1 files changed, 99 insertions, 45 deletions

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 6daf777105fb..5248bca5e2ed 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -527,12 +527,29 @@ static void prio_io(struct cache *ca, uint64_t bucket, int op,
 	closure_sync(cl);
 }
 
-void bch_prio_write(struct cache *ca)
+int bch_prio_write(struct cache *ca, bool wait)
 {
 	int i;
 	struct bucket *b;
 	struct closure cl;
 
+	pr_debug("free_prio=%zu, free_none=%zu, free_inc=%zu",
+		 fifo_used(&ca->free[RESERVE_PRIO]),
+		 fifo_used(&ca->free[RESERVE_NONE]),
+		 fifo_used(&ca->free_inc));
+
+	/*
+	 * Pre-check if there are enough free buckets. In the non-blocking
+	 * scenario it's better to fail early rather than starting to allocate
+	 * buckets and do a cleanup later in case of failure.
+	 */
+	if (!wait) {
+		size_t avail = fifo_used(&ca->free[RESERVE_PRIO]) +
+			       fifo_used(&ca->free[RESERVE_NONE]);
+		if (prio_buckets(ca) > avail)
+			return -ENOMEM;
+	}
+
 	closure_init_stack(&cl);
 
 	lockdep_assert_held(&ca->set->bucket_lock);
@@ -542,9 +559,6 @@ void bch_prio_write(struct cache *ca)
 	atomic_long_add(ca->sb.bucket_size * prio_buckets(ca),
 			&ca->meta_sectors_written);
 
-	//pr_debug("free %zu, free_inc %zu, unused %zu", fifo_used(&ca->free),
-	//	 fifo_used(&ca->free_inc), fifo_used(&ca->unused));
-
 	for (i = prio_buckets(ca) - 1; i >= 0; --i) {
 		long bucket;
 		struct prio_set *p = ca->disk_buckets;
@@ -562,7 +576,7 @@ void bch_prio_write(struct cache *ca)
 		p->magic	= pset_magic(&ca->sb);
 		p->csum		= bch_crc64(&p->magic, bucket_bytes(ca) - 8);
 
-		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, true);
+		bucket = bch_bucket_alloc(ca, RESERVE_PRIO, wait);
 		BUG_ON(bucket == -1);
 
 		mutex_unlock(&ca->set->bucket_lock);
@@ -591,6 +605,7 @@ void bch_prio_write(struct cache *ca)
 
 		ca->prio_last_buckets[i] = ca->prio_buckets[i];
 	}
+	return 0;
 }
 
 static void prio_read(struct cache *ca, uint64_t bucket)
@@ -754,20 +769,31 @@ static inline int idx_to_first_minor(int idx)
 
 static void bcache_device_free(struct bcache_device *d)
 {
+	struct gendisk *disk = d->disk;
+
 	lockdep_assert_held(&bch_register_lock);
 
-	pr_info("%s stopped", d->disk->disk_name);
+	if (disk)
+		pr_info("%s stopped", disk->disk_name);
+	else
+		pr_err("bcache device (NULL gendisk) stopped");
 
 	if (d->c)
 		bcache_device_detach(d);
-	if (d->disk && d->disk->flags & GENHD_FL_UP)
-		del_gendisk(d->disk);
-	if (d->disk && d->disk->queue)
-		blk_cleanup_queue(d->disk->queue);
-	if (d->disk) {
+
+	if (disk) {
+		bool disk_added = (disk->flags & GENHD_FL_UP) != 0;
+
+		if (disk_added)
+			del_gendisk(disk);
+
+		if (disk->queue)
+			blk_cleanup_queue(disk->queue);
+
 		ida_simple_remove(&bcache_device_idx,
-				  first_minor_to_idx(d->disk->first_minor));
-		put_disk(d->disk);
+				  first_minor_to_idx(disk->first_minor));
+		if (disk_added)
+			put_disk(disk);
 	}
 
 	bioset_exit(&d->bio_split);
@@ -1209,6 +1235,9 @@ static void cached_dev_free(struct closure *cl)
 
 	mutex_unlock(&bch_register_lock);
 
+	if (dc->sb_bio.bi_inline_vecs[0].bv_page)
+		put_page(bio_first_page_all(&dc->sb_bio));
+
 	if (!IS_ERR_OR_NULL(dc->bdev))
 		blkdev_put(dc->bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
 
@@ -1674,7 +1703,7 @@ void bch_cache_set_unregister(struct cache_set *c)
 }
 
 #define alloc_bucket_pages(gfp, c)			\
-	((void *) __get_free_pages(__GFP_ZERO|gfp, ilog2(bucket_pages(c))))
+	((void *) __get_free_pages(__GFP_ZERO|__GFP_COMP|gfp, ilog2(bucket_pages(c))))
 
 struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 {
@@ -1886,7 +1915,7 @@ static int run_cache_set(struct cache_set *c)
 
 		mutex_lock(&c->bucket_lock);
 		for_each_cache(ca, c, i)
-			bch_prio_write(ca);
+			bch_prio_write(ca, true);
 		mutex_unlock(&c->bucket_lock);
 
 		err = "cannot allocate new UUID bucket";
@@ -1994,7 +2023,14 @@ found:
 	    sysfs_create_link(&c->kobj, &ca->kobj, buf))
 		goto err;
 
