The following changes since commit a26a98dfb9d448d7234d931ae3720feddf6f0651: Merge remote-tracking branch 'remotes/cohuck/tags/s390x-20171006' into staging (2017-10-06 13:19:03 +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 fc3fd63fc0573ffd2ee569591a2e7f6c7310fd18: Merge remote-tracking branch 'mreitz/tags/pull-block-2017-10-06' into queue-block (2017-10-06 16:32:08 +0200) ---------------------------------------------------------------- Block layer patches ---------------------------------------------------------------- Daniel P. Berrange (6): block: use 1 MB bounce buffers for crypto instead of 16KB crypto: expose encryption sector size in APIs block: fix data type casting for crypto payload offset block: convert crypto driver to bdrv_co_preadv|pwritev block: convert qcrypto_block_encrypt|decrypt to take bytes offset block: support passthrough of BDRV_REQ_FUA in crypto driver Eric Blake (27): block: Typo fix in copy_on_readv() block: Make bdrv_img_create() size selection easier to read hbitmap: Rename serialization_granularity to serialization_align qcow2: Ensure bitmap serialization is aligned dirty-bitmap: Drop unused functions dirty-bitmap: Avoid size query failure during truncate dirty-bitmap: Change bdrv_dirty_bitmap_size() to report bytes dirty-bitmap: Track bitmap size by bytes dirty-bitmap: Change bdrv_dirty_bitmap_*serialize*() to take bytes qcow2: Switch sectors_covered_by_bitmap_cluster() to byte-based dirty-bitmap: Set iterator start by offset, not sector dirty-bitmap: Change bdrv_dirty_iter_next() to report byte offset dirty-bitmap: Change bdrv_get_dirty_count() to report bytes dirty-bitmap: Change bdrv_get_dirty_locked() to take bytes dirty-bitmap: Change bdrv_[re]set_dirty_bitmap() to use bytes mirror: Switch mirror_dirty_init() to byte-based iteration qcow2: Switch qcow2_measure() to byte-based iteration qcow2: Switch load_bitmap_data() to byte-based iteration qcow2: Switch store_bitmap_data() to byte-based iteration dirty-bitmap: Switch bdrv_set_dirty() to bytes dirty-bitmap: Convert internal hbitmap size/granularity qemu-io: Add -C for opening with copy-on-read block: Uniform handling of 0-length bdrv_get_block_status() iotests: Restore stty settings on completion block: Add blkdebug hook for copy-on-read block: Perform copy-on-read in loop iotests: Add test 197 for covering copy-on-read Kevin Wolf (6): block: Introduce BdrvChildRole.update_filename commit: Support multiple roots above top node qemu-iotests: Allow QMP pretty printing in common.qemu qemu-iotests: Test commit block job where top has two parents commit: Remove overlay_bs Merge remote-tracking branch 'mreitz/tags/pull-block-2017-10-06' into queue-block Max Reitz (1): iotests: Fix 195 if IMGFMT is part of TEST_DIR Paolo Bonzini (10): qemu-iotests: remove dead code qemu-iotests: get rid of AWK_PROG qemu-iotests: move "check" code out of common.rc qemu-iotests: cleanup and fix search for programs qemu-iotests: limit non-_PROG-suffixed variables to common.rc qemu-iotests: do not include common.rc in "check" qemu-iotests: disintegrate more parts of common.config qemu-iotests: fix uninitialized variable qemu-iotests: get rid of $iam qemu-iotests: merge "check" and "common" Pavel Butsykin (2): qcow2: fix return error code in qcow2_truncate() qcow2: truncate the tail of the image file after shrinking the image Thomas Huth (1): hw/block/onenand: Remove dead code block Vladimir Sementsov-Ogievskiy (2): block/mirror: check backing in bdrv_mirror_top_refresh_filename block/mirror: check backing in bdrv_mirror_top_flush qapi/block-core.json | 5 +- block/qcow2.h | 1 + crypto/blockpriv.h | 5 +- include/block/block.h | 3 +- include/block/block_int.h | 8 +- include/block/dirty-bitmap.h | 43 +- include/crypto/block.h | 29 +- include/qemu/hbitmap.h | 8 +- block.c | 109 ++++-- block/backup.c | 7 +- block/commit.c | 64 +-- block/crypto.c | 130 +++--- block/dirty-bitmap.c | 134 ++----- block/io.c | 131 +++++-- block/mirror.c | 88 ++--- block/qcow.c | 11 +- block/qcow2-bitmap.c | 62 +-- block/qcow2-cluster.c | 8 +- block/qcow2-refcount.c | 22 ++ block/qcow2.c | 53 ++- crypto/block-luks.c | 18 +- crypto/block-qcow.c | 13 +- crypto/block.c | 26 +- hw/block/onenand.c | 4 - migration/block.c | 12 +- qemu-io.c | 15 +- tests/test-hbitmap.c | 10 +- util/hbitmap.c | 8 +- tests/qemu-iotests/030 | 4 - tests/qemu-iotests/039.out | 10 +- tests/qemu-iotests/061.out | 4 +- tests/qemu-iotests/137.out | 2 +- tests/qemu-iotests/165 | 2 +- tests/qemu-iotests/191 | 153 ++++++++ tests/qemu-iotests/191.out | 827 +++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/195 | 7 +- tests/qemu-iotests/197 | 109 ++++++ tests/qemu-iotests/197.out | 26 ++ tests/qemu-iotests/check | 585 ++++++++++++++++++++++++--- tests/qemu-iotests/common | 459 ---------------------- tests/qemu-iotests/common.config | 206 +--------- tests/qemu-iotests/common.filter | 1 + tests/qemu-iotests/common.qemu | 15 +- tests/qemu-iotests/common.rc | 205 +++++----- tests/qemu-iotests/group | 2 + 45 files changed, 2333 insertions(+), 1311 deletions(-) create mode 100755 tests/qemu-iotests/191 create mode 100644 tests/qemu-iotests/191.out create mode 100755 tests/qemu-iotests/197 create mode 100644 tests/qemu-iotests/197.out delete mode 100644 tests/qemu-iotests/common From: Eric Blake <eblake@redhat.com> Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_do_copy_on_readv(BdrvChild *child, /* FIXME We cannot require callers to have write permissions when all they * are doing is a read request. If we did things right, write permissions * would be obtained anyway, but internally by the copy-on-read code. As - * long as it is implemented here rather than in a separat filter driver, + * long as it is implemented here rather than in a separate filter driver, * the copy-on-read code doesn't have its own BdrvChild, however, for which * it could request permissions. Therefore we have to bypass the permission * system for the moment. */ -- 2.13.6 From: Eric Blake <eblake@redhat.com> All callers of bdrv_img_create() pass in a size, or -1 to read the size from the backing file. We then set that size as the QemuOpt default, which means we will reuse that default rather than the final parameter to qemu_opt_get_size() several lines later. But it is rather confusing to read subsequent checks of 'size == -1' when it looks (without seeing the full context) like size defaults to 0; it also doesn't help that a size of 0 is valid (for some formats). Rework the logic to make things more legible. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_img_create(const char *filename, const char *fmt, /* The size for the image must always be specified, unless we have a backing * file and we have not been forbidden from opening it. */ - size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 0); + size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, img_size); if (backing_file && !(flags & BDRV_O_NO_BACKING)) { BlockDriverState *bs; char *full_backing = g_new0(char, PATH_MAX); -- 2.13.6 From: Eric Blake <eblake@redhat.com> The only client of hbitmap_serialization_granularity() is dirty-bitmap's bdrv_dirty_bitmap_serialization_align(). Keeping the two names consistent is worthwhile, and the shorter name is more representative of what the function returns (the required alignment to be used for start/count of other serialization functions, where violating the alignment causes assertion failures). Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/hbitmap.h | 8 ++++---- block/dirty-bitmap.c | 2 +- tests/test-hbitmap.c | 10 +++++----- util/hbitmap.c | 8 ++++---- 4 files changed, 14 insertions(+), 14 deletions(-) diff --git a/include/qemu/hbitmap.h b/include/qemu/hbitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/hbitmap.h +++ b/include/qemu/hbitmap.h @@ -XXX,XX +XXX,XX @@ bool hbitmap_get(const HBitmap *hb, uint64_t item); bool hbitmap_is_serializable(const HBitmap *hb); /** - * hbitmap_serialization_granularity: + * hbitmap_serialization_align: * @hb: HBitmap to operate on. * - * Granularity of serialization chunks, used by other serialization functions. - * For every chunk: + * Required alignment of serialization chunks, used by other serialization + * functions. For every chunk: * 1. Chunk start should be aligned to this granularity. * 2. Chunk size should be aligned too, except for last chunk (for which * start + count == hb->size) */ -uint64_t hbitmap_serialization_granularity(const HBitmap *hb); +uint64_t hbitmap_serialization_align(const HBitmap *hb); /** * hbitmap_serialization_size: diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ uint64_t bdrv_dirty_bitmap_serialization_size(const BdrvDirtyBitmap *bitmap, uint64_t bdrv_dirty_bitmap_serialization_align(const BdrvDirtyBitmap *bitmap) { - return hbitmap_serialization_granularity(bitmap->bitmap); + return hbitmap_serialization_align(bitmap->bitmap); } void bdrv_dirty_bitmap_serialize_part(const BdrvDirtyBitmap *bitmap, diff --git a/tests/test-hbitmap.c b/tests/test-hbitmap.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-hbitmap.c +++ b/tests/test-hbitmap.c @@ -XXX,XX +XXX,XX @@ static void test_hbitmap_meta_one(TestHBitmapData *data, const void *unused) } } -static void test_hbitmap_serialize_granularity(TestHBitmapData *data, - const void *unused) +static void test_hbitmap_serialize_align(TestHBitmapData *data, + const void *unused) { int r; hbitmap_test_init(data, L3 * 2, 3); g_assert(hbitmap_is_serializable(data->hb)); - r = hbitmap_serialization_granularity(data->hb); + r = hbitmap_serialization_align(data->hb); g_assert_cmpint(r, ==, 64 << 3); } @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) hbitmap_test_add("/hbitmap/meta/word", test_hbitmap_meta_word); hbitmap_test_add("/hbitmap/meta/sector", test_hbitmap_meta_sector); - hbitmap_test_add("/hbitmap/serialize/granularity", - test_hbitmap_serialize_granularity); + hbitmap_test_add("/hbitmap/serialize/align", + test_hbitmap_serialize_align); hbitmap_test_add("/hbitmap/serialize/basic", test_hbitmap_serialize_basic); hbitmap_test_add("/hbitmap/serialize/part", diff --git a/util/hbitmap.c b/util/hbitmap.c index XXXXXXX..XXXXXXX 100644 --- a/util/hbitmap.c +++ b/util/hbitmap.c @@ -XXX,XX +XXX,XX @@ bool hbitmap_is_serializable(const HBitmap *hb) { /* Every serialized chunk must be aligned to 64 bits so that endianness * requirements can be fulfilled on both 64 bit and 32 bit hosts. - * We have hbitmap_serialization_granularity() which converts this + * We have hbitmap_serialization_align() which converts this * alignment requirement from bitmap bits to items covered (e.g. sectors). * That value is: * 64 << hb->granularity * Since this value must not exceed UINT64_MAX, hb->granularity must be * less than 58 (== 64 - 6, where 6 is ld(64), i.e. 1 << 6 == 64). * - * In order for hbitmap_serialization_granularity() to always return a + * In order for hbitmap_serialization_align() to always return a * meaningful value, bitmaps that are to be serialized must have a * granularity of less than 58. */ @@ -XXX,XX +XXX,XX @@ bool hbitmap_get(const HBitmap *hb, uint64_t item) return (hb->levels[HBITMAP_LEVELS - 1][pos >> BITS_PER_LEVEL] & bit) != 0; } -uint64_t hbitmap_serialization_granularity(const HBitmap *hb) +uint64_t hbitmap_serialization_align(const HBitmap *hb) { assert(hbitmap_is_serializable(hb)); @@ -XXX,XX +XXX,XX @@ static void serialization_chunk(const HBitmap *hb, unsigned long **first_el, uint64_t *el_count) { uint64_t last = start + count - 1; - uint64_t gran = hbitmap_serialization_granularity(hb); + uint64_t gran = hbitmap_serialization_align(hb); assert((start & (gran - 1)) == 0); assert((last >> hb->granularity) < hb->size); -- 2.13.6 From: Eric Blake <eblake@redhat.com> When subdividing a bitmap serialization, the code in hbitmap.c enforces that start/count parameters are aligned (except that count can end early at end-of-bitmap). We exposed this required alignment through bdrv_dirty_bitmap_serialization_align(), but forgot to actually check that we comply with it. Fortunately, qcow2 is never dividing bitmap serialization smaller than one cluster (which is a minimum of 512 bytes); so we are always compliant with the serialization alignment (which insists that we partition at least 64 bits per chunk) because we are doing at least 4k bits per chunk. Still, it's safer to add an assertion (for the unlikely case that we'd ever support a cluster smaller than 512 bytes, or if the hbitmap implementation changes what it considers to be aligned), rather than leaving bdrv_dirty_bitmap_serialization_align() without a caller. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-bitmap.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) 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 int free_bitmap_clusters(BlockDriverState *bs, Qcow2BitmapTable *tb) static uint64_t sectors_covered_by_bitmap_cluster(const BDRVQcow2State *s, const BdrvDirtyBitmap *bitmap) { - uint32_t sector_granularity = + uint64_t sector_granularity = bdrv_dirty_bitmap_granularity(bitmap) >> BDRV_SECTOR_BITS; + uint64_t sbc = sector_granularity * (s->cluster_size << 3); - return (uint64_t)sector_granularity * (s->cluster_size << 3); + assert(QEMU_IS_ALIGNED(sbc, + bdrv_dirty_bitmap_serialization_align(bitmap))); + return sbc; } /* load_bitmap_data -- 2.13.6 From: Eric Blake <eblake@redhat.com> We had several functions that no one is currently using, and which use sector-based interfaces. I'm trying to convert towards byte-based interfaces, so it's easier to just drop the unused functions: bdrv_dirty_bitmap_get_meta bdrv_dirty_bitmap_get_meta_locked bdrv_dirty_bitmap_reset_meta bdrv_dirty_bitmap_meta_granularity Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/dirty-bitmap.h | 10 ---------- block/dirty-bitmap.c | 44 -------------------------------------------- 2 files changed, 54 deletions(-) diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -XXX,XX +XXX,XX @@ void bdrv_enable_dirty_bitmap(BdrvDirtyBitmap *bitmap); BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs); uint32_t bdrv_get_default_bitmap_granularity(BlockDriverState *bs); uint32_t bdrv_dirty_bitmap_granularity(const BdrvDirtyBitmap *bitmap); -uint32_t bdrv_dirty_bitmap_meta_granularity(BdrvDirtyBitmap *bitmap); bool bdrv_dirty_bitmap_enabled(BdrvDirtyBitmap *bitmap); bool bdrv_dirty_bitmap_frozen(BdrvDirtyBitmap *bitmap); const char *bdrv_dirty_bitmap_name(const BdrvDirtyBitmap *bitmap); @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, int64_t cur_sector, int64_t nr_sectors); void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, int64_t cur_sector, int64_t nr_sectors); -int bdrv_dirty_bitmap_get_meta(BlockDriverState *bs, - BdrvDirtyBitmap *bitmap, int64_t sector, - int nb_sectors); -int bdrv_dirty_bitmap_get_meta_locked(BlockDriverState *bs, - BdrvDirtyBitmap *bitmap, int64_t sector, - int nb_sectors); -void bdrv_dirty_bitmap_reset_meta(BlockDriverState *bs, - BdrvDirtyBitmap *bitmap, int64_t sector, - int nb_sectors); BdrvDirtyBitmapIter *bdrv_dirty_meta_iter_new(BdrvDirtyBitmap *bitmap); BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap, uint64_t first_sector); diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ void bdrv_release_meta_dirty_bitmap(BdrvDirtyBitmap *bitmap) qemu_mutex_unlock(bitmap->mutex); } -int bdrv_dirty_bitmap_get_meta_locked(BlockDriverState *bs, - BdrvDirtyBitmap *bitmap, int64_t sector, - int nb_sectors) -{ - uint64_t i; - int sectors_per_bit = 1 << hbitmap_granularity(bitmap->meta); - - /* To optimize: we can make hbitmap to internally check the range in a - * coarse level, or at least do it word by word. */ - for (i = sector; i < sector + nb_sectors; i += sectors_per_bit) { - if (hbitmap_get(bitmap->meta, i)) { - return true; - } - } - return false; -} - -int bdrv_dirty_bitmap_get_meta(BlockDriverState *bs, - BdrvDirtyBitmap *bitmap, int64_t sector, - int nb_sectors) -{ - bool dirty; - - qemu_mutex_lock(bitmap->mutex); - dirty = bdrv_dirty_bitmap_get_meta_locked(bs, bitmap, sector, nb_sectors); - qemu_mutex_unlock(bitmap->mutex); - - return dirty; -} - -void bdrv_dirty_bitmap_reset_meta(BlockDriverState *bs, - BdrvDirtyBitmap *bitmap, int64_t sector, - int nb_sectors) -{ - qemu_mutex_lock(bitmap->mutex); - hbitmap_reset(bitmap->meta, sector, nb_sectors); - qemu_mutex_unlock(bitmap->mutex); -} - int64_t bdrv_dirty_bitmap_size(const BdrvDirtyBitmap *bitmap) { return bitmap->size; @@ -XXX,XX +XXX,XX @@ uint32_t bdrv_dirty_bitmap_granularity(const BdrvDirtyBitmap *bitmap) return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->bitmap); } -uint32_t bdrv_dirty_bitmap_meta_granularity(BdrvDirtyBitmap *bitmap) -{ - return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->meta); -} - BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap, uint64_t first_sector) { -- 2.13.6 From: Eric Blake <eblake@redhat.com> We've previously fixed several places where we failed to account for possible errors from bdrv_nb_sectors(). Fix another one by making bdrv_dirty_bitmap_truncate() take the new size from the caller instead of querying itself; then adjust the sole caller bdrv_truncate() to pass the size just determined by a successful resize, or to reuse the size given to the original truncate operation when refresh_total_sectors() was not able to confirm the actual size (the two sizes can potentially differ according to rounding constraints), thus avoiding sizing the bitmaps to -1. This also fixes a bug where not all failure paths in bdrv_truncate() would set errp. Note that bdrv_truncate() is still a bit awkward. We may want to revisit it later and clean up things to better guarantee that a resize attempt either fails cleanly up front, or cannot fail after guest-visible changes have been made (if temporary changes are made, then they need to be cleanly rolled back). But that is a task for another day; for now, the goal is the bare minimum fix to ensure that just bdrv_dirty_bitmap_truncate() cannot fail. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/dirty-bitmap.h | 2 +- block.c | 16 +++++++++++----- block/dirty-bitmap.c | 6 +++--- 3 files changed, 15 insertions(+), 9 deletions(-) diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -XXX,XX +XXX,XX @@ int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter); void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *hbi, int64_t sector_num); int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap); int64_t bdrv_get_meta_dirty_count(BdrvDirtyBitmap *bitmap); -void bdrv_dirty_bitmap_truncate(BlockDriverState *bs); +void bdrv_dirty_bitmap_truncate(BlockDriverState *bs, int64_t bytes); bool bdrv_dirty_bitmap_readonly(const BdrvDirtyBitmap *bitmap); bool bdrv_has_readonly_bitmaps(BlockDriverState *bs); bool bdrv_dirty_bitmap_get_autoload(const BdrvDirtyBitmap *bitmap); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ int bdrv_truncate(BdrvChild *child, int64_t offset, PreallocMode prealloc, assert(!(bs->open_flags & BDRV_O_INACTIVE)); ret = drv->bdrv_truncate(bs, offset, prealloc, errp); - if (ret == 0) { - ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS); - bdrv_dirty_bitmap_truncate(bs); - bdrv_parent_cb_resize(bs); - atomic_inc(&bs->write_gen); + if (ret < 0) { + return ret; + } + ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS); + if (ret < 0) { + error_setg_errno(errp, -ret, "Could not refresh total sector count"); + } else { + offset = bs->total_sectors * BDRV_SECTOR_SIZE; } + bdrv_dirty_bitmap_truncate(bs, offset); + bdrv_parent_cb_resize(bs); + atomic_inc(&bs->write_gen); return ret; } diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ /* * Block Dirty Bitmap * - * Copyright (c) 2016 Red Hat. Inc + * Copyright (c) 2016-2017 Red Hat. Inc * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs, * Truncates _all_ bitmaps attached to a BDS. * Called with BQL taken. */ -void bdrv_dirty_bitmap_truncate(BlockDriverState *bs) +void bdrv_dirty_bitmap_truncate(BlockDriverState *bs, int64_t bytes) { BdrvDirtyBitmap *bitmap; - uint64_t size = bdrv_nb_sectors(bs); + int64_t size = DIV_ROUND_UP(bytes, BDRV_SECTOR_SIZE); bdrv_dirty_bitmaps_lock(bs); QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) { -- 2.13.6 From: Eric Blake <eblake@redhat.com> We're already reporting bytes for bdrv_dirty_bitmap_granularity(); mixing bytes and sectors in our return values is a recipe for confusion. A later cleanup will convert dirty bitmap internals to be entirely byte-based, but in the meantime, we should report the bitmap size in bytes. The only external caller in qcow2-bitmap.c is temporarily more verbose (because it is still using sector-based math), but will later be switched to track progress by bytes instead of sectors. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/dirty-bitmap.c | 2 +- block/qcow2-bitmap.c | 14 ++++++++------ 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ void bdrv_release_meta_dirty_bitmap(BdrvDirtyBitmap *bitmap) int64_t bdrv_dirty_bitmap_size(const BdrvDirtyBitmap *bitmap) { - return bitmap->size; + return bitmap->size * BDRV_SECTOR_SIZE; } const char *bdrv_dirty_bitmap_name(const BdrvDirtyBitmap *bitmap) 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 int load_bitmap_data(BlockDriverState *bs, BDRVQcow2State *s = bs->opaque; uint64_t sector, sbc; uint64_t bm_size = bdrv_dirty_bitmap_size(bitmap); + uint64_t bm_sectors = DIV_ROUND_UP(bm_size, BDRV_SECTOR_SIZE); uint8_t *buf = NULL; uint64_t i, tab_size = size_to_clusters(s, - bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_size)); + bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_sectors)); if (tab_size != bitmap_table_size || tab_size > BME_MAX_TABLE_SIZE) { return -EINVAL; @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, buf = g_malloc(s->cluster_size); sbc = sectors_covered_by_bitmap_cluster(s, bitmap); for (i = 0, sector = 0; i < tab_size; ++i, sector += sbc) { - uint64_t count = MIN(bm_size - sector, sbc); + uint64_t count = MIN(bm_sectors - sector, sbc); uint64_t entry = bitmap_table[i]; uint64_t offset = entry & BME_TABLE_ENTRY_OFFSET_MASK; @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, int64_t sector; uint64_t sbc; uint64_t bm_size = bdrv_dirty_bitmap_size(bitmap); + uint64_t bm_sectors = DIV_ROUND_UP(bm_size, BDRV_SECTOR_SIZE); const char *bm_name = bdrv_dirty_bitmap_name(bitmap); uint8_t *buf = NULL; BdrvDirtyBitmapIter *dbi; uint64_t *tb; uint64_t tb_size = size_to_clusters(s, - bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_size)); + bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_sectors)); if (tb_size > BME_MAX_TABLE_SIZE || tb_size * s->cluster_size > BME_MAX_PHYS_SIZE) @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, dbi = bdrv_dirty_iter_new(bitmap, 0); buf = g_malloc(s->cluster_size); sbc = sectors_covered_by_bitmap_cluster(s, bitmap); - assert(DIV_ROUND_UP(bm_size, sbc) == tb_size); + assert(DIV_ROUND_UP(bm_sectors, sbc) == tb_size); while ((sector = bdrv_dirty_iter_next(dbi)) != -1) { uint64_t cluster = sector / sbc; @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, int64_t off; sector = cluster * sbc; - end = MIN(bm_size, sector + sbc); + end = MIN(bm_sectors, sector + sbc); write_size = bdrv_dirty_bitmap_serialization_size(bitmap, sector, end - sector); assert(write_size <= s->cluster_size); @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, goto fail; } - if (end >= bm_size) { + if (end >= bm_sectors) { break; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> We are still using an internal hbitmap that tracks a size in sectors, with the granularity scaled down accordingly, because it lets us use a shortcut for our iterators which are currently sector-based. But there's no reason we can't track the dirty bitmap size in bytes, since it is (mostly) an internal-only variable (remember, the size is how many bytes are covered by the bitmap, not how many bytes the bitmap occupies). A later cleanup will convert dirty bitmap internals to be entirely byte-based, eliminating the intermediate sector rounding added here; and technically, since bdrv_getlength() already rounds up to sectors, our use of DIV_ROUND_UP is more for theoretical completeness than for any actual rounding. Use is_power_of_2() while at it, instead of open-coding that. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/dirty-bitmap.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ struct BdrvDirtyBitmap { HBitmap *meta; /* Meta dirty bitmap */ BdrvDirtyBitmap *successor; /* Anonymous child; implies frozen status */ char *name; /* Optional non-empty unique ID */ - int64_t size; /* Size of the bitmap (Number of sectors) */ + int64_t size; /* Size of the bitmap, in bytes */ bool disabled; /* Bitmap is disabled. It ignores all writes to the device */ int active_iterators; /* How many iterators are active */ @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, { int64_t bitmap_size; BdrvDirtyBitmap *bitmap; - uint32_t sector_granularity; - assert((granularity & (granularity - 1)) == 0); + assert(is_power_of_2(granularity) && granularity >= BDRV_SECTOR_SIZE); if (name && bdrv_find_dirty_bitmap(bs, name)) { error_setg(errp, "Bitmap already exists: %s", name); return NULL; } - sector_granularity = granularity >> BDRV_SECTOR_BITS; - assert(sector_granularity); - bitmap_size = bdrv_nb_sectors(bs); + bitmap_size = bdrv_getlength(bs); if (bitmap_size < 0) { error_setg_errno(errp, -bitmap_size, "could not get length of device"); errno = -bitmap_size; @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, } bitmap = g_new0(BdrvDirtyBitmap, 1); bitmap->mutex = &bs->dirty_bitmap_mutex; - bitmap->bitmap = hbitmap_alloc(bitmap_size, ctz32(sector_granularity)); + /* + * TODO - let hbitmap track full granularity. For now, it is tracking + * only sector granularity, as a shortcut for our iterators. + */ + bitmap->bitmap = hbitmap_alloc(DIV_ROUND_UP(bitmap_size, BDRV_SECTOR_SIZE), + ctz32(granularity) - BDRV_SECTOR_BITS); bitmap->size = bitmap_size; bitmap->name = g_strdup(name); bitmap->disabled = false; @@ -XXX,XX +XXX,XX @@ void bdrv_release_meta_dirty_bitmap(BdrvDirtyBitmap *bitmap) int64_t bdrv_dirty_bitmap_size(const BdrvDirtyBitmap *bitmap) { - return bitmap->size * BDRV_SECTOR_SIZE; + return bitmap->size; } const char *bdrv_dirty_bitmap_name(const BdrvDirtyBitmap *bitmap) @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs, void bdrv_dirty_bitmap_truncate(BlockDriverState *bs, int64_t bytes) { BdrvDirtyBitmap *bitmap; - int64_t size = DIV_ROUND_UP(bytes, BDRV_SECTOR_SIZE); bdrv_dirty_bitmaps_lock(bs); QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) { assert(!bdrv_dirty_bitmap_frozen(bitmap)); assert(!bitmap->active_iterators); - hbitmap_truncate(bitmap->bitmap, size); - bitmap->size = size; + hbitmap_truncate(bitmap->bitmap, DIV_ROUND_UP(bytes, BDRV_SECTOR_SIZE)); + bitmap->size = bytes; } bdrv_dirty_bitmaps_unlock(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out) hbitmap_reset_all(bitmap->bitmap); } else { HBitmap *backup = bitmap->bitmap; - bitmap->bitmap = hbitmap_alloc(bitmap->size, + bitmap->bitmap = hbitmap_alloc(DIV_ROUND_UP(bitmap->size, + BDRV_SECTOR_SIZE), hbitmap_granularity(backup)); *out = backup; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Right now, the dirty-bitmap code exposes the fact that we use a scale of sector granularity in the underlying hbitmap to anything that wants to serialize a dirty bitmap. It's nicer to uniformly expose bytes as our dirty-bitmap interface, matching the previous change to bitmap size. The only caller to serialization is currently qcow2-cluster.c, which becomes a bit more verbose because it is still tracking sectors for other reasons, but a later patch will fix that to more uniformly use byte offsets everywhere. Likewise, within dirty-bitmap, we have to add more assertions that we are not truncating incorrectly, which can go away once the internal hbitmap is byte-based rather than sector-based. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/dirty-bitmap.h | 14 +++++++------- block/dirty-bitmap.c | 37 ++++++++++++++++++++++++------------- block/qcow2-bitmap.c | 22 ++++++++++++++-------- 3 files changed, 45 insertions(+), 28 deletions(-) diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap, void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter); uint64_t bdrv_dirty_bitmap_serialization_size(const BdrvDirtyBitmap *bitmap, - uint64_t start, uint64_t count); + uint64_t offset, uint64_t bytes); uint64_t bdrv_dirty_bitmap_serialization_align(const BdrvDirtyBitmap *bitmap); void bdrv_dirty_bitmap_serialize_part(const BdrvDirtyBitmap *bitmap, - uint8_t *buf, uint64_t start, - uint64_t count); + uint8_t *buf, uint64_t offset, + uint64_t bytes); void bdrv_dirty_bitmap_deserialize_part(BdrvDirtyBitmap *bitmap, - uint8_t *buf, uint64_t start, - uint64_t count, bool finish); + uint8_t *buf, uint64_t offset, + uint64_t bytes, bool finish); void bdrv_dirty_bitmap_deserialize_zeroes(BdrvDirtyBitmap *bitmap, - uint64_t start, uint64_t count, + uint64_t offset, uint64_t bytes, bool finish); void bdrv_dirty_bitmap_deserialize_ones(BdrvDirtyBitmap *bitmap, - uint64_t start, uint64_t count, + uint64_t offset, uint64_t bytes, bool finish); void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap); diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in) } uint64_t bdrv_dirty_bitmap_serialization_size(const BdrvDirtyBitmap *bitmap, - uint64_t start, uint64_t count) + uint64_t offset, uint64_t bytes) { - return hbitmap_serialization_size(bitmap->bitmap, start, count); + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + return hbitmap_serialization_size(bitmap->bitmap, + offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS); } uint64_t bdrv_dirty_bitmap_serialization_align(const BdrvDirtyBitmap *bitmap) { - return hbitmap_serialization_align(bitmap->bitmap); + return hbitmap_serialization_align(bitmap->bitmap) * BDRV_SECTOR_SIZE; } void bdrv_dirty_bitmap_serialize_part(const BdrvDirtyBitmap *bitmap, - uint8_t *buf, uint64_t start, - uint64_t count) + uint8_t *buf, uint64_t offset, + uint64_t bytes) { - hbitmap_serialize_part(bitmap->bitmap, buf, start, count); + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + hbitmap_serialize_part(bitmap->bitmap, buf, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS); } void bdrv_dirty_bitmap_deserialize_part(BdrvDirtyBitmap *bitmap, - uint8_t *buf, uint64_t start, - uint64_t count, bool finish) + uint8_t *buf, uint64_t offset, + uint64_t bytes, bool finish) { - hbitmap_deserialize_part(bitmap->bitmap, buf, start, count, finish); + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + hbitmap_deserialize_part(bitmap->bitmap, buf, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, finish); } void bdrv_dirty_bitmap_deserialize_zeroes(BdrvDirtyBitmap *bitmap, - uint64_t start, uint64_t count, + uint64_t offset, uint64_t bytes, bool finish) { - hbitmap_deserialize_zeroes(bitmap->bitmap, start, count, finish); + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + hbitmap_deserialize_zeroes(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, finish); } void bdrv_dirty_bitmap_deserialize_ones(BdrvDirtyBitmap *bitmap, - uint64_t start, uint64_t count, + uint64_t offset, uint64_t bytes, bool finish) { - hbitmap_deserialize_ones(bitmap->bitmap, start, count, finish); + assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); + hbitmap_deserialize_ones(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, + bytes >> BDRV_SECTOR_BITS, finish); } void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap) 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 uint64_t sectors_covered_by_bitmap_cluster(const BDRVQcow2State *s, bdrv_dirty_bitmap_granularity(bitmap) >> BDRV_SECTOR_BITS; uint64_t sbc = sector_granularity * (s->cluster_size << 3); - assert(QEMU_IS_ALIGNED(sbc, + assert(QEMU_IS_ALIGNED(sbc << BDRV_SECTOR_BITS, bdrv_dirty_bitmap_serialization_align(bitmap))); return sbc; } @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, uint8_t *buf = NULL; uint64_t i, tab_size = size_to_clusters(s, - bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_sectors)); + bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_size)); if (tab_size != bitmap_table_size || tab_size > BME_MAX_TABLE_SIZE) { return -EINVAL; @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, if (offset == 0) { if (entry & BME_TABLE_ENTRY_FLAG_ALL_ONES) { - bdrv_dirty_bitmap_deserialize_ones(bitmap, sector, count, + bdrv_dirty_bitmap_deserialize_ones(bitmap, + sector * BDRV_SECTOR_SIZE, + count * BDRV_SECTOR_SIZE, false); } else { /* No need to deserialize zeros because the dirty bitmap is @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, if (ret < 0) { goto finish; } - bdrv_dirty_bitmap_deserialize_part(bitmap, buf, sector, count, + bdrv_dirty_bitmap_deserialize_part(bitmap, buf, + sector * BDRV_SECTOR_SIZE, + count * BDRV_SECTOR_SIZE, false); } } @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, uint64_t *tb; uint64_t tb_size = size_to_clusters(s, - bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_sectors)); + bdrv_dirty_bitmap_serialization_size(bitmap, 0, bm_size)); if (tb_size > BME_MAX_TABLE_SIZE || tb_size * s->cluster_size > BME_MAX_PHYS_SIZE) @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, sector = cluster * sbc; end = MIN(bm_sectors, sector + sbc); - write_size = - bdrv_dirty_bitmap_serialization_size(bitmap, sector, end - sector); + write_size = bdrv_dirty_bitmap_serialization_size(bitmap, + sector * BDRV_SECTOR_SIZE, (end - sector) * BDRV_SECTOR_SIZE); assert(write_size <= s->cluster_size); off = qcow2_alloc_clusters(bs, s->cluster_size); @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, } tb[cluster] = off; - bdrv_dirty_bitmap_serialize_part(bitmap, buf, sector, end - sector); + bdrv_dirty_bitmap_serialize_part(bitmap, buf, + sector * BDRV_SECTOR_SIZE, + (end - sector) * BDRV_SECTOR_SIZE); if (write_size < s->cluster_size) { memset(buf + write_size, 0, s->cluster_size - write_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. Change the qcow2 bitmap helper function sectors_covered_by_bitmap_cluster(), renaming it to bytes_covered_by_bitmap_cluster() in the process. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-bitmap.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) 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 int free_bitmap_clusters(BlockDriverState *bs, Qcow2BitmapTable *tb) return 0; } -/* This function returns the number of disk sectors covered by a single qcow2 - * cluster of bitmap data. */ -static uint64_t sectors_covered_by_bitmap_cluster(const BDRVQcow2State *s, - const BdrvDirtyBitmap *bitmap) +/* Return the disk size covered by a single qcow2 cluster of bitmap data. */ +static uint64_t bytes_covered_by_bitmap_cluster(const BDRVQcow2State *s, + const BdrvDirtyBitmap *bitmap) { - uint64_t sector_granularity = - bdrv_dirty_bitmap_granularity(bitmap) >> BDRV_SECTOR_BITS; - uint64_t sbc = sector_granularity * (s->cluster_size << 3); + uint64_t granularity = bdrv_dirty_bitmap_granularity(bitmap); + uint64_t limit = granularity * (s->cluster_size << 3); - assert(QEMU_IS_ALIGNED(sbc << BDRV_SECTOR_BITS, + assert(QEMU_IS_ALIGNED(limit, bdrv_dirty_bitmap_serialization_align(bitmap))); - return sbc; + return limit; } /* load_bitmap_data @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, { int ret = 0; BDRVQcow2State *s = bs->opaque; - uint64_t sector, sbc; + uint64_t sector, limit, sbc; uint64_t bm_size = bdrv_dirty_bitmap_size(bitmap); uint64_t bm_sectors = DIV_ROUND_UP(bm_size, BDRV_SECTOR_SIZE); uint8_t *buf = NULL; @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, } buf = g_malloc(s->cluster_size); - sbc = sectors_covered_by_bitmap_cluster(s, bitmap); + limit = bytes_covered_by_bitmap_cluster(s, bitmap); + sbc = limit >> BDRV_SECTOR_BITS; for (i = 0, sector = 0; i < tab_size; ++i, sector += sbc) { uint64_t count = MIN(bm_sectors - sector, sbc); uint64_t entry = bitmap_table[i]; @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, int ret; BDRVQcow2State *s = bs->opaque; int64_t sector; - uint64_t sbc; + uint64_t limit, sbc; uint64_t bm_size = bdrv_dirty_bitmap_size(bitmap); uint64_t bm_sectors = DIV_ROUND_UP(bm_size, BDRV_SECTOR_SIZE); const char *bm_name = bdrv_dirty_bitmap_name(bitmap); @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, dbi = bdrv_dirty_iter_new(bitmap, 0); buf = g_malloc(s->cluster_size); - sbc = sectors_covered_by_bitmap_cluster(s, bitmap); - assert(DIV_ROUND_UP(bm_sectors, sbc) == tb_size); + limit = bytes_covered_by_bitmap_cluster(s, bitmap); + sbc = limit >> BDRV_SECTOR_BITS; + assert(DIV_ROUND_UP(bm_size, limit) == tb_size); while ((sector = bdrv_dirty_iter_next(dbi)) != -1) { uint64_t cluster = sector / sbc; -- 2.13.6 From: Eric Blake <eblake@redhat.com> All callers to bdrv_dirty_iter_new() passed 0 for their initial starting point, drop that parameter. Most callers to bdrv_set_dirty_iter() were scaling a byte offset to a sector number; the exception qcow2-bitmap will be converted later to use byte rather than sector iteration. Move the scaling to occur internally to dirty bitmap code instead, so that callers now pass in bytes. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/dirty-bitmap.h | 5 ++--- block/backup.c | 5 ++--- block/dirty-bitmap.c | 9 ++++----- block/mirror.c | 4 ++-- block/qcow2-bitmap.c | 4 ++-- 5 files changed, 12 insertions(+), 15 deletions(-) diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, int64_t cur_sector, int64_t nr_sectors); BdrvDirtyBitmapIter *bdrv_dirty_meta_iter_new(BdrvDirtyBitmap *bitmap); -BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap, - uint64_t first_sector); +BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap); void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter); uint64_t bdrv_dirty_bitmap_serialization_size(const BdrvDirtyBitmap *bitmap, @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, void bdrv_reset_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, int64_t cur_sector, int64_t nr_sectors); int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter); -void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *hbi, int64_t sector_num); +void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *hbi, int64_t offset); int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap); int64_t bdrv_get_meta_dirty_count(BdrvDirtyBitmap *bitmap); void bdrv_dirty_bitmap_truncate(BlockDriverState *bs, int64_t bytes); diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job) granularity = bdrv_dirty_bitmap_granularity(job->sync_bitmap); clusters_per_iter = MAX((granularity / job->cluster_size), 1); - dbi = bdrv_dirty_iter_new(job->sync_bitmap, 0); + dbi = bdrv_dirty_iter_new(job->sync_bitmap); /* Find the next dirty sector(s) */ while ((offset = bdrv_dirty_iter_next(dbi) * BDRV_SECTOR_SIZE) >= 0) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job) /* If the bitmap granularity is smaller than the backup granularity, * we need to advance the iterator pointer to the next cluster. */ if (granularity < job->cluster_size) { - bdrv_set_dirty_iter(dbi, - cluster * job->cluster_size / BDRV_SECTOR_SIZE); + bdrv_set_dirty_iter(dbi, cluster * job->cluster_size); } last_cluster = cluster - 1; diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ uint32_t bdrv_dirty_bitmap_granularity(const BdrvDirtyBitmap *bitmap) return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->bitmap); } -BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap, - uint64_t first_sector) +BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap) { BdrvDirtyBitmapIter *iter = g_new(BdrvDirtyBitmapIter, 1); - hbitmap_iter_init(&iter->hbi, bitmap->bitmap, first_sector); + hbitmap_iter_init(&iter->hbi, bitmap->bitmap, 0); iter->bitmap = bitmap; bitmap->active_iterators++; return iter; @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, /** * Advance a BdrvDirtyBitmapIter to an arbitrary offset. */ -void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *iter, int64_t sector_num) +void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *iter, int64_t offset) { - hbitmap_iter_init(&iter->hbi, iter->hbi.hb, sector_num); + hbitmap_iter_init(&iter->hbi, iter->hbi.hb, offset >> BDRV_SECTOR_BITS); } int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap) 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) next_dirty = bdrv_dirty_iter_next(s->dbi) * BDRV_SECTOR_SIZE; if (next_dirty > next_offset || next_dirty < 0) { /* The bitmap iterator's cache is stale, refresh it */ - bdrv_set_dirty_iter(s->dbi, next_offset >> BDRV_SECTOR_BITS); + bdrv_set_dirty_iter(s->dbi, next_offset); next_dirty = bdrv_dirty_iter_next(s->dbi) * BDRV_SECTOR_SIZE; } assert(next_dirty == next_offset); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn mirror_run(void *opaque) } assert(!s->dbi); - s->dbi = bdrv_dirty_iter_new(s->dirty_bitmap, 0); + s->dbi = bdrv_dirty_iter_new(s->dirty_bitmap); for (;;) { uint64_t delay_ns = 0; int64_t cnt, delta; 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 uint64_t *store_bitmap_data(BlockDriverState *bs, return NULL; } - dbi = bdrv_dirty_iter_new(bitmap, 0); + dbi = bdrv_dirty_iter_new(bitmap); buf = g_malloc(s->cluster_size); limit = bytes_covered_by_bitmap_cluster(s, bitmap); sbc = limit >> BDRV_SECTOR_BITS; @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, break; } - bdrv_set_dirty_iter(dbi, end); + bdrv_set_dirty_iter(dbi, end * BDRV_SECTOR_SIZE); } *bitmap_table_size = tb_size; -- 2.13.6 From: Eric Blake <eblake@redhat.com> Thanks to recent cleanups, most callers were scaling a return value of sectors into bytes (the exception, in qcow2-bitmap, will be converted to byte-based iteration later). Update the interface to do the scaling internally instead. In qcow2-bitmap, the code was specifically checking for an error return of -1. To avoid a regression, we either have to make sure we continue to return -1 (rather than a scaled -512) on error, or we have to fix the caller to treat all negative values as error rather than just one magic value. It's easy enough to make both changes at the same time, even though either one in isolation would work. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/backup.c | 2 +- block/dirty-bitmap.c | 3 ++- block/mirror.c | 8 ++++---- block/qcow2-bitmap.c | 2 +- 4 files changed, 8 insertions(+), 7 deletions(-) diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job) dbi = bdrv_dirty_iter_new(job->sync_bitmap); /* Find the next dirty sector(s) */ - while ((offset = bdrv_dirty_iter_next(dbi) * BDRV_SECTOR_SIZE) >= 0) { + while ((offset = bdrv_dirty_iter_next(dbi)) >= 0) { cluster = offset / job->cluster_size; /* Fake progress updates for any clusters we skipped */ diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter) int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter) { - return hbitmap_iter_next(&iter->hbi); + int64_t ret = hbitmap_iter_next(&iter->hbi); + return ret < 0 ? -1 : ret * BDRV_SECTOR_SIZE; } /* Called within bdrv_dirty_bitmap_lock..unlock */ 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 max_io_bytes = MAX(s->buf_size / MAX_IN_FLIGHT, MAX_IO_BYTES); bdrv_dirty_bitmap_lock(s->dirty_bitmap); - offset = bdrv_dirty_iter_next(s->dbi) * BDRV_SECTOR_SIZE; + offset = bdrv_dirty_iter_next(s->dbi); if (offset < 0) { bdrv_set_dirty_iter(s->dbi, 0); - offset = bdrv_dirty_iter_next(s->dbi) * BDRV_SECTOR_SIZE; + offset = bdrv_dirty_iter_next(s->dbi); trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap) * BDRV_SECTOR_SIZE); assert(offset >= 0); @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) break; } - next_dirty = bdrv_dirty_iter_next(s->dbi) * BDRV_SECTOR_SIZE; + next_dirty = bdrv_dirty_iter_next(s->dbi); if (next_dirty > next_offset || next_dirty < 0) { /* The bitmap iterator's cache is stale, refresh it */ bdrv_set_dirty_iter(s->dbi, next_offset); - next_dirty = bdrv_dirty_iter_next(s->dbi) * BDRV_SECTOR_SIZE; + next_dirty = bdrv_dirty_iter_next(s->dbi); } assert(next_dirty == next_offset); nb_chunks++; 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 uint64_t *store_bitmap_data(BlockDriverState *bs, sbc = limit >> BDRV_SECTOR_BITS; assert(DIV_ROUND_UP(bm_size, limit) == tb_size); - while ((sector = bdrv_dirty_iter_next(dbi)) != -1) { + while ((sector = bdrv_dirty_iter_next(dbi) >> BDRV_SECTOR_BITS) >= 0) { uint64_t cluster = sector / sbc; uint64_t end, write_size; int64_t off; -- 2.13.6 From: Eric Blake <eblake@redhat.com> Thanks to recent cleanups, all callers were scaling a return value of sectors into bytes; do the scaling internally instead. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/dirty-bitmap.c | 4 ++-- block/mirror.c | 16 ++++++---------- migration/block.c | 2 +- 3 files changed, 9 insertions(+), 13 deletions(-) diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs) QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) { BlockDirtyInfo *info = g_new0(BlockDirtyInfo, 1); BlockDirtyInfoList *entry = g_new0(BlockDirtyInfoList, 1); - info->count = bdrv_get_dirty_count(bm) << BDRV_SECTOR_BITS; + info->count = bdrv_get_dirty_count(bm); info->granularity = bdrv_dirty_bitmap_granularity(bm); info->has_name = !!bm->name; info->name = g_strdup(bm->name); @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *iter, int64_t offset) int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap) { - return hbitmap_count(bitmap->bitmap); + return hbitmap_count(bitmap->bitmap) << BDRV_SECTOR_BITS; } int64_t bdrv_get_meta_dirty_count(BdrvDirtyBitmap *bitmap) 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) if (offset < 0) { bdrv_set_dirty_iter(s->dbi, 0); offset = bdrv_dirty_iter_next(s->dbi); - trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap) * - BDRV_SECTOR_SIZE); + trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap)); assert(offset >= 0); } bdrv_dirty_bitmap_unlock(s->dirty_bitmap); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn mirror_run(void *opaque) cnt = bdrv_get_dirty_count(s->dirty_bitmap); /* s->common.offset contains the number of bytes already processed so - * far, cnt is the number of dirty sectors remaining and + * far, cnt is the number of dirty bytes remaining and * s->bytes_in_flight is the number of bytes currently being * processed; together those are the current total operation length */ - s->common.len = s->common.offset + s->bytes_in_flight + - cnt * BDRV_SECTOR_SIZE; + s->common.len = s->common.offset + s->bytes_in_flight + cnt; /* Note that even when no rate limit is applied we need to yield * periodically with no pending I/O so that bdrv_drain_all() returns. @@ -XXX,XX +XXX,XX @@ static void coroutine_fn mirror_run(void *opaque) s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) { if (s->in_flight >= MAX_IN_FLIGHT || s->buf_free_count == 0 || (cnt == 0 && s->in_flight > 0)) { - trace_mirror_yield(s, cnt * BDRV_SECTOR_SIZE, - s->buf_free_count, s->in_flight); + trace_mirror_yield(s, cnt, s->buf_free_count, s->in_flight); mirror_wait_for_io(s); continue; } else if (cnt != 0) { @@ -XXX,XX +XXX,XX @@ static void coroutine_fn mirror_run(void *opaque) * whether to switch to target check one last time if I/O has * come in the meanwhile, and if not flush the data to disk. */ - trace_mirror_before_drain(s, cnt * BDRV_SECTOR_SIZE); + trace_mirror_before_drain(s, cnt); bdrv_drained_begin(bs); cnt = bdrv_get_dirty_count(s->dirty_bitmap); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn mirror_run(void *opaque) } ret = 0; - trace_mirror_before_sleep(s, cnt * BDRV_SECTOR_SIZE, - s->synced, delay_ns); + trace_mirror_before_sleep(s, cnt, s->synced, delay_ns); if (!s->synced) { block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns); if (block_job_is_cancelled(&s->common)) { diff --git a/migration/block.c b/migration/block.c index XXXXXXX..XXXXXXX 100644 --- a/migration/block.c +++ b/migration/block.c @@ -XXX,XX +XXX,XX @@ static int64_t get_remaining_dirty(void) aio_context_release(blk_get_aio_context(bmds->blk)); } - return dirty << BDRV_SECTOR_BITS; + return dirty; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Half the callers were already scaling bytes to sectors; the other half can eventually be simplified to use byte iteration. Both callers were already using the result as a bool, so make that explicit. Making the change also makes it easier for a future dirty-bitmap patch to offload scaling over to the internal hbitmap. Remember, asking whether a byte is dirty is effectively asking whether the entire granularity containing the byte is dirty, since we only track dirtiness by granularity. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/dirty-bitmap.h | 4 ++-- block/dirty-bitmap.c | 8 ++++---- block/mirror.c | 3 +-- migration/block.c | 3 ++- 4 files changed, 9 insertions(+), 9 deletions(-) diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_bitmap_set_persistance(BdrvDirtyBitmap *bitmap, /* Functions that require manual locking. */ void bdrv_dirty_bitmap_lock(BdrvDirtyBitmap *bitmap); void bdrv_dirty_bitmap_unlock(BdrvDirtyBitmap *bitmap); -int bdrv_get_dirty_locked(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, - int64_t sector); +bool bdrv_get_dirty_locked(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, + int64_t offset); void bdrv_set_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, int64_t cur_sector, int64_t nr_sectors); void bdrv_reset_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs) } /* Called within bdrv_dirty_bitmap_lock..unlock */ -int bdrv_get_dirty_locked(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, - int64_t sector) +bool bdrv_get_dirty_locked(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, + int64_t offset) { if (bitmap) { - return hbitmap_get(bitmap->bitmap, sector); + return hbitmap_get(bitmap->bitmap, offset >> BDRV_SECTOR_BITS); } else { - return 0; + return false; } } 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) int64_t next_offset = offset + nb_chunks * s->granularity; int64_t next_chunk = next_offset / s->granularity; if (next_offset >= s->bdev_length || - !bdrv_get_dirty_locked(source, s->dirty_bitmap, - next_offset >> BDRV_SECTOR_BITS)) { + !bdrv_get_dirty_locked(source, s->dirty_bitmap, next_offset)) { break; } if (test_bit(next_chunk, s->in_flight_bitmap)) { diff --git a/migration/block.c b/migration/block.c index XXXXXXX..XXXXXXX 100644 --- a/migration/block.c +++ b/migration/block.c @@ -XXX,XX +XXX,XX @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds, blk_mig_unlock(); } bdrv_dirty_bitmap_lock(bmds->dirty_bitmap); - if (bdrv_get_dirty_locked(bs, bmds->dirty_bitmap, sector)) { + if (bdrv_get_dirty_locked(bs, bmds->dirty_bitmap, + sector * BDRV_SECTOR_SIZE)) { if (total_sectors - sector < BDRV_SECTORS_PER_DIRTY_CHUNK) { nr_sectors = total_sectors - sector; } else { -- 2.13.6 From: Eric Blake <eblake@redhat.com> Some of the callers were already scaling bytes to sectors; others can be easily converted to pass byte offsets, all in our shift towards a consistent byte interface everywhere. Making the change will also make it easier to write the hold-out callers to use byte rather than sectors for their iterations; it also makes it easier for a future dirty-bitmap patch to offload scaling over to the internal hbitmap. Although all callers happen to pass sector-aligned values, make the internal scaling robust to any sub-sector requests. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/dirty-bitmap.h | 8 ++++---- block/dirty-bitmap.c | 22 ++++++++++++++-------- block/mirror.c | 16 ++++++++-------- migration/block.c | 7 +++++-- 4 files changed, 31 insertions(+), 22 deletions(-) diff --git a/include/block/dirty-bitmap.h b/include/block/dirty-bitmap.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/dirty-bitmap.h +++ b/include/block/dirty-bitmap.h @@ -XXX,XX +XXX,XX @@ const char *bdrv_dirty_bitmap_name(const BdrvDirtyBitmap *bitmap); int64_t bdrv_dirty_bitmap_size(const BdrvDirtyBitmap *bitmap); DirtyBitmapStatus bdrv_dirty_bitmap_status(BdrvDirtyBitmap *bitmap); void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors); + int64_t offset, int64_t bytes); void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors); + int64_t offset, int64_t bytes); BdrvDirtyBitmapIter *bdrv_dirty_meta_iter_new(BdrvDirtyBitmap *bitmap); BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap); void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter); @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_bitmap_unlock(BdrvDirtyBitmap *bitmap); bool bdrv_get_dirty_locked(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, int64_t offset); void bdrv_set_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors); + int64_t offset, int64_t bytes); void bdrv_reset_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors); + int64_t offset, int64_t bytes); int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter); void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *hbi, int64_t offset); int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap); diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter) /* Called within bdrv_dirty_bitmap_lock..unlock */ void bdrv_set_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors) + int64_t offset, int64_t bytes) { + int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); + assert(bdrv_dirty_bitmap_enabled(bitmap)); assert(!bdrv_dirty_bitmap_readonly(bitmap)); - hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors); + hbitmap_set(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, + end_sector - (offset >> BDRV_SECTOR_BITS)); } void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors) + int64_t offset, int64_t bytes) { bdrv_dirty_bitmap_lock(bitmap); - bdrv_set_dirty_bitmap_locked(bitmap, cur_sector, nr_sectors); + bdrv_set_dirty_bitmap_locked(bitmap, offset, bytes); bdrv_dirty_bitmap_unlock(bitmap); } /* Called within bdrv_dirty_bitmap_lock..unlock */ void bdrv_reset_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors) + int64_t offset, int64_t bytes) { + int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); + assert(bdrv_dirty_bitmap_enabled(bitmap)); assert(!bdrv_dirty_bitmap_readonly(bitmap)); - hbitmap_reset(bitmap->bitmap, cur_sector, nr_sectors); + hbitmap_reset(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, + end_sector - (offset >> BDRV_SECTOR_BITS)); } void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, - int64_t cur_sector, int64_t nr_sectors) + int64_t offset, int64_t bytes) { bdrv_dirty_bitmap_lock(bitmap); - bdrv_reset_dirty_bitmap_locked(bitmap, cur_sector, nr_sectors); + bdrv_reset_dirty_bitmap_locked(bitmap, offset, bytes); bdrv_dirty_bitmap_unlock(bitmap); } 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 void mirror_write_complete(void *opaque, int ret) if (ret < 0) { BlockErrorAction action; - bdrv_set_dirty_bitmap(s->dirty_bitmap, op->offset >> BDRV_SECTOR_BITS, - op->bytes >> BDRV_SECTOR_BITS); + bdrv_set_dirty_bitmap(s->dirty_bitmap, op->offset, op->bytes); action = mirror_error_action(s, false, -ret); if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) { s->ret = ret; @@ -XXX,XX +XXX,XX @@ static void mirror_read_complete(void *opaque, int ret) if (ret < 0) { BlockErrorAction action; - bdrv_set_dirty_bitmap(s->dirty_bitmap, op->offset >> BDRV_SECTOR_BITS, - op->bytes >> BDRV_SECTOR_BITS); + bdrv_set_dirty_bitmap(s->dirty_bitmap, op->offset, op->bytes); action = mirror_error_action(s, true, -ret); if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) { s->ret = ret; @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) * calling bdrv_get_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 >> BDRV_SECTOR_BITS, - nb_chunks * sectors_per_chunk); + bdrv_reset_dirty_bitmap_locked(s->dirty_bitmap, offset, + nb_chunks * s->granularity); bdrv_dirty_bitmap_unlock(s->dirty_bitmap); bitmap_set(s->in_flight_bitmap, offset / s->granularity, nb_chunks); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) if (base == NULL && !bdrv_has_zero_init(target_bs)) { if (!bdrv_can_write_zeroes_with_unmap(target_bs)) { - bdrv_set_dirty_bitmap(s->dirty_bitmap, 0, end); + bdrv_set_dirty_bitmap(s->dirty_bitmap, 0, s->bdev_length); return 0; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) n = count >> BDRV_SECTOR_BITS; assert(n > 0); if (ret == 1) { - bdrv_set_dirty_bitmap(s->dirty_bitmap, sector_num, n); + bdrv_set_dirty_bitmap(s->dirty_bitmap, + sector_num * BDRV_SECTOR_SIZE, + n * BDRV_SECTOR_SIZE); } sector_num += n; } diff --git a/migration/block.c b/migration/block.c index XXXXXXX..XXXXXXX 100644 --- a/migration/block.c +++ b/migration/block.c @@ -XXX,XX +XXX,XX @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds) blk->aiocb = blk_aio_preadv(bb, cur_sector * BDRV_SECTOR_SIZE, &blk->qiov, 0, blk_mig_read_cb, blk); - bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, cur_sector, nr_sectors); + bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, cur_sector * BDRV_SECTOR_SIZE, + nr_sectors * BDRV_SECTOR_SIZE); aio_context_release(blk_get_aio_context(bmds->blk)); qemu_mutex_unlock_iothread(); @@ -XXX,XX +XXX,XX @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds, } else { nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK; } - bdrv_reset_dirty_bitmap_locked(bmds->dirty_bitmap, sector, nr_sectors); + bdrv_reset_dirty_bitmap_locked(bmds->dirty_bitmap, + sector * BDRV_SECTOR_SIZE, + nr_sectors * BDRV_SECTOR_SIZE); bdrv_dirty_bitmap_unlock(bmds->dirty_bitmap); blk = g_new(BlkMigBlock, 1); -- 2.13.6 From: Eric Blake <eblake@redhat.com> Now that we have adjusted the majority of the calls this function makes to be byte-based, it is easier to read the code if it makes passes over the image using bytes rather than sectors. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/mirror.c | 38 ++++++++++++++------------------------ 1 file changed, 14 insertions(+), 24 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 void mirror_throttle(MirrorBlockJob *s) static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) { - int64_t sector_num, end; + int64_t offset; BlockDriverState *base = s->base; BlockDriverState *bs = s->source; BlockDriverState *target_bs = blk_bs(s->target); - int ret, n; + int ret; int64_t count; - end = s->bdev_length / BDRV_SECTOR_SIZE; - if (base == NULL && !bdrv_has_zero_init(target_bs)) { if (!bdrv_can_write_zeroes_with_unmap(target_bs)) { bdrv_set_dirty_bitmap(s->dirty_bitmap, 0, s->bdev_length); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) } s->initial_zeroing_ongoing = true; - for (sector_num = 0; sector_num < end; ) { - int nb_sectors = MIN(end - sector_num, - QEMU_ALIGN_DOWN(INT_MAX, s->granularity) >> BDRV_SECTOR_BITS); + for (offset = 0; offset < s->bdev_length; ) { + int bytes = MIN(s->bdev_length - offset, + QEMU_ALIGN_DOWN(INT_MAX, s->granularity)); mirror_throttle(s); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) continue; } - mirror_do_zero_or_discard(s, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, false); - sector_num += nb_sectors; + mirror_do_zero_or_discard(s, offset, bytes, false); + offset += bytes; } mirror_wait_for_all_io(s); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) } /* First part, loop on the sectors and initialize the dirty bitmap. */ - for (sector_num = 0; sector_num < end; ) { + for (offset = 0; offset < s->bdev_length; ) { /* Just to make sure we are not exceeding int limit. */ - int nb_sectors = MIN(INT_MAX >> BDRV_SECTOR_BITS, - end - sector_num); + int bytes = MIN(s->bdev_length - offset, + QEMU_ALIGN_DOWN(INT_MAX, s->granularity)); mirror_throttle(s); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) return 0; } - ret = bdrv_is_allocated_above(bs, base, sector_num * BDRV_SECTOR_SIZE, - nb_sectors * BDRV_SECTOR_SIZE, &count); + ret = bdrv_is_allocated_above(bs, base, offset, bytes, &count); if (ret < 0) { return ret; } - /* TODO: Relax this once bdrv_is_allocated_above and dirty - * bitmaps no longer require sector alignment. */ - assert(QEMU_IS_ALIGNED(count, BDRV_SECTOR_SIZE)); - n = count >> BDRV_SECTOR_BITS; - assert(n > 0); + assert(count); if (ret == 1) { - bdrv_set_dirty_bitmap(s->dirty_bitmap, - sector_num * BDRV_SECTOR_SIZE, - n * BDRV_SECTOR_SIZE); + bdrv_set_dirty_bitmap(s->dirty_bitmap, offset, count); } - sector_num += n; + offset += count; } return 0; } -- 2.13.6 From: Eric Blake <eblake@redhat.com> This is new code, but it is easier to read if it makes passes over the image using bytes rather than sectors (and will get easier in the future when bdrv_get_block_status is converted to byte-based). Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 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 BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs, */ required = virtual_size; } else { - int cluster_sectors = cluster_size / BDRV_SECTOR_SIZE; - int64_t sector_num; + int64_t offset; int pnum = 0; - for (sector_num = 0; - sector_num < ssize / BDRV_SECTOR_SIZE; - sector_num += pnum) { - int nb_sectors = MIN(ssize / BDRV_SECTOR_SIZE - sector_num, - BDRV_REQUEST_MAX_SECTORS); + for (offset = 0; offset < ssize; + 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, - sector_num, nb_sectors, + offset >> BDRV_SECTOR_BITS, + nb_sectors, &pnum, &file); if (ret < 0) { error_setg_errno(&local_err, -ret, @@ -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(sector_num + pnum, cluster_sectors) - - sector_num; + pnum = (ROUND_UP(offset + pnum * BDRV_SECTOR_SIZE, + cluster_size) - offset) >> BDRV_SECTOR_BITS; /* Count clusters we've seen */ - required += (sector_num % cluster_sectors + pnum) * - BDRV_SECTOR_SIZE; + required += offset % cluster_size + pnum * BDRV_SECTOR_SIZE; } } } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Now that we have adjusted the majority of the calls this function makes to be byte-based, it is easier to read the code if it makes passes over the image using bytes rather than sectors. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-bitmap.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) 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 int load_bitmap_data(BlockDriverState *bs, { int ret = 0; BDRVQcow2State *s = bs->opaque; - uint64_t sector, limit, sbc; + uint64_t offset, limit; uint64_t bm_size = bdrv_dirty_bitmap_size(bitmap); - uint64_t bm_sectors = DIV_ROUND_UP(bm_size, BDRV_SECTOR_SIZE); uint8_t *buf = NULL; uint64_t i, tab_size = size_to_clusters(s, @@ -XXX,XX +XXX,XX @@ static int load_bitmap_data(BlockDriverState *bs, buf = g_malloc(s->cluster_size); limit = bytes_covered_by_bitmap_cluster(s, bitmap); - sbc = limit >> BDRV_SECTOR_BITS; - for (i = 0, sector = 0; i < tab_size; ++i, sector += sbc) { - uint64_t count = MIN(bm_sectors - sector, sbc); + for (i = 0, offset = 0; i < tab_size; ++i, offset += limit) { + uint64_t count = MIN(bm_size - offset, limit); uint64_t entry = bitmap_table[i]; - uint64_t offset = entry & BME_TABLE_ENTRY_OFFSET_MASK; + uint64_t data_offset = entry & BME_TABLE_ENTRY_OFFSET_MASK; assert(check_table_entry(entry, s->cluster_size) == 0); - if (offset == 0) { + if (data_offset == 0) { if (entry & BME_TABLE_ENTRY_FLAG_ALL_ONES) { - bdrv_dirty_bitmap_deserialize_ones(bitmap, - sector * BDRV_SECTOR_SIZE, - count * BDRV_SECTOR_SIZE, + bdrv_dirty_bitmap_deserialize_ones(bitmap, offset, count, false); } else { /* No need to deserialize zeros because the dirty bitmap is * already cleared */ } } else { - ret = bdrv_pread(bs->file, offset, buf, s->cluster_size); + ret = bdrv_pread(bs->file, data_offset, buf, s->cluster_size); if (ret < 0) { goto finish; } - bdrv_dirty_bitmap_deserialize_part(bitmap, buf, - sector * BDRV_SECTOR_SIZE, - count * BDRV_SECTOR_SIZE, + bdrv_dirty_bitmap_deserialize_part(bitmap, buf, offset, count, false); } } -- 2.13.6 From: Eric Blake <eblake@redhat.com> Now that we have adjusted the majority of the calls this function makes to be byte-based, it is easier to read the code if it makes passes over the image using bytes rather than sectors. iotests 165 was rather weak - on a default 64k-cluster image, where bitmap granularity also defaults to 64k bytes, a single cluster of the bitmap table thus covers (64*1024*8) bits which each cover 64k bytes, or 32G of image space. But the test only uses a 1G image, so it cannot trigger any more than one loop of the code in store_bitmap_data(); and it was writing to the first cluster. In order to test that we are properly aligning which portions of the bitmap are being written to the file, we really want to test a case where the first dirty bit returned by bdrv_dirty_iter_next() is not aligned to the start of a cluster, which we can do by modifying the test to write data that doesn't happen to fall in the first cluster of the image. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-bitmap.c | 31 ++++++++++++++++--------------- tests/qemu-iotests/165 | 2 +- 2 files changed, 17 insertions(+), 16 deletions(-) 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 uint64_t *store_bitmap_data(BlockDriverState *bs, { int ret; BDRVQcow2State *s = bs->opaque; - int64_t sector; - uint64_t limit, sbc; + int64_t offset; + uint64_t limit; uint64_t bm_size = bdrv_dirty_bitmap_size(bitmap); - uint64_t bm_sectors = DIV_ROUND_UP(bm_size, BDRV_SECTOR_SIZE); const char *bm_name = bdrv_dirty_bitmap_name(bitmap); uint8_t *buf = NULL; BdrvDirtyBitmapIter *dbi; @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, dbi = bdrv_dirty_iter_new(bitmap); buf = g_malloc(s->cluster_size); limit = bytes_covered_by_bitmap_cluster(s, bitmap); - sbc = limit >> BDRV_SECTOR_BITS; assert(DIV_ROUND_UP(bm_size, limit) == tb_size); - while ((sector = bdrv_dirty_iter_next(dbi) >> BDRV_SECTOR_BITS) >= 0) { - uint64_t cluster = sector / sbc; + while ((offset = bdrv_dirty_iter_next(dbi)) >= 0) { + uint64_t cluster = offset / limit; uint64_t end, write_size; int64_t off; - sector = cluster * sbc; - end = MIN(bm_sectors, sector + sbc); - write_size = bdrv_dirty_bitmap_serialization_size(bitmap, - sector * BDRV_SECTOR_SIZE, (end - sector) * BDRV_SECTOR_SIZE); + /* + * We found the first dirty offset, but want to write out the + * entire cluster of the bitmap that includes that offset, + * including any leading zero bits. + */ + offset = QEMU_ALIGN_DOWN(offset, limit); + end = MIN(bm_size, offset + limit); + write_size = bdrv_dirty_bitmap_serialization_size(bitmap, offset, + end - offset); assert(write_size <= s->cluster_size); off = qcow2_alloc_clusters(bs, s->cluster_size); @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, } tb[cluster] = off; - bdrv_dirty_bitmap_serialize_part(bitmap, buf, - sector * BDRV_SECTOR_SIZE, - (end - sector) * BDRV_SECTOR_SIZE); + bdrv_dirty_bitmap_serialize_part(bitmap, buf, offset, end - offset); if (write_size < s->cluster_size) { memset(buf + write_size, 0, s->cluster_size - write_size); } @@ -XXX,XX +XXX,XX @@ static uint64_t *store_bitmap_data(BlockDriverState *bs, goto fail; } - if (end >= bm_sectors) { + if (end >= bm_size) { break; } - bdrv_set_dirty_iter(dbi, end * BDRV_SECTOR_SIZE); + bdrv_set_dirty_iter(dbi, end); } *bitmap_table_size = tb_size; diff --git a/tests/qemu-iotests/165 b/tests/qemu-iotests/165 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/165 +++ b/tests/qemu-iotests/165 @@ -XXX,XX +XXX,XX @@ disk = os.path.join(iotests.test_dir, 'disk') disk_size = 0x40000000 # 1G # regions for qemu_io: (start, count) in bytes -regions1 = ((0, 0x100000), +regions1 = ((0x0fff00, 0x10000), (0x200000, 0x100000)) regions2 = ((0x10000000, 0x20000), -- 2.13.6 From: Eric Blake <eblake@redhat.com> Both callers already had bytes available, but were scaling to sectors. Move the scaling to internal code. In the case of bdrv_aligned_pwritev(), we are now passing the exact offset rather than a rounded sector-aligned value, but that's okay as long as dirty bitmap widens start/bytes to granularity boundaries. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 2 +- block/dirty-bitmap.c | 7 ++++--- block/io.c | 6 ++---- 3 files changed, 7 insertions(+), 8 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 @@ void blk_dev_eject_request(BlockBackend *blk, bool force); bool blk_dev_is_tray_open(BlockBackend *blk); bool blk_dev_is_medium_locked(BlockBackend *blk); -void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int64_t nr_sect); +void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes); bool bdrv_requests_pending(BlockDriverState *bs); void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out); diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap) hbitmap_deserialize_finish(bitmap->bitmap); } -void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, - int64_t nr_sectors) +void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes) { BdrvDirtyBitmap *bitmap; + int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); if (QLIST_EMPTY(&bs->dirty_bitmaps)) { return; @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, continue; } assert(!bdrv_dirty_bitmap_readonly(bitmap)); - hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors); + hbitmap_set(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, + end_sector - (offset >> BDRV_SECTOR_BITS)); } bdrv_dirty_bitmaps_unlock(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 int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child, bool waited; int ret; - int64_t start_sector = offset >> BDRV_SECTOR_BITS; int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); uint64_t bytes_remaining = bytes; int max_transfer; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child, bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE); atomic_inc(&bs->write_gen); - bdrv_set_dirty(bs, start_sector, end_sector - start_sector); + bdrv_set_dirty(bs, offset, bytes); stat64_max(&bs->wr_highest_offset, offset + bytes); @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pdiscard(BlockDriverState *bs, int64_t offset, ret = 0; out: atomic_inc(&bs->write_gen); - bdrv_set_dirty(bs, req.offset >> BDRV_SECTOR_BITS, - req.bytes >> BDRV_SECTOR_BITS); + bdrv_set_dirty(bs, req.offset, req.bytes); tracked_request_end(&req); bdrv_dec_in_flight(bs); return ret; -- 2.13.6 From: Eric Blake <eblake@redhat.com> Now that all callers are using byte-based interfaces, there's no reason for our internal hbitmap to remain with sector-based granularity. It also simplifies our internal scaling, since we already know that hbitmap widens requests out to granularity boundaries. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/dirty-bitmap.c | 62 +++++++++++++++------------------------------------- 1 file changed, 18 insertions(+), 44 deletions(-) diff --git a/block/dirty-bitmap.c b/block/dirty-bitmap.c index XXXXXXX..XXXXXXX 100644 --- a/block/dirty-bitmap.c +++ b/block/dirty-bitmap.c @@ -XXX,XX +XXX,XX @@ */ struct BdrvDirtyBitmap { QemuMutex *mutex; - HBitmap *bitmap; /* Dirty sector bitmap implementation */ + HBitmap *bitmap; /* Dirty bitmap implementation */ HBitmap *meta; /* Meta dirty bitmap */ BdrvDirtyBitmap *successor; /* Anonymous child; implies frozen status */ char *name; /* Optional non-empty unique ID */ @@ -XXX,XX +XXX,XX @@ BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs, } bitmap = g_new0(BdrvDirtyBitmap, 1); bitmap->mutex = &bs->dirty_bitmap_mutex; - /* - * TODO - let hbitmap track full granularity. For now, it is tracking - * only sector granularity, as a shortcut for our iterators. - */ - bitmap->bitmap = hbitmap_alloc(DIV_ROUND_UP(bitmap_size, BDRV_SECTOR_SIZE), - ctz32(granularity) - BDRV_SECTOR_BITS); + bitmap->bitmap = hbitmap_alloc(bitmap_size, ctz32(granularity)); bitmap->size = bitmap_size; bitmap->name = g_strdup(name); bitmap->disabled = false; @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_bitmap_truncate(BlockDriverState *bs, int64_t bytes) QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) { assert(!bdrv_dirty_bitmap_frozen(bitmap)); assert(!bitmap->active_iterators); - hbitmap_truncate(bitmap->bitmap, DIV_ROUND_UP(bytes, BDRV_SECTOR_SIZE)); + hbitmap_truncate(bitmap->bitmap, bytes); bitmap->size = bytes; } bdrv_dirty_bitmaps_unlock(bs); @@ -XXX,XX +XXX,XX @@ bool bdrv_get_dirty_locked(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, int64_t offset) { if (bitmap) { - return hbitmap_get(bitmap->bitmap, offset >> BDRV_SECTOR_BITS); + return hbitmap_get(bitmap->bitmap, offset); } else { return false; } @@ -XXX,XX +XXX,XX @@ uint32_t bdrv_get_default_bitmap_granularity(BlockDriverState *bs) uint32_t bdrv_dirty_bitmap_granularity(const BdrvDirtyBitmap *bitmap) { - return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->bitmap); + return 1U << hbitmap_granularity(bitmap->bitmap); } BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap) @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter) int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter) { - int64_t ret = hbitmap_iter_next(&iter->hbi); - return ret < 0 ? -1 : ret * BDRV_SECTOR_SIZE; + return hbitmap_iter_next(&iter->hbi); } /* Called within bdrv_dirty_bitmap_lock..unlock */ void bdrv_set_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, int64_t offset, int64_t bytes) { - int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); - assert(bdrv_dirty_bitmap_enabled(bitmap)); assert(!bdrv_dirty_bitmap_readonly(bitmap)); - hbitmap_set(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, - end_sector - (offset >> BDRV_SECTOR_BITS)); + hbitmap_set(bitmap->bitmap, offset, bytes); } void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap, void bdrv_reset_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap, int64_t offset, int64_t bytes) { - int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); - assert(bdrv_dirty_bitmap_enabled(bitmap)); assert(!bdrv_dirty_bitmap_readonly(bitmap)); - hbitmap_reset(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, - end_sector - (offset >> BDRV_SECTOR_BITS)); + hbitmap_reset(bitmap->bitmap, offset, bytes); } void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap, @@ -XXX,XX +XXX,XX @@ void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out) hbitmap_reset_all(bitmap->bitmap); } else { HBitmap *backup = bitmap->bitmap; - bitmap->bitmap = hbitmap_alloc(DIV_ROUND_UP(bitmap->size, - BDRV_SECTOR_SIZE), + bitmap->bitmap = hbitmap_alloc(bitmap->size, hbitmap_granularity(backup)); *out = backup; } @@ -XXX,XX +XXX,XX @@ void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in) uint64_t bdrv_dirty_bitmap_serialization_size(const BdrvDirtyBitmap *bitmap, uint64_t offset, uint64_t bytes) { - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - return hbitmap_serialization_size(bitmap->bitmap, - offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS); + return hbitmap_serialization_size(bitmap->bitmap, offset, bytes); } uint64_t bdrv_dirty_bitmap_serialization_align(const BdrvDirtyBitmap *bitmap) { - return hbitmap_serialization_align(bitmap->bitmap) * BDRV_SECTOR_SIZE; + return hbitmap_serialization_align(bitmap->bitmap); } void bdrv_dirty_bitmap_serialize_part(const BdrvDirtyBitmap *bitmap, uint8_t *buf, uint64_t offset, uint64_t bytes) { - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - hbitmap_serialize_part(bitmap->bitmap, buf, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS); + hbitmap_serialize_part(bitmap->bitmap, buf, offset, bytes); } void bdrv_dirty_bitmap_deserialize_part(BdrvDirtyBitmap *bitmap, uint8_t *buf, uint64_t offset, uint64_t bytes, bool finish) { - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - hbitmap_deserialize_part(bitmap->bitmap, buf, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, finish); + hbitmap_deserialize_part(bitmap->bitmap, buf, offset, bytes, finish); } void bdrv_dirty_bitmap_deserialize_zeroes(BdrvDirtyBitmap *bitmap, uint64_t offset, uint64_t bytes, bool finish) { - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - hbitmap_deserialize_zeroes(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, finish); + hbitmap_deserialize_zeroes(bitmap->bitmap, offset, bytes, finish); } void bdrv_dirty_bitmap_deserialize_ones(BdrvDirtyBitmap *bitmap, uint64_t offset, uint64_t bytes, bool finish) { - assert(QEMU_IS_ALIGNED(offset | bytes, BDRV_SECTOR_SIZE)); - hbitmap_deserialize_ones(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, - bytes >> BDRV_SECTOR_BITS, finish); + hbitmap_deserialize_ones(bitmap->bitmap, offset, bytes, finish); } void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap) @@ -XXX,XX +XXX,XX @@ void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap) void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes) { BdrvDirtyBitmap *bitmap; - int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE); if (QLIST_EMPTY(&bs->dirty_bitmaps)) { return; @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes) continue; } assert(!bdrv_dirty_bitmap_readonly(bitmap)); - hbitmap_set(bitmap->bitmap, offset >> BDRV_SECTOR_BITS, - end_sector - (offset >> BDRV_SECTOR_BITS)); + hbitmap_set(bitmap->bitmap, offset, bytes); } bdrv_dirty_bitmaps_unlock(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes) */ void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *iter, int64_t offset) { - hbitmap_iter_init(&iter->hbi, iter->hbi.hb, offset >> BDRV_SECTOR_BITS); + hbitmap_iter_init(&iter->hbi, iter->hbi.hb, offset); } int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap) { - return hbitmap_count(bitmap->bitmap) << BDRV_SECTOR_BITS; + return hbitmap_count(bitmap->bitmap); } int64_t bdrv_get_meta_dirty_count(BdrvDirtyBitmap *bitmap) -- 2.13.6 From: Thomas Huth <thuth@redhat.com> The condition of the for-loop makes sure that b is always smaller than s->blocks, so the "if (b >= s->blocks)" statement is completely superfluous here. Buglink: https://bugs.launchpad.net/qemu/+bug/1715007 Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Laurent Vivier <lvivier@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/block/onenand.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/hw/block/onenand.c b/hw/block/onenand.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/onenand.c +++ b/hw/block/onenand.c @@ -XXX,XX +XXX,XX @@ static void onenand_command(OneNANDState *s) s->intstatus |= ONEN_INT; for (b = 0; b < s->blocks; b ++) { - if (b >= s->blocks) { - s->status |= ONEN_ERR_CMD; - break; - } if (s->blockwp[b] == ONEN_LOCK_LOCKTIGHTEN) break; -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> This includes shell function, shell variables and command line options (randomize.awk does not exist). Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 28 ----------------- tests/qemu-iotests/common | 23 -------------- tests/qemu-iotests/common.config | 26 --------------- tests/qemu-iotests/common.rc | 68 ---------------------------------------- 4 files changed, 145 deletions(-) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ then export SOCKET_SCM_HELPER="$build_iotests/socket_scm_helper" fi -# if ./qemu exists, it should be prioritized and will be chosen by common.config if [[ -z "$QEMU_PROG" && ! -x './qemu' ]] then arch=$(uname -m 2> /dev/null) @@ -XXX,XX +XXX,XX @@ _timestamp() _wrapup() { - # for hangcheck ... - # remove files that were used by hangcheck - # - [ -f "${TEST_DIR}"/check.pid ] && rm -rf "${TEST_DIR}"/check.pid - [ -f "${TEST_DIR}"/check.sts ] && rm -rf "${TEST_DIR}"/check.sts - if $showme then : @@ -XXX,XX +XXX,XX @@ END { if (NR > 0) { trap "_wrapup; exit \$status" 0 1 2 3 15 -# for hangcheck ... -# Save pid of check in a well known place, so that hangcheck can be sure it -# has the right pid (getting the pid from ps output is not reliable enough). -# -rm -rf "${TEST_DIR}"/check.pid -echo $$ > "${TEST_DIR}"/check.pid - -# for hangcheck ... -# Save the status of check in a well known place, so that hangcheck can be -# sure to know where check is up to (getting test number from ps output is -# not reliable enough since the trace stuff has been introduced). -# -rm -rf "${TEST_DIR}"/check.sts -echo "preamble" > "${TEST_DIR}"/check.sts - -# don't leave old full output behind on a clean run -rm -f check.full - [ -f $TIMESTAMP_FILE ] || touch $TIMESTAMP_FILE FULL_IMGFMT_DETAILS=`_full_imgfmt_details` @@ -XXX,XX +XXX,XX @@ do fi rm -f core $seq.notrun - # for hangcheck ... - echo "$seq" > "${TEST_DIR}"/check.sts - start=`_wallclock` $timestamp && printf %s " [$(date "+%T")]" diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common +++ b/tests/qemu-iotests/common @@ -XXX,XX +XXX,XX @@ # common procedures for QA scripts # -_setenvironment() -{ - MSGVERB="text:action" - export MSGVERB -} - -rm -f "$OUTPUT_DIR/$iam.out" -_setenvironment - -check=${check-true} - diff="diff -u" verbose=false debug=false @@ -XXX,XX +XXX,XX @@ showme=false sortme=false expunge=true have_test_arg=false -randomize=false cachemode=false rm -f $tmp.list $tmp.tmp $tmp.sed @@ -XXX,XX +XXX,XX @@ other options -n show me, do not run tests -o options -o options to pass to qemu-img create/convert -T output timestamps - -r randomize test order -c mode cache mode testlist options @@ -XXX,XX +XXX,XX @@ testlist options cachemode=true xpand=false ;; - -r) # randomize test order - randomize=true - xpand=false - ;; - -T) # turn on timestamp output timestamp=true xpand=false @@ -XXX,XX +XXX,XX @@ fi list=`sort $tmp.list` rm -f $tmp.list $tmp.tmp $tmp.sed -if $randomize -then - list=`echo $list | awk -f randomize.awk` -fi - [ "$QEMU" = "" ] && _fatal "qemu not found" [ "$QEMU_IMG" = "" ] && _fatal "qemu-img not found" [ "$QEMU_IO" = "" ] && _fatal "qemu-io not found" diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.config +++ b/tests/qemu-iotests/common.config @@ -XXX,XX +XXX,XX @@ # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. # -# -# setup and check for config parameters, and in particular -# -# EMAIL - email of the script runner. -# TEST_DIR - scratch test directory -# -# - These can be added to $HOST_CONFIG_DIR (witch default to ./config) -# below or a separate local configuration file can be used (using -# the HOST_OPTIONS variable). -# - This script is shared by the stress test system and the auto-qa -# system (includes both regression test and benchmark components). -# - this script shouldn't make any assertions about filesystem -# validity or mountedness. -# - # all tests should use a common language setting to prevent golden # output mismatches. export LANG=C PATH=".:$PATH" -HOST=`hostname -s 2> /dev/null` HOSTOS=`uname -s` -EMAIL=root@localhost # where auto-qa will send its status messages -export HOST_OPTIONS=${HOST_OPTIONS:=local.config} -export CHECK_OPTIONS=${CHECK_OPTIONS:="-g auto"} export PWD=`pwd` export _QEMU_HANDLE=0 @@ -XXX,XX +XXX,XX @@ _fatal() export AWK_PROG="`set_prog_path awk`" [ "$AWK_PROG" = "" ] && _fatal "awk not found" -export SED_PROG="`set_prog_path sed`" -[ "$SED_PROG" = "" ] && _fatal "sed not found" - -export PS_ALL_FLAGS="-ef" - if [ -z "$QEMU_PROG" ]; then export QEMU_PROG="`set_prog_path qemu`" fi @@ -XXX,XX +XXX,XX @@ fi export QEMU_DEFAULT_MACHINE="$default_machine" -[ -f /etc/qemu-iotest.config ] && . /etc/qemu-iotest.config - if [ -z "$TEST_DIR" ]; then TEST_DIR=`pwd`/scratch fi diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _img_info() done } -_get_pids_by_name() -{ - if [ $# -ne 1 ] - then - echo "Usage: _get_pids_by_name process-name" 1>&2 - exit 1 - fi - - # Algorithm ... all ps(1) variants have a time of the form MM:SS or - # HH:MM:SS before the psargs field, use this as the search anchor. - # - # Matches with $1 (process-name) occur if the first psarg is $1 - # or ends in /$1 ... the matching uses sed's regular expressions, - # so passing a regex into $1 will work. - - ps $PS_ALL_FLAGS \ - | sed -n \ - -e 's/$/ /' \ - -e 's/[ ][ ]*/ /g' \ - -e 's/^ //' \ - -e 's/^[^ ]* //' \ - -e "/[0-9]:[0-9][0-9] *[^ ]*\/$1 /s/ .*//p" \ - -e "/[0-9]:[0-9][0-9] *$1 /s/ .*//p" -} - -# fqdn for localhost -# -_get_fqdn() -{ - host=`hostname` - $NSLOOKUP_PROG $host | $AWK_PROG '{ if ($1 == "Name:") print $2 }' -} - -# check if run as root -# -_need_to_be_root() -{ - id=`id | $SED_PROG -e 's/(.*//' -e 's/.*=//'` - if [ "$id" -ne 0 ] - then - echo "Arrgh ... you need to be root (not uid=$id) to run this test" - exit 1 - fi -} - # bail out, setting up .notrun file # _notrun() @@ -XXX,XX +XXX,XX @@ _full_platform_details() echo "$os/$platform $host $kernel" } -_link_out_file() -{ - if [ -z "$1" ]; then - echo Error must pass \$seq. - exit - fi - rm -f $1 - if [ "`uname`" == "IRIX64" ] || [ "`uname`" == "IRIX" ]; then - ln -s $1.irix $1 - elif [ "`uname`" == "Linux" ]; then - ln -s $1.linux $1 - else - echo Error test $seq does not run on the operating system: `uname` - exit - fi -} - -_die() -{ - echo $@ - exit 1 -} - # make sure this script returns success true -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 4 ++-- tests/qemu-iotests/common | 2 +- tests/qemu-iotests/common.config | 3 --- 3 files changed, 3 insertions(+), 6 deletions(-) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ tmp="${TEST_DIR}"/$$ _wallclock() { - date "+%H %M %S" | $AWK_PROG '{ print $1*3600 + $2*60 + $3 }' + date "+%H %M %S" | awk '{ print $1*3600 + $2*60 + $3 }' } _timestamp() @@ -XXX,XX +XXX,XX @@ _wrapup() if [ -f $TIMESTAMP_FILE -a -f $tmp.time ] then cat $TIMESTAMP_FILE $tmp.time \ - | $AWK_PROG ' + | awk ' { t[$1] = $2 } END { if (NR > 0) { for (i in t) print i " " t[i] diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common +++ b/tests/qemu-iotests/common @@ -XXX,XX +XXX,XX @@ testlist options if $xpand then have_test_arg=true - $AWK_PROG </dev/null ' + awk </dev/null ' BEGIN { for (t='$start'; t<='$end'; t++) printf "%03d\n",t }' \ | while read id do diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.config +++ b/tests/qemu-iotests/common.config @@ -XXX,XX +XXX,XX @@ _fatal() exit 1 } -export AWK_PROG="`set_prog_path awk`" -[ "$AWK_PROG" = "" ] && _fatal "awk not found" - if [ -z "$QEMU_PROG" ]; then export QEMU_PROG="`set_prog_path qemu`" fi -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> Some functions in common.rc are never used by the tests. Move them out of that file and into common, which is already included only by "check". Code that actually *is* common to "check" and tests can be placed in common.config. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/common | 25 ++++++++++++++++++++++++- tests/qemu-iotests/common.config | 12 ++++++++++++ tests/qemu-iotests/common.rc | 40 ---------------------------------------- 3 files changed, 36 insertions(+), 41 deletions(-) diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common +++ b/tests/qemu-iotests/common @@ -XXX,XX +XXX,XX @@ # common procedures for QA scripts # +_full_imgfmt_details() +{ + if [ -n "$IMGOPTS" ]; then + echo "$IMGFMT ($IMGOPTS)" + else + echo "$IMGFMT" + fi +} + +_full_platform_details() +{ + os=`uname -s` + host=`hostname -s` + kernel=`uname -r` + platform=`uname -m` + echo "$os/$platform $host $kernel" +} + diff="diff -u" verbose=false debug=false @@ -XXX,XX +XXX,XX @@ if [ "$IMGOPTSSYNTAX" != "true" ]; then fi # Set default options for qemu-img create -o if they were not specified -_set_default_imgopts +if [ "$IMGFMT" == "qcow2" ] && ! (echo "$IMGOPTS" | grep "compat=" > /dev/null); then + IMGOPTS=$(_optstr_add "$IMGOPTS" "compat=1.1") +fi +if [ "$IMGFMT" == "luks" ] && ! (echo "$IMGOPTS" | grep "iter-time=" > /dev/null); then + IMGOPTS=$(_optstr_add "$IMGOPTS" "iter-time=10") +fi if [ -s $tmp.list ] then diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.config +++ b/tests/qemu-iotests/common.config @@ -XXX,XX +XXX,XX @@ export PWD=`pwd` export _QEMU_HANDLE=0 +# make sure we have a standard umask +umask 022 + # $1 = prog to look for, $2* = default pathnames if not found in $PATH set_prog_path() { @@ -XXX,XX +XXX,XX @@ set_prog_path() return 1 } +_optstr_add() +{ + if [ -n "$1" ]; then + echo "$1,$2" + else + echo "$2" + fi +} + _fatal() { echo "$*" diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ then fi fi -# make sure we have a standard umask -umask 022 - if [ "$IMGOPTSSYNTAX" = "true" ]; then DRIVER="driver=$IMGFMT" if [ "$IMGFMT" = "luks" ]; then @@ -XXX,XX +XXX,XX @@ else fi ORIG_TEST_IMG="$TEST_IMG" -_optstr_add() -{ - if [ -n "$1" ]; then - echo "$1,$2" - else - echo "$2" - fi -} - -_set_default_imgopts() -{ - if [ "$IMGFMT" == "qcow2" ] && ! (echo "$IMGOPTS" | grep "compat=" > /dev/null); then - IMGOPTS=$(_optstr_add "$IMGOPTS" "compat=1.1") - fi - if [ "$IMGFMT" == "luks" ] && ! (echo "$IMGOPTS" | grep "iter-time=" > /dev/null); then - IMGOPTS=$(_optstr_add "$IMGOPTS" "iter-time=10") - fi -} - _use_sample_img() { SAMPLE_IMG_FILE="${1%\.bz2}" @@ -XXX,XX +XXX,XX @@ _require_command() [ -x "$c" ] || _notrun "$1 utility required, skipped this test" } -_full_imgfmt_details() -{ - if [ -n "$IMGOPTS" ]; then - echo "$IMGFMT ($IMGOPTS)" - else - echo "$IMGFMT" - fi -} - -_full_platform_details() -{ - os=`uname -s` - host=`hostname -s` - kernel=`uname -r` - platform=`uname -m` - echo "$os/$platform $host $kernel" -} - # make sure this script returns success true -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> Instead of ./check failing when a binary is missing, we try each test case now and each one fails with tons of test case diffs. Also, all the variables were initialized by "check" prior to "common" being sourced, and then (uselessly) checked for emptiness again in "check". Centralize the search for programs in "common" (which will soon be one with "check"), including the "realpath" invocation which can be done just once in "check" rather than in the tests. For qnio_server, move the detection to "common", simplifying set_prog_path to stop handling the unused second argument, and embedding the "realpath" pass. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 41 --------------------- tests/qemu-iotests/common | 77 +++++++++++++++++++++++++++++++++++++--- tests/qemu-iotests/common.config | 61 +------------------------------ 3 files changed, 73 insertions(+), 106 deletions(-) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ fi build_root="$build_iotests/../.." -if [ -x "$build_iotests/socket_scm_helper" ] -then - export SOCKET_SCM_HELPER="$build_iotests/socket_scm_helper" -fi - -if [[ -z "$QEMU_PROG" && ! -x './qemu' ]] -then - arch=$(uname -m 2> /dev/null) - - if [[ -n $arch && -x "$build_root/$arch-softmmu/qemu-system-$arch" ]] - then - export QEMU_PROG="$build_root/$arch-softmmu/qemu-system-$arch" - else - pushd "$build_root" > /dev/null - for binary in *-softmmu/qemu-system-* - do - if [ -x "$binary" ] - then - export QEMU_PROG="$build_root/$binary" - break - fi - done - popd > /dev/null - fi -fi - -if [[ -z $QEMU_IMG_PROG && -x "$build_root/qemu-img" && ! -x './qemu-img' ]] -then - export QEMU_IMG_PROG="$build_root/qemu-img" -fi - -if [[ -z $QEMU_IO_PROG && -x "$build_root/qemu-io" && ! -x './qemu-io' ]] -then - export QEMU_IO_PROG="$build_root/qemu-io" -fi - -if [[ -z $QEMU_NBD_PROG && -x "$build_root/qemu-nbd" && ! -x './qemu-nbd' ]] -then - export QEMU_NBD_PROG="$build_root/qemu-nbd" -fi - # we need common.env if ! . "$build_iotests/common.env" then diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common +++ b/tests/qemu-iotests/common @@ -XXX,XX +XXX,XX @@ _full_platform_details() echo "$os/$platform $host $kernel" } +# $1 = prog to look for +set_prog_path() +{ + p=`command -v $1 2> /dev/null` + if [ -n "$p" -a -x "$p" ]; then + realpath -- "$(type -p "$p")" + else + return 1 + fi +} + diff="diff -u" verbose=false debug=false @@ -XXX,XX +XXX,XX @@ fi list=`sort $tmp.list` rm -f $tmp.list $tmp.tmp $tmp.sed -[ "$QEMU" = "" ] && _fatal "qemu not found" -[ "$QEMU_IMG" = "" ] && _fatal "qemu-img not found" -[ "$QEMU_IO" = "" ] && _fatal "qemu-io not found" +if [ -z "$QEMU_PROG" ] +then + if [ -x "$build_iotests/qemu" ]; then + export QEMU_PROG="$build_iotests/qemu" + elif [ -x "$build_root/$arch-softmmu/qemu-system-$arch" ]; then + export QEMU_PROG="$build_root/$arch-softmmu/qemu-system-$arch" + else + pushd "$build_root" > /dev/null + for binary in *-softmmu/qemu-system-* + do + if [ -x "$binary" ] + then + export QEMU_PROG="$build_root/$binary" + break + fi + done + popd > /dev/null + [ "$QEMU_PROG" = "" ] && _init_error "qemu not found" + fi +fi +export QEMU_PROG=$(realpath -- "$(type -p "$QEMU_PROG")") + +if [ -z "$QEMU_IMG_PROG" ]; then + if [ -x "$build_iotests/qemu-img" ]; then + export QEMU_IMG_PROG="$build_iotests/qemu-img" + elif [ -x "$build_root/qemu-img" ]; then + export QEMU_IMG_PROG="$build_root/qemu-img" + else + _init_error "qemu-img not found" + fi +fi +export QEMU_IMG_PROG=$(realpath -- "$(type -p "$QEMU_IMG_PROG")") + +if [ -z "$QEMU_IO_PROG" ]; then + if [ -x "$build_iotests/qemu-io" ]; then + export QEMU_IO_PROG="$build_iotests/qemu-io" + elif [ -x "$build_root/qemu-io" ]; then + export QEMU_IO_PROG="$build_root/qemu-io" + else + _init_error "qemu-io not found" + fi +fi +export QEMU_IO_PROG=$(realpath -- "$(type -p "$QEMU_IO_PROG")") -if [ "$IMGPROTO" = "nbd" ] ; then - [ "$QEMU_NBD" = "" ] && _fatal "qemu-nbd not found" +if [ -z $QEMU_NBD_PROG ]; then + if [ -x "$build_iotests/qemu-nbd" ]; then + export QEMU_NBD_PROG="$build_iotests/qemu-nbd" + elif [ -x "$build_root/qemu-nbd" ]; then + export QEMU_NBD_PROG="$build_root/qemu-nbd" + else + _init_error "qemu-nbd not found" + fi +fi +export QEMU_NBD_PROG=$(realpath -- "$(type -p "$QEMU_NBD_PROG")") + +if [ -z "$QEMU_VXHS_PROG" ]; then + export QEMU_VXHS_PROG="`set_prog_path qnio_server`" +fi + +if [ -x "$build_iotests/socket_scm_helper" ] +then + export SOCKET_SCM_HELPER="$build_iotests/socket_scm_helper" fi diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.config +++ b/tests/qemu-iotests/common.config @@ -XXX,XX +XXX,XX @@ export LANG=C PATH=".:$PATH" HOSTOS=`uname -s` +arch=`uname -m` export PWD=`pwd` @@ -XXX,XX +XXX,XX @@ export _QEMU_HANDLE=0 # make sure we have a standard umask umask 022 -# $1 = prog to look for, $2* = default pathnames if not found in $PATH -set_prog_path() -{ - p=`command -v $1 2> /dev/null` - if [ -n "$p" -a -x "$p" ]; then - echo $p - return 0 - fi - p=$1 - - shift - for f; do - if [ -x $f ]; then - echo $f - return 0 - fi - done - - echo "" - return 1 -} - _optstr_add() { if [ -n "$1" ]; then @@ -XXX,XX +XXX,XX @@ _optstr_add() fi } -_fatal() -{ - echo "$*" - status=1 - exit 1 -} - -if [ -z "$QEMU_PROG" ]; then - export QEMU_PROG="`set_prog_path qemu`" -fi - -if [ -z "$QEMU_IMG_PROG" ]; then - export QEMU_IMG_PROG="`set_prog_path qemu-img`" -fi - -if [ -z "$QEMU_IO_PROG" ]; then - export QEMU_IO_PROG="`set_prog_path qemu-io`" -fi - -if [ -z "$QEMU_NBD_PROG" ]; then - export QEMU_NBD_PROG="`set_prog_path qemu-nbd`" -fi - -if [ -z "$QEMU_VXHS_PROG" ]; then - export QEMU_VXHS_PROG="`set_prog_path qnio_server`" -fi - -export QEMU_PROG=$(realpath -- "$(type -p "$QEMU_PROG")") -export QEMU_IMG_PROG=$(realpath -- "$(type -p "$QEMU_IMG_PROG")") -export QEMU_IO_PROG=$(realpath -- "$(type -p "$QEMU_IO_PROG")") -export QEMU_NBD_PROG=$(realpath -- "$(type -p "$QEMU_NBD_PROG")") - -# This program is not built as part of qemu but (possibly) provided by the -# system, so it may not be present at all -if [ -n "$QEMU_VXHS_PROG" ]; then - export QEMU_VXHS_PROG=$(realpath -- "$(type -p "$QEMU_VXHS_PROG")") -fi - _qemu_wrapper() { ( -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> These are never used by "check", with one exception that does not need $QEMU_OPTIONS. Keep them in common.rc, which will be soon included only by the tests. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/039.out | 10 +++--- tests/qemu-iotests/061.out | 4 +-- tests/qemu-iotests/137.out | 2 +- tests/qemu-iotests/common.config | 69 ++-------------------------------------- tests/qemu-iotests/common.rc | 65 +++++++++++++++++++++++++++++++++++++ 5 files changed, 75 insertions(+), 75 deletions(-) diff --git a/tests/qemu-iotests/039.out b/tests/qemu-iotests/039.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/039.out +++ b/tests/qemu-iotests/039.out @@ -XXX,XX +XXX,XX @@ No errors were found on the image. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; @@ -XXX,XX +XXX,XX @@ read 512/512 bytes at offset 0 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; @@ -XXX,XX +XXX,XX @@ incompatible_features 0x0 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; @@ -XXX,XX +XXX,XX @@ No errors were found on the image. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; @@ -XXX,XX +XXX,XX @@ Data may be corrupted, or further writes to the image may corrupt it. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; diff --git a/tests/qemu-iotests/061.out b/tests/qemu-iotests/061.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/061.out +++ b/tests/qemu-iotests/061.out @@ -XXX,XX +XXX,XX @@ No errors were found on the image. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 wrote 131072/131072 bytes at offset 0 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; @@ -XXX,XX +XXX,XX @@ No errors were found on the image. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 wrote 131072/131072 bytes at offset 0 128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; diff --git a/tests/qemu-iotests/137.out b/tests/qemu-iotests/137.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/137.out +++ b/tests/qemu-iotests/137.out @@ -XXX,XX +XXX,XX @@ Cache clean interval too big Unsupported value 'blubb' for qcow2 option 'overlap-check'. Allowed are any of the following: none, constant, cached, all wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -./common.config: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then +./common.rc: Killed ( if [ "${VALGRIND_QEMU}" == "y" ]; then exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; else exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@"; diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.config +++ b/tests/qemu-iotests/common.config @@ -XXX,XX +XXX,XX @@ _optstr_add() fi } -_qemu_wrapper() -{ - ( - if [ -n "${QEMU_NEED_PID}" ]; then - echo $BASHPID > "${QEMU_TEST_DIR}/qemu-${_QEMU_HANDLE}.pid" - fi - exec "$QEMU_PROG" $QEMU_OPTIONS "$@" - ) -} - -_qemu_img_wrapper() -{ - (exec "$QEMU_IMG_PROG" $QEMU_IMG_OPTIONS "$@") -} - -_qemu_io_wrapper() -{ - local VALGRIND_LOGFILE="${TEST_DIR}"/$$.valgrind - local QEMU_IO_ARGS="$QEMU_IO_OPTIONS" - if [ "$IMGOPTSSYNTAX" = "true" ]; then - QEMU_IO_ARGS="--image-opts $QEMU_IO_ARGS" - if [ -n "$IMGKEYSECRET" ]; then - QEMU_IO_ARGS="--object secret,id=keysec0,data=$IMGKEYSECRET $QEMU_IO_ARGS" - fi - fi - local RETVAL - ( - if [ "${VALGRIND_QEMU}" == "y" ]; then - exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" - else - exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" - fi - ) - RETVAL=$? - if [ "${VALGRIND_QEMU}" == "y" ]; then - if [ $RETVAL == 99 ]; then - cat "${VALGRIND_LOGFILE}" - fi - rm -f "${VALGRIND_LOGFILE}" - fi - (exit $RETVAL) -} - -_qemu_nbd_wrapper() -{ - ( - echo $BASHPID > "${QEMU_TEST_DIR}/qemu-nbd.pid" - exec "$QEMU_NBD_PROG" $QEMU_NBD_OPTIONS "$@" - ) -} - -_qemu_vxhs_wrapper() -{ - ( - echo $BASHPID > "${TEST_DIR}/qemu-vxhs.pid" - exec "$QEMU_VXHS_PROG" $QEMU_VXHS_OPTIONS "$@" - ) -} - -export QEMU=_qemu_wrapper -export QEMU_IMG=_qemu_img_wrapper -export QEMU_IO=_qemu_io_wrapper -export QEMU_NBD=_qemu_nbd_wrapper -export QEMU_VXHS=_qemu_vxhs_wrapper - QEMU_IMG_EXTRA_ARGS= if [ "$IMGOPTSSYNTAX" = "true" ]; then QEMU_IMG_EXTRA_ARGS="--image-opts $QEMU_IMG_EXTRA_ARGS" @@ -XXX,XX +XXX,XX @@ fi export QEMU_IMG_EXTRA_ARGS -default_machine=$($QEMU -machine help | sed -n '/(default)/ s/ .*//p') -default_alias_machine=$($QEMU -machine help | \ +default_machine=$($QEMU_PROG -machine help | sed -n '/(default)/ s/ .*//p') +default_alias_machine=$($QEMU_PROG -machine help | \ sed -n "/(alias of $default_machine)/ { s/ .*//p; q; }") if [[ "$default_alias_machine" ]]; then default_machine="$default_alias_machine" diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ then fi fi +_qemu_wrapper() +{ + ( + if [ -n "${QEMU_NEED_PID}" ]; then + echo $BASHPID > "${QEMU_TEST_DIR}/qemu-${_QEMU_HANDLE}.pid" + fi + exec "$QEMU_PROG" $QEMU_OPTIONS "$@" + ) +} + +_qemu_img_wrapper() +{ + (exec "$QEMU_IMG_PROG" $QEMU_IMG_OPTIONS "$@") +} + +_qemu_io_wrapper() +{ + local VALGRIND_LOGFILE="${TEST_DIR}"/$$.valgrind + local QEMU_IO_ARGS="$QEMU_IO_OPTIONS" + if [ "$IMGOPTSSYNTAX" = "true" ]; then + QEMU_IO_ARGS="--image-opts $QEMU_IO_ARGS" + if [ -n "$IMGKEYSECRET" ]; then + QEMU_IO_ARGS="--object secret,id=keysec0,data=$IMGKEYSECRET $QEMU_IO_ARGS" + fi + fi + local RETVAL + ( + if [ "${VALGRIND_QEMU}" == "y" ]; then + exec valgrind --log-file="${VALGRIND_LOGFILE}" --error-exitcode=99 "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" + else + exec "$QEMU_IO_PROG" $QEMU_IO_ARGS "$@" + fi + ) + RETVAL=$? + if [ "${VALGRIND_QEMU}" == "y" ]; then + if [ $RETVAL == 99 ]; then + cat "${VALGRIND_LOGFILE}" + fi + rm -f "${VALGRIND_LOGFILE}" + fi + (exit $RETVAL) +} + +_qemu_nbd_wrapper() +{ + ( + echo $BASHPID > "${QEMU_TEST_DIR}/qemu-nbd.pid" + exec "$QEMU_NBD_PROG" $QEMU_NBD_OPTIONS "$@" + ) +} + +_qemu_vxhs_wrapper() +{ + ( + echo $BASHPID > "${TEST_DIR}/qemu-vxhs.pid" + exec "$QEMU_VXHS_PROG" $QEMU_VXHS_OPTIONS "$@" + ) +} + +export QEMU=_qemu_wrapper +export QEMU_IMG=_qemu_img_wrapper +export QEMU_IO=_qemu_io_wrapper +export QEMU_NBD=_qemu_nbd_wrapper +export QEMU_VXHS=_qemu_vxhs_wrapper + if [ "$IMGOPTSSYNTAX" = "true" ]; then DRIVER="driver=$IMGFMT" if [ "$IMGFMT" = "luks" ]; then -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> It only provides functions used by the test programs. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 6 ------ tests/qemu-iotests/common.rc | 13 +++++-------- 2 files changed, 5 insertions(+), 14 deletions(-) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ then _init_error "failed to source common.config" fi -# we need common.rc -if ! . "$source_iotests/common.rc" -then - _init_error "failed to source common.rc" -fi - # we need common . "$source_iotests/common" diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ poke_file() printf "$3" | dd "of=$1" bs=1 "seek=$2" conv=notrunc &>/dev/null } -# we need common.config -if [ "$iam" != "check" ] -then - if ! . ./common.config - then - echo "$iam: failed to source common.config" - exit 1 - fi + +if ! . ./common.config + then + echo "$iam: failed to source common.config" + exit 1 fi _qemu_wrapper() -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> Split "check" parts from tests part. For the directory setup, the actual computation of directories goes in "check", while the sanity checks go in the tests. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/common | 24 ++++++++++++++++++++ tests/qemu-iotests/common.config | 49 ---------------------------------------- tests/qemu-iotests/common.qemu | 1 + tests/qemu-iotests/common.rc | 25 ++++++++++++++++++++ 4 files changed, 50 insertions(+), 49 deletions(-) diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common +++ b/tests/qemu-iotests/common @@ -XXX,XX +XXX,XX @@ set_prog_path() fi } +if [ -z "$TEST_DIR" ]; then + TEST_DIR=`pwd`/scratch +fi + +if [ ! -e "$TEST_DIR" ]; then + mkdir "$TEST_DIR" +fi + diff="diff -u" verbose=false debug=false @@ -XXX,XX +XXX,XX @@ if [ "$IMGFMT" == "luks" ] && ! (echo "$IMGOPTS" | grep "iter-time=" > /dev/null IMGOPTS=$(_optstr_add "$IMGOPTS" "iter-time=10") fi +if [ -z "$SAMPLE_IMG_DIR" ]; then + SAMPLE_IMG_DIR="$source_iotests/sample_images" +fi + +export TEST_DIR +export SAMPLE_IMG_DIR + if [ -s $tmp.list ] then # found some valid test numbers ... this is good @@ -XXX,XX +XXX,XX @@ if [ -x "$build_iotests/socket_scm_helper" ] then export SOCKET_SCM_HELPER="$build_iotests/socket_scm_helper" fi + +default_machine=$($QEMU_PROG -machine help | sed -n '/(default)/ s/ .*//p') +default_alias_machine=$($QEMU_PROG -machine help | \ + sed -n "/(alias of $default_machine)/ { s/ .*//p; q; }") +if [[ "$default_alias_machine" ]]; then + default_machine="$default_alias_machine" +fi + +export QEMU_DEFAULT_MACHINE="$default_machine" diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.config +++ b/tests/qemu-iotests/common.config @@ -XXX,XX +XXX,XX @@ arch=`uname -m` export PWD=`pwd` -export _QEMU_HANDLE=0 - # make sure we have a standard umask umask 022 @@ -XXX,XX +XXX,XX @@ _optstr_add() fi } -QEMU_IMG_EXTRA_ARGS= -if [ "$IMGOPTSSYNTAX" = "true" ]; then - QEMU_IMG_EXTRA_ARGS="--image-opts $QEMU_IMG_EXTRA_ARGS" - if [ -n "$IMGKEYSECRET" ]; then - QEMU_IMG_EXTRA_ARGS="--object secret,id=keysec0,data=$IMGKEYSECRET $QEMU_IMG_EXTRA_ARGS" - fi -fi -export QEMU_IMG_EXTRA_ARGS - - -default_machine=$($QEMU_PROG -machine help | sed -n '/(default)/ s/ .*//p') -default_alias_machine=$($QEMU_PROG -machine help | \ - sed -n "/(alias of $default_machine)/ { s/ .*//p; q; }") -if [[ "$default_alias_machine" ]]; then - default_machine="$default_alias_machine" -fi - -export QEMU_DEFAULT_MACHINE="$default_machine" - -if [ -z "$TEST_DIR" ]; then - TEST_DIR=`pwd`/scratch -fi - -QEMU_TEST_DIR="${TEST_DIR}" - -if [ ! -e "$TEST_DIR" ]; then - mkdir "$TEST_DIR" -fi - -if [ ! -d "$TEST_DIR" ]; then - echo "common.config: Error: \$TEST_DIR ($TEST_DIR) is not a directory" - exit 1 -fi - -export TEST_DIR - -if [ -z "$SAMPLE_IMG_DIR" ]; then - SAMPLE_IMG_DIR="$source_iotests/sample_images" -fi - -if [ ! -d "$SAMPLE_IMG_DIR" ]; then - echo "common.config: Error: \$SAMPLE_IMG_DIR ($SAMPLE_IMG_DIR) is not a directory" - exit 1 -fi - -export SAMPLE_IMG_DIR - # make sure this script returns success true diff --git a/tests/qemu-iotests/common.qemu b/tests/qemu-iotests/common.qemu index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.qemu +++ b/tests/qemu-iotests/common.qemu @@ -XXX,XX +XXX,XX @@ QEMU_FIFO_IN="${QEMU_TEST_DIR}/qmp-in-$$" QEMU_FIFO_OUT="${QEMU_TEST_DIR}/qmp-out-$$" QEMU_HANDLE=0 +export _QEMU_HANDLE=0 # If bash version is >= 4.1, these will be overwritten and dynamic # file descriptor values assigned. diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ export QEMU_VXHS=_qemu_vxhs_wrapper if [ "$IMGOPTSSYNTAX" = "true" ]; then DRIVER="driver=$IMGFMT" + QEMU_IMG_EXTRA_ARGS="--image-opts $QEMU_IMG_EXTRA_ARGS" + if [ -n "$IMGKEYSECRET" ]; then + QEMU_IMG_EXTRA_ARGS="--object secret,id=keysec0,data=$IMGKEYSECRET $QEMU_IMG_EXTRA_ARGS" + fi if [ "$IMGFMT" = "luks" ]; then DRIVER="$DRIVER,key-secret=keysec0" fi @@ -XXX,XX +XXX,XX @@ if [ "$IMGOPTSSYNTAX" = "true" ]; then TEST_IMG="$DRIVER,file.driver=$IMGPROTO,file.filename=$TEST_DIR/t.$IMGFMT" fi else + QEMU_IMG_EXTRA_ARGS= if [ "$IMGPROTO" = "file" ]; then TEST_IMG=$TEST_DIR/t.$IMGFMT elif [ "$IMGPROTO" = "nbd" ]; then @@ -XXX,XX +XXX,XX @@ else fi ORIG_TEST_IMG="$TEST_IMG" +if [ -z "$TEST_DIR" ]; then + TEST_DIR=`pwd`/scratch +fi + +QEMU_TEST_DIR="${TEST_DIR}" + +if [ ! -e "$TEST_DIR" ]; then + mkdir "$TEST_DIR" +fi + +if [ ! -d "$TEST_DIR" ]; then + echo "common.config: Error: \$TEST_DIR ($TEST_DIR) is not a directory" + exit 1 +fi + +if [ ! -d "$SAMPLE_IMG_DIR" ]; then + echo "common.config: Error: \$SAMPLE_IMG_DIR ($SAMPLE_IMG_DIR) is not a directory" + exit 1 +fi + _use_sample_img() { SAMPLE_IMG_FILE="${1%\.bz2}" -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> The variable is used in "common" but defined only after the file is sourced. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 2 -- tests/qemu-iotests/common | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ fi TIMESTAMP_FILE=check.time-$IMGPROTO-$IMGFMT -tmp="${TEST_DIR}"/$$ - _wallclock() { date "+%H %M %S" | awk '{ print $1*3600 + $2*60 + $3 }' diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common +++ b/tests/qemu-iotests/common @@ -XXX,XX +XXX,XX @@ sortme=false expunge=true have_test_arg=false cachemode=false + +tmp="${TEST_DIR}"/$$ rm -f $tmp.list $tmp.tmp $tmp.sed export IMGFMT=raw -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> The variable is almost unused, and one of the two uses is actually uninitialized. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 5 +---- tests/qemu-iotests/common.rc | 2 +- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ interrupt=true # by default don't output timestamps timestamp=${TIMESTAMP:=false} -# generic initialization -iam=check - _init_error() { - echo "$iam: $1" >&2 + echo "check: $1" >&2 exit 1 } diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ poke_file() if ! . ./common.config then - echo "$iam: failed to source common.config" + echo "$0: failed to source common.config" exit 1 fi -- 2.13.6 From: Paolo Bonzini <pbonzini@redhat.com> "check" is full of qemu-iotests--specific details. Separating it from "common" does not make much sense anymore. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 533 +++++++++++++++++++++++++++++++++++++++++++- tests/qemu-iotests/common | 552 ---------------------------------------------- 2 files changed, 531 insertions(+), 554 deletions(-) delete mode 100644 tests/qemu-iotests/common diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ then _init_error "failed to source common.config" fi -# we need common -. "$source_iotests/common" +_full_imgfmt_details() +{ + if [ -n "$IMGOPTS" ]; then + echo "$IMGFMT ($IMGOPTS)" + else + echo "$IMGFMT" + fi +} + +_full_platform_details() +{ + os=`uname -s` + host=`hostname -s` + kernel=`uname -r` + platform=`uname -m` + echo "$os/$platform $host $kernel" +} + +# $1 = prog to look for +set_prog_path() +{ + p=`command -v $1 2> /dev/null` + if [ -n "$p" -a -x "$p" ]; then + realpath -- "$(type -p "$p")" + else + return 1 + fi +} + +if [ -z "$TEST_DIR" ]; then + TEST_DIR=`pwd`/scratch +fi + +if [ ! -e "$TEST_DIR" ]; then + mkdir "$TEST_DIR" +fi + +diff="diff -u" +verbose=false +debug=false +group=false +xgroup=false +imgopts=false +showme=false +sortme=false +expunge=true +have_test_arg=false +cachemode=false + +tmp="${TEST_DIR}"/$$ +rm -f $tmp.list $tmp.tmp $tmp.sed + +export IMGFMT=raw +export IMGFMT_GENERIC=true +export IMGPROTO=file +export IMGOPTS="" +export CACHEMODE="writeback" +export QEMU_IO_OPTIONS="" +export QEMU_IO_OPTIONS_NO_FMT="" +export CACHEMODE_IS_DEFAULT=true +export QEMU_OPTIONS="-nodefaults -machine accel=qtest" +export VALGRIND_QEMU= +export IMGKEYSECRET= +export IMGOPTSSYNTAX=false + +for r +do + + if $group + then + # arg after -g + group_list=`sed -n <"$source_iotests/group" -e 's/$/ /' -e "/^[0-9][0-9][0-9].* $r /"'{ +s/ .*//p +}'` + if [ -z "$group_list" ] + then + echo "Group \"$r\" is empty or not defined?" + exit 1 + fi + [ ! -s $tmp.list ] && touch $tmp.list + for t in $group_list + do + if grep -s "^$t\$" $tmp.list >/dev/null + then + : + else + echo "$t" >>$tmp.list + fi + done + group=false + continue + + elif $xgroup + then + # arg after -x + # Populate $tmp.list with all tests + awk '/^[0-9]{3,}/ {print $1}' "${source_iotests}/group" > $tmp.list 2>/dev/null + group_list=`sed -n <"$source_iotests/group" -e 's/$/ /' -e "/^[0-9][0-9][0-9].* $r /"'{ +s/ .*//p +}'` + if [ -z "$group_list" ] + then + echo "Group \"$r\" is empty or not defined?" + exit 1 + fi + numsed=0 + rm -f $tmp.sed + for t in $group_list + do + if [ $numsed -gt 100 ] + then + sed -f $tmp.sed <$tmp.list >$tmp.tmp + mv $tmp.tmp $tmp.list + numsed=0 + rm -f $tmp.sed + fi + echo "/^$t\$/d" >>$tmp.sed + numsed=`expr $numsed + 1` + done + sed -f $tmp.sed <$tmp.list >$tmp.tmp + mv $tmp.tmp $tmp.list + xgroup=false + continue + + elif $imgopts + then + IMGOPTS="$r" + imgopts=false + continue + elif $cachemode + then + CACHEMODE="$r" + CACHEMODE_IS_DEFAULT=false + cachemode=false + continue + fi + + xpand=true + case "$r" + in + + -\? | -h | --help) # usage + echo "Usage: $0 [options] [testlist]"' + +common options + -v verbose + -d debug + +image format options + -raw test raw (default) + -bochs test bochs + -cloop test cloop + -parallels test parallels + -qcow test qcow + -qcow2 test qcow2 + -qed test qed + -vdi test vdi + -vpc test vpc + -vhdx test vhdx + -vmdk test vmdk + -luks test luks + +image protocol options + -file test file (default) + -rbd test rbd + -sheepdog test sheepdog + -nbd test nbd + -ssh test ssh + -nfs test nfs + -vxhs test vxhs + +other options + -xdiff graphical mode diff + -nocache use O_DIRECT on backing file + -misalign misalign memory allocations + -n show me, do not run tests + -o options -o options to pass to qemu-img create/convert + -T output timestamps + -c mode cache mode + +testlist options + -g group[,group...] include tests from these groups + -x group[,group...] exclude tests from these groups + NNN include test NNN + NNN-NNN include test range (eg. 012-021) +' + exit 0 + ;; + + -raw) + IMGFMT=raw + xpand=false + ;; + + -bochs) + IMGFMT=bochs + IMGFMT_GENERIC=false + xpand=false + ;; + + -cloop) + IMGFMT=cloop + IMGFMT_GENERIC=false + xpand=false + ;; + + -parallels) + IMGFMT=parallels + IMGFMT_GENERIC=false + xpand=false + ;; + + -qcow) + IMGFMT=qcow + xpand=false + ;; + + -qcow2) + IMGFMT=qcow2 + xpand=false + ;; + + -luks) + IMGOPTSSYNTAX=true + IMGFMT=luks + IMGKEYSECRET=123456 + xpand=false + ;; + + -qed) + IMGFMT=qed + xpand=false + ;; + + -vdi) + IMGFMT=vdi + xpand=false + ;; + + -vmdk) + IMGFMT=vmdk + xpand=false + ;; + + -vpc) + IMGFMT=vpc + xpand=false + ;; + + -vhdx) + IMGFMT=vhdx + xpand=false + ;; + + -file) + IMGPROTO=file + xpand=false + ;; + + -rbd) + IMGPROTO=rbd + xpand=false + ;; + + -sheepdog) + IMGPROTO=sheepdog + xpand=false + ;; + + -nbd) + IMGPROTO=nbd + xpand=false + ;; + + -vxhs) + IMGPROTO=vxhs + xpand=false + ;; + + -ssh) + IMGPROTO=ssh + xpand=false + ;; + + -nfs) + IMGPROTO=nfs + xpand=false + ;; + + -nocache) + CACHEMODE="none" + CACHEMODE_IS_DEFAULT=false + xpand=false + ;; + + -misalign) + QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS --misalign" + xpand=false + ;; + + -valgrind) + VALGRIND_QEMU='y' + xpand=false + ;; + + -g) # -g group ... pick from group file + group=true + xpand=false + ;; + + -xdiff) # graphical diff mode + xpand=false + + if [ ! -z "$DISPLAY" ] + then + command -v xdiff >/dev/null 2>&1 && diff=xdiff + command -v gdiff >/dev/null 2>&1 && diff=gdiff + command -v tkdiff >/dev/null 2>&1 && diff=tkdiff + command -v xxdiff >/dev/null 2>&1 && diff=xxdiff + fi + ;; + + -n) # show me, don't do it + showme=true + xpand=false + ;; + -o) + imgopts=true + xpand=false + ;; + -c) + cachemode=true + xpand=false + ;; + -T) # turn on timestamp output + timestamp=true + xpand=false + ;; + + -v) + verbose=true + xpand=false + ;; + -d) + debug=true + xpand=false + ;; + -x) # -x group ... exclude from group file + xgroup=true + xpand=false + ;; + '[0-9][0-9][0-9] [0-9][0-9][0-9][0-9]') + echo "No tests?" + status=1 + exit $status + ;; + + [0-9]*-[0-9]*) + eval `echo $r | sed -e 's/^/start=/' -e 's/-/ end=/'` + ;; + + [0-9]*-) + eval `echo $r | sed -e 's/^/start=/' -e 's/-//'` + end=`echo [0-9][0-9][0-9] [0-9][0-9][0-9][0-9] | sed -e 's/\[0-9]//g' -e 's/ *$//' -e 's/.* //'` + if [ -z "$end" ] + then + echo "No tests in range \"$r\"?" + status=1 + exit $status + fi + ;; + + *) + start=$r + end=$r + ;; + + esac + + # get rid of leading 0s as can be interpreted as octal + start=`echo $start | sed 's/^0*//'` + end=`echo $end | sed 's/^0*//'` + + if $xpand + then + have_test_arg=true + awk </dev/null ' +BEGIN { for (t='$start'; t<='$end'; t++) printf "%03d\n",t }' \ + | while read id + do + if grep -s "^$id " "$source_iotests/group" >/dev/null + then + # in group file ... OK + echo $id >>$tmp.list + else + if [ -f expunged ] && $expunge && egrep "^$id([ ]|\$)" expunged >/dev/null + then + # expunged ... will be reported, but not run, later + echo $id >>$tmp.list + else + # oops + if [ "$start" == "$end" -a "$id" == "$end" ] + then + echo "$id - unknown test" + exit 1 + else + echo "$id - unknown test, ignored" + fi + fi + fi + done || exit 1 + fi + +done + +# Set qemu-io cache mode with $CACHEMODE we have +QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS --cache $CACHEMODE" + +QEMU_IO_OPTIONS_NO_FMT="$QEMU_IO_OPTIONS" +if [ "$IMGOPTSSYNTAX" != "true" ]; then + QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS -f $IMGFMT" +fi + +# Set default options for qemu-img create -o if they were not specified +if [ "$IMGFMT" == "qcow2" ] && ! (echo "$IMGOPTS" | grep "compat=" > /dev/null); then + IMGOPTS=$(_optstr_add "$IMGOPTS" "compat=1.1") +fi +if [ "$IMGFMT" == "luks" ] && ! (echo "$IMGOPTS" | grep "iter-time=" > /dev/null); then + IMGOPTS=$(_optstr_add "$IMGOPTS" "iter-time=10") +fi + +if [ -z "$SAMPLE_IMG_DIR" ]; then + SAMPLE_IMG_DIR="$source_iotests/sample_images" +fi + +export TEST_DIR +export SAMPLE_IMG_DIR + +if [ -s $tmp.list ] +then + # found some valid test numbers ... this is good + : +else + if $have_test_arg + then + # had test numbers, but none in group file ... do nothing + touch $tmp.list + else + # no test numbers, do everything from group file + sed -n -e '/^[0-9][0-9][0-9]*/s/[ ].*//p' <"$source_iotests/group" >$tmp.list + fi +fi + +# should be sort -n, but this did not work for Linux when this +# was ported from IRIX +# +list=`sort $tmp.list` +rm -f $tmp.list $tmp.tmp $tmp.sed + +if [ -z "$QEMU_PROG" ] +then + if [ -x "$build_iotests/qemu" ]; then + export QEMU_PROG="$build_iotests/qemu" + elif [ -x "$build_root/$arch-softmmu/qemu-system-$arch" ]; then + export QEMU_PROG="$build_root/$arch-softmmu/qemu-system-$arch" + else + pushd "$build_root" > /dev/null + for binary in *-softmmu/qemu-system-* + do + if [ -x "$binary" ] + then + export QEMU_PROG="$build_root/$binary" + break + fi + done + popd > /dev/null + [ "$QEMU_PROG" = "" ] && _init_error "qemu not found" + fi +fi +export QEMU_PROG=$(realpath -- "$(type -p "$QEMU_PROG")") + +if [ -z "$QEMU_IMG_PROG" ]; then + if [ -x "$build_iotests/qemu-img" ]; then + export QEMU_IMG_PROG="$build_iotests/qemu-img" + elif [ -x "$build_root/qemu-img" ]; then + export QEMU_IMG_PROG="$build_root/qemu-img" + else + _init_error "qemu-img not found" + fi +fi +export QEMU_IMG_PROG=$(realpath -- "$(type -p "$QEMU_IMG_PROG")") + +if [ -z "$QEMU_IO_PROG" ]; then + if [ -x "$build_iotests/qemu-io" ]; then + export QEMU_IO_PROG="$build_iotests/qemu-io" + elif [ -x "$build_root/qemu-io" ]; then + export QEMU_IO_PROG="$build_root/qemu-io" + else + _init_error "qemu-io not found" + fi +fi +export QEMU_IO_PROG=$(realpath -- "$(type -p "$QEMU_IO_PROG")") + +if [ -z $QEMU_NBD_PROG ]; then + if [ -x "$build_iotests/qemu-nbd" ]; then + export QEMU_NBD_PROG="$build_iotests/qemu-nbd" + elif [ -x "$build_root/qemu-nbd" ]; then + export QEMU_NBD_PROG="$build_root/qemu-nbd" + else + _init_error "qemu-nbd not found" + fi +fi +export QEMU_NBD_PROG=$(realpath -- "$(type -p "$QEMU_NBD_PROG")") + +if [ -z "$QEMU_VXHS_PROG" ]; then + export QEMU_VXHS_PROG="`set_prog_path qnio_server`" +fi + +if [ -x "$build_iotests/socket_scm_helper" ] +then + export SOCKET_SCM_HELPER="$build_iotests/socket_scm_helper" +fi + +default_machine=$($QEMU_PROG -machine help | sed -n '/(default)/ s/ .*//p') +default_alias_machine=$($QEMU_PROG -machine help | \ + sed -n "/(alias of $default_machine)/ { s/ .*//p; q; }") +if [[ "$default_alias_machine" ]]; then + default_machine="$default_alias_machine" +fi + +export QEMU_DEFAULT_MACHINE="$default_machine" TIMESTAMP_FILE=check.time-$IMGPROTO-$IMGFMT diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/tests/qemu-iotests/common +++ /dev/null @@ -XXX,XX +XXX,XX @@ -#!