The following changes since commit 6c599282f8ab382fe59f03a6cae755b89561a7b3: Merge remote-tracking branch 'remotes/armbru/tags/pull-monitor-2020-02-15-v2' into staging (2020-02-17 13:32:25 +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 c45a88f4429d7a8f384b75f3fd3fed5138a6edca: iotests: Check that @replaces can replace filters (2020-02-18 14:52:16 +0100) ---------------------------------------------------------------- Block layer patches: - Fix check_to_replace_node() - commit: Expose on-error option in QMP - qcow2: Fix qcow2_alloc_cluster_abort() for external data file - mirror: Fix deadlock - vvfat: Fix segfault while closing read-write node - Code cleanups ---------------------------------------------------------------- Alberto Garcia (1): qcow2: Fix alignment checks in encrypted images Hikaru Nishida (1): block/vvfat: Do not unref qcow on closing backing bdrv Kevin Wolf (12): mirror: Store MirrorOp.co for debuggability mirror: Don't let an operation wait for itself qcow2: update_refcount(): Reset old_table_index after qcow2_cache_put() qcow2: Fix qcow2_alloc_cluster_abort() for external data file iotests: Test copy offloading with external data file qapi: Document meaning of 'ignore' BlockdevOnError for jobs commit: Remove unused bytes_written commit: Fix argument order for block_job_error_action() commit: Inline commit_populate() commit: Fix is_read for block_job_error_action() commit: Expose on-error option in QMP iotests: Test error handling policies with block-commit Max Reitz (19): blockdev: Allow external snapshots everywhere blockdev: Allow resizing everywhere block: Drop bdrv_is_first_non_filter() iotests: Let 041 use -blockdev for quorum children quorum: Fix child permissions block: Add bdrv_recurse_can_replace() blkverify: Implement .bdrv_recurse_can_replace() quorum: Implement .bdrv_recurse_can_replace() block: Use bdrv_recurse_can_replace() block: Remove bdrv_recurse_is_first_non_filter() mirror: Double-check immediately before replacing quorum: Stop marking it as a filter iotests: Use complete_and_wait() in 155 iotests: Add VM.assert_block_path() iotests/041: Drop superfluous shutdowns iotests: Resolve TODOs in 041 iotests: Use self.image_len in TestRepairQuorum iotests: Add tests for invalid Quorum @replaces iotests: Check that @replaces can replace filters Philippe Mathieu-Daudé (3): block/qcow2-bitmap: Remove unneeded variable assignment block: Remove superfluous semicolons block/io_uring: Remove superfluous semicolon qapi/block-core.json | 9 +- include/block/block.h | 5 - include/block/block_int.h | 16 +-- block.c | 89 ++++++------- block/blkverify.c | 20 +-- block/commit.c | 37 ++---- block/copy-on-read.c | 9 -- block/filter-compress.c | 9 -- block/io_uring.c | 2 +- block/mirror.c | 37 ++++-- block/qcow2-bitmap.c | 1 - block/qcow2-cluster.c | 7 +- block/qcow2-refcount.c | 1 + block/qcow2-threads.c | 12 +- block/qcow2.c | 2 - block/quorum.c | 70 +++++++++-- block/replication.c | 7 -- block/throttle.c | 8 -- block/vvfat.c | 7 -- blockdev.c | 18 +-- tests/qemu-iotests/iotests.py | 59 +++++++++ tests/qemu-iotests/040 | 283 ++++++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/040.out | 4 +- tests/qemu-iotests/041 | 138 +++++++++++++++++--- tests/qemu-iotests/041.out | 4 +- tests/qemu-iotests/155 | 7 +- tests/qemu-iotests/244 | 14 +++ tests/qemu-iotests/244.out | 6 + 28 files changed, 675 insertions(+), 206 deletions(-) If a coroutine is launched, but the coroutine pointer isn't stored anywhere, debugging any problems inside the coroutine is quite hard. Let's store the coroutine pointer of a mirror operation in MirrorOp to have it available in the debugger. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/mirror.c | 2 ++ 1 file changed, 2 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 @@ struct MirrorOp { bool is_pseudo_op; bool is_active_write; CoQueue waiting_requests; + Coroutine *co; QTAILQ_ENTRY(MirrorOp) next; }; @@ -XXX,XX +XXX,XX @@ static unsigned mirror_perform(MirrorBlockJob *s, int64_t offset, default: abort(); } + op->co = co; QTAILQ_INSERT_TAIL(&s->ops_in_flight, op, next); qemu_coroutine_enter(co); -- 2.20.1 mirror_wait_for_free_in_flight_slot() just picks a random operation to wait for. However, when mirror_co_read() waits for free slots, its MirrorOp is already in s->ops_in_flight, so if not enough slots are immediately available, an operation can end up waiting for itself to complete, which results in a hang. Fix this by passing the current MirrorOp and skipping this operation when picking an operation to wait for. Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1794692 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/mirror.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static int mirror_cow_align(MirrorBlockJob *s, int64_t *offset, } static inline void coroutine_fn -mirror_wait_for_any_operation(MirrorBlockJob *s, bool active) +mirror_wait_for_any_operation(MirrorBlockJob *s, MirrorOp *self, bool active) { MirrorOp *op; QTAILQ_FOREACH(op, &s->ops_in_flight, next) { + if (self == op) { + continue; + } /* Do not wait on pseudo ops, because it may in turn wait on * some other operation to start, which may in fact be the * caller of this function. Since there is only one pseudo op @@ -XXX,XX +XXX,XX @@ mirror_wait_for_any_operation(MirrorBlockJob *s, bool active) } static inline void coroutine_fn -mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s) +mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s, MirrorOp *self) { /* Only non-active operations use up in-flight slots */ - mirror_wait_for_any_operation(s, false); + mirror_wait_for_any_operation(s, self, false); } /* Perform a mirror copy operation. @@ -XXX,XX +XXX,XX @@ static void coroutine_fn mirror_co_read(void *opaque) while (s->buf_free_count < nb_chunks) { trace_mirror_yield_in_flight(s, op->offset, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, op); } /* Now make a QEMUIOVector taking enough granularity-sized chunks @@ -XXX,XX +XXX,XX @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) while (s->in_flight >= MAX_IN_FLIGHT) { trace_mirror_yield_in_flight(s, offset, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, pseudo_op); } if (s->ret < 0) { @@ -XXX,XX +XXX,XX @@ static void mirror_free_init(MirrorBlockJob *s) static void coroutine_fn mirror_wait_for_all_io(MirrorBlockJob *s) { while (s->in_flight > 0) { - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, NULL); } } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) if (s->in_flight >= MAX_IN_FLIGHT) { trace_mirror_yield(s, UINT64_MAX, s->buf_free_count, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, NULL); continue; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_run(Job *job, Error **errp) /* Do not start passive operations while there are active * writes in progress */ while (s->in_active_write_counter) { - mirror_wait_for_any_operation(s, true); + mirror_wait_for_any_operation(s, NULL, true); } if (s->ret < 0) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_run(Job *job, Error **errp) if (s->in_flight >= MAX_IN_FLIGHT || s->buf_free_count == 0 || (cnt == 0 && s->in_flight > 0)) { trace_mirror_yield(s, cnt, s->buf_free_count, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, NULL); continue; } else if (cnt != 0) { delay_ns = mirror_iteration(s); -- 2.20.1 From: Alberto Garcia <berto@igalia.com> I/O requests to encrypted media should be aligned to the sector size used by the underlying encryption method, not to BDRV_SECTOR_SIZE. Fortunately this doesn't break anything at the moment because both existing QCRYPTO_BLOCK_*_SECTOR_SIZE have the same value as BDRV_SECTOR_SIZE. The checks in qcow2_co_preadv_encrypted() are also unnecessary because they are repeated immediately afterwards in qcow2_co_encdec(). Signed-off-by: Alberto Garcia <berto@igalia.com> Message-Id: <20200213171646.15876-1-berto@igalia.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-threads.c | 12 ++++++++---- block/qcow2.c | 2 -- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-threads.c +++ b/block/qcow2-threads.c @@ -XXX,XX +XXX,XX @@ qcow2_co_encdec(BlockDriverState *bs, uint64_t host_offset, .len = len, .func = func, }; + uint64_t sector_size; - assert(QEMU_IS_ALIGNED(guest_offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(host_offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(len, BDRV_SECTOR_SIZE)); assert(s->crypto); + sector_size = qcrypto_block_get_sector_size(s->crypto); + assert(QEMU_IS_ALIGNED(guest_offset, sector_size)); + assert(QEMU_IS_ALIGNED(host_offset, sector_size)); + assert(QEMU_IS_ALIGNED(len, sector_size)); + return len == 0 ? 0 : qcow2_co_process(bs, qcow2_encdec_pool_func, &arg); } @@ -XXX,XX +XXX,XX @@ qcow2_co_encdec(BlockDriverState *bs, uint64_t host_offset, * will be written to the underlying storage device at * @host_offset * - * @len - length of the buffer (must be a BDRV_SECTOR_SIZE multiple) + * @len - length of the buffer (must be a multiple of the encryption + * sector size) * * Depending on the encryption method, @host_offset and/or @guest_offset * may be used for generating the initialization vector for diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ qcow2_co_preadv_encrypted(BlockDriverState *bs, goto fail; } - assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE)); if (qcow2_co_decrypt(bs, file_cluster_offset + offset_into_cluster(s, offset), offset, buf, bytes) < 0) -- 2.20.1 From: Hikaru Nishida <hikarupsp@gmail.com> Before this commit, BDRVVVFATState.qcow is unrefed in write_target_close on closing backing bdrv of vvfat. However, qcow bdrv is opend as a child of vvfat in enable_write_target() so it will be also unrefed on closing vvfat itself. This causes use-after-free of qcow on freeing vvfat which has backing bdrv and qcow bdrv as children in this order because bdrv_close(vvfat) tries to free qcow bdrv after freeing backing bdrv as QLIST_FOREACH_SAFE() loop keeps next pointer, but BdrvChild of qcow is already freed in bdrv_close(backing bdrv). Signed-off-by: Hikaru Nishida <hikarupsp@gmail.com> Message-Id: <20200209175156.85748-1-hikarupsp@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vvfat.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/block/vvfat.c b/block/vvfat.c index XXXXXXX..XXXXXXX 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -XXX,XX +XXX,XX @@ write_target_commit(BlockDriverState *bs, uint64_t offset, uint64_t bytes, return ret; } -static void write_target_close(BlockDriverState *bs) { - BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque); - bdrv_unref_child(s->bs, s->qcow); - g_free(s->qcow_filename); -} - static BlockDriver vvfat_write_target = { .format_name = "vvfat_write_target", .instance_size = sizeof(void*), .bdrv_co_pwritev = write_target_commit, - .bdrv_close = write_target_close, }; static void vvfat_qcow_options(int *child_flags, QDict *child_options, -- 2.20.1 In the case that update_refcount() frees a refcount block, it evicts it from the metadata cache. Before doing so, however, it returns the currently used refcount block to the cache because it might be the same. Returning the refcount block early means that we need to reset old_table_index so that we reload the refcount block in the next iteration if it is actually still in use. Fixes: f71c08ea8e60f035485a512fd2af8908567592f0 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200211094900.17315-2-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-refcount.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs, offset); if (table != NULL) { qcow2_cache_put(s->refcount_block_cache, &refcount_block); + old_table_index = -1; qcow2_cache_discard(s->refcount_block_cache, table); } -- 2.20.1 For external data file, cluster allocations return an offset in the data file and are not refcounted. In this case, there is nothing to do for qcow2_alloc_cluster_abort(). Freeing the same offset in the qcow2 file is wrong and causes crashes in the better case or image corruption in the worse case. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200211094900.17315-3-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-cluster.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ err: void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m) { BDRVQcow2State *s = bs->opaque; - qcow2_free_clusters(bs, m->alloc_offset, m->nb_clusters << s->cluster_bits, - QCOW2_DISCARD_NEVER); + if (!has_data_file(bs)) { + qcow2_free_clusters(bs, m->alloc_offset, + m->nb_clusters << s->cluster_bits, + QCOW2_DISCARD_NEVER); + } } /* -- 2.20.1 This adds a test for 'qemu-img convert' with copy offloading where the target image has an external data file. If the test hosts supports it, it tests both the case where copy offloading is supported and the case where it isn't (otherwise we just test unsupported twice). More specifically, the case with unsupported copy offloading tests qcow2_alloc_cluster_abort() with external data files. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200211094900.17315-4-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/244 | 14 ++++++++++++++ tests/qemu-iotests/244.out | 6 ++++++ 2 files changed, 20 insertions(+) diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/244 +++ b/tests/qemu-iotests/244 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'read -P 0x11 0 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io $QEMU_IMG map --output=human "$TEST_IMG" | _filter_testdir $QEMU_IMG map --output=json "$TEST_IMG" +echo +echo "=== Copy offloading ===" +echo + +# Make use of copy offloading if the test host can provide it +_make_test_img -o "data_file=$TEST_IMG.data" 64M +$QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$TEST_IMG" +$QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$TEST_IMG" + +# blkdebug doesn't support copy offloading, so this tests the error path +$QEMU_IMG amend -f $IMGFMT -o "data_file=blkdebug::$TEST_IMG.data" "$TEST_IMG" +$QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$TEST_IMG" +$QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$TEST_IMG" + # success, all done echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/244.out b/tests/qemu-iotests/244.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/244.out +++ b/tests/qemu-iotests/244.out @@ -XXX,XX +XXX,XX @@ Offset Length Mapped to File 0 0x100000 0 TEST_DIR/t.qcow2.data [{ "start": 0, "length": 1048576, "depth": 0, "zero": false, "data": true, "offset": 0}, { "start": 1048576, "length": 66060288, "depth": 0, "zero": true, "data": false}] + +=== Copy offloading === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 data_file=TEST_DIR/t.IMGFMT.data +Images are identical. +Images are identical. *** done -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Fix warning reported by Clang static code analyzer: CC block/qcow2-bitmap.o block/qcow2-bitmap.c:650:5: warning: Value stored to 'ret' is never read ret = -EINVAL; ^ ~~~~~~~ Fixes: 88ddffae8 Reported-by: Clang Static Analyzer Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200215161557.4077-2-philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Ján Tomko <jtomko@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-bitmap.c | 1 - 1 file changed, 1 deletion(-) 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 Qcow2BitmapList *bitmap_list_load(BlockDriverState *bs, uint64_t offset, return bm_list; broken_dir: - ret = -EINVAL; error_setg(errp, "Broken bitmap directory"); fail: -- 2.20.1 It is not obvious what 'ignore' actually means for block jobs: It could be continuing the job and returning success in the end despite the error (no block job does this). It could also mean continuing and returning failure in the end (this is what stream does). And it can mean retrying the failed request later (this is what backup, commit and mirror do). This (somewhat inconsistent) behaviour was introduced and described for stream and mirror in commit 32c81a4a6ec. backup and commit were introduced later and use the same model as mirror. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200214200812.28180-2-kwolf@redhat.com> Reviewed-by: Ján Tomko <jtomko@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 5 ++++- 1 file changed, 4 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 @@ # for jobs, cancel the job # # @ignore: ignore the error, only report a QMP event (BLOCK_IO_ERROR -# or BLOCK_JOB_ERROR) +# or BLOCK_JOB_ERROR). The backup, mirror and commit block jobs retry +# the failing request later and may still complete successfully. The +# stream block job continues to stream and will complete with an +# error. # # @enospc: same as @stop on ENOSPC, same as @report otherwise. # -- 2.20.1 The bytes_written variable is only ever written to, it serves no purpose. This has actually been the case since the commit job was first introduced in commit 747ff602636. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200214200812.28180-3-kwolf@redhat.com> Reviewed-by: Ján Tomko <jtomko@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/commit.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) int ret = 0; int64_t n = 0; /* bytes */ void *buf = NULL; - int bytes_written = 0; int64_t len, base_len; ret = len = blk_getlength(s->top); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) trace_commit_one_iteration(s, offset, n, ret); if (copy) { ret = commit_populate(s->top, s->base, offset, n, buf); - bytes_written += n; } if (ret < 0) { BlockErrorAction action = -- 2.20.1 The block_job_error_action() error call in the commit job gives the on_err and is_read arguments in the wrong order. Fix this. (Of course, hard-coded is_read = false is wrong, too, but that's a separate problem for a separate patch.) Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200214200812.28180-4-kwolf@redhat.com> Reviewed-by: Ján Tomko <jtomko@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/commit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) } if (ret < 0) { BlockErrorAction action = - block_job_error_action(&s->common, false, s->on_error, -ret); + block_job_error_action(&s->common, s->on_error, false, -ret); if (action == BLOCK_ERROR_ACTION_REPORT) { goto out; } else { -- 2.20.1 commit_populate() is a very short function and only called in a single place. Its return value doesn't tell us whether an error happened while reading or writing, which would be necessary for sending the right data in the BLOCK_JOB_ERROR QMP event. