1 files changed, 131 insertions, 98 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 2cbd3dd5940d..4c3e6a44595f 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * async.c: Asynchronous function calls for boot performance
  *
  * (C) Copyright 2009 Intel Corporation
  * Author: Arjan van de Ven <arjan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 
 
@@ -50,11 +46,12 @@ asynchronous and synchronous parts of the kernel.
 
 #include <linux/async.h>
 #include <linux/atomic.h>
-#include <linux/ktime.h>
 #include <linux/export.h>
-#include <linux/wait.h>
+#include <linux/ktime.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/wait.h>
 #include <linux/workqueue.h>
 
 #include "workqueue_internal.h"
@@ -67,6 +64,7 @@ static async_cookie_t next_cookie = 1;
 static LIST_HEAD(async_global_pending);	/* pending from all registered doms */
 static ASYNC_DOMAIN(async_dfl_domain);
 static DEFINE_SPINLOCK(async_lock);
+static struct workqueue_struct *async_wq;
 
 struct async_entry {
 	struct list_head	domain_list;
@@ -82,22 +80,32 @@ static DECLARE_WAIT_QUEUE_HEAD(async_done);
 
 static atomic_t entry_count;
 
+static long long microseconds_since(ktime_t start)
+{
+	ktime_t now = ktime_get();
+	return ktime_to_ns(ktime_sub(now, start)) >> 10;
+}
+
 static async_cookie_t lowest_in_progress(struct async_domain *domain)
 {
-	struct list_head *pending;
+	struct async_entry *first = NULL;
 	async_cookie_t ret = ASYNC_COOKIE_MAX;
 	unsigned long flags;
 
 	spin_lock_irqsave(&async_lock, flags);
 
-	if (domain)
-		pending = &domain->pending;
-	else
-		pending = &async_global_pending;
+	if (domain) {
+		if (!list_empty(&domain->pending))
+			first = list_first_entry(&domain->pending,
+					struct async_entry, domain_list);
+	} else {
+		if (!list_empty(&async_global_pending))
+			first = list_first_entry(&async_global_pending,
+					struct async_entry, global_list);
+	}
 
-	if (!list_empty(pending))
-		ret = list_first_entry(pending, struct async_entry,
-				       domain_list)->cookie;
+	if (first)
+		ret = first->cookie;
 
 	spin_unlock_irqrestore(&async_lock, flags);
 	return ret;
@@ -111,24 +119,18 @@ static void async_run_entry_fn(struct work_struct *work)
 	struct async_entry *entry =
 		container_of(work, struct async_entry, work);
 	unsigned long flags;
-	ktime_t uninitialized_var(calltime), delta, rettime;
+	ktime_t calltime;
 
 	/* 1) run (and print duration) */
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		pr_debug("calling  %lli_%pF @ %i\n",
-			(long long)entry->cookie,
-			entry->func, task_pid_nr(current));
-		calltime = ktime_get();
-	}
+	pr_debug("calling  %lli_%pS @ %i\n", (long long)entry->cookie,
+		 entry->func, task_pid_nr(current));
+	calltime = ktime_get();
+
 	entry->func(entry->data, entry->cookie);
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		rettime = ktime_get();
-		delta = ktime_sub(rettime, calltime);
-		pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n",
-			(long long)entry->cookie,
-			entry->func,
-			(long long)ktime_to_ns(delta) >> 10);
-	}
+
+	pr_debug("initcall %lli_%pS returned after %lld usecs\n",
+		 (long long)entry->cookie, entry->func,
+		 microseconds_since(calltime));
 
 	/* 2) remove self from the pending queues */
 	spin_lock_irqsave(&async_lock, flags);
@@ -145,29 +147,14 @@ static void async_run_entry_fn(struct work_struct *work)
 	wake_up(&async_done);
 }
 
-static async_cookie_t __async_schedule(async_func_t func, void *data, struct async_domain *domain)
+static async_cookie_t __async_schedule_node_domain(async_func_t func,
+						   void *data, int node,
+						   struct async_domain *domain,
+						   struct async_entry *entry)
 {
-	struct async_entry *entry;
-	unsigned long flags;
 	async_cookie_t newcookie;
+	unsigned long flags;
 
