From ef770f8101f6a3f4fb38a4fa693dfe68a0ac6bf2 Mon Sep 17 00:00:00 2001 From: Alberto Faria Date: Wed, 5 Oct 2022 18:52:09 +0100 Subject: coroutine: Drop coroutine_fn annotation from qemu_coroutine_self() 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 Message-Id: <20221005175209.975797-1-afaria@redhat.com> Reviewed-by: Kevin Wolf Reviewed-by: Paolo Bonzini Signed-off-by: Kevin Wolf --- include/qemu/coroutine.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index 08c5bb3c76..414b677302 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -97,7 +97,7 @@ 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 -- cgit v1.2.3-55-g7522 From 9fb26291acf9806e5b1211db2315e1d4140cfe40 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 22 Sep 2022 10:49:02 +0200 Subject: nbd: remove incorrect coroutine_fn annotations 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 Reviewed-by: Eric Blake Signed-off-by: Paolo Bonzini Message-Id: <20220922084924.201610-5-pbonzini@redhat.com> Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf --- include/block/nbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/block/nbd.h b/include/block/nbd.h index c74b7a9d2e..4ede3b2bd0 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -424,6 +424,6 @@ 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 -- cgit v1.2.3-55-g7522 From a248b856a8a9683fa03bbb6e1d684a9c67d92791 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 22 Sep 2022 10:49:03 +0200 Subject: coroutine: remove incorrect coroutine_fn annotations 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 Reviewed-by: Eric Blake Signed-off-by: Paolo Bonzini Message-Id: <20220922084924.201610-6-pbonzini@redhat.com> Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf --- include/qemu/coroutine.h | 2 +- util/qemu-coroutine.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/qemu/coroutine.h b/include/qemu/coroutine.h index 414b677302..aae33cce17 100644 --- a/include/qemu/coroutine.h +++ b/include/qemu/coroutine.h @@ -92,7 +92,7 @@ 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 4a8bd63ef0..356b746f0b 100644 --- a/util/qemu-coroutine.c +++ b/util/qemu-coroutine.c @@ -213,7 +213,7 @@ 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; } -- cgit v1.2.3-55-g7522 From 06753a0750a1973983505c2b544445042f555ba6 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 22 Sep 2022 10:49:19 +0200 Subject: job: add missing coroutine_fn annotations 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 Signed-off-by: Paolo Bonzini Message-Id: <20220922084924.201610-22-pbonzini@redhat.com> Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf --- include/qemu/job.h | 2 +- job.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/qemu/job.h b/include/qemu/job.h index c105b31076..397ac39608 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -436,7 +436,7 @@ 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 075c6f3a20..20f0d8b2cd 100644 --- a/job.c +++ b/job.c @@ -525,7 +525,7 @@ void coroutine_fn job_pause_point(Job *job) } } -void job_yield(Job *job) +void coroutine_fn job_yield(Job *job) { assert(job->busy); -- cgit v1.2.3-55-g7522 From 55c5a25a0363f153d8875a60001342eb6fe6e4f5 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:31:54 -0400 Subject: job.c: make job_mutex and job_lock/unlock() public 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 Reviewed-by: Stefan Hajnoczi Reviewed-by: Vladimir Sementsov-Ogievskiy Message-Id: <20220926093214.506243-2-eesposit@redhat.com> Signed-off-by: Kevin Wolf --- include/qemu/job.h | 24 ++++++++++++++++++++++++ job.c | 35 +++++++++++++++++++++++------------ 2 files changed, 47 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/qemu/job.h b/include/qemu/job.h index 397ac39608..e625547bdb 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -303,6 +303,30 @@ 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 20f0d8b2cd..7365db827a 100644 --- a/job.c +++ b/job.c @@ -32,6 +32,12 @@ #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 */ @@ -74,17 +80,22 @@ 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); } @@ -450,21 +461,21 @@ 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); } @@ -481,13 +492,13 @@ 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. */ -- cgit v1.2.3-55-g7522 From d08f07541fa34eb83680837eb45a6e1f75d177bc Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:31:55 -0400 Subject: job.h: categorize fields in struct Job 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 Reviewed-by: Vladimir Sementsov-Ogievskiy Reviewed-by: Kevin Wolf Reviewed-by: Stefan Hajnoczi Message-Id: <20220926093214.506243-3-eesposit@redhat.com> Signed-off-by: Kevin Wolf --- include/qemu/job.h | 61 ++++++++++++++++++++++++++++++++---------------------- 1 file changed, 36 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/qemu/job.h