Merge v6.3.3linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

47 files changed, 752 insertions, 499 deletions

diff --git a/fs/afs/afs.h b/fs/afs/afs.h
index 432cb4b23961..81815724db6c 100644
--- a/fs/afs/afs.h
+++ b/fs/afs/afs.h
@@ -19,8 +19,8 @@
 #define AFSPATHMAX		1024	/* Maximum length of a pathname plus NUL */
 #define AFSOPAQUEMAX		1024	/* Maximum length of an opaque field */
 
-#define AFS_VL_MAX_LIFESPAN	(120 * HZ)
-#define AFS_PROBE_MAX_LIFESPAN	(30 * HZ)
+#define AFS_VL_MAX_LIFESPAN	120
+#define AFS_PROBE_MAX_LIFESPAN	30
 
 typedef u64			afs_volid_t;
 typedef u64			afs_vnodeid_t;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index ad8523d0d038..68ae91d21b57 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -128,7 +128,7 @@ struct afs_call {
 	spinlock_t		state_lock;
 	int			error;		/* error code */
 	u32			abort_code;	/* Remote abort ID or 0 */
-	unsigned int		max_lifespan;	/* Maximum lifespan to set if not 0 */
+	unsigned int		max_lifespan;	/* Maximum lifespan in secs to set if not 0 */
 	unsigned		request_size;	/* size of request data */
 	unsigned		reply_max;	/* maximum size of reply */
 	unsigned		count2;		/* count used in unmarshalling */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 7817e2b860e5..6862e3dde364 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -334,7 +334,9 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	/* create a call */
 	rxcall = rxrpc_kernel_begin_call(call->net->socket, srx, call->key,
 					 (unsigned long)call,
-					 tx_total_len, gfp,
+					 tx_total_len,
+					 call->max_lifespan,
+					 gfp,
 					 (call->async ?
 					  afs_wake_up_async_call :
 					  afs_wake_up_call_waiter),
@@ -349,10 +351,6 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	}
 
 	call->rxcall = rxcall;
-
-	if (call->max_lifespan)
-		rxrpc_kernel_set_max_life(call->net->socket, rxcall,
-					  call->max_lifespan);
 	call->issue_time = ktime_get_real();
 
 	/* send the request */
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index e54f0884802a..79336fa853db 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -45,7 +45,8 @@ static int check_extent_in_eb(struct btrfs_backref_walk_ctx *ctx,
 	int root_count;
 	bool cached;
 
-	if (!btrfs_file_extent_compression(eb, fi) &&
+	if (!ctx->ignore_extent_item_pos &&
+	    !btrfs_file_extent_compression(eb, fi) &&
 	    !btrfs_file_extent_encryption(eb, fi) &&
 	    !btrfs_file_extent_other_encoding(eb, fi)) {
 		u64 data_offset;
@@ -552,7 +553,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx,
 				count++;
 			else
 				goto next;
-			if (!ctx->ignore_extent_item_pos) {
+			if (!ctx->skip_inode_ref_list) {
 				ret = check_extent_in_eb(ctx, &key, eb, fi, &eie);
 				if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP ||
 				    ret < 0)
@@ -564,7 +565,7 @@ static int add_all_parents(struct btrfs_backref_walk_ctx *ctx,
 						  eie, (void **)&old, GFP_NOFS);
 			if (ret < 0)
 				break;
-			if (!ret && !ctx->ignore_extent_item_pos) {
+			if (!ret && !ctx->skip_inode_ref_list) {
 				while (old->next)
 					old = old->next;
 				old->next = eie;
@@ -1606,7 +1607,7 @@ again:
 				goto out;
 		}
 		if (ref->count && ref->parent) {
-			if (!ctx->ignore_extent_item_pos && !ref->inode_list &&
+			if (!ctx->skip_inode_ref_list && !ref->inode_list &&
 			    ref->level == 0) {
 				struct btrfs_tree_parent_check check = { 0 };
 				struct extent_buffer *eb;
@@ -1647,7 +1648,7 @@ again:
 						  (void **)&eie, GFP_NOFS);
 			if (ret < 0)
 				goto out;
-			if (!ret && !ctx->ignore_extent_item_pos) {
+			if (!ret && !ctx->skip_inode_ref_list) {
 				/*
 				 * We've recorded that parent, so we must extend
 				 * its inode list here.
@@ -1743,7 +1744,7 @@ int btrfs_find_all_leafs(struct btrfs_backref_walk_ctx *ctx)
 static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx)
 {
 	const u64 orig_bytenr = ctx->bytenr;
-	const bool orig_ignore_extent_item_pos = ctx->ignore_extent_item_pos;
+	const bool orig_skip_inode_ref_list = ctx->skip_inode_ref_list;
 	bool roots_ulist_allocated = false;
 	struct ulist_iterator uiter;
 	int ret = 0;
@@ -1764,7 +1765,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx)
 		roots_ulist_allocated = true;
 	}
 
-	ctx->ignore_extent_item_pos = true;
+	ctx->skip_inode_ref_list = true;
 
 	ULIST_ITER_INIT(&uiter);
 	while (1) {
@@ -1789,7 +1790,7 @@ static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx)
 	ulist_free(ctx->refs);
 	ctx->refs = NULL;
 	ctx->bytenr = orig_bytenr;
-	ctx->ignore_extent_item_pos = orig_ignore_extent_item_pos;
+	ctx->skip_inode_ref_list = orig_skip_inode_ref_list;
 
 	return ret;
 }
@@ -1912,7 +1913,7 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 		goto out_trans;
 	}
 
-	walk_ctx.ignore_extent_item_pos = true;
+	walk_ctx.skip_inode_ref_list = true;
 	walk_ctx.trans = trans;
 	walk_ctx.fs_info = fs_info;
 	walk_ctx.refs = &ctx->refs;
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index ef6bbea3f456..1616e3e3f1e4 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -60,6 +60,12 @@ struct btrfs_backref_walk_ctx {
 	 * @extent_item_pos is ignored.
 	 */
 	bool ignore_extent_item_pos;
+	/*
+	 * If true and bytenr corresponds to a data extent, then the inode list
+	 * (each member describing inode number, file offset and root) is not
+	 * added to each reference added to the @refs ulist.
+	 */
+	bool skip_inode_ref_list;
 	/* A valid transaction handle or NULL. */
 	struct btrfs_trans_handle *trans;
 	/*
diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c
index 5367a14d44d2..4bb4a4875872 100644
--- a/fs/btrfs/block-rsv.c
+++ b/fs/btrfs/block-rsv.c
@@ -124,7 +124,8 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 	} else {
 		num_bytes = 0;
 	}
-	if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
+	if (qgroup_to_release_ret &&
+	    block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
 		qgroup_to_release = block_rsv->qgroup_rsv_reserved -
 				    block_rsv->qgroup_rsv_size;
 		block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index a5b6bb54545f..26bb10b6ca85 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -4489,10 +4489,12 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
 {
 	struct btrfs_key key;
+	struct btrfs_key orig_key;
 	struct btrfs_disk_key found_key;
 	int ret;
 
 	btrfs_item_key_to_cpu(path->nodes[0], &key, 0);
+	orig_key = key;
 
 	if (key.offset > 0) {
 		key.offset--;
@@ -4509,8 +4511,36 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
 
 	btrfs_release_path(path);
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
+	if (ret <= 0)
 		return ret;
+
+	/*
+	 * Previous key not found. Even if we were at slot 0 of the leaf we had
+	 * before releasing the path and calling btrfs_search_slot(), we now may
+	 * be in a slot pointing to the same original key - this can happen if
+	 * after we released the path, one of more items were moved from a
+	 * sibling leaf into the front of the leaf we had due to an insertion
+	 * (see push_leaf_right()).
+	 * If we hit this case and our slot is > 0 and just decrement the slot
+	 * so that the caller does not process the same key again, which may or
+	 * may not break the caller, depending on its logic.
+	 */
+	if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
+		btrfs_item_key(path->nodes[0], &found_key, path->slots[0]);
+		ret = comp_keys(&found_key, &orig_key);
+		if (ret == 0) {
+			if (path->slots[0] > 0) {
+				path->slots[0]--;
+				return 0;
+			}
+			/*
+			 * At slot 0, same key as before, it means orig_key is
+			 * the lowest, leftmost, key in the tree. We're done.
+			 */
+			return 1;
+		}
+	}
+
 	btrfs_item_key(path->nodes[0], &found_key, 0);
 	ret = comp_keys(&found_key, &key);
 	/*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9e1596bb208d..9892dae178b7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3123,23 +3123,34 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 {
 	int ret;
 	const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE);
-	bool clear_free_space_tree = false;
+	bool rebuild_free_space_tree = false;
 
 	if (btrfs_test_opt(fs_info, CLEAR_CACHE) &&
 	    btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
-		clear_free_space_tree = true;
+		rebuild_free_space_tree = true;
 	} else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
 		   !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) {
 		btrfs_warn(fs_info, "free space tree is invalid");
-		clear_free_space_tree = true;
+		rebuild_free_space_tree = true;
 	}
 
-	if (clear_free_space_tree) {
-		btrfs_info(fs_info, "clearing free space tree");
-		ret = btrfs_clear_free_space_tree(fs_info);
+	if (rebuild_free_space_tree) {
+		btrfs_info(fs_info, "rebuilding free space tree");
+		ret = btrfs_rebuild_free_space_tree(fs_info);
 		if (ret) {
 			btrfs_warn(fs_info,
-				   "failed to clear free space tree: %d", ret);
+				   "failed to rebuild free space tree: %d", ret);
+			goto out;
+		}
+	}
+
+	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+	    !btrfs_test_opt(fs_info, FREE_SPACE_TREE)) {
+		btrfs_info(fs_info, "disabling free space tree");
+		ret = btrfs_delete_free_space_tree(fs_info);
+		if (ret) {
+			btrfs_warn(fs_info,
+				   "failed to disable free space tree: %d", ret);
 			goto out;
 		}
 	}
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 41c77a100853..a4584c629ba3 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -52,13 +52,13 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz
 	u64 start, end, i_size;
 	int ret;
 
+	spin_lock(&inode->lock);
 	i_size = new_i_size ?: i_size_read(&inode->vfs_inode);
 	if (btrfs_fs_incompat(fs_info, NO_HOLES)) {
 		inode->disk_i_size = i_size;
-		return;
+		goto out_unlock;
 	}
 
-	spin_lock(&inode->lock);
 	ret = find_contiguous_extent_bit(&inode->file_extent_tree, 0, &start,
 					 &end, EXTENT_DIRTY);
 	if (!ret && start == 0)
@@ -66,6 +66,7 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz
 	else
 		i_size = 0;
 	inode->disk_i_size = i_size;
+out_unlock:
 	spin_unlock(&inode->lock);
 }
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d84cef89cdff..cf98a3c05480 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -870,15 +870,16 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 			}
 			spin_lock(&ctl->tree_lock);
 			ret = link_free_space(ctl, e);
-			ctl->total_bitmaps++;
-			recalculate_thresholds(ctl);
-			spin_unlock(&ctl->tree_lock);
 			if (ret) {
+				spin_unlock(&ctl->tree_lock);
 				btrfs_err(fs_info,
 					"Duplicate entries in free space cache, dumping");
 				kmem_cache_free(btrfs_free_space_cachep, e);
 				goto free_cache;
 			}
+			ctl->total_bitmaps++;
+			recalculate_thresholds(ctl);
+			spin_unlock(&ctl->tree_lock);
 			list_add_tail(&e->list, &bitmaps);
 		}
 
