workqueue: Changes for v6.17

- Prepare for defaulting to unbound workqueue. A separate branch was created
   to ease pulling in from other trees but none of the conversions have
   landed yet.
 
 - Memory allocation profiling support added.
 
 - Misc changes.
 -----BEGIN PGP SIGNATURE-----
 
 iIQEABYKACwWIQTfIjM1kS57o3GsC/uxYfJx3gVYGQUCaIqiqg4cdGpAa2VybmVs
 Lm9yZwAKCRCxYfJx3gVYGa5uAP90MhiDmUxrIXK9A80f0+S6ujIpGm6tYQAOHHsZ
 s6gH3gD+PIsupQ6wF107+Z71ZFtMC2vkrKuTSGE88x5r3aWq+gw=
 =j/gv
 -----END PGP SIGNATURE-----

Merge tag 'wq-for-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:

 - Prepare for defaulting to unbound workqueue. A separate branch was
   created to ease pulling in from other trees but none of the
   conversions have landed yet

 - Memory allocation profiling support added

 - Misc changes

* tag 'wq-for-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: Use atomic_try_cmpxchg_relaxed() in tryinc_node_nr_active()
  workqueue: Remove unused work_on_cpu_safe
  workqueue: Add new WQ_PERCPU flag
  workqueue: Add system_percpu_wq and system_dfl_wq
  workqueue: Basic memory allocation profiling support
  workqueue: fix opencoded cpumask_next_and_wrap() in wq_select_unbound_cpu()

Documentation/core-api/workqueue.rst

@@ -183,6 +183,12 @@ resources, scheduled and executed.
   BH work items cannot sleep. All other features such as delayed queueing,
   flushing and canceling are supported.
 
+``WQ_PERCPU``
+  Work items queued to a per-cpu wq are bound to a specific CPU.
+  This flag is the right choice when cpu locality is important.
+
+  This flag is the complement of ``WQ_UNBOUND``.
+
 ``WQ_UNBOUND``
   Work items queued to an unbound wq are served by the special
   worker-pools which host workers which are not bound to any

include/linux/workqueue.h

@@ -6,6 +6,7 @@
 #ifndef _LINUX_WORKQUEUE_H
 #define _LINUX_WORKQUEUE_H
 
+#include <linux/alloc_tag.h>
 #include <linux/timer.h>
 #include <linux/linkage.h>
 #include <linux/bitops.h>
@@ -401,6 +402,7 @@ enum wq_flags {
 	 * http://thread.gmane.org/gmane.linux.kernel/1480396
 	 */
 	WQ_POWER_EFFICIENT	= 1 << 7,
+	WQ_PERCPU		= 1 << 8, /* bound to a specific cpu */
 
 	__WQ_DESTROYING		= 1 << 15, /* internal: workqueue is destroying */
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
@@ -427,7 +429,7 @@ enum wq_consts {
 /*
  * System-wide workqueues which are always present.
  *
- * system_wq is the one used by schedule[_delayed]_work[_on]().
+ * system_percpu_wq is the one used by schedule[_delayed]_work[_on]().
  * Multi-CPU multi-threaded.  There are users which expect relatively
  * short queue flush time.  Don't queue works which can run for too
  * long.
@@ -438,7 +440,7 @@ enum wq_consts {
  * system_long_wq is similar to system_wq but may host long running
  * works.  Queue flushing might take relatively long.
  *
- * system_unbound_wq is unbound workqueue.  Workers are not bound to
+ * system_dfl_wq is unbound workqueue.  Workers are not bound to
  * any specific CPU, not concurrency managed, and all queued works are
  * executed immediately as long as max_active limit is not reached and
  * resources are available.
@@ -455,10 +457,12 @@ enum wq_consts {
  * system_bh[_highpri]_wq are convenience interface to softirq. BH work items
  * are executed in the queueing CPU's BH context in the queueing order.
  */
-extern struct workqueue_struct *system_wq;
+extern struct workqueue_struct *system_wq; /* use system_percpu_wq, this will be removed */
+extern struct workqueue_struct *system_percpu_wq;
 extern struct workqueue_struct *system_highpri_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_unbound_wq;
+extern struct workqueue_struct *system_dfl_wq;
 extern struct workqueue_struct *system_freezable_wq;
 extern struct workqueue_struct *system_power_efficient_wq;
 extern struct workqueue_struct *system_freezable_power_efficient_wq;
@@ -505,7 +509,8 @@ void workqueue_softirq_dead(unsigned int cpu);
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 __printf(1, 4) struct workqueue_struct *
-alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
+alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...);
+#define alloc_workqueue(...)	alloc_hooks(alloc_workqueue_noprof(__VA_ARGS__))
 
