workqueue: make workqueue available early during boot

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@kernel.org>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/CA+55aFx0vPuMuxn00rBSM192n-Du5uxy+4AvKa0SBSOVJeuCGg@mail.gmail.com

3 files changed, 76 insertions, 17 deletions

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 26cc1df280d6..91d416f9c0a7 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -358,6 +358,8 @@ extern struct workqueue_struct *system_freezable_wq;
 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);
@@ -594,7 +596,7 @@ static inline bool schedule_delayed_work(struct delayed_work *dwork,
  */
 static inline bool keventd_up(void)
 {
-        return system_wq != NULL;
+        return wq_online;
 }
 
 #ifndef CONFIG_SMP
@@ -631,4 +633,7 @@ 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 a8a58e2794a5..5c4fd68a8671 100644
--- a/init/main.c
+++ b/init/main.c
@@ -551,6 +551,14 @@ 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 */
@@ -1005,6 +1013,8 @@ 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/workqueue.c b/kernel/workqueue.c
index 4eaec8b86d65..15d0811c9e91 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);
 
+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);
 
         /*
@@ -3352,7 +3366,7 @@ 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 */
@@ -3417,6 +3431,7 @@ 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);
@@ -3425,7 +3440,8 @@ 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
@@ -3448,7 +3464,7 @@ 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 */
@@ -5457,7 +5473,17 @@ 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;
@@ -5490,16 +5516,6 @@ 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;
@@ -5536,8 +5552,36 @@ 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);