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 4d155a48ec59..b21da1446f2a 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1252,7 +1252,7 @@ out:
 	return ret;
 }
 
-int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
+int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *tree_root = fs_info->tree_root;
@@ -1298,6 +1298,54 @@ abort:
 	return ret;
 }
 
+int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_key key = {
+		.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID,
+		.type = BTRFS_ROOT_ITEM_KEY,
+		.offset = 0,
+	};
+	struct btrfs_root *free_space_root = btrfs_global_root(fs_info, &key);
+	struct rb_node *node;
+	int ret;
+
+	trans = btrfs_start_transaction(free_space_root, 1);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+	set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
+
+	ret = clear_free_space_tree(trans, free_space_root);
+	if (ret)
+		goto abort;
+
+	node = rb_first_cached(&fs_info->block_group_cache_tree);
+	while (node) {
+		struct btrfs_block_group *block_group;
+
+		block_group = rb_entry(node, struct btrfs_block_group,
+				       cache_node);
+		ret = populate_free_space_tree(trans, block_group);
+		if (ret)
+			goto abort;
+		node = rb_next(node);
+	}
+
+	btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE);
+	btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
+	clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+
+	ret = btrfs_commit_transaction(trans);
+	clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
+	return ret;
+abort:
+	btrfs_abort_transaction(trans, ret);
+	btrfs_end_transaction(trans);
+	return ret;
+}
+
 static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
 					struct btrfs_block_group *block_group,
 					struct btrfs_path *path)
diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h
index dc2463e4cfe3..6d5551d0ced8 100644
--- a/fs/btrfs/free-space-tree.h
+++ b/fs/btrfs/free-space-tree.h
@@ -18,7 +18,8 @@ struct btrfs_caching_control;
 
 void set_free_space_tree_thresholds(struct btrfs_block_group *block_group);
 int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info);
-int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info);
+int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info);
+int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info);
 int load_free_space_tree(struct btrfs_caching_control *caching_ctl);
 int add_block_group_free_space(struct btrfs_trans_handle *trans,
 			       struct btrfs_block_group *block_group);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 957e4d76a7b6..b31bb3352477 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3167,6 +3167,9 @@ int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		btrfs_rewrite_logical_zoned(ordered_extent);
 		btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr,
 					ordered_extent->disk_num_bytes);
+	} else if (btrfs_is_data_reloc_root(inode->root)) {
+		btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr,
+					ordered_extent->disk_num_bytes);
 	}
 
 	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 25833b4eeaf5..2fa36f694daa 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -454,7 +454,9 @@ void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
 	case BTRFS_EXCLOP_BALANCE_PAUSED:
 		spin_lock(&fs_info->super_lock);
 		ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE ||
-		       fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD);
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD ||
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_NONE ||
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED);
 		fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED;
 		spin_unlock(&fs_info->super_lock);
 		break;
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index b93c96213304..497b9dbd8a13 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -151,10 +151,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 			pr_cont("shared data backref parent %llu count %u\n",
 			       offset, btrfs_shared_data_ref_count(eb, sref));
 			/*
-			 * offset is supposed to be a tree block which
-			 * must be aligned to nodesize.
+			 * Offset is supposed to be a tree block which must be
+			 * aligned to sectorsize.
 			 */
-			if (!IS_ALIGNED(offset, eb->fs_info->nodesize))
+			if (!IS_ALIGNED(offset, eb->fs_info->sectorsize))
 				pr_info(
 			"\t\t\t(parent %llu not aligned to sectorsize %u)\n",
 				     offset, eb->fs_info->sectorsize);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ef13a9d4e370..c10670915f96 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3422,7 +3422,7 @@ int add_data_references(struct reloc_control *rc,
 	btrfs_release_path(path);
 
 	ctx.bytenr = extent_key->objectid;
-	ctx.ignore_extent_item_pos = true;
+	ctx.skip_inode_ref_list = true;
 	ctx.fs_info = rc->extent_root->fs_info;
 
 	ret = btrfs_find_all_leafs(&ctx);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 366fb4cde145..e19792d919c6 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -826,7 +826,11 @@ out:
 	    !btrfs_test_opt(info, CLEAR_CACHE)) {
 		btrfs_err(info, "cannot disable free space tree");
 		ret = -EINVAL;
-
+	}
+	if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE) &&
+	     !btrfs_test_opt(info, FREE_SPACE_TREE)) {
+		btrfs_err(info, "cannot disable free space tree with block-group-tree feature");
+		ret = -EINVAL;
 	}
 	if (!ret)
 		ret = btrfs_check_mountopts_zoned(info);
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 45d04092f2f8..8db47f93007f 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -122,10 +122,9 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
 		int i;
 
 		for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
-			u64 bytenr;
-
-			bytenr = ((zones[i].start + zones[i].len)
-				   << SECTOR_SHIFT) - BTRFS_SUPER_INFO_SIZE;
+			u64 zone_end = (zones[i].start + zones[i].capacity) << SECTOR_SHIFT;
+			u64 bytenr = ALIGN_DOWN(zone_end, BTRFS_SUPER_INFO_SIZE) -
+						BTRFS_SUPER_INFO_SIZE;
 
 			page[i] = read_cache_page_gfp(mapping,
 					bytenr >> PAGE_SHIFT, GFP_NOFS);
@@ -1168,12 +1167,12 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
 		return -ERANGE;
 
 	/* All the zones are conventional */
-	if (find_next_bit(zinfo->seq_zones, begin, end) == end)
+	if (find_next_bit(zinfo->seq_zones, end, begin) == end)
 		return 0;
 
 	/* All the zones are sequential and empty */
-	if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end &&
-	    find_next_zero_bit(zinfo->empty_zones, begin, end) == end)
+	if (find_next_zero_bit(zinfo->seq_zones, end, begin) == end &&
+	    find_next_zero_bit(zinfo->empty_zones, end, begin) == end)
 		return 0;
 
 	for (pos = start; pos < start + size; pos += zinfo->zone_size) {
@@ -1610,11 +1609,11 @@ void btrfs_redirty_list_add(struct btrfs_transaction *trans,
 	    !list_empty(&eb->release_list))
 		return;
 
+	memzero_extent_buffer(eb, 0, eb->len);
+	set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
 	set_extent_buffer_dirty(eb);
 	set_extent_bits_nowait(&trans->dirty_pages, eb->start,
 			       eb->start + eb->len - 1, EXTENT_DIRTY);
-	memzero_extent_buffer(eb, 0, eb->len);
-	set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
 
 	spin_lock(&trans->releasing_ebs_lock);
 	list_add_tail(&eb->release_list, &trans->releasing_ebs);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index ac9034fce409..b30f8f768ac4 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -744,6 +744,7 @@ static void cifs_umount_begin(struct super_block *sb)
 	spin_unlock(&tcon->tc_lock);
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	cifs_close_all_deferred_files(tcon);
 	/* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */
 	/* cancel_notify_requests(tcon); */
 	if (tcon->ses && tcon->ses->server) {
@@ -759,6 +760,20 @@ static void cifs_umount_begin(struct super_block *sb)
 	return;
 }
 
+static int cifs_freeze(struct super_block *sb)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+	struct cifs_tcon *tcon;
+
+	if (cifs_sb == NULL)
+		return 0;
+
+	tcon = cifs_sb_master_tcon(cifs_sb);
+
+	cifs_close_all_deferred_files(tcon);
+	return 0;
+}
+
 #ifdef CONFIG_CIFS_STATS2
 static int cifs_show_stats(struct seq_file *s, struct dentry *root)
 {
@@ -797,6 +812,7 @@ static const struct super_operations cifs_super_ops = {
 	as opens */
 	.show_options = cifs_show_options,
 	.umount_begin   = cifs_umount_begin,
+	.freeze_fs      = cifs_freeze,
 #ifdef CONFIG_CIFS_STATS2
 	.show_stats = cifs_show_stats,
 #endif
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2c573062ec87..59a10330e299 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2705,6 +2705,13 @@ cifs_match_super(struct super_block *sb, void *data)
 
 	spin_lock(&cifs_tcp_ses_lock);
 	cifs_sb = CIFS_SB(sb);
+
+	/* We do not want to use a superblock that has been shutdown */
+	if (CIFS_MOUNT_SHUTDOWN & cifs_sb->mnt_cifs_flags) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return 0;
+	}
+
 	tlink = cifs_get_tlink(cifs_sb_master_tlink(cifs_sb));
 	if (tlink == NULL) {
 		/* can not match superblock if tlink were ever null */
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index a81758225fcd..a295e4c2d54e 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1682,7 +1682,7 @@ smb2_copychunk_range(const unsigned int xid,
 		pcchunk->SourceOffset = cpu_to_le64(src_off);
 		pcchunk->TargetOffset = cpu_to_le64(dest_off);
 		pcchunk->Length =
-			cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk));
+			cpu_to_le32(min_t(u64, len, tcon->max_bytes_chunk));
 
 		/* Request server copy to target from src identified by key */
 		kfree(retbuf);
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 8ff4b9192a9f..f2c415f31b75 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -303,6 +303,22 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
 	return desc;
 }
 
+static ext4_fsblk_t ext4_valid_block_bitmap_padding(struct super_block *sb,
+						    ext4_group_t block_group,
+						    struct buffer_head *bh)
+{
+	ext4_grpblk_t next_zero_bit;
+	unsigned long bitmap_size = sb->s_blocksize * 8;
+	unsigned int offset = num_clusters_in_group(sb, block_group);
+
+	if (bitmap_size <= offset)
+		return 0;
+
+	next_zero_bit = ext4_find_next_zero_bit(bh->b_data, bitmap_size, offset);
+
+	return (next_zero_bit < bitmap_size ? next_zero_bit : 0);
+}
+
 /*
  * Return the block number which was discovered to be invalid, or 0 if
  * the block bitmap is valid.
@@ -401,6 +417,15 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		return -EFSCORRUPTED;
 	}
+	blk = ext4_valid_block_bitmap_padding(sb, block_group, bh);
+	if (unlikely(blk != 0)) {
+		ext4_unlock_group(sb, block_group);
+		ext4_error(sb, "bg %u: block %llu: padding at end of block bitmap is not set",
+			   block_group, blk);
+		ext4_mark_group_bitmap_corrupted(sb, block_group,
+						 EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+		return -EFSCORRUPTED;
+	}
 	set_buffer_verified(bh);
 verified:
 	ext4_unlock_group(sb, block_group);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 08b29c289da4..df0255b7d1fa 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1774,6 +1774,30 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
 	return container_of(inode, struct ext4_inode_info, vfs_inode);
 }
 
