1 files changed, 198 insertions, 353 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4ba005c41983..820b1f1e6b67 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -5,6 +5,7 @@
 
 #include <linux/fs.h>
 #include <linux/blkdev.h>
+#include <linux/radix-tree.h>
 #include <linux/writeback.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
@@ -50,7 +51,6 @@
 				 BTRFS_SUPER_FLAG_METADUMP |\
 				 BTRFS_SUPER_FLAG_METADUMP_V2)
 
-static void end_workqueue_fn(struct btrfs_work *work);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_fs_info *fs_info);
@@ -63,40 +63,6 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,
 static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info);
 static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info);
 
-/*
- * btrfs_end_io_wq structs are used to do processing in task context when an IO
- * is complete.  This is used during reads to verify checksums, and it is used
- * by writes to insert metadata for new file extents after IO is complete.
- */
-struct btrfs_end_io_wq {
-	struct bio *bio;
-	bio_end_io_t *end_io;
-	void *private;
-	struct btrfs_fs_info *info;
-	blk_status_t status;
-	enum btrfs_wq_endio_type metadata;
-	struct btrfs_work work;
-};
-
-static struct kmem_cache *btrfs_end_io_wq_cache;
-
-int __init btrfs_end_io_wq_init(void)
-{
-	btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
-					sizeof(struct btrfs_end_io_wq),
-					0,
-					SLAB_MEM_SPREAD,
-					NULL);
-	if (!btrfs_end_io_wq_cache)
-		return -ENOMEM;
-	return 0;
-}
-
-void __cold btrfs_end_io_wq_exit(void)
-{
-	kmem_cache_destroy(btrfs_end_io_wq_cache);
-}
-
 static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info)
 {
 	if (fs_info->csum_shash)
@@ -121,88 +87,6 @@ struct async_submit_bio {
 };
 
 /*
- * Lockdep class keys for extent_buffer->lock's in this root.  For a given
- * eb, the lockdep key is determined by the btrfs_root it belongs to and
- * the level the eb occupies in the tree.
- *
- * Different roots are used for different purposes and may nest inside each
- * other and they require separate keysets.  As lockdep keys should be
- * static, assign keysets according to the purpose of the root as indicated
- * by btrfs_root->root_key.objectid.  This ensures that all special purpose
- * roots have separate keysets.
- *
- * Lock-nesting across peer nodes is always done with the immediate parent
- * node locked thus preventing deadlock.  As lockdep doesn't know this, use
- * subclass to avoid triggering lockdep warning in such cases.
- *
- * The key is set by the readpage_end_io_hook after the buffer has passed
- * csum validation but before the pages are unlocked.  It is also set by
- * btrfs_init_new_buffer on freshly allocated blocks.
- *
- * We also add a check to make sure the highest level of the tree is the
- * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
- * needs update as well.
- */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# if BTRFS_MAX_LEVEL != 8
-#  error
-# endif
-
-#define DEFINE_LEVEL(stem, level)					\
-	.names[level] = "btrfs-" stem "-0" #level,
-
-#define DEFINE_NAME(stem)						\
-	DEFINE_LEVEL(stem, 0)						\
-	DEFINE_LEVEL(stem, 1)						\
-	DEFINE_LEVEL(stem, 2)						\
-	DEFINE_LEVEL(stem, 3)						\
-	DEFINE_LEVEL(stem, 4)						\
-	DEFINE_LEVEL(stem, 5)						\
-	DEFINE_LEVEL(stem, 6)						\
-	DEFINE_LEVEL(stem, 7)
-
-static struct btrfs_lockdep_keyset {
-	u64			id;		/* root objectid */
-	/* Longest entry: btrfs-free-space-00 */
-	char			names[BTRFS_MAX_LEVEL][20];
-	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
-} btrfs_lockdep_keysets[] = {
-	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
-	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
-	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
-	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
-	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
-	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
-	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
-	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
-	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
-	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
-	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
-	{ .id = 0,				DEFINE_NAME("tree")	},
-};
-
-#undef DEFINE_LEVEL
-#undef DEFINE_NAME
-
-void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
-				    int level)
-{
-	struct btrfs_lockdep_keyset *ks;
-
-	BUG_ON(level >= ARRAY_SIZE(ks->keys));
-
-	/* find the matching keyset, id 0 is the default entry */
-	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
-		if (ks->id == objectid)
-			break;
-
-	lockdep_set_class_and_name(&eb->lock,
-				   &ks->keys[level], ks->names[level]);
-}
-
-#endif
-
-/*
  * Compute the csum of a btree block and store the result to provided buffer.
  */
 static void csum_tree_block(struct extent_buffer *buf, u8 *result)
@@ -255,8 +139,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		goto out;
 	}
 	btrfs_err_rl(eb->fs_info,
-		"parent transid verify failed on %llu wanted %llu found %llu",
-			eb->start,
+"parent transid verify failed on logical %llu mirror %u wanted %llu found %llu",
+			eb->start, eb->read_mirror,
 			parent_transid, btrfs_header_generation(eb));
 	ret = 1;
 	clear_extent_buffer_uptodate(eb);
@@ -485,7 +369,7 @@ static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info,
 		uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
 						       fs_info->nodesize);
 