 #ifdef CONFIG_LOCKDEP
 /**
@@ -544,8 +549,8 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...)	\
-	alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags),	\
-				    1, lockdep_map, ##args)
+	alloc_hooks(alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags),\
+						1, lockdep_map, ##args))
 #endif
 
 /**
@@ -577,7 +582,9 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
-struct workqueue_attrs *alloc_workqueue_attrs(void);
+struct workqueue_attrs *alloc_workqueue_attrs_noprof(void);
+#define alloc_workqueue_attrs(...)	alloc_hooks(alloc_workqueue_attrs_noprof(__VA_ARGS__))
+
 void free_workqueue_attrs(struct workqueue_attrs *attrs);
 int apply_workqueue_attrs(struct workqueue_struct *wq,
 			  const struct workqueue_attrs *attrs);
@@ -840,19 +847,6 @@ long work_on_cpu_key(int cpu, long (*fn)(void *),
 	work_on_cpu_key(_cpu, _fn, _arg, &__key);	\
 })
 
-long work_on_cpu_safe_key(int cpu, long (*fn)(void *),
-			  void *arg, struct lock_class_key *key);
-
-/*
- * A new key is defined for each caller to make sure the work
- * associated with the function doesn't share its locking class.
- */
-#define work_on_cpu_safe(_cpu, _fn, _arg)		\
-({							\
-	static struct lock_class_key __key;		\
-							\
-	work_on_cpu_safe_key(_cpu, _fn, _arg, &__key);	\
-})
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FREEZER

kernel/workqueue.c

@@ -505,12 +505,16 @@ static struct kthread_worker *pwq_release_worker __ro_after_init;
 
 struct workqueue_struct *system_wq __ro_after_init;
 EXPORT_SYMBOL(system_wq);
+struct workqueue_struct *system_percpu_wq __ro_after_init;
+EXPORT_SYMBOL(system_percpu_wq);
 struct workqueue_struct *system_highpri_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_highpri_wq);
 struct workqueue_struct *system_long_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_long_wq);
 struct workqueue_struct *system_unbound_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_unbound_wq);
+struct workqueue_struct *system_dfl_wq __ro_after_init;
+EXPORT_SYMBOL_GPL(system_dfl_wq);
 struct workqueue_struct *system_freezable_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_freezable_wq);
 struct workqueue_struct *system_power_efficient_wq __ro_after_init;
@@ -1686,18 +1690,15 @@ static void __pwq_activate_work(struct pool_workqueue *pwq,
 static bool tryinc_node_nr_active(struct wq_node_nr_active *nna)
 {
 	int max = READ_ONCE(nna->max);
+	int old = atomic_read(&nna->nr);
 
-	while (true) {
-		int old, tmp;
-
-		old = atomic_read(&nna->nr);
+	do {
 		if (old >= max)
 			return false;
-		tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1);
-		if (tmp == old)
+	} while (!atomic_try_cmpxchg_relaxed(&nna->nr, &old, old + 1));
+
 	return true;
 }
-}
 