+static inline int ext4_writepages_down_read(struct super_block *sb)
+{
+	percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);
+	return memalloc_nofs_save();
+}
+
+static inline void ext4_writepages_up_read(struct super_block *sb, int ctx)
+{
+	memalloc_nofs_restore(ctx);
+	percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);
+}
+
+static inline int ext4_writepages_down_write(struct super_block *sb)
+{
+	percpu_down_write(&EXT4_SB(sb)->s_writepages_rwsem);
+	return memalloc_nofs_save();
+}
+
+static inline void ext4_writepages_up_write(struct super_block *sb, int ctx)
+{
+	memalloc_nofs_restore(ctx);
+	percpu_up_write(&EXT4_SB(sb)->s_writepages_rwsem);
+}
+
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 7bc221038c6c..595abb9e7d74 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -267,14 +267,12 @@ static void __es_find_extent_range(struct inode *inode,
 
 	/* see if the extent has been cached */
 	es->es_lblk = es->es_len = es->es_pblk = 0;
-	if (tree->cache_es) {
-		es1 = tree->cache_es;
-		if (in_range(lblk, es1->es_lblk, es1->es_len)) {
-			es_debug("%u cached by [%u/%u) %llu %x\n",
-				 lblk, es1->es_lblk, es1->es_len,
-				 ext4_es_pblock(es1), ext4_es_status(es1));
-			goto out;
-		}
+	es1 = READ_ONCE(tree->cache_es);
+	if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) {
+		es_debug("%u cached by [%u/%u) %llu %x\n",
+			 lblk, es1->es_lblk, es1->es_len,
+			 ext4_es_pblock(es1), ext4_es_status(es1));
+		goto out;
 	}
 
 	es1 = __es_tree_search(&tree->root, lblk);
@@ -293,7 +291,7 @@ out:
 	}
 
 	if (es1 && matching_fn(es1)) {
-		tree->cache_es = es1;
+		WRITE_ONCE(tree->cache_es, es1);
 		es->es_lblk = es1->es_lblk;
 		es->es_len = es1->es_len;
 		es->es_pblk = es1->es_pblk;
@@ -931,14 +929,12 @@ int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
 
 	/* find extent in cache firstly */
 	es->es_lblk = es->es_len = es->es_pblk = 0;
-	if (tree->cache_es) {
-		es1 = tree->cache_es;
-		if (in_range(lblk, es1->es_lblk, es1->es_len)) {
-			es_debug("%u cached by [%u/%u)\n",
-				 lblk, es1->es_lblk, es1->es_len);
-			found = 1;
-			goto out;
-		}
+	es1 = READ_ONCE(tree->cache_es);
+	if (es1 && in_range(lblk, es1->es_lblk, es1->es_len)) {
+		es_debug("%u cached by [%u/%u)\n",
+			 lblk, es1->es_lblk, es1->es_len);
+		found = 1;
+		goto out;
 	}
 
 	node = tree->root.rb_node;
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 147b5241dd94..46c3423ddfa1 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -277,7 +277,11 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
 	}
 	default:
 		hinfo->hash = 0;
-		return -1;
+		hinfo->minor_hash = 0;
+		ext4_warning(dir->i_sb,
+			     "invalid/unsupported hash tree version %u",
+			     hinfo->hash_version);
+		return -EINVAL;
 	}
 	hash = hash & ~1;
 	if (hash == (EXT4_HTREE_EOF_32BIT << 1))
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 1602d74b5eeb..cb36037f20fc 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -34,6 +34,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
 	struct ext4_xattr_ibody_header *header;
 	struct ext4_xattr_entry *entry;
 	struct ext4_inode *raw_inode;
+	void *end;
 	int free, min_offs;
 
 	if (!EXT4_INODE_HAS_XATTR_SPACE(inode))
@@ -57,14 +58,23 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
 	raw_inode = ext4_raw_inode(iloc);
 	header = IHDR(inode, raw_inode);
 	entry = IFIRST(header);
+	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
 
 	/* Compute min_offs. */
-	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
+	while (!IS_LAST_ENTRY(entry)) {
+		void *next = EXT4_XATTR_NEXT(entry);
+
+		if (next >= end) {
+			EXT4_ERROR_INODE(inode,
+					 "corrupt xattr in inline inode");
+			return 0;
+		}
 		if (!entry->e_value_inum && entry->e_value_size) {
 			size_t offs = le16_to_cpu(entry->e_value_offs);
 			if (offs < min_offs)
 				min_offs = offs;
 		}
+		entry = next;
 	}
 	free = min_offs -
 		((void *)entry - (void *)IFIRST(header)) - sizeof(__u32);
@@ -350,7 +360,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
 
 	error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
 				     value, len);
-	if (error == -ENODATA)
+	if (error < 0)
 		goto out;
 
 	BUFFER_TRACE(is.iloc.bh, "get_write_access");
@@ -1177,6 +1187,7 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 		ext4_initialize_dirent_tail(dir_block,
 					    inode->i_sb->s_blocksize);
 	set_buffer_uptodate(dir_block);
+	unlock_buffer(dir_block);
 	err = ext4_handle_dirty_dirblock(handle, inode, dir_block);
 	if (err)
 		return err;
@@ -1251,6 +1262,7 @@ static int ext4_convert_inline_data_nolock(handle_t *handle,
 	if (!S_ISDIR(inode->i_mode)) {
 		memcpy(data_bh->b_data, buf, inline_size);
 		set_buffer_uptodate(data_bh);
+		unlock_buffer(data_bh);
 		error = ext4_handle_dirty_metadata(handle,
 						   inode, data_bh);
 	} else {
@@ -1258,7 +1270,6 @@ static int ext4_convert_inline_data_nolock(handle_t *handle,
 						       buf, inline_size);
 	}
 
-	unlock_buffer(data_bh);
 out_restore:
 	if (error)
 		ext4_restore_inline_data(handle, inode, iloc, buf, inline_size);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 41ba1c432844..145ea24d589b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2956,13 +2956,14 @@ static int ext4_writepages(struct address_space *mapping,
 		.can_map = 1,
 	};
 	int ret;
+	int alloc_ctx;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
 		return -EIO;
 
-	percpu_down_read(&EXT4_SB(sb)->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_read(sb);
 	ret = ext4_do_writepages(&mpd);
-	percpu_up_read(&EXT4_SB(sb)->s_writepages_rwsem);
+	ext4_writepages_up_read(sb, alloc_ctx);
 
 	return ret;
 }
@@ -2990,17 +2991,18 @@ static int ext4_dax_writepages(struct address_space *mapping,
 	long nr_to_write = wbc->nr_to_write;
 	struct inode *inode = mapping->host;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+	int alloc_ctx;
 
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_read(inode->i_sb);
 	trace_ext4_writepages(inode, wbc);
 
 	ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_read(inode->i_sb, alloc_ctx);
 	return ret;
 }
 
@@ -3574,7 +3576,7 @@ static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
 	 */
 	flags &= ~IOMAP_WRITE;
 	ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
-	WARN_ON_ONCE(iomap->type != IOMAP_MAPPED);
+	WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED);
 	return ret;
 }
 
@@ -6122,7 +6124,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	journal_t *journal;
 	handle_t *handle;
 	int err;
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int alloc_ctx;
 
 	/*
 	 * We have to be very careful here: changing a data block's
@@ -6160,7 +6162,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		}
 	}
 
-	percpu_down_write(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
 	jbd2_journal_lock_updates(journal);
 
 	/*
@@ -6177,7 +6179,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 		err = jbd2_journal_flush(journal, 0);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
-			percpu_up_write(&sbi->s_writepages_rwsem);
+			ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 			return err;
 		}
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);
@@ -6185,7 +6187,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
-	percpu_up_write(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 
 	if (val)
 		filemap_invalidate_unlock(inode->i_mapping);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5b2ae37a8b80..5639a4cf7ff9 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4820,7 +4820,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	trace_ext4_mb_release_group_pa(sb, pa);
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
-	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
+	if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
+		ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
+			     e4b->bd_group, group, pa->pa_pstart);
+		return 0;
+	}
 	mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
 	atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
 	trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index a19a9661646e..d98ac2af8199 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -408,7 +408,6 @@ static int free_ext_block(handle_t *handle, struct inode *inode)
 
 int ext4_ext_migrate(struct inode *inode)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	handle_t *handle;
 	int retval = 0, i;
 	__le32 *i_data;
@@ -418,6 +417,7 @@ int ext4_ext_migrate(struct inode *inode)
 	unsigned long max_entries;
 	__u32 goal, tmp_csum_seed;
 	uid_t owner[2];
+	int alloc_ctx;
 
 	/*
 	 * If the filesystem does not support extents, or the inode
@@ -434,7 +434,7 @@ int ext4_ext_migrate(struct inode *inode)
 		 */
 		return retval;
 
-	percpu_down_write(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
 
 	/*
 	 * Worst case we can touch the allocation bitmaps and a block
@@ -586,7 +586,7 @@ out_tmp_inode:
 	unlock_new_inode(tmp_inode);
 	iput(tmp_inode);
 out_unlock:
-	percpu_up_write(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 	return retval;
 }
 
@@ -605,6 +605,7 @@ int ext4_ind_migrate(struct inode *inode)
 	ext4_fsblk_t			blk;
 	handle_t			*handle;
 	int				ret, ret2 = 0;
+	int				alloc_ctx;
 
 	if (!ext4_has_feature_extents(inode->i_sb) ||
 	    (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
@@ -621,7 +622,7 @@ int ext4_ind_migrate(struct inode *inode)
 	if (test_opt(inode->i_sb, DELALLOC))
 		ext4_alloc_da_blocks(inode);
 
-	percpu_down_write(&sbi->s_writepages_rwsem);
+	alloc_ctx = ext4_writepages_down_write(inode->i_sb);
 
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
 	if (IS_ERR(handle)) {
@@ -665,6 +666,6 @@ errout:
 	ext4_journal_stop(handle);
 	up_write(&EXT4_I(inode)->i_data_sem);
 out_unlock:
-	percpu_up_write(&sbi->s_writepages_rwsem);
+	ext4_writepages_up_write(inode->i_sb, alloc_ctx);
 	return ret;
 }
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 4681fff6665f..46735ce315b5 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -39,28 +39,36 @@ static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
  * Write the MMP block using REQ_SYNC to try to get the block on-disk
  * faster.
  */
-static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+static int write_mmp_block_thawed(struct super_block *sb,
+				  struct buffer_head *bh)
 {
 	struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data);
 
-	/*
-	 * We protect against freezing so that we don't create dirty buffers
-	 * on frozen filesystem.
-	 */
-	sb_start_write(sb);
 	ext4_mmp_csum_set(sb, mmp);
 	lock_buffer(bh);
 	bh->b_end_io = end_buffer_write_sync;
 	get_bh(bh);
 	submit_bh(REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
-	sb_end_write(sb);
 	if (unlikely(!buffer_uptodate(bh)))
 		return -EIO;
-
 	return 0;
 }
 