-	/* allow irq-off callers */
-	entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC);
-
-	/*
-	 * If we're out of memory or if there's too much work
-	 * pending already, we execute synchronously.
-	 */
-	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
-		kfree(entry);
-		spin_lock_irqsave(&async_lock, flags);
-		newcookie = next_cookie++;
-		spin_unlock_irqrestore(&async_lock, flags);
-
-		/* low on memory.. run synchronously */
-		func(data, newcookie);
-		return newcookie;
-	}
 	INIT_LIST_HEAD(&entry->domain_list);
 	INIT_LIST_HEAD(&entry->global_list);
 	INIT_WORK(&entry->work, async_run_entry_fn);
@@ -187,76 +174,116 @@ static async_cookie_t __async_schedule(async_func_t func, void *data, struct asy
 	atomic_inc(&entry_count);
 	spin_unlock_irqrestore(&async_lock, flags);
 
-	/* mark that this task has queued an async job, used by module init */
-	current->flags |= PF_USED_ASYNC;
-
 	/* schedule for execution */
-	queue_work(system_unbound_wq, &entry->work);
+	queue_work_node(node, async_wq, &entry->work);
 
 	return newcookie;
 }
 
 /**
- * async_schedule - schedule a function for asynchronous execution
+ * async_schedule_node_domain - NUMA specific version of async_schedule_domain
  * @func: function to execute asynchronously
  * @data: data pointer to pass to the function
+ * @node: NUMA node that we want to schedule this on or close to
+ * @domain: the domain
  *
  * Returns an async_cookie_t that may be used for checkpointing later.
+ * @domain may be used in the async_synchronize_*_domain() functions to
+ * wait within a certain synchronization domain rather than globally.
+ *
  * Note: This function may be called from atomic or non-atomic contexts.
+ *
+ * The node requested will be honored on a best effort basis. If the node
+ * has no CPUs associated with it then the work is distributed among all
+ * available CPUs.
  */
-async_cookie_t async_schedule(async_func_t func, void *data)
+async_cookie_t async_schedule_node_domain(async_func_t func, void *data,
+					  int node, struct async_domain *domain)
 {
-	return __async_schedule(func, data, &async_dfl_domain);
+	struct async_entry *entry;
+	unsigned long flags;
+	async_cookie_t newcookie;
+
+	/* allow irq-off callers */
+	entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC);
+
+	/*
+	 * If we're out of memory or if there's too much work
+	 * pending already, we execute synchronously.
+	 */
+	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		spin_lock_irqsave(&async_lock, flags);
+		newcookie = next_cookie++;
+		spin_unlock_irqrestore(&async_lock, flags);
+
+		/* low on memory.. run synchronously */
+		func(data, newcookie);
+		return newcookie;
+	}
+
+	return __async_schedule_node_domain(func, data, node, domain, entry);
 }
-EXPORT_SYMBOL_GPL(async_schedule);
+EXPORT_SYMBOL_GPL(async_schedule_node_domain);
 
 /**
- * async_schedule_domain - schedule a function for asynchronous execution within a certain domain
+ * async_schedule_node - NUMA specific version of async_schedule
  * @func: function to execute asynchronously
  * @data: data pointer to pass to the function
- * @domain: the domain
+ * @node: NUMA node that we want to schedule this on or close to
  *
  * Returns an async_cookie_t that may be used for checkpointing later.
- * @domain may be used in the async_synchronize_*_domain() functions to
- * wait within a certain synchronization domain rather than globally.  A
- * synchronization domain is specified via @domain.  Note: This function
- * may be called from atomic or non-atomic contexts.
+ * Note: This function may be called from atomic or non-atomic contexts.
+ *
+ * The node requested will be honored on a best effort basis. If the node
+ * has no CPUs associated with it then the work is distributed among all
+ * available CPUs.
  */
-async_cookie_t async_schedule_domain(async_func_t func, void *data,
-				     struct async_domain *domain)
+async_cookie_t async_schedule_node(async_func_t func, void *data, int node)
 {
-	return __async_schedule(func, data, domain);
+	return async_schedule_node_domain(func, data, node, &async_dfl_domain);
 }
-EXPORT_SYMBOL_GPL(async_schedule_domain);
+EXPORT_SYMBOL_GPL(async_schedule_node);
 
