12 files changed, 76 insertions, 47 deletions

diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index 32814371b8d3..aa1b41ca40f7 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -1471,5 +1471,3 @@ module_exit(mq_exit);
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("mq cache policy");
-
-MODULE_ALIAS("dm-cache-default");
diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index 48a4a826ae07..200366c62231 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1789,3 +1789,5 @@ module_exit(smq_exit);
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("smq cache policy");
+
+MODULE_ALIAS("dm-cache-default");
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index 720ceeb7fa9b..80a439543259 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1919,9 +1919,7 @@ int __init dm_interface_init(void)
 
 void dm_interface_exit(void)
 {
-	if (misc_deregister(&_dm_misc) < 0)
-		DMERR("misc_deregister failed for control device");
-
+	misc_deregister(&_dm_misc);
 	dm_hash_exit();
 }
 
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 48dfe3c4d6aa..6ba47cfb1443 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1293,8 +1293,8 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd)
 		return r;
 
 	disk_super = dm_block_data(copy);
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root));
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root));
+	dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
+	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
 	dm_sm_dec_block(pmd->metadata_sm, held_root);
 
 	return dm_tm_unlock(pmd->tm, copy);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ab37ae114e94..0d7ab20c58df 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1729,7 +1729,8 @@ static int dm_merge_bvec(struct request_queue *q,
 	struct mapped_device *md = q->queuedata;
 	struct dm_table *map = dm_get_live_table_fast(md);
 	struct dm_target *ti;
-	sector_t max_sectors, max_size = 0;
+	sector_t max_sectors;
+	int max_size = 0;
 
 	if (unlikely(!map))
 		goto out;
@@ -1742,18 +1743,10 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * Find maximum amount of I/O that won't need splitting
 	 */
 	max_sectors = min(max_io_len(bvm->bi_sector, ti),
-			  (sector_t) queue_max_sectors(q));
+			  (sector_t) BIO_MAX_SECTORS);
 	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-
-	/*
-	 * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
-	 * to the targets' merge function since it holds sectors not bytes).
-	 * Just doing this as an interim fix for stable@ because the more
-	 * comprehensive cleanup of switching to sector_t will impact every
-	 * DM target that implements a ->merge hook.
-	 */
-	if (max_size > INT_MAX)
-		max_size = INT_MAX;
+	if (max_size < 0)
+		max_size = 0;
 
 	/*
 	 * merge_bvec_fn() returns number of bytes
@@ -1761,13 +1754,13 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * max is precomputed maximal io size
 	 */
 	if (max_size && ti->type->merge)
-		max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
+		max_size = ti->type->merge(ti, bvm, biovec, max_size);
 	/*
 	 * If the target doesn't support merge method and some of the devices
-	 * provided their merge_bvec method (we know this by looking for the
-	 * max_hw_sectors that dm_set_device_limits may set), then we can't
-	 * allow bios with multiple vector entries.  So always set max_size
-	 * to 0, and the code below allows just one page.
+	 * provided their merge_bvec method (we know this by looking at
+	 * queue_max_hw_sectors), then we can't allow bios with multiple vector
+	 * entries.  So always set max_size to 0, and the code below allows
+	 * just one page.
 	 */
 	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
 		max_size = 0;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0c2a4e8b873c..e25f00f0138a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5759,7 +5759,7 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
 	char *ptr;
 	int err;
 
-	file = kmalloc(sizeof(*file), GFP_NOIO);
+	file = kzalloc(sizeof(*file), GFP_NOIO);
 	if (!file)
 		return -ENOMEM;
 
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index bf2b80d5c470..8731b6ea026b 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -138,4 +138,10 @@ int lower_bound(struct btree_node *n, uint64_t key);
 
 extern struct dm_block_validator btree_node_validator;
 
+/*
+ * Value type for upper levels of multi-level btrees.
+ */
+extern void init_le64_type(struct dm_transaction_manager *tm,
+			   struct dm_btree_value_type *vt);
+
 #endif	/* DM_BTREE_INTERNAL_H */
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
index 9836c0ae897c..4222f774cf36 100644
--- a/drivers/md/persistent-data/dm-btree-remove.c
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -544,14 +544,6 @@ static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info,
 	return r;
 }
 
-static struct dm_btree_value_type le64_type = {
-	.context = NULL,
-	.size = sizeof(__le64),
-	.inc = NULL,
-	.dec = NULL,
-	.equal = NULL
-};
-
 int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
 		    uint64_t *keys, dm_block_t *new_root)
 {
@@ -559,12 +551,14 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
 	int index = 0, r = 0;
 	struct shadow_spine spine;
 	struct btree_node *n;
+	struct dm_btree_value_type le64_vt;
 
