG="${TEST_IMG}.ovl2" _make_test_img -b "${TEST_IMG}.mid" diff --git a/tests/qemu-iotests/191.out b/tests/qemu-iotests/191.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/191.out +++ b/tests/qemu-iotests/191.out @@ -XXX,XX +XXX,XX @@ QA output created by 191 === Preparing and starting VM === Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864 -Formatting 'TEST_DIR/t.IMGFMT.mid', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.base +Formatting 'TEST_DIR/t.IMGFMT.mid', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.base backing_fmt=IMGFMT Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.mid Formatting 'TEST_DIR/t.IMGFMT.ovl2', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.mid wrote 65536/65536 bytes at offset 1048576 -- 2.13.6 From: Eric Blake <eblake@redhat.com> Not all callers care about which BDS owns the mapping for a given range of the file. This patch merely simplifies the callers by consolidating the logic in the common call point, while guaranteeing a non-NULL file to all the driver callbacks, for no semantic change. The only caller that does not care about pnum is bdrv_is_allocated, as invoked by vvfat; we can likewise add assertions that the rest of the stack does not have to worry about a NULL pnum. Furthermore, this will also set the stage for a future cleanup: when a caller does not care about which BDS owns an offset, it would be nice to allow the driver to optimize things to not have to return BDRV_BLOCK_OFFSET_VALID in the first place. In the case of fragmented allocation (for example, it's fairly easy to create a qcow2 image where consecutive guest addresses are not at consecutive host addresses), the current contract requires bdrv_get_block_status() to clamp *pnum to the limit where host addresses are no longer consecutive, but allowing a NULL file means that *pnum could be set to the full length of known-allocated data. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 10 ++++++---- block/io.c | 49 ++++++++++++++++++++++++++--------------------- block/mirror.c | 3 +-- block/qcow2.c | 8 ++------ qemu-img.c | 10 ++++------ 5 files changed, 40 insertions(+), 40 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { int64_t offset, int bytes); /* - * Building block for bdrv_block_status[_above]. The driver should - * answer only according to the current layer, and should not - * set BDRV_BLOCK_ALLOCATED, but may set BDRV_BLOCK_RAW. See block.h - * for the meaning of _DATA, _ZERO, and _OFFSET_VALID. + * Building block for bdrv_block_status[_above] and + * bdrv_is_allocated[_above]. The driver should answer only + * according to the current layer, and should not set + * BDRV_BLOCK_ALLOCATED, but may set BDRV_BLOCK_RAW. See block.h + * for the meaning of _DATA, _ZERO, and _OFFSET_VALID. The block + * layer guarantees non-NULL pnum and file. */ int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ 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; target_sectors = bdrv_nb_sectors(bs); @@ -XXX,XX +XXX,XX @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) if (nb_sectors <= 0) { return 0; } - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, &file); + ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, NULL); if (ret < 0) { error_report("error getting block status at sector %" PRId64 ": %s", sector_num, strerror(-ret)); @@ -XXX,XX +XXX,XX @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * beyond the end of the disk image it will be clamped; if 'pnum' is set to * the end of the image, then the returned value will include BDRV_BLOCK_EOF. * - * If returned value is positive and BDRV_BLOCK_OFFSET_VALID bit is set, 'file' - * points to the BDS which the sector range is allocated in. + * If returned value is positive, BDRV_BLOCK_OFFSET_VALID bit is set, and + * 'file' is non-NULL, then '*file' points to the BDS which the sector range + * is allocated in. */ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, int64_t sector_num, @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, int64_t total_sectors; int64_t n; int64_t ret, ret2; + BlockDriverState *local_file = NULL; - *file = NULL; + assert(pnum); + *pnum = 0; total_sectors = bdrv_nb_sectors(bs); if (total_sectors < 0) { - return total_sectors; + ret = total_sectors; + goto early_out; } if (sector_num >= total_sectors) { - *pnum = 0; - return BDRV_BLOCK_EOF; + ret = BDRV_BLOCK_EOF; + goto early_out; } if (!nb_sectors) { - *pnum = 0; - return 0; + ret = 0; + goto early_out; } n = total_sectors - sector_num; @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, } if (bs->drv->protocol_name) { ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE); - *file = bs; + local_file = bs; } - return ret; + goto early_out; } bdrv_inc_in_flight(bs); ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum, - file); + &local_file); if (ret < 0) { *pnum = 0; goto out; } if (ret & BDRV_BLOCK_RAW) { - assert(ret & BDRV_BLOCK_OFFSET_VALID && *file); - ret = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS, - *pnum, pnum, file); + assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); + ret = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + *pnum, pnum, &local_file); goto out; } @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, } } - if (*file && *file != bs && + if (local_file && local_file != bs && (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) && (ret & BDRV_BLOCK_OFFSET_VALID)) { - BlockDriverState *file2; int file_pnum; - ret2 = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS, - *pnum, &file_pnum, &file2); + ret2 = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + *pnum, &file_pnum, NULL); if (ret2 >= 0) { /* Ignore errors. This is just providing extra information, it * is useful but not necessary. @@ -XXX,XX +XXX,XX @@ out: if (ret >= 0 && sector_num + *pnum == total_sectors) { ret |= BDRV_BLOCK_EOF; } +early_out: + if (file) { + *file = local_file; + } return ret; } @@ -XXX,XX +XXX,XX @@ int64_t bdrv_get_block_status(BlockDriverState *bs, int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum) { - BlockDriverState *file; int64_t sector_num = offset >> BDRV_SECTOR_BITS; int nb_sectors = bytes >> BDRV_SECTOR_BITS; int64_t ret; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE) && bytes < INT_MAX); ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &psectors, - &file); + NULL); if (ret < 0) { return ret; } diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) int io_sectors; unsigned int io_bytes; int64_t io_bytes_acct; - BlockDriverState *file; enum MirrorMethod { MIRROR_METHOD_COPY, MIRROR_METHOD_ZERO, @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) ret = bdrv_get_block_status_above(source, NULL, offset >> BDRV_SECTOR_BITS, nb_chunks * sectors_per_chunk, - &io_sectors, &file); + &io_sectors, NULL); io_bytes = io_sectors * BDRV_SECTOR_SIZE; if (ret < 0) { io_bytes = MIN(nb_chunks * s->granularity, max_io_bytes); diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static bool is_zero_sectors(BlockDriverState *bs, int64_t start, uint32_t count) { int nr; - BlockDriverState *file; int64_t res; if (start + count > bs->total_sectors) { @@ -XXX,XX +XXX,XX @@ static bool is_zero_sectors(BlockDriverState *bs, int64_t start, if (!count) { return true; } - res = bdrv_get_block_status_above(bs, NULL, start, count, - &nr, &file); + res = bdrv_get_block_status_above(bs, NULL, start, count, &nr, NULL); return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == count; } @@ -XXX,XX +XXX,XX @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, offset += pnum * BDRV_SECTOR_SIZE) { int nb_sectors = MIN(ssize - offset, BDRV_REQUEST_MAX_BYTES) / BDRV_SECTOR_SIZE; - BlockDriverState *file; int64_t ret; ret = bdrv_get_block_status_above(in_bs, NULL, offset >> BDRV_SECTOR_BITS, - nb_sectors, - &pnum, &file); + nb_sectors, &pnum, NULL); if (ret < 0) { error_setg_errno(&local_err, -ret, "Unable to get block status"); diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) for (;;) { int64_t status1, status2; - BlockDriverState *file; nb_sectors = sectors_to_process(total_sectors, sector_num); if (nb_sectors <= 0) { @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } status1 = bdrv_get_block_status_above(bs1, NULL, sector_num, total_sectors1 - sector_num, - &pnum1, &file); + &pnum1, NULL); if (status1 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename1); @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) status2 = bdrv_get_block_status_above(bs2, NULL, sector_num, total_sectors2 - sector_num, - &pnum2, &file); + &pnum2, NULL); if (status2 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename2); @@ -XXX,XX +XXX,XX @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS); if (s->sector_next_status <= sector_num) { - BlockDriverState *file; if (s->target_has_backing) { ret = bdrv_get_block_status(blk_bs(s->src[src_cur]), sector_num - src_cur_offset, - n, &n, &file); + n, &n, NULL); } else { ret = bdrv_get_block_status_above(blk_bs(s->src[src_cur]), NULL, sector_num - src_cur_offset, - n, &n, &file); + n, &n, NULL); } if (ret < 0) { return ret; -- 2.13.6 From: Eric Blake <eblake@redhat.com> Not all callers care about which BDS owns the mapping for a given range of the file, or where the zeroes lie within that mapping. In particular, bdrv_is_allocated() cares more about finding the largest run of allocated data from the guest perspective, whether or not that data is consecutive from the host perspective, and whether or not the data reads as zero. Therefore, doing subsequent refinements such as checking how much of the format-layer allocation also satisfies BDRV_BLOCK_ZERO at the protocol layer is wasted work - in the best case, it just costs extra CPU cycles during a single bdrv_is_allocated(), but in the worst case, it results in a smaller *pnum, and forces callers to iterate through more status probes when visiting the entire file for even more extra CPU cycles. This patch only optimizes the block layer (no behavior change when want_zero is true, but skip unnecessary effort when it is false). Then when subsequent patches tweak the driver callback to be byte-based, we can also pass this hint through to the driver. Tweak BdrvCoGetBlockStatusData to declare arguments in parameter order, rather than mixing things up (minimizing padding is not necessary here). Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 57 +++++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 41 insertions(+), 16 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_flush_all(void) typedef struct BdrvCoGetBlockStatusData { BlockDriverState *bs; BlockDriverState *base; - BlockDriverState **file; + bool want_zero; int64_t sector_num; int nb_sectors; int *pnum; + BlockDriverState **file; int64_t ret; bool done; } BdrvCoGetBlockStatusData; @@ -XXX,XX +XXX,XX @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * Drivers not implementing the functionality are assumed to not support * backing files, hence all their sectors are reported as allocated. * + * If 'want_zero' is true, the caller is querying for mapping purposes, + * and the result should include BDRV_BLOCK_OFFSET_VALID and + * BDRV_BLOCK_ZERO where possible; otherwise, the result may omit those + * bits particularly if it allows for a larger value in 'pnum'. + * * If 'sector_num' is beyond the end of the disk image the return value is * BDRV_BLOCK_EOF and 'pnum' is set to 0. * @@ -XXX,XX +XXX,XX @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * is allocated in. */ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, + bool want_zero, int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file) @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, if (ret & BDRV_BLOCK_RAW) { assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); - ret = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + ret = bdrv_co_get_block_status(local_file, want_zero, + ret >> BDRV_SECTOR_BITS, *pnum, pnum, &local_file); goto out; } if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) { ret |= BDRV_BLOCK_ALLOCATED; - } else { + } else if (want_zero) { if (bdrv_unallocated_blocks_are_zero(bs)) { ret |= BDRV_BLOCK_ZERO; } else if (bs->backing) { BlockDriverState *bs2 = bs->backing->bs; int64_t nb_sectors2 = bdrv_nb_sectors(bs2); + if (nb_sectors2 >= 0 && sector_num >= nb_sectors2) { ret |= BDRV_BLOCK_ZERO; } } } - if (local_file && local_file != bs && + if (want_zero && local_file && local_file != bs && (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) && (ret & BDRV_BLOCK_OFFSET_VALID)) { int file_pnum; - ret2 = bdrv_co_get_block_status(local_file, ret >> BDRV_SECTOR_BITS, + ret2 = bdrv_co_get_block_status(local_file, want_zero, + ret >> BDRV_SECTOR_BITS, *pnum, &file_pnum, NULL); if (ret2 >= 0) { /* Ignore errors. This is just providing extra information, it @@ -XXX,XX +XXX,XX @@ early_out: static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, BlockDriverState *base, + bool want_zero, int64_t sector_num, int nb_sectors, int *pnum, @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, assert(bs != base); for (p = bs; p != base; p = backing_bs(p)) { - ret = bdrv_co_get_block_status(p, sector_num, nb_sectors, pnum, file); + ret = bdrv_co_get_block_status(p, want_zero, sector_num, nb_sectors, + pnum, file); if (ret < 0) { break; } @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) BdrvCoGetBlockStatusData *data = opaque; data->ret = bdrv_co_get_block_status_above(data->bs, data->base, + data->want_zero, data->sector_num, data->nb_sectors, data->pnum, @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) * * See bdrv_co_get_block_status_above() for details. */ -int64_t bdrv_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +static int64_t bdrv_common_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + bool want_zero, + int64_t sector_num, + int nb_sectors, int *pnum, + BlockDriverState **file) { Coroutine *co; BdrvCoGetBlockStatusData data = { .bs = bs, .base = base, - .file = file, + .want_zero = want_zero, .sector_num = sector_num, .nb_sectors = nb_sectors, .pnum = pnum, + .file = file, .done = false, }; @@ -XXX,XX +XXX,XX @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs, return data.ret; } +int64_t bdrv_get_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + int64_t sector_num, + int nb_sectors, int *pnum, + BlockDriverState **file) +{ + return bdrv_common_block_status_above(bs, base, true, sector_num, + nb_sectors, pnum, file); +} + int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, @@ -XXX,XX +XXX,XX @@ int64_t bdrv_get_block_status(BlockDriverState *bs, int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum) { - int64_t sector_num = offset >> BDRV_SECTOR_BITS; - int nb_sectors = bytes >> BDRV_SECTOR_BITS; int64_t ret; int psectors; assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE) && bytes < INT_MAX); - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &psectors, - NULL); + ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, + offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &psectors, + NULL); if (ret < 0) { return ret; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> In the process of converting sector-based interfaces to bytes, I'm finding it easier to represent a byte count as a 64-bit integer at the block layer (even if we are internally capped by SIZE_MAX or even INT_MAX for individual transactions, it's still nicer to not have to worry about truncation/overflow issues on as many variables). Update the signature of bdrv_round_to_clusters() to uniformly use int64_t, matching the signature already chosen for bdrv_is_allocated and the fact that off_t is also a signed type, then adjust clients according to the required fallout (even where the result could now exceed 32 bits, no client is directly assigning the result into a 32-bit value without breaking things into a loop first). Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 4 ++-- block/io.c | 6 +++--- block/mirror.c | 7 +++---- block/trace-events | 2 +- 4 files changed, 9 insertions(+), 10 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ int bdrv_get_flags(BlockDriverState *bs); int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi); ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs); void bdrv_round_to_clusters(BlockDriverState *bs, - int64_t offset, unsigned int bytes, + int64_t offset, int64_t bytes, int64_t *cluster_offset, - unsigned int *cluster_bytes); + int64_t *cluster_bytes); const char *bdrv_get_encrypted_filename(BlockDriverState *bs); void bdrv_get_backing_filename(BlockDriverState *bs, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void mark_request_serialising(BdrvTrackedRequest *req, uint64_t align) * Round a region to cluster boundaries */ void bdrv_round_to_clusters(BlockDriverState *bs, - int64_t offset, unsigned int bytes, + int64_t offset, int64_t bytes, int64_t *cluster_offset, - unsigned int *cluster_bytes) + int64_t *cluster_bytes) { BlockDriverInfo bdi; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, struct iovec iov; QEMUIOVector local_qiov; int64_t cluster_offset; - unsigned int cluster_bytes; + int64_t cluster_bytes; size_t skip_bytes; int ret; int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static int mirror_cow_align(MirrorBlockJob *s, int64_t *offset, bool need_cow; int ret = 0; int64_t align_offset = *offset; - unsigned int align_bytes = *bytes; + int64_t align_bytes = *bytes; int max_bytes = s->granularity * s->max_iov; - assert(*bytes < INT_MAX); need_cow = !test_bit(*offset / s->granularity, s->cow_bitmap); need_cow |= !test_bit((*offset + *bytes - 1) / s->granularity, s->cow_bitmap); @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) while (nb_chunks > 0 && offset < s->bdev_length) { int64_t ret; int io_sectors; - unsigned int io_bytes; + int64_t io_bytes; int64_t io_bytes_acct; enum MirrorMethod { MIRROR_METHOD_COPY, @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) io_bytes = s->granularity; } else if (ret >= 0 && !(ret & BDRV_BLOCK_DATA)) { int64_t target_offset; - unsigned int target_bytes; + int64_t target_bytes; bdrv_round_to_clusters(blk_bs(s->target), offset, io_bytes, &target_offset, &target_bytes); if (target_offset == offset && diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ blk_co_pwritev(void *blk, void *bs, int64_t offset, unsigned int bytes, int flag bdrv_co_preadv(void *bs, int64_t offset, int64_t nbytes, unsigned int flags) "bs %p offset %"PRId64" nbytes %"PRId64" flags 0x%x" bdrv_co_pwritev(void *bs, int64_t offset, int64_t nbytes, unsigned int flags) "bs %p offset %"PRId64" nbytes %"PRId64" flags 0x%x" bdrv_co_pwrite_zeroes(void *bs, int64_t offset, int count, int flags) "bs %p offset %"PRId64" count %d flags 0x%x" -bdrv_co_do_copy_on_readv(void *bs, int64_t offset, unsigned int bytes, int64_t cluster_offset, unsigned int cluster_bytes) "bs %p offset %"PRId64" bytes %u cluster_offset %"PRId64" cluster_bytes %u" +bdrv_co_do_copy_on_readv(void *bs, int64_t offset, unsigned int bytes, int64_t cluster_offset, int64_t cluster_bytes) "bs %p offset %"PRId64" bytes %u cluster_offset %"PRId64" cluster_bytes %"PRId64 # block/stream.c stream_one_iteration(void *s, int64_t offset, uint64_t bytes, int is_allocated) "s %p offset %" PRId64 " bytes %" PRIu64 " is_allocated %d" -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal function (no semantic change), and rename it to is_zero() in the process. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ finish: } -static bool is_zero_sectors(BlockDriverState *bs, int64_t start, - uint32_t count) +static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) { int nr; int64_t res; + int64_t start; - if (start + count > bs->total_sectors) { - count = bs->total_sectors - start; + /* TODO: Widening to sector boundaries should only be needed as + * long as we can't query finer granularity. */ + start = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); + bytes = QEMU_ALIGN_UP(offset + bytes, BDRV_SECTOR_SIZE) - start; + + /* Clamp to image length, before checking status of underlying sectors */ + if (start + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) { + bytes = bs->total_sectors * BDRV_SECTOR_SIZE - start; } - if (!count) { + if (!bytes) { return true; } - res = bdrv_get_block_status_above(bs, NULL, start, count, &nr, NULL); - return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == count; + res = bdrv_get_block_status_above(bs, NULL, start >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &nr, NULL); + return res >= 0 && (res & BDRV_BLOCK_ZERO) && + nr * BDRV_SECTOR_SIZE == bytes; } static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, } if (head || tail) { - int64_t cl_start = (offset - head) >> BDRV_SECTOR_BITS; uint64_t off; unsigned int nr; assert(head + bytes <= s->cluster_size); /* check whether remainder of cluster already reads as zero */ - if (!(is_zero_sectors(bs, cl_start, - DIV_ROUND_UP(head, BDRV_SECTOR_SIZE)) && - is_zero_sectors(bs, (offset + bytes) >> BDRV_SECTOR_BITS, - DIV_ROUND_UP(-tail & (s->cluster_size - 1), - BDRV_SECTOR_SIZE)))) { + if (!(is_zero(bs, offset - head, head) && + is_zero(bs, offset + bytes, + tail ? s->cluster_size - tail : 0))) { return -ENOTSUP; } qemu_co_mutex_lock(&s->lock); /* We can have new write after previous check */ - offset = cl_start << BDRV_SECTOR_BITS; + offset = QEMU_ALIGN_DOWN(offset, s->cluster_size); bytes = s->cluster_size; nr = s->cluster_size; ret = qcow2_get_cluster_offset(bs, offset, &nr, &off); -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Change the internal loop iteration of zeroing a device to track by bytes instead of sectors (although we are still guaranteed that we iterate by steps that are sector-aligned). Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, */ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) { - int64_t target_sectors, ret, nb_sectors, sector_num = 0; + int64_t target_size, ret, bytes, offset = 0; BlockDriverState *bs = child->bs; - int n; + int n; /* sectors */ - target_sectors = bdrv_nb_sectors(bs); - if (target_sectors < 0) { - return target_sectors; + target_size = bdrv_getlength(bs); + if (target_size < 0) { + return target_size; } for (;;) { - nb_sectors = MIN(target_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS); - if (nb_sectors <= 0) { + bytes = MIN(target_size - offset, BDRV_REQUEST_MAX_BYTES); + if (bytes <= 0) { return 0; } - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, NULL); + ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &n, NULL); if (ret < 0) { - error_report("error getting block status at sector %" PRId64 ": %s", - sector_num, strerror(-ret)); + error_report("error getting block status at offset %" PRId64 ": %s", + offset, strerror(-ret)); return ret; } if (ret & BDRV_BLOCK_ZERO) { - sector_num += n; + offset += n * BDRV_SECTOR_BITS; continue; } - ret = bdrv_pwrite_zeroes(child, sector_num << BDRV_SECTOR_BITS, - n << BDRV_SECTOR_BITS, flags); + ret = bdrv_pwrite_zeroes(child, offset, n * BDRV_SECTOR_SIZE, flags); if (ret < 0) { - error_report("error writing zeroes at sector %" PRId64 ": %s", - sector_num, strerror(-ret)); + error_report("error writing zeroes at offset %" PRId64 ": %s", + offset, strerror(-ret)); return ret; } - sector_num += n; + offset += n * BDRV_SECTOR_SIZE; } } -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Continue by converting an internal function (no semantic change), and simplifying its caller accordingly. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static void dump_map_entry(OutputFormat output_format, MapEntry *e, } } -static int get_block_status(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, MapEntry *e) +static int get_block_status(BlockDriverState *bs, int64_t offset, + int64_t bytes, MapEntry *e) { int64_t ret; int depth; BlockDriverState *file; bool has_offset; + int nb_sectors = bytes >> BDRV_SECTOR_BITS; + assert(bytes < INT_MAX); /* As an optimization, we could cache the current range of unallocated * clusters in each file of the chain, and avoid querying the same * range repeatedly. @@ -XXX,XX +XXX,XX @@ static int get_block_status(BlockDriverState *bs, int64_t sector_num, depth = 0; for (;;) { - ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &nb_sectors, - &file); + ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, nb_sectors, + &nb_sectors, &file); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int get_block_status(BlockDriverState *bs, int64_t sector_num, has_offset = !!(ret & BDRV_BLOCK_OFFSET_VALID); *e = (MapEntry) { - .start = sector_num * BDRV_SECTOR_SIZE, + .start = offset, .length = nb_sectors * BDRV_SECTOR_SIZE, .data = !!(ret & BDRV_BLOCK_DATA), .zero = !!(ret & BDRV_BLOCK_ZERO), @@ -XXX,XX +XXX,XX @@ static int img_map(int argc, char **argv) length = blk_getlength(blk); while (curr.start + curr.length < length) { - int64_t nsectors_left; - int64_t sector_num; - int n; - - sector_num = (curr.start + curr.length) >> BDRV_SECTOR_BITS; + int64_t offset = curr.start + curr.length; + int64_t n; /* Probe up to 1 GiB at a time. */ - nsectors_left = DIV_ROUND_UP(length, BDRV_SECTOR_SIZE) - sector_num; - n = MIN(1 << (30 - BDRV_SECTOR_BITS), nsectors_left); - ret = get_block_status(bs, sector_num, n, &next); + n = QEMU_ALIGN_DOWN(MIN(1 << 30, length - offset), BDRV_SECTOR_SIZE); + ret = get_block_status(bs, offset, n, &next); if (ret < 0) { error_report("Could not read file metadata: %s", strerror(-ret)); -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually moving away from sector-based interfaces, towards byte-based. In the common case, allocation is unlikely to ever use values that are not naturally sector-aligned, but it is possible that byte-based values will let us be more precise about allocation at the end of an unaligned file that can do byte-based access. Changing the name of the function from bdrv_get_block_status() to bdrv_block_status() ensures that the compiler enforces that all callers are updated. For now, the io.c layer still assert()s that all callers are sector-aligned, but that can be relaxed when a later patch implements byte-based block status in the drivers. There was an inherent limitation in returning the offset via the return value: we only have room for BDRV_BLOCK_OFFSET_MASK bits, which means an offset can only be mapped for sector-aligned queries (or, if we declare that non-aligned input is at the same relative position modulo 512 of the answer), so the new interface also changes things to return the offset via output through a parameter by reference rather than mashed into the return value. We'll have some glue code that munges between the two styles until we finish converting all uses. For the most part this patch is just the addition of scaling at the callers followed by inverse scaling at bdrv_block_status(), coupled with the tweak in calling convention. But some code, particularly bdrv_is_allocated(), gets a lot simpler because it no longer has to mess with sectors. For ease of review, bdrv_get_block_status_above() will be tackled separately. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 17 +++++++++-------- block/io.c | 47 ++++++++++++++++++++++++++++++++++------------- block/qcow2-cluster.c | 2 +- qemu-img.c | 25 ++++++++++++++----------- 4 files changed, 58 insertions(+), 33 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ typedef struct HDGeometry { #define BDRV_REQUEST_MAX_BYTES (BDRV_REQUEST_MAX_SECTORS << BDRV_SECTOR_BITS) /* - * Allocation status flags for bdrv_get_block_status() and friends. + * Allocation status flags for bdrv_block_status() and friends. * * Public flags: * BDRV_BLOCK_DATA: allocation for data at offset is tied to this layer @@ -XXX,XX +XXX,XX @@ typedef struct HDGeometry { * that the block layer recompute the answer from the returned * BDS; must be accompanied by just BDRV_BLOCK_OFFSET_VALID. * - * If BDRV_BLOCK_OFFSET_VALID is set, bits 9-62 (BDRV_BLOCK_OFFSET_MASK) - * represent the offset in the returned BDS that is allocated for the - * corresponding raw data; however, whether that offset actually contains - * data also depends on BDRV_BLOCK_DATA and BDRV_BLOCK_ZERO, as follows: + * If BDRV_BLOCK_OFFSET_VALID is set, bits 9-62 (BDRV_BLOCK_OFFSET_MASK) of + * the return value (old interface) or the entire map parameter (new + * interface) represent the offset in the returned BDS that is allocated for + * the corresponding raw data. However, whether that offset actually + * contains data also depends on BDRV_BLOCK_DATA, as follows: * * DATA ZERO OFFSET_VALID * t t t sectors read as zero, returned file is zero at offset @@ -XXX,XX +XXX,XX @@ int bdrv_has_zero_init_1(BlockDriverState *bs); int bdrv_has_zero_init(BlockDriverState *bs); bool bdrv_unallocated_blocks_are_zero(BlockDriverState *bs); bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); -int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file); +int bdrv_block_status(BlockDriverState *bs, int64_t offset, + int64_t bytes, int64_t *pnum, int64_t *map, + BlockDriverState **file); int64_t bdrv_get_block_status_above(BlockDriverState *bs, BlockDriverState *base, int64_t sector_num, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_pwrite_zeroes(BdrvChild *child, int64_t offset, */ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) { - int64_t target_size, ret, bytes, offset = 0; + int ret; + int64_t target_size, bytes, offset = 0; BlockDriverState *bs = child->bs; - int n; /* sectors */ target_size = bdrv_getlength(bs); if (target_size < 0) { @@ -XXX,XX +XXX,XX @@ int bdrv_make_zero(BdrvChild *child, BdrvRequestFlags flags) if (bytes <= 0) { return 0; } - ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &n, NULL); + ret = bdrv_block_status(bs, offset, bytes, &bytes, NULL, NULL); if (ret < 0) { error_report("error getting block status at offset %" PRId64 ": %s", offset, strerror(-ret)); return ret; } if (ret & BDRV_BLOCK_ZERO) { - offset += n * BDRV_SECTOR_BITS; + offset += bytes; continue; } - ret = bdrv_pwrite_zeroes(child, offset, n * BDRV_SECTOR_SIZE, flags); + ret = bdrv_pwrite_zeroes(child, offset, bytes, flags); if (ret < 0) { error_report("error writing zeroes at offset %" PRId64 ": %s", offset, strerror(-ret)); return ret; } - offset += n * BDRV_SECTOR_SIZE; + offset += bytes; } } @@ -XXX,XX +XXX,XX @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs, nb_sectors, pnum, file); } -int64_t bdrv_get_block_status(BlockDriverState *bs, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, + int64_t *pnum, int64_t *map, BlockDriverState **file) { - return bdrv_get_block_status_above(bs, backing_bs(bs), - sector_num, nb_sectors, pnum, file); + int64_t ret; + int n; + + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + assert(pnum); + /* + * The contract allows us to return pnum smaller than bytes, even + * if the next query would see the same status; we truncate the + * request to avoid overflowing the driver's 32-bit interface. + */ + bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); + ret = bdrv_get_block_status_above(bs, backing_bs(bs), + offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &n, file); + if (ret < 0) { + assert(INT_MIN <= ret); + *pnum = 0; + return ret; + } + *pnum = n * BDRV_SECTOR_SIZE; + if (map) { + *map = ret & BDRV_BLOCK_OFFSET_MASK; + } else { + ret &= ~BDRV_BLOCK_OFFSET_VALID; + } + return ret & ~BDRV_BLOCK_OFFSET_MASK; } int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset, * cluster is already marked as zero, or if it's unallocated and we * don't have a backing file. * - * TODO We might want to use bdrv_get_block_status(bs) here, but we're + * TODO We might want to use bdrv_block_status(bs) here, but we're * holding s->lock, so that doesn't work today. * * If full_discard is true, the sector should not read back as zeroes, diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) if (s->sector_next_status <= sector_num) { if (s->target_has_backing) { - ret = bdrv_get_block_status(blk_bs(s->src[src_cur]), - sector_num - src_cur_offset, - n, &n, NULL); + int64_t count = n * BDRV_SECTOR_SIZE; + + ret = bdrv_block_status(blk_bs(s->src[src_cur]), + (sector_num - src_cur_offset) * + BDRV_SECTOR_SIZE, + count, &count, NULL, NULL); + assert(ret < 0 || QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); + n = count >> BDRV_SECTOR_BITS; } else { ret = bdrv_get_block_status_above(blk_bs(s->src[src_cur]), NULL, sector_num - src_cur_offset, @@ -XXX,XX +XXX,XX @@ static void dump_map_entry(OutputFormat output_format, MapEntry *e, static int get_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, MapEntry *e) { - int64_t ret; + int ret; int depth; BlockDriverState *file; bool has_offset; - int nb_sectors = bytes >> BDRV_SECTOR_BITS; + int64_t map; - assert(bytes < INT_MAX); /* As an optimization, we could cache the current range of unallocated * clusters in each file of the chain, and avoid querying the same * range repeatedly. @@ -XXX,XX +XXX,XX @@ static int get_block_status(BlockDriverState *bs, int64_t offset, depth = 0; for (;;) { - ret = bdrv_get_block_status(bs, offset >> BDRV_SECTOR_BITS, nb_sectors, - &nb_sectors, &file); + ret = bdrv_block_status(bs, offset, bytes, &bytes, &map, &file); if (ret < 0) { return ret; } - assert(nb_sectors); + assert(bytes); if (ret & (BDRV_BLOCK_ZERO|BDRV_BLOCK_DATA)) { break; } @@ -XXX,XX +XXX,XX @@ static int get_block_status(BlockDriverState *bs, int64_t offset, *e = (MapEntry) { .start = offset, - .length = nb_sectors * BDRV_SECTOR_SIZE, + .length = bytes, .data = !!(ret & BDRV_BLOCK_DATA), .zero = !!(ret & BDRV_BLOCK_ZERO), - .offset = ret & BDRV_BLOCK_OFFSET_MASK, + .offset = map, .has_offset = has_offset, .depth = depth, .has_filename = file && has_offset, -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal function (no semantic change); and as with its public counterpart, rename to bdrv_co_block_status() and split the offset return, to make the compiler enforce that we catch all uses. For now, we assert that callers and the return value still use aligned data, but ultimately, this will be the function where we hand off to a byte-based driver callback, and will eventually need to add logic to ensure we round calls according to the driver's request_alignment then touch up the result handed back to the caller, to start permitting a caller to pass unaligned offsets. Note that we are now prepared to accepts 'bytes' larger than INT_MAX; this is okay as long as we clamp things internally before violating any 32-bit limits, and makes no difference to how a client will use the information (clients looping over the entire file must already be prepared for consecutive calls to return the same status, as drivers are already free to return shorter-than-maximal status due to any other convenient split points, such as when the L2 table crosses cluster boundaries in qcow2). Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 124 ++++++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 81 insertions(+), 43 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs, * BDRV_BLOCK_ZERO where possible; otherwise, the result may omit those * bits particularly if it allows for a larger value in 'pnum'. * - * If 'sector_num' is beyond the end of the disk image the return value is + * If 'offset' is beyond the end of the disk image the return value is * BDRV_BLOCK_EOF and 'pnum' is set to 0. * - * 'pnum' is set to the number of sectors (including and immediately following - * the specified sector) that are known to be in the same - * allocated/unallocated state. - * - * 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes + * 'bytes' is the max value 'pnum' should be set to. If bytes goes * beyond the end of the disk image it will be clamped; if 'pnum' is set to * the end of the image, then the returned value will include BDRV_BLOCK_EOF. * - * If returned value is positive, BDRV_BLOCK_OFFSET_VALID bit is set, and - * 'file' is non-NULL, then '*file' points to the BDS which the sector range - * is allocated in. + * 'pnum' is set to the number of bytes (including and immediately + * following the specified offset) that are easily known to be in the + * same allocated/unallocated state. Note that a second call starting + * at the original offset plus returned pnum may have the same status. + * The returned value is non-zero on success except at end-of-file. + * + * Returns negative errno on failure. Otherwise, if the + * BDRV_BLOCK_OFFSET_VALID bit is set, 'map' and 'file' (if non-NULL) are + * set to the host mapping and BDS corresponding to the guest offset. */ -static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, - bool want_zero, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) -{ - int64_t total_sectors; - int64_t n; - int64_t ret, ret2; +static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, + bool want_zero, + int64_t offset, int64_t bytes, + int64_t *pnum, int64_t *map, + BlockDriverState **file) +{ + int64_t total_size; + int64_t n; /* bytes */ + int64_t ret; + int64_t local_map = 0; BlockDriverState *local_file = NULL; + int count; /* sectors */ assert(pnum); *pnum = 0; - total_sectors = bdrv_nb_sectors(bs); - if (total_sectors < 0) { - ret = total_sectors; + total_size = bdrv_getlength(bs); + if (total_size < 0) { + ret = total_size; goto early_out; } - if (sector_num >= total_sectors) { + if (offset >= total_size) { ret = BDRV_BLOCK_EOF; goto early_out; } - if (!nb_sectors) { + if (!bytes) { ret = 0; goto early_out; } - n = total_sectors - sector_num; - if (n < nb_sectors) { - nb_sectors = n; + n = total_size - offset; + if (n < bytes) { + bytes = n; } if (!bs->drv->bdrv_co_get_block_status) { - *pnum = nb_sectors; + *pnum = bytes; ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED; - if (sector_num + nb_sectors == total_sectors) { + if (offset + bytes == total_size) { ret |= BDRV_BLOCK_EOF; } if (bs->drv->protocol_name) { - ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE); + ret |= BDRV_BLOCK_OFFSET_VALID; + local_map = offset; local_file = bs; } goto early_out; } bdrv_inc_in_flight(bs); - ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum, + /* + * TODO: Rather than require aligned offsets, we could instead + * round to the driver's request_alignment here, then touch up + * count afterwards back to the caller's expectations. + */ + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + /* + * The contract allows us to return pnum smaller than bytes, even + * if the next query would see the same status; we truncate the + * request to avoid overflowing the driver's 32-bit interface. + */ + bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); + ret = bs->drv->bdrv_co_get_block_status(bs, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, &count, &local_file); if (ret < 0) { - *pnum = 0; goto out; } + if (ret & BDRV_BLOCK_OFFSET_VALID) { + local_map = ret & BDRV_BLOCK_OFFSET_MASK; + } + *pnum = count * BDRV_SECTOR_SIZE; if (ret & BDRV_BLOCK_RAW) { assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); - ret = bdrv_co_get_block_status(local_file, want_zero, - ret >> BDRV_SECTOR_BITS, - *pnum, pnum, &local_file); + ret = bdrv_co_block_status(local_file, want_zero, local_map, + *pnum, pnum, &local_map, &local_file); + assert(ret < 0 || + QEMU_IS_ALIGNED(*pnum | local_map, BDRV_SECTOR_SIZE)); goto out; } @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, ret |= BDRV_BLOCK_ZERO; } else if (bs->backing) { BlockDriverState *bs2 = bs->backing->bs; - int64_t nb_sectors2 = bdrv_nb_sectors(bs2); + int64_t size2 = bdrv_getlength(bs2); - if (nb_sectors2 >= 0 && sector_num >= nb_sectors2) { + if (size2 >= 0 && offset >= size2) { ret |= BDRV_BLOCK_ZERO; } } @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, if (want_zero && local_file && local_file != bs && (ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) && (ret & BDRV_BLOCK_OFFSET_VALID)) { - int file_pnum; + int64_t file_pnum; + int ret2; - ret2 = bdrv_co_get_block_status(local_file, want_zero, - ret >> BDRV_SECTOR_BITS, - *pnum, &file_pnum, NULL); + ret2 = bdrv_co_block_status(local_file, want_zero, local_map, + *pnum, &file_pnum, NULL, NULL); if (ret2 >= 0) { /* Ignore errors. This is just providing extra information, it * is useful but not necessary. @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, out: bdrv_dec_in_flight(bs); - if (ret >= 0 && sector_num + *pnum == total_sectors) { + if (ret >= 0 && offset + *pnum == total_size) { ret |= BDRV_BLOCK_EOF; } early_out: if (file) { *file = local_file; } + if (map) { + *map = local_map; + } + if (ret >= 0) { + ret &= ~BDRV_BLOCK_OFFSET_MASK; + } else { + assert(INT_MIN <= ret); + } return ret; } @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, BlockDriverState *p; int64_t ret = 0; bool first = true; + int64_t map = 0; assert(bs != base); for (p = bs; p != base; p = backing_bs(p)) { - ret = bdrv_co_get_block_status(p, want_zero, sector_num, nb_sectors, - pnum, file); + int64_t count; + + ret = bdrv_co_block_status(p, want_zero, + sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, &count, + &map, file); if (ret < 0) { break; } + assert(QEMU_IS_ALIGNED(count | map, BDRV_SECTOR_SIZE)); + ret |= map; + *pnum = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { /* * Reading beyond the end of the file continues to read -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal type (no semantic change), and rename it to match the corresponding public function rename. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 56 ++++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 38 insertions(+), 18 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int bdrv_flush_all(void) } -typedef struct BdrvCoGetBlockStatusData { +typedef struct BdrvCoBlockStatusData { BlockDriverState *bs; BlockDriverState *base; bool want_zero; - int64_t sector_num; - int nb_sectors; - int *pnum; + int64_t offset; + int64_t bytes; + int64_t *pnum; + int64_t *map; BlockDriverState **file; - int64_t ret; + int ret; bool done; -} BdrvCoGetBlockStatusData; +} BdrvCoBlockStatusData; int64_t coroutine_fn bdrv_co_get_block_status_from_file(BlockDriverState *bs, int64_t sector_num, @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, /* Coroutine wrapper for bdrv_get_block_status_above() */ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) { - BdrvCoGetBlockStatusData *data = opaque; + BdrvCoBlockStatusData *data = opaque; + int n = 0; + int64_t ret; - data->ret = bdrv_co_get_block_status_above(data->bs, data->base, - data->want_zero, - data->sector_num, - data->nb_sectors, - data->pnum, - data->file); + ret = bdrv_co_get_block_status_above(data->bs, data->base, + data->want_zero, + data->offset >> BDRV_SECTOR_BITS, + data->bytes >> BDRV_SECTOR_BITS, + &n, + data->file); + if (ret < 0) { + assert(INT_MIN <= ret); + data->ret = ret; + } else { + *data->pnum = n * BDRV_SECTOR_SIZE; + *data->map = ret & BDRV_BLOCK_OFFSET_MASK; + data->ret = ret & ~BDRV_BLOCK_OFFSET_MASK; + } data->done = true; } @@ -XXX,XX +XXX,XX @@ static int64_t bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState **file) { Coroutine *co; - BdrvCoGetBlockStatusData data = { + int64_t n; + int64_t map; + BdrvCoBlockStatusData data = { .bs = bs, .base = base, .want_zero = want_zero, - .sector_num = sector_num, - .nb_sectors = nb_sectors, - .pnum = pnum, + .offset = sector_num * BDRV_SECTOR_SIZE, + .bytes = nb_sectors * BDRV_SECTOR_SIZE, + .pnum = &n, + .map = &map, .file = file, .done = false, }; @@ -XXX,XX +XXX,XX @@ static int64_t bdrv_common_block_status_above(BlockDriverState *bs, bdrv_coroutine_enter(bs, co); BDRV_POLL_WHILE(bs, !data.done); } - return data.ret; + if (data.ret < 0) { + *pnum = 0; + return data.ret; + } + assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); + *pnum = n >> BDRV_SECTOR_BITS; + return data.ret | map; } int64_t bdrv_get_block_status_above(BlockDriverState *bs, -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal function (no semantic change). Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 61 ++++++++++++++++++++++++++++++------------------------------- 1 file changed, 30 insertions(+), 31 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) * * See bdrv_co_get_block_status_above() for details. */ -static int64_t bdrv_common_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - bool want_zero, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +static int bdrv_common_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + bool want_zero, int64_t offset, + int64_t bytes, int64_t *pnum, + int64_t *map, + BlockDriverState **file) { Coroutine *co; - int64_t n; - int64_t map; BdrvCoBlockStatusData data = { .bs = bs, .base = base, .want_zero = want_zero, - .offset = sector_num * BDRV_SECTOR_SIZE, - .bytes = nb_sectors * BDRV_SECTOR_SIZE, - .pnum = &n, - .map = &map, + .offset = offset, + .bytes = bytes, + .pnum = pnum, + .map = map, .file = file, .done = false, }; @@ -XXX,XX +XXX,XX @@ static int64_t bdrv_common_block_status_above(BlockDriverState *bs, bdrv_coroutine_enter(bs, co); BDRV_POLL_WHILE(bs, !data.done); } - if (data.ret < 0) { - *pnum = 0; - return data.ret; - } - assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); - *pnum = n >> BDRV_SECTOR_BITS; - return data.ret | map; + return data.ret; } int64_t bdrv_get_block_status_above(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs, int nb_sectors, int *pnum, BlockDriverState **file) { - return bdrv_common_block_status_above(bs, base, true, sector_num, - nb_sectors, pnum, file); + int64_t ret; + int64_t n; + int64_t map; + + ret = bdrv_common_block_status_above(bs, base, true, + sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, + &n, &map, file); + if (ret < 0) { + *pnum = 0; + return ret; + } + assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); + *pnum = n >> BDRV_SECTOR_BITS; + return ret | map; } int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, @@ -XXX,XX +XXX,XX @@ int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum) { - int64_t ret; - int psectors; + int ret; + int64_t dummy; - assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE) && bytes < INT_MAX); - ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, - offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &psectors, + ret = bdrv_common_block_status_above(bs, backing_bs(bs), false, offset, + bytes, pnum ? pnum : &dummy, NULL, NULL); if (ret < 0) { return ret; } - if (pnum) { - *pnum = psectors * BDRV_SECTOR_SIZE; - } return !!(ret & BDRV_BLOCK_ALLOCATED); } -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually converting to byte-based interfaces, as they are easier to reason about than sector-based. Convert another internal type (no semantic change), and rename it to match the corresponding public function rename. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 68 ++++++++++++++++++++++---------------------------------------- 1 file changed, 24 insertions(+), 44 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ early_out: return ret; } -static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - bool want_zero, - int64_t sector_num, - int nb_sectors, - int *pnum, - BlockDriverState **file) +static int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs, + BlockDriverState *base, + bool want_zero, + int64_t offset, + int64_t bytes, + int64_t *pnum, + int64_t *map, + BlockDriverState **file) { BlockDriverState *p; - int64_t ret = 0; + int ret = 0; bool first = true; - int64_t map = 0; assert(bs != base); for (p = bs; p != base; p = backing_bs(p)) { - int64_t count; - - ret = bdrv_co_block_status(p, want_zero, - sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, &count, - &map, file); + ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, + file); if (ret < 0) { break; } - assert(QEMU_IS_ALIGNED(count | map, BDRV_SECTOR_SIZE)); - ret |= map; - *pnum = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ZERO && ret & BDRV_BLOCK_EOF && !first) { /* * Reading beyond the end of the file continues to read @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs, * unallocated length we learned from an earlier * iteration. */ - *pnum = nb_sectors; + *pnum = bytes; } if (ret & (BDRV_BLOCK_ZERO | BDRV_BLOCK_DATA)) { break; } - /* [sector_num, pnum] unallocated on this layer, which could be only - * the first part of [sector_num, nb_sectors]. */ - nb_sectors = MIN(nb_sectors, *pnum); + /* [offset, pnum] unallocated on this layer, which could be only + * the first part of [offset, bytes]. */ + bytes = MIN(bytes, *pnum); first = false; } return ret; } /* Coroutine wrapper for bdrv_get_block_status_above() */ -static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque) +static void coroutine_fn bdrv_block_status_above_co_entry(void *opaque) { BdrvCoBlockStatusData *data = opaque; - int n = 0; - int64_t ret; - ret = bdrv_co_get_block_status_above(data->bs, data->base, - data->want_zero, - data->offset >> BDRV_SECTOR_BITS, - data->bytes >> BDRV_SECTOR_BITS, - &n, - data->file); - if (ret < 0) { - assert(INT_MIN <= ret); - data->ret = ret; - } else { - *data->pnum = n * BDRV_SECTOR_SIZE; - *data->map = ret & BDRV_BLOCK_OFFSET_MASK; - data->ret = ret & ~BDRV_BLOCK_OFFSET_MASK; - } + data->ret = bdrv_co_block_status_above(data->bs, data->base, + data->want_zero, + data->offset, data->bytes, + data->pnum, data->map, data->file); data->done = true; } /* - * Synchronous wrapper around bdrv_co_get_block_status_above(). + * Synchronous wrapper around bdrv_co_block_status_above(). * - * See bdrv_co_get_block_status_above() for details. + * See bdrv_co_block_status_above() for details. */ static int bdrv_common_block_status_above(BlockDriverState *bs, BlockDriverState *base, @@ -XXX,XX +XXX,XX @@ static int bdrv_common_block_status_above(BlockDriverState *bs, if (qemu_in_coroutine()) { /* Fast-path if already in coroutine context */ - bdrv_get_block_status_above_co_entry(&data); + bdrv_block_status_above_co_entry(&data); } else { - co = qemu_coroutine_create(bdrv_get_block_status_above_co_entry, - &data); + co = qemu_coroutine_create(bdrv_block_status_above_co_entry, &data); bdrv_coroutine_enter(bs, co); BDRV_POLL_WHILE(bs, !data.done); } -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are gradually moving away from sector-based interfaces, towards byte-based. In the common case, allocation is unlikely to ever use values that are not naturally sector-aligned, but it is possible that byte-based values will let us be more precise about allocation at the end of an unaligned file that can do byte-based access. Changing the name of the function from bdrv_get_block_status_above() to bdrv_block_status_above() ensures that the compiler enforces that all callers are updated. Likewise, since it a byte interface allows an offset mapping that might not be sector aligned, split the mapping out of the return value and into a pass-by-reference parameter. For now, the io.c layer still assert()s that all uses are sector-aligned, but that can be relaxed when a later patch implements byte-based block status in the drivers. For the most part this patch is just the addition of scaling at the callers followed by inverse scaling at bdrv_block_status(), plus updates for the new split return interface. But some code, particularly bdrv_block_status(), gets a lot simpler because it no longer has to mess with sectors. Likewise, mirror code no longer computes s->granularity >> BDRV_SECTOR_BITS, and can therefore drop an assertion about alignment because the loop no longer depends on alignment (never mind that we don't really have a driver that reports sub-sector alignments, so it's not really possible to test the effect of sub-sector mirroring). Fix a neighboring assertion to use is_power_of_2 while there. For ease of review, bdrv_get_block_status() was tackled separately. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 8 +++----- block/io.c | 55 ++++++++------------------------------------------- block/mirror.c | 18 ++++++----------- block/qcow2.c | 30 +++++++++++----------------- qemu-img.c | 49 +++++++++++++++++++++++++-------------------- 5 files changed, 57 insertions(+), 103 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file); -int64_t bdrv_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file); +int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, + int64_t offset, int64_t bytes, int64_t *pnum, + int64_t *map, BlockDriverState **file); int bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum); int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs, return ret; } -/* Coroutine wrapper for bdrv_get_block_status_above() */ +/* Coroutine wrapper for bdrv_block_status_above() */ static void coroutine_fn bdrv_block_status_above_co_entry(void *opaque) { BdrvCoBlockStatusData *data = opaque; @@ -XXX,XX +XXX,XX @@ static int bdrv_common_block_status_above(BlockDriverState *bs, return data.ret; } -int64_t bdrv_get_block_status_above(BlockDriverState *bs, - BlockDriverState *base, - int64_t sector_num, - int nb_sectors, int *pnum, - BlockDriverState **file) +int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, + int64_t offset, int64_t bytes, int64_t *pnum, + int64_t *map, BlockDriverState **file) { - int64_t ret; - int64_t n; - int64_t map; - - ret = bdrv_common_block_status_above(bs, base, true, - sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, - &n, &map, file); - if (ret < 0) { - *pnum = 0; - return ret; - } - assert(QEMU_IS_ALIGNED(n | map, BDRV_SECTOR_SIZE)); - *pnum = n >> BDRV_SECTOR_BITS; - return ret | map; + return bdrv_common_block_status_above(bs, base, true, offset, bytes, + pnum, map, file); } int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file) { - int64_t ret; - int n; - - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - assert(pnum); - /* - * The contract allows us to return pnum smaller than bytes, even - * if the next query would see the same status; we truncate the - * request to avoid overflowing the driver's 32-bit interface. - */ - bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); - ret = bdrv_get_block_status_above(bs, backing_bs(bs), - offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &n, file); - if (ret < 0) { - assert(INT_MIN <= ret); - *pnum = 0; - return ret; - } - *pnum = n * BDRV_SECTOR_SIZE; - if (map) { - *map = ret & BDRV_BLOCK_OFFSET_MASK; - } else { - ret &= ~BDRV_BLOCK_OFFSET_VALID; - } - return ret & ~BDRV_BLOCK_OFFSET_MASK; + return bdrv_block_status_above(bs, backing_bs(bs), + offset, bytes, pnum, map, file); } int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) uint64_t delay_ns = 0; /* At least the first dirty chunk is mirrored in one iteration. */ int nb_chunks = 1; - int sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS; bool write_zeroes_ok = bdrv_can_write_zeroes_with_unmap(blk_bs(s->target)); int max_io_bytes = MAX(s->buf_size / MAX_IN_FLIGHT, MAX_IO_BYTES); @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) } /* Clear dirty bits before querying the block status, because - * calling bdrv_get_block_status_above could yield - if some blocks are + * calling bdrv_block_status_above could yield - if some blocks are * marked dirty in this window, we need to know. */ bdrv_reset_dirty_bitmap_locked(s->dirty_bitmap, offset, @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) bitmap_set(s->in_flight_bitmap, offset / s->granularity, nb_chunks); while (nb_chunks > 0 && offset < s->bdev_length) { - int64_t ret; - int io_sectors; + int ret; int64_t io_bytes; int64_t io_bytes_acct; enum MirrorMethod { @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) } mirror_method = MIRROR_METHOD_COPY; assert(!(offset % s->granularity)); - ret = bdrv_get_block_status_above(source, NULL, - offset >> BDRV_SECTOR_BITS, - nb_chunks * sectors_per_chunk, - &io_sectors, NULL); - io_bytes = io_sectors * BDRV_SECTOR_SIZE; + ret = bdrv_block_status_above(source, NULL, offset, + nb_chunks * s->granularity, + &io_bytes, NULL, NULL); if (ret < 0) { io_bytes = MIN(nb_chunks * s->granularity, max_io_bytes); } else if (ret & BDRV_BLOCK_DATA) { @@ -XXX,XX +XXX,XX @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs, granularity = bdrv_get_default_bitmap_granularity(target); } - assert ((granularity & (granularity - 1)) == 0); - /* Granularity must be large enough for sector-based dirty bitmap */ - assert(granularity >= BDRV_SECTOR_SIZE); + assert(is_power_of_2(granularity)); if (buf_size < 0) { error_setg(errp, "Invalid parameter 'buf-size'"); diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ finish: static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) { - int nr; - int64_t res; + int64_t nr; + int res; int64_t start; /* TODO: Widening to sector boundaries should only be needed as @@ -XXX,XX +XXX,XX @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) if (!bytes) { return true; } - res = bdrv_get_block_status_above(bs, NULL, start >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &nr, NULL); - return res >= 0 && (res & BDRV_BLOCK_ZERO) && - nr * BDRV_SECTOR_SIZE == bytes; + res = bdrv_block_status_above(bs, NULL, start, bytes, &nr, NULL, NULL); + return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; } static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, required = virtual_size; } else { int64_t offset; - int pnum = 0; + int64_t pnum = 0; - for (offset = 0; offset < ssize; - offset += pnum * BDRV_SECTOR_SIZE) { - int nb_sectors = MIN(ssize - offset, - BDRV_REQUEST_MAX_BYTES) / BDRV_SECTOR_SIZE; - int64_t ret; + for (offset = 0; offset < ssize; offset += pnum) { + int ret; - ret = bdrv_get_block_status_above(in_bs, NULL, - offset >> BDRV_SECTOR_BITS, - nb_sectors, &pnum, NULL); + ret = bdrv_block_status_above(in_bs, NULL, offset, + ssize - offset, &pnum, NULL, + NULL); if (ret < 0) { error_setg_errno(&local_err, -ret, "Unable to get block status"); @@ -XXX,XX +XXX,XX @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, } else if ((ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED)) == (BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED)) { /* Extend pnum to end of cluster for next iteration */ - pnum = (ROUND_UP(offset + pnum * BDRV_SECTOR_SIZE, - cluster_size) - offset) >> BDRV_SECTOR_BITS; + pnum = ROUND_UP(offset + pnum, cluster_size) - offset; /* Count clusters we've seen */ - required += offset % cluster_size + pnum * BDRV_SECTOR_SIZE; + required += offset % cluster_size + pnum; } } } diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) BlockDriverState *bs1, *bs2; int64_t total_sectors1, total_sectors2; uint8_t *buf1 = NULL, *buf2 = NULL; - int pnum1, pnum2; + int64_t pnum1, pnum2; int allocated1, allocated2; int ret = 0; /* return value - 0 Ident, 1 Different, >1 Error */ bool progress = false, quiet = false, strict = false; @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } for (;;) { - int64_t status1, status2; + int status1, status2; nb_sectors = sectors_to_process(total_sectors, sector_num); if (nb_sectors <= 0) { break; } - status1 = bdrv_get_block_status_above(bs1, NULL, sector_num, - total_sectors1 - sector_num, - &pnum1, NULL); + status1 = bdrv_block_status_above(bs1, NULL, + sector_num * BDRV_SECTOR_SIZE, + (total_sectors1 - sector_num) * + BDRV_SECTOR_SIZE, + &pnum1, NULL, NULL); if (status1 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename1); @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } allocated1 = status1 & BDRV_BLOCK_ALLOCATED; - status2 = bdrv_get_block_status_above(bs2, NULL, sector_num, - total_sectors2 - sector_num, - &pnum2, NULL); + status2 = bdrv_block_status_above(bs2, NULL, + sector_num * BDRV_SECTOR_SIZE, + (total_sectors2 - sector_num) * + BDRV_SECTOR_SIZE, + &pnum2, NULL, NULL); if (status2 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename2); goto out; } allocated2 = status2 & BDRV_BLOCK_ALLOCATED; + /* TODO: Relax this once comparison is byte-based, and we no longer + * have to worry about sector alignment */ + assert(QEMU_IS_ALIGNED(pnum1 | pnum2, BDRV_SECTOR_SIZE)); if (pnum1) { - nb_sectors = MIN(nb_sectors, pnum1); + nb_sectors = MIN(nb_sectors, pnum1 >> BDRV_SECTOR_BITS); } if (pnum2) { - nb_sectors = MIN(nb_sectors, pnum2); + nb_sectors = MIN(nb_sectors, pnum2 >> BDRV_SECTOR_BITS); } if (strict) { - if ((status1 & ~BDRV_BLOCK_OFFSET_MASK) != - (status2 & ~BDRV_BLOCK_OFFSET_MASK)) { + if (status1 != status2) { ret = 1; qprintf(quiet, "Strict mode: Offset %" PRId64 " block status mismatch!\n", @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } } if ((status1 & BDRV_BLOCK_ZERO) && (status2 & BDRV_BLOCK_ZERO)) { - nb_sectors = MIN(pnum1, pnum2); + nb_sectors = DIV_ROUND_UP(MIN(pnum1, pnum2), BDRV_SECTOR_SIZE); } else if (allocated1 == allocated2) { if (allocated1) { ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, @@ -XXX,XX +XXX,XX @@ static void convert_select_part(ImgConvertState *s, int64_t sector_num, static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) { - int64_t ret, src_cur_offset; - int n, src_cur; + int64_t src_cur_offset; + int ret, n, src_cur; convert_select_part(s, sector_num, &src_cur, &src_cur_offset); @@ -XXX,XX +XXX,XX @@ static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num) n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS); if (s->sector_next_status <= sector_num) { + int64_t count = n * BDRV_SECTOR_SIZE; + if (s->target_has_backing) { - int64_t count = n * BDRV_SECTOR_SIZE; ret = bdrv_block_status(blk_bs(s->src[src_cur]), (sector_num - src_cur_offset) * BDRV_SECTOR_SIZE, count, &count, NULL, NULL); - assert(ret < 0 || QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); - n = count >> BDRV_SECTOR_BITS; } else { - ret = bdrv_get_block_status_above(blk_bs(s->src[src_cur]), NULL, - sector_num - src_cur_offset, - n, &n, NULL); + ret = bdrv_block_status_above(blk_bs(s->src[src_cur]), NULL, + (sector_num - src_cur_offset) * + BDRV_SECTOR_SIZE, + count, &count, NULL, NULL); } if (ret < 0) { return ret; } + n = DIV_ROUND_UP(count, BDRV_SECTOR_SIZE); if (ret & BDRV_BLOCK_ZERO) { s->status = BLK_ZERO; -- 2.13.6 From: Eric Blake <eblake@redhat.com> As long as we are querying the status for a chunk smaller than the known image size, we are guaranteed that a successful return will have set pnum to a non-zero size (pnum is zero only for queries beyond the end of the file). Use that to slightly simplify the calculation of the current chunk size being compared. Likewise, we don't have to shrink the amount of data operated on until we know we have to read the file, and therefore have to fit in the bounds of our buffer. Also, note that 'total_sectors_over' is equivalent to 'progress_base'. With these changes in place, sectors_to_process() is now dead code, and can be removed. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 38 +++++++++++--------------------------- 1 file changed, 11 insertions(+), 27 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int64_t sectors_to_bytes(int64_t sectors) return sectors << BDRV_SECTOR_BITS; } -static int64_t sectors_to_process(int64_t total, int64_t from) -{ - return MIN(total - from, IO_BUF_SIZE >> BDRV_SECTOR_BITS); -} - /* * Check if passed sectors are empty (not allocated or contain only 0 bytes) * @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) goto out; } - for (;;) { + while (sector_num < total_sectors) { int status1, status2; - nb_sectors = sectors_to_process(total_sectors, sector_num); - if (nb_sectors <= 0) { - break; - } status1 = bdrv_block_status_above(bs1, NULL, sector_num * BDRV_SECTOR_SIZE, (total_sectors1 - sector_num) * @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) /* TODO: Relax this once comparison is byte-based, and we no longer * have to worry about sector alignment */ assert(QEMU_IS_ALIGNED(pnum1 | pnum2, BDRV_SECTOR_SIZE)); - if (pnum1) { - nb_sectors = MIN(nb_sectors, pnum1 >> BDRV_SECTOR_BITS); - } - if (pnum2) { - nb_sectors = MIN(nb_sectors, pnum2 >> BDRV_SECTOR_BITS); - } + + assert(pnum1 && pnum2); + nb_sectors = MIN(pnum1, pnum2) >> BDRV_SECTOR_BITS; if (strict) { if (status1 != status2) { @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } } if ((status1 & BDRV_BLOCK_ZERO) && (status2 & BDRV_BLOCK_ZERO)) { - nb_sectors = DIV_ROUND_UP(MIN(pnum1, pnum2), BDRV_SECTOR_SIZE); + /* nothing to do */ } else if (allocated1 == allocated2) { if (allocated1) { + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, nb_sectors << BDRV_SECTOR_BITS); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } } } else { - + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); if (allocated1) { ret = check_empty_sectors(blk1, sector_num, nb_sectors, filename1, buf1, quiet); @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) if (total_sectors1 != total_sectors2) { BlockBackend *blk_over; - int64_t total_sectors_over; const char *filename_over; qprintf(quiet, "Warning: Image size mismatch!\n"); if (total_sectors1 > total_sectors2) { - total_sectors_over = total_sectors1; blk_over = blk1; filename_over = filename1; } else { - total_sectors_over = total_sectors2; blk_over = blk2; filename_over = filename2; } - for (;;) { + while (sector_num < progress_base) { int64_t count; - nb_sectors = sectors_to_process(total_sectors_over, sector_num); - if (nb_sectors <= 0) { - break; - } ret = bdrv_is_allocated_above(blk_bs(blk_over), NULL, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + (progress_base - sector_num) * + BDRV_SECTOR_SIZE, &count); if (ret < 0) { ret = 3; @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); nb_sectors = count >> BDRV_SECTOR_BITS; if (ret) { + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = check_empty_sectors(blk_over, sector_num, nb_sectors, filename_over, buf1, quiet); if (ret) { -- 2.13.6 From: Eric Blake <eblake@redhat.com> Compare the following images with all-zero contents: $ truncate --size 1M A $ qemu-img create -f qcow2 -o preallocation=off B 1G $ qemu-img create -f qcow2 -o preallocation=metadata C 1G On my machine, the difference is noticeable for pre-patch speeds, with more than an order of magnitude in difference caused by the choice of preallocation in the qcow2 file: $ time ./qemu-img compare -f raw -F qcow2 A B Warning: Image size mismatch! Images are identical. real 0m0.014s user 0m0.007s sys 0m0.007s $ time ./qemu-img compare -f raw -F qcow2 A C Warning: Image size mismatch! Images are identical. real 0m0.341s user 0m0.144s sys 0m0.188s Why? Because bdrv_is_allocated() returns false for image B but true for image C, throwing away the fact that both images know via lseek(SEEK_HOLE) that the entire image still reads as zero. From there, qemu-img ends up calling bdrv_pread() for every byte of the tail, instead of quickly looking for the next allocation. The solution: use block_status instead of is_allocated, giving: $ time ./qemu-img compare -f raw -F qcow2 A C Warning: Image size mismatch! Images are identical. real 0m0.014s user 0m0.011s sys 0m0.003s which is on par with the speeds for no pre-allocation. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) while (sector_num < progress_base) { int64_t count; - ret = bdrv_is_allocated_above(blk_bs(blk_over), NULL, + ret = bdrv_block_status_above(blk_bs(blk_over), NULL, sector_num * BDRV_SECTOR_SIZE, (progress_base - sector_num) * BDRV_SECTOR_SIZE, - &count); + &count, NULL, NULL); if (ret < 0) { ret = 3; error_report("Sector allocation test failed for %s", @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) goto out; } - /* TODO relax this once bdrv_is_allocated_above does not enforce + /* TODO relax this once bdrv_block_status_above does not enforce * sector alignment */ assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); nb_sectors = count >> BDRV_SECTOR_BITS; - if (ret) { + if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) { nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = check_empty_sectors(blk_over, sector_num, nb_sectors, filename_over, buf1, quiet); -- 2.13.6 From: Eric Blake <eblake@redhat.com> During 'qemu-img compare', when we are checking that an allocated portion of one file is all zeros, we don't need to waste time computing how many additional sectors after the first non-zero byte are also non-zero. Create a new helper find_nonzero() to do the check for a first non-zero sector, and rebase check_empty_sectors() to use it. The new interface intentionally uses bytes in its interface, even though it still crawls the buffer a sector at a time; it is robust to a partial sector at the end of the buffer. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ done: } /* + * Returns -1 if 'buf' contains only zeroes, otherwise the byte index + * of the first sector boundary within buf where the sector contains a + * non-zero byte. This function is robust to a buffer that is not + * sector-aligned. + */ +static int64_t find_nonzero(const uint8_t *buf, int64_t n) +{ + int64_t i; + int64_t end = QEMU_ALIGN_DOWN(n, BDRV_SECTOR_SIZE); + + for (i = 0; i < end; i += BDRV_SECTOR_SIZE) { + if (!buffer_is_zero(buf + i, BDRV_SECTOR_SIZE)) { + return i; + } + } + if (i < n && !buffer_is_zero(buf + i, n - end)) { + return i; + } + return -1; +} + +/* * Returns true iff the first sector pointed to by 'buf' contains at least * a non-NUL byte. * @@ -XXX,XX +XXX,XX @@ static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, int sect_count, const char *filename, uint8_t *buffer, bool quiet) { - int pnum, ret = 0; + int ret = 0; + int64_t idx; + ret = blk_pread(blk, sect_num << BDRV_SECTOR_BITS, buffer, sect_count << BDRV_SECTOR_BITS); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, sectors_to_bytes(sect_num), filename, strerror(-ret)); return ret; } - ret = is_allocated_sectors(buffer, sect_count, &pnum); - if (ret || pnum != sect_count) { + idx = find_nonzero(buffer, sect_count * BDRV_SECTOR_SIZE); + if (idx >= 0) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes(ret ? sect_num : sect_num + pnum)); + sectors_to_bytes(sect_num) + idx); return 1; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> If a read error is encountered during 'qemu-img compare', we were printing the "Error while reading offset ..." message twice; this was because our helper function was awkward, printing output on some but not all paths. Fix it to consistently report errors on all paths, so that the callers do not risk a redundant message, and update the testsuite for the improved output. Further simplify the code by hoisting the conversion from an error message to an exit code into the helper function, rather than repeating that logic at all callers (yes, the helper function is now less generic, but it's a net win in lines of code). Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 19 +++++-------------- tests/qemu-iotests/074.out | 2 -- 2 files changed, 5 insertions(+), 16 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int64_t sectors_to_bytes(int64_t sectors) /* * Check if passed sectors are empty (not allocated or contain only 0 bytes) * - * Returns 0 in case sectors are filled with 0, 1 if sectors contain non-zero - * data and negative value on error. + * Intended for use by 'qemu-img compare': Returns 0 in case sectors are + * filled with 0, 1 if sectors contain non-zero data (this is a comparison + * failure), and 4 on error (the exit status for read errors), after emitting + * an error message. * * @param blk: BlockBackend for the image * @param sect_num: Number of first sector to check @@ -XXX,XX +XXX,XX @@ static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", sectors_to_bytes(sect_num), filename, strerror(-ret)); - return ret; + return 4; } idx = find_nonzero(buffer, sect_count * BDRV_SECTOR_SIZE); if (idx >= 0) { @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) filename2, buf1, quiet); } if (ret) { - if (ret < 0) { - error_report("Error while reading offset %" PRId64 ": %s", - sectors_to_bytes(sector_num), strerror(-ret)); - ret = 4; - } goto out; } } @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) ret = check_empty_sectors(blk_over, sector_num, nb_sectors, filename_over, buf1, quiet); if (ret) { - if (ret < 0) { - error_report("Error while reading offset %" PRId64 - " of %s: %s", sectors_to_bytes(sector_num), - filename_over, strerror(-ret)); - ret = 4; - } goto out; } } diff --git a/tests/qemu-iotests/074.out b/tests/qemu-iotests/074.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/074.out +++ b/tests/qemu-iotests/074.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 wrote 512/512 bytes at offset 512 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-img: Error while reading offset 0 of blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error -qemu-img: Error while reading offset 0: Input/output error 4 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824 Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=0 @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.2', fmt=IMGFMT size=0 wrote 512/512 bytes at offset 512 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qemu-img: Error while reading offset 0 of blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error -qemu-img: Error while reading offset 0 of blkdebug:TEST_DIR/blkdebug.conf:TEST_DIR/t.IMGFMT: Input/output error Warning: Image size mismatch! 4 Cleanup -- 2.13.6 From: Eric Blake <eblake@redhat.com> Continue on the quest to make more things byte-based instead of sector-based. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int64_t sectors_to_bytes(int64_t sectors) * an error message. * * @param blk: BlockBackend for the image - * @param sect_num: Number of first sector to check - * @param sect_count: Number of sectors to check + * @param offset: Starting offset to check + * @param bytes: Number of bytes to check * @param filename: Name of disk file we are checking (logging purpose) * @param buffer: Allocated buffer for storing read data * @param quiet: Flag for quiet mode */ -static int check_empty_sectors(BlockBackend *blk, int64_t sect_num, - int sect_count, const char *filename, +static int check_empty_sectors(BlockBackend *blk, int64_t offset, + int64_t bytes, const char *filename, uint8_t *buffer, bool quiet) { int ret = 0; int64_t idx; - ret = blk_pread(blk, sect_num << BDRV_SECTOR_BITS, buffer, - sect_count << BDRV_SECTOR_BITS); + ret = blk_pread(blk, offset, buffer, bytes); if (ret < 0) { error_report("Error while reading offset %" PRId64 " of %s: %s", - sectors_to_bytes(sect_num), filename, strerror(-ret)); + offset, filename, strerror(-ret)); return 4; } - idx = find_nonzero(buffer, sect_count * BDRV_SECTOR_SIZE); + idx = find_nonzero(buffer, bytes); if (idx >= 0) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes(sect_num) + idx); + offset + idx); return 1; } @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } else { nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); if (allocated1) { - ret = check_empty_sectors(blk1, sector_num, nb_sectors, + ret = check_empty_sectors(blk1, sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, filename1, buf1, quiet); } else { - ret = check_empty_sectors(blk2, sector_num, nb_sectors, + ret = check_empty_sectors(blk2, sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, filename2, buf1, quiet); } if (ret) { @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) nb_sectors = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) { nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); - ret = check_empty_sectors(blk_over, sector_num, nb_sectors, + ret = check_empty_sectors(blk_over, + sector_num * BDRV_SECTOR_SIZE, + nb_sectors * BDRV_SECTOR_SIZE, filename_over, buf1, quiet); if (ret) { goto out; -- 2.13.6 From: Eric Blake <eblake@redhat.com> In the continuing quest to make more things byte-based, change compare_sectors(), renaming it to compare_buffers() in the process. Note that one caller (qemu-img compare) only cares about the first difference, while the other (qemu-img rebase) cares about how many consecutive sectors have the same equal/different status; however, this patch does not bother to micro-optimize the compare case to avoid the comparisons of sectors beyond the first mismatch. Both callers are always passing valid buffers in, so the initial check for buffer size can be turned into an assertion. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 55 +++++++++++++++++++++++++++---------------------------- 1 file changed, 27 insertions(+), 28 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int is_allocated_sectors_min(const uint8_t *buf, int n, int *pnum, } /* - * Compares two buffers sector by sector. Returns 0 if the first sector of both - * buffers matches, non-zero otherwise. + * Compares two buffers sector by sector. Returns 0 if the first + * sector of each buffer matches, non-zero otherwise. * - * pnum is set to the number of sectors (including and immediately following - * the first one) that are known to have the same comparison result + * pnum is set to the sector-aligned size of the buffer prefix that + * has the same matching status as the first sector. */ -static int compare_sectors(const uint8_t *buf1, const uint8_t *buf2, int n, - int *pnum) +static int compare_buffers(const uint8_t *buf1, const uint8_t *buf2, + int64_t bytes, int64_t *pnum) { bool res; - int i; + int64_t i = MIN(bytes, BDRV_SECTOR_SIZE); - if (n <= 0) { - *pnum = 0; - return 0; - } + assert(bytes > 0); - res = !!memcmp(buf1, buf2, 512); - for(i = 1; i < n; i++) { - buf1 += 512; - buf2 += 512; + res = !!memcmp(buf1, buf2, i); + while (i < bytes) { + int64_t len = MIN(bytes - i, BDRV_SECTOR_SIZE); - if (!!memcmp(buf1, buf2, 512) != res) { + if (!!memcmp(buf1 + i, buf2 + i, len) != res) { break; } + i += len; } *pnum = i; @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) int64_t total_sectors; int64_t sector_num = 0; int64_t nb_sectors; - int c, pnum; + int c; uint64_t progress_base; bool image_opts = false; bool force_share = false; @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) /* nothing to do */ } else if (allocated1 == allocated2) { if (allocated1) { + int64_t pnum; + nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, nb_sectors << BDRV_SECTOR_BITS); @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) ret = 4; goto out; } - ret = compare_sectors(buf1, buf2, nb_sectors, &pnum); - if (ret || pnum != nb_sectors) { + ret = compare_buffers(buf1, buf2, + nb_sectors * BDRV_SECTOR_SIZE, &pnum); + if (ret || pnum != nb_sectors * BDRV_SECTOR_SIZE) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes( - ret ? sector_num : sector_num + pnum)); + sectors_to_bytes(sector_num) + (ret ? 0 : pnum)); ret = 1; goto out; } @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) /* If they differ, we need to write to the COW file */ uint64_t written = 0; - while (written < n) { - int pnum; + while (written < n * BDRV_SECTOR_SIZE) { + int64_t pnum; - if (compare_sectors(buf_old + written * 512, - buf_new + written * 512, n - written, &pnum)) + if (compare_buffers(buf_old + written, + buf_new + written, + n * BDRV_SECTOR_SIZE - written, &pnum)) { ret = blk_pwrite(blk, - (sector + written) << BDRV_SECTOR_BITS, - buf_old + written * 512, - pnum << BDRV_SECTOR_BITS, 0); + (sector << BDRV_SECTOR_BITS) + written, + buf_old + written, pnum, 0); if (ret < 0) { error_report("Error while writing to COW image: %s", strerror(-ret)); -- 2.13.6 From: Eric Blake <eblake@redhat.com> In the continuing quest to make more things byte-based, change the internal iteration of img_rebase(). We can finally drop the TODO assertion added earlier, now that the entire algorithm is byte-based and no longer has to shift from bytes to sectors. Most of the change is mechanical ('num_sectors' becomes 'size', 'sector' becomes 'offset', 'n' goes from sectors to bytes); some of it is also a cleanup (use of MIN() instead of open-coding, loss of variable 'count' added earlier in commit d6a644bb). Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 84 +++++++++++++++++++++++++------------------------------------- 1 file changed, 34 insertions(+), 50 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) * the image is the same as the original one at any time. */ if (!unsafe) { - int64_t num_sectors; - int64_t old_backing_num_sectors; - int64_t new_backing_num_sectors = 0; - uint64_t sector; - int n; - int64_t count; + int64_t size; + int64_t old_backing_size; + int64_t new_backing_size = 0; + uint64_t offset; + int64_t n; float local_progress = 0; buf_old = blk_blockalign(blk, IO_BUF_SIZE); buf_new = blk_blockalign(blk, IO_BUF_SIZE); - num_sectors = blk_nb_sectors(blk); - if (num_sectors < 0) { + size = blk_getlength(blk); + if (size < 0) { error_report("Could not get size of '%s': %s", - filename, strerror(-num_sectors)); + filename, strerror(-size)); ret = -1; goto out; } - old_backing_num_sectors = blk_nb_sectors(blk_old_backing); - if (old_backing_num_sectors < 0) { + old_backing_size = blk_getlength(blk_old_backing); + if (old_backing_size < 0) { char backing_name[PATH_MAX]; bdrv_get_backing_filename(bs, backing_name, sizeof(backing_name)); error_report("Could not get size of '%s': %s", - backing_name, strerror(-old_backing_num_sectors)); + backing_name, strerror(-old_backing_size)); ret = -1; goto out; } if (blk_new_backing) { - new_backing_num_sectors = blk_nb_sectors(blk_new_backing); - if (new_backing_num_sectors < 0) { + new_backing_size = blk_getlength(blk_new_backing); + if (new_backing_size < 0) { error_report("Could not get size of '%s': %s", - out_baseimg, strerror(-new_backing_num_sectors)); + out_baseimg, strerror(-new_backing_size)); ret = -1; goto out; } } - if (num_sectors != 0) { - local_progress = (float)100 / - (num_sectors / MIN(num_sectors, IO_BUF_SIZE / 512)); + if (size != 0) { + local_progress = (float)100 / (size / MIN(size, IO_BUF_SIZE)); } - for (sector = 0; sector < num_sectors; sector += n) { - - /* How many sectors can we handle with the next read? */ - if (sector + (IO_BUF_SIZE / 512) <= num_sectors) { - n = (IO_BUF_SIZE / 512); - } else { - n = num_sectors - sector; - } + for (offset = 0; offset < size; offset += n) { + /* How many bytes can we handle with the next read? */ + n = MIN(IO_BUF_SIZE, size - offset); /* If the cluster is allocated, we don't need to take action */ - ret = bdrv_is_allocated(bs, sector << BDRV_SECTOR_BITS, - n << BDRV_SECTOR_BITS, &count); + ret = bdrv_is_allocated(bs, offset, n, &n); if (ret < 0) { error_report("error while reading image metadata: %s", strerror(-ret)); goto out; } - /* TODO relax this once bdrv_is_allocated does not enforce - * sector alignment */ - assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); - n = count >> BDRV_SECTOR_BITS; if (ret) { continue; } @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) * Read old and new backing file and take into consideration that * backing files may be smaller than the COW image. */ - if (sector >= old_backing_num_sectors) { - memset(buf_old, 0, n * BDRV_SECTOR_SIZE); + if (offset >= old_backing_size) { + memset(buf_old, 0, n); } else { - if (sector + n > old_backing_num_sectors) { - n = old_backing_num_sectors - sector; + if (offset + n > old_backing_size) { + n = old_backing_size - offset; } - ret = blk_pread(blk_old_backing, sector << BDRV_SECTOR_BITS, - buf_old, n << BDRV_SECTOR_BITS); + ret = blk_pread(blk_old_backing, offset, buf_old, n); if (ret < 0) { error_report("error while reading from old backing file"); goto out; } } - if (sector >= new_backing_num_sectors || !blk_new_backing) { - memset(buf_new, 0, n * BDRV_SECTOR_SIZE); + if (offset >= new_backing_size || !blk_new_backing) { + memset(buf_new, 0, n); } else { - if (sector + n > new_backing_num_sectors) { - n = new_backing_num_sectors - sector; + if (offset + n > new_backing_size) { + n = new_backing_size - offset; } - ret = blk_pread(blk_new_backing, sector << BDRV_SECTOR_BITS, - buf_new, n << BDRV_SECTOR_BITS); + ret = blk_pread(blk_new_backing, offset, buf_new, n); if (ret < 0) { error_report("error while reading from new backing file"); goto out; @@ -XXX,XX +XXX,XX @@ static int img_rebase(int argc, char **argv) /* If they differ, we need to write to the COW file */ uint64_t written = 0; - while (written < n * BDRV_SECTOR_SIZE) { + while (written < n) { int64_t pnum; - if (compare_buffers(buf_old + written, - buf_new + written, - n * BDRV_SECTOR_SIZE - written, &pnum)) + if (compare_buffers(buf_old + written, buf_new + written, + n - written, &pnum)) { - ret = blk_pwrite(blk, - (sector << BDRV_SECTOR_BITS) + written, + ret = blk_pwrite(blk, offset + written, buf_old + written, pnum, 0); if (ret < 0) { error_report("Error while writing to COW image: %s", -- 2.13.6 From: Eric Blake <eblake@redhat.com> In the continuing quest to make more things byte-based, change the internal iteration of img_compare(). We can finally drop the TODO assertions added earlier, now that the entire algorithm is byte-based and no longer has to shift from bytes to sectors. Most of the change is mechanical ('total_sectors' becomes 'total_size', 'sector_num' becomes 'offset', 'nb_sectors' becomes 'chunk', 'progress_base' goes from sectors to bytes); some of it is also a cleanup (sectors_to_bytes() is now unused, loss of variable 'count' added earlier in commit 51b0a488). Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.c | 124 ++++++++++++++++++++++++------------------------------------- 1 file changed, 48 insertions(+), 76 deletions(-) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int compare_buffers(const uint8_t *buf1, const uint8_t *buf2, #define IO_BUF_SIZE (2 * 1024 * 1024) -static int64_t sectors_to_bytes(int64_t sectors) -{ - return sectors << BDRV_SECTOR_BITS; -} - /* * Check if passed sectors are empty (not allocated or contain only 0 bytes) * @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) const char *fmt1 = NULL, *fmt2 = NULL, *cache, *filename1, *filename2; BlockBackend *blk1, *blk2; BlockDriverState *bs1, *bs2; - int64_t total_sectors1, total_sectors2; + int64_t total_size1, total_size2; uint8_t *buf1 = NULL, *buf2 = NULL; int64_t pnum1, pnum2; int allocated1, allocated2; @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) bool progress = false, quiet = false, strict = false; int flags; bool writethrough; - int64_t total_sectors; - int64_t sector_num = 0; - int64_t nb_sectors; + int64_t total_size; + int64_t offset = 0; + int64_t chunk; int c; uint64_t progress_base; bool image_opts = false; @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) buf1 = blk_blockalign(blk1, IO_BUF_SIZE); buf2 = blk_blockalign(blk2, IO_BUF_SIZE); - total_sectors1 = blk_nb_sectors(blk1); - if (total_sectors1 < 0) { + total_size1 = blk_getlength(blk1); + if (total_size1 < 0) { error_report("Can't get size of %s: %s", - filename1, strerror(-total_sectors1)); + filename1, strerror(-total_size1)); ret = 4; goto out; } - total_sectors2 = blk_nb_sectors(blk2); - if (total_sectors2 < 0) { + total_size2 = blk_getlength(blk2); + if (total_size2 < 0) { error_report("Can't get size of %s: %s", - filename2, strerror(-total_sectors2)); + filename2, strerror(-total_size2)); ret = 4; goto out; } - total_sectors = MIN(total_sectors1, total_sectors2); - progress_base = MAX(total_sectors1, total_sectors2); + total_size = MIN(total_size1, total_size2); + progress_base = MAX(total_size1, total_size2); qemu_progress_print(0, 100); - if (strict && total_sectors1 != total_sectors2) { + if (strict && total_size1 != total_size2) { ret = 1; qprintf(quiet, "Strict mode: Image size mismatch!\n"); goto out; } - while (sector_num < total_sectors) { + while (offset < total_size) { int status1, status2; - status1 = bdrv_block_status_above(bs1, NULL, - sector_num * BDRV_SECTOR_SIZE, - (total_sectors1 - sector_num) * - BDRV_SECTOR_SIZE, - &pnum1, NULL, NULL); + status1 = bdrv_block_status_above(bs1, NULL, offset, + total_size1 - offset, &pnum1, NULL, + NULL); if (status1 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename1); @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) } allocated1 = status1 & BDRV_BLOCK_ALLOCATED; - status2 = bdrv_block_status_above(bs2, NULL, - sector_num * BDRV_SECTOR_SIZE, - (total_sectors2 - sector_num) * - BDRV_SECTOR_SIZE, - &pnum2, NULL, NULL); + status2 = bdrv_block_status_above(bs2, NULL, offset, + total_size2 - offset, &pnum2, NULL, + NULL); if (status2 < 0) { ret = 3; error_report("Sector allocation test failed for %s", filename2); goto out; } allocated2 = status2 & BDRV_BLOCK_ALLOCATED; - /* TODO: Relax this once comparison is byte-based, and we no longer - * have to worry about sector alignment */ - assert(QEMU_IS_ALIGNED(pnum1 | pnum2, BDRV_SECTOR_SIZE)); assert(pnum1 && pnum2); - nb_sectors = MIN(pnum1, pnum2) >> BDRV_SECTOR_BITS; + chunk = MIN(pnum1, pnum2); if (strict) { if (status1 != status2) { ret = 1; qprintf(quiet, "Strict mode: Offset %" PRId64 - " block status mismatch!\n", - sectors_to_bytes(sector_num)); + " block status mismatch!\n", offset); goto out; } } @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) if (allocated1) { int64_t pnum; - nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); - ret = blk_pread(blk1, sector_num << BDRV_SECTOR_BITS, buf1, - nb_sectors << BDRV_SECTOR_BITS); + chunk = MIN(chunk, IO_BUF_SIZE); + ret = blk_pread(blk1, offset, buf1, chunk); if (ret < 0) { - error_report("Error while reading offset %" PRId64 " of %s:" - " %s", sectors_to_bytes(sector_num), filename1, - strerror(-ret)); + error_report("Error while reading offset %" PRId64 + " of %s: %s", + offset, filename1, strerror(-ret)); ret = 4; goto out; } - ret = blk_pread(blk2, sector_num << BDRV_SECTOR_BITS, buf2, - nb_sectors << BDRV_SECTOR_BITS); + ret = blk_pread(blk2, offset, buf2, chunk); if (ret < 0) { error_report("Error while reading offset %" PRId64 - " of %s: %s", sectors_to_bytes(sector_num), - filename2, strerror(-ret)); + " of %s: %s", + offset, filename2, strerror(-ret)); ret = 4; goto out; } - ret = compare_buffers(buf1, buf2, - nb_sectors * BDRV_SECTOR_SIZE, &pnum); - if (ret || pnum != nb_sectors * BDRV_SECTOR_SIZE) { + ret = compare_buffers(buf1, buf2, chunk, &pnum); + if (ret || pnum != chunk) { qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n", - sectors_to_bytes(sector_num) + (ret ? 0 : pnum)); + offset + (ret ? 0 : pnum)); ret = 1; goto out; } } } else { - nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); + chunk = MIN(chunk, IO_BUF_SIZE); if (allocated1) { - ret = check_empty_sectors(blk1, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + ret = check_empty_sectors(blk1, offset, chunk, filename1, buf1, quiet); } else { - ret = check_empty_sectors(blk2, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + ret = check_empty_sectors(blk2, offset, chunk, filename2, buf1, quiet); } if (ret) { goto out; } } - sector_num += nb_sectors; - qemu_progress_print(((float) nb_sectors / progress_base)*100, 100); + offset += chunk; + qemu_progress_print(((float) chunk / progress_base) * 100, 100); } - if (total_sectors1 != total_sectors2) { + if (total_size1 != total_size2) { BlockBackend *blk_over; const char *filename_over; qprintf(quiet, "Warning: Image size mismatch!\n"); - if (total_sectors1 > total_sectors2) { + if (total_size1 > total_size2) { blk_over = blk1; filename_over = filename1; } else { @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) filename_over = filename2; } - while (sector_num < progress_base) { - int64_t count; - - ret = bdrv_block_status_above(blk_bs(blk_over), NULL, - sector_num * BDRV_SECTOR_SIZE, - (progress_base - sector_num) * - BDRV_SECTOR_SIZE, - &count, NULL, NULL); + while (offset < progress_base) { + ret = bdrv_block_status_above(blk_bs(blk_over), NULL, offset, + progress_base - offset, &chunk, + NULL, NULL); if (ret < 0) { ret = 3; error_report("Sector allocation test failed for %s", @@ -XXX,XX +XXX,XX @@ static int img_compare(int argc, char **argv) goto out; } - /* TODO relax this once bdrv_block_status_above does not enforce - * sector alignment */ - assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); - nb_sectors = count >> BDRV_SECTOR_BITS; if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) { - nb_sectors = MIN(nb_sectors, IO_BUF_SIZE >> BDRV_SECTOR_BITS); - ret = check_empty_sectors(blk_over, - sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, + chunk = MIN(chunk, IO_BUF_SIZE); + ret = check_empty_sectors(blk_over, offset, chunk, filename_over, buf1, quiet); if (ret) { goto out; } } - sector_num += nb_sectors; - qemu_progress_print(((float) nb_sectors / progress_base)*100, 100); + offset += chunk; + qemu_progress_print(((float) chunk / progress_base) * 100, 100); } } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Any device that has request_alignment greater than 512 should be unable to report status at a finer granularity; it may also be simpler for such devices to be guaranteed that the block layer has rounded things out to the granularity boundary (the way the block layer already rounds all other I/O out). Besides, getting the code correct for super-sector alignment also benefits us for the fact that our public interface now has byte granularity, even though none of our drivers have byte-level callbacks. Add an assertion in blkdebug that proves that the block layer never requests status of unaligned sections, similar to what it does on other requests (while still keeping the generic helper in place for when future patches add a throttle driver). Note that iotest 177 already covers this (it would fail if you use just the blkdebug.c hunk without the io.c changes). Meanwhile, we can drop assertions in callers that no longer have to pass in sector-aligned addresses. There is a mid-function scope added for 'count' and 'longret', for a couple of reasons: first, an upcoming patch will add an 'if' statement that checks whether a driver has an old- or new-style callback, and can conveniently use the same scope for less indentation churn at that time. Second, since we are trying to get rid of sector-based computations, wrapping things in a scope makes it easier to group and see what will be deleted in a final cleanup patch once all drivers have been converted to the new-style callback. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 3 +- block/blkdebug.c | 13 ++++++++- block/io.c | 71 ++++++++++++++++++++++++++++++----------------- 3 files changed, 59 insertions(+), 28 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { * according to the current layer, and should not set * BDRV_BLOCK_ALLOCATED, but may set BDRV_BLOCK_RAW. See block.h * for the meaning of _DATA, _ZERO, and _OFFSET_VALID. The block - * layer guarantees non-NULL pnum and file. + * layer guarantees input aligned to request_alignment, as well as + * non-NULL pnum and file. */ int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, diff --git a/block/blkdebug.c b/block/blkdebug.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn blkdebug_co_pdiscard(BlockDriverState *bs, return bdrv_co_pdiscard(bs->file->bs, offset, bytes); } +static int64_t coroutine_fn blkdebug_co_get_block_status( + BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum, + BlockDriverState **file) +{ + assert(QEMU_IS_ALIGNED(sector_num | nb_sectors, + DIV_ROUND_UP(bs->bl.request_alignment, + BDRV_SECTOR_SIZE))); + return bdrv_co_get_block_status_from_file(bs, sector_num, nb_sectors, + pnum, file); +} + static void blkdebug_close(BlockDriverState *bs) { BDRVBlkdebugState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_blkdebug = { .bdrv_co_flush_to_disk = blkdebug_co_flush, .bdrv_co_pwrite_zeroes = blkdebug_co_pwrite_zeroes, .bdrv_co_pdiscard = blkdebug_co_pdiscard, - .bdrv_co_get_block_status = bdrv_co_get_block_status_from_file, + .bdrv_co_get_block_status = blkdebug_co_get_block_status, .bdrv_debug_event = blkdebug_debug_event, .bdrv_debug_breakpoint = blkdebug_debug_breakpoint, diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, { int64_t total_size; int64_t n; /* bytes */ - int64_t ret; + int ret; int64_t local_map = 0; BlockDriverState *local_file = NULL; - int count; /* sectors */ + int64_t aligned_offset, aligned_bytes; + uint32_t align; assert(pnum); *pnum = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, } bdrv_inc_in_flight(bs); + + /* Round out to request_alignment boundaries */ + /* TODO: until we have a byte-based driver callback, we also have to + * round out to sectors, even if that is bigger than request_alignment */ + align = MAX(bs->bl.request_alignment, BDRV_SECTOR_SIZE); + aligned_offset = QEMU_ALIGN_DOWN(offset, align); + aligned_bytes = ROUND_UP(offset + bytes, align) - aligned_offset; + + { + int count; /* sectors */ + int64_t longret; + + assert(QEMU_IS_ALIGNED(aligned_offset | aligned_bytes, + BDRV_SECTOR_SIZE)); + /* + * The contract allows us to return pnum smaller than bytes, even + * if the next query would see the same status; we truncate the + * request to avoid overflowing the driver's 32-bit interface. + */ + longret = bs->drv->bdrv_co_get_block_status( + bs, aligned_offset >> BDRV_SECTOR_BITS, + MIN(INT_MAX, aligned_bytes) >> BDRV_SECTOR_BITS, &count, + &local_file); + if (longret < 0) { + assert(INT_MIN <= longret); + ret = longret; + goto out; + } + if (longret & BDRV_BLOCK_OFFSET_VALID) { + local_map = longret & BDRV_BLOCK_OFFSET_MASK; + } + ret = longret & ~BDRV_BLOCK_OFFSET_MASK; + *pnum = count * BDRV_SECTOR_SIZE; + } + /* - * TODO: Rather than require aligned offsets, we could instead - * round to the driver's request_alignment here, then touch up - * count afterwards back to the caller's expectations. - */ - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - /* - * The contract allows us to return pnum smaller than bytes, even - * if the next query would see the same status; we truncate the - * request to avoid overflowing the driver's 32-bit interface. + * The driver's result must be a multiple of request_alignment. + * Clamp pnum and adjust map to original request. */ - bytes = MIN(bytes, BDRV_REQUEST_MAX_BYTES); - ret = bs->drv->bdrv_co_get_block_status(bs, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, &count, - &local_file); - if (ret < 0) { - goto out; + assert(QEMU_IS_ALIGNED(*pnum, align) && align > offset - aligned_offset); + *pnum -= offset - aligned_offset; + if (*pnum > bytes) { + *pnum = bytes; } if (ret & BDRV_BLOCK_OFFSET_VALID) { - local_map = ret & BDRV_BLOCK_OFFSET_MASK; + local_map += offset - aligned_offset; } - *pnum = count * BDRV_SECTOR_SIZE; if (ret & BDRV_BLOCK_RAW) { assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); ret = bdrv_co_block_status(local_file, want_zero, local_map, *pnum, pnum, &local_map, &local_file); - assert(ret < 0 || - QEMU_IS_ALIGNED(*pnum | local_map, BDRV_SECTOR_SIZE)); goto out; } @@ -XXX,XX +XXX,XX @@ early_out: if (map) { *map = local_map; } - if (ret >= 0) { - ret &= ~BDRV_BLOCK_OFFSET_MASK; - } else { - assert(INT_MIN <= ret); - } return ret; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Now that bdrv_is_allocated accepts non-aligned inputs, we can remove the TODO added in commit d6a644bb. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child, } if (flags & BDRV_REQ_COPY_ON_READ) { - /* TODO: Simplify further once bdrv_is_allocated no longer - * requires sector alignment */ - int64_t start = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); - int64_t end = QEMU_ALIGN_UP(offset + bytes, BDRV_SECTOR_SIZE); int64_t pnum; - ret = bdrv_is_allocated(bs, start, end - start, &pnum); + ret = bdrv_is_allocated(bs, offset, bytes, &pnum); if (ret < 0) { goto out; } - if (!ret || pnum != end - start) { + if (!ret || pnum != bytes) { ret = bdrv_co_do_copy_on_readv(child, offset, bytes, qiov); goto out; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Now that bdrv_is_allocated accepts non-aligned inputs, we can remove the TODO added in earlier refactoring. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) { int64_t nr; int res; - int64_t start; - - /* TODO: Widening to sector boundaries should only be needed as - * long as we can't query finer granularity. */ - start = QEMU_ALIGN_DOWN(offset, BDRV_SECTOR_SIZE); - bytes = QEMU_ALIGN_UP(offset + bytes, BDRV_SECTOR_SIZE) - start; /* Clamp to image length, before checking status of underlying sectors */ - if (start + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) { - bytes = bs->total_sectors * BDRV_SECTOR_SIZE - start; + if (offset + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) { + bytes = bs->total_sectors * BDRV_SECTOR_SIZE - offset; } if (!bytes) { return true; } - res = bdrv_block_status_above(bs, NULL, start, bytes, &nr, NULL, NULL); + res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); return res >= 0 && (res & BDRV_BLOCK_ZERO) && nr == bytes; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Previously, the alloc command required that input parameters be sector-aligned and clamped to 32 bits, because the underlying bdrv_is_allocated used a 32-bit parameter and asserted aligned inputs. But now that we have fixed block status to report a 64-bit bytes value, and to properly round requests on behalf of guests, we can pass any values, and can use qemu-io to add coverage that our rounding is correct regardless of the guest alignment constraints. Update iotest 177 to intentionally probe block status at unaligned boundaries as well as with a bytes value that does not map to 32-bit sectors, which also required tweaking the image prep to leave an unallocated portion to the image under test. Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-io-cmds.c | 13 ------------- tests/qemu-iotests/177 | 12 ++++++++++-- tests/qemu-iotests/177.out | 19 ++++++++++++++----- 3 files changed, 24 insertions(+), 20 deletions(-) diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int alloc_f(BlockBackend *blk, int argc, char **argv) if (offset < 0) { print_cvtnum_err(offset, argv[1]); return 0; - } else if (!QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)) { - printf("%" PRId64 " is not a sector-aligned value for 'offset'\n", - offset); - return 0; } if (argc == 3) { @@ -XXX,XX +XXX,XX @@ static int alloc_f(BlockBackend *blk, int argc, char **argv) if (count < 0) { print_cvtnum_err(count, argv[2]); return 0; - } else if (count > INT_MAX * BDRV_SECTOR_SIZE) { - printf("length argument cannot exceed %llu, given %s\n", - INT_MAX * BDRV_SECTOR_SIZE, argv[2]); - return 0; } } else { count = BDRV_SECTOR_SIZE; } - if (!QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)) { - printf("%" PRId64 " is not a sector-aligned value for 'count'\n", - count); - return 0; - } remaining = count; sum_alloc = 0; diff --git a/tests/qemu-iotests/177 b/tests/qemu-iotests/177 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/177 +++ b/tests/qemu-iotests/177 @@ -XXX,XX +XXX,XX @@ echo "== setting up files ==" TEST_IMG="$TEST_IMG.base" _make_test_img $size $QEMU_IO -c "write -P 11 0 $size" "$TEST_IMG.base" | _filter_qemu_io _make_test_img -b "$TEST_IMG.base" -$QEMU_IO -c "write -P 22 0 $size" "$TEST_IMG" | _filter_qemu_io +$QEMU_IO -c "write -P 22 0 110M" "$TEST_IMG" | _filter_qemu_io # Limited to 64k max-transfer echo @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c "open -o $options,$limits blkdebug::$TEST_IMG" \ -c "discard 80000001 30M" | _filter_qemu_io echo +echo "== block status smaller than alignment ==" +limits=align=4k +$QEMU_IO -c "open -o $options,$limits blkdebug::$TEST_IMG" \ + -c "alloc 1 1" -c "alloc 0x6dffff0 1000" -c "alloc 127m 5P" \ + -c map | _filter_qemu_io + +echo echo "== verify image content ==" function verify_io() @@ -XXX,XX +XXX,XX @@ function verify_io() echo read -P 0 32M 32M echo read -P 22 64M 13M echo read -P $discarded 77M 29M - echo read -P 22 106M 22M + echo read -P 22 106M 4M + echo read -P 11 110M 18M } verify_io | $QEMU_IO -r "$TEST_IMG" | _filter_qemu_io diff --git a/tests/qemu-iotests/177.out b/tests/qemu-iotests/177.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/177.out +++ b/tests/qemu-iotests/177.out @@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=134217728 wrote 134217728/134217728 bytes at offset 0 128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 backing_file=TEST_DIR/t.IMGFMT.base -wrote 134217728/134217728 bytes at offset 0 -128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 115343360/115343360 bytes at offset 0 +110 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) == constrained alignment and max-transfer == wrote 131072/131072 bytes at offset 1000 @@ -XXX,XX +XXX,XX @@ wrote 33554432/33554432 bytes at offset 33554432 discard 31457280/31457280 bytes at offset 80000001 30 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +== block status smaller than alignment == +1/1 bytes allocated at offset 1 bytes +16/1000 bytes allocated at offset 110 MiB +0/1048576 bytes allocated at offset 127 MiB +110 MiB (0x6e00000) bytes allocated at offset 0 bytes (0x0) +18 MiB (0x1200000) bytes not allocated at offset 110 MiB (0x6e00000) + == verify image content == read 1000/1000 bytes at offset 0 1000 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) @@ -XXX,XX +XXX,XX @@ read 13631488/13631488 bytes at offset 67108864 13 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 30408704/30408704 bytes at offset 80740352 29 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -read 23068672/23068672 bytes at offset 111149056 -22 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 4194304/4194304 bytes at offset 111149056 +4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 18874368/18874368 bytes at offset 115343360 +18 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Offset Length File 0 0x800000 TEST_DIR/t.IMGFMT 0x900000 0x2400000 TEST_DIR/t.IMGFMT 0x3c00000 0x1100000 TEST_DIR/t.IMGFMT -0x6a00000 0x1600000 TEST_DIR/t.IMGFMT +0x6a00000 0x400000 TEST_DIR/t.IMGFMT No errors were found on the image. *** done -- 2.13.6 From: Max Reitz <mreitz@redhat.com> qemu-img commit invalidates all images between base and top. This should be mentioned in the man page. Suggested-by: Ping Li <pingl@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-img.texi | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/qemu-img.texi b/qemu-img.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.texi +++ b/qemu-img.texi @@ -XXX,XX +XXX,XX @@ If the backing chain of the given image file @var{filename} has more than one layer, the backing file into which the changes will be committed may be specified as @var{base} (which has to be part of @var{filename}'s backing chain). If @var{base} is not specified, the immediate backing file of the top -image (which is @var{filename}) will be used. For reasons of consistency, -explicitly specifying @var{base} will always imply @code{-d} (since emptying an -image after committing to an indirect backing file would lead to different data -being read from the image due to content in the intermediate backing chain -overruling the commit target). +image (which is @var{filename}) will be used. Note that after a commit operation +all images between @var{base} and the top image will be invalid and may return +garbage data when read. For this reason, @code{-b} implies @code{-d} (so that +the top image stays valid). @item compare [-f @var{fmt}] [-F @var{fmt}] [-T @var{src_cache}] [-p] [-s] [-q] @var{filename1} @var{filename2} -- 2.13.6 From: Alberto Garcia <berto@igalia.com> BDRV_SECTOR_BITS is defined to be 9 in block.h (and BDRV_SECTOR_SIZE is calculated from that), but there are still a couple of places where we are using the literal value instead of the macro. Signed-off-by: Alberto Garcia <berto@igalia.com> Message-id: 20171009153856.20387-1-berto@igalia.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags, s->cluster_bits = header.cluster_bits; s->cluster_size = 1 << s->cluster_bits; - s->cluster_sectors = 1 << (s->cluster_bits - 9); + s->cluster_sectors = 1 << (s->cluster_bits - BDRV_SECTOR_BITS); /* Initialise version 3 header fields */ if (header.version == 2) { @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs, bytes = MIN(INT_MAX, nb_sectors * BDRV_SECTOR_SIZE); qemu_co_mutex_lock(&s->lock); - ret = qcow2_get_cluster_offset(bs, sector_num << 9, &bytes, + ret = qcow2_get_cluster_offset(bs, sector_num << BDRV_SECTOR_BITS, &bytes, &cluster_offset); qemu_co_mutex_unlock(&s->lock); if (ret < 0) { -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20170929170843.3711-1-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/127 | 97 ++++++++++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/127.out | 14 +++++++ tests/qemu-iotests/group | 1 + 3 files changed, 112 insertions(+) create mode 100755 tests/qemu-iotests/127 create mode 100644 tests/qemu-iotests/127.out diff --git a/tests/qemu-iotests/127 b/tests/qemu-iotests/127 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/127 @@ -XXX,XX +XXX,XX @@ +#!/bin/bash +# +# Test case for mirroring with dataplane +# +# Copyright (C) 2017 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=mreitz@redhat.com + +seq=$(basename $0) +echo "QA output created by $seq" + +here=$PWD +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_qemu + _cleanup_test_img + _rm_test_img "$TEST_IMG.overlay0" + _rm_test_img "$TEST_IMG.overlay1" +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and qemu instance handling +. ./common.rc +. ./common.filter +. ./common.qemu + +_supported_fmt qcow2 +_supported_proto file +_supported_os Linux + +IMG_SIZE=64K + +_make_test_img $IMG_SIZE +TEST_IMG="$TEST_IMG.overlay0" _make_test_img -b "$TEST_IMG" $IMG_SIZE +TEST_IMG="$TEST_IMG.overlay1" _make_test_img -b "$TEST_IMG" $IMG_SIZE + +# So that we actually have something to mirror and the job does not return +# immediately (which may be bad because then we cannot know whether the +# 'return' or the 'BLOCK_JOB_READY' comes first). +$QEMU_IO -c 'write 0 42' "$TEST_IMG.overlay0" | _filter_qemu_io + +# We cannot use virtio-blk here because that does not actually set the attached +# BB's AioContext in qtest mode +_launch_qemu \ + -object iothread,id=iothr \ + -blockdev node-name=source,driver=$IMGFMT,file.driver=file,file.filename="$TEST_IMG.overlay0" \ + -device virtio-scsi,id=scsi-bus,iothread=iothr \ + -device scsi-hd,bus=scsi-bus.0,drive=source + +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'qmp_capabilities' }" \ + 'return' + +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'drive-mirror', + 'arguments': { + 'job-id': 'mirror', + 'device': 'source', + 'target': '$TEST_IMG.overlay1', + 'mode': 'existing', + 'sync': 'top' + } }" \ + 'BLOCK_JOB_READY' + +# The backing BDS should be assigned the overlay's AioContext +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'block-job-complete', + 'arguments': { 'device': 'mirror' } }" \ + 'BLOCK_JOB_COMPLETED' + +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'quit' }" \ + 'return' + +wait=yes _cleanup_qemu + +# success, all done +echo '*** done' +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/127.out b/tests/qemu-iotests/127.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/127.out @@ -XXX,XX +XXX,XX @@ +QA output created by 127 +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=65536 +Formatting 'TEST_DIR/t.IMGFMT.overlay0', fmt=IMGFMT size=65536 backing_file=TEST_DIR/t.IMGFMT +Formatting 'TEST_DIR/t.IMGFMT.overlay1', fmt=IMGFMT size=65536 backing_file=TEST_DIR/t.IMGFMT +wrote 42/42 bytes at offset 0 +42 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +{"return": {}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "mirror", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "mirror", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} +*** done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -XXX,XX +XXX,XX @@ 124 rw auto backing 125 rw auto 126 rw auto backing +127 rw auto backing quick 128 rw auto quick 129 rw auto quick 130 rw auto quick -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Tests 067 and 087 filter the actual image size because it depends on the host filesystem (and is not part of the respective test). Since this is generally true, we should have a common filter function for this, so let's pull out the sed line from both tests into such a function. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20171009163456.485-2-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/067 | 2 +- tests/qemu-iotests/087 | 2 +- tests/qemu-iotests/common.filter | 6 ++++++ 3 files changed, 8 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/067 b/tests/qemu-iotests/067 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/067 +++ b/tests/qemu-iotests/067 @@ -XXX,XX +XXX,XX @@ _filter_qmp_events() function run_qemu() { do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qmp | _filter_qemu \ - | sed -e 's/\("actual-size":\s*\)[0-9]\+/\1SIZE/g' \ + | _filter_actual_image_size \ | _filter_generated_node_ids | _filter_qmp_events } diff --git a/tests/qemu-iotests/087 b/tests/qemu-iotests/087 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/087 +++ b/tests/qemu-iotests/087 @@ -XXX,XX +XXX,XX @@ function run_qemu() { do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qmp \ | _filter_qemu | _filter_imgfmt \ - | sed -e 's/\("actual-size":\s*\)[0-9]\+/\1SIZE/g' + | _filter_actual_image_size } size=128M diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -XXX,XX +XXX,XX @@ _filter_block_job_len() sed -e 's/, "len": [0-9]\+,/, "len": LEN,/g' } +# replace actual image size (depends on the host filesystem) +_filter_actual_image_size() +{ + sed -s 's/\("actual-size":\s*\)[0-9]\+/\1SIZE/g' +} + # replace driver-specific options in the "Formatting..." line _filter_img_create() { -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Whenever the actual image size is not part of the test, it should be filtered as it depends on the host filesystem. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20171009163456.485-3-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/184 | 3 ++- tests/qemu-iotests/184.out | 6 +++--- tests/qemu-iotests/191 | 4 ++-- tests/qemu-iotests/191.out | 46 +++++++++++++++++++++++----------------------- 4 files changed, 30 insertions(+), 29 deletions(-) diff --git a/tests/qemu-iotests/184 b/tests/qemu-iotests/184 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/184 +++ b/tests/qemu-iotests/184 @@ -XXX,XX +XXX,XX @@ function do_run_qemu() function run_qemu() { do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qemu | _filter_qmp\ - | _filter_qemu_io | _filter_generated_node_ids + | _filter_qemu_io | _filter_generated_node_ids \ + | _filter_actual_image_size } _make_test_img 64M diff --git a/tests/qemu-iotests/184.out b/tests/qemu-iotests/184.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/184.out +++ b/tests/qemu-iotests/184.out @@ -XXX,XX +XXX,XX @@ Testing: "filename": "json:{\"throttle-group\": \"group0\", \"driver\": \"throttle\", \"file\": {\"driver\": \"qcow2\", \"file\": {\"driver\": \"file\", \"filename\": \"TEST_DIR/t.qcow2\"}}}", "cluster-size": 65536, "format": "throttle", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ Testing: "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ Testing: "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/191 +++ b/tests/qemu-iotests/191 @@ -XXX,XX +XXX,XX @@ echo === Check that both top and top2 point to base now === echo _send_qemu_cmd $h "{ 'execute': 'query-named-block-nodes' }" "^}" | - _filter_generated_node_ids + _filter_generated_node_ids | _filter_actual_image_size _send_qemu_cmd $h "{ 'execute': 'quit' }" "^}" wait=1 _cleanup_qemu @@ -XXX,XX +XXX,XX @@ echo === Check that both top and top2 point to base now === echo _send_qemu_cmd $h "{ 'execute': 'query-named-block-nodes' }" "^}" | - _filter_generated_node_ids + _filter_generated_node_ids | _filter_actual_image_size _send_qemu_cmd $h "{ 'execute': 'quit' }" "^}" wait=1 _cleanup_qemu diff --git a/tests/qemu-iotests/191.out b/tests/qemu-iotests/191.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/191.out +++ b/tests/qemu-iotests/191.out @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2.ovl2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.mid", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 393216, "filename": "TEST_DIR/t.qcow2.mid", "format": "file", - "actual-size": 397312, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 393216, "filename": "TEST_DIR/t.qcow2.base", "format": "file", - "actual-size": 397312, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2.ovl2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.ovl3", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2.ovl3", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 393216, "filename": "TEST_DIR/t.qcow2.base", "format": "file", - "actual-size": 397312, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2.base", "cluster-size": 65536, "format": "qcow2", - "actual-size": 397312, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", - "actual-size": 200704, + "actual-size": SIZE, "format-specific": { "type": "qcow2", "data": { @@ -XXX,XX +XXX,XX @@ wrote 65536/65536 bytes at offset 1048576 "virtual-size": 197120, "filename": "TEST_DIR/t.qcow2", "format": "file", - "actual-size": 200704, + "actual-size": SIZE, "dirty-flag": false }, "iops_wr": 0, -- 2.13.6 From: Max Reitz <mreitz@redhat.com> bdrv_truncate() has an errp parameter which is always set when an error occurs. Let's use that instead of a plain strerror(). Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20171009155431.14093-1-mreitz@redhat.com Reviewed-by: Pavel Butsykin <pbutsykin@virtuozzo.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset, return last_cluster; } if ((last_cluster + 1) * s->cluster_size < old_file_size) { - ret = bdrv_truncate(bs->file, (last_cluster + 1) * s->cluster_size, - PREALLOC_MODE_OFF, NULL); - if (ret < 0) { - warn_report("Failed to truncate the tail of the image: %s", - strerror(-ret)); - ret = 0; + Error *local_err = NULL; + + bdrv_truncate(bs->file, (last_cluster + 1) * s->cluster_size, + PREALLOC_MODE_OFF, &local_err); + if (local_err) { + warn_reportf_err(local_err, + "Failed to truncate the tail of the image: "); } } } else { -- 2.13.6 From: Max Reitz <mreitz@redhat.com> A qcow2 image file's length is not required to have a length that is a multiple of the cluster size. However, qcow2_refcount_area() expects an aligned value for its @start_offset parameter, so we need to round @old_file_size up to the next cluster boundary. Reported-by: Ping Li <pingl@redhat.com> Bug: https://bugzilla.redhat.com/show_bug.cgi?id=1414049 Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20171009215533.12530-2-mreitz@redhat.com Cc: qemu-stable@nongnu.org Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset, "Failed to inquire current file length"); return old_file_size; } + old_file_size = ROUND_UP(old_file_size, s->cluster_size); nb_new_data_clusters = DIV_ROUND_UP(offset - old_length, s->cluster_size); -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Some qcow2 functions (at least perform_cow()) expect s->lock to be taken. Therefore, if we want to make use of them, we should execute preallocate() (as "preallocate_co") in a coroutine so that we can use the qemu_co_mutex_* functions. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20171009215533.12530-3-mreitz@redhat.com Cc: qemu-stable@nongnu.org Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.c | 41 ++++++++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_set_up_encryption(BlockDriverState *bs, const char *encryptfmt, } +typedef struct PreallocCo { + BlockDriverState *bs; + uint64_t offset; + uint64_t new_length; + + int ret; +} PreallocCo; + /** * Preallocates metadata structures for data clusters between @offset (in the * guest disk) and @new_length (which is thus generally the new guest disk @@ -XXX,XX +XXX,XX @@ static int qcow2_set_up_encryption(BlockDriverState *bs, const char *encryptfmt, * * Returns: 0 on success, -errno on failure. */ -static int preallocate(BlockDriverState *bs, - uint64_t offset, uint64_t new_length) +static void coroutine_fn preallocate_co(void *opaque) { + PreallocCo *params = opaque; + BlockDriverState *bs = params->bs; + uint64_t offset = params->offset; + uint64_t new_length = params->new_length; BDRVQcow2State *s = bs->opaque; uint64_t bytes; uint64_t host_offset = 0; @@ -XXX,XX +XXX,XX @@ static int preallocate(BlockDriverState *bs, int ret; QCowL2Meta *meta; - if (qemu_in_coroutine()) { - qemu_co_mutex_lock(&s->lock); - } + qemu_co_mutex_lock(&s->lock); assert(offset <= new_length); bytes = new_length - offset; @@ -XXX,XX +XXX,XX @@ static int preallocate(BlockDriverState *bs, ret = 0; done: + qemu_co_mutex_unlock(&s->lock); + params->ret = ret; +} + +static int preallocate(BlockDriverState *bs, + uint64_t offset, uint64_t new_length) +{ + PreallocCo params = { + .bs = bs, + .offset = offset, + .new_length = new_length, + .ret = -EINPROGRESS, + }; + if (qemu_in_coroutine()) { - qemu_co_mutex_unlock(&s->lock); + preallocate_co(&params); + } else { + Coroutine *co = qemu_coroutine_create(preallocate_co, &params); + bdrv_coroutine_enter(bs, co); + BDRV_POLL_WHILE(bs, params.ret == -EINPROGRESS); } - return ret; + return params.ret; } /* qcow2_refcount_metadata_size: -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Apparently it would be a good idea to test that, too. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20171009215533.12530-4-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/125 | 7 +- tests/qemu-iotests/125.out | 480 ++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 437 insertions(+), 50 deletions(-) diff --git a/tests/qemu-iotests/125 b/tests/qemu-iotests/125 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/125 +++ b/tests/qemu-iotests/125 @@ -XXX,XX +XXX,XX @@ fi # in B CREATION_SIZE=$((2 * 1024 * 1024 - 48 * 1024)) +# 512 is the actual test -- but it's good to test 64k as well, just to be sure. +for cluster_size in 512 64k; do # in kB for GROWTH_SIZE in 16 48 80; do for create_mode in off metadata falloc full; do for growth_mode in off metadata falloc full; do - echo "--- growth_size=$GROWTH_SIZE create_mode=$create_mode growth_mode=$growth_mode ---" + echo "--- cluster_size=$cluster_size growth_size=$GROWTH_SIZE create_mode=$create_mode growth_mode=$growth_mode ---" - IMGOPTS="preallocation=$create_mode,cluster_size=512" _make_test_img ${CREATION_SIZE} + IMGOPTS="preallocation=$create_mode,cluster_size=$cluster_size" _make_test_img ${CREATION_SIZE} $QEMU_IMG resize -f "$IMGFMT" --preallocation=$growth_mode "$TEST_IMG" +${GROWTH_SIZE}K host_size_0=$(get_image_size_on_host) @@ -XXX,XX +XXX,XX @@ for GROWTH_SIZE in 16 48 80; do done done done +done # success, all done echo '*** done' diff --git a/tests/qemu-iotests/125.out b/tests/qemu-iotests/125.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/125.out +++ b/tests/qemu-iotests/125.out @@ -XXX,XX +XXX,XX @@ QA output created by 125 ---- growth_size=16 create_mode=off growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=off growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=off growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=off growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=off growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=metadata growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=metadata growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=falloc growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=falloc growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=off --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=metadata --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=falloc --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=16 create_mode=full growth_mode=full --- +--- cluster_size=512 growth_size=16 create_mode=full growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 16384/16384 bytes at offset 2048000 16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=off growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=off growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=metadata growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=metadata growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=falloc growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=falloc growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=off --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=metadata --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=falloc --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=48 create_mode=full growth_mode=full --- +--- cluster_size=512 growth_size=48 create_mode=full growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 49152/49152 bytes at offset 2048000 48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=off growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=off growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=metadata growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=metadata growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=falloc growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=falloc growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=off --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=off --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=metadata --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=metadata --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=falloc --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=falloc --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 @@ -XXX,XX +XXX,XX @@ wrote 2048000/2048000 bytes at offset 0 wrote 81920/81920 bytes at offset 2048000 80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) ---- growth_size=80 create_mode=full growth_mode=full --- +--- cluster_size=512 growth_size=80 create_mode=full growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=off growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=metadata growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=falloc growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=16 create_mode=full growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 16384/16384 bytes at offset 2048000 +16 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=off growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=metadata growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=falloc growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=48 create_mode=full growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 49152/49152 bytes at offset 2048000 +48 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=off growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=off +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=metadata growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=metadata +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=falloc growth_mode=full --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=falloc +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=off --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=metadata --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=falloc --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full +Image resized. +wrote 2048000/2048000 bytes at offset 0 +1.953 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 81920/81920 bytes at offset 2048000 +80 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +--- cluster_size=64k growth_size=80 create_mode=full growth_mode=full --- Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=2048000 preallocation=full Image resized. wrote 2048000/2048000 bytes at offset 0 -- 2.13.6 The following changes since commit 344744e148e6e865f5a57e745b02a87e5ea534ad: Merge tag 'dump-pull-request' of https://gitlab.com/marcandre.lureau/qemu into staging (2022-10-26 10:53:49 -0400) are available in the Git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to be8da05b5ed8fb546731b9edb997f303f272bad8: block/block-backend: blk_set_enable_write_cache is IO_CODE (2022-10-27 20:27:37 +0200) ---------------------------------------------------------------- Block layer patches - Cleanup bs->backing and bs->file handling - Refactor bdrv_try_set_aio_context using transactions - Changes for improved coroutine_fn consistency - vhost-user-blk: fix the resize crash - io_uring: Use of io_uring_register_ring_fd() led to breakage, revert - vvfat: Fix some problems with r/w mode - Code cleanup - MAINTAINERS: Fold "Block QAPI, monitor, ..." into "Block layer core" ---------------------------------------------------------------- Alberto Faria (20): backup: remove incorrect coroutine_fn annotation block: remove incorrect coroutine_fn annotation monitor: add missing coroutine_fn annotation ssh: add missing coroutine_fn annotation block: add missing coroutine_fn annotation to prototypes coroutine-lock: add missing coroutine_fn annotation to prototypes coroutine-io: add missing coroutine_fn annotation to prototypes block: add missing coroutine_fn annotation to BlockDriverState callbacks qcow2: add coroutine_fn annotation for indirect-called functions commit: switch to *_co_* functions block: switch to *_co_* functions mirror: switch to *_co_* functions parallels: switch to *_co_* functions qcow: switch to *_co_* functions qcow2: switch to *_co_* functions qed: switch to *_co_* functions vdi: switch to *_co_* functions vhdx: switch to *_co_* functions vmdk: switch to *_co_* functions monitor: switch to *_co_* functions Bin Meng (3): block: Ignore close() failure in get_tmp_filename() block: Refactor get_tmp_filename() block/nfs: Fix 32-bit Windows build Emanuele Giuseppe Esposito (11): block.c: assert bs->aio_context is written under BQL and drains block: use transactions as a replacement of ->{can_}set_aio_context() bdrv_change_aio_context: use hash table instead of list of visited nodes blockjob: implement .change_aio_ctx in child_job block: implement .change_aio_ctx in child_of_bds block-backend: implement .change_aio_ctx in child_root block: use the new _change_ API instead of _can_set_ and _set_ block: remove all unused ->can_set_aio_ctx and ->set_aio_ctx callbacks block: rename bdrv_child_try_change_aio_context in bdrv_try_change_aio_context block: remove bdrv_try_set_aio_context and replace it with bdrv_try_change_aio_context block/block-backend: blk_set_enable_write_cache is IO_CODE Hervé Poussineau (2): vvfat: allow some writes to bootsector vvfat: allow spaces in file names Li Feng (1): vhost-user-blk: fix the resize crash Markus Armbruster (1): MAINTAINERS: Fold "Block QAPI, monitor, ..." into "Block layer core" Paolo Bonzini (4): blkdebug: add missing coroutine_fn annotation for indirect-called functions qcow: manually add more coroutine_fn annotations qcow2: manually add more coroutine_fn annotations vmdk: manually add more coroutine_fn annotations Sam Li (1): block/io_uring: revert "Use io_uring_register_ring_fd() to skip fd operations" Vladimir Sementsov-Ogievskiy (15): block: BlockDriver: add .filtered_child_is_backing field block: introduce bdrv_open_file_child() helper block/blklogwrites: don't care to remove bs->file child on failure test-bdrv-graph-mod: update test_parallel_perm_update test case tests-bdrv-drain: bdrv_replace_test driver: declare supports_backing test-bdrv-graph-mod: fix filters to be filters block: document connection between child roles and bs->backing/bs->file block/snapshot: stress that we fallback to primary child Revert "block: Let replace_child_noperm free children" Revert "block: Let replace_child_tran keep indirect pointer" Revert "block: Restructure remove_file_or_backing_child()" Revert "block: Pass BdrvChild ** to replace_child_noperm" block: Manipulate bs->file / bs->backing pointers in .attach/.detach block/snapshot: drop indirection around bdrv_snapshot_fallback_ptr block: refactor bdrv_remove_file_or_backing_child to bdrv_remove_child docs/devel/multiple-iothreads.txt | 4 +- block/qcow2.h | 32 +- include/block/block-common.h | 39 ++ include/block/block-global-state.h | 18 +- include/block/block-hmp-cmds.h | 2 +- include/block/block-io.h | 5 +- include/block/block_int-common.h | 49 ++- include/monitor/hmp.h | 3 +- include/qemu/coroutine.h | 18 +- block.c | 855 +++++++++++++++++-------------------- block/backup.c | 2 +- block/blkdebug.c | 11 +- block/blklogwrites.c | 11 +- block/blkreplay.c | 7 +- block/blkverify.c | 9 +- block/block-backend.c | 76 ++-- block/bochs.c | 7 +- block/cloop.c | 7 +- block/commit.c | 3 +- block/copy-before-write.c | 9 +- block/copy-on-read.c | 9 +- block/crypto.c | 11 +- block/dmg.c | 7 +- block/export/export.c | 2 +- block/filter-compress.c | 8 +- block/io.c | 8 +- block/io_uring.c | 13 +- block/mirror.c | 5 +- block/monitor/block-hmp-cmds.c | 2 +- block/nfs.c | 8 + block/parallels.c | 35 +- block/preallocate.c | 9 +- block/qcow.c | 66 +-- block/qcow2-bitmap.c | 4 +- block/qcow2-cluster.c | 29 +- block/qcow2-refcount.c | 18 +- block/qcow2-snapshot.c | 6 +- block/qcow2.c | 40 +- block/qed-table.c | 2 +- block/qed.c | 20 +- block/raw-format.c | 4 +- block/replication.c | 8 +- block/snapshot-access.c | 6 +- block/snapshot.c | 59 +-- block/ssh.c | 6 +- block/throttle.c | 8 +- block/vdi.c | 24 +- block/vhdx.c | 15 +- block/vmdk.c | 95 ++--- block/vpc.c | 7 +- block/vvfat.c | 35 +- blockdev.c | 24 +- blockjob.c | 50 ++- hw/block/vhost-user-blk.c | 4 + job.c | 2 +- tests/unit/test-bdrv-drain.c | 17 +- tests/unit/test-bdrv-graph-mod.c | 104 +++-- tests/unit/test-block-iothread.c | 10 +- MAINTAINERS | 12 +- meson.build | 1 - tests/qemu-iotests/051 | 3 +- tests/qemu-iotests/051.out | 2 +- tests/qemu-iotests/051.pc.out | 2 +- 63 files changed, 984 insertions(+), 983 deletions(-) From: Markus Armbruster <armbru@redhat.com> Section "Block QAPI, monitor, command line" is about the external interfaces we provide for block devices. It covers the relevant QAPI schema parts, monitor and command line code, more or less. The section's files are also covered by section "Block layer core", except for the QAPI schema files. I haven't acted as maintainer in this area for a long time. Make it official: add the QAPI schema files to section "Block layer core", and delete section "Block QAPI, monitor, command line". Cc: Kevin Wolf <kwolf@redhat.com> Cc: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20221020120541.80757-1-armbru@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- MAINTAINERS | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Supported F: block* F: block/ F: hw/block/ +F: qapi/block*.json +F: qapi/transaction.json F: include/block/ F: qemu-img* F: docs/tools/qemu-img.rst @@ -XXX,XX +XXX,XX @@ F: include/qemu/co-shared-resource.h T: git https://gitlab.com/jsnow/qemu.git jobs T: git https://gitlab.com/vsementsov/qemu.git block -Block QAPI, monitor, command line -M: Markus Armbruster <armbru@redhat.com> -S: Supported -F: blockdev.c -F: blockdev-hmp-cmds.c -F: block/qapi.c -F: qapi/block*.json -F: qapi/transaction.json -T: git https://repo.or.cz/qemu/armbru.git block-next - Compute Express Link M: Ben Widawsky <ben.widawsky@intel.com> M: Jonathan Cameron <jonathan.cameron@huawei.com> -- 2.37.3 From: Bin Meng <bin.meng@windriver.com> The temporary file has been created and is ready for use. Checking return value of close() does not seem useful. The file descriptor is almost certainly closed; see close(2) under "Dealing with error returns from close()". Let's simply ignore close() failure here. Suggested-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Bin Meng <bin.meng@windriver.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20221010040432.3380478-1-bin.meng@windriver.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ int get_tmp_filename(char *filename, int size) if (fd < 0) { return -errno; } - if (close(fd) != 0) { - unlink(filename); - return -errno; - } + close(fd); return 0; #endif } -- 2.37.3 From: Bin Meng <bin.meng@windriver.com> At present there are two callers of get_tmp_filename() and they are inconsistent. One does: /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */ char *tmp_filename = g_malloc0(PATH_MAX + 1); ... ret = get_tmp_filename(tmp_filename, PATH_MAX + 1); while the other does: s->qcow_filename = g_malloc(PATH_MAX); ret = get_tmp_filename(s->qcow_filename, PATH_MAX); As we can see different 'size' arguments are passed. There are also platform specific implementations inside the function, and the use of snprintf is really undesirable. The function name is also misleading. It creates a temporary file, not just a filename. Refactor this routine by changing its name and signature to: char *create_tmp_file(Error **errp) and use g_get_tmp_dir() / g_mkstemp() for a consistent implementation. While we are here, add some comments to mention that /var/tmp is preferred over /tmp on non-win32 hosts. Signed-off-by: Bin Meng <bin.meng@windriver.com> Message-Id: <20221010040432.3380478-2-bin.meng@windriver.com> [kwolf: Fixed incorrect errno negation and iotest 051] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int-common.h | 2 +- block.c | 56 +++++++++++++++++--------------- block/vvfat.c | 7 ++-- tests/qemu-iotests/051 | 3 +- tests/qemu-iotests/051.out | 2 +- tests/qemu-iotests/051.pc.out | 2 +- 6 files changed, 38 insertions(+), 34 deletions(-) diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ static inline BlockDriverState *child_bs(BdrvChild *child) } int bdrv_check_request(int64_t offset, int64_t bytes, Error **errp); -int get_tmp_filename(char *filename, int size); +char *create_tmp_file(Error **errp); void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix, QDict *options); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo) /* * Create a uniquely-named empty temporary file. - * Return 0 upon success, otherwise a negative errno value. + * Return the actual file name used upon success, otherwise NULL. + * This string should be freed with g_free() when not needed any longer. + * + * Note: creating a temporary file for the caller to (re)open is + * inherently racy. Use g_file_open_tmp() instead whenever practical. */ -int get_tmp_filename(char *filename, int size) +char *create_tmp_file(Error **errp) { -#ifdef _WIN32 - char temp_dir[MAX_PATH]; - /* GetTempFileName requires that its output buffer (4th param) - have length MAX_PATH or greater. */ - assert(size >= MAX_PATH); - return (GetTempPath(MAX_PATH, temp_dir) - && GetTempFileName(temp_dir, "qem", 0, filename) - ? 0 : -GetLastError()); -#else int fd; const char *tmpdir; - tmpdir = getenv("TMPDIR"); - if (!tmpdir) { + g_autofree char *filename = NULL; + + tmpdir = g_get_tmp_dir(); +#ifndef _WIN32 + /* + * See commit 69bef79 ("block: use /var/tmp instead of /tmp for -snapshot") + * + * This function is used to create temporary disk images (like -snapshot), + * so the files can become very large. /tmp is often a tmpfs where as + * /var/tmp is usually on a disk, so more appropriate for disk images. + */ + if (!g_strcmp0(tmpdir, "/tmp")) { tmpdir = "/var/tmp"; } - if (snprintf(filename, size, "%s/vl.XXXXXX", tmpdir) >= size) { - return -EOVERFLOW; - } - fd = mkstemp(filename); +#endif + + filename = g_strdup_printf("%s/vl.XXXXXX", tmpdir); + fd = g_mkstemp(filename); if (fd < 0) { - return -errno; + error_setg_errno(errp, errno, "Could not open temporary file '%s'", + filename); + return NULL; } close(fd); - return 0; -#endif + + return g_steal_pointer(&filename); } /* @@ -XXX,XX +XXX,XX @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs, QDict *snapshot_options, Error **errp) { - /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */ - char *tmp_filename = g_malloc0(PATH_MAX + 1); + g_autofree char *tmp_filename = NULL; int64_t total_size; QemuOpts *opts = NULL; BlockDriverState *bs_snapshot = NULL; @@ -XXX,XX +XXX,XX @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs, } /* Create the temporary image */ - ret = get_tmp_filename(tmp_filename, PATH_MAX + 1); - if (ret < 0) { - error_setg_errno(errp, -ret, "Could not get temporary filename"); + tmp_filename = create_tmp_file(errp); + if (!tmp_filename) { goto out; } @@ -XXX,XX +XXX,XX @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs, out: qobject_unref(snapshot_options); - g_free(tmp_filename); return bs_snapshot; } diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ static int enable_write_target(BlockDriverState *bs, Error **errp) array_init(&(s->commits), sizeof(commit_t)); - s->qcow_filename = g_malloc(PATH_MAX); - ret = get_tmp_filename(s->qcow_filename, PATH_MAX); - if (ret < 0) { - error_setg_errno(errp, -ret, "can't create temporary file"); + s->qcow_filename = create_tmp_file(errp); + if (!s->qcow_filename) { + ret = -ENOENT; goto err; } diff --git a/tests/qemu-iotests/051 b/tests/qemu-iotests/051 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/051 +++ b/tests/qemu-iotests/051 @@ -XXX,XX +XXX,XX @@ if [ "${VALGRIND_QEMU_VM}" == "y" ]; then _casenotrun "Valgrind needs a valid TMPDIR for itself" fi VALGRIND_QEMU_VM= \ -TMPDIR=/nonexistent run_qemu -drive driver=null-co,snapshot=on +TMPDIR=/nonexistent run_qemu -drive driver=null-co,snapshot=on | + sed -e "s#'[^']*/vl\.[A-Za-z0-9]\{6\}'#SNAPSHOT_PATH#g" # Using snapshot=on together with read-only=on echo "info block" | diff --git a/tests/qemu-iotests/051.out b/tests/qemu-iotests/051.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/051.out +++ b/tests/qemu-iotests/051.out @@ -XXX,XX +XXX,XX @@ wrote 4096/4096 bytes at offset 0 read 4096/4096 bytes at offset 0 4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Testing: -drive driver=null-co,snapshot=on -QEMU_PROG: -drive driver=null-co,snapshot=on: Could not get temporary filename: No such file or directory +QEMU_PROG: -drive driver=null-co,snapshot=on: Could not open temporary file SNAPSHOT_PATH: No such file or directory Testing: -drive file=TEST_DIR/t.qcow2,snapshot=on,read-only=on,if=none,id=drive0 QEMU X.Y.Z monitor - type 'help' for more information diff --git a/tests/qemu-iotests/051.pc.out b/tests/qemu-iotests/051.pc.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/051.pc.out +++ b/tests/qemu-iotests/051.pc.out @@ -XXX,XX +XXX,XX @@ wrote 4096/4096 bytes at offset 0 read 4096/4096 bytes at offset 0 4 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Testing: -drive driver=null-co,snapshot=on -QEMU_PROG: -drive driver=null-co,snapshot=on: Could not get temporary filename: No such file or directory +QEMU_PROG: -drive driver=null-co,snapshot=on: Could not open temporary file SNAPSHOT_PATH: No such file or directory Testing: -drive file=TEST_DIR/t.qcow2,snapshot=on,read-only=on,if=none,id=drive0 QEMU X.Y.Z monitor - type 'help' for more information -- 2.37.3 From: Hervé Poussineau <hpoussin@reactos.org> 'reserved1' field in bootsector is used to mark volume dirty, or need to verify. Allow writes to bootsector which only changes the 'reserved1' field. This fixes I/O errors on Windows guests. Resolves: https://bugs.launchpad.net/qemu/+bug/1889421 Signed-off-by: Hervé Poussineau <hpoussin@reactos.org> Message-Id: <20221010175511.3414357-2-hpoussin@reactos.org> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vvfat.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ DLOG(checkpoint()); vvfat_close_current_file(s); + if (sector_num == s->offset_to_bootsector && nb_sectors == 1) { + /* + * Write on bootsector. Allow only changing the reserved1 field, + * used to mark volume dirtiness + */ + unsigned char *bootsector = s->first_sectors + + s->offset_to_bootsector * 0x200; + /* + * LATER TODO: if FAT32, this is wrong (see init_directories(), + * which always creates a FAT16 bootsector) + */ + const int reserved1_offset = offsetof(bootsector_t, u.fat16.reserved1); + + for (i = 0; i < 0x200; i++) { + if (i != reserved1_offset && bootsector[i] != buf[i]) { + fprintf(stderr, "Tried to write to protected bootsector\n"); + return -1; + } + } + + /* Update bootsector with the only updatable byte, and return success */ + bootsector[reserved1_offset] = buf[reserved1_offset]; + return 0; + } + /* * Some sanity checks: * - do not allow writing to the boot sector */ - if (sector_num < s->offset_to_fat) return -1; -- 2.37.3 From: Hervé Poussineau <hpoussin@reactos.org> In R/W mode, files with spaces were never created on host side. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1176 Fixes: c79e243ed67683d6d06692bd7040f7394da178b0 Signed-off-by: Hervé Poussineau <hpoussin@reactos.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221010175511.3414357-3-hpoussin@reactos.org> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vvfat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ static bool valid_filename(const unsigned char *name) (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') || c > 127 || - strchr("$%'-_@~`!(){}^#&.+,;=[]", c) != NULL)) + strchr(" $%'-_@~`!(){}^#&.+,;=[]", c) != NULL)) { return false; } -- 2.37.3 From: Sam Li <faithilikerun@gmail.com> Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1193 The commit "Use io_uring_register_ring_fd() to skip fd operations" broke when booting a guest with iothread and io_uring. That is because the io_uring_register_ring_fd() call is made from the main thread instead of IOThread where io_uring_submit() is called. It can not be guaranteed to register the ring fd in the correct thread or unregister the same ring fd if the IOThread is disabled. This optimization is not critical so we will revert previous commit. This reverts commit e2848bc574fe2715c694bf8fe9a1ba7f78a1125a and 77e3f038af1764983087e3551a0fde9951952c4d. Cc: qemu-stable@nongnu.org Signed-off-by: Sam Li <faithilikerun@gmail.com> Message-Id: <20220924144815.5591-1-faithilikerun@gmail.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Tested-by: Dario Faggioli <dfaggioli@suse.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io_uring.c | 13 +------------ meson.build | 1 - 2 files changed, 1 insertion(+), 13 deletions(-) diff --git a/block/io_uring.c b/block/io_uring.c index XXXXXXX..XXXXXXX 100644 --- a/block/io_uring.c +++ b/block/io_uring.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include <liburing.h> #include "block/aio.h" -#include "qemu/error-report.h" #include "qemu/queue.h" #include "block/block.h" #include "block/raw-aio.h" @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "trace.h" - /* io_uring ring size */ #define MAX_ENTRIES 128 @@ -XXX,XX +XXX,XX @@ LuringState *luring_init(Error **errp) } ioq_init(&s->io_q); -#ifdef CONFIG_LIBURING_REGISTER_RING_FD - if (io_uring_register_ring_fd(&s->ring) < 0) { - /* - * Only warn about this error: we will fallback to the non-optimized - * io_uring operations. - */ - warn_report("failed to register linux io_uring ring file descriptor"); - } -#endif - return s; + } void luring_cleanup(LuringState *s) diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ config_host_data.set('CONFIG_LIBNFS', libnfs.found()) config_host_data.set('CONFIG_LIBSSH', libssh.found()) config_host_data.set('CONFIG_LINUX_AIO', libaio.found()) config_host_data.set('CONFIG_LINUX_IO_URING', linux_io_uring.found()) -config_host_data.set('CONFIG_LIBURING_REGISTER_RING_FD', cc.has_function('io_uring_register_ring_fd', prefix: '#include <liburing.h>', dependencies:linux_io_uring)) config_host_data.set('CONFIG_LIBPMEM', libpmem.found()) config_host_data.set('CONFIG_NUMA', numa.found()) config_host_data.set('CONFIG_OPENGL', opengl.found()) -- 2.37.3 From: Li Feng <fengli@smartx.com> If the os is not installed and doesn't have the virtio guest driver, the vhost dev isn't started, so the dev->vdev is NULL. Reproduce: mount a Win 2019 iso, go into the install ui, then resize the virtio-blk device, qemu crash. Signed-off-by: Li Feng <fengli@smartx.com> Message-Id: <20220919121816.3252223-1-fengli@smartx.com> Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/block/vhost-user-blk.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/vhost-user-blk.c +++ b/hw/block/vhost-user-blk.c @@ -XXX,XX +XXX,XX @@ static int vhost_user_blk_handle_config_change(struct vhost_dev *dev) VHostUserBlk *s = VHOST_USER_BLK(dev->vdev); Error *local_err = NULL; + if (!dev->started) { + return 0; + } + ret = vhost_dev_get_config(dev, (uint8_t *)&blkcfg, vdev->config_len, &local_err); if (ret < 0) { -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Unfortunately not all filters use .file child as filtered child. Two exclusions are mirror_top and commit_top. Happily they both are private filters. Bad thing is that this inconsistency is observable through qmp commands query-block / query-named-block-nodes. So, could we just change mirror_top and commit_top to use file child as all other filter driver is an open question. Probably, we could do that with some kind of deprecation period, but how to warn users during it? For now, let's just add a field so we can distinguish them in generic code, it will be used in further commits. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-2-vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int-common.h | 13 +++++++++++++ block/commit.c | 1 + block/mirror.c | 1 + 3 files changed, 15 insertions(+) diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { * (And this filtered child must then be bs->file or bs->backing.) */ bool is_filter; + /* + * Only make sense for filter drivers, for others must be false. + * If true, filtered child is bs->backing. Otherwise it's bs->file. + * Only two internal filters use bs->backing as filtered child and has this + * field set to true: mirror_top and commit_top. + * + * Never create any more such filters! + * + * TODO: imagine how to deprecate this behavior and make all filters work + * similarly using bs->file as filtered child. + */ + bool filtered_child_is_backing; + /* * Set to true if the BlockDriver is a format driver. Format nodes * generally do not expect their children to be other format nodes diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_commit_top = { .bdrv_child_perm = bdrv_commit_top_child_perm, .is_filter = true, + .filtered_child_is_backing = true, }; void commit_start(const char *job_id, BlockDriverState *bs, diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_mirror_top = { .bdrv_child_perm = bdrv_mirror_top_child_perm, .is_filter = true, + .filtered_child_is_backing = true, }; static BlockJob *mirror_start_job( -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Almost all drivers call bdrv_open_child() similarly. Let's create a helper for this. The only not updated drivers that call bdrv_open_child() to set bs->file are raw-format and snapshot-access: raw-format sometimes want to have filtered child but don't set drv->is_filter to true. snapshot-access wants only DATA | PRIMARY Possibly we should implement drv->is_filter_func() handler, to consider raw-format as filter when it works as filter.. But it's another story. Note also, that we decrease assignments to bs->file in code: it helps us restrict modifying this field in further commit. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-3-vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-global-state.h | 3 +++ block.c | 21 +++++++++++++++++++++ block/blkdebug.c | 9 +++------ block/blklogwrites.c | 7 ++----- block/blkreplay.c | 7 ++----- block/blkverify.c | 9 +++------ block/bochs.c | 7 +++---- block/cloop.c | 7 +++---- block/copy-before-write.c | 9 ++++----- block/copy-on-read.c | 9 ++++----- block/crypto.c | 11 ++++++----- block/dmg.c | 7 +++---- block/filter-compress.c | 8 +++----- block/parallels.c | 7 +++---- block/preallocate.c | 9 ++++----- block/qcow.c | 6 ++---- block/qcow2.c | 8 ++++---- block/qed.c | 8 ++++---- block/replication.c | 8 +++----- block/throttle.c | 8 +++----- block/vdi.c | 7 +++---- block/vhdx.c | 7 +++---- block/vmdk.c | 7 +++---- block/vpc.c | 7 +++---- 24 files changed, 95 insertions(+), 101 deletions(-) diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_open_child(const char *filename, const BdrvChildClass *child_class, BdrvChildRole child_role, bool allow_none, Error **errp); +int bdrv_open_file_child(const char *filename, + QDict *options, const char *bdref_key, + BlockDriverState *parent, Error **errp); BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp); int bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd, Error **errp); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_open_child(const char *filename, errp); } +/* + * Wrapper on bdrv_open_child() for most popular case: open primary child of bs. + */ +int bdrv_open_file_child(const char *filename, + QDict *options, const char *bdref_key, + BlockDriverState *parent, Error **errp) +{ + BdrvChildRole role; + + /* commit_top and mirror_top don't use this function */ + assert(!parent->drv->filtered_child_is_backing); + + role = parent->drv->is_filter ? + (BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY) : BDRV_CHILD_IMAGE; + + parent->file = bdrv_open_child(filename, options, bdref_key, parent, + &child_of_bds, role, false, errp); + + return parent->file ? 0 : -EINVAL; +} + /* * TODO Future callers may need to specify parent/child_class in order for * option inheritance to work. Existing callers use it for the root node. diff --git a/block/blkdebug.c b/block/blkdebug.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -XXX,XX +XXX,XX @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags, } /* Open the image file */ - bs->file = bdrv_open_child(qemu_opt_get(opts, "x-image"), options, "image", - bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - ret = -EINVAL; + ret = bdrv_open_file_child(qemu_opt_get(opts, "x-image"), options, "image", + bs, errp); + if (ret < 0) { goto out; } diff --git a/block/blklogwrites.c b/block/blklogwrites.c index XXXXXXX..XXXXXXX 100644 --- a/block/blklogwrites.c +++ b/block/blklogwrites.c @@ -XXX,XX +XXX,XX @@ static int blk_log_writes_open(BlockDriverState *bs, QDict *options, int flags, } /* Open the file */ - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, false, - errp); - if (!bs->file) { - ret = -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { goto fail; } diff --git a/block/blkreplay.c b/block/blkreplay.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkreplay.c +++ b/block/blkreplay.c @@ -XXX,XX +XXX,XX @@ static int blkreplay_open(BlockDriverState *bs, QDict *options, int flags, int ret; /* Open the image file */ - bs->file = bdrv_open_child(NULL, options, "image", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - ret = -EINVAL; + ret = bdrv_open_file_child(NULL, options, "image", bs, errp); + if (ret < 0) { goto fail; } diff --git a/block/blkverify.c b/block/blkverify.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkverify.c +++ b/block/blkverify.c @@ -XXX,XX +XXX,XX @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags, } /* Open the raw file */ - bs->file = bdrv_open_child(qemu_opt_get(opts, "x-raw"), options, "raw", - bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - ret = -EINVAL; + ret = bdrv_open_file_child(qemu_opt_get(opts, "x-raw"), options, "raw", + bs, errp); + if (ret < 0) { goto fail; } diff --git a/block/bochs.c b/block/bochs.c index XXXXXXX..XXXXXXX 100644 --- a/block/bochs.c +++ b/block/bochs.c @@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, return ret; } - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } ret = bdrv_pread(bs->file, 0, sizeof(bochs), &bochs, 0); diff --git a/block/cloop.c b/block/cloop.c index XXXXXXX..XXXXXXX 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, return ret; } - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } /* read header */ diff --git a/block/copy-before-write.c b/block/copy-before-write.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-before-write.c +++ b/block/copy-before-write.c @@ -XXX,XX +XXX,XX @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags, int64_t cluster_size; g_autoptr(BlockdevOptions) full_opts = NULL; BlockdevOptionsCbw *opts; + int ret; full_opts = cbw_parse_options(options, errp); if (!full_opts) { @@ -XXX,XX +XXX,XX @@ static int cbw_open(BlockDriverState *bs, QDict *options, int flags, assert(full_opts->driver == BLOCKDEV_DRIVER_COPY_BEFORE_WRITE); opts = &full_opts->u.copy_before_write; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } s->target = bdrv_open_child(NULL, options, "target", bs, &child_of_bds, diff --git a/block/copy-on-read.c b/block/copy-on-read.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -XXX,XX +XXX,XX @@ static int cor_open(BlockDriverState *bs, QDict *options, int flags, BDRVStateCOR *state = bs->opaque; /* Find a bottom node name, if any */ const char *bottom_node = qdict_get_try_str(options, "bottom"); + int ret; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } bs->supported_read_flags = BDRV_REQ_PREFETCH; diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static int block_crypto_open_generic(QCryptoBlockFormat format, { BlockCrypto *crypto = bs->opaque; QemuOpts *opts = NULL; - int ret = -EINVAL; + int ret; QCryptoBlockOpenOptions *open_opts = NULL; unsigned int cflags = 0; QDict *cryptoopts = NULL; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } bs->supported_write_flags = BDRV_REQ_FUA & @@ -XXX,XX +XXX,XX @@ static int block_crypto_open_generic(QCryptoBlockFormat format, opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort); if (!qemu_opts_absorb_qdict(opts, options, errp)) { + ret = -EINVAL; goto cleanup; } @@ -XXX,XX +XXX,XX @@ static int block_crypto_open_generic(QCryptoBlockFormat format, open_opts = block_crypto_open_opts_init(cryptoopts, errp); if (!open_opts) { + ret = -EINVAL; goto cleanup; } diff --git a/block/dmg.c b/block/dmg.c index XXXXXXX..XXXXXXX 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -XXX,XX +XXX,XX @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags, return ret; } - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } block_module_load_one("dmg-bz2"); diff --git a/block/filter-compress.c b/block/filter-compress.c index XXXXXXX..XXXXXXX 100644 --- a/block/filter-compress.c +++ b/block/filter-compress.c @@ -XXX,XX +XXX,XX @@ static int compress_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - return -EINVAL; + int ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } if (!bs->file->bs->drv || !block_driver_can_compress(bs->file->bs->drv)) { diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, Error *local_err = NULL; char *buf; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } ret = bdrv_pread(bs->file, 0, sizeof(ph), &ph, 0); diff --git a/block/preallocate.c b/block/preallocate.c index XXXXXXX..XXXXXXX 100644 --- a/block/preallocate.c +++ b/block/preallocate.c @@ -XXX,XX +XXX,XX @@ static int preallocate_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { BDRVPreallocateState *s = bs->opaque; + int ret; /* * s->data_end and friends should be initialized on permission update. @@ -XXX,XX +XXX,XX @@ static int preallocate_open(BlockDriverState *bs, QDict *options, int flags, */ s->file_end = s->zero_start = s->data_end = -EINVAL; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } if (!preallocate_absorb_opts(&s->opts, options, bs->file->bs, errp)) { diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, qdict_extract_subqdict(options, &encryptopts, "encrypt."); encryptfmt = qdict_get_try_str(encryptopts, "format"); - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - ret = -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { goto fail; } diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags, .errp = errp, .ret = -EINPROGRESS }; + int ret; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } /* Initialise locks */ diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags, .errp = errp, .ret = -EINPROGRESS }; + int ret; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } bdrv_qed_init_state(bs); diff --git a/block/replication.c b/block/replication.c index XXXXXXX..XXXXXXX 100644 --- a/block/replication.c +++ b/block/replication.c @@ -XXX,XX +XXX,XX @@ static int replication_open(BlockDriverState *bs, QDict *options, const char *mode; const char *top_id; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } ret = -EINVAL; diff --git a/block/throttle.c b/block/throttle.