+static int write_mmp_block(struct super_block *sb, struct buffer_head *bh)
+{
+	int err;
+
+	/*
+	 * We protect against freezing so that we don't create dirty buffers
+	 * on frozen filesystem.
+	 */
+	sb_start_write(sb);
+	err = write_mmp_block_thawed(sb, bh);
+	sb_end_write(sb);
+	return err;
+}
+
 /*
  * Read the MMP block. It _must_ be read from disk and hence we clear the
  * uptodate flag on the buffer.
@@ -340,7 +348,11 @@ skip:
 	seq = mmp_new_seq();
 	mmp->mmp_seq = cpu_to_le32(seq);
 
-	retval = write_mmp_block(sb, bh);
+	/*
+	 * On mount / remount we are protected against fs freezing (by s_umount
+	 * semaphore) and grabbing freeze protection upsets lockdep
+	 */
+	retval = write_mmp_block_thawed(sb, bh);
 	if (retval)
 		goto failed;
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index a5010b5b8a8c..45b579805c95 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -674,7 +674,7 @@ static struct stats dx_show_leaf(struct inode *dir,
 				len = de->name_len;
 				if (!IS_ENCRYPTED(dir)) {
 					/* Directory is not encrypted */
-					ext4fs_dirhash(dir, de->name,
+					(void) ext4fs_dirhash(dir, de->name,
 						de->name_len, &h);
 					printk("%*.s:(U)%x.%u ", len,
 					       name, h.hash,
@@ -709,8 +709,9 @@ static struct stats dx_show_leaf(struct inode *dir,
 					if (IS_CASEFOLDED(dir))
 						h.hash = EXT4_DIRENT_HASH(de);
 					else
-						ext4fs_dirhash(dir, de->name,
-						       de->name_len, &h);
+						(void) ext4fs_dirhash(dir,
+							de->name,
+							de->name_len, &h);
 					printk("%*.s:(E)%x.%u ", len, name,
 					       h.hash, (unsigned) ((char *) de
 								   - base));
@@ -720,7 +721,8 @@ static struct stats dx_show_leaf(struct inode *dir,
 #else
 				int len = de->name_len;
 				char *name = de->name;
-				ext4fs_dirhash(dir, de->name, de->name_len, &h);
+				(void) ext4fs_dirhash(dir, de->name,
+						      de->name_len, &h);
 				printk("%*.s:%x.%u ", len, name, h.hash,
 				       (unsigned) ((char *) de - base));
 #endif
@@ -849,8 +851,14 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	/* hash is already computed for encrypted casefolded directory */
 	if (fname && fname_name(fname) &&
-				!(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)))
-		ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo);
+	    !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir))) {
+		int ret = ext4fs_dirhash(dir, fname_name(fname),
+					 fname_len(fname), hinfo);
+		if (ret < 0) {
+			ret_err = ERR_PTR(ret);
+			goto fail;
+		}
+	}
 	hash = hinfo->hash;
 
 	if (root->info.unused_flags & 1) {
@@ -1111,7 +1119,12 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 				hinfo->minor_hash = 0;
 			}
 		} else {
-			ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
+			err = ext4fs_dirhash(dir, de->name,
+					     de->name_len, hinfo);
+			if (err < 0) {
+				count = err;
+				goto errout;
+			}
 		}
 		if ((hinfo->hash < start_hash) ||
 		    ((hinfo->hash == start_hash) &&
@@ -1313,8 +1326,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
 		if (de->name_len && de->inode) {
 			if (ext4_hash_in_dirent(dir))
 				h.hash = EXT4_DIRENT_HASH(de);
-			else
-				ext4fs_dirhash(dir, de->name, de->name_len, &h);
+			else {
+				int err = ext4fs_dirhash(dir, de->name,
+						     de->name_len, &h);
+				if (err < 0)
+					return err;
+			}
 			map_tail--;
 			map_tail->hash = h.hash;
 			map_tail->offs = ((char *) de - base)>>2;
@@ -1452,10 +1469,9 @@ int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
 	hinfo->hash_version = DX_HASH_SIPHASH;
 	hinfo->seed = NULL;
 	if (cf_name->name)
-		ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
+		return ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
 	else
-		ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
-	return 0;
+		return ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
 }
 #endif
 
@@ -2298,10 +2314,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
 	fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 
 	/* casefolded encrypted hashes are computed on fname setup */
-	if (!ext4_hash_in_dirent(dir))
-		ext4fs_dirhash(dir, fname_name(fname),
-				fname_len(fname), &fname->hinfo);
-
+	if (!ext4_hash_in_dirent(dir)) {
+		int err = ext4fs_dirhash(dir, fname_name(fname),
+					 fname_len(fname), &fname->hinfo);
+		if (err < 0) {
+			brelse(bh2);
+			brelse(bh);
+			return err;
+		}
+	}
 	memset(frames, 0, sizeof(frames));
 	frame = frames;
 	frame->entries = entries;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index f43e526112ae..d6ac61f43ac3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3184,11 +3184,9 @@ static __le16 ext4_group_desc_csum(struct super_block *sb, __u32 block_group,
 	crc = crc16(crc, (__u8 *)gdp, offset);
 	offset += sizeof(gdp->bg_checksum); /* skip checksum */
 	/* for checksum of struct ext4_group_desc do the rest...*/
-	if (ext4_has_feature_64bit(sb) &&
-	    offset < le16_to_cpu(sbi->s_es->s_desc_size))
+	if (ext4_has_feature_64bit(sb) && offset < sbi->s_desc_size)
 		crc = crc16(crc, (__u8 *)gdp + offset,
-			    le16_to_cpu(sbi->s_es->s_desc_size) -
-				offset);
+			    sbi->s_desc_size - offset);
 
 out:
 	return cpu_to_le16(crc);
@@ -6581,9 +6579,6 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 	}
 
 #ifdef CONFIG_QUOTA
-	/* Release old quota file names */
-	for (i = 0; i < EXT4_MAXQUOTAS; i++)
-		kfree(old_opts.s_qf_names[i]);
 	if (enable_quota) {
 		if (sb_any_quota_suspended(sb))
 			dquot_resume(sb, -1);
@@ -6593,6 +6588,9 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 				goto restore_opts;
 		}
 	}
+	/* Release old quota file names */
+	for (i = 0; i < EXT4_MAXQUOTAS; i++)
+		kfree(old_opts.s_qf_names[i]);
 #endif
 	if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks)
 		ext4_release_system_zone(sb);
@@ -6603,6 +6601,13 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 	return 0;
 
 restore_opts:
+	/*
+	 * If there was a failing r/w to ro transition, we may need to
+	 * re-enable quota
+	 */
+	if ((sb->s_flags & SB_RDONLY) && !(old_sb_flags & SB_RDONLY) &&
+	    sb_any_quota_suspended(sb))
+		dquot_resume(sb, -1);
 	sb->s_flags = old_sb_flags;
 	sbi->s_mount_opt = old_opts.s_mount_opt;
 	sbi->s_mount_opt2 = old_opts.s_mount_opt2;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 767454d74cd6..e33a323faf3c 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2615,6 +2615,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 		.in_inode = !!entry->e_value_inum,
 	};
 	struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
+	int needs_kvfree = 0;
 	int error;
 
 	is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
@@ -2637,7 +2638,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 			error = -ENOMEM;
 			goto out;
 		}
-
+		needs_kvfree = 1;
 		error = ext4_xattr_inode_get(inode, entry, buffer, value_size);
 		if (error)
 			goto out;
@@ -2676,7 +2677,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 
 out:
 	kfree(b_entry_name);
-	if (entry->e_value_inum && buffer)
+	if (needs_kvfree && buffer)
 		kvfree(buffer);
 	if (is)
 		brelse(is->iloc.bh);
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 28b12553f2b3..9a8153895d20 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -161,118 +161,52 @@ static bool __is_front_mergeable(struct extent_info *cur,
 	return __is_extent_mergeable(cur, front, type);
 }
 
-static struct rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re,
-							unsigned int ofs)
-{
-	if (cached_re) {
-		if (cached_re->ofs <= ofs &&
-				cached_re->ofs + cached_re->len > ofs) {
-			return cached_re;
-		}
-	}
-	return NULL;
-}
-
-static struct rb_entry *__lookup_rb_tree_slow(struct rb_root_cached *root,
-							unsigned int ofs)
+static struct extent_node *__lookup_extent_node(struct rb_root_cached *root,
+			struct extent_node *cached_en, unsigned int fofs)
 {
 	struct rb_node *node = root->rb_root.rb_node;
-	struct rb_entry *re;
+	struct extent_node *en;
 
+	/* check a cached entry */
+	if (cached_en && cached_en->ei.fofs <= fofs &&
+			cached_en->ei.fofs + cached_en->ei.len > fofs)
+		return cached_en;
+
+	/* check rb_tree */
 	while (node) {
-		re = rb_entry(node, struct rb_entry, rb_node);
+		en = rb_entry(node, struct extent_node, rb_node);
 
-		if (ofs < re->ofs)
+		if (fofs < en->ei.fofs)
 			node = node->rb_left;
-		else if (ofs >= re->ofs + re->len)
+		else if (fofs >= en->ei.fofs + en->ei.len)
 			node = node->rb_right;
 		else
-			return re;
+			return en;
 	}
 	return NULL;
 }
 
-struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
-				struct rb_entry *cached_re, unsigned int ofs)
-{
-	struct rb_entry *re;
-
-	re = __lookup_rb_tree_fast(cached_re, ofs);
-	if (!re)
-		return __lookup_rb_tree_slow(root, ofs);
-
-	return re;
-}
-
-struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
-					struct rb_root_cached *root,
-					struct rb_node **parent,
-					unsigned long long key, bool *leftmost)
-{
-	struct rb_node **p = &root->rb_root.rb_node;
-	struct rb_entry *re;
-
-	while (*p) {
-		*parent = *p;
-		re = rb_entry(*parent, struct rb_entry, rb_node);
-
-		if (key < re->key) {
-			p = &(*p)->rb_left;
-		} else {
-			p = &(*p)->rb_right;
-			*leftmost = false;
-		}
-	}
-
-	return p;
-}
-
-struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
-				struct rb_root_cached *root,
-				struct rb_node **parent,
-				unsigned int ofs, bool *leftmost)
-{
-	struct rb_node **p = &root->rb_root.rb_node;
-	struct rb_entry *re;
-
-	while (*p) {
-		*parent = *p;
-		re = rb_entry(*parent, struct rb_entry, rb_node);
-
-		if (ofs < re->ofs) {
-			p = &(*p)->rb_left;
-		} else if (ofs >= re->ofs + re->len) {
-			p = &(*p)->rb_right;
-			*leftmost = false;
-		} else {
-			f2fs_bug_on(sbi, 1);
-		}
-	}
-
-	return p;
-}
-
 /*
- * lookup rb entry in position of @ofs in rb-tree,
+ * lookup rb entry in position of @fofs in rb-tree,
  * if hit, return the entry, otherwise, return NULL
- * @prev_ex: extent before ofs
- * @next_ex: extent after ofs
- * @insert_p: insert point for new extent at ofs
+ * @prev_ex: extent before fofs
+ * @next_ex: extent after fofs
+ * @insert_p: insert point for new extent at fofs
  * in order to simplify the insertion after.
  * tree must stay unchanged between lookup and insertion.
  */
-struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
-				struct rb_entry *cached_re,
-				unsigned int ofs,
-				struct rb_entry **prev_entry,
-				struct rb_entry **next_entry,
+static struct extent_node *__lookup_extent_node_ret(struct rb_root_cached *root,
+				struct extent_node *cached_en,
+				unsigned int fofs,
+				struct extent_node **prev_entry,
+				struct extent_node **next_entry,
 				struct rb_node ***insert_p,
 				struct rb_node **insert_parent,
-				bool force, bool *leftmost)
+				bool *leftmost)
 {
 	struct rb_node **pnode = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL, *tmp_node;
-	struct rb_entry *re = cached_re;
+	struct extent_node *en = cached_en;
 