+	init_le64_type(info->tm, &le64_vt);
 	init_shadow_spine(&spine, info);
 	for (level = 0; level < info->levels; level++) {
 		r = remove_raw(&spine, info,
 			       (level == last_level ?
-				&info->value_type : &le64_type),
+				&info->value_type : &le64_vt),
 			       root, keys[level], (unsigned *)&index);
 		if (r < 0)
 			break;
@@ -654,11 +648,13 @@ static int remove_one(struct dm_btree_info *info, dm_block_t root,
 	int index = 0, r = 0;
 	struct shadow_spine spine;
 	struct btree_node *n;
+	struct dm_btree_value_type le64_vt;
 	uint64_t k;
 
+	init_le64_type(info->tm, &le64_vt);
 	init_shadow_spine(&spine, info);
 	for (level = 0; level < last_level; level++) {
-		r = remove_raw(&spine, info, &le64_type,
+		r = remove_raw(&spine, info, &le64_vt,
 			       root, keys[level], (unsigned *) &index);
 		if (r < 0)
 			goto out;
@@ -689,6 +685,7 @@ static int remove_one(struct dm_btree_info *info, dm_block_t root,
 					     value_ptr(n, index));
 
 		delete_at(n, index);
+		keys[last_level] = k + 1ull;
 
 	} else
 		r = -ENODATA;
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index 1b5e13ec7f96..0dee514ba4c5 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -249,3 +249,40 @@ int shadow_root(struct shadow_spine *s)
 {
 	return s->root;
 }
+
+static void le64_inc(void *context, const void *value_le)
+{
+	struct dm_transaction_manager *tm = context;
+	__le64 v_le;
+
+	memcpy(&v_le, value_le, sizeof(v_le));
+	dm_tm_inc(tm, le64_to_cpu(v_le));
+}
+
+static void le64_dec(void *context, const void *value_le)
+{
+	struct dm_transaction_manager *tm = context;
+	__le64 v_le;
+
+	memcpy(&v_le, value_le, sizeof(v_le));
+	dm_tm_dec(tm, le64_to_cpu(v_le));
+}
+
+static int le64_equal(void *context, const void *value1_le, const void *value2_le)
+{
+	__le64 v1_le, v2_le;
+
+	memcpy(&v1_le, value1_le, sizeof(v1_le));
+	memcpy(&v2_le, value2_le, sizeof(v2_le));
+	return v1_le == v2_le;
+}
+
+void init_le64_type(struct dm_transaction_manager *tm,
+		    struct dm_btree_value_type *vt)
+{
+	vt->context = tm;
+	vt->size = sizeof(__le64);
+	vt->inc = le64_inc;
+	vt->dec = le64_dec;
+	vt->equal = le64_equal;
+}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index fdd3793e22f9..c7726cebc495 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -667,12 +667,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root,
 	struct btree_node *n;
 	struct dm_btree_value_type le64_type;
 
-	le64_type.context = NULL;
-	le64_type.size = sizeof(__le64);
-	le64_type.inc = NULL;
-	le64_type.dec = NULL;
-	le64_type.equal = NULL;
-
+	init_le64_type(info->tm, &le64_type);
 	init_shadow_spine(&spine, info);
 
 	for (level = 0; level < (info->levels - 1); level++) {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 94f5b55069e0..967a4ed73929 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1476,6 +1476,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1495,14 +1496,13 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
 	 */
@@ -1568,7 +1568,10 @@ static int raid1_spare_active(struct mddev *mddev)
 	 * Find all failed disks within the RAID1 configuration
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
+	 * device_lock used to avoid races with raid1_end_read_request
+	 * which expects 'In_sync' flags and ->degraded to be consistent.
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1599,7 +1602,6 @@ static int raid1_spare_active(struct mddev *mddev)
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
-	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded -= count;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 643d217bfa13..f757023fc458 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2256,7 +2256,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 static int drop_one_stripe(struct r5conf *conf)
 {
 	struct stripe_head *sh;
-	int hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS;
+	int hash = (conf->max_nr_stripes - 1) & STRIPE_HASH_LOCKS_MASK;
 
 	spin_lock_irq(conf->hash_locks + hash);
 	sh = get_free_stripe(conf, hash);
@@ -6388,7 +6388,8 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink,
 
 	if (mutex_trylock(&conf->cache_size_mutex)) {
 		ret= 0;
-		while (ret < sc->nr_to_scan) {
+		while (ret < sc->nr_to_scan &&
+		       conf->max_nr_stripes > conf->min_nr_stripes) {
 			if (drop_one_stripe(conf) == 0) {
 				ret = SHRINK_STOP;
 				break;