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 281f327487c9c9b1599f93c589a408bbf4a651b8: Merge remote-tracking branch 'remotes/vivier/tags/m68k-for-2.12-pull-request' into staging (2017-12-22 00:11:36 +0000) are available in the git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to 1a63a907507fbbcfaee3f622907ec244b7eabda8: block: Keep nodes drained between reopen_queue/multiple (2017-12-22 15:05:32 +0100) ---------------------------------------------------------------- Block layer patches ---------------------------------------------------------------- Doug Gale (1): nvme: Add tracing Edgar Kaziakhmedov (1): qcow2: get rid of qcow2_backing_read1 routine Fam Zheng (2): block: Open backing image in force share mode for size probe block: Remove unused bdrv_requests_pending John Snow (1): iotests: fix 197 for vpc Kevin Wolf (27): block: Formats don't need CONSISTENT_READ with NO_IO block: Make bdrv_drain_invoke() recursive block: Call .drain_begin only once in bdrv_drain_all_begin() test-bdrv-drain: Test BlockDriver callbacks for drain block: bdrv_drain_recurse(): Remove unused begin parameter block: Don't wait for requests in bdrv_drain*_end() block: Unify order in drain functions block: Don't acquire AioContext in hmp_qemu_io() block: Document that x-blockdev-change breaks quorum children list block: Assert drain_all is only called from main AioContext block: Make bdrv_drain() driver callbacks non-recursive test-bdrv-drain: Test callback for bdrv_drain test-bdrv-drain: Test bs->quiesce_counter blockjob: Pause job on draining any job BDS test-bdrv-drain: Test drain vs. block jobs block: Don't block_job_pause_all() in bdrv_drain_all() block: Nested drain_end must still call callbacks test-bdrv-drain: Test nested drain sections block: Don't notify parents in drain call chain block: Add bdrv_subtree_drained_begin/end() test-bdrv-drain: Tests for bdrv_subtree_drain test-bdrv-drain: Test behaviour in coroutine context test-bdrv-drain: Recursive draining with multiple parents block: Allow graph changes in subtree drained section test-bdrv-drain: Test graph changes in drained section commit: Simplify reopen of base block: Keep nodes drained between reopen_queue/multiple Thomas Huth (3): block: Remove the obsolete -drive boot=on|off parameter block: Remove the deprecated -hdachs option block: Mention -drive cyls/heads/secs/trans/serial/addr in deprecation chapter qapi/block-core.json | 4 + block/qcow2.h | 3 - include/block/block.h | 15 +- include/block/block_int.h | 6 +- block.c | 75 ++++- block/commit.c | 8 +- block/io.c | 164 +++++++--- block/qcow2.c | 51 +-- block/replication.c | 6 + blockdev.c | 11 - blockjob.c | 22 +- hmp.c | 6 - hw/block/nvme.c | 349 +++++++++++++++++---- qemu-io-cmds.c | 3 + tests/test-bdrv-drain.c | 651 +++++++++++++++++++++++++++++++++++++++ vl.c | 86 +----- hw/block/trace-events | 93 ++++++ qemu-doc.texi | 29 +- qemu-options.hx | 19 +- tests/Makefile.include | 2 + tests/qemu-iotests/197 | 4 + tests/qemu-iotests/common.filter | 3 +- 22 files changed, 1294 insertions(+), 316 deletions(-) create mode 100644 tests/test-bdrv-drain.c Commit 1f4ad7d fixed 'qemu-img info' for raw images that are currently in use as a mirror target. It is not enough for image formats, though, as these still unconditionally request BLK_PERM_CONSISTENT_READ. As this permission is geared towards whether the guest-visible data is consistent, and has no impact on whether the metadata is sane, and 'qemu-img info' does not read guest-visible data (except for the raw format), it makes sense to not require BLK_PERM_CONSISTENT_READ if there is not going to be any guest I/O performed, regardless of image format. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, assert(role == &child_backing || role == &child_file); if (!backing) { + int flags = bdrv_reopen_get_flags(reopen_queue, bs); + /* Apart from the modifications below, the same permissions are * forwarded and left alone as for filters */ bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared, @@ -XXX,XX +XXX,XX @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, /* bs->file always needs to be consistent because of the metadata. We * can never allow other users to resize or write to it. */ - perm |= BLK_PERM_CONSISTENT_READ; + if (!(flags & BDRV_O_NO_IO)) { + perm |= BLK_PERM_CONSISTENT_READ; + } shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE); } else { /* We want consistent read from backing files if the parent needs it. -- 2.13.6 From: John Snow <jsnow@redhat.com> VPC has some difficulty creating geometries of particular size. However, we can indeed force it to use a literal one, so let's do that for the sake of test 197, which is testing some specific offsets. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Lukáš Doktor <ldoktor@redhat.com> --- tests/qemu-iotests/197 | 4 ++++ tests/qemu-iotests/common.filter | 3 ++- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/tests/qemu-iotests/197 b/tests/qemu-iotests/197 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/197 +++ b/tests/qemu-iotests/197 @@ -XXX,XX +XXX,XX @@ echo '=== Copy-on-read ===' echo # Prep the images +# VPC rounds image sizes to a specific geometry, force a specific size. +if [ "$IMGFMT" = "vpc" ]; then + IMGOPTS=$(_optstr_add "$IMGOPTS" "force_size") +fi _make_test_img 4G $QEMU_IO -c "write -P 55 3G 1k" "$TEST_IMG" | _filter_qemu_io IMGPROTO=file IMGFMT=qcow2 IMGOPTS= TEST_IMG_FILE="$TEST_WRAP" \ diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -XXX,XX +XXX,XX @@ _filter_img_create() -e "s# log_size=[0-9]\\+##g" \ -e "s# refcount_bits=[0-9]\\+##g" \ -e "s# key-secret=[a-zA-Z0-9]\\+##g" \ - -e "s# iter-time=[0-9]\\+##g" + -e "s# iter-time=[0-9]\\+##g" \ + -e "s# force_size=\\(on\\|off\\)##g" } _filter_img_info() -- 2.13.6 This change separates bdrv_drain_invoke(), which calls the BlockDriver drain callbacks, from bdrv_drain_recurse(). Instead, the function performs its own recursion now. One reason for this is that bdrv_drain_recurse() can be called multiple times by bdrv_drain_all_begin(), but the callbacks may only be called once. The separation is necessary to fix this bug. The other reason is that we intend to go to a model where we call all driver callbacks first, and only then start polling. This is not fully achieved yet with this patch, as bdrv_drain_invoke() contains a BDRV_POLL_WHILE() loop for the block driver callbacks, which can still call callbacks for any unrelated event. It's a step in this direction anyway. Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_drain_invoke_entry(void *opaque) bdrv_wakeup(bs); } +/* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) { + BdrvChild *child, *tmp; BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin}; if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) || @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) data.co = qemu_coroutine_create(bdrv_drain_invoke_entry, &data); bdrv_coroutine_enter(bs, data.co); BDRV_POLL_WHILE(bs, !data.done); + + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { + bdrv_drain_invoke(child->bs, begin); + } } static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) BdrvChild *child, *tmp; bool waited; - /* Ensure any pending metadata writes are submitted to bs->file. */ - bdrv_drain_invoke(bs, begin); - /* Wait for drained requests to finish */ waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) bdrv_parent_drained_begin(bs); } + bdrv_drain_invoke(bs, true); bdrv_drain_recurse(bs, true); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) } bdrv_parent_drained_end(bs); + bdrv_drain_invoke(bs, false); bdrv_drain_recurse(bs, false); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { + /* FIXME Calling this multiple times is wrong */ + bdrv_drain_invoke(bs, true); waited |= bdrv_drain_recurse(bs, true); } } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_context_acquire(aio_context); aio_enable_external(aio_context); bdrv_parent_drained_end(bs); + bdrv_drain_invoke(bs, false); bdrv_drain_recurse(bs, false); aio_context_release(aio_context); } -- 2.13.6 bdrv_drain_all_begin() used to call the .bdrv_co_drain_begin() driver callback inside its polling loop. This means that how many times it got called for each node depended on long it had to poll the event loop. This is obviously not right and results in nodes that stay drained even after bdrv_drain_all_end(), which calls .bdrv_co_drain_begin() once per node. Fix bdrv_drain_all_begin() to call the callback only once, too. Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); bdrv_parent_drained_begin(bs); aio_disable_external(aio_context); + bdrv_drain_invoke(bs, true); aio_context_release(aio_context); if (!g_slist_find(aio_ctxs, aio_context)) { @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { - /* FIXME Calling this multiple times is wrong */ - bdrv_drain_invoke(bs, true); waited |= bdrv_drain_recurse(bs, true); } } -- 2.13.6 This adds a test case that the BlockDriver callbacks for drain are called in bdrv_drained_all_begin/end(), and that both of them are called exactly once. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- tests/test-bdrv-drain.c | 137 ++++++++++++++++++++++++++++++++++++++++++++++++ tests/Makefile.include | 2 + 2 files changed, 139 insertions(+) create mode 100644 tests/test-bdrv-drain.c diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ +/* + * Block node draining tests + * + * Copyright (c) 2017 Kevin Wolf <kwolf@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "block/block.h" +#include "sysemu/block-backend.h" +#include "qapi/error.h" + +typedef struct BDRVTestState { + int drain_count; +} BDRVTestState; + +static void coroutine_fn bdrv_test_co_drain_begin(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + s->drain_count++; +} + +static void coroutine_fn bdrv_test_co_drain_end(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + s->drain_count--; +} + +static void bdrv_test_close(BlockDriverState *bs) +{ + BDRVTestState *s = bs->opaque; + g_assert_cmpint(s->drain_count, >, 0); +} + +static int coroutine_fn bdrv_test_co_preadv(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, int flags) +{ + /* We want this request to stay until the polling loop in drain waits for + * it to complete. We need to sleep a while as bdrv_drain_invoke() comes + * first and polls its result, too, but it shouldn't accidentally complete + * this request yet. */ + qemu_co_sleep_ns(QEMU_CLOCK_REALTIME, 100000); + + return 0; +} + +static BlockDriver bdrv_test = { + .format_name = "test", + .instance_size = sizeof(BDRVTestState), + + .bdrv_close = bdrv_test_close, + .bdrv_co_preadv = bdrv_test_co_preadv, + + .bdrv_co_drain_begin = bdrv_test_co_drain_begin, + .bdrv_co_drain_end = bdrv_test_co_drain_end, +}; + +static void aio_ret_cb(void *opaque, int ret) +{ + int *aio_ret = opaque; + *aio_ret = ret; +} + +static void test_drv_cb_drain_all(void) +{ + BlockBackend *blk; + BlockDriverState *bs; + BDRVTestState *s; + BlockAIOCB *acb; + int aio_ret; + + QEMUIOVector qiov; + struct iovec iov = { + .iov_base = NULL, + .iov_len = 0, + }; + qemu_iovec_init_external(&qiov, &iov, 1); + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + s = bs->opaque; + blk_insert_bs(blk, bs, &error_abort); + + /* Simple bdrv_drain_all_begin/end pair, check that CBs are called */ + g_assert_cmpint(s->drain_count, ==, 0); + bdrv_drain_all_begin(); + g_assert_cmpint(s->drain_count, ==, 1); + bdrv_drain_all_end(); + g_assert_cmpint(s->drain_count, ==, 0); + + /* Now do the same while a request is pending */ + aio_ret = -EINPROGRESS; + acb = blk_aio_preadv(blk, 0, &qiov, 0, aio_ret_cb, &aio_ret); + g_assert(acb != NULL); + g_assert_cmpint(aio_ret, ==, -EINPROGRESS); + + g_assert_cmpint(s->drain_count, ==, 0); + bdrv_drain_all_begin(); + g_assert_cmpint(aio_ret, ==, 0); + g_assert_cmpint(s->drain_count, ==, 1); + bdrv_drain_all_end(); + g_assert_cmpint(s->drain_count, ==, 0); + + bdrv_unref(bs); + blk_unref(blk); +} + +int main(int argc, char **argv) +{ + bdrv_init(); + qemu_init_main_loop(&error_abort); + + g_test_init(&argc, &argv, NULL); + + g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); + + return g_test_run(); +} diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ gcov-files-test-thread-pool-y = thread-pool.c gcov-files-test-hbitmap-y = util/hbitmap.c check-unit-y += tests/test-hbitmap$(EXESUF) gcov-files-test-hbitmap-y = blockjob.c +check-unit-y += tests/test-bdrv-drain$(EXESUF) check-unit-y += tests/test-blockjob$(EXESUF) check-unit-y += tests/test-blockjob-txn$(EXESUF) check-unit-y += tests/test-x86-cpuid$(EXESUF) @@ -XXX,XX +XXX,XX @@ tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y) tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y) tests/test-aio-multithread$(EXESUF): tests/test-aio-multithread.o $(test-block-obj-y) tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y) +tests/test-bdrv-drain$(EXESUF): tests/test-bdrv-drain.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob$(EXESUF): tests/test-blockjob.o $(test-block-obj-y) $(test-util-obj-y) tests/test-blockjob-txn$(EXESUF): tests/test-blockjob-txn.o $(test-block-obj-y) $(test-util-obj-y) tests/test-thread-pool$(EXESUF): tests/test-thread-pool.o $(test-block-obj-y) -- 2.13.6 Now that the bdrv_drain_invoke() calls are pulled up to the callers of bdrv_drain_recurse(), the 'begin' parameter isn't needed any more. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) } } -static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) +static bool bdrv_drain_recurse(BlockDriverState *bs) { BdrvChild *child, *tmp; bool waited; @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin) */ bdrv_ref(bs); } - waited |= bdrv_drain_recurse(bs, begin); + waited |= bdrv_drain_recurse(bs); if (in_main_loop) { bdrv_unref(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) } bdrv_drain_invoke(bs, true); - bdrv_drain_recurse(bs, true); + bdrv_drain_recurse(bs); } void bdrv_drained_end(BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs, false); + bdrv_drain_recurse(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { if (aio_context == bdrv_get_aio_context(bs)) { - waited |= bdrv_drain_recurse(bs, true); + waited |= bdrv_drain_recurse(bs); } } aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs, false); + bdrv_drain_recurse(bs); aio_context_release(aio_context); } -- 2.13.6 The device is drained, so there is no point in waiting for requests at the end of the drained section. Remove the bdrv_drain_recurse() calls there. The bdrv_drain_recurse() calls were introduced in commit 481cad48e5e in order to call the .bdrv_co_drain_end() driver callback. This is now done by a separate bdrv_drain_invoke() call. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); - bdrv_drain_recurse(bs); aio_context_release(aio_context); } -- 2.13.6 Drain requests are propagated to child nodes, parent nodes and directly to the AioContext. The order in which this happened was different between all combinations of drain/drain_all and begin/end. The correct order is to keep children only drained when their parents are also drained. This means that at the start of a drained section, the AioContext needs to be drained first, the parents second and only then the children. The correct order for the end of a drained section is the opposite. This patch changes the three other functions to follow the example of bdrv_drained_begin(), which is the only one that got it right. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/io.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) return; } + /* Stop things in parent-to-child order */ if (atomic_fetch_inc(&bs->quiesce_counter) == 0) { aio_disable_external(bdrv_get_aio_context(bs)); bdrv_parent_drained_begin(bs); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) return; } - bdrv_parent_drained_end(bs); + /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false); + bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); + /* Stop things in parent-to-child order */ aio_context_acquire(aio_context); - bdrv_parent_drained_begin(bs); aio_disable_external(aio_context); + bdrv_parent_drained_begin(bs); bdrv_drain_invoke(bs, true); aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); + /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); - aio_enable_external(aio_context); - bdrv_parent_drained_end(bs); bdrv_drain_invoke(bs, false); + bdrv_parent_drained_end(bs); + aio_enable_external(aio_context); aio_context_release(aio_context); } -- 2.13.6 Commit 15afd94a047 added code to acquire and release the AioContext in qemuio_command(). This means that the lock is taken twice now in the call path from hmp_qemu_io(). This causes BDRV_POLL_WHILE() to hang for any requests issued to nodes in a non-mainloop AioContext. Dropping the first locking from hmp_qemu_io() fixes the problem. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> --- hmp.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/hmp.c b/hmp.c index XXXXXXX..XXXXXXX 100644 --- a/hmp.c +++ b/hmp.c @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) { BlockBackend *blk; BlockBackend *local_blk = NULL; - AioContext *aio_context; const char* device = qdict_get_str(qdict, "device"); const char* command = qdict_get_str(qdict, "command"); Error *err = NULL; @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) } } - aio_context = blk_get_aio_context(blk); - aio_context_acquire(aio_context); - /* * Notably absent: Proper permission management. This is sad, but it seems * almost impossible to achieve without changing the semantics and thereby @@ -XXX,XX +XXX,XX @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict) */ qemuio_command(blk, command); - aio_context_release(aio_context); - fail: blk_unref(local_blk); hmp_handle_error(mon, &err); -- 2.13.6 From: Edgar Kaziakhmedov <edgar.kaziakhmedov@virtuozzo.com> Since bdrv_co_preadv does all neccessary checks including reading after the end of the backing file, avoid duplication of verification before bdrv_co_preadv call. Signed-off-by: Edgar Kaziakhmedov <edgar.kaziakhmedov@virtuozzo.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.h | 3 --- block/qcow2.c | 51 ++++++++------------------------------------------- 2 files changed, 8 insertions(+), 46 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ uint32_t offset_to_reftable_index(BDRVQcow2State *s, uint64_t offset) } /* qcow2.c functions */ -int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t sector_num, int nb_sectors); - int64_t qcow2_refcount_metadata_size(int64_t clusters, size_t cluster_size, int refcount_order, bool generous_increase, uint64_t *refblock_count); diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs, return status; } -/* handle reading after the end of the backing file */ -int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov, - int64_t offset, int bytes) -{ - uint64_t bs_size = bs->total_sectors * BDRV_SECTOR_SIZE; - int n1; - - if ((offset + bytes) <= bs_size) { - return bytes; - } - - if (offset >= bs_size) { - n1 = 0; - } else { - n1 = bs_size - offset; - } - - qemu_iovec_memset(qiov, n1, 0, bytes - n1); - - return n1; -} - static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) { BDRVQcow2State *s = bs->opaque; - int offset_in_cluster, n1; + int offset_in_cluster; int ret; unsigned int cur_bytes; /* number of bytes in current iteration */ uint64_t cluster_offset = 0; @@ -XXX,XX +XXX,XX @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset, case QCOW2_CLUSTER_UNALLOCATED: if (bs->backing) { - /* read from the base image */ - n1 = qcow2_backing_read1(bs->backing->bs, &hd_qiov, - offset, cur_bytes); - if (n1 > 0) { - QEMUIOVector local_qiov; - - qemu_iovec_init(&local_qiov, hd_qiov.niov); - qemu_iovec_concat(&local_qiov, &hd_qiov, 0, n1); - - BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); - qemu_co_mutex_unlock(&s->lock); - ret = bdrv_co_preadv(bs->backing, offset, n1, - &local_qiov, 0); - qemu_co_mutex_lock(&s->lock); - - qemu_iovec_destroy(&local_qiov); - - if (ret < 0) { - goto fail; - } + BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO); + qemu_co_mutex_unlock(&s->lock); + ret = bdrv_co_preadv(bs->backing, offset, cur_bytes, + &hd_qiov, 0); + qemu_co_mutex_lock(&s->lock); + if (ret < 0) { + goto fail; } } else { /* Note: in this case, no need to wait */ -- 2.13.6 Removing a quorum child node with x-blockdev-change results in a quorum driver state that cannot be recreated with create options because it would require a list with gaps. This causes trouble in at least .bdrv_refresh_filename(). Document this problem so that we won't accidentally mark the command stable without having addressed it. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Alberto Garcia <berto@igalia.com> --- qapi/block-core.json | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/qapi/block-core.json b/qapi/block-core.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -XXX,XX +XXX,XX @@ # does not support all kinds of operations, all kinds of children, nor # all block drivers. # +# FIXME Removing children from a quorum node means introducing gaps in the +# child indices. This cannot be represented in the 'children' list of +# BlockdevOptionsQuorum, as returned by .bdrv_refresh_filename(). +# # Warning: The data in a new quorum child MUST be consistent with that of # the rest of the array. # -- 2.13.6 From: Doug Gale <doug16k@gmail.com> Add trace output for commands, errors, and undefined behavior. Add guest error log output for undefined behavior. Report invalid undefined accesses to MMIO. Annotate unlikely error checks with unlikely. Signed-off-by: Doug Gale <doug16k@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/block/nvme.c | 349 ++++++++++++++++++++++++++++++++++++++++++-------- hw/block/trace-events | 93 ++++++++++++++ 2 files changed, 390 insertions(+), 52 deletions(-) diff --git a/hw/block/nvme.c b/hw/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/nvme.c +++ b/hw/block/nvme.c @@ -XXX,XX +XXX,XX @@ #include "qapi/visitor.h" #include "sysemu/block-backend.h" +#include "qemu/log.h" +#include "trace.h" #include "nvme.h" +#define NVME_GUEST_ERR(trace, fmt, ...) \ + do { \ + (trace_##trace)(__VA_ARGS__); \ + qemu_log_mask(LOG_GUEST_ERROR, #trace \ + " in %s: " fmt "\n", __func__, ## __VA_ARGS__); \ + } while (0) + static void nvme_process_sq(void *opaque); static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size) @@ -XXX,XX +XXX,XX @@ static void nvme_isr_notify(NvmeCtrl *n, NvmeCQueue *cq) { if (cq->irq_enabled) { if (msix_enabled(&(n->parent_obj))) { + trace_nvme_irq_msix(cq->vector); msix_notify(&(n->parent_obj), cq->vector); } else { + trace_nvme_irq_pin(); pci_irq_pulse(&n->parent_obj); } + } else { + trace_nvme_irq_masked(); } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, trans_len = MIN(len, trans_len); int num_prps = (len >> n->page_bits) + 1; - if (!prp1) { + if (unlikely(!prp1)) { + trace_nvme_err_invalid_prp(); return NVME_INVALID_FIELD | NVME_DNR; } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr && prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, } len -= trans_len; if (len) { - if (!prp2) { + if (unlikely(!prp2)) { + trace_nvme_err_invalid_prp2_missing(); goto unmap; } if (len > n->page_size) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, uint64_t prp_ent = le64_to_cpu(prp_list[i]); if (i == n->max_prp_ents - 1 && len > n->page_size) { - if (!prp_ent || prp_ent & (n->page_size - 1)) { + if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + trace_nvme_err_invalid_prplist_ent(prp_ent); goto unmap; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, prp_ent = le64_to_cpu(prp_list[i]); } - if (!prp_ent || prp_ent & (n->page_size - 1)) { + if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) { + trace_nvme_err_invalid_prplist_ent(prp_ent); goto unmap; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, i++; } } else { - if (prp2 & (n->page_size - 1)) { + if (unlikely(prp2 & (n->page_size - 1))) { + trace_nvme_err_invalid_prp2_align(prp2); goto unmap; } if (qsg->nsg) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, QEMUIOVector iov; uint16_t status = NVME_SUCCESS; + trace_nvme_dma_read(prp1, prp2); + if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) { return NVME_INVALID_FIELD | NVME_DNR; } if (qsg.nsg > 0) { - if (dma_buf_read(ptr, len, &qsg)) { + if (unlikely(dma_buf_read(ptr, len, &qsg))) { + trace_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } qemu_sglist_destroy(&qsg); } else { - if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) { + if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) { + trace_nvme_err_invalid_dma(); status = NVME_INVALID_FIELD | NVME_DNR; } qemu_iovec_destroy(&iov); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, uint64_t aio_slba = slba << (data_shift - BDRV_SECTOR_BITS); uint32_t aio_nlb = nlb << (data_shift - BDRV_SECTOR_BITS); - if (slba + nlb > ns->id_ns.nsze) { + if (unlikely(slba + nlb > ns->id_ns.nsze)) { + trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return NVME_LBA_RANGE | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0; enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ; - if ((slba + nlb) > ns->id_ns.nsze) { + trace_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba); + + if (unlikely((slba + nlb) > ns->id_ns.nsze)) { block_acct_invalid(blk_get_stats(n->conf.blk), acct); + trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze); return NVME_LBA_RANGE | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) NvmeNamespace *ns; uint32_t nsid = le32_to_cpu(cmd->nsid); - if (nsid == 0 || nsid > n->num_namespaces) { + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { + trace_nvme_err_invalid_ns(nsid, n->num_namespaces); return NVME_INVALID_NSID | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) case NVME_CMD_READ: return nvme_rw(n, ns, cmd, req); default: + trace_nvme_err_invalid_opc(cmd->opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd) NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); - if (!qid || nvme_check_sqid(n, qid)) { + if (unlikely(!qid || nvme_check_sqid(n, qid))) { + trace_nvme_err_invalid_del_sq(qid); return NVME_INVALID_QID | NVME_DNR; } + trace_nvme_del_sq(qid); + sq = n->sq[qid]; while (!QTAILQ_EMPTY(&sq->out_req_list)) { req = QTAILQ_FIRST(&sq->out_req_list); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd) uint16_t qflags = le16_to_cpu(c->sq_flags); uint64_t prp1 = le64_to_cpu(c->prp1); - if (!cqid || nvme_check_cqid(n, cqid)) { + trace_nvme_create_sq(prp1, sqid, cqid, qsize, qflags); + + if (unlikely(!cqid || nvme_check_cqid(n, cqid))) { + trace_nvme_err_invalid_create_sq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (!sqid || !nvme_check_sqid(n, sqid)) { + if (unlikely(!sqid || !nvme_check_sqid(n, sqid))) { + trace_nvme_err_invalid_create_sq_sqid(sqid); return NVME_INVALID_QID | NVME_DNR; } - if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + trace_nvme_err_invalid_create_sq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (!prp1 || prp1 & (n->page_size - 1)) { + if (unlikely(!prp1 || prp1 & (n->page_size - 1))) { + trace_nvme_err_invalid_create_sq_addr(prp1); return NVME_INVALID_FIELD | NVME_DNR; } - if (!