/bin/bash -# -# Copyright (C) 2009 Red Hat, Inc. -# Copyright (c) 2000-2005 Silicon Graphics, Inc. All Rights Reserved. -# -# 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. -# -# This program is distributed in the hope that it would 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/>. -# -# -# common procedures for QA scripts -# - -_full_imgfmt_details() -{ - if [ -n "$IMGOPTS" ]; then - echo "$IMGFMT ($IMGOPTS)" - else - echo "$IMGFMT" - fi -} - -_full_platform_details() -{ - os=`uname -s` - host=`hostname -s` - kernel=`uname -r` - platform=`uname -m` - echo "$os/$platform $host $kernel" -} - -# $1 = prog to look for -set_prog_path() -{ - p=`command -v $1 2> /dev/null` - if [ -n "$p" -a -x "$p" ]; then - realpath -- "$(type -p "$p")" - else - return 1 - fi -} - -if [ -z "$TEST_DIR" ]; then - TEST_DIR=`pwd`/scratch -fi - -if [ ! -e "$TEST_DIR" ]; then - mkdir "$TEST_DIR" -fi - -diff="diff -u" -verbose=false -debug=false -group=false -xgroup=false -imgopts=false -showme=false -sortme=false -expunge=true -have_test_arg=false -cachemode=false - -tmp="${TEST_DIR}"/$$ -rm -f $tmp.list $tmp.tmp $tmp.sed - -export IMGFMT=raw -export IMGFMT_GENERIC=true -export IMGPROTO=file -export IMGOPTS="" -export CACHEMODE="writeback" -export QEMU_IO_OPTIONS="" -export QEMU_IO_OPTIONS_NO_FMT="" -export CACHEMODE_IS_DEFAULT=true -export QEMU_OPTIONS="-nodefaults -machine accel=qtest" -export VALGRIND_QEMU= -export IMGKEYSECRET= -export IMGOPTSSYNTAX=false - -for r -do - - if $group - then - # arg after -g - group_list=`sed -n <"$source_iotests/group" -e 's/$/ /' -e "/^[0-9][0-9][0-9].* $r /"'{ -s/ .*//p -}'` - if [ -z "$group_list" ] - then - echo "Group \"$r\" is empty or not defined?" - exit 1 - fi - [ ! -s $tmp.list ] && touch $tmp.list - for t in $group_list - do - if grep -s "^$t\$" $tmp.list >/dev/null - then - : - else - echo "$t" >>$tmp.list - fi - done - group=false - continue - - elif $xgroup - then - # arg after -x - # Populate $tmp.list with all tests - awk '/^[0-9]{3,}/ {print $1}' "${source_iotests}/group" > $tmp.list 2>/dev/null - group_list=`sed -n <"$source_iotests/group" -e 's/$/ /' -e "/^[0-9][0-9][0-9].* $r /"'{ -s/ .*//p -}'` - if [ -z "$group_list" ] - then - echo "Group \"$r\" is empty or not defined?" - exit 1 - fi - numsed=0 - rm -f $tmp.sed - for t in $group_list - do - if [ $numsed -gt 100 ] - then - sed -f $tmp.sed <$tmp.list >$tmp.tmp - mv $tmp.tmp $tmp.list - numsed=0 - rm -f $tmp.sed - fi - echo "/^$t\$/d" >>$tmp.sed - numsed=`expr $numsed + 1` - done - sed -f $tmp.sed <$tmp.list >$tmp.tmp - mv $tmp.tmp $tmp.list - xgroup=false - continue - - elif $imgopts - then - IMGOPTS="$r" - imgopts=false - continue - elif $cachemode - then - CACHEMODE="$r" - CACHEMODE_IS_DEFAULT=false - cachemode=false - continue - fi - - xpand=true - case "$r" - in - - -\? | -h | --help) # usage - echo "Usage: $0 [options] [testlist]"' - -common options - -v verbose - -d debug - -image format options - -raw test raw (default) - -bochs test bochs - -cloop test cloop - -parallels test parallels - -qcow test qcow - -qcow2 test qcow2 - -qed test qed - -vdi test vdi - -vpc test vpc - -vhdx test vhdx - -vmdk test vmdk - -luks test luks - -image protocol options - -file test file (default) - -rbd test rbd - -sheepdog test sheepdog - -nbd test nbd - -ssh test ssh - -nfs test nfs - -vxhs test vxhs - -other options - -xdiff graphical mode diff - -nocache use O_DIRECT on backing file - -misalign misalign memory allocations - -n show me, do not run tests - -o options -o options to pass to qemu-img create/convert - -T output timestamps - -c mode cache mode - -testlist options - -g group[,group...] include tests from these groups - -x group[,group...] exclude tests from these groups - NNN include test NNN - NNN-NNN include test range (eg. 012-021) -' - exit 0 - ;; - - -raw) - IMGFMT=raw - xpand=false - ;; - - -bochs) - IMGFMT=bochs - IMGFMT_GENERIC=false - xpand=false - ;; - - -cloop) - IMGFMT=cloop - IMGFMT_GENERIC=false - xpand=false - ;; - - -parallels) - IMGFMT=parallels - IMGFMT_GENERIC=false - xpand=false - ;; - - -qcow) - IMGFMT=qcow - xpand=false - ;; - - -qcow2) - IMGFMT=qcow2 - xpand=false - ;; - - -luks) - IMGOPTSSYNTAX=true - IMGFMT=luks - IMGKEYSECRET=123456 - xpand=false - ;; - - -qed) - IMGFMT=qed - xpand=false - ;; - - -vdi) - IMGFMT=vdi - xpand=false - ;; - - -vmdk) - IMGFMT=vmdk - xpand=false - ;; - - -vpc) - IMGFMT=vpc - xpand=false - ;; - - -vhdx) - IMGFMT=vhdx - xpand=false - ;; - - -file) - IMGPROTO=file - xpand=false - ;; - - -rbd) - IMGPROTO=rbd - xpand=false - ;; - - -sheepdog) - IMGPROTO=sheepdog - xpand=false - ;; - - -nbd) - IMGPROTO=nbd - xpand=false - ;; - - -vxhs) - IMGPROTO=vxhs - xpand=false - ;; - - -ssh) - IMGPROTO=ssh - xpand=false - ;; - - -nfs) - IMGPROTO=nfs - xpand=false - ;; - - -nocache) - CACHEMODE="none" - CACHEMODE_IS_DEFAULT=false - xpand=false - ;; - - -misalign) - QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS --misalign" - xpand=false - ;; - - -valgrind) - VALGRIND_QEMU='y' - xpand=false - ;; - - -g) # -g group ... pick from group file - group=true - xpand=false - ;; - - -xdiff) # graphical diff mode - xpand=false - - if [ ! -z "$DISPLAY" ] - then - command -v xdiff >/dev/null 2>&1 && diff=xdiff - command -v gdiff >/dev/null 2>&1 && diff=gdiff - command -v tkdiff >/dev/null 2>&1 && diff=tkdiff - command -v xxdiff >/dev/null 2>&1 && diff=xxdiff - fi - ;; - - -n) # show me, don't do it - showme=true - xpand=false - ;; - -o) - imgopts=true - xpand=false - ;; - -c) - cachemode=true - xpand=false - ;; - -T) # turn on timestamp output - timestamp=true - xpand=false - ;; - - -v) - verbose=true - xpand=false - ;; - -d) - debug=true - xpand=false - ;; - -x) # -x group ... exclude from group file - xgroup=true - xpand=false - ;; - '[0-9][0-9][0-9] [0-9][0-9][0-9][0-9]') - echo "No tests?" - status=1 - exit $status - ;; - - [0-9]*-[0-9]*) - eval `echo $r | sed -e 's/^/start=/' -e 's/-/ end=/'` - ;; - - [0-9]*-) - eval `echo $r | sed -e 's/^/start=/' -e 's/-//'` - end=`echo [0-9][0-9][0-9] [0-9][0-9][0-9][0-9] | sed -e 's/\[0-9]//g' -e 's/ *$//' -e 's/.* //'` - if [ -z "$end" ] - then - echo "No tests in range \"$r\"?" - status=1 - exit $status - fi - ;; - - *) - start=$r - end=$r - ;; - - esac - - # get rid of leading 0s as can be interpreted as octal - start=`echo $start | sed 's/^0*//'` - end=`echo $end | sed 's/^0*//'` - - if $xpand - then - have_test_arg=true - awk </dev/null ' -BEGIN { for (t='$start'; t<='$end'; t++) printf "%03d\n",t }' \ - | while read id - do - if grep -s "^$id " "$source_iotests/group" >/dev/null - then - # in group file ... OK - echo $id >>$tmp.list - else - if [ -f expunged ] && $expunge && egrep "^$id([ ]|\$)" expunged >/dev/null - then - # expunged ... will be reported, but not run, later - echo $id >>$tmp.list - else - # oops - if [ "$start" == "$end" -a "$id" == "$end" ] - then - echo "$id - unknown test" - exit 1 - else - echo "$id - unknown test, ignored" - fi - fi - fi - done || exit 1 - fi - -done - -# Set qemu-io cache mode with $CACHEMODE we have -QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS --cache $CACHEMODE" - -QEMU_IO_OPTIONS_NO_FMT="$QEMU_IO_OPTIONS" -if [ "$IMGOPTSSYNTAX" != "true" ]; then - QEMU_IO_OPTIONS="$QEMU_IO_OPTIONS -f $IMGFMT" -fi - -# Set default options for qemu-img create -o if they were not specified -if [ "$IMGFMT" == "qcow2" ] && ! (echo "$IMGOPTS" | grep "compat=" > /dev/null); then - IMGOPTS=$(_optstr_add "$IMGOPTS" "compat=1.1") -fi -if [ "$IMGFMT" == "luks" ] && ! (echo "$IMGOPTS" | grep "iter-time=" > /dev/null); then - IMGOPTS=$(_optstr_add "$IMGOPTS" "iter-time=10") -fi - -if [ -z "$SAMPLE_IMG_DIR" ]; then - SAMPLE_IMG_DIR="$source_iotests/sample_images" -fi - -export TEST_DIR -export SAMPLE_IMG_DIR - -if [ -s $tmp.list ] -then - # found some valid test numbers ... this is good - : -else - if $have_test_arg - then - # had test numbers, but none in group file ... do nothing - touch $tmp.list - else - # no test numbers, do everything from group file - sed -n -e '/^[0-9][0-9][0-9]*/s/[ ].*//p' <"$source_iotests/group" >$tmp.list - fi -fi - -# should be sort -n, but this did not work for Linux when this -# was ported from IRIX -# -list=`sort $tmp.list` -rm -f $tmp.list $tmp.tmp $tmp.sed - -if [ -z "$QEMU_PROG" ] -then - if [ -x "$build_iotests/qemu" ]; then - export QEMU_PROG="$build_iotests/qemu" - elif [ -x "$build_root/$arch-softmmu/qemu-system-$arch" ]; then - export QEMU_PROG="$build_root/$arch-softmmu/qemu-system-$arch" - else - pushd "$build_root" > /dev/null - for binary in *-softmmu/qemu-system-* - do - if [ -x "$binary" ] - then - export QEMU_PROG="$build_root/$binary" - break - fi - done - popd > /dev/null - [ "$QEMU_PROG" = "" ] && _init_error "qemu not found" - fi -fi -export QEMU_PROG=$(realpath -- "$(type -p "$QEMU_PROG")") - -if [ -z "$QEMU_IMG_PROG" ]; then - if [ -x "$build_iotests/qemu-img" ]; then - export QEMU_IMG_PROG="$build_iotests/qemu-img" - elif [ -x "$build_root/qemu-img" ]; then - export QEMU_IMG_PROG="$build_root/qemu-img" - else - _init_error "qemu-img not found" - fi -fi -export QEMU_IMG_PROG=$(realpath -- "$(type -p "$QEMU_IMG_PROG")") - -if [ -z "$QEMU_IO_PROG" ]; then - if [ -x "$build_iotests/qemu-io" ]; then - export QEMU_IO_PROG="$build_iotests/qemu-io" - elif [ -x "$build_root/qemu-io" ]; then - export QEMU_IO_PROG="$build_root/qemu-io" - else - _init_error "qemu-io not found" - fi -fi -export QEMU_IO_PROG=$(realpath -- "$(type -p "$QEMU_IO_PROG")") - -if [ -z $QEMU_NBD_PROG ]; then - if [ -x "$build_iotests/qemu-nbd" ]; then - export QEMU_NBD_PROG="$build_iotests/qemu-nbd" - elif [ -x "$build_root/qemu-nbd" ]; then - export QEMU_NBD_PROG="$build_root/qemu-nbd" - else - _init_error "qemu-nbd not found" - fi -fi -export QEMU_NBD_PROG=$(realpath -- "$(type -p "$QEMU_NBD_PROG")") - -if [ -z "$QEMU_VXHS_PROG" ]; then - export QEMU_VXHS_PROG="`set_prog_path qnio_server`" -fi - -if [ -x "$build_iotests/socket_scm_helper" ] -then - export SOCKET_SCM_HELPER="$build_iotests/socket_scm_helper" -fi - -default_machine=$($QEMU_PROG -machine help | sed -n '/(default)/ s/ .*//p') -default_alias_machine=$($QEMU_PROG -machine help | \ - sed -n "/(alias of $default_machine)/ { s/ .*//p; q; }") -if [[ "$default_alias_machine" ]]; then - default_machine="$default_alias_machine" -fi - -export QEMU_DEFAULT_MACHINE="$default_machine" -- 2.13.6 There is no good reason for bdrv_drop_intermediate() to know the active layer above the subchain it is operating on - even more so, because the assumption that there is a single active layer above it is not generally true. In order to prepare removal of the active parameter, use a BdrvChildRole callback to update the backing file string in the overlay image instead of directly calling bdrv_change_backing_file(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- include/block/block_int.h | 6 ++++++ block.c | 33 ++++++++++++++++++++++++++++----- 2 files changed, 34 insertions(+), 5 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 BdrvChildRole { void (*attach)(BdrvChild *child); void (*detach)(BdrvChild *child); + + /* Notifies the parent that the filename of its child has changed (e.g. + * because the direct child was removed from the backing chain), so that it + * can update its reference. */ + int (*update_filename)(BdrvChild *child, BlockDriverState *new_base, + const char *filename, Error **errp); }; extern const BdrvChildRole child_file; 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_backing_options(int *child_flags, QDict *child_options, *child_flags = flags; } +static int bdrv_backing_update_filename(BdrvChild *c, BlockDriverState *base, + const char *filename, Error **errp) +{ + BlockDriverState *parent = c->opaque; + int ret; + + ret = bdrv_change_backing_file(parent, filename, + base->drv ? base->drv->format_name : ""); + if (ret < 0) { + error_setg_errno(errp, ret, "Could not update backing file link"); + } + + return ret; +} + const BdrvChildRole child_backing = { .get_parent_desc = bdrv_child_get_parent_desc, .attach = bdrv_backing_attach, @@ -XXX,XX +XXX,XX @@ const BdrvChildRole child_backing = { .drained_begin = bdrv_child_cb_drained_begin, .drained_end = bdrv_child_cb_drained_end, .inactivate = bdrv_child_cb_inactivate, + .update_filename = bdrv_backing_update_filename, }; static int bdrv_open_flags(BlockDriverState *bs, int flags) @@ -XXX,XX +XXX,XX @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, Error *local_err = NULL; int ret = -EIO; + bdrv_ref(top); + if (!top->drv || !base->drv) { goto exit; } @@ -XXX,XX +XXX,XX @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, } /* success - we can delete the intermediate states, and link top->base */ - backing_file_str = backing_file_str ? backing_file_str : base->filename; - ret = bdrv_change_backing_file(new_top_bs, backing_file_str, - base->drv ? base->drv->format_name : ""); - if (ret) { - goto exit; + if (new_top_bs->backing->role->update_filename) { + backing_file_str = backing_file_str ? backing_file_str : base->filename; + ret = new_top_bs->backing->role->update_filename(new_top_bs->backing, + base, backing_file_str, + &local_err); + if (ret < 0) { + bdrv_set_backing_hd(new_top_bs, top, &error_abort); + goto exit; + } } bdrv_set_backing_hd(new_top_bs, base, &local_err); @@ -XXX,XX +XXX,XX @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, ret = 0; exit: + bdrv_unref(top); return ret; } -- 2.13.6 This changes the commit block job to support operation in a graph where there is more than a single active layer that references the top node. This involves inserting the commit filter node not only on the path between the given active node and the top node, but between the top node and all of its parents. On completion, bdrv_drop_intermediate() must consider all parents for updating the backing file link. These parents may be backing files themselves and as such read-only; reopen them temporarily if necessary. Previously this was achieved by the bdrv_reopen() calls in the commit block job that made overlay_bs read-write for the whole duration of the block job, even though write access is only needed on completion. Now that we consider all parents, overlay_bs is meaningless. It is left in place in this commit, but we'll remove it soon. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 68 ++++++++++++++++++++++++++++++++++------------------------ block/commit.c | 2 +- 2 files changed, 41 insertions(+), 29 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_backing_update_filename(BdrvChild *c, BlockDriverState *base, const char *filename, Error **errp) { BlockDriverState *parent = c->opaque; + int orig_flags = bdrv_get_flags(parent); int ret; + if (!(orig_flags & BDRV_O_RDWR)) { + ret = bdrv_reopen(parent, orig_flags | BDRV_O_RDWR, errp); + if (ret < 0) { + return ret; + } + } + ret = bdrv_change_backing_file(parent, filename, base->drv ? base->drv->format_name : ""); if (ret < 0) { error_setg_errno(errp, ret, "Could not update backing file link"); } + if (!(orig_flags & BDRV_O_RDWR)) { + bdrv_reopen(parent, orig_flags, NULL); + } + return ret; } @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_find_base(BlockDriverState *bs) int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, BlockDriverState *base, const char *backing_file_str) { - BlockDriverState *new_top_bs = NULL; + BdrvChild *c, *next; Error *local_err = NULL; int ret = -EIO; @@ -XXX,XX +XXX,XX @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, goto exit; } - new_top_bs = bdrv_find_overlay(active, top); - - if (new_top_bs == NULL) { - /* we could not find the image above 'top', this is an error */ - goto exit; - } - - /* special case of new_top_bs->backing->bs already pointing to base - nothing - * to do, no intermediate images */ - if (backing_bs(new_top_bs) == base) { - ret = 0; - goto exit; - } - /* Make sure that base is in the backing chain of top */ if (!bdrv_chain_contains(top, base)) { goto exit; } /* success - we can delete the intermediate states, and link top->base */ - if (new_top_bs->backing->role->update_filename) { - backing_file_str = backing_file_str ? backing_file_str : base->filename; - ret = new_top_bs->backing->role->update_filename(new_top_bs->backing, - base, backing_file_str, - &local_err); - if (ret < 0) { - bdrv_set_backing_hd(new_top_bs, top, &error_abort); + backing_file_str = backing_file_str ? backing_file_str : base->filename; + + QLIST_FOREACH_SAFE(c, &top->parents, next_parent, next) { + /* Check whether we are allowed to switch c from top to base */ + GSList *ignore_children = g_slist_prepend(NULL, c); + bdrv_check_update_perm(base, NULL, c->perm, c->shared_perm, + ignore_children, &local_err); + if (local_err) { + ret = -EPERM; + error_report_err(local_err); goto exit; } - } + g_slist_free(ignore_children); - bdrv_set_backing_hd(new_top_bs, base, &local_err); - if (local_err) { - ret = -EPERM; - error_report_err(local_err); - goto exit; + /* If so, update the backing file path in the image file */ + if (c->role->update_filename) { + ret = c->role->update_filename(c, base, backing_file_str, + &local_err); + if (ret < 0) { + bdrv_abort_perm_update(base); + error_report_err(local_err); + goto exit; + } + } + + /* Do the actual switch in the in-memory graph. + * Completes bdrv_check_update_perm() transaction internally. */ + bdrv_ref(base); + bdrv_replace_child(c, base); + bdrv_unref(top); } ret = 0; 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 @@ void commit_start(const char *job_id, BlockDriverState *bs, error_propagate(errp, local_err); goto fail; } - bdrv_set_backing_hd(overlay_bs, commit_top_bs, &local_err); + bdrv_replace_node(top, commit_top_bs, &local_err); if (local_err) { bdrv_unref(commit_top_bs); commit_top_bs = NULL; -- 2.13.6 QMP responses to certain commands can become quite long, which doesn't only make reading them hard, but also means that the maximum line length in patch emails can be exceeded. Allow tests to switch to QMP pretty printing, which results in more, but shorter lines. We also need to make sure to keep indentation in the response for this to work as expected. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- tests/qemu-iotests/common.qemu | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/common.qemu b/tests/qemu-iotests/common.qemu index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.qemu +++ b/tests/qemu-iotests/common.qemu @@ -XXX,XX +XXX,XX @@ function _timed_wait_for() shift QEMU_STATUS[$h]=0 - while read -t ${QEMU_COMM_TIMEOUT} resp <&${QEMU_OUT[$h]} + while IFS= read -t ${QEMU_COMM_TIMEOUT} resp <&${QEMU_OUT[$h]} do if [ -z "${silent}" ]; then echo "${resp}" | _filter_testdir | _filter_qemu \ | _filter_qemu_io | _filter_qmp | _filter_hmp fi - grep -q "${*}" < <(echo ${resp}) + grep -q "${*}" < <(echo "${resp}") if [ $? -eq 0 ]; then return fi @@ -XXX,XX +XXX,XX @@ function _send_qemu_cmd() # $qemu_comm_method: set this variable to 'monitor' (case insensitive) # to use the QEMU HMP monitor for communication. # Otherwise, the default of QMP is used. +# $qmp_pretty: Set this variable to 'y' to enable QMP pretty printing. # $keep_stderr: Set this variable to 'y' to keep QEMU's stderr output on stderr. # If this variable is empty, stderr will be redirected to stdout. # Returns: @@ -XXX,XX +XXX,XX @@ function _launch_qemu() comm="-monitor stdio" else local qemu_comm_method="qmp" - comm="-monitor none -qmp stdio" + if [ "$qmp_pretty" = "y" ]; then + comm="-monitor none -qmp-pretty stdio" + else + comm="-monitor none -qmp stdio" + fi fi fifo_out=${QEMU_FIFO_OUT}_${_QEMU_HANDLE} @@ -XXX,XX +XXX,XX @@ function _launch_qemu() then # Don't print response, since it has version information in it silent=yes _timed_wait_for ${_QEMU_HANDLE} "capabilities" + if [ "$qmp_pretty" = "y" ]; then + silent=yes _timed_wait_for ${_QEMU_HANDLE} "^}" + fi fi QEMU_HANDLE=${_QEMU_HANDLE} let _QEMU_HANDLE++ -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/191 | 153 +++++++++ tests/qemu-iotests/191.out | 827 +++++++++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 981 insertions(+) create mode 100755 tests/qemu-iotests/191 create mode 100644 tests/qemu-iotests/191.out diff --git a/tests/qemu-iotests/191 b/tests/qemu-iotests/191 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/191 @@ -XXX,XX +XXX,XX @@ +#!/bin/bash +# +# Test commit block job where top has two parents +# +# 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=kwolf@redhat.com + +seq=`basename $0` +echo "QA output created by $seq" + +here=`pwd` +status=1 # failure is the default! + +MIG_SOCKET="${TEST_DIR}/migrate" + +_cleanup() +{ + rm -f "${TEST_IMG}.mid" + rm -f "${TEST_IMG}.ovl2" + rm -f "${TEST_IMG}.ovl3" + _cleanup_test_img + _cleanup_qemu +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter +. ./common.qemu + +_supported_fmt qcow2 +_unsupported_imgopts compat=0.10 +_supported_proto file +_supported_os Linux + +size=64M + +echo +echo === Preparing and starting VM === +echo + +TEST_IMG="${TEST_IMG}.base" _make_test_img $size +TEST_IMG="${TEST_IMG}.mid" _make_test_img -b "${TEST_IMG}.base" +_make_test_img -b "${TEST_IMG}.mid" +TEST_IMG="${TEST_IMG}.ovl2" _make_test_img -b "${TEST_IMG}.mid" + +$QEMU_IO -c 'write -P 0x55 1M 64k' "${TEST_IMG}.mid" | _filter_qemu_io + +qemu_comm_method="qmp" +qmp_pretty="y" + +_launch_qemu \ + -blockdev "driver=${IMGFMT},file.driver=file,file.filename=${TEST_IMG}.base,node-name=base" \ + -blockdev "driver=${IMGFMT},file.driver=file,file.filename=${TEST_IMG}.mid,node-name=mid,backing=base" \ + -blockdev "driver=${IMGFMT},file.driver=file,file.filename=${TEST_IMG},node-name=top,backing=mid" \ + -blockdev "driver=${IMGFMT},file.driver=file,file.filename=${TEST_IMG}.ovl2,node-name=top2,backing=mid" +h=$QEMU_HANDLE +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" '^}' + +echo +echo === Perform commit job === +echo + +_send_qemu_cmd $h \ + "{ 'execute': 'block-commit', + 'arguments': { 'job-id': 'commit0', + 'device': 'top', + 'base':'$TEST_IMG.base', + 'top': '$TEST_IMG.mid' } }" \ + "BLOCK_JOB_COMPLETED" +_send_qemu_cmd $h "" "^}" + +echo +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 + +_send_qemu_cmd $h "{ 'execute': 'quit' }" "^}" +wait=1 _cleanup_qemu + +_img_info +TEST_IMG="$TEST_IMG.ovl2" _img_info + + +echo +echo === Preparing and starting VM with -drive === +echo + +TEST_IMG="${TEST_IMG}.base" _make_test_img $size +TEST_IMG="${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" +TEST_IMG="${TEST_IMG}.ovl3" _make_test_img -b "${TEST_IMG}.ovl2" + +$QEMU_IO -c 'write -P 0x55 1M 64k' "${TEST_IMG}.mid" | _filter_qemu_io + +qemu_comm_method="qmp" +qmp_pretty="y" + +_launch_qemu \ + -drive "driver=${IMGFMT},file=${TEST_IMG},node-name=top,backing.node-name=mid" \ + -drive "driver=${IMGFMT},file=${TEST_IMG}.ovl3,node-name=top2,backing.backing=mid" +h=$QEMU_HANDLE +_send_qemu_cmd $h "{ 'execute': 'qmp_capabilities' }" '^}' + +echo +echo === Perform commit job === +echo + +_send_qemu_cmd $h \ + "{ 'execute': 'block-commit', + 'arguments': { 'job-id': 'commit0', + 'device': 'top', + 'base':'$TEST_IMG.base', + 'top': '$TEST_IMG.mid' } }" \ + "BLOCK_JOB_COMPLETED" +_send_qemu_cmd $h "" "^}" + +echo +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 + +_send_qemu_cmd $h "{ 'execute': 'quit' }" "^}" +wait=1 _cleanup_qemu + +_img_info +TEST_IMG="$TEST_IMG.ovl2" _img_info + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/191.out b/tests/qemu-iotests/191.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ 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', 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 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +{ + "return": { + } +} + +=== Perform commit job === + +{ + "return": { + } +} +{ + "timestamp": { + "seconds": TIMESTAMP, + "microseconds": TIMESTAMP + }, + "event": "BLOCK_JOB_COMPLETED", + "data": { + "device": "commit0", + "len": 67108864, + "offset": 67108864, + "speed": 0, + "type": "commit" + } +} + +=== Check that both top and top2 point to base now === + +{ + "return": [ + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "backing-image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "backing-filename-format": "qcow2", + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.ovl2", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 200704, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "full-backing-filename": "TEST_DIR/t.qcow2.base", + "backing-filename": "TEST_DIR/t.qcow2.base", + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "top2", + "backing_file_depth": 1, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "backing_file": "TEST_DIR/t.qcow2.base", + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.ovl2", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 197120, + "filename": "TEST_DIR/t.qcow2.ovl2", + "format": "file", + "actual-size": 200704, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.ovl2", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "backing-image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "backing-filename-format": "qcow2", + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 200704, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "full-backing-filename": "TEST_DIR/t.qcow2.base", + "backing-filename": "TEST_DIR/t.qcow2.base", + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "top", + "backing_file_depth": 1, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "backing_file": "TEST_DIR/t.qcow2.base", + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 197120, + "filename": "TEST_DIR/t.qcow2", + "format": "file", + "actual-size": 200704, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "backing-image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "backing-filename-format": "qcow2", + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.mid", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "full-backing-filename": "TEST_DIR/t.qcow2.base", + "backing-filename": "TEST_DIR/t.qcow2.base", + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "mid", + "backing_file_depth": 1, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "backing_file": "TEST_DIR/t.qcow2.base", + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.mid", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 393216, + "filename": "TEST_DIR/t.qcow2.mid", + "format": "file", + "actual-size": 397312, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.mid", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "base", + "backing_file_depth": 0, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.base", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 393216, + "filename": "TEST_DIR/t.qcow2.base", + "format": "file", + "actual-size": 397312, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.base", + "encryption_key_missing": false + } + ] +} +{ + "return": { + } +} +{ + "timestamp": { + "seconds": TIMESTAMP, + "microseconds": TIMESTAMP + }, + "event": "SHUTDOWN", + "data": { + "guest": false + } +} +image: TEST_DIR/t.IMGFMT +file format: IMGFMT +virtual size: 64M (67108864 bytes) +cluster_size: 65536 +backing file: TEST_DIR/t.IMGFMT.base +backing file format: IMGFMT +image: TEST_DIR/t.IMGFMT.ovl2 +file format: IMGFMT +virtual size: 64M (67108864 bytes) +cluster_size: 65536 +backing file: TEST_DIR/t.IMGFMT.base +backing file format: IMGFMT + +=== Preparing and starting VM with -drive === + +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', 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 +Formatting 'TEST_DIR/t.IMGFMT.ovl3', fmt=IMGFMT size=67108864 backing_file=TEST_DIR/t.IMGFMT.ovl2 +wrote 65536/65536 bytes at offset 1048576 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +{ + "return": { + } +} + +=== Perform commit job === + +{ + "return": { + } +} +{ + "timestamp": { + "seconds": TIMESTAMP, + "microseconds": TIMESTAMP + }, + "event": "BLOCK_JOB_COMPLETED", + "data": { + "device": "commit0", + "len": 67108864, + "offset": 67108864, + "speed": 0, + "type": "commit" + } +} + +=== Check that both top and top2 point to base now === + +{ + "return": [ + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "backing-image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "backing-filename-format": "qcow2", + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.ovl2", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 200704, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "full-backing-filename": "TEST_DIR/t.qcow2.base", + "backing-filename": "TEST_DIR/t.qcow2.base", + "dirty-flag": false + }, + "iops_wr": 0, + "ro": true, + "node-name": "NODE_NAME", + "backing_file_depth": 1, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "backing_file": "TEST_DIR/t.qcow2.base", + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.ovl2", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 197120, + "filename": "TEST_DIR/t.qcow2.ovl2", + "format": "file", + "actual-size": 200704, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": true, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.ovl2", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "backing-image": { + "backing-image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "backing-filename-format": "qcow2", + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.ovl2", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 200704, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "full-backing-filename": "TEST_DIR/t.qcow2.base", + "backing-filename": "TEST_DIR/t.qcow2.base", + "dirty-flag": false + }, + "backing-filename-format": "qcow2", + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.ovl3", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 200704, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "full-backing-filename": "TEST_DIR/t.qcow2.ovl2", + "backing-filename": "TEST_DIR/t.qcow2.ovl2", + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "top2", + "backing_file_depth": 2, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "backing_file": "TEST_DIR/t.qcow2.ovl2", + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.ovl3", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 197120, + "filename": "TEST_DIR/t.qcow2.ovl3", + "format": "file", + "actual-size": 200704, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.ovl3", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": true, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.base", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 393216, + "filename": "TEST_DIR/t.qcow2.base", + "format": "file", + "actual-size": 397312, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": true, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2.base", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "backing-image": { + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2.base", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 397312, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "dirty-flag": false + }, + "backing-filename-format": "qcow2", + "virtual-size": 67108864, + "filename": "TEST_DIR/t.qcow2", + "cluster-size": 65536, + "format": "qcow2", + "actual-size": 200704, + "format-specific": { + "type": "qcow2", + "data": { + "compat": "1.1", + "lazy-refcounts": false, + "refcount-bits": 16, + "corrupt": false + } + }, + "full-backing-filename": "TEST_DIR/t.qcow2.base", + "backing-filename": "TEST_DIR/t.qcow2.base", + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "top", + "backing_file_depth": 1, + "drv": "qcow2", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "backing_file": "TEST_DIR/t.qcow2.base", + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2", + "encryption_key_missing": false + }, + { + "iops_rd": 0, + "detect_zeroes": "off", + "image": { + "virtual-size": 197120, + "filename": "TEST_DIR/t.qcow2", + "format": "file", + "actual-size": 200704, + "dirty-flag": false + }, + "iops_wr": 0, + "ro": false, + "node-name": "NODE_NAME", + "backing_file_depth": 0, + "drv": "file", + "iops": 0, + "bps_wr": 0, + "write_threshold": 0, + "encrypted": false, + "bps": 0, + "bps_rd": 0, + "cache": { + "no-flush": false, + "direct": false, + "writeback": true + }, + "file": "TEST_DIR/t.qcow2", + "encryption_key_missing": false + } + ] +} +{ + "return": { + } +} +{ + "timestamp": { + "seconds": TIMESTAMP, + "microseconds": TIMESTAMP + }, + "event": "SHUTDOWN", + "data": { + "guest": false + } +} +image: TEST_DIR/t.IMGFMT +file format: IMGFMT +virtual size: 64M (67108864 bytes) +cluster_size: 65536 +backing file: TEST_DIR/t.IMGFMT.base +backing file format: IMGFMT +image: TEST_DIR/t.IMGFMT.ovl2 +file format: IMGFMT +virtual size: 64M (67108864 bytes) +cluster_size: 65536 +backing file: TEST_DIR/t.IMGFMT.base +backing file format: IMGFMT +*** 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 @@ 188 rw auto quick 189 rw auto 190 rw auto quick +191 rw auto 192 rw auto quick 194 rw auto migration quick 195 rw auto quick -- 2.13.6 We don't need to make any assumptions about the graph layout above the top node of the commit operation any more. Remove the use of bdrv_find_overlay() and related variables from the commit job code. bdrv_drop_intermediate() doesn't use the 'active' parameter any more, so we can just drop it. The overlay node was previously added to the block job to get a BLK_PERM_GRAPH_MOD. We really need to respect those permissions in bdrv_drop_intermediate() now, but as long as we haven't figured out yet how BLK_PERM_GRAPH_MOD is actually supposed to work, just leave a TODO comment there. With this change, it is now possible to perform another block job on an overlay node without conflicts. qemu-iotests 030 is changed accordingly. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- include/block/block.h | 3 +-- block.c | 6 +++-- block/commit.c | 62 ++++++++++++-------------------------------------- tests/qemu-iotests/030 | 4 ---- 4 files changed, 20 insertions(+), 55 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_commit(BlockDriverState *bs); int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file, const char *backing_fmt); void bdrv_register(BlockDriver *bdrv); -int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, - BlockDriverState *base, +int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, const char *backing_file_str); BlockDriverState *bdrv_find_overlay(BlockDriverState *active, BlockDriverState *bs); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_find_base(BlockDriverState *bs) * if active == top, that is considered an error * */ -int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, - BlockDriverState *base, const char *backing_file_str) +int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, + const char *backing_file_str) { BdrvChild *c, *next; Error *local_err = NULL; @@ -XXX,XX +XXX,XX @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top, } /* success - we can delete the intermediate states, and link top->base */ + /* TODO Check graph modification op blockers (BLK_PERM_GRAPH_MOD) once + * we've figured out how they should work. */ backing_file_str = backing_file_str ? backing_file_str : base->filename; QLIST_FOREACH_SAFE(c, &top->parents, next_parent, next) { 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 @@ enum { typedef struct CommitBlockJob { BlockJob common; RateLimit limit; - BlockDriverState *active; BlockDriverState *commit_top_bs; BlockBackend *top; BlockBackend *base; BlockdevOnError on_error; int base_flags; - int orig_overlay_flags; char *backing_file_str; } CommitBlockJob; @@ -XXX,XX +XXX,XX @@ static void commit_complete(BlockJob *job, void *opaque) { CommitBlockJob *s = container_of(job, CommitBlockJob, common); CommitCompleteData *data = opaque; - BlockDriverState *active = s->active; BlockDriverState *top = blk_bs(s->top); BlockDriverState *base = blk_bs(s->base); - BlockDriverState *overlay_bs = bdrv_find_overlay(active, s->commit_top_bs); + BlockDriverState *commit_top_bs = s->commit_top_bs; int ret = data->ret; bool remove_commit_top_bs = false; - /* Make sure overlay_bs and top stay around until bdrv_set_backing_hd() */ + /* Make sure commit_top_bs and top stay around until bdrv_replace_node() */ bdrv_ref(top); - if (overlay_bs) { - bdrv_ref(overlay_bs); - } + bdrv_ref(commit_top_bs); /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before * the normal backing chain can be restored. */ @@ -XXX,XX +XXX,XX @@ static void commit_complete(BlockJob *job, void *opaque) if (!block_job_is_cancelled(&s->common) && ret == 0) { /* success */ - ret = bdrv_drop_intermediate(active, s->commit_top_bs, base, + ret = bdrv_drop_intermediate(s->commit_top_bs, base, s->backing_file_str); - } else if (overlay_bs) { + } else { /* XXX Can (or should) we somehow keep 'consistent read' blocked even * after the failed/cancelled commit job is gone? If we already wrote * something to base, the intermediate images aren't valid any more. */ @@ -XXX,XX +XXX,XX @@ static void commit_complete(BlockJob *job, void *opaque) if (s->base_flags != bdrv_get_flags(base)) { bdrv_reopen(base, s->base_flags, NULL); } - if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) { - bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL); - } g_free(s->backing_file_str); blk_unref(s->top); @@ -XXX,XX +XXX,XX @@ static void commit_complete(BlockJob *job, void *opaque) * filter driver from the backing chain. Do this as the final step so that * the 'consistent read' permission can be granted. */ if (remove_commit_top_bs) { - bdrv_set_backing_hd(overlay_bs, top, &error_abort); + bdrv_child_try_set_perm(commit_top_bs->backing, 0, BLK_PERM_ALL, + &error_abort); + bdrv_replace_node(commit_top_bs, backing_bs(commit_top_bs), + &error_abort); } - bdrv_unref(overlay_bs); + bdrv_unref(commit_top_bs); bdrv_unref(top); } @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, { CommitBlockJob *s; BlockReopenQueue *reopen_queue = NULL; - int orig_overlay_flags; int orig_base_flags; BlockDriverState *iter; - BlockDriverState *overlay_bs; BlockDriverState *commit_top_bs = NULL; Error *local_err = NULL; int ret; @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, return; } - overlay_bs = bdrv_find_overlay(bs, top); - - if (overlay_bs == NULL) { - error_setg(errp, "Could not find overlay image for %s:", top->filename); - return; - } - s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL, speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp); if (!s) { return; } - orig_base_flags = bdrv_get_flags(base); - orig_overlay_flags = bdrv_get_flags(overlay_bs); - - /* convert base & overlay_bs to r/w, if necessary */ + /* convert base to r/w, if necessary */ + orig_base_flags = bdrv_get_flags(base); if (!(orig_base_flags & BDRV_O_RDWR)) { reopen_queue = bdrv_reopen_queue(reopen_queue, base, NULL, orig_base_flags | BDRV_O_RDWR); } - if (!(orig_overlay_flags & BDRV_O_RDWR)) { - reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs, NULL, - orig_overlay_flags | BDRV_O_RDWR); - } + if (reopen_queue) { bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err); if (local_err != NULL) { @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, goto fail; } - /* overlay_bs must be blocked because it needs to be modified to - * update the backing image string. */ - ret = block_job_add_bdrv(&s->common, "overlay of top", overlay_bs, - BLK_PERM_GRAPH_MOD, BLK_PERM_ALL, errp); - if (ret < 0) { - goto fail; - } - s->base = blk_new(BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE | BLK_PERM_RESIZE, @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, goto fail; } - s->active = bs; - - s->base_flags = orig_base_flags; - s->orig_overlay_flags = orig_overlay_flags; - + s->base_flags = orig_base_flags; s->backing_file_str = g_strdup(backing_file_str); - s->on_error = on_error; trace_commit_start(bs, base, top, s); @@ -XXX,XX +XXX,XX @@ fail: blk_unref(s->top); } if (commit_top_bs) { - bdrv_set_backing_hd(overlay_bs, top, &error_abort); + bdrv_replace_node(commit_top_bs, top, &error_abort); } block_job_early_fail(&s->common); } diff --git a/tests/qemu-iotests/030 b/tests/qemu-iotests/030 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/030 +++ b/tests/qemu-iotests/030 @@ -XXX,XX +XXX,XX @@ class TestParallelOps(iotests.QMPTestCase): result = self.vm.qmp('block-stream', device='node6', base=self.imgs[4], job_id='stream-node6-v2') self.assert_qmp(result, 'error/class', 'GenericError') - # This fails because block-commit needs to block node6, the overlay of the 'top' image - result = self.vm.qmp('block-stream', device='node7', base=self.imgs[5], job_id='stream-node6-v3') - self.assert_qmp(result, 'error/class', 'GenericError') - # This fails because block-commit currently blocks the active layer even if it's not used result = self.vm.qmp('block-stream', device='drive0', base=self.imgs[5], job_id='stream-drive0') self.assert_qmp(result, 'error/class', 'GenericError') -- 2.13.6 From: Eric Blake <eblake@redhat.com> Make it easier to enable copy-on-read during iotests, by exposing a new bool option to main and open. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-io.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/qemu-io.c b/qemu-io.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io.c +++ b/qemu-io.c @@ -XXX,XX +XXX,XX @@ static void open_help(void) " Opens a file for subsequent use by all of the other qemu-io commands.\n" " -r, -- open file read-only\n" " -s, -- use snapshot file\n" +" -C, -- use copy-on-read\n" " -n, -- disable host cache, short for -t none\n" " -U, -- force shared permissions\n" " -k, -- use kernel AIO implementation (on Linux only)\n" @@ -XXX,XX +XXX,XX @@ static const cmdinfo_t open_cmd = { .argmin = 1, .argmax = -1, .flags = CMD_NOFILE_OK, - .args = "[-rsnkU] [-t cache] [-d discard] [-o options] [path]", + .args = "[-rsCnkU] [-t cache] [-d discard] [-o options] [path]", .oneline = "open the file specified by path", .help = open_help, }; @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) QDict *opts; bool force_share = false; - while ((c = getopt(argc, argv, "snro:kt:d:U")) != -1) { + while ((c = getopt(argc, argv, "snCro:kt:d:U")) != -1) { switch (c) { case 's': flags |= BDRV_O_SNAPSHOT; @@ -XXX,XX +XXX,XX @@ static int open_f(BlockBackend *blk, int argc, char **argv) flags |= BDRV_O_NOCACHE; writethrough = false; break; + case 'C': + flags |= BDRV_O_COPY_ON_READ; + break; case 'r': readonly = 1; break; @@ -XXX,XX +XXX,XX @@ static void usage(const char *name) " -r, --read-only export read-only\n" " -s, --snapshot use snapshot file\n" " -n, --nocache disable host cache, short for -t none\n" +" -C, --copy-on-read enable copy-on-read\n" " -m, --misalign misalign allocations for O_DIRECT\n" " -k, --native-aio use kernel AIO implementation (on Linux only)\n" " -t, --cache=MODE use the given cache mode for the image\n" @@ -XXX,XX +XXX,XX @@ static QemuOptsList file_opts = { int main(int argc, char **argv) { int readonly = 0; - const char *sopt = "hVc:d:f:rsnmkt:T:U"; + const char *sopt = "hVc:d:f:rsnCmkt:T:U"; const struct option lopt[] = { { "help", no_argument, NULL, 'h' }, { "version", no_argument, NULL, 'V' }, @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) { "read-only", no_argument, NULL, 'r' }, { "snapshot", no_argument, NULL, 's' }, { "nocache", no_argument, NULL, 'n' }, + { "copy-on-read", no_argument, NULL, 'C' }, { "misalign", no_argument, NULL, 'm' }, { "native-aio", no_argument, NULL, 'k' }, { "discard", required_argument, NULL, 'd' }, @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) flags |= BDRV_O_NOCACHE; writethrough = false; break; + case 'C': + flags |= BDRV_O_COPY_ON_READ; + break; case 'd': if (bdrv_parse_discard_flags(optarg, &flags) < 0) { error_report("Invalid discard option: %s", optarg); -- 2.13.6 From: Eric Blake <eblake@redhat.com> Handle a 0-length block status request up front, with a uniform return value claiming the area is not allocated. Most callers don't pass a length of 0 to bdrv_get_block_status() and friends; but it definitely happens with a 0-length read when copy-on-read is enabled. While we could audit all callers to ensure that they never make a 0-length request, and then assert that fact, it was just as easy to fix things to always report success (as long as the callers are careful to not go into an infinite loop). However, we had inconsistent behavior on whether the status is reported as allocated or defers to the backing layer, depending on what callbacks the driver implements, and possibly wasting quite a few CPU cycles to get to that answer. Consistently reporting unallocated up front doesn't really hurt anything, and makes it easier both for callers (0-length requests now have well-defined behavior) and for drivers (drivers don't have to deal with 0-length requests). Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 4 ++++ 1 file changed, 4 insertions(+) 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 int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, *pnum = 0; return BDRV_BLOCK_EOF; } + if (!nb_sectors) { + *pnum = 0; + return 0; + } n = total_sectors - sector_num; if (n < nb_sectors) { -- 2.13.6 From: Eric Blake <eblake@redhat.com> Executing qemu with a terminal as stdin will temporarily alter stty settings on that terminal (for example, disabling echo), because of how we run both the monitor and any multiplexing with guest input. Normally, qemu restores the original settings on exit; but if an iotest triggers qemu to abort in the middle, we can be left with the altered terminal setup. This can make life very annoying when debugging an iotest failure (not everyone remembers the trick of blind-typing 'stty sane' without echo, and some people prefer terminal settings that are slightly different than the defaults picked by 'stty sane'). It is possible to avoid qemu corrupting the terminal by not passing a terminal to qemu's stdin in the first place (as in, use './check ... </dev/null'), but that's extra typing to have to remember. But running 'exec </dev/null' in the harness seems like it might be too heavy of a hammer. So I instead went the the solution of saving and restoring the stty settings, only when the harness detects that it is run interactively. I tested this patch by forcing an allocation failure (I can't guarantee that this particular limit will work on all setups, but it shows the idea): $ (ulimit -S -v 500000; ./check -qcow2 1) Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/check | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ export VALGRIND_QEMU= export IMGKEYSECRET= export IMGOPTSSYNTAX=false +# Save current tty settings, since an aborting qemu call may leave things +# screwed up +STTY_RESTORE= +if test -t 0; then + STTY_RESTORE=$(stty -g) +fi + for r do @@ -XXX,XX +XXX,XX @@ END { if (NR > 0) { needwrap=false fi + if test -n "$STTY_RESTORE"; then + stty $STTY_RESTORE + fi rm -f "${TEST_DIR}"/*.out "${TEST_DIR}"/*.err "${TEST_DIR}"/*.time rm -f "${TEST_DIR}"/check.pid "${TEST_DIR}"/check.sts rm -f $tmp.* -- 2.13.6 From: Eric Blake <eblake@redhat.com> Make it possible to inject errors on writes performed during a read operation due to copy-on-read semantics. Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 5 ++++- block/io.c | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # # @l1_shrink_free_l2_clusters: discard the l2 tables. (since 2.11) # +# @cor_write: a write due to copy-on-read (since 2.11) +# # Since: 2.9 ## { 'enum': 'BlkdebugEvent', 'prefix': 'BLKDBG', @@ -XXX,XX +XXX,XX @@ 'flush_to_disk', 'pwritev_rmw_head', 'pwritev_rmw_after_head', 'pwritev_rmw_tail', 'pwritev_rmw_after_tail', 'pwritev', 'pwritev_zero', 'pwritev_done', 'empty_image_prepare', - 'l1_shrink_write_table', 'l1_shrink_free_l2_clusters' ] } + 'l1_shrink_write_table', 'l1_shrink_free_l2_clusters', + 'cor_write'] } ## # @BlkdebugInjectErrorOptions: 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_do_copy_on_readv(BdrvChild *child, goto err; } + bdrv_debug_event(bs, BLKDBG_COR_WRITE); if (drv->bdrv_co_pwrite_zeroes && buffer_is_zero(bounce_buffer, iov.iov_len)) { /* FIXME: Should we (perhaps conditionally) be setting -- 2.13.6 From: Eric Blake <eblake@redhat.com> Improve our braindead copy-on-read implementation. Pre-patch, we have multiple issues: - we create a bounce buffer and perform a write for the entire request, even if the active image already has 99% of the clusters occupied, and really only needs to copy-on-read the remaining 1% of the clusters - our bounce buffer was as large as the read request, and can needlessly exhaust our memory by using double the memory of the request size (the original request plus our bounce buffer), rather than a capped maximum overhead beyond the original - if a driver has a max_transfer limit, we are bypassing the normal code in bdrv_aligned_preadv() that fragments to that limit, and instead attempt to read the entire buffer from the driver in one go, which some drivers may assert on - a client can request a large request of nearly 2G such that rounding the request out to cluster boundaries results in a byte count larger than 2G. While this cannot exceed 32 bits, it DOES have some follow-on problems: -- the call to bdrv_driver_pread() can assert for exceeding BDRV_REQUEST_MAX_BYTES, if the driver is old and lacks .bdrv_co_preadv -- if the buffer is all zeroes, the subsequent call to bdrv_co_do_pwrite_zeroes is a no-op due to a negative size, which means we did not actually copy on read Fix all of these issues by breaking up the action into a loop, where each iteration is capped to sane limits. Also, querying the allocation status allows us to optimize: when data is already present in the active layer, we don't need to bounce. Note that the code has a telling comment that copy-on-read should probably be a filter driver rather than a bolt-on hack in io.c; but that remains a task for another day. CC: qemu-stable@nongnu.org Signed-off-by: Eric Blake <eblake@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 120 +++++++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 82 insertions(+), 38 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */ +/* Maximum bounce buffer for copy-on-read and write zeroes, in bytes */ +#define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS) + static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, BlockDriver *drv = bs->drv; struct iovec iov; - QEMUIOVector bounce_qiov; + QEMUIOVector local_qiov; int64_t cluster_offset; unsigned int cluster_bytes; size_t skip_bytes; int ret; + int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, + BDRV_REQUEST_MAX_BYTES); + unsigned int progress = 0; /* FIXME We cannot require callers to have write permissions when all they * are doing is a read request. If we did things right, write permissions @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child, // assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE)); /* Cover entire cluster so no additional backing file I/O is required when - * allocating cluster in the image file. + * allocating cluster in the image file. Note that this value may exceed + * BDRV_REQUEST_MAX_BYTES (even when the original read did not), which + * is one reason we loop rather than doing it all at once. */ bdrv_round_to_clusters(bs, offset, bytes, &cluster_offset, &cluster_bytes); + skip_bytes = offset - cluster_offset; trace_bdrv_co_do_copy_on_readv(bs, offset, bytes, cluster_offset, cluster_bytes); - iov.iov_len = cluster_bytes; - iov.iov_base = bounce_buffer = qemu_try_blockalign(bs, iov.iov_len); + bounce_buffer = qemu_try_blockalign(bs, + MIN(MIN(max_transfer, cluster_bytes), + MAX_BOUNCE_BUFFER)); if (bounce_buffer == NULL) { ret = -ENOMEM; goto err; } - qemu_iovec_init_external(&bounce_qiov, &iov, 1); + while (cluster_bytes) { + int64_t pnum; - ret = bdrv_driver_preadv(bs, cluster_offset, cluster_bytes, - &bounce_qiov, 0); - if (ret < 0) { - goto err; - } + ret = bdrv_is_allocated(bs, cluster_offset, + MIN(cluster_bytes, max_transfer), &pnum); + if (ret < 0) { + /* Safe to treat errors in querying allocation as if + * unallocated; we'll probably fail again soon on the + * read, but at least that will set a decent errno. + */ + pnum = MIN(cluster_bytes, max_transfer); + } - bdrv_debug_event(bs, BLKDBG_COR_WRITE); - if (drv->bdrv_co_pwrite_zeroes && - buffer_is_zero(bounce_buffer, iov.iov_len)) { - /* FIXME: Should we (perhaps conditionally) be setting - * BDRV_REQ_MAY_UNMAP, if it will allow for a sparser copy - * that still correctly reads as zero? */ - ret = bdrv_co_do_pwrite_zeroes(bs, cluster_offset, cluster_bytes, 0); - } else { - /* This does not change the data on the disk, it is not necessary - * to flush even in cache=writethrough mode. - */ - ret = bdrv_driver_pwritev(bs, cluster_offset, cluster_bytes, - &bounce_qiov, 0); - } + assert(skip_bytes < pnum); - if (ret < 0) { - /* It might be okay to ignore write errors for guest requests. If this - * is a deliberate copy-on-read then we don't want to ignore the error. - * Simply report it in all cases. - */ - goto err; - } + if (ret <= 0) { + /* Must copy-on-read; use the bounce buffer */ + iov.iov_base = bounce_buffer; + iov.iov_len = pnum = MIN(pnum, MAX_BOUNCE_BUFFER); + qemu_iovec_init_external(&local_qiov, &iov, 1); - skip_bytes = offset - cluster_offset; - qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes, bytes); + ret = bdrv_driver_preadv(bs, cluster_offset, pnum, + &local_qiov, 0); + if (ret < 0) { + goto err; + } + + bdrv_debug_event(bs, BLKDBG_COR_WRITE); + if (drv->bdrv_co_pwrite_zeroes && + buffer_is_zero(bounce_buffer, pnum)) { + /* FIXME: Should we (perhaps conditionally) be setting + * BDRV_REQ_MAY_UNMAP, if it will allow for a sparser copy + * that still correctly reads as zero? */ + ret = bdrv_co_do_pwrite_zeroes(bs, cluster_offset, pnum, 0); + } else { + /* This does not change the data on the disk, it is not + * necessary to flush even in cache=writethrough mode. + */ + ret = bdrv_driver_pwritev(bs, cluster_offset, pnum, + &local_qiov, 0); + } + + if (ret < 0) { + /* It might be okay to ignore write errors for guest + * requests. If this is a deliberate copy-on-read + * then we don't want to ignore the error. Simply + * report it in all cases. + */ + goto err; + } + + qemu_iovec_from_buf(qiov, progress, bounce_buffer + skip_bytes, + pnum - skip_bytes); + } else { + /* Read directly into the destination */ + qemu_iovec_init(&local_qiov, qiov->niov); + qemu_iovec_concat(&local_qiov, qiov, progress, pnum - skip_bytes); + ret = bdrv_driver_preadv(bs, offset + progress, local_qiov.size, + &local_qiov, 0); + qemu_iovec_destroy(&local_qiov); + if (ret < 0) { + goto err; + } + } + + cluster_offset += pnum; + cluster_bytes -= pnum; + progress += pnum - skip_bytes; + skip_bytes = 0; + } + ret = 0; err: qemu_vfree(bounce_buffer); @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_readv(BdrvChild *child, int64_t sector_num, return bdrv_co_do_readv(child, sector_num, nb_sectors, qiov, 0); } -/* Maximum buffer for write zeroes fallback, in bytes */ -#define MAX_WRITE_ZEROES_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS) - static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int max_write_zeroes = MIN_NON_ZERO(bs->bl.max_pwrite_zeroes, INT_MAX); int alignment = MAX(bs->bl.pwrite_zeroes_alignment, bs->bl.request_alignment); - int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, - MAX_WRITE_ZEROES_BOUNCE_BUFFER); + int max_transfer = MIN_NON_ZERO(bs->bl.max_transfer, MAX_BOUNCE_BUFFER); assert(alignment % bs->bl.request_alignment == 0); head = offset % alignment; -- 2.13.6 From: Eric Blake <eblake@redhat.com> Add a test for qcow2 copy-on-read behavior, including exposure for the just-fixed bugs. The copy-on-read behavior is always to a qcow2 image, but the test is careful to allow running with most image protocol/format combos as the backing file being copied from (luks being the exception, as it is harder to pass the right secret to all the right places). In fact, for './check nbd', this appears to be the first time we've had a qcow2 image wrapping NBD, requiring an additional line in _filter_img_create to match the similar line in _filter_img_info. Invoking blkdebug to prove we don't write too much took some effort to get working; and it requires that $TEST_WRAP (based on $TEST_DIR) not be subject to word splitting. We may decide later to have the entire iotests suite use relative rather than absolute names, to avoid problems inherited by the absolute name of $PWD or $TEST_DIR, at which point the sanity check in this commit could be simplified. This test requires at least 2G of consecutive memory to succeed; as such, it is prone to spurious failures, particularly on 32-bit machines under load. This situation is detected and triggers an early exit to skip the test, rather than a failure. To manually provoke this setup on a beefier machine, I used: $ (ulimit -S -v 1000000; ./check -qcow2 197) Signed-off-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/197 | 109 +++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/197.out | 26 ++++++++++ tests/qemu-iotests/common.filter | 1 + tests/qemu-iotests/group | 1 + 4 files changed, 137 insertions(+) create mode 100755 tests/qemu-iotests/197 create mode 100644 tests/qemu-iotests/197.out diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/197 @@ -XXX,XX +XXX,XX @@ +#!/bin/bash +# +# Test case for copy-on-read into qcow2 +# +# 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=eblake@redhat.com + +seq="$(basename $0)" +echo "QA output created by $seq" + +here="$PWD" +status=1 # failure is the default! + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +TEST_WRAP="$TEST_DIR/t.wrap.qcow2" +BLKDBG_CONF="$TEST_DIR/blkdebug.conf" + +# Sanity check: our use of blkdebug fails if $TEST_DIR contains spaces +# or other problems +case "$TEST_DIR" in + *[^-_a-zA-Z0-9/]*) + _notrun "Suspicious TEST_DIR='$TEST_DIR', cowardly refusing to run" ;; +esac + +_cleanup() +{ + _cleanup_test_img + rm -f "$BLKDBG_CONF" +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# Test is supported for any backing file; but we force qcow2 for our wrapper. +_supported_fmt generic +_supported_proto generic +_supported_os Linux +# LUKS support may be possible, but it complicates things. +_unsupported_fmt luks + +echo +echo '=== Copy-on-read ===' +echo + +# Prep the images +_make_test_img 4G +$QEMU_IO -c "write -P 55 3G 1k" "$TEST_IMG" | _filter_qemu_io +IMGPROTO=file IMGFMT=qcow2 IMGOPTS= TEST_IMG_FILE="$TEST_WRAP" \ + _make_test_img -F "$IMGFMT" -b "$TEST_IMG" | _filter_img_create +$QEMU_IO -f qcow2 -c "write -z -u 1M 64k" "$TEST_WRAP" | _filter_qemu_io + +# Ensure that a read of two clusters, but where one is already allocated, +# does not re-write the allocated cluster +cat > "$BLKDBG_CONF" <<EOF +[inject-error] +event = "cor_write" +sector = "2048" +EOF +$QEMU_IO -c "open -C \ + -o driver=blkdebug,config=$BLKDBG_CONF,image.driver=qcow2 $TEST_WRAP" \ + -c "read -P 0 1M 128k" | _filter_qemu_io + +# Read the areas we want copied. A zero-length read should still be a +# no-op. The next read is under 2G, but aligned so that rounding to +# clusters copies more than 2G of zeroes. The final read will pick up +# the non-zero data in the same cluster. Since a 2G read may exhaust +# memory on some machines (particularly 32-bit), we skip the test if +# that fails due to memory pressure. +$QEMU_IO -f qcow2 -C -c "read 0 0" "$TEST_WRAP" | _filter_qemu_io +output=$($QEMU_IO -f qcow2 -C -c "read -P 0 1k $((2*1024*1024*1024 - 512))" \ + "$TEST_WRAP" 2>&1 | _filter_qemu_io) +case $output in + *allocate*) + _notrun "Insufficent memory to run test" ;; + *) printf '%s\n' "$output" ;; +esac +$QEMU_IO -f qcow2 -C -c "read -P 0 $((3*1024*1024*1024 + 1024)) 1k" \ + "$TEST_WRAP" | _filter_qemu_io + +# Copy-on-read is incompatible with read-only +$QEMU_IO -f qcow2 -C -r "$TEST_WRAP" 2>&1 | _filter_testdir + +# Break the backing chain, and show that images are identical, and that +# we properly copied over explicit zeros. +$QEMU_IMG rebase -u -b "" -f qcow2 "$TEST_WRAP" +$QEMU_IO -f qcow2 -c map "$TEST_WRAP" +_check_test_img +$QEMU_IMG compare -f $IMGFMT -F qcow2 "$TEST_IMG" "$TEST_WRAP" + +# success, all done +echo '*** done' +status=0 diff --git a/tests/qemu-iotests/197.out b/tests/qemu-iotests/197.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/197.out @@ -XXX,XX +XXX,XX @@ +QA output created by 197 + +=== Copy-on-read === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=4294967296 +wrote 1024/1024 bytes at offset 3221225472 +1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +Formatting 'TEST_DIR/t.wrap.IMGFMT', fmt=IMGFMT size=4294967296 backing_file=TEST_DIR/t.IMGFMT backing_fmt=IMGFMT +wrote 65536/65536 bytes at offset 1048576 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 131072/131072 bytes at offset 1048576 +128 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 0/0 bytes at offset 0 +0 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 2147483136/2147483136 bytes at offset 1024 +2 GiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 1024/1024 bytes at offset 3221226496 +1 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +can't open device TEST_DIR/t.wrap.qcow2: Can't use copy-on-read on read-only device +2 GiB (0x80010000) bytes allocated at offset 0 bytes (0x0) +1023.938 MiB (0x3fff0000) bytes not allocated at offset 2 GiB (0x80010000) +64 KiB (0x10000) bytes allocated at offset 3 GiB (0xc0000000) +1023.938 MiB (0x3fff0000) bytes not allocated at offset 3 GiB (0xc0010000) +No errors were found on the image. +Images are identical. +*** done diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -XXX,XX +XXX,XX @@ _filter_img_create() sed -e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \ -e "s#$TEST_DIR#TEST_DIR#g" \ -e "s#$IMGFMT#IMGFMT#g" \ + -e 's#nbd:127.0.0.1:10810#TEST_DIR/t.IMGFMT#g' \ -e "s# encryption=off##g" \ -e "s# cluster_size=[0-9]\\+##g" \ -e "s# table_size=[0-9]\\+##g" \ 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 @@ 192 rw auto quick 194 rw auto migration quick 195 rw auto quick +197 rw auto quick -- 2.13.6 From: "Daniel P. Berrange" <berrange@redhat.com> Using 16KB bounce buffers creates a significant performance penalty for I/O to encrypted volumes on storage which high I/O latency (rotating rust & network drives), because it triggers lots of fairly small I/O operations. On tests with rotating rust, and cache=none|directsync, write speed increased from 2MiB/s to 32MiB/s, on a par with that achieved by the in-kernel luks driver. With other cache modes the in-kernel driver is still notably faster because it is able to report completion of the I/O request before any encryption is done, while the in-QEMU driver must encrypt the data before completion. Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170927125340.12360-2-berrange@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/crypto.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) 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 void block_crypto_close(BlockDriverState *bs) } -#define BLOCK_CRYPTO_MAX_SECTORS 32 +/* + * 1 MB bounce buffer gives good performance / memory tradeoff + * when using cache=none|directsync. + */ +#define BLOCK_CRYPTO_MAX_IO_SIZE (1024 * 1024) static coroutine_fn int block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, @@ -XXX,XX +XXX,XX @@ block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, qemu_iovec_init(&hd_qiov, qiov->niov); - /* Bounce buffer so we have a linear mem region for - * entire sector. XXX optimize so we avoid bounce - * buffer in case that qiov->niov == 1 + /* Bounce buffer because we don't wish to expose cipher text + * in qiov which points to guest memory. */ cipher_data = - qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512, + qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_IO_SIZE, qiov->size)); if (cipher_data == NULL) { ret = -ENOMEM; @@ -XXX,XX +XXX,XX @@ block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, while (remaining_sectors) { cur_nr_sectors = remaining_sectors; - if (cur_nr_sectors > BLOCK_CRYPTO_MAX_SECTORS) { - cur_nr_sectors = BLOCK_CRYPTO_MAX_SECTORS; + if (cur_nr_sectors > (BLOCK_CRYPTO_MAX_IO_SIZE / 512)) { + cur_nr_sectors = (BLOCK_CRYPTO_MAX_IO_SIZE / 512); } qemu_iovec_reset(&hd_qiov); @@ -XXX,XX +XXX,XX @@ block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num, qemu_iovec_init(&hd_qiov, qiov->niov); - /* Bounce buffer so we have a linear mem region for - * entire sector. XXX optimize so we avoid bounce - * buffer in case that qiov->niov == 1 + /* Bounce buffer because we're not permitted to touch + * contents of qiov - it points to guest memory. */ cipher_data = - qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512, + qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_IO_SIZE, qiov->size)); if (cipher_data == NULL) { ret = -ENOMEM; @@ -XXX,XX +XXX,XX @@ block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num, while (remaining_sectors) { cur_nr_sectors = remaining_sectors; - if (cur_nr_sectors > BLOCK_CRYPTO_MAX_SECTORS) { - cur_nr_sectors = BLOCK_CRYPTO_MAX_SECTORS; + if (cur_nr_sectors > (BLOCK_CRYPTO_MAX_IO_SIZE / 512)) { + cur_nr_sectors = (BLOCK_CRYPTO_MAX_IO_SIZE / 512); } qemu_iovec_to_buf(qiov, bytes_done, -- 2.13.6 From: "Daniel P. Berrange" <berrange@redhat.com> While current encryption schemes all have a fixed sector size of 512 bytes, this is not guaranteed to be the case in future. Expose the sector size in the APIs so the block layer can remove assumptions about fixed 512 byte sectors. Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170927125340.12360-3-berrange@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- crypto/blockpriv.h | 1 + include/crypto/block.h | 15 +++++++++++++++ crypto/block-luks.c | 6 ++++-- crypto/block-qcow.c | 1 + crypto/block.c | 6 ++++++ 5 files changed, 27 insertions(+), 2 deletions(-) diff --git a/crypto/blockpriv.h b/crypto/blockpriv.h index XXXXXXX..XXXXXXX 100644 --- a/crypto/blockpriv.h +++ b/crypto/blockpriv.h @@ -XXX,XX +XXX,XX @@ struct QCryptoBlock { QCryptoHashAlgorithm kdfhash; size_t niv; uint64_t payload_offset; /* In bytes */ + uint64_t sector_size; /* In bytes */ }; struct QCryptoBlockDriver { diff --git a/include/crypto/block.h b/include/crypto/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/crypto/block.h +++ b/include/crypto/block.h @@ -XXX,XX +XXX,XX @@ QCryptoHashAlgorithm qcrypto_block_get_kdf_hash(QCryptoBlock *block); uint64_t qcrypto_block_get_payload_offset(QCryptoBlock *block); /** + * qcrypto_block_get_sector_size: + * @block: the block encryption object + * + * Get the size of sectors used for payload encryption. A new + * IV is used at the start of each sector. The encryption + * sector size is not required to match the sector size of the + * underlying storage. For example LUKS will always use a 512 + * byte sector size, even if the volume is on a disk with 4k + * sectors. + * + * Returns: the sector in bytes + */ +uint64_t qcrypto_block_get_sector_size(QCryptoBlock *block); + +/** * qcrypto_block_free: * @block: the block encryption object * diff --git a/crypto/block-luks.c b/crypto/block-luks.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block-luks.c +++ b/crypto/block-luks.c @@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_open(QCryptoBlock *block, } } + block->sector_size = QCRYPTO_BLOCK_LUKS_SECTOR_SIZE; block->payload_offset = luks->header.payload_offset * - QCRYPTO_BLOCK_LUKS_SECTOR_SIZE; + block->sector_size; luks->cipher_alg = cipheralg; luks->cipher_mode = ciphermode; @@ -XXX,XX +XXX,XX @@ qcrypto_block_luks_create(QCryptoBlock *block, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE)) * QCRYPTO_BLOCK_LUKS_NUM_KEY_SLOTS); + block->sector_size = QCRYPTO_BLOCK_LUKS_SECTOR_SIZE; block->payload_offset = luks->header.payload_offset * - QCRYPTO_BLOCK_LUKS_SECTOR_SIZE; + block->sector_size; /* Reserve header space to match payload offset */ initfunc(block, block->payload_offset, opaque, &local_err); diff --git a/crypto/block-qcow.c b/crypto/block-qcow.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block-qcow.c +++ b/crypto/block-qcow.c @@ -XXX,XX +XXX,XX @@ qcrypto_block_qcow_init(QCryptoBlock *block, goto fail; } + block->sector_size = QCRYPTO_BLOCK_QCOW_SECTOR_SIZE; block->payload_offset = 0; return 0; diff --git a/crypto/block.c b/crypto/block.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block.c +++ b/crypto/block.c @@ -XXX,XX +XXX,XX @@ uint64_t qcrypto_block_get_payload_offset(QCryptoBlock *block) } +uint64_t qcrypto_block_get_sector_size(QCryptoBlock *block) +{ + return block->sector_size; +} + + void qcrypto_block_free(QCryptoBlock *block) { if (!block) { -- 2.13.6 From: "Daniel P. Berrange" <berrange@redhat.com> The crypto APIs report the offset of the data payload as an uint64_t type, but the block driver is casting to size_t or ssize_t which will potentially truncate. Most of the block APIs use int64_t for offsets meanwhile, so even if using uint64_t in the crypto block driver we are still at risk of truncation. Change the block crypto driver to use uint64_t, but add asserts that the value is less than INT64_MAX. Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170927125340.12360-4-berrange@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/crypto.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) 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_truncate(BlockDriverState *bs, int64_t offset, PreallocMode prealloc, Error **errp) { BlockCrypto *crypto = bs->opaque; - size_t payload_offset = + uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block); + assert(payload_offset < (INT64_MAX - offset)); offset += payload_offset; @@ -XXX,XX +XXX,XX @@ block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, uint8_t *cipher_data = NULL; QEMUIOVector hd_qiov; int ret = 0; - size_t payload_offset = + uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block) / 512; + assert(payload_offset < (INT64_MAX / 512)); qemu_iovec_init(&hd_qiov, qiov->niov); @@ -XXX,XX +XXX,XX @@ block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num, uint8_t *cipher_data = NULL; QEMUIOVector hd_qiov; int ret = 0; - size_t payload_offset = + uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block) / 512; + assert(payload_offset < (INT64_MAX / 512)); qemu_iovec_init(&hd_qiov, qiov->niov); @@ -XXX,XX +XXX,XX @@ static int64_t block_crypto_getlength(BlockDriverState *bs) BlockCrypto *crypto = bs->opaque; int64_t len = bdrv_getlength(bs->file->bs); - ssize_t offset = qcrypto_block_get_payload_offset(crypto->block); + uint64_t offset = qcrypto_block_get_payload_offset(crypto->block); + assert(offset < INT64_MAX); + assert(offset < len); len -= offset; -- 2.13.6 From: "Daniel P. Berrange" <berrange@redhat.com> Make the crypto driver implement the bdrv_co_preadv|pwritev callbacks, and also use bdrv_co_preadv|pwritev for I/O with the protocol driver beneath. This replaces sector based I/O with byte based I/O, and allows us to stop assuming the physical sector size matches the encryption sector size. Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170927125340.12360-5-berrange@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/crypto.c | 106 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 54 insertions(+), 52 deletions(-) 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 void block_crypto_close(BlockDriverState *bs) #define BLOCK_CRYPTO_MAX_IO_SIZE (1024 * 1024) static coroutine_fn int -block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, - int remaining_sectors, QEMUIOVector *qiov) +block_crypto_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, int flags) { BlockCrypto *crypto = bs->opaque; - int cur_nr_sectors; /* number of sectors in current iteration */ + uint64_t cur_bytes; /* number of bytes in current iteration */ uint64_t bytes_done = 0; uint8_t *cipher_data = NULL; QEMUIOVector hd_qiov; int ret = 0; - uint64_t payload_offset = - qcrypto_block_get_payload_offset(crypto->block) / 512; - assert(payload_offset < (INT64_MAX / 512)); + uint64_t sector_size = qcrypto_block_get_sector_size(crypto->block); + uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block); + uint64_t sector_num = offset / sector_size; + + assert(!flags); + assert(payload_offset < INT64_MAX); + assert(QEMU_IS_ALIGNED(offset, sector_size)); + assert(QEMU_IS_ALIGNED(bytes, sector_size)); qemu_iovec_init(&hd_qiov, qiov->niov); @@ -XXX,XX +XXX,XX @@ block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, goto cleanup; } - while (remaining_sectors) { - cur_nr_sectors = remaining_sectors; - - if (cur_nr_sectors > (BLOCK_CRYPTO_MAX_IO_SIZE / 512)) { - cur_nr_sectors = (BLOCK_CRYPTO_MAX_IO_SIZE / 512); - } + while (bytes) { + cur_bytes = MIN(bytes, BLOCK_CRYPTO_MAX_IO_SIZE); qemu_iovec_reset(&hd_qiov); - qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512); + qemu_iovec_add(&hd_qiov, cipher_data, cur_bytes); - ret = bdrv_co_readv(bs->file, - payload_offset + sector_num, - cur_nr_sectors, &hd_qiov); + ret = bdrv_co_preadv(bs->file, payload_offset + offset + bytes_done, + cur_bytes, &hd_qiov, 0); if (ret < 0) { goto cleanup; } - if (qcrypto_block_decrypt(crypto->block, - sector_num, - cipher_data, cur_nr_sectors * 512, - NULL) < 0) { + if (qcrypto_block_decrypt(crypto->block, sector_num, cipher_data, + cur_bytes, NULL) < 0) { ret = -EIO; goto cleanup; } - qemu_iovec_from_buf(qiov, bytes_done, - cipher_data, cur_nr_sectors * 512); + qemu_iovec_from_buf(qiov, bytes_done, cipher_data, cur_bytes); - remaining_sectors -= cur_nr_sectors; - sector_num += cur_nr_sectors; - bytes_done += cur_nr_sectors * 512; + sector_num += cur_bytes / sector_size; + bytes -= cur_bytes; + bytes_done += cur_bytes; } cleanup: @@ -XXX,XX +XXX,XX @@ block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num, static coroutine_fn int -block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num, - int remaining_sectors, QEMUIOVector *qiov) +block_crypto_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, int flags) { BlockCrypto *crypto = bs->opaque; - int cur_nr_sectors; /* number of sectors in current iteration */ + uint64_t cur_bytes; /* number of bytes in current iteration */ uint64_t bytes_done = 0; uint8_t *cipher_data = NULL; QEMUIOVector hd_qiov; int ret = 0; - uint64_t payload_offset = - qcrypto_block_get_payload_offset(crypto->block) / 512; - assert(payload_offset < (INT64_MAX / 512)); + uint64_t sector_size = qcrypto_block_get_sector_size(crypto->block); + uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block); + uint64_t sector_num = offset / sector_size; + + assert(!flags); + assert(payload_offset < INT64_MAX); + assert(QEMU_IS_ALIGNED(offset, sector_size)); + assert(QEMU_IS_ALIGNED(bytes, sector_size)); qemu_iovec_init(&hd_qiov, qiov->niov); @@ -XXX,XX +XXX,XX @@ block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num, goto cleanup; } - while (remaining_sectors) { - cur_nr_sectors = remaining_sectors; + while (bytes) { + cur_bytes = MIN(bytes, BLOCK_CRYPTO_MAX_IO_SIZE); - if (cur_nr_sectors > (BLOCK_CRYPTO_MAX_IO_SIZE / 512)) { - cur_nr_sectors = (BLOCK_CRYPTO_MAX_IO_SIZE / 512); - } - - qemu_iovec_to_buf(qiov, bytes_done, - cipher_data, cur_nr_sectors * 512); + qemu_iovec_to_buf(qiov, bytes_done, cipher_data, cur_bytes); - if (qcrypto_block_encrypt(crypto->block, - sector_num, - cipher_data, cur_nr_sectors * 512, - NULL) < 0) { + if (qcrypto_block_encrypt(crypto->block, sector_num, cipher_data, + cur_bytes, NULL) < 0) { ret = -EIO; goto cleanup; } qemu_iovec_reset(&hd_qiov); - qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512); + qemu_iovec_add(&hd_qiov, cipher_data, cur_bytes); - ret = bdrv_co_writev(bs->file, - payload_offset + sector_num, - cur_nr_sectors, &hd_qiov); + ret = bdrv_co_pwritev(bs->file, payload_offset + offset + bytes_done, + cur_bytes, &hd_qiov, 0); if (ret < 0) { goto cleanup; } - remaining_sectors -= cur_nr_sectors; - sector_num += cur_nr_sectors; - bytes_done += cur_nr_sectors * 512; + sector_num += cur_bytes / sector_size; + bytes -= cur_bytes; + bytes_done += cur_bytes; } cleanup: @@ -XXX,XX +XXX,XX @@ block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num, return ret; } +static void block_crypto_refresh_limits(BlockDriverState *bs, Error **errp) +{ + BlockCrypto *crypto = bs->opaque; + uint64_t sector_size = qcrypto_block_get_sector_size(crypto->block); + bs->bl.request_alignment = sector_size; /* No sub-sector I/O */ +} + static int64_t block_crypto_getlength(BlockDriverState *bs) { @@ -XXX,XX +XXX,XX @@ BlockDriver bdrv_crypto_luks = { .bdrv_truncate = block_crypto_truncate, .create_opts = &block_crypto_create_opts_luks, - .bdrv_co_readv = block_crypto_co_readv, - .bdrv_co_writev = block_crypto_co_writev, + .bdrv_refresh_limits = block_crypto_refresh_limits, + .bdrv_co_preadv = block_crypto_co_preadv, + .bdrv_co_pwritev = block_crypto_co_pwritev, .bdrv_getlength = block_crypto_getlength, .bdrv_get_info = block_crypto_get_info_luks, .bdrv_get_specific_info = block_crypto_get_specific_info_luks, -- 2.13.6 From: "Daniel P. Berrange" <berrange@redhat.com> Instead of sector offset, take the bytes offset when encrypting or decrypting data. Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170927125340.12360-6-berrange@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- crypto/blockpriv.h | 4 ++-- include/crypto/block.h | 14 ++++++++------ block/crypto.c | 12 ++++-------- block/qcow.c | 11 +++++++---- block/qcow2-cluster.c | 8 +++----- block/qcow2.c | 4 ++-- crypto/block-luks.c | 12 ++++++++---- crypto/block-qcow.c | 12 ++++++++---- crypto/block.c | 20 ++++++++++++++------ 9 files changed, 56 insertions(+), 41 deletions(-) diff --git a/crypto/blockpriv.h b/crypto/blockpriv.h index XXXXXXX..XXXXXXX 100644 --- a/crypto/blockpriv.h +++ b/crypto/blockpriv.h @@ -XXX,XX +XXX,XX @@ int qcrypto_block_decrypt_helper(QCryptoCipher *cipher, size_t niv, QCryptoIVGen *ivgen, int sectorsize, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp); @@ -XXX,XX +XXX,XX @@ int qcrypto_block_encrypt_helper(QCryptoCipher *cipher, size_t niv, QCryptoIVGen *ivgen, int sectorsize, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp); diff --git a/include/crypto/block.h b/include/crypto/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/crypto/block.h +++ b/include/crypto/block.h @@ -XXX,XX +XXX,XX @@ QCryptoBlockInfo *qcrypto_block_get_info(QCryptoBlock *block, /** * @qcrypto_block_decrypt: * @block: the block encryption object - * @startsector: the sector from which @buf was read + * @offset: the position at which @iov was read * @buf: the buffer to decrypt * @len: the length of @buf in bytes * @errp: pointer to a NULL-initialized error object * * Decrypt @len bytes of cipher text in @buf, writing - * plain text back into @buf + * plain text back into @buf. @len and @offset must be + * a multiple of the encryption format sector size. * * Returns 0 on success, -1 on failure */ int qcrypto_block_decrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp); @@ -XXX,XX +XXX,XX @@ int qcrypto_block_decrypt(QCryptoBlock *block, /** * @qcrypto_block_encrypt: * @block: the block encryption object - * @startsector: the sector to which @buf will be written + * @offset: the position at which @iov will be written * @buf: the buffer to decrypt * @len: the length of @buf in bytes * @errp: pointer to a NULL-initialized error object * * Encrypt @len bytes of plain text in @buf, writing - * cipher text back into @buf + * cipher text back into @buf. @len and @offset must be + * a multiple of the encryption format sector size. * * Returns 0 on success, -1 on failure */ int qcrypto_block_encrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp); 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 @@ block_crypto_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, int ret = 0; uint64_t sector_size = qcrypto_block_get_sector_size(crypto->block); uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block); - uint64_t sector_num = offset / sector_size; assert(!flags); assert(payload_offset < INT64_MAX); @@ -XXX,XX +XXX,XX @@ block_crypto_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, goto cleanup; } - if (qcrypto_block_decrypt(crypto->block, sector_num, cipher_data, - cur_bytes, NULL) < 0) { + if (qcrypto_block_decrypt(crypto->block, offset + bytes_done, + cipher_data, cur_bytes, NULL) < 0) { ret = -EIO; goto cleanup; } qemu_iovec_from_buf(qiov, bytes_done, cipher_data, cur_bytes); - sector_num += cur_bytes / sector_size; bytes -= cur_bytes; bytes_done += cur_bytes; } @@ -XXX,XX +XXX,XX @@ block_crypto_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, int ret = 0; uint64_t sector_size = qcrypto_block_get_sector_size(crypto->block); uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block); - uint64_t sector_num = offset / sector_size; assert(!flags); assert(payload_offset < INT64_MAX); @@ -XXX,XX +XXX,XX @@ block_crypto_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_to_buf(qiov, bytes_done, cipher_data, cur_bytes); - if (qcrypto_block_encrypt(crypto->block, sector_num, cipher_data, - cur_bytes, NULL) < 0) { + if (qcrypto_block_encrypt(crypto->block, offset + bytes_done, + cipher_data, cur_bytes, NULL) < 0) { ret = -EIO; goto cleanup; } @@ -XXX,XX +XXX,XX @@ block_crypto_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, goto cleanup; } - sector_num += cur_bytes / sector_size; bytes -= cur_bytes; bytes_done += cur_bytes; } 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 get_cluster_offset(BlockDriverState *bs, for(i = 0; i < s->cluster_sectors; i++) { if (i < n_start || i >= n_end) { memset(s->cluster_data, 0x00, 512); - if (qcrypto_block_encrypt(s->crypto, start_sect + i, + if (qcrypto_block_encrypt(s->crypto, + (start_sect + i) * + BDRV_SECTOR_SIZE, s->cluster_data, BDRV_SECTOR_SIZE, NULL) < 0) { @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num, } if (bs->encrypted) { assert(s->crypto); - if (qcrypto_block_decrypt(s->crypto, sector_num, buf, + if (qcrypto_block_decrypt(s->crypto, + sector_num * BDRV_SECTOR_SIZE, buf, n * BDRV_SECTOR_SIZE, NULL) < 0) { ret = -EIO; break; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num, } if (bs->encrypted) { assert(s->crypto); - if (qcrypto_block_encrypt(s->crypto, sector_num, buf, - n * BDRV_SECTOR_SIZE, NULL) < 0) { + if (qcrypto_block_encrypt(s->crypto, sector_num * BDRV_SECTOR_SIZE, + buf, n * BDRV_SECTOR_SIZE, NULL) < 0) { ret = -EIO; break; } 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 bool coroutine_fn do_perform_cow_encrypt(BlockDriverState *bs, { if (bytes && bs->encrypted) { BDRVQcow2State *s = bs->opaque; - int64_t sector = (s->crypt_physical_offset ? + int64_t offset = (s->crypt_physical_offset ? (cluster_offset + offset_in_cluster) : - (src_cluster_offset + offset_in_cluster)) - >> BDRV_SECTOR_BITS; + (src_cluster_offset + offset_in_cluster)); assert((offset_in_cluster & ~BDRV_SECTOR_MASK) == 0); assert((bytes & ~BDRV_SECTOR_MASK) == 0); assert(s->crypto); - if (qcrypto_block_encrypt(s->crypto, sector, buffer, - bytes, NULL) < 0) { + if (qcrypto_block_encrypt(s->crypto, offset, buffer, bytes, NULL) < 0) { return false; } } 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 coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, if (qcrypto_block_decrypt(s->crypto, (s->crypt_physical_offset ? cluster_offset + offset_in_cluster : - offset) >> BDRV_SECTOR_BITS, + offset), cluster_data, cur_bytes, NULL) < 0) { @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset, if (qcrypto_block_encrypt(s->crypto, (s->crypt_physical_offset ? cluster_offset + offset_in_cluster : - offset) >> BDRV_SECTOR_BITS, + offset), cluster_data, cur_bytes, NULL) < 0) { ret = -EIO; diff --git a/crypto/block-luks.c b/crypto/block-luks.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block-luks.c +++ b/crypto/block-luks.c @@ -XXX,XX +XXX,XX @@ static void qcrypto_block_luks_cleanup(QCryptoBlock *block) static int qcrypto_block_luks_decrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { + assert(QEMU_IS_ALIGNED(offset, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE)); + assert(QEMU_IS_ALIGNED(len, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE)); return qcrypto_block_decrypt_helper(block->cipher, block->niv, block->ivgen, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE, - startsector, buf, len, errp); + offset, buf, len, errp); } static int qcrypto_block_luks_encrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { + assert(QEMU_IS_ALIGNED(offset, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE)); + assert(QEMU_IS_ALIGNED(len, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE)); return qcrypto_block_encrypt_helper(block->cipher, block->niv, block->ivgen, QCRYPTO_BLOCK_LUKS_SECTOR_SIZE, - startsector, buf, len, errp); + offset, buf, len, errp); } diff --git a/crypto/block-qcow.c b/crypto/block-qcow.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block-qcow.c +++ b/crypto/block-qcow.c @@ -XXX,XX +XXX,XX @@ qcrypto_block_qcow_cleanup(QCryptoBlock *block) static int qcrypto_block_qcow_decrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { + assert(QEMU_IS_ALIGNED(offset, QCRYPTO_BLOCK_QCOW_SECTOR_SIZE)); + assert(QEMU_IS_ALIGNED(len, QCRYPTO_BLOCK_QCOW_SECTOR_SIZE)); return qcrypto_block_decrypt_helper(block->cipher, block->niv, block->ivgen, QCRYPTO_BLOCK_QCOW_SECTOR_SIZE, - startsector, buf, len, errp); + offset, buf, len, errp); } static int qcrypto_block_qcow_encrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { + assert(QEMU_IS_ALIGNED(offset, QCRYPTO_BLOCK_QCOW_SECTOR_SIZE)); + assert(QEMU_IS_ALIGNED(len, QCRYPTO_BLOCK_QCOW_SECTOR_SIZE)); return qcrypto_block_encrypt_helper(block->cipher, block->niv, block->ivgen, QCRYPTO_BLOCK_QCOW_SECTOR_SIZE, - startsector, buf, len, errp); + offset, buf, len, errp); } diff --git a/crypto/block.c b/crypto/block.c index XXXXXXX..XXXXXXX 100644 --- a/crypto/block.c +++ b/crypto/block.c @@ -XXX,XX +XXX,XX @@ QCryptoBlockInfo *qcrypto_block_get_info(QCryptoBlock *block, int qcrypto_block_decrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { - return block->driver->decrypt(block, startsector, buf, len, errp); + return block->driver->decrypt(block, offset, buf, len, errp); } int qcrypto_block_encrypt(QCryptoBlock *block, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { - return block->driver->encrypt(block, startsector, buf, len, errp); + return block->driver->encrypt(block, offset, buf, len, errp); } @@ -XXX,XX +XXX,XX @@ int qcrypto_block_decrypt_helper(QCryptoCipher *cipher, size_t niv, QCryptoIVGen *ivgen, int sectorsize, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { uint8_t *iv; int ret = -1; + uint64_t startsector = offset / sectorsize; + + assert(QEMU_IS_ALIGNED(offset, sectorsize)); + assert(QEMU_IS_ALIGNED(len, sectorsize)); iv = niv ? g_new0(uint8_t, niv) : NULL; @@ -XXX,XX +XXX,XX @@ int qcrypto_block_encrypt_helper(QCryptoCipher *cipher, size_t niv, QCryptoIVGen *ivgen, int sectorsize, - uint64_t startsector, + uint64_t offset, uint8_t *buf, size_t len, Error **errp) { uint8_t *iv; int ret = -1; + uint64_t startsector = offset / sectorsize; + + assert(QEMU_IS_ALIGNED(offset, sectorsize)); + assert(QEMU_IS_ALIGNED(len, sectorsize)); iv = niv ? g_new0(uint8_t, niv) : NULL; -- 2.13.6 From: "Daniel P. Berrange" <berrange@redhat.com> The BDRV_REQ_FUA flag can trivially be allowed in the crypt driver as a passthrough to the underlying block driver. Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Daniel P. Berrange <berrange@redhat.com> Message-id: 20170927125340.12360-7-berrange@redhat.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/crypto.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) 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, return -EINVAL; } + bs->supported_write_flags = BDRV_REQ_FUA & + bs->file->bs->supported_write_flags; + opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &local_err); if (local_err) { @@ -XXX,XX +XXX,XX @@ block_crypto_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, uint64_t sector_size = qcrypto_block_get_sector_size(crypto->block); uint64_t payload_offset = qcrypto_block_get_payload_offset(crypto->block); - assert(!flags); + assert(!(flags & ~BDRV_REQ_FUA)); assert(payload_offset < INT64_MAX); assert(QEMU_IS_ALIGNED(offset, sector_size)); assert(QEMU_IS_ALIGNED(bytes, sector_size)); @@ -XXX,XX +XXX,XX @@ block_crypto_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes, qemu_iovec_add(&hd_qiov, cipher_data, cur_bytes); ret = bdrv_co_pwritev(bs->file, payload_offset + offset + bytes_done, - cur_bytes, &hd_qiov, 0); + cur_bytes, &hd_qiov, flags); if (ret < 0) { goto cleanup; } -- 2.13.6 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Backing may be zero after failed bdrv_attach_child in bdrv_set_backing_hd, which leads to SIGSEGV. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20170928120300.58164-1-vsementsov@virtuozzo.com Reviewed-by: John Snow <jsnow@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/mirror.c | 5 +++++ 1 file changed, 5 insertions(+) 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 bdrv_mirror_top_pdiscard(BlockDriverState *bs, static void bdrv_mirror_top_refresh_filename(BlockDriverState *bs, QDict *opts) { + if (bs->backing == NULL) { + /* we can be here after failed bdrv_attach_child in + * bdrv_set_backing_hd */ + return; + } bdrv_refresh_filename(bs->backing->bs); pstrcpy(bs->exact_filename, sizeof(bs->exact_filename), bs->backing->bs->filename); -- 2.13.6 From: Max Reitz <mreitz@redhat.com> do_run_qemu() in iotest 195 first applies _filter_imgfmt when printing qemu's command line and _filter_testdir only afterwards. Therefore, if the image format is part of the test directory path, _filter_testdir will no longer apply and the actual output will differ from the reference output even in case of success. For example, TEST_DIR might be "/tmp/test-qcow2", in which case _filter_imgfmt first transforms this to "/tmp/test-IMGFMT" which is no longer recognized as the TEST_DIR by _filter_testdir. Fix this by not applying _filter_imgfmt in do_run_qemu() but in run_qemu() instead, and only after _filter_testdir. Signed-off-by: Max Reitz <mreitz@redhat.com> Message-id: 20170927211334.3988-1-mreitz@redhat.com Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> --- tests/qemu-iotests/195 | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/195 b/tests/qemu-iotests/195 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/195 +++ b/tests/qemu-iotests/195 @@ -XXX,XX +XXX,XX @@ _supported_os Linux function do_run_qemu() { - echo Testing: "$@" | _filter_imgfmt + echo Testing: "$@" $QEMU -nographic -qmp-pretty stdio -serial none "$@" echo } function run_qemu() { - do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qemu | _filter_qmp \ - | _filter_qemu_io | _filter_generated_node_ids + do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_imgfmt | _filter_qemu \ + | _filter_qmp | _filter_qemu_io \ + | _filter_generated_node_ids } size=64M -- 2.13.6 From: Pavel Butsykin <pbutsykin@virtuozzo.com> Signed-off-by: Pavel Butsykin <pbutsykin@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-id: 20170929121613.25997-2-pbutsykin@virtuozzo.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_truncate(BlockDriverState *bs, int64_t offset, if (old_file_size < 0) { error_setg_errno(errp, -old_file_size, "Failed to inquire current file length"); - return ret; + return old_file_size; } nb_new_data_clusters = DIV_ROUND_UP(offset - old_length, @@ -XXX,XX +XXX,XX @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset, if (allocation_start < 0) { error_setg_errno(errp, -allocation_start, "Failed to resize refcount structures"); - return -allocation_start; + return allocation_start; } clusters_allocated = qcow2_alloc_clusters_at(bs, allocation_start, -- 2.13.6 From: Pavel Butsykin <pbutsykin@virtuozzo.com> Now after shrinking the image, at the end of the image file, there might be a tail that probably will never be used. So we can find the last used cluster and cut the tail. Signed-off-by: Pavel Butsykin <pbutsykin@virtuozzo.com> Reviewed-by: John Snow <jsnow@redhat.com> Message-id: 20170929121613.25997-3-pbutsykin@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/qcow2.h | 1 + block/qcow2-refcount.c | 22 ++++++++++++++++++++++ block/qcow2.c | 23 +++++++++++++++++++++++ 3 files changed, 46 insertions(+) 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_change_refcount_order(BlockDriverState *bs, int refcount_order, BlockDriverAmendStatusCB *status_cb, void *cb_opaque, Error **errp); int qcow2_shrink_reftable(BlockDriverState *bs); +int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size); /* qcow2-cluster.c functions */ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, 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 @@ out: g_free(reftable_tmp); return ret; } + +int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size) +{ + BDRVQcow2State *s = bs->opaque; + int64_t i; + + for (i = size_to_clusters(s, size) - 1; i >= 0; i--) { + uint64_t refcount; + int ret = qcow2_get_refcount(bs, i, &refcount); + if (ret < 0) { + fprintf(stderr, "Can't get refcount for cluster %" PRId64 ": %s\n", + i, strerror(-ret)); + return ret; + } + if (refcount > 0) { + return i; + } + } + qcow2_signal_corruption(bs, true, -1, -1, + "There are no references in the refcount table."); + return -EIO; +} 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, new_l1_size = size_to_l1(s, offset); if (offset < old_length) { + int64_t last_cluster, old_file_size; if (prealloc != PREALLOC_MODE_OFF) { error_setg(errp, "Preallocation can't be used for shrinking an image"); @@ -XXX,XX +XXX,XX @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset, "Failed to discard unused refblocks"); return ret; } + + old_file_size = bdrv_getlength(bs->file->bs); + if (old_file_size < 0) { + error_setg_errno(errp, -old_file_size, + "Failed to inquire current file length"); + return old_file_size; + } + last_cluster = qcow2_get_last_cluster(bs, old_file_size); + if (last_cluster < 0) { + error_setg_errno(errp, -last_cluster, + "Failed to find the last cluster"); + 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; + } + } } else { ret = qcow2_grow_l1_table(bs, new_l1_size, true); if (ret < 0) { -- 2.13.6 From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Backing may be zero after failed bdrv_append in mirror_start_job, which leads to SIGSEGV. Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20170929152255.5431-1-vsementsov@virtuozzo.com Signed-off-by: Max Reitz <mreitz@redhat.com> --- block/mirror.c | 4 ++++ 1 file changed, 4 insertions(+) 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 bdrv_mirror_top_pwritev(BlockDriverState *bs, static int coroutine_fn bdrv_mirror_top_flush(BlockDriverState *bs) { + if (bs->backing == NULL) { + /* we can be here after failed bdrv_append in mirror_start_job */ + return 0; + } return bdrv_co_flush(bs->backing->bs); } -- 2.13.6 The following changes since commit 281f327487c9c9b1599f93c589a408bbf4a651b8: Merge remote-tracking branch 'remotes/vivier/tags/m68k-for-2.12-pull-request' into staging (2017-12-22 00:11:36 +0000) are available in the git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to 1a63a907507fbbcfaee3f622907ec244b7eabda8: block: Keep nodes drained between reopen_queue/multiple (2017-12-22 15:05:32 +0100) ---------------------------------------------------------------- Block layer patches ---------------------------------------------------------------- Doug Gale (1): nvme: Add tracing Edgar Kaziakhmedov (1): qcow2: get rid of qcow2_backing_read1 routine Fam Zheng (2): block: Open backing image in force share mode for size probe block: Remove unused bdrv_requests_pending John Snow (1): iotests: fix 197 for vpc Kevin Wolf (27): block: Formats don't need CONSISTENT_READ with NO_IO block: Make bdrv_drain_invoke() recursive block: Call .drain_begin only once in bdrv_drain_all_begin() test-bdrv-drain: Test BlockDriver callbacks for drain block: bdrv_drain_recurse(): Remove unused begin parameter block: Don't wait for requests in bdrv_drain*_end() block: Unify order in drain functions block: Don't acquire AioContext in hmp_qemu_io() block: Document that x-blockdev-change breaks quorum children list block: Assert drain_all is only called from main AioContext block: Make bdrv_drain() driver callbacks non-recursive test-bdrv-drain: Test callback for bdrv_drain test-bdrv-drain: Test bs->quiesce_counter blockjob: Pause job on draining any job BDS test-bdrv-drain: Test drain vs. block jobs block: Don't block_job_pause_all() in bdrv_drain_all() block: Nested drain_end must still call callbacks test-bdrv-drain: Test nested drain sections block: Don't notify parents in drain call chain block: Add bdrv_subtree_drained_begin/end() test-bdrv-drain: Tests for bdrv_subtree_drain test-bdrv-drain: Test behaviour in coroutine context test-bdrv-drain: Recursive draining with multiple parents block: Allow graph changes in subtree drained section test-bdrv-drain: Test graph changes in drained section commit: Simplify reopen of base block: Keep nodes drained between reopen_queue/multiple Thomas Huth (3): block: Remove the obsolete -drive boot=on|off parameter block: Remove the deprecated -hdachs option block: Mention -drive cyls/heads/secs/trans/serial/addr in deprecation chapter qapi/block-core.json | 4 + block/qcow2.h | 3 - include/block/block.h | 15 +- include/block/block_int.h | 6 +- block.c | 75 ++++- block/commit.c | 8 +- block/io.c | 164 +++++++--- block/qcow2.c | 51 +-- block/replication.c | 6 + blockdev.c | 11 - blockjob.c | 22 +- hmp.c | 6 - hw/block/nvme.c | 349 +++++++++++++++++---- qemu-io-cmds.c | 3 + tests/test-bdrv-drain.c | 651 +++++++++++++++++++++++++++++++++++++++ vl.c | 86 +----- hw/block/trace-events | 93 ++++++ qemu-doc.texi | 29 +- qemu-options.hx | 19 +- tests/Makefile.include | 2 + tests/qemu-iotests/197 | 4 + tests/qemu-iotests/common.filter | 3 +- 22 files changed, 1294 insertions(+), 316 deletions(-) create mode 100644 tests/test-bdrv-drain.c Commit 1f4ad7d fixed 'qemu-img info' for raw images that are currently in use as a mirror target. It is not enough for image formats, though, as these still unconditionally request BLK_PERM_CONSISTENT_READ. As this permission is geared towards whether the guest-visible data is consistent, and has no impact on whether the metadata is sane, and 'qemu-img info' does not read guest-visible data (except for the raw format), it makes sense to not require BLK_PERM_CONSISTENT_READ if there is not going to be any guest I/O performed, regardless of image format. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 6 +++++- 1 file changed, 5 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 @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, assert(role == &child_backing || role == &child_file); if (!backing) { + int flags = bdrv_reopen_get_flags(reopen_queue, bs); + /* Apart from the modifications below, the same permissions are * forwarded and left alone as for filters */ bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared, @@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, /* bs->file always needs to be consistent because of the metadata. We * can never allow other users to resize or write to it. */ - perm |= BLK_PERM_CONSISTENT_READ; + if (!(flags & BDRV_O_NO_IO)) { + perm |= BLK_PERM_CONSISTENT_READ; + } shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE); } else { /* We want consistent read from backing files if the parent needs it. -- 2.13.6 From: John Snow <jsnow@redhat.com> VPC has some difficulty creating geometries of particular size. However, we can indeed force it to use a literal one, so let's do that for the sake of test 197, which is testing some specific offsets. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Lukáš Doktor <ldoktor@redhat.com> --- tests/qemu-iotests/197 | 4 ++++ tests/qemu-iotests/common.filter | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/197 +++ b/tests/qemu-iotests/197 @@ -XXX,XX +XXX,XX @@ echo '=== Copy-on-read ===' echo # Prep the images +# VPC rounds image sizes to a specific geometry, force a specific size. +if [ "$IMGFMT" = "vpc" ]; then + IMGOPTS=$(_optstr_add "$IMGOPTS" "force_size") +fi _make_test_img 4G $QEMU_IO -c "write -P 55 3G 1k" "$TEST_IMG" | _filter_qemu_io IMGPROTO=file IMGFMT=qcow2 IMGOPTS= TEST_IMG_FILE="$TEST_WRAP" \ 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_img_create() -e "s# log_size=[0-9]\\+##g" \ -e "s# refcount_bits=[0-9]\\+##g" \ -e "s# key-secret=[a-zA-Z0-9]\\+##g" \ - -e "s# iter-time=[0-9]\\+##g" + -e "s# iter-time=[0-9]\\+##g" \ + -e "s# force_size=\\(on\\|off\\)##g" } _filter_img_info() -- 2.13.6 This change separates bdrv_drain_invoke(), which calls the BlockDriver drain callbacks, from bdrv_drain_recurse(). Instead, the function performs its own recursion now. One reason for this is that bdrv_drain_recurse() can be called multiple times by bdrv_drain_all_begin(), but the callbacks may only be called once. The separation is necessary to fix this bug. The other reason is that we intend to go to a model where we call all driver callbacks first, and only then start polling. This is not fully achieved yet with this patch, as bdrv_drain_invoke() contains a BDRV_POLL_WHILE() loop for the block driver callbacks, which can still call callbacks for any unrelated event. It's a step in this direction anyway. Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 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_drain_invoke_entry(void *opaque) bdrv_wakeup(bs); } +/* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) { + BdrvChild *child, *tmp; BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin}; if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) || @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) data.co = qemu_coroutine_create(bdrv_drain_invoke_entry, &data); bdrv_coroutine_enter(bs, data.co); BDRV_POLL_WHILE(bs, !data.done); + + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { + bdrv_drain_invoke(child->bs, begin); + } } static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) BdrvChild *child, *tmp; bool waited; - /* Ensure any pending metadata writes are submitted to bs->file. */ - bdrv_drain_invoke(bs, begin); - /* Wait for drained requests to finish */ waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) bdrv_parent_drained_begin(bs); } + bdrv_drain_invoke(bs, true); bdrv_drain_recurse(bs, true); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) } bdrv_parent_drained_end(bs); + bdrv_drain_invoke(bs, false); bdrv_drain_recurse(bs, false); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { + /* FIXME Calling this multiple times is wrong */ + bdrv_drain_invoke(bs, true); waited |= bdrv_drain_recurse(bs, true); } } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_context_acquire(aio_context); aio_enable_external(aio_context); bdrv_parent_drained_end(bs); + bdrv_drain_invoke(bs, false); bdrv_drain_recurse(bs, false); aio_context_release(aio_context); } -- 2.13.6 bdrv_drain_all_begin() used to call the .bdrv_co_drain_begin() driver callback inside its polling loop. This means that how many times it got called for each node depended on long it had to poll the event loop. This is obviously not right and results in nodes that stay drained even after bdrv_drain_all_end(), which calls .bdrv_co_drain_begin() once per node. Fix bdrv_drain_all_begin() to call the callback only once, too. Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 3 +-- 1 file changed, 1 insertion(+), 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 @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); bdrv_parent_drained_begin(bs); aio_disable_external(aio_context); + bdrv_drain_invoke(bs, true); aio_context_release(aio_context); if (!g_slist_find(aio_ctxs, aio_context)) { @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { - /* FIXME Calling this multiple times is wrong */ - bdrv_drain_invoke(bs, true); waited |= bdrv_drain_recurse(bs, true); } } -- 2.13.6 This adds a test case that the BlockDriver callbacks for drain are called in bdrv_drained_all_begin/end(), and that both of them are called exactly once. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- tests/test-bdrv-drain.c | 137 ++++++++++++++++++++++++++++++++++++++++++++++++ tests/Makefile.include | 2 + 2 files changed, 139 insertions(+) create mode 100644 tests/test-bdrv-drain.c diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ +/* + * Block node draining tests + * + * Copyright (c) 2017 Kevin Wolf <kwolf@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "block/block.h" +#include "sysemu/block-backend.h" +#include "qapi/error.h" + +typedef struct BDRVTestState { + int drain_count; +} BDRVTestState; + +static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + s->drain_count++; +} + +static void coroutine_fn bdrv_test_co_drain_end(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + s->drain_count--; +} + +static void bdrv_test_close(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + g_assert_cmpint(s->drain_count, >, 0); +} + +static int coroutine_fn bdrv_test_co_preadv(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, int flags) +{ + /* We want this request to stay until the polling loop in drain waits for + * it to complete. We need to sleep a while as bdrv_drain_invoke() comes + * first and polls its result, too, but it shouldn't accidentally complete + * this request yet. */ + qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 100000); + + return 0; +} + +static BlockDriver bdrv_test = { + .format_name = "test", + .instance_size = sizeof(BDRVTestState), + + .bdrv_close = bdrv_test_close, + .bdrv_co_preadv = bdrv_test_co_preadv, + + .bdrv_co_drain_begin = bdrv_test_co_drain_begin, + .bdrv_co_drain_end = bdrv_test_co_drain_end, +}; + +static void aio_ret_cb(void *opaque, int ret) +{ + int *aio_ret = opaque; + *aio_ret = ret; +} + +static void test_drv_cb_drain_all(void) +{ + BlockBackend *blk; + BlockDriverState *bs; + BDRVTestState *s; + BlockAIOCB *acb; + int aio_ret; + + QEMUIOVector qiov; + struct iovec iov = { + .iov_base = NULL, + .iov_len = 0, + }; + qemu_iovec_init_external(&qiov, &iov, 1); + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + s = bs->opaque; + blk_insert_bs(blk, bs, &error_abort); + + /* Simple bdrv_drain_all_begin/end pair, check that CBs are called */ + g_assert_cmpint(s->drain_count, ==, 0); + bdrv_drain_all_begin(); + g_assert_cmpint(s->drain_count, ==, 1); + bdrv_drain_all_end(); + g_assert_cmpint(s->drain_count, ==, 0); + + /* Now do the same while a request is pending */ + aio_ret = -EINPROGRESS; + acb = blk_aio_preadv(blk, 0, &qiov, 0, aio_ret_cb, &aio_ret); + g_assert(acb != NULL); + g_assert_cmpint(aio_ret, ==, -EINPROGRESS); + + g_assert_cmpint(s->drain_count, ==, 0); + bdrv_drain_all_begin(); + g_assert_cmpint(aio_ret, ==, 0); + g_assert_cmpint(s->drain_count, ==, 1); + bdrv_drain_all_end(); + g_assert_cmpint(s->drain_count, ==, 0); + + bdrv_unref(bs); + blk_unref(blk); +} + +int main(int argc, char **argv) +{ + bdrv_init(); + qemu_init_main_loop(&error_abort); + + g_test_init(&argc, &argv, NULL); + + g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); + + return g_test_run(); +} diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ gcov-files-test-thread-pool-y = thread-pool.c gcov-files-test-hbitmap-y = util/hbitmap.c check-unit-y += tests/test-hbitmap$(EXESUF) gcov-files-test-hbitmap-y = blockjob.c +check-unit-y += tests/test-bdrv-drain$(EXESUF) check-unit-y += tests/test-blockjob$(EXESUF) check-unit-y += tests/test-blockjob-txn$(EXESUF) check-unit-y += tests/test-x86-cpuid$(EXESUF) @@ -XXX,XX +XXX,XX @@ tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y) tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y) tests/test-aio-multithread$(EXESUF): tests/test-aio-multithread.o $(test-block-obj-y) tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y) +tests/test-bdrv-drain$(EXESUF): tests/test-bdrv-drain.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob$(EXESUF): tests/test-blockjob.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob-txn$(EXESUF): tests/test-blockjob-txn.o $(test-block-obj-y) $(test-util-obj-y) tests/test-thread-pool$(EXESUF): tests/test-thread-pool.o $(test-block-obj-y) -- 2.13.6 Now that the bdrv_drain_invoke() calls are pulled up to the callers of bdrv_drain_recurse(), the 'begin' parameter isn't needed any more. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 12 ++++++------ 1 file changed, 6 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 void bdrv_drain_invoke(BlockDriverState *bs, bool begin) } } -static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) +static bool bdrv_drain_recurse(BlockDriverState *bs) { BdrvChild *child, *tmp; bool waited; @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) */ bdrv_ref(bs); } - waited |= bdrv_drain_recurse(bs, begin); + waited |= bdrv_drain_recurse(bs); if (in_main_loop) { bdrv_unref(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) } bdrv_drain_invoke(bs, true); - bdrv_drain_recurse(bs, true); + bdrv_drain_recurse(bs); } void bdrv_drained_end(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs, false); + bdrv_drain_recurse(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { - waited |= bdrv_drain_recurse(bs, true); + waited |= bdrv_drain_recurse(bs); } } aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs, false); + bdrv_drain_recurse(bs); aio_context_release(aio_context); } -- 2.13.6 The device is drained, so there is no point in waiting for requests at the end of the drained section. Remove the bdrv_drain_recurse() calls there. The bdrv_drain_recurse() calls were introduced in commit 481cad48e5e in order to call the .bdrv_co_drain_end() driver callback. This is now done by a separate bdrv_drain_invoke() call. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 2 -- 1 file changed, 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 @@ void bdrv_drained_end(BlockDriverState *bs) bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs); aio_context_release(aio_context); } -- 2.13.6 Drain requests are propagated to child nodes, parent nodes and directly to the AioContext. The order in which this happened was different between all combinations of drain/drain_all and begin/end. The correct order is to keep children only drained when their parents are also drained. This means that at the start of a drained section, the AioContext needs to be drained first, the parents second and only then the children. The correct order for the end of a drained section is the opposite. This patch changes the three other functions to follow the example of bdrv_drained_begin(), which is the only one that got it right. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 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 @@ void bdrv_drained_begin(BlockDriverState *bs) return; } + /* Stop things in parent-to-child order */ if (atomic_fetch_inc(&bs->quiesce_counter) == 0) { aio_disable_external(bdrv_get_aio_context(bs)); bdrv_parent_drained_begin(bs); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) return; } - bdrv_parent_drained_end(bs); + /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false); + bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); + /* Stop things in parent-to-child order */ aio_context_acquire(aio_context); - bdrv_parent_drained_begin(bs); aio_disable_external(aio_context); + bdrv_parent_drained_begin(bs); bdrv_drain_invoke(bs, true); aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); + /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); - aio_enable_external(aio_context); - bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); + bdrv_parent_drained_end(bs); + aio_enable_external(aio_context); aio_context_release(aio_context); } -- 2.13.6 Commit 15afd94a047 added code to acquire and release the AioContext in qemuio_command(). This means that the lock is taken twice now in the call path from hmp_qemu_io(). This causes BDRV_POLL_WHILE() to hang for any requests issued to nodes in a non-mainloop AioContext. Dropping the first locking from hmp_qemu_io() fixes the problem. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- hmp.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/hmp.c b/hmp.c index XXXXXXX..XXXXXXX 100644 --- a/hmp.c +++ b/hmp.c @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) { BlockBackend *blk; BlockBackend *local_blk = NULL; - AioContext *aio_context; const char* device = qdict_get_str(qdict, "device"); const char* command = qdict_get_str(qdict, "command"); Error *err = NULL; @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) } } - aio_context = blk_get_aio_context(blk); - aio_context_acquire(aio_context); - /* * Notably absent: Proper permission management. This is sad, but it seems * almost impossible to achieve without changing the semantics and thereby @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) */ qemuio_command(blk, command); - aio_context_release(aio_context); - fail: blk_unref(local_blk); hmp_handle_error(mon, &err); -- 2.13.6 From: Edgar Kaziakhmedov <edgar.kaziakhmedov@virtuozzo.com> Since bdrv_co_preadv does all neccessary checks including reading after the end of the backing file, avoid duplication of verification before bdrv_co_preadv call. Signed-off-by: Edgar Kaziakhmedov <edgar.kaziakhmedov@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.h | 3 --- block/qcow2.c | 51 ++++++++------------------------------------------- 2 files changed, 8 insertions(+), 46 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 @@ uint32_t offset_to_reftable_index(BDRVQcow2State *s, uint64_t offset) } /* qcow2.c functions */ -int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t sector_num, int nb_sectors); - int64_t qcow2_refcount_metadata_size(int64_t clusters, size_t cluster_size, int refcount_order, bool generous_increase, uint64_t *refblock_count); 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 coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs, return status; } -/* handle reading after the end of the backing file */ -int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t offset, int bytes) -{ - uint64_t bs_size = bs->total_sectors * BDRV_SECTOR_SIZE; - int n1; - - if ((offset + bytes) <= bs_size) { - return bytes; - } - - if (offset >= bs_size) { - n1 = 0; - } else { - n1 = bs_size - offset; - } - - qemu_iovec_memset(qiov, n1, 0, bytes - n1); - - return n1; -} - static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) { BDRVQcow2State *s = bs->opaque; - int offset_in_cluster, n1; + int offset_in_cluster; int ret; unsigned int cur_bytes; /* number of bytes in current iteration */ uint64_t cluster_offset = 0; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, case QCOW2_CLUSTER_UNALLOCATED: if (bs->backing) { - /* read from the base image */ - n1 = qcow2_backing_read1(bs->backing->bs, &hd_qiov, - offset, cur_bytes); - if (n1 > 0) { - QEMUIOVector local_qiov; - - qemu_iovec_init(&local_qiov, hd_qiov.niov); - qemu_iovec_concat(&local_qiov, &hd_qiov, 0, n1); - - BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); - qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_preadv(bs->backing, offset, n1, - &local_qiov, 0); - qemu_co_mutex_lock(&s->lock); - - qemu_iovec_destroy(&local_qiov); - - if (ret < 0) { - goto fail; - } + BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); + qemu_co_mutex_unlock(&s->lock); + ret = bdrv_co_preadv(bs->backing, offset, cur_bytes, + &hd_qiov, 0); + qemu_co_mutex_lock(&s->lock); + if (ret < 0) { + goto fail; } } else { /* Note: in this case, no need to wait */ -- 2.13.6 Removing a quorum child node with x-blockdev-change results in a quorum driver state that cannot be recreated with create options because it would require a list with gaps. This causes trouble in at least .bdrv_refresh_filename(). Document this problem so that we won't accidentally mark the command stable without having addressed it. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> --- qapi/block-core.json | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # does not support all kinds of operations, all kinds of children, nor # all block drivers. # +# FIXME Removing children from a quorum node means introducing gaps in the +# child indices. This cannot be represented in the 'children' list of +# BlockdevOptionsQuorum, as returned by .bdrv_refresh_filename(). +# # Warning: The data in a new quorum child MUST be consistent with that of # the rest of the array. # -- 2.13.6 From: Doug Gale <doug16k@gmail.com> Add trace output for commands, errors, and undefined behavior. Add guest error log output for undefined behavior. Report invalid undefined accesses to MMIO. Annotate unlikely error checks with unlikely. Signed-off-by: Doug Gale <doug16k@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/block/nvme.c | 349 ++++++++++++++++++++++++++++++++++++++++++-------- hw/block/trace-events | 93 ++++++++++++++ 2 files changed, 390 insertions(+), 52 deletions(-) diff --git a/hw/block/nvme.c b/hw/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nvme.c +++ b/hw/block/nvme.c @@ -XXX,XX +XXX,XX @@ #include "qapi/visitor.h" #include "sysemu/block-backend.h" +#include "qemu/log.h" +#include "trace.h" #include "nvme.h" +#define NVME_GUEST_ERR(trace, fmt, ...) \ + do { \ + (trace_##trace)(__VA_ARGS__); \ + qemu_log_mask(LOG_GUEST_ERROR, #trace \ + " in %s: " fmt "\n", __func__, ## __VA_ARGS__); \ + } while (0) + static void nvme_process_sq(void *opaque); static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size) @@ -XXX,XX +XXX,XX @@ static void nvme_isr_notify(NvmeCtrl *n, NvmeCQueue *cq) { if (cq->irq_enabled) { if (msix_enabled(&(n->parent_obj))) { + trace_nvme_irq_msix(cq->vector); msix_notify(&(n->parent_obj), cq->vector); } else { + trace_nvme_irq_pin(); pci_irq_pulse(&n->parent_obj); } + } else { + trace_nvme_irq_masked(); } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, trans_len = MIN(len, trans_len); int num_prps = (len >> n->page_bits) + 1; - if (!prp1) { + if (unlikely(!prp1)) { + trace_nvme_err_invalid_prp(); return NVME_INVALID_FIELD | NVME_DNR; } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr && prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, } len -= trans_len; if (len) { - if (!prp2) { + if (unlikely(!prp2)) { + trace_nvme_err_invalid_prp2_missing(); goto unmap; } if (len > n->page_size) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, uint64_t prp_ent = le64_to_cpu(prp_list[i]); if (i == n->max_prp_ents - 1 && len > n->page_size) { - if (!prp_ent || prp_ent & (n->page_size - 1)) { + if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + trace_nvme_err_invalid_prplist_ent(prp_ent); goto unmap; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, prp_ent = le64_to_cpu(prp_list[i]); } - if (!prp_ent || prp_ent & (n->page_size - 1)) { + if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + trace_nvme_err_invalid_prplist_ent(prp_ent); goto unmap; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, i++; } } else { - if (prp2 & (n->page_size - 1)) { + if (unlikely(prp2 & (n->page_size - 1))) { + trace_nvme_err_invalid_prp2_align(prp2); goto unmap; } if (qsg->nsg) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, QEMUIOVector iov; uint16_t status = NVME_SUCCESS; + trace_nvme_dma_read(prp1, prp2); + if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) { return NVME_INVALID_FIELD | NVME_DNR; } if (qsg.nsg > 0) { - if (dma_buf_read(ptr, len, &qsg)) { + if (unlikely(dma_buf_read(ptr, len, &qsg))) { + trace_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } qemu_sglist_destroy(&qsg); } else { - if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) { + if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) { + trace_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } qemu_iovec_destroy(&iov); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, uint64_t aio_slba = slba << (data_shift - BDRV_SECTOR_BITS); uint32_t aio_nlb = nlb << (data_shift - BDRV_SECTOR_BITS); - if (slba + nlb > ns->id_ns.nsze) { + if (unlikely(slba + nlb > ns->id_ns.nsze)) { + trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return NVME_LBA_RANGE | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0; enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ; - if ((slba + nlb) > ns->id_ns.nsze) { + trace_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba); + + if (unlikely((slba + nlb) > ns->id_ns.nsze)) { block_acct_invalid(blk_get_stats(n->conf.blk), acct); + trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return NVME_LBA_RANGE | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) NvmeNamespace *ns; uint32_t nsid = le32_to_cpu(cmd->nsid); - if (nsid == 0 || nsid > n->num_namespaces) { + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { + trace_nvme_err_invalid_ns(nsid, n->num_namespaces); return NVME_INVALID_NSID | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) case NVME_CMD_READ: return nvme_rw(n, ns, cmd, req); default: + trace_nvme_err_invalid_opc(cmd->opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd) NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); - if (!qid || nvme_check_sqid(n, qid)) { + if (unlikely(!qid || nvme_check_sqid(n, qid))) { + trace_nvme_err_invalid_del_sq(qid); return NVME_INVALID_QID | NVME_DNR; } + trace_nvme_del_sq(qid); + sq = n->sq[qid]; while (!QTAILQ_EMPTY(&sq->out_req_list)) { req = QTAILQ_FIRST(&sq->out_req_list); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd) uint16_t qflags = le16_to_cpu(c->sq_flags); uint64_t prp1 = le64_to_cpu(c->prp1); - if (!cqid || nvme_check_cqid(n, cqid)) { + trace_nvme_create_sq(prp1, sqid, cqid, qsize, qflags); + + if (unlikely(!cqid || nvme_check_cqid(n, cqid))) { + trace_nvme_err_invalid_create_sq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (!sqid || !nvme_check_sqid(n, sqid)) { + if (unlikely(!sqid || !nvme_check_sqid(n, sqid))) { + trace_nvme_err_invalid_create_sq_sqid(sqid); return NVME_INVALID_QID | NVME_DNR; } - if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + trace_nvme_err_invalid_create_sq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (!prp1 || prp1 & (n->page_size - 1)) { + if (unlikely(!prp1 || prp1 & (n->page_size - 1))) { + trace_nvme_err_invalid_create_sq_addr(prp1); return NVME_INVALID_FIELD | NVME_DNR; } - if (!