 	*insert_p = NULL;
 	*insert_parent = NULL;
@@ -282,24 +216,20 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
 	if (RB_EMPTY_ROOT(&root->rb_root))
 		return NULL;
 
-	if (re) {
-		if (re->ofs <= ofs && re->ofs + re->len > ofs)
-			goto lookup_neighbors;
-	}
+	if (en && en->ei.fofs <= fofs && en->ei.fofs + en->ei.len > fofs)
+		goto lookup_neighbors;
 
-	if (leftmost)
-		*leftmost = true;
+	*leftmost = true;
 
 	while (*pnode) {
 		parent = *pnode;
-		re = rb_entry(*pnode, struct rb_entry, rb_node);
+		en = rb_entry(*pnode, struct extent_node, rb_node);
 
-		if (ofs < re->ofs) {
+		if (fofs < en->ei.fofs) {
 			pnode = &(*pnode)->rb_left;
-		} else if (ofs >= re->ofs + re->len) {
+		} else if (fofs >= en->ei.fofs + en->ei.len) {
 			pnode = &(*pnode)->rb_right;
-			if (leftmost)
-				*leftmost = false;
+			*leftmost = false;
 		} else {
 			goto lookup_neighbors;
 		}
@@ -308,71 +238,32 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
 	*insert_p = pnode;
 	*insert_parent = parent;
 
-	re = rb_entry(parent, struct rb_entry, rb_node);
+	en = rb_entry(parent, struct extent_node, rb_node);
 	tmp_node = parent;
-	if (parent && ofs > re->ofs)
+	if (parent && fofs > en->ei.fofs)
 		tmp_node = rb_next(parent);
-	*next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+	*next_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 
 	tmp_node = parent;
-	if (parent && ofs < re->ofs)
+	if (parent && fofs < en->ei.fofs)
 		tmp_node = rb_prev(parent);
-	*prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+	*prev_entry = rb_entry_safe(tmp_node, struct extent_node, rb_node);
 	return NULL;
 
 lookup_neighbors:
-	if (ofs == re->ofs || force) {
+	if (fofs == en->ei.fofs) {
 		/* lookup prev node for merging backward later */
-		tmp_node = rb_prev(&re->rb_node);
-		*prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+		tmp_node = rb_prev(&en->rb_node);
+		*prev_entry = rb_entry_safe(tmp_node,
+					struct extent_node, rb_node);
 	}
-	if (ofs == re->ofs + re->len - 1 || force) {
+	if (fofs == en->ei.fofs + en->ei.len - 1) {
 		/* lookup next node for merging frontward later */
-		tmp_node = rb_next(&re->rb_node);
-		*next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+		tmp_node = rb_next(&en->rb_node);
+		*next_entry = rb_entry_safe(tmp_node,
+					struct extent_node, rb_node);
 	}
-	return re;
-}
-
-bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
-				struct rb_root_cached *root, bool check_key)
-{
-#ifdef CONFIG_F2FS_CHECK_FS
-	struct rb_node *cur = rb_first_cached(root), *next;
-	struct rb_entry *cur_re, *next_re;
-
-	if (!cur)
-		return true;
-
-	while (cur) {
-		next = rb_next(cur);
-		if (!next)
-			return true;
-
-		cur_re = rb_entry(cur, struct rb_entry, rb_node);
-		next_re = rb_entry(next, struct rb_entry, rb_node);
-
-		if (check_key) {
-			if (cur_re->key > next_re->key) {
-				f2fs_info(sbi, "inconsistent rbtree, "
-					"cur(%llu) next(%llu)",
-					cur_re->key, next_re->key);
-				return false;
-			}
-			goto next;
-		}
-
-		if (cur_re->ofs + cur_re->len > next_re->ofs) {
-			f2fs_info(sbi, "inconsistent rbtree, cur(%u, %u) next(%u, %u)",
-				  cur_re->ofs, cur_re->len,
-				  next_re->ofs, next_re->len);
-			return false;
-		}
-next:
-		cur = next;
-	}
-#endif
-	return true;
+	return en;
 }
 
 static struct kmem_cache *extent_tree_slab;
@@ -587,8 +478,7 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 		goto out;
 	}
 
-	en = (struct extent_node *)f2fs_lookup_rb_tree(&et->root,
-				(struct rb_entry *)et->cached_en, pgofs);
+	en = __lookup_extent_node(&et->root, et->cached_en, pgofs);
 	if (!en)
 		goto out;
 
@@ -662,7 +552,7 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 				bool leftmost)
 {
 	struct extent_tree_info *eti = &sbi->extent_tree[et->type];
-	struct rb_node **p;
+	struct rb_node **p = &et->root.rb_root.rb_node;
 	struct rb_node *parent = NULL;
 	struct extent_node *en = NULL;
 
@@ -674,8 +564,21 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 
 	leftmost = true;
 
-	p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent,
-						ei->fofs, &leftmost);
+	/* look up extent_node in the rb tree */
+	while (*p) {
+		parent = *p;
+		en = rb_entry(parent, struct extent_node, rb_node);
+
+		if (ei->fofs < en->ei.fofs) {
+			p = &(*p)->rb_left;
+		} else if (ei->fofs >= en->ei.fofs + en->ei.len) {
+			p = &(*p)->rb_right;
+			leftmost = false;
+		} else {
+			f2fs_bug_on(sbi, 1);
+		}
+	}
+
 do_insert:
 	en = __attach_extent_node(sbi, et, ei, parent, p, leftmost);
 	if (!en)
@@ -734,11 +637,10 @@ static void __update_extent_tree_range(struct inode *inode,
 	}
 
 	/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
-	en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root,
-					(struct rb_entry *)et->cached_en, fofs,
-					(struct rb_entry **)&prev_en,
-					(struct rb_entry **)&next_en,
-					&insert_p, &insert_parent, false,
+	en = __lookup_extent_node_ret(&et->root,
+					et->cached_en, fofs,
+					&prev_en, &next_en,
+					&insert_p, &insert_parent,
 					&leftmost);
 	if (!en)
 		en = next_en;
@@ -876,12 +778,11 @@ void f2fs_update_read_extent_tree_range_compressed(struct inode *inode,
 
 	write_lock(&et->lock);
 
-	en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root,
-				(struct rb_entry *)et->cached_en, fofs,
-				(struct rb_entry **)&prev_en,
-				(struct rb_entry **)&next_en,
-				&insert_p, &insert_parent, false,
-				&leftmost);
+	en = __lookup_extent_node_ret(&et->root,
+					et->cached_en, fofs,
+					&prev_en, &next_en,
+					&insert_p, &insert_parent,
+					&leftmost);
 	if (en)
 		goto unlock_out;
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 620343c65ab6..d6f9d6e0f13b 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -353,15 +353,7 @@ struct discard_info {
 
 struct discard_cmd {
 	struct rb_node rb_node;		/* rb node located in rb-tree */
-	union {
-		struct {
-			block_t lstart;	/* logical start address */
-			block_t len;	/* length */
-			block_t start;	/* actual start address in dev */
-		};
-		struct discard_info di;	/* discard info */
-
-	};
+	struct discard_info di;		/* discard info */
 	struct list_head list;		/* command list */
 	struct completion wait;		/* compleation */
 	struct block_device *bdev;	/* bdev */
@@ -628,17 +620,6 @@ enum extent_type {
 	NR_EXTENT_CACHES,
 };
 
-struct rb_entry {
-	struct rb_node rb_node;		/* rb node located in rb-tree */
-	union {
-		struct {
-			unsigned int ofs;	/* start offset of the entry */
-			unsigned int len;	/* length of the entry */
-		};
-		unsigned long long key;		/* 64-bits key */
-	} __packed;
-};
-
 struct extent_info {
 	unsigned int fofs;		/* start offset in a file */
 	unsigned int len;		/* length of the extent */
@@ -4139,23 +4120,6 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
  * extent_cache.c
  */
 bool sanity_check_extent_cache(struct inode *inode);
-struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root,
-				struct rb_entry *cached_re, unsigned int ofs);
-struct rb_node **f2fs_lookup_rb_tree_ext(struct f2fs_sb_info *sbi,
-				struct rb_root_cached *root,
-				struct rb_node **parent,
-				unsigned long long key, bool *left_most);
-struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
-				struct rb_root_cached *root,
-				struct rb_node **parent,
-				unsigned int ofs, bool *leftmost);
-struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
-		struct rb_entry *cached_re, unsigned int ofs,
-		struct rb_entry **prev_entry, struct rb_entry **next_entry,
-		struct rb_node ***insert_p, struct rb_node **insert_parent,
-		bool force, bool *leftmost);
-bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
-				struct rb_root_cached *root, bool check_key);
 void f2fs_init_extent_tree(struct inode *inode);
 void f2fs_drop_extent_tree(struct inode *inode);
 void f2fs_destroy_extent_node(struct inode *inode);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 292a17d62f56..2996d38aa89c 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -390,40 +390,95 @@ static unsigned int count_bits(const unsigned long *addr,
 	return sum;
 }
 
-static struct victim_entry *attach_victim_entry(struct f2fs_sb_info *sbi,
-				unsigned long long mtime, unsigned int segno,
-				struct rb_node *parent, struct rb_node **p,
-				bool left_most)
+static bool f2fs_check_victim_tree(struct f2fs_sb_info *sbi,
+				struct rb_root_cached *root)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+	struct rb_node *cur = rb_first_cached(root), *next;
+	struct victim_entry *cur_ve, *next_ve;
+
+	while (cur) {
+		next = rb_next(cur);
+		if (!next)
+			return true;
+
+		cur_ve = rb_entry(cur, struct victim_entry, rb_node);
+		next_ve = rb_entry(next, struct victim_entry, rb_node);
+
+		if (cur_ve->mtime > next_ve->mtime) {
+			f2fs_info(sbi, "broken victim_rbtree, "
+				"cur_mtime(%llu) next_mtime(%llu)",
+				cur_ve->mtime, next_ve->mtime);
+			return false;
+		}
+		cur = next;
+	}
+#endif
+	return true;
+}
+
+static struct victim_entry *__lookup_victim_entry(struct f2fs_sb_info *sbi,
+					unsigned long long mtime)
+{
+	struct atgc_management *am = &sbi->am;
+	struct rb_node *node = am->root.rb_root.rb_node;
+	struct victim_entry *ve = NULL;
+
+	while (node) {
+		ve = rb_entry(node, struct victim_entry, rb_node);
+
+		if (mtime < ve->mtime)
+			node = node->rb_left;
+		else
+			node = node->rb_right;
+	}
+	return ve;
+}
+
+static struct victim_entry *__create_victim_entry(struct f2fs_sb_info *sbi,
+		unsigned long long mtime, unsigned int segno)
 {
 	struct atgc_management *am = &sbi->am;
 	struct victim_entry *ve;
 