(NVME_SQ_FLAGS_PC(qflags))) { + if (unlikely(!(NVME_SQ_FLAGS_PC(qflags)))) { + trace_nvme_err_invalid_create_sq_qflags(NVME_SQ_FLAGS_PC(qflags)); return NVME_INVALID_FIELD | NVME_DNR; } sq = g_malloc0(sizeof(*sq)); @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd) NvmeCQueue *cq; uint16_t qid = le16_to_cpu(c->qid); - if (!qid || nvme_check_cqid(n, qid)) { + if (unlikely(!qid || nvme_check_cqid(n, qid))) { + trace_nvme_err_invalid_del_cq_cqid(qid); return NVME_INVALID_CQID | NVME_DNR; } cq = n->cq[qid]; - if (!QTAILQ_EMPTY(&cq->sq_list)) { + if (unlikely(!QTAILQ_EMPTY(&cq->sq_list))) { + trace_nvme_err_invalid_del_cq_notempty(qid); return NVME_INVALID_QUEUE_DEL; } + trace_nvme_del_cq(qid); nvme_free_cq(cq, n); return NVME_SUCCESS; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd) uint16_t qflags = le16_to_cpu(c->cq_flags); uint64_t prp1 = le64_to_cpu(c->prp1); - if (!cqid || !nvme_check_cqid(n, cqid)) { + trace_nvme_create_cq(prp1, cqid, vector, qsize, qflags, + NVME_CQ_FLAGS_IEN(qflags) != 0); + + if (unlikely(!cqid || !nvme_check_cqid(n, cqid))) { + trace_nvme_err_invalid_create_cq_cqid(cqid); return NVME_INVALID_CQID | NVME_DNR; } - if (!qsize || qsize > NVME_CAP_MQES(n->bar.cap)) { + if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) { + trace_nvme_err_invalid_create_cq_size(qsize); return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR; } - if (!prp1) { + if (unlikely(!prp1)) { + trace_nvme_err_invalid_create_cq_addr(prp1); return NVME_INVALID_FIELD | NVME_DNR; } - if (vector > n->num_queues) { + if (unlikely(vector > n->num_queues)) { + trace_nvme_err_invalid_create_cq_vector(vector); return NVME_INVALID_IRQ_VECTOR | NVME_DNR; } - if (!(NVME_CQ_FLAGS_PC(qflags))) { + if (unlikely(!(NVME_CQ_FLAGS_PC(qflags)))) { + trace_nvme_err_invalid_create_cq_qflags(NVME_CQ_FLAGS_PC(qflags)); return NVME_INVALID_FIELD | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c) uint64_t prp1 = le64_to_cpu(c->prp1); uint64_t prp2 = le64_to_cpu(c->prp2); + trace_nvme_identify_ctrl(); + return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl), prp1, prp2); } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c) uint64_t prp1 = le64_to_cpu(c->prp1); uint64_t prp2 = le64_to_cpu(c->prp2); - if (nsid == 0 || nsid > n->num_namespaces) { + trace_nvme_identify_ns(nsid); + + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) { + trace_nvme_err_invalid_ns(nsid, n->num_namespaces); return NVME_INVALID_NSID | NVME_DNR; } ns = &n->namespaces[nsid - 1]; + return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns), prp1, prp2); } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c) uint16_t ret; int i, j = 0; + trace_nvme_identify_nslist(min_nsid); + list = g_malloc0(data_len); for (i = 0; i < n->num_namespaces; i++) { if (i < min_nsid) { @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd) case 0x02: return nvme_identify_nslist(n, c); default: + trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns)); return NVME_INVALID_FIELD | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) switch (dw10) { case NVME_VOLATILE_WRITE_CACHE: result = blk_enable_write_cache(n->conf.blk); + trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled"); break; case NVME_NUMBER_OF_QUEUES: result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16)); + trace_nvme_getfeat_numq(result); break; default: + trace_nvme_err_invalid_getfeat(dw10); return NVME_INVALID_FIELD | NVME_DNR; } @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) blk_set_enable_write_cache(n->conf.blk, dw11 & 1); break; case NVME_NUMBER_OF_QUEUES: + trace_nvme_setfeat_numq((dw11 & 0xFFFF) + 1, + ((dw11 >> 16) & 0xFFFF) + 1, + n->num_queues - 1, n->num_queues - 1); req->cqe.result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16)); break; default: + trace_nvme_err_invalid_setfeat(dw10); return NVME_INVALID_FIELD | NVME_DNR; } return NVME_SUCCESS; @@ -XXX,XX +XXX,XX @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) case NVME_ADM_CMD_GET_FEATURES: return nvme_get_feature(n, cmd, req); default: + trace_nvme_err_invalid_admin_opc(cmd->opcode); return NVME_INVALID_OPCODE | NVME_DNR; } } @@ -XXX,XX +XXX,XX @@ static int nvme_start_ctrl(NvmeCtrl *n) uint32_t page_bits = NVME_CC_MPS(n->bar.cc) + 12; uint32_t page_size = 1 << page_bits; - if (n->cq[0] || n->sq[0] || !n->bar.asq || !n->bar.acq || - n->bar.asq & (page_size - 1) || n->bar.acq & (page_size - 1) || - NVME_CC_MPS(n->bar.cc) < NVME_CAP_MPSMIN(n->bar.cap) || - NVME_CC_MPS(n->bar.cc) > NVME_CAP_MPSMAX(n->bar.cap) || - NVME_CC_IOCQES(n->bar.cc) < NVME_CTRL_CQES_MIN(n->id_ctrl.cqes) || - NVME_CC_IOCQES(n->bar.cc) > NVME_CTRL_CQES_MAX(n->id_ctrl.cqes) || - NVME_CC_IOSQES(n->bar.cc) < NVME_CTRL_SQES_MIN(n->id_ctrl.sqes) || - NVME_CC_IOSQES(n->bar.cc) > NVME_CTRL_SQES_MAX(n->id_ctrl.sqes) || - !NVME_AQA_ASQS(n->bar.aqa) || !NVME_AQA_ACQS(n->bar.aqa)) { + if (unlikely(n->cq[0])) { + trace_nvme_err_startfail_cq(); + return -1; + } + if (unlikely(n->sq[0])) { + trace_nvme_err_startfail_sq(); + return -1; + } + if (unlikely(!n->bar.asq)) { + trace_nvme_err_startfail_nbarasq(); + return -1; + } + if (unlikely(!n->bar.acq)) { + trace_nvme_err_startfail_nbaracq(); + return -1; + } + if (unlikely(n->bar.asq & (page_size - 1))) { + trace_nvme_err_startfail_asq_misaligned(n->bar.asq); + return -1; + } + if (unlikely(n->bar.acq & (page_size - 1))) { + trace_nvme_err_startfail_acq_misaligned(n->bar.acq); + return -1; + } + if (unlikely(NVME_CC_MPS(n->bar.cc) < + NVME_CAP_MPSMIN(n->bar.cap))) { + trace_nvme_err_startfail_page_too_small( + NVME_CC_MPS(n->bar.cc), + NVME_CAP_MPSMIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_MPS(n->bar.cc) > + NVME_CAP_MPSMAX(n->bar.cap))) { + trace_nvme_err_startfail_page_too_large( + NVME_CC_MPS(n->bar.cc), + NVME_CAP_MPSMAX(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOCQES(n->bar.cc) < + NVME_CTRL_CQES_MIN(n->id_ctrl.cqes))) { + trace_nvme_err_startfail_cqent_too_small( + NVME_CC_IOCQES(n->bar.cc), + NVME_CTRL_CQES_MIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOCQES(n->bar.cc) > + NVME_CTRL_CQES_MAX(n->id_ctrl.cqes))) { + trace_nvme_err_startfail_cqent_too_large( + NVME_CC_IOCQES(n->bar.cc), + NVME_CTRL_CQES_MAX(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOSQES(n->bar.cc) < + NVME_CTRL_SQES_MIN(n->id_ctrl.sqes))) { + trace_nvme_err_startfail_sqent_too_small( + NVME_CC_IOSQES(n->bar.cc), + NVME_CTRL_SQES_MIN(n->bar.cap)); + return -1; + } + if (unlikely(NVME_CC_IOSQES(n->bar.cc) > + NVME_CTRL_SQES_MAX(n->id_ctrl.sqes))) { + trace_nvme_err_startfail_sqent_too_large( + NVME_CC_IOSQES(n->bar.cc), + NVME_CTRL_SQES_MAX(n->bar.cap)); + return -1; + } + if (unlikely(!NVME_AQA_ASQS(n->bar.aqa))) { + trace_nvme_err_startfail_asqent_sz_zero(); + return -1; + } + if (unlikely(!NVME_AQA_ACQS(n->bar.aqa))) { + trace_nvme_err_startfail_acqent_sz_zero(); return -1; } @@ -XXX,XX +XXX,XX @@ static int nvme_start_ctrl(NvmeCtrl *n) static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, unsigned size) { + if (unlikely(offset & (sizeof(uint32_t) - 1))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_misaligned32, + "MMIO write not 32-bit aligned," + " offset=0x%"PRIx64"", offset); + /* should be ignored, fall through for now */ + } + + if (unlikely(size < sizeof(uint32_t))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_toosmall, + "MMIO write smaller than 32-bits," + " offset=0x%"PRIx64", size=%u", + offset, size); + /* should be ignored, fall through for now */ + } + switch (offset) { - case 0xc: + case 0xc: /* INTMS */ + if (unlikely(msix_enabled(&(n->parent_obj)))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix, + "undefined access to interrupt mask set" + " when MSI-X is enabled"); + /* should be ignored, fall through for now */ + } n->bar.intms |= data & 0xffffffff; n->bar.intmc = n->bar.intms; + trace_nvme_mmio_intm_set(data & 0xffffffff, + n->bar.intmc); break; - case 0x10: + case 0x10: /* INTMC */ + if (unlikely(msix_enabled(&(n->parent_obj)))) { + NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix, + "undefined access to interrupt mask clr" + " when MSI-X is enabled"); + /* should be ignored, fall through for now */ + } n->bar.intms &= ~(data & 0xffffffff); n->bar.intmc = n->bar.intms; + trace_nvme_mmio_intm_clr(data & 0xffffffff, + n->bar.intmc); break; - case 0x14: + case 0x14: /* CC */ + trace_nvme_mmio_cfg(data & 0xffffffff); /* Windows first sends data, then sends enable bit */ if (!NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc) && !NVME_CC_SHN(data) && !NVME_CC_SHN(n->bar.cc)) @@ -XXX,XX +XXX,XX @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data, if (NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc)) { n->bar.cc = data; - if (nvme_start_ctrl(n)) { + if (unlikely(nvme_start_ctrl(n))) { + trace_nvme_err_startfail(); n->bar.csts = NVME_CSTS_FAILED; } else { + trace_nvme_mmio_start_success(); n->bar.csts = NVME_CSTS_READY; } } else if (!NVME_CC_EN(data) && NVME_CC_EN(n->bar.cc)) { + trace_nvme_mmio_stopped(); nvme_clear_ctrl(n); n->bar.csts &= ~NVME_CSTS_READY; } if (NVME_CC_SHN(data) && !(NVME_CC_SHN(n->bar.cc))) { - nvme_clear_ctrl(n); - n->bar.cc = data; - n->bar.csts |= NVME_CSTS_SHST_COMPLETE; + trace_nvme_mmio_shutdown_set(); + nvme_clear_ctrl(n); + n->bar.cc = data; + n->bar.csts |= NVME_CSTS_SHST_COMPLETE; } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(n->bar.cc)) { - n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE; - n->bar.cc = data; + trace_nvme_mmio_shutdown_cleared(); + n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE; + n->bar.cc = data; + } + break; + case 0x1C: /* CSTS */ + if (data & (1 << 4)) { + NVME_GUEST_ERR(nvme_ub_mmiowr_ssreset_w1c_unsupported, + "attempted to W1C CSTS.NSSRO" + " but CAP.NSSRS is zero (not supported)"); + } else if (data != 0) { + NVME_GUEST_ERR(nvme_ub_mmiowr_ro_csts, + "attempted to set a read only bit" + " of controller status"); + } + break; + case 0x20: /* NSSR */ + if (data == 0x4E564D65) { + trace_nvme_ub_mmiowr_ssreset_unsupported(); + } else { + /* The spec says that writes of other values have no effect */ + return; } break; - case 0x24: + case 0x24: /* AQA */ n->bar.aqa = data & 0xffffffff; + trace_nvme_mmio_aqattr(data & 0xffffffff); break; - case 0x28: + case 0x28: /* ASQ */ n->bar.asq = data; + trace_nvme_mmio_asqaddr(data); break; - case 0x2c: + case 0x2c: /* ASQ hi */ n->bar.asq |= data << 32; + trace_nvme_mmio_asqaddr_hi(data, n->bar.asq); break; - case 0x30: + case 0x30: /* ACQ */ + trace_nvme_mmio_acqaddr(data); n->bar.acq = data; break; - case 0x34: + case 0x34: /* ACQ hi */ n->bar.acq |= data << 32; + trace_nvme_mmio_acqaddr_hi(data, n->bar.acq); break; + case 0x38: /* CMBLOC */ + NVME_GUEST_ERR(nvme_ub_mmiowr_cmbloc_reserved, + "invalid write to reserved CMBLOC" + " when CMBSZ is zero, ignored"); + return; + case 0x3C: /* CMBSZ */ + NVME_GUEST_ERR(nvme_ub_mmiowr_cmbsz_readonly, + "invalid write to read only CMBSZ, ignored"); + return; default: + NVME_GUEST_ERR(nvme_ub_mmiowr_invalid, + "invalid MMIO write," + " offset=0x%"PRIx64", data=%"PRIx64"", + offset, data); break; } } @@ -XXX,XX +XXX,XX @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size) uint8_t *ptr = (uint8_t *)&n->bar; uint64_t val = 0; + if (unlikely(addr & (sizeof(uint32_t) - 1))) { + NVME_GUEST_ERR(nvme_ub_mmiord_misaligned32, + "MMIO read not 32-bit aligned," + " offset=0x%"PRIx64"", addr); + /* should RAZ, fall through for now */ + } else if (unlikely(size < sizeof(uint32_t))) { + NVME_GUEST_ERR(nvme_ub_mmiord_toosmall, + "MMIO read smaller than 32-bits," + " offset=0x%"PRIx64"", addr); + /* should RAZ, fall through for now */ + } + if (addr < sizeof(n->bar)) { memcpy(&val, ptr + addr, size); + } else { + NVME_GUEST_ERR(nvme_ub_mmiord_invalid_ofs, + "MMIO read beyond last register," + " offset=0x%"PRIx64", returning 0", addr); } + return val; } @@ -XXX,XX +XXX,XX @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) { uint32_t qid; - if (addr & ((1 << 2) - 1)) { + if (unlikely(addr & ((1 << 2) - 1))) { + NVME_GUEST_ERR(nvme_ub_db_wr_misaligned, + "doorbell write not 32-bit aligned," + " offset=0x%"PRIx64", ignoring", addr); return; } if (((addr - 0x1000) >> 2) & 1) { + /* Completion queue doorbell write */ + uint16_t new_head = val & 0xffff; int start_sqs; NvmeCQueue *cq; qid = (addr - (0x1000 + (1 << 2))) >> 3; - if (nvme_check_cqid(n, qid)) { + if (unlikely(nvme_check_cqid(n, qid))) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cq, + "completion queue doorbell write" + " for nonexistent queue," + " sqid=%"PRIu32", ignoring", qid); return; } cq = n->cq[qid]; - if (new_head >= cq->size) { + if (unlikely(new_head >= cq->size)) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cqhead, + "completion queue doorbell write value" + " beyond queue size, sqid=%"PRIu32"," + " new_head=%"PRIu16", ignoring", + qid, new_head); return; } @@ -XXX,XX +XXX,XX @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val) nvme_isr_notify(n, cq); } } else { + /* Submission queue doorbell write */ + uint16_t new_tail = val & 0xffff; NvmeSQueue *sq; qid = (addr - 0x1000) >> 3; - if (nvme_check_sqid(n, qid)) { + if (unlikely(nvme_check_sqid(n, qid))) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sq, + "submission queue doorbell write" + " for nonexistent queue," + " sqid=%"PRIu32", ignoring", qid); return; } sq = n->sq[qid]; - if (new_tail >= sq->size) { + if (unlikely(new_tail >= sq->size)) { + NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sqtail, + "submission queue doorbell write value" + " beyond queue size, sqid=%"PRIu32"," + " new_tail=%"PRIu16", ignoring", + qid, new_tail); return; } diff --git a/hw/block/trace-events b/hw/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/block/trace-events +++ b/hw/block/trace-events @@ -XXX,XX +XXX,XX @@ virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint6 hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d" hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int trans) "blk %p CHS %u %u %u trans %d" +# hw/block/nvme.c +# nvme traces for successful events +nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u" +nvme_irq_pin(void) "pulsing IRQ pin" +nvme_irq_masked(void) "IRQ is masked" +nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" +nvme_rw(char const *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64"" +nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16"" +nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d" +nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16"" +nvme_del_cq(uint16_t cqid) "deleted completion queue, sqid=%"PRIu16"" +nvme_identify_ctrl(void) "identify controller" +nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16"" +nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16"" +nvme_getfeat_vwcache(char const* result) "get feature volatile write cache, result=%s" +nvme_getfeat_numq(int result) "get feature number of queues, result=%d" +nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d" +nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64"" +nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64"" +nvme_mmio_aqattr(uint64_t data) "wrote MMIO, admin queue attributes=0x%"PRIx64"" +nvme_mmio_asqaddr(uint64_t data) "wrote MMIO, admin submission queue address=0x%"PRIx64"" +nvme_mmio_acqaddr(uint64_t data) "wrote MMIO, admin completion queue address=0x%"PRIx64"" +nvme_mmio_asqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin submission queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +nvme_mmio_acqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin completion queue high half=0x%"PRIx64", new_address=0x%"PRIx64"" +nvme_mmio_start_success(void) "setting controller enable bit succeeded" +nvme_mmio_stopped(void) "cleared controller enable bit" +nvme_mmio_shutdown_set(void) "shutdown bit set" +nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" + +# nvme traces for error conditions +nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" +nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64"" +nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64"" +nvme_err_invalid_prp2_missing(void) "PRP2 is null and more data to be transferred" +nvme_err_invalid_field(void) "invalid field" +nvme_err_invalid_prp(void) "invalid PRP" +nvme_err_invalid_sgl(void) "invalid SGL" +nvme_err_invalid_ns(uint32_t ns, uint32_t limit) "invalid namespace %u not within 1-%u" +nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8"" +nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8"" +nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64"" +nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, sid=%"PRIu16"" +nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission queue, invalid cqid=%"PRIu16"" +nvme_err_invalid_create_sq_sqid(uint16_t sqid) "failed creating submission queue, invalid sqid=%"PRIu16"" +nvme_err_invalid_create_sq_size(uint16_t qsize) "failed creating submission queue, invalid qsize=%"PRIu16"" +nvme_err_invalid_create_sq_addr(uint64_t addr) "failed creating submission queue, addr=0x%"PRIx64"" +nvme_err_invalid_create_sq_qflags(uint16_t qflags) "failed creating submission queue, qflags=%"PRIu16"" +nvme_err_invalid_del_cq_cqid(uint16_t cqid) "failed deleting completion queue, cqid=%"PRIu16"" +nvme_err_invalid_del_cq_notempty(uint16_t cqid) "failed deleting completion queue, it is not empty, cqid=%"PRIu16"" +nvme_err_invalid_create_cq_cqid(uint16_t cqid) "failed creating completion queue, cqid=%"PRIu16"" +nvme_err_invalid_create_cq_size(uint16_t size) "failed creating completion queue, size=%"PRIu16"" +nvme_err_invalid_create_cq_addr(uint64_t addr) "failed creating completion queue, addr=0x%"PRIx64"" +nvme_err_invalid_create_cq_vector(uint16_t vector) "failed creating completion queue, vector=%"PRIu16"" +nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion queue, qflags=%"PRIu16"" +nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16"" +nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32"" +nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32"" +nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues" +nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues" +nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null" +nvme_err_startfail_nbaracq(void) "nvme_start_ctrl failed because the admin completion queue address is null" +nvme_err_startfail_asq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin submission queue address is misaligned: 0x%"PRIx64"" +nvme_err_startfail_acq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin completion queue address is misaligned: 0x%"PRIx64"" +nvme_err_startfail_page_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too small: log2size=%u, min=%u" +nvme_err_startfail_page_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too large: log2size=%u, max=%u" +nvme_err_startfail_cqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too small: log2size=%u, min=%u" +nvme_err_startfail_cqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too large: log2size=%u, max=%u" +nvme_err_startfail_sqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too small: log2size=%u, min=%u" +nvme_err_startfail_sqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too large: log2size=%u, max=%u" +nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the admin submission queue size is zero" +nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero" +nvme_err_startfail(void) "setting controller enable bit failed" + +# Traces for undefined behavior +nvme_ub_mmiowr_misaligned32(uint64_t offset) "MMIO write not 32-bit aligned, offset=0x%"PRIx64"" +nvme_ub_mmiowr_toosmall(uint64_t offset, unsigned size) "MMIO write smaller than 32 bits, offset=0x%"PRIx64", size=%u" +nvme_ub_mmiowr_intmask_with_msix(void) "undefined access to interrupt mask set when MSI-X is enabled" +nvme_ub_mmiowr_ro_csts(void) "attempted to set a read only bit of controller status" +nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CAP.NSSRS is zero (not supported)" +nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)" +nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored" +nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored" +nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64"" +nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64"" +nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64"" +nvme_ub_mmiord_invalid_ofs(uint64_t offset) "MMIO read beyond last register, offset=0x%"PRIx64", returning 0" +nvme_ub_db_wr_misaligned(uint64_t offset) "doorbell write not 32-bit aligned, offset=0x%"PRIx64", ignoring" +nvme_ub_db_wr_invalid_cq(uint32_t qid) "completion queue doorbell write for nonexistent queue, cqid=%"PRIu32", ignoring" +nvme_ub_db_wr_invalid_cqhead(uint32_t qid, uint16_t new_head) "completion queue doorbell write value beyond queue size, cqid=%"PRIu32", new_head=%"PRIu16", ignoring" +nvme_ub_db_wr_invalid_sq(uint32_t qid) "submission queue doorbell write for nonexistent queue, sqid=%"PRIu32", ignoring" +nvme_ub_db_wr_invalid_sqtail(uint32_t qid, uint16_t new_tail) "submission queue doorbell write value beyond queue size, sqid=%"PRIu32", new_head=%"PRIu16", ignoring" + # hw/block/xen_disk.c xen_disk_alloc(char *name) "%s" xen_disk_init(char *name) "%s" -- 2.13.6 From: Fam Zheng <famz@redhat.com> Management tools create overlays of running guests with qemu-img: $ qemu-img create -b /image/in/use.qcow2 -f qcow2 /overlay/image.qcow2 but this doesn't work anymore due to image locking: qemu-img: /overlay/image.qcow2: Failed to get shared "write" lock Is another process using the image? Could not open backing image to determine size. Use the force share option to allow this use case again. Cc: qemu-stable@nongnu.org Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ void bdrv_img_create(const char *filename, const char *fmt, back_flags = flags; back_flags &= ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING); + backing_options = qdict_new(); if (backing_fmt) { - backing_options = qdict_new(); qdict_put_str(backing_options, "driver", backing_fmt); } + qdict_put_bool(backing_options, BDRV_OPT_FORCE_SHARE, true); bs = bdrv_open(full_backing, NULL, backing_options, back_flags, &local_err); -- 2.13.6 From: Thomas Huth <thuth@redhat.com> It's not working anymore since QEMU v1.3.0 - time to remove it now. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 11 ----------- qemu-doc.texi | 6 ------ 2 files changed, 17 deletions(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ QemuOptsList qemu_legacy_drive_opts = { .type = QEMU_OPT_STRING, .help = "chs translation (auto, lba, none)", },{ - .name = "boot", - .type = QEMU_OPT_BOOL, - .help = "(deprecated, ignored)", - },{ .name = "addr", .type = QEMU_OPT_STRING, .help = "pci address (virtio only)", @@ -XXX,XX +XXX,XX @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type) goto fail; } - /* Deprecated option boot=[on|off] */ - if (qemu_opt_get(legacy_opts, "boot") != NULL) { - fprintf(stderr, "qemu-kvm: boot=on|off is deprecated and will be " - "ignored. Future versions will reject this parameter. Please " - "update your scripts.\n"); - } - /* Other deprecated options */ if (!qtest_enabled()) { for (i = 0; i < ARRAY_SIZE(deprecated); i++) { diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ deprecated. @section System emulator command line arguments -@subsection -drive boot=on|off (since 1.3.0) - -The ``boot=on|off'' option to the ``-drive'' argument is -ignored. Applications should use the ``bootindex=N'' parameter -to set an absolute ordering between devices instead. - @subsection -tdf (since 1.3.0) The ``-tdf'' argument is ignored. The behaviour implemented -- 2.13.6 From: Thomas Huth <thuth@redhat.com> It's been marked as deprecated since QEMU v2.10.0, and so far nobody complained that we should keep it, so let's remove this legacy option now to simplify the code quite a bit. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- vl.c | 86 ++------------------------------------------------------- qemu-doc.texi | 8 ------ qemu-options.hx | 19 ++----------- 3 files changed, 4 insertions(+), 109 deletions(-) diff --git a/vl.c b/vl.c index XXXXXXX..XXXXXXX 100644 --- a/vl.c +++ b/vl.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) const char *boot_order = NULL; const char *boot_once = NULL; DisplayState *ds; - int cyls, heads, secs, translation; QemuOpts *opts, *machine_opts; - QemuOpts *hda_opts = NULL, *icount_opts = NULL, *accel_opts = NULL; + QemuOpts *icount_opts = NULL, *accel_opts = NULL; QemuOptsList *olist; int optind; const char *optarg; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) cpu_model = NULL; snapshot = 0; - cyls = heads = secs = 0; - translation = BIOS_ATA_TRANSLATION_AUTO; nb_nics = 0; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) if (optind >= argc) break; if (argv[optind][0] != '-') { - hda_opts = drive_add(IF_DEFAULT, 0, argv[optind++], HD_OPTS); + drive_add(IF_DEFAULT, 0, argv[optind++], HD_OPTS); } else { const QEMUOption *popt; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) cpu_model = optarg; break; case QEMU_OPTION_hda: - { - char buf[256]; - if (cyls == 0) - snprintf(buf, sizeof(buf), "%s", HD_OPTS); - else - snprintf(buf, sizeof(buf), - "%s,cyls=%d,heads=%d,secs=%d%s", - HD_OPTS , cyls, heads, secs, - translation == BIOS_ATA_TRANSLATION_LBA ? - ",trans=lba" : - translation == BIOS_ATA_TRANSLATION_NONE ? - ",trans=none" : ""); - drive_add(IF_DEFAULT, 0, optarg, buf); - break; - } case QEMU_OPTION_hdb: case QEMU_OPTION_hdc: case QEMU_OPTION_hdd: @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) case QEMU_OPTION_snapshot: snapshot = 1; break; - case QEMU_OPTION_hdachs: - { - const char *p; - p = optarg; - cyls = strtol(p, (char **)&p, 0); - if (cyls < 1 || cyls > 16383) - goto chs_fail; - if (*p != ',') - goto chs_fail; - p++; - heads = strtol(p, (char **)&p, 0); - if (heads < 1 || heads > 16) - goto chs_fail; - if (*p != ',') - goto chs_fail; - p++; - secs = strtol(p, (char **)&p, 0); - if (secs < 1 || secs > 63) - goto chs_fail; - if (*p == ',') { - p++; - if (!strcmp(p, "large")) { - translation = BIOS_ATA_TRANSLATION_LARGE; - } else if (!strcmp(p, "rechs")) { - translation = BIOS_ATA_TRANSLATION_RECHS; - } else if (!strcmp(p, "none")) { - translation = BIOS_ATA_TRANSLATION_NONE; - } else if (!strcmp(p, "lba")) { - translation = BIOS_ATA_TRANSLATION_LBA; - } else if (!strcmp(p, "auto")) { - translation = BIOS_ATA_TRANSLATION_AUTO; - } else { - goto chs_fail; - } - } else if (*p != '\0') { - chs_fail: - error_report("invalid physical CHS format"); - exit(1); - } - if (hda_opts != NULL) { - qemu_opt_set_number(hda_opts, "cyls", cyls, - &error_abort); - qemu_opt_set_number(hda_opts, "heads", heads, - &error_abort); - qemu_opt_set_number(hda_opts, "secs", secs, - &error_abort); - if (translation == BIOS_ATA_TRANSLATION_LARGE) { - qemu_opt_set(hda_opts, "trans", "large", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_RECHS) { - qemu_opt_set(hda_opts, "trans", "rechs", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_LBA) { - qemu_opt_set(hda_opts, "trans", "lba", - &error_abort); - } else if (translation == BIOS_ATA_TRANSLATION_NONE) { - qemu_opt_set(hda_opts, "trans", "none", - &error_abort); - } - } - } - error_report("'-hdachs' is deprecated, please use '-device" - " ide-hd,cyls=c,heads=h,secs=s,...' instead"); - break; case QEMU_OPTION_numa: opts = qemu_opts_parse_noisily(qemu_find_opts("numa"), optarg, true); diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ The ``--net dump'' argument is now replaced with the ``-object filter-dump'' argument which works in combination with the modern ``-netdev`` backends instead. -@subsection -hdachs (since 2.10.0) - -The ``-hdachs'' argument is now a synonym for setting -the ``cyls'', ``heads'', ``secs'', and ``trans'' properties -on the ``ide-hd'' device using the ``-device'' argument. -The new syntax allows different settings to be provided -per disk. - @subsection -usbdevice (since 2.10.0) The ``-usbdevice DEV'' argument is now a synonym for setting diff --git a/qemu-options.hx b/qemu-options.