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200214200812.28180-5-kwolf@redhat.com> Reviewed-by: Ján Tomko <jtomko@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/commit.c | 28 ++++++---------------------- 1 file changed, 6 insertions(+), 22 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 @@ typedef struct CommitBlockJob { char *backing_file_str; } CommitBlockJob; -static int coroutine_fn commit_populate(BlockBackend *bs, BlockBackend *base, - int64_t offset, uint64_t bytes, - void *buf) -{ - int ret = 0; - - assert(bytes < SIZE_MAX); - - ret = blk_co_pread(bs, offset, bytes, buf, 0); - if (ret < 0) { - return ret; - } - - ret = blk_co_pwrite(base, offset, bytes, buf, 0); - if (ret < 0) { - return ret; - } - - return 0; -} - static int commit_prepare(Job *job) { CommitBlockJob *s = container_of(job, CommitBlockJob, common.job); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) copy = (ret == 1); trace_commit_one_iteration(s, offset, n, ret); if (copy) { - ret = commit_populate(s->top, s->base, offset, n, buf); + assert(n < SIZE_MAX); + + ret = blk_co_pread(s->top, offset, n, buf, 0); + if (ret >= 0) { + ret = blk_co_pwrite(s->base, offset, n, buf, 0); + } } if (ret < 0) { BlockErrorAction action = -- 2.20.1 block_job_error_action() needs to know if reading from the top node or writing to the base node failed so that it can set the right 'operation' in the BLOCK_JOB_ERROR QMP event. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200214200812.28180-6-kwolf@redhat.com> Reviewed-by: Ján Tomko <jtomko@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/commit.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) for (offset = 0; offset < len; offset += n) { bool copy; + bool error_in_source = true; /* Note that even when no rate limit is applied we need to yield * with no pending I/O here so that bdrv_drain_all() returns. @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) ret = blk_co_pread(s->top, offset, n, buf, 0); if (ret >= 0) { ret = blk_co_pwrite(s->base, offset, n, buf, 0); + if (ret < 0) { + error_in_source = false; + } } } if (ret < 0) { BlockErrorAction action = - block_job_error_action(&s->common, s->on_error, false, -ret); + block_job_error_action(&s->common, s->on_error, + error_in_source, -ret); if (action == BLOCK_ERROR_ACTION_REPORT) { goto out; } else { -- 2.20.1 Now that the error handling in the common block job is fixed, we can expose the on-error option in QMP instead of hard-coding it as 'report' in qmp_block_commit(). This fulfills the promise that the old comment in that function made, even if a bit later than expected: "This will be part of the QMP command, if/when the BlockdevOnError change for blkmirror makes it in". Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200214200812.28180-7-kwolf@redhat.com> Reviewed-by: Ján Tomko <jtomko@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 4 ++++ blockdev.c | 8 ++++---- 2 files changed, 8 insertions(+), 4 deletions(-) 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 @@ # # @speed: the maximum speed, in bytes per second # +# @on-error: the action to take on an error. 'ignore' means that the request +# should be retried. (default: report; Since: 5.0) +# # @filter-node-name: the node name that should be assigned to the # filter driver that the commit job inserts into the graph # above @top. If this option is not given, a node name is @@ -XXX,XX +XXX,XX @@ 'data': { '*job-id': 'str', 'device': 'str', '*base-node': 'str', '*base': 'str', '*top-node': 'str', '*top': 'str', '*backing-file': 'str', '*speed': 'int', + '*on-error': 'BlockdevOnError', '*filter-node-name': 'str', '*auto-finalize': 'bool', '*auto-dismiss': 'bool' } } diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device, bool has_top, const char *top, bool has_backing_file, const char *backing_file, bool has_speed, int64_t speed, + bool has_on_error, BlockdevOnError on_error, bool has_filter_node_name, const char *filter_node_name, bool has_auto_finalize, bool auto_finalize, bool has_auto_dismiss, bool auto_dismiss, @@ -XXX,XX +XXX,XX @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device, BlockDriverState *base_bs, *top_bs; AioContext *aio_context; Error *local_err = NULL; - /* This will be part of the QMP command, if/when the - * BlockdevOnError change for blkmirror makes it in - */ - BlockdevOnError on_error = BLOCKDEV_ON_ERROR_REPORT; int job_flags = JOB_DEFAULT; if (!has_speed) { speed = 0; } + if (!has_on_error) { + on_error = BLOCKDEV_ON_ERROR_REPORT; + } if (!has_filter_node_name) { filter_node_name = NULL; } -- 2.20.1 This tests both read failure (from the top node) and write failure (to the base node) for on-error=report/stop/ignore. As block-commit actually starts two different types of block jobs (mirror.c for committing the active later, commit.c for intermediate layers), all tests are run for both cases. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200214200812.28180-8-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/040 | 283 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/040.out | 4 +- 2 files changed, 285 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/040 b/tests/qemu-iotests/040 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/040 +++ b/tests/qemu-iotests/040 @@ -XXX,XX +XXX,XX @@ class TestReopenOverlay(ImageCommitTestCase): def test_reopen_overlay(self): self.run_commit_test(self.img1, self.img0) +class TestErrorHandling(iotests.QMPTestCase): + image_len = 2 * 1024 * 1024 + + def setUp(self): + iotests.create_image(backing_img, self.image_len) + qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % backing_img, mid_img) + qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % mid_img, test_img) + + qemu_io('-f', iotests.imgfmt, '-c', 'write -P 0x11 0 512k', mid_img) + qemu_io('-f', iotests.imgfmt, '-c', 'write -P 0x22 0 512k', test_img) + + self.vm = iotests.VM() + self.vm.launch() + + self.blkdebug_file = iotests.file_path("blkdebug.conf") + + def tearDown(self): + self.vm.shutdown() + os.remove(test_img) + os.remove(mid_img) + os.remove(backing_img) + + def blockdev_add(self, **kwargs): + result = self.vm.qmp('blockdev-add', **kwargs) + self.assert_qmp(result, 'return', {}) + + def add_block_nodes(self, base_debug=None, mid_debug=None, top_debug=None): + self.blockdev_add(node_name='base-file', driver='file', + filename=backing_img) + self.blockdev_add(node_name='mid-file', driver='file', + filename=mid_img) + self.blockdev_add(node_name='top-file', driver='file', + filename=test_img) + + if base_debug: + self.blockdev_add(node_name='base-dbg', driver='blkdebug', + image='base-file', inject_error=base_debug) + if mid_debug: + self.blockdev_add(node_name='mid-dbg', driver='blkdebug', + image='mid-file', inject_error=mid_debug) + if top_debug: + self.blockdev_add(node_name='top-dbg', driver='blkdebug', + image='top-file', inject_error=top_debug) + + self.blockdev_add(node_name='base-fmt', driver='raw', + file=('base-dbg' if base_debug else 'base-file')) + self.blockdev_add(node_name='mid-fmt', driver=iotests.imgfmt, + file=('mid-dbg' if mid_debug else 'mid-file'), + backing='base-fmt') + self.blockdev_add(node_name='top-fmt', driver=iotests.imgfmt, + file=('top-dbg' if top_debug else 'top-file'), + backing='mid-fmt') + + def run_job(self, expected_events, error_pauses_job=False): + match_device = {'data': {'device': 'job0'}} + events = [ + ('BLOCK_JOB_COMPLETED', match_device), + ('BLOCK_JOB_CANCELLED', match_device), + ('BLOCK_JOB_ERROR', match_device), + ('BLOCK_JOB_READY', match_device), + ] + + completed = False + log = [] + while not completed: + ev = self.vm.events_wait(events, timeout=5.0) + if ev['event'] == 'BLOCK_JOB_COMPLETED': + completed = True + elif ev['event'] == 'BLOCK_JOB_ERROR': + if error_pauses_job: + result = self.vm.qmp('block-job-resume', device='job0') + self.assert_qmp(result, 'return', {}) + elif ev['event'] == 'BLOCK_JOB_READY': + result = self.vm.qmp('block-job-complete', device='job0') + self.assert_qmp(result, 'return', {}) + else: + self.fail("Unexpected event: %s" % ev) + log.append(iotests.filter_qmp_event(ev)) + + self.maxDiff = None + self.assertEqual(expected_events, log) + + def event_error(self, op, action): + return { + 'event': 'BLOCK_JOB_ERROR', + 'data': {'action': action, 'device': 'job0', 'operation': op}, + 'timestamp': {'microseconds': 'USECS', 'seconds': 'SECS'} + } + + def event_ready(self): + return { + 'event': 'BLOCK_JOB_READY', + 'data': {'device': 'job0', + 'len': 524288, + 'offset': 524288, + 'speed': 0, + 'type': 'commit'}, + 'timestamp': {'microseconds': 'USECS', 'seconds': 'SECS'}, + } + + def event_completed(self, errmsg=None, active=True): + max_len = 524288 if active else self.image_len + data = { + 'device': 'job0', + 'len': max_len, + 'offset': 0 if errmsg else max_len, + 'speed': 0, + 'type': 'commit' + } + if errmsg: + data['error'] = errmsg + + return { + 'event': 'BLOCK_JOB_COMPLETED', + 'data': data, + 'timestamp': {'microseconds': 'USECS', 'seconds': 'SECS'}, + } + + def blkdebug_event(self, event, is_raw=False): + if event: + return [{ + 'event': event, + 'sector': 512 if is_raw else 1024, + 'once': True, + }] + return None + + def prepare_and_start_job(self, on_error, active=True, + top_event=None, mid_event=None, base_event=None): + + top_debug = self.blkdebug_event(top_event) + mid_debug = self.blkdebug_event(mid_event) + base_debug = self.blkdebug_event(base_event, True) + + self.add_block_nodes(top_debug=top_debug, mid_debug=mid_debug, + base_debug=base_debug) + + result = self.vm.qmp('block-commit', job_id='job0', device='top-fmt', + top_node='top-fmt' if active else 'mid-fmt', + base_node='mid-fmt' if active else 'base-fmt', + on_error=on_error) + self.assert_qmp(result, 'return', {}) + + def testActiveReadErrorReport(self): + self.prepare_and_start_job('report', top_event='read_aio') + self.run_job([ + self.event_error('read', 'report'), + self.event_completed('Input/output error') + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(test_img, mid_img), + 'target image matches source after error') + + def testActiveReadErrorStop(self): + self.prepare_and_start_job('stop', top_event='read_aio') + self.run_job([ + self.event_error('read', 'stop'), + self.event_ready(), + self.event_completed() + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testActiveReadErrorIgnore(self): + self.prepare_and_start_job('ignore', top_event='read_aio') + self.run_job([ + self.event_error('read', 'ignore'), + self.event_ready(), + self.event_completed() + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testActiveWriteErrorReport(self): + self.prepare_and_start_job('report', mid_event='write_aio') + self.run_job([ + self.event_error('write', 'report'), + self.event_completed('Input/output error') + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(test_img, mid_img), + 'target image matches source after error') + + def testActiveWriteErrorStop(self): + self.prepare_and_start_job('stop', mid_event='write_aio') + self.run_job([ + self.event_error('write', 'stop'), + self.event_ready(), + self.event_completed() + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testActiveWriteErrorIgnore(self): + self.prepare_and_start_job('ignore', mid_event='write_aio') + self.run_job([ + self.event_error('write', 'ignore'), + self.event_ready(), + self.event_completed() + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testIntermediateReadErrorReport(self): + self.prepare_and_start_job('report', active=False, mid_event='read_aio') + self.run_job([ + self.event_error('read', 'report'), + self.event_completed('Input/output error', active=False) + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image matches source after error') + + def testIntermediateReadErrorStop(self): + self.prepare_and_start_job('stop', active=False, mid_event='read_aio') + self.run_job([ + self.event_error('read', 'stop'), + self.event_completed(active=False) + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + + def testIntermediateReadErrorIgnore(self): + self.prepare_and_start_job('ignore', active=False, mid_event='read_aio') + self.run_job([ + self.event_error('read', 'ignore'), + self.event_completed(active=False) + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + + def testIntermediateWriteErrorReport(self): + self.prepare_and_start_job('report', active=False, base_event='write_aio') + self.run_job([ + self.event_error('write', 'report'), + self.event_completed('Input/output error', active=False) + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image matches source after error') + + def testIntermediateWriteErrorStop(self): + self.prepare_and_start_job('stop', active=False, base_event='write_aio') + self.run_job([ + self.event_error('write', 'stop'), + self.event_completed(active=False) + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + + def testIntermediateWriteErrorIgnore(self): + self.prepare_and_start_job('ignore', active=False, base_event='write_aio') + self.run_job([ + self.event_error('write', 'ignore'), + self.event_completed(active=False) + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + if __name__ == '__main__': iotests.main(supported_fmts=['qcow2', 'qed'], supported_protocols=['file']) diff --git a/tests/qemu-iotests/040.out b/tests/qemu-iotests/040.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/040.out +++ b/tests/qemu-iotests/040.out @@ -XXX,XX +XXX,XX @@ -............................................... +........................................................... ---------------------------------------------------------------------- -Ran 47 tests +Ran 59 tests OK -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Fixes: 132ada80c4a Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200218094402.26625-4-philmd@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, if (bdrv_get_aio_context(child_bs) != ctx) { ret = bdrv_try_set_aio_context(child_bs, ctx, &local_err); if (ret < 0 && child_role->can_set_aio_ctx) { - GSList *ignore = g_slist_prepend(NULL, child);; + GSList *ignore = g_slist_prepend(NULL, child); ctx = bdrv_get_aio_context(child_bs); if (child_role->can_set_aio_ctx(child, ctx, &ignore, NULL)) { error_free(local_err); ret = 0; g_slist_free(ignore); - ignore = g_slist_prepend(NULL, child);; + ignore = g_slist_prepend(NULL, child); child_role->set_aio_ctx(child, ctx, &ignore); } g_slist_free(ignore); -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Fixes: 6663a0a3376 Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-Id: <20200218094402.26625-5-philmd@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/io_uring.c b/block/io_uring.c index XXXXXXX..XXXXXXX 100644 --- a/block/io_uring.c +++ b/block/io_uring.c @@ -XXX,XX +XXX,XX @@ static void luring_process_completions(LuringState *s) ret = 0; } } else { - ret = -ENOSPC;; + ret = -ENOSPC; } } end: -- 2.20.1 From: Max Reitz <mreitz@redhat.com> There is no good reason why we would allow external snapshots only on the first non-filter node in a chain. Parent BDSs should not care whether their child is replaced by a snapshot. (If they do care, they should announce that via freezing the chain, which is checked in bdrv_append() through bdrv_set_backing_hd().) Before we had bdrv_is_first_non_filter() here (since 212a5a8f095), there was a special function bdrv_check_ext_snapshot() that allowed snapshots by default, but block drivers could override this. Only blkverify did so, however. It is not clear to me why blkverify would do so; maybe just so that the testee block driver would not be replaced. The introducing commit f6186f49e2c does not explain why. Maybe because 08b24cfe376 would have been the correct solution? (Which adds a .supports_backing check.) Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-2-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static void external_snapshot_prepare(BlkActionState *common, } } - if (!bdrv_is_first_non_filter(state->old_bs)) { - error_setg(errp, QERR_FEATURE_DISABLED, "snapshot"); - goto out; - } - if (action->type == TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC) { BlockdevSnapshotSync *s = action->u.blockdev_snapshot_sync.data; const char *format = s->has_format ? s->format : "qcow2"; -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Block nodes that do not allow resizing should not share BLK_PERM_RESIZE. It does not matter whether they are the first non-filter in their chain or not. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-3-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_resize(bool has_device, const char *device, aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); - if (!bdrv_is_first_non_filter(bs)) { - error_setg(errp, QERR_FEATURE_DISABLED, "resize"); - goto out; - } - if (size < 0) { error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "size", "a >0 size"); goto out; -- 2.20.1 From: Max Reitz <mreitz@redhat.com> It is unused now. (And it was ugly because it needed to explore all BDS chains from the top.) Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-4-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 1 - block.c | 26 -------------------------- 2 files changed, 27 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_amend_options(BlockDriverState *bs_new, QemuOpts *opts, /* external snapshots */ bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, BlockDriverState *candidate); -bool bdrv_is_first_non_filter(BlockDriverState *candidate); /* check if a named node can be replaced when doing drive-mirror */ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, return false; } -/* This function checks if the candidate is the first non filter bs down it's - * bs chain. Since we don't have pointers to parents it explore all bs chains - * from the top. Some filters can choose not to pass down the recursion. - */ -bool bdrv_is_first_non_filter(BlockDriverState *candidate) -{ - BlockDriverState *bs; - BdrvNextIterator it; - - /* walk down the bs forest recursively */ - for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { - bool perm; - - /* try to recurse in this top level bs */ - perm = bdrv_recurse_is_first_non_filter(bs, candidate); - - /* candidate is the first non filter */ - if (perm) { - bdrv_next_cleanup(&it); - return true; - } - } - - return false; -} - BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp) { -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Using -drive with default options means that a virtio-blk drive will be created that has write access to the to-be quorum children. Quorum should have exclusive write access to them, so we should use -blockdev instead. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-5-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/041 | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): # Assign a node name to each quorum image in order to manipulate # them opts = "node-name=img%i" % self.IMAGES.index(i) - self.vm = self.vm.add_drive(i, opts) + opts += ',driver=%s' % iotests.imgfmt + opts += ',file.driver=file' + opts += ',file.filename=%s' % i + self.vm = self.vm.add_blockdev(opts) self.vm.launch() -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Quorum cannot share WRITE or RESIZE on its children. Presumably, it only does so because as a filter, it seemed intuitively correct to point its .bdrv_child_perm to bdrv_filter_default_perm(). However, it is not really a filter, and bdrv_filter_default_perm() does not work for it, so we have to provide a custom .bdrv_child_perm implementation. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-6-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static char *quorum_dirname(BlockDriverState *bs, Error **errp) return NULL; } +static void quorum_child_perm(BlockDriverState *bs, BdrvChild *c, + const BdrvChildRole *role, + BlockReopenQueue *reopen_queue, + uint64_t perm, uint64_t shared, + uint64_t *nperm, uint64_t *nshared) +{ + *nperm = perm & DEFAULT_PERM_PASSTHROUGH; + + /* + * We cannot share RESIZE or WRITE, as this would make the + * children differ from each other. + */ + *nshared = (shared & (BLK_PERM_CONSISTENT_READ | + BLK_PERM_WRITE_UNCHANGED)) + | DEFAULT_PERM_UNCHANGED; +} + static const char *const quorum_strong_runtime_opts[] = { QUORUM_OPT_VOTE_THRESHOLD, QUORUM_OPT_BLKVERIFY, @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = { .bdrv_add_child = quorum_add_child, .bdrv_del_child = quorum_del_child, - .bdrv_child_perm = bdrv_filter_default_perms, + .bdrv_child_perm = quorum_child_perm, .is_filter = true, .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter, -- 2.20.1 From: Max Reitz <mreitz@redhat.com> After a couple of follow-up patches, this function will replace bdrv_recurse_is_first_non_filter() in check_to_replace_node(). bdrv_recurse_is_first_non_filter() is both not sufficiently specific for check_to_replace_node() (it allows cases that should not be allowed, like replacing child nodes of quorum with dissenting data that have more parents than just quorum), and it is too restrictive (it is perfectly fine to replace filters). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-7-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 10 ++++++++++ block.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { */ bool (*bdrv_recurse_is_first_non_filter)(BlockDriverState *bs, BlockDriverState *candidate); + /* + * Return true if @to_replace can be replaced by a BDS with the + * same data as @bs without it affecting @bs's behavior (that is, + * without it being visible to @bs's parents). + */ + bool (*bdrv_recurse_can_replace)(BlockDriverState *bs, + BlockDriverState *to_replace); int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename); int (*bdrv_probe_device)(const char *filename); @@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared); +bool bdrv_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace); + /* * Default implementation for drivers to pass bdrv_co_block_status() to * their file. diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, return false; } +/* + * This function checks whether the given @to_replace is allowed to be + * replaced by a node that always shows the same data as @bs. This is + * used for example to verify whether the mirror job can replace + * @to_replace by the target mirrored from @bs. + * To be replaceable, @bs and @to_replace may either be guaranteed to + * always show the same data (because they are only connected through + * filters), or some driver may allow replacing one of its children + * because it can guarantee that this child's data is not visible at + * all (for example, for dissenting quorum children that have no other + * parents). + */ +bool bdrv_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace) +{ + if (!bs || !bs->drv) { + return false; + } + + if (bs == to_replace) { + return true; + } + + /* See what the driver can do */ + if (bs->drv->bdrv_recurse_can_replace) { + return bs->drv->bdrv_recurse_can_replace(bs, to_replace); + } + + /* For filters without an own implementation, we can recurse on our own */ + if (bs->drv->is_filter) { + BdrvChild *child = bs->file ?: bs->backing; + return bdrv_recurse_can_replace(child->bs, to_replace); + } + + /* Safe default */ + return false; +} + BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp) { -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-8-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/blkverify.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/block/blkverify.c b/block/blkverify.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkverify.c +++ b/block/blkverify.c @@ -XXX,XX +XXX,XX @@ static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs, return bdrv_recurse_is_first_non_filter(s->test_file->bs, candidate); } +static bool blkverify_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace) +{ + BDRVBlkverifyState *s = bs->opaque; + + /* + * blkverify quits the whole qemu process if there is a mismatch + * between bs->file->bs and s->test_file->bs. Therefore, we know + * know that both must match bs and we can recurse down to either. + */ + return bdrv_recurse_can_replace(bs->file->bs, to_replace) || + bdrv_recurse_can_replace(s->test_file->bs, to_replace); +} + static void blkverify_refresh_filename(BlockDriverState *bs) { BDRVBlkverifyState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_blkverify = { .is_filter = true, .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter, + .bdrv_recurse_can_replace = blkverify_recurse_can_replace, }; static void bdrv_blkverify_init(void) -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200218103454.296704-9-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static bool quorum_recurse_is_first_non_filter(BlockDriverState *bs, return false; } +static bool quorum_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace) +{ + BDRVQuorumState *s = bs->opaque; + int i; + + for (i = 0; i < s->num_children; i++) { + /* + * We have no idea whether our children show the same data as + * this node (@bs). It is actually highly likely that + * @to_replace does not, because replacing a broken child is + * one of the main use cases here. + * + * We do know that the new BDS will match @bs, so replacing + * any of our children by it will be safe. It cannot change + * the data this quorum node presents to its parents. + * + * However, replacing @to_replace by @bs in any of our + * children's chains may change visible data somewhere in + * there. We therefore cannot recurse down those chains with + * bdrv_recurse_can_replace(). + * (More formally, bdrv_recurse_can_replace() requires that + * @to_replace will be replaced by something matching the @bs + * passed to it. We cannot guarantee that.) + * + * Thus, we can only check whether any of our immediate + * children matches @to_replace. + * + * (In the future, we might add a function to recurse down a + * chain that checks that nothing there cares about a change + * in data from the respective child in question. For + * example, most filters do not care when their child's data + * suddenly changes, as long as their parents do not care.) + */ + if (s->children[i]->bs == to_replace) { + /* + * We now have to ensure that there is no other parent + * that cares about replacing this child by a node with + * potentially different data. + * We do so by checking whether there are any other parents + * at all, which is stricter than necessary, but also very + * simple. (We may decide to implement something more + * complex and permissive when there is an actual need for + * it.) + */ + return QLIST_FIRST(&to_replace->parents) == s->children[i] && + QLIST_NEXT(s->children[i], next_parent) == NULL; + } + } + + return false; +} + static int quorum_valid_threshold(int threshold, int num_children, Error **errp) { @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = { .is_filter = true, .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter, + .bdrv_recurse_can_replace = quorum_recurse_can_replace, .strong_runtime_opts = quorum_strong_runtime_opts, }; -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Let check_to_replace_node() use the more specialized bdrv_recurse_can_replace() instead of bdrv_recurse_is_first_non_filter(), which is too restrictive (or, in the case of quorum, sometimes not restrictive enough). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-10-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ bool bdrv_recurse_can_replace(BlockDriverState *bs, return false; } +/* + * Check whether the given @node_name can be replaced by a node that + * has the same data as @parent_bs. If so, return @node_name's BDS; + * NULL otherwise. + * + * @node_name must be a (recursive) *child of @parent_bs (or this + * function will return NULL). + * + * The result (whether the node can be replaced or not) is only valid + * for as long as no graph or permission changes occur. + */ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp) { @@ -XXX,XX +XXX,XX @@ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, * Another benefit is that this tests exclude backing files which are * blocked by the backing blockers. */ - if (!bdrv_recurse_is_first_non_filter(parent_bs, to_replace_bs)) { - error_setg(errp, "Only top most non filter can be replaced"); + if (!bdrv_recurse_can_replace(parent_bs, to_replace_bs)) { + error_setg(errp, "Cannot replace '%s' by a node mirrored from '%s', " + "because it cannot be guaranteed that doing so would not " + "lead to an abrupt change of visible data", + node_name, parent_bs->node_name); to_replace_bs = NULL; goto out; } -- 2.20.1 From: Max Reitz <mreitz@redhat.com> It no longer has any users. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-11-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 4 ---- include/block/block_int.h | 8 -------- block.c | 33 --------------------------------- block/blkverify.c | 15 --------------- block/copy-on-read.c | 9 --------- block/filter-compress.c | 9 --------- block/quorum.c | 18 ------------------ block/replication.c | 7 ------- block/throttle.c | 8 -------- 9 files changed, 111 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_amend_options(BlockDriverState *bs_new, QemuOpts *opts, BlockDriverAmendStatusCB *status_cb, void *cb_opaque, Error **errp); -/* external snapshots */ -bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate); - /* check if a named node can be replaced when doing drive-mirror */ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp); diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { * must implement them and return -ENOTSUP. */ bool is_filter; - /* for snapshots block filter like Quorum can implement the - * following recursive callback. - * It's purpose is to recurse on the filter children while calling - * bdrv_recurse_is_first_non_filter on them. - * For a sample implementation look in the future Quorum block filter. - */ - bool (*bdrv_recurse_is_first_non_filter)(BlockDriverState *bs, - BlockDriverState *candidate); /* * Return true if @to_replace can be replaced by a BDS with the * same data as @bs without it affecting @bs's behavior (that is, diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts, return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque, errp); } -/* This function will be called by the bdrv_recurse_is_first_non_filter method - * of block filter and by bdrv_is_first_non_filter. - * It is used to test if the given bs is the candidate or recurse more in the - * node graph. - */ -bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - /* return false if basic checks fails */ - if (!bs || !bs->drv) { - return false; - } - - /* the code reached a non block filter driver -> check if the bs is - * the same as the candidate. It's the recursion termination condition. - */ - if (!bs->drv->is_filter) { - return bs == candidate; - } - /* Down this path the driver is a block filter driver */ - - /* If the block filter recursion method is defined use it to recurse down - * the node graph. - */ - if (bs->drv->bdrv_recurse_is_first_non_filter) { - return bs->drv->bdrv_recurse_is_first_non_filter(bs, candidate); - } - - /* the driver is a block filter but don't allow to recurse -> return false - */ - return false; -} - /* * This function checks whether the given @to_replace is allowed to be * replaced by a node that always shows the same data as @bs. This is diff --git a/block/blkverify.c b/block/blkverify.c index XXXXXXX..XXXXXXX 100644 --- a/block/blkverify.c +++ b/block/blkverify.c @@ -XXX,XX +XXX,XX @@ static int blkverify_co_flush(BlockDriverState *bs) return bdrv_co_flush(s->test_file->bs); } -static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - BDRVBlkverifyState *s = bs->opaque; - - bool perm = bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); - - if (perm) { - return true; - } - - return bdrv_recurse_is_first_non_filter(s->test_file->bs, candidate); -} - static bool blkverify_recurse_can_replace(BlockDriverState *bs, BlockDriverState *to_replace) { @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_blkverify = { .bdrv_co_flush = blkverify_co_flush, .is_filter = true, - .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter, .bdrv_recurse_can_replace = blkverify_recurse_can_replace, }; diff --git a/block/copy-on-read.c b/block/copy-on-read.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -XXX,XX +XXX,XX @@ static void cor_lock_medium(BlockDriverState *bs, bool locked) } -static bool cor_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - - static BlockDriver bdrv_copy_on_read = { .format_name = "copy-on-read", @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_copy_on_read = { .bdrv_co_block_status = bdrv_co_block_status_from_file, - .bdrv_recurse_is_first_non_filter = cor_recurse_is_first_non_filter, - .has_variable_length = true, .is_filter = true, }; diff --git a/block/filter-compress.c b/block/filter-compress.c index XXXXXXX..XXXXXXX 100644 --- a/block/filter-compress.c +++ b/block/filter-compress.c @@ -XXX,XX +XXX,XX @@ static void compress_lock_medium(BlockDriverState *bs, bool locked) } -static bool compress_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - - static BlockDriver bdrv_compress = { .format_name = "compress", @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_compress = { .bdrv_co_block_status = bdrv_co_block_status_from_file, - .bdrv_recurse_is_first_non_filter = compress_recurse_is_first_non_filter, - .has_variable_length = true, .is_filter = true, }; diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs) return result; } -static bool quorum_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - BDRVQuorumState *s = bs->opaque; - int i; - - for (i = 0; i < s->num_children; i++) { - bool perm = bdrv_recurse_is_first_non_filter(s->children[i]->bs, - candidate); - if (perm) { - return true; - } - } - - return false; -} - static bool quorum_recurse_can_replace(BlockDriverState *bs, BlockDriverState *to_replace) { @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = { .bdrv_child_perm = quorum_child_perm, .is_filter = true, - .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter, .bdrv_recurse_can_replace = quorum_recurse_can_replace, .strong_runtime_opts = quorum_strong_runtime_opts, 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 @@ out: return ret; } -static bool replication_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) { Error *local_err = NULL; @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_replication = { .bdrv_co_writev = replication_co_writev, .is_filter = true, - .bdrv_recurse_is_first_non_filter = replication_recurse_is_first_non_filter, .has_variable_length = true, .strong_runtime_opts = replication_strong_runtime_opts, diff --git a/block/throttle.c b/block/throttle.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle.c +++ b/block/throttle.c @@ -XXX,XX +XXX,XX @@ static void throttle_reopen_abort(BDRVReopenState *reopen_state) reopen_state->opaque = NULL; } -static bool throttle_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs) { ThrottleGroupMember *tgm = bs->opaque; @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_throttle = { .bdrv_co_pwrite_zeroes = throttle_co_pwrite_zeroes, .bdrv_co_pdiscard = throttle_co_pdiscard, - .bdrv_recurse_is_first_non_filter = throttle_recurse_is_first_non_filter, - .bdrv_attach_aio_context = throttle_attach_aio_context, .bdrv_detach_aio_context = throttle_detach_aio_context, -- 2.20.1 From: Max Reitz <mreitz@redhat.com> There is no guarantee that we can still replace the node we want to replace at the end of the mirror job. Double-check by calling bdrv_recurse_can_replace(). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-12-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/mirror.