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle.c +++ b/block/throttle.c @@ -XXX,XX +XXX,XX @@ static int throttle_open(BlockDriverState *bs, QDict *options, char *group; int ret; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, - false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } bs->supported_write_flags = bs->file->bs->supported_write_flags | BDRV_REQ_WRITE_UNCHANGED; diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, int ret; QemuUUID uuid_link, uuid_parent; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } logout("\n"); diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, uint64_t signature; Error *local_err = NULL; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } s->bat = NULL; diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags, BDRVVmdkState *s = bs->opaque; uint32_t magic; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } buf = vmdk_read_desc(bs->file, 0, errp); diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, int ret; int64_t bs_size; - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_IMAGE, false, errp); - if (!bs->file) { - return -EINVAL; + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); + if (ret < 0) { + return ret; } opts = qemu_opts_create(&vpc_runtime_opts, NULL, 0, &error_abort); -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> We don't need to remove bs->file, generic layer takes care of it. No other driver cares to remove bs->file on failure by hand. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-4-vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/blklogwrites.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/block/blklogwrites.c b/block/blklogwrites.c index XXXXXXX..XXXXXXX 100644 --- a/block/blklogwrites.c +++ b/block/blklogwrites.c @@ -XXX,XX +XXX,XX @@ fail_log: s->log_file = NULL; } fail: - if (ret < 0) { - bdrv_unref_child(bs, bs->file); - bs->file = NULL; - } qemu_opts_del(opts); return ret; } -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> test_parallel_perm_update() does two things that we are going to restrict in the near future: 1. It updates bs->file field by hand. bs->file will be managed automatically by generic code (together with bs->children list). Let's better refactor our "tricky" bds to have own state where one of children is linked as "selected". This also looks less "tricky", so avoid using this word. 2. It create FILTERED children that are not PRIMARY. Except for tests all FILTERED children in the Qemu block layer are always PRIMARY as well. We are going to formalize this rule, so let's better use DATA children here. 3. It creates more than one FILTERED child, which is already abandoned in BDRV_CHILD_FILTERED's description. While being here, update the picture to better correspond to the test code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-5-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/unit/test-bdrv-graph-mod.c | 80 +++++++++++++++++++------------- 1 file changed, 49 insertions(+), 31 deletions(-) diff --git a/tests/unit/test-bdrv-graph-mod.c b/tests/unit/test-bdrv-graph-mod.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-bdrv-graph-mod.c +++ b/tests/unit/test-bdrv-graph-mod.c @@ -XXX,XX +XXX,XX @@ static void test_parallel_exclusive_write(void) bdrv_unref(top); } -static void write_to_file_perms(BlockDriverState *bs, BdrvChild *c, - BdrvChildRole role, - BlockReopenQueue *reopen_queue, - uint64_t perm, uint64_t shared, - uint64_t *nperm, uint64_t *nshared) +/* + * write-to-selected node may have several DATA children, one of them may be + * "selected". Exclusive write permission is taken on selected child. + * + * We don't realize write handler itself, as we need only to test how permission + * update works. + */ +typedef struct BDRVWriteToSelectedState { + BdrvChild *selected; +} BDRVWriteToSelectedState; + +static void write_to_selected_perms(BlockDriverState *bs, BdrvChild *c, + BdrvChildRole role, + BlockReopenQueue *reopen_queue, + uint64_t perm, uint64_t shared, + uint64_t *nperm, uint64_t *nshared) { - if (bs->file && c == bs->file) { + BDRVWriteToSelectedState *s = bs->opaque; + + if (s->selected && c == s->selected) { *nperm = BLK_PERM_WRITE; *nshared = BLK_PERM_ALL & ~BLK_PERM_WRITE; } else { @@ -XXX,XX +XXX,XX @@ static void write_to_file_perms(BlockDriverState *bs, BdrvChild *c, } } -static BlockDriver bdrv_write_to_file = { - .format_name = "tricky-perm", - .bdrv_child_perm = write_to_file_perms, +static BlockDriver bdrv_write_to_selected = { + .format_name = "write-to-selected", + .instance_size = sizeof(BDRVWriteToSelectedState), + .bdrv_child_perm = write_to_selected_perms, }; @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_write_to_file = { * The following test shows that topological-sort order is required for * permission update, simple DFS is not enough. * - * Consider the block driver which has two filter children: one active - * with exclusive write access and one inactive with no specific - * permissions. + * Consider the block driver (write-to-selected) which has two children: one is + * selected so we have exclusive write access to it and for the other one we + * don't need any specific permissions. * * And, these two children has a common base child, like this: + * (additional "top" on top is used in test just because the only public + * function to update permission should get a specific child to update. + * Making bdrv_refresh_perms() public just for this test isn't worth it) * - * ┌─────┐ ┌──────┐ - * │ fl2 │ ◀── │ top │ - * └─────┘ └──────┘ + * ┌─────┐ ┌───────────────────┐ ┌─────┐ + * │ fl2 │ ◀── │ write-to-selected │ ◀── │ top │ + * └─────┘ └───────────────────┘ └─────┘ * │ │ * │ │ w * │ ▼ @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_write_to_file = { * * So, exclusive write is propagated. * - * Assume, we want to make fl2 active instead of fl1. - * So, we set some option for top driver and do permission update. + * Assume, we want to select fl2 instead of fl1. + * So, we set some option for write-to-selected driver and do permission update. * * With simple DFS, if permission update goes first through - * top->fl1->base branch it will succeed: it firstly drop exclusive write - * permissions and than apply them for another BdrvChildren. - * But if permission update goes first through top->fl2->base branch it - * will fail, as when we try to update fl2->base child, old not yet + * write-to-selected -> fl1 -> base branch it will succeed: it firstly drop + * exclusive write permissions and than apply them for another BdrvChildren. + * But if permission update goes first through write-to-selected -> fl2 -> base + * branch it will fail, as when we try to update fl2->base child, old not yet * updated fl1->base child will be in conflict. * * With topological-sort order we always update parents before children, so fl1 @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_write_to_file = { static void test_parallel_perm_update(void) { BlockDriverState *top = no_perm_node("top"); - BlockDriverState *tricky = - bdrv_new_open_driver(&bdrv_write_to_file, "tricky", BDRV_O_RDWR, + BlockDriverState *ws = + bdrv_new_open_driver(&bdrv_write_to_selected, "ws", BDRV_O_RDWR, &error_abort); + BDRVWriteToSelectedState *s = ws->opaque; BlockDriverState *base = no_perm_node("base"); BlockDriverState *fl1 = pass_through_node("fl1"); BlockDriverState *fl2 = pass_through_node("fl2"); @@ -XXX,XX +XXX,XX @@ static void test_parallel_perm_update(void) */ bdrv_ref(base); - bdrv_attach_child(top, tricky, "file", &child_of_bds, BDRV_CHILD_DATA, + bdrv_attach_child(top, ws, "file", &child_of_bds, BDRV_CHILD_DATA, &error_abort); - c_fl1 = bdrv_attach_child(tricky, fl1, "first", &child_of_bds, - BDRV_CHILD_FILTERED, &error_abort); - c_fl2 = bdrv_attach_child(tricky, fl2, "second", &child_of_bds, - BDRV_CHILD_FILTERED, &error_abort); + c_fl1 = bdrv_attach_child(ws, fl1, "first", &child_of_bds, + BDRV_CHILD_DATA, &error_abort); + c_fl2 = bdrv_attach_child(ws, fl2, "second", &child_of_bds, + BDRV_CHILD_DATA, &error_abort); bdrv_attach_child(fl1, base, "backing", &child_of_bds, BDRV_CHILD_FILTERED, &error_abort); bdrv_attach_child(fl2, base, "backing", &child_of_bds, BDRV_CHILD_FILTERED, &error_abort); /* Select fl1 as first child to be active */ - tricky->file = c_fl1; + s->selected = c_fl1; bdrv_child_refresh_perms(top, top->children.lh_first, &error_abort); assert(c_fl1->perm & BLK_PERM_WRITE); assert(!(c_fl2->perm & BLK_PERM_WRITE)); /* Now, try to switch active child and update permissions */ - tricky->file = c_fl2; + s->selected = c_fl2; bdrv_child_refresh_perms(top, top->children.lh_first, &error_abort); assert(c_fl2->perm & BLK_PERM_WRITE); assert(!(c_fl1->perm & BLK_PERM_WRITE)); /* Switch once more, to not care about real child order in the list */ - tricky->file = c_fl1; + s->selected = c_fl1; bdrv_child_refresh_perms(top, top->children.lh_first, &error_abort); assert(c_fl1->perm & BLK_PERM_WRITE); -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> We do add COW child to the node. In future we are going to forbid adding COW child to the node that doesn't support backing. So, fix it here now. Don't worry about setting bs->backing itself: in further commit we'll update the block-layer to automatically set/unset this field in generic code. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-6-vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/unit/test-bdrv-drain.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-bdrv-drain.c +++ b/tests/unit/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_replace_test_co_drain_end(BlockDriverState *bs) static BlockDriver bdrv_replace_test = { .format_name = "replace_test", .instance_size = sizeof(BDRVReplaceTestState), + .supports_backing = true, .bdrv_close = bdrv_replace_test_close, .bdrv_co_preadv = bdrv_replace_test_co_preadv, -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> bdrv_pass_through is used as filter, even all node variables has corresponding names. We want to append it, so it should be backing-child-based filter like mirror_top. So, in test_update_perm_tree, first child should be DATA, as we don't want filters with two filtered children. bdrv_exclusive_writer is used as a filter once. So it should be filter anyway. We want to append it, so it should be backing-child-based fitler too. Make all FILTERED children to be PRIMARY as well. We are going to force this rule by assertion soon. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-7-vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int-common.h | 5 +++-- tests/unit/test-bdrv-graph-mod.c | 24 +++++++++++++++++------- 2 files changed, 20 insertions(+), 9 deletions(-) diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { /* * Only make sense for filter drivers, for others must be false. * If true, filtered child is bs->backing. Otherwise it's bs->file. - * Only two internal filters use bs->backing as filtered child and has this - * field set to true: mirror_top and commit_top. + * Two internal filters use bs->backing as filtered child and has this + * field set to true: mirror_top and commit_top. There also two such test + * filters in tests/unit/test-bdrv-graph-mod.c. * * Never create any more such filters! * diff --git a/tests/unit/test-bdrv-graph-mod.c b/tests/unit/test-bdrv-graph-mod.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-bdrv-graph-mod.c +++ b/tests/unit/test-bdrv-graph-mod.c @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_pass_through = { .format_name = "pass-through", + .is_filter = true, + .filtered_child_is_backing = true, .bdrv_child_perm = bdrv_default_perms, }; @@ -XXX,XX +XXX,XX @@ static void exclusive_write_perms(BlockDriverState *bs, BdrvChild *c, static BlockDriver bdrv_exclusive_writer = { .format_name = "exclusive-writer", + .is_filter = true, + .filtered_child_is_backing = true, .bdrv_child_perm = exclusive_write_perms, }; @@ -XXX,XX +XXX,XX @@ static void test_update_perm_tree(void) blk_insert_bs(root, bs, &error_abort); bdrv_attach_child(filter, bs, "child", &child_of_bds, - BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, &error_abort); + BDRV_CHILD_DATA, &error_abort); ret = bdrv_append(filter, bs, NULL); g_assert_cmpint(ret, <, 0); @@ -XXX,XX +XXX,XX @@ static void test_parallel_exclusive_write(void) */ bdrv_ref(base); - bdrv_attach_child(top, fl1, "backing", &child_of_bds, BDRV_CHILD_DATA, + bdrv_attach_child(top, fl1, "backing", &child_of_bds, + BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, &error_abort); - bdrv_attach_child(fl1, base, "backing", &child_of_bds, BDRV_CHILD_FILTERED, + bdrv_attach_child(fl1, base, "backing", &child_of_bds, + BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, &error_abort); - bdrv_attach_child(fl2, base, "backing", &child_of_bds, BDRV_CHILD_FILTERED, + bdrv_attach_child(fl2, base, "backing", &child_of_bds, + BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, &error_abort); bdrv_replace_node(fl1, fl2, &error_abort); @@ -XXX,XX +XXX,XX @@ static void test_parallel_perm_update(void) BDRV_CHILD_DATA, &error_abort); c_fl2 = bdrv_attach_child(ws, fl2, "second", &child_of_bds, BDRV_CHILD_DATA, &error_abort); - bdrv_attach_child(fl1, base, "backing", &child_of_bds, BDRV_CHILD_FILTERED, + bdrv_attach_child(fl1, base, "backing", &child_of_bds, + BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, &error_abort); - bdrv_attach_child(fl2, base, "backing", &child_of_bds, BDRV_CHILD_FILTERED, + bdrv_attach_child(fl2, base, "backing", &child_of_bds, + BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, &error_abort); /* Select fl1 as first child to be active */ @@ -XXX,XX +XXX,XX @@ static void test_append_greedy_filter(void) BlockDriverState *base = no_perm_node("base"); BlockDriverState *fl = exclusive_writer_node("fl1"); - bdrv_attach_child(top, base, "backing", &child_of_bds, BDRV_CHILD_COW, + bdrv_attach_child(top, base, "backing", &child_of_bds, + BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY, &error_abort); bdrv_append(fl, base, &error_abort); -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Make the informal rules formal. In further commit we'll add corresponding assertions. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-8-vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-common.h | 39 ++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/include/block/block-common.h b/include/block/block-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-common.h +++ b/include/block/block-common.h @@ -XXX,XX +XXX,XX @@ enum { * * At least one of DATA, METADATA, FILTERED, or COW must be set for * every child. + * + * + * = Connection with bs->children, bs->file and bs->backing fields = + * + * 1. Filters + * + * Filter drivers have drv->is_filter = true. + * + * Filter node has exactly one FILTERED|PRIMARY child, and may have other + * children which must not have these bits (one example is the + * copy-before-write filter, which also has its target DATA child). + * + * Filter nodes never have COW children. + * + * For most filters, the filtered child is linked in bs->file, bs->backing is + * NULL. For some filters (as an exception), it is the other way around; those + * drivers will have drv->filtered_child_is_backing set to true (see that + * field’s documentation for what drivers this concerns) + * + * 2. "raw" driver (block/raw-format.c) + * + * Formally it's not a filter (drv->is_filter = false) + * + * bs->backing is always NULL + * + * Only has one child, linked in bs->file. Its role is either FILTERED|PRIMARY + * (like filter) or DATA|PRIMARY depending on options. + * + * 3. Other drivers + * + * Don't have any FILTERED children. + * + * May have at most one COW child. In this case it's linked in bs->backing. + * Otherwise bs->backing is NULL. COW child is never PRIMARY. + * + * May have at most one PRIMARY child. In this case it's linked in bs->file. + * Otherwise bs->file is NULL. + * + * May also have some other children that don't have the PRIMARY or COW bit set. */ enum BdrvChildRoleBits { /* -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Actually what we chose is a primary child. Let's stress it in the code. We are going to drop indirect pointer logic here in future. Actually this commit simplifies the future work: we drop use of indirection in the assertion now. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-9-vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/snapshot.c | 30 ++++++++++-------------------- 1 file changed, 10 insertions(+), 20 deletions(-) diff --git a/block/snapshot.c b/block/snapshot.c index XXXXXXX..XXXXXXX 100644 --- a/block/snapshot.c +++ b/block/snapshot.c @@ -XXX,XX +XXX,XX @@ bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs, static BdrvChild **bdrv_snapshot_fallback_ptr(BlockDriverState *bs) { BdrvChild **fallback; - BdrvChild *child; + BdrvChild *child = bdrv_primary_child(bs); - /* - * The only BdrvChild pointers that are safe to modify (and which - * we can thus return a reference to) are bs->file and - * bs->backing. - */ - fallback = &bs->file; - if (!*fallback && bs->drv && bs->drv->is_filter) { - fallback = &bs->backing; - } - - if (!*fallback) { + /* We allow fallback only to primary child */ + if (!child) { return NULL; } + fallback = (child == bs->file ? &bs->file : &bs->backing); + assert(*fallback == child); /* * Check that there are no other children that would need to be @@ -XXX,XX +XXX,XX @@ int bdrv_snapshot_goto(BlockDriverState *bs, } /* - * fallback_ptr is &bs->file or &bs->backing. *fallback_ptr - * was closed above and set to NULL, but the .bdrv_open() call - * has opened it again, because we set the respective option - * (with the qdict_put_str() call above). - * Assert that .bdrv_open() has attached some child on - * *fallback_ptr, and that it has attached the one we wanted - * it to (i.e., fallback_bs). + * fallback was a primary child. It was closed above and set to NULL, + * but the .bdrv_open() call has opened it again, because we set the + * respective option (with the qdict_put_str() call above). + * Assert that .bdrv_open() has attached the right BDS as primary child. */ - assert(*fallback_ptr && fallback_bs == (*fallback_ptr)->bs); + assert(bdrv_primary_bs(bs) == fallback_bs); bdrv_unref(fallback_bs); return ret; } -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> We are going to reimplement this behavior (clear bs->file / bs->backing pointers automatically when child->bs is cleared) in a nicer way, see further commit "block: Manipulate bs->file / bs->backing pointers in .attach/.detach". With this revert we bring back a problem that was fixed by b0a9f6fed3d8. Still the problem was mostly theoretical, we don't have concrete bugs fixed by b0a9f6fed3d8, we don't have a specific test. Probably some accidental failures of iotests are related. Alternatively, we may merge this and following three reverts into final "block: Manipulate ..." to avoid any kind of regression. But seems that in this case having separate clear revert commits is better. This reverts commit b0a9f6fed3d80de610dcd04a7e66f9f30a04174f. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-10-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 102 +++++++++++++------------------------------------------- 1 file changed, 23 insertions(+), 79 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static BlockDriverState *bdrv_open_inherit(const char *filename, static bool bdrv_recurse_has_child(BlockDriverState *bs, BlockDriverState *child); -static void bdrv_child_free(BdrvChild *child); static void bdrv_replace_child_noperm(BdrvChild **child, - BlockDriverState *new_bs, - bool free_empty_child); + BlockDriverState *new_bs); static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, BdrvChild *child, Transaction *tran); @@ -XXX,XX +XXX,XX @@ typedef struct BdrvReplaceChildState { BdrvChild *child; BdrvChild **childp; BlockDriverState *old_bs; - bool free_empty_child; } BdrvReplaceChildState; static void bdrv_replace_child_commit(void *opaque) @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_commit(void *opaque) BdrvReplaceChildState *s = opaque; GLOBAL_STATE_CODE(); - if (s->free_empty_child && !s->child->bs) { - bdrv_child_free(s->child); - } bdrv_unref(s->old_bs); } @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_abort(void *opaque) * modify the BdrvChild * pointer we indirectly pass to it, i.e. it * will not modify s->child. From that perspective, it does not matter * whether we pass s->childp or &s->child. + * (TODO: Right now, bdrv_replace_child_noperm() never modifies that + * pointer anyway (though it will in the future), so at this point it + * absolutely does not matter whether we pass s->childp or &s->child.) * (2) If new_bs is not NULL, s->childp will be NULL. We then cannot use * it here. * (3) If new_bs is NULL, *s->childp will have been NULLed by * bdrv_replace_child_tran()'s bdrv_replace_child_noperm() call, and we * must not pass a NULL *s->childp here. + * (TODO: In its current state, bdrv_replace_child_noperm() will not + * have NULLed *s->childp, so this does not apply yet. It will in the + * future.) * * So whether new_bs was NULL or not, we cannot pass s->childp here; and in * any case, there is no reason to pass it anyway. */ - bdrv_replace_child_noperm(&s->child, s->old_bs, true); - /* - * The child was pre-existing, so s->old_bs must be non-NULL, and - * s->child thus must not have been freed - */ - assert(s->child != NULL); - if (!new_bs) { - /* As described above, *s->childp was cleared, so restore it */ - assert(s->childp != NULL); - *s->childp = s->child; - } + bdrv_replace_child_noperm(&s->child, s->old_bs); bdrv_unref(new_bs); } @@ -XXX,XX +XXX,XX @@ static TransactionActionDrv bdrv_replace_child_drv = { * * The function doesn't update permissions, caller is responsible for this. * - * (*childp)->bs must not be NULL. - * * Note that if new_bs == NULL, @childp is stored in a state object attached * to @tran, so that the old child can be reinstated in the abort handler. * Therefore, if @new_bs can be NULL, @childp must stay valid until the * transaction is committed or aborted. * - * If @free_empty_child is true and @new_bs is NULL, the BdrvChild is - * freed (on commit). @free_empty_child should only be false if the - * caller will free the BDrvChild themselves (which may be important - * if this is in turn called in another transactional context). + * (TODO: The reinstating does not happen yet, but it will once + * bdrv_replace_child_noperm() NULLs *childp when new_bs is NULL.) */ static void bdrv_replace_child_tran(BdrvChild **childp, BlockDriverState *new_bs, - Transaction *tran, - bool free_empty_child) + Transaction *tran) { BdrvReplaceChildState *s = g_new(BdrvReplaceChildState, 1); *s = (BdrvReplaceChildState) { .child = *childp, .childp = new_bs == NULL ? childp : NULL, .old_bs = (*childp)->bs, - .free_empty_child = free_empty_child, }; tran_add(tran, &bdrv_replace_child_drv, s); - /* The abort handler relies on this */ - assert(s->old_bs != NULL); - if (new_bs) { bdrv_ref(new_bs); } - /* - * Pass free_empty_child=false, we will free the child (if - * necessary) in bdrv_replace_child_commit() (if our - * @free_empty_child parameter was true). - */ - bdrv_replace_child_noperm(childp, new_bs, false); + bdrv_replace_child_noperm(childp, new_bs); /* old_bs reference is transparently moved from *childp to @s */ } @@ -XXX,XX +XXX,XX @@ uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm) return permissions[qapi_perm]; } -/** - * Replace (*childp)->bs by @new_bs. - * - * If @new_bs is NULL, *childp will be set to NULL, too: BDS parents - * generally cannot handle a BdrvChild with .bs == NULL, so clearing - * BdrvChild.bs should generally immediately be followed by the - * BdrvChild pointer being cleared as well. - * - * If @free_empty_child is true and @new_bs is NULL, the BdrvChild is - * freed. @free_empty_child should only be false if the caller will - * free the BdrvChild themselves (this may be important in a - * transactional context, where it may only be freed on commit). - */ static void bdrv_replace_child_noperm(BdrvChild **childp, - BlockDriverState *new_bs, - bool free_empty_child) + BlockDriverState *new_bs) { BdrvChild *child = *childp; BlockDriverState *old_bs = child->bs; @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild **childp, } child->bs = new_bs; - if (!new_bs) { - *childp = NULL; - } if (new_bs) { assert_bdrv_graph_writable(new_bs); @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild **childp, bdrv_parent_drained_end_single(child); drain_saldo++; } - - if (free_empty_child && !child->bs) { - bdrv_child_free(child); - } } /** @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_child_common_abort(void *opaque) BlockDriverState *bs = child->bs; GLOBAL_STATE_CODE(); - /* - * Pass free_empty_child=false, because we still need the child - * for the AioContext operations on the parent below; those - * BdrvChildClass methods all work on a BdrvChild object, so we - * need to keep it as an empty shell (after this function, it will - * not be attached to any parent, and it will not have a .bs). - */ - bdrv_replace_child_noperm(s->child, NULL, false); + bdrv_replace_child_noperm(s->child, NULL); if (bdrv_get_aio_context(bs) != s->old_child_ctx) { bdrv_try_set_aio_context(bs, s->old_child_ctx, &error_abort); @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_child_common_abort(void *opaque) bdrv_unref(bs); bdrv_child_free(child); + *s->child = NULL; } static TransactionActionDrv bdrv_attach_child_common_drv = { @@ -XXX,XX +XXX,XX @@ static int bdrv_attach_child_common(BlockDriverState *child_bs, } bdrv_ref(child_bs); - bdrv_replace_child_noperm(&new_child, child_bs, true); - /* child_bs was non-NULL, so new_child must not have been freed */ - assert(new_child != NULL); + bdrv_replace_child_noperm(&new_child, child_bs); *child = new_child; @@ -XXX,XX +XXX,XX @@ static void bdrv_detach_child(BdrvChild **childp) BlockDriverState *old_bs = (*childp)->bs; GLOBAL_STATE_CODE(); - bdrv_replace_child_noperm(childp, NULL, true); + bdrv_replace_child_noperm(childp, NULL); + bdrv_child_free(*childp); if (old_bs) { /* @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, } if (child->bs) { - /* - * Pass free_empty_child=false, we will free the child in - * bdrv_remove_filter_or_cow_child_commit() - */ - bdrv_replace_child_tran(childp, NULL, tran, false); + bdrv_replace_child_tran(childp, NULL, tran); } s = g_new(BdrvRemoveFilterOrCowChild, 1); @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, .is_backing = (childp == &bs->backing), }; tran_add(tran, &bdrv_remove_filter_or_cow_child_drv, s); + + *childp = NULL; } /* @@ -XXX,XX +XXX,XX @@ static int bdrv_replace_node_noperm(BlockDriverState *from, * Passing a pointer to the local variable @c is fine here, because * @to is not NULL, and so &c will not be attached to the transaction. */ - bdrv_replace_child_tran(&c, to, tran, true); + bdrv_replace_child_tran(&c, to, tran); } return 0; @@ -XXX,XX +XXX,XX @@ int bdrv_replace_child_bs(BdrvChild *child, BlockDriverState *new_bs, bdrv_drained_begin(old_bs); bdrv_drained_begin(new_bs); - bdrv_replace_child_tran(&child, new_bs, tran, true); - /* @new_bs must have been non-NULL, so @child must not have been freed */ - assert(child != NULL); + bdrv_replace_child_tran(&child, new_bs, tran); found = g_hash_table_new(NULL, NULL); refresh_list = bdrv_topological_dfs(refresh_list, found, old_bs); -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> That's a preparation to previously reverted "block: Let replace_child_noperm free children". Drop it too, we don't need it for a new approach. This reverts commit 82b54cf51656bf3cd5ed1ac549e8a1085a0e3290. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-11-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 81 +++++++-------------------------------------------------- 1 file changed, 10 insertions(+), 71 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int bdrv_drv_set_perm(BlockDriverState *bs, uint64_t perm, typedef struct BdrvReplaceChildState { BdrvChild *child; - BdrvChild **childp; BlockDriverState *old_bs; } BdrvReplaceChildState; @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_abort(void *opaque) BlockDriverState *new_bs = s->child->bs; GLOBAL_STATE_CODE(); - /* - * old_bs reference is transparently moved from @s to s->child. - * - * Pass &s->child here instead of s->childp, because: - * (1) s->old_bs must be non-NULL, so bdrv_replace_child_noperm() will not - * modify the BdrvChild * pointer we indirectly pass to it, i.e. it - * will not modify s->child. From that perspective, it does not matter - * whether we pass s->childp or &s->child. - * (TODO: Right now, bdrv_replace_child_noperm() never modifies that - * pointer anyway (though it will in the future), so at this point it - * absolutely does not matter whether we pass s->childp or &s->child.) - * (2) If new_bs is not NULL, s->childp will be NULL. We then cannot use - * it here. - * (3) If new_bs is NULL, *s->childp will have been NULLed by - * bdrv_replace_child_tran()'s bdrv_replace_child_noperm() call, and we - * must not pass a NULL *s->childp here. - * (TODO: In its current state, bdrv_replace_child_noperm() will not - * have NULLed *s->childp, so this does not apply yet. It will in the - * future.) - * - * So whether new_bs was NULL or not, we cannot pass s->childp here; and in - * any case, there is no reason to pass it anyway. - */ + /* old_bs reference is transparently moved from @s to @s->child */ bdrv_replace_child_noperm(&s->child, s->old_bs); bdrv_unref(new_bs); } @@ -XXX,XX +XXX,XX @@ static TransactionActionDrv bdrv_replace_child_drv = { * Note: real unref of old_bs is done only on commit. * * The function doesn't update permissions, caller is responsible for this. - * - * Note that if new_bs == NULL, @childp is stored in a state object attached - * to @tran, so that the old child can be reinstated in the abort handler. - * Therefore, if @new_bs can be NULL, @childp must stay valid until the - * transaction is committed or aborted. - * - * (TODO: The reinstating does not happen yet, but it will once - * bdrv_replace_child_noperm() NULLs *childp when new_bs is NULL.) */ -static void bdrv_replace_child_tran(BdrvChild **childp, - BlockDriverState *new_bs, +static void bdrv_replace_child_tran(BdrvChild *child, BlockDriverState *new_bs, Transaction *tran) { BdrvReplaceChildState *s = g_new(BdrvReplaceChildState, 1); *s = (BdrvReplaceChildState) { - .child = *childp, - .childp = new_bs == NULL ? childp : NULL, - .old_bs = (*childp)->bs, + .child = child, + .old_bs = child->bs, }; tran_add(tran, &bdrv_replace_child_drv, s); if (new_bs) { bdrv_ref(new_bs); } - bdrv_replace_child_noperm(childp, new_bs); - /* old_bs reference is transparently moved from *childp to @s */ + bdrv_replace_child_noperm(&child, new_bs); + /* old_bs reference is transparently moved from @child to @s */ } /* @@ -XXX,XX +XXX,XX @@ static bool should_update_child(BdrvChild *c, BlockDriverState *to) typedef struct BdrvRemoveFilterOrCowChild { BdrvChild *child; - BlockDriverState *bs; bool is_backing; } BdrvRemoveFilterOrCowChild; @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_filter_or_cow_child_commit(void *opaque) bdrv_child_free(s->child); } -static void bdrv_remove_filter_or_cow_child_clean(void *opaque) -{ - BdrvRemoveFilterOrCowChild *s = opaque; - - /* Drop the bs reference after the transaction is done */ - bdrv_unref(s->bs); - g_free(s); -} - static TransactionActionDrv bdrv_remove_filter_or_cow_child_drv = { .abort = bdrv_remove_filter_or_cow_child_abort, .commit = bdrv_remove_filter_or_cow_child_commit, - .clean = bdrv_remove_filter_or_cow_child_clean, + .clean = g_free, }; /* @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, return; } - /* - * Keep a reference to @bs so @childp will stay valid throughout the - * transaction (required by bdrv_replace_child_tran()) - */ - bdrv_ref(bs); if (child == bs->backing) { childp = &bs->backing; } else if (child == bs->file) { @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, } if (child->bs) { - bdrv_replace_child_tran(childp, NULL, tran); + bdrv_replace_child_tran(*childp, NULL, tran); } s = g_new(BdrvRemoveFilterOrCowChild, 1); *s = (BdrvRemoveFilterOrCowChild) { .child = child, - .bs = bs, .is_backing = (childp == &bs->backing), }; tran_add(tran, &bdrv_remove_filter_or_cow_child_drv, s); @@ -XXX,XX +XXX,XX @@ static int bdrv_replace_node_noperm(BlockDriverState *from, { BdrvChild *c, *next; - assert(to != NULL); GLOBAL_STATE_CODE(); QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) { @@ -XXX,XX +XXX,XX @@ static int bdrv_replace_node_noperm(BlockDriverState *from, c->name, from->node_name); return -EPERM; } - - /* - * Passing a pointer to the local variable @c is fine here, because - * @to is not NULL, and so &c will not be attached to the transaction. - */ - bdrv_replace_child_tran(&c, to, tran); + bdrv_replace_child_tran(c, to, tran); } return 0; @@ -XXX,XX +XXX,XX @@ static int bdrv_replace_node_noperm(BlockDriverState *from, * * With @detach_subchain=true @to must be in a backing chain of @from. In this * case backing link of the cow-parent of @to is removed. - * - * @to must not be NULL. */ static int bdrv_replace_node_common(BlockDriverState *from, BlockDriverState *to, @@ -XXX,XX +XXX,XX @@ static int bdrv_replace_node_common(BlockDriverState *from, int ret; GLOBAL_STATE_CODE(); - assert(to != NULL); if (detach_subchain) { assert(bdrv_chain_contains(from, to)); @@ -XXX,XX +XXX,XX @@ out: return ret; } -/** - * Replace node @from by @to (where neither may be NULL). - */ int bdrv_replace_node(BlockDriverState *from, BlockDriverState *to, Error **errp) { @@ -XXX,XX +XXX,XX @@ int bdrv_replace_child_bs(BdrvChild *child, BlockDriverState *new_bs, bdrv_drained_begin(old_bs); bdrv_drained_begin(new_bs); - bdrv_replace_child_tran(&child, new_bs, tran); + bdrv_replace_child_tran(child, new_bs, tran); found = g_hash_table_new(NULL, NULL); refresh_list = bdrv_topological_dfs(refresh_list, found, old_bs); -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> That's a preparation to previously reverted "block: Let replace_child_noperm free children". Drop it too, we don't need it for a new approach. This reverts commit 562bda8bb41879eeda0bd484dd3d55134579b28e. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-12-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 21 +++++++++------------ 1 file changed, 9 insertions(+), 12 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, BdrvChild *child, Transaction *tran) { - BdrvChild **childp; BdrvRemoveFilterOrCowChild *s; + assert(child == bs->backing || child == bs->file); + if (!child) { return; } - if (child == bs->backing) { - childp = &bs->backing; - } else if (child == bs->file) { - childp = &bs->file; - } else { - g_assert_not_reached(); - } - if (child->bs) { - bdrv_replace_child_tran(*childp, NULL, tran); + bdrv_replace_child_tran(child, NULL, tran); } s = g_new(BdrvRemoveFilterOrCowChild, 1); *s = (BdrvRemoveFilterOrCowChild) { .child = child, - .is_backing = (childp == &bs->backing), + .is_backing = (child == bs->backing), }; tran_add(tran, &bdrv_remove_filter_or_cow_child_drv, s); - *childp = NULL; + if (s->is_backing) { + bs->backing = NULL; + } else { + bs->file = NULL; + } } /* -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> That's a preparation to previously reverted "block: Let replace_child_noperm free children". Drop it too, we don't need it for a new approach. This reverts commit be64bbb0149748f3999c49b13976aafb8330ea86. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-13-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 23 +++++++++++------------ 1 file changed, 11 insertions(+), 12 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static BlockDriverState *bdrv_open_inherit(const char *filename, static bool bdrv_recurse_has_child(BlockDriverState *bs, BlockDriverState *child); -static void bdrv_replace_child_noperm(BdrvChild **child, +static void bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs); static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, BdrvChild *child, @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_abort(void *opaque) GLOBAL_STATE_CODE(); /* old_bs reference is transparently moved from @s to @s->child */ - bdrv_replace_child_noperm(&s->child, s->old_bs); + bdrv_replace_child_noperm(s->child, s->old_bs); bdrv_unref(new_bs); } @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_tran(BdrvChild *child, BlockDriverState *new_bs, if (new_bs) { bdrv_ref(new_bs); } - bdrv_replace_child_noperm(&child, new_bs); + bdrv_replace_child_noperm(child, new_bs); /* old_bs reference is transparently moved from @child to @s */ } @@ -XXX,XX +XXX,XX @@ uint64_t bdrv_qapi_perm_to_blk_perm(BlockPermission qapi_perm) return permissions[qapi_perm]; } -static void bdrv_replace_child_noperm(BdrvChild **childp, +static void bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs) { - BdrvChild *child = *childp; BlockDriverState *old_bs = child->bs; int new_bs_quiesce_counter; int drain_saldo; @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_child_common_abort(void *opaque) BlockDriverState *bs = child->bs; GLOBAL_STATE_CODE(); - bdrv_replace_child_noperm(s->child, NULL); + bdrv_replace_child_noperm(child, NULL); if (bdrv_get_aio_context(bs) != s->old_child_ctx) { bdrv_try_set_aio_context(bs, s->old_child_ctx, &error_abort); @@ -XXX,XX +XXX,XX @@ static int bdrv_attach_child_common(BlockDriverState *child_bs, } bdrv_ref(child_bs); - bdrv_replace_child_noperm(&new_child, child_bs); + bdrv_replace_child_noperm(new_child, child_bs); *child = new_child; @@ -XXX,XX +XXX,XX @@ static int bdrv_attach_child_noperm(BlockDriverState *parent_bs, return 0; } -static void bdrv_detach_child(BdrvChild **childp) +static void bdrv_detach_child(BdrvChild *child) { - BlockDriverState *old_bs = (*childp)->bs; + BlockDriverState *old_bs = child->bs; GLOBAL_STATE_CODE(); - bdrv_replace_child_noperm(childp, NULL); - bdrv_child_free(*childp); + bdrv_replace_child_noperm(child, NULL); + bdrv_child_free(child); if (old_bs) { /* @@ -XXX,XX +XXX,XX @@ void bdrv_root_unref_child(BdrvChild *child) GLOBAL_STATE_CODE(); child_bs = child->bs; - bdrv_detach_child(&child); + bdrv_detach_child(child); bdrv_unref(child_bs); } -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> bs->file and bs->backing are a kind of duplication of part of bs->children. But very useful diplication, so let's not drop them at all:) We should manage bs->file and bs->backing in same place, where we manage bs->children, to keep them in sync. Moreover, generic io paths are unprepared to BdrvChild without a bs, so it's double good to clear bs->file / bs->backing when we detach the child. Detach is simple: if we detach bs->file or bs->backing child, just set corresponding field to NULL. Attach is a bit more complicated. But we still can precisely detect should we set one of bs->file / bs->backing or not: - if role is BDRV_CHILD_COW, we definitely deal with bs->backing - else, if role is BDRV_CHILD_FILTERED (it must be also BDRV_CHILD_PRIMARY), it's a filtered child. Use bs->drv->filtered_child_is_backing to chose the pointer field to modify. - else, if role is BDRV_CHILD_PRIMARY, we deal with bs->file - in all other cases, it's neither bs->backing nor bs->file. It's some other child and we shouldn't care OK. This change brings one more good thing: we can (and should) get rid of all indirect pointers in the block-graph-change transactions: bdrv_attach_child_common() stores BdrvChild** into transaction to clear it on abort. bdrv_attach_child_common() has two callers: bdrv_attach_child_noperm() just pass-through this feature, bdrv_root_attach_child() doesn't need the feature. Look at bdrv_attach_child_noperm() callers: - bdrv_attach_child() doesn't need the feature - bdrv_set_file_or_backing_noperm() uses the feature to manage bs->file and bs->backing, we don't want it anymore - bdrv_append() uses the feature to manage bs->backing, again we don't want it anymore So, we should drop this stuff! Great! We could probably keep BdrvChild** argument to keep the int return value, but it seems not worth the complexity. Finally, we now set .file / .backing automatically in generic code and want to restring setting them by hand outside of .attach/.detach. So, this patch cleanups all remaining places where they were set. To find such places I use: git grep '\->file =' git grep '\->backing =' git grep '&.