-		/* A dirty eb shouldn't disappear from extent_buffers */
+		/* A dirty eb shouldn't disappear from buffer_radix */
 		if (WARN_ON(!eb))
 			return -EUCLEAN;
 
@@ -586,21 +470,23 @@ static int validate_extent_buffer(struct extent_buffer *eb)
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu",
-			     eb->start, found_start);
+		btrfs_err_rl(fs_info,
+			"bad tree block start, mirror %u want %llu have %llu",
+			     eb->read_mirror, eb->start, found_start);
 		ret = -EIO;
 		goto out;
 	}
 	if (check_tree_block_fsid(eb)) {
-		btrfs_err_rl(fs_info, "bad fsid on block %llu",
-			     eb->start);
+		btrfs_err_rl(fs_info, "bad fsid on logical %llu mirror %u",
+			     eb->start, eb->read_mirror);
 		ret = -EIO;
 		goto out;
 	}
 	found_level = btrfs_header_level(eb);
 	if (found_level >= BTRFS_MAX_LEVEL) {
-		btrfs_err(fs_info, "bad tree block level %d on %llu",
-			  (int)btrfs_header_level(eb), eb->start);
+		btrfs_err(fs_info,
+			"bad tree block level, mirror %u level %d on logical %llu",
+			eb->read_mirror, btrfs_header_level(eb), eb->start);
 		ret = -EIO;
 		goto out;
 	}
@@ -611,8 +497,8 @@ static int validate_extent_buffer(struct extent_buffer *eb)
 
 	if (memcmp(result, header_csum, csum_size) != 0) {
 		btrfs_warn_rl(fs_info,
-	"checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d",
-			      eb->start,
+"checksum verify failed on logical %llu mirror %u wanted " CSUM_FMT " found " CSUM_FMT " level %d",
+			      eb->start, eb->read_mirror,
 			      CSUM_FMT_VALUE(csum_size, header_csum),
 			      CSUM_FMT_VALUE(csum_size, result),
 			      btrfs_header_level(eb));
@@ -637,8 +523,8 @@ static int validate_extent_buffer(struct extent_buffer *eb)
 		set_extent_buffer_uptodate(eb);
 	else
 		btrfs_err(fs_info,
-			  "block=%llu read time tree block corruption detected",
-			  eb->start);
+		"read time tree block corruption detected on logical %llu mirror %u",
+			  eb->start, eb->read_mirror);
 out:
 	return ret;
 }
@@ -739,58 +625,6 @@ err:
 	return ret;
 }
 
-static void end_workqueue_bio(struct bio *bio)
-{
-	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
-	struct btrfs_fs_info *fs_info;
-	struct btrfs_workqueue *wq;
-
-	fs_info = end_io_wq->info;
-	end_io_wq->status = bio->bi_status;
-
-	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
-			wq = fs_info->endio_meta_write_workers;
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
-			wq = fs_info->endio_freespace_worker;
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			wq = fs_info->endio_raid56_workers;
-		else
-			wq = fs_info->endio_write_workers;
-	} else {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			wq = fs_info->endio_raid56_workers;
-		else if (end_io_wq->metadata)
-			wq = fs_info->endio_meta_workers;
-		else
-			wq = fs_info->endio_workers;
-	}
-
-	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
-	btrfs_queue_work(wq, &end_io_wq->work);
-}
-
-blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
-			enum btrfs_wq_endio_type metadata)
-{
-	struct btrfs_end_io_wq *end_io_wq;
-
-	end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
-	if (!end_io_wq)
-		return BLK_STS_RESOURCE;
-
-	end_io_wq->private = bio->bi_private;
-	end_io_wq->end_io = bio->bi_end_io;
-	end_io_wq->info = info;
-	end_io_wq->status = 0;
-	end_io_wq->bio = bio;
-	end_io_wq->metadata = metadata;
-
-	bio->bi_private = end_io_wq;
-	bio->bi_end_io = end_workqueue_bio;
-	return 0;
-}
-
 static void run_one_async_start(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
@@ -815,7 +649,6 @@ static void run_one_async_done(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
 	struct inode *inode;
-	blk_status_t ret;
 
