The following changes since commit 22ef7ba8e8ce7fef297549b3defcac333742b804: Merge remote-tracking branch 'remotes/famz/tags/staging-pull-request' into staging (2018-03-13 11:42:45 +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 be6c885842efded81a20f4ca24f0d4e123a80c00: block/mirror: change the semantic of 'force' of block-job-cancel (2018-03-13 16:54:47 +0100) ---------------------------------------------------------------- Block layer patches ---------------------------------------------------------------- Fam Zheng (2): block: Fix flags in reopen queue iotests: Add regression test for commit base locking John Snow (21): blockjobs: fix set-speed kick blockjobs: model single jobs as transactions Blockjobs: documentation touchup blockjobs: add status enum blockjobs: add state transition table iotests: add pause_wait blockjobs: add block_job_verb permission table blockjobs: add ABORTING state blockjobs: add CONCLUDED state blockjobs: add NULL state blockjobs: add block_job_dismiss blockjobs: ensure abort is called for cancelled jobs blockjobs: add commit, abort, clean helpers blockjobs: add block_job_txn_apply function blockjobs: add prepare callback blockjobs: add waiting status blockjobs: add PENDING status and event blockjobs: add block-job-finalize blockjobs: Expose manual property iotests: test manual job dismissal tests/test-blockjob: test cancellations Kevin Wolf (14): luks: Separate image file creation from formatting luks: Create block_crypto_co_create_generic() luks: Support .bdrv_co_create luks: Turn invalid assertion into check luks: Catch integer overflow for huge sizes qemu-iotests: Test luks QMP image creation parallels: Support .bdrv_co_create qemu-iotests: Enable write tests for parallels qcow: Support .bdrv_co_create qed: Support .bdrv_co_create vdi: Make comments consistent with other drivers vhdx: Support .bdrv_co_create vpc: Support .bdrv_co_create vpc: Require aligned size in .bdrv_co_create Liang Li (1): block/mirror: change the semantic of 'force' of block-job-cancel Max Reitz (3): vdi: Pull option parsing from vdi_co_create vdi: Move file creation to vdi_co_create_opts vdi: Implement .bdrv_co_create qapi/block-core.json | 363 ++++++++++++++++++++++++++++++++++++++++-- include/block/blockjob.h | 71 ++++++++- include/block/blockjob_int.h | 17 +- block.c | 8 + block/backup.c | 5 +- block/commit.c | 2 +- block/crypto.c | 150 ++++++++++++----- block/mirror.c | 12 +- block/parallels.c | 199 +++++++++++++++++------ block/qcow.c | 196 +++++++++++++++-------- block/qed.c | 204 ++++++++++++++++-------- block/stream.c | 2 +- block/vdi.c | 147 +++++++++++++---- block/vhdx.c | 216 +++++++++++++++++++------ block/vpc.c | 241 +++++++++++++++++++++------- blockdev.c | 71 +++++++-- blockjob.c | 358 +++++++++++++++++++++++++++++++++++------ tests/test-bdrv-drain.c | 5 +- tests/test-blockjob-txn.c | 27 ++-- tests/test-blockjob.c | 233 ++++++++++++++++++++++++++- block/trace-events | 7 + hmp-commands.hx | 3 +- tests/qemu-iotests/030 | 6 +- tests/qemu-iotests/055 | 17 +- tests/qemu-iotests/056 | 187 ++++++++++++++++++++++ tests/qemu-iotests/056.out | 4 +- tests/qemu-iotests/109.out | 24 +-- tests/qemu-iotests/153 | 12 ++ tests/qemu-iotests/153.out | 5 + tests/qemu-iotests/181 | 2 +- tests/qemu-iotests/209 | 210 ++++++++++++++++++++++++ tests/qemu-iotests/209.out | 136 ++++++++++++++++ tests/qemu-iotests/check | 1 - tests/qemu-iotests/common.rc | 2 +- tests/qemu-iotests/group | 1 + tests/qemu-iotests/iotests.py | 12 +- 36 files changed, 2642 insertions(+), 514 deletions(-) create mode 100755 tests/qemu-iotests/209 create mode 100644 tests/qemu-iotests/209.out From: John Snow <jsnow@redhat.com> If speed is '0' it's not actually "less than" the previous speed. Kick the job in this case too. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) } job->speed = speed; - if (speed <= old_speed) { + if (speed && speed <= old_speed) { return; } -- 2.13.6 From: John Snow <jsnow@redhat.com> model all independent jobs as single job transactions. It's one less case we have to worry about when we add more states to the transition machine. This way, we can just treat all job lifetimes exactly the same. This helps tighten assertions of the STM graph and removes some conditionals that would have been needed in the coming commits adding a more explicit job lifetime management API. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/blockjob.h | 1 - include/block/blockjob_int.h | 3 ++- block/backup.c | 3 +-- block/commit.c | 2 +- block/mirror.c | 2 +- block/stream.c | 2 +- blockjob.c | 25 ++++++++++++++++--------- tests/test-bdrv-drain.c | 4 ++-- tests/test-blockjob-txn.c | 19 +++++++------------ tests/test-blockjob.c | 2 +- 10 files changed, 32 insertions(+), 31 deletions(-) diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { */ QEMUTimer sleep_timer; - /** Non-NULL if this job is part of a transaction */ BlockJobTxn *txn; QLIST_ENTRY(BlockJob) txn_list; } BlockJob; diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob_int.h +++ b/include/block/blockjob_int.h @@ -XXX,XX +XXX,XX @@ struct BlockJobDriver { * @job_id: The id of the newly-created job, or %NULL to have one * generated automatically. * @job_type: The class object for the newly-created job. + * @txn: The transaction this job belongs to, if any. %NULL otherwise. * @bs: The block * @perm, @shared_perm: Permissions to request for @bs * @speed: The maximum speed, in bytes per second, or 0 for unlimited. @@ -XXX,XX +XXX,XX @@ struct BlockJobDriver { * called from a wrapper that is specific to the job type. */ void *block_job_create(const char *job_id, const BlockJobDriver *driver, - BlockDriverState *bs, uint64_t perm, + BlockJobTxn *txn, BlockDriverState *bs, uint64_t perm, uint64_t shared_perm, int64_t speed, int flags, BlockCompletionFunc *cb, void *opaque, Error **errp); diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, } /* job->common.len is fixed, so we can't allow resize */ - job = block_job_create(job_id, &backup_job_driver, bs, + job = block_job_create(job_id, &backup_job_driver, txn, bs, BLK_PERM_CONSISTENT_READ, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD, @@ -XXX,XX +XXX,XX @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL, &error_abort); job->common.len = len; - block_job_txn_add_job(txn, &job->common); return &job->common; 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, return; } - s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL, + s = block_job_create(job_id, &commit_job_driver, NULL, bs, 0, BLK_PERM_ALL, speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp); if (!s) { return; diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs, } /* Make sure that the source is not resized while the job is running */ - s = block_job_create(job_id, driver, mirror_top_bs, + s = block_job_create(job_id, driver, NULL, mirror_top_bs, BLK_PERM_CONSISTENT_READ, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD, speed, diff --git a/block/stream.c b/block/stream.c index XXXXXXX..XXXXXXX 100644 --- a/block/stream.c +++ b/block/stream.c @@ -XXX,XX +XXX,XX @@ void stream_start(const char *job_id, BlockDriverState *bs, /* Prevent concurrent jobs trying to modify the graph structure here, we * already have our own plans. Also don't allow resize as the image size is * queried only at the job start and then cached. */ - s = block_job_create(job_id, &stream_job_driver, bs, + s = block_job_create(job_id, &stream_job_driver, NULL, bs, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED | diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static void block_job_completed_single(BlockJob *job) } } - if (job->txn) { - QLIST_REMOVE(job, txn_list); - block_job_txn_unref(job->txn); - } + QLIST_REMOVE(job, txn_list); + block_job_txn_unref(job->txn); block_job_unref(job); } @@ -XXX,XX +XXX,XX @@ static void block_job_event_completed(BlockJob *job, const char *msg) */ void *block_job_create(const char *job_id, const BlockJobDriver *driver, - BlockDriverState *bs, uint64_t perm, + BlockJobTxn *txn, BlockDriverState *bs, uint64_t perm, uint64_t shared_perm, int64_t speed, int flags, BlockCompletionFunc *cb, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, return NULL; } } + + /* Single jobs are modeled as single-job transactions for sake of + * consolidating the job management logic */ + if (!txn) { + txn = block_job_txn_new(); + block_job_txn_add_job(txn, job); + block_job_txn_unref(txn); + } else { + block_job_txn_add_job(txn, job); + } + return job; } @@ -XXX,XX +XXX,XX @@ void block_job_early_fail(BlockJob *job) void block_job_completed(BlockJob *job, int ret) { + assert(job && job->txn && !job->completed); assert(blk_bs(job->blk)->job == job); - assert(!job->completed); job->completed = true; job->ret = ret; - if (!job->txn) { - block_job_completed_single(job); - } else if (ret < 0 || block_job_is_cancelled(job)) { + if (ret < 0 || block_job_is_cancelled(job)) { block_job_completed_txn_abort(job); } else { block_job_completed_txn_success(job); 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) 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); + job = block_job_create("job0", &test_job_driver, NULL, 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); diff --git a/tests/test-blockjob-txn.c b/tests/test-blockjob-txn.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-blockjob-txn.c +++ b/tests/test-blockjob-txn.c @@ -XXX,XX +XXX,XX @@ static const BlockJobDriver test_block_job_driver = { */ static BlockJob *test_block_job_start(unsigned int iterations, bool use_timer, - int rc, int *result) + int rc, int *result, BlockJobTxn *txn) { BlockDriverState *bs; TestBlockJob *s; @@ -XXX,XX +XXX,XX @@ static BlockJob *test_block_job_start(unsigned int iterations, g_assert_nonnull(bs); snprintf(job_id, sizeof(job_id), "job%u", counter++); - s = block_job_create(job_id, &test_block_job_driver, bs, + s = block_job_create(job_id, &test_block_job_driver, txn, bs, 0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT, test_block_job_cb, data, &error_abort); s->iterations = iterations; @@ -XXX,XX +XXX,XX @@ static void test_single_job(int expected) int result = -EINPROGRESS; txn = block_job_txn_new(); - job = test_block_job_start(1, true, expected, &result); - block_job_txn_add_job(txn, job); + job = test_block_job_start(1, true, expected, &result, txn); block_job_start(job); if (expected == -ECANCELED) { @@ -XXX,XX +XXX,XX @@ static void test_pair_jobs(int expected1, int expected2) int result2 = -EINPROGRESS; txn = block_job_txn_new(); - job1 = test_block_job_start(1, true, expected1, &result1); - block_job_txn_add_job(txn, job1); - job2 = test_block_job_start(2, true, expected2, &result2); - block_job_txn_add_job(txn, job2); + job1 = test_block_job_start(1, true, expected1, &result1, txn); + job2 = test_block_job_start(2, true, expected2, &result2, txn); block_job_start(job1); block_job_start(job2); @@ -XXX,XX +XXX,XX @@ static void test_pair_jobs_fail_cancel_race(void) int result2 = -EINPROGRESS; txn = block_job_txn_new(); - job1 = test_block_job_start(1, true, -ECANCELED, &result1); - block_job_txn_add_job(txn, job1); - job2 = test_block_job_start(2, false, 0, &result2); - block_job_txn_add_job(txn, job2); + job1 = test_block_job_start(1, true, -ECANCELED, &result1, txn); + job2 = test_block_job_start(2, false, 0, &result2, txn); block_job_start(job1); block_job_start(job2); diff --git a/tests/test-blockjob.c b/tests/test-blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-blockjob.c +++ b/tests/test-blockjob.c @@ -XXX,XX +XXX,XX @@ static BlockJob *do_test_id(BlockBackend *blk, const char *id, BlockJob *job; Error *errp = NULL; - job = block_job_create(id, &test_block_job_driver, blk_bs(blk), + job = block_job_create(id, &test_block_job_driver, NULL, blk_bs(blk), 0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT, block_job_cb, NULL, &errp); if (should_succeed) { -- 2.13.6 From: John Snow <jsnow@redhat.com> Trivial; Document what the job creation flags do, and some general tidying. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/blockjob.h | 8 ++++---- include/block/blockjob_int.h | 4 +++- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { /** Reference count of the block job */ int refcnt; - /* True if this job has reported completion by calling block_job_completed. - */ + /** True when job has reported completion by calling block_job_completed. */ bool completed; - /* ret code passed to block_job_completed. - */ + /** ret code passed to block_job_completed. */ int ret; /** @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { } BlockJob; typedef enum BlockJobCreateFlags { + /* Default behavior */ BLOCK_JOB_DEFAULT = 0x00, + /* BlockJob is not QMP-created and should not send QMP events */ BLOCK_JOB_INTERNAL = 0x01, } BlockJobCreateFlags; diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob_int.h +++ b/include/block/blockjob_int.h @@ -XXX,XX +XXX,XX @@ struct BlockJobDriver { * block_job_create: * @job_id: The id of the newly-created job, or %NULL to have one * generated automatically. - * @job_type: The class object for the newly-created job. + * @driver: The class object for the newly-created job. * @txn: The transaction this job belongs to, if any. %NULL otherwise. * @bs: The block * @perm, @shared_perm: Permissions to request for @bs * @speed: The maximum speed, in bytes per second, or 0 for unlimited. + * @flags: Creation flags for the Block Job. + * See @BlockJobCreateFlags * @cb: Completion function for the job. * @opaque: Opaque pointer value passed to @cb. * @errp: Error object. -- 2.13.6 From: John Snow <jsnow@redhat.com> We're about to add several new states, and booleans are becoming unwieldly and difficult to reason about. It would help to have a more explicit bookkeeping of the state of blockjobs. To this end, add a new "status" field and add our existing states in a redundant manner alongside the bools they are replacing: UNDEFINED: Placeholder, default state. Not currently visible to QMP unless changes occur in the future to allow creating jobs without starting them via QMP. CREATED: replaces !!job->co && paused && !busy RUNNING: replaces effectively (!paused && busy) PAUSED: Nearly redundant with info->paused, which shows pause_count. This reports the actual status of the job, which almost always matches the paused request status. It differs in that it is strictly only true when the job has actually gone dormant. READY: replaces job->ready. STANDBY: Paused, but job->ready is true. New state additions in coming commits will not be quite so redundant: WAITING: Waiting on transaction. This job has finished all the work it can until the transaction converges, fails, or is canceled. PENDING: Pending authorization from user. This job has finished all the work it can until the job or transaction is finalized via block_job_finalize. This implies the transaction has converged and left the WAITING phase. ABORTING: Job has encountered an error condition and is in the process of aborting. CONCLUDED: Job has ceased all operations and has a return code available for query and may be dismissed via block_job_dismiss. NULL: Job has been dismissed and (should) be destroyed. Should never be visible to QMP. Some of these states appear somewhat superfluous, but it helps define the expected flow of a job; so some of the states wind up being synchronous empty transitions. Importantly, jobs can be in only one of these states at any given time, which helps code and external users alike reason about the current condition of a job unambiguously. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 31 ++++++++++++++++++++++++++++++- include/block/blockjob.h | 3 +++ blockjob.c | 9 +++++++++ tests/qemu-iotests/109.out | 24 ++++++++++++------------ 4 files changed, 54 insertions(+), 13 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 @@ 'data': ['commit', 'stream', 'mirror', 'backup'] } ## +# @BlockJobStatus: +# +# Indicates the present state of a given blockjob in its lifetime. +# +# @undefined: Erroneous, default state. Should not ever be visible. +# +# @created: The job has been created, but not yet started. +# +# @running: The job is currently running. +# +# @paused: The job is running, but paused. The pause may be requested by +# either the QMP user or by internal processes. +# +# @ready: The job is running, but is ready for the user to signal completion. +# This is used for long-running jobs like mirror that are designed to +# run indefinitely. +# +# @standby: The job is ready, but paused. This is nearly identical to @paused. +# The job may return to @ready or otherwise be canceled. +# +# Since: 2.12 +## +{ 'enum': 'BlockJobStatus', + 'data': ['undefined', 'created', 'running', 'paused', 'ready', 'standby'] } + +## # @BlockJobInfo: # # Information about a long-running block device operation. @@ -XXX,XX +XXX,XX @@ # # @ready: true if the job may be completed (since 2.2) # +# @status: Current job state/status (since 2.12) +# # Since: 1.1 ## { 'struct': 'BlockJobInfo', 'data': {'type': 'str', 'device': 'str', 'len': 'int', 'offset': 'int', 'busy': 'bool', 'paused': 'bool', 'speed': 'int', - 'io-status': 'BlockDeviceIoStatus', 'ready': 'bool'} } + 'io-status': 'BlockDeviceIoStatus', 'ready': 'bool', + 'status': 'BlockJobStatus' } } ## # @query-block-jobs: diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { */ QEMUTimer sleep_timer; + /** Current state; See @BlockJobStatus for details. */ + BlockJobStatus status; + BlockJobTxn *txn; QLIST_ENTRY(BlockJob) txn_list; } BlockJob; diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ void block_job_start(BlockJob *job) job->pause_count--; job->busy = true; job->paused = false; + job->status = BLOCK_JOB_STATUS_RUNNING; bdrv_coroutine_enter(blk_bs(job->blk), job->co); } @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp) info->speed = job->speed; info->io_status = job->iostatus; info->ready = job->ready; + info->status = job->status; return info; } @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, job->paused = true; job->pause_count = 1; job->refcnt = 1; + job->status = BLOCK_JOB_STATUS_CREATED; aio_timer_init(qemu_get_aio_context(), &job->sleep_timer, QEMU_CLOCK_REALTIME, SCALE_NS, block_job_sleep_timer_cb, job); @@ -XXX,XX +XXX,XX @@ void coroutine_fn block_job_pause_point(BlockJob *job) } if (block_job_should_pause(job) && !block_job_is_cancelled(job)) { + BlockJobStatus status = job->status; + job->status = status == BLOCK_JOB_STATUS_READY ? \ + BLOCK_JOB_STATUS_STANDBY : \ + BLOCK_JOB_STATUS_PAUSED; job->paused = true; block_job_do_yield(job, -1); job->paused = false; + job->status = status; } if (job->driver->resume) { @@ -XXX,XX +XXX,XX @@ void block_job_iostatus_reset(BlockJob *job) void block_job_event_ready(BlockJob *job) { + job->status = BLOCK_JOB_STATUS_READY; job->ready = true; if (block_job_is_internal(job)) { diff --git a/tests/qemu-iotests/109.out b/tests/qemu-iotests/109.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/109.out +++ b/tests/qemu-iotests/109.out @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 1024, "offset": 1024, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 1024, "offset": 1024, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 197120, "offset": 197120, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 197120, "offset": 197120, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 197120, "offset": 197120, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 197120, "offset": 197120, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 327680, "offset": 327680, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 327680, "offset": 327680, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 1024, "offset": 1024, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 1024, "offset": 1024, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 65536, "offset": 65536, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 65536, "offset": 65536, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2560, "offset": 2560, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2560, "offset": 2560, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2560, "offset": 2560, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2560, "offset": 2560, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 31457280, "offset": 31457280, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 31457280, "offset": 31457280, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 31457280, "offset": 31457280, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 31457280, "offset": 31457280, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 327680, "offset": 327680, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 327680, "offset": 327680, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 2048, "offset": 2048, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2048, "offset": 2048, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2048, "offset": 2048, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2048, "offset": 2048, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ Automatically detecting the format is dangerous for raw images, write operations Specify the 'raw' format explicitly to remove the restrictions. {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 512, "offset": 512, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 512, "offset": 512, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ Images are identical. {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 512, "offset": 512, "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 512, "offset": 512, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} -- 2.13.6 From: John Snow <jsnow@redhat.com> The state transition table has mostly been implied. We're about to make it a bit more complex, so let's make the STM explicit instead. Perform state transitions with a function that for now just asserts the transition is appropriate. Transitions: Undefined -> Created: During job initialization. Created -> Running: Once the job is started. Jobs cannot transition from "Created" to "Paused" directly, but will instead synchronously transition to running to paused immediately. Running -> Paused: Normal workflow for pauses. Running -> Ready: Normal workflow for jobs reaching their sync point. (e.g. mirror) Ready -> Standby: Normal workflow for pausing ready jobs. Paused -> Running: Normal resume. Standby -> Ready: Resume of a Standby job. +---------+ |UNDEFINED| +--+------+ | +--v----+ |CREATED| +--+----+ | +--v----+ +------+ |RUNNING<----->PAUSED| +--+----+ +------+ | +--v--+ +-------+ |READY<------->STANDBY| +-----+ +-------+ Notably, there is no state presently defined as of this commit that deals with a job after the "running" or "ready" states, so this table will be adjusted alongside the commits that introduce those states. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 40 +++++++++++++++++++++++++++++++++------- block/trace-events | 3 +++ 2 files changed, 36 insertions(+), 7 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ #include "block/block.h" #include "block/blockjob_int.h" #include "block/block_int.h" +#include "block/trace.h" #include "sysemu/block-backend.h" #include "qapi/error.h" #include "qapi/qapi-events-block-core.h" @@ -XXX,XX +XXX,XX @@ * block_job_enter. */ static QemuMutex block_job_mutex; +/* BlockJob State Transition Table */ +bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { + /* U, C, R, P, Y, S */ + /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0}, + /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0}, + /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0}, + /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0}, + /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1}, + /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0}, +}; + +static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) +{ + BlockJobStatus s0 = job->status; + assert(s1 >= 0 && s1 <= BLOCK_JOB_STATUS__MAX); + trace_block_job_state_transition(job, job->ret, BlockJobSTT[s0][s1] ? + "allowed" : "disallowed", + qapi_enum_lookup(&BlockJobStatus_lookup, + s0), + qapi_enum_lookup(&BlockJobStatus_lookup, + s1)); + assert(BlockJobSTT[s0][s1]); + job->status = s1; +} + static void block_job_lock(void) { qemu_mutex_lock(&block_job_mutex); @@ -XXX,XX +XXX,XX @@ void block_job_start(BlockJob *job) job->pause_count--; job->busy = true; job->paused = false; - job->status = BLOCK_JOB_STATUS_RUNNING; + block_job_state_transition(job, BLOCK_JOB_STATUS_RUNNING); bdrv_coroutine_enter(blk_bs(job->blk), job->co); } @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, job->paused = true; job->pause_count = 1; job->refcnt = 1; - job->status = BLOCK_JOB_STATUS_CREATED; + block_job_state_transition(job, BLOCK_JOB_STATUS_CREATED); aio_timer_init(qemu_get_aio_context(), &job->sleep_timer, QEMU_CLOCK_REALTIME, SCALE_NS, block_job_sleep_timer_cb, job); @@ -XXX,XX +XXX,XX @@ void coroutine_fn block_job_pause_point(BlockJob *job) if (block_job_should_pause(job) && !block_job_is_cancelled(job)) { BlockJobStatus status = job->status; - job->status = status == BLOCK_JOB_STATUS_READY ? \ - BLOCK_JOB_STATUS_STANDBY : \ - BLOCK_JOB_STATUS_PAUSED; + block_job_state_transition(job, status == BLOCK_JOB_STATUS_READY ? \ + BLOCK_JOB_STATUS_STANDBY : \ + BLOCK_JOB_STATUS_PAUSED); job->paused = true; block_job_do_yield(job, -1); job->paused = false; - job->status = status; + block_job_state_transition(job, status); } if (job->driver->resume) { @@ -XXX,XX +XXX,XX @@ void block_job_iostatus_reset(BlockJob *job) void block_job_event_ready(BlockJob *job) { - job->status = BLOCK_JOB_STATUS_READY; + block_job_state_transition(job, BLOCK_JOB_STATUS_READY); job->ready = true; if (block_job_is_internal(job)) { diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ bdrv_open_common(void *bs, const char *filename, int flags, const char *format_name) "bs %p filename \"%s\" flags 0x%x format_name \"%s\"" bdrv_lock_medium(void *bs, bool locked) "bs %p locked %d" +# blockjob.c +block_job_state_transition(void *job, int ret, const char *legal, const char *s0, const char *s1) "job %p (ret: %d) attempting %s transition (%s-->%s)" + # block/block-backend.c blk_co_preadv(void *blk, void *bs, int64_t offset, unsigned int bytes, int flags) "blk %p bs %p offset %"PRId64" bytes %u flags 0x%x" blk_co_pwritev(void *blk, void *bs, int64_t offset, unsigned int bytes, int flags) "blk %p bs %p offset %"PRId64" bytes %u flags 0x%x" -- 2.13.6 From: John Snow <jsnow@redhat.com> Split out the pause command into the actual pause and the wait. Not every usage presently needs to resubmit a pause request. The intent with the next commit will be to explicitly disallow redundant or meaningless pause/resume requests, so the tests need to become more judicious to reflect that. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/030 | 6 ++---- tests/qemu-iotests/055 | 17 ++++++----------- tests/qemu-iotests/iotests.py | 12 ++++++++---- 3 files changed, 16 insertions(+), 19 deletions(-) diff --git a/tests/qemu-iotests/030 b/tests/qemu-iotests/030 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/030 +++ b/tests/qemu-iotests/030 @@ -XXX,XX +XXX,XX @@ class TestSingleDrive(iotests.QMPTestCase): result = self.vm.qmp('block-stream', device='drive0') self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('block-job-pause', device='drive0') - self.assert_qmp(result, 'return', {}) - + self.pause_job('drive0', wait=False) self.vm.resume_drive('drive0') - self.pause_job('drive0') + self.pause_wait('drive0') result = self.vm.qmp('query-block-jobs') offset = self.dictpath(result, 'return[0]/offset') diff --git a/tests/qemu-iotests/055 b/tests/qemu-iotests/055 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/055 +++ b/tests/qemu-iotests/055 @@ -XXX,XX +XXX,XX @@ class TestSingleDrive(iotests.QMPTestCase): target=target, sync='full') self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('block-job-pause', device='drive0') - self.assert_qmp(result, 'return', {}) - + self.pause_job('drive0', wait=False) self.vm.resume_drive('drive0') - self.pause_job('drive0') + self.pause_wait('drive0') result = self.vm.qmp('query-block-jobs') offset = self.dictpath(result, 'return[0]/offset') @@ -XXX,XX +XXX,XX @@ class TestSingleTransaction(iotests.QMPTestCase): ]) self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('block-job-pause', device='drive0') - self.assert_qmp(result, 'return', {}) + self.pause_job('drive0', wait=False) result = self.vm.qmp('block-job-set-speed', device='drive0', speed=0) self.assert_qmp(result, 'return', {}) - self.pause_job('drive0') + self.pause_wait('drive0') result = self.vm.qmp('query-block-jobs') offset = self.dictpath(result, 'return[0]/offset') @@ -XXX,XX +XXX,XX @@ class TestDriveCompression(iotests.QMPTestCase): result = self.vm.qmp(cmd, device='drive0', sync='full', compress=True, **args) self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('block-job-pause', device='drive0') - self.assert_qmp(result, 'return', {}) - + self.pause_job('drive0', wait=False) self.vm.resume_drive('drive0') - self.pause_job('drive0') + self.pause_wait('drive0') result = self.vm.qmp('query-block-jobs') offset = self.dictpath(result, 'return[0]/offset') 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 QMPTestCase(unittest.TestCase): event = self.wait_until_completed(drive=drive) self.assert_qmp(event, 'data/type', 'mirror') - def pause_job(self, job_id='job0'): - result = self.vm.qmp('block-job-pause', device=job_id) - self.assert_qmp(result, 'return', {}) - + def pause_wait(self, job_id='job0'): with Timeout(1, "Timeout waiting for job to pause"): while True: result = self.vm.qmp('query-block-jobs') @@ -XXX,XX +XXX,XX @@ class QMPTestCase(unittest.TestCase): if job['device'] == job_id and job['paused'] == True and job['busy'] == False: return job + def pause_job(self, job_id='job0', wait=True): + result = self.vm.qmp('block-job-pause', device=job_id) + self.assert_qmp(result, 'return', {}) + if wait: + return self.pause_wait(job_id) + return result + def notrun(reason): '''Skip this test suite''' -- 2.13.6 From: John Snow <jsnow@redhat.com> Which commands ("verbs") are appropriate for jobs in which state is also somewhat burdensome to keep track of. As of this commit, it looks rather useless, but begins to look more interesting the more states we add to the STM table. A recurring theme is that no verb will apply to an 'undefined' job. Further, it's not presently possible to restrict the "pause" or "resume" verbs any more than they are in this commit because of the asynchronous nature of how jobs enter the PAUSED state; justifications for some seemingly erroneous applications are given below. ===== Verbs ===== Cancel: Any state except undefined. Pause: Any state except undefined; 'created': Requests that the job pauses as it starts. 'running': Normal usage. (PAUSED) 'paused': The job may be paused for internal reasons, but the user may wish to force an indefinite user-pause, so this is allowed. 'ready': Normal usage. (STANDBY) 'standby': Same logic as above. Resume: Any state except undefined; 'created': Will lift a user's pause-on-start request. 'running': Will lift a pause request before it takes effect. 'paused': Normal usage. 'ready': Will lift a pause request before it takes effect. 'standby': Normal usage. Set-speed: Any state except undefined, though ready may not be meaningful. Complete: Only a 'ready' job may accept a complete request. ======= Changes ======= (1) To facilitate "nice" error checking, all five major block-job verb interfaces in blockjob.c now support an errp parameter: - block_job_user_cancel is added as a new interface. - block_job_user_pause gains an errp paramter - block_job_user_resume gains an errp parameter - block_job_set_speed already had an errp parameter. - block_job_complete already had an errp parameter. (2) block-job-pause and block-job-resume will no longer no-op when trying to pause an already paused job, or trying to resume a job that isn't paused. These functions will now report that they did not perform the action requested because it was not possible. iotests have been adjusted to address this new behavior. (3) block-job-complete doesn't worry about checking !block_job_started, because the permission table guards against this. (4) test-bdrv-drain's job implementation needs to announce that it is 'ready' now, in order to be completed. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 20 ++++++++++++++ include/block/blockjob.h | 13 +++++++-- blockdev.c | 10 +++---- blockjob.c | 71 ++++++++++++++++++++++++++++++++++++++++++------ tests/test-bdrv-drain.c | 1 + block/trace-events | 1 + 6 files changed, 100 insertions(+), 16 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 @@ 'data': ['commit', 'stream', 'mirror', 'backup'] } ## +# @BlockJobVerb: +# +# Represents command verbs that can be applied to a blockjob. +# +# @cancel: see @block-job-cancel +# +# @pause: see @block-job-pause +# +# @resume: see @block-job-resume +# +# @set-speed: see @block-job-set-speed +# +# @complete: see @block-job-complete +# +# Since: 2.12 +## +{ 'enum': 'BlockJobVerb', + 'data': ['cancel', 'pause', 'resume', 'set-speed', 'complete' ] } + +## # @BlockJobStatus: # # Indicates the present state of a given blockjob in its lifetime. diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp); * Asynchronously pause the specified job. * Do not allow a resume until a matching call to block_job_user_resume. */ -void block_job_user_pause(BlockJob *job); +void block_job_user_pause(BlockJob *job, Error **errp); /** * block_job_paused: @@ -XXX,XX +XXX,XX @@ bool block_job_user_paused(BlockJob *job); * Resume the specified job. * Must be paired with a preceding block_job_user_pause. */ -void block_job_user_resume(BlockJob *job); +void block_job_user_resume(BlockJob *job, Error **errp); + +/** + * block_job_user_cancel: + * @job: The job to be cancelled. + * + * Cancels the specified job, but may refuse to do so if the + * operation isn't currently meaningful. + */ +void block_job_user_cancel(BlockJob *job, Error **errp); /** * block_job_cancel_sync: 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_job_cancel(const char *device, } trace_qmp_block_job_cancel(job); - block_job_cancel(job); + block_job_user_cancel(job, errp); out: aio_context_release(aio_context); } @@ -XXX,XX +XXX,XX @@ void qmp_block_job_pause(const char *device, Error **errp) AioContext *aio_context; BlockJob *job = find_block_job(device, &aio_context, errp); - if (!job || block_job_user_paused(job)) { + if (!job) { return; } trace_qmp_block_job_pause(job); - block_job_user_pause(job); + block_job_user_pause(job, errp); aio_context_release(aio_context); } @@ -XXX,XX +XXX,XX @@ void qmp_block_job_resume(const char *device, Error **errp) AioContext *aio_context; BlockJob *job = find_block_job(device, &aio_context, errp); - if (!job || !block_job_user_paused(job)) { + if (!job) { return; } trace_qmp_block_job_resume(job); - block_job_user_resume(job); + block_job_user_resume(job, errp); aio_context_release(aio_context); } diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0}, }; +bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { + /* U, C, R, P, Y, S */ + [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1}, + [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1}, + [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1}, + [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1}, + [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0}, +}; + static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) { BlockJobStatus s0 = job->status; @@ -XXX,XX +XXX,XX @@ static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) job->status = s1; } +static int block_job_apply_verb(BlockJob *job, BlockJobVerb bv, Error **errp) +{ + assert(bv >= 0 && bv <= BLOCK_JOB_VERB__MAX); + trace_block_job_apply_verb(job, qapi_enum_lookup(&BlockJobStatus_lookup, + job->status), + qapi_enum_lookup(&BlockJobVerb_lookup, bv), + BlockJobVerbTable[bv][job->status] ? + "allowed" : "prohibited"); + if (BlockJobVerbTable[bv][job->status]) { + return 0; + } + error_setg(errp, "Job '%s' in state '%s' cannot accept command verb '%s'", + job->id, qapi_enum_lookup(&BlockJobStatus_lookup, job->status), + qapi_enum_lookup(&BlockJobVerb_lookup, bv)); + return -EPERM; +} + static void block_job_lock(void) { qemu_mutex_lock(&block_job_mutex); @@ -XXX,XX +XXX,XX @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) error_setg(errp, QERR_UNSUPPORTED); return; } + if (block_job_apply_verb(job, BLOCK_JOB_VERB_SET_SPEED, errp)) { + return; + } job->driver->set_speed(job, speed, &local_err); if (local_err) { error_propagate(errp, local_err); @@ -XXX,XX +XXX,XX @@ void block_job_complete(BlockJob *job, Error **errp) { /* Should not be reachable via external interface for internal jobs */ assert(job->id); - if (job->pause_count || job->cancelled || - !block_job_started(job) || !job->driver->complete) { + if (block_job_apply_verb(job, BLOCK_JOB_VERB_COMPLETE, errp)) { + return; + } + if (job->pause_count || job->cancelled || !job->driver->complete) { error_setg(errp, "The active block job '%s' cannot be completed", job->id); return; @@ -XXX,XX +XXX,XX @@ void block_job_complete(BlockJob *job, Error **errp) job->driver->complete(job, errp); } -void block_job_user_pause(BlockJob *job) +void block_job_user_pause(BlockJob *job, Error **errp) { + if (block_job_apply_verb(job, BLOCK_JOB_VERB_PAUSE, errp)) { + return; + } + if (job->user_paused) { + error_setg(errp, "Job is already paused"); + return; + } job->user_paused = true; block_job_pause(job); } @@ -XXX,XX +XXX,XX @@ bool block_job_user_paused(BlockJob *job) return job->user_paused; } -void block_job_user_resume(BlockJob *job) +void block_job_user_resume(BlockJob *job, Error **errp) { - if (job && job->user_paused && job->pause_count > 0) { - block_job_iostatus_reset(job); - job->user_paused = false; - block_job_resume(job); + assert(job); + if (!job->user_paused || job->pause_count <= 0) { + error_setg(errp, "Can't resume a job that was not paused"); + return; + } + if (block_job_apply_verb(job, BLOCK_JOB_VERB_RESUME, errp)) { + return; } + block_job_iostatus_reset(job); + job->user_paused = false; + block_job_resume(job); } void block_job_cancel(BlockJob *job) @@ -XXX,XX +XXX,XX @@ void block_job_cancel(BlockJob *job) } } +void block_job_user_cancel(BlockJob *job, Error **errp) +{ + if (block_job_apply_verb(job, BLOCK_JOB_VERB_CANCEL, errp)) { + return; + } + block_job_cancel(job); +} + /* A wrapper around block_job_cancel() taking an Error ** parameter so it may be * used with block_job_finish_sync() without the need for (rather nasty) * function pointer casts there. */ @@ -XXX,XX +XXX,XX @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err, action, &error_abort); } if (action == BLOCK_ERROR_ACTION_STOP) { + block_job_pause(job); /* make the pause user visible, which will be resumed from QMP. */ - block_job_user_pause(job); + job->user_paused = true; block_job_iostatus_set_err(job, error); } return action; 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 coroutine_fn test_job_start(void *opaque) { TestBlockJob *s = opaque; + block_job_event_ready(&s->common); while (!s->should_complete) { block_job_sleep_ns(&s->common, 100000); } diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ bdrv_lock_medium(void *bs, bool locked) "bs %p locked %d" # blockjob.c block_job_state_transition(void *job, int ret, const char *legal, const char *s0, const char *s1) "job %p (ret: %d) attempting %s transition (%s-->%s)" +block_job_apply_verb(void *job, const char *state, const char *verb, const char *legal) "job %p in state %s; applying verb %s (%s)" # block/block-backend.c blk_co_preadv(void *blk, void *bs, int64_t offset, unsigned int bytes, int flags) "blk %p bs %p offset %"PRId64" bytes %u flags 0x%x" -- 2.13.6 From: John Snow <jsnow@redhat.com> Add a new state ABORTING. This makes transitions from normative states to error states explicit in the STM, and serves as a disambiguation for which states may complete normally when normal end-states (CONCLUDED) are added in future commits. Notably, Paused/Standby jobs do not transition directly to aborting, as they must wake up first and cooperate in their cancellation. Transitions: Created -> Aborting: can be cancelled (by the system) Running -> Aborting: can be cancelled or encounter an error Ready -> Aborting: can be cancelled or encounter an error Verbs: None. The job must finish cleaning itself up and report its final status. +---------+ |UNDEFINED| +--+------+ | +--v----+ +---------+CREATED| | +--+----+ | | | +--v----+ +------+ +---------+RUNNING<----->PAUSED| | +--+----+ +------+ | | | +--v--+ +-------+ +---------+READY<------->STANDBY| | +-----+ +-------+ | +--v-----+ |ABORTING| +--------+ Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 7 ++++++- blockjob.c | 31 ++++++++++++++++++------------- 2 files changed, 24 insertions(+), 14 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 @@ # @standby: The job is ready, but paused. This is nearly identical to @paused. # The job may return to @ready or otherwise be canceled. # +# @aborting: The job is in the process of being aborted, and will finish with +# an error. +# This status may not be visible to the management process. +# # Since: 2.12 ## { 'enum': 'BlockJobStatus', - 'data': ['undefined', 'created', 'running', 'paused', 'ready', 'standby'] } + 'data': ['undefined', 'created', 'running', 'paused', 'ready', 'standby', + 'aborting' ] } ## # @BlockJobInfo: diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static QemuMutex block_job_mutex; /* BlockJob State Transition Table */ bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S */ - /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0}, - /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0}, - /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0}, - /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0}, - /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1}, - /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0}, + /* U, C, R, P, Y, S, X */ + /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0}, + /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 1}, + /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1}, + /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0}, + /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1}, + /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0}, + /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0}, }; bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S */ - [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1}, - [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1}, - [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1}, - [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1}, - [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0}, + /* U, C, R, P, Y, S, X */ + [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 0}, + [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0}, + [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0}, + [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0}, + [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0}, }; static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) @@ -XXX,XX +XXX,XX @@ static void block_job_completed_single(BlockJob *job) { assert(job->completed); + if (job->ret || block_job_is_cancelled(job)) { + block_job_state_transition(job, BLOCK_JOB_STATUS_ABORTING); + } + if (!job->ret) { if (job->driver->commit) { job->driver->commit(job); -- 2.13.6 From: John Snow <jsnow@redhat.com> add a new state "CONCLUDED" that identifies a job that has ceased all operations. The wording was chosen to avoid any phrasing that might imply success, error, or cancellation. The task has simply ceased all operation and can never again perform any work. ("finished", "done", and "completed" might all imply success.) Transitions: Running -> Concluded: normal completion Ready -> Concluded: normal completion Aborting -> Concluded: error and cancellations Verbs: None as of this commit. (a future commit adds 'dismiss') +---------+ |UNDEFINED| +--+------+ | +--v----+ +---------+CREATED| | +--+----+ | | | +--v----+ +------+ +---------+RUNNING<----->PAUSED| | +--+-+--+ +------+ | | | | | +------------------+ | | | | +--v--+ +-------+ | +---------+READY<------->STANDBY| | | +--+--+ +-------+ | | | | +--v-----+ +--v------+ | |ABORTING+--->CONCLUDED<-------------+ +--------+ +---------+ Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 7 +++++-- blockjob.c | 39 ++++++++++++++++++++++++--------------- 2 files changed, 29 insertions(+), 17 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 @@ # The job may return to @ready or otherwise be canceled. # # @aborting: The job is in the process of being aborted, and will finish with -# an error. +# an error. The job will afterwards report that it is @concluded. # This status may not be visible to the management process. # +# @concluded: The job has finished all work. If manual was set to true, the job +# will remain in the query list until it is dismissed. +# # Since: 2.12 ## { 'enum': 'BlockJobStatus', 'data': ['undefined', 'created', 'running', 'paused', 'ready', 'standby', - 'aborting' ] } + 'aborting', 'concluded' ] } ## # @BlockJobInfo: diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static QemuMutex block_job_mutex; /* BlockJob State Transition Table */ bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, X */ - /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0}, - /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 1}, - /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1}, - /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0}, - /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1}, - /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0}, - /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0}, + /* U, C, R, P, Y, S, X, E */ + /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0}, + /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 1, 0}, + /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 1}, + /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0}, + /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 1}, + /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0}, + /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 1}, + /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0}, }; bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, X */ - [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 0}, - [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0}, - [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0}, - [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0}, - [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0}, + /* U, C, R, P, Y, S, X, E */ + [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 0, 0}, + [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0}, + [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0}, + [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0}, + [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0}, }; static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) @@ -XXX,XX +XXX,XX @@ void block_job_start(BlockJob *job) bdrv_coroutine_enter(blk_bs(job->blk), job->co); } +static void block_job_conclude(BlockJob *job) +{ + block_job_state_transition(job, BLOCK_JOB_STATUS_CONCLUDED); +} + static void block_job_completed_single(BlockJob *job) { assert(job->completed); @@ -XXX,XX +XXX,XX @@ static void block_job_completed_single(BlockJob *job) QLIST_REMOVE(job, txn_list); block_job_txn_unref(job->txn); + block_job_conclude(job); block_job_unref(job); } @@ -XXX,XX +XXX,XX @@ void block_job_user_resume(BlockJob *job, Error **errp) void block_job_cancel(BlockJob *job) { - if (block_job_started(job)) { + if (job->status == BLOCK_JOB_STATUS_CONCLUDED) { + return; + } else if (block_job_started(job)) { block_job_cancel_async(job); block_job_enter(job); } else { -- 2.13.6 From: John Snow <jsnow@redhat.com> Add a new state that specifically demarcates when we begin to permanently demolish a job after it has performed all work. This makes the transition explicit in the STM table and highlights conditions under which a job may be demolished. Alongside this state, add a new helper command "block_job_decommission", which transitions to the NULL state and puts down our implicit reference. This separates instances in the code for "block_job_unref" which merely undo a matching "block_job_ref" with instances intended to initiate the full destruction of the object. This decommission action also sets a number of fields to make sure that block internals or external users that are holding a reference to a job to see when it "finishes" are convinced that the job object is "done." This is necessary, for instance, to do a block_job_cancel_sync on a created object which will not make any progress. Now, all jobs must go through block_job_decommission prior to being freed, giving us start-to-finish state machine coverage for jobs. Transitions: Created -> Null: Early failure event before the job is started Concluded -> Null: Standard transition. Verbs: None. This should not ever be visible to the monitor. +---------+ |UNDEFINED| +--+------+ | +--v----+ +---------+CREATED+------------------+ | +--+----+ | | | | | +--v----+ +------+ | +---------+RUNNING<----->PAUSED| | | +--+-+--+ +------+ | | | | | | | +------------------+ | | | | | | +--v--+ +-------+ | | +---------+READY<------->STANDBY| | | | +--+--+ +-------+ | | | | | | +--v-----+ +--v------+ | | |ABORTING+--->CONCLUDED<-------------+ | +--------+ +--+------+ | | | +--v-+ | |NULL<---------------------+ +----+ Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 5 ++++- blockjob.c | 50 ++++++++++++++++++++++++++++++++------------------ 2 files changed, 36 insertions(+), 19 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 @@ # @concluded: The job has finished all work. If manual was set to true, the job # will remain in the query list until it is dismissed. # +# @null: The job is in the process of being dismantled. This state should not +# ever be visible externally. +# # Since: 2.12 ## { 'enum': 'BlockJobStatus', 'data': ['undefined', 'created', 'running', 'paused', 'ready', 'standby', - 'aborting', 'concluded' ] } + 'aborting', 'concluded', 'null' ] } ## # @BlockJobInfo: diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static QemuMutex block_job_mutex; /* BlockJob State Transition Table */ bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, X, E */ - /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0}, - /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 1, 0}, - /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 1}, - /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0}, - /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 1}, - /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0}, - /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 1}, - /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0}, + /* U, C, R, P, Y, S, X, E, N */ + /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0, 0}, + /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 1, 0, 1}, + /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 1, 0}, + /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0, 0}, + /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 1, 0}, + /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0, 0}, + /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 1, 0}, + /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 1}, + /* N: */ [BLOCK_JOB_STATUS_NULL] = {0, 0, 0, 0, 0, 0, 0, 0, 0}, }; bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, X, E */ - [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 0, 0}, - [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0}, - [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0}, - [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0}, - [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0}, + /* U, C, R, P, Y, S, X, E, N */ + [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, + [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, + [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, + [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, + [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0}, }; static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) @@ -XXX,XX +XXX,XX @@ static void block_job_detach_aio_context(void *opaque); void block_job_unref(BlockJob *job) { if (--job->refcnt == 0) { + assert(job->status == BLOCK_JOB_STATUS_NULL); BlockDriverState *bs = blk_bs(job->blk); QLIST_REMOVE(job, job_list); bs->job = NULL; @@ -XXX,XX +XXX,XX @@ void block_job_start(BlockJob *job) bdrv_coroutine_enter(blk_bs(job->blk), job->co); } +static void block_job_decommission(BlockJob *job) +{ + assert(job); + job->completed = true; + job->busy = false; + job->paused = false; + job->deferred_to_main_loop = true; + block_job_state_transition(job, BLOCK_JOB_STATUS_NULL); + block_job_unref(job); +} + static void block_job_conclude(BlockJob *job) { block_job_state_transition(job, BLOCK_JOB_STATUS_CONCLUDED); @@ -XXX,XX +XXX,XX @@ static void block_job_completed_single(BlockJob *job) QLIST_REMOVE(job, txn_list); block_job_txn_unref(job->txn); block_job_conclude(job); - block_job_unref(job); + block_job_decommission(job); } static void block_job_cancel_async(BlockJob *job) @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, block_job_set_speed(job, speed, &local_err); if (local_err) { - block_job_unref(job); + block_job_early_fail(job); error_propagate(errp, local_err); return NULL; } @@ -XXX,XX +XXX,XX @@ void block_job_pause_all(void) void block_job_early_fail(BlockJob *job) { - block_job_unref(job); + assert(job->status == BLOCK_JOB_STATUS_CREATED); + block_job_decommission(job); } void block_job_completed(BlockJob *job, int ret) -- 2.13.6 From: John Snow <jsnow@redhat.com> For jobs that have reached their CONCLUDED state, prior to having their last reference put down (meaning jobs that have completed successfully, unsuccessfully, or have been canceled), allow the user to dismiss the job's lingering status report via block-job-dismiss. This gives management APIs the chance to conclusively determine if a job failed or succeeded, even if the event broadcast was missed. Note: block_job_do_dismiss and block_job_decommission happen to do exactly the same thing, but they're called from different semantic contexts, so both aliases are kept to improve readability. Note 2: Don't worry about the 0x04 flag definition for AUTO_DISMISS, she has a friend coming in a future patch to fill the hole where 0x02 is. Verbs: Dismiss: operates on CONCLUDED jobs only. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 24 +++++++++++++++++++++++- include/block/blockjob.h | 14 ++++++++++++++ blockdev.c | 14 ++++++++++++++ blockjob.c | 26 ++++++++++++++++++++++++-- block/trace-events | 1 + 5 files changed, 76 insertions(+), 3 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 @@ # # @complete: see @block-job-complete # +# @dismiss: see @block-job-dismiss +# # Since: 2.12 ## { 'enum': 'BlockJobVerb', - 'data': ['cancel', 'pause', 'resume', 'set-speed', 'complete' ] } + 'data': ['cancel', 'pause', 'resume', 'set-speed', 'complete', 'dismiss' ] } ## # @BlockJobStatus: @@ -XXX,XX +XXX,XX @@ { 'command': 'block-job-complete', 'data': { 'device': 'str' } } ## +# @block-job-dismiss: +# +# For jobs that have already concluded, remove them from the block-job-query +# list. This command only needs to be run for jobs which were started with +# QEMU 2.12+ job lifetime management semantics. +# +# This command will refuse to operate on any job that has not yet reached +# its terminal state, BLOCK_JOB_STATUS_CONCLUDED. For jobs that make use of +# BLOCK_JOB_READY event, block-job-cancel or block-job-complete will still need +# to be used as appropriate. +# +# @id: The job identifier. +# +# Returns: Nothing on success +# +# Since: 2.12 +## +{ 'command': 'block-job-dismiss', 'data': { 'id': 'str' } } + +## # @BlockdevDiscardOptions: # # Determines how to handle discard requests. diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { /** Current state; See @BlockJobStatus for details. */ BlockJobStatus status; + /** True if this job should automatically dismiss itself */ + bool auto_dismiss; + BlockJobTxn *txn; QLIST_ENTRY(BlockJob) txn_list; } BlockJob; @@ -XXX,XX +XXX,XX @@ typedef enum BlockJobCreateFlags { BLOCK_JOB_DEFAULT = 0x00, /* BlockJob is not QMP-created and should not send QMP events */ BLOCK_JOB_INTERNAL = 0x01, + /* BlockJob requires manual dismiss step */ + BLOCK_JOB_MANUAL_DISMISS = 0x04, } BlockJobCreateFlags; /** @@ -XXX,XX +XXX,XX @@ void block_job_cancel(BlockJob *job); void block_job_complete(BlockJob *job, Error **errp); /** + * block_job_dismiss: + * @job: The job to be dismissed. + * @errp: Error object. + * + * Remove a concluded job from the query list. + */ +void block_job_dismiss(BlockJob **job, Error **errp); + +/** * block_job_query: * @job: The job to get information about. * 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_job_complete(const char *device, Error **errp) aio_context_release(aio_context); } +void qmp_block_job_dismiss(const char *id, Error **errp) +{ + AioContext *aio_context; + BlockJob *job = find_block_job(id, &aio_context, errp); + + if (!job) { + return; + } + + trace_qmp_block_job_dismiss(job); + block_job_dismiss(&job, errp); + aio_context_release(aio_context); +} + void qmp_change_backing_file(const char *device, const char *image_node_name, const char *backing_file, diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 1, 0}, }; static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) @@ -XXX,XX +XXX,XX @@ static void block_job_decommission(BlockJob *job) block_job_unref(job); } +static void block_job_do_dismiss(BlockJob *job) +{ + block_job_decommission(job); +} + static void block_job_conclude(BlockJob *job) { block_job_state_transition(job, BLOCK_JOB_STATUS_CONCLUDED); + if (job->auto_dismiss || !block_job_started(job)) { + block_job_do_dismiss(job); + } } static void block_job_completed_single(BlockJob *job) @@ -XXX,XX +XXX,XX @@ static void block_job_completed_single(BlockJob *job) QLIST_REMOVE(job, txn_list); block_job_txn_unref(job->txn); block_job_conclude(job); - block_job_decommission(job); } static void block_job_cancel_async(BlockJob *job) @@ -XXX,XX +XXX,XX @@ void block_job_complete(BlockJob *job, Error **errp) job->driver->complete(job, errp); } +void block_job_dismiss(BlockJob **jobptr, Error **errp) +{ + BlockJob *job = *jobptr; + /* similarly to _complete, this is QMP-interface only. */ + assert(job->id); + if (block_job_apply_verb(job, BLOCK_JOB_VERB_DISMISS, errp)) { + return; + } + + block_job_do_dismiss(job); + *jobptr = NULL; +} + void block_job_user_pause(BlockJob *job, Error **errp) { if (block_job_apply_verb(job, BLOCK_JOB_VERB_PAUSE, errp)) { @@ -XXX,XX +XXX,XX @@ void block_job_user_resume(BlockJob *job, Error **errp) void block_job_cancel(BlockJob *job) { if (job->status == BLOCK_JOB_STATUS_CONCLUDED) { - return; + block_job_do_dismiss(job); } else if (block_job_started(job)) { block_job_cancel_async(job); block_job_enter(job); @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, job->paused = true; job->pause_count = 1; job->refcnt = 1; + job->auto_dismiss = !(flags & BLOCK_JOB_MANUAL_DISMISS); block_job_state_transition(job, BLOCK_JOB_STATUS_CREATED); aio_timer_init(qemu_get_aio_context(), &job->sleep_timer, QEMU_CLOCK_REALTIME, SCALE_NS, diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ qmp_block_job_cancel(void *job) "job %p" qmp_block_job_pause(void *job) "job %p" qmp_block_job_resume(void *job) "job %p" qmp_block_job_complete(void *job) "job %p" +qmp_block_job_dismiss(void *job) "job %p" qmp_block_stream(void *bs, void *job) "bs %p job %p" # block/file-win32.c -- 2.13.6 From: John Snow <jsnow@redhat.com> Presently, even if a job is canceled post-completion as a result of a failing peer in a transaction, it will still call .commit because nothing has updated or changed its return code. The reason why this does not cause problems currently is because backup's implementation of .commit checks for cancellation itself. I'd like to simplify this contract: (1) Abort is called if the job/transaction fails (2) Commit is called if the job/transaction succeeds To this end: A job's return code, if 0, will be forcibly set as -ECANCELED if that job has already concluded. Remove the now redundant check in the backup job implementation. We need to check for cancellation in both block_job_completed AND block_job_completed_single, because jobs may be cancelled between those two calls; for instance in transactions. This also necessitates an ABORTING -> ABORTING transition to be allowed. The check in block_job_completed could be removed, but there's no point in starting to attempt to succeed a transaction that we know in advance will fail. This does NOT affect mirror jobs that are "canceled" during their synchronous phase. The mirror job itself forcibly sets the canceled property to false prior to ceding control, so such cases will invoke the "commit" callback. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/backup.c | 2 +- blockjob.c | 21 ++++++++++++++++----- block/trace-events | 1 + 3 files changed, 18 insertions(+), 6 deletions(-) diff --git a/block/backup.c b/block/backup.c index XXXXXXX..XXXXXXX 100644 --- a/block/backup.c +++ b/block/backup.c @@ -XXX,XX +XXX,XX @@ static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret) BdrvDirtyBitmap *bm; BlockDriverState *bs = blk_bs(job->common.blk); - if (ret < 0 || block_job_is_cancelled(&job->common)) { + if (ret < 0) { /* Merge the successor back into the parent, delete nothing. */ bm = bdrv_reclaim_dirty_bitmap(bs, job->sync_bitmap, NULL); assert(bm); diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0, 0}, /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 1, 0}, /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0, 0}, - /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 1, 0}, + /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 1, 1, 0}, /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 1}, /* N: */ [BLOCK_JOB_STATUS_NULL] = {0, 0, 0, 0, 0, 0, 0, 0, 0}, }; @@ -XXX,XX +XXX,XX @@ static void block_job_conclude(BlockJob *job) } } +static void block_job_update_rc(BlockJob *job) +{ + if (!job->ret && block_job_is_cancelled(job)) { + job->ret = -ECANCELED; + } + if (job->ret) { + block_job_state_transition(job, BLOCK_JOB_STATUS_ABORTING); + } +} + static void block_job_completed_single(BlockJob *job) { assert(job->completed); - if (job->ret || block_job_is_cancelled(job)) { - block_job_state_transition(job, BLOCK_JOB_STATUS_ABORTING); - } + /* Ensure abort is called for late-transactional failures */ + block_job_update_rc(job); if (!job->ret) { if (job->driver->commit) { @@ -XXX,XX +XXX,XX @@ void block_job_completed(BlockJob *job, int ret) assert(blk_bs(job->blk)->job == job); job->completed = true; job->ret = ret; - if (ret < 0 || block_job_is_cancelled(job)) { + block_job_update_rc(job); + trace_block_job_completed(job, ret, job->ret); + if (job->ret) { block_job_completed_txn_abort(job); } else { block_job_completed_txn_success(job); diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ bdrv_open_common(void *bs, const char *filename, int flags, const char *format_n bdrv_lock_medium(void *bs, bool locked) "bs %p locked %d" # blockjob.c +block_job_completed(void *job, int ret, int jret) "job %p ret %d corrected ret %d" block_job_state_transition(void *job, int ret, const char *legal, const char *s0, const char *s1) "job %p (ret: %d) attempting %s transition (%s-->%s)" block_job_apply_verb(void *job, const char *state, const char *verb, const char *legal) "job %p in state %s; applying verb %s (%s)" -- 2.13.6 From: John Snow <jsnow@redhat.com> The completed_single function is getting a little mucked up with checking to see which callbacks exist, so let's factor them out. Signed-off-by: John Snow <jsnow@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static void block_job_update_rc(BlockJob *job) } } +static void block_job_commit(BlockJob *job) +{ + assert(!job->ret); + if (job->driver->commit) { + job->driver->commit(job); + } +} + +static void block_job_abort(BlockJob *job) +{ + assert(job->ret); + if (job->driver->abort) { + job->driver->abort(job); + } +} + +static void block_job_clean(BlockJob *job) +{ + if (job->driver->clean) { + job->driver->clean(job); + } +} + static void block_job_completed_single(BlockJob *job) { assert(job->completed); @@ -XXX,XX +XXX,XX @@ static void block_job_completed_single(BlockJob *job) block_job_update_rc(job); if (!job->ret) { - if (job->driver->commit) { - job->driver->commit(job); - } + block_job_commit(job); } else { - if (job->driver->abort) { - job->driver->abort(job); - } - } - if (job->driver->clean) { - job->driver->clean(job); + block_job_abort(job); } + block_job_clean(job); if (job->cb) { job->cb(job->opaque, job->ret); -- 2.13.6 From: John Snow <jsnow@redhat.com> Simply apply a function transaction-wide. A few more uses of this in forthcoming patches. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static void block_job_cancel_async(BlockJob *job) job->cancelled = true; } +static void block_job_txn_apply(BlockJobTxn *txn, void fn(BlockJob *)) +{ + AioContext *ctx; + BlockJob *job, *next; + + QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) { + ctx = blk_get_aio_context(job->blk); + aio_context_acquire(ctx); + fn(job); + aio_context_release(ctx); + } +} + static int block_job_finish_sync(BlockJob *job, void (*finish)(BlockJob *, Error **errp), Error **errp) @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_abort(BlockJob *job) static void block_job_completed_txn_success(BlockJob *job) { - AioContext *ctx; BlockJobTxn *txn = job->txn; - BlockJob *other_job, *next; + BlockJob *other_job; /* * Successful completion, see if there are other running jobs in this * txn. @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_success(BlockJob *job) if (!other_job->completed) { return; } - } - /* We are the last completed job, commit the transaction. */ - QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) { - ctx = blk_get_aio_context(other_job->blk); - aio_context_acquire(ctx); assert(other_job->ret == 0); - block_job_completed_single(other_job); - aio_context_release(ctx); } + /* We are the last completed job, commit the transaction. */ + block_job_txn_apply(txn, block_job_completed_single); } /* Assumes the block_job_mutex is held */ -- 2.13.6 From: John Snow <jsnow@redhat.com> Some jobs upon finalization may need to perform some work that can still fail. If these jobs are part of a transaction, it's important that these callbacks fail the entire transaction. We allow for a new callback in addition to commit/abort/clean that allows us the opportunity to have fairly late-breaking failures in the transactional process. The expected flow is: - All jobs in a transaction converge to the PENDING state, added in a forthcoming commit. - Upon being finalized, either automatically or explicitly by the user, jobs prepare to complete. - If any job fails preparation, all jobs call .abort. - Otherwise, they succeed and call .commit. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/blockjob_int.h | 10 ++++++++++ blockjob.c | 30 +++++++++++++++++++++++++++--- 2 files changed, 37 insertions(+), 3 deletions(-) diff --git a/include/block/blockjob_int.h b/include/block/blockjob_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob_int.h +++ b/include/block/blockjob_int.h @@ -XXX,XX +XXX,XX @@ struct BlockJobDriver { void (*complete)(BlockJob *job, Error **errp); /** + * If the callback is not NULL, prepare will be invoked when all the jobs + * belonging to the same transaction complete; or upon this job's completion + * if it is not in a transaction. + * + * This callback will not be invoked if the job has already failed. + * If it fails, abort and then clean will be called. + */ + int (*prepare)(BlockJob *job); + + /** * If the callback is not NULL, it will be invoked when all the jobs * belonging to the same transaction complete; or upon this job's * completion if it is not in a transaction. Skipped if NULL. diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static void block_job_update_rc(BlockJob *job) } } +static int block_job_prepare(BlockJob *job) +{ + if (job->ret == 0 && job->driver->prepare) { + job->ret = job->driver->prepare(job); + } + return job->ret; +} + static void block_job_commit(BlockJob *job) { assert(!job->ret); @@ -XXX,XX +XXX,XX @@ static void block_job_clean(BlockJob *job) } } -static void block_job_completed_single(BlockJob *job) +static int block_job_completed_single(BlockJob *job) { assert(job->completed); @@ -XXX,XX +XXX,XX @@ static void block_job_completed_single(BlockJob *job) QLIST_REMOVE(job, txn_list); block_job_txn_unref(job->txn); block_job_conclude(job); + return 0; } static void block_job_cancel_async(BlockJob *job) @@ -XXX,XX +XXX,XX @@ static void block_job_cancel_async(BlockJob *job) job->cancelled = true; } -static void block_job_txn_apply(BlockJobTxn *txn, void fn(BlockJob *)) +static int block_job_txn_apply(BlockJobTxn *txn, int fn(BlockJob *)) { AioContext *ctx; BlockJob *job, *next; + int rc; QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) { ctx = blk_get_aio_context(job->blk); aio_context_acquire(ctx); - fn(job); + rc = fn(job); aio_context_release(ctx); + if (rc) { + break; + } } + return rc; } static int block_job_finish_sync(BlockJob *job, @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_success(BlockJob *job) { BlockJobTxn *txn = job->txn; BlockJob *other_job; + int rc = 0; + /* * Successful completion, see if there are other running jobs in this * txn. @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_success(BlockJob *job) } assert(other_job->ret == 0); } + + /* Jobs may require some prep-work to complete without failure */ + rc = block_job_txn_apply(txn, block_job_prepare); + if (rc) { + block_job_completed_txn_abort(job); + return; + } + /* We are the last completed job, commit the transaction. */ block_job_txn_apply(txn, block_job_completed_single); } -- 2.13.6 From: John Snow <jsnow@redhat.com> For jobs that are stuck waiting on others in a transaction, it would be nice to know that they are no longer "running" in that sense, but instead are waiting on other jobs in the transaction. Jobs that are "waiting" in this sense cannot be meaningfully altered any longer as they have left their running loop. The only meaningful user verb for jobs in this state is "cancel," which will cancel the whole transaction, too. Transitions: Running -> Waiting: Normal transition. Ready -> Waiting: Normal transition. Waiting -> Aborting: Transactional cancellation. Waiting -> Concluded: Normal transition. Removed Transitions: Running -> Concluded: Jobs must go to WAITING first. Ready -> Concluded: Jobs must go to WAITING first. Verbs: Cancel: Can be applied to WAITING jobs. +---------+ |UNDEFINED| +--+------+ | +--v----+ +---------+CREATED+-----------------+ | +--+----+ | | | | | +--v----+ +------+ | +---------+RUNNING<----->PAUSED| | | +--+-+--+ +------+ | | | | | | | +------------------+ | | | | | | +--v--+ +-------+ | | +---------+READY<------->STANDBY| | | | +--+--+ +-------+ | | | | | | | +--v----+ | | +---------+WAITING<---------------+ | | +--+----+ | | | | +--v-----+ +--v------+ | |ABORTING+--->CONCLUDED| | +--------+ +--+------+ | | | +--v-+ | |NULL<--------------------+ +----+ Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 6 +++++- blockjob.c | 37 ++++++++++++++++++++----------------- 2 files changed, 25 insertions(+), 18 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 @@ # @standby: The job is ready, but paused. This is nearly identical to @paused. # The job may return to @ready or otherwise be canceled. # +# @waiting: The job is waiting for other jobs in the transaction to converge +# to the waiting state. This status will likely not be visible for +# the last job in a transaction. +# # @aborting: The job is in the process of being aborted, and will finish with # an error. The job will afterwards report that it is @concluded. # This status may not be visible to the management process. @@ -XXX,XX +XXX,XX @@ ## { 'enum': 'BlockJobStatus', 'data': ['undefined', 'created', 'running', 'paused', 'ready', 'standby', - 'aborting', 'concluded', 'null' ] } + 'waiting', 'aborting', 'concluded', 'null' ] } ## # @BlockJobInfo: diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static QemuMutex block_job_mutex; /* BlockJob State Transition Table */ bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, X, E, N */ - /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0, 0}, - /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 1, 0, 1}, - /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 1, 0}, - /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0, 0}, - /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 1, 0}, - /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0, 0}, - /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 1, 1, 0}, - /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 1}, - /* N: */ [BLOCK_JOB_STATUS_NULL] = {0, 0, 0, 0, 0, 0, 0, 0, 0}, + /* U, C, R, P, Y, S, W, X, E, N */ + /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0, 0, 0}, + /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 0, 1, 0, 1}, + /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 1, 0, 0}, + /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0, 0, 0}, + /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 1, 0, 0}, + /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0}, + /* W: */ [BLOCK_JOB_STATUS_WAITING] = {0, 0, 0, 0, 0, 0, 0, 1, 1, 0}, + /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 1, 1, 0}, + /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1}, + /* N: */ [BLOCK_JOB_STATUS_NULL] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0}, }; bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, X, E, N */ - [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, - [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, - [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, - [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0}, - [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0}, - [BLOCK_JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 1, 0}, + /* U, C, R, P, Y, S, W, X, E, N */ + [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 1, 0, 0, 0}, + [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 0}, }; static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_success(BlockJob *job) BlockJob *other_job; int rc = 0; + block_job_state_transition(job, BLOCK_JOB_STATUS_WAITING); + /* * Successful completion, see if there are other running jobs in this * txn. -- 2.13.6 From: John Snow <jsnow@redhat.com> For jobs utilizing the new manual workflow, we intend to prohibit them from modifying the block graph until the management layer provides an explicit ACK via block-job-finalize to move the process forward. To distinguish this runstate from "ready" or "waiting," we add a new "pending" event and status. For now, the transition from PENDING to CONCLUDED/ABORTING is automatic, but a future commit will add the explicit block-job-finalize step. Transitions: Waiting -> Pending: Normal transition. Pending -> Concluded: Normal transition. Pending -> Aborting: Late transactional failures and cancellations. Removed Transitions: Waiting -> Concluded: Jobs must go to PENDING first. Verbs: Cancel: Can be applied to a pending job. +---------+ |UNDEFINED| +--+------+ | +--v----+ +---------+CREATED+-----------------+ | +--+----+ | | | | | +--+----+ +------+ | +---------+RUNNING<----->PAUSED| | | +--+-+--+ +------+ | | | | | | | +------------------+ | | | | | | +--v--+ +-------+ | | +---------+READY<------->STANDBY| | | | +--+--+ +-------+ | | | | | | | +--v----+ | | +---------+WAITING<---------------+ | | +--+----+ | | | | | +--v----+ | +---------+PENDING| | | +--+----+ | | | | +--v-----+ +--v------+ | |ABORTING+--->CONCLUDED| | +--------+ +--+------+ | | | +--v-+ | |NULL<--------------------+ +----+ Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 31 +++++++++++++++++++++- include/block/blockjob.h | 5 ++++ blockjob.c | 67 +++++++++++++++++++++++++++++++----------------- 3 files changed, 78 insertions(+), 25 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 @@ # to the waiting state. This status will likely not be visible for # the last job in a transaction. # +# @pending: The job has finished its work, but has finalization steps that it +# needs to make prior to completing. These changes may require +# manual intervention by the management process if manual was set +# to true. These changes may still fail. +# # @aborting: The job is in the process of being aborted, and will finish with # an error. The job will afterwards report that it is @concluded. # This status may not be visible to the management process. @@ -XXX,XX +XXX,XX @@ ## { 'enum': 'BlockJobStatus', 'data': ['undefined', 'created', 'running', 'paused', 'ready', 'standby', - 'waiting', 'aborting', 'concluded', 'null' ] } + 'waiting', 'pending', 'aborting', 'concluded', 'null' ] } ## # @BlockJobInfo: @@ -XXX,XX +XXX,XX @@ 'speed' : 'int' } } ## +# @BLOCK_JOB_PENDING: +# +# Emitted when a block job is awaiting explicit authorization to finalize graph +# changes via @block-job-finalize. If this job is part of a transaction, it will +# not emit this event until the transaction has converged first. +# +# @type: job type +# +# @id: The job identifier. +# +# Since: 2.12 +# +# Example: +# +# <- { "event": "BLOCK_JOB_WAITING", +# "data": { "device": "drive0", "type": "mirror" }, +# "timestamp": { "seconds": 1265044230, "microseconds": 450486 } } +# +## +{ 'event': 'BLOCK_JOB_PENDING', + 'data': { 'type' : 'BlockJobType', + 'id' : 'str' } } + +## # @PreallocMode: # # Preallocation mode of QEMU image file diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { /** Current state; See @BlockJobStatus for details. */ BlockJobStatus status; + /** True if this job should automatically finalize itself */ + bool auto_finalize; + /** True if this job should automatically dismiss itself */ bool auto_dismiss; @@ -XXX,XX +XXX,XX @@ typedef enum BlockJobCreateFlags { BLOCK_JOB_DEFAULT = 0x00, /* BlockJob is not QMP-created and should not send QMP events */ BLOCK_JOB_INTERNAL = 0x01, + /* BlockJob requires manual finalize step */ + BLOCK_JOB_MANUAL_FINALIZE = 0x02, /* BlockJob requires manual dismiss step */ BLOCK_JOB_MANUAL_DISMISS = 0x04, } BlockJobCreateFlags; diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static QemuMutex block_job_mutex; /* BlockJob State Transition Table */ bool BlockJobSTT[BLOCK_JOB_STATUS__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, W, X, E, N */ - /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0, 0, 0}, - /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 0, 1, 0, 1}, - /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 1, 0, 0}, - /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0, 0, 0}, - /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 1, 0, 0}, - /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0}, - /* W: */ [BLOCK_JOB_STATUS_WAITING] = {0, 0, 0, 0, 0, 0, 0, 1, 1, 0}, - /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 1, 1, 0}, - /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1}, - /* N: */ [BLOCK_JOB_STATUS_NULL] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0}, + /* U, C, R, P, Y, S, W, D, X, E, N */ + /* U: */ [BLOCK_JOB_STATUS_UNDEFINED] = {0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0}, + /* C: */ [BLOCK_JOB_STATUS_CREATED] = {0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1}, + /* R: */ [BLOCK_JOB_STATUS_RUNNING] = {0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0}, + /* P: */ [BLOCK_JOB_STATUS_PAUSED] = {0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0}, + /* Y: */ [BLOCK_JOB_STATUS_READY] = {0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0}, + /* S: */ [BLOCK_JOB_STATUS_STANDBY] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0}, + /* W: */ [BLOCK_JOB_STATUS_WAITING] = {0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0}, + /* D: */ [BLOCK_JOB_STATUS_PENDING] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0}, + /* X: */ [BLOCK_JOB_STATUS_ABORTING] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0}, + /* E: */ [BLOCK_JOB_STATUS_CONCLUDED] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1}, + /* N: */ [BLOCK_JOB_STATUS_NULL] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}, }; bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { - /* U, C, R, P, Y, S, W, X, E, N */ - [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 1, 0, 0, 0}, - [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0}, - [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0}, - [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0}, - [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0}, - [BLOCK_JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 0}, + /* U, C, R, P, Y, S, W, D, X, E, N */ + [BLOCK_JOB_VERB_CANCEL] = {0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0}, + [BLOCK_JOB_VERB_PAUSE] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0}, }; static void block_job_state_transition(BlockJob *job, BlockJobStatus s1) @@ -XXX,XX +XXX,XX @@ static void __attribute__((__constructor__)) block_job_init(void) static void block_job_event_cancelled(BlockJob *job); static void block_job_event_completed(BlockJob *job, const char *msg); +static int block_job_event_pending(BlockJob *job); static void block_job_enter_cond(BlockJob *job, bool(*fn)(BlockJob *job)); /* Transactional group of block jobs */ @@ -XXX,XX +XXX,XX @@ static void block_job_cancel_async(BlockJob *job) job->cancelled = true; } -static int block_job_txn_apply(BlockJobTxn *txn, int fn(BlockJob *)) +static int block_job_txn_apply(BlockJobTxn *txn, int fn(BlockJob *), bool lock) { AioContext *ctx; BlockJob *job, *next; int rc; QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) { - ctx = blk_get_aio_context(job->blk); - aio_context_acquire(ctx); + if (lock) { + ctx = blk_get_aio_context(job->blk); + aio_context_acquire(ctx); + } rc = fn(job); - aio_context_release(ctx); + if (lock) { + aio_context_release(ctx); + } if (rc) { break; } @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_success(BlockJob *job) } /* Jobs may require some prep-work to complete without failure */ - rc = block_job_txn_apply(txn, block_job_prepare); + rc = block_job_txn_apply(txn, block_job_prepare, true); if (rc) { block_job_completed_txn_abort(job); return; } /* We are the last completed job, commit the transaction. */ - block_job_txn_apply(txn, block_job_completed_single); + block_job_txn_apply(txn, block_job_event_pending, false); + block_job_txn_apply(txn, block_job_completed_single, true); } /* Assumes the block_job_mutex is held */ @@ -XXX,XX +XXX,XX @@ static void block_job_event_completed(BlockJob *job, const char *msg) &error_abort); } +static int block_job_event_pending(BlockJob *job) +{ + block_job_state_transition(job, BLOCK_JOB_STATUS_PENDING); + if (!job->auto_finalize && !block_job_is_internal(job)) { + qapi_event_send_block_job_pending(job->driver->job_type, + job->id, + &error_abort); + } + return 0; +} + /* * API for block job drivers and the block layer. These functions are * declared in blockjob_int.h. @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, job->paused = true; job->pause_count = 1; job->refcnt = 1; + job->auto_finalize = !(flags & BLOCK_JOB_MANUAL_FINALIZE); job->auto_dismiss = !(flags & BLOCK_JOB_MANUAL_DISMISS); block_job_state_transition(job, BLOCK_JOB_STATUS_CREATED); aio_timer_init(qemu_get_aio_context(), &job->sleep_timer, -- 2.13.6 From: John Snow <jsnow@redhat.com> Instead of automatically transitioning from PENDING to CONCLUDED, gate the .prepare() and .commit() phases behind an explicit acknowledgement provided by the QMP monitor if auto_finalize = false has been requested. This allows us to perform graph changes in prepare and/or commit so that graph changes do not occur autonomously without knowledge of the controlling management layer. Transactions that have reached the "PENDING" state together can all be moved to invoke their finalization methods by issuing block_job_finalize to any one job in the transaction. Jobs in a transaction with mixed job->auto_finalize settings will all remain stuck in the "PENDING" state, as if the entire transaction was specified with auto_finalize = false. Jobs that specified auto_finalize = true, however, will still not emit the PENDING event. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 23 ++++++++++++++++++- include/block/blockjob.h | 17 ++++++++++++++ blockdev.c | 14 +++++++++++ blockjob.c | 60 +++++++++++++++++++++++++++++++++++------------- block/trace-events | 1 + 5 files changed, 98 insertions(+), 17 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 @@ # # @dismiss: see @block-job-dismiss # +# @finalize: see @block-job-finalize +# # Since: 2.12 ## { 'enum': 'BlockJobVerb', - 'data': ['cancel', 'pause', 'resume', 'set-speed', 'complete', 'dismiss' ] } + 'data': ['cancel', 'pause', 'resume', 'set-speed', 'complete', 'dismiss', + 'finalize' ] } ## # @BlockJobStatus: @@ -XXX,XX +XXX,XX @@ { 'command': 'block-job-dismiss', 'data': { 'id': 'str' } } ## +# @block-job-finalize: +# +# Once a job that has manual=true reaches the pending state, it can be +# instructed to finalize any graph changes and do any necessary cleanup +# via this command. +# For jobs in a transaction, instructing one job to finalize will force +# ALL jobs in the transaction to finalize, so it is only necessary to instruct +# a single member job to finalize. +# +# @id: The job identifier. +# +# Returns: Nothing on success +# +# Since: 2.12 +## +{ 'command': 'block-job-finalize', 'data': { 'id': 'str' } } + +## # @BlockdevDiscardOptions: # # Determines how to handle discard requests. diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ void block_job_cancel(BlockJob *job); */ void block_job_complete(BlockJob *job, Error **errp); + +/** + * block_job_finalize: + * @job: The job to fully commit and finish. + * @errp: Error object. + * + * For jobs that have finished their work and are pending + * awaiting explicit acknowledgement to commit their work, + * This will commit that work. + * + * FIXME: Make the below statement universally true: + * For jobs that support the manual workflow mode, all graph + * changes that occur as a result will occur after this command + * and before a successful reply. + */ +void block_job_finalize(BlockJob *job, Error **errp); + /** * block_job_dismiss: * @job: The job to be dismissed. 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_job_complete(const char *device, Error **errp) aio_context_release(aio_context); } +void qmp_block_job_finalize(const char *id, Error **errp) +{ + AioContext *aio_context; + BlockJob *job = find_block_job(id, &aio_context, errp); + + if (!job) { + return; + } + + trace_qmp_block_job_finalize(job); + block_job_finalize(job, errp); + aio_context_release(aio_context); +} + void qmp_block_job_dismiss(const char *id, Error **errp) { AioContext *aio_context; diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ bool BlockJobVerbTable[BLOCK_JOB_VERB__MAX][BLOCK_JOB_STATUS__MAX] = { [BLOCK_JOB_VERB_RESUME] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0}, [BLOCK_JOB_VERB_SET_SPEED] = {0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0}, [BLOCK_JOB_VERB_COMPLETE] = {0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0}, + [BLOCK_JOB_VERB_FINALIZE] = {0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0}, [BLOCK_JOB_VERB_DISMISS] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0}, }; @@ -XXX,XX +XXX,XX @@ static void block_job_clean(BlockJob *job) } } -static int block_job_completed_single(BlockJob *job) +static int block_job_finalize_single(BlockJob *job) { assert(job->completed); @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_abort(BlockJob *job) assert(other_job->cancelled); block_job_finish_sync(other_job, NULL, NULL); } - block_job_completed_single(other_job); + block_job_finalize_single(other_job); aio_context_release(ctx); } block_job_txn_unref(txn); } +static int block_job_needs_finalize(BlockJob *job) +{ + return !job->auto_finalize; +} + +static void block_job_do_finalize(BlockJob *job) +{ + int rc; + assert(job && job->txn); + + /* prepare the transaction to complete */ + rc = block_job_txn_apply(job->txn, block_job_prepare, true); + if (rc) { + block_job_completed_txn_abort(job); + } else { + block_job_txn_apply(job->txn, block_job_finalize_single, true); + } +} + static void block_job_completed_txn_success(BlockJob *job) { BlockJobTxn *txn = job->txn; BlockJob *other_job; - int rc = 0; block_job_state_transition(job, BLOCK_JOB_STATUS_WAITING); @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_success(BlockJob *job) assert(other_job->ret == 0); } - /* Jobs may require some prep-work to complete without failure */ - rc = block_job_txn_apply(txn, block_job_prepare, true); - if (rc) { - block_job_completed_txn_abort(job); - return; - } - - /* We are the last completed job, commit the transaction. */ block_job_txn_apply(txn, block_job_event_pending, false); - block_job_txn_apply(txn, block_job_completed_single, true); + + /* If no jobs need manual finalization, automatically do so */ + if (block_job_txn_apply(txn, block_job_needs_finalize, false) == 0) { + block_job_do_finalize(job); + } } /* Assumes the block_job_mutex is held */ @@ -XXX,XX +XXX,XX @@ void block_job_complete(BlockJob *job, Error **errp) job->driver->complete(job, errp); } +void block_job_finalize(BlockJob *job, Error **errp) +{ + assert(job && job->id && job->txn); + if (block_job_apply_verb(job, BLOCK_JOB_VERB_FINALIZE, errp)) { + return; + } + block_job_do_finalize(job); +} + void block_job_dismiss(BlockJob **jobptr, Error **errp) { BlockJob *job = *jobptr; @@ -XXX,XX +XXX,XX @@ void block_job_cancel(BlockJob *job) { if (job->status == BLOCK_JOB_STATUS_CONCLUDED) { block_job_do_dismiss(job); - } else if (block_job_started(job)) { - block_job_cancel_async(job); - block_job_enter(job); - } else { + return; + } + block_job_cancel_async(job); + if (!block_job_started(job)) { block_job_completed(job, -ECANCELED); + } else if (job->deferred_to_main_loop) { + block_job_completed_txn_abort(job); + } else { + block_job_enter(job); } } diff --git a/block/trace-events b/block/trace-events index XXXXXXX..XXXXXXX 100644 --- a/block/trace-events +++ b/block/trace-events @@ -XXX,XX +XXX,XX @@ qmp_block_job_cancel(void *job) "job %p" qmp_block_job_pause(void *job) "job %p" qmp_block_job_resume(void *job) "job %p" qmp_block_job_complete(void *job) "job %p" +qmp_block_job_finalize(void *job) "job %p" qmp_block_job_dismiss(void *job) "job %p" qmp_block_stream(void *bs, void *job) "bs %p job %p" -- 2.13.6 From: John Snow <jsnow@redhat.com> Expose the "manual" property via QAPI for the backup-related jobs. As of this commit, this allows the management API to request the "concluded" and "dismiss" semantics for backup jobs. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 48 ++++++++++++++++++++++++++++++++++++++-------- blockdev.c | 31 +++++++++++++++++++++++++++--- blockjob.c | 2 ++ tests/qemu-iotests/109.out | 24 +++++++++++------------ 4 files changed, 82 insertions(+), 23 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 @@ # # @status: Current job state/status (since 2.12) # +# @auto-finalize: Job will finalize itself when PENDING, moving to +# the CONCLUDED state. (since 2.12) +# +# @auto-dismiss: Job will dismiss itself when CONCLUDED, moving to the NULL +# state and disappearing from the query list. (since 2.12) +# # Since: 1.1 ## { 'struct': 'BlockJobInfo', 'data': {'type': 'str', 'device': 'str', 'len': 'int', 'offset': 'int', 'busy': 'bool', 'paused': 'bool', 'speed': 'int', 'io-status': 'BlockDeviceIoStatus', 'ready': 'bool', - 'status': 'BlockJobStatus' } } + 'status': 'BlockJobStatus', + 'auto-finalize': 'bool', 'auto-dismiss': 'bool' } } ## # @query-block-jobs: @@ -XXX,XX +XXX,XX @@ # default 'report' (no limitations, since this applies to # a different block device than @device). # +# @auto-finalize: When false, this job will wait in a PENDING state after it has +# finished its work, waiting for @block-job-finalize. +# When true, this job will automatically perform its abort or +# commit actions. +# Defaults to true. (Since 2.12) +# +# @auto-dismiss: When false, this job will wait in a CONCLUDED state after it +# has completed ceased all work, and wait for @block-job-dismiss. +# When true, this job will automatically disappear from the query +# list without user intervention. +# Defaults to true. (Since 2.12) +# # Note: @on-source-error and @on-target-error only affect background # I/O. If an error occurs during a guest write request, the device's # rerror/werror actions will be used. @@ -XXX,XX +XXX,XX @@ ## { 'struct': 'DriveBackup', 'data': { '*job-id': 'str', 'device': 'str', 'target': 'str', - '*format': 'str', 'sync': 'MirrorSyncMode', '*mode': 'NewImageMode', - '*speed': 'int', '*bitmap': 'str', '*compress': 'bool', + '*format': 'str', 'sync': 'MirrorSyncMode', + '*mode': 'NewImageMode', '*speed': 'int', + '*bitmap': 'str', '*compress': 'bool', '*on-source-error': 'BlockdevOnError', - '*on-target-error': 'BlockdevOnError' } } + '*on-target-error': 'BlockdevOnError', + '*auto-finalize': 'bool', '*auto-dismiss': 'bool' } } ## # @BlockdevBackup: @@ -XXX,XX +XXX,XX @@ # default 'report' (no limitations, since this applies to # a different block device than @device). # +# @auto-finalize: When false, this job will wait in a PENDING state after it has +# finished its work, waiting for @block-job-finalize. +# When true, this job will automatically perform its abort or +# commit actions. +# Defaults to true. (Since 2.12) +# +# @auto-dismiss: When false, this job will wait in a CONCLUDED state after it +# has completed ceased all work, and wait for @block-job-dismiss. +# When true, this job will automatically disappear from the query +# list without user intervention. +# Defaults to true. (Since 2.12) +# # Note: @on-source-error and @on-target-error only affect background # I/O. If an error occurs during a guest write request, the device's # rerror/werror actions will be used. @@ -XXX,XX +XXX,XX @@ ## { 'struct': 'BlockdevBackup', 'data': { '*job-id': 'str', 'device': 'str', 'target': 'str', - 'sync': 'MirrorSyncMode', - '*speed': 'int', - '*compress': 'bool', + 'sync': 'MirrorSyncMode', '*speed': 'int', '*compress': 'bool', '*on-source-error': 'BlockdevOnError', - '*on-target-error': 'BlockdevOnError' } } + '*on-target-error': 'BlockdevOnError', + '*auto-finalize': 'bool', '*auto-dismiss': 'bool' } } ## # @blockdev-snapshot-sync: diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn, AioContext *aio_context; QDict *options = NULL; Error *local_err = NULL; - int flags; + int flags, job_flags = BLOCK_JOB_DEFAULT; int64_t size; bool set_backing_hd = false; @@ -XXX,XX +XXX,XX @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn, if (!backup->has_job_id) { backup->job_id = NULL; } + if (!backup->has_auto_finalize) { + backup->auto_finalize = true; + } + if (!backup->has_auto_dismiss) { + backup->auto_dismiss = true; + } if (!backup->has_compress) { backup->compress = false; } @@ -XXX,XX +XXX,XX @@ static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn, goto out; } } + if (!backup->auto_finalize) { + job_flags |= BLOCK_JOB_MANUAL_FINALIZE; + } + if (!backup->auto_dismiss) { + job_flags |= BLOCK_JOB_MANUAL_DISMISS; + } job = backup_job_create(backup->job_id, bs, target_bs, backup->speed, backup->sync, bmap, backup->compress, backup->on_source_error, backup->on_target_error, - BLOCK_JOB_DEFAULT, NULL, NULL, txn, &local_err); + job_flags, NULL, NULL, txn, &local_err); bdrv_unref(target_bs); if (local_err != NULL) { error_propagate(errp, local_err); @@ -XXX,XX +XXX,XX @@ BlockJob *do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn, Error *local_err = NULL; AioContext *aio_context; BlockJob *job = NULL; + int job_flags = BLOCK_JOB_DEFAULT; if (!backup->has_speed) { backup->speed = 0; @@ -XXX,XX +XXX,XX @@ BlockJob *do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn, if (!backup->has_job_id) { backup->job_id = NULL; } + if (!backup->has_auto_finalize) { + backup->auto_finalize = true; + } + if (!backup->has_auto_dismiss) { + backup->auto_dismiss = true; + } if (!backup->has_compress) { backup->compress = false; } @@ -XXX,XX +XXX,XX @@ BlockJob *do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn, goto out; } } + if (!backup->auto_finalize) { + job_flags |= BLOCK_JOB_MANUAL_FINALIZE; + } + if (!backup->auto_dismiss) { + job_flags |= BLOCK_JOB_MANUAL_DISMISS; + } job = backup_job_create(backup->job_id, bs, target_bs, backup->speed, backup->sync, NULL, backup->compress, backup->on_source_error, backup->on_target_error, - BLOCK_JOB_DEFAULT, NULL, NULL, txn, &local_err); + job_flags, NULL, NULL, txn, &local_err); if (local_err != NULL) { error_propagate(errp, local_err); } diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp) info->io_status = job->iostatus; info->ready = job->ready; info->status = job->status; + info->auto_finalize = job->auto_finalize; + info->auto_dismiss = job->auto_dismiss; return info; } diff --git a/tests/qemu-iotests/109.out b/tests/qemu-iotests/109.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/109.out +++ b/tests/qemu-iotests/109.out @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 1024, "offset": 1024, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 1024, "offset": 1024, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 197120, "offset": 197120, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 197120, "offset": 197120, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 197120, "offset": 197120, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 197120, "offset": 197120, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 327680, "offset": 327680, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 327680, "offset": 327680, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 1024, "offset": 1024, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 1024, "offset": 1024, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 1024, "offset": 1024, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 65536, "offset": 65536, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 65536, "offset": 65536, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 65536, "offset": 65536, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2560, "offset": 2560, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 2560, "offset": 2560, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2560, "offset": 2560, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 2560, "offset": 2560, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2560, "offset": 2560, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 31457280, "offset": 31457280, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 31457280, "offset": 31457280, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 31457280, "offset": 31457280, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 31457280, "offset": 31457280, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 327680, "offset": 327680, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 327680, "offset": 327680, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 327680, "offset": 327680, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ read 65536/65536 bytes at offset 0 {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 2048, "offset": 2048, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 2048, "offset": 2048, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 2048, "offset": 2048, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 2048, "offset": 2048, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ Automatically detecting the format is dangerous for raw images, write operations Specify the 'raw' format explicitly to remove the restrictions. {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 512, "offset": 512, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 512, "offset": 512, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} @@ -XXX,XX +XXX,XX @@ Images are identical. {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_READY", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} -{"return": [{"io-status": "ok", "device": "src", "busy": false, "len": 512, "offset": 512, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} +{"return": [{"auto-finalize": true, "io-status": "ok", "device": "src", "auto-dismiss": true, "busy": false, "len": 512, "offset": 512, "status": "ready", "paused": false, "speed": 0, "ready": true, "type": "mirror"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "BLOCK_JOB_COMPLETED", "data": {"device": "src", "len": 512, "offset": 512, "speed": 0, "type": "mirror"}} -- 2.13.6 From: John Snow <jsnow@redhat.com> Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/056 | 187 +++++++++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/056.out | 4 +- 2 files changed, 189 insertions(+), 2 deletions(-) diff --git a/tests/qemu-iotests/056 b/tests/qemu-iotests/056 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/056 +++ b/tests/qemu-iotests/056 @@ -XXX,XX +XXX,XX @@ backing_img = os.path.join(iotests.test_dir, 'backing.img') test_img = os.path.join(iotests.test_dir, 'test.img') target_img = os.path.join(iotests.test_dir, 'target.img') +def img_create(img, fmt=iotests.imgfmt, size='64M', **kwargs): + fullname = os.path.join(iotests.test_dir, '%s.