8 files changed, 102 insertions, 48 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 132e1ec67da0..00ef43233e03 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -516,7 +516,7 @@ int mce_available(struct cpuinfo_x86 *c)
 
 static void mce_schedule_work(void)
 {
-        if (!mce_gen_pool_empty() && keventd_up())
+        if (!mce_gen_pool_empty())
                 schedule_work(&mce_work);
 }
 
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 623264445100..4c10a9df3b91 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -3923,10 +3923,6 @@ void unblank_screen(void)
  */
 static void blank_screen_t(unsigned long dummy)
 {
-        if (unlikely(!keventd_up())) {
-                mod_timer(&console_timer, jiffies + (blankinterval * HZ));
-                return;
-        }
         blank_timer_expired = 1;
         schedule_work(&console_work);
 }
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index d4f16cf6281c..a26cc437293c 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -603,14 +603,6 @@ static inline bool schedule_delayed_work(struct delayed_work *dwork,
         return queue_delayed_work(system_wq, dwork, delay);
 }
 
-/**
- * keventd_up - is workqueue initialized yet?
- */
-static inline bool keventd_up(void)
-{
-        return system_wq != NULL;
-}
-
 #ifndef CONFIG_SMP
 static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 {
@@ -645,4 +637,7 @@ int workqueue_online_cpu(unsigned int cpu);
 int workqueue_offline_cpu(unsigned int cpu);
 #endif
 
+int __init workqueue_init_early(void);
+int __init workqueue_init(void);
+
 #endif
diff --git a/init/main.c b/init/main.c
index fa201166cba7..23c275cca73a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -553,6 +553,14 @@ asmlinkage __visible void __init start_kernel(void)
                  "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 */
@@ -1009,6 +1017,8 @@ static noinline void __init kernel_init_freeable(void)
 
         smp_prepare_cpus(setup_max_cpus);
 
+        workqueue_init();
+
         do_pre_smp_initcalls();
         lockup_detector_init();
 
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 168ff442ebde..97b0df71303e 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -482,16 +482,7 @@ void pm_qos_update_request(struct pm_qos_request *req,
                 return;
         }
 
-        /*
-         * This function may be called very early during boot, for example,
-         * from of_clk_init(), where irq needs to stay disabled.
-         * cancel_delayed_work_sync() assumes that irq is enabled on
-         * invocation and re-enables it on return.  Avoid calling it until
-         * workqueue is initialized.
-         */
-        if (keventd_up())
-                cancel_delayed_work_sync(&req->work);
-
+        cancel_delayed_work_sync(&req->work);
         __pm_qos_update_request(req, new_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_update_request);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 479d840db286..1d9fb6543a66 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -290,6 +290,8 @@ module_param_named(disable_numa, wq_disable_numa, bool, 0444);
 static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
 module_param_named(power_efficient, wq_power_efficient, bool, 0444);
 
+static 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 */
@@ -2583,6 +2585,9 @@ void flush_workqueue(struct workqueue_struct *wq)
         };
         int next_color;
 
+        if (WARN_ON(!wq_online))
+                return;
+
         lock_map_acquire(&wq->lockdep_map);
         lock_map_release(&wq->lockdep_map);
 
@@ -2843,6 +2848,9 @@ 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);
 
@@ -2913,7 +2921,13 @@ static bool __cancel_work_timer(struct work_struct *work, bool is_dwork)
         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);
 
         /*
@@ -3364,7 +3378,7 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
                 goto fail;
 
         /* create and start the initial worker */
-        if (!create_worker(pool))
+        if (wq_online && !create_worker(pool))
                 goto fail;
 
         /* install */
@@ -3429,6 +3443,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
 {
         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);
@@ -3437,7 +3452,8 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
         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
@@ -3460,7 +3476,7 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
                 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 */
@@ -4033,6 +4049,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
                 for (i = 0; i < WORK_NR_COLORS; i++) {
                         if (WARN_ON(pwq->nr_in_flight[i])) {
                                 mutex_unlock(&wq->mutex);
+                                show_workqueue_state();
                                 return;
                         }
                 }
@@ -4041,6 +4058,7 @@ void destroy_workqueue(struct workqueue_struct *wq)
                     WARN_ON(pwq->nr_active) ||
                     WARN_ON(!list_empty(&pwq->delayed_works))) {
                         mutex_unlock(&wq->mutex);
+                        show_workqueue_state();
                         return;
                 }
         }
@@ -5467,7 +5485,17 @@ 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;
@@ -5479,8 +5507,6 @@ static int __init init_workqueues(void)
 
         pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
 
-        wq_numa_init();
-
         /* initialize CPU pools */
         for_each_possible_cpu(cpu) {
                 struct worker_pool *pool;
@@ -5500,16 +5526,6 @@ 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;
@@ -5546,8 +5562,59 @@ 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 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.
+         */
+        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);
+
+        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;
 }
-early_initcall(init_workqueues);
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 056052dc8e91..04c1ef717fe0 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -199,7 +199,7 @@ static void free_object(struct debug_obj *obj)
          * initialized:
          */
         if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache)
-                sched = keventd_up();
+                sched = 1;
         hlist_add_head(&obj->node, &obj_pool);
         obj_pool_free++;
         obj_pool_used--;
diff --git a/mm/slab.c b/mm/slab.c
index 87b29e76cafd..29bc6c0dedd0 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -552,12 +552,7 @@ static void start_cpu_timer(int cpu)
 {
         struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
 
-        /*
-         * When this gets called from do_initcalls via cpucache_init(),
-         * init_workqueues() has already run, so keventd will be setup
-         * at that time.
-         */
-        if (keventd_up() && reap_work->work.func == NULL) {
+        if (reap_work->work.func == NULL) {
                 init_reap_node(cpu);
                 INIT_DEFERRABLE_WORK(reap_work, cache_reap);
                 schedule_delayed_work_on(cpu, reap_work,