-	if (ca->sb.seq > c->sb.seq) {
+	/*
+	 * A special case is both ca->sb.seq and c->sb.seq are 0,
+	 * such condition happens on a new created cache device whose
+	 * super block is never flushed yet. In this case c->sb.version
+	 * and other members should be updated too, otherwise we will
+	 * have a mistaken super block version in cache set.
+	 */
+	if (ca->sb.seq > c->sb.seq || c->sb.seq == 0) {
 		c->sb.version		= ca->sb.version;
 		memcpy(c->sb.set_uuid, ca->sb.set_uuid, 16);
 		c->sb.flags             = ca->sb.flags;
@@ -2274,29 +2310,35 @@ static bool bch_is_open(struct block_device *bdev)
 static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			       const char *buffer, size_t size)
 {
-	ssize_t ret = -EINVAL;
-	const char *err = "cannot allocate memory";
+	const char *err;
 	char *path = NULL;
-	struct cache_sb *sb = NULL;
+	struct cache_sb *sb;
 	struct block_device *bdev = NULL;
-	struct page *sb_page = NULL;
+	struct page *sb_page;
+	ssize_t ret;
 
+	ret = -EBUSY;
+	err = "failed to reference bcache module";
 	if (!try_module_get(THIS_MODULE))
-		return -EBUSY;
+		goto out;
 
 	/* For latest state of bcache_is_reboot */
 	smp_mb();
+	err = "bcache is in reboot";
 	if (bcache_is_reboot)
-		return -EBUSY;
+		goto out_module_put;
 
+	ret = -ENOMEM;
+	err = "cannot allocate memory";
 	path = kstrndup(buffer, size, GFP_KERNEL);
 	if (!path)
-		goto err;
+		goto out_module_put;
 
 	sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL);
 	if (!sb)
-		goto err;
+		goto out_free_path;
 
+	ret = -EINVAL;
 	err = "failed to open device";
 	bdev = blkdev_get_by_path(strim(path),
 				  FMODE_READ|FMODE_WRITE|FMODE_EXCL,
@@ -2313,57 +2355,69 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 			if (!IS_ERR(bdev))
 				bdput(bdev);
 			if (attr == &ksysfs_register_quiet)
-				goto quiet_out;
+				goto done;
 		}
-		goto err;
+		goto out_free_sb;
 	}
 
 	err = "failed to set blocksize";
 	if (set_blocksize(bdev, 4096))
-		goto err_close;
+		goto out_blkdev_put;
 
 	err = read_super(sb, bdev, &sb_page);
 	if (err)
-		goto err_close;
+		goto out_blkdev_put;
 
 	err = "failed to register device";
 	if (SB_IS_BDEV(sb)) {
 		struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
 
 		if (!dc)
-			goto err_close;
+			goto out_put_sb_page;
 
 		mutex_lock(&bch_register_lock);
 		ret = register_bdev(sb, sb_page, bdev, dc);
 		mutex_unlock(&bch_register_lock);
 		/* blkdev_put() will be called in cached_dev_free() */
-		if (ret < 0)
-			goto err;
+		if (ret < 0) {
+			bdev = NULL;
+			goto out_put_sb_page;
+		}
 	} else {
 		struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
 
 		if (!ca)
-			goto err_close;
+			goto out_put_sb_page;
 
 		/* blkdev_put() will be called in bch_cache_release() */
-		if (register_cache(sb, sb_page, bdev, ca) != 0)
-			goto err;
+		if (register_cache(sb, sb_page, bdev, ca) != 0) {
+			bdev = NULL;
+			goto out_put_sb_page;
+		}
 	}
-quiet_out:
-	ret = size;
-out:
-	if (sb_page)
-		put_page(sb_page);
+
+	put_page(sb_page);
+done:
+	kfree(sb);
+	kfree(path);
+	module_put(THIS_MODULE);
+	return size;
+
+out_put_sb_page:
+	put_page(sb_page);
+out_blkdev_put:
+	if (bdev)
+		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+out_free_sb:
 	kfree(sb);
+out_free_path:
 	kfree(path);
+	path = NULL;
+out_module_put:
 	module_put(THIS_MODULE);
+out:
+	pr_info("error %s: %s", path?path:"", err);
 	return ret;
-
-err_close:
-	blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
-err:
-	pr_info("error %s: %s", path, err);
-	goto out;
 }
 
 static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)