-	ve =  f2fs_kmem_cache_alloc(victim_entry_slab,
-				GFP_NOFS, true, NULL);
+	ve =  f2fs_kmem_cache_alloc(victim_entry_slab, GFP_NOFS, true, NULL);
 
 	ve->mtime = mtime;
 	ve->segno = segno;
 
-	rb_link_node(&ve->rb_node, parent, p);
-	rb_insert_color_cached(&ve->rb_node, &am->root, left_most);
-
 	list_add_tail(&ve->list, &am->victim_list);
-
 	am->victim_count++;
 
 	return ve;
 }
 
-static void insert_victim_entry(struct f2fs_sb_info *sbi,
+static void __insert_victim_entry(struct f2fs_sb_info *sbi,
 				unsigned long long mtime, unsigned int segno)
 {
 	struct atgc_management *am = &sbi->am;
-	struct rb_node **p;
+	struct rb_root_cached *root = &am->root;
+	struct rb_node **p = &root->rb_root.rb_node;
 	struct rb_node *parent = NULL;
+	struct victim_entry *ve;
 	bool left_most = true;
 
-	p = f2fs_lookup_rb_tree_ext(sbi, &am->root, &parent, mtime, &left_most);
-	attach_victim_entry(sbi, mtime, segno, parent, p, left_most);
+	/* look up rb tree to find parent node */
+	while (*p) {
+		parent = *p;
+		ve = rb_entry(parent, struct victim_entry, rb_node);
+
+		if (mtime < ve->mtime) {
+			p = &(*p)->rb_left;
+		} else {
+			p = &(*p)->rb_right;
+			left_most = false;
+		}
+	}
+
+	ve = __create_victim_entry(sbi, mtime, segno);
+
+	rb_link_node(&ve->rb_node, parent, p);
+	rb_insert_color_cached(&ve->rb_node, root, left_most);
 }
 
 static void add_victim_entry(struct f2fs_sb_info *sbi,
@@ -459,19 +514,7 @@ static void add_victim_entry(struct f2fs_sb_info *sbi,
 	if (sit_i->dirty_max_mtime - mtime < p->age_threshold)
 		return;
 
-	insert_victim_entry(sbi, mtime, segno);
-}
-
-static struct rb_node *lookup_central_victim(struct f2fs_sb_info *sbi,
-						struct victim_sel_policy *p)
-{
-	struct atgc_management *am = &sbi->am;
-	struct rb_node *parent = NULL;
-	bool left_most;
-
-	f2fs_lookup_rb_tree_ext(sbi, &am->root, &parent, p->age, &left_most);
-
-	return parent;
+	__insert_victim_entry(sbi, mtime, segno);
 }
 
 static void atgc_lookup_victim(struct f2fs_sb_info *sbi,
@@ -481,7 +524,6 @@ static void atgc_lookup_victim(struct f2fs_sb_info *sbi,
 	struct atgc_management *am = &sbi->am;
 	struct rb_root_cached *root = &am->root;
 	struct rb_node *node;
-	struct rb_entry *re;
 	struct victim_entry *ve;
 	unsigned long long total_time;
 	unsigned long long age, u, accu;
@@ -508,12 +550,10 @@ static void atgc_lookup_victim(struct f2fs_sb_info *sbi,
 
 	node = rb_first_cached(root);
 next:
-	re = rb_entry_safe(node, struct rb_entry, rb_node);
-	if (!re)
+	ve = rb_entry_safe(node, struct victim_entry, rb_node);
+	if (!ve)
 		return;
 
-	ve = (struct victim_entry *)re;
-
 	if (ve->mtime >= max_mtime || ve->mtime < min_mtime)
 		goto skip;
 
@@ -555,8 +595,6 @@ static void atssr_lookup_victim(struct f2fs_sb_info *sbi,
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct atgc_management *am = &sbi->am;
-	struct rb_node *node;
-	struct rb_entry *re;
 	struct victim_entry *ve;
 	unsigned long long age;
 	unsigned long long max_mtime = sit_i->dirty_max_mtime;
@@ -566,25 +604,22 @@ static void atssr_lookup_victim(struct f2fs_sb_info *sbi,
 	unsigned int dirty_threshold = max(am->max_candidate_count,
 					am->candidate_ratio *
 					am->victim_count / 100);
-	unsigned int cost;
-	unsigned int iter = 0;
+	unsigned int cost, iter;
 	int stage = 0;
 
 	if (max_mtime < min_mtime)
 		return;
 	max_mtime += 1;
 next_stage:
-	node = lookup_central_victim(sbi, p);
+	iter = 0;
+	ve = __lookup_victim_entry(sbi, p->age);
 next_node:
-	re = rb_entry_safe(node, struct rb_entry, rb_node);
-	if (!re) {
-		if (stage == 0)
-			goto skip_stage;
+	if (!ve) {
+		if (stage++ == 0)
+			goto next_stage;
 		return;
 	}
 
-	ve = (struct victim_entry *)re;
-
 	if (ve->mtime >= max_mtime || ve->mtime < min_mtime)
 		goto skip_node;
 
@@ -610,24 +645,20 @@ next_node:
 	}
 skip_node:
 	if (iter < dirty_threshold) {
-		if (stage == 0)
-			node = rb_prev(node);
-		else if (stage == 1)
-			node = rb_next(node);
+		ve = rb_entry(stage == 0 ? rb_prev(&ve->rb_node) :
+					rb_next(&ve->rb_node),
+					struct victim_entry, rb_node);
 		goto next_node;
 	}
-skip_stage:
-	if (stage < 1) {
-		stage++;
-		iter = 0;
+
+	if (stage++ == 0)
 		goto next_stage;
-	}
 }
+
 static void lookup_victim_by_age(struct f2fs_sb_info *sbi,
 						struct victim_sel_policy *p)
 {
-	f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
-						&sbi->am.root, true));
+	f2fs_bug_on(sbi, !f2fs_check_victim_tree(sbi, &sbi->am.root));
 
 	if (p->gc_mode == GC_AT)
 		atgc_lookup_victim(sbi, p);
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 15bd1d680f67..5ad6ac63e13f 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -55,20 +55,10 @@ struct gc_inode_list {
 	struct radix_tree_root iroot;
 };
 
-struct victim_info {
-	unsigned long long mtime;	/* mtime of section */
-	unsigned int segno;		/* section No. */
-};
-
 struct victim_entry {
 	struct rb_node rb_node;		/* rb node located in rb-tree */
-	union {
-		struct {
-			unsigned long long mtime;	/* mtime of section */
-			unsigned int segno;		/* segment No. */
-		};
-		struct victim_info vi;	/* victim info */
-	};
+	unsigned long long mtime;	/* mtime of section */
+	unsigned int segno;		/* segment No. */
 	struct list_head list;
 };
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 11fc4c8036a9..f97073c75d67 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -995,12 +995,20 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 			goto out;
 	}
 
+	/*
+	 * Copied from ext4_rename: we need to protect against old.inode
+	 * directory getting converted from inline directory format into
+	 * a normal one.
+	 */
+	if (S_ISDIR(old_inode->i_mode))
+		inode_lock_nested(old_inode, I_MUTEX_NONDIR2);
+
 	err = -ENOENT;
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry) {
 		if (IS_ERR(old_page))
 			err = PTR_ERR(old_page);
-		goto out;
+		goto out_unlock_old;
 	}
 
 	if (S_ISDIR(old_inode->i_mode)) {
@@ -1108,6 +1116,9 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 
 	f2fs_unlock_op(sbi);
 
+	if (S_ISDIR(old_inode->i_mode))
+		inode_unlock(old_inode);
+
 	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
 		f2fs_sync_fs(sbi->sb, 1);
 
@@ -1122,6 +1133,9 @@ out_dir:
 		f2fs_put_page(old_dir_page, 0);
 out_old:
 	f2fs_put_page(old_page, 0);
+out_unlock_old:
+	if (S_ISDIR(old_inode->i_mode))
+		inode_unlock(old_inode);
 out:
 	iput(whiteout);
 	return err;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index b2a080c660c8..a705c1d42716 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -263,7 +263,7 @@ retry:
 	f2fs_put_dnode(&dn);
 
 	trace_f2fs_replace_atomic_write_block(inode, F2FS_I(inode)->cow_inode,
-					index, *old_addr, new_addr, recover);
+			index, old_addr ? *old_addr : 0, new_addr, recover);
 	return 0;
 }
 
@@ -939,9 +939,9 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
 	dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS, true, NULL);
 	INIT_LIST_HEAD(&dc->list);
 	dc->bdev = bdev;
-	dc->lstart = lstart;
-	dc->start = start;
-	dc->len = len;
+	dc->di.lstart = lstart;
+	dc->di.start = start;
+	dc->di.len = len;
 	dc->ref = 0;
 	dc->state = D_PREP;
 	dc->queued = 0;
@@ -956,20 +956,108 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
 	return dc;
 }
 
-static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi,
-				struct block_device *bdev, block_t lstart,
-				block_t start, block_t len,
-				struct rb_node *parent, struct rb_node **p,
-				bool leftmost)
+static bool f2fs_check_discard_tree(struct f2fs_sb_info *sbi)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct rb_node *cur = rb_first_cached(&dcc->root), *next;
+	struct discard_cmd *cur_dc, *next_dc;
+
+	while (cur) {
+		next = rb_next(cur);
+		if (!next)
+			return true;
+
+		cur_dc = rb_entry(cur, struct discard_cmd, rb_node);
+		next_dc = rb_entry(next, struct discard_cmd, rb_node);
+
+		if (cur_dc->di.lstart + cur_dc->di.len > next_dc->di.lstart) {
+			f2fs_info(sbi, "broken discard_rbtree, "
+				"cur(%u, %u) next(%u, %u)",
+				cur_dc->di.lstart, cur_dc->di.len,
+				next_dc->di.lstart, next_dc->di.len);
+			return false;
+		}
+		cur = next;
+	}
+#endif
+	return true;
+}
+
+static struct discard_cmd *__lookup_discard_cmd(struct f2fs_sb_info *sbi,
+						block_t blkaddr)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct rb_node *node = dcc->root.rb_root.rb_node;
 	struct discard_cmd *dc;
 
-	dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
+	while (node) {
+		dc = rb_entry(node, struct discard_cmd, rb_node);
 