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -XXX,XX +XXX,XX @@ of available connectors of a given interface type. @item media=@var{media} This option defines the type of the media: disk or cdrom. @item cyls=@var{c},heads=@var{h},secs=@var{s}[,trans=@var{t}] -These options have the same definition as they have in @option{-hdachs}. -These parameters are deprecated, use the corresponding parameters +Force disk physical geometry and the optional BIOS translation (trans=none or +lba). These parameters are deprecated, use the corresponding parameters of @code{-device} instead. @item snapshot=@var{snapshot} @var{snapshot} is "on" or "off" and controls snapshot mode for the given drive @@ -XXX,XX +XXX,XX @@ the raw disk image you use is not written back. You can however force the write back by pressing @key{C-a s} (@pxref{disk_images}). ETEXI -DEF("hdachs", HAS_ARG, QEMU_OPTION_hdachs, \ - "-hdachs c,h,s[,t]\n" \ - " force hard disk 0 physical geometry and the optional BIOS\n" \ - " translation (t=none or lba) (usually QEMU can guess them)\n", - QEMU_ARCH_ALL) -STEXI -@item -hdachs @var{c},@var{h},@var{s},[,@var{t}] -@findex -hdachs -Force hard disk 0 physical geometry (1 <= @var{c} <= 16383, 1 <= -@var{h} <= 16, 1 <= @var{s} <= 63) and optionally force the BIOS -translation mode (@var{t}=none, lba or auto). Usually QEMU can guess -all those parameters. This option is deprecated, please use -@code{-device ide-hd,cyls=c,heads=h,secs=s,...} instead. -ETEXI - DEF("fsdev", HAS_ARG, QEMU_OPTION_fsdev, "-fsdev fsdriver,id=id[,path=path,][security_model={mapped-xattr|mapped-file|passthrough|none}]\n" " [,writeout=immediate][,readonly][,socket=socket|sock_fd=sock_fd][,fmode=fmode][,dmode=dmode]\n" -- 2.13.6 From: Thomas Huth <thuth@redhat.com> Looks like we forgot to announce the deprecation of these options in the corresponding chapter of the qemu-doc text, so let's do that now. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: John Snow <jsnow@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qemu-doc.texi | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/qemu-doc.texi b/qemu-doc.texi index XXXXXXX..XXXXXXX 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -XXX,XX +XXX,XX @@ longer be directly supported in QEMU. The ``-drive if=scsi'' argument is replaced by the the ``-device BUS-TYPE'' argument combined with ``-drive if=none''. +@subsection -drive cyls=...,heads=...,secs=...,trans=... (since 2.10.0) + +The drive geometry arguments are replaced by the the geometry arguments +that can be specified with the ``-device'' parameter. + +@subsection -drive serial=... (since 2.10.0) + +The drive serial argument is replaced by the the serial argument +that can be specified with the ``-device'' parameter. + +@subsection -drive addr=... (since 2.10.0) + +The drive addr argument is replaced by the the addr argument +that can be specified with the ``-device'' parameter. + @subsection -net dump (since 2.10.0) The ``--net dump'' argument is now replaced with the -- 2.13.6 From: Fam Zheng <famz@redhat.com> Signed-off-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block_int.h | 1 - block/io.c | 18 ------------------ 2 files changed, 19 deletions(-) diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ bool blk_dev_is_tray_open(BlockBackend *blk); bool blk_dev_is_medium_locked(BlockBackend *blk); void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes); -bool bdrv_requests_pending(BlockDriverState *bs); void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out); void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in); diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_disable_copy_on_read(BlockDriverState *bs) assert(old >= 1); } -/* Check if any requests are in-flight (including throttled requests) */ -bool bdrv_requests_pending(BlockDriverState *bs) -{ - BdrvChild *child; - - if (atomic_read(&bs->in_flight)) { - return true; - } - - QLIST_FOREACH(child, &bs->children, next) { - if (bdrv_requests_pending(child->bs)) { - return true; - } - } - - return false; -} - typedef struct { Coroutine *co; BlockDriverState *bs; -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/io.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) BdrvNextIterator it; GSList *aio_ctxs = NULL, *ctx; + /* BDRV_POLL_WHILE() for a node can only be called from its own I/O thread + * or the main loop AioContext. We potentially use BDRV_POLL_WHILE() on + * nodes in several different AioContexts, so make sure we're in the main + * context. */ + assert(qemu_get_current_aio_context() == qemu_get_aio_context()); + block_job_pause_all(); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { -- 2.13.6 bdrv_drained_begin() doesn't increase bs->quiesce_counter recursively and also doesn't notify other parent nodes of children, which both means that the child nodes are not actually drained, and bdrv_drained_begin() is providing useful functionality only on a single node. To keep things consistent, we also shouldn't call the block driver callbacks recursively. A proper recursive drain version that provides an actually working drained section for child nodes will be introduced later. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/io.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_drain_invoke_entry(void *opaque) } /* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */ -static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) +static void bdrv_drain_invoke(BlockDriverState *bs, bool begin, bool recursive) { BdrvChild *child, *tmp; BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin}; @@ -XXX,XX +XXX,XX @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin) bdrv_coroutine_enter(bs, data.co); BDRV_POLL_WHILE(bs, !data.done); - QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { - bdrv_drain_invoke(child->bs, begin); + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) { + bdrv_drain_invoke(child->bs, begin, true); + } } } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) bdrv_parent_drained_begin(bs); } - bdrv_drain_invoke(bs, true); + bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); } @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) } /* Re-enable things in child-to-parent order */ - bdrv_drain_invoke(bs, false); + bdrv_drain_invoke(bs, false, false); bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) aio_context_acquire(aio_context); aio_disable_external(aio_context); bdrv_parent_drained_begin(bs); - bdrv_drain_invoke(bs, true); + bdrv_drain_invoke(bs, true, true); aio_context_release(aio_context); if (!g_slist_find(aio_ctxs, aio_context)) { @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); - bdrv_drain_invoke(bs, false); + bdrv_drain_invoke(bs, false, true); bdrv_parent_drained_end(bs); aio_enable_external(aio_context); aio_context_release(aio_context); -- 2.13.6 The existing test is for bdrv_drain_all_begin/end() only. Generalise the test case so that it can be run for the other variants as well. At the moment this is only bdrv_drain_begin/end(), but in a while, we'll add another one. Also, add a backing file to the test node to test whether the operations work recursively. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 69 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 62 insertions(+), 7 deletions(-) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_test = { .bdrv_co_drain_begin = bdrv_test_co_drain_begin, .bdrv_co_drain_end = bdrv_test_co_drain_end, + + .bdrv_child_perm = bdrv_format_default_perms, }; static void aio_ret_cb(void *opaque, int ret) @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) *aio_ret = ret; } -static void test_drv_cb_drain_all(void) +enum drain_type { + BDRV_DRAIN_ALL, + BDRV_DRAIN, +}; + +static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) +{ + switch (drain_type) { + case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break; + case BDRV_DRAIN: bdrv_drained_begin(bs); break; + default: g_assert_not_reached(); + } +} + +static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs) +{ + switch (drain_type) { + case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break; + case BDRV_DRAIN: bdrv_drained_end(bs); break; + default: g_assert_not_reached(); + } +} + +static void test_drv_cb_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; - BlockDriverState *bs; - BDRVTestState *s; + BlockDriverState *bs, *backing; + BDRVTestState *s, *backing_s; BlockAIOCB *acb; int aio_ret; @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_all(void) s = bs->opaque; blk_insert_bs(blk, bs, &error_abort); + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs, backing, &error_abort); + /* Simple bdrv_drain_all_begin/end pair, check that CBs are called */ g_assert_cmpint(s->drain_count, ==, 0); - bdrv_drain_all_begin(); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 1); - bdrv_drain_all_end(); + g_assert_cmpint(backing_s->drain_count, ==, !!recursive); + + do_drain_end(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); /* Now do the same while a request is pending */ aio_ret = -EINPROGRESS; @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_all(void) g_assert_cmpint(aio_ret, ==, -EINPROGRESS); g_assert_cmpint(s->drain_count, ==, 0); - bdrv_drain_all_begin(); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(drain_type, bs); + g_assert_cmpint(aio_ret, ==, 0); g_assert_cmpint(s->drain_count, ==, 1); - bdrv_drain_all_end(); + g_assert_cmpint(backing_s->drain_count, ==, !!recursive); + + do_drain_end(drain_type, bs); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + bdrv_unref(backing); bdrv_unref(bs); blk_unref(blk); } +static void test_drv_cb_drain_all(void) +{ + test_drv_cb_common(BDRV_DRAIN_ALL, true); +} + +static void test_drv_cb_drain(void) +{ + test_drv_cb_common(BDRV_DRAIN, false); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_init(&argc, &argv, NULL); g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); + g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); return g_test_run(); } -- 2.13.6 This is currently only working correctly for bdrv_drain(), not for bdrv_drain_all(). Leave a comment for the drain_all case, we'll address it later. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain(void) test_drv_cb_common(BDRV_DRAIN, false); } +static void test_quiesce_common(enum drain_type drain_type, bool recursive) +{ + BlockBackend *blk; + BlockDriverState *bs, *backing; + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + blk_insert_bs(blk, bs, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + bdrv_set_backing_hd(bs, backing, &error_abort); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + + do_drain_begin(drain_type, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, !!recursive); + + do_drain_end(drain_type, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs); + blk_unref(blk); +} + +static void test_quiesce_drain_all(void) +{ + // XXX drain_all doesn't quiesce + //test_quiesce_common(BDRV_DRAIN_ALL, true); +} + +static void test_quiesce_drain(void) +{ + test_quiesce_common(BDRV_DRAIN, false); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); + g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); + g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + return g_test_run(); } -- 2.13.6 Block jobs already paused themselves when their main BlockBackend entered a drained section. This is not good enough: We also want to pause a block job and may not submit new requests if, for example, the mirror target node should be drained. This implements .drained_begin/end callbacks in child_job in order to consider all block nodes related to the job, and removes the BlockBackend callbacks which are unnecessary now because the root of the job main BlockBackend is always referenced with a child_job, too. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 22 +++++++++------------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static char *child_job_get_parent_desc(BdrvChild *c) job->id); } -static const BdrvChildRole child_job = { - .get_parent_desc = child_job_get_parent_desc, - .stay_at_node = true, -}; - -static void block_job_drained_begin(void *opaque) +static void child_job_drained_begin(BdrvChild *c) { - BlockJob *job = opaque; + BlockJob *job = c->opaque; block_job_pause(job); } -static void block_job_drained_end(void *opaque) +static void child_job_drained_end(BdrvChild *c) { - BlockJob *job = opaque; + BlockJob *job = c->opaque; block_job_resume(job); } -static const BlockDevOps block_job_dev_ops = { - .drained_begin = block_job_drained_begin, - .drained_end = block_job_drained_end, +static const BdrvChildRole child_job = { + .get_parent_desc = child_job_get_parent_desc, + .drained_begin = child_job_drained_begin, + .drained_end = child_job_drained_end, + .stay_at_node = true, }; void block_job_remove_all_bdrv(BlockJob *job) @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort); bs->job = job; - blk_set_dev_ops(blk, &block_job_dev_ops, job); bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker); QLIST_INSERT_HEAD(&block_jobs, job, job_list); -- 2.13.6 Block jobs must be paused if any of the involved nodes are drained. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 121 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 121 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "block/block.h" +#include "block/blockjob_int.h" #include "sysemu/block-backend.h" #include "qapi/error.h" @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } + +typedef struct TestBlockJob { + BlockJob common; + bool should_complete; +} TestBlockJob; + +static void test_job_completed(BlockJob *job, void *opaque) +{ + block_job_completed(job, 0); +} + +static void coroutine_fn test_job_start(void *opaque) +{ + TestBlockJob *s = opaque; + + while (!s->should_complete) { + block_job_sleep_ns(&s->common, 100000); + } + + block_job_defer_to_main_loop(&s->common, test_job_completed, NULL); +} + +static void test_job_complete(BlockJob *job, Error **errp) +{ + TestBlockJob *s = container_of(job, TestBlockJob, common); + s->should_complete = true; +} + +BlockJobDriver test_job_driver = { + .instance_size = sizeof(TestBlockJob), + .start = test_job_start, + .complete = test_job_complete, +}; + +static void test_blockjob_common(enum drain_type drain_type) +{ + BlockBackend *blk_src, *blk_target; + BlockDriverState *src, *target; + BlockJob *job; + int ret; + + src = bdrv_new_open_driver(&bdrv_test, "source", BDRV_O_RDWR, + &error_abort); + blk_src = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + blk_insert_bs(blk_src, src, &error_abort); + + target = bdrv_new_open_driver(&bdrv_test, "target", BDRV_O_RDWR, + &error_abort); + blk_target = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + blk_insert_bs(blk_target, target, &error_abort); + + job = block_job_create("job0", &test_job_driver, src, 0, BLK_PERM_ALL, 0, + 0, NULL, NULL, &error_abort); + block_job_add_bdrv(job, "target", target, 0, BLK_PERM_ALL, &error_abort); + block_job_start(job); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + do_drain_begin(drain_type, src); + + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target, and involves an + * additional block_job_pause_all() */ + g_assert_cmpint(job->pause_count, ==, 3); + } else { + g_assert_cmpint(job->pause_count, ==, 1); + } + /* XXX We don't wait until the job is actually paused. Is this okay? */ + /* g_assert_true(job->paused); */ + g_assert_false(job->busy); /* The job is paused */ + + do_drain_end(drain_type, src); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + do_drain_begin(drain_type, target); + + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target, and involves an + * additional block_job_pause_all() */ + g_assert_cmpint(job->pause_count, ==, 3); + } else { + g_assert_cmpint(job->pause_count, ==, 1); + } + /* XXX We don't wait until the job is actually paused. Is this okay? */ + /* g_assert_true(job->paused); */ + g_assert_false(job->busy); /* The job is paused */ + + do_drain_end(drain_type, target); + + g_assert_cmpint(job->pause_count, ==, 0); + g_assert_false(job->paused); + g_assert_false(job->busy); /* We're in block_job_sleep_ns() */ + + ret = block_job_complete_sync(job, &error_abort); + g_assert_cmpint(ret, ==, 0); + + blk_unref(blk_src); + blk_unref(blk_target); + bdrv_unref(src); + bdrv_unref(target); +} + +static void test_blockjob_drain_all(void) +{ + test_blockjob_common(BDRV_DRAIN_ALL); +} + +static void test_blockjob_drain(void) +{ + test_blockjob_common(BDRV_DRAIN); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); + g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); + return g_test_run(); } -- 2.13.6 Block jobs are already paused using the BdrvChildRole drain callbacks, so we don't need an additional block_job_pause_all() call. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 4 ---- tests/test-bdrv-drain.c | 10 ++++------ 2 files changed, 4 insertions(+), 10 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) * context. */ assert(qemu_get_current_aio_context() == qemu_get_aio_context()); - block_job_pause_all(); - for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) aio_enable_external(aio_context); aio_context_release(aio_context); } - - block_job_resume_all(); } void bdrv_drain_all(void) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common(enum drain_type drain_type) do_drain_begin(drain_type, src); if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target, and involves an - * additional block_job_pause_all() */ - g_assert_cmpint(job->pause_count, ==, 3); + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->pause_count, ==, 2); } else { g_assert_cmpint(job->pause_count, ==, 1); } @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common(enum drain_type drain_type) do_drain_begin(drain_type, target); if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target, and involves an - * additional block_job_pause_all() */ - g_assert_cmpint(job->pause_count, ==, 3); + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->pause_count, ==, 2); } else { g_assert_cmpint(job->pause_count, ==, 1); } -- 2.13.6 bdrv_do_drained_begin() restricts the call of parent callbacks and aio_disable_external() to the outermost drain section, but the block driver callbacks are always called. bdrv_do_drained_end() must match this behaviour, otherwise nodes stay drained even if begin/end calls were balanced. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs) void bdrv_drained_end(BlockDriverState *bs) { + int old_quiesce_counter; + if (qemu_in_coroutine()) { bdrv_co_yield_to_drain(bs, false); return; } assert(bs->quiesce_counter > 0); - if (atomic_fetch_dec(&bs->quiesce_counter) > 1) { - return; - } + old_quiesce_counter = atomic_fetch_dec(&bs->quiesce_counter); /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false, false); - bdrv_parent_drained_end(bs); - aio_enable_external(bdrv_get_aio_context(bs)); + if (old_quiesce_counter == 1) { + bdrv_parent_drained_end(bs); + aio_enable_external(bdrv_get_aio_context(bs)); + } } /* -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, + DRAIN_TYPE_MAX, }; static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } +static void test_nested(void) +{ + BlockBackend *blk; + BlockDriverState *bs, *backing; + BDRVTestState *s, *backing_s; + enum drain_type outer, inner; + + blk = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs = bdrv_new_open_driver(&bdrv_test, "test-node", BDRV_O_RDWR, + &error_abort); + s = bs->opaque; + blk_insert_bs(blk, bs, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs, backing, &error_abort); + + for (outer = 0; outer < DRAIN_TYPE_MAX; outer++) { + for (inner = 0; inner < DRAIN_TYPE_MAX; inner++) { + /* XXX bdrv_drain_all() doesn't increase the quiesce_counter */ + int bs_quiesce = (outer != BDRV_DRAIN_ALL) + + (inner != BDRV_DRAIN_ALL); + int backing_quiesce = 0; + int backing_cb_cnt = (outer != BDRV_DRAIN) + + (inner != BDRV_DRAIN); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(outer, bs); + do_drain_begin(inner, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, bs_quiesce); + g_assert_cmpint(backing->quiesce_counter, ==, backing_quiesce); + g_assert_cmpint(s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, backing_cb_cnt); + + do_drain_end(inner, bs); + do_drain_end(outer, bs); + + g_assert_cmpint(bs->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + } + } + + bdrv_unref(backing); + bdrv_unref(bs); + blk_unref(blk); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/nested", test_nested); + g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 This is in preparation for subtree drains, i.e. drained sections that affect not only a single node, but recursively all child nodes, too. Calling the parent callbacks for drain is pointless when we just came from that parent node recursively and leads to multiple increases of bs->quiesce_counter in a single drain call. Don't do it. In order for this to work correctly, the parent callback must be called for every bdrv_drain_begin/end() call, not only for the outermost one: If we have a node N with two parents A and B, recursive draining of A should cause the quiesce_counter of B to increase because its child N is drained independently of B. If now B is recursively drained, too, A must increase its quiesce_counter because N is drained independently of A only now, even if N is going from quiesce_counter 1 to 2. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 4 ++-- block.c | 13 +++++++++---- block/io.c | 47 ++++++++++++++++++++++++++++++++++------------- 3 files changed, 45 insertions(+), 19 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_io_unplug(BlockDriverState *bs); * Begin a quiesced section of all users of @bs. This is part of * bdrv_drained_begin. */ -void bdrv_parent_drained_begin(BlockDriverState *bs); +void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore); /** * bdrv_parent_drained_end: @@ -XXX,XX +XXX,XX @@ void bdrv_parent_drained_begin(BlockDriverState *bs); * End a quiesced section of all users of @bs. This is part of * bdrv_drained_end. */ -void bdrv_parent_drained_end(BlockDriverState *bs); +void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore); /** * bdrv_drained_begin: diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, BlockDriverState *new_bs) { BlockDriverState *old_bs = child->bs; + int i; if (old_bs && new_bs) { assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)); } if (old_bs) { if (old_bs->quiesce_counter && child->role->drained_end) { - child->role->drained_end(child); + for (i = 0; i < old_bs->quiesce_counter; i++) { + child->role->drained_end(child); + } } if (child->role->detach) { child->role->detach(child); @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, if (new_bs) { QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent); if (new_bs->quiesce_counter && child->role->drained_begin) { - child->role->drained_begin(child); + for (i = 0; i < new_bs->quiesce_counter; i++) { + child->role->drained_begin(child); + } } if (child->role->attach) { @@ -XXX,XX +XXX,XX @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context) AioContext *ctx = bdrv_get_aio_context(bs); aio_disable_external(ctx); - bdrv_parent_drained_begin(bs); + bdrv_parent_drained_begin(bs, NULL); bdrv_drain(bs); /* ensure there are no in-flight requests */ while (aio_poll(ctx, false)) { @@ -XXX,XX +XXX,XX @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context) */ aio_context_acquire(new_context); bdrv_attach_aio_context(bs, new_context); - bdrv_parent_drained_end(bs); + bdrv_parent_drained_end(bs, NULL); aio_enable_external(ctx); aio_context_release(new_context); } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags); -void bdrv_parent_drained_begin(BlockDriverState *bs) +void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c, *next; QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { + if (c == ignore) { + continue; + } if (c->role->drained_begin) { c->role->drained_begin(c); } } } -void bdrv_parent_drained_end(BlockDriverState *bs) +void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c, *next; QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { + if (c == ignore) { + continue; + } if (c->role->drained_end) { c->role->drained_end(c); } @@ -XXX,XX +XXX,XX @@ typedef struct { BlockDriverState *bs; bool done; bool begin; + BdrvChild *parent; } BdrvCoDrainData; static void coroutine_fn bdrv_drain_invoke_entry(void *opaque) @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs) return waited; } +static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent); +static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent); + static void bdrv_co_drain_bh_cb(void *opaque) { BdrvCoDrainData *data = opaque; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); if (data->begin) { - bdrv_drained_begin(bs); + bdrv_do_drained_begin(bs, data->parent); } else { - bdrv_drained_end(bs); + bdrv_do_drained_end(bs, data->parent); } data->done = true; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, - bool begin) + bool begin, BdrvChild *parent) { BdrvCoDrainData data; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, .bs = bs, .done = false, .begin = begin, + .parent = parent, }; bdrv_inc_in_flight(bs); aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -void bdrv_drained_begin(BlockDriverState *bs) +static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) { if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, true); + bdrv_co_yield_to_drain(bs, true, parent); return; } /* Stop things in parent-to-child order */ if (atomic_fetch_inc(&bs->quiesce_counter) == 0) { aio_disable_external(bdrv_get_aio_context(bs)); - bdrv_parent_drained_begin(bs); } + bdrv_parent_drained_begin(bs, parent); bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); } -void bdrv_drained_end(BlockDriverState *bs) +void bdrv_drained_begin(BlockDriverState *bs) +{ + bdrv_do_drained_begin(bs, NULL); +} + +static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) { int old_quiesce_counter; if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, false); + bdrv_co_yield_to_drain(bs, false, parent); return; } assert(bs->quiesce_counter > 0); @@ -XXX,XX +XXX,XX @@ void bdrv_drained_end(BlockDriverState *bs) /* Re-enable things in child-to-parent order */ bdrv_drain_invoke(bs, false, false); + bdrv_parent_drained_end(bs, parent); if (old_quiesce_counter == 1) { - bdrv_parent_drained_end(bs); aio_enable_external(bdrv_get_aio_context(bs)); } } +void bdrv_drained_end(BlockDriverState *bs) +{ + bdrv_do_drained_end(bs, NULL); +} + /* * Wait for pending requests to complete on a single BlockDriverState subtree, * and suspend block driver's internal I/O until next request arrives. @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_begin(void) /* Stop things in parent-to-child order */ aio_context_acquire(aio_context); aio_disable_external(aio_context); - bdrv_parent_drained_begin(bs); + bdrv_parent_drained_begin(bs, NULL); bdrv_drain_invoke(bs, true, true); aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void bdrv_drain_all_end(void) /* Re-enable things in child-to-parent order */ aio_context_acquire(aio_context); bdrv_drain_invoke(bs, false, true); - bdrv_parent_drained_end(bs); + bdrv_parent_drained_end(bs, NULL); aio_enable_external(aio_context); aio_context_release(aio_context); } -- 2.13.6 bdrv_drained_begin() waits for the completion of requests in the whole subtree, but it only actually keeps its immediate bs parameter quiesced until bdrv_drained_end(). Add a version that keeps the whole subtree drained. As of this commit, graph changes cannot be allowed during a subtree drained section, but this will be fixed soon. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 13 +++++++++++++ block/io.c | 54 ++++++++++++++++++++++++++++++++++++++++----------- 2 files changed, 56 insertions(+), 11 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore); void bdrv_drained_begin(BlockDriverState *bs); /** + * Like bdrv_drained_begin, but recursively begins a quiesced section for + * exclusive access to all child nodes as well. + * + * Graph changes are not allowed during a subtree drain section. + */ +void bdrv_subtree_drained_begin(BlockDriverState *bs); + +/** * bdrv_drained_end: * * End a quiescent section started by bdrv_drained_begin(). */ void bdrv_drained_end(BlockDriverState *bs); +/** + * End a quiescent section started by bdrv_subtree_drained_begin(). + */ +void bdrv_subtree_drained_end(BlockDriverState *bs); + void bdrv_add_child(BlockDriverState *parent, BlockDriverState *child, Error **errp); void bdrv_del_child(BlockDriverState *parent, BdrvChild *child, Error **errp); diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ typedef struct { BlockDriverState *bs; bool done; bool begin; + bool recursive; BdrvChild *parent; } BdrvCoDrainData; @@ -XXX,XX +XXX,XX @@ static bool bdrv_drain_recurse(BlockDriverState *bs) return waited; } -static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent); -static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent); +static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent); +static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent); static void bdrv_co_drain_bh_cb(void *opaque) { @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) bdrv_dec_in_flight(bs); if (data->begin) { - bdrv_do_drained_begin(bs, data->parent); + bdrv_do_drained_begin(bs, data->recursive, data->parent); } else { - bdrv_do_drained_end(bs, data->parent); + bdrv_do_drained_end(bs, data->recursive, data->parent); } data->done = true; @@ -XXX,XX +XXX,XX @@ static void bdrv_co_drain_bh_cb(void *opaque) } static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, - bool begin, BdrvChild *parent) + bool begin, bool recursive, + BdrvChild *parent) { BdrvCoDrainData data; @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, .bs = bs, .done = false, .begin = begin, + .recursive = recursive, .parent = parent, }; bdrv_inc_in_flight(bs); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) +static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { + BdrvChild *child, *next; + if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, true, parent); + bdrv_co_yield_to_drain(bs, true, recursive, parent); return; } @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent) bdrv_parent_drained_begin(bs, parent); bdrv_drain_invoke(bs, true, false); bdrv_drain_recurse(bs); + + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, next) { + bdrv_do_drained_begin(child->bs, true, child); + } + } } void bdrv_drained_begin(BlockDriverState *bs) { - bdrv_do_drained_begin(bs, NULL); + bdrv_do_drained_begin(bs, false, NULL); +} + +void bdrv_subtree_drained_begin(BlockDriverState *bs) +{ + bdrv_do_drained_begin(bs, true, NULL); } -static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) +static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { + BdrvChild *child, *next; int old_quiesce_counter; if (qemu_in_coroutine()) { - bdrv_co_yield_to_drain(bs, false, parent); + bdrv_co_yield_to_drain(bs, false, recursive, parent); return; } assert(bs->quiesce_counter > 0); @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) if (old_quiesce_counter == 1) { aio_enable_external(bdrv_get_aio_context(bs)); } + + if (recursive) { + QLIST_FOREACH_SAFE(child, &bs->children, next, next) { + bdrv_do_drained_end(child->bs, true, child); + } + } } void bdrv_drained_end(BlockDriverState *bs) { - bdrv_do_drained_end(bs, NULL); + bdrv_do_drained_end(bs, false, NULL); +} + +void bdrv_subtree_drained_end(BlockDriverState *bs) +{ + bdrv_do_drained_end(bs, true, NULL); } /* -- 2.13.6 Add a subtree drain version to the existing test cases. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, + BDRV_SUBTREE_DRAIN, DRAIN_TYPE_MAX, }; @@ -XXX,XX +XXX,XX @@ static void do_drain_begin(enum drain_type drain_type, BlockDriverState *bs) switch (drain_type) { case BDRV_DRAIN_ALL: bdrv_drain_all_begin(); break; case BDRV_DRAIN: bdrv_drained_begin(bs); break; + case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_begin(bs); break; default: g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void do_drain_end(enum drain_type drain_type, BlockDriverState *bs) switch (drain_type) { case BDRV_DRAIN_ALL: bdrv_drain_all_end(); break; case BDRV_DRAIN: bdrv_drained_end(bs); break; + case BDRV_SUBTREE_DRAIN: bdrv_subtree_drained_end(bs); break; default: g_assert_not_reached(); } } @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain(void) test_drv_cb_common(BDRV_DRAIN, false); } +static void test_drv_cb_drain_subtree(void) +{ + test_drv_cb_common(BDRV_SUBTREE_DRAIN, true); +} + static void test_quiesce_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain(void) test_quiesce_common(BDRV_DRAIN, false); } +static void test_quiesce_drain_subtree(void) +{ + test_quiesce_common(BDRV_SUBTREE_DRAIN, true); +} + static void test_nested(void) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_nested(void) /* XXX bdrv_drain_all() doesn't increase the quiesce_counter */ int bs_quiesce = (outer != BDRV_DRAIN_ALL) + (inner != BDRV_DRAIN_ALL); - int backing_quiesce = 0; + int backing_quiesce = (outer == BDRV_SUBTREE_DRAIN) + + (inner == BDRV_SUBTREE_DRAIN); int backing_cb_cnt = (outer != BDRV_DRAIN) + (inner != BDRV_DRAIN); @@ -XXX,XX +XXX,XX @@ static void test_blockjob_drain(void) test_blockjob_common(BDRV_DRAIN); } +static void test_blockjob_drain_subtree(void) +{ + test_blockjob_common(BDRV_SUBTREE_DRAIN); +} + int main(int argc, char **argv) { bdrv_init(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_all", test_drv_cb_drain_all); g_test_add_func("/bdrv-drain/driver-cb/drain", test_drv_cb_drain); + g_test_add_func("/bdrv-drain/driver-cb/drain_subtree", + test_drv_cb_drain_subtree); g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); + g_test_add_func("/bdrv-drain/quiesce/drain_subtree", + test_quiesce_drain_subtree); g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); + g_test_add_func("/bdrv-drain/blockjob/drain_subtree", + test_blockjob_drain_subtree); return g_test_run(); } -- 2.13.6 If bdrv_do_drained_begin/end() are called in coroutine context, they first use a BH to get out of the coroutine context. Call some existing tests again from a coroutine to cover this code path. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void aio_ret_cb(void *opaque, int ret) *aio_ret = ret; } +typedef struct CallInCoroutineData { + void (*entry)(void); + bool done; +} CallInCoroutineData; + +static coroutine_fn void call_in_coroutine_entry(void *opaque) +{ + CallInCoroutineData *data = opaque; + + data->entry(); + data->done = true; +} + +static void call_in_coroutine(void (*entry)(void)) +{ + Coroutine *co; + CallInCoroutineData data = { + .entry = entry, + .done = false, + }; + + co = qemu_coroutine_create(call_in_coroutine_entry, &data); + qemu_coroutine_enter(co); + while (!data.done) { + aio_poll(qemu_get_aio_context(), true); + } +} + enum drain_type { BDRV_DRAIN_ALL, BDRV_DRAIN, @@ -XXX,XX +XXX,XX @@ static void test_drv_cb_drain_subtree(void) test_drv_cb_common(BDRV_SUBTREE_DRAIN, true); } +static void test_drv_cb_co_drain(void) +{ + call_in_coroutine(test_drv_cb_drain); +} + +static void test_drv_cb_co_drain_subtree(void) +{ + call_in_coroutine(test_drv_cb_drain_subtree); +} + static void test_quiesce_common(enum drain_type drain_type, bool recursive) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ static void test_quiesce_drain_subtree(void) test_quiesce_common(BDRV_SUBTREE_DRAIN, true); } +static void test_quiesce_co_drain(void) +{ + call_in_coroutine(test_quiesce_drain); +} + +static void test_quiesce_co_drain_subtree(void) +{ + call_in_coroutine(test_quiesce_drain_subtree); +} + static void test_nested(void) { BlockBackend *blk; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/driver-cb/drain_subtree", test_drv_cb_drain_subtree); + // XXX bdrv_drain_all() doesn't work in coroutine context + g_test_add_func("/bdrv-drain/driver-cb/co/drain", test_drv_cb_co_drain); + g_test_add_func("/bdrv-drain/driver-cb/co/drain_subtree", + test_drv_cb_co_drain_subtree); + + g_test_add_func("/bdrv-drain/quiesce/drain_all", test_quiesce_drain_all); g_test_add_func("/bdrv-drain/quiesce/drain", test_quiesce_drain); g_test_add_func("/bdrv-drain/quiesce/drain_subtree", test_quiesce_drain_subtree); + // XXX bdrv_drain_all() doesn't work in coroutine context + g_test_add_func("/bdrv-drain/quiesce/co/drain", test_quiesce_co_drain); + g_test_add_func("/bdrv-drain/quiesce/co/drain_subtree", + test_quiesce_co_drain_subtree); + g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); -- 2.13.6 Test that drain sections are correctly propagated through the graph. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_nested(void) blk_unref(blk); } +static void test_multiparent(void) +{ + BlockBackend *blk_a, *blk_b; + BlockDriverState *bs_a, *bs_b, *backing; + BDRVTestState *a_s, *b_s, *backing_s; + + blk_a = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR, + &error_abort); + a_s = bs_a->opaque; + blk_insert_bs(blk_a, bs_a, &error_abort); + + blk_b = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR, + &error_abort); + b_s = bs_b->opaque; + blk_insert_bs(blk_b, bs_b, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs_a, backing, &error_abort); + bdrv_set_backing_hd(bs_b, backing, &error_abort); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 1); + g_assert_cmpint(bs_b->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, 1); + g_assert_cmpint(a_s->drain_count, ==, 1); + g_assert_cmpint(b_s->drain_count, ==, 1); + g_assert_cmpint(backing_s->drain_count, ==, 1); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 2); + g_assert_cmpint(bs_b->quiesce_counter, ==, 2); + g_assert_cmpint(backing->quiesce_counter, ==, 2); + g_assert_cmpint(a_s->drain_count, ==, 2); + g_assert_cmpint(b_s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, 2); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 1); + g_assert_cmpint(bs_b->quiesce_counter, ==, 1); + g_assert_cmpint(backing->quiesce_counter, ==, 1); + g_assert_cmpint(a_s->drain_count, ==, 1); + g_assert_cmpint(b_s->drain_count, ==, 1); + g_assert_cmpint(backing_s->drain_count, ==, 1); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs_a); + bdrv_unref(bs_b); + blk_unref(blk_a); + blk_unref(blk_b); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) test_quiesce_co_drain_subtree); g_test_add_func("/bdrv-drain/nested", test_nested); + g_test_add_func("/bdrv-drain/multiparent", test_multiparent); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 We need to remember how many of the drain sections in which a node is were recursive (i.e. subtree drain rather than node drain), so that they can be correctly applied when children are added or removed during the drained section. With this change, it is safe to modify the graph even inside a bdrv_subtree_drained_begin/end() section. Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/block.h | 2 -- include/block/block_int.h | 5 +++++ block.c | 32 +++++++++++++++++++++++++++++--- block/io.c | 28 ++++++++++++++++++++++++---- 4 files changed, 58 insertions(+), 9 deletions(-) diff --git a/include/block/block.h b/include/block/block.