%s' % (img, fmt)) + optargs = [] + for k,v in kwargs.iteritems(): + optargs = optargs + ['-o', '%s=%s' % (k,v)] + args = ['create', '-f', fmt] + optargs + [fullname, size] + iotests.qemu_img(*args) + return fullname + +def try_remove(img): + try: + os.remove(img) + except OSError: + pass + +def io_write_patterns(img, patterns): + for pattern in patterns: + iotests.qemu_io('-c', 'write -P%s %s %s' % pattern, img) + + class TestSyncModesNoneAndTop(iotests.QMPTestCase): image_len = 64 * 1024 * 1024 # MB @@ -XXX,XX +XXX,XX @@ class TestBeforeWriteNotifier(iotests.QMPTestCase): event = self.cancel_and_wait() self.assert_qmp(event, 'data/type', 'backup') +class BackupTest(iotests.QMPTestCase): + def setUp(self): + self.vm = iotests.VM() + self.test_img = img_create('test') + self.dest_img = img_create('dest') + self.vm.add_drive(self.test_img) + self.vm.launch() + + def tearDown(self): + self.vm.shutdown() + try_remove(self.test_img) + try_remove(self.dest_img) + + def hmp_io_writes(self, drive, patterns): + for pattern in patterns: + self.vm.hmp_qemu_io(drive, 'write -P%s %s %s' % pattern) + self.vm.hmp_qemu_io(drive, 'flush') + + def qmp_backup_and_wait(self, cmd='drive-backup', serror=None, + aerror=None, **kwargs): + if not self.qmp_backup(cmd, serror, **kwargs): + return False + return self.qmp_backup_wait(kwargs['device'], aerror) + + def qmp_backup(self, cmd='drive-backup', + error=None, **kwargs): + self.assertTrue('device' in kwargs) + res = self.vm.qmp(cmd, **kwargs) + if error: + self.assert_qmp(res, 'error/desc', error) + return False + self.assert_qmp(res, 'return', {}) + return True + + def qmp_backup_wait(self, device, error=None): + event = self.vm.event_wait(name="BLOCK_JOB_COMPLETED", + match={'data': {'device': device}}) + self.assertNotEqual(event, None) + try: + failure = self.dictpath(event, 'data/error') + except AssertionError: + # Backup succeeded. + self.assert_qmp(event, 'data/offset', event['data']['len']) + return True + else: + # Failure. + self.assert_qmp(event, 'data/error', qerror) + return False + + def test_dismiss_false(self): + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + self.qmp_backup_and_wait(device='drive0', format=iotests.imgfmt, + sync='full', target=self.dest_img, + auto_dismiss=True) + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + + def test_dismiss_true(self): + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + self.qmp_backup_and_wait(device='drive0', format=iotests.imgfmt, + sync='full', target=self.dest_img, + auto_dismiss=False) + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return[0]/status', 'concluded') + res = self.vm.qmp('block-job-dismiss', id='drive0') + self.assert_qmp(res, 'return', {}) + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + + def test_dismiss_bad_id(self): + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + res = self.vm.qmp('block-job-dismiss', id='foobar') + self.assert_qmp(res, 'error/class', 'DeviceNotActive') + + def test_dismiss_collision(self): + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + self.qmp_backup_and_wait(device='drive0', format=iotests.imgfmt, + sync='full', target=self.dest_img, + auto_dismiss=False) + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return[0]/status', 'concluded') + # Leave zombie job un-dismissed, observe a failure: + res = self.qmp_backup_and_wait(serror='Need a root block node', + device='drive0', format=iotests.imgfmt, + sync='full', target=self.dest_img, + auto_dismiss=False) + self.assertEqual(res, False) + # OK, dismiss the zombie. + res = self.vm.qmp('block-job-dismiss', id='drive0') + self.assert_qmp(res, 'return', {}) + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + # Ensure it's really gone. + self.qmp_backup_and_wait(device='drive0', format=iotests.imgfmt, + sync='full', target=self.dest_img, + auto_dismiss=False) + + def dismissal_failure(self, dismissal_opt): + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + # Give blkdebug something to chew on + self.hmp_io_writes('drive0', + (('0x9a', 0, 512), + ('0x55', '8M', '352k'), + ('0x78', '15872k', '1M'))) + # Add destination node via blkdebug + res = self.vm.qmp('blockdev-add', + node_name='target0', + driver=iotests.imgfmt, + file={ + 'driver': 'blkdebug', + 'image': { + 'driver': 'file', + 'filename': self.dest_img + }, + 'inject-error': [{ + 'event': 'write_aio', + 'errno': 5, + 'immediately': False, + 'once': True + }], + }) + self.assert_qmp(res, 'return', {}) + + res = self.qmp_backup(cmd='blockdev-backup', + device='drive0', target='target0', + on_target_error='stop', + sync='full', + auto_dismiss=dismissal_opt) + self.assertTrue(res) + event = self.vm.event_wait(name="BLOCK_JOB_ERROR", + match={'data': {'device': 'drive0'}}) + self.assertNotEqual(event, None) + # OK, job should be wedged + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return[0]/status', 'paused') + res = self.vm.qmp('block-job-dismiss', id='drive0') + self.assert_qmp(res, 'error/desc', + "Job 'drive0' in state 'paused' cannot accept" + " command verb 'dismiss'") + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return[0]/status', 'paused') + # OK, unstick job and move forward. + res = self.vm.qmp('block-job-resume', device='drive0') + self.assert_qmp(res, 'return', {}) + # And now we need to wait for it to conclude; + res = self.qmp_backup_wait(device='drive0') + self.assertTrue(res) + if not dismissal_opt: + # Job should now be languishing: + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return[0]/status', 'concluded') + res = self.vm.qmp('block-job-dismiss', id='drive0') + self.assert_qmp(res, 'return', {}) + res = self.vm.qmp('query-block-jobs') + self.assert_qmp(res, 'return', []) + + def test_dismiss_premature(self): + self.dismissal_failure(False) + + def test_dismiss_erroneous(self): + self.dismissal_failure(True) + if __name__ == '__main__': iotests.main(supported_fmts=['qcow2', 'qed']) diff --git a/tests/qemu-iotests/056.out b/tests/qemu-iotests/056.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/056.out +++ b/tests/qemu-iotests/056.out @@ -XXX,XX +XXX,XX @@ -... +......... ---------------------------------------------------------------------- -Ran 3 tests +Ran 9 tests OK -- 2.13.6 From: John Snow <jsnow@redhat.com> Whatever the state a blockjob is in, it should be able to be canceled by the block layer. Signed-off-by: John Snow <jsnow@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/test-blockjob.c | 233 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 229 insertions(+), 4 deletions(-) diff --git a/tests/test-blockjob.c b/tests/test-blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-blockjob.c +++ b/tests/test-blockjob.c @@ -XXX,XX +XXX,XX @@ static void block_job_cb(void *opaque, int ret) { } -static BlockJob *do_test_id(BlockBackend *blk, const char *id, - bool should_succeed) +static BlockJob *mk_job(BlockBackend *blk, const char *id, + const BlockJobDriver *drv, bool should_succeed, + int flags) { BlockJob *job; Error *errp = NULL; - job = block_job_create(id, &test_block_job_driver, NULL, blk_bs(blk), - 0, BLK_PERM_ALL, 0, BLOCK_JOB_DEFAULT, block_job_cb, + job = block_job_create(id, drv, NULL, blk_bs(blk), + 0, BLK_PERM_ALL, 0, flags, block_job_cb, NULL, &errp); if (should_succeed) { g_assert_null(errp); @@ -XXX,XX +XXX,XX @@ static BlockJob *do_test_id(BlockBackend *blk, const char *id, return job; } +static BlockJob *do_test_id(BlockBackend *blk, const char *id, + bool should_succeed) +{ + return mk_job(blk, id, &test_block_job_driver, + should_succeed, BLOCK_JOB_DEFAULT); +} + /* This creates a BlockBackend (optionally with a name) with a * BlockDriverState inserted. */ static BlockBackend *create_blk(const char *name) @@ -XXX,XX +XXX,XX @@ static void test_job_ids(void) destroy_blk(blk[2]); } +typedef struct CancelJob { + BlockJob common; + BlockBackend *blk; + bool should_converge; + bool should_complete; + bool completed; +} CancelJob; + +static void cancel_job_completed(BlockJob *job, void *opaque) +{ + CancelJob *s = opaque; + s->completed = true; + block_job_completed(job, 0); +} + +static void cancel_job_complete(BlockJob *job, Error **errp) +{ + CancelJob *s = container_of(job, CancelJob, common); + s->should_complete = true; +} + +static void coroutine_fn cancel_job_start(void *opaque) +{ + CancelJob *s = opaque; + + while (!s->should_complete) { + if (block_job_is_cancelled(&s->common)) { + goto defer; + } + + if (!s->common.ready && s->should_converge) { + block_job_event_ready(&s->common); + } + + block_job_sleep_ns(&s->common, 100000); + } + + defer: + block_job_defer_to_main_loop(&s->common, cancel_job_completed, s); +} + +static const BlockJobDriver test_cancel_driver = { + .instance_size = sizeof(CancelJob), + .start = cancel_job_start, + .complete = cancel_job_complete, +}; + +static CancelJob *create_common(BlockJob **pjob) +{ + BlockBackend *blk; + BlockJob *job; + CancelJob *s; + + blk = create_blk(NULL); + job = mk_job(blk, "Steve", &test_cancel_driver, true, + BLOCK_JOB_MANUAL_FINALIZE | BLOCK_JOB_MANUAL_DISMISS); + block_job_ref(job); + assert(job->status == BLOCK_JOB_STATUS_CREATED); + s = container_of(job, CancelJob, common); + s->blk = blk; + + *pjob = job; + return s; +} + +static void cancel_common(CancelJob *s) +{ + BlockJob *job = &s->common; + BlockBackend *blk = s->blk; + BlockJobStatus sts = job->status; + + block_job_cancel_sync(job); + if ((sts != BLOCK_JOB_STATUS_CREATED) && + (sts != BLOCK_JOB_STATUS_CONCLUDED)) { + BlockJob *dummy = job; + block_job_dismiss(&dummy, &error_abort); + } + assert(job->status == BLOCK_JOB_STATUS_NULL); + block_job_unref(job); + destroy_blk(blk); +} + +static void test_cancel_created(void) +{ + BlockJob *job; + CancelJob *s; + + s = create_common(&job); + cancel_common(s); +} + +static void test_cancel_running(void) +{ + BlockJob *job; + CancelJob *s; + + s = create_common(&job); + + block_job_start(job); + assert(job->status == BLOCK_JOB_STATUS_RUNNING); + + cancel_common(s); +} + +static void test_cancel_paused(void) +{ + BlockJob *job; + CancelJob *s; + + s = create_common(&job); + + block_job_start(job); + assert(job->status == BLOCK_JOB_STATUS_RUNNING); + + block_job_user_pause(job, &error_abort); + block_job_enter(job); + assert(job->status == BLOCK_JOB_STATUS_PAUSED); + + cancel_common(s); +} + +static void test_cancel_ready(void) +{ + BlockJob *job; + CancelJob *s; + + s = create_common(&job); + + block_job_start(job); + assert(job->status == BLOCK_JOB_STATUS_RUNNING); + + s->should_converge = true; + block_job_enter(job); + assert(job->status == BLOCK_JOB_STATUS_READY); + + cancel_common(s); +} + +static void test_cancel_standby(void) +{ + BlockJob *job; + CancelJob *s; + + s = create_common(&job); + + block_job_start(job); + assert(job->status == BLOCK_JOB_STATUS_RUNNING); + + s->should_converge = true; + block_job_enter(job); + assert(job->status == BLOCK_JOB_STATUS_READY); + + block_job_user_pause(job, &error_abort); + block_job_enter(job); + assert(job->status == BLOCK_JOB_STATUS_STANDBY); + + cancel_common(s); +} + +static void test_cancel_pending(void) +{ + BlockJob *job; + CancelJob *s; + + s = create_common(&job); + + block_job_start(job); + assert(job->status == BLOCK_JOB_STATUS_RUNNING); + + s->should_converge = true; + block_job_enter(job); + assert(job->status == BLOCK_JOB_STATUS_READY); + + block_job_complete(job, &error_abort); + block_job_enter(job); + while (!s->completed) { + aio_poll(qemu_get_aio_context(), true); + } + assert(job->status == BLOCK_JOB_STATUS_PENDING); + + cancel_common(s); +} + +static void test_cancel_concluded(void) +{ + BlockJob *job; + CancelJob *s; + + s = create_common(&job); + + block_job_start(job); + assert(job->status == BLOCK_JOB_STATUS_RUNNING); + + s->should_converge = true; + block_job_enter(job); + assert(job->status == BLOCK_JOB_STATUS_READY); + + block_job_complete(job, &error_abort); + block_job_enter(job); + while (!s->completed) { + aio_poll(qemu_get_aio_context(), true); + } + assert(job->status == BLOCK_JOB_STATUS_PENDING); + + block_job_finalize(job, &error_abort); + assert(job->status == BLOCK_JOB_STATUS_CONCLUDED); + + cancel_common(s); +} + int main(int argc, char **argv) { qemu_init_main_loop(&error_abort); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_init(&argc, &argv, NULL); g_test_add_func("/blockjob/ids", test_job_ids); + g_test_add_func("/blockjob/cancel/created", test_cancel_created); + g_test_add_func("/blockjob/cancel/running", test_cancel_running); + g_test_add_func("/blockjob/cancel/paused", test_cancel_paused); + g_test_add_func("/blockjob/cancel/ready", test_cancel_ready); + g_test_add_func("/blockjob/cancel/standby", test_cancel_standby); + g_test_add_func("/blockjob/cancel/pending", test_cancel_pending); + g_test_add_func("/blockjob/cancel/concluded", test_cancel_concluded); return g_test_run(); } -- 2.13.6 The crypto driver used to create the image file in a callback from the crypto subsystem. If we want to implement .bdrv_co_create, this needs to go away because that callback will get a reference to an already existing block node. Move the image file creation to block_crypto_create_generic(). Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/crypto.c | 37 +++++++++++++++++-------------------- 1 file changed, 17 insertions(+), 20 deletions(-) diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_read_func(QCryptoBlock *block, struct BlockCryptoCreateData { - const char *filename; - QemuOpts *opts; BlockBackend *blk; uint64_t size; }; @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_init_func(QCryptoBlock *block, Error **errp) { struct BlockCryptoCreateData *data = opaque; - int ret; /* User provided size should reflect amount of space made * available to the guest, so we must take account of that * which will be used by the crypto header */ - data->size += headerlen; - - qemu_opt_set_number(data->opts, BLOCK_OPT_SIZE, data->size, &error_abort); - ret = bdrv_create_file(data->filename, data->opts, errp); - if (ret < 0) { - return -1; - } - - data->blk = blk_new_open(data->filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_PROTOCOL, errp); - if (!data->blk) { - return -1; - } - - return 0; + return blk_truncate(data->blk, data->size + headerlen, PREALLOC_MODE_OFF, + errp); } @@ -XXX,XX +XXX,XX @@ static int block_crypto_create_generic(QCryptoBlockFormat format, struct BlockCryptoCreateData data = { .size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), BDRV_SECTOR_SIZE), - .opts = opts, - .filename = filename, }; QDict *cryptoopts; + /* Parse options */ cryptoopts = qemu_opts_to_qdict(opts, NULL); create_opts = block_crypto_create_opts_init(format, cryptoopts, errp); @@ -XXX,XX +XXX,XX @@ static int block_crypto_create_generic(QCryptoBlockFormat format, return -1; } + /* Create protocol layer */ + ret = bdrv_create_file(filename, opts, errp); + if (ret < 0) { + return ret; + } + + data.blk = blk_new_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, + errp); + if (!data.blk) { + return -EINVAL; + } + + /* Create format layer */ crypto = qcrypto_block_create(create_opts, NULL, block_crypto_init_func, block_crypto_write_func, -- 2.13.6 Everything that refers to the protocol layer or QemuOpts is moved out of block_crypto_create_generic(), so that the remaining function is suitable to be called by a .bdrv_co_create implementation. LUKS is the only driver that actually implements the old interface, and we don't intend to use it in any new drivers, so put the moved out code directly into a LUKS function rather than creating a generic intermediate one. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> --- block/crypto.c | 95 +++++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 61 insertions(+), 34 deletions(-) diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static int block_crypto_open_generic(QCryptoBlockFormat format, } -static int block_crypto_create_generic(QCryptoBlockFormat format, - const char *filename, - QemuOpts *opts, - Error **errp) +static int block_crypto_co_create_generic(BlockDriverState *bs, + int64_t size, + QCryptoBlockCreateOptions *opts, + Error **errp) { - int ret = -EINVAL; - QCryptoBlockCreateOptions *create_opts = NULL; + int ret; + BlockBackend *blk; QCryptoBlock *crypto = NULL; - struct BlockCryptoCreateData data = { - .size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE), - }; - QDict *cryptoopts; - - /* Parse options */ - cryptoopts = qemu_opts_to_qdict(opts, NULL); + struct BlockCryptoCreateData data; - create_opts = block_crypto_create_opts_init(format, cryptoopts, errp); - if (!create_opts) { - return -1; - } + blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL); - /* Create protocol layer */ - ret = bdrv_create_file(filename, opts, errp); + ret = blk_insert_bs(blk, bs, errp); if (ret < 0) { - return ret; + goto cleanup; } - data.blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, - errp); - if (!data.blk) { - return -EINVAL; - } + data = (struct BlockCryptoCreateData) { + .blk = blk, + .size = size, + }; - /* Create format layer */ - crypto = qcrypto_block_create(create_opts, NULL, + crypto = qcrypto_block_create(opts, NULL, block_crypto_init_func, block_crypto_write_func, &data, @@ -XXX,XX +XXX,XX @@ static int block_crypto_create_generic(QCryptoBlockFormat format, ret = 0; cleanup: - QDECREF(cryptoopts); qcrypto_block_free(crypto); - blk_unref(data.blk); - qapi_free_QCryptoBlockCreateOptions(create_opts); + blk_unref(blk); return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn block_crypto_co_create_opts_luks(const char *filename, QemuOpts *opts, Error **errp) { - return block_crypto_create_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS, - filename, opts, errp); + QCryptoBlockCreateOptions *create_opts = NULL; + BlockDriverState *bs = NULL; + QDict *cryptoopts; + int64_t size; + int ret; + + /* Parse options */ + size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0); + + cryptoopts = qemu_opts_to_qdict_filtered(opts, NULL, + &block_crypto_create_opts_luks, + true); + + create_opts = block_crypto_create_opts_init(Q_CRYPTO_BLOCK_FORMAT_LUKS, + cryptoopts, errp); + if (!create_opts) { + ret = -EINVAL; + goto fail; + } + + /* Create protocol layer */ + ret = bdrv_create_file(filename, opts, errp); + if (ret < 0) { + return ret; + } + + bs = bdrv_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); + if (!bs) { + ret = -EINVAL; + goto fail; + } + + /* Create format layer */ + ret = block_crypto_co_create_generic(bs, size, create_opts, errp); + if (ret < 0) { + goto fail; + } + + ret = 0; +fail: + bdrv_unref(bs); + qapi_free_QCryptoBlockCreateOptions(create_opts); + QDECREF(cryptoopts); + return ret; } static int block_crypto_get_info_luks(BlockDriverState *bs, -- 2.13.6 This adds the .bdrv_co_create driver callback to luks, which enables image creation over QMP. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> --- qapi/block-core.json | 17 ++++++++++++++++- block/crypto.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 50 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 @@ '*preallocation': 'PreallocMode' } } ## +# @BlockdevCreateOptionsLUKS: +# +# Driver specific image creation options for LUKS. +# +# @file Node to create the image format on +# @size Size of the virtual disk in bytes +# +# Since: 2.12 +## +{ 'struct': 'BlockdevCreateOptionsLUKS', + 'base': 'QCryptoBlockCreateOptionsLUKS', + 'data': { 'file': 'BlockdevRef', + 'size': 'size' } } + +## # @BlockdevCreateOptionsNfs: # # Driver specific image creation options for NFS. @@ -XXX,XX +XXX,XX @@ 'http': 'BlockdevCreateNotSupported', 'https': 'BlockdevCreateNotSupported', 'iscsi': 'BlockdevCreateNotSupported', - 'luks': 'BlockdevCreateNotSupported', + 'luks': 'BlockdevCreateOptionsLUKS', 'nbd': 'BlockdevCreateNotSupported', 'nfs': 'BlockdevCreateOptionsNfs', 'null-aio': 'BlockdevCreateNotSupported', diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static int block_crypto_open_luks(BlockDriverState *bs, bs, options, flags, errp); } +static int coroutine_fn +block_crypto_co_create_luks(BlockdevCreateOptions *create_options, Error **errp) +{ + BlockdevCreateOptionsLUKS *luks_opts; + BlockDriverState *bs = NULL; + QCryptoBlockCreateOptions create_opts; + int ret; + + assert(create_options->driver == BLOCKDEV_DRIVER_LUKS); + luks_opts = &create_options->u.luks; + + bs = bdrv_open_blockdev_ref(luks_opts->file, errp); + if (bs == NULL) { + return -EIO; + } + + create_opts = (QCryptoBlockCreateOptions) { + .format = Q_CRYPTO_BLOCK_FORMAT_LUKS, + .u.luks = *qapi_BlockdevCreateOptionsLUKS_base(luks_opts), + }; + + ret = block_crypto_co_create_generic(bs, luks_opts->size, &create_opts, + errp); + if (ret < 0) { + goto fail; + } + + ret = 0; +fail: + bdrv_unref(bs); + return ret; +} + static int coroutine_fn block_crypto_co_create_opts_luks(const char *filename, QemuOpts *opts, Error **errp) @@ -XXX,XX +XXX,XX @@ BlockDriver bdrv_crypto_luks = { .bdrv_open = block_crypto_open_luks, .bdrv_close = block_crypto_close, .bdrv_child_perm = bdrv_format_default_perms, + .bdrv_co_create = block_crypto_co_create_luks, .bdrv_co_create_opts = block_crypto_co_create_opts_luks, .bdrv_truncate = block_crypto_truncate, .create_opts = &block_crypto_create_opts_luks, -- 2.13.6 The .bdrv_getlength implementation of the crypto block driver asserted that the payload offset isn't after EOF. This is an invalid assertion to make as the image file could be corrupted. Instead, check it and return -EIO if the file is too small for the payload offset. Zero length images are fine, so trigger -EIO only on offset > len, not on offset >= len as the assertion did before. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> --- block/crypto.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static int64_t block_crypto_getlength(BlockDriverState *bs) uint64_t offset = qcrypto_block_get_payload_offset(crypto->block); assert(offset < INT64_MAX); - assert(offset < len); + + if (offset > len) { + return -EIO; + } len -= offset; -- 2.13.6 When you request an image size close to UINT64_MAX, the addition of the crypto header may cause an integer overflow. Catch it instead of silently truncating the image size. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> --- block/crypto.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/block/crypto.c b/block/crypto.c index XXXXXXX..XXXXXXX 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -XXX,XX +XXX,XX @@ static ssize_t block_crypto_init_func(QCryptoBlock *block, { struct BlockCryptoCreateData *data = opaque; + if (data->size > INT64_MAX || headerlen > INT64_MAX - data->size) { + error_setg(errp, "The requested file size is too large"); + return -EFBIG; + } + /* User provided size should reflect amount of space made * available to the guest, so we must take account of that * which will be used by the crypto header -- 2.13.6 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> --- tests/qemu-iotests/209 | 210 +++++++++++++++++++++++++++++++++++++++++++ tests/qemu-iotests/209.out | 136 ++++++++++++++++++++++++++++ tests/qemu-iotests/common.rc | 2 +- tests/qemu-iotests/group | 1 + 4 files changed, 348 insertions(+), 1 deletion(-) create mode 100755 tests/qemu-iotests/209 create mode 100644 tests/qemu-iotests/209.out diff --git a/tests/qemu-iotests/209 b/tests/qemu-iotests/209 new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/209 @@ -XXX,XX +XXX,XX @@ +#!/bin/bash +# +# Test luks and file image creation +# +# Copyright (C) 2018 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=kwolf@redhat.com + +seq=`basename $0` +echo "QA output created by $seq" + +here=`pwd` +status=1 # failure is the default! + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt luks +_supported_proto file +_supported_os Linux + +function do_run_qemu() +{ + echo Testing: "$@" + $QEMU -nographic -qmp stdio -serial none "$@" + echo +} + +function run_qemu() +{ + do_run_qemu "$@" 2>&1 | _filter_testdir | _filter_qmp \ + | _filter_qemu | _filter_imgfmt \ + | _filter_actual_image_size +} + +echo +echo "=== Successful image creation (defaults) ===" +echo + +size=$((128 * 1024 * 1024)) + +run_qemu -object secret,id=keysec0,data="foo" <<EOF +{ "execute": "qmp_capabilities" } +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "file", + "filename": "$TEST_IMG_FILE", + "size": 0 + } +} +{ "execute": "blockdev-add", + "arguments": { + "driver": "file", + "node-name": "imgfile", + "filename": "$TEST_IMG_FILE" + } +} +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "$IMGFMT", + "file": "imgfile", + "key-secret": "keysec0", + "size": $size, + "iter-time": 10 + } +} +{ "execute": "quit" } +EOF + +_img_info --format-specific | _filter_img_info --format-specific + +echo +echo "=== Successful image creation (with non-default options) ===" +echo + +# Choose a different size to show that we got a new image +size=$((64 * 1024 * 1024)) + +run_qemu -object secret,id=keysec0,data="foo" <<EOF +{ "execute": "qmp_capabilities" } +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "file", + "filename": "$TEST_IMG_FILE", + "size": 0 + } +} +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "$IMGFMT", + "file": { + "driver": "file", + "filename": "$TEST_IMG_FILE" + }, + "size": $size, + "key-secret": "keysec0", + "cipher-alg": "twofish-128", + "cipher-mode": "ctr", + "ivgen-alg": "plain64", + "ivgen-hash-alg": "md5", + "hash-alg": "sha1", + "iter-time": 10 + } +} +{ "execute": "quit" } +EOF + +_img_info --format-specific | _filter_img_info --format-specific + +echo +echo "=== Invalid BlockdevRef ===" +echo + +run_qemu <<EOF +{ "execute": "qmp_capabilities" } +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "$IMGFMT", + "file": "this doesn't exist", + "size": $size + } +} +{ "execute": "quit" } +EOF + +echo +echo "=== Zero size ===" +echo + +run_qemu -blockdev driver=file,filename="$TEST_IMG_FILE",node-name=node0 \ + -object secret,id=keysec0,data="foo" <<EOF +{ "execute": "qmp_capabilities" } +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "$IMGFMT", + "file": "node0", + "key-secret": "keysec0", + "size": 0, + "iter-time": 10 + } +} +{ "execute": "quit" } +EOF + +_img_info | _filter_img_info + + +echo +echo "=== Invalid sizes ===" +echo + +# TODO Negative image sizes aren't handled correctly, but this is a problem +# with QAPI's implementation of the 'size' type and affects other commands as +# well. Once this is fixed, we may want to add a test case here. + +# 1. 2^64 - 512 +# 2. 2^63 = 8 EB (qemu-img enforces image sizes less than this) +# 3. 2^63 - 512 (generally valid, but with the crypto header the file will +# exceed 63 bits) + +run_qemu -blockdev driver=file,filename="$TEST_IMG_FILE",node-name=node0 \ + -object secret,id=keysec0,data="foo" <<EOF +{ "execute": "qmp_capabilities" } +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "$IMGFMT", + "file": "node0", + "key-secret": "keysec0", + "size": 18446744073709551104 + } +} +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "$IMGFMT", + "file": "node0", + "key-secret": "keysec0", + "size": 9223372036854775808 + } +} +{ "execute": "x-blockdev-create", + "arguments": { + "driver": "$IMGFMT", + "file": "node0", + "key-secret": "keysec0", + "size": 9223372036854775296 + } +} +{ "execute": "quit" } +EOF + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/209.out b/tests/qemu-iotests/209.out new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qemu-iotests/209.out @@ -XXX,XX +XXX,XX @@ +QA output created by 209 + +=== Successful image creation (defaults) === + +Testing: -object secret,id=keysec0,data=foo +QMP_VERSION +{"return": {}} +{"return": {}} +{"return": {}} +{"return": {}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +image: json:{"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, "key-secret": "keysec0"} +file format: IMGFMT +virtual size: 128M (134217728 bytes) +Format specific information: + ivgen alg: plain64 + hash alg: sha256 + cipher alg: aes-256 + uuid: 00000000-0000-0000-0000-000000000000 + cipher mode: xts + slots: + [0]: + active: true + iters: 1024 + key offset: 4096 + stripes: 4000 + [1]: + active: false + key offset: 262144 + [2]: + active: false + key offset: 520192 + [3]: + active: false + key offset: 778240 + [4]: + active: false + key offset: 1036288 + [5]: + active: false + key offset: 1294336 + [6]: + active: false + key offset: 1552384 + [7]: + active: false + key offset: 1810432 + payload offset: 2068480 + master key iters: 1024 + +=== Successful image creation (with non-default options) === + +Testing: -object secret,id=keysec0,data=foo +QMP_VERSION +{"return": {}} +{"return": {}} +{"return": {}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +image: json:{"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, "key-secret": "keysec0"} +file format: IMGFMT +virtual size: 64M (67108864 bytes) +Format specific information: + ivgen alg: plain64 + hash alg: sha1 + cipher alg: twofish-128 + uuid: 00000000-0000-0000-0000-000000000000 + cipher mode: ctr + slots: + [0]: + active: true + iters: 1024 + key offset: 4096 + stripes: 4000 + [1]: + active: false + key offset: 69632 + [2]: + active: false + key offset: 135168 + [3]: + active: false + key offset: 200704 + [4]: + active: false + key offset: 266240 + [5]: + active: false + key offset: 331776 + [6]: + active: false + key offset: 397312 + [7]: + active: false + key offset: 462848 + payload offset: 528384 + master key iters: 1024 + +=== Invalid BlockdevRef === + +Testing: +QMP_VERSION +{"return": {}} +{"error": {"class": "GenericError", "desc": "Cannot find device=this doesn't exist nor node_name=this doesn't exist"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + + +=== Zero size === + +Testing: -blockdev driver=file,filename=TEST_DIR/t.IMGFMT,node-name=node0 -object secret,id=keysec0,data=foo +QMP_VERSION +{"return": {}} +{"return": {}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +image: json:{"driver": "IMGFMT", "file": {"driver": "file", "filename": "TEST_DIR/t.IMGFMT"}, "key-secret": "keysec0"} +file format: IMGFMT +virtual size: 0 (0 bytes) + +=== Invalid sizes === + +Testing: -blockdev driver=file,filename=TEST_DIR/t.IMGFMT,node-name=node0 -object secret,id=keysec0,data=foo +QMP_VERSION +{"return": {}} +{"error": {"class": "GenericError", "desc": "The requested file size is too large"}} +{"error": {"class": "GenericError", "desc": "The requested file size is too large"}} +{"error": {"class": "GenericError", "desc": "The requested file size is too large"}} +{"return": {}} +{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN", "data": {"guest": false}} + +*** done diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/common.rc +++ b/tests/qemu-iotests/common.rc @@ -XXX,XX +XXX,XX @@ _img_info() discard=0 regex_json_spec_start='^ *"format-specific": \{' - $QEMU_IMG info "$@" "$TEST_IMG" 2>&1 | \ + $QEMU_IMG info $QEMU_IMG_EXTRA_ARGS "$@" "$TEST_IMG" 2>&1 | \ sed -e "s#$IMGPROTO:$TEST_DIR#TEST_DIR#g" \ -e "s#$TEST_DIR#TEST_DIR#g" \ -e "s#$IMGFMT#IMGFMT#g" \ diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -XXX,XX +XXX,XX @@ 205 rw auto quick 206 rw auto 207 rw auto +209 rw auto -- 2.13.6 From: Max Reitz <mreitz@redhat.com> In preparation of QAPI-fying VDI image creation, we have to create a BlockdevCreateOptionsVdi type which is received by a (future) vdi_co_create(). vdi_co_create_opts() now converts the QemuOpts object into such a BlockdevCreateOptionsVdi object. The protocol-layer file is still created in vdi_co_do_create() (and BlockdevCreateOptionsVdi.file is set to an empty string), but that will be addressed by a follow-up patch. Note that cluster-size is not part of the QAPI schema because it is not supported by default. Signed-off-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 18 +++++++++++ block/vdi.c | 91 ++++++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 95 insertions(+), 14 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 @@ 'size': 'size' } } ## +# @BlockdevCreateOptionsVdi: +# +# Driver specific image creation options for VDI. +# +# @file Node to create the image format on +# @size Size of the virtual disk in bytes +# @static Whether to create a statically (true) or +# dynamically (false) allocated image +# (default: false, i.e. dynamic) +# +# Since: 2.12 +## +{ 'struct': 'BlockdevCreateOptionsVdi', + 'data': { 'file': 'BlockdevRef', + 'size': 'size', + '*static': 'bool' } } + +## # @BlockdevCreateNotSupported: # # This is used for all drivers that don't support creating images. diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qobject-input-visitor.h" +#include "qapi/qapi-visit-block-core.h" #include "block/block_int.h" #include "sysemu/block-backend.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ #define VDI_DISK_SIZE_MAX ((uint64_t)VDI_BLOCKS_IN_IMAGE_MAX * \ (uint64_t)DEFAULT_CLUSTER_SIZE) +static QemuOptsList vdi_create_opts; + typedef struct { char text[0x40]; uint32_t signature; @@ -XXX,XX +XXX,XX @@ nonallocating_write: return ret; } -static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, - Error **errp) +static int coroutine_fn vdi_co_do_create(const char *filename, + QemuOpts *file_opts, + BlockdevCreateOptionsVdi *vdi_opts, + size_t block_size, Error **errp) { int ret = 0; uint64_t bytes = 0; uint32_t blocks; - size_t block_size = DEFAULT_CLUSTER_SIZE; uint32_t image_type = VDI_TYPE_DYNAMIC; VdiHeader header; size_t i; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, logout("\n"); /* Read out options. */ - bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); -#if defined(CONFIG_VDI_BLOCK_SIZE) - /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */ - block_size = qemu_opt_get_size_del(opts, - BLOCK_OPT_CLUSTER_SIZE, - DEFAULT_CLUSTER_SIZE); -#endif -#if defined(CONFIG_VDI_STATIC_IMAGE) - if (qemu_opt_get_bool_del(opts, BLOCK_OPT_STATIC, false)) { + bytes = vdi_opts->size; + if (vdi_opts->q_static) { image_type = VDI_TYPE_STATIC; } +#ifndef CONFIG_VDI_STATIC_IMAGE + if (image_type == VDI_TYPE_STATIC) { + ret = -ENOTSUP; + error_setg(errp, "Statically allocated images cannot be created in " + "this build"); + goto exit; + } +#endif +#ifndef CONFIG_VDI_BLOCK_SIZE + if (block_size != DEFAULT_CLUSTER_SIZE) { + ret = -ENOTSUP; + error_setg(errp, + "A non-default cluster size is not supported in this build"); + goto exit; + } #endif if (bytes > VDI_DISK_SIZE_MAX) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, goto exit; } - ret = bdrv_create_file(filename, opts, &local_err); + ret = bdrv_create_file(filename, file_opts, &local_err); if (ret < 0) { error_propagate(errp, local_err); goto exit; @@ -XXX,XX +XXX,XX @@ exit: return ret; } +static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, + Error **errp) +{ + QDict *qdict = NULL; + BlockdevCreateOptionsVdi *create_options = NULL; + uint64_t block_size = DEFAULT_CLUSTER_SIZE; + Visitor *v; + Error *local_err = NULL; + int ret; + + /* Since CONFIG_VDI_BLOCK_SIZE is disabled by default, + * cluster-size is not part of the QAPI schema; therefore we have + * to parse it before creating the QAPI object. */ +#if defined(CONFIG_VDI_BLOCK_SIZE) + block_size = qemu_opt_get_size_del(opts, + BLOCK_OPT_CLUSTER_SIZE, + DEFAULT_CLUSTER_SIZE); + if (block_size < BDRV_SECTOR_SIZE || block_size > UINT32_MAX || + !is_power_of_2(block_size)) + { + error_setg(errp, "Invalid cluster size"); + ret = -EINVAL; + goto done; + } +#endif + + qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vdi_create_opts, true); + + qdict_put_str(qdict, "file", ""); /* FIXME */ + + /* Get the QAPI object */ + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + visit_type_BlockdevCreateOptionsVdi(v, NULL, &create_options, &local_err); + visit_free(v); + + if (local_err) { + error_propagate(errp, local_err); + ret = -EINVAL; + goto done; + } + + create_options->size = ROUND_UP(create_options->size, BDRV_SECTOR_SIZE); + + ret = vdi_co_do_create(filename, opts, create_options, block_size, errp); +done: + QDECREF(qdict); + qapi_free_BlockdevCreateOptionsVdi(create_options); + return ret; +} + static void vdi_close(BlockDriverState *bs) { BDRVVdiState *s = bs->opaque; -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vdi.c | 46 ++++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ nonallocating_write: return ret; } -static int coroutine_fn vdi_co_do_create(const char *filename, - QemuOpts *file_opts, - BlockdevCreateOptionsVdi *vdi_opts, +static int coroutine_fn vdi_co_do_create(BlockdevCreateOptionsVdi *vdi_opts, size_t block_size, Error **errp) { int ret = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(const char *filename, size_t i; size_t bmap_size; int64_t offset = 0; - Error *local_err = NULL; + BlockDriverState *bs_file = NULL; BlockBackend *blk = NULL; uint32_t *bmap = NULL; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(const char *filename, goto exit; } - ret = bdrv_create_file(filename, file_opts, &local_err); - if (ret < 0) { - error_propagate(errp, local_err); + bs_file = bdrv_open_blockdev_ref(vdi_opts->file, errp); + if (!bs_file) { + ret = -EIO; goto exit; } - blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, - &local_err); - if (blk == NULL) { - error_propagate(errp, local_err); - ret = -EIO; + blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL); + ret = blk_insert_bs(blk, bs_file, errp); + if (ret < 0) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(const char *filename, vdi_header_to_le(&header); ret = blk_pwrite(blk, offset, &header, sizeof(header), 0); if (ret < 0) { - error_setg(errp, "Error writing header to %s", filename); + error_setg(errp, "Error writing header"); goto exit; } offset += sizeof(header); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(const char *filename, } ret = blk_pwrite(blk, offset, bmap, bmap_size, 0); if (ret < 0) { - error_setg(errp, "Error writing bmap to %s", filename); + error_setg(errp, "Error writing bmap"); goto exit; } offset += bmap_size; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(const char *filename, ret = blk_truncate(blk, offset + blocks * block_size, PREALLOC_MODE_OFF, errp); if (ret < 0) { - error_prepend(errp, "Failed to statically allocate %s", filename); + error_prepend(errp, "Failed to statically allocate file"); goto exit; } } exit: blk_unref(blk); + bdrv_unref(bs_file); g_free(bmap); return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, { QDict *qdict = NULL; BlockdevCreateOptionsVdi *create_options = NULL; + BlockDriverState *bs_file = NULL; uint64_t block_size = DEFAULT_CLUSTER_SIZE; Visitor *v; Error *local_err = NULL; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vdi_create_opts, true); - qdict_put_str(qdict, "file", ""); /* FIXME */ + ret = bdrv_create_file(filename, opts, errp); + if (ret < 0) { + goto done; + } + + bs_file = bdrv_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); + if (!bs_file) { + ret = -EIO; + goto done; + } + + qdict_put_str(qdict, "file", bs_file->node_name); /* Get the QAPI object */ v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, create_options->size = ROUND_UP(create_options->size, BDRV_SECTOR_SIZE); - ret = vdi_co_do_create(filename, opts, create_options, block_size, errp); + ret = vdi_co_do_create(create_options, block_size, errp); done: QDECREF(qdict); qapi_free_BlockdevCreateOptionsVdi(create_options); + bdrv_unref(bs_file); return ret; } -- 2.13.6 From: Max Reitz <mreitz@redhat.com> Signed-off-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 2 +- block/vdi.c | 24 +++++++++++++++++++----- 2 files changed, 20 insertions(+), 6 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 @@ 'sheepdog': 'BlockdevCreateOptionsSheepdog', 'ssh': 'BlockdevCreateOptionsSsh', 'throttle': 'BlockdevCreateNotSupported', - 'vdi': 'BlockdevCreateNotSupported', + 'vdi': 'BlockdevCreateOptionsVdi', 'vhdx': 'BlockdevCreateNotSupported', 'vmdk': 'BlockdevCreateNotSupported', 'vpc': 'BlockdevCreateNotSupported', diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ nonallocating_write: return ret; } -static int coroutine_fn vdi_co_do_create(BlockdevCreateOptionsVdi *vdi_opts, +static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, size_t block_size, Error **errp) { + BlockdevCreateOptionsVdi *vdi_opts; int ret = 0; uint64_t bytes = 0; uint32_t blocks; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptionsVdi *vdi_opts, BlockBackend *blk = NULL; uint32_t *bmap = NULL; + assert(create_options->driver == BLOCKDEV_DRIVER_VDI); + vdi_opts = &create_options->u.vdi; + logout("\n"); /* Read out options. */ @@ -XXX,XX +XXX,XX @@ exit: return ret; } +static int coroutine_fn vdi_co_create(BlockdevCreateOptions *create_options, + Error **errp) +{ + return vdi_co_do_create(create_options, DEFAULT_CLUSTER_SIZE, errp); +} + static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, Error **errp) { QDict *qdict = NULL; - BlockdevCreateOptionsVdi *create_options = NULL; + BlockdevCreateOptions *create_options = NULL; BlockDriverState *bs_file = NULL; uint64_t block_size = DEFAULT_CLUSTER_SIZE; Visitor *v; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, goto done; } + qdict_put_str(qdict, "driver", "vdi"); qdict_put_str(qdict, "file", bs_file->node_name); /* Get the QAPI object */ v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); - visit_type_BlockdevCreateOptionsVdi(v, NULL, &create_options, &local_err); + visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err); visit_free(v); if (local_err) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, goto done; } - create_options->size = ROUND_UP(create_options->size, BDRV_SECTOR_SIZE); + assert(create_options->driver == BLOCKDEV_DRIVER_VDI); + create_options->u.vdi.size = ROUND_UP(create_options->u.vdi.size, + BDRV_SECTOR_SIZE); ret = vdi_co_do_create(create_options, block_size, errp); done: QDECREF(qdict); - qapi_free_BlockdevCreateOptionsVdi(create_options); + qapi_free_BlockdevCreateOptions(create_options); bdrv_unref(bs_file); return ret; } @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_vdi = { .bdrv_reopen_prepare = vdi_reopen_prepare, .bdrv_child_perm = bdrv_format_default_perms, .bdrv_co_create_opts = vdi_co_create_opts, + .bdrv_co_create = vdi_co_create, .bdrv_has_zero_init = bdrv_has_zero_init_1, .bdrv_co_block_status = vdi_co_block_status, .bdrv_make_empty = vdi_make_empty, -- 2.13.6 From: Fam Zheng <famz@redhat.com> Reopen flags are not synchronized according to the bdrv_reopen_queue_child precedence until bdrv_reopen_prepare. It is a bit too late: we already check the consistency in bdrv_check_perm before that. This fixes the bug that when bdrv_reopen a RO node as RW, the flags for backing child are wrong. Before, we could recurse with flags.rw=1; now, role->inherit_options + update_flags_from_options will make sure to clear the bit when necessary. Note that this will not clear an explicitly set bit, as in the case of parallel block jobs (e.g. test_stream_parallel in 030), because the explicit options include 'read-only=false' (for an intermediate node used by a different job). Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, /* Inherit from parent node */ if (parent_options) { + QemuOpts *opts; + QDict *options_copy; assert(!flags); role->inherit_options(&flags, options, parent_flags, parent_options); + options_copy = qdict_clone_shallow(options); + opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort); + qemu_opts_absorb_qdict(opts, options_copy, NULL); + update_flags_from_options(&flags, opts); + qemu_opts_del(opts); + QDECREF(options_copy); } /* Old values are used for options that aren't set yet */ -- 2.13.6 From: Fam Zheng <famz@redhat.com> Signed-off-by: Fam Zheng <famz@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/qemu-iotests/153 | 12 ++++++++++++ tests/qemu-iotests/153.out | 5 +++++ 2 files changed, 17 insertions(+) diff --git a/tests/qemu-iotests/153 b/tests/qemu-iotests/153 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/153 +++ b/tests/qemu-iotests/153 @@ -XXX,XX +XXX,XX @@ rm -f "${TEST_IMG}.lnk" &>/dev/null ln -s ${TEST_IMG} "${TEST_IMG}.lnk" || echo "Failed to create link" _run_qemu_with_images "${TEST_IMG}.lnk" "${TEST_IMG}" +echo +echo "== Active commit to intermediate layer should work when base in use ==" +_launch_qemu -drive format=$IMGFMT,file="${TEST_IMG}.a",id=drive0,if=none \ + -device virtio-blk,drive=drive0 + +_send_qemu_cmd $QEMU_HANDLE \ + "{ 'execute': 'qmp_capabilities' }" \ + 'return' +_run_cmd $QEMU_IMG commit -b "${TEST_IMG}.b" "${TEST_IMG}.c" + +_cleanup_qemu + _launch_qemu _send_qemu_cmd $QEMU_HANDLE \ diff --git a/tests/qemu-iotests/153.out b/tests/qemu-iotests/153.out index XXXXXXX..XXXXXXX 100644 --- a/tests/qemu-iotests/153.out +++ b/tests/qemu-iotests/153.out @@ -XXX,XX +XXX,XX @@ Is another process using the image? == Symbolic link == QEMU_PROG: -drive if=none,file=TEST_DIR/t.qcow2: Failed to get "write" lock Is another process using the image? + +== Active commit to intermediate layer should work when base in use == +{"return": {}} + +_qemu_img_wrapper commit -b TEST_DIR/t.qcow2.b TEST_DIR/t.qcow2.c {"return": {}} Adding drive -- 2.13.6 This adds the .bdrv_co_create driver callback to parallels, which enables image creation over QMP. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> --- qapi/block-core.json | 18 ++++- block/parallels.c | 199 ++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 168 insertions(+), 49 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 @@ 'size': 'size' } } ## +# @BlockdevCreateOptionsParallels: +# +# Driver specific image creation options for parallels. +# +# @file Node to create the image format on +# @size Size of the virtual disk in bytes +# @cluster-size Cluster size in bytes (default: 1 MB) +# +# Since: 2.12 +## +{ 'struct': 'BlockdevCreateOptionsParallels', + 'data': { 'file': 'BlockdevRef', + 'size': 'size', + '*cluster-size': 'size' } } + +## # @BlockdevQcow2Version: # # @v2: The original QCOW2 format as introduced in qemu 0.10 (version 2) @@ -XXX,XX +XXX,XX @@ 'null-aio': 'BlockdevCreateNotSupported', 'null-co': 'BlockdevCreateNotSupported', 'nvme': 'BlockdevCreateNotSupported', - 'parallels': 'BlockdevCreateNotSupported', + 'parallels': 'BlockdevCreateOptionsParallels', 'qcow2': 'BlockdevCreateOptionsQcow2', 'qcow': 'BlockdevCreateNotSupported', 'qed': 'BlockdevCreateNotSupported', diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/block-backend.h" #include "qemu/module.h" #include "qemu/option.