 	async = container_of(work, struct  async_submit_bio, work);
 	inode = async->inode;
@@ -833,11 +666,7 @@ static void run_one_async_done(struct btrfs_work *work)
 	 * This changes nothing when cgroups aren't in use.
 	 */
 	async->bio->bi_opf |= REQ_CGROUP_PUNT;
-	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
-	if (ret) {
-		async->bio->bi_status = ret;
-		bio_endio(async->bio);
-	}
+	btrfs_submit_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
 }
 
 static void run_one_async_free(struct btrfs_work *work)
@@ -848,16 +677,23 @@ static void run_one_async_free(struct btrfs_work *work)
 	kfree(async);
 }
 
-blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio,
-				 int mirror_num, u64 dio_file_offset,
-				 extent_submit_bio_start_t *submit_bio_start)
+/*
+ * Submit bio to an async queue.
+ *
+ * Retrun:
+ * - true if the work has been succesfuly submitted
+ * - false in case of error
+ */
+bool btrfs_wq_submit_bio(struct inode *inode, struct bio *bio, int mirror_num,
+			 u64 dio_file_offset,
+			 extent_submit_bio_start_t *submit_bio_start)
 {
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct async_submit_bio *async;
 
 	async = kmalloc(sizeof(*async), GFP_NOFS);
 	if (!async)
-		return BLK_STS_RESOURCE;
+		return false;
 
 	async->inode = inode;
 	async->bio = bio;
@@ -875,7 +711,7 @@ blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio,
 		btrfs_queue_work(fs_info->hipri_workers, &async->work);
 	else
 		btrfs_queue_work(fs_info->workers, &async->work);
-	return 0;
+	return true;
 }
 
 static blk_status_t btree_csum_one_bio(struct bio *bio)
@@ -901,7 +737,7 @@ static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio,
 {
 	/*
 	 * when we're called for a write, we're already in the async
-	 * submission context.  Just jump into btrfs_map_bio
+	 * submission context.  Just jump into btrfs_submit_bio.
 	 */
 	return btree_csum_one_bio(bio);
 }
@@ -923,57 +759,54 @@ void btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int mirror_
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	blk_status_t ret;
 
+	bio->bi_opf |= REQ_META;
+
 	if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
-		/*
-		 * called for a read, do the setup so that checksum validation
-		 * can happen in the async kernel threads
-		 */
-		ret = btrfs_bio_wq_end_io(fs_info, bio,
-					  BTRFS_WQ_ENDIO_METADATA);
-		if (!ret)
-			ret = btrfs_map_bio(fs_info, bio, mirror_num);
-	} else if (!should_async_write(fs_info, BTRFS_I(inode))) {
-		ret = btree_csum_one_bio(bio);
-		if (!ret)
-			ret = btrfs_map_bio(fs_info, bio, mirror_num);
-	} else {
-		/*
-		 * kthread helpers are used to submit writes so that
-		 * checksumming can happen in parallel across all CPUs
-		 */
-		ret = btrfs_wq_submit_bio(inode, bio, mirror_num, 0,
-					  btree_submit_bio_start);
+		btrfs_submit_bio(fs_info, bio, mirror_num);
+		return;
 	}
 
+	/*
+	 * Kthread helpers are used to submit writes so that checksumming can
+	 * happen in parallel across all CPUs.
+	 */
+	if (should_async_write(fs_info, BTRFS_I(inode)) &&
+	    btrfs_wq_submit_bio(inode, bio, mirror_num, 0, btree_submit_bio_start))
+		return;
+
+	ret = btree_csum_one_bio(bio);
 	if (ret) {
 		bio->bi_status = ret;
 		bio_endio(bio);
+		return;
 	}
+
+	btrfs_submit_bio(fs_info, bio, mirror_num);
 }
 
