1 files changed, 80 insertions, 43 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e7abfdd77c3b..c17d4517af22 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -168,14 +168,14 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 {
 	const char *err;
 	struct cache_sb_disk *s;
-	struct page *page;
+	struct folio *folio;
 	unsigned int i;
 
-	page = read_cache_page_gfp(bdev->bd_mapping,
-				   SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
-	if (IS_ERR(page))
+	folio = mapping_read_folio_gfp(bdev->bd_mapping,
+			SB_OFFSET >> PAGE_SHIFT, GFP_KERNEL);
+	if (IS_ERR(folio))
 		return "IO error";
-	s = page_address(page) + offset_in_page(SB_OFFSET);
+	s = folio_address(folio) + offset_in_folio(folio, SB_OFFSET);
 
 	sb->offset		= le64_to_cpu(s->offset);
 	sb->version		= le64_to_cpu(s->version);
@@ -272,7 +272,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 	*res = s;
 	return NULL;
 err:
-	put_page(page);
+	folio_put(folio);
 	return err;
 }
 
@@ -293,8 +293,7 @@ static void __write_super(struct cache_sb *sb, struct cache_sb_disk *out,
 
 	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_META;
 	bio->bi_iter.bi_sector	= SB_SECTOR;
-	__bio_add_page(bio, virt_to_page(out), SB_SIZE,
-			offset_in_page(out));
+	bio_add_virt_nofail(bio, out, SB_SIZE);
 
 	out->offset		= cpu_to_le64(sb->offset);
 
@@ -546,7 +545,8 @@ static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
 
 static struct uuid_entry *uuid_find_empty(struct cache_set *c)
 {
-	static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
+	static const char zero_uuid[16] __nonstring =
+		{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
 
 	return uuid_find(c, zero_uuid);
 }
@@ -1366,7 +1366,7 @@ static CLOSURE_CALLBACK(cached_dev_free)
 	mutex_unlock(&bch_register_lock);
 
 	if (dc->sb_disk)
-		put_page(virt_to_page(dc->sb_disk));
+		folio_put(virt_to_folio(dc->sb_disk));
 
 	if (dc->bdev_file)
 		fput(dc->bdev_file);
@@ -1388,7 +1388,7 @@ static CLOSURE_CALLBACK(cached_dev_flush)
 	bch_cache_accounting_destroy(&dc->accounting);
 	kobject_del(&d->kobj);
 
-	continue_at(cl, cached_dev_free, system_wq);
+	continue_at(cl, cached_dev_free, system_percpu_wq);
 }
 
 static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
@@ -1400,7 +1400,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
 	__module_get(THIS_MODULE);
 	INIT_LIST_HEAD(&dc->list);
 	closure_init(&dc->disk.cl, NULL);
-	set_closure_fn(&dc->disk.cl, cached_dev_flush, system_wq);
+	set_closure_fn(&dc->disk.cl, cached_dev_flush, system_percpu_wq);
 	kobject_init(&dc->disk.kobj, &bch_cached_dev_ktype);
 	INIT_WORK(&dc->detach, cached_dev_detach_finish);
 	sema_init(&dc->sb_write_mutex, 1);
@@ -1513,7 +1513,7 @@ static CLOSURE_CALLBACK(flash_dev_flush)
 	bcache_device_unlink(d);
 	mutex_unlock(&bch_register_lock);
 	kobject_del(&d->kobj);
-	continue_at(cl, flash_dev_free, system_wq);
+	continue_at(cl, flash_dev_free, system_percpu_wq);
 }
 
 static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
@@ -1525,7 +1525,7 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
 		goto err_ret;
 
 	closure_init(&d->cl, NULL);
-	set_closure_fn(&d->cl, flash_dev_flush, system_wq);
+	set_closure_fn(&d->cl, flash_dev_flush, system_percpu_wq);
 
 	kobject_init(&d->kobj, &bch_flash_dev_ktype);
 
@@ -1718,7 +1718,7 @@ static CLOSURE_CALLBACK(cache_set_flush)
 	if (!IS_ERR_OR_NULL(c->gc_thread))
 		kthread_stop(c->gc_thread);
 
