* * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */#ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30;static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES;static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static void wq_watchdog_reset_touched(void){ int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;} static void wq_watchdog_timer_fn(struct timer_list *unused){ unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; if (list_empty(&pool->worklist)) continue; /* get the latest of pool and touched timestamps */ pool_ts = READ_ONCE(pool->watchdog_ts); touched = READ_ONCE(wq_watchdog_touched); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; if (pool->cpu >= 0) { unsigned long cpu_touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); if (time_after(cpu_touched, ts)) ts = cpu_touched; } /* did we stall? */ if (time_after(jiffies, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(jiffies - pool_ts) / 1000); } } rcu_read_unlock(); if (lockup_detected) show_workqueue_state(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh);} notrace void wq_watchdog_touch(int cpu){ if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; else wq_watchdog_touched = jiffies;} static void wq_watchdog_set_thresh(unsigned long thresh){ wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); }} static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp){ unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0;} static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong,}; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void){ timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh);} #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void __init wq_numa_init(void){ cpumask_var_t *tbl; int node, cpu; if (num_possible_nodes() <= 1) return; if (wq_disable_numa) { pr_info("workqueue: NUMA affinity support disabled\n"); return; } wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL); BUG_ON(!wq_update_unbound_numa_attrs_buf); /* * We want masks of possible CPUs of each node which isn't readily * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL); BUG_ON(!tbl); for_each_node(node) BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); if (WARN_ON(node == NUMA_NO_NODE)) { pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu); /* happens iff arch is bonkers, let's just proceed */ return; } cpumask_set_cpu(cpu, tbl[node]); } wq_numa_possible_cpumask = tbl; wq_numa_enabled = true;} /** * 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 hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; int i, cpu; WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); /* initialize CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_cpu_worker_pool(pool, cpu) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); pool->attrs->nice = std_nice[i++]; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. * Turn off NUMA so that dfl_pwq is used for all nodes. */ BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); attrs->nice = std_nice[i]; attrs->no_numa = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !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 workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; /* * It'd be simpler to initialize NUMA in workqueue_init_early() but * CPU to node mapping may not be available that early on some * archs such as power and arm64. As per-cpu pools created * previously could be missing node hint and unbound pools NUMA * affinity, fix them up. * * Also, while iterating workqueues, create rescuers if requested. */ wq_numa_init(); mutex_lock(&wq_pool_mutex); for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->node = cpu_to_node(cpu); } } list_for_each_entry(wq, &workqueues, list) { wq_update_unbound_numa(wq, smp_processor_id(), true); WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* 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;}Lines 5501–5816 of 5816. Previous lines
* * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; if (list_empty(&pool->worklist)) continue; /* get the latest of pool and touched timestamps */ pool_ts = READ_ONCE(pool->watchdog_ts); touched = READ_ONCE(wq_watchdog_touched); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; if (pool->cpu >= 0) { unsigned long cpu_touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); if (time_after(cpu_touched, ts)) ts = cpu_touched; } /* did we stall? */ if (time_after(jiffies, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(jiffies - pool_ts) / 1000); } } rcu_read_unlock(); if (lockup_detected) show_workqueue_state(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; else wq_watchdog_touched = jiffies; } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void __init wq_numa_init(void) { cpumask_var_t *tbl; int node, cpu; if (num_possible_nodes() <= 1) return; if (wq_disable_numa) { pr_info("workqueue: NUMA affinity support disabled\n"); return; } wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(GFP_KERNEL); BUG_ON(!wq_update_unbound_numa_attrs_buf); /* * We want masks of possible CPUs of each node which isn't readily * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL); BUG_ON(!tbl); for_each_node(node) BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); if (WARN_ON(node == NUMA_NO_NODE)) { pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu); /* happens iff arch is bonkers, let's just proceed */ return; } cpumask_set_cpu(cpu, tbl[node]); } wq_numa_possible_cpumask = tbl; wq_numa_enabled = true; } /** * 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 hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; int i, cpu; WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); /* initialize CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_cpu_worker_pool(pool, cpu) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); pool->attrs->nice = std_nice[i++]; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. * Turn off NUMA so that dfl_pwq is used for all nodes. */ BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); attrs->nice = std_nice[i]; attrs->no_numa = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !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 workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; /* * It'd be simpler to initialize NUMA in workqueue_init_early() but * CPU to node mapping may not be available that early on some * archs such as power and arm64. As per-cpu pools created * previously could be missing node hint and unbound pools NUMA * affinity, fix them up. * * Also, while iterating workqueues, create rescuers if requested. */ wq_numa_init(); mutex_lock(&wq_pool_mutex); for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->node = cpu_to_node(cpu); } } list_for_each_entry(wq, &workqueues, list) { wq_update_unbound_numa(wq, smp_processor_id(), true); WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* 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; }