This is a note to let you know that I've just added the patch titled workqueue: make workqueue available early during boot to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: workqueue-make-workqueue-available-early-during-boot.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From foo@baz Thu Jun 16 06:59:24 PM CEST 2022 From: Tejun Heo <tj@xxxxxxxxxx> Date: Fri, 16 Sep 2016 15:49:32 -0400 Subject: workqueue: make workqueue available early during boot From: Tejun Heo <tj@xxxxxxxxxx> commit 3347fa0928210d96aaa2bd6cd5a8391d5e630873 upstream. Workqueue is currently initialized in an early init call; however, there are cases where early boot code has to be split and reordered to come after workqueue initialization or the same code path which makes use of workqueues is used both before workqueue initailization and after. The latter cases have to gate workqueue usages with keventd_up() tests, which is nasty and easy to get wrong. Workqueue usages have become widespread and it'd be a lot more convenient if it can be used very early from boot. This patch splits workqueue initialization into two steps. workqueue_init_early() which sets up the basic data structures so that workqueues can be created and work items queued, and workqueue_init() which actually brings up workqueues online and starts executing queued work items. The former step can be done very early during boot once memory allocation, cpumasks and idr are initialized. The latter right after kthreads become available. This allows work item queueing and canceling from very early boot which is what most of these use cases want. * As systemd_wq being initialized doesn't indicate that workqueue is fully online anymore, update keventd_up() to test wq_online instead. The follow-up patches will get rid of all its usages and the function itself. * Flushing doesn't make sense before workqueue is fully initialized. The flush functions trigger WARN and return immediately before fully online. * Work items are never in-flight before fully online. Canceling can always succeed by skipping the flush step. * Some code paths can no longer assume to be called with irq enabled as irq is disabled during early boot. Use irqsave/restore operations instead. v2: Watchdog init, which requires timer to be running, moved from workqueue_init_early() to workqueue_init(). Signed-off-by: Tejun Heo <tj@xxxxxxxxxx> Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Link: http://lkml.kernel.org/r/CA+55aFx0vPuMuxn00rBSM192n-Du5uxy+4AvKa0SBSOVJeuCGg@xxxxxxxxxxxxxx Signed-off-by: Jason A. Donenfeld <Jason@xxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- include/linux/workqueue.h | 7 +++- init/main.c | 10 ++++++ kernel/workqueue.c | 76 ++++++++++++++++++++++++++++++++++++---------- 3 files changed, 76 insertions(+), 17 deletions(-) --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -359,6 +359,8 @@ extern struct workqueue_struct *system_f extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; +extern bool wq_online; + extern struct workqueue_struct * __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, struct lock_class_key *key, const char *lock_name, ...) __printf(1, 6); @@ -598,7 +600,7 @@ static inline bool schedule_delayed_work */ static inline bool keventd_up(void) { - return system_wq != NULL; + return wq_online; } #ifndef CONFIG_SMP @@ -635,4 +637,7 @@ int workqueue_online_cpu(unsigned int cp int workqueue_offline_cpu(unsigned int cpu); #endif +int __init workqueue_init_early(void); +int __init workqueue_init(void); + #endif --- a/init/main.c +++ b/init/main.c @@ -554,6 +554,14 @@ asmlinkage __visible void __init start_k "Interrupts were enabled *very* early, fixing it\n")) local_irq_disable(); idr_init_cache(); + + /* + * Allow workqueue creation and work item queueing/cancelling + * early. Work item execution depends on kthreads and starts after + * workqueue_init(). + */ + workqueue_init_early(); + rcu_init(); /* trace_printk() and trace points may be used after this */ @@ -1026,6 +1034,8 @@ static noinline void __init kernel_init_ smp_prepare_cpus(setup_max_cpus); + workqueue_init(); + do_pre_smp_initcalls(); lockup_detector_init(); --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -292,6 +292,8 @@ module_param_named(disable_numa, wq_disa static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); +bool wq_online; /* can kworkers be created yet? */ + static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ @@ -2588,6 +2590,9 @@ void flush_workqueue(struct workqueue_st }; int next_color; + if (WARN_ON(!wq_online)) + return; + lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); @@ -2848,6 +2853,9 @@ bool flush_work(struct work_struct *work { struct wq_barrier barr; + if (WARN_ON(!wq_online)) + return false; + lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); @@ -2918,7 +2926,13 @@ static bool __cancel_work_timer(struct w mark_work_canceling(work); local_irq_restore(flags); - flush_work(work); + /* + * This allows canceling during early boot. We know that @work + * isn't executing. + */ + if (wq_online) + flush_work(work); + clear_work_data(work); /* @@ -3368,7 +3382,7 @@ static struct worker_pool *get_unbound_p goto fail; /* create and start the initial worker */ - if (!create_worker(pool)) + if (wq_online && !create_worker(pool)) goto fail; /* install */ @@ -3439,6 +3453,7 @@ static void pwq_adjust_max_active(struct { struct workqueue_struct *wq = pwq->wq; bool freezable = wq->flags & WQ_FREEZABLE; + unsigned long flags; /* for @wq->saved_max_active */ lockdep_assert_held(&wq->mutex); @@ -3447,7 +3462,8 @@ static void pwq_adjust_max_active(struct if (!freezable && pwq->max_active == wq->saved_max_active) return; - spin_lock_irq(&pwq->pool->lock); + /* this function can be called during early boot w/ irq disabled */ + spin_lock_irqsave(&pwq->pool->lock, flags); /* * During [un]freezing, the caller is responsible for ensuring that @@ -3477,7 +3493,7 @@ static void pwq_adjust_max_active(struct pwq->max_active = 0; } - spin_unlock_irq(&pwq->pool->lock); + spin_unlock_irqrestore(&pwq->pool->lock, flags); } /* initialize newly alloced @pwq which is associated with @wq and @pool */ @@ -5550,7 +5566,17 @@ static void __init wq_numa_init(void) wq_numa_enabled = true; } -static int __init init_workqueues(void) +/** + * workqueue_init_early - early init for workqueue subsystem + * + * This is the first half of two-staged workqueue subsystem initialization + * and invoked as soon as the bare basics - memory allocation, cpumasks and + * idr are up. It sets up all the data structures and system workqueues + * and allows early boot code to create workqueues and queue/cancel work + * items. Actual work item execution starts only after kthreads can be + * created and scheduled right before early initcalls. + */ +int __init workqueue_init_early(void) { int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; int i, cpu; @@ -5583,16 +5609,6 @@ static int __init init_workqueues(void) } } - /* create the initial worker */ - for_each_online_cpu(cpu) { - struct worker_pool *pool; - - for_each_cpu_worker_pool(pool, cpu) { - pool->flags &= ~POOL_DISASSOCIATED; - BUG_ON(!create_worker(pool)); - } - } - /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; @@ -5629,8 +5645,36 @@ static int __init init_workqueues(void) !system_power_efficient_wq || !system_freezable_power_efficient_wq); + return 0; +} + +/** + * workqueue_init - bring workqueue subsystem fully online + * + * This is the latter half of two-staged workqueue subsystem initialization + * and invoked as soon as kthreads can be created and scheduled. + * Workqueues have been created and work items queued on them, but there + * are no kworkers executing the work items yet. Populate the worker pools + * with the initial workers and enable future kworker creations. + */ +int __init workqueue_init(void) +{ + struct worker_pool *pool; + int cpu, bkt; + + /* create the initial workers */ + for_each_online_cpu(cpu) { + for_each_cpu_worker_pool(pool, cpu) { + pool->flags &= ~POOL_DISASSOCIATED; + BUG_ON(!create_worker(pool)); + } + } + + hash_for_each(unbound_pool_hash, bkt, pool, hash_node) + BUG_ON(!create_worker(pool)); + + wq_online = true; wq_watchdog_init(); return 0; } -early_initcall(init_workqueues); Patches currently in stable-queue which might be from tj@xxxxxxxxxx are queue-4.9/random-do-not-ignore-early-device-randomness.patch queue-4.9/workqueue-make-workqueue-available-early-during-boot.patch