-	rb_link_node(&dc->rb_node, parent, p);
-	rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost);
+		if (blkaddr < dc->di.lstart)
+			node = node->rb_left;
+		else if (blkaddr >= dc->di.lstart + dc->di.len)
+			node = node->rb_right;
+		else
+			return dc;
+	}
+	return NULL;
+}
+
+static struct discard_cmd *__lookup_discard_cmd_ret(struct rb_root_cached *root,
+				block_t blkaddr,
+				struct discard_cmd **prev_entry,
+				struct discard_cmd **next_entry,
+				struct rb_node ***insert_p,
+				struct rb_node **insert_parent)
+{
+	struct rb_node **pnode = &root->rb_root.rb_node;
+	struct rb_node *parent = NULL, *tmp_node;
+	struct discard_cmd *dc;
+
+	*insert_p = NULL;
+	*insert_parent = NULL;
+	*prev_entry = NULL;
+	*next_entry = NULL;
+
+	if (RB_EMPTY_ROOT(&root->rb_root))
+		return NULL;
+
+	while (*pnode) {
+		parent = *pnode;
+		dc = rb_entry(*pnode, struct discard_cmd, rb_node);
+
+		if (blkaddr < dc->di.lstart)
+			pnode = &(*pnode)->rb_left;
+		else if (blkaddr >= dc->di.lstart + dc->di.len)
+			pnode = &(*pnode)->rb_right;
+		else
+			goto lookup_neighbors;
+	}
+
+	*insert_p = pnode;
+	*insert_parent = parent;
+
+	dc = rb_entry(parent, struct discard_cmd, rb_node);
+	tmp_node = parent;
+	if (parent && blkaddr > dc->di.lstart)
+		tmp_node = rb_next(parent);
+	*next_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
+
+	tmp_node = parent;
+	if (parent && blkaddr < dc->di.lstart)
+		tmp_node = rb_prev(parent);
+	*prev_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
+	return NULL;
+
+lookup_neighbors:
+	/* lookup prev node for merging backward later */
+	tmp_node = rb_prev(&dc->rb_node);
+	*prev_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
 
+	/* lookup next node for merging frontward later */
+	tmp_node = rb_next(&dc->rb_node);
+	*next_entry = rb_entry_safe(tmp_node, struct discard_cmd, rb_node);
 	return dc;
 }
 
@@ -981,7 +1069,7 @@ static void __detach_discard_cmd(struct discard_cmd_control *dcc,
 
 	list_del(&dc->list);
 	rb_erase_cached(&dc->rb_node, &dcc->root);
-	dcc->undiscard_blks -= dc->len;
+	dcc->undiscard_blks -= dc->di.len;
 
 	kmem_cache_free(discard_cmd_slab, dc);
 
@@ -994,7 +1082,7 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	unsigned long flags;
 
-	trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len);
+	trace_f2fs_remove_discard(dc->bdev, dc->di.start, dc->di.len);
 
 	spin_lock_irqsave(&dc->lock, flags);
 	if (dc->bio_ref) {
@@ -1012,7 +1100,7 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
 		printk_ratelimited(
 			"%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d",
 			KERN_INFO, sbi->sb->s_id,
-			dc->lstart, dc->start, dc->len, dc->error);
+			dc->di.lstart, dc->di.start, dc->di.len, dc->error);
 	__detach_discard_cmd(dcc, dc);
 }
 
@@ -1128,14 +1216,14 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
 		return 0;
 
-	trace_f2fs_issue_discard(bdev, dc->start, dc->len);
+	trace_f2fs_issue_discard(bdev, dc->di.start, dc->di.len);
 
-	lstart = dc->lstart;
-	start = dc->start;
-	len = dc->len;
+	lstart = dc->di.lstart;
+	start = dc->di.start;
+	len = dc->di.len;
 	total_len = len;
 
-	dc->len = 0;
+	dc->di.len = 0;
 
 	while (total_len && *issued < dpolicy->max_requests && !err) {
 		struct bio *bio = NULL;
@@ -1151,7 +1239,7 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 		if (*issued == dpolicy->max_requests)
 			last = true;
 
-		dc->len += len;
+		dc->di.len += len;
 
 		if (time_to_inject(sbi, FAULT_DISCARD)) {
 			err = -EIO;
@@ -1213,34 +1301,41 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
 	return err;
 }
 
-static void __insert_discard_tree(struct f2fs_sb_info *sbi,
+static void __insert_discard_cmd(struct f2fs_sb_info *sbi,
 				struct block_device *bdev, block_t lstart,
-				block_t start, block_t len,
-				struct rb_node **insert_p,
-				struct rb_node *insert_parent)
+				block_t start, block_t len)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
-	struct rb_node **p;
+	struct rb_node **p = &dcc->root.rb_root.rb_node;
 	struct rb_node *parent = NULL;
+	struct discard_cmd *dc;
 	bool leftmost = true;
 
-	if (insert_p && insert_parent) {
-		parent = insert_parent;
-		p = insert_p;
-		goto do_insert;
+	/* look up rb tree to find parent node */
+	while (*p) {
+		parent = *p;
+		dc = rb_entry(parent, struct discard_cmd, rb_node);
+
+		if (lstart < dc->di.lstart) {
+			p = &(*p)->rb_left;
+		} else if (lstart >= dc->di.lstart + dc->di.len) {
+			p = &(*p)->rb_right;
+			leftmost = false;
+		} else {
+			f2fs_bug_on(sbi, 1);
+		}
 	}
 
-	p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent,
-							lstart, &leftmost);
-do_insert:
-	__attach_discard_cmd(sbi, bdev, lstart, start, len, parent,
-								p, leftmost);
+	dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
+
+	rb_link_node(&dc->rb_node, parent, p);
+	rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost);
 }
 
 static void __relocate_discard_cmd(struct discard_cmd_control *dcc,
 						struct discard_cmd *dc)
 {
-	list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->len)]);
+	list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->di.len)]);
 }
 
 static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
@@ -1250,7 +1345,7 @@ static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
 	struct discard_info di = dc->di;
 	bool modified = false;
 
-	if (dc->state == D_DONE || dc->len == 1) {
+	if (dc->state == D_DONE || dc->di.len == 1) {
 		__remove_discard_cmd(sbi, dc);
 		return;
 	}
@@ -1258,23 +1353,22 @@ static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
 	dcc->undiscard_blks -= di.len;
 
 	if (blkaddr > di.lstart) {
-		dc->len = blkaddr - dc->lstart;
-		dcc->undiscard_blks += dc->len;
+		dc->di.len = blkaddr - dc->di.lstart;
+		dcc->undiscard_blks += dc->di.len;
 		__relocate_discard_cmd(dcc, dc);
 		modified = true;
 	}
 
 	if (blkaddr < di.lstart + di.len - 1) {
 		if (modified) {
-			__insert_discard_tree(sbi, dc->bdev, blkaddr + 1,
+			__insert_discard_cmd(sbi, dc->bdev, blkaddr + 1,
 					di.start + blkaddr + 1 - di.lstart,
-					di.lstart + di.len - 1 - blkaddr,
-					NULL, NULL);
+					di.lstart + di.len - 1 - blkaddr);
 		} else {
-			dc->lstart++;
-			dc->len--;
-			dc->start++;
-			dcc->undiscard_blks += dc->len;
+			dc->di.lstart++;
+			dc->di.len--;
+			dc->di.start++;
+			dcc->undiscard_blks += dc->di.len;
 			__relocate_discard_cmd(dcc, dc);
 		}
 	}
@@ -1293,17 +1387,14 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 			SECTOR_TO_BLOCK(bdev_max_discard_sectors(bdev));
 	block_t end = lstart + len;
 
-	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
-					NULL, lstart,
-					(struct rb_entry **)&prev_dc,
-					(struct rb_entry **)&next_dc,
-					&insert_p, &insert_parent, true, NULL);
+	dc = __lookup_discard_cmd_ret(&dcc->root, lstart,
+				&prev_dc, &next_dc, &insert_p, &insert_parent);
 	if (dc)
 		prev_dc = dc;
 
 	if (!prev_dc) {
 		di.lstart = lstart;
-		di.len = next_dc ? next_dc->lstart - lstart : len;
+		di.len = next_dc ? next_dc->di.lstart - lstart : len;
 		di.len = min(di.len, len);
 		di.start = start;
 	}
@@ -1314,16 +1405,16 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 		struct discard_cmd *tdc = NULL;
 
 		if (prev_dc) {
-			di.lstart = prev_dc->lstart + prev_dc->len;
+			di.lstart = prev_dc->di.lstart + prev_dc->di.len;
 			if (di.lstart < lstart)
 				di.lstart = lstart;
 			if (di.lstart >= end)
 				break;
 
-			if (!next_dc || next_dc->lstart > end)
+			if (!next_dc || next_dc->di.lstart > end)
 				di.len = end - di.lstart;
 			else
-				di.len = next_dc->lstart - di.lstart;
+				di.len = next_dc->di.lstart - di.lstart;
 			di.start = start + di.lstart - lstart;
 		}
 
@@ -1356,10 +1447,9 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
 			merged = true;
 		}
 
-		if (!merged) {
-			__insert_discard_tree(sbi, bdev, di.lstart, di.start,
-							di.len, NULL, NULL);
-		}
+		if (!merged)
+			__insert_discard_cmd(sbi, bdev,
+						di.lstart, di.start, di.len);
  next:
 		prev_dc = next_dc;
 		if (!prev_dc)
@@ -1398,15 +1488,11 @@ static void __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
 	struct rb_node **insert_p = NULL, *insert_parent = NULL;
 	struct discard_cmd *dc;
 	struct blk_plug plug;
-	unsigned int pos = dcc->next_pos;
 	bool io_interrupted = false;
 
 	mutex_lock(&dcc->cmd_lock);
-	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
-					NULL, pos,
-					(struct rb_entry **)&prev_dc,
-					(struct rb_entry **)&next_dc,
-					&insert_p, &insert_parent, true, NULL);
+	dc = __lookup_discard_cmd_ret(&dcc->root, dcc->next_pos,
+				&prev_dc, &next_dc, &insert_p, &insert_parent);
 	if (!dc)
 		dc = next_dc;
 
@@ -1424,7 +1510,7 @@ static void __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi,
 			break;
 		}
 