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static int mirror_exit_common(Job *job) * drain potential other users of the BDS before changing the graph. */ assert(s->in_drain); bdrv_drained_begin(target_bs); - bdrv_replace_node(to_replace, target_bs, &local_err); + /* + * Cannot use check_to_replace_node() here, because that would + * check for an op blocker on @to_replace, and we have our own + * there. + */ + if (bdrv_recurse_can_replace(src, to_replace)) { + bdrv_replace_node(to_replace, target_bs, &local_err); + } else { + error_setg(&local_err, "Can no longer replace '%s' by '%s', " + "because it can no longer be guaranteed that doing so " + "would not lead to an abrupt change of visible data", + to_replace->node_name, target_bs->node_name); + } bdrv_drained_end(target_bs); if (local_err) { error_report_err(local_err); -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Quorum is not a filter, for example because it cannot guarantee which of its children will serve the next request. Thus, any of its children may differ from the data visible to quorum's parents. We have other filters with multiple children, but they differ in this aspect: - blkverify quits the whole qemu process if its children differ. As such, we can always skip it when we want to skip it (as a filter node) by going to any of its children. Both have the same data. - replication generally serves requests from bs->file, so this is its only actually filtered child. - Block job filters currently only have one child, but they will probably get more children in the future. Still, they will always have only one actually filtered child. Having "filters" as a dedicated node category only makes sense if you can skip them by going to a one fixed child that always shows the same data as the filter node. Quorum cannot fulfill this, so it is not a filter. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-13-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 1 - 1 file changed, 1 deletion(-) diff --git a/block/quorum.c b/block/quorum.c index XXXXXXX..XXXXXXX 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_quorum = { .bdrv_child_perm = quorum_child_perm, - .is_filter = true, .bdrv_recurse_can_replace = quorum_recurse_can_replace, .strong_runtime_opts = quorum_strong_runtime_opts, -- 2.20.1 From: Max Reitz <mreitz@redhat.com> This way, we get to see errors during the completion phase. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-14-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/155 | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/tests/qemu-iotests/155 b/tests/qemu-iotests/155 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/155 +++ b/tests/qemu-iotests/155 @@ -XXX,XX +XXX,XX @@ class MirrorBaseClass(BaseClass): self.assert_qmp(result, 'return', {}) - self.vm.event_wait('BLOCK_JOB_READY') - - result = self.vm.qmp('block-job-complete', device='mirror-job') - self.assert_qmp(result, 'return', {}) - - self.vm.event_wait('BLOCK_JOB_COMPLETED') + self.complete_and_wait('mirror-job') def testFull(self): self.runMirror('full') -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200218103454.296704-15-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/iotests.py | 59 +++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ class VM(qtest.QEMUQtestMachine): return fields.items() <= ret.items() + def assert_block_path(self, root, path, expected_node, graph=None): + """ + Check whether the node under the given path in the block graph + is @expected_node. + + @root is the node name of the node where the @path is rooted. + + @path is a string that consists of child names separated by + slashes. It must begin with a slash. + + Examples for @root + @path: + - root="qcow2-node", path="/backing/file" + - root="quorum-node", path="/children.2/file" + + Hypothetically, @path could be empty, in which case it would + point to @root. However, in practice this case is not useful + and hence not allowed. + + @expected_node may be None. (All elements of the path but the + leaf must still exist.) + + @graph may be None or the result of an x-debug-query-block-graph + call that has already been performed. + """ + if graph is None: + graph = self.qmp('x-debug-query-block-graph')['return'] + + iter_path = iter(path.split('/')) + + # Must start with a / + assert next(iter_path) == '' + + node = next((node for node in graph['nodes'] if node['name'] == root), + None) + + # An empty @path is not allowed, so the root node must be present + assert node is not None, 'Root node %s not found' % root + + for child_name in iter_path: + assert node is not None, 'Cannot follow path %s%s' % (root, path) + + try: + node_id = next(edge['child'] for edge in graph['edges'] \ + if edge['parent'] == node['id'] and + edge['name'] == child_name) + + node = next(node for node in graph['nodes'] \ + if node['id'] == node_id) + except StopIteration: + node = None + + if node is None: + assert expected_node is None, \ + 'No node found under %s (but expected %s)' % \ + (path, expected_node) + else: + assert node['name'] == expected_node, \ + 'Found node %s under %s (but expected %s)' % \ + (node['name'], path, expected_node) index_re = re.compile(r'([^\[]+)\[([^\]]+)\]') -- 2.20.1 From: Max Reitz <mreitz@redhat.com> All tearDowns in 041 shutdown the VM. Thus, test cases do not need to do it themselves (unless they need the VM to be down for some post-operation check). Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-16-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/041 | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -XXX,XX +XXX,XX @@ class TestSingleDrive(iotests.QMPTestCase): self.cancel_and_wait(force=True) result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/file', test_img) - self.vm.shutdown() def test_cancel_after_ready(self): self.assert_no_active_block_jobs() @@ -XXX,XX +XXX,XX @@ class TestSingleDrive(iotests.QMPTestCase): self.assert_qmp(result, 'return[0]/node-name', 'top') self.assert_qmp(result, 'return[0]/backing/node-name', 'base') - self.vm.shutdown() - def test_medium_not_found(self): if iotests.qemu_default_machine != 'pc': return @@ -XXX,XX +XXX,XX @@ new_state = "1" self.assert_qmp(event, 'data/id', 'drive0') self.assert_no_active_block_jobs() - self.vm.shutdown() def test_ignore_read(self): self.assert_no_active_block_jobs() @@ -XXX,XX +XXX,XX @@ new_state = "1" result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/paused', False) self.complete_and_wait() - self.vm.shutdown() def test_large_cluster(self): self.assert_no_active_block_jobs() @@ -XXX,XX +XXX,XX @@ new_state = "1" self.complete_and_wait(wait_ready=False) self.assert_no_active_block_jobs() - self.vm.shutdown() class TestWriteErrors(iotests.QMPTestCase): image_len = 2 * 1024 * 1024 # MB @@ -XXX,XX +XXX,XX @@ new_state = "1" completed = True self.assert_no_active_block_jobs() - self.vm.shutdown() def test_ignore_write(self): self.assert_no_active_block_jobs() @@ -XXX,XX +XXX,XX @@ new_state = "1" result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/paused', False) self.complete_and_wait() - self.vm.shutdown() def test_stop_write(self): self.assert_no_active_block_jobs() @@ -XXX,XX +XXX,XX @@ new_state = "1" self.complete_and_wait(wait_ready=False) self.assert_no_active_block_jobs() - self.vm.shutdown() class TestSetSpeed(iotests.QMPTestCase): image_len = 80 * 1024 * 1024 # MB @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): # here we check that the last registered quorum file has not been # swapped out and unref self.assert_has_block_node(None, quorum_img3) - self.vm.shutdown() def test_cancel_after_ready(self): self.assert_no_active_block_jobs() @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): self.assert_has_block_node("repair0", quorum_repair_img) # TODO: a better test requiring some QEMU infrastructure will be added # to check that this file is really driven by quorum - self.vm.shutdown() # Test mirroring with a source that does not have any parents (not even a # BlockBackend) -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-17-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/041 | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): self.complete_and_wait(drive="job0") self.assert_has_block_node("repair0", quorum_repair_img) - # TODO: a better test requiring some QEMU infrastructure will be added - # to check that this file is really driven by quorum + self.vm.assert_block_path('quorum0', '/children.1', 'repair0') self.vm.shutdown() self.assertTrue(iotests.compare_images(quorum_img2, quorum_repair_img), 'target image does not match source after mirroring') @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): self.complete_and_wait('job0') self.assert_has_block_node("repair0", quorum_repair_img) - # TODO: a better test requiring some QEMU infrastructure will be added - # to check that this file is really driven by quorum + self.vm.assert_block_path('quorum0', '/children.1', 'repair0') # Test mirroring with a source that does not have any parents (not even a # BlockBackend) -- 2.20.1 From: Max Reitz <mreitz@redhat.com> 041's TestRepairQuorum has its own image_len, no need to refer to TestSingleDrive. (This patch allows commenting out TestSingleDrive to speed up 041 during test testing.) Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-18-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/041 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): # Add each individual quorum images for i in self.IMAGES: qemu_img('create', '-f', iotests.imgfmt, i, - str(TestSingleDrive.image_len)) + str(self.image_len)) # Assign a node name to each quorum image in order to manipulate # them opts = "node-name=img%i" % self.IMAGES.index(i) -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Add two tests to see that you cannot replace a Quorum child with the mirror job while the child is in use by a different parent. Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-19-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/041 | 70 +++++++++++++++++++++++++++++++++++++- tests/qemu-iotests/041.out | 4 +-- 2 files changed, 71 insertions(+), 3 deletions(-) diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -XXX,XX +XXX,XX @@ import time import os +import re import iotests from iotests import qemu_img, qemu_io @@ -XXX,XX +XXX,XX @@ quorum_img3 = os.path.join(iotests.test_dir, 'quorum3.img') quorum_repair_img = os.path.join(iotests.test_dir, 'quorum_repair.img') quorum_snapshot_file = os.path.join(iotests.test_dir, 'quorum_snapshot.img') +nbd_sock_path = os.path.join(iotests.test_dir, 'nbd.sock') + class TestSingleDrive(iotests.QMPTestCase): image_len = 1 * 1024 * 1024 # MB qmp_cmd = 'drive-mirror' @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): def tearDown(self): self.vm.shutdown() - for i in self.IMAGES + [ quorum_repair_img, quorum_snapshot_file ]: + for i in self.IMAGES + [ quorum_repair_img, quorum_snapshot_file, + nbd_sock_path ]: # Do a try/except because the test may have deleted some images try: os.remove(i) @@ -XXX,XX +XXX,XX @@ class TestRepairQuorum(iotests.QMPTestCase): self.assert_has_block_node("repair0", quorum_repair_img) self.vm.assert_block_path('quorum0', '/children.1', 'repair0') + def test_with_other_parent(self): + """ + Check that we cannot replace a Quorum child when it has other + parents. + """ + result = self.vm.qmp('nbd-server-start', + addr={ + 'type': 'unix', + 'data': {'path': nbd_sock_path} + }) + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('nbd-server-add', device='img1') + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('drive-mirror', job_id='mirror', device='quorum0', + sync='full', node_name='repair0', replaces='img1', + target=quorum_repair_img, format=iotests.imgfmt) + self.assert_qmp(result, 'error/desc', + "Cannot replace 'img1' by a node mirrored from " + "'quorum0', because it cannot be guaranteed that doing " + "so would not lead to an abrupt change of visible data") + + def test_with_other_parents_after_mirror_start(self): + """ + The same as test_with_other_parent(), but add the NBD server + only when the mirror job is already running. + """ + result = self.vm.qmp('nbd-server-start', + addr={ + 'type': 'unix', + 'data': {'path': nbd_sock_path} + }) + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('drive-mirror', job_id='mirror', device='quorum0', + sync='full', node_name='repair0', replaces='img1', + target=quorum_repair_img, format=iotests.imgfmt) + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('nbd-server-add', device='img1') + self.assert_qmp(result, 'return', {}) + + # The full error message goes to stderr, we will check it later + self.complete_and_wait('mirror', + completion_error='Operation not permitted') + + # Should not have been replaced + self.vm.assert_block_path('quorum0', '/children.1', 'img1') + + # Check the full error message now + self.vm.shutdown() + log = self.vm.get_log() + log = re.sub(r'^\[I \d+\.\d+\] OPENED\n', '', log) + log = re.sub(r'^Formatting.*\n', '', log) + log = re.sub(r'\n\[I \+\d+\.\d+\] CLOSED\n?$', '', log) + log = re.sub(r'^%s: ' % os.path.basename(iotests.qemu_prog), '', log) + + self.assertEqual(log, + "Can no longer replace 'img1' by 'repair0', because " + + "it can no longer be guaranteed that doing so would " + + "not lead to an abrupt change of visible data") + + # Test mirroring with a source that does not have any parents (not even a # BlockBackend) class TestOrphanedSource(iotests.QMPTestCase): diff --git a/tests/qemu-iotests/041.out b/tests/qemu-iotests/041.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/041.out +++ b/tests/qemu-iotests/041.out @@ -XXX,XX +XXX,XX @@ -........................................................................................... +............................................................................................. ---------------------------------------------------------------------- -Ran 91 tests +Ran 93 tests OK -- 2.20.1 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200218103454.296704-20-mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/041 | 46 ++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/041.out | 4 ++-- 2 files changed, 48 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -XXX,XX +XXX,XX @@ class TestOrphanedSource(iotests.QMPTestCase): self.assertFalse('mirror-filter' in nodes, 'Mirror filter node did not disappear') +# Test cases for @replaces that do not necessarily involve Quorum +class TestReplaces(iotests.QMPTestCase): + # Each of these test cases needs their own block graph, so do not + # create any nodes here + def setUp(self): + self.vm = iotests.VM() + self.vm.launch() + + def tearDown(self): + self.vm.shutdown() + for img in (test_img, target_img): + try: + os.remove(img) + except OSError: + pass + + @iotests.skip_if_unsupported(['copy-on-read']) + def test_replace_filter(self): + """ + Check that we can replace filter nodes. + """ + result = self.vm.qmp('blockdev-add', **{ + 'driver': 'copy-on-read', + 'node-name': 'filter0', + 'file': { + 'driver': 'copy-on-read', + 'node-name': 'filter1', + 'file': { + 'driver': 'null-co' + } + } + }) + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('blockdev-add', + node_name='target', driver='null-co') + self.assert_qmp(result, 'return', {}) + + result = self.vm.qmp('blockdev-mirror', job_id='mirror', device='filter0', + target='target', sync='full', replaces='filter1') + self.assert_qmp(result, 'return', {}) + + self.complete_and_wait('mirror') + + self.vm.assert_block_path('filter0', '/file', 'target') + if __name__ == '__main__': iotests.main(supported_fmts=['qcow2', 'qed'], supported_protocols=['file'], diff --git a/tests/qemu-iotests/041.out b/tests/qemu-iotests/041.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/041.out +++ b/tests/qemu-iotests/041.out @@ -XXX,XX +XXX,XX @@ -............................................................................................. +.............................................................................................. ---------------------------------------------------------------------- -Ran 93 tests +Ran 94 tests OK -- 2.20.1 The following changes since commit 16aaacb307ed607b9780c12702c44f0fe52edc7e: Merge remote-tracking branch 'remotes/cohuck/tags/s390x-20200430' into staging (2020-04-30 14:00:36 +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 eaae29ef89d498d0eac553c77b554f310a47f809: qemu-storage-daemon: Fix non-string --object properties (2020-04-30 17:51:07 +0200) ---------------------------------------------------------------- Block layer patches: - Fix resize (extending) of short overlays - nvme: introduce PMR support from NVMe 1.4 spec - qemu-storage-daemon: Fix non-string --object properties ---------------------------------------------------------------- Alberto Garcia (1): qcow2: Add incompatibility note between backing files and raw external data files Andrzej Jakowski (1): nvme: introduce PMR support from NVMe 1.4 spec Kevin Wolf (12): block: Add flags to BlockDriver.bdrv_co_truncate() block: Add flags to bdrv(_co)_truncate() block-backend: Add flags to blk_truncate() qcow2: Support BDRV_REQ_ZERO_WRITE for truncate raw-format: Support BDRV_REQ_ZERO_WRITE for truncate file-posix: Support BDRV_REQ_ZERO_WRITE for truncate block: truncate: Don't make backing file data visible iotests: Filter testfiles out in filter_img_info() iotests: Test committing to short backing file qcow2: Forward ZERO_WRITE flag for full preallocation qom: Factor out user_creatable_add_dict() qemu-storage-daemon: Fix non-string --object properties Paolo Bonzini (1): qemu-iotests: allow qcow2 external discarded clusters to contain stale data docs/interop/qcow2.txt | 3 + hw/block/nvme.h | 2 + include/block/block.h | 5 +- include/block/block_int.h | 10 +- include/block/nvme.h | 172 ++++++++++++++++++++++++++ include/qom/object_interfaces.h | 16 +++ include/sysemu/block-backend.h | 2 +- block.c | 3 +- block/block-backend.c | 4 +- block/commit.c | 4 +- block/crypto.c | 7 +- block/file-posix.c | 6 +- block/file-win32.c | 2 +- block/gluster.c | 1 + block/io.c | 43 ++++++- block/iscsi.c | 2 +- block/mirror.c | 2 +- block/nfs.c | 3 +- block/parallels.c | 6 +- block/qcow.c | 4 +- block/qcow2-cluster.c | 2 +- block/qcow2-refcount.c | 2 +- block/qcow2.c | 73 +++++++++-- block/qed.c | 3 +- block/raw-format.c | 6 +- block/rbd.c | 1 + block/sheepdog.c | 4 +- block/ssh.c | 2 +- block/vdi.c | 2 +- block/vhdx-log.c | 2 +- block/vhdx.c | 6 +- block/vmdk.c | 8 +- block/vpc.c | 2 +- blockdev.c | 2 +- hw/block/nvme.c | 109 ++++++++++++++++ qemu-img.c | 2 +- qemu-io-cmds.c | 2 +- qemu-storage-daemon.c | 4 +- qom/object_interfaces.c | 31 +++++ qom/qom-qmp-cmds.c | 24 +--- tests/test-block-iothread.c | 9 +- tests/qemu-iotests/iotests.py | 5 +- hw/block/Makefile.objs | 2 +- hw/block/trace-events | 4 + tests/qemu-iotests/244 | 10 +- tests/qemu-iotests/244.out | 9 +- tests/qemu-iotests/274 | 155 +++++++++++++++++++++++ tests/qemu-iotests/274.out | 268 ++++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/group | 1 + 49 files changed, 951 insertions(+), 96 deletions(-) create mode 100755 tests/qemu-iotests/274 create mode 100644 tests/qemu-iotests/274.out From: Alberto Garcia <berto@igalia.com> Backing files and raw external data files are mutually exclusive. The documentation of the raw external data bit (in autoclear_features) already indicates that, but we should also mention it on the other side. Suggested-by: Eric Blake <eblake@redhat.com> Signed-off-by: Alberto Garcia <berto@igalia.com> Message-Id: <20200410121816.8334-1-berto@igalia.