*\<backing\>' git grep '&.*\<file\>' Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-14-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int-common.h | 15 +- block.c | 234 ++++++++++++++----------------- block/raw-format.c | 4 +- block/snapshot-access.c | 6 +- block/snapshot.c | 1 - tests/unit/test-bdrv-drain.c | 10 +- 6 files changed, 126 insertions(+), 144 deletions(-) diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { QDict *full_open_options; char exact_filename[PATH_MAX]; - BdrvChild *backing; - BdrvChild *file; - /* I/O Limits */ BlockLimits bl; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { * parent node of this node. */ BlockDriverState *inherits_from; + + /* + * @backing and @file are some of @children or NULL. All these three fields + * (@file, @backing and @children) are modified only in + * bdrv_child_cb_attach() and bdrv_child_cb_detach(). + * + * See also comment in include/block/block.h, to learn how backing and file + * are connected with BdrvChildRole. + */ QLIST_HEAD(, BdrvChild) children; + BdrvChild *backing; + BdrvChild *file; + QLIST_HEAD(, BdrvChild) parents; QDict *options; diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_child_cb_attach(BdrvChild *child) assert_bdrv_graph_writable(bs); QLIST_INSERT_HEAD(&bs->children, child, next); - - if (child->role & BDRV_CHILD_COW) { + if (bs->drv->is_filter || (child->role & BDRV_CHILD_FILTERED)) { + /* + * Here we handle filters and block/raw-format.c when it behave like + * filter. They generally have a single PRIMARY child, which is also the + * FILTERED child, and that they may have multiple more children, which + * are neither PRIMARY nor FILTERED. And never we have a COW child here. + * So bs->file will be the PRIMARY child, unless the PRIMARY child goes + * into bs->backing on exceptional cases; and bs->backing will be + * nothing else. + */ + assert(!(child->role & BDRV_CHILD_COW)); + if (child->role & BDRV_CHILD_PRIMARY) { + assert(child->role & BDRV_CHILD_FILTERED); + assert(!bs->backing); + assert(!bs->file); + + if (bs->drv->filtered_child_is_backing) { + bs->backing = child; + } else { + bs->file = child; + } + } else { + assert(!(child->role & BDRV_CHILD_FILTERED)); + } + } else if (child->role & BDRV_CHILD_COW) { + assert(bs->drv->supports_backing); + assert(!(child->role & BDRV_CHILD_PRIMARY)); + assert(!bs->backing); + bs->backing = child; bdrv_backing_attach(child); + } else if (child->role & BDRV_CHILD_PRIMARY) { + assert(!bs->file); + bs->file = child; } bdrv_apply_subtree_drain(child, bs); @@ -XXX,XX +XXX,XX @@ static void bdrv_child_cb_detach(BdrvChild *child) assert_bdrv_graph_writable(bs); QLIST_REMOVE(child, next); + if (child == bs->backing) { + assert(child != bs->file); + bs->backing = NULL; + } else if (child == bs->file) { + bs->file = NULL; + } } static int bdrv_child_cb_update_filename(BdrvChild *c, BlockDriverState *base, @@ -XXX,XX +XXX,XX @@ open_failed: bs->drv = NULL; if (bs->file != NULL) { bdrv_unref_child(bs, bs->file); - bs->file = NULL; + assert(!bs->file); } g_free(bs->opaque); bs->opaque = NULL; @@ -XXX,XX +XXX,XX @@ static void bdrv_child_free(BdrvChild *child) } typedef struct BdrvAttachChildCommonState { - BdrvChild **child; + BdrvChild *child; AioContext *old_parent_ctx; AioContext *old_child_ctx; } BdrvAttachChildCommonState; @@ -XXX,XX +XXX,XX @@ typedef struct BdrvAttachChildCommonState { static void bdrv_attach_child_common_abort(void *opaque) { BdrvAttachChildCommonState *s = opaque; - BdrvChild *child = *s->child; - BlockDriverState *bs = child->bs; + BlockDriverState *bs = s->child->bs; GLOBAL_STATE_CODE(); - bdrv_replace_child_noperm(child, NULL); + bdrv_replace_child_noperm(s->child, NULL); if (bdrv_get_aio_context(bs) != s->old_child_ctx) { bdrv_try_set_aio_context(bs, s->old_child_ctx, &error_abort); } - if (bdrv_child_get_parent_aio_context(child) != s->old_parent_ctx) { + if (bdrv_child_get_parent_aio_context(s->child) != s->old_parent_ctx) { GSList *ignore; /* No need to ignore `child`, because it has been detached already */ ignore = NULL; - child->klass->can_set_aio_ctx(child, s->old_parent_ctx, &ignore, - &error_abort); + s->child->klass->can_set_aio_ctx(s->child, s->old_parent_ctx, &ignore, + &error_abort); g_slist_free(ignore); ignore = NULL; - child->klass->set_aio_ctx(child, s->old_parent_ctx, &ignore); + s->child->klass->set_aio_ctx(s->child, s->old_parent_ctx, &ignore); g_slist_free(ignore); } bdrv_unref(bs); - bdrv_child_free(child); - *s->child = NULL; + bdrv_child_free(s->child); } static TransactionActionDrv bdrv_attach_child_common_drv = { @@ -XXX,XX +XXX,XX @@ static TransactionActionDrv bdrv_attach_child_common_drv = { /* * Common part of attaching bdrv child to bs or to blk or to job * - * Resulting new child is returned through @child. - * At start *@child must be NULL. - * @child is saved to a new entry of @tran, so that *@child could be reverted to - * NULL on abort(). So referenced variable must live at least until transaction - * end. - * * Function doesn't update permissions, caller is responsible for this. + * + * Returns new created child. */ -static int bdrv_attach_child_common(BlockDriverState *child_bs, - const char *child_name, - const BdrvChildClass *child_class, - BdrvChildRole child_role, - uint64_t perm, uint64_t shared_perm, - void *opaque, BdrvChild **child, - Transaction *tran, Error **errp) +static BdrvChild *bdrv_attach_child_common(BlockDriverState *child_bs, + const char *child_name, + const BdrvChildClass *child_class, + BdrvChildRole child_role, + uint64_t perm, uint64_t shared_perm, + void *opaque, + Transaction *tran, Error **errp) { BdrvChild *new_child; AioContext *parent_ctx; AioContext *child_ctx = bdrv_get_aio_context(child_bs); - assert(child); - assert(*child == NULL); assert(child_class->get_parent_desc); GLOBAL_STATE_CODE(); @@ -XXX,XX +XXX,XX @@ static int bdrv_attach_child_common(BlockDriverState *child_bs, if (ret < 0) { error_propagate(errp, local_err); bdrv_child_free(new_child); - return ret; + return NULL; } } bdrv_ref(child_bs); bdrv_replace_child_noperm(new_child, child_bs); - *child = new_child; - BdrvAttachChildCommonState *s = g_new(BdrvAttachChildCommonState, 1); *s = (BdrvAttachChildCommonState) { - .child = child, + .child = new_child, .old_parent_ctx = parent_ctx, .old_child_ctx = child_ctx, }; tran_add(tran, &bdrv_attach_child_common_drv, s); - return 0; + return new_child; } /* - * Variable referenced by @child must live at least until transaction end. - * (see bdrv_attach_child_common() doc for details) - * * Function doesn't update permissions, caller is responsible for this. */ -static int bdrv_attach_child_noperm(BlockDriverState *parent_bs, - BlockDriverState *child_bs, - const char *child_name, - const BdrvChildClass *child_class, - BdrvChildRole child_role, - BdrvChild **child, - Transaction *tran, - Error **errp) +static BdrvChild *bdrv_attach_child_noperm(BlockDriverState *parent_bs, + BlockDriverState *child_bs, + const char *child_name, + const BdrvChildClass *child_class, + BdrvChildRole child_role, + Transaction *tran, + Error **errp) { - int ret; uint64_t perm, shared_perm; assert(parent_bs->drv); @@ -XXX,XX +XXX,XX @@ static int bdrv_attach_child_noperm(BlockDriverState *parent_bs, if (bdrv_recurse_has_child(child_bs, parent_bs)) { error_setg(errp, "Making '%s' a %s child of '%s' would create a cycle", child_bs->node_name, child_name, parent_bs->node_name); - return -EINVAL; + return NULL; } bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm); bdrv_child_perm(parent_bs, child_bs, NULL, child_role, NULL, perm, shared_perm, &perm, &shared_perm); - ret = bdrv_attach_child_common(child_bs, child_name, child_class, - child_role, perm, shared_perm, parent_bs, - child, tran, errp); - if (ret < 0) { - return ret; - } - - return 0; + return bdrv_attach_child_common(child_bs, child_name, child_class, + child_role, perm, shared_perm, parent_bs, + tran, errp); } static void bdrv_detach_child(BdrvChild *child) @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, void *opaque, Error **errp) { int ret; - BdrvChild *child = NULL; + BdrvChild *child; Transaction *tran = tran_new(); GLOBAL_STATE_CODE(); - ret = bdrv_attach_child_common(child_bs, child_name, child_class, + child = bdrv_attach_child_common(child_bs, child_name, child_class, child_role, perm, shared_perm, opaque, - &child, tran, errp); - if (ret < 0) { + tran, errp); + if (!child) { + ret = -EINVAL; goto out; } @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, out: tran_finalize(tran, ret); - /* child is unset on failure by bdrv_attach_child_common_abort() */ - assert((ret < 0) == !child); bdrv_unref(child_bs); - return child; + + return ret < 0 ? NULL : child; } /* @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs, Error **errp) { int ret; - BdrvChild *child = NULL; + BdrvChild *child; Transaction *tran = tran_new(); GLOBAL_STATE_CODE(); - ret = bdrv_attach_child_noperm(parent_bs, child_bs, child_name, child_class, - child_role, &child, tran, errp); - if (ret < 0) { + child = bdrv_attach_child_noperm(parent_bs, child_bs, child_name, + child_class, child_role, tran, errp); + if (!child) { + ret = -EINVAL; goto out; } @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs, out: tran_finalize(tran, ret); - /* child is unset on failure by bdrv_attach_child_common_abort() */ - assert((ret < 0) == !child); bdrv_unref(child_bs); - return child; + return ret < 0 ? NULL : child; } /* Callers must ensure that child->frozen is false. */ @@ -XXX,XX +XXX,XX @@ static int bdrv_set_file_or_backing_noperm(BlockDriverState *parent_bs, bool is_backing, Transaction *tran, Error **errp) { - int ret = 0; bool update_inherits_from = bdrv_inherits_from_recursive(child_bs, parent_bs); BdrvChild *child = is_backing ? parent_bs->backing : parent_bs->file; @@ -XXX,XX +XXX,XX @@ static int bdrv_set_file_or_backing_noperm(BlockDriverState *parent_bs, goto out; } - ret = bdrv_attach_child_noperm(parent_bs, child_bs, - is_backing ? "backing" : "file", - &child_of_bds, role, - is_backing ? &parent_bs->backing : - &parent_bs->file, - tran, errp); - if (ret < 0) { - return ret; + child = bdrv_attach_child_noperm(parent_bs, child_bs, + is_backing ? "backing" : "file", + &child_of_bds, role, + tran, errp); + if (!child) { + return -EINVAL; } @@ -XXX,XX +XXX,XX @@ int bdrv_open_file_child(const char *filename, /* commit_top and mirror_top don't use this function */ assert(!parent->drv->filtered_child_is_backing); - role = parent->drv->is_filter ? (BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY) : BDRV_CHILD_IMAGE; - parent->file = bdrv_open_child(filename, options, bdref_key, parent, - &child_of_bds, role, false, errp); + if (!bdrv_open_child(filename, options, bdref_key, parent, + &child_of_bds, role, false, errp)) + { + return -EINVAL; + } - return parent->file ? 0 : -EINVAL; + return 0; } /* @@ -XXX,XX +XXX,XX @@ static void bdrv_close(BlockDriverState *bs) bdrv_unref_child(bs, child); } - bs->backing = NULL; - bs->file = NULL; + assert(!bs->backing); + assert(!bs->file); g_free(bs->opaque); bs->opaque = NULL; qatomic_set(&bs->copy_on_read, 0); @@ -XXX,XX +XXX,XX @@ static bool should_update_child(BdrvChild *c, BlockDriverState *to) return ret; } -typedef struct BdrvRemoveFilterOrCowChild { - BdrvChild *child; - bool is_backing; -} BdrvRemoveFilterOrCowChild; - -static void bdrv_remove_filter_or_cow_child_abort(void *opaque) -{ - BdrvRemoveFilterOrCowChild *s = opaque; - BlockDriverState *parent_bs = s->child->opaque; - - if (s->is_backing) { - parent_bs->backing = s->child; - } else { - parent_bs->file = s->child; - } - - /* - * We don't have to restore child->bs here to undo bdrv_replace_child_tran() - * because that function is transactionable and it registered own completion - * entries in @tran, so .abort() for bdrv_replace_child_safe() will be - * called automatically. - */ -} - static void bdrv_remove_filter_or_cow_child_commit(void *opaque) { - BdrvRemoveFilterOrCowChild *s = opaque; GLOBAL_STATE_CODE(); - bdrv_child_free(s->child); + bdrv_child_free(opaque); } static TransactionActionDrv bdrv_remove_filter_or_cow_child_drv = { - .abort = bdrv_remove_filter_or_cow_child_abort, .commit = bdrv_remove_filter_or_cow_child_commit, - .clean = g_free, }; /* @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, BdrvChild *child, Transaction *tran) { - BdrvRemoveFilterOrCowChild *s; - assert(child == bs->backing || child == bs->file); if (!child) { @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, bdrv_replace_child_tran(child, NULL, tran); } - s = g_new(BdrvRemoveFilterOrCowChild, 1); - *s = (BdrvRemoveFilterOrCowChild) { - .child = child, - .is_backing = (child == bs->backing), - }; - tran_add(tran, &bdrv_remove_filter_or_cow_child_drv, s); - - if (s->is_backing) { - bs->backing = NULL; - } else { - bs->file = NULL; - } + tran_add(tran, &bdrv_remove_filter_or_cow_child_drv, child); } /* @@ -XXX,XX +XXX,XX @@ int bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top, Error **errp) { int ret; + BdrvChild *child; Transaction *tran = tran_new(); GLOBAL_STATE_CODE(); assert(!bs_new->backing); - ret = bdrv_attach_child_noperm(bs_new, bs_top, "backing", - &child_of_bds, bdrv_backing_role(bs_new), - &bs_new->backing, tran, errp); - if (ret < 0) { + child = bdrv_attach_child_noperm(bs_new, bs_top, "backing", + &child_of_bds, bdrv_backing_role(bs_new), + tran, errp); + if (!child) { + ret = -EINVAL; goto out; } diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, file_role = BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY; } - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - file_role, false, errp); + bdrv_open_child(NULL, options, "file", bs, &child_of_bds, + file_role, false, errp); if (!bs->file) { return -EINVAL; } diff --git a/block/snapshot-access.c b/block/snapshot-access.c index XXXXXXX..XXXXXXX 100644 --- a/block/snapshot-access.c +++ b/block/snapshot-access.c @@ -XXX,XX +XXX,XX @@ static void snapshot_access_refresh_filename(BlockDriverState *bs) static int snapshot_access_open(BlockDriverState *bs, QDict *options, int flags, Error **errp) { - bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds, - BDRV_CHILD_DATA | BDRV_CHILD_PRIMARY, - false, errp); + bdrv_open_child(NULL, options, "file", bs, &child_of_bds, + BDRV_CHILD_DATA | BDRV_CHILD_PRIMARY, + false, errp); if (!bs->file) { return -EINVAL; } diff --git a/block/snapshot.c b/block/snapshot.c index XXXXXXX..XXXXXXX 100644 --- a/block/snapshot.c +++ b/block/snapshot.c @@ -XXX,XX +XXX,XX @@ int bdrv_snapshot_goto(BlockDriverState *bs, /* .bdrv_open() will re-attach it */ bdrv_unref_child(bs, *fallback_ptr); - *fallback_ptr = NULL; ret = bdrv_snapshot_goto(fallback_bs, snapshot_id, errp); open_ret = drv->bdrv_open(bs, options, bs->open_flags, &local_err); diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-bdrv-drain.c +++ b/tests/unit/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_drop_intermediate_poll(void) for (i = 0; i < 3; i++) { if (i) { /* Takes the reference to chain[i - 1] */ - chain[i]->backing = bdrv_attach_child(chain[i], chain[i - 1], - "chain", &chain_child_class, - BDRV_CHILD_COW, &error_abort); + bdrv_attach_child(chain[i], chain[i - 1], "chain", + &chain_child_class, BDRV_CHILD_COW, &error_abort); } } @@ -XXX,XX +XXX,XX @@ static void do_test_replace_child_mid_drain(int old_drain_count, new_child_bs->total_sectors = 1; bdrv_ref(old_child_bs); - parent_bs->backing = bdrv_attach_child(parent_bs, old_child_bs, "child", - &child_of_bds, BDRV_CHILD_COW, - &error_abort); + bdrv_attach_child(parent_bs, old_child_bs, "child", &child_of_bds, + BDRV_CHILD_COW, &error_abort); for (i = 0; i < old_drain_count; i++) { bdrv_drained_begin(old_child_bs); -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Now the indirection is not actually used, we can safely reduce it to simple pointer. For consistency do a bit of refactoring to get rid of _ptr suffixes that become meaningless. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-15-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/snapshot.c | 38 ++++++++++++++++---------------------- 1 file changed, 16 insertions(+), 22 deletions(-) diff --git a/block/snapshot.c b/block/snapshot.c index XXXXXXX..XXXXXXX 100644 --- a/block/snapshot.c +++ b/block/snapshot.c @@ -XXX,XX +XXX,XX @@ bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs, } /** - * Return a pointer to the child BDS pointer to which we can fall + * Return a pointer to child of given BDS to which we can fall * back if the given BDS does not support snapshots. * Return NULL if there is no BDS to (safely) fall back to. - * - * We need to return an indirect pointer because bdrv_snapshot_goto() - * has to modify the BdrvChild pointer. */ -static BdrvChild **bdrv_snapshot_fallback_ptr(BlockDriverState *bs) +static BdrvChild *bdrv_snapshot_fallback_child(BlockDriverState *bs) { - BdrvChild **fallback; - BdrvChild *child = bdrv_primary_child(bs); + BdrvChild *fallback = bdrv_primary_child(bs); + BdrvChild *child; /* We allow fallback only to primary child */ - if (!child) { + if (!fallback) { return NULL; } - fallback = (child == bs->file ? &bs->file : &bs->backing); - assert(*fallback == child); /* * Check that there are no other children that would need to be * snapshotted. If there are, it is not safe to fall back to - * *fallback. + * fallback. */ QLIST_FOREACH(child, &bs->children, next) { if (child->role & (BDRV_CHILD_DATA | BDRV_CHILD_METADATA | BDRV_CHILD_FILTERED) && - child != *fallback) + child != fallback) { return NULL; } @@ -XXX,XX +XXX,XX @@ static BdrvChild **bdrv_snapshot_fallback_ptr(BlockDriverState *bs) static BlockDriverState *bdrv_snapshot_fallback(BlockDriverState *bs) { - BdrvChild **child_ptr = bdrv_snapshot_fallback_ptr(bs); - return child_ptr ? (*child_ptr)->bs : NULL; + return child_bs(bdrv_snapshot_fallback_child(bs)); } int bdrv_can_snapshot(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ int bdrv_snapshot_goto(BlockDriverState *bs, Error **errp) { BlockDriver *drv = bs->drv; - BdrvChild **fallback_ptr; + BdrvChild *fallback; int ret, open_ret; GLOBAL_STATE_CODE(); @@ -XXX,XX +XXX,XX @@ int bdrv_snapshot_goto(BlockDriverState *bs, return ret; } - fallback_ptr = bdrv_snapshot_fallback_ptr(bs); - if (fallback_ptr) { + fallback = bdrv_snapshot_fallback_child(bs); + if (fallback) { QDict *options; QDict *file_options; Error *local_err = NULL; - BlockDriverState *fallback_bs = (*fallback_ptr)->bs; - char *subqdict_prefix = g_strdup_printf("%s.", (*fallback_ptr)->name); + BlockDriverState *fallback_bs = fallback->bs; + char *subqdict_prefix = g_strdup_printf("%s.", fallback->name); options = qdict_clone_shallow(bs->options); @@ -XXX,XX +XXX,XX @@ int bdrv_snapshot_goto(BlockDriverState *bs, qobject_unref(file_options); g_free(subqdict_prefix); - /* Force .bdrv_open() below to re-attach fallback_bs on *fallback_ptr */ - qdict_put_str(options, (*fallback_ptr)->name, + /* Force .bdrv_open() below to re-attach fallback_bs on fallback */ + qdict_put_str(options, fallback->name, bdrv_get_node_name(fallback_bs)); /* Now close bs, apply the snapshot on fallback_bs, and re-open bs */ @@ -XXX,XX +XXX,XX @@ int bdrv_snapshot_goto(BlockDriverState *bs, } /* .bdrv_open() will re-attach it */ - bdrv_unref_child(bs, *fallback_ptr); + bdrv_unref_child(bs, fallback); ret = bdrv_snapshot_goto(fallback_bs, snapshot_id, errp); open_ret = drv->bdrv_open(bs, options, bs->open_flags, &local_err); -- 2.37.3 From: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Now the function can remove any child, so give it more common name. Drop assertions and drop bs argument which becomes unused. Function would be reused in a further commit. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20220726201134.924743-16-vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 27 +++++++++------------------ 1 file changed, 9 insertions(+), 18 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static bool bdrv_recurse_has_child(BlockDriverState *bs, static void bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs); -static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, - BdrvChild *child, - Transaction *tran); +static void bdrv_remove_child(BdrvChild *child, Transaction *tran); static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs, Transaction *tran); @@ -XXX,XX +XXX,XX @@ static int bdrv_set_file_or_backing_noperm(BlockDriverState *parent_bs, if (child) { bdrv_unset_inherits_from(parent_bs, child, tran); - bdrv_remove_file_or_backing_child(parent_bs, child, tran); + bdrv_remove_child(child, tran); } if (!child_bs) { @@ -XXX,XX +XXX,XX @@ static bool should_update_child(BdrvChild *c, BlockDriverState *to) return ret; } -static void bdrv_remove_filter_or_cow_child_commit(void *opaque) +static void bdrv_remove_child_commit(void *opaque) { GLOBAL_STATE_CODE(); bdrv_child_free(opaque); } -static TransactionActionDrv bdrv_remove_filter_or_cow_child_drv = { - .commit = bdrv_remove_filter_or_cow_child_commit, +static TransactionActionDrv bdrv_remove_child_drv = { + .commit = bdrv_remove_child_commit, }; -/* - * A function to remove backing or file child of @bs. - * Function doesn't update permissions, caller is responsible for this. - */ -static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, - BdrvChild *child, - Transaction *tran) +/* Function doesn't update permissions, caller is responsible for this. */ +static void bdrv_remove_child(BdrvChild *child, Transaction *tran) { - assert(child == bs->backing || child == bs->file); - if (!child) { return; } @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, bdrv_replace_child_tran(child, NULL, tran); } - tran_add(tran, &bdrv_remove_filter_or_cow_child_drv, child); + tran_add(tran, &bdrv_remove_child_drv, child); } /* @@ -XXX,XX +XXX,XX @@ static void bdrv_remove_file_or_backing_child(BlockDriverState *bs, static void bdrv_remove_filter_or_cow_child(BlockDriverState *bs, Transaction *tran) { - bdrv_remove_file_or_backing_child(bs, bdrv_filter_or_cow_child(bs), tran); + bdrv_remove_child(bdrv_filter_or_cow_child(bs), tran); } static int bdrv_replace_node_noperm(BlockDriverState *from, -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Also here ->aio_context is read by I/O threads and written under BQL. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Message-Id: <20221025084952.2139888-2-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_detach_aio_context(BlockDriverState *bs) if (bs->quiesce_counter) { aio_enable_external(bs->aio_context); } + assert_bdrv_graph_writable(bs); bs->aio_context = NULL; } @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_aio_context(BlockDriverState *bs, aio_disable_external(new_context); } + assert_bdrv_graph_writable(bs); bs->aio_context = new_context; if (bs->drv && bs->drv->bdrv_attach_aio_context) { -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Simplify the way the aiocontext can be changed in a BDS graph. There are currently two problems in bdrv_try_set_aio_context: - There is a confusion of AioContext locks taken and released, because we assume that old aiocontext is always taken and new one is taken inside. - It doesn't look very safe to call bdrv_drained_begin while some nodes have already switched to the new aiocontext and others haven't. This could be especially dangerous because bdrv_drained_begin polls, so something else could be executed while graph is in an inconsistent state. Additional minor nitpick: can_set and set_ callbacks both traverse the graph, both using the ignored list of visited nodes in a different way. Therefore, get rid of all of this and introduce a new callback, change_aio_context, that uses transactions to efficiently, cleanly and most importantly safely change the aiocontext of a graph. This new callback is a "merge" of the two previous ones: - Just like can_set_aio_context, recursively traverses the graph. Marks all nodes that are visited using a GList, and checks if they *could* change the aio_context. - For each node that passes the above check, drain it and add a new transaction that implements a callback that effectively changes the aiocontext. - Once done, the recursive function returns if *all* nodes can change the AioContext. If so, commit the above transactions. Regardless of the outcome, call transaction.clean() to undo all drains done in the recursion. - The transaction list is scanned only after all nodes are being drained, so we are sure that they all are in the same context, and then we switch their AioContext, concluding the drain only after all nodes switched to the new AioContext. In this way we make sure that bdrv_drained_begin() is always called under the old AioContext, and bdrv_drained_end() under the new one. - Because of the above, we don't need to release and re-acquire the old AioContext every time, as everything is done once (and not per-node drain and aiocontext change). Note that the "change" API is not yet invoked anywhere. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-Id: <20221025084952.2139888-3-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-global-state.h | 6 + include/block/block_int-common.h | 3 + block.c | 220 ++++++++++++++++++++++++++++- 3 files changed, 228 insertions(+), 1 deletion(-) diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -XXX,XX +XXX,XX @@ bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, GSList **ignore, Error **errp); AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c); +bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, + GSList **visited, Transaction *tran, + Error **errp); +int bdrv_child_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, + BdrvChild *ignore_child, Error **errp); + int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz); int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo); diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BdrvChildClass { GSList **ignore, Error **errp); void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore); + bool (*change_aio_ctx)(BdrvChild *child, AioContext *ctx, + GSList **visited, Transaction *tran, Error **errp); + AioContext *(*get_parent_aio_context)(BdrvChild *child); /* diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_reopen_abort(BDRVReopenState *reopen_state); static bool bdrv_backing_overridden(BlockDriverState *bs); +static bool bdrv_change_aio_context(BlockDriverState *bs, AioContext *ctx, + GSList **visited, Transaction *tran, + Error **errp); + /* If non-zero, use only whitelisted block drivers */ static int use_bdrv_whitelist; @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_aio_context(BlockDriverState *bs, * must not own the AioContext lock for new_context (unless new_context is the * same as the current context of bs). * - * @ignore will accumulate all visited BdrvChild object. The caller is + * @ignore will accumulate all visited BdrvChild objects. The caller is * responsible for freeing the list afterwards. */ void bdrv_set_aio_context_ignore(BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static bool bdrv_parent_can_set_aio_context(BdrvChild *c, AioContext *ctx, return true; } +typedef struct BdrvStateSetAioContext { + AioContext *new_ctx; + BlockDriverState *bs; +} BdrvStateSetAioContext; + +static bool bdrv_parent_change_aio_context(BdrvChild *c, AioContext *ctx, + GSList **visited, Transaction *tran, + Error **errp) +{ + GLOBAL_STATE_CODE(); + if (g_slist_find(*visited, c)) { + return true; + } + *visited = g_slist_prepend(*visited, c); + + /* + * A BdrvChildClass that doesn't handle AioContext changes cannot + * tolerate any AioContext changes + */ + if (!c->klass->change_aio_ctx) { + char *user = bdrv_child_user_desc(c); + error_setg(errp, "Changing iothreads is not supported by %s", user); + g_free(user); + return false; + } + if (!c->klass->change_aio_ctx(c, ctx, visited, tran, errp)) { + assert(!errp || *errp); + return false; + } + return true; +} + bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx, GSList **ignore, Error **errp) { @@ -XXX,XX +XXX,XX @@ bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx, return bdrv_can_set_aio_context(c->bs, ctx, ignore, errp); } +bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, + GSList **visited, Transaction *tran, + Error **errp) +{ + GLOBAL_STATE_CODE(); + if (g_slist_find(*visited, c)) { + return true; + } + *visited = g_slist_prepend(*visited, c); + return bdrv_change_aio_context(c->bs, ctx, visited, tran, errp); +} + /* @ignore will accumulate all visited BdrvChild object. The caller is * responsible for freeing the list afterwards. */ bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, @@ -XXX,XX +XXX,XX @@ bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, return true; } +static void bdrv_set_aio_context_clean(void *opaque) +{ + BdrvStateSetAioContext *state = (BdrvStateSetAioContext *) opaque; + BlockDriverState *bs = (BlockDriverState *) state->bs; + + /* Paired with bdrv_drained_begin in bdrv_change_aio_context() */ + bdrv_drained_end(bs); + + g_free(state); +} + +static void bdrv_set_aio_context_commit(void *opaque) +{ + BdrvStateSetAioContext *state = (BdrvStateSetAioContext *) opaque; + BlockDriverState *bs = (BlockDriverState *) state->bs; + AioContext *new_context = state->new_ctx; + AioContext *old_context = bdrv_get_aio_context(bs); + assert_bdrv_graph_writable(bs); + + /* + * Take the old AioContex when detaching it from bs. + * At this point, new_context lock is already acquired, and we are now + * also taking old_context. This is safe as long as bdrv_detach_aio_context + * does not call AIO_POLL_WHILE(). + */ + if (old_context != qemu_get_aio_context()) { + aio_context_acquire(old_context); + } + bdrv_detach_aio_context(bs); + if (old_context != qemu_get_aio_context()) { + aio_context_release(old_context); + } + bdrv_attach_aio_context(bs, new_context); +} + +static TransactionActionDrv set_aio_context = { + .commit = bdrv_set_aio_context_commit, + .clean = bdrv_set_aio_context_clean, +}; + +/* + * Changes the AioContext used for fd handlers, timers, and BHs by this + * BlockDriverState and all its children and parents. + * + * Must be called from the main AioContext. + * + * The caller must own the AioContext lock for the old AioContext of bs, but it + * must not own the AioContext lock for new_context (unless new_context is the + * same as the current context of bs). + * + * @visited will accumulate all visited BdrvChild objects. The caller is + * responsible for freeing the list afterwards. + */ +static bool bdrv_change_aio_context(BlockDriverState *bs, AioContext *ctx, + GSList **visited, Transaction *tran, + Error **errp) +{ + BdrvChild *c; + BdrvStateSetAioContext *state; + + GLOBAL_STATE_CODE(); + + if (bdrv_get_aio_context(bs) == ctx) { + return true; + } + + QLIST_FOREACH(c, &bs->parents, next_parent) { + if (!bdrv_parent_change_aio_context(c, ctx, visited, tran, errp)) { + return false; + } + } + + QLIST_FOREACH(c, &bs->children, next) { + if (!bdrv_child_change_aio_context(c, ctx, visited, tran, errp)) { + return false; + } + } + + state = g_new(BdrvStateSetAioContext, 1); + *state = (BdrvStateSetAioContext) { + .new_ctx = ctx, + .bs = bs, + }; + + /* Paired with bdrv_drained_end in bdrv_set_aio_context_clean() */ + bdrv_drained_begin(bs); + + tran_add(tran, &set_aio_context, state); + + return true; +} + int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, BdrvChild *ignore_child, Error **errp) { @@ -XXX,XX +XXX,XX @@ int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, return 0; } +/* + * Change bs's and recursively all of its parents' and children's AioContext + * to the given new context, returning an error if that isn't possible. + * + * If ignore_child is not NULL, that child (and its subgraph) will not + * be touched. + * + * This function still requires the caller to take the bs current + * AioContext lock, otherwise draining will fail since AIO_WAIT_WHILE + * assumes the lock is always held if bs is in another AioContext. + * For the same reason, it temporarily also holds the new AioContext, since + * bdrv_drained_end calls BDRV_POLL_WHILE that assumes the lock is taken too. + * Therefore the new AioContext lock must not be taken by the caller. + */ +int bdrv_child_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, + BdrvChild *ignore_child, Error **errp) +{ + Transaction *tran; + GSList *visited; + int ret; + AioContext *old_context = bdrv_get_aio_context(bs); + GLOBAL_STATE_CODE(); + + /* + * Recursion phase: go through all nodes of the graph. + * Take care of checking that all nodes support changing AioContext + * and drain them, builing a linear list of callbacks to run if everything + * is successful (the transaction itself). + */ + tran = tran_new(); + visited = ignore_child ? g_slist_prepend(NULL, ignore_child) : NULL; + ret = bdrv_change_aio_context(bs, ctx, &visited, tran, errp); + g_slist_free(visited); + + /* + * Linear phase: go through all callbacks collected in the transaction. + * Run all callbacks collected in the recursion to switch all nodes + * AioContext lock (transaction commit), or undo all changes done in the + * recursion (transaction abort). + */ + + if (!ret) { + /* Just run clean() callbacks. No AioContext changed. */ + tran_abort(tran); + return -EPERM; + } + + /* + * Release old AioContext, it won't be needed anymore, as all + * bdrv_drained_begin() have been called already. + */ + if (qemu_get_aio_context() != old_context) { + aio_context_release(old_context); + } + + /* + * Acquire new AioContext since bdrv_drained_end() is going to be called + * after we switched all nodes in the new AioContext, and the function + * assumes that the lock of the bs is always taken. + */ + if (qemu_get_aio_context() != ctx) { + aio_context_acquire(ctx); + } + + tran_commit(tran); + + if (qemu_get_aio_context() != ctx) { + aio_context_release(ctx); + } + + /* Re-acquire the old AioContext, since the caller takes and releases it. */ + if (qemu_get_aio_context() != old_context) { + aio_context_acquire(old_context); + } + + return 0; +} + int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, Error **errp) { -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Minor performance improvement, but given that we have hash tables available, avoid iterating in the visited nodes list every time just to check if a node has been already visited. The data structure is not actually a proper hash map, but an hash set, as we are just adding nodes and not key,value pairs. Suggested-by: Hanna Reitz <hreitz@redhat.com> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-4-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-global-state.h | 2 +- include/block/block_int-common.h | 3 ++- block.c | 28 ++++++++++++++++------------ 3 files changed, 19 insertions(+), 14 deletions(-) diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -XXX,XX +XXX,XX @@ bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c); bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, - GSList **visited, Transaction *tran, + GHashTable *visited, Transaction *tran, Error **errp); int bdrv_child_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, BdrvChild *ignore_child, Error **errp); diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BdrvChildClass { void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore); bool (*change_aio_ctx)(BdrvChild *child, AioContext *ctx, - GSList **visited, Transaction *tran, Error **errp); + GHashTable *visited, Transaction *tran, + Error **errp); AioContext *(*get_parent_aio_context)(BdrvChild *child); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_reopen_abort(BDRVReopenState *reopen_state); static bool bdrv_backing_overridden(BlockDriverState *bs); static bool bdrv_change_aio_context(BlockDriverState *bs, AioContext *ctx, - GSList **visited, Transaction *tran, + GHashTable *visited, Transaction *tran, Error **errp); /* If non-zero, use only whitelisted block drivers */ @@ -XXX,XX +XXX,XX @@ typedef struct BdrvStateSetAioContext { } BdrvStateSetAioContext; static bool bdrv_parent_change_aio_context(BdrvChild *c, AioContext *ctx, - GSList **visited, Transaction *tran, + GHashTable *visited, + Transaction *tran, Error **errp) { GLOBAL_STATE_CODE(); - if (g_slist_find(*visited, c)) { + if (g_hash_table_contains(visited, c)) { return true; } - *visited = g_slist_prepend(*visited, c); + g_hash_table_add(visited, c); /* * A BdrvChildClass that doesn't handle AioContext changes cannot @@ -XXX,XX +XXX,XX @@ bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx, } bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, - GSList **visited, Transaction *tran, + GHashTable *visited, Transaction *tran, Error **errp) { GLOBAL_STATE_CODE(); - if (g_slist_find(*visited, c)) { + if (g_hash_table_contains(visited, c)) { return true; } - *visited = g_slist_prepend(*visited, c); + g_hash_table_add(visited, c); return bdrv_change_aio_context(c->bs, ctx, visited, tran, errp); } @@ -XXX,XX +XXX,XX @@ static TransactionActionDrv set_aio_context = { * responsible for freeing the list afterwards. */ static bool bdrv_change_aio_context(BlockDriverState *bs, AioContext *ctx, - GSList **visited, Transaction *tran, + GHashTable *visited, Transaction *tran, Error **errp) { BdrvChild *c; @@ -XXX,XX +XXX,XX @@ int bdrv_child_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, BdrvChild *ignore_child, Error **errp) { Transaction *tran; - GSList *visited; + GHashTable *visited; int ret; AioContext *old_context = bdrv_get_aio_context(bs); GLOBAL_STATE_CODE(); @@ -XXX,XX +XXX,XX @@ int bdrv_child_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, * is successful (the transaction itself). */ tran = tran_new(); - visited = ignore_child ? g_slist_prepend(NULL, ignore_child) : NULL; - ret = bdrv_change_aio_context(bs, ctx, &visited, tran, errp); - g_slist_free(visited); + visited = g_hash_table_new(NULL, NULL); + if (ignore_child) { + g_hash_table_add(visited, ignore_child); + } + ret = bdrv_change_aio_context(bs, ctx, visited, tran, errp); + g_hash_table_destroy(visited); /* * Linear phase: go through all callbacks collected in the transaction. -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> child_job_change_aio_ctx() is very similar to child_job_can_set_aio_ctx(), but it implements a new transaction so that if all check pass, the new transaction's .commit() will take care of changin the BlockJob AioContext. child_job_set_aio_ctx_commit() is similar to child_job_set_aio_ctx(), but it doesn't need to invoke the recursion, as this is already taken care by child_job_change_aio_ctx(). Note: bdrv_child_try_change_aio_context() is not called by anyone at this point. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-5-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static void child_job_drained_end(BdrvChild *c, int *drained_end_counter) job_resume(&job->job); } +typedef struct BdrvStateChildJobContext { + AioContext *new_ctx; + BlockJob *job; +} BdrvStateChildJobContext; + +static void child_job_set_aio_ctx_commit(void *opaque) +{ + BdrvStateChildJobContext *s = opaque; + BlockJob *job = s->job; + + job_set_aio_context(&job->job, s->new_ctx); +} + +static TransactionActionDrv change_child_job_context = { + .commit = child_job_set_aio_ctx_commit, + .clean = g_free, +}; + +static bool child_job_change_aio_ctx(BdrvChild *c, AioContext *ctx, + GHashTable *visited, Transaction *tran, + Error **errp) +{ + BlockJob *job = c->opaque; + BdrvStateChildJobContext *s; + GSList *l; + + for (l = job->nodes; l; l = l->next) { + BdrvChild *sibling = l->data; + if (!bdrv_child_change_aio_context(sibling, ctx, visited, + tran, errp)) { + return false; + } + } + + s = g_new(BdrvStateChildJobContext, 1); + *s = (BdrvStateChildJobContext) { + .new_ctx = ctx, + .job = job, + }; + + tran_add(tran, &change_child_job_context, s); + return true; +} + static bool child_job_can_set_aio_ctx(BdrvChild *c, AioContext *ctx, GSList **ignore, Error **errp) { @@ -XXX,XX +XXX,XX @@ static const BdrvChildClass child_job = { .drained_end = child_job_drained_end, .can_set_aio_ctx = child_job_can_set_aio_ctx, .set_aio_ctx = child_job_set_aio_ctx, + .change_aio_ctx = child_job_change_aio_ctx, .stay_at_node = true, .get_parent_aio_context = child_job_get_parent_aio_context, }; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> bdrv_child_cb_change_aio_ctx() is identical to bdrv_child_cb_can_set_aio_ctx(), as we only need to recursively go on the parent bs. Note: bdrv_child_try_change_aio_context() is not called by anyone at this point. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-6-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int bdrv_child_cb_inactivate(BdrvChild *child) return 0; } +static bool bdrv_child_cb_change_aio_ctx(BdrvChild *child, AioContext *ctx, + GHashTable *visited, Transaction *tran, + Error **errp) +{ + BlockDriverState *bs = child->opaque; + return bdrv_change_aio_context(bs, ctx, visited, tran, errp); +} + static bool bdrv_child_cb_can_set_aio_ctx(BdrvChild *child, AioContext *ctx, GSList **ignore, Error **errp) { @@ -XXX,XX +XXX,XX @@ const BdrvChildClass child_of_bds = { .inactivate = bdrv_child_cb_inactivate, .can_set_aio_ctx = bdrv_child_cb_can_set_aio_ctx, .set_aio_ctx = bdrv_child_cb_set_aio_ctx, + .change_aio_ctx = bdrv_child_cb_change_aio_ctx, .update_filename = bdrv_child_cb_update_filename, .get_parent_aio_context = child_of_bds_get_parent_aio_context, }; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> blk_root_change_aio_ctx() is very similar to blk_root_can_set_aio_ctx(), but implements a new transaction so that if all check pass, the new transaction's .commit will take care of changing the BlockBackend AioContext. blk_root_set_aio_ctx_commit() is the same as blk_root_set_aio_ctx(). Note: bdrv_child_try_change_aio_context() is not called by anyone at this point. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-7-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/block-backend.c | 52 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static bool blk_root_can_set_aio_ctx(BdrvChild *child, AioContext *ctx, GSList **ignore, Error **errp); static void blk_root_set_aio_ctx(BdrvChild *child, AioContext *ctx, GSList **ignore); +static bool blk_root_change_aio_ctx(BdrvChild *child, AioContext *ctx, + GHashTable *visited, Transaction *tran, + Error **errp); static char *blk_root_get_parent_desc(BdrvChild *child) { @@ -XXX,XX +XXX,XX @@ static const BdrvChildClass child_root = { .can_set_aio_ctx = blk_root_can_set_aio_ctx, .set_aio_ctx = blk_root_set_aio_ctx, + .change_aio_ctx = blk_root_change_aio_ctx, .get_parent_aio_context = blk_root_get_parent_aio_context, }; @@ -XXX,XX +XXX,XX @@ int blk_set_aio_context(BlockBackend *blk, AioContext *new_context, return blk_do_set_aio_context(blk, new_context, true, errp); } +typedef struct BdrvStateBlkRootContext { + AioContext *new_ctx; + BlockBackend *blk; +} BdrvStateBlkRootContext; + +static void blk_root_set_aio_ctx_commit(void *opaque) +{ + BdrvStateBlkRootContext *s = opaque; + BlockBackend *blk = s->blk; + + blk_do_set_aio_context(blk, s->new_ctx, false, &error_abort); +} + +static TransactionActionDrv set_blk_root_context = { + .commit = blk_root_set_aio_ctx_commit, + .clean = g_free, +}; + +static bool blk_root_change_aio_ctx(BdrvChild *child, AioContext *ctx, + GHashTable *visited, Transaction *tran, + Error **errp) +{ + BlockBackend *blk = child->opaque; + BdrvStateBlkRootContext *s; + + if (!blk->allow_aio_context_change) { + /* + * Manually created BlockBackends (those with a name) that are not + * attached to anything can change their AioContext without updating + * their user; return an error for others. + */ + if (!blk->name || blk->dev) { + /* TODO Add BB name/QOM path */ + error_setg(errp, "Cannot change iothread of active block backend"); + return false; + } + } + + s = g_new(BdrvStateBlkRootContext, 1); + *s = (BdrvStateBlkRootContext) { + .new_ctx = ctx, + .blk = blk, + }; + + tran_add(tran, &set_blk_root_context, s); + return true; +} + static bool blk_root_can_set_aio_ctx(BdrvChild *child, AioContext *ctx, GSList **ignore, Error **errp) { -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Replace all direct usage of ->can_set_aio_ctx and ->set_aio_ctx, and call bdrv_child_try_change_aio_context() in bdrv_try_set_aio_context(), the main function called through the whole block layer. From this point onwards, ->can_set_aio_ctx and ->set_aio_ctx won't be used anymore. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-8-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 44 ++++++++++++++++++++++++------------------- block/block-backend.c | 8 ++++++-- 2 files changed, 31 insertions(+), 21 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_child_common_abort(void *opaque) } if (bdrv_child_get_parent_aio_context(s->child) != s->old_parent_ctx) { - GSList *ignore; + Transaction *tran; + GHashTable *visited; + bool ret; - /* No need to ignore `child`, because it has been detached already */ - ignore = NULL; - s->child->klass->can_set_aio_ctx(s->child, s->old_parent_ctx, &ignore, - &error_abort); - g_slist_free(ignore); + tran = tran_new(); - ignore = NULL; - s->child->klass->set_aio_ctx(s->child, s->old_parent_ctx, &ignore); - g_slist_free(ignore); + /* No need to visit `child`, because it has been detached already */ + visited = g_hash_table_new(NULL, NULL); + ret = s->child->klass->change_aio_ctx(s->child, s->old_parent_ctx, + visited, tran, &error_abort); + g_hash_table_destroy(visited); + + /* transaction is supposed to always succeed */ + assert(ret == true); + tran_commit(tran); } bdrv_unref(bs); @@ -XXX,XX +XXX,XX @@ static BdrvChild *bdrv_attach_child_common(BlockDriverState *child_bs, Error *local_err = NULL; int ret = bdrv_try_set_aio_context(child_bs, parent_ctx, &local_err); - if (ret < 0 && child_class->can_set_aio_ctx) { - GSList *ignore = g_slist_prepend(NULL, new_child); - if (child_class->can_set_aio_ctx(new_child, child_ctx, &ignore, - NULL)) - { + if (ret < 0 && child_class->change_aio_ctx) { + Transaction *tran = tran_new(); + GHashTable *visited = g_hash_table_new(NULL, NULL); + bool ret_child; + + g_hash_table_add(visited, new_child); + ret_child = child_class->change_aio_ctx(new_child, child_ctx, + visited, tran, NULL); + if (ret_child == true) { error_free(local_err); ret = 0; - g_slist_free(ignore); - ignore = g_slist_prepend(NULL, new_child); - child_class->set_aio_ctx(new_child, child_ctx, &ignore); } - g_slist_free(ignore); + tran_finalize(tran, ret_child == true ? 0 : -1); + g_hash_table_destroy(visited); } if (ret < 0) { @@ -XXX,XX +XXX,XX @@ int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, Error **errp) { GLOBAL_STATE_CODE(); - return bdrv_child_try_set_aio_context(bs, ctx, NULL, errp); + return bdrv_child_try_change_aio_context(bs, ctx, NULL, errp); } void bdrv_add_aio_context_notifier(BlockDriverState *bs, diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static int blk_do_set_aio_context(BlockBackend *blk, AioContext *new_context, bdrv_ref(bs); if (update_root_node) { - ret = bdrv_child_try_set_aio_context(bs, new_context, blk->root, - errp); + /* + * update_root_node MUST be false for blk_root_set_aio_ctx_commit(), + * as we are already in the commit function of a transaction. + */ + ret = bdrv_child_try_change_aio_context(bs, new_context, blk->root, + errp); if (ret < 0) { bdrv_unref(bs); return ret; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Together with all _can_set_ and _set_ APIs, as they are not needed anymore. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-9-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-global-state.h | 9 -- include/block/block_int-common.h | 4 - block.c | 196 ----------------------------- block/block-backend.c | 33 ----- blockjob.c | 35 ------ 5 files changed, 277 deletions(-) diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -XXX,XX +XXX,XX @@ void coroutine_fn bdrv_co_lock(BlockDriverState *bs); */ void coroutine_fn bdrv_co_unlock(BlockDriverState *bs); -void bdrv_set_aio_context_ignore(BlockDriverState *bs, - AioContext *new_context, GSList **ignore); int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, Error **errp); -int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, - BdrvChild *ignore_child, Error **errp); -bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx, - GSList **ignore, Error **errp); -bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, - GSList **ignore, Error **errp); AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c); - bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, GHashTable *visited, Transaction *tran, Error **errp); diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BdrvChildClass { int (*update_filename)(BdrvChild *child, BlockDriverState *new_base, const char *filename, Error **errp); - bool (*can_set_aio_ctx)(BdrvChild *child, AioContext *ctx, - GSList **ignore, Error **errp); - void (*set_aio_ctx)(BdrvChild *child, AioContext *ctx, GSList **ignore); - bool (*change_aio_ctx)(BdrvChild *child, AioContext *ctx, GHashTable *visited, Transaction *tran, Error **errp); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static bool bdrv_child_cb_change_aio_ctx(BdrvChild *child, AioContext *ctx, return bdrv_change_aio_context(bs, ctx, visited, tran, errp); } -static bool bdrv_child_cb_can_set_aio_ctx(BdrvChild *child, AioContext *ctx, - GSList **ignore, Error **errp) -{ - BlockDriverState *bs = child->opaque; - return bdrv_can_set_aio_context(bs, ctx, ignore, errp); -} - -static void bdrv_child_cb_set_aio_ctx(BdrvChild *child, AioContext *ctx, - GSList **ignore) -{ - BlockDriverState *bs = child->opaque; - return bdrv_set_aio_context_ignore(bs, ctx, ignore); -} - /* * Returns the options and flags that a temporary snapshot should get, based on * the originally requested flags (the originally requested image will have @@ -XXX,XX +XXX,XX @@ const BdrvChildClass child_of_bds = { .attach = bdrv_child_cb_attach, .detach = bdrv_child_cb_detach, .inactivate = bdrv_child_cb_inactivate, - .can_set_aio_ctx = bdrv_child_cb_can_set_aio_ctx, - .set_aio_ctx = bdrv_child_cb_set_aio_ctx, .change_aio_ctx = bdrv_child_cb_change_aio_ctx, .update_filename = bdrv_child_cb_update_filename, .get_parent_aio_context = child_of_bds_get_parent_aio_context, @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_aio_context(BlockDriverState *bs, bs->walking_aio_notifiers = false; } -/* - * Changes the AioContext used for fd handlers, timers, and BHs by this - * BlockDriverState and all its children and parents. - * - * Must be called from the main AioContext. - * - * The caller must own the AioContext lock for the old AioContext of bs, but it - * must not own the AioContext lock for new_context (unless new_context is the - * same as the current context of bs). - * - * @ignore will accumulate all visited BdrvChild objects. The caller is - * responsible for freeing the list afterwards. - */ -void bdrv_set_aio_context_ignore(BlockDriverState *bs, - AioContext *new_context, GSList **ignore) -{ - AioContext *old_context = bdrv_get_aio_context(bs); - GSList *children_to_process = NULL; - GSList *parents_to_process = NULL; - GSList *entry; - BdrvChild *child, *parent; - - g_assert(qemu_get_current_aio_context() == qemu_get_aio_context()); - GLOBAL_STATE_CODE(); - - if (old_context == new_context) { - return; - } - - bdrv_drained_begin(bs); - - QLIST_FOREACH(child, &bs->children, next) { - if (g_slist_find(*ignore, child)) { - continue; - } - *ignore = g_slist_prepend(*ignore, child); - children_to_process = g_slist_prepend(children_to_process, child); - } - - QLIST_FOREACH(parent, &bs->parents, next_parent) { - if (g_slist_find(*ignore, parent)) { - continue; - } - *ignore = g_slist_prepend(*ignore, parent); - parents_to_process = g_slist_prepend(parents_to_process, parent); - } - - for (entry = children_to_process; - entry != NULL; - entry = g_slist_next(entry)) { - child = entry->data; - bdrv_set_aio_context_ignore(child->bs, new_context, ignore); - } - g_slist_free(children_to_process); - - for (entry = parents_to_process; - entry != NULL; - entry = g_slist_next(entry)) { - parent = entry->data; - assert(parent->klass->set_aio_ctx); - parent->klass->set_aio_ctx(parent, new_context, ignore); - } - g_slist_free(parents_to_process); - - bdrv_detach_aio_context(bs); - - /* Acquire the new context, if necessary */ - if (qemu_get_aio_context() != new_context) { - aio_context_acquire(new_context); - } - - bdrv_attach_aio_context(bs, new_context); - - /* - * If this function was recursively called from - * bdrv_set_aio_context_ignore(), there may be nodes in the - * subtree that have not yet been moved to the new AioContext. - * Release the old one so bdrv_drained_end() can poll them. - */ - if (qemu_get_aio_context() != old_context) { - aio_context_release(old_context); - } - - bdrv_drained_end(bs); - - if (qemu_get_aio_context() != old_context) { - aio_context_acquire(old_context); - } - if (qemu_get_aio_context() != new_context) { - aio_context_release(new_context); - } -} - -static bool bdrv_parent_can_set_aio_context(BdrvChild *c, AioContext *ctx, - GSList **ignore, Error **errp) -{ - GLOBAL_STATE_CODE(); - if (g_slist_find(*ignore, c)) { - return true; - } - *ignore = g_slist_prepend(*ignore, c); - - /* - * A BdrvChildClass that doesn't handle AioContext changes cannot - * tolerate any AioContext changes - */ - if (!c->klass->can_set_aio_ctx) { - char *user = bdrv_child_user_desc(c); - error_setg(errp, "Changing iothreads is not supported by %s", user); - g_free(user); - return false; - } - if (!c->klass->can_set_aio_ctx(c, ctx, ignore, errp)) { - assert(!errp || *errp); - return false; - } - return true; -} - typedef struct BdrvStateSetAioContext { AioContext *new_ctx; BlockDriverState *bs; @@ -XXX,XX +XXX,XX @@ static bool bdrv_parent_change_aio_context(BdrvChild *c, AioContext *ctx, return true; } -bool bdrv_child_can_set_aio_context(BdrvChild *c, AioContext *ctx, - GSList **ignore, Error **errp) -{ - GLOBAL_STATE_CODE(); - if (g_slist_find(*ignore, c)) { - return true; - } - *ignore = g_slist_prepend(*ignore, c); - return bdrv_can_set_aio_context(c->bs, ctx, ignore, errp); -} - bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, GHashTable *visited, Transaction *tran, Error **errp) @@ -XXX,XX +XXX,XX @@ bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, return bdrv_change_aio_context(c->bs, ctx, visited, tran, errp); } -/* @ignore will accumulate all visited BdrvChild object. The caller is - * responsible for freeing the list afterwards. */ -bool bdrv_can_set_aio_context(BlockDriverState *bs, AioContext *ctx, - GSList **ignore, Error **errp) -{ - BdrvChild *c; - - if (bdrv_get_aio_context(bs) == ctx) { - return true; - } - - GLOBAL_STATE_CODE(); - - QLIST_FOREACH(c, &bs->parents, next_parent) { - if (!bdrv_parent_can_set_aio_context(c, ctx, ignore, errp)) { - return false; - } - } - QLIST_FOREACH(c, &bs->children, next) { - if (!bdrv_child_can_set_aio_context(c, ctx, ignore, errp)) { - return false; - } - } - - return true; -} - static void bdrv_set_aio_context_clean(void *opaque) { BdrvStateSetAioContext *state = (BdrvStateSetAioContext *) opaque; @@ -XXX,XX +XXX,XX @@ static bool bdrv_change_aio_context(BlockDriverState *bs, AioContext *ctx, return true; } -int bdrv_child_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, - BdrvChild *ignore_child, Error **errp) -{ - GSList *ignore; - bool ret; - - GLOBAL_STATE_CODE(); - - ignore = ignore_child ? g_slist_prepend(NULL, ignore_child) : NULL; - ret = bdrv_can_set_aio_context(bs, ctx, &ignore, errp); - g_slist_free(ignore); - - if (!ret) { - return -EPERM; - } - - ignore = ignore_child ? g_slist_prepend(NULL, ignore_child) : NULL; - bdrv_set_aio_context_ignore(bs, ctx, &ignore); - g_slist_free(ignore); - - return 0; -} - /* * Change bs's and recursively all of its parents' and children's AioContext * to the given new context, returning an error if that isn't possible. diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static void blk_root_drained_end(BdrvChild *child, int *drained_end_counter); static void blk_root_change_media(BdrvChild *child, bool load); static void blk_root_resize(BdrvChild *child); -static bool blk_root_can_set_aio_ctx(BdrvChild *child, AioContext *ctx, - GSList **ignore, Error **errp); -static void blk_root_set_aio_ctx(BdrvChild *child, AioContext *ctx, - GSList **ignore); static bool blk_root_change_aio_ctx(BdrvChild *child, AioContext *ctx, GHashTable *visited, Transaction *tran, Error **errp); @@ -XXX,XX +XXX,XX @@ static const BdrvChildClass child_root = { .attach = blk_root_attach, .detach = blk_root_detach, - .can_set_aio_ctx = blk_root_can_set_aio_ctx, - .set_aio_ctx = blk_root_set_aio_ctx, .change_aio_ctx = blk_root_change_aio_ctx, .get_parent_aio_context = blk_root_get_parent_aio_context, @@ -XXX,XX +XXX,XX @@ static bool blk_root_change_aio_ctx(BdrvChild *child, AioContext *ctx, return true; } -static bool blk_root_can_set_aio_ctx(BdrvChild *child, AioContext *ctx, - GSList **ignore, Error **errp) -{ - BlockBackend *blk = child->opaque; - - if (blk->allow_aio_context_change) { - return true; - } - - /* Only manually created BlockBackends that are not attached to anything - * can change their AioContext without updating their user. */ - if (!blk->name || blk->dev) { - /* TODO Add BB name/QOM path */ - error_setg(errp, "Cannot change iothread of active block backend"); - return false; - } - - return true; -} - -static void blk_root_set_aio_ctx(BdrvChild *child, AioContext *ctx, - GSList **ignore) -{ - BlockBackend *blk = child->opaque; - blk_do_set_aio_context(blk, ctx, false, &error_abort); -} - void blk_add_aio_context_notifier(BlockBackend *blk, void (*attached_aio_context)(AioContext *new_context, void *opaque), void (*detach_aio_context)(void *opaque), void *opaque) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static bool child_job_change_aio_ctx(BdrvChild *c, AioContext *ctx, return true; } -static bool child_job_can_set_aio_ctx(BdrvChild *c, AioContext *ctx, - GSList **ignore, Error **errp) -{ - BlockJob *job = c->opaque; - GSList *l; - - for (l = job->nodes; l; l = l->next) { - BdrvChild *sibling = l->data; - if (!bdrv_child_can_set_aio_context(sibling, ctx, ignore, errp)) { - return false; - } - } - return true; -} - -static void child_job_set_aio_ctx(BdrvChild *c, AioContext *ctx, - GSList **ignore) -{ - BlockJob *job = c->opaque; - GSList *l; - - for (l = job->nodes; l; l = l->next) { - BdrvChild *sibling = l->data; - if (g_slist_find(*ignore, sibling)) { - continue; - } - *ignore = g_slist_prepend(*ignore, sibling); - bdrv_set_aio_context_ignore(sibling->bs, ctx, ignore); - } - - job_set_aio_context(&job->job, ctx); -} - static AioContext *child_job_get_parent_aio_context(BdrvChild *c) { BlockJob *job = c->opaque; @@ -XXX,XX +XXX,XX @@ static const BdrvChildClass child_job = { .drained_begin = child_job_drained_begin, .drained_poll = child_job_drained_poll, .drained_end = child_job_drained_end, - .can_set_aio_ctx = child_job_can_set_aio_ctx, - .set_aio_ctx = child_job_set_aio_ctx, .change_aio_ctx = child_job_change_aio_ctx, .stay_at_node = true, .get_parent_aio_context = child_job_get_parent_aio_context, -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> No functional changes intended. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-10-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-global-state.h | 4 ++-- block.c | 6 +++--- block/block-backend.c | 3 +-- 3 files changed, 6 insertions(+), 7 deletions(-) diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -XXX,XX +XXX,XX @@ AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c); bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, GHashTable *visited, Transaction *tran, Error **errp); -int bdrv_child_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, - BdrvChild *ignore_child, Error **errp); +int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, + BdrvChild *ignore_child, Error **errp); int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz); int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static bool bdrv_change_aio_context(BlockDriverState *bs, AioContext *ctx, * bdrv_drained_end calls BDRV_POLL_WHILE that assumes the lock is taken too. * Therefore the new AioContext lock must not be taken by the caller. */ -int bdrv_child_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, - BdrvChild *ignore_child, Error **errp) +int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, + BdrvChild *ignore_child, Error **errp) { Transaction *tran; GHashTable *visited; @@ -XXX,XX +XXX,XX @@ int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, Error **errp) { GLOBAL_STATE_CODE(); - return bdrv_child_try_change_aio_context(bs, ctx, NULL, errp); + return bdrv_try_change_aio_context(bs, ctx, NULL, errp); } void bdrv_add_aio_context_notifier(BlockDriverState *bs, diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static int blk_do_set_aio_context(BlockBackend *blk, AioContext *new_context, * update_root_node MUST be false for blk_root_set_aio_ctx_commit(), * as we are already in the commit function of a transaction. */ - ret = bdrv_child_try_change_aio_context(bs, new_context, blk->root, - errp); + ret = bdrv_try_change_aio_context(bs, new_context, blk->root, errp); if (ret < 0) { bdrv_unref(bs); return ret; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> No functional change intended. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221025084952.2139888-11-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- docs/devel/multiple-iothreads.txt | 4 ++-- include/block/block-global-state.h | 2 -- block.c | 14 ++++---------- block/export/export.c | 2 +- blockdev.c | 22 +++++++++++----------- job.c | 2 +- tests/unit/test-bdrv-drain.c | 6 +++--- tests/unit/test-block-iothread.c | 10 +++++----- 8 files changed, 27 insertions(+), 35 deletions(-) diff --git a/docs/devel/multiple-iothreads.txt b/docs/devel/multiple-iothreads.txt index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/multiple-iothreads.txt +++ b/docs/devel/multiple-iothreads.txt @@ -XXX,XX +XXX,XX @@ The AioContext originates from the QEMU block layer, even though nowadays AioContext is a generic event loop that can be used by any QEMU subsystem. The block layer has support for AioContext integrated. Each BlockDriverState -is associated with an AioContext using bdrv_try_set_aio_context() and +is associated with an AioContext using bdrv_try_change_aio_context() and bdrv_get_aio_context(). This allows block layer code to process I/O inside the right AioContext. Other subsystems may wish to follow a similar approach. @@ -XXX,XX +XXX,XX @@ Long-running jobs (usually in the form of coroutines) are best scheduled in the BlockDriverState's AioContext to avoid the need to acquire/release around each bdrv_*() call. The functions bdrv_add/remove_aio_context_notifier, or alternatively blk_add/remove_aio_context_notifier if you use BlockBackends, -can be used to get a notification whenever bdrv_try_set_aio_context() moves a +can be used to get a notification whenever bdrv_try_change_aio_context() moves a BlockDriverState to a different AioContext. diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -XXX,XX +XXX,XX @@ void coroutine_fn bdrv_co_lock(BlockDriverState *bs); */ void coroutine_fn bdrv_co_unlock(BlockDriverState *bs); -int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, - Error **errp); AioContext *bdrv_child_get_parent_aio_context(BdrvChild *c); bool bdrv_child_change_aio_context(BdrvChild *c, AioContext *ctx, GHashTable *visited, Transaction *tran, diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_attach_child_common_abort(void *opaque) bdrv_replace_child_noperm(s->child, NULL); if (bdrv_get_aio_context(bs) != s->old_child_ctx) { - bdrv_try_set_aio_context(bs, s->old_child_ctx, &error_abort); + bdrv_try_change_aio_context(bs, s->old_child_ctx, NULL, &error_abort); } if (bdrv_child_get_parent_aio_context(s->child) != s->old_parent_ctx) { @@ -XXX,XX +XXX,XX @@ static BdrvChild *bdrv_attach_child_common(BlockDriverState *child_bs, parent_ctx = bdrv_child_get_parent_aio_context(new_child); if (child_ctx != parent_ctx) { Error *local_err = NULL; - int ret = bdrv_try_set_aio_context(child_bs, parent_ctx, &local_err); + int ret = bdrv_try_change_aio_context(child_bs, parent_ctx, NULL, + &local_err); if (ret < 0 && child_class->change_aio_ctx) { Transaction *tran = tran_new(); @@ -XXX,XX +XXX,XX @@ static void bdrv_detach_child(BdrvChild *child) * When the parent requiring a non-default AioContext is removed, the * node moves back to the main AioContext */ - bdrv_try_set_aio_context(old_bs, qemu_get_aio_context(), NULL); + bdrv_try_change_aio_context(old_bs, qemu_get_aio_context(), NULL, NULL); } } @@ -XXX,XX +XXX,XX @@ int bdrv_try_change_aio_context(BlockDriverState *bs, AioContext *ctx, return 0; } -int bdrv_try_set_aio_context(BlockDriverState *bs, AioContext *ctx, - Error **errp) -{ - GLOBAL_STATE_CODE(); - return bdrv_try_change_aio_context(bs, ctx, NULL, errp); -} - void bdrv_add_aio_context_notifier(BlockDriverState *bs, void (*attached_aio_context)(AioContext *new_context, void *opaque), void (*detach_aio_context)(void *opaque), void *opaque) diff --git a/block/export/export.c b/block/export/export.c index XXXXXXX..XXXXXXX 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -XXX,XX +XXX,XX @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) /* Ignore errors with fixed-iothread=false */ set_context_errp = fixed_iothread ? errp : NULL; - ret = bdrv_try_set_aio_context(bs, new_ctx, set_context_errp); + ret = bdrv_try_change_aio_context(bs, new_ctx, NULL, set_context_errp); if (ret == 0) { aio_context_release(ctx); aio_context_acquire(new_ctx); diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static void external_snapshot_abort(BlkActionState *common) aio_context_release(aio_context); aio_context_acquire(tmp_context); - ret = bdrv_try_set_aio_context(state->old_bs, - aio_context, NULL); + ret = bdrv_try_change_aio_context(state->old_bs, + aio_context, NULL, NULL); assert(ret == 0); aio_context_release(tmp_context); @@ -XXX,XX +XXX,XX @@ static void drive_backup_prepare(BlkActionState *common, Error **errp) goto out; } - /* Honor bdrv_try_set_aio_context() context acquisition requirements. */ + /* Honor bdrv_try_change_aio_context() context acquisition requirements. */ old_context = bdrv_get_aio_context(target_bs); aio_context_release(aio_context); aio_context_acquire(old_context); - ret = bdrv_try_set_aio_context(target_bs, aio_context, errp); + ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp); if (ret < 0) { bdrv_unref(target_bs); aio_context_release(old_context); @@ -XXX,XX +XXX,XX @@ static void blockdev_backup_prepare(BlkActionState *common, Error **errp) return; } - /* Honor bdrv_try_set_aio_context() context acquisition requirements. */ + /* Honor bdrv_try_change_aio_context() context acquisition requirements. */ aio_context = bdrv_get_aio_context(bs); old_context = bdrv_get_aio_context(target_bs); aio_context_acquire(old_context); - ret = bdrv_try_set_aio_context(target_bs, aio_context, errp); + ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp); if (ret < 0) { aio_context_release(old_context); return; @@ -XXX,XX +XXX,XX @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp) !bdrv_has_zero_init(target_bs))); - /* Honor bdrv_try_set_aio_context() context acquisition requirements. */ + /* Honor bdrv_try_change_aio_context() context acquisition requirements. */ old_context = bdrv_get_aio_context(target_bs); aio_context_release(aio_context); aio_context_acquire(old_context); - ret = bdrv_try_set_aio_context(target_bs, aio_context, errp); + ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp); if (ret < 0) { bdrv_unref(target_bs); aio_context_release(old_context); @@ -XXX,XX +XXX,XX @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id, zero_target = (sync == MIRROR_SYNC_MODE_FULL); - /* Honor bdrv_try_set_aio_context() context acquisition requirements. */ + /* Honor bdrv_try_change_aio_context() context acquisition requirements. */ old_context = bdrv_get_aio_context(target_bs); aio_context = bdrv_get_aio_context(bs); aio_context_acquire(old_context); - ret = bdrv_try_set_aio_context(target_bs, aio_context, errp); + ret = bdrv_try_change_aio_context(target_bs, aio_context, NULL, errp); aio_context_release(old_context); aio_context_acquire(aio_context); @@ -XXX,XX +XXX,XX @@ void qmp_x_blockdev_set_iothread(const char *node_name, StrOrNull *iothread, old_context = bdrv_get_aio_context(bs); aio_context_acquire(old_context); - bdrv_try_set_aio_context(bs, new_context, errp); + bdrv_try_change_aio_context(bs, new_context, NULL, errp); aio_context_release(old_context); } diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn job_do_yield_locked(Job *job, uint64_t ns) next_aio_context = job->aio_context; /* * Coroutine has resumed, but in the meanwhile the job AioContext - * might have changed via bdrv_try_set_aio_context(), so we need to move + * might have changed via bdrv_try_change_aio_context(), so we need to move * the coroutine too in the new aiocontext. */ while (qemu_get_current_aio_context() != next_aio_context) { diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-bdrv-drain.c +++ b/tests/unit/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_set_aio_context(void) &error_abort); bdrv_drained_begin(bs); - bdrv_try_set_aio_context(bs, ctx_a, &error_abort); + bdrv_try_change_aio_context(bs, ctx_a, NULL, &error_abort); aio_context_acquire(ctx_a); bdrv_drained_end(bs); bdrv_drained_begin(bs); - bdrv_try_set_aio_context(bs, ctx_b, &error_abort); + bdrv_try_change_aio_context(bs, ctx_b, NULL, &error_abort); aio_context_release(ctx_a); aio_context_acquire(ctx_b); - bdrv_try_set_aio_context(bs, qemu_get_aio_context(), &error_abort); + bdrv_try_change_aio_context(bs, qemu_get_aio_context(), NULL, &error_abort); aio_context_release(ctx_b); bdrv_drained_end(bs); diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_propagate_mirror(void) filter = bdrv_find_node("filter_node"); /* Change the AioContext of src */ - bdrv_try_set_aio_context(src, ctx, &error_abort); + bdrv_try_change_aio_context(src, ctx, NULL, &error_abort); g_assert(bdrv_get_aio_context(src) == ctx); g_assert(bdrv_get_aio_context(target) == ctx); g_assert(bdrv_get_aio_context(filter) == ctx); @@ -XXX,XX +XXX,XX @@ static void test_propagate_mirror(void) /* Change the AioContext of target */ aio_context_acquire(ctx); - bdrv_try_set_aio_context(target, main_ctx, &error_abort); + bdrv_try_change_aio_context(target, main_ctx, NULL, &error_abort); aio_context_release(ctx); g_assert(bdrv_get_aio_context(src) == main_ctx); g_assert(bdrv_get_aio_context(target) == main_ctx); @@ -XXX,XX +XXX,XX @@ static void test_propagate_mirror(void) blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL); blk_insert_bs(blk, src, &error_abort); - bdrv_try_set_aio_context(target, ctx, &local_err); + bdrv_try_change_aio_context(target, ctx, NULL, &local_err); error_free_or_abort(&local_err); g_assert(blk_get_aio_context(blk) == main_ctx); @@ -XXX,XX +XXX,XX @@ static void test_propagate_mirror(void) /* ...unless we explicitly allow it */ aio_context_acquire(ctx); blk_set_allow_aio_context_change(blk, true); - bdrv_try_set_aio_context(target, ctx, &error_abort); + bdrv_try_change_aio_context(target, ctx, NULL, &error_abort); aio_context_release(ctx); g_assert(blk_get_aio_context(blk) == ctx); @@ -XXX,XX +XXX,XX @@ static void test_propagate_mirror(void) aio_context_acquire(ctx); blk_set_aio_context(blk, main_ctx, &error_abort); - bdrv_try_set_aio_context(target, main_ctx, &error_abort); + bdrv_try_change_aio_context(target, main_ctx, NULL, &error_abort); aio_context_release(ctx); blk_unref(blk); -- 2.37.3 From: Bin Meng <bin.meng@windriver.com> libnfs.h declares nfs_fstat() as the following for win32: int nfs_fstat(struct nfs_context *nfs, struct nfsfh *nfsfh, struct __stat64 *st); The 'st' parameter should be of type 'struct __stat64'. The codes happen to build successfully for 64-bit Windows, but it does not build for 32-bit Windows. Fixes: 6542aa9c75bc ("block: add native support for NFS") Fixes: 18a8056e0bc7 ("block/nfs: cache allocated filesize for read-only files") Signed-off-by: Bin Meng <bin.meng@windriver.com> Message-Id: <20220908132817.1831008-6-bmeng.cn@gmail.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/nfs.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static int64_t nfs_client_open(NFSClient *client, BlockdevOptionsNfs *opts, int flags, int open_flags, Error **errp) { int64_t ret = -EINVAL; +#ifdef _WIN32 + struct __stat64 st; +#else struct stat st; +#endif char *file = NULL, *strp = NULL; qemu_mutex_init(&client->mutex); @@ -XXX,XX +XXX,XX @@ static int nfs_reopen_prepare(BDRVReopenState *state, BlockReopenQueue *queue, Error **errp) { NFSClient *client = state->bs->opaque; +#ifdef _WIN32 + struct __stat64 st; +#else struct stat st; +#endif int ret = 0; if (state->flags & BDRV_O_RDWR && bdrv_is_read_only(state->bs)) { -- 2.37.3 From: Alberto Faria <afaria@redhat.com> The .set_speed callback is not called from coroutine. Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-2-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/backup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn backup_pause(Job *job) } } -static void coroutine_fn backup_set_speed(BlockJob *job, int64_t speed) +static void backup_set_speed(BlockJob *job, int64_t speed) { BackupBlockJob *s = container_of(job, BackupBlockJob, common); -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-3-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset, return (pnum == bytes) && (ret & BDRV_BLOCK_ZERO); } -int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t offset, - int64_t bytes, int64_t *pnum) +int bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, + int64_t *pnum) { int ret; int64_t dummy; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> hmp_block_resize and hmp_screendump are defined as a ".coroutine = true" command, so they must be coroutine_fn. Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-4-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-hmp-cmds.h | 2 +- include/monitor/hmp.h | 3 ++- block/monitor/block-hmp-cmds.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/block/block-hmp-cmds.h b/include/block/block-hmp-cmds.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-hmp-cmds.h +++ b/include/block/block-hmp-cmds.h @@ -XXX,XX +XXX,XX @@ void hmp_nbd_server_add(Monitor *mon, const QDict *qdict); void hmp_nbd_server_remove(Monitor *mon, const QDict *qdict); void hmp_nbd_server_stop(Monitor *mon, const QDict *qdict); -void hmp_block_resize(Monitor *mon, const QDict *qdict); +void coroutine_fn hmp_block_resize(Monitor *mon, const QDict *qdict); void hmp_block_stream(Monitor *mon, const QDict *qdict); void hmp_block_passwd(Monitor *mon, const QDict *qdict); void hmp_block_set_io_throttle(Monitor *mon, const QDict *qdict); diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/monitor/hmp.h +++ b/include/monitor/hmp.h @@ -XXX,XX +XXX,XX @@ #define HMP_H #include "qemu/readline.h" +#include "qemu/coroutine.h" #include "qapi/qapi-types-common.h" bool hmp_handle_error(Monitor *mon, Error *err); @@ -XXX,XX +XXX,XX @@ void hmp_netdev_del(Monitor *mon, const QDict *qdict); void hmp_getfd(Monitor *mon, const QDict *qdict); void hmp_closefd(Monitor *mon, const QDict *qdict); void hmp_sendkey(Monitor *mon, const QDict *qdict); -void hmp_screendump(Monitor *mon, const QDict *qdict); +void coroutine_fn hmp_screendump(Monitor *mon, const QDict *qdict); void hmp_chardev_add(Monitor *mon, const QDict *qdict); void hmp_chardev_change(Monitor *mon, const QDict *qdict); void hmp_chardev_remove(Monitor *mon, const QDict *qdict); diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/block/monitor/block-hmp-cmds.c +++ b/block/monitor/block-hmp-cmds.c @@ -XXX,XX +XXX,XX @@ void hmp_nbd_server_stop(Monitor *mon, const QDict *qdict) hmp_handle_error(mon, err); } -void hmp_block_resize(Monitor *mon, const QDict *qdict) +void coroutine_fn hmp_block_resize(Monitor *mon, const QDict *qdict) { const char *device = qdict_get_str(qdict, "device"); int64_t size = qdict_get_int(qdict, "size"); -- 2.37.3 From: Alberto Faria <afaria@redhat.com> ssh_write is only called from ssh_co_writev. Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-5-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/ssh.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block/ssh.c b/block/ssh.c index XXXXXXX..XXXXXXX 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_co_readv(BlockDriverState *bs, return ret; } -static int ssh_write(BDRVSSHState *s, BlockDriverState *bs, - int64_t offset, size_t size, - QEMUIOVector *qiov) +static coroutine_fn int ssh_write(BDRVSSHState *s, BlockDriverState *bs, + int64_t offset, size_t size, + QEMUIOVector *qiov) { ssize_t r; size_t written; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> The functions are marked coroutine_fn in the definition. Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-6-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block-io.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/block/block-io.h b/include/block/block-io.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -XXX,XX +XXX,XX @@ void bdrv_aio_cancel(BlockAIOCB *acb); void bdrv_aio_cancel_async(BlockAIOCB *acb); /* sg packet commands */ -int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf); +int coroutine_fn bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf); /* Ensure contents are flushed to disk. */ int coroutine_fn bdrv_co_flush(BlockDriverState *bs); -int bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int64_t bytes); +int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, + int64_t bytes); bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, -- 2.37.3 From: Alberto Faria <afaria@redhat.com> The functions are marked coroutine_fn in the definition. Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-7-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/coroutine.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_init(CoRwlock *lock); * of a parallel writer, control is transferred to the caller of the current * coroutine. */ -void qemu_co_rwlock_rdlock(CoRwlock *lock); +void coroutine_fn qemu_co_rwlock_rdlock(CoRwlock *lock); /** * Write Locks the CoRwlock from a reader. This is a bit more efficient than @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_rdlock(CoRwlock *lock); * to the caller of the current coroutine; another writer might run while * @qemu_co_rwlock_upgrade blocks. */ -void qemu_co_rwlock_upgrade(CoRwlock *lock); +void coroutine_fn qemu_co_rwlock_upgrade(CoRwlock *lock); /** * Downgrades a write-side critical section to a reader. Downgrading with @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_upgrade(CoRwlock *lock); * followed by @qemu_co_rwlock_rdlock. This makes it more efficient, but * may also sometimes be necessary for correctness. */ -void qemu_co_rwlock_downgrade(CoRwlock *lock); +void coroutine_fn qemu_co_rwlock_downgrade(CoRwlock *lock); /** * Write Locks the mutex. If the lock cannot be taken immediately because * of a parallel reader, control is transferred to the caller of the current * coroutine. */ -void qemu_co_rwlock_wrlock(CoRwlock *lock); +void coroutine_fn qemu_co_rwlock_wrlock(CoRwlock *lock); /** * Unlocks the read/write lock and schedules the next coroutine that was * waiting for this lock to be run. */ -void qemu_co_rwlock_unlock(CoRwlock *lock); +void coroutine_fn qemu_co_rwlock_unlock(CoRwlock *lock); typedef struct QemuCoSleep { Coroutine *to_wake; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-8-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/coroutine.