-		dcc->next_pos = dc->lstart + dc->len;
+		dcc->next_pos = dc->di.lstart + dc->di.len;
 		err = __submit_discard_cmd(sbi, dpolicy, dc, issued);
 
 		if (*issued >= dpolicy->max_requests)
@@ -1483,8 +1569,7 @@ retry:
 		if (list_empty(pend_list))
 			goto next;
 		if (unlikely(dcc->rbtree_check))
-			f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
-							&dcc->root, false));
+			f2fs_bug_on(sbi, !f2fs_check_discard_tree(sbi));
 		blk_start_plug(&plug);
 		list_for_each_entry_safe(dc, tmp, pend_list, list) {
 			f2fs_bug_on(sbi, dc->state != D_PREP);
@@ -1562,7 +1647,7 @@ static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi,
 	dc->ref--;
 	if (!dc->ref) {
 		if (!dc->error)
-			len = dc->len;
+			len = dc->di.len;
 		__remove_discard_cmd(sbi, dc);
 	}
 	mutex_unlock(&dcc->cmd_lock);
@@ -1585,14 +1670,15 @@ next:
 
 	mutex_lock(&dcc->cmd_lock);
 	list_for_each_entry_safe(iter, tmp, wait_list, list) {
-		if (iter->lstart + iter->len <= start || end <= iter->lstart)
+		if (iter->di.lstart + iter->di.len <= start ||
+					end <= iter->di.lstart)
 			continue;
-		if (iter->len < dpolicy->granularity)
+		if (iter->di.len < dpolicy->granularity)
 			continue;
 		if (iter->state == D_DONE && !iter->ref) {
 			wait_for_completion_io(&iter->wait);
 			if (!iter->error)
-				trimmed += iter->len;
+				trimmed += iter->di.len;
 			__remove_discard_cmd(sbi, iter);
 		} else {
 			iter->ref++;
@@ -1636,8 +1722,7 @@ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
 	bool need_wait = false;
 
 	mutex_lock(&dcc->cmd_lock);
-	dc = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root,
-							NULL, blkaddr);
+	dc = __lookup_discard_cmd(sbi, blkaddr);
 	if (dc) {
 		if (dc->state == D_PREP) {
 			__punch_discard_cmd(sbi, dc, blkaddr);
@@ -2970,24 +3055,20 @@ next:
 
 	mutex_lock(&dcc->cmd_lock);
 	if (unlikely(dcc->rbtree_check))
-		f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
-							&dcc->root, false));
-
-	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
-					NULL, start,
-					(struct rb_entry **)&prev_dc,
-					(struct rb_entry **)&next_dc,
-					&insert_p, &insert_parent, true, NULL);
+		f2fs_bug_on(sbi, !f2fs_check_discard_tree(sbi));
+
+	dc = __lookup_discard_cmd_ret(&dcc->root, start,
+				&prev_dc, &next_dc, &insert_p, &insert_parent);
 	if (!dc)
 		dc = next_dc;
 
 	blk_start_plug(&plug);
 
-	while (dc && dc->lstart <= end) {
+	while (dc && dc->di.lstart <= end) {
 		struct rb_node *node;
 		int err = 0;
 
-		if (dc->len < dpolicy->granularity)
+		if (dc->di.len < dpolicy->granularity)
 			goto skip;
 
 		if (dc->state != D_PREP) {
@@ -2998,7 +3079,7 @@ next:
 		err = __submit_discard_cmd(sbi, dpolicy, dc, &issued);
 
 		if (issued >= dpolicy->max_requests) {
-			start = dc->lstart + dc->len;
+			start = dc->di.lstart + dc->di.len;
 
 			if (err)
 				__remove_discard_cmd(sbi, dc);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1db3e3c24b43..ae4e51e91ee3 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -829,7 +829,7 @@ void wbc_detach_inode(struct writeback_control *wbc)
 		 * is okay.  The main goal is avoiding keeping an inode on
 		 * the wrong wb for an extended period of time.
 		 */
-		if (hweight32(history) > WB_FRN_HIST_THR_SLOTS)
+		if (hweight16(history) > WB_FRN_HIST_THR_SLOTS)
 			inode_switch_wbs(inode, max_id);
 	}
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 49cfe2ae6d23..993375f0db67 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -65,7 +65,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
 	struct fsnotify_event *fsn_event;
 	struct fsnotify_group *group = inode_mark->group;
 	int ret;
-	int len = 0;
+	int len = 0, wd;
 	int alloc_len = sizeof(struct inotify_event_info);
 	struct mem_cgroup *old_memcg;
 
@@ -81,6 +81,13 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
 			      fsn_mark);
 
 	/*
+	 * We can be racing with mark being detached. Don't report event with
+	 * invalid wd.
+	 */
+	wd = READ_ONCE(i_mark->wd);
+	if (wd == -1)
+		return 0;
+	/*
 	 * Whoever is interested in the event, pays for the allocation. Do not
 	 * trigger OOM killer in the target monitoring memcg as it may have
 	 * security repercussion.
@@ -110,7 +117,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
 	fsn_event = &event->fse;
 	fsnotify_init_event(fsn_event);
 	event->mask = mask;
-	event->wd = i_mark->wd;
+	event->wd = wd;
 	event->sync_cookie = cookie;
 	event->name_len = len;
 	if (len)
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 723fb64e6531..393c726ef17a 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -658,7 +658,8 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits)
 	if (!wnd->bits_last)
 		wnd->bits_last = wbits;
 
-	wnd->free_bits = kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN);
+	wnd->free_bits =
+		kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN);
 	if (!wnd->free_bits)
 		return -ENOMEM;
 
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index f1df52dfab74..7d0473da12c3 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -1645,7 +1645,7 @@ struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni,
 {
 	struct ATTRIB *attr = NULL;
 	struct ATTR_FILE_NAME *fname;
-       struct le_str *fns;
+	struct le_str *fns;
 
 	if (le)
 		*le = NULL;
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 567563771bf8..24c9aeb5a49e 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -2594,8 +2594,10 @@ static inline bool is_reserved_name(struct ntfs_sb_info *sbi,
 	if (len == 4 || (len > 4 && le16_to_cpu(name[4]) == '.')) {
 		port_digit = le16_to_cpu(name[3]);
 		if (port_digit >= '1' && port_digit <= '9')
-			if (!ntfs_cmp_names(name, 3, COM_NAME, 3, upcase, false) ||
-			    !ntfs_cmp_names(name, 3, LPT_NAME, 3, upcase, false))
+			if (!ntfs_cmp_names(name, 3, COM_NAME, 3, upcase,
+					    false) ||
+			    !ntfs_cmp_names(name, 3, LPT_NAME, 3, upcase,
+					    false))
 				return true;
 	}
 
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index 407fe92394e2..92bbc8ee83ca 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -88,6 +88,16 @@ static struct dentry *ntfs_lookup(struct inode *dir, struct dentry *dentry,
 		__putname(uni);
 	}
 
+	/*
+	 * Check for a null pointer
+	 * If the MFT record of ntfs inode is not a base record, inode->i_op can be NULL.
+	 * This causes null pointer dereference in d_splice_alias().
+	 */
+	if (!IS_ERR_OR_NULL(inode) && !inode->i_op) {
+		iput(inode);
+		inode = ERR_PTR(-EINVAL);
+	}
+
 	return d_splice_alias(inode, dentry);
 }
 
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 86ea1826d099..90151e56c122 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -435,9 +435,6 @@ static inline u64 attr_svcn(const struct ATTRIB *attr)
 	return attr->non_res ? le64_to_cpu(attr->nres.svcn) : 0;
 }
 
-/* The size of resident attribute by its resident size. */
-#define BYTES_PER_RESIDENT(b) (0x18 + (b))
-
 static_assert(sizeof(struct ATTRIB) == 0x48);
 static_assert(sizeof(((struct ATTRIB *)NULL)->res) == 0x08);
 static_assert(sizeof(((struct ATTRIB *)NULL)->nres) == 0x38);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5851eb5bc726..faf32caef89b 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1287,7 +1287,10 @@ out:
  * __register_sysctl_table - register a leaf sysctl table
  * @set: Sysctl tree to register on
  * @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure
+ * @table: the top-level table structure without any child. This table
+ * 	 should not be free'd after registration. So it should not be
+ * 	 used on stack. It can either be a global or dynamically allocated
+ * 	 by the caller and free'd later after sysctl unregistration.
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
@@ -1308,9 +1311,12 @@ out:
  * proc_handler - the text handler routine (described below)
  *
  * extra1, extra2 - extra pointers usable by the proc handler routines
+ * XXX: we should eventually modify these to use long min / max [0]
+ * [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org
  *
  * Leaf nodes in the sysctl tree will be represented by a single file
- * under /proc; non-leaf nodes will be represented by directories.
+ * under /proc; non-leaf nodes (where child is not NULL) are not allowed,
+ * sysctl_check_table() verifies this.
  *
  * There must be a proc_handler routine for any terminal nodes.
  * Several default handlers are available to cover common cases -
@@ -1352,7 +1358,7 @@ struct ctl_table_header *__register_sysctl_table(
 
 	spin_lock(&sysctl_lock);
 	dir = &set->dir;
-	/* Reference moved down the diretory tree get_subdir */
+	/* Reference moved down the directory tree get_subdir */
 	dir->header.nreg++;
 	spin_unlock(&sysctl_lock);
 
@@ -1369,6 +1375,11 @@ struct ctl_table_header *__register_sysctl_table(
 		if (namelen == 0)
 			continue;
 
+		/*
+		 * namelen ensures if name is "foo/bar/yay" only foo is
+		 * registered first. We traverse as if using mkdir -p and
+		 * return a ctl_dir for the last directory entry.
+		 */
 		dir = get_subdir(dir, name, namelen);
 		if (IS_ERR(dir))
 			goto fail;
@@ -1394,8 +1405,15 @@ fail:
 
 /**
  * register_sysctl - register a sysctl table
- * @path: The path to the directory the sysctl table is in.
- * @table: the table structure
+ * @path: The path to the directory the sysctl table is in. If the path
+ * 	doesn't exist we will create it for you.
+ * @table: the table structure. The calller must ensure the life of the @table
+ * 	will be kept during the lifetime use of the syctl. It must not be freed
+ * 	until unregister_sysctl_table() is called with the given returned table
+ * 	with this registration. If your code is non modular then you don't need
+ * 	to call unregister_sysctl_table() and can instead use something like
+ * 	register_sysctl_init() which does not care for the result of the syctl
+ * 	registration.
  *
  * Register a sysctl table. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
@@ -1411,8 +1429,11 @@ EXPORT_SYMBOL(register_sysctl);
 
 /**
  * __register_sysctl_init() - register sysctl table to path
- * @path: path name for sysctl base
- * @table: This is the sysctl table that needs to be registered to the path
+ * @path: path name for sysctl base. If that path doesn't exist we will create
+ * 	it for you.
+ * @table: This is the sysctl table that needs to be registered to the path.
+ * 	The caller must ensure the life of the @table will be kept during the
+ * 	lifetime use of the sysctl.
  * @table_name: The name of sysctl table, only used for log printing when
  *              registration fails
  *
@@ -1424,10 +1445,7 @@ EXPORT_SYMBOL(register_sysctl);
  * register_sysctl() failing on init are extremely low, and so for both reasons
  * this function does not return any error as it is used by initialization code.
  *
- * Context: Can only be called after your respective sysctl base path has been
- * registered. So for instance, most base directories are registered early on
- * init before init levels are processed through proc_sys_init() and
- * sysctl_init_bases().
+ * Context: if your base directory does not exist it will be created for you.
  */
 void __init __register_sysctl_init(const char *path, struct ctl_table *table,
 				 const char *table_name)
@@ -1557,6 +1575,7 @@ out:
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
+ * We are slowly deprecating this call so avoid its use.
  *
  * See __register_sysctl_table for more details.
  */
@@ -1628,6 +1647,7 @@ err_register_leaves:
  *
  * Register a sysctl table hierarchy. @table should be a filled in ctl_table
  * array. A completely 0 filled entry terminates the table.
+ * We are slowly deprecating this caller so avoid future uses of it.
  *
  * See __register_sysctl_paths for more details.
  */