1 files changed, 152 insertions, 77 deletions

diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index f496213f8b67..4bb6553278c7 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2005-2007 Red Hat GmbH
  *
@@ -12,25 +13,32 @@
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
 
 #include <linux/device-mapper.h>
 
 #define DM_MSG_PREFIX "delay"
 
+#define SLEEP_SHIFT 3
+
 struct delay_class {
 	struct dm_dev *dev;
 	sector_t start;
-	unsigned delay;
-	unsigned ops;
+	unsigned int delay;
+	unsigned int ops;
 };
 
 struct delay_c {
 	struct timer_list delay_timer;
-	struct mutex timer_lock;
+	struct mutex process_bios_lock; /* hold while removing bios to be processed from list */
+	spinlock_t delayed_bios_lock; /* hold on all accesses to delayed_bios list */
 	struct workqueue_struct *kdelayd_wq;
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
-	atomic_t may_delay;
+	struct task_struct *worker;
+	unsigned int worker_sleep_us;
+	bool may_delay;
 
 	struct delay_class read;
 	struct delay_class write;
@@ -46,23 +54,21 @@ struct dm_delay_info {
 	unsigned long expires;
 };
 
-static DEFINE_MUTEX(delayed_bios_lock);
-
 static void handle_delayed_timer(struct timer_list *t)
 {
-	struct delay_c *dc = from_timer(dc, t, delay_timer);
+	struct delay_c *dc = timer_container_of(dc, t, delay_timer);
 
 	queue_work(dc->kdelayd_wq, &dc->flush_expired_bios);
 }
 
 static void queue_timeout(struct delay_c *dc, unsigned long expires)
 {
-	mutex_lock(&dc->timer_lock);
-
-	if (!timer_pending(&dc->delay_timer) || expires < dc->delay_timer.expires)
-		mod_timer(&dc->delay_timer, expires);
+	timer_reduce(&dc->delay_timer, expires);
+}
 
-	mutex_unlock(&dc->timer_lock);
+static inline bool delay_is_fast(struct delay_c *dc)
+{
+	return !!dc->worker;
 }
 
 static void flush_bios(struct bio *bio)
@@ -72,41 +78,74 @@ static void flush_bios(struct bio *bio)
 	while (bio) {
 		n = bio->bi_next;
 		bio->bi_next = NULL;
-		generic_make_request(bio);
+		dm_submit_bio_remap(bio, NULL);
 		bio = n;
 	}
 }
 
-static struct bio *flush_delayed_bios(struct delay_c *dc, int flush_all)
+static void flush_delayed_bios(struct delay_c *dc, bool flush_all)
 {
 	struct dm_delay_info *delayed, *next;
+	struct bio_list flush_bio_list;
+	LIST_HEAD(local_list);
 	unsigned long next_expires = 0;
-	unsigned long start_timer = 0;
-	struct bio_list flush_bios = { };
-
-	mutex_lock(&delayed_bios_lock);
-	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+	bool start_timer = false;
+	bio_list_init(&flush_bio_list);
+
+	mutex_lock(&dc->process_bios_lock);
+	spin_lock(&dc->delayed_bios_lock);
+	list_replace_init(&dc->delayed_bios, &local_list);
+	spin_unlock(&dc->delayed_bios_lock);
+	list_for_each_entry_safe(delayed, next, &local_list, list) {
+		cond_resched();
 		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
 			struct bio *bio = dm_bio_from_per_bio_data(delayed,
 						sizeof(struct dm_delay_info));
 			list_del(&delayed->list);
-			bio_list_add(&flush_bios, bio);
+			bio_list_add(&flush_bio_list, bio);
 			delayed->class->ops--;
 			continue;
 		}
 
-		if (!start_timer) {
-			start_timer = 1;
-			next_expires = delayed->expires;
-		} else
-			next_expires = min(next_expires, delayed->expires);
+		if (!delay_is_fast(dc)) {
+			if (!start_timer) {
+				start_timer = true;
+				next_expires = delayed->expires;
+			} else {
+				next_expires = min(next_expires, delayed->expires);
+			}
+		}
 	}
-	mutex_unlock(&delayed_bios_lock);
+	spin_lock(&dc->delayed_bios_lock);
+	list_splice(&local_list, &dc->delayed_bios);
+	spin_unlock(&dc->delayed_bios_lock);
+	mutex_unlock(&dc->process_bios_lock);
 
 	if (start_timer)
 		queue_timeout(dc, next_expires);
 