 /**
- * async_synchronize_full - synchronize all asynchronous function calls
+ * async_schedule_dev_nocall - A simplified variant of async_schedule_dev()
+ * @func: function to execute asynchronously
+ * @dev: device argument to be passed to function
  *
- * This function waits until all asynchronous function calls have been done.
+ * @dev is used as both the argument for the function and to provide NUMA
+ * context for where to run the function.
+ *
+ * If the asynchronous execution of @func is scheduled successfully, return
+ * true. Otherwise, do nothing and return false, unlike async_schedule_dev()
+ * that will run the function synchronously then.
  */
-void async_synchronize_full(void)
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev)
 {
-	async_synchronize_full_domain(NULL);
+	struct async_entry *entry;
+
+	entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL);
+
+	/* Give up if there is no memory or too much work. */
+	if (!entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		return false;
+	}
+
+	__async_schedule_node_domain(func, dev, dev_to_node(dev),
+				     &async_dfl_domain, entry);
+	return true;
 }
-EXPORT_SYMBOL_GPL(async_synchronize_full);
 
 /**
- * async_unregister_domain - ensure no more anonymous waiters on this domain
- * @domain: idle domain to flush out of any async_synchronize_full instances
- *
- * async_synchronize_{cookie|full}_domain() are not flushed since callers
- * of these routines should know the lifetime of @domain
+ * async_synchronize_full - synchronize all asynchronous function calls
  *
- * Prefer ASYNC_DOMAIN_EXCLUSIVE() declarations over flushing
+ * This function waits until all asynchronous function calls have been done.
  */
-void async_unregister_domain(struct async_domain *domain)
+void async_synchronize_full(void)
 {
-	spin_lock_irq(&async_lock);
-	WARN_ON(!domain->registered || !list_empty(&domain->pending));
-	domain->registered = 0;
-	spin_unlock_irq(&async_lock);
+	async_synchronize_full_domain(NULL);
 }
-EXPORT_SYMBOL_GPL(async_unregister_domain);
+EXPORT_SYMBOL_GPL(async_synchronize_full);
 
 /**
  * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain
@@ -282,23 +309,15 @@ EXPORT_SYMBOL_GPL(async_synchronize_full_domain);
  */
 void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain)
 {
-	ktime_t uninitialized_var(starttime), delta, endtime;
+	ktime_t starttime;
 
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		pr_debug("async_waiting @ %i\n", task_pid_nr(current));
-		starttime = ktime_get();
-	}
+	pr_debug("async_waiting @ %i\n", task_pid_nr(current));
+	starttime = ktime_get();
 
 	wait_event(async_done, lowest_in_progress(domain) >= cookie);
 
-	if (initcall_debug && system_state < SYSTEM_RUNNING) {
-		endtime = ktime_get();
-		delta = ktime_sub(endtime, starttime);
-
-		pr_debug("async_continuing @ %i after %lli usec\n",
-			task_pid_nr(current),
-			(long long)ktime_to_ns(delta) >> 10);
-	}
+	pr_debug("async_continuing @ %i after %lli usec\n", task_pid_nr(current),
+		 microseconds_since(starttime));
 }
 EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain);
 
@@ -327,3 +346,17 @@ bool current_is_async(void)
 	return worker && worker->current_func == async_run_entry_fn;
 }
 EXPORT_SYMBOL_GPL(current_is_async);
+
+void __init async_init(void)
+{
+	/*
+	 * Async can schedule a number of interdependent work items. However,
+	 * unbound workqueues can handle only upto min_active interdependent
+	 * work items. The default min_active of 8 isn't sufficient for async
+	 * and can lead to stalls. Let's use a dedicated workqueue with raised
+	 * min_active.
+	 */
+	async_wq = alloc_workqueue("async", WQ_UNBOUND, 0);
+	BUG_ON(!async_wq);
+	workqueue_set_min_active(async_wq, WQ_DFL_ACTIVE);
+}