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ void qemu_coroutine_dec_pool_size(unsigned int additional_pool_size); * The same interface as qemu_sendv_recvv(), with added yielding. * XXX should mark these as coroutine_fn */ -ssize_t qemu_co_sendv_recvv(int sockfd, struct iovec *iov, unsigned iov_cnt, - size_t offset, size_t bytes, bool do_send); +ssize_t coroutine_fn qemu_co_sendv_recvv(int sockfd, struct iovec *iov, + unsigned iov_cnt, size_t offset, + size_t bytes, bool do_send); #define qemu_co_recvv(sockfd, iov, iov_cnt, offset, bytes) \ qemu_co_sendv_recvv(sockfd, iov, iov_cnt, offset, bytes, false) #define qemu_co_sendv(sockfd, iov, iov_cnt, offset, bytes) \ @@ -XXX,XX +XXX,XX @@ ssize_t qemu_co_sendv_recvv(int sockfd, struct iovec *iov, unsigned iov_cnt, /** * The same as above, but with just a single buffer */ -ssize_t qemu_co_send_recv(int sockfd, void *buf, size_t bytes, bool do_send); +ssize_t coroutine_fn qemu_co_send_recv(int sockfd, void *buf, size_t bytes, + bool do_send); #define qemu_co_recv(sockfd, buf, bytes) \ qemu_co_send_recv(sockfd, buf, bytes, false) #define qemu_co_send(sockfd, buf, bytes) \ -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-9-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.h | 14 +++++++------- include/block/block_int-common.h | 12 +++++------- 2 files changed, 12 insertions(+), 14 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_truncate_bitmaps_check(BlockDriverState *bs, Error **errp); bool qcow2_store_persistent_dirty_bitmaps(BlockDriverState *bs, bool release_stored, Error **errp); int qcow2_reopen_bitmaps_ro(BlockDriverState *bs, Error **errp); -bool qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs, - const char *name, - uint32_t granularity, - Error **errp); -int qcow2_co_remove_persistent_dirty_bitmap(BlockDriverState *bs, - const char *name, - Error **errp); +bool coroutine_fn qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs, + const char *name, + uint32_t granularity, + Error **errp); +int coroutine_fn qcow2_co_remove_persistent_dirty_bitmap(BlockDriverState *bs, + const char *name, + Error **errp); bool qcow2_supports_persistent_dirty_bitmap(BlockDriverState *bs); uint64_t qcow2_get_persistent_dirty_bitmap_size(BlockDriverState *bs, uint32_t cluster_size); diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { void coroutine_fn (*bdrv_co_drain_end)(BlockDriverState *bs); bool (*bdrv_supports_persistent_dirty_bitmap)(BlockDriverState *bs); - bool (*bdrv_co_can_store_new_dirty_bitmap)(BlockDriverState *bs, - const char *name, - uint32_t granularity, - Error **errp); - int (*bdrv_co_remove_persistent_dirty_bitmap)(BlockDriverState *bs, - const char *name, - Error **errp); + bool coroutine_fn (*bdrv_co_can_store_new_dirty_bitmap)( + BlockDriverState *bs, const char *name, uint32_t granularity, + Error **errp); + int coroutine_fn (*bdrv_co_remove_persistent_dirty_bitmap)( + BlockDriverState *bs, const char *name, Error **errp); }; static inline bool block_driver_can_compress(BlockDriver *drv) -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-10-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int64_t qcow2_check_vmstate_request(BlockDriverState *bs, return pos; } -static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t pos) +static coroutine_fn int qcow2_save_vmstate(BlockDriverState *bs, + QEMUIOVector *qiov, int64_t pos) { int64_t offset = qcow2_check_vmstate_request(bs, qiov, pos); if (offset < 0) { @@ -XXX,XX +XXX,XX @@ static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, return bs->drv->bdrv_co_pwritev_part(bs, offset, qiov->size, qiov, 0, 0); } -static int qcow2_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t pos) +static coroutine_fn int qcow2_load_vmstate(BlockDriverState *bs, + QEMUIOVector *qiov, int64_t pos) { int64_t offset = qcow2_check_vmstate_request(bs, qiov, pos); if (offset < 0) { -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-11-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/blkdebug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blkdebug.c b/block/blkdebug.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkdebug.c +++ b/block/blkdebug.c @@ -XXX,XX +XXX,XX @@ blkdebug_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes, return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags); } -static int blkdebug_co_flush(BlockDriverState *bs) +static int coroutine_fn blkdebug_co_flush(BlockDriverState *bs) { int err = rule_check(bs, 0, 0, BLKDEBUG_IO_TYPE_FLUSH); -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> get_cluster_offset() and decompress_cluster() are only called from the read and write paths. The validity of these was double-checked with Alberto Faria's static analyzer. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-12-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ typedef struct BDRVQcowState { static QemuOptsList qcow_create_opts; -static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset); +static int coroutine_fn decompress_cluster(BlockDriverState *bs, + uint64_t cluster_offset); static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename) { @@ -XXX,XX +XXX,XX @@ static int qcow_reopen_prepare(BDRVReopenState *state, * return 0 if not allocated, 1 if *result is assigned, and negative * errno on failure. */ -static int get_cluster_offset(BlockDriverState *bs, - uint64_t offset, int allocate, - int compressed_size, - int n_start, int n_end, uint64_t *result) +static int coroutine_fn get_cluster_offset(BlockDriverState *bs, + uint64_t offset, int allocate, + int compressed_size, + int n_start, int n_end, + uint64_t *result) { BDRVQcowState *s = bs->opaque; int min_index, i, j, l1_index, l2_index, ret; @@ -XXX,XX +XXX,XX @@ static int decompress_buffer(uint8_t *out_buf, int out_buf_size, return 0; } -static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset) +static int coroutine_fn decompress_cluster(BlockDriverState *bs, + uint64_t cluster_offset) { BDRVQcowState *s = bs->opaque; int ret, csize; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> The validity of these was double-checked with Alberto Faria's static analyzer. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-13-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.h | 18 +++++++++--------- block/qcow2-bitmap.c | 4 ++-- block/qcow2-cluster.c | 21 ++++++++++++--------- block/qcow2-refcount.c | 8 ++++---- 4 files changed, 27 insertions(+), 24 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_validate_table(BlockDriverState *bs, uint64_t offset, Error **errp); /* qcow2-refcount.c functions */ -int qcow2_refcount_init(BlockDriverState *bs); +int coroutine_fn qcow2_refcount_init(BlockDriverState *bs); void qcow2_refcount_close(BlockDriverState *bs); int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index, @@ -XXX,XX +XXX,XX @@ int qcow2_inc_refcounts_imrt(BlockDriverState *bs, BdrvCheckResult *res, int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order, BlockDriverAmendStatusCB *status_cb, void *cb_opaque, Error **errp); -int qcow2_shrink_reftable(BlockDriverState *bs); +int coroutine_fn qcow2_shrink_reftable(BlockDriverState *bs); int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size); int coroutine_fn qcow2_detect_metadata_preallocation(BlockDriverState *bs); /* qcow2-cluster.c functions */ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, bool exact_size); -int qcow2_shrink_l1_table(BlockDriverState *bs, uint64_t max_size); +int coroutine_fn qcow2_shrink_l1_table(BlockDriverState *bs, uint64_t max_size); int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index); int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num, uint8_t *buf, int nb_sectors, bool enc, Error **errp); @@ -XXX,XX +XXX,XX @@ int qcow2_get_host_offset(BlockDriverState *bs, uint64_t offset, int coroutine_fn qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset, unsigned int *bytes, uint64_t *host_offset, QCowL2Meta **m); -int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, - uint64_t offset, - int compressed_size, - uint64_t *host_offset); +int coroutine_fn qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, + uint64_t offset, + int compressed_size, + uint64_t *host_offset); void qcow2_parse_compressed_l2_entry(BlockDriverState *bs, uint64_t l2_entry, uint64_t *coffset, int *csize); @@ -XXX,XX +XXX,XX @@ void qcow2_cache_discard(Qcow2Cache *c, void *table); int qcow2_check_bitmaps_refcounts(BlockDriverState *bs, BdrvCheckResult *res, void **refcount_table, int64_t *refcount_table_size); -bool qcow2_load_dirty_bitmaps(BlockDriverState *bs, bool *header_updated, - Error **errp); +bool coroutine_fn qcow2_load_dirty_bitmaps(BlockDriverState *bs, + bool *header_updated, Error **errp); bool qcow2_get_bitmap_info_list(BlockDriverState *bs, Qcow2BitmapInfoList **info_list, Error **errp); int qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp); diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -XXX,XX +XXX,XX @@ static void set_readonly_helper(gpointer bitmap, gpointer value) * If header_updated is not NULL then it is set appropriately regardless of * the return value. */ -bool qcow2_load_dirty_bitmaps(BlockDriverState *bs, bool *header_updated, - Error **errp) +bool coroutine_fn qcow2_load_dirty_bitmaps(BlockDriverState *bs, + bool *header_updated, Error **errp) { BDRVQcow2State *s = bs->opaque; Qcow2BitmapList *bm_list; diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ #include "qemu/memalign.h" #include "trace.h" -int qcow2_shrink_l1_table(BlockDriverState *bs, uint64_t exact_size) +int coroutine_fn qcow2_shrink_l1_table(BlockDriverState *bs, + uint64_t exact_size) { BDRVQcow2State *s = bs->opaque; int new_l1_size, i, ret; @@ -XXX,XX +XXX,XX @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset, * * Return 0 on success and -errno in error cases */ -int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, - uint64_t offset, - int compressed_size, - uint64_t *host_offset) +int coroutine_fn qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, + uint64_t offset, + int compressed_size, + uint64_t *host_offset) { BDRVQcow2State *s = bs->opaque; int l2_index, ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn handle_dependencies(BlockDriverState *bs, * * -errno: in error cases */ -static int handle_copied(BlockDriverState *bs, uint64_t guest_offset, - uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m) +static int coroutine_fn handle_copied(BlockDriverState *bs, + uint64_t guest_offset, uint64_t *host_offset, uint64_t *bytes, + QCowL2Meta **m) { BDRVQcow2State *s = bs->opaque; int l2_index; @@ -XXX,XX +XXX,XX @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset, * * -errno: in error cases */ -static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset, - uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m) +static int coroutine_fn handle_alloc(BlockDriverState *bs, + uint64_t guest_offset, uint64_t *host_offset, uint64_t *bytes, + QCowL2Meta **m) { BDRVQcow2State *s = bs->opaque; int l2_index; diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static void update_max_refcount_table_index(BDRVQcow2State *s) s->max_refcount_table_index = i; } -int qcow2_refcount_init(BlockDriverState *bs) +int coroutine_fn qcow2_refcount_init(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; unsigned int refcount_table_size2, i; @@ -XXX,XX +XXX,XX @@ static int64_t get_refblock_offset(BlockDriverState *bs, uint64_t offset) return covering_refblock_offset; } -static int qcow2_discard_refcount_block(BlockDriverState *bs, - uint64_t discard_block_offs) +static int coroutine_fn +qcow2_discard_refcount_block(BlockDriverState *bs, uint64_t discard_block_offs) { BDRVQcow2State *s = bs->opaque; int64_t refblock_offs; @@ -XXX,XX +XXX,XX @@ static int qcow2_discard_refcount_block(BlockDriverState *bs, return 0; } -int qcow2_shrink_reftable(BlockDriverState *bs) +int coroutine_fn qcow2_shrink_reftable(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; uint64_t *reftable_tmp = -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> The validity of these was double-checked with Alberto Faria's static analyzer. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-14-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vmdk.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static void vmdk_refresh_limits(BlockDriverState *bs, Error **errp) * [@skip_start_sector, @skip_end_sector) is not copied or written, and leave * it for call to write user data in the request. */ -static int get_whole_cluster(BlockDriverState *bs, - VmdkExtent *extent, - uint64_t cluster_offset, - uint64_t offset, - uint64_t skip_start_bytes, - uint64_t skip_end_bytes, - bool zeroed) +static int coroutine_fn get_whole_cluster(BlockDriverState *bs, + VmdkExtent *extent, + uint64_t cluster_offset, + uint64_t offset, + uint64_t skip_start_bytes, + uint64_t skip_end_bytes, + bool zeroed) { int ret = VMDK_OK; int64_t cluster_bytes; @@ -XXX,XX +XXX,XX @@ exit: return ret; } -static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, - uint32_t offset) +static int coroutine_fn vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, + uint32_t offset) { offset = cpu_to_le32(offset); /* update L2 table */ @@ -XXX,XX +XXX,XX @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, * VMDK_UNALLOC if cluster is not mapped and @allocate is false. * VMDK_ERROR if failed. */ -static int get_cluster_offset(BlockDriverState *bs, - VmdkExtent *extent, - VmdkMetaData *m_data, - uint64_t offset, - bool allocate, - uint64_t *cluster_offset, - uint64_t skip_start_bytes, - uint64_t skip_end_bytes) +static int coroutine_fn get_cluster_offset(BlockDriverState *bs, + VmdkExtent *extent, + VmdkMetaData *m_data, + uint64_t offset, + bool allocate, + uint64_t *cluster_offset, + uint64_t skip_start_bytes, + uint64_t skip_end_bytes) { unsigned int l1_index, l2_offset, l2_index; int min_index, i, j; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-15-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/commit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) } if (base_len < len) { - ret = blk_truncate(s->base, len, false, PREALLOC_MODE_OFF, 0, NULL); + ret = blk_co_truncate(s->base, len, false, PREALLOC_MODE_OFF, 0, NULL); if (ret) { return ret; } -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-16-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 2 +- block/io.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ create_file_fallback_zero_first_sector(BlockBackend *blk, bytes_to_clear = MIN(current_size, BDRV_SECTOR_SIZE); if (bytes_to_clear) { - ret = blk_pwrite_zeroes(blk, 0, bytes_to_clear, BDRV_REQ_MAY_UNMAP); + ret = blk_co_pwrite_zeroes(blk, 0, bytes_to_clear, BDRV_REQ_MAY_UNMAP); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to clear the new image's first sector"); diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset, return 1; } - ret = bdrv_common_block_status_above(bs, NULL, false, false, offset, - bytes, &pnum, NULL, NULL, NULL); + ret = bdrv_co_common_block_status_above(bs, NULL, false, false, offset, + bytes, &pnum, NULL, NULL, NULL); if (ret < 0) { return ret; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-17-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/mirror.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_run(Job *job, Error **errp) * active layer. */ if (s->base == blk_bs(s->target)) { if (s->bdev_length > target_length) { - ret = blk_truncate(s->target, s->bdev_length, false, - PREALLOC_MODE_OFF, 0, NULL); + ret = blk_co_truncate(s->target, s->bdev_length, false, + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { goto immediate_exit; } -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-18-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/parallels.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int64_t allocate_clusters(BlockDriverState *bs, * force the safer-but-slower fallocate. */ if (s->prealloc_mode == PRL_PREALLOC_MODE_TRUNCATE) { - ret = bdrv_truncate(bs->file, - (s->data_end + space) << BDRV_SECTOR_BITS, - false, PREALLOC_MODE_OFF, BDRV_REQ_ZERO_WRITE, - NULL); + ret = bdrv_co_truncate(bs->file, + (s->data_end + space) << BDRV_SECTOR_BITS, + false, PREALLOC_MODE_OFF, + BDRV_REQ_ZERO_WRITE, NULL); if (ret == -ENOTSUP) { s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE; } } if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE) { - ret = bdrv_pwrite_zeroes(bs->file, - s->data_end << BDRV_SECTOR_BITS, - space << BDRV_SECTOR_BITS, 0); + ret = bdrv_co_pwrite_zeroes(bs->file, + s->data_end << BDRV_SECTOR_BITS, + space << BDRV_SECTOR_BITS, 0); } if (ret < 0) { return ret; @@ -XXX,XX +XXX,XX @@ 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, off, to_write, (uint8_t *)s->header + off, - 0); + ret = bdrv_co_pwrite(bs->file, off, to_write, + (uint8_t *)s->header + off, 0); if (ret < 0) { qemu_co_mutex_unlock(&s->lock); return ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, * In order to really repair the image, we must shrink it. * That means we have to pass exact=true. */ - ret = bdrv_truncate(bs->file, res->image_end_offset, true, - PREALLOC_MODE_OFF, 0, &local_err); + ret = bdrv_co_truncate(bs->file, res->image_end_offset, true, + PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); res->check_errors++; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_create(BlockdevCreateOptions* opts, memset(tmp, 0, sizeof(tmp)); memcpy(tmp, &header, sizeof(header)); - ret = blk_pwrite(blk, 0, BDRV_SECTOR_SIZE, tmp, 0); + ret = blk_co_pwrite(blk, 0, BDRV_SECTOR_SIZE, tmp, 0); if (ret < 0) { goto exit; } - ret = blk_pwrite_zeroes(blk, BDRV_SECTOR_SIZE, - (bat_sectors - 1) << BDRV_SECTOR_BITS, 0); + ret = blk_co_pwrite_zeroes(blk, BDRV_SECTOR_SIZE, + (bat_sectors - 1) << BDRV_SECTOR_BITS, 0); if (ret < 0) { goto exit; } -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-19-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow.c | 45 +++++++++++++++++++++++---------------------- 1 file changed, 23 insertions(+), 22 deletions(-) diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_cluster_offset(BlockDriverState *bs, s->l1_table[l1_index] = l2_offset; tmp = cpu_to_be64(l2_offset); BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE); - ret = bdrv_pwrite_sync(bs->file, - s->l1_table_offset + l1_index * sizeof(tmp), - sizeof(tmp), &tmp, 0); + ret = bdrv_co_pwrite_sync(bs->file, + s->l1_table_offset + l1_index * sizeof(tmp), + sizeof(tmp), &tmp, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_cluster_offset(BlockDriverState *bs, BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD); if (new_l2_table) { memset(l2_table, 0, s->l2_size * sizeof(uint64_t)); - ret = bdrv_pwrite_sync(bs->file, l2_offset, - s->l2_size * sizeof(uint64_t), l2_table, 0); + ret = bdrv_co_pwrite_sync(bs->file, l2_offset, + s->l2_size * sizeof(uint64_t), l2_table, 0); if (ret < 0) { return ret; } } else { - ret = bdrv_pread(bs->file, l2_offset, s->l2_size * sizeof(uint64_t), - l2_table, 0); + ret = bdrv_co_pread(bs->file, l2_offset, + s->l2_size * sizeof(uint64_t), l2_table, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_cluster_offset(BlockDriverState *bs, cluster_offset = QEMU_ALIGN_UP(cluster_offset, s->cluster_size); /* write the cluster content */ BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); - ret = bdrv_pwrite(bs->file, cluster_offset, s->cluster_size, - s->cluster_cache, 0); + ret = bdrv_co_pwrite(bs->file, cluster_offset, s->cluster_size, + s->cluster_cache, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_cluster_offset(BlockDriverState *bs, if (cluster_offset + s->cluster_size > INT64_MAX) { return -E2BIG; } - ret = bdrv_truncate(bs->file, cluster_offset + s->cluster_size, - false, PREALLOC_MODE_OFF, 0, NULL); + ret = bdrv_co_truncate(bs->file, + cluster_offset + s->cluster_size, + false, PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_cluster_offset(BlockDriverState *bs, return -EIO; } BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO); - ret = bdrv_pwrite(bs->file, cluster_offset + i, - BDRV_SECTOR_SIZE, - s->cluster_data, 0); + ret = bdrv_co_pwrite(bs->file, cluster_offset + i, + BDRV_SECTOR_SIZE, + s->cluster_data, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_cluster_offset(BlockDriverState *bs, } else { BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE); } - ret = bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp), - sizeof(tmp), &tmp, 0); + ret = bdrv_co_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp), + sizeof(tmp), &tmp, 0); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn decompress_cluster(BlockDriverState *bs, csize = cluster_offset >> (63 - s->cluster_bits); csize &= (s->cluster_size - 1); BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED); - ret = bdrv_pread(bs->file, coffset, csize, s->cluster_data, 0); + ret = bdrv_co_pread(bs->file, coffset, csize, s->cluster_data, 0); if (ret < 0) return -1; if (decompress_buffer(s->cluster_cache, s->cluster_size, @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts, } /* write all the data */ - ret = blk_pwrite(qcow_blk, 0, sizeof(header), &header, 0); + ret = blk_co_pwrite(qcow_blk, 0, sizeof(header), &header, 0); if (ret < 0) { goto exit; } if (qcow_opts->has_backing_file) { - ret = blk_pwrite(qcow_blk, sizeof(header), backing_filename_len, - qcow_opts->backing_file, 0); + ret = blk_co_pwrite(qcow_blk, sizeof(header), backing_filename_len, + qcow_opts->backing_file, 0); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts, tmp = g_malloc0(BDRV_SECTOR_SIZE); for (i = 0; i < DIV_ROUND_UP(sizeof(uint64_t) * l1_size, BDRV_SECTOR_SIZE); i++) { - ret = blk_pwrite(qcow_blk, header_size + BDRV_SECTOR_SIZE * i, - BDRV_SECTOR_SIZE, tmp, 0); + ret = blk_co_pwrite(qcow_blk, header_size + BDRV_SECTOR_SIZE * i, + BDRV_SECTOR_SIZE, tmp, 0); if (ret < 0) { g_free(tmp); goto exit; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-20-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-cluster.c | 8 ++++---- block/qcow2-refcount.c | 10 +++++----- block/qcow2-snapshot.c | 6 +++--- block/qcow2.c | 24 ++++++++++++------------ 4 files changed, 24 insertions(+), 24 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_shrink_l1_table(BlockDriverState *bs, #endif BLKDBG_EVENT(bs->file, BLKDBG_L1_SHRINK_WRITE_TABLE); - ret = bdrv_pwrite_zeroes(bs->file, s->l1_table_offset + - new_l1_size * L1E_SIZE, - (s->l1_size - new_l1_size) * L1E_SIZE, 0); + ret = bdrv_co_pwrite_zeroes(bs->file, + s->l1_table_offset + new_l1_size * L1E_SIZE, + (s->l1_size - new_l1_size) * L1E_SIZE, 0); if (ret < 0) { goto fail; } - ret = bdrv_flush(bs->file->bs); + ret = bdrv_co_flush(bs->file->bs); if (ret < 0) { goto fail; } diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_refcount_init(BlockDriverState *bs) goto fail; } BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD); - ret = bdrv_pread(bs->file, s->refcount_table_offset, - refcount_table_size2, s->refcount_table, 0); + ret = bdrv_co_pread(bs->file, s->refcount_table_offset, + refcount_table_size2, s->refcount_table, 0); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_shrink_reftable(BlockDriverState *bs) reftable_tmp[i] = unused_block ? 0 : cpu_to_be64(s->refcount_table[i]); } - ret = bdrv_pwrite_sync(bs->file, s->refcount_table_offset, - s->refcount_table_size * REFTABLE_ENTRY_SIZE, - reftable_tmp, 0); + ret = bdrv_co_pwrite_sync(bs->file, s->refcount_table_offset, + s->refcount_table_size * REFTABLE_ENTRY_SIZE, + reftable_tmp, 0); /* * If the write in the reftable failed the image may contain a partially * overwritten reftable. In this case it would be better to clear the diff --git a/block/qcow2-snapshot.c b/block/qcow2-snapshot.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-snapshot.c +++ b/block/qcow2-snapshot.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_check_read_snapshot_table(BlockDriverState *bs, } QEMU_PACKED snapshot_table_pointer; /* qcow2_do_open() discards this information in check mode */ - ret = bdrv_pread(bs->file, offsetof(QCowHeader, nb_snapshots), - sizeof(snapshot_table_pointer), &snapshot_table_pointer, - 0); + ret = bdrv_co_pread(bs->file, offsetof(QCowHeader, nb_snapshots), + sizeof(snapshot_table_pointer), &snapshot_table_pointer, + 0); if (ret < 0) { result->check_errors++; fprintf(stderr, "ERROR failed to read the snapshot table pointer from " diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, uint64_t l1_vm_state_index; bool update_header = false; - ret = bdrv_pread(bs->file, 0, sizeof(header), &header, 0); + ret = bdrv_co_pread(bs->file, 0, sizeof(header), &header, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read qcow2 header"); goto fail; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, 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, sizeof(header), - s->unknown_header_fields_size, - s->unknown_header_fields, 0); + ret = bdrv_co_pread(bs->file, sizeof(header), + s->unknown_header_fields_size, + s->unknown_header_fields, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read unknown qcow2 header " "fields"); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, ret = -ENOMEM; goto fail; } - ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_size * L1E_SIZE, - s->l1_table, 0); + ret = bdrv_co_pread(bs->file, s->l1_table_offset, s->l1_size * L1E_SIZE, + s->l1_table, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read L1 table"); goto fail; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, } s->image_backing_file = g_malloc(len + 1); - ret = bdrv_pread(bs->file, header.backing_file_offset, len, - s->image_backing_file, 0); + ret = bdrv_co_pread(bs->file, header.backing_file_offset, len, + s->image_backing_file, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not read backing file name"); goto fail; @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) cpu_to_be64(QCOW2_INCOMPAT_EXTL2); } - ret = blk_pwrite(blk, 0, cluster_size, header, 0); + ret = blk_co_pwrite(blk, 0, cluster_size, header, 0); g_free(header); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write qcow2 header"); @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) /* Write a refcount table with one refcount block */ refcount_table = g_malloc0(2 * cluster_size); refcount_table[0] = cpu_to_be64(2 * cluster_size); - ret = blk_pwrite(blk, cluster_size, 2 * cluster_size, refcount_table, 0); + ret = blk_co_pwrite(blk, cluster_size, 2 * cluster_size, refcount_table, 0); g_free(refcount_table); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) } /* Okay, now that we have a valid image, let's give it the right size */ - ret = blk_truncate(blk, qcow2_opts->size, false, qcow2_opts->preallocation, - 0, errp); + ret = blk_co_truncate(blk, qcow2_opts->size, false, + qcow2_opts->preallocation, 0, errp); if (ret < 0) { error_prepend(errp, "Could not resize image: "); goto out; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-21-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qed-table.c | 2 +- block/qed.c | 12 ++++++------ 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/block/qed-table.c b/block/qed-table.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed-table.c +++ b/block/qed-table.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qed_write_table(BDRVQEDState *s, uint64_t offset, } if (flush) { - ret = bdrv_flush(s->bs); + ret = bdrv_co_flush(s->bs); if (ret < 0) { goto out; } diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int64_t file_size; int ret; - ret = bdrv_pread(bs->file, 0, sizeof(le_header), &le_header, 0); + ret = bdrv_co_pread(bs->file, 0, sizeof(le_header), &le_header, 0); if (ret < 0) { error_setg(errp, "Failed to read QED header"); return ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_do_open(BlockDriverState *bs, QDict *options, } /* From here on only known autoclear feature bits are valid */ - bdrv_flush(bs->file->bs); + bdrv_co_flush(bs->file->bs); } s->l1_table = qed_alloc_table(s); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts, * The QED format associates file length with allocation status, * so a new file (which is empty) must have a length of 0. */ - ret = blk_truncate(blk, 0, true, PREALLOC_MODE_OFF, 0, errp); + ret = blk_co_truncate(blk, 0, true, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts, } qed_header_cpu_to_le(&header, &le_header); - ret = blk_pwrite(blk, 0, sizeof(le_header), &le_header, 0); + ret = blk_co_pwrite(blk, 0, sizeof(le_header), &le_header, 0); if (ret < 0) { goto out; } - ret = blk_pwrite(blk, sizeof(le_header), header.backing_filename_size, + ret = blk_co_pwrite(blk, sizeof(le_header), header.backing_filename_size, qed_opts->backing_file, 0); if (ret < 0) { goto out; } l1_table = g_malloc0(l1_size); - ret = blk_pwrite(blk, header.l1_table_offset, l1_size, l1_table, 0); + ret = blk_co_pwrite(blk, header.l1_table_offset, l1_size, l1_table, 0); if (ret < 0) { goto out; } -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-22-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vdi.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ vdi_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes, * so this full-cluster write does not overlap a partial write * of the same cluster, issued from the "else" branch. */ - ret = bdrv_pwrite(bs->file, data_offset, s->block_size, block, 0); + ret = bdrv_co_pwrite(bs->file, data_offset, s->block_size, block, + 0); qemu_co_rwlock_unlock(&s->bmap_lock); } else { nonallocating_write: @@ -XXX,XX +XXX,XX @@ nonallocating_write: assert(VDI_IS_ALLOCATED(bmap_first)); *header = s->header; vdi_header_to_le(header); - ret = bdrv_pwrite(bs->file, 0, sizeof(*header), header, 0); + ret = bdrv_co_pwrite(bs->file, 0, sizeof(*header), header, 0); g_free(header); if (ret < 0) { @@ -XXX,XX +XXX,XX @@ nonallocating_write: 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_pwrite(bs->file, offset * SECTOR_SIZE, - n_sectors * SECTOR_SIZE, base, 0); + ret = bdrv_co_pwrite(bs->file, offset * SECTOR_SIZE, + n_sectors * SECTOR_SIZE, base, 0); } return ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, vdi_header_print(&header); } vdi_header_to_le(&header); - ret = blk_pwrite(blk, offset, sizeof(header), &header, 0); + ret = blk_co_pwrite(blk, offset, sizeof(header), &header, 0); if (ret < 0) { error_setg(errp, "Error writing header"); goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, bmap[i] = VDI_UNALLOCATED; } } - ret = blk_pwrite(blk, offset, bmap_size, bmap, 0); + ret = blk_co_pwrite(blk, offset, bmap_size, bmap, 0); if (ret < 0) { error_setg(errp, "Error writing bmap"); goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, } if (image_type == VDI_TYPE_STATIC) { - ret = blk_truncate(blk, offset + blocks * block_size, false, - PREALLOC_MODE_OFF, 0, errp); + ret = blk_co_truncate(blk, offset + blocks * block_size, false, + PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { error_prepend(errp, "Failed to statically allocate file"); goto exit; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-23-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vhdx.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts, creator = g_utf8_to_utf16("QEMU v" QEMU_VERSION, -1, NULL, &creator_items, NULL); signature = cpu_to_le64(VHDX_FILE_SIGNATURE); - ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET, sizeof(signature), &signature, - 0); + ret = blk_co_pwrite(blk, VHDX_FILE_ID_OFFSET, sizeof(signature), &signature, + 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write file signature"); goto delete_and_exit; } if (creator) { - ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET + sizeof(signature), - creator_items * sizeof(gunichar2), creator, 0); + ret = blk_co_pwrite(blk, VHDX_FILE_ID_OFFSET + sizeof(signature), + creator_items * sizeof(gunichar2), creator, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Failed to write creator field"); goto delete_and_exit; -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-24-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vmdk.c | 54 ++++++++++++++++++++++++++-------------------------- 1 file changed, 27 insertions(+), 27 deletions(-) diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_whole_cluster(BlockDriverState *bs, if (copy_from_backing) { /* qcow2 emits this on bs->file instead of bs->backing */ BLKDBG_EVENT(extent->file, BLKDBG_COW_READ); - ret = bdrv_pread(bs->backing, offset, skip_start_bytes, - whole_grain, 0); + ret = bdrv_co_pread(bs->backing, offset, skip_start_bytes, + whole_grain, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } BLKDBG_EVENT(extent->file, BLKDBG_COW_WRITE); - ret = bdrv_pwrite(extent->file, cluster_offset, skip_start_bytes, - whole_grain, 0); + ret = bdrv_co_pwrite(extent->file, cluster_offset, skip_start_bytes, + whole_grain, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_whole_cluster(BlockDriverState *bs, if (copy_from_backing) { /* qcow2 emits this on bs->file instead of bs->backing */ BLKDBG_EVENT(extent->file, BLKDBG_COW_READ); - ret = bdrv_pread(bs->backing, offset + skip_end_bytes, - cluster_bytes - skip_end_bytes, - whole_grain + skip_end_bytes, 0); + ret = bdrv_co_pread(bs->backing, offset + skip_end_bytes, + cluster_bytes - skip_end_bytes, + whole_grain + skip_end_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; } } BLKDBG_EVENT(extent->file, BLKDBG_COW_WRITE); - ret = bdrv_pwrite(extent->file, cluster_offset + skip_end_bytes, - cluster_bytes - skip_end_bytes, - whole_grain + skip_end_bytes, 0); + ret = bdrv_co_pwrite(extent->file, cluster_offset + skip_end_bytes, + cluster_bytes - skip_end_bytes, + whole_grain + skip_end_bytes, 0); if (ret < 0) { ret = VMDK_ERROR; goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data, offset = cpu_to_le32(offset); /* update L2 table */ BLKDBG_EVENT(extent->file, BLKDBG_L2_UPDATE); - if (bdrv_pwrite(extent->file, - ((int64_t)m_data->l2_offset * 512) - + (m_data->l2_index * sizeof(offset)), - sizeof(offset), &offset, 0) < 0) { + if (bdrv_co_pwrite(extent->file, + ((int64_t)m_data->l2_offset * 512) + + (m_data->l2_index * sizeof(offset)), + sizeof(offset), &offset, 0) < 0) { return VMDK_ERROR; } /* 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(extent->file, - ((int64_t)m_data->l2_offset * 512) - + (m_data->l2_index * sizeof(offset)), - sizeof(offset), &offset, 0) < 0) { + if (bdrv_co_pwrite(extent->file, + ((int64_t)m_data->l2_offset * 512) + + (m_data->l2_index * sizeof(offset)), + sizeof(offset), &offset, 0) < 0) { return VMDK_ERROR; } } - if (bdrv_flush(extent->file->bs) < 0) { + if (bdrv_co_flush(extent->file->bs) < 0) { return VMDK_ERROR; } if (m_data->l2_cache_entry) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn get_cluster_offset(BlockDriverState *bs, } l2_table = (char *)extent->l2_cache + (min_index * l2_size_bytes); BLKDBG_EVENT(extent->file, BLKDBG_L2_LOAD); - if (bdrv_pread(extent->file, + if (bdrv_co_pread(extent->file, (int64_t)l2_offset * 512, l2_size_bytes, - l2_table, - 0 + l2_table, 0 ) < 0) { return VMDK_ERROR; } @@ -XXX,XX +XXX,XX @@ vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, cluster_buf = g_malloc(buf_bytes); uncomp_buf = g_malloc(cluster_bytes); BLKDBG_EVENT(extent->file, BLKDBG_READ_COMPRESSED); - ret = bdrv_pread(extent->file, cluster_offset, buf_bytes, cluster_buf, 0); + ret = bdrv_co_pread(extent->file, cluster_offset, buf_bytes, cluster_buf, + 0); if (ret < 0) { goto out; } @@ -XXX,XX +XXX,XX @@ vmdk_co_pwritev_compressed(BlockDriverState *bs, int64_t offset, int64_t bytes, return length; } length = QEMU_ALIGN_UP(length, BDRV_SECTOR_SIZE); - ret = bdrv_truncate(s->extents[i].file, length, false, - PREALLOC_MODE_OFF, 0, NULL); + ret = bdrv_co_truncate(s->extents[i].file, length, false, + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vmdk_co_do_create(int64_t size, desc_offset = 0x200; } - ret = blk_pwrite(blk, desc_offset, desc_len, desc, 0); + ret = blk_co_pwrite(blk, desc_offset, desc_len, desc, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not write description"); goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vmdk_co_do_create(int64_t size, /* bdrv_pwrite write padding zeros to align to sector, we don't need that * for description file */ if (desc_offset == 0) { - ret = blk_truncate(blk, desc_len, false, PREALLOC_MODE_OFF, 0, errp); + ret = blk_co_truncate(blk, desc_len, false, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto exit; } -- 2.37.3 From: Alberto Faria <afaria@redhat.com> Signed-off-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20221013123711.620631-25-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void coroutine_fn qmp_block_resize(bool has_device, const char *device, bdrv_co_unlock(bs); old_ctx = bdrv_co_enter(bs); - blk_truncate(blk, size, false, PREALLOC_MODE_OFF, 0, errp); + blk_co_truncate(blk, size, false, PREALLOC_MODE_OFF, 0, errp); bdrv_co_leave(bs, old_ctx); bdrv_co_lock(bs); -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> blk_set_enable_write_cache() is defined as GLOBAL_STATE_CODE but can be invoked from iothreads when handling scsi requests. This triggers an assertion failure: 0x00007fd6c3515ce1 in raise () from /lib/x86_64-linux-gnu/libc.so.6 0x00007fd6c34ff537 in abort () from /lib/x86_64-linux-gnu/libc.so.6 0x00007fd6c34ff40f in ?? () from /lib/x86_64-linux-gnu/libc.so.6 0x00007fd6c350e662 in __assert_fail () from /lib/x86_64-linux-gnu/libc.so.6 0x000056149e2cea03 in blk_set_enable_write_cache (wce=true, blk=0x5614a01c27f0) at ../src/block/block-backend.c:1949 0x000056149e2d0a67 in blk_set_enable_write_cache (blk=0x5614a01c27f0, wce=<optimized out>) at ../src/block/block-backend.c:1951 0x000056149dfe9c59 in scsi_disk_apply_mode_select (p=0x7fd6b400c00e "\004", page=<optimized out>, s=<optimized out>) at ../src/hw/scsi/scsi-disk.c:1520 mode_select_pages (change=true, len=18, p=0x7fd6b400c00e "\004", r=0x7fd6b4001ff0) at ../src/hw/scsi/scsi-disk.c:1570 scsi_disk_emulate_mode_select (inbuf=<optimized out>, r=0x7fd6b4001ff0) at ../src/hw/scsi/scsi-disk.c:1640 scsi_disk_emulate_write_data (req=0x7fd6b4001ff0) at ../src/hw/scsi/scsi-disk.c:1934 0x000056149e18ff16 in virtio_scsi_handle_cmd_req_submit (req=<optimized out>, req=<optimized out>, s=0x5614a12f16b0) at ../src/hw/scsi/virtio-scsi.c:719 virtio_scsi_handle_cmd_vq (vq=0x7fd6bab92140, s=0x5614a12f16b0) at ../src/hw/scsi/virtio-scsi.c:761 virtio_scsi_handle_cmd (vq=<optimized out>, vdev=<optimized out>) at ../src/hw/scsi/virtio-scsi.c:775 virtio_scsi_handle_cmd (vdev=0x5614a12f16b0, vq=0x7fd6bab92140) at ../src/hw/scsi/virtio-scsi.c:765 0x000056149e1a8aa6 in virtio_queue_notify_vq (vq=0x7fd6bab92140) at ../src/hw/virtio/virtio.c:2365 0x000056149e3ccea5 in aio_dispatch_handler (ctx=ctx@entry=0x5614a01babe0, node=<optimized out>) at ../src/util/aio-posix.c:369 0x000056149e3cd868 in aio_dispatch_ready_handlers (ready_list=0x7fd6c09b2680, ctx=0x5614a01babe0) at ../src/util/aio-posix.c:399 aio_poll (ctx=0x5614a01babe0, blocking=blocking@entry=true) at ../src/util/aio-posix.c:713 0x000056149e2a7796 in iothread_run (opaque=opaque@entry=0x56149ffde500) at ../src/iothread.c:67 0x000056149e3d0859 in qemu_thread_start (args=0x7fd6c09b26f0) at ../src/util/qemu-thread-posix.c:504 0x00007fd6c36b9ea7 in start_thread () from /lib/x86_64-linux-gnu/libpthread.so.0 0x00007fd6c35d9aef in clone () from /lib/x86_64-linux-gnu/libc.so.6 Changing GLOBAL_STATE_CODE in IO_CODE is allowed, since GSC callers are allowed to call IO_CODE. Resolves: #1272 Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-Id: <20221027072726.2681500-1-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Hanna Reitz <hreitz@redhat.com> Tested-by: Antoine Damhet <antoine.damhet@shadow.tech> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/block-backend.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ bool blk_enable_write_cache(BlockBackend *blk) void blk_set_enable_write_cache(BlockBackend *blk, bool wce) { - GLOBAL_STATE_CODE(); + IO_CODE(); blk->enable_write_cache = wce; } -- 2.37.3