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- docs/interop/qcow2.txt | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs/interop/qcow2.txt b/docs/interop/qcow2.txt index XXXXXXX..XXXXXXX 100644 --- a/docs/interop/qcow2.txt +++ b/docs/interop/qcow2.txt @@ -XXX,XX +XXX,XX @@ The first cluster of a qcow2 image contains the file header: is stored (NB: The string is not null terminated). 0 if the image doesn't have a backing file. + Note: backing files are incompatible with raw external data + files (auto-clear feature bit 1). + 16 - 19: backing_file_size Length of the backing file name in bytes. Must not be longer than 1023 bytes. Undefined if the image doesn't have -- 2.25.3 From: Paolo Bonzini <pbonzini@redhat.com> Test 244 checks the expected behavior of qcow2 external data files with respect to zero and discarded clusters. Filesystems however are free to ignore discard requests, and this seems to be the case for overlayfs. Relax the tests to skip checks on the external data file for discarded areas, which implies not using qemu-img compare in the data_file_raw=on case. This fixes docker tests on RHEL8. Cc: Kevin Wolf <kwolf@redhat.com> Cc: qemu-block@nongnu.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20200409191006.24429-1-pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/244 | 10 ++++++++-- tests/qemu-iotests/244.out | 9 ++++++--- 2 files changed, 14 insertions(+), 5 deletions(-) diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/244 +++ b/tests/qemu-iotests/244 @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'read -P 0 0 1M' \ echo $QEMU_IO -c 'read -P 0 0 1M' \ -c 'read -P 0x11 1M 1M' \ - -c 'read -P 0 2M 2M' \ -c 'read -P 0x11 4M 1M' \ -c 'read -P 0 5M 1M' \ -f raw "$TEST_IMG.data" | @@ -XXX,XX +XXX,XX @@ $QEMU_IO -c 'read -P 0 0 1M' \ -f $IMGFMT "$TEST_IMG" | _filter_qemu_io +# Discarded clusters are only marked as such in the qcow2 metadata, but +# they can contain stale data in the external data file. Instead, zero +# clusters must be zeroed in the external data file too. echo -$QEMU_IMG compare "$TEST_IMG" "$TEST_IMG.data" +$QEMU_IO -c 'read -P 0 0 1M' \ + -c 'read -P 0x11 1M 1M' \ + -c 'read -P 0 3M 3M' \ + -f raw "$TEST_IMG".data | + _filter_qemu_io echo -n "qcow2 file size after I/O: " du -b $TEST_IMG | cut -f1 diff --git a/tests/qemu-iotests/244.out b/tests/qemu-iotests/244.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/244.out +++ b/tests/qemu-iotests/244.out @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 0 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 1048576/1048576 bytes at offset 1048576 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -read 2097152/2097152 bytes at offset 2097152 -2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 1048576/1048576 bytes at offset 4194304 1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) read 1048576/1048576 bytes at offset 5242880 @@ -XXX,XX +XXX,XX @@ read 1048576/1048576 bytes at offset 1048576 read 4194304/4194304 bytes at offset 2097152 4 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) -Images are identical. +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 3145728/3145728 bytes at offset 3145728 +3 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) qcow2 file size after I/O: 327680 === bdrv_co_block_status test for file and offset=0 === -- 2.25.3 This adds a new BdrvRequestFlags parameter to the .bdrv_co_truncate() driver callbacks, and a supported_truncate_flags field in BlockDriverState that allows drivers to advertise support for request flags in the context of truncate. For now, we always pass 0 and no drivers declare support for any flag. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-2-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 10 +++++++++- block/crypto.c | 3 ++- block/file-posix.c | 2 +- block/file-win32.c | 2 +- block/gluster.c | 1 + block/io.c | 8 +++++++- block/iscsi.c | 2 +- block/nfs.c | 3 ++- block/qcow2.c | 2 +- block/qed.c | 1 + block/raw-format.c | 2 +- block/rbd.c | 1 + block/sheepdog.c | 4 ++-- block/ssh.c | 2 +- tests/test-block-iothread.c | 3 ++- 15 files changed, 33 insertions(+), 13 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriver { */ int coroutine_fn (*bdrv_co_truncate)(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp); + BdrvRequestFlags flags, Error **errp); int64_t (*bdrv_getlength)(BlockDriverState *bs); bool has_variable_length; @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* Flags honored during pwrite_zeroes (so far: BDRV_REQ_FUA, * BDRV_REQ_MAY_UNMAP, BDRV_REQ_WRITE_UNCHANGED) */ unsigned int supported_zero_flags; + /* + * Flags honoured during truncate (so far: BDRV_REQ_ZERO_WRITE). + * + * If BDRV_REQ_ZERO_WRITE is given, the truncate operation must make sure + * that any added space reads as all zeros. If this can't be guaranteed, + * the operation must fail. + */ + unsigned int supported_truncate_flags; /* the following member gives a name to every node on the bs graph. */ char node_name[32]; 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_co_create_generic(BlockDriverState *bs, static int coroutine_fn block_crypto_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { BlockCrypto *crypto = bs->opaque; uint64_t payload_offset = diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ raw_regular_truncate(BlockDriverState *bs, int fd, int64_t offset, static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVRawState *s = bs->opaque; struct stat st; diff --git a/block/file-win32.c b/block/file-win32.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-win32.c +++ b/block/file-win32.c @@ -XXX,XX +XXX,XX @@ static void raw_close(BlockDriverState *bs) static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVRawState *s = bs->opaque; LONG low, high; diff --git a/block/gluster.c b/block/gluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qemu_gluster_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) { BDRVGlusterState *s = bs->opaque; diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, BlockDriverState *bs = child->bs; BlockDriver *drv = bs->drv; BdrvTrackedRequest req; + BdrvRequestFlags flags = 0; int64_t old_size, new_bytes; int ret; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, } if (drv->bdrv_co_truncate) { - ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, errp); + if (flags & ~bs->supported_truncate_flags) { + error_setg(errp, "Block driver does not support requested flags"); + ret = -ENOTSUP; + goto out; + } + ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, flags, errp); } else if (bs->file && drv->is_filter) { ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); } else { diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ static void iscsi_reopen_commit(BDRVReopenState *reopen_state) static int coroutine_fn iscsi_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { IscsiLun *iscsilun = bs->opaque; int64_t cur_length; diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs) static int coroutine_fn nfs_file_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { NFSClient *client = bs->opaque; int ret; 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 @@ fail: static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVQcow2State *s = bs->opaque; uint64_t old_length; diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) { BDRVQEDState *s = bs->opaque; diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp) static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVRawState *s = bs->opaque; diff --git a/block/rbd.c b/block/rbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qemu_rbd_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, + BdrvRequestFlags flags, Error **errp) { int r; diff --git a/block/sheepdog.c b/block/sheepdog.c index XXXXXXX..XXXXXXX 100644 --- a/block/sheepdog.c +++ b/block/sheepdog.c @@ -XXX,XX +XXX,XX @@ static int64_t sd_getlength(BlockDriverState *bs) static int coroutine_fn sd_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVSheepdogState *s = bs->opaque; int ret, fd; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num, assert(!flags); if (offset > s->inode.vdi_size) { - ret = sd_co_truncate(bs, offset, false, PREALLOC_MODE_OFF, NULL); + ret = sd_co_truncate(bs, offset, false, PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } diff --git a/block/ssh.c b/block/ssh.c index XXXXXXX..XXXXXXX 100644 --- a/block/ssh.c +++ b/block/ssh.c @@ -XXX,XX +XXX,XX @@ static int64_t ssh_getlength(BlockDriverState *bs) static int coroutine_fn ssh_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, PreallocMode prealloc, - Error **errp) + BdrvRequestFlags flags, Error **errp) { BDRVSSHState *s = bs->opaque; diff --git a/tests/test-block-iothread.c b/tests/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-block-iothread.c +++ b/tests/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_test_co_pdiscard(BlockDriverState *bs, static int coroutine_fn bdrv_test_co_truncate(BlockDriverState *bs, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { return 0; } -- 2.25.3 Now that block drivers can support flags for .bdrv_co_truncate, expose the parameter in the node level interfaces bdrv_co_truncate() and bdrv_truncate(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-3-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 5 +++-- block/block-backend.c | 2 +- block/crypto.c | 2 +- block/io.c | 12 +++++++----- block/parallels.c | 6 +++--- block/qcow.c | 4 ++-- block/qcow2-refcount.c | 2 +- block/qcow2.c | 15 +++++++++------ block/raw-format.c | 2 +- block/vhdx-log.c | 2 +- block/vhdx.c | 2 +- block/vmdk.c | 2 +- tests/test-block-iothread.c | 6 +++--- 13 files changed, 34 insertions(+), 28 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 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs, void bdrv_refresh_filename(BlockDriverState *bs); int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp); + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp); int bdrv_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp); + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp); int64_t bdrv_nb_sectors(BlockDriverState *bs); int64_t bdrv_getlength(BlockDriverState *bs); diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, return -ENOMEDIUM; } - return bdrv_truncate(blk->root, offset, exact, prealloc, errp); + return bdrv_truncate(blk->root, offset, exact, prealloc, 0, errp); } int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, 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_truncate(BlockDriverState *bs, int64_t offset, bool exact, offset += payload_offset; - return bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); + return bdrv_co_truncate(bs->file, offset, exact, prealloc, 0, errp); } static void block_crypto_close(BlockDriverState *bs) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_parent_cb_resize(BlockDriverState *bs) * 'offset' bytes in length. */ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, + Error **errp) { BlockDriverState *bs = child->bs; BlockDriver *drv = bs->drv; BdrvTrackedRequest req; - BdrvRequestFlags flags = 0; int64_t old_size, new_bytes; int ret; @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, } ret = drv->bdrv_co_truncate(bs, offset, exact, prealloc, flags, errp); } else if (bs->file && drv->is_filter) { - ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); + ret = bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp); } else { error_setg(errp, "Image format driver does not support resize"); ret = -ENOTSUP; @@ -XXX,XX +XXX,XX @@ typedef struct TruncateCo { int64_t offset; bool exact; PreallocMode prealloc; + BdrvRequestFlags flags; Error **errp; int ret; } TruncateCo; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_truncate_co_entry(void *opaque) { TruncateCo *tco = opaque; tco->ret = bdrv_co_truncate(tco->child, tco->offset, tco->exact, - tco->prealloc, tco->errp); + tco->prealloc, tco->flags, tco->errp); aio_wait_kick(); } int bdrv_truncate(BdrvChild *child, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp) { Coroutine *co; TruncateCo tco = { @@ -XXX,XX +XXX,XX @@ int bdrv_truncate(BdrvChild *child, int64_t offset, bool exact, .offset = offset, .exact = exact, .prealloc = prealloc, + .flags = flags, .errp = errp, .ret = NOT_DONE, }; diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num, } else { ret = bdrv_truncate(bs->file, (s->data_end + space) << BDRV_SECTOR_BITS, - false, PREALLOC_MODE_OFF, NULL); + false, PREALLOC_MODE_OFF, 0, NULL); } if (ret < 0) { return ret; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_check(BlockDriverState *bs, * That means we have to pass exact=true. */ ret = bdrv_truncate(bs->file, res->image_end_offset, true, - PREALLOC_MODE_OFF, &local_err); + PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); res->check_errors++; @@ -XXX,XX +XXX,XX @@ static void parallels_close(BlockDriverState *bs) /* errors are ignored, so we might as well pass exact=true */ bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS, true, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); } g_free(s->bat_dirty_bmap); 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, return -E2BIG; } ret = bdrv_truncate(bs->file, cluster_offset + s->cluster_size, - false, PREALLOC_MODE_OFF, NULL); + false, PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int qcow_make_empty(BlockDriverState *bs) l1_length) < 0) return -1; ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) return ret; diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -XXX,XX +XXX,XX @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res, } ret = bdrv_truncate(bs->file, offset + s->cluster_size, false, - PREALLOC_MODE_OFF, &local_err); + PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); goto resize_fail; diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn preallocate_co(BlockDriverState *bs, uint64_t offset, mode = PREALLOC_MODE_OFF; } ret = bdrv_co_truncate(s->data_file, host_offset + cur_bytes, false, - mode, errp); + mode, 0, errp); if (ret < 0) { return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, * always fulfilled, so there is no need to pass it on.) */ bdrv_co_truncate(bs->file, (last_cluster + 1) * s->cluster_size, - false, PREALLOC_MODE_OFF, &local_err); + false, PREALLOC_MODE_OFF, 0, &local_err); if (local_err) { warn_reportf_err(local_err, "Failed to truncate the tail of the image: "); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, * file should be resized to the exact target size, too, * so we pass @exact here. */ - ret = bdrv_co_truncate(s->data_file, offset, exact, prealloc, errp); + ret = bdrv_co_truncate(s->data_file, offset, exact, prealloc, 0, + errp); if (ret < 0) { goto fail; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, new_file_size = allocation_start + nb_new_data_clusters * s->cluster_size; /* Image file grows, so @exact does not matter */ - ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, errp); + ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, 0, + errp); if (ret < 0) { error_prepend(errp, "Failed to resize underlying file: "); qcow2_free_clusters(bs, allocation_start, @@ -XXX,XX +XXX,XX @@ qcow2_co_pwritev_compressed_part(BlockDriverState *bs, if (len < 0) { return len; } - return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, NULL); + return bdrv_co_truncate(bs->file, len, false, PREALLOC_MODE_OFF, 0, + NULL); } if (offset_into_cluster(s, offset)) { @@ -XXX,XX +XXX,XX @@ static int make_completely_empty(BlockDriverState *bs) } ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size, false, - PREALLOC_MODE_OFF, &local_err); + PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); goto fail; diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, s->size = offset; offset += s->offset; - return bdrv_co_truncate(bs->file, offset, exact, prealloc, errp); + return bdrv_co_truncate(bs->file, offset, exact, prealloc, 0, errp); } static void raw_eject(BlockDriverState *bs, bool eject_flag) diff --git a/block/vhdx-log.c b/block/vhdx-log.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx-log.c +++ b/block/vhdx-log.c @@ -XXX,XX +XXX,XX @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s, goto exit; } ret = bdrv_truncate(bs->file, new_file_size, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { goto exit; } diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s, } return bdrv_truncate(bs->file, *new_offset + s->block_size, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); } /* diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ vmdk_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset, } length = QEMU_ALIGN_UP(length, BDRV_SECTOR_SIZE); ret = bdrv_truncate(s->extents[i].file, length, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { return ret; } diff --git a/tests/test-block-iothread.c b/tests/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-block-iothread.c +++ b/tests/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_sync_op_truncate(BdrvChild *c) int ret; /* Normal success path */ - ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, NULL); + ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, 0, NULL); g_assert_cmpint(ret, ==, 0); /* Early error: Negative offset */ - ret = bdrv_truncate(c, -2, false, PREALLOC_MODE_OFF, NULL); + ret = bdrv_truncate(c, -2, false, PREALLOC_MODE_OFF, 0, NULL); g_assert_cmpint(ret, ==, -EINVAL); /* Error: Read-only image */ c->bs->read_only = true; c->bs->open_flags &= ~BDRV_O_RDWR; - ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, NULL); + ret = bdrv_truncate(c, 65536, false, PREALLOC_MODE_OFF, 0, NULL); g_assert_cmpint(ret, ==, -EACCES); c->bs->read_only = false; -- 2.25.3 Now that node level interface bdrv_truncate() supports passing request flags to the block driver, expose this on the BlockBackend level, too. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-4-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/sysemu/block-backend.h | 2 +- block.c | 3 ++- block/block-backend.c | 4 ++-- block/commit.c | 4 ++-- block/crypto.c | 2 +- block/mirror.c | 2 +- block/qcow2.c | 4 ++-- block/qed.c | 2 +- block/vdi.c | 2 +- block/vhdx.c | 4 ++-- block/vmdk.c | 6 +++--- block/vpc.c | 2 +- blockdev.c | 2 +- qemu-img.c | 2 +- qemu-io-cmds.c | 2 +- 15 files changed, 22 insertions(+), 21 deletions(-) diff --git a/include/sysemu/block-backend.h b/include/sysemu/block-backend.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/block-backend.h +++ b/include/sysemu/block-backend.h @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_pwrite_zeroes(BlockBackend *blk, int64_t offset, int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf, int bytes); int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp); + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp); int blk_pdiscard(BlockBackend *blk, int64_t offset, int bytes); int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, int64_t pos, int size); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int64_t create_file_fallback_truncate(BlockBackend *blk, int64_t size; int ret; - ret = blk_truncate(blk, minimum_size, false, PREALLOC_MODE_OFF, &local_err); + ret = blk_truncate(blk, minimum_size, false, PREALLOC_MODE_OFF, 0, + &local_err); if (ret < 0 && ret != -ENOTSUP) { error_propagate(errp, local_err); return ret; diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ int blk_pwrite_compressed(BlockBackend *blk, int64_t offset, const void *buf, } int blk_truncate(BlockBackend *blk, int64_t offset, bool exact, - PreallocMode prealloc, Error **errp) + PreallocMode prealloc, BdrvRequestFlags flags, Error **errp) { if (!blk_is_available(blk)) { error_setg(errp, "No medium inserted"); return -ENOMEDIUM; } - return bdrv_truncate(blk->root, offset, exact, prealloc, 0, errp); + return bdrv_truncate(blk->root, offset, exact, prealloc, flags, errp); } int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf, diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn commit_run(Job *job, Error **errp) } if (base_len < len) { - ret = blk_truncate(s->base, len, false, PREALLOC_MODE_OFF, NULL); + ret = blk_truncate(s->base, len, false, PREALLOC_MODE_OFF, 0, NULL); if (ret) { goto out; } @@ -XXX,XX +XXX,XX @@ int bdrv_commit(BlockDriverState *bs) * grow the backing file image if possible. If not possible, * we must return an error */ if (length > backing_length) { - ret = blk_truncate(backing, length, false, PREALLOC_MODE_OFF, + ret = blk_truncate(backing, length, false, PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); 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 ssize_t block_crypto_init_func(QCryptoBlock *block, * which will be used by the crypto header */ return blk_truncate(data->blk, data->size + headerlen, false, - data->prealloc, errp); + data->prealloc, 0, errp); } diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_run(Job *job, Error **errp) if (s->bdev_length > base_length) { ret = blk_truncate(s->target, s->bdev_length, false, - PREALLOC_MODE_OFF, NULL); + PREALLOC_MODE_OFF, 0, NULL); if (ret < 0) { goto immediate_exit; } diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ qcow2_co_create(BlockdevCreateOptions *create_options, Error **errp) /* Okay, now that we have a valid image, let's give it the right size */ ret = blk_truncate(blk, qcow2_opts->size, false, qcow2_opts->preallocation, - errp); + 0, errp); if (ret < 0) { error_prepend(errp, "Could not resize image: "); goto out; @@ -XXX,XX +XXX,XX @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, * Amending image options should ensure that the image has * exactly the given new values, so pass exact=true here. */ - ret = blk_truncate(blk, new_size, true, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, new_size, true, PREALLOC_MODE_OFF, 0, errp); blk_unref(blk); if (ret < 0) { return ret; diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts, * The QED format associates file length with allocation status, * so a new file (which is empty) must have a length of 0. */ - ret = blk_truncate(blk, 0, true, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, 0, true, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto out; } diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, if (image_type == VDI_TYPE_STATIC) { ret = blk_truncate(blk, offset + blocks * block_size, false, - PREALLOC_MODE_OFF, errp); + PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { error_prepend(errp, "Failed to statically allocate file"); goto exit; diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s, /* All zeroes, so we can just extend the file - the end of the BAT * is the furthest thing we have written yet */ ret = blk_truncate(blk, data_file_offset, false, PREALLOC_MODE_OFF, - errp); + 0, errp); if (ret < 0) { goto exit; } } else if (type == VHDX_TYPE_FIXED) { ret = blk_truncate(blk, data_file_offset + image_size, false, - PREALLOC_MODE_OFF, errp); + PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto exit; } diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int vmdk_init_extent(BlockBackend *blk, int gd_buf_size; if (flat) { - ret = blk_truncate(blk, filesize, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, filesize, false, PREALLOC_MODE_OFF, 0, errp); goto exit; } magic = cpu_to_be32(VMDK4_MAGIC); @@ -XXX,XX +XXX,XX @@ static int vmdk_init_extent(BlockBackend *blk, } ret = blk_truncate(blk, le64_to_cpu(header.grain_offset) << 9, false, - PREALLOC_MODE_OFF, errp); + PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vmdk_co_do_create(int64_t size, /* bdrv_pwrite write padding zeros to align to sector, we don't need that * for description file */ if (desc_offset == 0) { - ret = blk_truncate(blk, desc_len, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, desc_len, false, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { goto exit; } diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int create_fixed_disk(BlockBackend *blk, uint8_t *buf, /* Add footer to total size */ total_size += HEADER_SIZE; - ret = blk_truncate(blk, total_size, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, total_size, false, PREALLOC_MODE_OFF, 0, errp); if (ret < 0) { return ret; } diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void qmp_block_resize(bool has_device, const char *device, } bdrv_drained_begin(bs); - ret = blk_truncate(blk, size, false, PREALLOC_MODE_OFF, errp); + ret = blk_truncate(blk, size, false, PREALLOC_MODE_OFF, 0, errp); bdrv_drained_end(bs); out: diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static int img_resize(int argc, char **argv) * resizing, so pass @exact=true. It is of no use to report * success when the image has not actually been resized. */ - ret = blk_truncate(blk, total_size, true, prealloc, &err); + ret = blk_truncate(blk, total_size, true, prealloc, 0, &err); if (!ret) { qprintf(quiet, "Image resized.\n"); } else { 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 truncate_f(BlockBackend *blk, int argc, char **argv) * exact=true. It is better to err on the "emit more errors" side * than to be overly permissive. */ - ret = blk_truncate(blk, offset, true, PREALLOC_MODE_OFF, &local_err); + ret = blk_truncate(blk, offset, true, PREALLOC_MODE_OFF, 0, &local_err); if (ret < 0) { error_report_err(local_err); return ret; -- 2.25.3 If BDRV_REQ_ZERO_WRITE is set and we're extending the image, calling qcow2_cluster_zeroize() with flags=0 does the right thing: It doesn't undo any previous preallocation, but just adds the zero flag to all relevant L2 entries. If an external data file is in use, a write_zeroes request to the data file is made instead. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200424125448.63318-5-kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2-cluster.c | 2 +- block/qcow2.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 1 deletion(-) diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset, /* Caller must pass aligned values, except at image end */ assert(QEMU_IS_ALIGNED(offset, s->cluster_size)); assert(QEMU_IS_ALIGNED(end_offset, s->cluster_size) || - end_offset == bs->total_sectors << BDRV_SECTOR_BITS); + end_offset >= bs->total_sectors << BDRV_SECTOR_BITS); /* The zero flag is only supported by version 3 and newer */ if (s->qcow_version < 3) { diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_do_open(BlockDriverState *bs, QDict *options, bs->supported_zero_flags = header.version >= 3 ? BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK : 0; + bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; /* Repair image if dirty */ if (!(flags & (BDRV_O_CHECK | BDRV_O_INACTIVE)) && !bs->read_only && @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, g_assert_not_reached(); } + if ((flags & BDRV_REQ_ZERO_WRITE) && offset > old_length) { + uint64_t zero_start = QEMU_ALIGN_UP(old_length, s->cluster_size); + + /* + * Use zero clusters as much as we can. qcow2_cluster_zeroize() + * requires a cluster-aligned start. The end may be unaligned if it is + * at the end of the image (which it is here). + */ + ret = qcow2_cluster_zeroize(bs, zero_start, offset - zero_start, 0); + if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to zero out new clusters"); + goto fail; + } + + /* Write explicit zeros for the unaligned head */ + if (zero_start > old_length) { + uint64_t len = zero_start - old_length; + uint8_t *buf = qemu_blockalign0(bs, len); + QEMUIOVector qiov; + qemu_iovec_init_buf(&qiov, buf, len); + + qemu_co_mutex_unlock(&s->lock); + ret = qcow2_co_pwritev_part(bs, old_length, len, &qiov, 0, 0); + qemu_co_mutex_lock(&s->lock); + + qemu_vfree(buf); + if (ret < 0) { + error_setg_errno(errp, -ret, "Failed to zero out the new area"); + goto fail; + } + } + } + if (prealloc != PREALLOC_MODE_OFF) { /* Flush metadata before actually changing the image size */ ret = qcow2_write_caches(bs); -- 2.25.3 The raw format driver can simply forward the flag and let its bs->file child take care of actually providing the zeros. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200424125448.63318-6-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/raw-format.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset, s->size = offset; offset += s->offset; - return bdrv_co_truncate(bs->file, offset, exact, prealloc, 0, errp); + return bdrv_co_truncate(bs->file, offset, exact, prealloc, flags, errp); } static void raw_eject(BlockDriverState *bs, bool eject_flag) @@ -XXX,XX +XXX,XX @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED | ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & bs->file->bs->supported_zero_flags); + bs->supported_truncate_flags = bs->file->bs->supported_truncate_flags & + BDRV_REQ_ZERO_WRITE; if (bs->probed && !bdrv_is_read_only(bs)) { bdrv_refresh_filename(bs->file->bs); -- 2.25.3 For regular files, we always get BDRV_REQ_ZERO_WRITE behaviour from the OS, so we can advertise the flag and just ignore it. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Alberto Garcia <berto@igalia.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424125448.63318-7-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/file-posix.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, #endif bs->supported_zero_flags = BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK; + if (S_ISREG(st.st_mode)) { + /* When extending regular files, we get zeros from the OS */ + bs->supported_truncate_flags = BDRV_REQ_ZERO_WRITE; + } ret = 0; fail: if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) { -- 2.25.3 When extending the size of an image that has a backing file larger than its old size, make sure that the backing file data doesn't become visible in the guest, but the added area is properly zeroed out. Consider the following scenario where the overlay is shorter than its backing file: base.qcow2: AAAAAAAA overlay.qcow2: BBBB When resizing (extending) overlay.qcow2, the new blocks should not stay unallocated and make the additional As from base.qcow2 visible like before this patch, but zeros should be read. A similar case happens with the various variants of a commit job when an intermediate file is short (- for unallocated): base.qcow2: A-A-AAAA mid.qcow2: BB-B top.qcow2: C--C--C- After commit top.qcow2 to mid.qcow2, the following happens: mid.qcow2: CB-C00C0 (correct result) mid.qcow2: CB-C--C- (before this fix) Without the fix, blocks that previously read as zeros on top.qcow2 suddenly turn into A. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200424125448.63318-8-kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 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 @@ int coroutine_fn bdrv_co_truncate(BdrvChild *child, int64_t offset, bool exact, goto out; } + /* + * If the image has a backing file that is large enough that it would + * provide data for the new area, we cannot leave it unallocated because + * then the backing file content would become visible. Instead, zero-fill + * the new area. + * + * Note that if the image has a backing file, but was opened without the + * backing file, taking care of keeping things consistent with that backing + * file is the user's responsibility. + */ + if (new_bytes && bs->backing) { + int64_t backing_len; + + backing_len = bdrv_getlength(backing_bs(bs)); + if (backing_len < 0) { + ret = backing_len; + error_setg_errno(errp, -ret, "Could not get backing file size"); + goto out; + } + + if (backing_len > old_size) { + flags |= BDRV_REQ_ZERO_WRITE; + } + } + if (drv->bdrv_co_truncate) { if (flags & ~bs->supported_truncate_flags) { error_setg(errp, "Block driver does not support requested flags"); -- 2.25.3 We want to keep TEST_IMG for the full path of the main test image, but filter_testfiles() must be called for other test images before replacing other things like the image format because the test directory path could contain the format as a substring. Insert a filter_testfiles() call between both. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-Id: <20200424125448.63318-9-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/iotests.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -XXX,XX +XXX,XX @@ def filter_img_info(output, filename): for line in output.split('\n'): if 'disk size' in line or 'actual-size' in line: continue - line = line.replace(filename, 'TEST_IMG') \ - .replace(imgfmt, 'IMGFMT') + line = line.replace(filename, 'TEST_IMG') + line = filter_testfiles(line) + line = line.replace(imgfmt, 'IMGFMT') line = re.sub('iters: [0-9]+', 'iters: XXX', line) line = re.sub('uuid: [-a-f0-9]+', 'uuid: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX', line) line = re.sub('cid: [0-9]+', 'cid: XXXXXXXXXX', line) -- 2.25.3 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20200424125448.63318-10-kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/274 | 155 +++++++++++++++++++++ tests/qemu-iotests/274.out | 268 +++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/group | 1 + 3 files changed, 424 insertions(+) create mode 100755 tests/qemu-iotests/274 create mode 100644 tests/qemu-iotests/274.out diff --git a/tests/qemu-iotests/274 b/tests/qemu-iotests/274 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/274 @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Copyright (C) 2019 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: Kevin Wolf <kwolf@redhat.com> +# +# Some tests for short backing files and short overlays + +import iotests + +iotests.verify_image_format(supported_fmts=['qcow2']) +iotests.verify_platform(['linux']) + +size_short = 1 * 1024 * 1024 +size_long = 2 * 1024 * 1024 +size_diff = size_long - size_short + +def create_chain() -> None: + iotests.qemu_img_log('create', '-f', iotests.imgfmt, base, + str(size_long)) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, '-b', base, mid, + str(size_short)) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, '-b', mid, top, + str(size_long)) + + iotests.qemu_io_log('-c', 'write -P 1 0 %d' % size_long, base) + +def create_vm() -> iotests.VM: + vm = iotests.VM() + vm.add_blockdev('file,filename=%s,node-name=base-file' % base) + vm.add_blockdev('%s,file=base-file,node-name=base' % iotests.imgfmt) + vm.add_blockdev('file,filename=%s,node-name=mid-file' % mid) + vm.add_blockdev('%s,file=mid-file,node-name=mid,backing=base' + % iotests.imgfmt) + vm.add_drive(top, 'backing=mid,node-name=top') + return vm + +with iotests.FilePath('base') as base, \ + iotests.FilePath('mid') as mid, \ + iotests.FilePath('top') as top: + + iotests.log('== Commit tests ==') + + create_chain() + + iotests.log('=== Check visible data ===') + + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, top) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), top) + + iotests.log('=== Checking allocation status ===') + + iotests.qemu_io_log('-c', 'alloc 0 %d' % size_short, + '-c', 'alloc %d %d' % (size_short, size_diff), + base) + + iotests.qemu_io_log('-c', 'alloc 0 %d' % size_short, + '-c', 'alloc %d %d' % (size_short, size_diff), + mid) + + iotests.qemu_io_log('-c', 'alloc 0 %d' % size_short, + '-c', 'alloc %d %d' % (size_short, size_diff), + top) + + iotests.log('=== Checking map ===') + + iotests.qemu_img_log('map', '--output=json', base) + iotests.qemu_img_log('map', '--output=human', base) + iotests.qemu_img_log('map', '--output=json', mid) + iotests.qemu_img_log('map', '--output=human', mid) + iotests.qemu_img_log('map', '--output=json', top) + iotests.qemu_img_log('map', '--output=human', top) + + iotests.log('=== Testing qemu-img commit (top -> mid) ===') + + iotests.qemu_img_log('commit', top) + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + + iotests.log('=== Testing HMP commit (top -> mid) ===') + + create_chain() + with create_vm() as vm: + vm.launch() + vm.qmp_log('human-monitor-command', command_line='commit drive0') + + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + + iotests.log('=== Testing QMP active commit (top -> mid) ===') + + create_chain() + with create_vm() as vm: + vm.launch() + vm.qmp_log('block-commit', device='top', base_node='mid', + job_id='job0', auto_dismiss=False) + vm.run_job('job0', wait=5) + + iotests.img_info_log(mid) + iotests.qemu_io_log('-c', 'read -P 1 0 %d' % size_short, mid) + iotests.qemu_io_log('-c', 'read -P 0 %d %d' % (size_short, size_diff), mid) + + + iotests.log('== Resize tests ==') + + # Use different sizes for different allocation modes: + # + # We want to have at least one test where 32 bit truncation in the size of + # the overlapping area becomes visible. This is covered by the + # prealloc='off' case (1G to 6G is an overlap of 5G). + # + # However, we can only do this for modes that don't preallocate data + # because otherwise we might run out of space on the test host. + # + # We also want to test some unaligned combinations. + for (prealloc, base_size, top_size_old, top_size_new, off) in [ + ('off', '6G', '1G', '8G', '5G'), + ('metadata', '32G', '30G', '33G', '31G'), + ('falloc', '10M', '5M', '15M', '9M'), + ('full', '16M', '8M', '12M', '11M'), + ('off', '384k', '253k', '512k', '253k'), + ('off', '400k', '256k', '512k', '336k'), + ('off', '512k', '256k', '500k', '436k')]: + + iotests.log('=== preallocation=%s ===' % prealloc) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, base, base_size) + iotests.qemu_img_log('create', '-f', iotests.imgfmt, '-b', base, top, + top_size_old) + iotests.qemu_io_log('-c', 'write -P 1 %s 64k' % off, base) + + # After this, top_size_old to base_size should be allocated/zeroed. + # + # In theory, leaving base_size to top_size_new unallocated would be + # correct, but in practice, if we zero out anything, we zero out + # everything up to top_size_new. + iotests.qemu_img_log('resize', '-f', iotests.imgfmt, + '--preallocation', prealloc, top, top_size_new) + iotests.qemu_io_log('-c', 'read -P 0 %s 64k' % off, top) + iotests.qemu_io_log('-c', 'map', top) + iotests.qemu_img_log('map', '--output=json', top) diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ +== Commit tests == +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Check visible data === +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Checking allocation status === +1048576/1048576 bytes allocated at offset 0 bytes +1048576/1048576 bytes allocated at offset 1 MiB + +0/1048576 bytes allocated at offset 0 bytes +0/0 bytes allocated at offset 1 MiB + +0/1048576 bytes allocated at offset 0 bytes +0/1048576 bytes allocated at offset 1 MiB + +=== Checking map === +[{ "start": 0, "length": 2097152, "depth": 0, "zero": false, "data": true, "offset": 327680}] + +Offset Length Mapped to File +0 0x200000 0x50000 TEST_DIR/PID-base + +[{ "start": 0, "length": 1048576, "depth": 1, "zero": false, "data": true, "offset": 327680}] + +Offset Length Mapped to File +0 0x100000 0x50000 TEST_DIR/PID-base + +[{ "start": 0, "length": 1048576, "depth": 2, "zero": false, "data": true, "offset": 327680}, +{ "start": 1048576, "length": 1048576, "depth": 0, "zero": true, "data": false}] + +Offset Length Mapped to File +0 0x100000 0x50000 TEST_DIR/PID-base + +=== Testing qemu-img commit (top -> mid) === +Image committed. + +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +Format specific information: + compat: 1.1 + lazy refcounts: false + refcount bits: 16 + corrupt: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing HMP commit (top -> mid) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +{"execute": "human-monitor-command", "arguments": {"command-line": "commit drive0"}} +{"return": ""} +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +Format specific information: + compat: 1.1 + lazy refcounts: false + refcount bits: 16 + corrupt: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing QMP active commit (top -> mid) === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=2097152 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-mid', fmt=qcow2 size=1048576 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=2097152 backing_file=TEST_DIR/PID-mid cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 2097152/2097152 bytes at offset 0 +2 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +{"execute": "block-commit", "arguments": {"auto-dismiss": false, "base-node": "mid", "device": "top", "job-id": "job0"}} +{"return": {}} +{"execute": "job-complete", "arguments": {"id": "job0"}} +{"return": {}} +{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_READY", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"data": {"device": "job0", "len": 0, "offset": 0, "speed": 0, "type": "commit"}, "event": "BLOCK_JOB_COMPLETED", "timestamp": {"microseconds": "USECS", "seconds": "SECS"}} +{"execute": "job-dismiss", "arguments": {"id": "job0"}} +{"return": {}} +image: TEST_IMG +file format: IMGFMT +virtual size: 2 MiB (2097152 bytes) +cluster_size: 65536 +backing file: TEST_DIR/PID-base +Format specific information: + compat: 1.1 + lazy refcounts: false + refcount bits: 16 + corrupt: false + +read 1048576/1048576 bytes at offset 0 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +read 1048576/1048576 bytes at offset 1048576 +1 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== Resize tests == +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=6442450944 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=1073741824 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 5368709120 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 5368709120 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +1 GiB (0x40000000) bytes not allocated at offset 0 bytes (0x0) +7 GiB (0x1c0000000) bytes allocated at offset 1 GiB (0x40000000) + +[{ "start": 0, "length": 1073741824, "depth": 1, "zero": true, "data": false}, +{ "start": 1073741824, "length": 7516192768, "depth": 0, "zero": true, "data": false}] + +=== preallocation=metadata === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=34359738368 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=32212254720 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 33285996544 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 33285996544 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +30 GiB (0x780000000) bytes not allocated at offset 0 bytes (0x0) +3 GiB (0xc0000000) bytes allocated at offset 30 GiB (0x780000000) + +[{ "start": 0, "length": 32212254720, "depth": 1, "zero": true, "data": false}, +{ "start": 32212254720, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 327680}, +{ "start": 32749125632, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 537264128}, +{ "start": 33285996544, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 1074200576}, +{ "start": 33822867456, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 1611137024}, +{ "start": 34359738368, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 2148139008}, +{ "start": 34896609280, "length": 536870912, "depth": 0, "zero": true, "data": false, "offset": 2685075456}] + +=== preallocation=falloc === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=10485760 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=5242880 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 9437184 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 9437184 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +5 MiB (0x500000) bytes not allocated at offset 0 bytes (0x0) +10 MiB (0xa00000) bytes allocated at offset 5 MiB (0x500000) + +[{ "start": 0, "length": 5242880, "depth": 1, "zero": true, "data": false}, +{ "start": 5242880, "length": 10485760, "depth": 0, "zero": true, "data": false, "offset": 327680}] + +=== preallocation=full === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=16777216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=8388608 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 11534336 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 11534336 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +8 MiB (0x800000) bytes not allocated at offset 0 bytes (0x0) +4 MiB (0x400000) bytes allocated at offset 8 MiB (0x800000) + +[{ "start": 0, "length": 8388608, "depth": 1, "zero": true, "data": false}, +{ "start": 8388608, "length": 4194304, "depth": 0, "zero": true, "data": false, "offset": 327680}] + +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=393216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=259072 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 259072 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 259072 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +192 KiB (0x30000) bytes not allocated at offset 0 bytes (0x0) +320 KiB (0x50000) bytes allocated at offset 192 KiB (0x30000) + +[{ "start": 0, "length": 196608, "depth": 1, "zero": true, "data": false}, +{ "start": 196608, "length": 65536, "depth": 0, "zero": false, "data": true, "offset": 327680}, +{ "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}] + +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=409600 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 344064 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 344064 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +256 KiB (0x40000) bytes not allocated at offset 0 bytes (0x0) +256 KiB (0x40000) bytes allocated at offset 256 KiB (0x40000) + +[{ "start": 0, "length": 262144, "depth": 1, "zero": true, "data": false}, +{ "start": 262144, "length": 262144, "depth": 0, "zero": true, "data": false}] + +=== preallocation=off === +Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=524288 cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +Formatting 'TEST_DIR/PID-top', fmt=qcow2 size=262144 backing_file=TEST_DIR/PID-base cluster_size=65536 lazy_refcounts=off refcount_bits=16 + +wrote 65536/65536 bytes at offset 446464 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +Image resized. + +read 65536/65536 bytes at offset 446464 +64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +256 KiB (0x40000) bytes not allocated at offset 0 bytes (0x0) +244 KiB (0x3d000) bytes allocated at offset 256 KiB (0x40000) + +[{ "start": 0, "length": 262144, "depth": 1, "zero": true, "data": false}, +{ "start": 262144, "length": 249856, "depth": 0, "zero": true, "data": false}] + 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 @@ 270 rw backing quick 272 rw 273 backing quick +274 rw backing 277 rw quick 279 rw backing quick 280 rw migration quick -- 2.25.3 The BDRV_REQ_ZERO_WRITE is currently implemented in a way that first the image is possibly preallocated and then the zero flag is added to all clusters. This means that a copy-on-write operation may be needed when writing to these clusters, despite having used preallocation, negating one of the major benefits of preallocation. Instead, try to forward the BDRV_REQ_ZERO_WRITE to the protocol driver, and if the protocol driver can ensure that the new area reads as zeros, we can skip setting the zero flag in the qcow2 layer. Unfortunately, the same approach doesn't work for metadata preallocation, so we'll still set the zero flag there. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Message-Id: <20200424142701.67053-1-kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.c | 22 +++++++++++++++++++--- tests/qemu-iotests/274.out | 4 ++-- 2 files changed, 21 insertions(+), 5 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 coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset, /* Allocate the data area */ new_file_size = allocation_start + nb_new_data_clusters * s->cluster_size; - /* Image file grows, so @exact does not matter */ - ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, 0, - errp); + /* + * Image file grows, so @exact does not matter. + * + * If we need to zero out the new area, try first whether the protocol + * driver can already take care of this. + */ + if (flags & BDRV_REQ_ZERO_WRITE) { + ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, + BDRV_REQ_ZERO_WRITE, NULL); + if (ret >= 0) { + flags &= ~BDRV_REQ_ZERO_WRITE; + } + } else { + ret = -1; + } + if (ret < 0) { + ret = bdrv_co_truncate(bs->file, new_file_size, false, prealloc, 0, + errp); + } if (ret < 0) { error_prepend(errp, "Failed to resize underlying file: "); qcow2_free_clusters(bs, allocation_start, diff --git a/tests/qemu-iotests/274.out b/tests/qemu-iotests/274.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/274.out +++ b/tests/qemu-iotests/274.out @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 9437184 10 MiB (0xa00000) bytes allocated at offset 5 MiB (0x500000) [{ "start": 0, "length": 5242880, "depth": 1, "zero": true, "data": false}, -{ "start": 5242880, "length": 10485760, "depth": 0, "zero": true, "data": false, "offset": 327680}] +{ "start": 5242880, "length": 10485760, "depth": 0, "zero": false, "data": true, "offset": 327680}] === preallocation=full === Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=16777216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 11534336 4 MiB (0x400000) bytes allocated at offset 8 MiB (0x800000) [{ "start": 0, "length": 8388608, "depth": 1, "zero": true, "data": false}, -{ "start": 8388608, "length": 4194304, "depth": 0, "zero": true, "data": false, "offset": 327680}] +{ "start": 8388608, "length": 4194304, "depth": 0, "zero": false, "data": true, "offset": 327680}] === preallocation=off === Formatting 'TEST_DIR/PID-base', fmt=qcow2 size=393216 cluster_size=65536 lazy_refcounts=off refcount_bits=16 -- 2.25.3 From: Andrzej Jakowski <andrzej.jakowski@linux.intel.com> This patch introduces support for PMR that has been defined as part of NVMe 1.4 spec. User can now specify a pmrdev option that should point to HostMemoryBackend. pmrdev memory region will subsequently be exposed as PCI BAR 2 in emulated NVMe device. Guest OS can perform mmio read and writes to the PMR region that will stay persistent across system reboot. Signed-off-by: Andrzej Jakowski <andrzej.jakowski@linux.intel.com> Reviewed-by: Klaus Jensen <k.jensen@samsung.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20200330164656.9348-1-andrzej.jakowski@linux.intel.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/block/nvme.h | 2 + include/block/nvme.h | 172 +++++++++++++++++++++++++++++++++++++++++ hw/block/nvme.c | 109 ++++++++++++++++++++++++++ hw/block/Makefile.objs | 2 +- hw/block/trace-events | 4 + 5 files changed, 288 insertions(+), 1 deletion(-) diff --git a/hw/block/nvme.h b/hw/block/nvme.h index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nvme.h +++ b/hw/block/nvme.h @@ -XXX,XX +XXX,XX @@ typedef struct NvmeCtrl { uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */ char *serial; + HostMemoryBackend *pmrdev; + NvmeNamespace *namespaces; NvmeSQueue **sq; NvmeCQueue **cq; diff --git a/include/block/nvme.h b/include/block/nvme.