 #ifdef CONFIG_MIGRATION
-static int btree_migratepage(struct address_space *mapping,
-			struct page *newpage, struct page *page,
-			enum migrate_mode mode)
+static int btree_migrate_folio(struct address_space *mapping,
+		struct folio *dst, struct folio *src, enum migrate_mode mode)
 {
 	/*
 	 * we can't safely write a btree page from here,
 	 * we haven't done the locking hook
 	 */
-	if (PageDirty(page))
+	if (folio_test_dirty(src))
 		return -EAGAIN;
 	/*
 	 * Buffers may be managed in a filesystem specific way.
 	 * We must have no buffers or drop them.
 	 */
-	if (page_has_private(page) &&
-	    !try_to_release_page(page, GFP_KERNEL))
+	if (folio_get_private(src) &&
+	    !filemap_release_folio(src, GFP_KERNEL))
 		return -EAGAIN;
-	return migrate_page(mapping, newpage, page, mode);
+	return migrate_folio(mapping, dst, src, mode);
 }
+#else
+#define btree_migrate_folio NULL
 #endif
 
-
 static int btree_writepages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -1073,10 +906,8 @@ static const struct address_space_operations btree_aops = {
 	.writepages	= btree_writepages,
 	.release_folio	= btree_release_folio,
 	.invalidate_folio = btree_invalidate_folio,
-#ifdef CONFIG_MIGRATION
-	.migratepage	= btree_migratepage,
-#endif
-	.dirty_folio = btree_dirty_folio,
+	.migrate_folio	= btree_migrate_folio,
+	.dirty_folio	= btree_dirty_folio,
 };
 
 struct extent_buffer *btrfs_find_create_tree_block(
@@ -1158,7 +989,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
 	root->inode_tree = RB_ROOT;
-	xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);
+	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
 
 	btrfs_init_root_block_rsv(root);
 
@@ -1210,9 +1041,9 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
 #ifdef CONFIG_BTRFS_DEBUG
 	INIT_LIST_HEAD(&root->leak_list);
-	spin_lock(&fs_info->fs_roots_lock);
+	spin_lock(&fs_info->fs_roots_radix_lock);
 	list_add_tail(&root->leak_list, &fs_info->allocated_roots);
-	spin_unlock(&fs_info->fs_roots_lock);
+	spin_unlock(&fs_info->fs_roots_radix_lock);
 #endif
 }
 
@@ -1659,11 +1490,12 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_root *root;
 
-	spin_lock(&fs_info->fs_roots_lock);
-	root = xa_load(&fs_info->fs_roots, (unsigned long)root_id);
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	root = radix_tree_lookup(&fs_info->fs_roots_radix,
+				 (unsigned long)root_id);
 	if (root)
 		root = btrfs_grab_root(root);
-	spin_unlock(&fs_info->fs_roots_lock);
+	spin_unlock(&fs_info->fs_roots_radix_lock);
 	return root;
 }
 
@@ -1705,14 +1537,20 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
 {
 	int ret;
 
-	spin_lock(&fs_info->fs_roots_lock);
-	ret = xa_insert(&fs_info->fs_roots, (unsigned long)root->root_key.objectid,
-			root, GFP_NOFS);
+	ret = radix_tree_preload(GFP_NOFS);
+	if (ret)
+		return ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	ret = radix_tree_insert(&fs_info->fs_roots_radix,
+				(unsigned long)root->root_key.objectid,
+				root);
 	if (ret == 0) {
 		btrfs_grab_root(root);
-		set_bit(BTRFS_ROOT_REGISTERED, &root->state);
+		set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
 	}
-	spin_unlock(&fs_info->fs_roots_lock);
+	spin_unlock(&fs_info->fs_roots_radix_lock);
+	radix_tree_preload_end();
 
 	return ret;
 }
@@ -1864,7 +1702,7 @@ again:
 fail:
 	/*
 	 * If our caller provided us an anonymous device, then it's his
-	 * responsability to free it in case we fail. So we have to set our
+	 * responsibility to free it in case we fail. So we have to set our
 	 * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root()
 	 * and once again by our caller.
 	 */
@@ -1947,25 +1785,6 @@ struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
 	return root;
 }
 