(NVME_SQ_FLAGS_PC(qflags))) { + if (unlikely(!(NVME_SQ_FLAGS_PC(qflags)))) { + trace_nvme_err_invalid_create_sq_qflags(NVME_SQ_FLAGS_PC(qflags)); return NVME_INVALID_FIELD | NVME_DNR; } sq = g_malloc0(sizeof(*sq)); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd) NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); - if (!qid || nvme_check_cqid(n, qid)) { + if (unlikely(!qid || nvme_check_cqid(n, qid))) { + trace_nvme_err_invalid_del_cq_cqid(qid); return NVME_INVALID_CQID | NVME_DNR; } cq = n->cq[qid]; - if (!QTAILQ_EMPTY(&cq->sq_list)) { + if (unlikely(!QTAILQ_EMPTY(&cq->sq_list))) { + trace_nvme_err_invalid_del_cq_notempty(qid); return NVME_INVALID_QUEUE_DEL; } + trace_nvme_del_cq(qid); nvme_free_cq(cq, n); return NVME_SUCCESS; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd) uint16_t qflags = le16_to_cpu(c->cq_flags); uint64_t prp1 = le64_to_cpu(c->prp1); - if (!cqid || !nvme_check_cqid(n, cqid)) { + trace_nvme_create_cq(prp1, cqid, vector, qsize, qflags, + NVME_CQ_FLAGS_IEN(qflags) != 0); + + if (unlikely(!cqid || !nvme_check_cqid(n, cqid))) { + trace_nvme_err_invalid_create_cq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + trace_nvme_err_invalid_create_cq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (!prp1) { + if (unlikely(!prp1)) { + trace_nvme_err_invalid_create_cq_addr(prp1); return NVME_INVALID_FIELD | NVME_DNR; } - if (vector > n->num_queues) { + if (unlikely(vector > n->num_queues)) { + trace_nvme_err_invalid_create_cq_vector(vector); return NVME_INVALID_IRQ_VECTOR | NVME_DNR; } - if (!(NVME_CQ_FLAGS_PC(qflags))) { + if (unlikely(!(NVME_CQ_FLAGS_PC(qflags)))) { + trace_nvme_err_invalid_create_cq_qflags(NVME_CQ_FLAGS_PC(qflags)); return NVME_INVALID_FIELD | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c) uint64_t prp1 = le64_to_cpu(c->prp1); uint64_t prp2 = le64_to_cpu(c->prp2); + trace_nvme_identify_ctrl(); + return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl), prp1, prp2); } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c) uint64_t prp1 = le64_to_cpu(c->prp1); uint64_t prp2 = le64_to_cpu(c->prp2); - if (nsid == 0 || nsid > n->num_namespaces) { + trace_nvme_identify_ns(nsid); + + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { + trace_nvme_err_invalid_ns(nsid, n->num_namespaces); return NVME_INVALID_NSID | NVME_DNR; } ns = &n->namespaces[nsid - 1]; + return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns), prp1, prp2); } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c) uint16_t ret; int i, j = 0; + trace_nvme_identify_nslist(min_nsid); + list = g_malloc0(data_len); for (i = 0; i < n->num_namespaces; i++) { if (i < min_nsid) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd) case 0x02: return nvme_identify_nslist(n, c); default: + trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns)); return NVME_INVALID_FIELD | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) switch (dw10) { case NVME_VOLATILE_WRITE_CACHE: result = blk_enable_write_cache(n->conf.blk); + trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled"); break; case NVME_NUMBER_OF_QUEUES: result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16)); + trace_nvme_getfeat_numq(result); break; default: + trace_nvme_err_invalid_getfeat(dw10); return NVME_INVALID_FIELD | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) blk_set_enable_write_cache(n->conf.blk, dw11 & 1); break; case NVME_NUMBER_OF_QUEUES: + trace_nvme_setfeat_numq((dw11 & 0xFFFF) + 1, + ((dw11 >> 16) & 0xFFFF) + 1, + n->num_queues - 1, n->num_queues - 1); req->cqe.result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16)); break; default: + trace_nvme_err_invalid_setfeat(dw10); return NVME_INVALID_FIELD | NVME_DNR; } return NVME_SUCCESS; @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) case NVME_ADM_CMD_GET_FEATURES: return nvme_get_feature(n, cmd, req); default: + trace_nvme_err_invalid_admin_opc(cmd->opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static int nvme_start_ctrl(NvmeCtrl *n) uint32_t page_bits = NVME_CC_MPS(n->bar.cc) + 12; uint32_t page_size = 1 << page_bits; - if (n->cq[0] || n->sq[0] || !n->bar.asq || !n->bar.acq || - n->bar.asq & (page_size - 1) || n->bar.acq & (page_size - 1) || - NVME_CC_MPS(n->bar.cc) < NVME_CAP_MPSMIN(n->bar.cap) || - NVME_CC_MPS(n->bar.cc) > NVME_CAP_MPSMAX(n->bar.cap) || - NVME_CC_IOCQES(n->bar.cc) < NVME_CTRL_CQES_MIN(n->id_ctrl.cqes) || - NVME_CC_IOCQES(n->bar.cc) > NVME_CTRL_CQES_MAX(n->id_ctrl.cqes) || - NVME_CC_IOSQES(n->bar.cc) < NVME_CTRL_SQES_MIN(n->id_ctrl.sqes) || - NVME_CC_IOSQES(n->bar.cc) > NVME_CTRL_SQES_MAX(n->id_ctrl.sqes) || - !NVME_AQA_ASQS(n->bar.aqa) || !NVME_AQA_ACQS(n->bar.aqa)) { + if (unlikely(n->cq[0])) { + trace_nvme_err_startfail_cq(); + return -1; + } + if (unlikely(n->sq[0])) { + trace_nvme_err_startfail_sq(); + return -1; + } + if (unlikely(!n->bar.asq)) { + trace_nvme_err_startfail_nbarasq(); + return -1; + } + if (unlikely(!n->bar.acq)) { + trace_nvme_err_startfail_nbaracq(); + return -1; + } + if (unlikely(n->bar.asq & (page_size - 1))) { + trace_nvme_err_startfail_asq_misaligned(n->bar.asq); + return -1; + } + if (unlikely(n->bar.acq & (page_size - 1))) { + trace_nvme_err_startfail_acq_misaligned(n->bar.acq); + return -1; + } + if (unlikely(NVME_CC_MPS(n->bar.cc) < + NVME_CAP_MPSMIN(n->bar.cap))) { + trace_nvme_err_startfail_page_too_small( + NVME_CC_MPS(n->bar.cc), + NVME_CAP_MPSMIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_MPS(n->bar.cc) > + NVME_CAP_MPSMAX(n->bar.cap))) { + trace_nvme_err_startfail_page_too_large( + NVME_CC_MPS(n->bar.cc), + NVME_CAP_MPSMAX(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOCQES(n->bar.cc) < + NVME_CTRL_CQES_MIN(n->id_ctrl.cqes))) { + trace_nvme_err_startfail_cqent_too_small( + NVME_CC_IOCQES(n->bar.cc), + NVME_CTRL_CQES_MIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOCQES(n->bar.cc) > + NVME_CTRL_CQES_MAX(n->id_ctrl.cqes))) { + trace_nvme_err_startfail_cqent_too_large( + NVME_CC_IOCQES(n->bar.cc), + NVME_CTRL_CQES_MAX(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOSQES(n->bar.cc) < + NVME_CTRL_SQES_MIN(n->id_ctrl.sqes))) { + trace_nvme_err_startfail_sqent_too_small( + NVME_CC_IOSQES(n->bar.cc), + NVME_CTRL_SQES_MIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOSQES(n->bar.cc) > + NVME_CTRL_SQES_MAX(n->id_ctrl.sqes))) { + trace_nvme_err_startfail_sqent_too_large( + NVME_CC_IOSQES(n->bar.cc), + NVME_CTRL_SQES_MAX(n->bar.cap)); + return -1; + } + if (unlikely(!NVME_AQA_ASQS(n->bar.aqa))) { + trace_nvme_err_startfail_asqent_sz_zero(); + return -1; + } + if (unlikely(!NVME_AQA_ACQS(n->bar.aqa))) { + trace_nvme_err_startfail_acqent_sz_zero(); return -1; } @@ -XXX,XX +XXX,XX @@ static int nvme_start_ctrl(NvmeCtrl *n) static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, unsigned size) { + if (unlikely(offset & (sizeof(uint32_t) - 1))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_misaligned32, + "MMIO write not 32-bit aligned," + " offset=0x%"PRIx64"", offset); + /* should be ignored, fall through for now */ + } + + if (unlikely(size < sizeof(uint32_t))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_toosmall, + "MMIO write smaller than 32-bits," + " offset=0x%"PRIx64", size=%u", + offset, size); + /* should be ignored, fall through for now */ + } + switch (offset) { - case 0xc: + case 0xc: /* INTMS */ + if (unlikely(msix_enabled(&(n->parent_obj)))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix, + "undefined access to interrupt mask set" + " when MSI-X is enabled"); + /* should be ignored, fall through for now */ + } n->bar.intms |= data & 0xffffffff; n->bar.intmc = n->bar.intms; + trace_nvme_mmio_intm_set(data & 0xffffffff, + n->bar.intmc); break; - case 0x10: + case 0x10: /* INTMC */ + if (unlikely(msix_enabled(&(n->parent_obj)))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix, + "undefined access to interrupt mask clr" + " when MSI-X is enabled"); + /* should be ignored, fall through for now */ + } n->bar.intms &= ~(data & 0xffffffff); n->bar.intmc = n->bar.intms; + trace_nvme_mmio_intm_clr(data & 0xffffffff, + n->bar.intmc); break; - case 0x14: + case 0x14: /* CC */ + trace_nvme_mmio_cfg(data & 0xffffffff); /* Windows first sends data, then sends enable bit */ if (!NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc) && !NVME_CC_SHN(data) && !NVME_CC_SHN(n->bar.cc)) @@ -XXX,XX +XXX,XX @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, if (NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc)) { n->bar.cc = data; - if (nvme_start_ctrl(n)) { + if (unlikely(nvme_start_ctrl(n))) { + trace_nvme_err_startfail(); n->bar.csts = NVME_CSTS_FAILED; } else { + trace_nvme_mmio_start_success(); n->bar.csts = NVME_CSTS_READY; } } else if (!NVME_CC_EN(data) && NVME_CC_EN(n->bar.cc)) { + trace_nvme_mmio_stopped(); nvme_clear_ctrl(n); n->bar.csts &= ~NVME_CSTS_READY; } if (NVME_CC_SHN(data) && !(NVME_CC_SHN(n->bar.cc))) { - nvme_clear_ctrl(n); - n->bar.cc = data; - n->bar.csts |= NVME_CSTS_SHST_COMPLETE; + trace_nvme_mmio_shutdown_set(); + nvme_clear_ctrl(n); + n->bar.cc = data; + n->bar.csts |= NVME_CSTS_SHST_COMPLETE; } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(n->bar.cc)) { - n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE; - n->bar.cc = data; + trace_nvme_mmio_shutdown_cleared(); + n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE; + n->bar.cc = data; + } + break; + case 0x1C: /* CSTS */ + if (data & (1 << 4)) { + NVME_GUEST_ERR(nvme_ub_mmiowr_ssreset_w1c_unsupported, + "attempted to W1C CSTS.NSSRO" + " but CAP.NSSRS is zero (not supported)"); + } else if (data != 0) { + NVME_GUEST_ERR(nvme_ub_mmiowr_ro_csts, + "attempted to set a read only bit" + " of controller status"); + } + break; + case 0x20: /* NSSR */ + if (data == 0x4E564D65) { + trace_nvme_ub_mmiowr_ssreset_unsupported(); + } else { + /* The spec says that writes of other values have no effect */ + return; } break; - case 0x24: + case 0x24: /* AQA */ n->bar.aqa = data & 0xffffffff; + trace_nvme_mmio_aqattr(data & 0xffffffff); break; - case 0x28: + case 0x28: /* ASQ */ n->bar.asq = data; + trace_nvme_mmio_asqaddr(data); break; - case 0x2c: + case 0x2c: /* ASQ hi */ n->bar.asq |= data << 32; + trace_nvme_mmio_asqaddr_hi(data, n->bar.asq); break; - case 0x30: + case 0x30: /* ACQ */ + trace_nvme_mmio_acqaddr(data); n->bar.acq = data; break; - case 0x34: + case 0x34: /* ACQ hi */ n->bar.acq |= data << 32; + trace_nvme_mmio_acqaddr_hi(data, n->bar.acq); break; + case 0x38: /* CMBLOC */ + NVME_GUEST_ERR(nvme_ub_mmiowr_cmbloc_reserved, + "invalid write to reserved CMBLOC" + " when CMBSZ is zero, ignored"); + return; + case 0x3C: /* CMBSZ */ + NVME_GUEST_ERR(nvme_ub_mmiowr_cmbsz_readonly, + "invalid write to read only CMBSZ, ignored"); + return; default: + NVME_GUEST_ERR(nvme_ub_mmiowr_invalid, + "invalid MMIO write," + " offset=0x%"PRIx64", data=%"PRIx64"", + offset, data); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) uint8_t *ptr = (uint8_t *)&n->bar; uint64_t val = 0; + if (unlikely(addr & (sizeof(uint32_t) - 1))) { + NVME_GUEST_ERR(nvme_ub_mmiord_misaligned32, + "MMIO read not 32-bit aligned," + " offset=0x%"PRIx64"", addr); + /* should RAZ, fall through for now */ + } else if (unlikely(size < sizeof(uint32_t))) { + NVME_GUEST_ERR(nvme_ub_mmiord_toosmall, + "MMIO read smaller than 32-bits," + " offset=0x%"PRIx64"", addr); + /* should RAZ, fall through for now */ + } + if (addr < sizeof(n->bar)) { memcpy(&val, ptr + addr, size); + } else { + NVME_GUEST_ERR(nvme_ub_mmiord_invalid_ofs, + "MMIO read beyond last register," + " offset=0x%"PRIx64", returning 0", addr); } + return val; } @@ -XXX,XX +XXX,XX @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) { uint32_t qid; - if (addr & ((1 << 2) - 1)) { + if (unlikely(addr & ((1 << 2) - 1))) { + NVME_GUEST_ERR(nvme_ub_db_wr_misaligned, + "doorbell write not 32-bit aligned," + " offset=0x%"PRIx64", ignoring", addr); return; } if (((addr - 0x1000) >> 2) & 1) { + /* Completion queue doorbell write */ + uint16_t new_head = val & 0xffff; int start_sqs; NvmeCQueue *cq; qid = (addr - (0x1000 + (1 << 2))) >> 3; - if (nvme_check_cqid(n, qid)) { + if (unlikely(nvme_check_cqid(n, qid))) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cq, + "completion queue doorbell write" + " for nonexistent queue," + " sqid=%"PRIu32", ignoring", qid); return; } cq = n->cq[qid]; - if (new_head >= cq->size) { + if (unlikely(new_head >= cq->size)) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cqhead, + "completion queue doorbell write value" + " beyond queue size, sqid=%"PRIu32"," + " new_head=%"PRIu16", ignoring", + qid, new_head); return; } @@ -XXX,XX +XXX,XX @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) nvme_isr_notify(n, cq); } } else { + /* Submission queue doorbell write */ + uint16_t new_tail = val & 0xffff; NvmeSQueue *sq; qid = (addr - 0x1000) >> 3; - if (nvme_check_sqid(n, qid)) { + if (unlikely(nvme_check_sqid(n, qid))) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sq, + "submission queue doorbell write" + " for nonexistent queue," + " sqid=%"PRIu32", ignoring", qid); return; } sq = n->sq[qid]; - if (new_tail >= sq->size) { + if (unlikely(new_tail >= sq->size)) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sqtail, + "submission queue doorbell write value" + " beyond queue size, sqid=%"PRIu32"," + " new_tail=%"PRIu16", ignoring", + qid, new_tail); return; } diff --git a/hw/block/trace-events b/hw/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -XXX,XX +XXX,XX @@ virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint6 hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d" hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int trans) "blk %p CHS %u %u %u trans %d" +# hw/block/nvme.c +# nvme traces for successful events +nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u" +nvme_irq_pin(void) "pulsing IRQ pin" +nvme_irq_masked(void) "IRQ is masked" +nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" +nvme_rw(char const *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64"" +nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16"" +nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d" +nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16"" +nvme_del_cq(uint16_t cqid) "deleted completion queue, sqid=%"PRIu16"" +nvme_identify_ctrl(void) "identify controller" +nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16"" +nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16"" +nvme_getfeat_vwcache(char const* result) "get feature volatile write cache, result=%s" +nvme_getfeat_numq(int result) "get feature number of queues, result=%d" +nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d" +nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64"" +nvme_mmio_aqattr(uint64_t data) "wrote MMIO, admin queue attributes=0x%"PRIx64"" +nvme_mmio_asqaddr(uint64_t data) "wrote MMIO, admin submission queue address=0x%"PRIx64"" +nvme_mmio_acqaddr(uint64_t data) "wrote MMIO, admin completion queue address=0x%"PRIx64"" +nvme_mmio_asqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin submission queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +nvme_mmio_acqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin completion queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +nvme_mmio_start_success(void) "setting controller enable bit succeeded" +nvme_mmio_stopped(void) "cleared controller enable bit" +nvme_mmio_shutdown_set(void) "shutdown bit set" +nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" + +# nvme traces for error conditions +nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" +nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64"" +nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64"" +nvme_err_invalid_prp2_missing(void) "PRP2 is null and more data to be transferred" +nvme_err_invalid_field(void) "invalid field" +nvme_err_invalid_prp(void) "invalid PRP" +nvme_err_invalid_sgl(void) "invalid SGL" +nvme_err_invalid_ns(uint32_t ns, uint32_t limit) "invalid namespace %u not within 1-%u" +nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8"" +nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8"" +nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64"" +nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, sid=%"PRIu16"" +nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission queue, invalid cqid=%"PRIu16"" +nvme_err_invalid_create_sq_sqid(uint16_t sqid) "failed creating submission queue, invalid sqid=%"PRIu16"" +nvme_err_invalid_create_sq_size(uint16_t qsize) "failed creating submission queue, invalid qsize=%"PRIu16"" +nvme_err_invalid_create_sq_addr(uint64_t addr) "failed creating submission queue, addr=0x%"PRIx64"" +nvme_err_invalid_create_sq_qflags(uint16_t qflags) "failed creating submission queue, qflags=%"PRIu16"" +nvme_err_invalid_del_cq_cqid(uint16_t cqid) "failed deleting completion queue, cqid=%"PRIu16"" +nvme_err_invalid_del_cq_notempty(uint16_t cqid) "failed deleting completion queue, it is not empty, cqid=%"PRIu16"" +nvme_err_invalid_create_cq_cqid(uint16_t cqid) "failed creating completion queue, cqid=%"PRIu16"" +nvme_err_invalid_create_cq_size(uint16_t size) "failed creating completion queue, size=%"PRIu16"" +nvme_err_invalid_create_cq_addr(uint64_t addr) "failed creating completion queue, addr=0x%"PRIx64"" +nvme_err_invalid_create_cq_vector(uint16_t vector) "failed creating completion queue, vector=%"PRIu16"" +nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion queue, qflags=%"PRIu16"" +nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16"" +nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32"" +nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32"" +nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues" +nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues" +nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null" +nvme_err_startfail_nbaracq(void) "nvme_start_ctrl failed because the admin completion queue address is null" +nvme_err_startfail_asq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin submission queue address is misaligned: 0x%"PRIx64"" +nvme_err_startfail_acq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin completion queue address is misaligned: 0x%"PRIx64"" +nvme_err_startfail_page_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too small: log2size=%u, min=%u" +nvme_err_startfail_page_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too large: log2size=%u, max=%u" +nvme_err_startfail_cqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too small: log2size=%u, min=%u" +nvme_err_startfail_cqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too large: log2size=%u, max=%u" +nvme_err_startfail_sqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too small: log2size=%u, min=%u" +nvme_err_startfail_sqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too large: log2size=%u, max=%u" +nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the admin submission queue size is zero" +nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero" +nvme_err_startfail(void) "setting controller enable bit failed" + +# Traces for undefined behavior +nvme_ub_mmiowr_misaligned32(uint64_t offset) "MMIO write not 32-bit aligned, offset=0x%"PRIx64"" +nvme_ub_mmiowr_toosmall(uint64_t offset, unsigned size) "MMIO write smaller than 32 bits, offset=0x%"PRIx64", size=%u" +nvme_ub_mmiowr_intmask_with_msix(void) "undefined access to interrupt mask set when MSI-X is enabled" +nvme_ub_mmiowr_ro_csts(void) "attempted to set a read only bit of controller status" +nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CAP.NSSRS is zero (not supported)" +nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)" +nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored" +nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored" +nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64"" +nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64"" +nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64"" +nvme_ub_mmiord_invalid_ofs(uint64_t offset) "MMIO read beyond last register, offset=0x%"PRIx64", returning 0" +nvme_ub_db_wr_misaligned(uint64_t offset) "doorbell write not 32-bit aligned, offset=0x%"PRIx64", ignoring" +nvme_ub_db_wr_invalid_cq(uint32_t qid) "completion queue doorbell write for nonexistent queue, cqid=%"PRIu32", ignoring" +nvme_ub_db_wr_invalid_cqhead(uint32_t qid, uint16_t new_head) "completion queue doorbell write value beyond queue size, cqid=%"PRIu32", new_head=%"PRIu16", ignoring" +nvme_ub_db_wr_invalid_sq(uint32_t qid) "submission queue doorbell write for nonexistent queue, sqid=%"PRIu32", ignoring" +nvme_ub_db_wr_invalid_sqtail(uint32_t qid, uint16_t new_tail) "submission queue doorbell write value beyond queue size, sqid=%"PRIu32", new_head=%"PRIu16", ignoring" + # hw/block/xen_disk.c xen_disk_alloc(char *name) "%s" xen_disk_init(char *name) "%s" -- 2.13.6 From: Fam Zheng <famz@redhat.com> Management tools create overlays of running guests with qemu-img: $ qemu-img create -b /image/in/use.qcow2 -f qcow2 /overlay/image.qcow2 but this doesn't work anymore due to image locking: qemu-img: /overlay/image.qcow2: Failed to get shared "write" lock Is another process using the image? Could not open backing image to determine size. Use the force share option to allow this use case again. Cc: qemu-stable@nongnu.org Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Eric Blake <eblake@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 @@ void bdrv_img_create(const char *filename, const char *fmt, back_flags = flags; back_flags &= ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING); + backing_options = qdict_new(); if (backing_fmt) { - backing_options = qdict_new(); qdict_put_str(backing_options, "driver", backing_fmt); } + qdict_put_bool(backing_options, BDRV_OPT_FORCE_SHARE, true); bs = bdrv_open(full_backing, NULL, backing_options, back_flags, &local_err); -- 2.13.6 From: Thomas Huth <thuth@redhat.com> It's not working anymore since QEMU v1.3.0 - time to remove it now. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 11 ----------- qemu-doc.texi | 6 ------ 2 files changed, 17 deletions(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_legacy_drive_opts = { .type = QEMU_OPT_STRING, .help = "chs translation (auto, lba, none)", },{ - .name = "boot", - .type = QEMU_OPT_BOOL, - .help = "(deprecated, ignored)", - },{ .name = "addr", .type = QEMU_OPT_STRING, .help = "pci address (virtio only)", @@ -XXX,XX +XXX,XX @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type) goto fail; } - /* Deprecated option boot=[on|off] */ - if (qemu_opt_get(legacy_opts, "boot") != NULL) { - fprintf(stderr, "qemu-kvm: boot=on|off is deprecated and will be " - "ignored. Future versions will reject this parameter. Please " - "update your scripts.\n"); - } - /* Other deprecated options */ if (!qtest_enabled()) { for (i = 0; i < ARRAY_SIZE(deprecated); i++) { diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ deprecated. @section System emulator command line arguments -@subsection -drive boot=on|off (since 1.3.0) - -The ``boot=on|off'' option to the ``-drive'' argument is -ignored. Applications should use the ``bootindex=N'' parameter -to set an absolute ordering between devices instead. - @subsection -tdf (since 1.3.0) The ``-tdf'' argument is ignored. The behaviour implemented -- 2.13.6 From: Thomas Huth <thuth@redhat.com> It's been marked as deprecated since QEMU v2.10.0, and so far nobody complained that we should keep it, so let's remove this legacy option now to simplify the code quite a bit. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- vl.c | 86 ++------------------------------------------------------- qemu-doc.texi | 8 ------ qemu-options.hx | 19 ++----------- 3 files changed, 4 insertions(+), 109 deletions(-) diff --git a/vl.c b/vl.c index XXXXXXX..XXXXXXX 100644 --- a/vl.c +++ b/vl.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) const char *boot_order = NULL; const char *boot_once = NULL; DisplayState *ds; - int cyls, heads, secs, translation; QemuOpts *opts, *machine_opts; - QemuOpts *hda_opts = NULL, *icount_opts = NULL, *accel_opts = NULL; + QemuOpts *icount_opts = NULL, *accel_opts = NULL; QemuOptsList *olist; int optind; const char *optarg; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) cpu_model = NULL; snapshot = 0; - cyls = heads = secs = 0; - translation = BIOS_ATA_TRANSLATION_AUTO; nb_nics = 0; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) if (optind >= argc) break; if (argv[optind][0] != '-') { - hda_opts = drive_add(IF_DEFAULT, 0, argv[optind++], HD_OPTS); + drive_add(IF_DEFAULT, 0, argv[optind++], HD_OPTS); } else { const QEMUOption *popt; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) cpu_model = optarg; break; case QEMU_OPTION_hda: - { - char buf[256]; - if (cyls == 0) - snprintf(buf, sizeof(buf), "%s", HD_OPTS); - else - snprintf(buf, sizeof(buf), - "%s,cyls=%d,heads=%d,secs=%d%s", - HD_OPTS , cyls, heads, secs, - translation == BIOS_ATA_TRANSLATION_LBA ? - ",trans=lba" : - translation == BIOS_ATA_TRANSLATION_NONE ? - ",trans=none" : ""); - drive_add(IF_DEFAULT, 0, optarg, buf); - break; - } case QEMU_OPTION_hdb: case QEMU_OPTION_hdc: case QEMU_OPTION_hdd: @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) case QEMU_OPTION_snapshot: snapshot = 1; break; - case QEMU_OPTION_hdachs: - { - const char *p; - p = optarg; - cyls = strtol(p, (char **)&p, 0); - if (cyls < 1 || cyls > 16383) - goto chs_fail; - if (*p != ',') - goto chs_fail; - p++; - heads = strtol(p, (char **)&p, 0); - if (heads < 1 || heads > 16) - goto chs_fail; - if (*p != ',') - goto chs_fail; - p++; - secs = strtol(p, (char **)&p, 0); - if (secs < 1 || secs > 63) - goto chs_fail; - if (*p == ',') { - p++; - if (!strcmp(p, "large")) { - translation = BIOS_ATA_TRANSLATION_LARGE; - } else if (!strcmp(p, "rechs")) { - translation = BIOS_ATA_TRANSLATION_RECHS; - } else if (!strcmp(p, "none")) { - translation = BIOS_ATA_TRANSLATION_NONE; - } else if (!strcmp(p, "lba")) { - translation = BIOS_ATA_TRANSLATION_LBA; - } else if (!strcmp(p, "auto")) { - translation = BIOS_ATA_TRANSLATION_AUTO; - } else { - goto chs_fail; - } - } else if (*p != '\0') { - chs_fail: - error_report("invalid physical CHS format"); - exit(1); - } - if (hda_opts != NULL) { - qemu_opt_set_number(hda_opts, "cyls", cyls, - &error_abort); - qemu_opt_set_number(hda_opts, "heads", heads, - &error_abort); - qemu_opt_set_number(hda_opts, "secs", secs, - &error_abort); - if (translation == BIOS_ATA_TRANSLATION_LARGE) { - qemu_opt_set(hda_opts, "trans", "large", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_RECHS) { - qemu_opt_set(hda_opts, "trans", "rechs", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_LBA) { - qemu_opt_set(hda_opts, "trans", "lba", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_NONE) { - qemu_opt_set(hda_opts, "trans", "none", - &error_abort); - } - } - } - error_report("'-hdachs' is deprecated, please use '-device" - " ide-hd,cyls=c,heads=h,secs=s,...' instead"); - break; case QEMU_OPTION_numa: opts = qemu_opts_parse_noisily(qemu_find_opts("numa"), optarg, true); diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ The ``--net dump'' argument is now replaced with the ``-object filter-dump'' argument which works in combination with the modern ``-netdev`` backends instead. -@subsection -hdachs (since 2.10.0) - -The ``-hdachs'' argument is now a synonym for setting -the ``cyls'', ``heads'', ``secs'', and ``trans'' properties -on the ``ide-hd'' device using the ``-device'' argument. -The new syntax allows different settings to be provided -per disk. - @subsection -usbdevice (since 2.10.0) The ``-usbdevice DEV'' argument is now a synonym for setting diff --git a/qemu-options.hx b/qemu-options.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -XXX,XX +XXX,XX @@ of available connectors of a given interface type. @item media=@var{media} This option defines the type of the media: disk or cdrom. @item cyls=@var{c},heads=@var{h},secs=@var{s}[,trans=@var{t}] -These options have the same definition as they have in @option{-hdachs}. -These parameters are deprecated, use the corresponding parameters +Force disk physical geometry and the optional BIOS translation (trans=none or +lba). These parameters are deprecated, use the corresponding parameters of @code{-device} instead. @item snapshot=@var{snapshot} @var{snapshot} is "on" or "off" and controls snapshot mode for the given drive @@ -XXX,XX +XXX,XX @@ the raw disk image you use is not written back. You can however force the write back by pressing @key{C-a s} (@pxref{disk_images}). ETEXI -DEF("hdachs", HAS_ARG, QEMU_OPTION_hdachs, \ - "-hdachs c,h,s[,t]\n" \ - " force hard disk 0 physical geometry and the optional BIOS\n" \ - " translation (t=none or lba) (usually QEMU can guess them)\n", - QEMU_ARCH_ALL) -STEXI -@item -hdachs @var{c},@var{h},@var{s},[,@var{t}] -@findex -hdachs -Force hard disk 0 physical geometry (1 <= @var{c} <= 16383, 1 <= -@var{h} <= 16, 1 <= @var{s} <= 63) and optionally force the BIOS -translation mode (@var{t}=none, lba or auto). Usually QEMU can guess -all those parameters. This option is deprecated, please use -@code{-device ide-hd,cyls=c,heads=h,secs=s,...} instead. -ETEXI - DEF("fsdev", HAS_ARG, QEMU_OPTION_fsdev, "-fsdev fsdriver,id=id[,path=path,][security_model={mapped-xattr|mapped-file|passthrough|none}]\n" " [,writeout=immediate][,readonly][,socket=socket|sock_fd=sock_fd][,fmode=fmode][,dmode=dmode]\n" -- 2.13.6 From: Thomas Huth <thuth@redhat.com> Looks like we forgot to announce the deprecation of these options in the corresponding chapter of the qemu-doc text, so let's do that now. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-doc.texi | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ longer be directly supported in QEMU. The ``-drive if=scsi'' argument is replaced by the the ``-device BUS-TYPE'' argument combined with ``-drive if=none''. +@subsection -drive cyls=...,heads=...,secs=...,trans=... (since 2.10.0) + +The drive geometry arguments are replaced by the the geometry arguments +that can be specified with the ``-device'' parameter. + +@subsection -drive serial=... (since 2.10.0) + +The drive serial argument is replaced by the the serial argument +that can be specified with the ``-device'' parameter. + +@subsection -drive addr=... (since 2.10.0) + +The drive addr argument is replaced by the the addr argument +that can be specified with the ``-device'' parameter. + @subsection -net dump (since 2.10.0) The ``--net dump'' argument is now replaced with the -- 2.13.6 From: Fam Zheng <famz@redhat.com> Signed-off-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 1 - block/io.c | 18 ------------------ 2 files changed, 19 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 @@ bool blk_dev_is_tray_open(BlockBackend *blk); bool blk_dev_is_medium_locked(BlockBackend *blk); void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes); -bool bdrv_requests_pending(BlockDriverState *bs); void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out); void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in); 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 @@ void bdrv_disable_copy_on_read(BlockDriverState *bs) assert(old >= 1); } -/* Check if any requests are in-flight (including throttled requests) */ -bool bdrv_requests_pending(BlockDriverState *bs) -{ - BdrvChild *child; - - if (atomic_read(&bs->in_flight)) { - return true; - } - - QLIST_FOREACH(child, &bs->children, next) { - if (bdrv_requests_pending(child->bs)) { - return true; - } - } - - return false; -} - typedef struct { Coroutine *co; BlockDriverState *bs; -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/io.c | 6 ++++++ 1 file changed, 6 insertions(+) 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 @@ void bdrv_drain_all_begin(void) BdrvNextIterator it; GSList *aio_ctxs = NULL, *ctx; + /* BDRV_POLL_WHILE() for a node can only be called from its own I/O thread + * or the main loop AioContext. We potentially use BDRV_POLL_WHILE() on + * nodes in several different AioContexts, so make sure we're in the main + * context. */ + assert(qemu_get_current_aio_context() == qemu_get_aio_context()); + block_job_pause_all(); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { -- 2.13.6 bdrv_drained_begin() doesn't increase bs->quiesce_counter recursively and also doesn't notify other parent nodes of children, which both means that the child nodes are not actually drained, and bdrv_drained_begin() is providing useful functionality only on a single node. To keep things consistent, we also shouldn't call the block driver callbacks recursively. A proper recursive drain version that provides an actually working drained section for child nodes will be introduced later. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/io.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 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_drain_invoke_entry(void *opaque) } /* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */ -static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) +static void bdrv_drain_invoke(BlockDriverState *bs, bool begin, bool recursive) { BdrvChild *child, *tmp; BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin}; @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) bdrv_coroutine_enter(bs, data.co); BDRV_POLL_WHILE(bs, !data.done); - QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { - bdrv_drain_invoke(child->bs, begin); + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { + bdrv_drain_invoke(child->bs, begin, true); + } } } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) bdrv_parent_drained_begin(bs); } - bdrv_drain_invoke(bs, true); + bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) } /* Re-enable things in child-to-parent order */ - bdrv_drain_invoke(bs, false); + bdrv_drain_invoke(bs, false, false); bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); aio_disable_external(aio_context); bdrv_parent_drained_begin(bs); - bdrv_drain_invoke(bs, true); + bdrv_drain_invoke(bs, true, true); aio_context_release(aio_context); if (!g_slist_find(aio_ctxs, aio_context)) { @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); - bdrv_drain_invoke(bs, false); + bdrv_drain_invoke(bs, false, true); bdrv_parent_drained_end(bs); aio_enable_external(aio_context); aio_context_release(aio_context); -- 2.13.6 The existing test is for bdrv_drain_all_begin/end() only. Generalise the test case so that it can be run for the other variants as well. At the moment this is only bdrv_drain_begin/end(), but in a while, we'll add another one. Also, add a backing file to the test node to test whether the operations work recursively. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 69 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 62 insertions(+), 7 deletions(-) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_test = { .bdrv_co_drain_begin = bdrv_test_co_drain_begin, .bdrv_co_drain_end = bdrv_test_co_drain_end, + + .bdrv_child_perm = bdrv_format_default_perms, }; static void aio_ret_cb(void *opaque, int ret) @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) *aio_ret = ret; } -static void test_drv_cb_drain_all(void) +enum drain_type { + BDRV_DRAIN_ALL, + BDRV_DRAIN, +}; + +static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) +{ + switch (drain_type) { + case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break; + case BDRV_DRAIN: bdrv_drained_begin(bs); break; + default: g_assert_not_reached(); + } +} + +static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs) +{ + switch (drain_type) { + case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break; + case BDRV_DRAIN: bdrv_drained_end(bs); break; + default: g_assert_not_reached(); + } +} + +static void test_drv_cb_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; - BlockDriverState *bs; - BDRVTestState *s; + BlockDriverState *bs, *backing; + BDRVTestState *s, *backing_s; BlockAIOCB *acb; int aio_ret; @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_all(void) s = bs->opaque; blk_insert_bs(blk, bs, &error_abort); + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs, backing, &error_abort); + /* Simple bdrv_drain_all_begin/end pair, check that CBs are called */ g_assert_cmpint(s->drain_count, ==, 0); - bdrv_drain_all_begin(); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 1); - bdrv_drain_all_end(); + g_assert_cmpint(backing_s->drain_count, ==, !!recursive); + + do_drain_end(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); /* Now do the same while a request is pending */ aio_ret = -EINPROGRESS; @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_all(void) g_assert_cmpint(aio_ret, ==, -EINPROGRESS); g_assert_cmpint(s->drain_count, ==, 0); - bdrv_drain_all_begin(); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(drain_type, bs); + g_assert_cmpint(aio_ret, ==, 0); g_assert_cmpint(s->drain_count, ==, 1); - bdrv_drain_all_end(); + g_assert_cmpint(backing_s->drain_count, ==, !!recursive); + + do_drain_end(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + bdrv_unref(backing); bdrv_unref(bs); blk_unref(blk); } +static void test_drv_cb_drain_all(void) +{ + test_drv_cb_common(BDRV_DRAIN_ALL, true); +} + +static void test_drv_cb_drain(void) +{ + test_drv_cb_common(BDRV_DRAIN, false); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_init(&argc, &argv, NULL); g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); + g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); return g_test_run(); } -- 2.13.6 This is currently only working correctly for bdrv_drain(), not for bdrv_drain_all(). Leave a comment for the drain_all case, we'll address it later. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain(void) test_drv_cb_common(BDRV_DRAIN, false); } +static void test_quiesce_common(enum drain_type drain_type, bool recursive) +{ + BlockBackend *blk; + BlockDriverState *bs, *backing; + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + blk_insert_bs(blk, bs, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + bdrv_set_backing_hd(bs, backing, &error_abort); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + + do_drain_begin(drain_type, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, !!recursive); + + do_drain_end(drain_type, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs); + blk_unref(blk); +} + +static void test_quiesce_drain_all(void) +{ + // XXX drain_all doesn't quiesce + //test_quiesce_common(BDRV_DRAIN_ALL, true); +} + +static void test_quiesce_drain(void) +{ + test_quiesce_common(BDRV_DRAIN, false); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); + g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); + g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + return g_test_run(); } -- 2.13.6 Block jobs already paused themselves when their main BlockBackend entered a drained section. This is not good enough: We also want to pause a block job and may not submit new requests if, for example, the mirror target node should be drained. This implements .drained_begin/end callbacks in child_job in order to consider all block nodes related to the job, and removes the BlockBackend callbacks which are unnecessary now because the root of the job main BlockBackend is always referenced with a child_job, too. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static char *child_job_get_parent_desc(BdrvChild *c) job->id); } -static const BdrvChildRole child_job = { - .get_parent_desc = child_job_get_parent_desc, - .stay_at_node = true, -}; - -static void block_job_drained_begin(void *opaque) +static void child_job_drained_begin(BdrvChild *c) { - BlockJob *job = opaque; + BlockJob *job = c->opaque; block_job_pause(job); } -static void block_job_drained_end(void *opaque) +static void child_job_drained_end(BdrvChild *c) { - BlockJob *job = opaque; + BlockJob *job = c->opaque; block_job_resume(job); } -static const BlockDevOps block_job_dev_ops = { - .drained_begin = block_job_drained_begin, - .drained_end = block_job_drained_end, +static const BdrvChildRole child_job = { + .get_parent_desc = child_job_get_parent_desc, + .drained_begin = child_job_drained_begin, + .drained_end = child_job_drained_end, + .stay_at_node = true, }; void block_job_remove_all_bdrv(BlockJob *job) @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort); bs->job = job; - blk_set_dev_ops(blk, &block_job_dev_ops, job); bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker); QLIST_INSERT_HEAD(&block_jobs, job, job_list); -- 2.13.6 Block jobs must be paused if any of the involved nodes are drained. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 121 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "block/block.h" +#include "block/blockjob_int.h" #include "sysemu/block-backend.h" #include "qapi/error.h" @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } + +typedef struct TestBlockJob { + BlockJob common; + bool should_complete; +} TestBlockJob; + +static void test_job_completed(BlockJob *job, void *opaque) +{ + block_job_completed(job, 0); +} + +static void coroutine_fn test_job_start(void *opaque) +{ + TestBlockJob *s = opaque; + + while (!s->should_complete) { + block_job_sleep_ns(&s->common, 100000); + } + + block_job_defer_to_main_loop(&s->common, test_job_completed, NULL); +} + +static void test_job_complete(BlockJob *job, Error **errp) +{ + TestBlockJob *s = container_of(job, TestBlockJob, common); + s->should_complete = true; +} + +BlockJobDriver test_job_driver = { + .instance_size = sizeof(TestBlockJob), + .start = test_job_start, + .complete = test_job_complete, +}; + +static void test_blockjob_common(enum drain_type drain_type) +{ + BlockBackend *blk_src, *blk_target; + BlockDriverState *src, *target; + BlockJob *job; + int ret; + + src = bdrv_new_open_driver(&bdrv_test, "source", BDRV_O_RDWR, + &error_abort); + blk_src = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + blk_insert_bs(blk_src, src, &error_abort); + + target = bdrv_new_open_driver(&bdrv_test, "target", BDRV_O_RDWR, + &error_abort); + blk_target = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + blk_insert_bs(blk_target, target, &error_abort); + + job = block_job_create("job0", &test_job_driver, src, 0, BLK_PERM_ALL, 0, + 0, NULL, NULL, &error_abort); + block_job_add_bdrv(job, "target", target, 0, BLK_PERM_ALL, &error_abort); + block_job_start(job); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + do_drain_begin(drain_type, src); + + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target, and involves an + * additional block_job_pause_all() */ + g_assert_cmpint(job->pause_count, ==, 3); + } else { + g_assert_cmpint(job->pause_count, ==, 1); + } + /* XXX We don't wait until the job is actually paused. Is this okay? */ + /* g_assert_true(job->paused); */ + g_assert_false(job->busy); /* The job is paused */ + + do_drain_end(drain_type, src); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + do_drain_begin(drain_type, target); + + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target, and involves an + * additional block_job_pause_all() */ + g_assert_cmpint(job->pause_count, ==, 3); + } else { + g_assert_cmpint(job->pause_count, ==, 1); + } + /* XXX We don't wait until the job is actually paused. Is this okay? */ + /* g_assert_true(job->paused); */ + g_assert_false(job->busy); /* The job is paused */ + + do_drain_end(drain_type, target); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + ret = block_job_complete_sync(job, &error_abort); + g_assert_cmpint(ret, ==, 0); + + blk_unref(blk_src); + blk_unref(blk_target); + bdrv_unref(src); + bdrv_unref(target); +} + +static void test_blockjob_drain_all(void) +{ + test_blockjob_common(BDRV_DRAIN_ALL); +} + +static void test_blockjob_drain(void) +{ + test_blockjob_common(BDRV_DRAIN); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); + g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); + return g_test_run(); } -- 2.13.6 Block jobs are already paused using the BdrvChildRole drain callbacks, so we don't need an additional block_job_pause_all() call. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 4 ---- tests/test-bdrv-drain.c | 10 ++++------ 2 files changed, 4 insertions(+), 10 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 @@ void bdrv_drain_all_begin(void) * context. */ assert(qemu_get_current_aio_context() == qemu_get_aio_context()); - block_job_pause_all(); - for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); aio_context_release(aio_context); } - - block_job_resume_all(); } void bdrv_drain_all(void) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common(enum drain_type drain_type) do_drain_begin(drain_type, src); if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target, and involves an - * additional block_job_pause_all() */ - g_assert_cmpint(job->pause_count, ==, 3); + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->pause_count, ==, 2); } else { g_assert_cmpint(job->pause_count, ==, 1); } @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common(enum drain_type drain_type) do_drain_begin(drain_type, target); if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target, and involves an - * additional block_job_pause_all() */ - g_assert_cmpint(job->pause_count, ==, 3); + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->pause_count, ==, 2); } else { g_assert_cmpint(job->pause_count, ==, 1); } -- 2.13.6 bdrv_do_drained_begin() restricts the call of parent callbacks and aio_disable_external() to the outermost drain section, but the block driver callbacks are always called. bdrv_do_drained_end() must match this behaviour, otherwise nodes stay drained even if begin/end calls were balanced. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 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 @@ void bdrv_drained_begin(BlockDriverState *bs) void bdrv_drained_end(BlockDriverState *bs) { + int old_quiesce_counter; + if (qemu_in_coroutine()) { bdrv_co_yield_to_drain(bs, false); return; } assert(bs->quiesce_counter > 0); - if (atomic_fetch_dec(&bs->quiesce_counter) > 1) { - return; - } + old_quiesce_counter = atomic_fetch_dec(&bs->quiesce_counter); /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false, false); - bdrv_parent_drained_end(bs); - aio_enable_external(bdrv_get_aio_context(bs)); + if (old_quiesce_counter == 1) { + bdrv_parent_drained_end(bs); + aio_enable_external(bdrv_get_aio_context(bs)); + } } /* -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, + DRAIN_TYPE_MAX, }; static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } +static void test_nested(void) +{ + BlockBackend *blk; + BlockDriverState *bs, *backing; + BDRVTestState *s, *backing_s; + enum drain_type outer, inner; + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + s = bs->opaque; + blk_insert_bs(blk, bs, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs, backing, &error_abort); + + for (outer = 0; outer < DRAIN_TYPE_MAX; outer++) { + for (inner = 0; inner < DRAIN_TYPE_MAX; inner++) { + /* XXX bdrv_drain_all() doesn't increase the quiesce_counter */ + int bs_quiesce = (outer != BDRV_DRAIN_ALL) + + (inner != BDRV_DRAIN_ALL); + int backing_quiesce = 0; + int backing_cb_cnt = (outer != BDRV_DRAIN) + + (inner != BDRV_DRAIN); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(outer, bs); + do_drain_begin(inner, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, bs_quiesce); + g_assert_cmpint(backing->quiesce_counter, ==, backing_quiesce); + g_assert_cmpint(s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, backing_cb_cnt); + + do_drain_end(inner, bs); + do_drain_end(outer, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + } + } + + bdrv_unref(backing); + bdrv_unref(bs); + blk_unref(blk); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/nested", test_nested); + g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 This is in preparation for subtree drains, i.e. drained sections that affect not only a single node, but recursively all child nodes, too. Calling the parent callbacks for drain is pointless when we just came from that parent node recursively and leads to multiple increases of bs->quiesce_counter in a single drain call. Don't do it. In order for this to work correctly, the parent callback must be called for every bdrv_drain_begin/end() call, not only for the outermost one: If we have a node N with two parents A and B, recursive draining of A should cause the quiesce_counter of B to increase because its child N is drained independently of B. If now B is recursively drained, too, A must increase its quiesce_counter because N is drained independently of A only now, even if N is going from quiesce_counter 1 to 2. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 4 ++-- block.c | 13 +++++++++---- block/io.c | 47 ++++++++++++++++++++++++++++++++++------------- 3 files changed, 45 insertions(+), 19 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 @@ void bdrv_io_unplug(BlockDriverState *bs); * Begin a quiesced section of all users of @bs. This is part of * bdrv_drained_begin. */ -void bdrv_parent_drained_begin(BlockDriverState *bs); +void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore); /** * bdrv_parent_drained_end: @@ -XXX,XX +XXX,XX @@ void bdrv_parent_drained_begin(BlockDriverState *bs); * End a quiesced section of all users of @bs. This is part of * bdrv_drained_end. */ -void bdrv_parent_drained_end(BlockDriverState *bs); +void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore); /** * bdrv_drained_begin: 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_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs) { BlockDriverState *old_bs = child->bs; + int i; if (old_bs && new_bs) { assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)); } if (old_bs) { if (old_bs->quiesce_counter && child->role->drained_end) { - child->role->drained_end(child); + for (i = 0; i < old_bs->quiesce_counter; i++) { + child->role->drained_end(child); + } } if (child->role->detach) { child->role->detach(child); @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, if (new_bs) { QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent); if (new_bs->quiesce_counter && child->role->drained_begin) { - child->role->drained_begin(child); + for (i = 0; i < new_bs->quiesce_counter; i++) { + child->role->drained_begin(child); + } } if (child->role->attach) { @@ -XXX,XX +XXX,XX @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context) AioContext *ctx = bdrv_get_aio_context(bs); aio_disable_external(ctx); - bdrv_parent_drained_begin(bs); + bdrv_parent_drained_begin(bs, NULL); bdrv_drain(bs); /* ensure there are no in-flight requests */ while (aio_poll(ctx, false)) { @@ -XXX,XX +XXX,XX @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context) */ aio_context_acquire(new_context); bdrv_attach_aio_context(bs, new_context); - bdrv_parent_drained_end(bs); + bdrv_parent_drained_end(bs, NULL); aio_enable_external(ctx); aio_context_release(new_context); } 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_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags); -void bdrv_parent_drained_begin(BlockDriverState *bs) +void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c, *next; QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { + if (c == ignore) { + continue; + } if (c->role->drained_begin) { c->role->drained_begin(c); } } } -void bdrv_parent_drained_end(BlockDriverState *bs) +void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c, *next; QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { + if (c == ignore) { + continue; + } if (c->role->drained_end) { c->role->drained_end(c); } @@ -XXX,XX +XXX,XX @@ typedef struct { BlockDriverState *bs; bool done; bool begin; + BdrvChild *parent; } BdrvCoDrainData; static void coroutine_fn bdrv_drain_invoke_entry(void *opaque) @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs) return waited; } +static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent); +static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent); + static void bdrv_co_drain_bh_cb(void *opaque) { BdrvCoDrainData *data = opaque; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); if (data->begin) { - bdrv_drained_begin(bs); + bdrv_do_drained_begin(bs, data->parent); } else { - bdrv_drained_end(bs); + bdrv_do_drained_end(bs, data->parent); } data->done = true; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, - bool begin) + bool begin, BdrvChild *parent) { BdrvCoDrainData data; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, .bs = bs, .done = false, .begin = begin, + .parent = parent, }; bdrv_inc_in_flight(bs); aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -void bdrv_drained_begin(BlockDriverState *bs) +static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) { if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, true); + bdrv_co_yield_to_drain(bs, true, parent); return; } /* Stop things in parent-to-child order */ if (atomic_fetch_inc(&bs->quiesce_counter) == 0) { aio_disable_external(bdrv_get_aio_context(bs)); - bdrv_parent_drained_begin(bs); } + bdrv_parent_drained_begin(bs, parent); bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); } -void bdrv_drained_end(BlockDriverState *bs) +void bdrv_drained_begin(BlockDriverState *bs) +{ + bdrv_do_drained_begin(bs, NULL); +} + +static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) { int old_quiesce_counter; if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, false); + bdrv_co_yield_to_drain(bs, false, parent); return; } assert(bs->quiesce_counter > 0); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false, false); + bdrv_parent_drained_end(bs, parent); if (old_quiesce_counter == 1) { - bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } } +void bdrv_drained_end(BlockDriverState *bs) +{ + bdrv_do_drained_end(bs, NULL); +} + /* * Wait for pending requests to complete on a single BlockDriverState subtree, * and suspend block driver's internal I/O until next request arrives. @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) /* Stop things in parent-to-child order */ aio_context_acquire(aio_context); aio_disable_external(aio_context); - bdrv_parent_drained_begin(bs); + bdrv_parent_drained_begin(bs, NULL); bdrv_drain_invoke(bs, true, true); aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); bdrv_drain_invoke(bs, false, true); - bdrv_parent_drained_end(bs); + bdrv_parent_drained_end(bs, NULL); aio_enable_external(aio_context); aio_context_release(aio_context); } -- 2.13.6 bdrv_drained_begin() waits for the completion of requests in the whole subtree, but it only actually keeps its immediate bs parameter quiesced until bdrv_drained_end(). Add a version that keeps the whole subtree drained. As of this commit, graph changes cannot be allowed during a subtree drained section, but this will be fixed soon. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 13 +++++++++++++ block/io.c | 54 ++++++++++++++++++++++++++++++++++++++++----------- 2 files changed, 56 insertions(+), 11 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 @@ void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore); void bdrv_drained_begin(BlockDriverState *bs); /** + * Like bdrv_drained_begin, but recursively begins a quiesced section for + * exclusive access to all child nodes as well. + * + * Graph changes are not allowed during a subtree drain section. + */ +void bdrv_subtree_drained_begin(BlockDriverState *bs); + +/** * bdrv_drained_end: * * End a quiescent section started by bdrv_drained_begin(). */ void bdrv_drained_end(BlockDriverState *bs); +/** + * End a quiescent section started by bdrv_subtree_drained_begin(). + */ +void bdrv_subtree_drained_end(BlockDriverState *bs); + void bdrv_add_child(BlockDriverState *parent, BlockDriverState *child, Error **errp); void bdrv_del_child(BlockDriverState *parent, BdrvChild *child, Error **errp); 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 @@ typedef struct { BlockDriverState *bs; bool done; bool begin; + bool recursive; BdrvChild *parent; } BdrvCoDrainData; @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs) return waited; } -static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent); -static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent); +static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent); +static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent); static void bdrv_co_drain_bh_cb(void *opaque) { @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); if (data->begin) { - bdrv_do_drained_begin(bs, data->parent); + bdrv_do_drained_begin(bs, data->recursive, data->parent); } else { - bdrv_do_drained_end(bs, data->parent); + bdrv_do_drained_end(bs, data->recursive, data->parent); } data->done = true; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, - bool begin, BdrvChild *parent) + bool begin, bool recursive, + BdrvChild *parent) { BdrvCoDrainData data; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, .bs = bs, .done = false, .begin = begin, + .recursive = recursive, .parent = parent, }; bdrv_inc_in_flight(bs); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) +static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { + BdrvChild *child, *next; + if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, true, parent); + bdrv_co_yield_to_drain(bs, true, recursive, parent); return; } @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) bdrv_parent_drained_begin(bs, parent); bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); + + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, next) { + bdrv_do_drained_begin(child->bs, true, child); + } + } } void bdrv_drained_begin(BlockDriverState *bs) { - bdrv_do_drained_begin(bs, NULL); + bdrv_do_drained_begin(bs, false, NULL); +} + +void bdrv_subtree_drained_begin(BlockDriverState *bs) +{ + bdrv_do_drained_begin(bs, true, NULL); } -static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) +static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { + BdrvChild *child, *next; int old_quiesce_counter; if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, false, parent); + bdrv_co_yield_to_drain(bs, false, recursive, parent); return; } assert(bs->quiesce_counter > 0); @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) if (old_quiesce_counter == 1) { aio_enable_external(bdrv_get_aio_context(bs)); } + + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, next) { + bdrv_do_drained_end(child->bs, true, child); + } + } } void bdrv_drained_end(BlockDriverState *bs) { - bdrv_do_drained_end(bs, NULL); + bdrv_do_drained_end(bs, false, NULL); +} + +void bdrv_subtree_drained_end(BlockDriverState *bs) +{ + bdrv_do_drained_end(bs, true, NULL); } /* -- 2.13.6 Add a subtree drain version to the existing test cases. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, + BDRV_SUBTREE_DRAIN, DRAIN_TYPE_MAX, }; @@ -XXX,XX +XXX,XX @@ static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) switch (drain_type) { case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break; case BDRV_DRAIN: bdrv_drained_begin(bs); break; + case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_begin(bs); break; default: g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs) switch (drain_type) { case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break; case BDRV_DRAIN: bdrv_drained_end(bs); break; + case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_end(bs); break; default: g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain(void) test_drv_cb_common(BDRV_DRAIN, false); } +static void test_drv_cb_drain_subtree(void) +{ + test_drv_cb_common(BDRV_SUBTREE_DRAIN, true); +} + static void test_quiesce_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } +static void test_quiesce_drain_subtree(void) +{ + test_quiesce_common(BDRV_SUBTREE_DRAIN, true); +} + static void test_nested(void) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_nested(void) /* XXX bdrv_drain_all() doesn't increase the quiesce_counter */ int bs_quiesce = (outer != BDRV_DRAIN_ALL) + (inner != BDRV_DRAIN_ALL); - int backing_quiesce = 0; + int backing_quiesce = (outer == BDRV_SUBTREE_DRAIN) + + (inner == BDRV_SUBTREE_DRAIN); int backing_cb_cnt = (outer != BDRV_DRAIN) + (inner != BDRV_DRAIN); @@ -XXX,XX +XXX,XX @@ static void test_blockjob_drain(void) test_blockjob_common(BDRV_DRAIN); } +static void test_blockjob_drain_subtree(void) +{ + test_blockjob_common(BDRV_SUBTREE_DRAIN); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); + g_test_add_func("/bdrv-drain/driver-cb/drain_subtree", + test_drv_cb_drain_subtree); g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/quiesce/drain_subtree", + test_quiesce_drain_subtree); g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); + g_test_add_func("/bdrv-drain/blockjob/drain_subtree", + test_blockjob_drain_subtree); return g_test_run(); } -- 2.13.6 If bdrv_do_drained_begin/end() are called in coroutine context, they first use a BH to get out of the coroutine context. Call some existing tests again from a coroutine to cover this code path. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) *aio_ret = ret; } +typedef struct CallInCoroutineData { + void (*entry)(void); + bool done; +} CallInCoroutineData; + +static coroutine_fn void call_in_coroutine_entry(void *opaque) +{ + CallInCoroutineData *data = opaque; + + data->entry(); + data->done = true; +} + +static void call_in_coroutine(void (*entry)(void)) +{ + Coroutine *co; + CallInCoroutineData data = { + .entry = entry, + .done = false, + }; + + co = qemu_coroutine_create(call_in_coroutine_entry, &data); + qemu_coroutine_enter(co); + while (!data.done) { + aio_poll(qemu_get_aio_context(), true); + } +} + enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_subtree(void) test_drv_cb_common(BDRV_SUBTREE_DRAIN, true); } +static void test_drv_cb_co_drain(void) +{ + call_in_coroutine(test_drv_cb_drain); +} + +static void test_drv_cb_co_drain_subtree(void) +{ + call_in_coroutine(test_drv_cb_drain_subtree); +} + static void test_quiesce_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain_subtree(void) test_quiesce_common(BDRV_SUBTREE_DRAIN, true); } +static void test_quiesce_co_drain(void) +{ + call_in_coroutine(test_quiesce_drain); +} + +static void test_quiesce_co_drain_subtree(void) +{ + call_in_coroutine(test_quiesce_drain_subtree); +} + static void test_nested(void) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_subtree", test_drv_cb_drain_subtree); + // XXX bdrv_drain_all() doesn't work in coroutine context + g_test_add_func("/bdrv-drain/driver-cb/co/drain", test_drv_cb_co_drain); + g_test_add_func("/bdrv-drain/driver-cb/co/drain_subtree", + test_drv_cb_co_drain_subtree); + + g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); g_test_add_func("/bdrv-drain/quiesce/drain_subtree", test_quiesce_drain_subtree); + // XXX bdrv_drain_all() doesn't work in coroutine context + g_test_add_func("/bdrv-drain/quiesce/co/drain", test_quiesce_co_drain); + g_test_add_func("/bdrv-drain/quiesce/co/drain_subtree", + test_quiesce_co_drain_subtree); + g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); -- 2.13.6 Test that drain sections are correctly propagated through the graph. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_nested(void) blk_unref(blk); } +static void test_multiparent(void) +{ + BlockBackend *blk_a, *blk_b; + BlockDriverState *bs_a, *bs_b, *backing; + BDRVTestState *a_s, *b_s, *backing_s; + + blk_a = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR, + &error_abort); + a_s = bs_a->opaque; + blk_insert_bs(blk_a, bs_a, &error_abort); + + blk_b = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR, + &error_abort); + b_s = bs_b->opaque; + blk_insert_bs(blk_b, bs_b, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs_a, backing, &error_abort); + bdrv_set_backing_hd(bs_b, backing, &error_abort); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 1); + g_assert_cmpint(bs_b->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, 1); + g_assert_cmpint(a_s->drain_count, ==, 1); + g_assert_cmpint(b_s->drain_count, ==, 1); + g_assert_cmpint(backing_s->drain_count, ==, 1); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 2); + g_assert_cmpint(bs_b->quiesce_counter, ==, 2); + g_assert_cmpint(backing->quiesce_counter, ==, 2); + g_assert_cmpint(a_s->drain_count, ==, 2); + g_assert_cmpint(b_s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, 2); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 1); + g_assert_cmpint(bs_b->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, 1); + g_assert_cmpint(a_s->drain_count, ==, 1); + g_assert_cmpint(b_s->drain_count, ==, 1); + g_assert_cmpint(backing_s->drain_count, ==, 1); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs_a); + bdrv_unref(bs_b); + blk_unref(blk_a); + blk_unref(blk_b); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) test_quiesce_co_drain_subtree); g_test_add_func("/bdrv-drain/nested", test_nested); + g_test_add_func("/bdrv-drain/multiparent", test_multiparent); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 We need to remember how many of the drain sections in which a node is were recursive (i.e. subtree drain rather than node drain), so that they can be correctly applied when children are added or removed during the drained section. With this change, it is safe to modify the graph even inside a bdrv_subtree_drained_begin/end() section. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 2 -- include/block/block_int.h | 5 +++++ block.c | 32 +++++++++++++++++++++++++++++--- block/io.c | 28 ++++++++++++++++++++++++---- 4 files changed, 58 insertions(+), 9 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 @@ void bdrv_drained_begin(BlockDriverState *bs); /** * Like bdrv_drained_begin, but recursively begins a quiesced section for * exclusive access to all child nodes as well. - * - * Graph changes are not allowed during a subtree drain section. */ void bdrv_subtree_drained_begin(BlockDriverState *bs); 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 BlockDriverState { /* Accessed with atomic ops. */ int quiesce_counter; + int recursive_quiesce_counter; + unsigned int write_gen; /* Current data generation */ /* Protected by reqs_lock. */ @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); +void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent); +void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent); + int get_tmp_filename(char *filename, int size); BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size, const char *filename); 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_drained_end(BdrvChild *child) bdrv_drained_end(bs); } +static void bdrv_child_cb_attach(BdrvChild *child) +{ + BlockDriverState *bs = child->opaque; + bdrv_apply_subtree_drain(child, bs); +} + +static void bdrv_child_cb_detach(BdrvChild *child) +{ + BlockDriverState *bs = child->opaque; + bdrv_unapply_subtree_drain(child, bs); +} + static int bdrv_child_cb_inactivate(BdrvChild *child) { BlockDriverState *bs = child->opaque; @@ -XXX,XX +XXX,XX @@ const BdrvChildRole child_file = { .inherit_options = bdrv_inherited_options, .drained_begin = bdrv_child_cb_drained_begin, .drained_end = bdrv_child_cb_drained_end, + .attach = bdrv_child_cb_attach, + .detach = bdrv_child_cb_detach, .inactivate = bdrv_child_cb_inactivate, }; @@ -XXX,XX +XXX,XX @@ const BdrvChildRole child_format = { .inherit_options = bdrv_inherited_fmt_options, .drained_begin = bdrv_child_cb_drained_begin, .drained_end = bdrv_child_cb_drained_end, + .attach = bdrv_child_cb_attach, + .detach = bdrv_child_cb_detach, .inactivate = bdrv_child_cb_inactivate, }; @@ -XXX,XX +XXX,XX @@ static void bdrv_backing_attach(BdrvChild *c) parent->backing_blocker); bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET, parent->backing_blocker); + + bdrv_child_cb_attach(c); } static void bdrv_backing_detach(BdrvChild *c) @@ -XXX,XX +XXX,XX @@ static void bdrv_backing_detach(BdrvChild *c) bdrv_op_unblock_all(c->bs, parent->backing_blocker); error_free(parent->backing_blocker); parent->backing_blocker = NULL; + + bdrv_child_cb_detach(c); } /* @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)); } if (old_bs) { + /* Detach first so that the recursive drain sections coming from @child + * are already gone and we only end the drain sections that came from + * elsewhere. */ + if (child->role->detach) { + child->role->detach(child); + } if (old_bs->quiesce_counter && child->role->drained_end) { for (i = 0; i < old_bs->quiesce_counter; i++) { child->role->drained_end(child); } } - if (child->role->detach) { - child->role->detach(child); - } QLIST_REMOVE(child, next_parent); } @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, } } + /* Attach only after starting new drained sections, so that recursive + * drain sections coming from @child don't get an extra .drained_begin + * callback. */ if (child->role->attach) { child->role->attach(child); } 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_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, - BdrvChild *parent) +void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { BdrvChild *child, *next; @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, bdrv_drain_recurse(bs); if (recursive) { + bs->recursive_quiesce_counter++; QLIST_FOREACH_SAFE(child, &bs->children, next, next) { bdrv_do_drained_begin(child->bs, true, child); } @@ -XXX,XX +XXX,XX @@ void bdrv_subtree_drained_begin(BlockDriverState *bs) bdrv_do_drained_begin(bs, true, NULL); } -static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, - BdrvChild *parent) +void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { BdrvChild *child, *next; int old_quiesce_counter; @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, } if (recursive) { + bs->recursive_quiesce_counter--; QLIST_FOREACH_SAFE(child, &bs->children, next, next) { bdrv_do_drained_end(child->bs, true, child); } @@ -XXX,XX +XXX,XX @@ void bdrv_subtree_drained_end(BlockDriverState *bs) bdrv_do_drained_end(bs, true, NULL); } +void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent) +{ + int i; + + for (i = 0; i < new_parent->recursive_quiesce_counter; i++) { + bdrv_do_drained_begin(child->bs, true, child); + } +} + +void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent) +{ + int i; + + for (i = 0; i < old_parent->recursive_quiesce_counter; i++) { + bdrv_do_drained_end(child->bs, true, child); + } +} + /* * Wait for pending requests to complete on a single BlockDriverState subtree, * and suspend block driver's internal I/O until next request arrives. -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_multiparent(void) blk_unref(blk_b); } +static void test_graph_change(void) +{ + BlockBackend *blk_a, *blk_b; + BlockDriverState *bs_a, *bs_b, *backing; + BDRVTestState *a_s, *b_s, *backing_s; + + blk_a = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR, + &error_abort); + a_s = bs_a->opaque; + blk_insert_bs(blk_a, bs_a, &error_abort); + + blk_b = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR, + &error_abort); + b_s = bs_b->opaque; + blk_insert_bs(blk_b, bs_b, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs_a, backing, &error_abort); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + + bdrv_set_backing_hd(bs_b, backing, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 5); + g_assert_cmpint(bs_b->quiesce_counter, ==, 5); + g_assert_cmpint(backing->quiesce_counter, ==, 5); + g_assert_cmpint(a_s->drain_count, ==, 5); + g_assert_cmpint(b_s->drain_count, ==, 5); + g_assert_cmpint(backing_s->drain_count, ==, 5); + + bdrv_set_backing_hd(bs_b, NULL, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 3); + g_assert_cmpint(bs_b->quiesce_counter, ==, 2); + g_assert_cmpint(backing->quiesce_counter, ==, 3); + g_assert_cmpint(a_s->drain_count, ==, 3); + g_assert_cmpint(b_s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, 3); + + bdrv_set_backing_hd(bs_b, backing, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 5); + g_assert_cmpint(bs_b->quiesce_counter, ==, 5); + g_assert_cmpint(backing->quiesce_counter, ==, 5); + g_assert_cmpint(a_s->drain_count, ==, 5); + g_assert_cmpint(b_s->drain_count, ==, 5); + g_assert_cmpint(backing_s->drain_count, ==, 5); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs_a); + bdrv_unref(bs_b); + blk_unref(blk_a); + blk_unref(blk_b); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/multiparent", test_multiparent); + g_test_add_func("/bdrv-drain/graph-change", test_graph_change); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 Since commit bde70715, base is the only node that is reopened in commit_start(). This means that the code, which still involves an explicit BlockReopenQueue, can now be simplified by using bdrv_reopen(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/commit.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, const char *filter_node_name, Error **errp) { CommitBlockJob *s; - BlockReopenQueue *reopen_queue = NULL; int orig_base_flags; BlockDriverState *iter; BlockDriverState *commit_top_bs = NULL; @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, /* convert base to r/w, if necessary */ orig_base_flags = bdrv_get_flags(base); if (!(orig_base_flags & BDRV_O_RDWR)) { - reopen_queue = bdrv_reopen_queue(reopen_queue, base, NULL, - orig_base_flags | BDRV_O_RDWR); - } - - if (reopen_queue) { - bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err); + bdrv_reopen(base, orig_base_flags | BDRV_O_RDWR, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); goto fail; -- 2.13.6 The bdrv_reopen*() implementation doesn't like it if the graph is changed between queuing nodes for reopen and actually reopening them (one of the reasons is that queuing can be recursive). So instead of draining the device only in bdrv_reopen_multiple(), require that callers already drained all affected nodes, and assert this in bdrv_reopen_queue(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block.c | 23 ++++++++++++++++------- block/replication.c | 6 ++++++ qemu-io-cmds.c | 3 +++ 3 files changed, 25 insertions(+), 7 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_open(const char *filename, const char *reference, * returns a pointer to bs_queue, which is either the newly allocated * bs_queue, or the existing bs_queue being used. * + * bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple(). */ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, BdrvChild *child; QDict *old_options, *explicit_options; + /* Make sure that the caller remembered to use a drained section. This is + * important to avoid graph changes between the recursive queuing here and + * bdrv_reopen_multiple(). */ + assert(bs->quiesce_counter > 0); + if (bs_queue == NULL) { bs_queue = g_new0(BlockReopenQueue, 1); QSIMPLEQ_INIT(bs_queue); @@ -XXX,XX +XXX,XX @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, * If all devices prepare successfully, then the changes are committed * to all devices. * + * All affected nodes must be drained between bdrv_reopen_queue() and + * bdrv_reopen_multiple(). */ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **errp) { @@ -XXX,XX +XXX,XX @@ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **er assert(bs_queue != NULL); - aio_context_release(ctx); - bdrv_drain_all_begin(); - aio_context_acquire(ctx); - QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) { + assert(bs_entry->state.bs->quiesce_counter > 0); if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, &local_err)) { error_propagate(errp, local_err); goto cleanup; @@ -XXX,XX +XXX,XX @@ cleanup: } g_free(bs_queue); - bdrv_drain_all_end(); - return ret; } @@ -XXX,XX +XXX,XX @@ int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp) { int ret = -1; Error *local_err = NULL; - BlockReopenQueue *queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags); + BlockReopenQueue *queue; + bdrv_subtree_drained_begin(bs); + + queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags); ret = bdrv_reopen_multiple(bdrv_get_aio_context(bs), queue, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); } + + bdrv_subtree_drained_end(bs); + return ret; } 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 void reopen_backing_file(BlockDriverState *bs, bool writable, new_secondary_flags = s->orig_secondary_flags; } + bdrv_subtree_drained_begin(s->hidden_disk->bs); + bdrv_subtree_drained_begin(s->secondary_disk->bs); + if (orig_hidden_flags != new_hidden_flags) { reopen_queue = bdrv_reopen_queue(reopen_queue, s->hidden_disk->bs, NULL, new_hidden_flags); @@ -XXX,XX +XXX,XX @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, reopen_queue, &local_err); error_propagate(errp, local_err); } + + bdrv_subtree_drained_end(s->hidden_disk->bs); + bdrv_subtree_drained_end(s->secondary_disk->bs); } static void backup_job_cleanup(BlockDriverState *bs) 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 reopen_f(BlockBackend *blk, int argc, char **argv) opts = qopts ? qemu_opts_to_qdict(qopts, NULL) : NULL; qemu_opts_reset(&reopen_opts); + bdrv_subtree_drained_begin(bs); brq = bdrv_reopen_queue(NULL, bs, opts, flags); bdrv_reopen_multiple(bdrv_get_aio_context(bs), brq, &local_err); + bdrv_subtree_drained_end(bs); + if (local_err) { error_report_err(local_err); } else { -- 2.13.6