-	return bio_list_get(&flush_bios);
+	flush_bios(bio_list_get(&flush_bio_list));
+}
+
+static int flush_worker_fn(void *data)
+{
+	struct delay_c *dc = data;
+
+	while (!kthread_should_stop()) {
+		flush_delayed_bios(dc, false);
+		spin_lock(&dc->delayed_bios_lock);
+		if (unlikely(list_empty(&dc->delayed_bios))) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			spin_unlock(&dc->delayed_bios_lock);
+			schedule();
+		} else {
+			spin_unlock(&dc->delayed_bios_lock);
+			fsleep(dc->worker_sleep_us);
+			cond_resched();
+		}
+	}
+
+	return 0;
 }
 
 static void flush_expired_bios(struct work_struct *work)
@@ -114,15 +153,17 @@ static void flush_expired_bios(struct work_struct *work)
 	struct delay_c *dc;
 
 	dc = container_of(work, struct delay_c, flush_expired_bios);
-	flush_bios(flush_delayed_bios(dc, 0));
+	flush_delayed_bios(dc, false);
 }
 
 static void delay_dtr(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	if (dc->kdelayd_wq)
+	if (dc->kdelayd_wq) {
+		timer_shutdown_sync(&dc->delay_timer);
 		destroy_workqueue(dc->kdelayd_wq);
+	}
 
 	if (dc->read.dev)
 		dm_put_device(ti, dc->read.dev);
@@ -130,8 +171,10 @@ static void delay_dtr(struct dm_target *ti)
 		dm_put_device(ti, dc->write.dev);
 	if (dc->flush.dev)
 		dm_put_device(ti, dc->flush.dev);
+	if (dc->worker)
+		kthread_stop(dc->worker);
 
-	mutex_destroy(&dc->timer_lock);
+	mutex_destroy(&dc->process_bios_lock);
 
 	kfree(dc);
 }
@@ -174,6 +217,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct delay_c *dc;
 	int ret;
+	unsigned int max_delay, min_delay;
 
 	if (argc != 3 && argc != 6 && argc != 9) {
 		ti->error = "Requires exactly 3, 6 or 9 arguments";
@@ -187,16 +231,16 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ti->private = dc;
-	timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
-	INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
 	INIT_LIST_HEAD(&dc->delayed_bios);
-	mutex_init(&dc->timer_lock);
-	atomic_set(&dc->may_delay, 1);
+	mutex_init(&dc->process_bios_lock);
+	spin_lock_init(&dc->delayed_bios_lock);
+	dc->may_delay = true;
 	dc->argc = argc;
 
 	ret = delay_class_ctr(ti, &dc->read, argv);
 	if (ret)
 		goto bad;
+	min_delay = max_delay = dc->read.delay;
 
 	if (argc == 3) {
 		ret = delay_class_ctr(ti, &dc->write, argv);
@@ -211,6 +255,9 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ret = delay_class_ctr(ti, &dc->write, argv + 3);
 	if (ret)
 		goto bad;
+	max_delay = max(max_delay, dc->write.delay);
+	min_delay = min_not_zero(min_delay, dc->write.delay);
+
 	if (argc == 6) {
 		ret = delay_class_ctr(ti, &dc->flush, argv + 3);
 		if (ret)
@@ -221,17 +268,39 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	ret = delay_class_ctr(ti, &dc->flush, argv + 6);
 	if (ret)
 		goto bad;
+	max_delay = max(max_delay, dc->flush.delay);
+	min_delay = min_not_zero(min_delay, dc->flush.delay);
 
 out:
-	dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
-	if (!dc->kdelayd_wq) {
-		ret = -EINVAL;
-		DMERR("Couldn't start kdelayd");
-		goto bad;
+	if (max_delay < 50) {
+		if (min_delay >> SLEEP_SHIFT)
+			dc->worker_sleep_us = 1000;
+		else
+			dc->worker_sleep_us = (min_delay * 1000) >> SLEEP_SHIFT;
+		/*
+		 * In case of small requested delays, use kthread instead of
+		 * timers and workqueue to achieve better latency.
+		 */
+		dc->worker = kthread_run(&flush_worker_fn, dc, "dm-delay-flush-worker");
+		if (IS_ERR(dc->worker)) {
+			ret = PTR_ERR(dc->worker);
+			dc->worker = NULL;
+			goto bad;
+		}
+	} else {
+		timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
+		INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
+		dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
+		if (!dc->kdelayd_wq) {
+			ret = -EINVAL;
+			DMERR("Couldn't start kdelayd");
+			goto bad;
+		}
 	}
 
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
+	ti->accounts_remapped_io = true;
 	ti->per_io_data_size = sizeof(struct dm_delay_info);
 	return 0;
 
@@ -245,7 +314,7 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	struct dm_delay_info *delayed;
 	unsigned long expires = 0;
 