b/include/qemu/job.h index e625547bdb..8530c6a4e1 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -40,27 +40,52 @@ 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). @@ -112,14 +137,6 @@ 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. @@ -134,12 +151,6 @@ 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; @@ -167,6 +178,7 @@ typedef struct Job { /** * Callbacks and other information about a Job driver. + * All callbacks are invoked with job_mutex *not* held. */ struct JobDriver { @@ -472,7 +484,6 @@ 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); -- cgit v1.2.3-55-g7522 From 544f4d5258d4e4dd6652d28607b605e7801ed7dd Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:31:56 -0400 Subject: job.c: API functions not used outside should be static 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 Reviewed-by: Stefan Hajnoczi Reviewed-by: Vladimir Sementsov-Ogievskiy Reviewed-by: Kevin Wolf Message-Id: <20220926093214.506243-4-eesposit@redhat.com> Signed-off-by: Kevin Wolf --- include/qemu/job.h | 18 ------------------ job.c | 22 +++++++++++++++++++--- 2 files changed, 19 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/qemu/job.h b/include/qemu/job.h index 8530c6a4e1..e3e31e2548 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -358,18 +358,6 @@ 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. * @@ -431,12 +419,6 @@ 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 7365db827a..9500b5b36e 100644 --- a/job.c +++ b/job.c @@ -125,7 +125,17 @@ 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; @@ -427,12 +437,18 @@ 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); } -- cgit v1.2.3-55-g7522 From fd4b14e299d7def753f2d753e61d125cd5e1cbd8 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:31:57 -0400 Subject: aio-wait.h: introduce AIO_WAIT_WHILE_UNLOCKED 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 Reviewed-by: Stefan Hajnoczi Reviewed-by: Vladimir Sementsov-Ogievskiy Message-Id: <20220926093214.506243-5-eesposit@redhat.com> Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf --- include/block/aio-wait.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h index 54840f8622..dd9a7f6461 100644 --- a/include/block/aio-wait.h +++ b/include/block/aio-wait.h @@ -59,10 +59,13 @@ 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. @@ -75,7 +78,7 @@ 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); \ @@ -92,11 +95,11 @@ 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; \ @@ -105,6 +108,12 @@ 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 -- cgit v1.2.3-55-g7522 From afe1e8a7b3e671993cf55e2321408650c7620999 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:31:58 -0400 Subject: job.c: add job_lock/unlock while keeping job.h intact 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 Reviewed-by: Kevin Wolf Reviewed-by: Stefan Hajnoczi Reviewed-by: Vladimir Sementsov-Ogievskiy Message-Id: <20220926093214.506243-6-eesposit@redhat.com> Signed-off-by: Kevin Wolf --- include/qemu/job.h | 138 +++++++++++- job.c | 610 +++++++++++++++++++++++++++++++++++++---------------- 2 files changed, 561 insertions(+), 187 deletions(-) (limited to 'include') diff --git a/include/qemu/job.h b/include/qemu/job.h index e3e31e2548..870dce1535 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -358,8 +358,15 @@ 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. @@ -380,17 +387,25 @@ 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); @@ -401,6 +416,8 @@ 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); @@ -416,6 +433,8 @@ 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); @@ -426,11 +445,19 @@ 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); @@ -438,6 +465,7 @@ 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); @@ -446,6 +474,8 @@ 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); @@ -453,6 +483,7 @@ 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); @@ -463,6 +494,8 @@ 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); @@ -475,21 +508,40 @@ 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 @@ -497,24 +549,45 @@ 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. @@ -523,6 +596,9 @@ 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). * @@ -530,6 +606,9 @@ 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 @@ -537,27 +616,48 @@ 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 @@ -571,7 +671,14 @@ 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); /** @@ -590,6 +697,9 @@ 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. @@ -600,12 +710,18 @@ 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. @@ -615,6 +731,14 @@ 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 9500b5b36e..87564979cb 100644 --- a/job.c +++ b/job.c @@ -38,6 +38,7 @@ */ QemuMutex job_mutex; +/* Protected by job_mutex */ static