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -XXX,XX +XXX,XX @@ void bdrv_drained_begin(BlockDriverState *bs); /** * Like bdrv_drained_begin, but recursively begins a quiesced section for * exclusive access to all child nodes as well. - * - * Graph changes are not allowed during a subtree drain section. */ void bdrv_subtree_drained_begin(BlockDriverState *bs); diff --git a/include/block/block_int.h b/include/block/block_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -XXX,XX +XXX,XX @@ struct BlockDriverState { /* Accessed with atomic ops. */ int quiesce_counter; + int recursive_quiesce_counter; + unsigned int write_gen; /* Current data generation */ /* Protected by reqs_lock. */ @@ -XXX,XX +XXX,XX @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child, int64_t offset, unsigned int bytes, QEMUIOVector *qiov, BdrvRequestFlags flags); +void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent); +void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent); + int get_tmp_filename(char *filename, int size); BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size, const char *filename); diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_child_cb_drained_end(BdrvChild *child) bdrv_drained_end(bs); } +static void bdrv_child_cb_attach(BdrvChild *child) +{ + BlockDriverState *bs = child->opaque; + bdrv_apply_subtree_drain(child, bs); +} + +static void bdrv_child_cb_detach(BdrvChild *child) +{ + BlockDriverState *bs = child->opaque; + bdrv_unapply_subtree_drain(child, bs); +} + static int bdrv_child_cb_inactivate(BdrvChild *child) { BlockDriverState *bs = child->opaque; @@ -XXX,XX +XXX,XX @@ const BdrvChildRole child_file = { .inherit_options = bdrv_inherited_options, .drained_begin = bdrv_child_cb_drained_begin, .drained_end = bdrv_child_cb_drained_end, + .attach = bdrv_child_cb_attach, + .detach = bdrv_child_cb_detach, .inactivate = bdrv_child_cb_inactivate, }; @@ -XXX,XX +XXX,XX @@ const BdrvChildRole child_format = { .inherit_options = bdrv_inherited_fmt_options, .drained_begin = bdrv_child_cb_drained_begin, .drained_end = bdrv_child_cb_drained_end, + .attach = bdrv_child_cb_attach, + .detach = bdrv_child_cb_detach, .inactivate = bdrv_child_cb_inactivate, }; @@ -XXX,XX +XXX,XX @@ static void bdrv_backing_attach(BdrvChild *c) parent->backing_blocker); bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET, parent->backing_blocker); + + bdrv_child_cb_attach(c); } static void bdrv_backing_detach(BdrvChild *c) @@ -XXX,XX +XXX,XX @@ static void bdrv_backing_detach(BdrvChild *c) bdrv_op_unblock_all(c->bs, parent->backing_blocker); error_free(parent->backing_blocker); parent->backing_blocker = NULL; + + bdrv_child_cb_detach(c); } /* @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs)); } if (old_bs) { + /* Detach first so that the recursive drain sections coming from @child + * are already gone and we only end the drain sections that came from + * elsewhere. */ + if (child->role->detach) { + child->role->detach(child); + } if (old_bs->quiesce_counter && child->role->drained_end) { for (i = 0; i < old_bs->quiesce_counter; i++) { child->role->drained_end(child); } } - if (child->role->detach) { - child->role->detach(child); - } QLIST_REMOVE(child, next_parent); } @@ -XXX,XX +XXX,XX @@ static void bdrv_replace_child_noperm(BdrvChild *child, } } + /* Attach only after starting new drained sections, so that recursive + * drain sections coming from @child don't get an extra .drained_begin + * callback. */ if (child->role->attach) { child->role->attach(child); } diff --git a/block/io.c b/block/io.c index XXXXXXX..XXXXXXX 100644 --- a/block/io.c +++ b/block/io.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs, assert(data.done); } -static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, - BdrvChild *parent) +void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { BdrvChild *child, *next; @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive, bdrv_drain_recurse(bs); if (recursive) { + bs->recursive_quiesce_counter++; QLIST_FOREACH_SAFE(child, &bs->children, next, next) { bdrv_do_drained_begin(child->bs, true, child); } @@ -XXX,XX +XXX,XX @@ void bdrv_subtree_drained_begin(BlockDriverState *bs) bdrv_do_drained_begin(bs, true, NULL); } -static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, - BdrvChild *parent) +void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, + BdrvChild *parent) { BdrvChild *child, *next; int old_quiesce_counter; @@ -XXX,XX +XXX,XX @@ static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive, } if (recursive) { + bs->recursive_quiesce_counter--; QLIST_FOREACH_SAFE(child, &bs->children, next, next) { bdrv_do_drained_end(child->bs, true, child); } @@ -XXX,XX +XXX,XX @@ void bdrv_subtree_drained_end(BlockDriverState *bs) bdrv_do_drained_end(bs, true, NULL); } +void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent) +{ + int i; + + for (i = 0; i < new_parent->recursive_quiesce_counter; i++) { + bdrv_do_drained_begin(child->bs, true, child); + } +} + +void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent) +{ + int i; + + for (i = 0; i < old_parent->recursive_quiesce_counter; i++) { + bdrv_do_drained_end(child->bs, true, child); + } +} + /* * Wait for pending requests to complete on a single BlockDriverState subtree, * and suspend block driver's internal I/O until next request arrives. -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-bdrv-drain.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/tests/test-bdrv-drain.c b/tests/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-bdrv-drain.c +++ b/tests/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_multiparent(void) blk_unref(blk_b); } +static void test_graph_change(void) +{ + BlockBackend *blk_a, *blk_b; + BlockDriverState *bs_a, *bs_b, *backing; + BDRVTestState *a_s, *b_s, *backing_s; + + blk_a = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_a = bdrv_new_open_driver(&bdrv_test, "test-node-a", BDRV_O_RDWR, + &error_abort); + a_s = bs_a->opaque; + blk_insert_bs(blk_a, bs_a, &error_abort); + + blk_b = blk_new(BLK_PERM_ALL, BLK_PERM_ALL); + bs_b = bdrv_new_open_driver(&bdrv_test, "test-node-b", BDRV_O_RDWR, + &error_abort); + b_s = bs_b->opaque; + blk_insert_bs(blk_b, bs_b, &error_abort); + + backing = bdrv_new_open_driver(&bdrv_test, "backing", 0, &error_abort); + backing_s = backing->opaque; + bdrv_set_backing_hd(bs_a, backing, &error_abort); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_begin(BDRV_SUBTREE_DRAIN, bs_b); + + bdrv_set_backing_hd(bs_b, backing, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 5); + g_assert_cmpint(bs_b->quiesce_counter, ==, 5); + g_assert_cmpint(backing->quiesce_counter, ==, 5); + g_assert_cmpint(a_s->drain_count, ==, 5); + g_assert_cmpint(b_s->drain_count, ==, 5); + g_assert_cmpint(backing_s->drain_count, ==, 5); + + bdrv_set_backing_hd(bs_b, NULL, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 3); + g_assert_cmpint(bs_b->quiesce_counter, ==, 2); + g_assert_cmpint(backing->quiesce_counter, ==, 3); + g_assert_cmpint(a_s->drain_count, ==, 3); + g_assert_cmpint(b_s->drain_count, ==, 2); + g_assert_cmpint(backing_s->drain_count, ==, 3); + + bdrv_set_backing_hd(bs_b, backing, &error_abort); + g_assert_cmpint(bs_a->quiesce_counter, ==, 5); + g_assert_cmpint(bs_b->quiesce_counter, ==, 5); + g_assert_cmpint(backing->quiesce_counter, ==, 5); + g_assert_cmpint(a_s->drain_count, ==, 5); + g_assert_cmpint(b_s->drain_count, ==, 5); + g_assert_cmpint(backing_s->drain_count, ==, 5); + + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_b); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + do_drain_end(BDRV_SUBTREE_DRAIN, bs_a); + + g_assert_cmpint(bs_a->quiesce_counter, ==, 0); + g_assert_cmpint(bs_b->quiesce_counter, ==, 0); + g_assert_cmpint(backing->quiesce_counter, ==, 0); + g_assert_cmpint(a_s->drain_count, ==, 0); + g_assert_cmpint(b_s->drain_count, ==, 0); + g_assert_cmpint(backing_s->drain_count, ==, 0); + + bdrv_unref(backing); + bdrv_unref(bs_a); + bdrv_unref(bs_b); + blk_unref(blk_a); + blk_unref(blk_b); +} + typedef struct TestBlockJob { BlockJob common; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_add_func("/bdrv-drain/nested", test_nested); g_test_add_func("/bdrv-drain/multiparent", test_multiparent); + g_test_add_func("/bdrv-drain/graph-change", test_graph_change); g_test_add_func("/bdrv-drain/blockjob/drain_all", test_blockjob_drain_all); g_test_add_func("/bdrv-drain/blockjob/drain", test_blockjob_drain); -- 2.13.6 Since commit bde70715, base is the only node that is reopened in commit_start(). This means that the code, which still involves an explicit BlockReopenQueue, can now be simplified by using bdrv_reopen(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block/commit.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/block/commit.c b/block/commit.c index XXXXXXX..XXXXXXX 100644 --- a/block/commit.c +++ b/block/commit.c @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, const char *filter_node_name, Error **errp) { CommitBlockJob *s; - BlockReopenQueue *reopen_queue = NULL; int orig_base_flags; BlockDriverState *iter; BlockDriverState *commit_top_bs = NULL; @@ -XXX,XX +XXX,XX @@ void commit_start(const char *job_id, BlockDriverState *bs, /* convert base to r/w, if necessary */ orig_base_flags = bdrv_get_flags(base); if (!(orig_base_flags & BDRV_O_RDWR)) { - reopen_queue = bdrv_reopen_queue(reopen_queue, base, NULL, - orig_base_flags | BDRV_O_RDWR); - } - - if (reopen_queue) { - bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err); + bdrv_reopen(base, orig_base_flags | BDRV_O_RDWR, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); goto fail; -- 2.13.6 The bdrv_reopen*() implementation doesn't like it if the graph is changed between queuing nodes for reopen and actually reopening them (one of the reasons is that queuing can be recursive). So instead of draining the device only in bdrv_reopen_multiple(), require that callers already drained all affected nodes, and assert this in bdrv_reopen_queue(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> --- block.c | 23 ++++++++++++++++------- block/replication.c | 6 ++++++ qemu-io-cmds.c | 3 +++ 3 files changed, 25 insertions(+), 7 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ BlockDriverState *bdrv_open(const char *filename, const char *reference, * returns a pointer to bs_queue, which is either the newly allocated * bs_queue, or the existing bs_queue being used. * + * bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple(). */ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, BlockDriverState *bs, @@ -XXX,XX +XXX,XX @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, BdrvChild *child; QDict *old_options, *explicit_options; + /* Make sure that the caller remembered to use a drained section. This is + * important to avoid graph changes between the recursive queuing here and + * bdrv_reopen_multiple(). */ + assert(bs->quiesce_counter > 0); + if (bs_queue == NULL) { bs_queue = g_new0(BlockReopenQueue, 1); QSIMPLEQ_INIT(bs_queue); @@ -XXX,XX +XXX,XX @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, * If all devices prepare successfully, then the changes are committed * to all devices. * + * All affected nodes must be drained between bdrv_reopen_queue() and + * bdrv_reopen_multiple(). */ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **errp) { @@ -XXX,XX +XXX,XX @@ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **er assert(bs_queue != NULL); - aio_context_release(ctx); - bdrv_drain_all_begin(); - aio_context_acquire(ctx); - QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) { + assert(bs_entry->state.bs->quiesce_counter > 0); if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, &local_err)) { error_propagate(errp, local_err); goto cleanup; @@ -XXX,XX +XXX,XX @@ cleanup: } g_free(bs_queue); - bdrv_drain_all_end(); - return ret; } @@ -XXX,XX +XXX,XX @@ int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp) { int ret = -1; Error *local_err = NULL; - BlockReopenQueue *queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags); + BlockReopenQueue *queue; + bdrv_subtree_drained_begin(bs); + + queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags); ret = bdrv_reopen_multiple(bdrv_get_aio_context(bs), queue, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); } + + bdrv_subtree_drained_end(bs); + return ret; } diff --git a/block/replication.c b/block/replication.c index XXXXXXX..XXXXXXX 100644 --- a/block/replication.c +++ b/block/replication.c @@ -XXX,XX +XXX,XX @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, new_secondary_flags = s->orig_secondary_flags; } + bdrv_subtree_drained_begin(s->hidden_disk->bs); + bdrv_subtree_drained_begin(s->secondary_disk->bs); + if (orig_hidden_flags != new_hidden_flags) { reopen_queue = bdrv_reopen_queue(reopen_queue, s->hidden_disk->bs, NULL, new_hidden_flags); @@ -XXX,XX +XXX,XX @@ static void reopen_backing_file(BlockDriverState *bs, bool writable, reopen_queue, &local_err); error_propagate(errp, local_err); } + + bdrv_subtree_drained_end(s->hidden_disk->bs); + bdrv_subtree_drained_end(s->secondary_disk->bs); } static void backup_job_cleanup(BlockDriverState *bs) diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -XXX,XX +XXX,XX @@ static int reopen_f(BlockBackend *blk, int argc, char **argv) opts = qopts ? qemu_opts_to_qdict(qopts, NULL) : NULL; qemu_opts_reset(&reopen_opts); + bdrv_subtree_drained_begin(bs); brq = bdrv_reopen_queue(NULL, bs, opts, flags); bdrv_reopen_multiple(bdrv_get_aio_context(bs), brq, &local_err); + bdrv_subtree_drained_end(bs); + if (local_err) { error_report_err(local_err); } else { -- 2.13.6