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qobject-input-visitor.h" +#include "qapi/qapi-visit-block-core.h" #include "qemu/bswap.h" #include "qemu/bitmap.h" #include "migration/blocker.h" @@ -XXX,XX +XXX,XX @@ static QemuOptsList parallels_runtime_opts = { }, }; +static QemuOptsList parallels_create_opts = { + .name = "parallels-create-opts", + .head = QTAILQ_HEAD_INITIALIZER(parallels_create_opts.head), + .desc = { + { + .name = BLOCK_OPT_SIZE, + .type = QEMU_OPT_SIZE, + .help = "Virtual disk size", + }, + { + .name = BLOCK_OPT_CLUSTER_SIZE, + .type = QEMU_OPT_SIZE, + .help = "Parallels image cluster size", + .def_value_str = stringify(DEFAULT_CLUSTER_SIZE), + }, + { /* end of list */ } + } +}; + static int64_t bat2sect(BDRVParallelsState *s, uint32_t idx) { @@ -XXX,XX +XXX,XX @@ out: } -static int coroutine_fn parallels_co_create_opts(const char *filename, - QemuOpts *opts, - Error **errp) +static int coroutine_fn parallels_co_create(BlockdevCreateOptions* opts, + Error **errp) { + BlockdevCreateOptionsParallels *parallels_opts; + BlockDriverState *bs; + BlockBackend *blk; int64_t total_size, cl_size; - uint8_t tmp[BDRV_SECTOR_SIZE]; - Error *local_err = NULL; - BlockBackend *file; uint32_t bat_entries, bat_sectors; ParallelsHeader header; + uint8_t tmp[BDRV_SECTOR_SIZE]; int ret; - total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); - cl_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE, - DEFAULT_CLUSTER_SIZE), BDRV_SECTOR_SIZE); + assert(opts->driver == BLOCKDEV_DRIVER_PARALLELS); + parallels_opts = &opts->u.parallels; + + /* Sanity checks */ + total_size = parallels_opts->size; + + if (parallels_opts->has_cluster_size) { + cl_size = parallels_opts->cluster_size; + } else { + cl_size = DEFAULT_CLUSTER_SIZE; + } + if (total_size >= MAX_PARALLELS_IMAGE_FACTOR * cl_size) { - error_propagate(errp, local_err); + error_setg(errp, "Image size is too large for this cluster size"); return -E2BIG; } - ret = bdrv_create_file(filename, opts, &local_err); - if (ret < 0) { - error_propagate(errp, local_err); - return ret; + if (!QEMU_IS_ALIGNED(total_size, BDRV_SECTOR_SIZE)) { + error_setg(errp, "Image size must be a multiple of 512 bytes"); + return -EINVAL; } - file = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, - &local_err); - if (file == NULL) { - error_propagate(errp, local_err); + if (!QEMU_IS_ALIGNED(cl_size, BDRV_SECTOR_SIZE)) { + error_setg(errp, "Cluster size must be a multiple of 512 bytes"); + return -EINVAL; + } + + /* Create BlockBackend to write to the image */ + bs = bdrv_open_blockdev_ref(parallels_opts->file, errp); + if (bs == NULL) { return -EIO; } - blk_set_allow_write_beyond_eof(file, true); + blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL); + ret = blk_insert_bs(blk, bs, errp); + if (ret < 0) { + goto out; + } + blk_set_allow_write_beyond_eof(blk, true); - ret = blk_truncate(file, 0, PREALLOC_MODE_OFF, errp); + /* Create image format */ + ret = blk_truncate(blk, 0, PREALLOC_MODE_OFF, errp); if (ret < 0) { - goto exit; + goto out; } bat_entries = DIV_ROUND_UP(total_size, cl_size); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn parallels_co_create_opts(const char *filename, memset(tmp, 0, sizeof(tmp)); memcpy(tmp, &header, sizeof(header)); - ret = blk_pwrite(file, 0, tmp, BDRV_SECTOR_SIZE, 0); + ret = blk_pwrite(blk, 0, tmp, BDRV_SECTOR_SIZE, 0); if (ret < 0) { goto exit; } - ret = blk_pwrite_zeroes(file, BDRV_SECTOR_SIZE, + ret = blk_pwrite_zeroes(blk, BDRV_SECTOR_SIZE, (bat_sectors - 1) << BDRV_SECTOR_BITS, 0); if (ret < 0) { goto exit; } - ret = 0; -done: - blk_unref(file); + ret = 0; +out: + blk_unref(blk); + bdrv_unref(bs); return ret; exit: error_setg_errno(errp, -ret, "Failed to create Parallels image"); - goto done; + goto out; +} + +static int coroutine_fn parallels_co_create_opts(const char *filename, + QemuOpts *opts, + Error **errp) +{ + BlockdevCreateOptions *create_options = NULL; + Error *local_err = NULL; + BlockDriverState *bs = NULL; + QDict *qdict = NULL; + QObject *qobj; + Visitor *v; + int ret; + + static const QDictRenames opt_renames[] = { + { BLOCK_OPT_CLUSTER_SIZE, "cluster-size" }, + { NULL, NULL }, + }; + + /* Parse options and convert legacy syntax */ + qdict = qemu_opts_to_qdict_filtered(opts, NULL, &parallels_create_opts, + true); + + if (!qdict_rename_keys(qdict, opt_renames, errp)) { + ret = -EINVAL; + goto done; + } + + /* Create and open the file (protocol layer) */ + ret = bdrv_create_file(filename, opts, &local_err); + if (ret < 0) { + error_propagate(errp, local_err); + goto done; + } + + bs = bdrv_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); + if (bs == NULL) { + ret = -EIO; + goto done; + } + + /* Now get the QAPI type BlockdevCreateOptions */ + qdict_put_str(qdict, "driver", "parallels"); + qdict_put_str(qdict, "file", bs->node_name); + + qobj = qdict_crumple(qdict, errp); + QDECREF(qdict); + qdict = qobject_to_qdict(qobj); + if (qdict == NULL) { + ret = -EINVAL; + goto done; + } + + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err); + visit_free(v); + + if (local_err) { + error_propagate(errp, local_err); + ret = -EINVAL; + goto done; + } + + /* Silently round up sizes */ + create_options->u.parallels.size = + ROUND_UP(create_options->u.parallels.size, BDRV_SECTOR_SIZE); + create_options->u.parallels.cluster_size = + ROUND_UP(create_options->u.parallels.cluster_size, BDRV_SECTOR_SIZE); + + /* Create the Parallels image (format layer) */ + ret = parallels_co_create(create_options, errp); + if (ret < 0) { + goto done; + } + ret = 0; + +done: + QDECREF(qdict); + bdrv_unref(bs); + qapi_free_BlockdevCreateOptions(create_options); + return ret; } @@ -XXX,XX +XXX,XX @@ static void parallels_close(BlockDriverState *bs) error_free(s->migration_blocker); } -static QemuOptsList parallels_create_opts = { - .name = "parallels-create-opts", - .head = QTAILQ_HEAD_INITIALIZER(parallels_create_opts.head), - .desc = { - { - .name = BLOCK_OPT_SIZE, - .type = QEMU_OPT_SIZE, - .help = "Virtual disk size", - }, - { - .name = BLOCK_OPT_CLUSTER_SIZE, - .type = QEMU_OPT_SIZE, - .help = "Parallels image cluster size", - .def_value_str = stringify(DEFAULT_CLUSTER_SIZE), - }, - { /* end of list */ } - } -}; - static BlockDriver bdrv_parallels = { .format_name = "parallels", .instance_size = sizeof(BDRVParallelsState), @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_parallels = { .bdrv_co_readv = parallels_co_readv, .bdrv_co_writev = parallels_co_writev, .supports_backing = true, + .bdrv_co_create = parallels_co_create, .bdrv_co_create_opts = parallels_co_create_opts, .bdrv_co_check = parallels_co_check, .create_opts = &parallels_create_opts, -- 2.13.6 Originally we added parallels as a read-only format to qemu-iotests where we did just some tests with a binary image. Since then, write and image creation support has been added to the driver, so we can now enable it in _supported_fmt generic. The driver doesn't support migration yet, though, so we need to add it to the list of exceptions in 181. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> --- tests/qemu-iotests/181 | 2 +- tests/qemu-iotests/check | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/tests/qemu-iotests/181 b/tests/qemu-iotests/181 index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/181 +++ b/tests/qemu-iotests/181 @@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt generic # Formats that do not support live migration -_unsupported_fmt qcow vdi vhdx vmdk vpc vvfat +_unsupported_fmt qcow vdi vhdx vmdk vpc vvfat parallels _supported_proto generic _supported_os Linux diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check index XXXXXXX..XXXXXXX 100755 --- a/tests/qemu-iotests/check +++ b/tests/qemu-iotests/check @@ -XXX,XX +XXX,XX @@ testlist options -parallels) IMGFMT=parallels - IMGFMT_GENERIC=false xpand=false ;; -- 2.13.6 This adds the .bdrv_co_create driver callback to qcow, which enables image creation over QMP. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Jeff Cody <jcody@redhat.com> --- qapi/block-core.json | 21 +++++- block/qcow.c | 196 ++++++++++++++++++++++++++++++++++----------------- 2 files changed, 150 insertions(+), 67 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 @@ '*cluster-size': 'size' } } ## +# @BlockdevCreateOptionsQcow: +# +# Driver specific image creation options for qcow. +# +# @file Node to create the image format on +# @size Size of the virtual disk in bytes +# @backing-file File name of the backing file if a backing file +# should be used +# @encrypt Encryption options if the image should be encrypted +# +# Since: 2.12 +## +{ 'struct': 'BlockdevCreateOptionsQcow', + 'data': { 'file': 'BlockdevRef', + 'size': 'size', + '*backing-file': 'str', + '*encrypt': 'QCryptoBlockCreateOptions' } } + +## # @BlockdevQcow2Version: # # @v2: The original QCOW2 format as introduced in qemu 0.10 (version 2) @@ -XXX,XX +XXX,XX @@ 'null-co': 'BlockdevCreateNotSupported', 'nvme': 'BlockdevCreateNotSupported', 'parallels': 'BlockdevCreateOptionsParallels', + 'qcow': 'BlockdevCreateOptionsQcow', 'qcow2': 'BlockdevCreateOptionsQcow2', - 'qcow': 'BlockdevCreateNotSupported', 'qed': 'BlockdevCreateNotSupported', 'quorum': 'BlockdevCreateNotSupported', 'raw': 'BlockdevCreateNotSupported', diff --git a/block/qcow.c b/block/qcow.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -XXX,XX +XXX,XX @@ #include <zlib.h> #include "qapi/qmp/qdict.h" #include "qapi/qmp/qstring.h" +#include "qapi/qobject-input-visitor.h" +#include "qapi/qapi-visit-block-core.h" #include "crypto/block.h" #include "migration/blocker.h" #include "block/crypto.h" @@ -XXX,XX +XXX,XX @@ typedef struct BDRVQcowState { Error *migration_blocker; } BDRVQcowState; +static QemuOptsList qcow_create_opts; + static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset); static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename) @@ -XXX,XX +XXX,XX @@ static void qcow_close(BlockDriverState *bs) error_free(s->migration_blocker); } -static int coroutine_fn qcow_co_create_opts(const char *filename, QemuOpts *opts, - Error **errp) +static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts, + Error **errp) { + BlockdevCreateOptionsQcow *qcow_opts; int header_size, backing_filename_len, l1_size, shift, i; QCowHeader header; uint8_t *tmp; int64_t total_size = 0; - char *backing_file = NULL; - Error *local_err = NULL; int ret; + BlockDriverState *bs; BlockBackend *qcow_blk; - char *encryptfmt = NULL; - QDict *options; - QDict *encryptopts = NULL; - QCryptoBlockCreateOptions *crypto_opts = NULL; QCryptoBlock *crypto = NULL; - /* Read out options */ - total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); + assert(opts->driver == BLOCKDEV_DRIVER_QCOW); + qcow_opts = &opts->u.qcow; + + /* Sanity checks */ + total_size = qcow_opts->size; if (total_size == 0) { error_setg(errp, "Image size is too small, cannot be zero length"); - ret = -EINVAL; - goto cleanup; + return -EINVAL; } - backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE); - encryptfmt = qemu_opt_get_del(opts, BLOCK_OPT_ENCRYPT_FORMAT); - if (encryptfmt) { - if (qemu_opt_get(opts, BLOCK_OPT_ENCRYPT)) { - error_setg(errp, "Options " BLOCK_OPT_ENCRYPT " and " - BLOCK_OPT_ENCRYPT_FORMAT " are mutually exclusive"); - ret = -EINVAL; - goto cleanup; - } - } else if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) { - encryptfmt = g_strdup("aes"); + if (qcow_opts->has_encrypt && + qcow_opts->encrypt->format != Q_CRYPTO_BLOCK_FORMAT_QCOW) + { + error_setg(errp, "Unsupported encryption format"); + return -EINVAL; } - ret = bdrv_create_file(filename, opts, &local_err); - if (ret < 0) { - error_propagate(errp, local_err); - goto cleanup; + /* Create BlockBackend to write to the image */ + bs = bdrv_open_blockdev_ref(qcow_opts->file, errp); + if (bs == NULL) { + return -EIO; } - qcow_blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, - &local_err); - if (qcow_blk == NULL) { - error_propagate(errp, local_err); - ret = -EIO; - goto cleanup; + qcow_blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL); + ret = blk_insert_bs(qcow_blk, bs, errp); + if (ret < 0) { + goto exit; } - blk_set_allow_write_beyond_eof(qcow_blk, true); + /* Create image format */ ret = blk_truncate(qcow_blk, 0, PREALLOC_MODE_OFF, errp); if (ret < 0) { goto exit; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create_opts(const char *filename, QemuOpts *opts header.size = cpu_to_be64(total_size); header_size = sizeof(header); backing_filename_len = 0; - if (backing_file) { - if (strcmp(backing_file, "fat:")) { + if (qcow_opts->has_backing_file) { + if (strcmp(qcow_opts->backing_file, "fat:")) { header.backing_file_offset = cpu_to_be64(header_size); - backing_filename_len = strlen(backing_file); + backing_filename_len = strlen(qcow_opts->backing_file); header.backing_file_size = cpu_to_be32(backing_filename_len); header_size += backing_filename_len; } else { /* special backing file for vvfat */ - g_free(backing_file); - backing_file = NULL; + qcow_opts->has_backing_file = false; } header.cluster_bits = 9; /* 512 byte cluster to avoid copying unmodified sectors */ @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create_opts(const char *filename, QemuOpts *opts header.l1_table_offset = cpu_to_be64(header_size); - options = qemu_opts_to_qdict(opts, NULL); - qdict_extract_subqdict(options, &encryptopts, "encrypt."); - QDECREF(options); - if (encryptfmt) { - if (!g_str_equal(encryptfmt, "aes")) { - error_setg(errp, "Unknown encryption format '%s', expected 'aes'", - encryptfmt); - ret = -EINVAL; - goto exit; - } + if (qcow_opts->has_encrypt) { header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES); - crypto_opts = block_crypto_create_opts_init( - Q_CRYPTO_BLOCK_FORMAT_QCOW, encryptopts, errp); - if (!crypto_opts) { - ret = -EINVAL; - goto exit; - } - - crypto = qcrypto_block_create(crypto_opts, "encrypt.", + crypto = qcrypto_block_create(qcow_opts->encrypt, "encrypt.", NULL, NULL, NULL, errp); if (!crypto) { ret = -EINVAL; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create_opts(const char *filename, QemuOpts *opts goto exit; } - if (backing_file) { + if (qcow_opts->has_backing_file) { ret = blk_pwrite(qcow_blk, sizeof(header), - backing_file, backing_filename_len, 0); + qcow_opts->backing_file, backing_filename_len, 0); if (ret != backing_filename_len) { goto exit; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn qcow_co_create_opts(const char *filename, QemuOpts *opts ret = 0; exit: blk_unref(qcow_blk); -cleanup: - QDECREF(encryptopts); - g_free(encryptfmt); qcrypto_block_free(crypto); - qapi_free_QCryptoBlockCreateOptions(crypto_opts); - g_free(backing_file); + return ret; +} + +static int coroutine_fn qcow_co_create_opts(const char *filename, + QemuOpts *opts, Error **errp) +{ + BlockdevCreateOptions *create_options = NULL; + BlockDriverState *bs = NULL; + QDict *qdict = NULL; + QObject *qobj; + Visitor *v; + const char *val; + Error *local_err = NULL; + int ret; + + static const QDictRenames opt_renames[] = { + { BLOCK_OPT_BACKING_FILE, "backing-file" }, + { BLOCK_OPT_ENCRYPT, BLOCK_OPT_ENCRYPT_FORMAT }, + { NULL, NULL }, + }; + + /* Parse options and convert legacy syntax */ + qdict = qemu_opts_to_qdict_filtered(opts, NULL, &qcow_create_opts, true); + + val = qdict_get_try_str(qdict, BLOCK_OPT_ENCRYPT); + if (val && !strcmp(val, "on")) { + qdict_put_str(qdict, BLOCK_OPT_ENCRYPT, "qcow"); + } else if (val && !strcmp(val, "off")) { + qdict_del(qdict, BLOCK_OPT_ENCRYPT); + } + + val = qdict_get_try_str(qdict, BLOCK_OPT_ENCRYPT_FORMAT); + if (val && !strcmp(val, "aes")) { + qdict_put_str(qdict, BLOCK_OPT_ENCRYPT_FORMAT, "qcow"); + } + + if (!qdict_rename_keys(qdict, opt_renames, errp)) { + ret = -EINVAL; + goto fail; + } + + /* Create and open the file (protocol layer) */ + ret = bdrv_create_file(filename, opts, &local_err); + if (ret < 0) { + error_propagate(errp, local_err); + goto fail; + } + + bs = bdrv_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); + if (bs == NULL) { + ret = -EIO; + goto fail; + } + + /* Now get the QAPI type BlockdevCreateOptions */ + qdict_put_str(qdict, "driver", "qcow"); + qdict_put_str(qdict, "file", bs->node_name); + + qobj = qdict_crumple(qdict, errp); + QDECREF(qdict); + qdict = qobject_to_qdict(qobj); + if (qdict == NULL) { + ret = -EINVAL; + goto fail; + } + + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err); + visit_free(v); + + if (local_err) { + error_propagate(errp, local_err); + ret = -EINVAL; + goto fail; + } + + /* Silently round up size */ + assert(create_options->driver == BLOCKDEV_DRIVER_QCOW); + create_options->u.qcow.size = + ROUND_UP(create_options->u.qcow.size, BDRV_SECTOR_SIZE); + + /* Create the qcow image (format layer) */ + ret = qcow_co_create(create_options, errp); + if (ret < 0) { + goto fail; + } + + ret = 0; +fail: + QDECREF(qdict); + bdrv_unref(bs); + qapi_free_BlockdevCreateOptions(create_options); return ret; } @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_qcow = { .bdrv_close = qcow_close, .bdrv_child_perm = bdrv_format_default_perms, .bdrv_reopen_prepare = qcow_reopen_prepare, + .bdrv_co_create = qcow_co_create, .bdrv_co_create_opts = qcow_co_create_opts, .bdrv_has_zero_init = bdrv_has_zero_init_1, .supports_backing = true, -- 2.13.6 This adds the .bdrv_co_create driver callback to qed, which enables image creation over QMP. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 25 ++++++- block/qed.c | 204 ++++++++++++++++++++++++++++++++++----------------- 2 files changed, 162 insertions(+), 67 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 @@ '*refcount-bits': 'int' } } ## +# @BlockdevCreateOptionsQed: +# +# Driver specific image creation options for qed. +# +# @file Node to create the image format on +# @size Size of the virtual disk in bytes +# @backing-file File name of the backing file if a backing file +# should be used +# @backing-fmt Name of the block driver to use for the backing file +# @cluster-size Cluster size in bytes (default: 65536) +# @table-size L1/L2 table size (in clusters) +# +# Since: 2.12 +## +{ 'struct': 'BlockdevCreateOptionsQed', + 'data': { 'file': 'BlockdevRef', + 'size': 'size', + '*backing-file': 'str', + '*backing-fmt': 'BlockdevDriver', + '*cluster-size': 'size', + '*table-size': 'int' } } + +## # @BlockdevCreateOptionsRbd: # # Driver specific image creation options for rbd/Ceph. @@ -XXX,XX +XXX,XX @@ 'parallels': 'BlockdevCreateOptionsParallels', 'qcow': 'BlockdevCreateOptionsQcow', 'qcow2': 'BlockdevCreateOptionsQcow2', - 'qed': 'BlockdevCreateNotSupported', + 'qed': 'BlockdevCreateOptionsQed', 'quorum': 'BlockdevCreateNotSupported', 'raw': 'BlockdevCreateNotSupported', 'rbd': 'BlockdevCreateOptionsRbd', diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include "qed.h" #include "sysemu/block-backend.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qobject-input-visitor.h" +#include "qapi/qapi-visit-block-core.h" + +static QemuOptsList qed_create_opts; static int bdrv_qed_probe(const uint8_t *buf, int buf_size, const char *filename) @@ -XXX,XX +XXX,XX @@ static void bdrv_qed_close(BlockDriverState *bs) qemu_vfree(s->l1_table); } -static int qed_create(const char *filename, uint32_t cluster_size, - uint64_t image_size, uint32_t table_size, - const char *backing_file, const char *backing_fmt, - QemuOpts *opts, Error **errp) +static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts, + Error **errp) { - QEDHeader header = { - .magic = QED_MAGIC, - .cluster_size = cluster_size, - .table_size = table_size, - .header_size = 1, - .features = 0, - .compat_features = 0, - .l1_table_offset = cluster_size, - .image_size = image_size, - }; + BlockdevCreateOptionsQed *qed_opts; + BlockBackend *blk = NULL; + BlockDriverState *bs = NULL; + + QEDHeader header; QEDHeader le_header; uint8_t *l1_table = NULL; - size_t l1_size = header.cluster_size * header.table_size; - Error *local_err = NULL; + size_t l1_size; int ret = 0; - BlockBackend *blk; - ret = bdrv_create_file(filename, opts, &local_err); - if (ret < 0) { - error_propagate(errp, local_err); - return ret; + assert(opts->driver == BLOCKDEV_DRIVER_QED); + qed_opts = &opts->u.qed; + + /* Validate options and set default values */ + if (!qed_opts->has_cluster_size) { + qed_opts->cluster_size = QED_DEFAULT_CLUSTER_SIZE; + } + if (!qed_opts->has_table_size) { + qed_opts->table_size = QED_DEFAULT_TABLE_SIZE; } - blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, - &local_err); - if (blk == NULL) { - error_propagate(errp, local_err); + if (!qed_is_cluster_size_valid(qed_opts->cluster_size)) { + error_setg(errp, "QED cluster size must be within range [%u, %u] " + "and power of 2", + QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE); + return -EINVAL; + } + if (!qed_is_table_size_valid(qed_opts->table_size)) { + error_setg(errp, "QED table size must be within range [%u, %u] " + "and power of 2", + QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE); + return -EINVAL; + } + if (!qed_is_image_size_valid(qed_opts->size, qed_opts->cluster_size, + qed_opts->table_size)) + { + error_setg(errp, "QED image size must be a non-zero multiple of " + "cluster size and less than %" PRIu64 " bytes", + qed_max_image_size(qed_opts->cluster_size, + qed_opts->table_size)); + return -EINVAL; + } + + /* Create BlockBackend to write to the image */ + bs = bdrv_open_blockdev_ref(qed_opts->file, errp); + if (bs == NULL) { return -EIO; } + blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL); + ret = blk_insert_bs(blk, bs, errp); + if (ret < 0) { + goto out; + } blk_set_allow_write_beyond_eof(blk, true); + /* Prepare image format */ + header = (QEDHeader) { + .magic = QED_MAGIC, + .cluster_size = qed_opts->cluster_size, + .table_size = qed_opts->table_size, + .header_size = 1, + .features = 0, + .compat_features = 0, + .l1_table_offset = qed_opts->cluster_size, + .image_size = qed_opts->size, + }; + + l1_size = header.cluster_size * header.table_size; + /* File must start empty and grow, check truncate is supported */ ret = blk_truncate(blk, 0, PREALLOC_MODE_OFF, errp); if (ret < 0) { goto out; } - if (backing_file) { + if (qed_opts->has_backing_file) { header.features |= QED_F_BACKING_FILE; header.backing_filename_offset = sizeof(le_header); - header.backing_filename_size = strlen(backing_file); + header.backing_filename_size = strlen(qed_opts->backing_file); - if (qed_fmt_is_raw(backing_fmt)) { - header.features |= QED_F_BACKING_FORMAT_NO_PROBE; + if (qed_opts->has_backing_fmt) { + const char *backing_fmt = BlockdevDriver_str(qed_opts->backing_fmt); + if (qed_fmt_is_raw(backing_fmt)) { + header.features |= QED_F_BACKING_FORMAT_NO_PROBE; + } } } @@ -XXX,XX +XXX,XX @@ static int qed_create(const char *filename, uint32_t cluster_size, if (ret < 0) { goto out; } - ret = blk_pwrite(blk, sizeof(le_header), backing_file, + ret = blk_pwrite(blk, sizeof(le_header), qed_opts->backing_file, header.backing_filename_size, 0); if (ret < 0) { goto out; @@ -XXX,XX +XXX,XX @@ static int qed_create(const char *filename, uint32_t cluster_size, out: g_free(l1_table); blk_unref(blk); + bdrv_unref(bs); return ret; } @@ -XXX,XX +XXX,XX @@ static int coroutine_fn bdrv_qed_co_create_opts(const char *filename, QemuOpts *opts, Error **errp) { - uint64_t image_size = 0; - uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE; - uint32_t table_size = QED_DEFAULT_TABLE_SIZE; - char *backing_file = NULL; - char *backing_fmt = NULL; + BlockdevCreateOptions *create_options = NULL; + QDict *qdict = NULL; + QObject *qobj; + Visitor *v; + BlockDriverState *bs = NULL; + Error *local_err = NULL; int ret; - image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); - backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE); - backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT); - cluster_size = qemu_opt_get_size_del(opts, - BLOCK_OPT_CLUSTER_SIZE, - QED_DEFAULT_CLUSTER_SIZE); - table_size = qemu_opt_get_size_del(opts, BLOCK_OPT_TABLE_SIZE, - QED_DEFAULT_TABLE_SIZE); - - if (!qed_is_cluster_size_valid(cluster_size)) { - error_setg(errp, "QED cluster size must be within range [%u, %u] " - "and power of 2", - QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE); + static const QDictRenames opt_renames[] = { + { BLOCK_OPT_BACKING_FILE, "backing-file" }, + { BLOCK_OPT_BACKING_FMT, "backing-fmt" }, + { BLOCK_OPT_CLUSTER_SIZE, "cluster-size" }, + { BLOCK_OPT_TABLE_SIZE, "table-size" }, + { NULL, NULL }, + }; + + /* Parse options and convert legacy syntax */ + qdict = qemu_opts_to_qdict_filtered(opts, NULL, &qed_create_opts, true); + + if (!qdict_rename_keys(qdict, opt_renames, errp)) { ret = -EINVAL; - goto finish; + goto fail; } - if (!qed_is_table_size_valid(table_size)) { - error_setg(errp, "QED table size must be within range [%u, %u] " - "and power of 2", - QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE); + + /* Create and open the file (protocol layer) */ + ret = bdrv_create_file(filename, opts, &local_err); + if (ret < 0) { + error_propagate(errp, local_err); + goto fail; + } + + bs = bdrv_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); + if (bs == NULL) { + ret = -EIO; + goto fail; + } + + /* Now get the QAPI type BlockdevCreateOptions */ + qdict_put_str(qdict, "driver", "qed"); + qdict_put_str(qdict, "file", bs->node_name); + + qobj = qdict_crumple(qdict, errp); + QDECREF(qdict); + qdict = qobject_to_qdict(qobj); + if (qdict == NULL) { ret = -EINVAL; - goto finish; + goto fail; } - if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) { - error_setg(errp, "QED image size must be a non-zero multiple of " - "cluster size and less than %" PRIu64 " bytes", - qed_max_image_size(cluster_size, table_size)); + + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err); + visit_free(v); + + if (local_err) { + error_propagate(errp, local_err); ret = -EINVAL; - goto finish; + goto fail; } - ret = qed_create(filename, cluster_size, image_size, table_size, - backing_file, backing_fmt, opts, errp); + /* Silently round up size */ + assert(create_options->driver == BLOCKDEV_DRIVER_QED); + create_options->u.qed.size = + ROUND_UP(create_options->u.qed.size, BDRV_SECTOR_SIZE); + + /* Create the qed image (format layer) */ + ret = bdrv_qed_co_create(create_options, errp); -finish: - g_free(backing_file); - g_free(backing_fmt); +fail: + QDECREF(qdict); + bdrv_unref(bs); + qapi_free_BlockdevCreateOptions(create_options); return ret; } @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_qed = { .bdrv_close = bdrv_qed_close, .bdrv_reopen_prepare = bdrv_qed_reopen_prepare, .bdrv_child_perm = bdrv_format_default_perms, + .bdrv_co_create = bdrv_qed_co_create, .bdrv_co_create_opts = bdrv_qed_co_create_opts, .bdrv_has_zero_init = bdrv_has_zero_init_1, .bdrv_co_block_status = bdrv_qed_co_block_status, -- 2.13.6 This makes the .bdrv_co_create(_opts) implementation of vdi look more like the other recently converted block drivers. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> --- block/vdi.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/block/vdi.c b/block/vdi.c index XXXXXXX..XXXXXXX 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, logout("\n"); - /* Read out options. */ + /* Validate options and set default values */ bytes = vdi_opts->size; if (vdi_opts->q_static) { image_type = VDI_TYPE_STATIC; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options, goto exit; } + /* Create BlockBackend to write to the image */ bs_file = bdrv_open_blockdev_ref(vdi_opts->file, errp); if (!bs_file) { ret = -EIO; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, Error *local_err = NULL; int ret; - /* Since CONFIG_VDI_BLOCK_SIZE is disabled by default, + /* Parse options and convert legacy syntax. + * + * Since CONFIG_VDI_BLOCK_SIZE is disabled by default, * cluster-size is not part of the QAPI schema; therefore we have * to parse it before creating the QAPI object. */ #if defined(CONFIG_VDI_BLOCK_SIZE) @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vdi_create_opts, true); + /* Create and open the file (protocol layer) */ ret = bdrv_create_file(filename, opts, errp); if (ret < 0) { goto done; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts, goto done; } + /* Silently round up size */ assert(create_options->driver == BLOCKDEV_DRIVER_VDI); create_options->u.vdi.size = ROUND_UP(create_options->u.vdi.size, BDRV_SECTOR_SIZE); + /* Create the vdi image (format layer) */ ret = vdi_co_do_create(create_options, block_size, errp); done: QDECREF(qdict); @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_vdi = { .bdrv_close = vdi_close, .bdrv_reopen_prepare = vdi_reopen_prepare, .bdrv_child_perm = bdrv_format_default_perms, - .bdrv_co_create_opts = vdi_co_create_opts, .bdrv_co_create = vdi_co_create, + .bdrv_co_create_opts = vdi_co_create_opts, .bdrv_has_zero_init = bdrv_has_zero_init_1, .bdrv_co_block_status = vdi_co_block_status, .bdrv_make_empty = vdi_make_empty, -- 2.13.6 This adds the .bdrv_co_create driver callback to vhdx, which enables image creation over QMP. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 40 +++++++++- block/vhdx.c | 216 ++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 203 insertions(+), 53 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 @@ '*static': 'bool' } } ## +# @BlockdevVhdxSubformat: +# +# @dynamic: Growing image file +# @fixed: Preallocated fixed-size image file +# +# Since: 2.12 +## +{ 'enum': 'BlockdevVhdxSubformat', + 'data': [ 'dynamic', 'fixed' ] } + +## +# @BlockdevCreateOptionsVhdx: +# +# Driver specific image creation options for vhdx. +# +# @file Node to create the image format on +# @size Size of the virtual disk in bytes +# @log-size Log size in bytes, must be a multiple of 1 MB +# (default: 1 MB) +# @block-size Block size in bytes, must be a multiple of 1 MB and not +# larger than 256 MB (default: automatically choose a block +# size depending on the image size) +# @subformat vhdx subformat (default: dynamic) +# @block-state-zero Force use of payload blocks of type 'ZERO'. Non-standard, +# but default. Do not set to 'off' when using 'qemu-img +# convert' with subformat=dynamic. +# +# Since: 2.12 +## +{ 'struct': 'BlockdevCreateOptionsVhdx', + 'data': { 'file': 'BlockdevRef', + 'size': 'size', + '*log-size': 'size', + '*block-size': 'size', + '*subformat': 'BlockdevVhdxSubformat', + '*block-state-zero': 'bool' } } + +## # @BlockdevCreateNotSupported: # # This is used for all drivers that don't support creating images. @@ -XXX,XX +XXX,XX @@ 'ssh': 'BlockdevCreateOptionsSsh', 'throttle': 'BlockdevCreateNotSupported', 'vdi': 'BlockdevCreateOptionsVdi', - 'vhdx': 'BlockdevCreateNotSupported', + 'vhdx': 'BlockdevCreateOptionsVhdx', 'vmdk': 'BlockdevCreateNotSupported', 'vpc': 'BlockdevCreateNotSupported', 'vvfat': 'BlockdevCreateNotSupported', diff --git a/block/vhdx.c b/block/vhdx.c index XXXXXXX..XXXXXXX 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -XXX,XX +XXX,XX @@ #include "block/vhdx.h" #include "migration/blocker.h" #include "qemu/uuid.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qobject-input-visitor.h" +#include "qapi/qapi-visit-block-core.h" /* Options for VHDX creation */ @@ -XXX,XX +XXX,XX @@ typedef enum VHDXImageType { VHDX_TYPE_DIFFERENCING, /* Currently unsupported */ } VHDXImageType; +static QemuOptsList vhdx_create_opts; + /* Several metadata and region table data entries are identified by * guids in a MS-specific GUID format. */ @@ -XXX,XX +XXX,XX @@ exit: * .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------. * 1MB */ -static int coroutine_fn vhdx_co_create_opts(const char *filename, QemuOpts *opts, - Error **errp) +static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts, + Error **errp) { + BlockdevCreateOptionsVhdx *vhdx_opts; + BlockBackend *blk = NULL; + BlockDriverState *bs = NULL; + int ret = 0; - uint64_t image_size = (uint64_t) 2 * GiB; - uint32_t log_size = 1 * MiB; - uint32_t block_size = 0; + uint64_t image_size; + uint32_t log_size; + uint32_t block_size; uint64_t signature; uint64_t metadata_offset; bool use_zero_blocks = false; gunichar2 *creator = NULL; glong creator_items; - BlockBackend *blk; - char *type = NULL; VHDXImageType image_type; - Error *local_err = NULL; - image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); - log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0); - block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0); - type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT); - use_zero_blocks = qemu_opt_get_bool_del(opts, VHDX_BLOCK_OPT_ZERO, true); + assert(opts->driver == BLOCKDEV_DRIVER_VHDX); + vhdx_opts = &opts->u.vhdx; + /* Validate options and set default values */ + image_size = vhdx_opts->size; if (image_size > VHDX_MAX_IMAGE_SIZE) { error_setg_errno(errp, EINVAL, "Image size too large; max of 64TB"); - ret = -EINVAL; - goto exit; + return -EINVAL; } - if (type == NULL) { - type = g_strdup("dynamic"); + if (!vhdx_opts->has_log_size) { + log_size = DEFAULT_LOG_SIZE; + } else { + log_size = vhdx_opts->log_size; + } + if (log_size < MiB || (log_size % MiB) != 0) { + error_setg_errno(errp, EINVAL, "Log size must be a multiple of 1 MB"); + return -EINVAL; } - if (!strcmp(type, "dynamic")) { + if (!vhdx_opts->has_block_state_zero) { + use_zero_blocks = true; + } else { + use_zero_blocks = vhdx_opts->block_state_zero; + } + + if (!vhdx_opts->has_subformat) { + vhdx_opts->subformat = BLOCKDEV_VHDX_SUBFORMAT_DYNAMIC; + } + + switch (vhdx_opts->subformat) { + case BLOCKDEV_VHDX_SUBFORMAT_DYNAMIC: image_type = VHDX_TYPE_DYNAMIC; - } else if (!strcmp(type, "fixed")) { + break; + case BLOCKDEV_VHDX_SUBFORMAT_FIXED: image_type = VHDX_TYPE_FIXED; - } else if (!strcmp(type, "differencing")) { - error_setg_errno(errp, ENOTSUP, - "Differencing files not yet supported"); - ret = -ENOTSUP; - goto exit; - } else { - error_setg(errp, "Invalid subformat '%s'", type); - ret = -EINVAL; - goto exit; + break; + default: + g_assert_not_reached(); } /* These are pretty arbitrary, and mainly designed to keep the BAT * size reasonable to load into RAM */ - if (block_size == 0) { + if (vhdx_opts->has_block_size) { + block_size = vhdx_opts->block_size; + } else { if (image_size > 32 * TiB) { block_size = 64 * MiB; } else if (image_size > (uint64_t) 100 * GiB) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vhdx_co_create_opts(const char *filename, QemuOpts *opts } } - - /* make the log size close to what was specified, but must be - * min 1MB, and multiple of 1MB */ - log_size = ROUND_UP(log_size, MiB); - - block_size = ROUND_UP(block_size, MiB); - block_size = block_size > VHDX_BLOCK_SIZE_MAX ? VHDX_BLOCK_SIZE_MAX : - block_size; - - ret = bdrv_create_file(filename, opts, &local_err); - if (ret < 0) { - error_propagate(errp, local_err); - goto exit; + if (block_size < MiB || (block_size % MiB) != 0) { + error_setg_errno(errp, EINVAL, "Block size must be a multiple of 1 MB"); + return -EINVAL; + } + if (block_size > VHDX_BLOCK_SIZE_MAX) { + error_setg_errno(errp, EINVAL, "Block size must not exceed %d", + VHDX_BLOCK_SIZE_MAX); + return -EINVAL; } - blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, - &local_err); - if (blk == NULL) { - error_propagate(errp, local_err); - ret = -EIO; - goto exit; + /* Create BlockBackend to write to the image */ + bs = bdrv_open_blockdev_ref(vhdx_opts->file, errp); + if (bs == NULL) { + return -EIO; } + blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL); + ret = blk_insert_bs(blk, bs, errp); + if (ret < 0) { + goto delete_and_exit; + } blk_set_allow_write_beyond_eof(blk, true); /* Create (A) */ @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vhdx_co_create_opts(const char *filename, QemuOpts *opts delete_and_exit: blk_unref(blk); -exit: - g_free(type); + bdrv_unref(bs); g_free(creator); return ret; } +static int coroutine_fn vhdx_co_create_opts(const char *filename, + QemuOpts *opts, + Error **errp) +{ + BlockdevCreateOptions *create_options = NULL; + QDict *qdict = NULL; + QObject *qobj; + Visitor *v; + BlockDriverState *bs = NULL; + Error *local_err = NULL; + int ret; + + static const QDictRenames opt_renames[] = { + { VHDX_BLOCK_OPT_LOG_SIZE, "log-size" }, + { VHDX_BLOCK_OPT_BLOCK_SIZE, "block-size" }, + { VHDX_BLOCK_OPT_ZERO, "block-state-zero" }, + { NULL, NULL }, + }; + + /* Parse options and convert legacy syntax */ + qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vhdx_create_opts, true); + + if (!qdict_rename_keys(qdict, opt_renames, errp)) { + ret = -EINVAL; + goto fail; + } + + /* Create and open the file (protocol layer) */ + ret = bdrv_create_file(filename, opts, &local_err); + if (ret < 0) { + error_propagate(errp, local_err); + goto fail; + } + + bs = bdrv_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); + if (bs == NULL) { + ret = -EIO; + goto fail; + } + + /* Now get the QAPI type BlockdevCreateOptions */ + qdict_put_str(qdict, "driver", "vhdx"); + qdict_put_str(qdict, "file", bs->node_name); + + qobj = qdict_crumple(qdict, errp); + QDECREF(qdict); + qdict = qobject_to_qdict(qobj); + if (qdict == NULL) { + ret = -EINVAL; + goto fail; + } + + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err); + visit_free(v); + + if (local_err) { + error_propagate(errp, local_err); + ret = -EINVAL; + goto fail; + } + + /* Silently round up sizes: + * The image size is rounded to 512 bytes. Make the block and log size + * close to what was specified, but must be at least 1MB, and a multiple of + * 1 MB. Also respect VHDX_BLOCK_SIZE_MAX for block sizes. block_size = 0 + * means auto, which is represented by a missing key in QAPI. */ + assert(create_options->driver == BLOCKDEV_DRIVER_VHDX); + create_options->u.vhdx.size = + ROUND_UP(create_options->u.vhdx.size, BDRV_SECTOR_SIZE); + + if (create_options->u.vhdx.has_log_size) { + create_options->u.vhdx.log_size = + ROUND_UP(create_options->u.vhdx.log_size, MiB); + } + if (create_options->u.vhdx.has_block_size) { + create_options->u.vhdx.block_size = + ROUND_UP(create_options->u.vhdx.block_size, MiB); + + if (create_options->u.vhdx.block_size == 0) { + create_options->u.vhdx.has_block_size = false; + } + if (create_options->u.vhdx.block_size > VHDX_BLOCK_SIZE_MAX) { + create_options->u.vhdx.block_size = VHDX_BLOCK_SIZE_MAX; + } + } + + /* Create the vhdx image (format layer) */ + ret = vhdx_co_create(create_options, errp); + +fail: + QDECREF(qdict); + bdrv_unref(bs); + qapi_free_BlockdevCreateOptions(create_options); + return ret; +} + /* If opened r/w, the VHDX driver will automatically replay the log, * if one is present, inside the vhdx_open() call. * @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_vhdx = { .bdrv_child_perm = bdrv_format_default_perms, .bdrv_co_readv = vhdx_co_readv, .bdrv_co_writev = vhdx_co_writev, + .bdrv_co_create = vhdx_co_create, .bdrv_co_create_opts = vhdx_co_create_opts, .bdrv_get_info = vhdx_get_info, .bdrv_co_check = vhdx_co_check, -- 2.13.6 This adds the .bdrv_co_create driver callback to vpc, which enables image creation over QMP. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> --- qapi/block-core.json | 33 ++++++++++- block/vpc.c | 152 ++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 147 insertions(+), 38 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 @@ '*block-state-zero': 'bool' } } ## +# @BlockdevVpcSubformat: +# +# @dynamic: Growing image file +# @fixed: Preallocated fixed-size image file +# +# Since: 2.12 +## +{ 'enum': 'BlockdevVpcSubformat', + 'data': [ 'dynamic', 'fixed' ] } + +## +# @BlockdevCreateOptionsVpc: +# +# Driver specific image creation options for vpc (VHD). +# +# @file Node to create the image format on +# @size Size of the virtual disk in bytes +# @subformat vhdx subformat (default: dynamic) +# @force-size Force use of the exact byte size instead of rounding to the +# next size that can be represented in CHS geometry +# (default: false) +# +# Since: 2.12 +## +{ 'struct': 'BlockdevCreateOptionsVpc', + 'data': { 'file': 'BlockdevRef', + 'size': 'size', + '*subformat': 'BlockdevVpcSubformat', + '*force-size': 'bool' } } + +## # @BlockdevCreateNotSupported: # # This is used for all drivers that don't support creating images. @@ -XXX,XX +XXX,XX @@ 'vdi': 'BlockdevCreateOptionsVdi', 'vhdx': 'BlockdevCreateOptionsVhdx', 'vmdk': 'BlockdevCreateNotSupported', - 'vpc': 'BlockdevCreateNotSupported', + 'vpc': 'BlockdevCreateOptionsVpc', 'vvfat': 'BlockdevCreateNotSupported', 'vxhs': 'BlockdevCreateNotSupported' } } diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ #include "migration/blocker.h" #include "qemu/bswap.h" #include "qemu/uuid.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qobject-input-visitor.h" +#include "qapi/qapi-visit-block-core.h" /**************************************************************/ @@ -XXX,XX +XXX,XX @@ static QemuOptsList vpc_runtime_opts = { } }; +static QemuOptsList vpc_create_opts; + static uint32_t vpc_checksum(uint8_t* buf, size_t size) { uint32_t res = 0; @@ -XXX,XX +XXX,XX @@ static int create_fixed_disk(BlockBackend *blk, uint8_t *buf, return ret; } -static int coroutine_fn vpc_co_create_opts(const char *filename, QemuOpts *opts, - Error **errp) +static int coroutine_fn vpc_co_create(BlockdevCreateOptions *opts, + Error **errp) { + BlockdevCreateOptionsVpc *vpc_opts; + BlockBackend *blk = NULL; + BlockDriverState *bs = NULL; + uint8_t buf[1024]; VHDFooter *footer = (VHDFooter *) buf; - char *disk_type_param; int i; uint16_t cyls = 0; uint8_t heads = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_create_opts(const char *filename, QemuOpts *opts, int64_t total_size; int disk_type; int ret = -EIO; - bool force_size; - Error *local_err = NULL; - BlockBackend *blk = NULL; - /* Read out options */ - total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); - disk_type_param = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT); - if (disk_type_param) { - if (!strcmp(disk_type_param, "dynamic")) { - disk_type = VHD_DYNAMIC; - } else if (!strcmp(disk_type_param, "fixed")) { - disk_type = VHD_FIXED; - } else { - error_setg(errp, "Invalid disk type, %s", disk_type_param); - ret = -EINVAL; - goto out; - } - } else { + assert(opts->driver == BLOCKDEV_DRIVER_VPC); + vpc_opts = &opts->u.vpc; + + /* Validate options and set default values */ + total_size = vpc_opts->size; + + if (!vpc_opts->has_subformat) { + vpc_opts->subformat = BLOCKDEV_VPC_SUBFORMAT_DYNAMIC; + } + switch (vpc_opts->subformat) { + case BLOCKDEV_VPC_SUBFORMAT_DYNAMIC: disk_type = VHD_DYNAMIC; + break; + case BLOCKDEV_VPC_SUBFORMAT_FIXED: + disk_type = VHD_FIXED; + break; + default: + g_assert_not_reached(); } - force_size = qemu_opt_get_bool_del(opts, VPC_OPT_FORCE_SIZE, false); - - ret = bdrv_create_file(filename, opts, &local_err); - if (ret < 0) { - error_propagate(errp, local_err); - goto out; + /* Create BlockBackend to write to the image */ + bs = bdrv_open_blockdev_ref(vpc_opts->file, errp); + if (bs == NULL) { + return -EIO; } - blk = blk_new_open(filename, NULL, NULL, - BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, - &local_err); - if (blk == NULL) { - error_propagate(errp, local_err); - ret = -EIO; + blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL); + ret = blk_insert_bs(blk, bs, errp); + if (ret < 0) { goto out; } - blk_set_allow_write_beyond_eof(blk, true); /* @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_create_opts(const char *filename, QemuOpts *opts, * we set the geometry to 65535 x 16 x 255 (CxHxS) sectors and use * the image size from the VHD footer to calculate total_sectors. */ - if (force_size) { + if (vpc_opts->force_size) { /* This will force the use of total_size for sector count, below */ cyls = VHD_CHS_MAX_C; heads = VHD_CHS_MAX_H; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_create_opts(const char *filename, QemuOpts *opts, memset(buf, 0, 1024); memcpy(footer->creator, "conectix", 8); - if (force_size) { + if (vpc_opts->force_size) { memcpy(footer->creator_app, "qem2", 4); } else { memcpy(footer->creator_app, "qemu", 4); @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_create_opts(const char *filename, QemuOpts *opts, out: blk_unref(blk); - g_free(disk_type_param); + bdrv_unref(bs); + return ret; +} + +static int coroutine_fn vpc_co_create_opts(const char *filename, + QemuOpts *opts, Error **errp) +{ + BlockdevCreateOptions *create_options = NULL; + QDict *qdict = NULL; + QObject *qobj; + Visitor *v; + BlockDriverState *bs = NULL; + Error *local_err = NULL; + int ret; + + static const QDictRenames opt_renames[] = { + { VPC_OPT_FORCE_SIZE, "force-size" }, + { NULL, NULL }, + }; + + /* Parse options and convert legacy syntax */ + qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vpc_create_opts, true); + + if (!qdict_rename_keys(qdict, opt_renames, errp)) { + ret = -EINVAL; + goto fail; + } + + /* Create and open the file (protocol layer) */ + ret = bdrv_create_file(filename, opts, &local_err); + if (ret < 0) { + error_propagate(errp, local_err); + goto fail; + } + + bs = bdrv_open(filename, NULL, NULL, + BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp); + if (bs == NULL) { + ret = -EIO; + goto fail; + } + + /* Now get the QAPI type BlockdevCreateOptions */ + qdict_put_str(qdict, "driver", "vpc"); + qdict_put_str(qdict, "file", bs->node_name); + + qobj = qdict_crumple(qdict, errp); + QDECREF(qdict); + qdict = qobject_to_qdict(qobj); + if (qdict == NULL) { + ret = -EINVAL; + goto fail; + } + + v = qobject_input_visitor_new_keyval(QOBJECT(qdict)); + visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err); + visit_free(v); + + if (local_err) { + error_propagate(errp, local_err); + ret = -EINVAL; + goto fail; + } + + /* Silently round up size */ + assert(create_options->driver == BLOCKDEV_DRIVER_VPC); + create_options->u.vpc.size = + ROUND_UP(create_options->u.vpc.size, BDRV_SECTOR_SIZE); + + /* Create the vpc image (format layer) */ + ret = vpc_co_create(create_options, errp); + +fail: + QDECREF(qdict); + bdrv_unref(bs); + qapi_free_BlockdevCreateOptions(create_options); return ret; } + static int vpc_has_zero_init(BlockDriverState *bs) { BDRVVPCState *s = bs->opaque; @@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_vpc = { .bdrv_close = vpc_close, .bdrv_reopen_prepare = vpc_reopen_prepare, .bdrv_child_perm = bdrv_format_default_perms, + .bdrv_co_create = vpc_co_create, .bdrv_co_create_opts = vpc_co_create_opts, .bdrv_co_preadv = vpc_co_preadv, -- 2.13.6 Perform the rounding to match a CHS geometry only in the legacy code path in .bdrv_co_create_opts. QMP now requires that the user already passes a CHS aligned image size, unless force-size=true is given. CHS alignment is required to make the image compatible with Virtual PC, but not for use with newer Microsoft hypervisors. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> --- block/vpc.c | 113 +++++++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 82 insertions(+), 31 deletions(-) diff --git a/block/vpc.c b/block/vpc.c index XXXXXXX..XXXXXXX 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -XXX,XX +XXX,XX @@ static int create_fixed_disk(BlockBackend *blk, uint8_t *buf, return ret; } +static int calculate_rounded_image_size(BlockdevCreateOptionsVpc *vpc_opts, + uint16_t *out_cyls, + uint8_t *out_heads, + uint8_t *out_secs_per_cyl, + int64_t *out_total_sectors, + Error **errp) +{ + int64_t total_size = vpc_opts->size; + uint16_t cyls = 0; + uint8_t heads = 0; + uint8_t secs_per_cyl = 0; + int64_t total_sectors; + int i; + + /* + * Calculate matching total_size and geometry. Increase the number of + * sectors requested until we get enough (or fail). This ensures that + * qemu-img convert doesn't truncate images, but rather rounds up. + * + * If the image size can't be represented by a spec conformant CHS geometry, + * we set the geometry to 65535 x 16 x 255 (CxHxS) sectors and use + * the image size from the VHD footer to calculate total_sectors. + */ + if (vpc_opts->force_size) { + /* This will force the use of total_size for sector count, below */ + cyls = VHD_CHS_MAX_C; + heads = VHD_CHS_MAX_H; + secs_per_cyl = VHD_CHS_MAX_S; + } else { + total_sectors = MIN(VHD_MAX_GEOMETRY, total_size / BDRV_SECTOR_SIZE); + for (i = 0; total_sectors > (int64_t)cyls * heads * secs_per_cyl; i++) { + calculate_geometry(total_sectors + i, &cyls, &heads, &secs_per_cyl); + } + } + + if ((int64_t)cyls * heads * secs_per_cyl == VHD_MAX_GEOMETRY) { + total_sectors = total_size / BDRV_SECTOR_SIZE; + /* Allow a maximum disk size of 2040 GiB */ + if (total_sectors > VHD_MAX_SECTORS) { + error_setg(errp, "Disk size is too large, max size is 2040 GiB"); + return -EFBIG; + } + } else { + total_sectors = (int64_t) cyls * heads * secs_per_cyl; + } + + *out_total_sectors = total_sectors; + if (out_cyls) { + *out_cyls = cyls; + *out_heads = heads; + *out_secs_per_cyl = secs_per_cyl; + } + + return 0; +} + static int coroutine_fn vpc_co_create(BlockdevCreateOptions *opts, Error **errp) { @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_create(BlockdevCreateOptions *opts, uint8_t buf[1024]; VHDFooter *footer = (VHDFooter *) buf; - int i; uint16_t cyls = 0; uint8_t heads = 0; uint8_t secs_per_cyl = 0; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_create(BlockdevCreateOptions *opts, } blk_set_allow_write_beyond_eof(blk, true); - /* - * Calculate matching total_size and geometry. Increase the number of - * sectors requested until we get enough (or fail). This ensures that - * qemu-img convert doesn't truncate images, but rather rounds up. - * - * If the image size can't be represented by a spec conformant CHS geometry, - * we set the geometry to 65535 x 16 x 255 (CxHxS) sectors and use - * the image size from the VHD footer to calculate total_sectors. - */ - if (vpc_opts->force_size) { - /* This will force the use of total_size for sector count, below */ - cyls = VHD_CHS_MAX_C; - heads = VHD_CHS_MAX_H; - secs_per_cyl = VHD_CHS_MAX_S; - } else { - total_sectors = MIN(VHD_MAX_GEOMETRY, total_size / BDRV_SECTOR_SIZE); - for (i = 0; total_sectors > (int64_t)cyls * heads * secs_per_cyl; i++) { - calculate_geometry(total_sectors + i, &cyls, &heads, &secs_per_cyl); - } + /* Get geometry and check that it matches the image size*/ + ret = calculate_rounded_image_size(vpc_opts, &cyls, &heads, &secs_per_cyl, + &total_sectors, errp); + if (ret < 0) { + goto out; } - if ((int64_t)cyls * heads * secs_per_cyl == VHD_MAX_GEOMETRY) { - total_sectors = total_size / BDRV_SECTOR_SIZE; - /* Allow a maximum disk size of 2040 GiB */ - if (total_sectors > VHD_MAX_SECTORS) { - error_setg(errp, "Disk size is too large, max size is 2040 GiB"); - ret = -EFBIG; - goto out; - } - } else { - total_sectors = (int64_t)cyls * heads * secs_per_cyl; - total_size = total_sectors * BDRV_SECTOR_SIZE; + if (total_size != total_sectors * BDRV_SECTOR_SIZE) { + error_setg(errp, "The requested image size cannot be represented in " + "CHS geometry"); + error_append_hint(errp, "Try size=%llu or force-size=on (the " + "latter makes the image incompatible with " + "Virtual PC)", + total_sectors * BDRV_SECTOR_SIZE); + ret = -EINVAL; + goto out; } /* Prepare the Hard Disk Footer */ @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vpc_co_create_opts(const char *filename, create_options->u.vpc.size = ROUND_UP(create_options->u.vpc.size, BDRV_SECTOR_SIZE); + if (!create_options->u.vpc.force_size) { + int64_t total_sectors; + ret = calculate_rounded_image_size(&create_options->u.vpc, NULL, NULL, + NULL, &total_sectors, errp); + if (ret < 0) { + goto fail; + } + + create_options->u.vpc.size = total_sectors * BDRV_SECTOR_SIZE; + } + + /* Create the vpc image (format layer) */ ret = vpc_co_create(create_options, errp); -- 2.13.6 From: Liang Li <liliang.opensource@gmail.com> When doing drive mirror to a low speed shared storage, if there was heavy BLK IO write workload in VM after the 'ready' event, drive mirror block job can't be canceled immediately, it would keep running until the heavy BLK IO workload stopped in the VM. Libvirt depends on the current block-job-cancel semantics, which is that when used without a flag after the 'ready' event, the command blocks until data is in sync. However, these semantics are awkward in other situations, for example, people may use drive mirror for realtime backups while still wanting to use block live migration. Libvirt cannot start a block live migration while another drive mirror is in progress, but the user would rather abandon the backup attempt as broken and proceed with the live migration than be stuck waiting for the current drive mirror backup to finish. The drive-mirror command already includes a 'force' flag, which libvirt does not use, although it documented the flag as only being useful to quit a job which is paused. However, since quitting a paused job has the same effect as abandoning a backup in a non-paused job (namely, the destination file is not in sync, and the command completes immediately), we can just improve the documentation to make the force flag obviously useful. Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Jeff Cody <jcody@redhat.com> Cc: Kevin Wolf <kwolf@redhat.com> Cc: Max Reitz <mreitz@redhat.com> Cc: Eric Blake <eblake@redhat.com> Cc: John Snow <jsnow@redhat.com> Reported-by: Huaitong Han <huanhuaitong@didichuxing.com> Signed-off-by: Huaitong Han <huanhuaitong@didichuxing.com> Signed-off-by: Liang Li <liliangleo@didichuxing.com> Signed-off-by: Jeff Cody <jcody@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 5 +++-- include/block/blockjob.h | 12 ++++++++++-- block/mirror.c | 10 ++++------ blockdev.c | 4 ++-- blockjob.c | 16 +++++++++------- tests/test-blockjob-txn.c | 8 ++++---- hmp-commands.hx | 3 ++- 7 files changed, 34 insertions(+), 24 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 @@ # the name of the parameter), but since QEMU 2.7 it can have # other values. # -# @force: whether to allow cancellation of a paused job (default -# false). Since 1.3. +# @force: If true, and the job has already emitted the event BLOCK_JOB_READY, +# abandon the job immediately (even if it is paused) instead of waiting +# for the destination to complete its final synchronization (since 1.3) # # Returns: Nothing on success # If no background operation is active on this device, DeviceNotActive diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { bool cancelled; /** + * Set to true if the job should abort immediately without waiting + * for data to be in sync. + */ + bool force; + + /** * Counter for pause request. If non-zero, the block job is either paused, * or if busy == true will pause itself as soon as possible. */ @@ -XXX,XX +XXX,XX @@ void block_job_start(BlockJob *job); /** * block_job_cancel: * @job: The job to be canceled. + * @force: Quit a job without waiting for data to be in sync. * * Asynchronously cancel the specified job. */ -void block_job_cancel(BlockJob *job); +void block_job_cancel(BlockJob *job, bool force); /** * block_job_complete: @@ -XXX,XX +XXX,XX @@ void block_job_user_resume(BlockJob *job, Error **errp); /** * block_job_user_cancel: * @job: The job to be cancelled. + * @force: Quit a job without waiting for data to be in sync. * * Cancels the specified job, but may refuse to do so if the * operation isn't currently meaningful. */ -void block_job_user_cancel(BlockJob *job, Error **errp); +void block_job_user_cancel(BlockJob *job, bool force, Error **errp); /** * block_job_cancel_sync: diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static void coroutine_fn mirror_run(void *opaque) ret = 0; trace_mirror_before_sleep(s, cnt, s->synced, delay_ns); - if (!s->synced) { - block_job_sleep_ns(&s->common, delay_ns); - if (block_job_is_cancelled(&s->common)) { - break; - } + if (block_job_is_cancelled(&s->common) && s->common.force) { + break; } else if (!should_complete) { delay_ns = (s->in_flight == 0 && cnt == 0 ? SLICE_TIME : 0); block_job_sleep_ns(&s->common, delay_ns); @@ -XXX,XX +XXX,XX @@ immediate_exit: * or it was cancelled prematurely so that we do not guarantee that * the target is a copy of the source. */ - assert(ret < 0 || (!s->synced && block_job_is_cancelled(&s->common))); + assert(ret < 0 || ((s->common.force || !s->synced) && + block_job_is_cancelled(&s->common))); assert(need_drain); mirror_wait_for_all_io(s); } diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void blockdev_mark_auto_del(BlockBackend *blk) aio_context_acquire(aio_context); if (bs->job) { - block_job_cancel(bs->job); + block_job_cancel(bs->job, false); } aio_context_release(aio_context); @@ -XXX,XX +XXX,XX @@ void qmp_block_job_cancel(const char *device, } trace_qmp_block_job_cancel(job); - block_job_user_cancel(job, errp); + block_job_user_cancel(job, force, errp); out: aio_context_release(aio_context); } diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static int block_job_finalize_single(BlockJob *job) return 0; } -static void block_job_cancel_async(BlockJob *job) +static void block_job_cancel_async(BlockJob *job, bool force) { if (job->iostatus != BLOCK_DEVICE_IO_STATUS_OK) { block_job_iostatus_reset(job); @@ -XXX,XX +XXX,XX @@ static void block_job_cancel_async(BlockJob *job) job->pause_count--; } job->cancelled = true; + /* To prevent 'force == false' overriding a previous 'force == true' */ + job->force |= force; } static int block_job_txn_apply(BlockJobTxn *txn, int fn(BlockJob *), bool lock) @@ -XXX,XX +XXX,XX @@ static void block_job_completed_txn_abort(BlockJob *job) * on the caller, so leave it. */ QLIST_FOREACH(other_job, &txn->jobs, txn_list) { if (other_job != job) { - block_job_cancel_async(other_job); + block_job_cancel_async(other_job, false); } } while (!QLIST_EMPTY(&txn->jobs)) { @@ -XXX,XX +XXX,XX @@ void block_job_user_resume(BlockJob *job, Error **errp) block_job_resume(job); } -void block_job_cancel(BlockJob *job) +void block_job_cancel(BlockJob *job, bool force) { if (job->status == BLOCK_JOB_STATUS_CONCLUDED) { block_job_do_dismiss(job); return; } - block_job_cancel_async(job); + block_job_cancel_async(job, force); if (!block_job_started(job)) { block_job_completed(job, -ECANCELED); } else if (job->deferred_to_main_loop) { @@ -XXX,XX +XXX,XX @@ void block_job_cancel(BlockJob *job) } } -void block_job_user_cancel(BlockJob *job, Error **errp) +void block_job_user_cancel(BlockJob *job, bool force, Error **errp) { if (block_job_apply_verb(job, BLOCK_JOB_VERB_CANCEL, errp)) { return; } - block_job_cancel(job); + block_job_cancel(job, force); } /* A wrapper around block_job_cancel() taking an Error ** parameter so it may be @@ -XXX,XX +XXX,XX @@ void block_job_user_cancel(BlockJob *job, Error **errp) * function pointer casts there. */ static void block_job_cancel_err(BlockJob *job, Error **errp) { - block_job_cancel(job); + block_job_cancel(job, false); } int block_job_cancel_sync(BlockJob *job) diff --git a/tests/test-blockjob-txn.c b/tests/test-blockjob-txn.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-blockjob-txn.c +++ b/tests/test-blockjob-txn.c @@ -XXX,XX +XXX,XX @@ static void test_single_job(int expected) block_job_start(job); if (expected == -ECANCELED) { - block_job_cancel(job); + block_job_cancel(job, false); } while (result == -EINPROGRESS) { @@ -XXX,XX +XXX,XX @@ static void test_pair_jobs(int expected1, int expected2) block_job_txn_unref(txn); if (expected1 == -ECANCELED) { - block_job_cancel(job1); + block_job_cancel(job1, false); } if (expected2 == -ECANCELED) { - block_job_cancel(job2); + block_job_cancel(job2, false); } while (result1 == -EINPROGRESS || result2 == -EINPROGRESS) { @@ -XXX,XX +XXX,XX @@ static void test_pair_jobs_fail_cancel_race(void) block_job_start(job1); block_job_start(job2); - block_job_cancel(job1); + block_job_cancel(job1, false); /* Now make job2 finish before the main loop kicks jobs. This simulates * the race between a pending kick and another job completing. diff --git a/hmp-commands.hx b/hmp-commands.hx index XXXXXXX..XXXXXXX 100644 --- a/hmp-commands.hx +++ b/hmp-commands.hx @@ -XXX,XX +XXX,XX @@ ETEXI .args_type = "force:-f,device:B", .params = "[-f] device", .help = "stop an active background block operation (use -f" - "\n\t\t\t if the operation is currently paused)", + "\n\t\t\t if you want to abort the operation immediately" + "\n\t\t\t instead of keep running until data is in sync)", .cmd = hmp_block_job_cancel, }, -- 2.13.6 The following changes since commit f1d33f55c47dfdaf8daacd618588ad3ae4c452d1: Merge tag 'pull-testing-gdbstub-plugins-gitdm-061022-3' of https://github.com/stsquad/qemu into staging (2022-10-06 07:11:56 -0400) are available in the Git repository at: git://repo.or.cz/qemu/kevin.git tags/for-upstream for you to fetch changes up to a7ca2eb488ff149c898f43abe103f8bd8e3ca3c4: file-posix: Remove unused s->discard_zeroes (2022-10-07 12:11:41 +0200) ---------------------------------------------------------------- Block layer patches - job: replace AioContext lock with job_mutex - Fixes to make coroutine_fn annotations more accurate - QAPI schema: Fix incorrect example - Code cleanup ---------------------------------------------------------------- Alberto Faria (1): coroutine: Drop coroutine_fn annotation from qemu_coroutine_self() Emanuele Giuseppe Esposito (20): job.c: make job_mutex and job_lock/unlock() public job.h: categorize fields in struct Job job.c: API functions not used outside should be static aio-wait.h: introduce AIO_WAIT_WHILE_UNLOCKED job.c: add job_lock/unlock while keeping job.h intact job: move and update comments from blockjob.c blockjob: introduce block_job _locked() APIs jobs: add job lock in find_* functions jobs: use job locks also in the unit tests block/mirror.c: use of job helpers in drivers jobs: group together API calls under the same job lock jobs: protect job.aio_context with BQL and job_mutex blockjob.h: categorize fields in struct BlockJob blockjob: rename notifier callbacks as _locked blockjob: protect iostatus field in BlockJob struct job.h: categorize JobDriver callbacks that need the AioContext lock job.c: enable job lock/unlock and remove Aiocontext locks block_job_query: remove atomic read blockjob: remove unused functions job: remove unused functions Kevin Wolf (2): quorum: Remove unnecessary forward declaration file-posix: Remove unused s->discard_zeroes Marc-André Lureau (3): 9p: add missing coroutine_fn annotations migration: add missing coroutine_fn annotations test-coroutine: add missing coroutine_fn annotations Markus Armbruster (1): Revert "qapi: fix examples of blockdev-add with qcow2" Paolo Bonzini (23): block/nvme: separate nvme_get_free_req cases for coroutine/non-coroutine context block: add missing coroutine_fn annotations qcow2: remove incorrect coroutine_fn annotations nbd: remove incorrect coroutine_fn annotations coroutine: remove incorrect coroutine_fn annotations blkverify: add missing coroutine_fn annotations file-posix: add missing coroutine_fn annotations iscsi: add missing coroutine_fn annotations nbd: add missing coroutine_fn annotations nfs: add missing coroutine_fn annotations nvme: add missing coroutine_fn annotations parallels: add missing coroutine_fn annotations qcow2: add missing coroutine_fn annotations copy-before-write: add missing coroutine_fn annotations curl: add missing coroutine_fn annotations qed: add missing coroutine_fn annotations quorum: add missing coroutine_fn annotations throttle: add missing coroutine_fn annotations vmdk: add missing coroutine_fn annotations job: add missing coroutine_fn annotations coroutine-lock: add missing coroutine_fn annotations raw-format: add missing coroutine_fn annotations job: detect change of aiocontext within job coroutine qapi/block-core.json | 10 +- block/qcow2.h | 19 +- hw/9pfs/9p.h | 9 +- include/block/aio-wait.h | 17 +- include/block/blockjob.h | 59 +++- include/block/nbd.h | 2 +- include/qemu/coroutine.h | 4 +- include/qemu/job.h | 306 +++++++++++++----- block.c | 24 +- block/blkverify.c | 2 +- block/block-backend.c | 10 +- block/copy-before-write.c | 9 +- block/curl.c | 2 +- block/file-posix.c | 11 +- block/io.c | 22 +- block/iscsi.c | 3 +- block/mirror.c | 19 +- block/nbd.c | 11 +- block/nfs.c | 2 +- block/nvme.c | 54 ++-- block/parallels.c | 5 +- block/qcow2-cluster.c | 21 +- block/qcow2-refcount.c | 6 +- block/qcow2.c | 5 +- block/qed.c | 4 +- block/quorum.c | 38 +-- block/raw-format.c | 3 +- block/replication.c | 3 + block/throttle.c | 2 +- block/vmdk.c | 22 +- blockdev.c | 129 ++++---- blockjob.c | 132 ++++---- job-qmp.c | 92 +++--- job.c | 674 +++++++++++++++++++++++++-------------- migration/migration.c | 3 +- monitor/qmp-cmds.c | 7 +- qemu-img.c | 17 +- tests/unit/test-bdrv-drain.c | 80 +++-- tests/unit/test-block-iothread.c | 8 +- tests/unit/test-blockjob-txn.c | 24 +- tests/unit/test-blockjob.c | 136 ++++---- tests/unit/test-coroutine.c | 2 +- util/qemu-coroutine-lock.c | 14 +- util/qemu-coroutine.c | 2 +- 44 files changed, 1237 insertions(+), 787 deletions(-) From: Markus Armbruster <armbru@redhat.com> This reverts commit b6522938327141235b97ab38e40c6c4512587373. Kevin Wolf NAKed this patch, because: 'file' is a required member (defined in BlockdevOptionsGenericFormat), removing it makes the example invalid. 'data-file' is only an additional optional member to be used for external data files (i.e. when the guest data is kept separate from the metadata in the .qcow2 file). However, it had already been merged then. Revert. Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20220930171908.846769-1-armbru@redhat.com> Reviewed-by: Victor Toso <victortoso@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- qapi/block-core.json | 10 +++++----- 1 file changed, 5 insertions(+), 5 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 @@ # -> { "execute": "blockdev-add", # "arguments": { "driver": "qcow2", # "node-name": "node1534", -# "data-file": { "driver": "file", -# "filename": "hd1.qcow2" }, +# "file": { "driver": "file", +# "filename": "hd1.qcow2" }, # "backing": null } } # # <- { "return": {} } @@ -XXX,XX +XXX,XX @@ # "arguments": { # "driver": "qcow2", # "node-name": "test1", -# "data-file": { +# "file": { # "driver": "file", # "filename": "test.qcow2" # } @@ -XXX,XX +XXX,XX @@ # "cache": { # "direct": true # }, -# "data-file": { +# "file": { # "driver": "file", # "filename": "/tmp/test.qcow2" # }, @@ -XXX,XX +XXX,XX @@ # "arguments": { # "driver": "qcow2", # "node-name": "node0", -# "data-file": { +# "file": { # "driver": "file", # "filename": "test.qcow2" # } -- 2.37.3 From: Alberto Faria <afaria@redhat.com> qemu_coroutine_self() can be called from outside coroutine context, returning the leader coroutine, and several such invocations currently exist (mostly in qcow2 tracing calls). Signed-off-by: Alberto Faria <afaria@redhat.com> Message-Id: <20221005175209.975797-1-afaria@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/coroutine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co); /** * Get the currently executing coroutine */ -Coroutine *coroutine_fn qemu_coroutine_self(void); +Coroutine *qemu_coroutine_self(void); /** * Return whether or not currently inside a coroutine -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> nvme_get_free_req has very difference semantics when called in coroutine context (where it waits) and in non-coroutine context (where it doesn't). Split the two cases to make it clear what is being requested. Cc: qemu-block@nongnu.org Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-2-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/nvme.c | 48 ++++++++++++++++++++++++++++-------------------- 1 file changed, 28 insertions(+), 20 deletions(-) diff --git a/block/nvme.c b/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -XXX,XX +XXX,XX @@ static void nvme_kick(NVMeQueuePair *q) q->need_kick = 0; } -/* Find a free request element if any, otherwise: - * a) if in coroutine context, try to wait for one to become available; - * b) if not in coroutine, return NULL; - */ -static NVMeRequest *nvme_get_free_req(NVMeQueuePair *q) +static NVMeRequest *nvme_get_free_req_nofail_locked(NVMeQueuePair *q) { NVMeRequest *req; - qemu_mutex_lock(&q->lock); - - while (q->free_req_head == -1) { - if (qemu_in_coroutine()) { - trace_nvme_free_req_queue_wait(q->s, q->index); - qemu_co_queue_wait(&q->free_req_queue, &q->lock); - } else { - qemu_mutex_unlock(&q->lock); - return NULL; - } - } - req = &q->reqs[q->free_req_head]; q->free_req_head = req->free_req_next; req->free_req_next = -1; - - qemu_mutex_unlock(&q->lock); return req; } +/* Return a free request element if any, otherwise return NULL. */ +static NVMeRequest *nvme_get_free_req_nowait(NVMeQueuePair *q) +{ + QEMU_LOCK_GUARD(&q->lock); + if (q->free_req_head == -1) { + return NULL; + } + return nvme_get_free_req_nofail_locked(q); +} + +/* + * Wait for a free request to become available if necessary, then + * return it. + */ +static coroutine_fn NVMeRequest *nvme_get_free_req(NVMeQueuePair *q) +{ + QEMU_LOCK_GUARD(&q->lock); + + while (q->free_req_head == -1) { + trace_nvme_free_req_queue_wait(q->s, q->index); + qemu_co_queue_wait(&q->free_req_queue, &q->lock); + } + + return nvme_get_free_req_nofail_locked(q); +} + /* With q->lock */ static void nvme_put_free_req_locked(NVMeQueuePair *q, NVMeRequest *req) { @@ -XXX,XX +XXX,XX @@ static int nvme_admin_cmd_sync(BlockDriverState *bs, NvmeCmd *cmd) AioContext *aio_context = bdrv_get_aio_context(bs); NVMeRequest *req; int ret = -EINPROGRESS; - req = nvme_get_free_req(q); + req = nvme_get_free_req_nowait(q); if (!req) { return -EBUSY; } -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-3-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 7 ++++--- block/block-backend.c | 10 +++++----- block/io.c | 22 +++++++++++----------- 3 files changed, 20 insertions(+), 19 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static int64_t create_file_fallback_truncate(BlockBackend *blk, * Helper function for bdrv_create_file_fallback(): Zero the first * sector to remove any potentially pre-existing image header. */ -static int create_file_fallback_zero_first_sector(BlockBackend *blk, - int64_t current_size, - Error **errp) +static int coroutine_fn +create_file_fallback_zero_first_sector(BlockBackend *blk, + int64_t current_size, + Error **errp) { int64_t bytes_to_clear; int ret; diff --git a/block/block-backend.c b/block/block-backend.c index XXXXXXX..XXXXXXX 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -XXX,XX +XXX,XX @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, return &acb->common; } -static void blk_aio_read_entry(void *opaque) +static void coroutine_fn blk_aio_read_entry(void *opaque) { BlkAioEmAIOCB *acb = opaque; BlkRwCo *rwco = &acb->rwco; @@ -XXX,XX +XXX,XX @@ static void blk_aio_read_entry(void *opaque) blk_aio_complete(acb); } -static void blk_aio_write_entry(void *opaque) +static void coroutine_fn blk_aio_write_entry(void *opaque) { BlkAioEmAIOCB *acb = opaque; BlkRwCo *rwco = &acb->rwco; @@ -XXX,XX +XXX,XX @@ int coroutine_fn blk_co_ioctl(BlockBackend *blk, unsigned long int req, return ret; } -static void blk_aio_ioctl_entry(void *opaque) +static void coroutine_fn blk_aio_ioctl_entry(void *opaque) { BlkAioEmAIOCB *acb = opaque; BlkRwCo *rwco = &acb->rwco; @@ -XXX,XX +XXX,XX @@ blk_co_do_pdiscard(BlockBackend *blk, int64_t offset, int64_t bytes) return bdrv_co_pdiscard(blk->root, offset, bytes); } -static void blk_aio_pdiscard_entry(void *opaque) +static void coroutine_fn blk_aio_pdiscard_entry(void *opaque) { BlkAioEmAIOCB *acb = opaque; BlkRwCo *rwco = &acb->rwco; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn blk_co_do_flush(BlockBackend *blk) return bdrv_co_flush(blk_bs(blk)); } -static void blk_aio_flush_entry(void *opaque) +static void coroutine_fn blk_aio_flush_entry(void *opaque) { BlkAioEmAIOCB *acb = opaque; BlkRwCo *rwco = &acb->rwco; 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 tracked_request_end(BdrvTrackedRequest *req) /** * Add an active request to the tracked requests list */ -static void tracked_request_begin(BdrvTrackedRequest *req, - BlockDriverState *bs, - int64_t offset, - int64_t bytes, - enum BdrvTrackedRequestType type) +static void coroutine_fn tracked_request_begin(BdrvTrackedRequest *req, + BlockDriverState *bs, + int64_t offset, + int64_t bytes, + enum BdrvTrackedRequestType type) { bdrv_check_request(offset, bytes, &error_abort); @@ -XXX,XX +XXX,XX @@ static bool tracked_request_overlaps(BdrvTrackedRequest *req, } /* Called with self->bs->reqs_lock held */ -static BdrvTrackedRequest * +static coroutine_fn BdrvTrackedRequest * bdrv_find_conflicting_request(BdrvTrackedRequest *self) { BdrvTrackedRequest *req; @@ -XXX,XX +XXX,XX @@ static bool bdrv_init_padding(BlockDriverState *bs, return true; } -static int bdrv_padding_rmw_read(BdrvChild *child, - BdrvTrackedRequest *req, - BdrvRequestPadding *pad, - bool zero_middle) +static coroutine_fn int bdrv_padding_rmw_read(BdrvChild *child, + BdrvTrackedRequest *req, + BdrvRequestPadding *pad, + bool zero_middle) { QEMUIOVector local_qiov; BlockDriverState *bs = child->bs; @@ -XXX,XX +XXX,XX @@ out: return ret; } -int bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf) +int coroutine_fn bdrv_co_ioctl(BlockDriverState *bs, int req, void *buf) { BlockDriver *drv = bs->drv; CoroutineIOCompletion co = { -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> This is incorrect because qcow2_mark_clean() calls qcow2_flush_caches(). qcow2_mark_clean() is called from non-coroutine context in qcow2_inactivate() and qcow2_amend_options(). Reviewed-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-4-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.h | 4 ++-- block/qcow2-refcount.c | 4 ++-- 2 files changed, 4 insertions(+), 4 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 @@ void qcow2_free_any_cluster(BlockDriverState *bs, uint64_t l2_entry, int qcow2_update_snapshot_refcount(BlockDriverState *bs, int64_t l1_table_offset, int l1_size, int addend); -int coroutine_fn qcow2_flush_caches(BlockDriverState *bs); -int coroutine_fn qcow2_write_caches(BlockDriverState *bs); +int qcow2_flush_caches(BlockDriverState *bs); +int qcow2_write_caches(BlockDriverState *bs); int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix); 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 @@ void qcow2_free_any_cluster(BlockDriverState *bs, uint64_t l2_entry, } } -int coroutine_fn qcow2_write_caches(BlockDriverState *bs) +int qcow2_write_caches(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; int ret; @@ -XXX,XX +XXX,XX @@ int coroutine_fn qcow2_write_caches(BlockDriverState *bs) return 0; } -int coroutine_fn qcow2_flush_caches(BlockDriverState *bs) +int qcow2_flush_caches(BlockDriverState *bs) { int ret = qcow2_write_caches(bs); if (ret < 0) { -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> nbd_co_establish_connection_cancel() cancels a coroutine but is not called from coroutine context itself, for example in nbd_cancel_in_flight() and in timer callbacks reconnect_delay_timer_cb() and open_timer_cb(). Reviewed-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-5-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/nbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/block/nbd.h b/include/block/nbd.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -XXX,XX +XXX,XX @@ QIOChannel *coroutine_fn nbd_co_establish_connection(NBDClientConnection *conn, NBDExportInfo *info, bool blocking, Error **errp); -void coroutine_fn nbd_co_establish_connection_cancel(NBDClientConnection *conn); +void nbd_co_establish_connection_cancel(NBDClientConnection *conn); #endif -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> qemu_coroutine_get_aio_context inspects a coroutine, but it does not have to be called from the coroutine itself (or from any coroutine). Reviewed-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-6-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/coroutine.h | 2 +- util/qemu-coroutine.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -XXX,XX +XXX,XX @@ void coroutine_fn qemu_coroutine_yield(void); /** * Get the AioContext of the given coroutine */ -AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co); +AioContext *qemu_coroutine_get_aio_context(Coroutine *co); /** * Get the currently executing coroutine diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine.c +++ b/util/qemu-coroutine.c @@ -XXX,XX +XXX,XX @@ bool qemu_coroutine_entered(Coroutine *co) return co->caller; } -AioContext *coroutine_fn qemu_coroutine_get_aio_context(Coroutine *co) +AioContext *qemu_coroutine_get_aio_context(Coroutine *co) { return co->ctx; } -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-8-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/blkverify.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 @@ blkverify_co_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes, return blkverify_co_prwv(bs, &r, offset, bytes, qiov, qiov, flags, true); } -static int blkverify_co_flush(BlockDriverState *bs) +static int coroutine_fn blkverify_co_flush(BlockDriverState *bs) { BDRVBlkverifyState *s = bs->opaque; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-9-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/file-posix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ static void raw_aio_unplug(BlockDriverState *bs) #endif } -static int raw_co_flush_to_disk(BlockDriverState *bs) +static int coroutine_fn raw_co_flush_to_disk(BlockDriverState *bs) { BDRVRawState *s = bs->opaque; RawPosixAIOData acb; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-10-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/iscsi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/iscsi.c b/block/iscsi.c index XXXXXXX..XXXXXXX 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -XXX,XX +XXX,XX @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status, } } -static void iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask) +static void coroutine_fn +iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask) { *iTask = (struct IscsiTask) { .co = qemu_coroutine_self(), -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-11-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/nbd.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/block/nbd.c b/block/nbd.c index XXXXXXX..XXXXXXX 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -XXX,XX +XXX,XX @@ static void nbd_iter_request_error(NBDReplyChunkIter *iter, int ret) * nbd_reply_chunk_iter_receive * The pointer stored in @payload requires g_free() to free it. */ -static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s, - NBDReplyChunkIter *iter, - uint64_t handle, - QEMUIOVector *qiov, NBDReply *reply, - void **payload) +static bool coroutine_fn nbd_reply_chunk_iter_receive(BDRVNBDState *s, + NBDReplyChunkIter *iter, + uint64_t handle, + QEMUIOVector *qiov, + NBDReply *reply, + void **payload) { int ret, request_ret; NBDReply local_reply; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-12-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/nfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/nfs.c b/block/nfs.c index XXXXXXX..XXXXXXX 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -XXX,XX +XXX,XX @@ static void nfs_process_write(void *arg) qemu_mutex_unlock(&client->mutex); } -static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task) +static void coroutine_fn nfs_co_init_task(BlockDriverState *bs, NFSRPC *task) { *task = (NFSRPC) { .co = qemu_coroutine_self(), -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-13-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/nvme.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/nvme.c b/block/nvme.c index XXXXXXX..XXXXXXX 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -XXX,XX +XXX,XX @@ static inline bool nvme_qiov_aligned(BlockDriverState *bs, return true; } -static int nvme_co_prw(BlockDriverState *bs, uint64_t offset, uint64_t bytes, - QEMUIOVector *qiov, bool is_write, int flags) +static coroutine_fn int nvme_co_prw(BlockDriverState *bs, + uint64_t offset, uint64_t bytes, + QEMUIOVector *qiov, bool is_write, + int flags) { BDRVNVMeState *s = bs->opaque; int r; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-14-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/parallels.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/block/parallels.c b/block/parallels.c index XXXXXXX..XXXXXXX 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -XXX,XX +XXX,XX @@ static int64_t block_status(BDRVParallelsState *s, int64_t sector_num, return start_off; } -static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num, - int nb_sectors, int *pnum) +static coroutine_fn int64_t allocate_clusters(BlockDriverState *bs, + int64_t sector_num, + int nb_sectors, int *pnum) { int ret = 0; BDRVParallelsState *s = bs->opaque; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-15-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qcow2.h | 15 ++++++++------- block/qcow2-cluster.c | 21 ++++++++++++--------- block/qcow2-refcount.c | 2 +- block/qcow2.c | 5 +++-- 4 files changed, 24 insertions(+), 19 deletions(-) diff --git a/block/qcow2.h b/block/qcow2.h index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -XXX,XX +XXX,XX @@ int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order, void *cb_opaque, Error **errp); int qcow2_shrink_reftable(BlockDriverState *bs); int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size); -int qcow2_detect_metadata_preallocation(BlockDriverState *bs); +int coroutine_fn qcow2_detect_metadata_preallocation(BlockDriverState *bs); /* qcow2-cluster.c functions */ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, @@ -XXX,XX +XXX,XX @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num, int qcow2_get_host_offset(BlockDriverState *bs, uint64_t offset, unsigned int *bytes, uint64_t *host_offset, QCow2SubclusterType *subcluster_type); -int qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset, - unsigned int *bytes, uint64_t *host_offset, - QCowL2Meta **m); +int coroutine_fn qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset, + unsigned int *bytes, + uint64_t *host_offset, QCowL2Meta **m); int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, uint64_t offset, int compressed_size, @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, void qcow2_parse_compressed_l2_entry(BlockDriverState *bs, uint64_t l2_entry, uint64_t *coffset, int *csize); -int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m); +int coroutine_fn qcow2_alloc_cluster_link_l2(BlockDriverState *bs, + QCowL2Meta *m); void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m); int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset, uint64_t bytes, enum qcow2_discard_type type, bool full_discard); -int qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset, - uint64_t bytes, int flags); +int coroutine_fn qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, int flags); int qcow2_expand_zero_clusters(BlockDriverState *bs, BlockDriverAmendStatusCB *status_cb, diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -XXX,XX +XXX,XX @@ int qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, return 0; } -static int perform_cow(BlockDriverState *bs, QCowL2Meta *m) +static int coroutine_fn perform_cow(BlockDriverState *bs, QCowL2Meta *m) { BDRVQcow2State *s = bs->opaque; Qcow2COWRegion *start = &m->cow_start; @@ -XXX,XX +XXX,XX @@ fail: return ret; } -int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m) +int coroutine_fn qcow2_alloc_cluster_link_l2(BlockDriverState *bs, + QCowL2Meta *m) { BDRVQcow2State *s = bs->opaque; int i, j = 0, l2_index, ret; @@ -XXX,XX +XXX,XX @@ static int count_single_write_clusters(BlockDriverState *bs, int nb_clusters, * information on cluster allocation may be invalid now. The caller * must start over anyway, so consider *cur_bytes undefined. */ -static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset, - uint64_t *cur_bytes, QCowL2Meta **m) +static int coroutine_fn handle_dependencies(BlockDriverState *bs, + uint64_t guest_offset, + uint64_t *cur_bytes, QCowL2Meta **m) { BDRVQcow2State *s = bs->opaque; QCowL2Meta *old_alloc; @@ -XXX,XX +XXX,XX @@ out: * * Return 0 on success and -errno in error cases */ -int qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset, - unsigned int *bytes, uint64_t *host_offset, - QCowL2Meta **m) +int coroutine_fn qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset, + unsigned int *bytes, + uint64_t *host_offset, + QCowL2Meta **m) { BDRVQcow2State *s = bs->opaque; uint64_t start, remaining; @@ -XXX,XX +XXX,XX @@ out: return ret; } -int qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset, - uint64_t bytes, int flags) +int coroutine_fn qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, int flags) { BDRVQcow2State *s = bs->opaque; uint64_t end_offset = offset + bytes; 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 @@ int64_t qcow2_get_last_cluster(BlockDriverState *bs, int64_t size) return -EIO; } -int qcow2_detect_metadata_preallocation(BlockDriverState *bs) +int coroutine_fn qcow2_detect_metadata_preallocation(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; int64_t i, end_cluster, cluster_count = 0, threshold; diff --git a/block/qcow2.c b/block/qcow2.c index XXXXXXX..XXXXXXX 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -XXX,XX +XXX,XX @@ static bool merge_cow(uint64_t offset, unsigned bytes, * Return 1 if the COW regions read as zeroes, 0 if not, < 0 on error. * Note that returning 0 does not guarantee non-zero data. */ -static int is_zero_cow(BlockDriverState *bs, QCowL2Meta *m) +static int coroutine_fn is_zero_cow(BlockDriverState *bs, QCowL2Meta *m) { /* * This check is designed for optimization shortcut so it must be @@ -XXX,XX +XXX,XX @@ static int is_zero_cow(BlockDriverState *bs, QCowL2Meta *m) m->cow_end.nb_bytes); } -static int handle_alloc_space(BlockDriverState *bs, QCowL2Meta *l2meta) +static int coroutine_fn handle_alloc_space(BlockDriverState *bs, + QCowL2Meta *l2meta) { BDRVQcow2State *s = bs->opaque; QCowL2Meta *m; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-16-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/copy-before-write.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/block/copy-before-write.c b/block/copy-before-write.c index XXXXXXX..XXXXXXX 100644 --- a/block/copy-before-write.c +++ b/block/copy-before-write.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn cbw_co_flush(BlockDriverState *bs) * It's guaranteed that guest writes will not interact in the region until * cbw_snapshot_read_unlock() called. */ -static BlockReq *cbw_snapshot_read_lock(BlockDriverState *bs, - int64_t offset, int64_t bytes, - int64_t *pnum, BdrvChild **file) +static coroutine_fn BlockReq * +cbw_snapshot_read_lock(BlockDriverState *bs, int64_t offset, int64_t bytes, + int64_t *pnum, BdrvChild **file) { BDRVCopyBeforeWriteState *s = bs->opaque; BlockReq *req = g_new(BlockReq, 1); @@ -XXX,XX +XXX,XX @@ static BlockReq *cbw_snapshot_read_lock(BlockDriverState *bs, return req; } -static void cbw_snapshot_read_unlock(BlockDriverState *bs, BlockReq *req) +static coroutine_fn void +cbw_snapshot_read_unlock(BlockDriverState *bs, BlockReq *req) { BDRVCopyBeforeWriteState *s = bs->opaque; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-17-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/curl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/curl.c b/block/curl.c index XXXXXXX..XXXXXXX 100644 --- a/block/curl.c +++ b/block/curl.c @@ -XXX,XX +XXX,XX @@ out_noclean: return -EINVAL; } -static void curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb) +static void coroutine_fn curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb) { CURLState *state; int running; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-18-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/qed.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/qed.c b/block/qed.c index XXXXXXX..XXXXXXX 100644 --- a/block/qed.c +++ b/block/qed.c @@ -XXX,XX +XXX,XX @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s) return l2_table; } -static bool qed_plug_allocating_write_reqs(BDRVQEDState *s) +static bool coroutine_fn qed_plug_allocating_write_reqs(BDRVQEDState *s) { qemu_co_mutex_lock(&s->table_lock); @@ -XXX,XX +XXX,XX @@ static bool qed_plug_allocating_write_reqs(BDRVQEDState *s) return true; } -static void qed_unplug_allocating_write_reqs(BDRVQEDState *s) +static void coroutine_fn qed_unplug_allocating_write_reqs(BDRVQEDState *s) { qemu_co_mutex_lock(&s->table_lock); assert(s->allocating_write_reqs_plugged); -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-19-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 36 +++++++++++++++++++----------------- 1 file changed, 19 insertions(+), 17 deletions(-) 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_64bits_compare(QuorumVoteValue *a, QuorumVoteValue *b) return a->l == b->l; } -static QuorumAIOCB *quorum_aio_get(BlockDriverState *bs, - QEMUIOVector *qiov, - uint64_t offset, - uint64_t bytes, - int flags) +static QuorumAIOCB *coroutine_fn quorum_aio_get(BlockDriverState *bs, + QEMUIOVector *qiov, + uint64_t offset, uint64_t bytes, + int flags) { BDRVQuorumState *s = bs->opaque; QuorumAIOCB *acb = g_new(QuorumAIOCB, 1); @@ -XXX,XX +XXX,XX @@ static void quorum_report_bad_versions(BDRVQuorumState *s, } } -static void quorum_rewrite_entry(void *opaque) +static void coroutine_fn quorum_rewrite_entry(void *opaque) { QuorumCo *co = opaque; QuorumAIOCB *acb = co->acb; @@ -XXX,XX +XXX,XX @@ free_exit: quorum_free_vote_list(&acb->votes); } -static void read_quorum_children_entry(void *opaque) +static void coroutine_fn read_quorum_children_entry(void *opaque) { QuorumCo *co = opaque; QuorumAIOCB *acb = co->acb; @@ -XXX,XX +XXX,XX @@ static void read_quorum_children_entry(void *opaque) } } -static int read_quorum_children(QuorumAIOCB *acb) +static int coroutine_fn read_quorum_children(QuorumAIOCB *acb) { BDRVQuorumState *s = acb->bs->opaque; int i; @@ -XXX,XX +XXX,XX @@ static int read_quorum_children(QuorumAIOCB *acb) return acb->vote_ret; } -static int read_fifo_child(QuorumAIOCB *acb) +static int coroutine_fn read_fifo_child(QuorumAIOCB *acb) { BDRVQuorumState *s = acb->bs->opaque; int n, ret; @@ -XXX,XX +XXX,XX @@ static int read_fifo_child(QuorumAIOCB *acb) return ret; } -static int quorum_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes, - QEMUIOVector *qiov, BdrvRequestFlags flags) +static int coroutine_fn quorum_co_preadv(BlockDriverState *bs, + int64_t offset, int64_t bytes, + QEMUIOVector *qiov, + BdrvRequestFlags flags) { BDRVQuorumState *s = bs->opaque; QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes, flags); @@ -XXX,XX +XXX,XX @@ static int quorum_co_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes, return ret; } -static void write_quorum_entry(void *opaque) +static void coroutine_fn write_quorum_entry(void *opaque) { QuorumCo *co = opaque; QuorumAIOCB *acb = co->acb; @@ -XXX,XX +XXX,XX @@ static void write_quorum_entry(void *opaque) } } -static int quorum_co_pwritev(BlockDriverState *bs, int64_t offset, - int64_t bytes, QEMUIOVector *qiov, - BdrvRequestFlags flags) +static int coroutine_fn quorum_co_pwritev(BlockDriverState *bs, int64_t offset, + int64_t bytes, QEMUIOVector *qiov, + BdrvRequestFlags flags) { BDRVQuorumState *s = bs->opaque; QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes, flags); @@ -XXX,XX +XXX,XX @@ static int quorum_co_pwritev(BlockDriverState *bs, int64_t offset, return ret; } -static int quorum_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, - int64_t bytes, BdrvRequestFlags flags) +static int coroutine_fn quorum_co_pwrite_zeroes(BlockDriverState *bs, + int64_t offset, int64_t bytes, + BdrvRequestFlags flags) { return quorum_co_pwritev(bs, offset, bytes, NULL, -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-20-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/throttle.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/throttle.c b/block/throttle.c index XXXXXXX..XXXXXXX 100644 --- a/block/throttle.c +++ b/block/throttle.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn throttle_co_pwritev_compressed(BlockDriverState *bs, BDRV_REQ_WRITE_COMPRESSED); } -static int throttle_co_flush(BlockDriverState *bs) +static int coroutine_fn throttle_co_flush(BlockDriverState *bs) { return bdrv_co_flush(bs->file->bs); } -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-21-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/vmdk.c | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/block/vmdk.c b/block/vmdk.c index XXXXXXX..XXXXXXX 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn vmdk_co_block_status(BlockDriverState *bs, return ret; } -static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, - int64_t offset_in_cluster, QEMUIOVector *qiov, - uint64_t qiov_offset, uint64_t n_bytes, - uint64_t offset) +static int coroutine_fn +vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, + int64_t offset_in_cluster, QEMUIOVector *qiov, + uint64_t qiov_offset, uint64_t n_bytes, + uint64_t offset) { int ret; VmdkGrainMarker *data = NULL; @@ -XXX,XX +XXX,XX @@ static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset, return ret; } -static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, - int64_t offset_in_cluster, QEMUIOVector *qiov, - int bytes) +static int coroutine_fn +vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset, + int64_t offset_in_cluster, QEMUIOVector *qiov, + int bytes) { int ret; int cluster_bytes, buf_bytes; @@ -XXX,XX +XXX,XX @@ fail: * * Returns: error code with 0 for success. */ -static int vmdk_pwritev(BlockDriverState *bs, uint64_t offset, - uint64_t bytes, QEMUIOVector *qiov, - bool zeroed, bool zero_dry_run) +static int coroutine_fn vmdk_pwritev(BlockDriverState *bs, uint64_t offset, + uint64_t bytes, QEMUIOVector *qiov, + bool zeroed, bool zero_dry_run) { BDRVVmdkState *s = bs->opaque; VmdkExtent *extent = NULL; -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-22-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 2 +- job.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ void coroutine_fn job_pause_point(Job *job); * * Yield the job coroutine. */ -void job_yield(Job *job); +void coroutine_fn job_yield(Job *job); /** * @job: The job that calls the function. diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ void coroutine_fn job_pause_point(Job *job) } } -void job_yield(Job *job) +void coroutine_fn job_yield(Job *job) { assert(job->busy); -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-23-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- util/qemu-coroutine-lock.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/util/qemu-coroutine-lock.c b/util/qemu-coroutine-lock.c index XXXXXXX..XXXXXXX 100644 --- a/util/qemu-coroutine-lock.c +++ b/util/qemu-coroutine-lock.c @@ -XXX,XX +XXX,XX @@ typedef struct CoWaitRecord { QSLIST_ENTRY(CoWaitRecord) next; } CoWaitRecord; -static void push_waiter(CoMutex *mutex, CoWaitRecord *w) +static void coroutine_fn push_waiter(CoMutex *mutex, CoWaitRecord *w) { w->co = qemu_coroutine_self(); QSLIST_INSERT_HEAD_ATOMIC(&mutex->from_push, w, next); @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_init(CoRwlock *lock) } /* Releases the internal CoMutex. */ -static void qemu_co_rwlock_maybe_wake_one(CoRwlock *lock) +static void coroutine_fn qemu_co_rwlock_maybe_wake_one(CoRwlock *lock) { CoRwTicket *tkt = QSIMPLEQ_FIRST(&lock->tickets); Coroutine *co = NULL; @@ -XXX,XX +XXX,XX @@ static void qemu_co_rwlock_maybe_wake_one(CoRwlock *lock) } } -void qemu_co_rwlock_rdlock(CoRwlock *lock) +void coroutine_fn qemu_co_rwlock_rdlock(CoRwlock *lock) { Coroutine *self = qemu_coroutine_self(); @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_rdlock(CoRwlock *lock) self->locks_held++; } -void qemu_co_rwlock_unlock(CoRwlock *lock) +void coroutine_fn qemu_co_rwlock_unlock(CoRwlock *lock) { Coroutine *self = qemu_coroutine_self(); @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_unlock(CoRwlock *lock) qemu_co_rwlock_maybe_wake_one(lock); } -void qemu_co_rwlock_downgrade(CoRwlock *lock) +void coroutine_fn qemu_co_rwlock_downgrade(CoRwlock *lock) { qemu_co_mutex_lock(&lock->mutex); assert(lock->owners == -1); @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_downgrade(CoRwlock *lock) qemu_co_rwlock_maybe_wake_one(lock); } -void qemu_co_rwlock_wrlock(CoRwlock *lock) +void coroutine_fn qemu_co_rwlock_wrlock(CoRwlock *lock) { Coroutine *self = qemu_coroutine_self(); @@ -XXX,XX +XXX,XX @@ void qemu_co_rwlock_wrlock(CoRwlock *lock) self->locks_held++; } -void qemu_co_rwlock_upgrade(CoRwlock *lock) +void coroutine_fn qemu_co_rwlock_upgrade(CoRwlock *lock) { qemu_co_mutex_lock(&lock->mutex); assert(lock->owners > 0); -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-24-pbonzini@redhat.com> [kwolf: Fixed up coding style] Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/raw-format.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/raw-format.c b/block/raw-format.c index XXXXXXX..XXXXXXX 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -XXX,XX +XXX,XX @@ static void raw_lock_medium(BlockDriverState *bs, bool locked) bdrv_lock_medium(bs->file->bs, locked); } -static int raw_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf) +static int coroutine_fn raw_co_ioctl(BlockDriverState *bs, + unsigned long int req, void *buf) { BDRVRawState *s = bs->opaque; if (s->offset || s->has_size) { -- 2.37.3 From: Marc-André Lureau <marcandre.lureau@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com> Acked-by: Greg Kurz <groug@kaod.org> Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-25-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- hw/9pfs/9p.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/hw/9pfs/9p.h b/hw/9pfs/9p.h index XXXXXXX..XXXXXXX 100644 --- a/hw/9pfs/9p.h +++ b/hw/9pfs/9p.h @@ -XXX,XX +XXX,XX @@ typedef struct V9fsGetlock extern int open_fd_hw; extern int total_open_fd; -static inline void v9fs_path_write_lock(V9fsState *s) +static inline void coroutine_fn +v9fs_path_write_lock(V9fsState *s) { if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) { qemu_co_rwlock_wrlock(&s->rename_lock); } } -static inline void v9fs_path_read_lock(V9fsState *s) +static inline void coroutine_fn +v9fs_path_read_lock(V9fsState *s) { if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) { qemu_co_rwlock_rdlock(&s->rename_lock); } } -static inline void v9fs_path_unlock(V9fsState *s) +static inline void coroutine_fn +v9fs_path_unlock(V9fsState *s) { if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) { qemu_co_rwlock_unlock(&s->rename_lock); -- 2.37.3 From: Marc-André Lureau <marcandre.lureau@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-26-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- migration/migration.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/migration/migration.c b/migration/migration.c index XXXXXXX..XXXXXXX 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -XXX,XX +XXX,XX @@ static void process_incoming_migration_bh(void *opaque) migration_incoming_state_destroy(); } -static void process_incoming_migration_co(void *opaque) +static void coroutine_fn +process_incoming_migration_co(void *opaque) { MigrationIncomingState *mis = migration_incoming_get_current(); PostcopyState ps; -- 2.37.3 From: Marc-André Lureau <marcandre.lureau@redhat.com> Callers of coroutine_fn must be coroutine_fn themselves, or the call must be within "if (qemu_in_coroutine())". Apply coroutine_fn to functions where this holds. Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com> Reviewed-by: Alberto Faria <afaria@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220922084924.201610-27-pbonzini@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/unit/test-coroutine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/unit/test-coroutine.c b/tests/unit/test-coroutine.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-coroutine.c +++ b/tests/unit/test-coroutine.c @@ -XXX,XX +XXX,XX @@ static void perf_baseline(void) g_test_message("Function call %u iterations: %f s", maxcycles, duration); } -static __attribute__((noinline)) void perf_cost_func(void *opaque) +static __attribute__((noinline)) void coroutine_fn perf_cost_func(void *opaque) { qemu_coroutine_yield(); } -- 2.37.3 Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20221006122607.162769-1-kwolf@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/quorum.c | 2 -- 1 file changed, 2 deletions(-) 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_has_too_much_io_failed(QuorumAIOCB *acb) return false; } -static int read_fifo_child(QuorumAIOCB *acb); - static void quorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source) { int i; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> job mutex will be used to protect the job struct elements and list, replacing AioContext locks. Right now use a shared lock for all jobs, in order to keep things simple. Once the AioContext lock is gone, we can introduce per-job locks. To simplify the switch from aiocontext to job lock, introduce *nop* lock/unlock functions and macros. We want to always call job_lock/unlock outside the AioContext locks, and not vice-versa, otherwise we might get a deadlock. This is not straightforward to do, and that's why we start with nop functions. Once everything is protected by job_lock/unlock, we can change the nop into an actual mutex and remove the aiocontext lock. Since job_mutex is already being used, add static real_job_{lock/unlock} for the existing usage. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-2-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 24 ++++++++++++++++++++++++ job.c | 35 +++++++++++++++++++++++------------ 2 files changed, 47 insertions(+), 12 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ typedef enum JobCreateFlags { JOB_MANUAL_DISMISS = 0x04, } JobCreateFlags; +extern QemuMutex job_mutex; + +#define JOB_LOCK_GUARD() /* QEMU_LOCK_GUARD(&job_mutex) */ + +#define WITH_JOB_LOCK_GUARD() /* WITH_QEMU_LOCK_GUARD(&job_mutex) */ + +/** + * job_lock: + * + * Take the mutex protecting the list of jobs and their status. + * Most functions called by the monitor need to call job_lock + * and job_unlock manually. On the other hand, function called + * by the block jobs themselves and by the block layer will take the + * lock for you. + */ +void job_lock(void); + +/** + * job_unlock: + * + * Release the mutex protecting the list of jobs and their status. + */ +void job_unlock(void); + /** * Allocate and return a new job transaction. Jobs can be added to the * transaction using job_txn_add_job(). diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ #include "trace/trace-root.h" #include "qapi/qapi-events-job.h" +/* + * job_mutex protects the jobs list, but also makes the + * struct job fields thread-safe. + */ +QemuMutex job_mutex; + static QLIST_HEAD(, Job) jobs = QLIST_HEAD_INITIALIZER(jobs); /* Job State Transition Table */ @@ -XXX,XX +XXX,XX @@ struct JobTxn { int refcnt; }; -/* Right now, this mutex is only needed to synchronize accesses to job->busy - * and job->sleep_timer, such as concurrent calls to job_do_yield and - * job_enter. */ -static QemuMutex job_mutex; +void job_lock(void) +{ + /* nop */ +} + +void job_unlock(void) +{ + /* nop */ +} -static void job_lock(void) +static void real_job_lock(void) { qemu_mutex_lock(&job_mutex); } -static void job_unlock(void) +static void real_job_unlock(void) { qemu_mutex_unlock(&job_mutex); } @@ -XXX,XX +XXX,XX @@ void job_enter_cond(Job *job, bool(*fn)(Job *job)) return; } - job_lock(); + real_job_lock(); if (job->busy) { - job_unlock(); + real_job_unlock(); return; } if (fn && !fn(job)) { - job_unlock(); + real_job_unlock(); return; } assert(!job->deferred_to_main_loop); timer_del(&job->sleep_timer); job->busy = true; - job_unlock(); + real_job_unlock(); aio_co_enter(job->aio_context, job->co); } @@ -XXX,XX +XXX,XX @@ void job_enter(Job *job) * called explicitly. */ static void coroutine_fn job_do_yield(Job *job, uint64_t ns) { - job_lock(); + real_job_lock(); if (ns != -1) { timer_mod(&job->sleep_timer, ns); } job->busy = false; job_event_idle(job); - job_unlock(); + real_job_unlock(); qemu_coroutine_yield(); /* Set by job_enter_cond() before re-entering the coroutine. */ -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Categorize the fields in struct Job to understand which ones need to be protected by the job mutex and which don't. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220926093214.506243-3-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 61 +++++++++++++++++++++++++++------------------- 1 file changed, 36 insertions(+), 25 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ typedef struct JobTxn JobTxn; * Long-running operation. */ typedef struct Job { + + /* Fields set at initialization (job_create), and never modified */ + /** The ID of the job. May be NULL for internal jobs. */ char *id; - /** The type of this job. */ + /** + * The type of this job. + * All callbacks are called with job_mutex *not* held. + */ const JobDriver *driver; - /** Reference count of the block job */ - int refcnt; - - /** Current state; See @JobStatus for details. */ - JobStatus status; - - /** AioContext to run the job coroutine in */ - AioContext *aio_context; - /** * The coroutine that executes the job. If not NULL, it is reentered when * busy is false and the job is cancelled. + * Initialized in job_start() */ Coroutine *co; + /** True if this job should automatically finalize itself */ + bool auto_finalize; + + /** True if this job should automatically dismiss itself */ + bool auto_dismiss; + + /** The completion function that will be called when the job completes. */ + BlockCompletionFunc *cb; + + /** The opaque value that is passed to the completion function. */ + void *opaque; + + /* ProgressMeter API is thread-safe */ + ProgressMeter progress; + + + /** Protected by AioContext lock */ + + /** AioContext to run the job coroutine in */ + AioContext *aio_context; + + /** Reference count of the block job */ + int refcnt; + + /** Current state; See @JobStatus for details. */ + JobStatus status; + /** * Timer that is used by @job_sleep_ns. Accessed under job_mutex (in * job.c). @@ -XXX,XX +XXX,XX @@ typedef struct Job { /** Set to true when the job has deferred work to the main loop. */ bool deferred_to_main_loop; - /** True if this job should automatically finalize itself */ - bool auto_finalize; - - /** True if this job should automatically dismiss itself */ - bool auto_dismiss; - - ProgressMeter progress; - /** * Return code from @run and/or @prepare callback(s). * Not final until the job has reached the CONCLUDED status. @@ -XXX,XX +XXX,XX @@ typedef struct Job { */ Error *err; - /** The completion function that will be called when the job completes. */ - BlockCompletionFunc *cb; - - /** The opaque value that is passed to the completion function. */ - void *opaque; - /** Notifiers called when a cancelled job is finalised */ NotifierList on_finalize_cancelled; @@ -XXX,XX +XXX,XX @@ typedef struct Job { /** * Callbacks and other information about a Job driver. + * All callbacks are invoked with job_mutex *not* held. */ struct JobDriver { @@ -XXX,XX +XXX,XX @@ void coroutine_fn job_yield(Job *job); */ void coroutine_fn job_sleep_ns(Job *job, int64_t ns); - /** Returns the JobType of a given Job. */ JobType job_type(const Job *job); -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> job_event_* functions can all be static, as they are not used outside job.c. Same applies for job_txn_add_job(). Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220926093214.506243-4-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 18 ------------------ job.c | 22 +++++++++++++++++++--- 2 files changed, 19 insertions(+), 21 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ JobTxn *job_txn_new(void); */ void job_txn_unref(JobTxn *txn); -/** - * @txn: The transaction (may be NULL) - * @job: Job to add to the transaction - * - * Add @job to the transaction. The @job must not already be in a transaction. - * The caller must call either job_txn_unref() or job_completed() to release - * the reference that is automatically grabbed here. - * - * If @txn is NULL, the function does nothing. - */ -void job_txn_add_job(JobTxn *txn, Job *job); - /** * Create a new long-running job and return it. * @@ -XXX,XX +XXX,XX @@ void job_progress_set_remaining(Job *job, uint64_t remaining); */ void job_progress_increase_remaining(Job *job, uint64_t delta); -/** To be called when a cancelled job is finalised. */ -void job_event_cancelled(Job *job); - -/** To be called when a successfully completed job is finalised. */ -void job_event_completed(Job *job); - /** * Conditionally enter the job coroutine if the job is ready to run, not * already busy and fn() returns true. fn() is called while under the job_lock diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ void job_txn_unref(JobTxn *txn) } } -void job_txn_add_job(JobTxn *txn, Job *job) +/** + * @txn: The transaction (may be NULL) + * @job: Job to add to the transaction + * + * Add @job to the transaction. The @job must not already be in a transaction. + * The caller must call either job_txn_unref() or job_completed() to release + * the reference that is automatically grabbed here. + * + * If @txn is NULL, the function does nothing. + */ +static void job_txn_add_job(JobTxn *txn, Job *job) { if (!txn) { return; @@ -XXX,XX +XXX,XX @@ void job_progress_increase_remaining(Job *job, uint64_t delta) progress_increase_remaining(&job->progress, delta); } -void job_event_cancelled(Job *job) +/** + * To be called when a cancelled job is finalised. + */ +static void job_event_cancelled(Job *job) { notifier_list_notify(&job->on_finalize_cancelled, job); } -void job_event_completed(Job *job) +/** + * To be called when a successfully completed job is finalised. + */ +static void job_event_completed(Job *job) { notifier_list_notify(&job->on_finalize_completed, job); } -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Same as AIO_WAIT_WHILE macro, but if we are in the Main loop do not release and then acquire ctx_ 's aiocontext. Once all Aiocontext locks go away, this macro will replace AIO_WAIT_WHILE. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-5-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/aio-wait.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio-wait.h +++ b/include/block/aio-wait.h @@ -XXX,XX +XXX,XX @@ typedef struct { extern AioWait global_aio_wait; /** - * AIO_WAIT_WHILE: + * AIO_WAIT_WHILE_INTERNAL: * @ctx: the aio context, or NULL if multiple aio contexts (for which the * caller does not hold a lock) are involved in the polling condition. * @cond: wait while this conditional expression is true + * @unlock: whether to unlock and then lock again @ctx. This apples + * only when waiting for another AioContext from the main loop. + * Otherwise it's ignored. * * Wait while a condition is true. Use this to implement synchronous * operations that require event loop activity. @@ -XXX,XX +XXX,XX @@ extern AioWait global_aio_wait; * wait on conditions between two IOThreads since that could lead to deadlock, * go via the main loop instead. */ -#define AIO_WAIT_WHILE(ctx, cond) ({ \ +#define AIO_WAIT_WHILE_INTERNAL(ctx, cond, unlock) ({ \ bool waited_ = false; \ AioWait *wait_ = &global_aio_wait; \ AioContext *ctx_ = (ctx); \ @@ -XXX,XX +XXX,XX @@ extern AioWait global_aio_wait; assert(qemu_get_current_aio_context() == \ qemu_get_aio_context()); \ while ((cond)) { \ - if (ctx_) { \ + if (unlock && ctx_) { \ aio_context_release(ctx_); \ } \ aio_poll(qemu_get_aio_context(), true); \ - if (ctx_) { \ + if (unlock && ctx_) { \ aio_context_acquire(ctx_); \ } \ waited_ = true; \ @@ -XXX,XX +XXX,XX @@ extern AioWait global_aio_wait; qatomic_dec(&wait_->num_waiters); \ waited_; }) +#define AIO_WAIT_WHILE(ctx, cond) \ + AIO_WAIT_WHILE_INTERNAL(ctx, cond, true) + +#define AIO_WAIT_WHILE_UNLOCKED(ctx, cond) \ + AIO_WAIT_WHILE_INTERNAL(ctx, cond, false) + /** * aio_wait_kick: * Wake up the main thread if it is waiting on AIO_WAIT_WHILE(). During -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> With "intact" we mean that all job.h functions implicitly take the lock. Therefore API callers are unmodified. This means that: - many static functions that will be always called with job lock held become _locked, and call _locked functions - all public functions take the lock internally if needed, and call _locked functions - all public functions called internally by other functions in job.c will have a _locked counterpart (sometimes public), to avoid deadlocks (job lock already taken). These functions are not used for now. - some public functions called only from exernal files (not job.c) do not have _locked() counterpart and take the lock inside. Others won't need the lock at all because use fields only set at initialization and never modified. job_{lock/unlock} is independent from real_job_{lock/unlock}. Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop* Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-6-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 138 +++++++++- job.c | 610 ++++++++++++++++++++++++++++++++------------- 2 files changed, 561 insertions(+), 187 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ JobTxn *job_txn_new(void); */ void job_txn_unref(JobTxn *txn); +/* + * Same as job_txn_unref(), but called with job lock held. + * Might release the lock temporarily. + */ +void job_txn_unref_locked(JobTxn *txn); + /** * Create a new long-running job and return it. + * Called with job_mutex *not* held. * * @job_id: The id of the newly-created job, or %NULL for internal jobs * @driver: The class object for the newly-created job. @@ -XXX,XX +XXX,XX @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, */ void job_ref(Job *job); +/* Same as job_ref(), but called with job lock held. */ +void job_ref_locked(Job *job); + /** * Release a reference that was previously acquired with job_ref() or * job_create(). If it's the last reference to the object, it will be freed. */ void job_unref(Job *job); +/* Same as job_unref(), but called with job lock held. */ +void job_unref_locked(Job *job); + /** * @job: The job that has made progress * @done: How much progress the job made since the last call * * Updates the progress counter of the job. + * + * May be called with mutex held or not held. */ void job_progress_update(Job *job, uint64_t done); @@ -XXX,XX +XXX,XX @@ void job_progress_update(Job *job, uint64_t done); * * Sets the expected end value of the progress counter of a job so that a * completion percentage can be calculated when the progress is updated. + * + * May be called with mutex held or not held. */ void job_progress_set_remaining(Job *job, uint64_t remaining); @@ -XXX,XX +XXX,XX @@ void job_progress_set_remaining(Job *job, uint64_t remaining); * length before, and job_progress_update() afterwards. * (So the operation acts as a parenthesis in regards to the main job * operation running in background.) + * + * May be called with mutex held or not held. */ void job_progress_increase_remaining(Job *job, uint64_t delta); @@ -XXX,XX +XXX,XX @@ void job_progress_increase_remaining(Job *job, uint64_t delta); */ void job_enter_cond(Job *job, bool(*fn)(Job *job)); +/* + * Same as job_enter_cond(), but called with job lock held. + * Might release the lock temporarily. + */ +void job_enter_cond_locked(Job *job, bool(*fn)(Job *job)); + /** * @job: A job that has not yet been started. * * Begins execution of a job. * Takes ownership of one reference to the job object. + * + * Called with job_mutex *not* held. */ void job_start(Job *job); @@ -XXX,XX +XXX,XX @@ void job_start(Job *job); * @job: The job to enter. * * Continue the specified job by entering the coroutine. + * Called with job_mutex *not* held. */ void job_enter(Job *job); @@ -XXX,XX +XXX,XX @@ void job_enter(Job *job); * * Pause now if job_pause() has been called. Jobs that perform lots of I/O * must call this between requests so that the job can be paused. + * + * Called with job_mutex *not* held. */ void coroutine_fn job_pause_point(Job *job); @@ -XXX,XX +XXX,XX @@ void coroutine_fn job_pause_point(Job *job); * @job: The job that calls the function. * * Yield the job coroutine. + * Called with job_mutex *not* held. */ void coroutine_fn job_yield(Job *job); @@ -XXX,XX +XXX,XX @@ void coroutine_fn job_yield(Job *job); * Put the job to sleep (assuming that it wasn't canceled) for @ns * %QEMU_CLOCK_REALTIME nanoseconds. Canceling the job will immediately * interrupt the wait. + * + * Called with job_mutex *not* held. */ void coroutine_fn job_sleep_ns(Job *job, int64_t ns); @@ -XXX,XX +XXX,XX @@ const char *job_type_str(const Job *job); /** Returns true if the job should not be visible to the management layer. */ bool job_is_internal(Job *job); -/** Returns whether the job is being cancelled. */ +/** + * Returns whether the job is being cancelled. + * Called with job_mutex *not* held. + */ bool job_is_cancelled(Job *job); +/* Same as job_is_cancelled(), but called with job lock held. */ +bool job_is_cancelled_locked(Job *job); + /** * Returns whether the job is scheduled for cancellation (at an * indefinite point). + * Called with job_mutex *not* held. */ bool job_cancel_requested(Job *job); -/** Returns whether the job is in a completed state. */ +/** + * Returns whether the job is in a completed state. + * Called with job_mutex *not* held. + */ bool job_is_completed(Job *job); -/** Returns whether the job is ready to be completed. */ +/* Same as job_is_completed(), but called with job lock held. */ +bool job_is_completed_locked(Job *job); + +/** + * Returns whether the job is ready to be completed. + * Called with job_mutex *not* held. + */ bool job_is_ready(Job *job); +/* Same as job_is_ready(), but called with job lock held. */ +bool job_is_ready_locked(Job *job); + /** * Request @job to pause at the next pause point. Must be paired with * job_resume(). If the job is supposed to be resumed by user action, call @@ -XXX,XX +XXX,XX @@ bool job_is_ready(Job *job); */ void job_pause(Job *job); +/* Same as job_pause(), but called with job lock held. */ +void job_pause_locked(Job *job); + /** Resumes a @job paused with job_pause. */ void job_resume(Job *job); +/* + * Same as job_resume(), but called with job lock held. + * Might release the lock temporarily. + */ +void job_resume_locked(Job *job); + /** * Asynchronously pause the specified @job. * Do not allow a resume until a matching call to job_user_resume. */ void job_user_pause(Job *job, Error **errp); +/* Same as job_user_pause(), but called with job lock held. */ +void job_user_pause_locked(Job *job, Error **errp); + /** Returns true if the job is user-paused. */ bool job_user_paused(Job *job); +/* Same as job_user_paused(), but called with job lock held. */ +bool job_user_paused_locked(Job *job); + /** * Resume the specified @job. * Must be paired with a preceding job_user_pause. */ void job_user_resume(Job *job, Error **errp); +/* + * Same as job_user_resume(), but called with job lock held. + * Might release the lock temporarily. + */ +void job_user_resume_locked(Job *job, Error **errp); + /** * Get the next element from the list of block jobs after @job, or the * first one if @job is %NULL. @@ -XXX,XX +XXX,XX @@ void job_user_resume(Job *job, Error **errp); */ Job *job_next(Job *job); +/* Same as job_next(), but called with job lock held. */ +Job *job_next_locked(Job *job); + /** * Get the job identified by @id (which must not be %NULL). * @@ -XXX,XX +XXX,XX @@ Job *job_next(Job *job); */ Job *job_get(const char *id); +/* Same as job_get(), but called with job lock held. */ +Job *job_get_locked(const char *id); + /** * Check whether the verb @verb can be applied to @job in its current state. * Returns 0 if the verb can be applied; otherwise errp is set and -EPERM @@ -XXX,XX +XXX,XX @@ Job *job_get(const char *id); */ int job_apply_verb(Job *job, JobVerb verb, Error **errp); -/** The @job could not be started, free it. */ +/* Same as job_apply_verb, but called with job lock held. */ +int job_apply_verb_locked(Job *job, JobVerb verb, Error **errp); + +/** + * The @job could not be started, free it. + * Called with job_mutex *not* held. + */ void job_early_fail(Job *job); -/** Moves the @job from RUNNING to READY */ +/** + * Moves the @job from RUNNING to READY. + * Called with job_mutex *not* held. + */ void job_transition_to_ready(Job *job); /** Asynchronously complete the specified @job. */ void job_complete(Job *job, Error **errp); +/* + * Same as job_complete(), but called with job lock held. + * Might release the lock temporarily. + */ +void job_complete_locked(Job *job, Error **errp); + /** * Asynchronously cancel the specified @job. If @force is true, the job should * be cancelled immediately without waiting for a consistent state. */ void job_cancel(Job *job, bool force); +/* Same as job_cancel(), but called with job lock held. */ +void job_cancel_locked(Job *job, bool force); + /** * Cancels the specified job like job_cancel(), but may refuse to do so if the * operation isn't meaningful in the current state of the job. */ void job_user_cancel(Job *job, bool force, Error **errp); +/* Same as job_user_cancel(), but called with job lock held. */ +void job_user_cancel_locked(Job *job, bool force, Error **errp); + /** * Synchronously cancel the @job. The completion callback is called * before the function returns. If @force is false, the job may @@ -XXX,XX +XXX,XX @@ void job_user_cancel(Job *job, bool force, Error **errp); */ int job_cancel_sync(Job *job, bool force); -/** Synchronously force-cancels all jobs using job_cancel_sync(). */ +/* Same as job_cancel_sync, but called with job lock held. */ +int job_cancel_sync_locked(Job *job, bool force); + +/** + * Synchronously force-cancels all jobs using job_cancel_sync_locked(). + * + * Called with job_lock *not* held. + */ void job_cancel_sync_all(void); /** @@ -XXX,XX +XXX,XX @@ void job_cancel_sync_all(void); */ int job_complete_sync(Job *job, Error **errp); +/* Same as job_complete_sync, but called with job lock held. */ +int job_complete_sync_locked(Job *job, Error **errp); + /** * For a @job that has finished its work and is pending awaiting explicit * acknowledgement to commit its work, this will commit that work. @@ -XXX,XX +XXX,XX @@ int job_complete_sync(Job *job, Error **errp); */ void job_finalize(Job *job, Error **errp); +/* Same as job_finalize(), but called with job lock held. */ +void job_finalize_locked(Job *job, Error **errp); + /** * Remove the concluded @job from the query list and resets the passed pointer * to %NULL. Returns an error if the job is not actually concluded. */ void job_dismiss(Job **job, Error **errp); +/* Same as job_dismiss(), but called with job lock held. */ +void job_dismiss_locked(Job **job, Error **errp); + /** * Synchronously finishes the given @job. If @finish is given, it is called to * trigger completion or cancellation of the job. @@ -XXX,XX +XXX,XX @@ void job_dismiss(Job **job, Error **errp); * * Callers must hold the AioContext lock of job->aio_context. */ -int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp); +int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), + Error **errp); + +/* + * Same as job_finish_sync(), but called with job lock held. + * Might release the lock temporarily. + */ +int job_finish_sync_locked(Job *job, void (*finish)(Job *, Error **errp), + Error **errp); #endif diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ */ QemuMutex job_mutex; +/* Protected by job_mutex */ static QLIST_HEAD(, Job) jobs = QLIST_HEAD_INITIALIZER(jobs); /* Job State Transition Table */ @@ -XXX,XX +XXX,XX @@ JobTxn *job_txn_new(void) return txn; } -static void job_txn_ref(JobTxn *txn) +/* Called with job_mutex held. */ +static void job_txn_ref_locked(JobTxn *txn) { txn->refcnt++; } -void job_txn_unref(JobTxn *txn) +void job_txn_unref_locked(JobTxn *txn) { if (txn && --txn->refcnt == 0) { g_free(txn); } } +void job_txn_unref(JobTxn *txn) +{ + JOB_LOCK_GUARD(); + job_txn_unref_locked(txn); +} + /** * @txn: The transaction (may be NULL) * @job: Job to add to the transaction @@ -XXX,XX +XXX,XX @@ void job_txn_unref(JobTxn *txn) * the reference that is automatically grabbed here. * * If @txn is NULL, the function does nothing. + * + * Called with job_mutex held. */ -static void job_txn_add_job(JobTxn *txn, Job *job) +static void job_txn_add_job_locked(JobTxn *txn, Job *job) { if (!txn) { return; @@ -XXX,XX +XXX,XX @@ static void job_txn_add_job(JobTxn *txn, Job *job) job->txn = txn; QLIST_INSERT_HEAD(&txn->jobs, job, txn_list); - job_txn_ref(txn); + job_txn_ref_locked(txn); } -static void job_txn_del_job(Job *job) +/* Called with job_mutex held. */ +static void job_txn_del_job_locked(Job *job) { if (job->txn) { QLIST_REMOVE(job, txn_list); - job_txn_unref(job->txn); + job_txn_unref_locked(job->txn); job->txn = NULL; } } -static int job_txn_apply(Job *job, int fn(Job *)) +/* Called with job_mutex held, but releases it temporarily. */ +static int job_txn_apply_locked(Job *job, int fn(Job *)) { AioContext *inner_ctx; Job *other_job, *next; @@ -XXX,XX +XXX,XX @@ static int job_txn_apply(Job *job, int fn(Job *)) * we need to release it here to avoid holding the lock twice - which would * break AIO_WAIT_WHILE from within fn. */ - job_ref(job); + job_ref_locked(job); aio_context_release(job->aio_context); QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) { @@ -XXX,XX +XXX,XX @@ static int job_txn_apply(Job *job, int fn(Job *)) * can't use a local variable to cache it. */ aio_context_acquire(job->aio_context); - job_unref(job); + job_unref_locked(job); return rc; } @@ -XXX,XX +XXX,XX @@ bool job_is_internal(Job *job) return (job->id == NULL); } -static void job_state_transition(Job *job, JobStatus s1) +/* Called with job_mutex held. */ +static void job_state_transition_locked(Job *job, JobStatus s1) { JobStatus s0 = job->status; assert(s1 >= 0 && s1 < JOB_STATUS__MAX); @@ -XXX,XX +XXX,XX @@ static void job_state_transition(Job *job, JobStatus s1) } } -int job_apply_verb(Job *job, JobVerb verb, Error **errp) +int job_apply_verb_locked(Job *job, JobVerb verb, Error **errp) { JobStatus s0 = job->status; assert(verb >= 0 && verb < JOB_VERB__MAX); @@ -XXX,XX +XXX,XX @@ int job_apply_verb(Job *job, JobVerb verb, Error **errp) return -EPERM; } +int job_apply_verb(Job *job, JobVerb verb, Error **errp) +{ + JOB_LOCK_GUARD(); + return job_apply_verb_locked(job, verb, errp); +} + JobType job_type(const Job *job) { return job->driver->job_type; @@ -XXX,XX +XXX,XX @@ const char *job_type_str(const Job *job) return JobType_str(job_type(job)); } -bool job_is_cancelled(Job *job) +bool job_is_cancelled_locked(Job *job) { /* force_cancel may be true only if cancelled is true, too */ assert(job->cancelled || !job->force_cancel); return job->force_cancel; } -bool job_cancel_requested(Job *job) +bool job_is_cancelled(Job *job) +{ + JOB_LOCK_GUARD(); + return job_is_cancelled_locked(job); +} + +/* Called with job_mutex held. */ +static bool job_cancel_requested_locked(Job *job) { return job->cancelled; } -bool job_is_ready(Job *job) +bool job_cancel_requested(Job *job) +{ + JOB_LOCK_GUARD(); + return job_cancel_requested_locked(job); +} + +bool job_is_ready_locked(Job *job) { switch (job->status) { case JOB_STATUS_UNDEFINED: @@ -XXX,XX +XXX,XX @@ bool job_is_ready(Job *job) return false; } -bool job_is_completed(Job *job) +bool job_is_ready(Job *job) +{ + JOB_LOCK_GUARD(); + return job_is_ready_locked(job); +} + +bool job_is_completed_locked(Job *job) { switch (job->status) { case JOB_STATUS_UNDEFINED: @@ -XXX,XX +XXX,XX @@ bool job_is_completed(Job *job) return false; } -static bool job_started(Job *job) +bool job_is_completed(Job *job) +{ + JOB_LOCK_GUARD(); + return job_is_completed_locked(job); +} + +static bool job_started_locked(Job *job) { return job->co; } -static bool job_should_pause(Job *job) +/* Called with job_mutex held. */ +static bool job_should_pause_locked(Job *job) { return job->pause_count > 0; } -Job *job_next(Job *job) +Job *job_next_locked(Job *job) { if (!job) { return QLIST_FIRST(&jobs); @@ -XXX,XX +XXX,XX @@ Job *job_next(Job *job) return QLIST_NEXT(job, job_list); } -Job *job_get(const char *id) +Job *job_next(Job *job) +{ + JOB_LOCK_GUARD(); + return job_next_locked(job); +} + +Job *job_get_locked(const char *id) { Job *job; @@ -XXX,XX +XXX,XX @@ Job *job_get(const char *id) return NULL; } +Job *job_get(const char *id) +{ + JOB_LOCK_GUARD(); + return job_get_locked(id); +} + +/* Called with job_mutex *not* held. */ static void job_sleep_timer_cb(void *opaque) { Job *job = opaque; @@ -XXX,XX +XXX,XX @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, { Job *job; + JOB_LOCK_GUARD(); + if (job_id) { if (flags & JOB_INTERNAL) { error_setg(errp, "Cannot specify job ID for internal job"); @@ -XXX,XX +XXX,XX @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, error_setg(errp, "Invalid job ID '%s'", job_id); return NULL; } - if (job_get(job_id)) { + if (job_get_locked(job_id)) { error_setg(errp, "Job ID '%s' already in use", job_id); return NULL; } @@ -XXX,XX +XXX,XX @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, notifier_list_init(&job->on_ready); notifier_list_init(&job->on_idle); - job_state_transition(job, JOB_STATUS_CREATED); + job_state_transition_locked(job, JOB_STATUS_CREATED); aio_timer_init(qemu_get_aio_context(), &job->sleep_timer, QEMU_CLOCK_REALTIME, SCALE_NS, job_sleep_timer_cb, job); @@ -XXX,XX +XXX,XX @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, * consolidating the job management logic */ if (!txn) { txn = job_txn_new(); - job_txn_add_job(txn, job); - job_txn_unref(txn); + job_txn_add_job_locked(txn, job); + job_txn_unref_locked(txn); } else { - job_txn_add_job(txn, job); + job_txn_add_job_locked(txn, job); } return job; } -void job_ref(Job *job) +void job_ref_locked(Job *job) { ++job->refcnt; } -void job_unref(Job *job) +void job_ref(Job *job) +{ + JOB_LOCK_GUARD(); + job_ref_locked(job); +} + +void job_unref_locked(Job *job) { GLOBAL_STATE_CODE(); @@ -XXX,XX +XXX,XX @@ void job_unref(Job *job) assert(!job->txn); if (job->driver->free) { + job_unlock(); job->driver->free(job); + job_lock(); } QLIST_REMOVE(job, job_list); @@ -XXX,XX +XXX,XX @@ void job_unref(Job *job) } } +void job_unref(Job *job) +{ + JOB_LOCK_GUARD(); + job_unref_locked(job); +} + void job_progress_update(Job *job, uint64_t done) { progress_work_done(&job->progress, done); @@ -XXX,XX +XXX,XX @@ void job_progress_increase_remaining(Job *job, uint64_t delta) /** * To be called when a cancelled job is finalised. + * Called with job_mutex held. */ -static void job_event_cancelled(Job *job) +static void job_event_cancelled_locked(Job *job) { notifier_list_notify(&job->on_finalize_cancelled, job); } /** * To be called when a successfully completed job is finalised. + * Called with job_mutex held. */ -static void job_event_completed(Job *job) +static void job_event_completed_locked(Job *job) { notifier_list_notify(&job->on_finalize_completed, job); } -static void job_event_pending(Job *job) +/* Called with job_mutex held. */ +static void job_event_pending_locked(Job *job) { notifier_list_notify(&job->on_pending, job); } -static void job_event_ready(Job *job) +/* Called with job_mutex held. */ +static void job_event_ready_locked(Job *job) { notifier_list_notify(&job->on_ready, job); } -static void job_event_idle(Job *job) +/* Called with job_mutex held. */ +static void job_event_idle_locked(Job *job) { notifier_list_notify(&job->on_idle, job); } -void job_enter_cond(Job *job, bool(*fn)(Job *job)) +void job_enter_cond_locked(Job *job, bool(*fn)(Job *job)) { - if (!job_started(job)) { + if (!job_started_locked(job)) { return; } if (job->deferred_to_main_loop) { @@ -XXX,XX +XXX,XX @@ void job_enter_cond(Job *job, bool(*fn)(Job *job)) timer_del(&job->sleep_timer); job->busy = true; real_job_unlock(); + job_unlock(); aio_co_enter(job->aio_context, job->co); + job_lock(); +} + +void job_enter_cond(Job *job, bool(*fn)(Job *job)) +{ + JOB_LOCK_GUARD(); + job_enter_cond_locked(job, fn); } void job_enter(Job *job) { - job_enter_cond(job, NULL); + JOB_LOCK_GUARD(); + job_enter_cond_locked(job, NULL); } /* Yield, and schedule a timer to reenter the coroutine after @ns nanoseconds. @@ -XXX,XX +XXX,XX @@ void job_enter(Job *job) * is allowed and cancels the timer. * * If @ns is (uint64_t) -1, no timer is scheduled and job_enter() must be - * called explicitly. */ -static void coroutine_fn job_do_yield(Job *job, uint64_t ns) + * called explicitly. + * + * Called with job_mutex held, but releases it temporarily. + */ +static void coroutine_fn job_do_yield_locked(Job *job, uint64_t ns) { real_job_lock(); if (ns != -1) { timer_mod(&job->sleep_timer, ns); } job->busy = false; - job_event_idle(job); + job_event_idle_locked(job); real_job_unlock(); + job_unlock(); qemu_coroutine_yield(); + job_lock(); /* Set by job_enter_cond() before re-entering the coroutine. */ assert(job->busy); } -void coroutine_fn job_pause_point(Job *job) +/* Called with job_mutex held, but releases it temporarily. */ +static void coroutine_fn job_pause_point_locked(Job *job) { - assert(job && job_started(job)); + assert(job && job_started_locked(job)); - if (!job_should_pause(job)) { + if (!job_should_pause_locked(job)) { return; } - if (job_is_cancelled(job)) { + if (job_is_cancelled_locked(job)) { return; } if (job->driver->pause) { + job_unlock(); job->driver->pause(job); + job_lock(); } - if (job_should_pause(job) && !job_is_cancelled(job)) { + if (job_should_pause_locked(job) && !job_is_cancelled_locked(job)) { JobStatus status = job->status; - job_state_transition(job, status == JOB_STATUS_READY - ? JOB_STATUS_STANDBY - : JOB_STATUS_PAUSED); + job_state_transition_locked(job, status == JOB_STATUS_READY + ? JOB_STATUS_STANDBY + : JOB_STATUS_PAUSED); job->paused = true; - job_do_yield(job, -1); + job_do_yield_locked(job, -1); job->paused = false; - job_state_transition(job, status); + job_state_transition_locked(job, status); } if (job->driver->resume) { + job_unlock(); job->driver->resume(job); + job_lock(); } } -void coroutine_fn job_yield(Job *job) +void coroutine_fn job_pause_point(Job *job) +{ + JOB_LOCK_GUARD(); + job_pause_point_locked(job); +} + +static void coroutine_fn job_yield_locked(Job *job) { assert(job->busy); /* Check cancellation *before* setting busy = false, too! */ - if (job_is_cancelled(job)) { + if (job_is_cancelled_locked(job)) { return; } - if (!job_should_pause(job)) { - job_do_yield(job, -1); + if (!job_should_pause_locked(job)) { + job_do_yield_locked(job, -1); } - job_pause_point(job); + job_pause_point_locked(job); +} + +void coroutine_fn job_yield(Job *job) +{ + JOB_LOCK_GUARD(); + job_yield_locked(job); } void coroutine_fn job_sleep_ns(Job *job, int64_t ns) { + JOB_LOCK_GUARD(); assert(job->busy); /* Check cancellation *before* setting busy = false, too! */ - if (job_is_cancelled(job)) { + if (job_is_cancelled_locked(job)) { return; } - if (!job_should_pause(job)) { - job_do_yield(job, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + ns); + if (!job_should_pause_locked(job)) { + job_do_yield_locked(job, qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + ns); } - job_pause_point(job); + job_pause_point_locked(job); } -/* Assumes the block_job_mutex is held */ -static bool job_timer_not_pending(Job *job) +/* Assumes the job_mutex is held */ +static bool job_timer_not_pending_locked(Job *job) { return !timer_pending(&job->sleep_timer); } -void job_pause(Job *job) +void job_pause_locked(Job *job) { job->pause_count++; if (!job->paused) { - job_enter(job); + job_enter_cond_locked(job, NULL); } } -void job_resume(Job *job) +void job_pause(Job *job) +{ + JOB_LOCK_GUARD(); + job_pause_locked(job); +} + +void job_resume_locked(Job *job) { assert(job->pause_count > 0); job->pause_count--; @@ -XXX,XX +XXX,XX @@ void job_resume(Job *job) } /* kick only if no timer is pending */ - job_enter_cond(job, job_timer_not_pending); + job_enter_cond_locked(job, job_timer_not_pending_locked); } -void job_user_pause(Job *job, Error **errp) +void job_resume(Job *job) { - if (job_apply_verb(job, JOB_VERB_PAUSE, errp)) { + JOB_LOCK_GUARD(); + job_resume_locked(job); +} + +void job_user_pause_locked(Job *job, Error **errp) +{ + if (job_apply_verb_locked(job, JOB_VERB_PAUSE, errp)) { return; } if (job->user_paused) { @@ -XXX,XX +XXX,XX @@ void job_user_pause(Job *job, Error **errp) return; } job->user_paused = true; - job_pause(job); + job_pause_locked(job); } -bool job_user_paused(Job *job) +void job_user_pause(Job *job, Error **errp) +{ + JOB_LOCK_GUARD(); + job_user_pause_locked(job, errp); +} + +bool job_user_paused_locked(Job *job) { return job->user_paused; } -void job_user_resume(Job *job, Error **errp) +bool job_user_paused(Job *job) +{ + JOB_LOCK_GUARD(); + return job_user_paused_locked(job); +} + +void job_user_resume_locked(Job *job, Error **errp) { assert(job); GLOBAL_STATE_CODE(); @@ -XXX,XX +XXX,XX @@ void job_user_resume(Job *job, Error **errp) error_setg(errp, "Can't resume a job that was not paused"); return; } - if (job_apply_verb(job, JOB_VERB_RESUME, errp)) { + if (job_apply_verb_locked(job, JOB_VERB_RESUME, errp)) { return; } if (job->driver->user_resume) { + job_unlock(); job->driver->user_resume(job); + job_lock(); } job->user_paused = false; - job_resume(job); + job_resume_locked(job); } -static void job_do_dismiss(Job *job) +void job_user_resume(Job *job, Error **errp) +{ + JOB_LOCK_GUARD(); + job_user_resume_locked(job, errp); +} + +/* Called with job_mutex held, but releases it temporarily. */ +static void job_do_dismiss_locked(Job *job) { assert(job); job->busy = false; job->paused = false; job->deferred_to_main_loop = true; - job_txn_del_job(job); + job_txn_del_job_locked(job); - job_state_transition(job, JOB_STATUS_NULL); - job_unref(job); + job_state_transition_locked(job, JOB_STATUS_NULL); + job_unref_locked(job); } -void job_dismiss(Job **jobptr, Error **errp) +void job_dismiss_locked(Job **jobptr, Error **errp) { Job *job = *jobptr; /* similarly to _complete, this is QMP-interface only. */ assert(job->id); - if (job_apply_verb(job, JOB_VERB_DISMISS, errp)) { + if (job_apply_verb_locked(job, JOB_VERB_DISMISS, errp)) { return; } - job_do_dismiss(job); + job_do_dismiss_locked(job); *jobptr = NULL; } +void job_dismiss(Job **jobptr, Error **errp) +{ + JOB_LOCK_GUARD(); + job_dismiss_locked(jobptr, errp); +} + void job_early_fail(Job *job) { + JOB_LOCK_GUARD(); assert(job->status == JOB_STATUS_CREATED); - job_do_dismiss(job); + job_do_dismiss_locked(job); } -static void job_conclude(Job *job) +/* Called with job_mutex held. */ +static void job_conclude_locked(Job *job) { - job_state_transition(job, JOB_STATUS_CONCLUDED); - if (job->auto_dismiss || !job_started(job)) { - job_do_dismiss(job); + job_state_transition_locked(job, JOB_STATUS_CONCLUDED); + if (job->auto_dismiss || !job_started_locked(job)) { + job_do_dismiss_locked(job); } } -static void job_update_rc(Job *job) +/* Called with job_mutex held. */ +static void job_update_rc_locked(Job *job) { - if (!job->ret && job_is_cancelled(job)) { + if (!job->ret && job_is_cancelled_locked(job)) { job->ret = -ECANCELED; } if (job->ret) { if (!job->err) { error_setg(&job->err, "%s", strerror(-job->ret)); } - job_state_transition(job, JOB_STATUS_ABORTING); + job_state_transition_locked(job, JOB_STATUS_ABORTING); } } @@ -XXX,XX +XXX,XX @@ static void job_clean(Job *job) } } -static int job_finalize_single(Job *job) +/* Called with job_mutex held, but releases it temporarily */ +static int job_finalize_single_locked(Job *job) { - assert(job_is_completed(job)); + int job_ret; + + assert(job_is_completed_locked(job)); /* Ensure abort is called for late-transactional failures */ - job_update_rc(job); + job_update_rc_locked(job); + + job_ret = job->ret; + job_unlock(); - if (!job->ret) { + if (!job_ret) { job_commit(job); } else { job_abort(job); } job_clean(job); + job_lock(); + if (job->cb) { - job->cb(job->opaque, job->ret); + job_ret = job->ret; + job_unlock(); + job->cb(job->opaque, job_ret); + job_lock(); } /* Emit events only if we actually started */ - if (job_started(job)) { - if (job_is_cancelled(job)) { - job_event_cancelled(job); + if (job_started_locked(job)) { + if (job_is_cancelled_locked(job)) { + job_event_cancelled_locked(job); } else { - job_event_completed(job); + job_event_completed_locked(job); } } - job_txn_del_job(job); - job_conclude(job); + job_txn_del_job_locked(job); + job_conclude_locked(job); return 0; } -static void job_cancel_async(Job *job, bool force) +/* Called with job_mutex held, but releases it temporarily */ +static void job_cancel_async_locked(Job *job, bool force) { GLOBAL_STATE_CODE(); if (job->driver->cancel) { + job_unlock(); force = job->driver->cancel(job, force); + job_lock(); } else { /* No .cancel() means the job will behave as if force-cancelled */ force = true; @@ -XXX,XX +XXX,XX @@ static void job_cancel_async(Job *job, bool force) if (job->user_paused) { /* Do not call job_enter here, the caller will handle it. */ if (job->driver->user_resume) { + job_unlock(); job->driver->user_resume(job); + job_lock(); } job->user_paused = false; assert(job->pause_count > 0); @@ -XXX,XX +XXX,XX @@ static void job_cancel_async(Job *job, bool force) } } -static void job_completed_txn_abort(Job *job) +/* Called with job_mutex held, but releases it temporarily. */ +static void job_completed_txn_abort_locked(Job *job) { AioContext *ctx; JobTxn *txn = job->txn; @@ -XXX,XX +XXX,XX @@ static void job_completed_txn_abort(Job *job) return; } txn->aborting = true; - job_txn_ref(txn); + job_txn_ref_locked(txn); /* * We can only hold the single job's AioContext lock while calling @@ -XXX,XX +XXX,XX @@ static void job_completed_txn_abort(Job *job) * calls of AIO_WAIT_WHILE(), which could deadlock otherwise. * Note that the job's AioContext may change when it is finalized. */ - job_ref(job); + job_ref_locked(job); aio_context_release(job->aio_context); /* Other jobs are effectively cancelled by us, set the status for @@ -XXX,XX +XXX,XX @@ static void job_completed_txn_abort(Job *job) * Therefore, pass force=true to terminate all other jobs as quickly * as possible. */ - job_cancel_async(other_job, true); + job_cancel_async_locked(other_job, true); aio_context_release(ctx); } } @@ -XXX,XX +XXX,XX @@ static void job_completed_txn_abort(Job *job) */ ctx = other_job->aio_context; aio_context_acquire(ctx); - if (!job_is_completed(other_job)) { - assert(job_cancel_requested(other_job)); - job_finish_sync(other_job, NULL, NULL); + if (!job_is_completed_locked(other_job)) { + assert(job_cancel_requested_locked(other_job)); + job_finish_sync_locked(other_job, NULL, NULL); } - job_finalize_single(other_job); + job_finalize_single_locked(other_job); aio_context_release(ctx); } @@ -XXX,XX +XXX,XX @@ static void job_completed_txn_abort(Job *job) * even if the job went away during job_finalize_single(). */ aio_context_acquire(job->aio_context); - job_unref(job); + job_unref_locked(job); - job_txn_unref(txn); + job_txn_unref_locked(txn); } -static int job_prepare(Job *job) +/* Called with job_mutex held, but releases it temporarily */ +static int job_prepare_locked(Job *job) { + int ret; + GLOBAL_STATE_CODE(); if (job->ret == 0 && job->driver->prepare) { - job->ret = job->driver->prepare(job); - job_update_rc(job); + job_unlock(); + ret = job->driver->prepare(job); + job_lock(); + job->ret = ret; + job_update_rc_locked(job); } return job->ret; } -static int job_needs_finalize(Job *job) +/* Called with job_mutex held */ +static int job_needs_finalize_locked(Job *job) { return !job->auto_finalize; } -static void job_do_finalize(Job *job) +/* Called with job_mutex held */ +static void job_do_finalize_locked(Job *job) { int rc; assert(job && job->txn); /* prepare the transaction to complete */ - rc = job_txn_apply(job, job_prepare); + rc = job_txn_apply_locked(job, job_prepare_locked); if (rc) { - job_completed_txn_abort(job); + job_completed_txn_abort_locked(job); } else { - job_txn_apply(job, job_finalize_single); + job_txn_apply_locked(job, job_finalize_single_locked); } } -void job_finalize(Job *job, Error **errp) +void job_finalize_locked(Job *job, Error **errp) { assert(job && job->id); - if (job_apply_verb(job, JOB_VERB_FINALIZE, errp)) { + if (job_apply_verb_locked(job, JOB_VERB_FINALIZE, errp)) { return; } - job_do_finalize(job); + job_do_finalize_locked(job); } -static int job_transition_to_pending(Job *job) +void job_finalize(Job *job, Error **errp) { - job_state_transition(job, JOB_STATUS_PENDING); + JOB_LOCK_GUARD(); + job_finalize_locked(job, errp); +} + +/* Called with job_mutex held. */ +static int job_transition_to_pending_locked(Job *job) +{ + job_state_transition_locked(job, JOB_STATUS_PENDING); if (!job->auto_finalize) { - job_event_pending(job); + job_event_pending_locked(job); } return 0; } void job_transition_to_ready(Job *job) { - job_state_transition(job, JOB_STATUS_READY); - job_event_ready(job); + JOB_LOCK_GUARD(); + job_state_transition_locked(job, JOB_STATUS_READY); + job_event_ready_locked(job); } -static void job_completed_txn_success(Job *job) +/* Called with job_mutex held. */ +static void job_completed_txn_success_locked(Job *job) { JobTxn *txn = job->txn; Job *other_job; - job_state_transition(job, JOB_STATUS_WAITING); + job_state_transition_locked(job, JOB_STATUS_WAITING); /* * Successful completion, see if there are other running jobs in this * txn. */ QLIST_FOREACH(other_job, &txn->jobs, txn_list) { - if (!job_is_completed(other_job)) { + if (!job_is_completed_locked(other_job)) { return; } assert(other_job->ret == 0); } - job_txn_apply(job, job_transition_to_pending); + job_txn_apply_locked(job, job_transition_to_pending_locked); /* If no jobs need manual finalization, automatically do so */ - if (job_txn_apply(job, job_needs_finalize) == 0) { - job_do_finalize(job); + if (job_txn_apply_locked(job, job_needs_finalize_locked) == 0) { + job_do_finalize_locked(job); } } -static void job_completed(Job *job) +/* Called with job_mutex held. */ +static void job_completed_locked(Job *job) { - assert(job && job->txn && !job_is_completed(job)); + assert(job && job->txn && !job_is_completed_locked(job)); - job_update_rc(job); + job_update_rc_locked(job); trace_job_completed(job, job->ret); if (job->ret) { - job_completed_txn_abort(job); + job_completed_txn_abort_locked(job); } else { - job_completed_txn_success(job); + job_completed_txn_success_locked(job); } } -/** Useful only as a type shim for aio_bh_schedule_oneshot. */ +/** + * Useful only as a type shim for aio_bh_schedule_oneshot. + * Called with job_mutex *not* held. + */ static void job_exit(void *opaque) { Job *job = (Job *)opaque; AioContext *ctx; + JOB_LOCK_GUARD(); - job_ref(job); + job_ref_locked(job); aio_context_acquire(job->aio_context); /* This is a lie, we're not quiescent, but still doing the completion @@ -XXX,XX +XXX,XX @@ static void job_exit(void *opaque) * drain block nodes, and if .drained_poll still returned true, we would * deadlock. */ job->busy = false; - job_event_idle(job); + job_event_idle_locked(job); - job_completed(job); + job_completed_locked(job); /* * Note that calling job_completed can move the job to a different @@ -XXX,XX +XXX,XX @@ static void job_exit(void *opaque) * the job underneath us. */ ctx = job->aio_context; - job_unref(job); + job_unref_locked(job); aio_context_release(ctx); } @@ -XXX,XX +XXX,XX @@ static void job_exit(void *opaque) static void coroutine_fn job_co_entry(void *opaque) { Job *job = opaque; + int ret; assert(job && job->driver && job->driver->run); - assert(job->aio_context == qemu_get_current_aio_context()); - job_pause_point(job); - job->ret = job->driver->run(job, &job->err); - job->deferred_to_main_loop = true; - job->busy = true; + WITH_JOB_LOCK_GUARD() { + assert(job->aio_context == qemu_get_current_aio_context()); + job_pause_point_locked(job); + } + ret = job->driver->run(job, &job->err); + WITH_JOB_LOCK_GUARD() { + job->ret = ret; + job->deferred_to_main_loop = true; + job->busy = true; + } aio_bh_schedule_oneshot(qemu_get_aio_context(), job_exit, job); } void job_start(Job *job) { - assert(job && !job_started(job) && job->paused && - job->driver && job->driver->run); - job->co = qemu_coroutine_create(job_co_entry, job); - job->pause_count--; - job->busy = true; - job->paused = false; - job_state_transition(job, JOB_STATUS_RUNNING); + assert(qemu_in_main_thread()); + + WITH_JOB_LOCK_GUARD() { + assert(job && !job_started_locked(job) && job->paused && + job->driver && job->driver->run); + job->co = qemu_coroutine_create(job_co_entry, job); + job->pause_count--; + job->busy = true; + job->paused = false; + job_state_transition_locked(job, JOB_STATUS_RUNNING); + } aio_co_enter(job->aio_context, job->co); } -void job_cancel(Job *job, bool force) +void job_cancel_locked(Job *job, bool force) { if (job->status == JOB_STATUS_CONCLUDED) { - job_do_dismiss(job); + job_do_dismiss_locked(job); return; } - job_cancel_async(job, force); - if (!job_started(job)) { - job_completed(job); + job_cancel_async_locked(job, force); + if (!job_started_locked(job)) { + job_completed_locked(job); } else if (job->deferred_to_main_loop) { /* * job_cancel_async() ignores soft-cancel requests for jobs @@ -XXX,XX +XXX,XX @@ void job_cancel(Job *job, bool force) * choose to call job_is_cancelled() to show that we invoke * job_completed_txn_abort() only for force-cancelled jobs.) */ - if (job_is_cancelled(job)) { - job_completed_txn_abort(job); + if (job_is_cancelled_locked(job)) { + job_completed_txn_abort_locked(job); } } else { - job_enter(job); + job_enter_cond_locked(job, NULL); } } -void job_user_cancel(Job *job, bool force, Error **errp) +void job_cancel(Job *job, bool force) { - if (job_apply_verb(job, JOB_VERB_CANCEL, errp)) { + JOB_LOCK_GUARD(); + job_cancel_locked(job, force); +} + +void job_user_cancel_locked(Job *job, bool force, Error **errp) +{ + if (job_apply_verb_locked(job, JOB_VERB_CANCEL, errp)) { return; } - job_cancel(job, force); + job_cancel_locked(job, force); +} + +void job_user_cancel(Job *job, bool force, Error **errp) +{ + JOB_LOCK_GUARD(); + job_user_cancel_locked(job, force, errp); } /* A wrapper around job_cancel() taking an Error ** parameter so it may be * used with job_finish_sync() without the need for (rather nasty) function - * pointer casts there. */ -static void job_cancel_err(Job *job, Error **errp) + * pointer casts there. + * + * Called with job_mutex held. + */ +static void job_cancel_err_locked(Job *job, Error **errp) { - job_cancel(job, false); + job_cancel_locked(job, false); } /** * Same as job_cancel_err(), but force-cancel. + * Called with job_mutex held. */ -static void job_force_cancel_err(Job *job, Error **errp) +static void job_force_cancel_err_locked(Job *job, Error **errp) { - job_cancel(job, true); + job_cancel_locked(job, true); } -int job_cancel_sync(Job *job, bool force) +int job_cancel_sync_locked(Job *job, bool force) { if (force) { - return job_finish_sync(job, &job_force_cancel_err, NULL); + return job_finish_sync_locked(job, &job_force_cancel_err_locked, NULL); } else { - return job_finish_sync(job, &job_cancel_err, NULL); + return job_finish_sync_locked(job, &job_cancel_err_locked, NULL); } } +int job_cancel_sync(Job *job, bool force) +{ + JOB_LOCK_GUARD(); + return job_cancel_sync_locked(job, force); +} + void job_cancel_sync_all(void) { Job *job; AioContext *aio_context; + JOB_LOCK_GUARD(); - while ((job = job_next(NULL))) { + while ((job = job_next_locked(NULL))) { aio_context = job->aio_context; aio_context_acquire(aio_context); - job_cancel_sync(job, true); + job_cancel_sync_locked(job, true); aio_context_release(aio_context); } } +int job_complete_sync_locked(Job *job, Error **errp) +{ + return job_finish_sync_locked(job, job_complete_locked, errp); +} + int job_complete_sync(Job *job, Error **errp) { - return job_finish_sync(job, job_complete, errp); + JOB_LOCK_GUARD(); + return job_complete_sync_locked(job, errp); } -void job_complete(Job *job, Error **errp) +void job_complete_locked(Job *job, Error **errp) { /* Should not be reachable via external interface for internal jobs */ assert(job->id); GLOBAL_STATE_CODE(); - if (job_apply_verb(job, JOB_VERB_COMPLETE, errp)) { + if (job_apply_verb_locked(job, JOB_VERB_COMPLETE, errp)) { return; } - if (job_cancel_requested(job) || !job->driver->complete) { + if (job_cancel_requested_locked(job) || !job->driver->complete) { error_setg(errp, "The active block job '%s' cannot be completed", job->id); return; } + job_unlock(); job->driver->complete(job, errp); + job_lock(); } -int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp) +void job_complete(Job *job, Error **errp) +{ + JOB_LOCK_GUARD(); + job_complete_locked(job, errp); +} + +int job_finish_sync_locked(Job *job, + void (*finish)(Job *, Error **errp), + Error **errp) { Error *local_err = NULL; int ret; - job_ref(job); + job_ref_locked(job); if (finish) { finish(job, &local_err); } if (local_err) { error_propagate(errp, local_err); - job_unref(job); + job_unref_locked(job); return -EBUSY; } + job_unlock(); AIO_WAIT_WHILE(job->aio_context, (job_enter(job), !job_is_completed(job))); + job_lock(); - ret = (job_is_cancelled(job) && job->ret == 0) ? -ECANCELED : job->ret; - job_unref(job); + ret = (job_is_cancelled_locked(job) && job->ret == 0) + ? -ECANCELED : job->ret; + job_unref_locked(job); return ret; } + +int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp) +{ + JOB_LOCK_GUARD(); + return job_finish_sync_locked(job, finish, errp); +} -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> This comment applies more on job, it was left in blockjob as in the past the whole job logic was implemented there. Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop*. No functional change intended. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220926093214.506243-7-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 20 -------------------- job.c | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 20 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ #include "qemu/main-loop.h" #include "qemu/timer.h" -/* - * The block job API is composed of two categories of functions. - * - * The first includes functions used by the monitor. The monitor is - * peculiar in that it accesses the block job list with block_job_get, and - * therefore needs consistency across block_job_get and the actual operation - * (e.g. block_job_set_speed). The consistency is achieved with - * aio_context_acquire/release. These functions are declared in blockjob.h. - * - * The second includes functions used by the block job drivers and sometimes - * by the core block layer. These do not care about locking, because the - * whole coroutine runs under the AioContext lock, and are declared in - * blockjob_int.h. - */ - static bool is_block_job(Job *job) { return job_type(job) == JOB_TYPE_BACKUP || @@ -XXX,XX +XXX,XX @@ static void block_job_event_ready(Notifier *n, void *opaque) } -/* - * API for block job drivers and the block layer. These functions are - * declared in blockjob_int.h. - */ - void *block_job_create(const char *job_id, const BlockJobDriver *driver, JobTxn *txn, BlockDriverState *bs, uint64_t perm, uint64_t shared_perm, int64_t speed, int flags, diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ #include "trace/trace-root.h" #include "qapi/qapi-events-job.h" +/* + * The job API is composed of two categories of functions. + * + * The first includes functions used by the monitor. The monitor is + * peculiar in that it accesses the job list with job_get, and + * therefore needs consistency across job_get and the actual operation + * (e.g. job_user_cancel). To achieve this consistency, the caller + * calls job_lock/job_unlock itself around the whole operation. + * + * + * The second includes functions used by the job drivers and sometimes + * by the core block layer. These delegate the locking to the callee instead. + * + * TODO Actually make this true + */ + /* * job_mutex protects the jobs list, but also makes the * struct job fields thread-safe. -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Just as done with job.h, create _locked() functions in blockjob.h These functions will be later useful when caller has already taken the lock. All blockjob _locked functions call job _locked functions. Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop*. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-Id: <20220926093214.506243-8-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/blockjob.h | 18 ++++++++++++++ blockjob.c | 52 ++++++++++++++++++++++++++++++++-------- 2 files changed, 60 insertions(+), 10 deletions(-) diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { */ BlockJob *block_job_next(BlockJob *job); +/* Same as block_job_next(), but called with job lock held. */ +BlockJob *block_job_next_locked(BlockJob *job); + /** * block_job_get: * @id: The id of the block job. @@ -XXX,XX +XXX,XX @@ BlockJob *block_job_next(BlockJob *job); */ BlockJob *block_job_get(const char *id); +/* Same as block_job_get(), but called with job lock held. */ +BlockJob *block_job_get_locked(const char *id); + /** * block_job_add_bdrv: * @job: A block job @@ -XXX,XX +XXX,XX @@ bool block_job_has_bdrv(BlockJob *job, BlockDriverState *bs); */ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp); +/* + * Same as block_job_set_speed(), but called with job lock held. + * Might release the lock temporarily. + */ +bool block_job_set_speed_locked(BlockJob *job, int64_t speed, Error **errp); + /** * block_job_query: * @job: The job to get information about. @@ -XXX,XX +XXX,XX @@ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp); */ BlockJobInfo *block_job_query(BlockJob *job, Error **errp); +/* Same as block_job_query(), but called with job lock held. */ +BlockJobInfo *block_job_query_locked(BlockJob *job, Error **errp); + /** * block_job_iostatus_reset: * @job: The job whose I/O status should be reset. @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp); */ void block_job_iostatus_reset(BlockJob *job); +/* Same as block_job_iostatus_reset(), but called with job lock held. */ +void block_job_iostatus_reset_locked(BlockJob *job); + /* * block_job_get_aio_context: * diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static bool is_block_job(Job *job) job_type(job) == JOB_TYPE_STREAM; } -BlockJob *block_job_next(BlockJob *bjob) +BlockJob *block_job_next_locked(BlockJob *bjob) { Job *job = bjob ? &bjob->job : NULL; GLOBAL_STATE_CODE(); do { - job = job_next(job); + job = job_next_locked(job); } while (job && !is_block_job(job)); return job ? container_of(job, BlockJob, job) : NULL; } -BlockJob *block_job_get(const char *id) +BlockJob *block_job_next(BlockJob *bjob) { - Job *job = job_get(id); + JOB_LOCK_GUARD(); + return block_job_next_locked(bjob); +} + +BlockJob *block_job_get_locked(const char *id) +{ + Job *job = job_get_locked(id); GLOBAL_STATE_CODE(); if (job && is_block_job(job)) { @@ -XXX,XX +XXX,XX @@ BlockJob *block_job_get(const char *id) } } +BlockJob *block_job_get(const char *id) +{ + JOB_LOCK_GUARD(); + return block_job_get_locked(id); +} + void block_job_free(Job *job) { BlockJob *bjob = container_of(job, BlockJob, job); @@ -XXX,XX +XXX,XX @@ static bool job_timer_pending(Job *job) return timer_pending(&job->sleep_timer); } -bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) +bool block_job_set_speed_locked(BlockJob *job, int64_t speed, Error **errp) { const BlockJobDriver *drv = block_job_driver(job); int64_t old_speed = job->speed; GLOBAL_STATE_CODE(); - if (job_apply_verb(&job->job, JOB_VERB_SET_SPEED, errp) < 0) { + if (job_apply_verb_locked(&job->job, JOB_VERB_SET_SPEED, errp) < 0) { return false; } if (speed < 0) { @@ -XXX,XX +XXX,XX @@ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) job->speed = speed; if (drv->set_speed) { + job_unlock(); drv->set_speed(job, speed); + job_lock(); } if (speed && speed <= old_speed) { @@ -XXX,XX +XXX,XX @@ bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) } /* kick only if a timer is pending */ - job_enter_cond(&job->job, job_timer_pending); + job_enter_cond_locked(&job->job, job_timer_pending); return true; } +bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) +{ + JOB_LOCK_GUARD(); + return block_job_set_speed_locked(job, speed, errp); +} + int64_t block_job_ratelimit_get_delay(BlockJob *job, uint64_t n) { IO_CODE(); return ratelimit_calculate_delay(&job->limit, n); } -BlockJobInfo *block_job_query(BlockJob *job, Error **errp) +BlockJobInfo *block_job_query_locked(BlockJob *job, Error **errp) { BlockJobInfo *info; uint64_t progress_current, progress_total; @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp) info->len = progress_total; info->speed = job->speed; info->io_status = job->iostatus; - info->ready = job_is_ready(&job->job), + info->ready = job_is_ready_locked(&job->job), info->status = job->job.status; info->auto_finalize = job->job.auto_finalize; info->auto_dismiss = job->job.auto_dismiss; @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp) return info; } +BlockJobInfo *block_job_query(BlockJob *job, Error **errp) +{ + JOB_LOCK_GUARD(); + return block_job_query_locked(job, errp); +} + static void block_job_iostatus_set_err(BlockJob *job, int error) { if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) { @@ -XXX,XX +XXX,XX @@ fail: return NULL; } -void block_job_iostatus_reset(BlockJob *job) +void block_job_iostatus_reset_locked(BlockJob *job) { GLOBAL_STATE_CODE(); if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) { @@ -XXX,XX +XXX,XX @@ void block_job_iostatus_reset(BlockJob *job) job->iostatus = BLOCK_DEVICE_IO_STATUS_OK; } +void block_job_iostatus_reset(BlockJob *job) +{ + JOB_LOCK_GUARD(); + block_job_iostatus_reset_locked(job); +} + void block_job_user_resume(Job *job) { BlockJob *bjob = container_of(job, BlockJob, job); -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Both blockdev.c and job-qmp.c have TOC/TOU conditions, because they first search for the job and then perform an action on it. Therefore, we need to do the search + action under the same job mutex critical section. Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop*. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220926093214.506243-9-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockdev.c | 67 +++++++++++++++++++++++++++++++++++++----------------- job-qmp.c | 57 ++++++++++++++++++++++++++++++++-------------- 2 files changed, 86 insertions(+), 38 deletions(-) diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ out: aio_context_release(aio_context); } -/* Get a block job using its ID and acquire its AioContext */ -static BlockJob *find_block_job(const char *id, AioContext **aio_context, - Error **errp) +/* + * Get a block job using its ID and acquire its AioContext. + * Called with job_mutex held. + */ +static BlockJob *find_block_job_locked(const char *id, + AioContext **aio_context, + Error **errp) { BlockJob *job; @@ -XXX,XX +XXX,XX @@ static BlockJob *find_block_job(const char *id, AioContext **aio_context, *aio_context = NULL; - job = block_job_get(id); + job = block_job_get_locked(id); if (!job) { error_set(errp, ERROR_CLASS_DEVICE_NOT_ACTIVE, @@ -XXX,XX +XXX,XX @@ static BlockJob *find_block_job(const char *id, AioContext **aio_context, void qmp_block_job_set_speed(const char *device, int64_t speed, Error **errp) { AioContext *aio_context; - BlockJob *job = find_block_job(device, &aio_context, errp); + BlockJob *job; + + JOB_LOCK_GUARD(); + job = find_block_job_locked(device, &aio_context, errp); if (!job) { return; } - block_job_set_speed(job, speed, errp); + block_job_set_speed_locked(job, speed, errp); aio_context_release(aio_context); } @@ -XXX,XX +XXX,XX @@ void qmp_block_job_cancel(const char *device, bool has_force, bool force, Error **errp) { AioContext *aio_context; - BlockJob *job = find_block_job(device, &aio_context, errp); + BlockJob *job; + + JOB_LOCK_GUARD(); + job = find_block_job_locked(device, &aio_context, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_block_job_cancel(const char *device, force = false; } - if (job_user_paused(&job->job) && !force) { + if (job_user_paused_locked(&job->job) && !force) { error_setg(errp, "The block job for device '%s' is currently paused", device); goto out; } trace_qmp_block_job_cancel(job); - job_user_cancel(&job->job, force, errp); + job_user_cancel_locked(&job->job, force, errp); out: aio_context_release(aio_context); } @@ -XXX,XX +XXX,XX @@ out: void qmp_block_job_pause(const char *device, Error **errp) { AioContext *aio_context; - BlockJob *job = find_block_job(device, &aio_context, errp); + BlockJob *job; + + JOB_LOCK_GUARD(); + job = find_block_job_locked(device, &aio_context, errp); if (!job) { return; } trace_qmp_block_job_pause(job); - job_user_pause(&job->job, errp); + job_user_pause_locked(&job->job, errp); aio_context_release(aio_context); } void qmp_block_job_resume(const char *device, Error **errp) { AioContext *aio_context; - BlockJob *job = find_block_job(device, &aio_context, errp); + BlockJob *job; + + JOB_LOCK_GUARD(); + job = find_block_job_locked(device, &aio_context, errp); if (!job) { return; } trace_qmp_block_job_resume(job); - job_user_resume(&job->job, errp); + job_user_resume_locked(&job->job, errp); aio_context_release(aio_context); } void qmp_block_job_complete(const char *device, Error **errp) { AioContext *aio_context; - BlockJob *job = find_block_job(device, &aio_context, errp); + BlockJob *job; + + JOB_LOCK_GUARD(); + job = find_block_job_locked(device, &aio_context, errp); if (!job) { return; } trace_qmp_block_job_complete(job); - job_complete(&job->job, errp); + job_complete_locked(&job->job, errp); aio_context_release(aio_context); } void qmp_block_job_finalize(const char *id, Error **errp) { AioContext *aio_context; - BlockJob *job = find_block_job(id, &aio_context, errp); + BlockJob *job; + + JOB_LOCK_GUARD(); + job = find_block_job_locked(id, &aio_context, errp); if (!job) { return; } trace_qmp_block_job_finalize(job); - job_ref(&job->job); - job_finalize(&job->job, errp); + job_ref_locked(&job->job); + job_finalize_locked(&job->job, errp); /* * Job's context might have changed via job_finalize (and job_txn_apply @@ -XXX,XX +XXX,XX @@ void qmp_block_job_finalize(const char *id, Error **errp) * one. */ aio_context = block_job_get_aio_context(job); - job_unref(&job->job); + job_unref_locked(&job->job); aio_context_release(aio_context); } void qmp_block_job_dismiss(const char *id, Error **errp) { AioContext *aio_context; - BlockJob *bjob = find_block_job(id, &aio_context, errp); + BlockJob *bjob; Job *job; + JOB_LOCK_GUARD(); + bjob = find_block_job_locked(id, &aio_context, errp); + if (!bjob) { return; } trace_qmp_block_job_dismiss(bjob); job = &bjob->job; - job_dismiss(&job, errp); + job_dismiss_locked(&job, errp); aio_context_release(aio_context); } diff --git a/job-qmp.c b/job-qmp.c index XXXXXXX..XXXXXXX 100644 --- a/job-qmp.c +++ b/job-qmp.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "trace/trace-root.h" -/* Get a job using its ID and acquire its AioContext */ -static Job *find_job(const char *id, AioContext **aio_context, Error **errp) +/* + * Get a job using its ID and acquire its AioContext. + * Called with job_mutex held. + */ +static Job *find_job_locked(const char *id, + AioContext **aio_context, + Error **errp) { Job *job; *aio_context = NULL; - job = job_get(id); + job = job_get_locked(id); if (!job) { error_setg(errp, "Job not found"); return NULL; @@ -XXX,XX +XXX,XX @@ static Job *find_job(const char *id, AioContext **aio_context, Error **errp) void qmp_job_cancel(const char *id, Error **errp) { AioContext *aio_context; - Job *job = find_job(id, &aio_context, errp); + Job *job; + + JOB_LOCK_GUARD(); + job = find_job_locked(id, &aio_context, errp); if (!job) { return; } trace_qmp_job_cancel(job); - job_user_cancel(job, true, errp); + job_user_cancel_locked(job, true, errp); aio_context_release(aio_context); } void qmp_job_pause(const char *id, Error **errp) { AioContext *aio_context; - Job *job = find_job(id, &aio_context, errp); + Job *job; + + JOB_LOCK_GUARD(); + job = find_job_locked(id, &aio_context, errp); if (!job) { return; } trace_qmp_job_pause(job); - job_user_pause(job, errp); + job_user_pause_locked(job, errp); aio_context_release(aio_context); } void qmp_job_resume(const char *id, Error **errp) { AioContext *aio_context; - Job *job = find_job(id, &aio_context, errp); + Job *job; + + JOB_LOCK_GUARD(); + job = find_job_locked(id, &aio_context, errp); if (!job) { return; } trace_qmp_job_resume(job); - job_user_resume(job, errp); + job_user_resume_locked(job, errp); aio_context_release(aio_context); } void qmp_job_complete(const char *id, Error **errp) { AioContext *aio_context; - Job *job = find_job(id, &aio_context, errp); + Job *job; + + JOB_LOCK_GUARD(); + job = find_job_locked(id, &aio_context, errp); if (!job) { return; } trace_qmp_job_complete(job); - job_complete(job, errp); + job_complete_locked(job, errp); aio_context_release(aio_context); } void qmp_job_finalize(const char *id, Error **errp) { AioContext *aio_context; - Job *job = find_job(id, &aio_context, errp); + Job *job; + + JOB_LOCK_GUARD(); + job = find_job_locked(id, &aio_context, errp); if (!job) { return; } trace_qmp_job_finalize(job); - job_ref(job); - job_finalize(job, errp); + job_ref_locked(job); + job_finalize_locked(job, errp); /* * Job's context might have changed via job_finalize (and job_txn_apply @@ -XXX,XX +XXX,XX @@ void qmp_job_finalize(const char *id, Error **errp) * one. */ aio_context = job->aio_context; - job_unref(job); + job_unref_locked(job); aio_context_release(aio_context); } void qmp_job_dismiss(const char *id, Error **errp) { AioContext *aio_context; - Job *job = find_job(id, &aio_context, errp); + Job *job; + + JOB_LOCK_GUARD(); + job = find_job_locked(id, &aio_context, errp); if (!job) { return; } trace_qmp_job_dismiss(job); - job_dismiss(&job, errp); + job_dismiss_locked(&job, errp); aio_context_release(aio_context); } -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Add missing job synchronization in the unit tests, with explicit locks. We are deliberately using _locked functions wrapped by a guard instead of a normal call because the normal call will be removed in future, as the only usage is limited to the tests. In other words, if a function like job_pause() is/will be only used in tests to avoid: WITH_JOB_LOCK_GUARD(){ job_pause_locked(); } then it is not worth keeping job_pause(), and just use the guard. Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop*. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220926093214.506243-10-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- tests/unit/test-bdrv-drain.c | 76 ++++++++++++-------- tests/unit/test-block-iothread.c | 8 ++- tests/unit/test-blockjob-txn.c | 24 ++++--- tests/unit/test-blockjob.c | 115 +++++++++++++++++++------------ 4 files changed, 140 insertions(+), 83 deletions(-) diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-bdrv-drain.c +++ b/tests/unit/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common_drain_node(enum drain_type drain_type, } } - g_assert_cmpint(job->job.pause_count, ==, 0); - g_assert_false(job->job.paused); - g_assert_true(tjob->running); - g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */ + WITH_JOB_LOCK_GUARD() { + g_assert_cmpint(job->job.pause_count, ==, 0); + g_assert_false(job->job.paused); + g_assert_true(tjob->running); + g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */ + } do_drain_begin_unlocked(drain_type, drain_bs); - if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target */ - g_assert_cmpint(job->job.pause_count, ==, 2); - } else { - g_assert_cmpint(job->job.pause_count, ==, 1); + WITH_JOB_LOCK_GUARD() { + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->job.pause_count, ==, 2); + } else { + g_assert_cmpint(job->job.pause_count, ==, 1); + } + g_assert_true(job->job.paused); + g_assert_false(job->job.busy); /* The job is paused */ } - g_assert_true(job->job.paused); - g_assert_false(job->job.busy); /* The job is paused */ do_drain_end_unlocked(drain_type, drain_bs); if (use_iothread) { - /* paused is reset in the I/O thread, wait for it */ + /* + * Here we are waiting for the paused status to change, + * so don't bother protecting the read every time. + * + * paused is reset in the I/O thread, wait for it + */ while (job->job.paused) { aio_poll(qemu_get_aio_context(), false); } } - g_assert_cmpint(job->job.pause_count, ==, 0); - g_assert_false(job->job.paused); - g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */ + WITH_JOB_LOCK_GUARD() { + g_assert_cmpint(job->job.pause_count, ==, 0); + g_assert_false(job->job.paused); + g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */ + } do_drain_begin_unlocked(drain_type, target); - if (drain_type == BDRV_DRAIN_ALL) { - /* bdrv_drain_all() drains both src and target */ - g_assert_cmpint(job->job.pause_count, ==, 2); - } else { - g_assert_cmpint(job->job.pause_count, ==, 1); + WITH_JOB_LOCK_GUARD() { + if (drain_type == BDRV_DRAIN_ALL) { + /* bdrv_drain_all() drains both src and target */ + g_assert_cmpint(job->job.pause_count, ==, 2); + } else { + g_assert_cmpint(job->job.pause_count, ==, 1); + } + g_assert_true(job->job.paused); + g_assert_false(job->job.busy); /* The job is paused */ } - g_assert_true(job->job.paused); - g_assert_false(job->job.busy); /* The job is paused */ do_drain_end_unlocked(drain_type, target); if (use_iothread) { - /* paused is reset in the I/O thread, wait for it */ + /* + * Here we are waiting for the paused status to change, + * so don't bother protecting the read every time. + * + * paused is reset in the I/O thread, wait for it + */ while (job->job.paused) { aio_poll(qemu_get_aio_context(), false); } } - g_assert_cmpint(job->job.pause_count, ==, 0); - g_assert_false(job->job.paused); - g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */ + WITH_JOB_LOCK_GUARD() { + g_assert_cmpint(job->job.pause_count, ==, 0); + g_assert_false(job->job.paused); + g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */ + } aio_context_acquire(ctx); - ret = job_complete_sync(&job->job, &error_abort); + WITH_JOB_LOCK_GUARD() { + ret = job_complete_sync_locked(&job->job, &error_abort); + } g_assert_cmpint(ret, ==, (result == TEST_JOB_SUCCESS ? 0 : -EIO)); if (use_iothread) { diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_attach_blockjob(void) } aio_context_acquire(ctx); - job_complete_sync(&tjob->common.job, &error_abort); + WITH_JOB_LOCK_GUARD() { + job_complete_sync_locked(&tjob->common.job, &error_abort); + } blk_set_aio_context(blk, qemu_get_aio_context(), &error_abort); aio_context_release(ctx); @@ -XXX,XX +XXX,XX @@ static void test_propagate_mirror(void) BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT, false, "filter_node", MIRROR_COPY_MODE_BACKGROUND, &error_abort); - job = job_get("job0"); + WITH_JOB_LOCK_GUARD() { + job = job_get_locked("job0"); + } filter = bdrv_find_node("filter_node"); /* Change the AioContext of src */ diff --git a/tests/unit/test-blockjob-txn.c b/tests/unit/test-blockjob-txn.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-blockjob-txn.c +++ b/tests/unit/test-blockjob-txn.c @@ -XXX,XX +XXX,XX @@ static void test_single_job(int expected) job = test_block_job_start(1, true, expected, &result, txn); job_start(&job->job); - if (expected == -ECANCELED) { - job_cancel(&job->job, false); + WITH_JOB_LOCK_GUARD() { + if (expected == -ECANCELED) { + job_cancel_locked(&job->job, false); + } } while (result == -EINPROGRESS) { @@ -XXX,XX +XXX,XX @@ static void test_pair_jobs(int expected1, int expected2) /* Release our reference now to trigger as many nice * use-after-free bugs as possible. */ - job_txn_unref(txn); + WITH_JOB_LOCK_GUARD() { + job_txn_unref_locked(txn); - if (expected1 == -ECANCELED) { - job_cancel(&job1->job, false); - } - if (expected2 == -ECANCELED) { - job_cancel(&job2->job, false); + if (expected1 == -ECANCELED) { + job_cancel_locked(&job1->job, false); + } + if (expected2 == -ECANCELED) { + job_cancel_locked(&job2->job, false); + } } while (result1 == -EINPROGRESS || result2 == -EINPROGRESS) { @@ -XXX,XX +XXX,XX @@ static void test_pair_jobs_fail_cancel_race(void) job_start(&job1->job); job_start(&job2->job); - job_cancel(&job1->job, false); + WITH_JOB_LOCK_GUARD() { + job_cancel_locked(&job1->job, false); + } /* Now make job2 finish before the main loop kicks jobs. This simulates * the race between a pending kick and another job completing. diff --git a/tests/unit/test-blockjob.c b/tests/unit/test-blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-blockjob.c +++ b/tests/unit/test-blockjob.c @@ -XXX,XX +XXX,XX @@ static CancelJob *create_common(Job **pjob) bjob = mk_job(blk, "Steve", &test_cancel_driver, true, JOB_MANUAL_FINALIZE | JOB_MANUAL_DISMISS); job = &bjob->job; - job_ref(job); - assert(job->status == JOB_STATUS_CREATED); + WITH_JOB_LOCK_GUARD() { + job_ref_locked(job); + assert(job->status == JOB_STATUS_CREATED); + } + s = container_of(bjob, CancelJob, common); s->blk = blk; @@ -XXX,XX +XXX,XX @@ static void cancel_common(CancelJob *s) aio_context_acquire(ctx); job_cancel_sync(&job->job, true); - if (sts != JOB_STATUS_CREATED && sts != JOB_STATUS_CONCLUDED) { - Job *dummy = &job->job; - job_dismiss(&dummy, &error_abort); + WITH_JOB_LOCK_GUARD() { + if (sts != JOB_STATUS_CREATED && sts != JOB_STATUS_CONCLUDED) { + Job *dummy = &job->job; + job_dismiss_locked(&dummy, &error_abort); + } + assert(job->job.status == JOB_STATUS_NULL); + job_unref_locked(&job->job); } - assert(job->job.status == JOB_STATUS_NULL); - job_unref(&job->job); destroy_blk(blk); aio_context_release(ctx); @@ -XXX,XX +XXX,XX @@ static void test_cancel_created(void) cancel_common(s); } +static void assert_job_status_is(Job *job, int status) +{ + WITH_JOB_LOCK_GUARD() { + assert(job->status == status); + } +} + static void test_cancel_running(void) { Job *job; @@ -XXX,XX +XXX,XX @@ static void test_cancel_running(void) s = create_common(&job); job_start(job); - assert(job->status == JOB_STATUS_RUNNING); + assert_job_status_is(job, JOB_STATUS_RUNNING); cancel_common(s); } @@ -XXX,XX +XXX,XX @@ static void test_cancel_paused(void) s = create_common(&job); job_start(job); - assert(job->status == JOB_STATUS_RUNNING); - - job_user_pause(job, &error_abort); + WITH_JOB_LOCK_GUARD() { + assert(job->status == JOB_STATUS_RUNNING); + job_user_pause_locked(job, &error_abort); + } job_enter(job); - assert(job->status == JOB_STATUS_PAUSED); + assert_job_status_is(job, JOB_STATUS_PAUSED); cancel_common(s); } @@ -XXX,XX +XXX,XX @@ static void test_cancel_ready(void) s = create_common(&job); job_start(job); - assert(job->status == JOB_STATUS_RUNNING); + assert_job_status_is(job, JOB_STATUS_RUNNING); s->should_converge = true; job_enter(job); - assert(job->status == JOB_STATUS_READY); + assert_job_status_is(job, JOB_STATUS_READY); cancel_common(s); } @@ -XXX,XX +XXX,XX @@ static void test_cancel_standby(void) s = create_common(&job); job_start(job); - assert(job->status == JOB_STATUS_RUNNING); + assert_job_status_is(job, JOB_STATUS_RUNNING); s->should_converge = true; job_enter(job); - assert(job->status == JOB_STATUS_READY); - - job_user_pause(job, &error_abort); + WITH_JOB_LOCK_GUARD() { + assert(job->status == JOB_STATUS_READY); + job_user_pause_locked(job, &error_abort); + } job_enter(job); - assert(job->status == JOB_STATUS_STANDBY); + assert_job_status_is(job, JOB_STATUS_STANDBY); cancel_common(s); } @@ -XXX,XX +XXX,XX @@ static void test_cancel_pending(void) s = create_common(&job); job_start(job); - assert(job->status == JOB_STATUS_RUNNING); + assert_job_status_is(job, JOB_STATUS_RUNNING); s->should_converge = true; job_enter(job); - assert(job->status == JOB_STATUS_READY); - - job_complete(job, &error_abort); + WITH_JOB_LOCK_GUARD() { + assert(job->status == JOB_STATUS_READY); + job_complete_locked(job, &error_abort); + } job_enter(job); while (!job->deferred_to_main_loop) { aio_poll(qemu_get_aio_context(), true); } - assert(job->status == JOB_STATUS_READY); + assert_job_status_is(job, JOB_STATUS_READY); aio_poll(qemu_get_aio_context(), true); - assert(job->status == JOB_STATUS_PENDING); + assert_job_status_is(job, JOB_STATUS_PENDING); cancel_common(s); } @@ -XXX,XX +XXX,XX @@ static void test_cancel_concluded(void) s = create_common(&job); job_start(job); - assert(job->status == JOB_STATUS_RUNNING); + assert_job_status_is(job, JOB_STATUS_RUNNING); s->should_converge = true; job_enter(job); - assert(job->status == JOB_STATUS_READY); - - job_complete(job, &error_abort); + WITH_JOB_LOCK_GUARD() { + assert(job->status == JOB_STATUS_READY); + job_complete_locked(job, &error_abort); + } job_enter(job); while (!job->deferred_to_main_loop) { aio_poll(qemu_get_aio_context(), true); } - assert(job->status == JOB_STATUS_READY); + assert_job_status_is(job, JOB_STATUS_READY); aio_poll(qemu_get_aio_context(), true); - assert(job->status == JOB_STATUS_PENDING); + assert_job_status_is(job, JOB_STATUS_PENDING); aio_context_acquire(job->aio_context); - job_finalize(job, &error_abort); + WITH_JOB_LOCK_GUARD() { + job_finalize_locked(job, &error_abort); + } aio_context_release(job->aio_context); - assert(job->status == JOB_STATUS_CONCLUDED); + assert_job_status_is(job, JOB_STATUS_CONCLUDED); cancel_common(s); } @@ -XXX,XX +XXX,XX @@ static void test_complete_in_standby(void) bjob = mk_job(blk, "job", &test_yielding_driver, true, JOB_MANUAL_FINALIZE | JOB_MANUAL_DISMISS); job = &bjob->job; - assert(job->status == JOB_STATUS_CREATED); + assert_job_status_is(job, JOB_STATUS_CREATED); /* Wait for the job to become READY */ job_start(job); aio_context_acquire(ctx); + /* + * Here we are waiting for the status to change, so don't bother + * protecting the read every time. + */ AIO_WAIT_WHILE(ctx, job->status != JOB_STATUS_READY); aio_context_release(ctx); /* Begin the drained section, pausing the job */ bdrv_drain_all_begin(); - assert(job->status == JOB_STATUS_STANDBY); + assert_job_status_is(job, JOB_STATUS_STANDBY); + /* Lock the IO thread to prevent the job from being run */ aio_context_acquire(ctx); /* This will schedule the job to resume it */ bdrv_drain_all_end(); - /* But the job cannot run, so it will remain on standby */ - assert(job->status == JOB_STATUS_STANDBY); + WITH_JOB_LOCK_GUARD() { + /* But the job cannot run, so it will remain on standby */ + assert(job->status == JOB_STATUS_STANDBY); - /* Even though the job is on standby, this should work */ - job_complete(job, &error_abort); + /* Even though the job is on standby, this should work */ + job_complete_locked(job, &error_abort); - /* The test is done now, clean up. */ - job_finish_sync(job, NULL, &error_abort); - assert(job->status == JOB_STATUS_PENDING); + /* The test is done now, clean up. */ + job_finish_sync_locked(job, NULL, &error_abort); + assert(job->status == JOB_STATUS_PENDING); - job_finalize(job, &error_abort); - assert(job->status == JOB_STATUS_CONCLUDED); + job_finalize_locked(job, &error_abort); + assert(job->status == JOB_STATUS_CONCLUDED); - job_dismiss(&job, &error_abort); + job_dismiss_locked(&job, &error_abort); + } destroy_blk(blk); aio_context_release(ctx); -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Once job lock is used and aiocontext is removed, mirror has to perform job operations under the same critical section, Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop*. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-11-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/mirror.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static void mirror_complete(Job *job, Error **errp) s->should_complete = true; /* If the job is paused, it will be re-entered when it is resumed */ - if (!job->paused) { - job_enter(job); + WITH_JOB_LOCK_GUARD() { + if (!job->paused) { + job_enter_cond_locked(job, NULL); + } } } @@ -XXX,XX +XXX,XX @@ static bool mirror_drained_poll(BlockJob *job) * from one of our own drain sections, to avoid a deadlock waiting for * ourselves. */ - if (!s->common.job.paused && !job_is_cancelled(&job->job) && !s->in_drain) { - return true; + WITH_JOB_LOCK_GUARD() { + if (!s->common.job.paused && !job_is_cancelled_locked(&job->job) + && !s->in_drain) { + return true; + } } return !!s->in_flight; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Now that the API offers also _locked() functions, take advantage of it and give also the caller control to take the lock and call _locked functions. This makes sense especially when we have for loops, because it makes no sense to have: for(job = job_next(); ...) where each job_next() takes the lock internally. Instead we want JOB_LOCK_GUARD(); for(job = job_next_locked(); ...) In addition, protect also direct field accesses, by either creating a new critical section or widening the existing ones. Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop*. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-12-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block.c | 17 ++++++++++------- blockdev.c | 14 ++++++++++---- blockjob.c | 35 ++++++++++++++++++++++------------- job-qmp.c | 9 ++++++--- monitor/qmp-cmds.c | 7 +++++-- qemu-img.c | 15 ++++++++++----- 6 files changed, 63 insertions(+), 34 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ static void bdrv_close(BlockDriverState *bs) void bdrv_close_all(void) { - assert(job_next(NULL) == NULL); GLOBAL_STATE_CODE(); + assert(job_next(NULL) == NULL); /* Drop references from requests still in flight, such as canceled block * jobs whose AIO context has not been polled yet */ @@ -XXX,XX +XXX,XX @@ XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp) } } - for (job = block_job_next(NULL); job; job = block_job_next(job)) { - GSList *el; + WITH_JOB_LOCK_GUARD() { + for (job = block_job_next_locked(NULL); job; + job = block_job_next_locked(job)) { + GSList *el; - xdbg_graph_add_node(gr, job, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_JOB, - job->job.id); - for (el = job->nodes; el; el = el->next) { - xdbg_graph_add_edge(gr, job, (BdrvChild *)el->data); + xdbg_graph_add_node(gr, job, X_DBG_BLOCK_GRAPH_NODE_TYPE_BLOCK_JOB, + job->job.id); + for (el = job->nodes; el; el = el->next) { + xdbg_graph_add_edge(gr, job, (BdrvChild *)el->data); + } } } diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void blockdev_mark_auto_del(BlockBackend *blk) return; } - for (job = block_job_next(NULL); job; job = block_job_next(job)) { + JOB_LOCK_GUARD(); + + for (job = block_job_next_locked(NULL); job; + job = block_job_next_locked(job)) { if (block_job_has_bdrv(job, blk_bs(blk))) { AioContext *aio_context = job->job.aio_context; aio_context_acquire(aio_context); - job_cancel(&job->job, false); + job_cancel_locked(&job->job, false); aio_context_release(aio_context); } @@ -XXX,XX +XXX,XX @@ BlockJobInfoList *qmp_query_block_jobs(Error **errp) BlockJobInfoList *head = NULL, **tail = &head; BlockJob *job; - for (job = block_job_next(NULL); job; job = block_job_next(job)) { + JOB_LOCK_GUARD(); + + for (job = block_job_next_locked(NULL); job; + job = block_job_next_locked(job)) { BlockJobInfo *value; AioContext *aio_context; @@ -XXX,XX +XXX,XX @@ BlockJobInfoList *qmp_query_block_jobs(Error **errp) } aio_context = block_job_get_aio_context(job); aio_context_acquire(aio_context); - value = block_job_query(job, errp); + value = block_job_query_locked(job, errp); aio_context_release(aio_context); if (!value) { qapi_free_BlockJobInfoList(head); diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static bool child_job_drained_poll(BdrvChild *c) /* An inactive or completed job doesn't have any pending requests. Jobs * with !job->busy are either already paused or have a pause point after * being reentered, so no job driver code will run before they pause. */ - if (!job->busy || job_is_completed(job)) { - return false; + WITH_JOB_LOCK_GUARD() { + if (!job->busy || job_is_completed_locked(job)) { + return false; + } } /* Otherwise, assume that it isn't fully stopped yet, but allow the job to @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, job->ready_notifier.notify = block_job_event_ready; job->idle_notifier.notify = block_job_on_idle; - notifier_list_add(&job->job.on_finalize_cancelled, - &job->finalize_cancelled_notifier); - notifier_list_add(&job->job.on_finalize_completed, - &job->finalize_completed_notifier); - notifier_list_add(&job->job.on_pending, &job->pending_notifier); - notifier_list_add(&job->job.on_ready, &job->ready_notifier); - notifier_list_add(&job->job.on_idle, &job->idle_notifier); + WITH_JOB_LOCK_GUARD() { + notifier_list_add(&job->job.on_finalize_cancelled, + &job->finalize_cancelled_notifier); + notifier_list_add(&job->job.on_finalize_completed, + &job->finalize_completed_notifier); + notifier_list_add(&job->job.on_pending, &job->pending_notifier); + notifier_list_add(&job->job.on_ready, &job->ready_notifier); + notifier_list_add(&job->job.on_idle, &job->idle_notifier); + } error_setg(&job->blocker, "block device is in use by block job: %s", job_type_str(&job->job)); @@ -XXX,XX +XXX,XX @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err, action); } if (action == BLOCK_ERROR_ACTION_STOP) { - if (!job->job.user_paused) { - job_pause(&job->job); - /* make the pause user visible, which will be resumed from QMP. */ - job->job.user_paused = true; + WITH_JOB_LOCK_GUARD() { + if (!job->job.user_paused) { + job_pause_locked(&job->job); + /* + * make the pause user visible, which will be + * resumed from QMP. + */ + job->job.user_paused = true; + } } block_job_iostatus_set_err(job, error); } diff --git a/job-qmp.c b/job-qmp.c index XXXXXXX..XXXXXXX 100644 --- a/job-qmp.c +++ b/job-qmp.c @@ -XXX,XX +XXX,XX @@ void qmp_job_dismiss(const char *id, Error **errp) aio_context_release(aio_context); } -static JobInfo *job_query_single(Job *job, Error **errp) +/* Called with job_mutex held. */ +static JobInfo *job_query_single_locked(Job *job, Error **errp) { JobInfo *info; uint64_t progress_current; @@ -XXX,XX +XXX,XX @@ JobInfoList *qmp_query_jobs(Error **errp) JobInfoList *head = NULL, **tail = &head; Job *job; - for (job = job_next(NULL); job; job = job_next(job)) { + JOB_LOCK_GUARD(); + + for (job = job_next_locked(NULL); job; job = job_next_locked(job)) { JobInfo *value; AioContext *aio_context; @@ -XXX,XX +XXX,XX @@ JobInfoList *qmp_query_jobs(Error **errp) } aio_context = job->aio_context; aio_context_acquire(aio_context); - value = job_query_single(job, errp); + value = job_query_single_locked(job, errp); aio_context_release(aio_context); if (!value) { qapi_free_JobInfoList(head); diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/monitor/qmp-cmds.c +++ b/monitor/qmp-cmds.c @@ -XXX,XX +XXX,XX @@ void qmp_cont(Error **errp) blk_iostatus_reset(blk); } - for (job = block_job_next(NULL); job; job = block_job_next(job)) { - block_job_iostatus_reset(job); + WITH_JOB_LOCK_GUARD() { + for (job = block_job_next_locked(NULL); job; + job = block_job_next_locked(job)) { + block_job_iostatus_reset_locked(job); + } } /* Continuing after completed migration. Images have been inactivated to diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static void run_block_job(BlockJob *job, Error **errp) int ret = 0; aio_context_acquire(aio_context); - job_ref(&job->job); + job_lock(); + job_ref_locked(&job->job); do { float progress = 0.0f; + job_unlock(); aio_poll(aio_context, true); progress_get_snapshot(&job->job.progress, &progress_current, @@ -XXX,XX +XXX,XX @@ static void run_block_job(BlockJob *job, Error **errp) progress = (float)progress_current / progress_total * 100.f; } qemu_progress_print(progress, 0); - } while (!job_is_ready(&job->job) && !job_is_completed(&job->job)); + job_lock(); + } while (!job_is_ready_locked(&job->job) && + !job_is_completed_locked(&job->job)); - if (!job_is_completed(&job->job)) { - ret = job_complete_sync(&job->job, errp); + if (!job_is_completed_locked(&job->job)) { + ret = job_complete_sync_locked(&job->job, errp); } else { ret = job->job.ret; } - job_unref(&job->job); + job_unref_locked(&job->job); + job_unlock(); aio_context_release(aio_context); /* publish completion progress only when success */ -- 2.37.3 From: Paolo Bonzini <pbonzini@redhat.com> We want to make sure access of job->aio_context is always done under either BQL or job_mutex. The problem is that using aio_co_enter(job->aiocontext, job->co) in job_start and job_enter_cond makes the coroutine immediately resume, so we can't hold the job lock. And caching it is not safe either, as it might change. job_start is under BQL, so it can freely read job->aiocontext, but job_enter_cond is not. We want to avoid reading job->aio_context in job_enter_cond, therefore: 1) use aio_co_wake(), since it doesn't want an aiocontext as argument but uses job->co->ctx 2) detect possible discrepancy between job->co->ctx and job->aio_context by checking right after the coroutine resumes back from yielding if job->aio_context has changed. If so, reschedule the coroutine to the new context. Calling bdrv_try_set_aio_context() will issue the following calls (simplified): * in terms of bdrv callbacks: .drained_begin -> .set_aio_context -> .drained_end * in terms of child_job functions: child_job_drained_begin -> child_job_set_aio_context -> child_job_drained_end * in terms of job functions: job_pause_locked -> job_set_aio_context -> job_resume_locked We can see that after setting the new aio_context, job_resume_locked calls again job_enter_cond, which then invokes aio_co_wake(). But while job->aiocontext has been set in job_set_aio_context, job->co->ctx has not changed, so the coroutine would be entering in the wrong aiocontext. Using aio_co_schedule in job_resume_locked() might seem as a valid alternative, but the problem is that the bh resuming the coroutine is not scheduled immediately, and if in the meanwhile another bdrv_try_set_aio_context() is run (see test_propagate_mirror() in test-block-iothread.c), we would have the first schedule in the wrong aiocontext, and the second set of drains won't even manage to schedule the coroutine, as job->busy would still be true from the previous job_resume_locked(). The solution is to stick with aio_co_wake() and detect every time the coroutine resumes back from yielding if job->aio_context has changed. If so, we can reschedule it to the new context. Check for the aiocontext change in job_do_yield_locked because: 1) aio_co_reschedule_self requires to be in the running coroutine 2) since child_job_set_aio_context allows changing the aiocontext only while the job is paused, this is the exact place where the coroutine resumes, before running JobDriver's code. Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <20220926093214.506243-13-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- job.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ void job_enter_cond_locked(Job *job, bool(*fn)(Job *job)) job->busy = true; real_job_unlock(); job_unlock(); - aio_co_enter(job->aio_context, job->co); + aio_co_wake(job->co); job_lock(); } @@ -XXX,XX +XXX,XX @@ void job_enter(Job *job) */ static void coroutine_fn job_do_yield_locked(Job *job, uint64_t ns) { + AioContext *next_aio_context; + real_job_lock(); if (ns != -1) { timer_mod(&job->sleep_timer, ns); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn job_do_yield_locked(Job *job, uint64_t ns) qemu_coroutine_yield(); job_lock(); - /* Set by job_enter_cond() before re-entering the coroutine. */ + next_aio_context = job->aio_context; + /* + * Coroutine has resumed, but in the meanwhile the job AioContext + * might have changed via bdrv_try_set_aio_context(), so we need to move + * the coroutine too in the new aiocontext. + */ + while (qemu_get_current_aio_context() != next_aio_context) { + job_unlock(); + aio_co_reschedule_self(next_aio_context); + job_lock(); + next_aio_context = job->aio_context; + } + + /* Set by job_enter_cond_locked() before re-entering the coroutine. */ assert(job->busy); } -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> In order to make it thread safe, implement a "fake rwlock", where we allow reads under BQL *or* job_mutex held, but writes only under BQL *and* job_mutex. The only write we have is in child_job_set_aio_ctx, which always happens under drain (so the job is paused). For this reason, introduce job_set_aio_context and make sure that the context is set under BQL, job_mutex and drain. Also make sure all other places where the aiocontext is read are protected. The reads in commit.c and mirror.c are actually safe, because always done under BQL. Note: at this stage, job_{lock/unlock} and job lock guard macros are *nop*. Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-Id: <20220926093214.506243-14-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 23 ++++++++++++++++++++--- block/replication.c | 1 + blockjob.c | 3 ++- job.c | 12 ++++++++++++ 4 files changed, 35 insertions(+), 4 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ typedef struct Job { /* ProgressMeter API is thread-safe */ ProgressMeter progress; + /** + * AioContext to run the job coroutine in. + * The job Aiocontext can be read when holding *either* + * the BQL (so we are in the main loop) or the job_mutex. + * It can only be written when we hold *both* BQL + * and the job_mutex. + */ + AioContext *aio_context; - /** Protected by AioContext lock */ - /** AioContext to run the job coroutine in */ - AioContext *aio_context; + /** Protected by AioContext lock */ /** Reference count of the block job */ int refcnt; @@ -XXX,XX +XXX,XX @@ int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), int job_finish_sync_locked(Job *job, void (*finish)(Job *, Error **errp), Error **errp); +/** + * Sets the @job->aio_context. + * Called with job_mutex *not* held. + * + * This function must run in the main thread to protect against + * concurrent read in job_finish_sync_locked(), takes the job_mutex + * lock to protect against the read in job_do_yield_locked(), and must + * be called when the job is quiescent. + */ +void job_set_aio_context(Job *job, AioContext *ctx); + #endif 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 replication_close(BlockDriverState *bs) { BDRVReplicationState *s = bs->opaque; Job *commit_job; + GLOBAL_STATE_CODE(); if (s->stage == BLOCK_REPLICATION_RUNNING) { replication_stop(s->rs, false, NULL); diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ static void child_job_set_aio_ctx(BdrvChild *c, AioContext *ctx, bdrv_set_aio_context_ignore(sibling->bs, ctx, ignore); } - job->job.aio_context = ctx; + job_set_aio_context(&job->job, ctx); } static AioContext *child_job_get_parent_aio_context(BdrvChild *c) { BlockJob *job = c->opaque; + GLOBAL_STATE_CODE(); return job->job.aio_context; } diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ Job *job_get(const char *id) return job_get_locked(id); } +void job_set_aio_context(Job *job, AioContext *ctx) +{ + /* protect against read in job_finish_sync_locked and job_start */ + GLOBAL_STATE_CODE(); + /* protect against read in job_do_yield_locked */ + JOB_LOCK_GUARD(); + /* ensure the job is quiescent while the AioContext is changed */ + assert(job->paused || job_is_completed_locked(job)); + job->aio_context = ctx; +} + /* Called with job_mutex *not* held. */ static void job_sleep_timer_cb(void *opaque) { @@ -XXX,XX +XXX,XX @@ int job_finish_sync_locked(Job *job, { Error *local_err = NULL; int ret; + GLOBAL_STATE_CODE(); job_ref_locked(job); -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> The same job lock is being used also to protect some of blockjob fields. Categorize them just as done in job.h. Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-Id: <20220926093214.506243-15-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/blockjob.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJobDriver BlockJobDriver; * Long-running operation on a BlockDriverState. */ typedef struct BlockJob { - /** Data belonging to the generic Job infrastructure */ + /** + * Data belonging to the generic Job infrastructure. + * Protected by job mutex. + */ Job job; - /** Status that is published by the query-block-jobs QMP API */ + /** + * Status that is published by the query-block-jobs QMP API. + * Protected by job mutex. + */ BlockDeviceIoStatus iostatus; - /** Speed that was set with @block_job_set_speed. */ + /** + * Speed that was set with @block_job_set_speed. + * Always modified and read under QEMU global mutex (GLOBAL_STATE_CODE). + */ int64_t speed; - /** Rate limiting data structure for implementing @speed. */ + /** + * Rate limiting data structure for implementing @speed. + * RateLimit API is thread-safe. + */ RateLimit limit; - /** Block other operations when block job is running */ + /** + * Block other operations when block job is running. + * Always modified and read under QEMU global mutex (GLOBAL_STATE_CODE). + */ Error *blocker; + /** All notifiers are set once in block_job_create() and never modified. */ + /** Called when a cancelled job is finalised. */ Notifier finalize_cancelled_notifier; @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { /** Called when the job coroutine yields or terminates */ Notifier idle_notifier; - /** BlockDriverStates that are involved in this block job */ + /** + * BlockDriverStates that are involved in this block job. + * Always modified and read under QEMU global mutex (GLOBAL_STATE_CODE). + */ GSList *nodes; } BlockJob; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> They all are called with job_lock held, in job_event_*_locked() Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220926093214.506243-16-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ int block_job_add_bdrv(BlockJob *job, const char *name, BlockDriverState *bs, return 0; } -static void block_job_on_idle(Notifier *n, void *opaque) +/* Called with job_mutex lock held. */ +static void block_job_on_idle_locked(Notifier *n, void *opaque) { aio_wait_kick(); } @@ -XXX,XX +XXX,XX @@ static void block_job_iostatus_set_err(BlockJob *job, int error) } } -static void block_job_event_cancelled(Notifier *n, void *opaque) +/* Called with job_mutex lock held. */ +static void block_job_event_cancelled_locked(Notifier *n, void *opaque) { BlockJob *job = opaque; uint64_t progress_current, progress_total; @@ -XXX,XX +XXX,XX @@ static void block_job_event_cancelled(Notifier *n, void *opaque) job->speed); } -static void block_job_event_completed(Notifier *n, void *opaque) +/* Called with job_mutex lock held. */ +static void block_job_event_completed_locked(Notifier *n, void *opaque) { BlockJob *job = opaque; const char *msg = NULL; @@ -XXX,XX +XXX,XX @@ static void block_job_event_completed(Notifier *n, void *opaque) msg); } -static void block_job_event_pending(Notifier *n, void *opaque) +/* Called with job_mutex lock held. */ +static void block_job_event_pending_locked(Notifier *n, void *opaque) { BlockJob *job = opaque; @@ -XXX,XX +XXX,XX @@ static void block_job_event_pending(Notifier *n, void *opaque) job->job.id); } -static void block_job_event_ready(Notifier *n, void *opaque) +/* Called with job_mutex lock held. */ +static void block_job_event_ready_locked(Notifier *n, void *opaque) { BlockJob *job = opaque; uint64_t progress_current, progress_total; @@ -XXX,XX +XXX,XX @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, ratelimit_init(&job->limit); - job->finalize_cancelled_notifier.notify = block_job_event_cancelled; - job->finalize_completed_notifier.notify = block_job_event_completed; - job->pending_notifier.notify = block_job_event_pending; - job->ready_notifier.notify = block_job_event_ready; - job->idle_notifier.notify = block_job_on_idle; + job->finalize_cancelled_notifier.notify = block_job_event_cancelled_locked; + job->finalize_completed_notifier.notify = block_job_event_completed_locked; + job->pending_notifier.notify = block_job_event_pending_locked; + job->ready_notifier.notify = block_job_event_ready_locked; + job->idle_notifier.notify = block_job_on_idle_locked; WITH_JOB_LOCK_GUARD() { notifier_list_add(&job->job.on_finalize_cancelled, -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> iostatus is the only field (together with .job) that needs protection using the job mutex. It is set in the main loop (GLOBAL_STATE functions) but read in I/O code (block_job_error_action). In order to protect it, change block_job_iostatus_set_err to block_job_iostatus_set_err_locked(), always called under job lock. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-17-eesposit@redhat.com> [kwolf: Fixed up type of iostatus] Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/mirror.c | 6 +++++- blockjob.c | 5 +++-- 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/block/mirror.c b/block/mirror.c index XXXXXXX..XXXXXXX 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_run(Job *job, Error **errp) BlockDriverState *bs = s->mirror_top_bs->backing->bs; BlockDriverState *target_bs = blk_bs(s->target); bool need_drain = true; + BlockDeviceIoStatus iostatus; int64_t length; int64_t target_length; BlockDriverInfo bdi; @@ -XXX,XX +XXX,XX @@ static int coroutine_fn mirror_run(Job *job, Error **errp) * We do so every BLKOCK_JOB_SLICE_TIME nanoseconds, or when there is * an error, or when the source is clean, whichever comes first. */ delta = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - s->last_pause_ns; + WITH_JOB_LOCK_GUARD() { + iostatus = s->common.iostatus; + } if (delta < BLOCK_JOB_SLICE_TIME && - s->common.iostatus == BLOCK_DEVICE_IO_STATUS_OK) { + iostatus == BLOCK_DEVICE_IO_STATUS_OK) { if (s->in_flight >= MAX_IN_FLIGHT || s->buf_free_count == 0 || (cnt == 0 && s->in_flight > 0)) { trace_mirror_yield(s, cnt, s->buf_free_count, s->in_flight); diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp) return block_job_query_locked(job, errp); } -static void block_job_iostatus_set_err(BlockJob *job, int error) +/* Called with job lock held */ +static void block_job_iostatus_set_err_locked(BlockJob *job, int error) { if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) { job->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE : @@ -XXX,XX +XXX,XX @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockdevOnError on_err, */ job->job.user_paused = true; } + block_job_iostatus_set_err_locked(job, error); } - block_job_iostatus_set_err(job, error); } return action; } -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Some callbacks implementation use bdrv_* APIs that assume the AioContext lock is held. Make sure this invariant is documented. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-18-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ typedef struct Job { /** True if this job should automatically dismiss itself */ bool auto_dismiss; - /** The completion function that will be called when the job completes. */ + /** + * The completion function that will be called when the job completes. + * Called with AioContext lock held, since many callback implementations + * use bdrv_* functions that require to hold the lock. + */ BlockCompletionFunc *cb; /** The opaque value that is passed to the completion function. */ @@ -XXX,XX +XXX,XX @@ struct JobDriver { * * This callback will not be invoked if the job has already failed. * If it fails, abort and then clean will be called. + * + * Called with AioContext lock held, since many callbacs implementations + * use bdrv_* functions that require to hold the lock. */ int (*prepare)(Job *job); @@ -XXX,XX +XXX,XX @@ struct JobDriver { * * All jobs will complete with a call to either .commit() or .abort() but * never both. + * + * Called with AioContext lock held, since many callback implementations + * use bdrv_* functions that require to hold the lock. */ void (*commit)(Job *job); @@ -XXX,XX +XXX,XX @@ struct JobDriver { * * All jobs will complete with a call to either .commit() or .abort() but * never both. + * + * Called with AioContext lock held, since many callback implementations + * use bdrv_* functions that require to hold the lock. */ void (*abort)(Job *job); @@ -XXX,XX +XXX,XX @@ struct JobDriver { * .commit() or .abort(). Regardless of which callback is invoked after * completion, .clean() will always be called, even if the job does not * belong to a transaction group. + * + * Called with AioContext lock held, since many callbacs implementations + * use bdrv_* functions that require to hold the lock. */ void (*clean)(Job *job); @@ -XXX,XX +XXX,XX @@ struct JobDriver { * READY). * (If the callback is NULL, the job is assumed to terminate * without I/O.) + * + * Called with AioContext lock held, since many callback implementations + * use bdrv_* functions that require to hold the lock. */ bool (*cancel)(Job *job, bool force); - /** Called when the job is freed */ + /** + * Called when the job is freed. + * Called with AioContext lock held, since many callback implementations + * use bdrv_* functions that require to hold the lock. + */ void (*free)(Job *job); }; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Change the job_{lock/unlock} and macros to use job_mutex. Now that they are not nop anymore, remove the aiocontext to avoid deadlocks. Therefore: - when possible, remove completely the aiocontext lock/unlock pair - if it is used by some other function too, reduce the locking section as much as possible, leaving the job API outside. - change AIO_WAIT_WHILE in AIO_WAIT_WHILE_UNLOCKED, since we are not using the aiocontext lock anymore The only functions that still need the aiocontext lock are: - the JobDriver callbacks, already documented in job.h - job_cancel_sync() in replication.c is called with aio_context_lock taken, but now job is using AIO_WAIT_WHILE_UNLOCKED so we need to release the lock. Reduce the locking section to only cover the callback invocation and document the functions that take the AioContext lock, to avoid taking it twice. Also remove real_job_{lock/unlock}, as they are replaced by the public functions. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Message-Id: <20220926093214.506243-19-eesposit@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 17 ++--- block/replication.c | 2 + blockdev.c | 72 +++----------------- job-qmp.c | 46 +++---------- job.c | 111 +++++++++---------------------- qemu-img.c | 2 - tests/unit/test-bdrv-drain.c | 4 +- tests/unit/test-block-iothread.c | 2 +- tests/unit/test-blockjob.c | 19 +++--- 9 files changed, 72 insertions(+), 203 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ typedef struct Job { AioContext *aio_context; - /** Protected by AioContext lock */ + /** Protected by job_mutex */ /** Reference count of the block job */ int refcnt; @@ -XXX,XX +XXX,XX @@ typedef struct Job { /** * Set to false by the job while the coroutine has yielded and may be * re-entered by job_enter(). There may still be I/O or event loop activity - * pending. Accessed under block_job_mutex (in blockjob.c). + * pending. Accessed under job_mutex. * * When the job is deferred to the main loop, busy is true as long as the * bottom half is still pending. @@ -XXX,XX +XXX,XX @@ typedef enum JobCreateFlags { extern QemuMutex job_mutex; -#define JOB_LOCK_GUARD() /* QEMU_LOCK_GUARD(&job_mutex) */ +#define JOB_LOCK_GUARD() QEMU_LOCK_GUARD(&job_mutex) -#define WITH_JOB_LOCK_GUARD() /* WITH_QEMU_LOCK_GUARD(&job_mutex) */ +#define WITH_JOB_LOCK_GUARD() WITH_QEMU_LOCK_GUARD(&job_mutex) /** * job_lock: @@ -XXX,XX +XXX,XX @@ void job_ref_locked(Job *job); /** * Release a reference that was previously acquired with job_ref() or * job_create(). If it's the last reference to the object, it will be freed. + * + * Takes AioContext lock internally to invoke a job->driver callback. */ void job_unref(Job *job); @@ -XXX,XX +XXX,XX @@ void job_user_cancel_locked(Job *job, bool force, Error **errp); * Returns the return value from the job if the job actually completed * during the call, or -ECANCELED if it was canceled. * - * Callers must hold the AioContext lock of job->aio_context. + * Called with job_lock *not* held. */ int job_cancel_sync(Job *job, bool force); @@ -XXX,XX +XXX,XX @@ void job_cancel_sync_all(void); * function). * * Returns the return value from the job. - * - * Callers must hold the AioContext lock of job->aio_context. + * Called with job_lock *not* held. */ int job_complete_sync(Job *job, Error **errp); @@ -XXX,XX +XXX,XX @@ void job_dismiss_locked(Job **job, Error **errp); * Returns 0 if the job is successfully completed, -ECANCELED if the job was * cancelled before completing, and -errno in other error cases. * - * Callers must hold the AioContext lock of job->aio_context. + * Called with job_lock *not* held. */ int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp); 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 replication_stop(ReplicationState *rs, bool failover, Error **errp) * disk, secondary disk in backup_job_completed(). */ if (s->backup_job) { + aio_context_release(aio_context); job_cancel_sync(&s->backup_job->job, true); + aio_context_acquire(aio_context); } if (!failover) { diff --git a/blockdev.c b/blockdev.c index XXXXXXX..XXXXXXX 100644 --- a/blockdev.c +++ b/blockdev.c @@ -XXX,XX +XXX,XX @@ void blockdev_mark_auto_del(BlockBackend *blk) for (job = block_job_next_locked(NULL); job; job = block_job_next_locked(job)) { if (block_job_has_bdrv(job, blk_bs(blk))) { - AioContext *aio_context = job->job.aio_context; - aio_context_acquire(aio_context); - job_cancel_locked(&job->job, false); - - aio_context_release(aio_context); } } @@ -XXX,XX +XXX,XX @@ static void drive_backup_abort(BlkActionState *common) DriveBackupState *state = DO_UPCAST(DriveBackupState, common, common); if (state->job) { - AioContext *aio_context; - - aio_context = bdrv_get_aio_context(state->bs); - aio_context_acquire(aio_context); - job_cancel_sync(&state->job->job, true); - - aio_context_release(aio_context); } } @@ -XXX,XX +XXX,XX @@ static void blockdev_backup_abort(BlkActionState *common) BlockdevBackupState *state = DO_UPCAST(BlockdevBackupState, common, common); if (state->job) { - AioContext *aio_context; - - aio_context = bdrv_get_aio_context(state->bs); - aio_context_acquire(aio_context); - job_cancel_sync(&state->job->job, true); - - aio_context_release(aio_context); } } @@ -XXX,XX +XXX,XX @@ out: } /* - * Get a block job using its ID and acquire its AioContext. - * Called with job_mutex held. + * Get a block job using its ID. Called with job_mutex held. */ -static BlockJob *find_block_job_locked(const char *id, - AioContext **aio_context, - Error **errp) +static BlockJob *find_block_job_locked(const char *id, Error **errp) { BlockJob *job; assert(id != NULL); - *aio_context = NULL; - job = block_job_get_locked(id); if (!job) { @@ -XXX,XX +XXX,XX @@ static BlockJob *find_block_job_locked(const char *id, return NULL; } - *aio_context = block_job_get_aio_context(job); - aio_context_acquire(*aio_context); - return job; } void qmp_block_job_set_speed(const char *device, int64_t speed, Error **errp) { - AioContext *aio_context; BlockJob *job; JOB_LOCK_GUARD(); - job = find_block_job_locked(device, &aio_context, errp); + job = find_block_job_locked(device, errp); if (!job) { return; } block_job_set_speed_locked(job, speed, errp); - aio_context_release(aio_context); } void qmp_block_job_cancel(const char *device, bool has_force, bool force, Error **errp) { - AioContext *aio_context; BlockJob *job; JOB_LOCK_GUARD(); - job = find_block_job_locked(device, &aio_context, errp); + job = find_block_job_locked(device, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_block_job_cancel(const char *device, if (job_user_paused_locked(&job->job) && !force) { error_setg(errp, "The block job for device '%s' is currently paused", device); - goto out; + return; } trace_qmp_block_job_cancel(job); job_user_cancel_locked(&job->job, force, errp); -out: - aio_context_release(aio_context); } void qmp_block_job_pause(const char *device, Error **errp) { - AioContext *aio_context; BlockJob *job; JOB_LOCK_GUARD(); - job = find_block_job_locked(device, &aio_context, errp); + job = find_block_job_locked(device, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_block_job_pause(const char *device, Error **errp) trace_qmp_block_job_pause(job); job_user_pause_locked(&job->job, errp); - aio_context_release(aio_context); } void qmp_block_job_resume(const char *device, Error **errp) { - AioContext *aio_context; BlockJob *job; JOB_LOCK_GUARD(); - job = find_block_job_locked(device, &aio_context, errp); + job = find_block_job_locked(device, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_block_job_resume(const char *device, Error **errp) trace_qmp_block_job_resume(job); job_user_resume_locked(&job->job, errp); - aio_context_release(aio_context); } void qmp_block_job_complete(const char *device, Error **errp) { - AioContext *aio_context; BlockJob *job; JOB_LOCK_GUARD(); - job = find_block_job_locked(device, &aio_context, errp); + job = find_block_job_locked(device, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_block_job_complete(const char *device, Error **errp) trace_qmp_block_job_complete(job); job_complete_locked(&job->job, errp); - aio_context_release(aio_context); } void qmp_block_job_finalize(const char *id, Error **errp) { - AioContext *aio_context; BlockJob *job; JOB_LOCK_GUARD(); - job = find_block_job_locked(id, &aio_context, errp); + job = find_block_job_locked(id, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_block_job_finalize(const char *id, Error **errp) job_ref_locked(&job->job); job_finalize_locked(&job->job, errp); - /* - * Job's context might have changed via job_finalize (and job_txn_apply - * automatically acquires the new one), so make sure we release the correct - * one. - */ - aio_context = block_job_get_aio_context(job); job_unref_locked(&job->job); - aio_context_release(aio_context); } void qmp_block_job_dismiss(const char *id, Error **errp) { - AioContext *aio_context; BlockJob *bjob; Job *job; JOB_LOCK_GUARD(); - bjob = find_block_job_locked(id, &aio_context, errp); + bjob = find_block_job_locked(id, errp); if (!bjob) { return; @@ -XXX,XX +XXX,XX @@ void qmp_block_job_dismiss(const char *id, Error **errp) trace_qmp_block_job_dismiss(bjob); job = &bjob->job; job_dismiss_locked(&job, errp); - aio_context_release(aio_context); } void qmp_change_backing_file(const char *device, @@ -XXX,XX +XXX,XX @@ BlockJobInfoList *qmp_query_block_jobs(Error **errp) for (job = block_job_next_locked(NULL); job; job = block_job_next_locked(job)) { BlockJobInfo *value; - AioContext *aio_context; if (block_job_is_internal(job)) { continue; } - aio_context = block_job_get_aio_context(job); - aio_context_acquire(aio_context); value = block_job_query_locked(job, errp); - aio_context_release(aio_context); if (!value) { qapi_free_BlockJobInfoList(head); return NULL; diff --git a/job-qmp.c b/job-qmp.c index XXXXXXX..XXXXXXX 100644 --- a/job-qmp.c +++ b/job-qmp.c @@ -XXX,XX +XXX,XX @@ #include "trace/trace-root.h" /* - * Get a job using its ID and acquire its AioContext. - * Called with job_mutex held. + * Get a job using its ID. Called with job_mutex held. */ -static Job *find_job_locked(const char *id, - AioContext **aio_context, - Error **errp) +static Job *find_job_locked(const char *id, Error **errp) { Job *job; - *aio_context = NULL; - job = job_get_locked(id); if (!job) { error_setg(errp, "Job not found"); return NULL; } - *aio_context = job->aio_context; - aio_context_acquire(*aio_context); - return job; } void qmp_job_cancel(const char *id, Error **errp) { - AioContext *aio_context; Job *job; JOB_LOCK_GUARD(); - job = find_job_locked(id, &aio_context, errp); + job = find_job_locked(id, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_job_cancel(const char *id, Error **errp) trace_qmp_job_cancel(job); job_user_cancel_locked(job, true, errp); - aio_context_release(aio_context); } void qmp_job_pause(const char *id, Error **errp) { - AioContext *aio_context; Job *job; JOB_LOCK_GUARD(); - job = find_job_locked(id, &aio_context, errp); + job = find_job_locked(id, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_job_pause(const char *id, Error **errp) trace_qmp_job_pause(job); job_user_pause_locked(job, errp); - aio_context_release(aio_context); } void qmp_job_resume(const char *id, Error **errp) { - AioContext *aio_context; Job *job; JOB_LOCK_GUARD(); - job = find_job_locked(id, &aio_context, errp); + job = find_job_locked(id, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_job_resume(const char *id, Error **errp) trace_qmp_job_resume(job); job_user_resume_locked(job, errp); - aio_context_release(aio_context); } void qmp_job_complete(const char *id, Error **errp) { - AioContext *aio_context; Job *job; JOB_LOCK_GUARD(); - job = find_job_locked(id, &aio_context, errp); + job = find_job_locked(id, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_job_complete(const char *id, Error **errp) trace_qmp_job_complete(job); job_complete_locked(job, errp); - aio_context_release(aio_context); } void qmp_job_finalize(const char *id, Error **errp) { - AioContext *aio_context; Job *job; JOB_LOCK_GUARD(); - job = find_job_locked(id, &aio_context, errp); + job = find_job_locked(id, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_job_finalize(const char *id, Error **errp) job_ref_locked(job); job_finalize_locked(job, errp); - /* - * Job's context might have changed via job_finalize (and job_txn_apply - * automatically acquires the new one), so make sure we release the correct - * one. - */ - aio_context = job->aio_context; job_unref_locked(job); - aio_context_release(aio_context); } void qmp_job_dismiss(const char *id, Error **errp) { - AioContext *aio_context; Job *job; JOB_LOCK_GUARD(); - job = find_job_locked(id, &aio_context, errp); + job = find_job_locked(id, errp); if (!job) { return; @@ -XXX,XX +XXX,XX @@ void qmp_job_dismiss(const char *id, Error **errp) trace_qmp_job_dismiss(job); job_dismiss_locked(&job, errp); - aio_context_release(aio_context); } /* Called with job_mutex held. */ @@ -XXX,XX +XXX,XX @@ JobInfoList *qmp_query_jobs(Error **errp) for (job = job_next_locked(NULL); job; job = job_next_locked(job)) { JobInfo *value; - AioContext *aio_context; if (job_is_internal(job)) { continue; } - aio_context = job->aio_context; - aio_context_acquire(aio_context); value = job_query_single_locked(job, errp); - aio_context_release(aio_context); if (!value) { qapi_free_JobInfoList(head); return NULL; diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ * * The second includes functions used by the job drivers and sometimes * by the core block layer. These delegate the locking to the callee instead. - * - * TODO Actually make this true */ /* @@ -XXX,XX +XXX,XX @@ struct JobTxn { }; void job_lock(void) -{ - /* nop */ -} - -void job_unlock(void) -{ - /* nop */ -} - -static void real_job_lock(void) { qemu_mutex_lock(&job_mutex); } -static void real_job_unlock(void) +void job_unlock(void) { qemu_mutex_unlock(&job_mutex); } @@ -XXX,XX +XXX,XX @@ static void job_txn_del_job_locked(Job *job) /* Called with job_mutex held, but releases it temporarily. */ static int job_txn_apply_locked(Job *job, int fn(Job *)) { - AioContext *inner_ctx; Job *other_job, *next; JobTxn *txn = job->txn; int rc = 0; @@ -XXX,XX +XXX,XX @@ static int job_txn_apply_locked(Job *job, int fn(Job *)) * break AIO_WAIT_WHILE from within fn. */ job_ref_locked(job); - aio_context_release(job->aio_context); QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) { - inner_ctx = other_job->aio_context; - aio_context_acquire(inner_ctx); rc = fn(other_job); - aio_context_release(inner_ctx); if (rc) { break; } } - /* - * Note that job->aio_context might have been changed by calling fn, so we - * can't use a local variable to cache it. - */ - aio_context_acquire(job->aio_context); job_unref_locked(job); return rc; } @@ -XXX,XX +XXX,XX @@ void job_unref_locked(Job *job) assert(!job->txn); if (job->driver->free) { + AioContext *aio_context = job->aio_context; job_unlock(); + /* FIXME: aiocontext lock is required because cb calls blk_unref */ + aio_context_acquire(aio_context); job->driver->free(job); + aio_context_release(aio_context); job_lock(); } @@ -XXX,XX +XXX,XX @@ void job_enter_cond_locked(Job *job, bool(*fn)(Job *job)) return; } - real_job_lock(); if (job->busy) { - real_job_unlock(); return; } if (fn && !fn(job)) { - real_job_unlock(); return; } assert(!job->deferred_to_main_loop); timer_del(&job->sleep_timer); job->busy = true; - real_job_unlock(); job_unlock(); aio_co_wake(job->co); job_lock(); @@ -XXX,XX +XXX,XX @@ static void coroutine_fn job_do_yield_locked(Job *job, uint64_t ns) { AioContext *next_aio_context; - real_job_lock(); if (ns != -1) { timer_mod(&job->sleep_timer, ns); } job->busy = false; job_event_idle_locked(job); - real_job_unlock(); job_unlock(); qemu_coroutine_yield(); job_lock(); @@ -XXX,XX +XXX,XX @@ static void job_clean(Job *job) } } -/* Called with job_mutex held, but releases it temporarily */ +/* + * Called with job_mutex held, but releases it temporarily. + * Takes AioContext lock internally to invoke a job->driver callback. + */ static int job_finalize_single_locked(Job *job) { int job_ret; + AioContext *ctx = job->aio_context; assert(job_is_completed_locked(job)); @@ -XXX,XX +XXX,XX @@ static int job_finalize_single_locked(Job *job) job_ret = job->ret; job_unlock(); + aio_context_acquire(ctx); if (!job_ret) { job_commit(job); @@ -XXX,XX +XXX,XX @@ static int job_finalize_single_locked(Job *job) } job_clean(job); - job_lock(); - if (job->cb) { - job_ret = job->ret; - job_unlock(); job->cb(job->opaque, job_ret); - job_lock(); } + aio_context_release(ctx); + job_lock(); + /* Emit events only if we actually started */ if (job_started_locked(job)) { if (job_is_cancelled_locked(job)) { @@ -XXX,XX +XXX,XX @@ static int job_finalize_single_locked(Job *job) return 0; } -/* Called with job_mutex held, but releases it temporarily */ +/* + * Called with job_mutex held, but releases it temporarily. + * Takes AioContext lock internally to invoke a job->driver callback. + */ static void job_cancel_async_locked(Job *job, bool force) { + AioContext *ctx = job->aio_context; GLOBAL_STATE_CODE(); if (job->driver->cancel) { job_unlock(); + aio_context_acquire(ctx); force = job->driver->cancel(job, force); + aio_context_release(ctx); job_lock(); } else { /* No .cancel() means the job will behave as if force-cancelled */ @@ -XXX,XX +XXX,XX @@ static void job_cancel_async_locked(Job *job, bool force) } } -/* Called with job_mutex held, but releases it temporarily. */ +/* + * Called with job_mutex held, but releases it temporarily. + * Takes AioContext lock internally to invoke a job->driver callback. + */ static void job_completed_txn_abort_locked(Job *job) { - AioContext *ctx; JobTxn *txn = job->txn; Job *other_job; @@ -XXX,XX +XXX,XX @@ static void job_completed_txn_abort_locked(Job *job) txn->aborting = true; job_txn_ref_locked(txn); - /* - * We can only hold the single job's AioContext lock while calling - * job_finalize_single() because the finalization callbacks can involve - * calls of AIO_WAIT_WHILE(), which could deadlock otherwise. - * Note that the job's AioContext may change when it is finalized. - */ job_ref_locked(job); - aio_context_release(job->aio_context); /* Other jobs are effectively cancelled by us, set the status for * them; this job, however, may or may not be cancelled, depending * on the caller, so leave it. */ QLIST_FOREACH(other_job, &txn->jobs, txn_list) { if (other_job != job) { - ctx = other_job->aio_context; - aio_context_acquire(ctx); /* * This is a transaction: If one job failed, no result will matter. * Therefore, pass force=true to terminate all other jobs as quickly * as possible. */ job_cancel_async_locked(other_job, true); - aio_context_release(ctx); } } while (!QLIST_EMPTY(&txn->jobs)) { other_job = QLIST_FIRST(&txn->jobs); - /* - * The job's AioContext may change, so store it in @ctx so we - * release the same context that we have acquired before. - */ - ctx = other_job->aio_context; - aio_context_acquire(ctx); if (!job_is_completed_locked(other_job)) { assert(job_cancel_requested_locked(other_job)); job_finish_sync_locked(other_job, NULL, NULL); } job_finalize_single_locked(other_job); - aio_context_release(ctx); } - /* - * Use job_ref()/job_unref() so we can read the AioContext here - * even if the job went away during job_finalize_single(). - */ - aio_context_acquire(job->aio_context); job_unref_locked(job); - job_txn_unref_locked(txn); } @@ -XXX,XX +XXX,XX @@ static void job_completed_txn_abort_locked(Job *job) static int job_prepare_locked(Job *job) { int ret; + AioContext *ctx = job->aio_context; GLOBAL_STATE_CODE(); + if (job->ret == 0 && job->driver->prepare) { job_unlock(); + aio_context_acquire(ctx); ret = job->driver->prepare(job); + aio_context_release(ctx); job_lock(); job->ret = ret; job_update_rc_locked(job); } + return job->ret; } @@ -XXX,XX +XXX,XX @@ static void job_completed_locked(Job *job) static void job_exit(void *opaque) { Job *job = (Job *)opaque; - AioContext *ctx; JOB_LOCK_GUARD(); - job_ref_locked(job); - aio_context_acquire(job->aio_context); /* This is a lie, we're not quiescent, but still doing the completion * callbacks. However, completion callbacks tend to involve operations that @@ -XXX,XX +XXX,XX @@ static void job_exit(void *opaque) job_event_idle_locked(job); job_completed_locked(job); - - /* - * Note that calling job_completed can move the job to a different - * aio_context, so we cannot cache from above. job_txn_apply takes care of - * acquiring the new lock, and we ref/unref to avoid job_completed freeing - * the job underneath us. - */ - ctx = job->aio_context; job_unref_locked(job); - aio_context_release(ctx); } /** @@ -XXX,XX +XXX,XX @@ int job_cancel_sync(Job *job, bool force) void job_cancel_sync_all(void) { Job *job; - AioContext *aio_context; JOB_LOCK_GUARD(); while ((job = job_next_locked(NULL))) { - aio_context = job->aio_context; - aio_context_acquire(aio_context); job_cancel_sync_locked(job, true); - aio_context_release(aio_context); } } @@ -XXX,XX +XXX,XX @@ int job_finish_sync_locked(Job *job, } job_unlock(); - AIO_WAIT_WHILE(job->aio_context, - (job_enter(job), !job_is_completed(job))); + AIO_WAIT_WHILE_UNLOCKED(job->aio_context, + (job_enter(job), !job_is_completed(job))); job_lock(); ret = (job_is_cancelled_locked(job) && job->ret == 0) diff --git a/qemu-img.c b/qemu-img.c index XXXXXXX..XXXXXXX 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -XXX,XX +XXX,XX @@ static void run_block_job(BlockJob *job, Error **errp) AioContext *aio_context = block_job_get_aio_context(job); int ret = 0; - aio_context_acquire(aio_context); job_lock(); job_ref_locked(&job->job); do { @@ -XXX,XX +XXX,XX @@ static void run_block_job(BlockJob *job, Error **errp) } job_unref_locked(&job->job); job_unlock(); - aio_context_release(aio_context); /* publish completion progress only when success */ if (!ret) { diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-bdrv-drain.c +++ b/tests/unit/test-bdrv-drain.c @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common_drain_node(enum drain_type drain_type, tjob->prepare_ret = -EIO; break; } + aio_context_release(ctx); job_start(&job->job); - aio_context_release(ctx); if (use_iothread) { /* job_co_entry() is run in the I/O thread, wait for the actual job @@ -XXX,XX +XXX,XX @@ static void test_blockjob_common_drain_node(enum drain_type drain_type, g_assert_true(job->job.busy); /* We're in qemu_co_sleep_ns() */ } - aio_context_acquire(ctx); WITH_JOB_LOCK_GUARD() { ret = job_complete_sync_locked(&job->job, &error_abort); } g_assert_cmpint(ret, ==, (result == TEST_JOB_SUCCESS ? 0 : -EIO)); + aio_context_acquire(ctx); if (use_iothread) { blk_set_aio_context(blk_src, qemu_get_aio_context(), &error_abort); assert(blk_get_aio_context(blk_target) == qemu_get_aio_context()); diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -XXX,XX +XXX,XX @@ static void test_attach_blockjob(void) aio_poll(qemu_get_aio_context(), false); } - aio_context_acquire(ctx); WITH_JOB_LOCK_GUARD() { job_complete_sync_locked(&tjob->common.job, &error_abort); } + aio_context_acquire(ctx); blk_set_aio_context(blk, qemu_get_aio_context(), &error_abort); aio_context_release(ctx); diff --git a/tests/unit/test-blockjob.c b/tests/unit/test-blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-blockjob.c +++ b/tests/unit/test-blockjob.c @@ -XXX,XX +XXX,XX @@ static void cancel_common(CancelJob *s) BlockJob *job = &s->common; BlockBackend *blk = s->blk; JobStatus sts = job->job.status; - AioContext *ctx; - - ctx = job->job.aio_context; - aio_context_acquire(ctx); + AioContext *ctx = job->job.aio_context; job_cancel_sync(&job->job, true); WITH_JOB_LOCK_GUARD() { @@ -XXX,XX +XXX,XX @@ static void cancel_common(CancelJob *s) assert(job->job.status == JOB_STATUS_NULL); job_unref_locked(&job->job); } - destroy_blk(blk); + aio_context_acquire(ctx); + destroy_blk(blk); aio_context_release(ctx); + } static void test_cancel_created(void) @@ -XXX,XX +XXX,XX @@ static void test_cancel_concluded(void) aio_poll(qemu_get_aio_context(), true); assert_job_status_is(job, JOB_STATUS_PENDING); - aio_context_acquire(job->aio_context); WITH_JOB_LOCK_GUARD() { job_finalize_locked(job, &error_abort); + assert(job->status == JOB_STATUS_CONCLUDED); } - aio_context_release(job->aio_context); - assert_job_status_is(job, JOB_STATUS_CONCLUDED); cancel_common(s); } @@ -XXX,XX +XXX,XX @@ static void test_complete_in_standby(void) /* Wait for the job to become READY */ job_start(job); - aio_context_acquire(ctx); /* * Here we are waiting for the status to change, so don't bother * protecting the read every time. */ - AIO_WAIT_WHILE(ctx, job->status != JOB_STATUS_READY); - aio_context_release(ctx); + AIO_WAIT_WHILE_UNLOCKED(ctx, job->status != JOB_STATUS_READY); /* Begin the drained section, pausing the job */ bdrv_drain_all_begin(); @@ -XXX,XX +XXX,XX @@ static void test_complete_in_standby(void) aio_context_acquire(ctx); /* This will schedule the job to resume it */ bdrv_drain_all_end(); + aio_context_release(ctx); WITH_JOB_LOCK_GUARD() { /* But the job cannot run, so it will remain on standby */ @@ -XXX,XX +XXX,XX @@ static void test_complete_in_standby(void) job_dismiss_locked(&job, &error_abort); } + aio_context_acquire(ctx); destroy_blk(blk); aio_context_release(ctx); iothread_join(iothread); -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> Not sure what the atomic here was supposed to do, since job.busy is protected by the job lock. Since the whole function is called under job_mutex, just remove the atomic. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220926093214.506243-20-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- blockjob.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query_locked(BlockJob *job, Error **errp) info = g_new0(BlockJobInfo, 1); info->type = g_strdup(job_type_str(&job->job)); info->device = g_strdup(job->job.id); - info->busy = qatomic_read(&job->job.busy); + info->busy = job->job.busy; info->paused = job->job.pause_count > 0; info->offset = progress_current; info->len = progress_total; -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> These public functions are not used anywhere, thus can be dropped. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Message-Id: <20220926093214.506243-21-eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/block/blockjob.h | 31 ++++++++++++------------------- blockjob.c | 16 ++-------------- 2 files changed, 14 insertions(+), 33 deletions(-) diff --git a/include/block/blockjob.h b/include/block/blockjob.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -XXX,XX +XXX,XX @@ typedef struct BlockJob { */ /** - * block_job_next: + * block_job_next_locked: * @job: A block job, or %NULL. * * Get the next element from the list of block jobs after @job, or the * first one if @job is %NULL. * * Returns the requested job, or %NULL if there are no more jobs left. + * Called with job lock held. */ -BlockJob *block_job_next(BlockJob *job); - -/* Same as block_job_next(), but called with job lock held. */ BlockJob *block_job_next_locked(BlockJob *job); /** @@ -XXX,XX +XXX,XX @@ BlockJob *block_job_next_locked(BlockJob *job); * Get the block job identified by @id (which must not be %NULL). * * Returns the requested job, or %NULL if it doesn't exist. + * Called with job lock *not* held. */ BlockJob *block_job_get(const char *id); @@ -XXX,XX +XXX,XX @@ void block_job_remove_all_bdrv(BlockJob *job); bool block_job_has_bdrv(BlockJob *job, BlockDriverState *bs); /** - * block_job_set_speed: + * block_job_set_speed_locked: * @job: The job to set the speed for. * @speed: The new value * @errp: Error object. * * Set a rate-limiting parameter for the job; the actual meaning may * vary depending on the job type. - */ -bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp); - -/* - * Same as block_job_set_speed(), but called with job lock held. - * Might release the lock temporarily. + * + * Called with job lock held, but might release it temporarily. */ bool block_job_set_speed_locked(BlockJob *job, int64_t speed, Error **errp); /** - * block_job_query: + * block_job_query_locked: * @job: The job to get information about. * * Return information about a job. + * + * Called with job lock held. */ -BlockJobInfo *block_job_query(BlockJob *job, Error **errp); - -/* Same as block_job_query(), but called with job lock held. */ BlockJobInfo *block_job_query_locked(BlockJob *job, Error **errp); /** - * block_job_iostatus_reset: + * block_job_iostatus_reset_locked: * @job: The job whose I/O status should be reset. * * Reset I/O status on @job and on BlockDriverState objects it uses, * other than job->blk. + * + * Called with job lock held. */ -void block_job_iostatus_reset(BlockJob *job); - -/* Same as block_job_iostatus_reset(), but called with job lock held. */ void block_job_iostatus_reset_locked(BlockJob *job); /* diff --git a/blockjob.c b/blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/blockjob.c +++ b/blockjob.c @@ -XXX,XX +XXX,XX @@ BlockJob *block_job_next_locked(BlockJob *bjob) return job ? container_of(job, BlockJob, job) : NULL; } -BlockJob *block_job_next(BlockJob *bjob) -{ - JOB_LOCK_GUARD(); - return block_job_next_locked(bjob); -} - BlockJob *block_job_get_locked(const char *id) { Job *job = job_get_locked(id); @@ -XXX,XX +XXX,XX @@ bool block_job_set_speed_locked(BlockJob *job, int64_t speed, Error **errp) return true; } -bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) +static bool block_job_set_speed(BlockJob *job, int64_t speed, Error **errp) { JOB_LOCK_GUARD(); return block_job_set_speed_locked(job, speed, errp); @@ -XXX,XX +XXX,XX @@ BlockJobInfo *block_job_query_locked(BlockJob *job, Error **errp) return info; } -BlockJobInfo *block_job_query(BlockJob *job, Error **errp) -{ - JOB_LOCK_GUARD(); - return block_job_query_locked(job, errp); -} - /* Called with job lock held */ static void block_job_iostatus_set_err_locked(BlockJob *job, int error) { @@ -XXX,XX +XXX,XX @@ void block_job_iostatus_reset_locked(BlockJob *job) job->iostatus = BLOCK_DEVICE_IO_STATUS_OK; } -void block_job_iostatus_reset(BlockJob *job) +static void block_job_iostatus_reset(BlockJob *job) { JOB_LOCK_GUARD(); block_job_iostatus_reset_locked(job); -- 2.37.3 From: Emanuele Giuseppe Esposito <eesposit@redhat.com> These public functions are not used anywhere, thus can be dropped. Also, since this is the final job API that doesn't use AioContext lock and replaces it with job_lock, adjust all remaining function documentation to clearly specify if the job lock is taken or not. Also document the locking requirements for a few functions where the second version is not removed. Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220926093214.506243-22-eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- include/qemu/job.h | 110 +++++++++++++------------------------ job.c | 107 ++---------------------------------- tests/unit/test-blockjob.c | 4 +- 3 files changed, 46 insertions(+), 175 deletions(-) diff --git a/include/qemu/job.h b/include/qemu/job.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -XXX,XX +XXX,XX @@ JobTxn *job_txn_new(void); /** * Release a reference that was previously acquired with job_txn_add_job or * job_txn_new. If it's the last reference to the object, it will be freed. + * + * Called with job lock *not* held. */ void job_txn_unref(JobTxn *txn); @@ -XXX,XX +XXX,XX @@ void *job_create(const char *job_id, const JobDriver *driver, JobTxn *txn, /** * Add a reference to Job refcnt, it will be decreased with job_unref, and then * be freed if it comes to be the last reference. + * + * Called with job lock held. */ -void job_ref(Job *job); - -/* Same as job_ref(), but called with job lock held. */ void job_ref_locked(Job *job); /** - * Release a reference that was previously acquired with job_ref() or + * Release a reference that was previously acquired with job_ref_locked() or * job_create(). If it's the last reference to the object, it will be freed. * * Takes AioContext lock internally to invoke a job->driver callback. + * Called with job lock held. */ -void job_unref(Job *job); - -/* Same as job_unref(), but called with job lock held. */ void job_unref_locked(Job *job); /** @@ -XXX,XX +XXX,XX @@ void job_progress_increase_remaining(Job *job, uint64_t delta); * Conditionally enter the job coroutine if the job is ready to run, not * already busy and fn() returns true. fn() is called while under the job_lock * critical section. - */ -void job_enter_cond(Job *job, bool(*fn)(Job *job)); - -/* - * Same as job_enter_cond(), but called with job lock held. - * Might release the lock temporarily. + * + * Called with job lock held, but might release it temporarily. */ void job_enter_cond_locked(Job *job, bool(*fn)(Job *job)); @@ -XXX,XX +XXX,XX @@ bool job_cancel_requested(Job *job); /** * Returns whether the job is in a completed state. - * Called with job_mutex *not* held. + * Called with job lock held. */ -bool job_is_completed(Job *job); - -/* Same as job_is_completed(), but called with job lock held. */ bool job_is_completed_locked(Job *job); /** @@ -XXX,XX +XXX,XX @@ bool job_is_ready_locked(Job *job); /** * Request @job to pause at the next pause point. Must be paired with * job_resume(). If the job is supposed to be resumed by user action, call - * job_user_pause() instead. + * job_user_pause_locked() instead. + * + * Called with job lock *not* held. */ void job_pause(Job *job); /* Same as job_pause(), but called with job lock held. */ void job_pause_locked(Job *job); -/** Resumes a @job paused with job_pause. */ +/** Resumes a @job paused with job_pause. Called with job lock *not* held. */ void job_resume(Job *job); /* @@ -XXX,XX +XXX,XX @@ void job_resume_locked(Job *job); /** * Asynchronously pause the specified @job. * Do not allow a resume until a matching call to job_user_resume. + * Called with job lock held. */ -void job_user_pause(Job *job, Error **errp); - -/* Same as job_user_pause(), but called with job lock held. */ void job_user_pause_locked(Job *job, Error **errp); -/** Returns true if the job is user-paused. */ -bool job_user_paused(Job *job); - -/* Same as job_user_paused(), but called with job lock held. */ +/** + * Returns true if the job is user-paused. + * Called with job lock held. + */ bool job_user_paused_locked(Job *job); /** * Resume the specified @job. - * Must be paired with a preceding job_user_pause. - */ -void job_user_resume(Job *job, Error **errp); - -/* - * Same as job_user_resume(), but called with job lock held. - * Might release the lock temporarily. + * Must be paired with a preceding job_user_pause_locked. + * Called with job lock held, but might release it temporarily. */ void job_user_resume_locked(Job *job, Error **errp); @@ -XXX,XX +XXX,XX @@ void job_user_resume_locked(Job *job, Error **errp); * first one if @job is %NULL. * * Returns the requested job, or %NULL if there are no more jobs left. + * Called with job lock *not* held. */ Job *job_next(Job *job); @@ -XXX,XX +XXX,XX @@ Job *job_next_locked(Job *job); * Get the job identified by @id (which must not be %NULL). * * Returns the requested job, or %NULL if it doesn't exist. + * Called with job lock held. */ -Job *job_get(const char *id); - -/* Same as job_get(), but called with job lock held. */ Job *job_get_locked(const char *id); /** * Check whether the verb @verb can be applied to @job in its current state. * Returns 0 if the verb can be applied; otherwise errp is set and -EPERM * returned. + * + * Called with job lock held. */ -int job_apply_verb(Job *job, JobVerb verb, Error **errp); - -/* Same as job_apply_verb, but called with job lock held. */ int job_apply_verb_locked(Job *job, JobVerb verb, Error **errp); /** @@ -XXX,XX +XXX,XX @@ void job_early_fail(Job *job); */ void job_transition_to_ready(Job *job); -/** Asynchronously complete the specified @job. */ -void job_complete(Job *job, Error **errp); - -/* - * Same as job_complete(), but called with job lock held. - * Might release the lock temporarily. +/** + * Asynchronously complete the specified @job. + * Called with job lock held, but might release it temporarily. */ void job_complete_locked(Job *job, Error **errp); /** * Asynchronously cancel the specified @job. If @force is true, the job should * be cancelled immediately without waiting for a consistent state. + * Called with job lock held. */ -void job_cancel(Job *job, bool force); - -/* Same as job_cancel(), but called with job lock held. */ void job_cancel_locked(Job *job, bool force); /** - * Cancels the specified job like job_cancel(), but may refuse to do so if the - * operation isn't meaningful in the current state of the job. + * Cancels the specified job like job_cancel_locked(), but may refuse + * to do so if the operation isn't meaningful in the current state of the job. + * Called with job lock held. */ -void job_user_cancel(Job *job, bool force, Error **errp); - -/* Same as job_user_cancel(), but called with job lock held. */ void job_user_cancel_locked(Job *job, bool force, Error **errp); /** @@ -XXX,XX +XXX,XX @@ void job_cancel_sync_all(void); /** * @job: The job to be completed. - * @errp: Error object which may be set by job_complete(); this is not + * @errp: Error object which may be set by job_complete_locked(); this is not * necessarily set on every error, the job return value has to be * checked as well. * @@ -XXX,XX +XXX,XX @@ void job_cancel_sync_all(void); * function). * * Returns the return value from the job. - * Called with job_lock *not* held. + * Called with job_lock held. */ -int job_complete_sync(Job *job, Error **errp); - -/* Same as job_complete_sync, but called with job lock held. */ int job_complete_sync_locked(Job *job, Error **errp); /** @@ -XXX,XX +XXX,XX @@ int job_complete_sync_locked(Job *job, Error **errp); * FIXME: Make the below statement universally true: * For jobs that support the manual workflow mode, all graph changes that occur * as a result will occur after this command and before a successful reply. + * + * Called with job lock held. */ -void job_finalize(Job *job, Error **errp); - -/* Same as job_finalize(), but called with job lock held. */ void job_finalize_locked(Job *job, Error **errp); /** * Remove the concluded @job from the query list and resets the passed pointer * to %NULL. Returns an error if the job is not actually concluded. + * + * Called with job lock held. */ -void job_dismiss(Job **job, Error **errp); - -/* Same as job_dismiss(), but called with job lock held. */ void job_dismiss_locked(Job **job, Error **errp); /** @@ -XXX,XX +XXX,XX @@ void job_dismiss_locked(Job **job, Error **errp); * Returns 0 if the job is successfully completed, -ECANCELED if the job was * cancelled before completing, and -errno in other error cases. * - * Called with job_lock *not* held. - */ -int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), - Error **errp); - -/* - * Same as job_finish_sync(), but called with job lock held. - * Might release the lock temporarily. + * Called with job_lock held, but might release it temporarily. */ int job_finish_sync_locked(Job *job, void (*finish)(Job *, Error **errp), Error **errp); diff --git a/job.c b/job.c index XXXXXXX..XXXXXXX 100644 --- a/job.c +++ b/job.c @@ -XXX,XX +XXX,XX @@ int job_apply_verb_locked(Job *job, JobVerb verb, Error **errp) return -EPERM; } -int job_apply_verb(Job *job, JobVerb verb, Error **errp) -{ - JOB_LOCK_GUARD(); - return job_apply_verb_locked(job, verb, errp); -} - JobType job_type(const Job *job) { return job->driver->job_type; @@ -XXX,XX +XXX,XX @@ bool job_is_completed_locked(Job *job) return false; } -bool job_is_completed(Job *job) +static bool job_is_completed(Job *job) { JOB_LOCK_GUARD(); return job_is_completed_locked(job); @@ -XXX,XX +XXX,XX @@ Job *job_get_locked(const char *id) return NULL; } -Job *job_get(const char *id) -{ - JOB_LOCK_GUARD(); - return job_get_locked(id); -} - void job_set_aio_context(Job *job, AioContext *ctx) { /* protect against read in job_finish_sync_locked and job_start */ @@ -XXX,XX +XXX,XX @@ void job_ref_locked(Job *job) ++job->refcnt; } -void job_ref(Job *job) -{ - JOB_LOCK_GUARD(); - job_ref_locked(job); -} - void job_unref_locked(Job *job) { GLOBAL_STATE_CODE(); @@ -XXX,XX +XXX,XX @@ void job_unref_locked(Job *job) } } -void job_unref(Job *job) -{ - JOB_LOCK_GUARD(); - job_unref_locked(job); -} - void job_progress_update(Job *job, uint64_t done) { progress_work_done(&job->progress, done); @@ -XXX,XX +XXX,XX @@ void job_enter_cond_locked(Job *job, bool(*fn)(Job *job)) job_lock(); } -void job_enter_cond(Job *job, bool(*fn)(Job *job)) -{ - JOB_LOCK_GUARD(); - job_enter_cond_locked(job, fn); -} - void job_enter(Job *job) { JOB_LOCK_GUARD(); @@ -XXX,XX +XXX,XX @@ void coroutine_fn job_pause_point(Job *job) job_pause_point_locked(job); } -static void coroutine_fn job_yield_locked(Job *job) +void coroutine_fn job_yield(Job *job) { + JOB_LOCK_GUARD(); assert(job->busy); /* Check cancellation *before* setting busy = false, too! */ @@ -XXX,XX +XXX,XX @@ static void coroutine_fn job_yield_locked(Job *job) job_pause_point_locked(job); } -void coroutine_fn job_yield(Job *job) -{ - JOB_LOCK_GUARD(); - job_yield_locked(job); -} - void coroutine_fn job_sleep_ns(Job *job, int64_t ns) { JOB_LOCK_GUARD(); @@ -XXX,XX +XXX,XX @@ void job_user_pause_locked(Job *job, Error **errp) job_pause_locked(job); } -void job_user_pause(Job *job, Error **errp) -{ - JOB_LOCK_GUARD(); - job_user_pause_locked(job, errp); -} - bool job_user_paused_locked(Job *job) { return job->user_paused; } -bool job_user_paused(Job *job) -{ - JOB_LOCK_GUARD(); - return job_user_paused_locked(job); -} - void job_user_resume_locked(Job *job, Error **errp) { assert(job); @@ -XXX,XX +XXX,XX @@ void job_user_resume_locked(Job *job, Error **errp) job_resume_locked(job); } -void job_user_resume(Job *job, Error **errp) -{ - JOB_LOCK_GUARD(); - job_user_resume_locked(job, errp); -} - /* Called with job_mutex held, but releases it temporarily. */ static void job_do_dismiss_locked(Job *job) { @@ -XXX,XX +XXX,XX @@ void job_dismiss_locked(Job **jobptr, Error **errp) *jobptr = NULL; } -void job_dismiss(Job **jobptr, Error **errp) -{ - JOB_LOCK_GUARD(); - job_dismiss_locked(jobptr, errp); -} - void job_early_fail(Job *job) { JOB_LOCK_GUARD(); @@ -XXX,XX +XXX,XX @@ void job_finalize_locked(Job *job, Error **errp) job_do_finalize_locked(job); } -void job_finalize(Job *job, Error **errp) -{ - JOB_LOCK_GUARD(); - job_finalize_locked(job, errp); -} - /* Called with job_mutex held. */ static int job_transition_to_pending_locked(Job *job) { @@ -XXX,XX +XXX,XX @@ void job_cancel_locked(Job *job, bool force) } } -void job_cancel(Job *job, bool force) -{ - JOB_LOCK_GUARD(); - job_cancel_locked(job, force); -} - void job_user_cancel_locked(Job *job, bool force, Error **errp) { if (job_apply_verb_locked(job, JOB_VERB_CANCEL, errp)) { @@ -XXX,XX +XXX,XX @@ void job_user_cancel_locked(Job *job, bool force, Error **errp) job_cancel_locked(job, force); } -void job_user_cancel(Job *job, bool force, Error **errp) -{ - JOB_LOCK_GUARD(); - job_user_cancel_locked(job, force, errp); -} - -/* A wrapper around job_cancel() taking an Error ** parameter so it may be - * used with job_finish_sync() without the need for (rather nasty) function - * pointer casts there. +/* A wrapper around job_cancel_locked() taking an Error ** parameter so it may + * be used with job_finish_sync_locked() without the need for (rather nasty) + * function pointer casts there. * * Called with job_mutex held. */ @@ -XXX,XX +XXX,XX @@ int job_complete_sync_locked(Job *job, Error **errp) return job_finish_sync_locked(job, job_complete_locked, errp); } -int job_complete_sync(Job *job, Error **errp) -{ - JOB_LOCK_GUARD(); - return job_complete_sync_locked(job, errp); -} - void job_complete_locked(Job *job, Error **errp) { /* Should not be reachable via external interface for internal jobs */ @@ -XXX,XX +XXX,XX @@ void job_complete_locked(Job *job, Error **errp) job_lock(); } -void job_complete(Job *job, Error **errp) -{ - JOB_LOCK_GUARD(); - job_complete_locked(job, errp); -} - int job_finish_sync_locked(Job *job, void (*finish)(Job *, Error **errp), Error **errp) @@ -XXX,XX +XXX,XX @@ int job_finish_sync_locked(Job *job, job_unref_locked(job); return ret; } - -int job_finish_sync(Job *job, void (*finish)(Job *, Error **errp), Error **errp) -{ - JOB_LOCK_GUARD(); - return job_finish_sync_locked(job, finish, errp); -} diff --git a/tests/unit/test-blockjob.c b/tests/unit/test-blockjob.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-blockjob.c +++ b/tests/unit/test-blockjob.c @@ -XXX,XX +XXX,XX @@ static const BlockJobDriver test_yielding_driver = { }; /* - * Test that job_complete() works even on jobs that are in a paused + * Test that job_complete_locked() works even on jobs that are in a paused * state (i.e., STANDBY). * * To do this, run YieldingJob in an IO thread, get it into the READY @@ -XXX,XX +XXX,XX @@ static const BlockJobDriver test_yielding_driver = { * acquire the context so the job will not be entered and will thus * remain on STANDBY. * - * job_complete() should still work without error. + * job_complete_locked() should still work without error. * * Note that on the QMP interface, it is impossible to lock an IO * thread before a drained section ends. In practice, the -- 2.37.3 The field is unused (only ever set, but never read) since commit ac9185603. Additionally, the commit message of commit 34fa110e already explained earlier why it's unreliable. Remove it. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Message-Id: <20220923142838.91043-1-kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com> --- block/file-posix.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/block/file-posix.c b/block/file-posix.c index XXXXXXX..XXXXXXX 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -XXX,XX +XXX,XX @@ typedef struct BDRVRawState { bool has_discard:1; bool has_write_zeroes:1; - bool discard_zeroes:1; bool use_linux_aio:1; bool use_linux_io_uring:1; int page_cache_inconsistent; /* errno from fdatasync failure */ @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, ret = -EINVAL; goto fail; } else { - s->discard_zeroes = true; s->has_fallocate = true; } } else { @@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options, } if (S_ISBLK(st.st_mode)) { -#ifdef BLKDISCARDZEROES - unsigned int arg; - if (ioctl(s->fd, BLKDISCARDZEROES, &arg) == 0 && arg) { - s->discard_zeroes = true; - } -#endif #ifdef __linux__ /* On Linux 3.10, BLKDISCARD leaves stale data in the page cache. Do * not rely on the contents of discarded blocks unless using O_DIRECT. * Same for BLKZEROOUT. */ if (!(bs->open_flags & BDRV_O_NOCACHE)) { - s->discard_zeroes = false; s->has_write_zeroes = false; } #endif -- 2.37.3