-	if (!IS_ERR(c->root))
+	if (!IS_ERR_OR_NULL(c->root))
 		list_add(&c->root->list, &c->btree_cache);
 
 	/*
@@ -1733,7 +1733,12 @@ static CLOSURE_CALLBACK(cache_set_flush)
 			mutex_unlock(&b->write_lock);
 		}
 
-	if (ca->alloc_thread)
+	/*
+	 * If the register_cache_set() call to bch_cache_set_alloc() failed,
+	 * ca has not been assigned a value and return error.
+	 * So we need check ca is not NULL during bch_cache_set_unregister().
+	 */
+	if (ca && ca->alloc_thread)
 		kthread_stop(ca->alloc_thread);
 
 	if (c->journal.cur) {
@@ -1828,7 +1833,7 @@ static CLOSURE_CALLBACK(__cache_set_unregister)
 
 	mutex_unlock(&bch_register_lock);
 
-	continue_at(cl, cache_set_flush, system_wq);
+	continue_at(cl, cache_set_flush, system_percpu_wq);
 }
 
 void bch_cache_set_stop(struct cache_set *c)
@@ -1858,10 +1863,10 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 
 	__module_get(THIS_MODULE);
 	closure_init(&c->cl, NULL);
-	set_closure_fn(&c->cl, cache_set_free, system_wq);
+	set_closure_fn(&c->cl, cache_set_free, system_percpu_wq);
 
 	closure_init(&c->caching, &c->cl);
-	set_closure_fn(&c->caching, __cache_set_unregister, system_wq);
+	set_closure_fn(&c->caching, __cache_set_unregister, system_percpu_wq);
 
 	/* Maybe create continue_at_noreturn() and use it here? */
 	closure_set_stopped(&c->cl);
@@ -1907,7 +1912,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
+	iter_size = sizeof(struct btree_iter) +
+		    ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
 			    sizeof(struct btree_iter_set);
 
 	c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);
@@ -1933,7 +1939,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	if (!c->uuids)
 		goto err;
 
-	c->moving_gc_wq = alloc_workqueue("bcache_gc", WQ_MEM_RECLAIM, 0);
+	c->moving_gc_wq = alloc_workqueue("bcache_gc",
+					  WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!c->moving_gc_wq)
 		goto err;
 
@@ -2210,7 +2217,7 @@ void bch_cache_release(struct kobject *kobj)
 		free_fifo(&ca->free[i]);
 
 	if (ca->sb_disk)
-		put_page(virt_to_page(ca->sb_disk));
+		folio_put(virt_to_folio(ca->sb_disk));
 
 	if (ca->bdev_file)
 		fput(ca->bdev_file);
@@ -2230,18 +2237,50 @@ static int cache_alloc(struct cache *ca)
 	__module_get(THIS_MODULE);
 	kobject_init(&ca->kobj, &bch_cache_ktype);
 
-	bio_init(&ca->journal.bio, NULL, ca->journal.bio.bi_inline_vecs, 8, 0);
+	bio_init_inline(&ca->journal.bio, NULL, 8, 0);
 