 /**
  * pwq_tryinc_nr_active - Try to increment nr_active for a pwq
@@ -2221,12 +2222,9 @@ static int wq_select_unbound_cpu(int cpu)
 	}
 
 	new_cpu = __this_cpu_read(wq_rr_cpu_last);
-	new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
-	if (unlikely(new_cpu >= nr_cpu_ids)) {
-		new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
+	new_cpu = cpumask_next_and_wrap(new_cpu, wq_unbound_cpumask, cpu_online_mask);
 	if (unlikely(new_cpu >= nr_cpu_ids))
 		return cpu;
-	}
 	__this_cpu_write(wq_rr_cpu_last, new_cpu);
 
 	return new_cpu;
@@ -4629,7 +4627,7 @@ void free_workqueue_attrs(struct workqueue_attrs *attrs)
  *
  * Return: The allocated new workqueue_attr on success. %NULL on failure.
  */
-struct workqueue_attrs *alloc_workqueue_attrs(void)
+struct workqueue_attrs *alloc_workqueue_attrs_noprof(void)
 {
 	struct workqueue_attrs *attrs;
 
@@ -5682,12 +5680,12 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 	else
 		wq_size = sizeof(*wq);
 
-	wq = kzalloc(wq_size, GFP_KERNEL);
+	wq = kzalloc_noprof(wq_size, GFP_KERNEL);
 	if (!wq)
 		return NULL;
 
 	if (flags & WQ_UNBOUND) {
-		wq->unbound_attrs = alloc_workqueue_attrs();
+		wq->unbound_attrs = alloc_workqueue_attrs_noprof();
 		if (!wq->unbound_attrs)
 			goto err_free_wq;
 	}
@@ -5777,7 +5775,7 @@ err_destroy:
 }
 
 __printf(1, 4)
-struct workqueue_struct *alloc_workqueue(const char *fmt,
+struct workqueue_struct *alloc_workqueue_noprof(const char *fmt,
 						unsigned int flags,
 						int max_active, ...)
 {
@@ -5794,7 +5792,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 
 	return wq;
 }
-EXPORT_SYMBOL_GPL(alloc_workqueue);
+EXPORT_SYMBOL_GPL(alloc_workqueue_noprof);
 
 #ifdef CONFIG_LOCKDEP
 __printf(1, 5)
@@ -6770,31 +6768,6 @@ long work_on_cpu_key(int cpu, long (*fn)(void *),
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu_key);
-
-/**
- * work_on_cpu_safe_key - run a function in thread context on a particular cpu
- * @cpu: the cpu to run on
- * @fn:  the function to run
- * @arg: the function argument
- * @key: The lock class key for lock debugging purposes
- *
- * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold
- * any locks which would prevent @fn from completing.
- *
- * Return: The value @fn returns.
- */
-long work_on_cpu_safe_key(int cpu, long (*fn)(void *),
-			  void *arg, struct lock_class_key *key)
-{
-	long ret = -ENODEV;
-
-	cpus_read_lock();
-	if (cpu_online(cpu))
-		ret = work_on_cpu_key(cpu, fn, arg, key);
-	cpus_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(work_on_cpu_safe_key);
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FREEZER
@@ -7830,10 +7803,11 @@ void __init workqueue_init_early(void)
 	}
 
 	system_wq = alloc_workqueue("events", 0, 0);
+	system_percpu_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_MAX_ACTIVE);
+	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
+	system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
 	system_freezable_wq = alloc_workqueue("events_freezable",
 					      WQ_FREEZABLE, 0);
 	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
@@ -7844,8 +7818,8 @@ void __init workqueue_init_early(void)
 	system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0);
 	system_bh_highpri_wq = alloc_workqueue("events_bh_highpri",
 					       WQ_BH | WQ_HIGHPRI, 0);
-	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
-	       !system_unbound_wq || !system_freezable_wq ||
+	BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq ||
+	       !system_unbound_wq || !system_freezable_wq || !system_dfl_wq ||
 	       !system_power_efficient_wq ||
 	       !system_freezable_power_efficient_wq ||
 	       !system_bh_wq || !system_bh_highpri_wq);