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -XXX,XX +XXX,XX @@ typedef struct NvmeBar { uint64_t acq; uint32_t cmbloc; uint32_t cmbsz; + uint8_t padding[3520]; /* not used by QEMU */ + uint32_t pmrcap; + uint32_t pmrctl; + uint32_t pmrsts; + uint32_t pmrebs; + uint32_t pmrswtp; + uint32_t pmrmsc; } NvmeBar; enum NvmeCapShift { @@ -XXX,XX +XXX,XX @@ enum NvmeCapShift { CAP_CSS_SHIFT = 37, CAP_MPSMIN_SHIFT = 48, CAP_MPSMAX_SHIFT = 52, + CAP_PMR_SHIFT = 56, }; enum NvmeCapMask { @@ -XXX,XX +XXX,XX @@ enum NvmeCapMask { CAP_CSS_MASK = 0xff, CAP_MPSMIN_MASK = 0xf, CAP_MPSMAX_MASK = 0xf, + CAP_PMR_MASK = 0x1, }; #define NVME_CAP_MQES(cap) (((cap) >> CAP_MQES_SHIFT) & CAP_MQES_MASK) @@ -XXX,XX +XXX,XX @@ enum NvmeCapMask { << CAP_MPSMIN_SHIFT) #define NVME_CAP_SET_MPSMAX(cap, val) (cap |= (uint64_t)(val & CAP_MPSMAX_MASK)\ << CAP_MPSMAX_SHIFT) +#define NVME_CAP_SET_PMRS(cap, val) (cap |= (uint64_t)(val & CAP_PMR_MASK)\ + << CAP_PMR_SHIFT) enum NvmeCcShift { CC_EN_SHIFT = 0, @@ -XXX,XX +XXX,XX @@ enum NvmeCmbszMask { #define NVME_CMBSZ_GETSIZE(cmbsz) \ (NVME_CMBSZ_SZ(cmbsz) * (1 << (12 + 4 * NVME_CMBSZ_SZU(cmbsz)))) +enum NvmePmrcapShift { + PMRCAP_RDS_SHIFT = 3, + PMRCAP_WDS_SHIFT = 4, + PMRCAP_BIR_SHIFT = 5, + PMRCAP_PMRTU_SHIFT = 8, + PMRCAP_PMRWBM_SHIFT = 10, + PMRCAP_PMRTO_SHIFT = 16, + PMRCAP_CMSS_SHIFT = 24, +}; + +enum NvmePmrcapMask { + PMRCAP_RDS_MASK = 0x1, + PMRCAP_WDS_MASK = 0x1, + PMRCAP_BIR_MASK = 0x7, + PMRCAP_PMRTU_MASK = 0x3, + PMRCAP_PMRWBM_MASK = 0xf, + PMRCAP_PMRTO_MASK = 0xff, + PMRCAP_CMSS_MASK = 0x1, +}; + +#define NVME_PMRCAP_RDS(pmrcap) \ + ((pmrcap >> PMRCAP_RDS_SHIFT) & PMRCAP_RDS_MASK) +#define NVME_PMRCAP_WDS(pmrcap) \ + ((pmrcap >> PMRCAP_WDS_SHIFT) & PMRCAP_WDS_MASK) +#define NVME_PMRCAP_BIR(pmrcap) \ + ((pmrcap >> PMRCAP_BIR_SHIFT) & PMRCAP_BIR_MASK) +#define NVME_PMRCAP_PMRTU(pmrcap) \ + ((pmrcap >> PMRCAP_PMRTU_SHIFT) & PMRCAP_PMRTU_MASK) +#define NVME_PMRCAP_PMRWBM(pmrcap) \ + ((pmrcap >> PMRCAP_PMRWBM_SHIFT) & PMRCAP_PMRWBM_MASK) +#define NVME_PMRCAP_PMRTO(pmrcap) \ + ((pmrcap >> PMRCAP_PMRTO_SHIFT) & PMRCAP_PMRTO_MASK) +#define NVME_PMRCAP_CMSS(pmrcap) \ + ((pmrcap >> PMRCAP_CMSS_SHIFT) & PMRCAP_CMSS_MASK) + +#define NVME_PMRCAP_SET_RDS(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_RDS_MASK) << PMRCAP_RDS_SHIFT) +#define NVME_PMRCAP_SET_WDS(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_WDS_MASK) << PMRCAP_WDS_SHIFT) +#define NVME_PMRCAP_SET_BIR(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_BIR_MASK) << PMRCAP_BIR_SHIFT) +#define NVME_PMRCAP_SET_PMRTU(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_PMRTU_MASK) << PMRCAP_PMRTU_SHIFT) +#define NVME_PMRCAP_SET_PMRWBM(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_PMRWBM_MASK) << PMRCAP_PMRWBM_SHIFT) +#define NVME_PMRCAP_SET_PMRTO(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_PMRTO_MASK) << PMRCAP_PMRTO_SHIFT) +#define NVME_PMRCAP_SET_CMSS(pmrcap, val) \ + (pmrcap |= (uint64_t)(val & PMRCAP_CMSS_MASK) << PMRCAP_CMSS_SHIFT) + +enum NvmePmrctlShift { + PMRCTL_EN_SHIFT = 0, +}; + +enum NvmePmrctlMask { + PMRCTL_EN_MASK = 0x1, +}; + +#define NVME_PMRCTL_EN(pmrctl) ((pmrctl >> PMRCTL_EN_SHIFT) & PMRCTL_EN_MASK) + +#define NVME_PMRCTL_SET_EN(pmrctl, val) \ + (pmrctl |= (uint64_t)(val & PMRCTL_EN_MASK) << PMRCTL_EN_SHIFT) + +enum NvmePmrstsShift { + PMRSTS_ERR_SHIFT = 0, + PMRSTS_NRDY_SHIFT = 8, + PMRSTS_HSTS_SHIFT = 9, + PMRSTS_CBAI_SHIFT = 12, +}; + +enum NvmePmrstsMask { + PMRSTS_ERR_MASK = 0xff, + PMRSTS_NRDY_MASK = 0x1, + PMRSTS_HSTS_MASK = 0x7, + PMRSTS_CBAI_MASK = 0x1, +}; + +#define NVME_PMRSTS_ERR(pmrsts) \ + ((pmrsts >> PMRSTS_ERR_SHIFT) & PMRSTS_ERR_MASK) +#define NVME_PMRSTS_NRDY(pmrsts) \ + ((pmrsts >> PMRSTS_NRDY_SHIFT) & PMRSTS_NRDY_MASK) +#define NVME_PMRSTS_HSTS(pmrsts) \ + ((pmrsts >> PMRSTS_HSTS_SHIFT) & PMRSTS_HSTS_MASK) +#define NVME_PMRSTS_CBAI(pmrsts) \ + ((pmrsts >> PMRSTS_CBAI_SHIFT) & PMRSTS_CBAI_MASK) + +#define NVME_PMRSTS_SET_ERR(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_ERR_MASK) << PMRSTS_ERR_SHIFT) +#define NVME_PMRSTS_SET_NRDY(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_NRDY_MASK) << PMRSTS_NRDY_SHIFT) +#define NVME_PMRSTS_SET_HSTS(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_HSTS_MASK) << PMRSTS_HSTS_SHIFT) +#define NVME_PMRSTS_SET_CBAI(pmrsts, val) \ + (pmrsts |= (uint64_t)(val & PMRSTS_CBAI_MASK) << PMRSTS_CBAI_SHIFT) + +enum NvmePmrebsShift { + PMREBS_PMRSZU_SHIFT = 0, + PMREBS_RBB_SHIFT = 4, + PMREBS_PMRWBZ_SHIFT = 8, +}; + +enum NvmePmrebsMask { + PMREBS_PMRSZU_MASK = 0xf, + PMREBS_RBB_MASK = 0x1, + PMREBS_PMRWBZ_MASK = 0xffffff, +}; + +#define NVME_PMREBS_PMRSZU(pmrebs) \ + ((pmrebs >> PMREBS_PMRSZU_SHIFT) & PMREBS_PMRSZU_MASK) +#define NVME_PMREBS_RBB(pmrebs) \ + ((pmrebs >> PMREBS_RBB_SHIFT) & PMREBS_RBB_MASK) +#define NVME_PMREBS_PMRWBZ(pmrebs) \ + ((pmrebs >> PMREBS_PMRWBZ_SHIFT) & PMREBS_PMRWBZ_MASK) + +#define NVME_PMREBS_SET_PMRSZU(pmrebs, val) \ + (pmrebs |= (uint64_t)(val & PMREBS_PMRSZU_MASK) << PMREBS_PMRSZU_SHIFT) +#define NVME_PMREBS_SET_RBB(pmrebs, val) \ + (pmrebs |= (uint64_t)(val & PMREBS_RBB_MASK) << PMREBS_RBB_SHIFT) +#define NVME_PMREBS_SET_PMRWBZ(pmrebs, val) \ + (pmrebs |= (uint64_t)(val & PMREBS_PMRWBZ_MASK) << PMREBS_PMRWBZ_SHIFT) + +enum NvmePmrswtpShift { + PMRSWTP_PMRSWTU_SHIFT = 0, + PMRSWTP_PMRSWTV_SHIFT = 8, +}; + +enum NvmePmrswtpMask { + PMRSWTP_PMRSWTU_MASK = 0xf, + PMRSWTP_PMRSWTV_MASK = 0xffffff, +}; + +#define NVME_PMRSWTP_PMRSWTU(pmrswtp) \ + ((pmrswtp >> PMRSWTP_PMRSWTU_SHIFT) & PMRSWTP_PMRSWTU_MASK) +#define NVME_PMRSWTP_PMRSWTV(pmrswtp) \ + ((pmrswtp >> PMRSWTP_PMRSWTV_SHIFT) & PMRSWTP_PMRSWTV_MASK) + +#define NVME_PMRSWTP_SET_PMRSWTU(pmrswtp, val) \ + (pmrswtp |= (uint64_t)(val & PMRSWTP_PMRSWTU_MASK) << PMRSWTP_PMRSWTU_SHIFT) +#define NVME_PMRSWTP_SET_PMRSWTV(pmrswtp, val) \ + (pmrswtp |= (uint64_t)(val & PMRSWTP_PMRSWTV_MASK) << PMRSWTP_PMRSWTV_SHIFT) + +enum NvmePmrmscShift { + PMRMSC_CMSE_SHIFT = 1, + PMRMSC_CBA_SHIFT = 12, +}; + +enum NvmePmrmscMask { + PMRMSC_CMSE_MASK = 0x1, + PMRMSC_CBA_MASK = 0xfffffffffffff, +}; + +#define NVME_PMRMSC_CMSE(pmrmsc) \ + ((pmrmsc >> PMRMSC_CMSE_SHIFT) & PMRMSC_CMSE_MASK) +#define NVME_PMRMSC_CBA(pmrmsc) \ + ((pmrmsc >> PMRMSC_CBA_SHIFT) & PMRMSC_CBA_MASK) + +#define NVME_PMRMSC_SET_CMSE(pmrmsc, val) \ + (pmrmsc |= (uint64_t)(val & PMRMSC_CMSE_MASK) << PMRMSC_CMSE_SHIFT) +#define NVME_PMRMSC_SET_CBA(pmrmsc, val) \ + (pmrmsc |= (uint64_t)(val & PMRMSC_CBA_MASK) << PMRMSC_CBA_SHIFT) + typedef struct NvmeCmd { uint8_t opcode; uint8_t fuse; 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 @@ * -drive file=<file>,if=none,id=<drive_id> * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \ * cmb_size_mb=<cmb_size_mb[optional]>, \ + * [pmrdev=<mem_backend_file_id>,] \ * num_queues=<N[optional]> * * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at * offset 0 in BAR2 and supports only WDS, RDS and SQS for now. + * + * cmb_size_mb= and pmrdev= options are mutually exclusive due to limitation + * in available BAR's. cmb_size_mb= will take precedence over pmrdev= when + * both provided. + * Enabling pmr emulation can be achieved by pointing to memory-backend-file. + * For example: + * -object memory-backend-file,id=<mem_id>,share=on,mem-path=<file_path>, \ + * size=<size> .... -device nvme,...,pmrdev=<mem_id> */ #include "qemu/osdep.h" @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "qapi/error.h" #include "qapi/visitor.h" +#include "sysemu/hostmem.h" #include "sysemu/block-backend.h" +#include "exec/ram_addr.h" #include "qemu/log.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, NVME_GUEST_ERR(nvme_ub_mmiowr_cmbsz_readonly, "invalid write to read only CMBSZ, ignored"); return; + case 0xE00: /* PMRCAP */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrcap_readonly, + "invalid write to PMRCAP register, ignored"); + return; + case 0xE04: /* TODO PMRCTL */ + break; + case 0xE08: /* PMRSTS */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrsts_readonly, + "invalid write to PMRSTS register, ignored"); + return; + case 0xE0C: /* PMREBS */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrebs_readonly, + "invalid write to PMREBS register, ignored"); + return; + case 0xE10: /* PMRSWTP */ + NVME_GUEST_ERR(nvme_ub_mmiowr_pmrswtp_readonly, + "invalid write to PMRSWTP register, ignored"); + return; + case 0xE14: /* TODO PMRMSC */ + break; default: NVME_GUEST_ERR(nvme_ub_mmiowr_invalid, "invalid MMIO write," @@ -XXX,XX +XXX,XX @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) } if (addr < sizeof(n->bar)) { + /* + * When PMRWBM bit 1 is set then read from + * from PMRSTS should ensure prior writes + * made it to persistent media + */ + if (addr == 0xE08 && + (NVME_PMRCAP_PMRWBM(n->bar.pmrcap) & 0x02)) { + qemu_ram_writeback(n->pmrdev->mr.ram_block, + 0, n->pmrdev->size); + } memcpy(&val, ptr + addr, size); } else { NVME_GUEST_ERR(nvme_ub_mmiord_invalid_ofs, @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) error_setg(errp, "serial property not set"); return; } + + if (!n->cmb_size_mb && n->pmrdev) { + if (host_memory_backend_is_mapped(n->pmrdev)) { + char *path = object_get_canonical_path_component(OBJECT(n->pmrdev)); + error_setg(errp, "can't use already busy memdev: %s", path); + g_free(path); + return; + } + + if (!is_power_of_2(n->pmrdev->size)) { + error_setg(errp, "pmr backend size needs to be power of 2 in size"); + return; + } + + host_memory_backend_set_mapped(n->pmrdev, true); + } + blkconf_blocksizes(&n->conf); if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk), false, errp)) { @@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 | PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem); + } else if (n->pmrdev) { + /* Controller Capabilities register */ + NVME_CAP_SET_PMRS(n->bar.cap, 1); + + /* PMR Capabities register */ + n->bar.pmrcap = 0; + NVME_PMRCAP_SET_RDS(n->bar.pmrcap, 0); + NVME_PMRCAP_SET_WDS(n->bar.pmrcap, 0); + NVME_PMRCAP_SET_BIR(n->bar.pmrcap, 2); + NVME_PMRCAP_SET_PMRTU(n->bar.pmrcap, 0); + /* Turn on bit 1 support */ + NVME_PMRCAP_SET_PMRWBM(n->bar.pmrcap, 0x02); + NVME_PMRCAP_SET_PMRTO(n->bar.pmrcap, 0); + NVME_PMRCAP_SET_CMSS(n->bar.pmrcap, 0); + + /* PMR Control register */ + n->bar.pmrctl = 0; + NVME_PMRCTL_SET_EN(n->bar.pmrctl, 0); + + /* PMR Status register */ + n->bar.pmrsts = 0; + NVME_PMRSTS_SET_ERR(n->bar.pmrsts, 0); + NVME_PMRSTS_SET_NRDY(n->bar.pmrsts, 0); + NVME_PMRSTS_SET_HSTS(n->bar.pmrsts, 0); + NVME_PMRSTS_SET_CBAI(n->bar.pmrsts, 0); + + /* PMR Elasticity Buffer Size register */ + n->bar.pmrebs = 0; + NVME_PMREBS_SET_PMRSZU(n->bar.pmrebs, 0); + NVME_PMREBS_SET_RBB(n->bar.pmrebs, 0); + NVME_PMREBS_SET_PMRWBZ(n->bar.pmrebs, 0); + + /* PMR Sustained Write Throughput register */ + n->bar.pmrswtp = 0; + NVME_PMRSWTP_SET_PMRSWTU(n->bar.pmrswtp, 0); + NVME_PMRSWTP_SET_PMRSWTV(n->bar.pmrswtp, 0); + + /* PMR Memory Space Control register */ + n->bar.pmrmsc = 0; + NVME_PMRMSC_SET_CMSE(n->bar.pmrmsc, 0); + NVME_PMRMSC_SET_CBA(n->bar.pmrmsc, 0); + + pci_register_bar(pci_dev, NVME_PMRCAP_BIR(n->bar.pmrcap), + PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 | + PCI_BASE_ADDRESS_MEM_PREFETCH, &n->pmrdev->mr); } for (i = 0; i < n->num_namespaces; i++) { @@ -XXX,XX +XXX,XX @@ static void nvme_exit(PCIDevice *pci_dev) if (n->cmb_size_mb) { g_free(n->cmbuf); } + + if (n->pmrdev) { + host_memory_backend_set_mapped(n->pmrdev, false); + } msix_uninit_exclusive_bar(pci_dev); } static Property nvme_props[] = { DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf), + DEFINE_PROP_LINK("pmrdev", NvmeCtrl, pmrdev, TYPE_MEMORY_BACKEND, + HostMemoryBackend *), DEFINE_PROP_STRING("serial", NvmeCtrl, serial), DEFINE_PROP_UINT32("cmb_size_mb", NvmeCtrl, cmb_size_mb, 0), DEFINE_PROP_UINT32("num_queues", NvmeCtrl, num_queues, 64), diff --git a/hw/block/Makefile.objs b/hw/block/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/block/Makefile.objs +++ b/hw/block/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_PFLASH_CFI02) += pflash_cfi02.o common-obj-$(CONFIG_XEN) += xen-block.o common-obj-$(CONFIG_ECC) += ecc.o common-obj-$(CONFIG_ONENAND) += onenand.o -common-obj-$(CONFIG_NVME_PCI) += nvme.o common-obj-$(CONFIG_SWIM) += swim.o common-obj-$(CONFIG_SH4) += tc58128.o obj-$(CONFIG_VIRTIO_BLK) += virtio-blk.o obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk.o +obj-$(CONFIG_NVME_PCI) += nvme.o obj-y += dataplane/ 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 @@ nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CA 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_pmrcap_readonly(void) "invalid write to read only PMRCAP, ignored" +nvme_ub_mmiowr_pmrsts_readonly(void) "invalid write to read only PMRSTS, ignored" +nvme_ub_mmiowr_pmrebs_readonly(void) "invalid write to read only PMREBS, ignored" +nvme_ub_mmiowr_pmrswtp_readonly(void) "invalid write to read only PMRSWTP, 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"" -- 2.25.3 The QMP handler qmp_object_add() and the implementation of --object in qemu-storage-daemon can share most of the code. Currently, qemu-storage-daemon calls qmp_object_add(), but this is not correct because different visitors need to be used. As a first step towards a fix, make qmp_object_add() a wrapper around a new function user_creatable_add_dict() that can get an additional parameter. The handling of "props" is only required for compatibility and not required for the qemu-storage-daemon command line, so it stays in qmp_object_add(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qom/object_interfaces.h | 12 ++++++++++++ qom/object_interfaces.c | 27 +++++++++++++++++++++++++++ qom/qom-qmp-cmds.c | 24 +----------------------- 3 files changed, 40 insertions(+), 23 deletions(-) diff --git a/include/qom/object_interfaces.h b/include/qom/object_interfaces.h index XXXXXXX..XXXXXXX 100644 --- a/include/qom/object_interfaces.h +++ b/include/qom/object_interfaces.h @@ -XXX,XX +XXX,XX @@ Object *user_creatable_add_type(const char *type, const char *id, const QDict *qdict, Visitor *v, Error **errp); +/** + * user_creatable_add_dict: + * @qdict: the object definition + * @errp: if an error occurs, a pointer to an area to store the error + * + * Create an instance of the user creatable object that is defined by + * @qdict. The object type is taken from the QDict key 'qom-type', its + * ID from the key 'id'. The remaining entries in @qdict are used to + * initialize the object properties. + */ +void user_creatable_add_dict(QDict *qdict, Error **errp); + /** * user_creatable_add_opts: * @opts: the object definition diff --git a/qom/object_interfaces.c b/qom/object_interfaces.c index XXXXXXX..XXXXXXX 100644 --- a/qom/object_interfaces.c +++ b/qom/object_interfaces.c @@ -XXX,XX +XXX,XX @@ #include "qapi/qmp/qerror.h" #include "qapi/qmp/qjson.h" #include "qapi/qmp/qstring.h" +#include "qapi/qobject-input-visitor.h" #include "qom/object_interfaces.h" #include "qemu/help_option.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ out: return obj; } +void user_creatable_add_dict(QDict *qdict, Error **errp) +{ + Visitor *v; + Object *obj; + g_autofree char *type = NULL; + g_autofree char *id = NULL; + + type = g_strdup(qdict_get_try_str(qdict, "qom-type")); + if (!type) { + error_setg(errp, QERR_MISSING_PARAMETER, "qom-type"); + return; + } + qdict_del(qdict, "qom-type"); + + id = g_strdup(qdict_get_try_str(qdict, "id")); + if (!id) { + error_setg(errp, QERR_MISSING_PARAMETER, "id"); + return; + } + qdict_del(qdict, "id"); + + v = qobject_input_visitor_new(QOBJECT(qdict)); + obj = user_creatable_add_type(type, id, qdict, v, errp); + visit_free(v); + object_unref(obj); +} Object *user_creatable_add_opts(QemuOpts *opts, Error **errp) { diff --git a/qom/qom-qmp-cmds.c b/qom/qom-qmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qom/qom-qmp-cmds.c +++ b/qom/qom-qmp-cmds.c @@ -XXX,XX +XXX,XX @@ #include "qapi/qapi-commands-qom.h" #include "qapi/qmp/qdict.h" #include "qapi/qmp/qerror.h" -#include "qapi/qobject-input-visitor.h" #include "qemu/cutils.h" #include "qom/object_interfaces.h" #include "qom/qom-qobject.h" @@ -XXX,XX +XXX,XX @@ void qmp_object_add(QDict *qdict, QObject **ret_data, Error **errp) { QObject *props; QDict *pdict; - Visitor *v; - Object *obj; - g_autofree char *type = NULL; - g_autofree char *id = NULL; - - type = g_strdup(qdict_get_try_str(qdict, "qom-type")); - if (!type) { - error_setg(errp, QERR_MISSING_PARAMETER, "qom-type"); - return; - } - qdict_del(qdict, "qom-type"); - - id = g_strdup(qdict_get_try_str(qdict, "id")); - if (!id) { - error_setg(errp, QERR_MISSING_PARAMETER, "id"); - return; - } - qdict_del(qdict, "id"); props = qdict_get(qdict, "props"); if (props) { @@ -XXX,XX +XXX,XX @@ void qmp_object_add(QDict *qdict, QObject **ret_data, Error **errp) qobject_unref(pdict); } - v = qobject_input_visitor_new(QOBJECT(qdict)); - obj = user_creatable_add_type(type, id, qdict, v, errp); - visit_free(v); - object_unref(obj); + user_creatable_add_dict(qdict, errp); } void qmp_object_del(const char *id, Error **errp) -- 2.25.3 After processing the option string with the keyval parser, we get a QDict that contains only strings. This QDict must be fed to a keyval visitor which converts the strings into the right data types. qmp_object_add(), however, uses the normal QObject input visitor, which expects a QDict where all properties already have the QType that matches the data type required by the QOM object type. Change the --object implementation in qemu-storage-daemon so that it doesn't call qmp_object_add(), but calls user_creatable_add_dict() directly instead and pass it a new keyval boolean that decides which visitor must be used. Reported-by: Coiby Xu <coiby.xu@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qom/object_interfaces.h | 6 +++++- qemu-storage-daemon.c | 4 +--- qom/object_interfaces.c | 8 ++++++-- qom/qom-qmp-cmds.c | 2 +- 4 files changed, 13 insertions(+), 7 deletions(-) diff --git a/include/qom/object_interfaces.h b/include/qom/object_interfaces.h index XXXXXXX..XXXXXXX 100644 --- a/include/qom/object_interfaces.h +++ b/include/qom/object_interfaces.h @@ -XXX,XX +XXX,XX @@ Object *user_creatable_add_type(const char *type, const char *id, /** * user_creatable_add_dict: * @qdict: the object definition + * @keyval: if true, use a keyval visitor for processing @qdict (i.e. + * assume that all @qdict values are strings); otherwise, use + * the normal QObject visitor (i.e. assume all @qdict values + * have the QType expected by the QOM object type) * @errp: if an error occurs, a pointer to an area to store the error * * Create an instance of the user creatable object that is defined by @@ -XXX,XX +XXX,XX @@ Object *user_creatable_add_type(const char *type, const char *id, * ID from the key 'id'. The remaining entries in @qdict are used to * initialize the object properties. */ -void user_creatable_add_dict(QDict *qdict, Error **errp); +void user_creatable_add_dict(QDict *qdict, bool keyval, Error **errp); /** * user_creatable_add_opts: diff --git a/qemu-storage-daemon.c b/qemu-storage-daemon.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-storage-daemon.c +++ b/qemu-storage-daemon.c @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) QemuOpts *opts; const char *type; QDict *args; - QObject *ret_data = NULL; /* FIXME The keyval parser rejects 'help' arguments, so we must * unconditionall try QemuOpts first. */ @@ -XXX,XX +XXX,XX @@ static void process_options(int argc, char *argv[]) qemu_opts_del(opts); args = keyval_parse(optarg, "qom-type", &error_fatal); - qmp_object_add(args, &ret_data, &error_fatal); + user_creatable_add_dict(args, true, &error_fatal); qobject_unref(args); - qobject_unref(ret_data); break; } default: diff --git a/qom/object_interfaces.c b/qom/object_interfaces.c index XXXXXXX..XXXXXXX 100644 --- a/qom/object_interfaces.c +++ b/qom/object_interfaces.c @@ -XXX,XX +XXX,XX @@ out: return obj; } -void user_creatable_add_dict(QDict *qdict, Error **errp) +void user_creatable_add_dict(QDict *qdict, bool keyval, Error **errp) { Visitor *v; Object *obj; @@ -XXX,XX +XXX,XX @@ void user_creatable_add_dict(QDict *qdict, Error **errp) } qdict_del(qdict, "id"); - v = qobject_input_visitor_new(QOBJECT(qdict)); + if (keyval) { + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + } else { + v = qobject_input_visitor_new(QOBJECT(qdict)); + } obj = user_creatable_add_type(type, id, qdict, v, errp); visit_free(v); object_unref(obj); diff --git a/qom/qom-qmp-cmds.c b/qom/qom-qmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qom/qom-qmp-cmds.c +++ b/qom/qom-qmp-cmds.c @@ -XXX,XX +XXX,XX @@ void qmp_object_add(QDict *qdict, QObject **ret_data, Error **errp) qobject_unref(pdict); } - user_creatable_add_dict(qdict, errp); + user_creatable_add_dict(qdict, false, errp); } void qmp_object_del(const char *id, Error **errp) -- 2.25.3