-	if (!c->delay || !atomic_read(&dc->may_delay))
+	if (!c->delay)
 		return DM_MAPIO_REMAPPED;
 
 	delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info));
@@ -253,12 +322,19 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	delayed->context = dc;
 	delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay);
 
-	mutex_lock(&delayed_bios_lock);
+	spin_lock(&dc->delayed_bios_lock);
+	if (unlikely(!dc->may_delay)) {
+		spin_unlock(&dc->delayed_bios_lock);
+		return DM_MAPIO_REMAPPED;
+	}
 	c->ops++;
 	list_add_tail(&delayed->list, &dc->delayed_bios);
-	mutex_unlock(&delayed_bios_lock);
+	spin_unlock(&dc->delayed_bios_lock);
 
-	queue_timeout(dc, expires);
+	if (delay_is_fast(dc))
+		wake_up_process(dc->worker);
+	else
+		queue_timeout(dc, expires);
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -267,16 +343,20 @@ static void delay_presuspend(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 0);
-	del_timer_sync(&dc->delay_timer);
-	flush_bios(flush_delayed_bios(dc, 1));
+	spin_lock(&dc->delayed_bios_lock);
+	dc->may_delay = false;
+	spin_unlock(&dc->delayed_bios_lock);
+
+	if (!delay_is_fast(dc))
+		timer_delete(&dc->delay_timer);
+	flush_delayed_bios(dc, true);
 }
 
 static void delay_resume(struct dm_target *ti)
 {
 	struct delay_c *dc = ti->private;
 
-	atomic_set(&dc->may_delay, 1);
+	dc->may_delay = true;
 }
 
 static int delay_map(struct dm_target *ti, struct bio *bio)
@@ -295,17 +375,31 @@ static int delay_map(struct dm_target *ti, struct bio *bio)
 	}
 	delayed->class = c;
 	bio_set_dev(bio, c->dev->bdev);
-	if (bio_sectors(bio))
-		bio->bi_iter.bi_sector = c->start + dm_target_offset(ti, bio->bi_iter.bi_sector);
+	bio->bi_iter.bi_sector = c->start + dm_target_offset(ti, bio->bi_iter.bi_sector);
 
 	return delay_bio(dc, c, bio);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int delay_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
+{
+	struct delay_c *dc = ti->private;
+	struct delay_class *c = &dc->read;
+
+	return dm_report_zones(c->dev->bdev, c->start,
+			c->start + dm_target_offset(ti, args->next_sector),
+			args, nr_zones);
+}
+#else
+#define delay_report_zones	NULL
+#endif
+
 #define DMEMIT_DELAY_CLASS(c) \
 	DMEMIT("%s %llu %u", (c)->dev->name, (unsigned long long)(c)->start, (c)->delay)
 
 static void delay_status(struct dm_target *ti, status_type_t type,
-			 unsigned status_flags, char *result, unsigned maxlen)
+			 unsigned int status_flags, char *result, unsigned int maxlen)
 {
 	struct delay_c *dc = ti->private;
 	int sz = 0;
@@ -326,6 +420,10 @@ static void delay_status(struct dm_target *ti, status_type_t type,
 			DMEMIT_DELAY_CLASS(&dc->flush);
 		}
 		break;
+
+	case STATUSTYPE_IMA:
+		*result = '\0';
+		break;
 	}
 }
 
@@ -351,42 +449,19 @@ out:
 
 static struct target_type delay_target = {
 	.name	     = "delay",
-	.version     = {1, 2, 1},
-	.features    = DM_TARGET_PASSES_INTEGRITY,
+	.version     = {1, 5, 0},
+	.features    = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
 	.module      = THIS_MODULE,
 	.ctr	     = delay_ctr,
 	.dtr	     = delay_dtr,
 	.map	     = delay_map,
+	.report_zones = delay_report_zones,
 	.presuspend  = delay_presuspend,
 	.resume	     = delay_resume,
 	.status	     = delay_status,
 	.iterate_devices = delay_iterate_devices,
 };
-
-static int __init dm_delay_init(void)
-{
-	int r;
-
-	r = dm_register_target(&delay_target);
-	if (r < 0) {
-		DMERR("register failed %d", r);
-		goto bad_register;
-	}
-
-	return 0;
-
-bad_register:
-	return r;
-}
-
-static void __exit dm_delay_exit(void)
-{
-	dm_unregister_target(&delay_target);
-}
-
-/* Module hooks */
-module_init(dm_delay_init);
-module_exit(dm_delay_exit);
+module_dm(delay);
 
 MODULE_DESCRIPTION(DM_NAME " delay target");
 MODULE_AUTHOR("Heinz Mauelshagen <mauelshagen@redhat.com>");