 	/*
-	 * when ca->sb.njournal_buckets is not zero, journal exists,
-	 * and in bch_journal_replay(), tree node may split,
-	 * so bucket of RESERVE_BTREE type is needed,
-	 * the worst situation is all journal buckets are valid journal,
-	 * and all the keys need to replay,
-	 * so the number of  RESERVE_BTREE type buckets should be as much
-	 * as journal buckets
+	 * When the cache disk is first registered, ca->sb.njournal_buckets
+	 * is zero, and it is assigned in run_cache_set().
+	 *
+	 * When ca->sb.njournal_buckets is not zero, journal exists,
+	 * and in bch_journal_replay(), tree node may split.
+	 * The worst situation is all journal buckets are valid journal,
+	 * and all the keys need to replay, so the number of RESERVE_BTREE
+	 * type buckets should be as much as journal buckets.
+	 *
+	 * If the number of RESERVE_BTREE type buckets is too few, the
+	 * bch_allocator_thread() may hang up and unable to allocate
+	 * bucket. The situation is roughly as follows:
+	 *
+	 * 1. In bch_data_insert_keys(), if the operation is not op->replace,
+	 *    it will call the bch_journal(), which increments the journal_ref
+	 *    counter. This counter is only decremented after bch_btree_insert
+	 *    completes.
+	 *
+	 * 2. When calling bch_btree_insert, if the btree needs to split,
+	 *    it will call btree_split() and btree_check_reserve() to check
+	 *    whether there are enough reserved buckets in the RESERVE_BTREE
+	 *    slot. If not enough, bcache_btree_root() will repeatedly retry.
+	 *
+	 * 3. Normally, the bch_allocator_thread is responsible for filling
+	 *    the reservation slots from the free_inc bucket list. When the
+	 *    free_inc bucket list is exhausted, the bch_allocator_thread
+	 *    will call invalidate_buckets() until free_inc is refilled.
+	 *    Then bch_allocator_thread calls bch_prio_write() once. and
+	 *    bch_prio_write() will call bch_journal_meta() and waits for
+	 *    the journal write to complete.
+	 *
+	 * 4. During journal_write, journal_write_unlocked() is be called.
+	 *    If journal full occurs, journal_reclaim() and btree_flush_write()
+	 *    will be called sequentially, then retry journal_write.
+	 *
+	 * 5. When 2 and 4 occur together, IO will hung up and cannot recover.
+	 *
+	 * Therefore, reserve more RESERVE_BTREE type buckets.
 	 */
-	btree_buckets = ca->sb.njournal_buckets ?: 8;
+	btree_buckets = clamp_t(size_t, ca->sb.nbuckets >> 7,
+				32, SB_JOURNAL_BUCKETS);
 	free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
 	if (!free) {
 		ret = -EPERM;
@@ -2344,9 +2383,6 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
 	ca->bdev = file_bdev(bdev_file);
 	ca->sb_disk = sb_disk;
 
-	if (bdev_max_discard_sectors(file_bdev(bdev_file)))
-		ca->discard = CACHE_DISCARD(&ca->sb);
-
 	ret = cache_alloc(ca);
 	if (ret != 0) {
 		if (ret == -ENOMEM)
@@ -2493,7 +2529,7 @@ static void register_device_async(struct async_reg_args *args)
 		INIT_DELAYED_WORK(&args->reg_work, register_cache_worker);
 
 	/* 10 jiffies is enough for a delay */
-	queue_delayed_work(system_wq, &args->reg_work, 10);
+	queue_delayed_work(system_percpu_wq, &args->reg_work, 10);
 }
 
 static void *alloc_holder_object(struct cache_sb *sb)
@@ -2555,7 +2591,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (!holder) {
 		ret = -ENOMEM;
 		err = "cannot allocate memory";
-		goto out_put_sb_page;
+		goto out_put_sb_folio;
 	}
 
 	/* Now reopen in exclusive mode with proper holder */
@@ -2629,8 +2665,8 @@ async_done:
 
 out_free_holder:
 	kfree(holder);
-out_put_sb_page:
-	put_page(virt_to_page(sb_disk));
+out_put_sb_folio:
+	folio_put(virt_to_folio(sb_disk));
 out_blkdev_put:
 	if (bdev_file)
 		fput(bdev_file);
@@ -2867,24 +2903,25 @@ static int __init bcache_init(void)
 	if (bch_btree_init())
 		goto err;
 
-	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!bcache_wq)
 		goto err;
 
 	/*
 	 * Let's not make this `WQ_MEM_RECLAIM` for the following reasons:
 	 *
-	 * 1. It used `system_wq` before which also does no memory reclaim.
+	 * 1. It used `system_percpu_wq` before which also does no memory reclaim.
 	 * 2. With `WQ_MEM_RECLAIM` desktop stalls, increased boot times, and
 	 *    reduced throughput can be observed.
 	 *
-	 * We still want to user our own queue to not congest the `system_wq`.
+	 * We still want to user our own queue to not congest the `system_percpu_wq`.
 	 */
-	bch_flush_wq = alloc_workqueue("bch_flush", 0, 0);
+	bch_flush_wq = alloc_workqueue("bch_flush", WQ_PERCPU, 0);
 	if (!bch_flush_wq)
 		goto err;
 
-	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
+	bch_journal_wq = alloc_workqueue("bch_journal",
+					 WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!bch_journal_wq)
 		goto err;