QLIST_HEAD(, Job) jobs = QLIST_HEAD_INITIALIZER(jobs); /* Job State Transition Table */ @@ -113,18 +114,25 @@ 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 @@ -134,8 +142,10 @@ 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; @@ -145,19 +155,21 @@ 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; @@ -170,7 +182,7 @@ 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) { @@ -188,7 +200,7 @@ 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; } @@ -197,7 +209,8 @@ 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); @@ -212,7 +225,7 @@ 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); @@ -226,6 +239,12 @@ 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; @@ -236,19 +255,32 @@ 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: @@ -270,7 +302,13 @@ 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: @@ -292,17 +330,24 @@ 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); @@ -310,7 +355,13 @@ 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; @@ -323,6 +374,13 @@ 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; @@ -336,6 +394,8 @@ 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"); @@ -345,7 +405,7 @@ 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; } @@ -375,7 +435,7 @@ 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); @@ -386,21 +446,27 @@ 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(); @@ -410,7 +476,9 @@ 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); @@ -422,6 +490,12 @@ 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); @@ -439,38 +513,43 @@ 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) { @@ -492,12 +571,21 @@ 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. @@ -505,100 +593,129 @@ 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--; @@ -607,12 +724,18 @@ 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) { @@ -620,15 +743,27 @@ 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(); @@ -636,66 +771,84 @@ 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); } } @@ -725,43 +878,57 @@ 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; @@ -770,7 +937,9 @@ 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); @@ -791,7 +960,8 @@ 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; @@ -804,7 +974,7 @@ 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 @@ -812,7 +982,7 @@ 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 @@ -827,7 +997,7 @@ 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); } } @@ -839,11 +1009,11 @@ 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); } @@ -852,110 +1022,132 @@ 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 @@ -963,9 +1155,9 @@ 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 @@ -974,7 +1166,7 @@ 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); } @@ -985,37 +1177,47 @@ 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 @@ -1027,102 +1229,150 @@ 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); +} -- cgit v1.2.3-55-g7522 From f41ab73fa283f4f4d79102d1c8e8bad456218751 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:32:00 -0400 Subject: blockjob: introduce block_job _locked() APIs 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 Reviewed-by: Vladimir Sementsov-Ogievskiy Reviewed-by: Kevin Wolf Reviewed-by: Stefan Hajnoczi Message-Id: <20220926093214.506243-8-eesposit@redhat.com> Signed-off-by: Kevin Wolf --- blockjob.c | 52 ++++++++++++++++++++++++++++++++++++++---------- include/block/blockjob.h | 18 +++++++++++++++++ 2 files changed, 60 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/blockjob.c b/blockjob.c index 7da59a1f1c..0d59aba439 100644 --- a/blockjob.c +++ b/blockjob.c @@ -44,21 +44,27 @@ 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)) { @@ -68,6 +74,12 @@ 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); @@ -256,14 +268,14 @@ 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) { @@ -277,7 +289,9 @@ 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) { @@ -285,18 +299,24 @@ 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; @@ -320,7 +340,7 @@ 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; @@ -333,6 +353,12 @@ 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) { @@ -478,7 +504,7 @@ 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) { @@ -488,6 +514,12 @@ 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); diff --git a/include/block/blockjob.h b/include/block/blockjob.h index 6525e16fd5..8b65d3949d 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -92,6 +92,9 @@ 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. @@ -102,6 +105,9 @@ 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 @@ -145,6 +151,12 @@ 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. @@ -153,6 +165,9 @@ 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. @@ -162,6 +177,9 @@ 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: * -- cgit v1.2.3-55-g7522 From 3ed4f708fe12537066d21f3dd111af013f7a6b8c Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:32:06 -0400 Subject: jobs: protect job.aio_context with BQL and job_mutex 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 Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20220926093214.506243-14-eesposit@redhat.com> Reviewed-by: Kevin Wolf Reviewed-by: Vladimir Sementsov-Ogievskiy Signed-off-by: Kevin Wolf --- block/replication.c | 1 + blockjob.c | 3 ++- include/qemu/job.h | 23 ++++++++++++++++++++--- job.c | 12 ++++++++++++ 4 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/block/replication.c b/block/replication.c index 55c8f894aa..5977f7a833 100644 --- a/block/replication.c +++ b/block/replication.c @@ -142,6 +142,7 @@ 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 96fb9d9f73..c8919cef9b 100644 --- a/blockjob.c +++ b/blockjob.c @@ -162,12 +162,13 @@ 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/include/qemu/job.h b/include/qemu/job.h index 870dce1535..c96387069d 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -74,11 +74,17 @@ 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; @@ -741,4 +747,15 @@ 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/job.c b/job.c index 3ef5028751..3e6f61c523 100644 --- a/job.c +++ b/job.c @@ -396,6 +396,17 @@ 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) { @@ -1379,6 +1390,7 @@ int job_finish_sync_locked(Job *job, { Error *local_err = NULL; int ret; + GLOBAL_STATE_CODE(); job_ref_locked(job); -- cgit v1.2.3-55-g7522 From 3937e12cf8887660d86034c7d54c4f2236f0cb0e Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:32:07 -0400 Subject: blockjob.h: categorize fields in struct BlockJob 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 Signed-off-by: Emanuele Giuseppe Esposito Message-Id: <20220926093214.506243-15-eesposit@redhat.com> Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf --- include/block/blockjob.h | 32 ++++++++++++++++++++++++++------ 1 file changed, 26 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/block/blockjob.h b/include/block/blockjob.h index 8b65d3949d..10c24e240a 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -40,21 +40,38 @@ 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; @@ -70,7 +87,10 @@ 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; -- cgit v1.2.3-55-g7522 From 2fc3bdc3843d2d8bde54c2be4d4f4cc8a9ffcf50 Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:32:10 -0400 Subject: job.h: categorize JobDriver callbacks that need the AioContext lock 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 Reviewed-by: Vladimir Sementsov-Ogievskiy Message-Id: <20220926093214.506243-18-eesposit@redhat.com> Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf --- include/qemu/job.h | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/qemu/job.h b/include/qemu/job.h index c96387069d..b943d90e8f 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -65,7 +65,11 @@ 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. */ @@ -260,6 +264,9 @@ 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); @@ -270,6 +277,9 @@ 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); @@ -280,6 +290,9 @@ 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); @@ -288,6 +301,9 @@ 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); @@ -302,11 +318,18 @@ 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); }; -- cgit v1.2.3-55-g7522 From 6f592e5aca1a27fe1c1f661cfe68b35b90850acf Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:32:11 -0400 Subject: job.c: enable job lock/unlock and remove Aiocontext locks 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 Message-Id: <20220926093214.506243-19-eesposit@redhat.com> Reviewed-by: Kevin Wolf Reviewed-by: Vladimir Sementsov-Ogievskiy Signed-off-by: Kevin Wolf --- block/replication.c | 2 + blockdev.c | 72 ++++--------------------- include/qemu/job.h | 17 +++--- 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(-) (limited to 'include') diff --git a/block/replication.c b/block/replication.c index 5977f7a833..c67f931f37 100644 --- a/block/replication.c +++ b/block/replication.c @@ -727,7 +727,9 @@ 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 46090bb0aa..a32bafc07a 100644 --- a/blockdev.c +++ b/blockdev.c @@ -155,12 +155,7 @@ 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); } } @@ -1847,14 +1842,7 @@ 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); } } @@ -1948,14 +1936,7 @@ 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); } } @@ -3317,19 +3298,14 @@ 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) { @@ -3338,36 +3314,30 @@ 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; @@ -3380,22 +3350,19 @@ 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; @@ -3403,16 +3370,14 @@ 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; @@ -3420,16 +3385,14 @@ 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; @@ -3437,16 +3400,14 @@ 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; @@ -3456,24 +3417,16 @@ 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; @@ -3482,7 +3435,6 @@ 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, @@ -3764,15 +3716,11 @@ 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/include/qemu/job.h b/include/qemu/job.h index b943d90e8f..a54fb83887 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -88,7 +88,7 @@ typedef struct Job { AioContext *aio_context; - /** Protected by AioContext lock */ + /** Protected by job_mutex */ /** Reference count of the block job */ int refcnt; @@ -111,7 +111,7 @@ 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. @@ -346,9 +346,9 @@ 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: @@ -422,6 +422,8 @@ 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); @@ -696,7 +698,7 @@ 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); @@ -721,8 +723,7 @@ 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); @@ -758,7 +759,7 @@ 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/job-qmp.c b/job-qmp.c index 393d3a5b81..d498fc89c0 100644 --- a/job-qmp.c +++ b/job-qmp.c @@ -30,36 +30,27 @@ #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; @@ -67,16 +58,14 @@ 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; @@ -84,16 +73,14 @@ 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; @@ -101,16 +88,14 @@ 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; @@ -118,16 +103,14 @@ 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; @@ -137,23 +120,15 @@ 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; @@ -161,7 +136,6 @@ 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. */ @@ -199,15 +173,11 @@ 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 3e6f61c523..76c6d7f79d 100644 --- a/job.c +++ b/job.c @@ -44,8 +44,6 @@ * * 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 */ /* @@ -98,21 +96,11 @@ 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); } @@ -187,7 +175,6 @@ 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; @@ -199,23 +186,14 @@ 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; } @@ -503,8 +481,12 @@ 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(); } @@ -583,21 +565,17 @@ 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(); @@ -628,13 +606,11 @@ 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(); @@ -920,10 +896,14 @@ 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)); @@ -932,6 +912,7 @@ static int job_finalize_single_locked(Job *job) job_ret = job->ret; job_unlock(); + aio_context_acquire(ctx); if (!job_ret) { job_commit(job); @@ -940,15 +921,13 @@ 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)) { @@ -963,13 +942,19 @@ 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 */ @@ -1002,10 +987,12 @@ 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; @@ -1018,54 +1005,31 @@ 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); } @@ -1073,15 +1037,20 @@ 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; } @@ -1186,11 +1155,8 @@ 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 @@ -1200,16 +1166,7 @@ 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); } /** @@ -1337,14 +1294,10 @@ 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); } } @@ -1404,8 +1357,8 @@ 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 e0a30b1f4c..ace3adf8ae 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -911,7 +911,6 @@ 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 { @@ -936,7 +935,6 @@ 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 0db056ea63..4924ceb562 100644 --- a/tests/unit/test-bdrv-drain.c +++ b/tests/unit/test-bdrv-drain.c @@ -930,9 +930,9 @@ 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 @@ -1016,12 +1016,12 @@ 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 96fd21c00a..def0709b2b 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -582,10 +582,10 @@ 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 e4f126bb6d..f88e10e356 100644 --- a/tests/unit/test-blockjob.c +++ b/tests/unit/test-blockjob.c @@ -228,10 +228,7 @@ 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() { @@ -242,9 +239,11 @@ 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) @@ -384,12 +383,10 @@ 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); } @@ -481,13 +478,11 @@ 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(); @@ -497,6 +492,7 @@ 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 */ @@ -515,6 +511,7 @@ 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); -- cgit v1.2.3-55-g7522 From ba6a91005270c8e199d739c2e2afb49372ba0f7f Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:32:13 -0400 Subject: blockjob: remove unused functions These public functions are not used anywhere, thus can be dropped. Signed-off-by: Emanuele Giuseppe Esposito Reviewed-by: Stefan Hajnoczi Reviewed-by: Kevin Wolf Reviewed-by: Vladimir Sementsov-Ogievskiy Message-Id: <20220926093214.506243-21-eesposit@redhat.com> Signed-off-by: Kevin Wolf --- blockjob.c | 16 ++-------------- include/block/blockjob.h | 31 ++++++++++++------------------- 2 files changed, 14 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/blockjob.c b/blockjob.c index 120c1b7ead..bdf20a0e35 100644 --- a/blockjob.c +++ b/blockjob.c @@ -56,12 +56,6 @@ 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); @@ -308,7 +302,7 @@ 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); @@ -357,12 +351,6 @@ 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) { @@ -525,7 +513,7 @@ 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); diff --git a/include/block/blockjob.h b/include/block/blockjob.h index 10c24e240a..03032b2eca 100644 --- a/include/block/blockjob.h +++ b/include/block/blockjob.h @@ -102,17 +102,15 @@ 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); /** @@ -122,6 +120,7 @@ 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); @@ -161,43 +160,37 @@ 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); /* -- cgit v1.2.3-55-g7522 From 9bd4d3c2e3d2e1df979e818ff0a5c05ca455721a Mon Sep 17 00:00:00 2001 From: Emanuele Giuseppe Esposito Date: Mon, 26 Sep 2022 05:32:14 -0400 Subject: job: remove unused functions 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 Reviewed-by: Stefan Hajnoczi Reviewed-by: Kevin Wolf Message-Id: <20220926093214.506243-22-eesposit@redhat.com> Reviewed-by: Vladimir Sementsov-Ogievskiy Signed-off-by: Kevin Wolf --- include/qemu/job.h | 110 ++++++++++++++++----------------------------- job.c | 107 +++---------------------------------------- tests/unit/test-blockjob.c | 4 +- 3 files changed, 46 insertions(+), 175 deletions(-) (limited to 'include') diff --git a/include/qemu/job.h b/include/qemu/job.h index a54fb83887..e502787dd8 100644 --- a/include/qemu/job.h +++ b/include/qemu/job.h @@ -384,6 +384,8 @@ 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); @@ -413,21 +415,18 @@ 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); /** @@ -473,12 +472,8 @@ 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)); @@ -557,11 +552,8 @@ 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); /** @@ -576,14 +568,16 @@ 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); /* @@ -595,27 +589,20 @@ 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); @@ -624,6 +611,7 @@ 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); @@ -634,20 +622,17 @@ 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); /** @@ -662,31 +647,24 @@ 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); /** @@ -714,7 +692,7 @@ 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. * @@ -723,11 +701,8 @@ 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); /** @@ -737,19 +712,17 @@ 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); /** @@ -759,14 +732,7 @@ 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 76c6d7f79d..78feae05fb 100644 --- a/job.c +++ b/job.c @@ -233,12 +233,6 @@ 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; @@ -324,7 +318,7 @@ 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); @@ -368,12 +362,6 @@ 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 */ @@ -465,12 +453,6 @@ 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(); @@ -499,12 +481,6 @@ 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); @@ -581,12 +557,6 @@ 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(); @@ -674,8 +644,9 @@ 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! */ @@ -690,12 +661,6 @@ 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(); @@ -764,23 +729,11 @@ 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); @@ -801,12 +754,6 @@ 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) { @@ -834,12 +781,6 @@ 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(); @@ -1084,12 +1025,6 @@ 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) { @@ -1236,12 +1171,6 @@ 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)) { @@ -1250,15 +1179,9 @@ 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. */ @@ -1306,12 +1229,6 @@ 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 */ @@ -1331,12 +1248,6 @@ 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) @@ -1366,9 +1277,3 @@ 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 f88e10e356..c0426bd10c 100644 --- a/tests/unit/test-blockjob.c +++ b/tests/unit/test-blockjob.c @@ -432,7 +432,7 @@ 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 @@ -440,7 +440,7 @@ 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 -- cgit v1.2.3-55-g7522