-/*
- * called by the kthread helper functions to finally call the bio end_io
- * functions.  This is where read checksum verification actually happens
- */
-static void end_workqueue_fn(struct btrfs_work *work)
-{
-	struct bio *bio;
-	struct btrfs_end_io_wq *end_io_wq;
-
-	end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
-	bio = end_io_wq->bio;
-
-	bio->bi_status = end_io_wq->status;
-	bio->bi_private = end_io_wq->private;
-	bio->bi_end_io = end_io_wq->end_io;
-	bio_endio(bio);
-	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
-}
-
 static int cleaner_kthread(void *arg)
 {
 	struct btrfs_fs_info *fs_info = arg;
@@ -2272,10 +2091,14 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->delalloc_workers);
 	btrfs_destroy_workqueue(fs_info->hipri_workers);
 	btrfs_destroy_workqueue(fs_info->workers);
-	btrfs_destroy_workqueue(fs_info->endio_workers);
-	btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
+	if (fs_info->endio_workers)
+		destroy_workqueue(fs_info->endio_workers);
+	if (fs_info->endio_raid56_workers)
+		destroy_workqueue(fs_info->endio_raid56_workers);
 	if (fs_info->rmw_workers)
 		destroy_workqueue(fs_info->rmw_workers);
+	if (fs_info->compressed_write_workers)
+		destroy_workqueue(fs_info->compressed_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
 	btrfs_destroy_workqueue(fs_info->delayed_workers);
@@ -2289,8 +2112,8 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	 * the queues used for metadata I/O, since tasks from those other work
 	 * queues can do metadata I/O operations.
 	 */
-	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
-	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
+	if (fs_info->endio_meta_workers)
+		destroy_workqueue(fs_info->endio_meta_workers);
 }
 
 static void free_root_extent_buffers(struct btrfs_root *root)
@@ -2342,9 +2165,9 @@ void btrfs_put_root(struct btrfs_root *root)
 		btrfs_drew_lock_destroy(&root->snapshot_lock);
 		free_root_extent_buffers(root);
 #ifdef CONFIG_BTRFS_DEBUG
-		spin_lock(&root->fs_info->fs_roots_lock);
+		spin_lock(&root->fs_info->fs_roots_radix_lock);
 		list_del_init(&root->leak_list);
-		spin_unlock(&root->fs_info->fs_roots_lock);
+		spin_unlock(&root->fs_info->fs_roots_radix_lock);
 #endif
 		kfree(root);
 	}
@@ -2352,21 +2175,28 @@ void btrfs_put_root(struct btrfs_root *root)
 
 void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_root *root;
-	unsigned long index = 0;
+	int ret;
+	struct btrfs_root *gang[8];
+	int i;
 
 	while (!list_empty(&fs_info->dead_roots)) {
-		root = list_entry(fs_info->dead_roots.next,
-				  struct btrfs_root, root_list);
-		list_del(&root->root_list);
+		gang[0] = list_entry(fs_info->dead_roots.next,
+				     struct btrfs_root, root_list);
+		list_del(&gang[0]->root_list);
 
-		if (test_bit(BTRFS_ROOT_REGISTERED, &root->state))
-			btrfs_drop_and_free_fs_root(fs_info, root);
-		btrfs_put_root(root);
+		if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state))
+			btrfs_drop_and_free_fs_root(fs_info, gang[0]);
+		btrfs_put_root(gang[0]);
 	}
 
-	xa_for_each(&fs_info->fs_roots, index, root) {
-		btrfs_drop_and_free_fs_root(fs_info, root);
+	while (1) {
+		ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+					     (void **)gang, 0,
+					     ARRAY_SIZE(gang));
+		if (!ret)
+			break;
+		for (i = 0; i < ret; i++)
+			btrfs_drop_and_free_fs_root(fs_info, gang[i]);
 	}
 }
 
@@ -2413,7 +2243,9 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 	extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
 
 	BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root);
-	memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key));
+	BTRFS_I(inode)->location.objectid = BTRFS_BTREE_INODE_OBJECTID;
+	BTRFS_I(inode)->location.type = 0;
+	BTRFS_I(inode)->location.offset = 0;
 	set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
 	btrfs_insert_inode_hash(inode);
 }
@@ -2462,25 +2294,18 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info)
 	fs_info->fixup_workers =
 		btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
 
-	/*
-	 * endios are largely parallel and should have a very
-	 * low idle thresh
-	 */
 	fs_info->endio_workers =
-		btrfs_alloc_workqueue(fs_info, "endio", flags, max_active, 4);
+		alloc_workqueue("btrfs-endio", flags, max_active);
 	fs_info->endio_meta_workers =
-		btrfs_alloc_workqueue(fs_info, "endio-meta", flags,
-				      max_active, 4);
-	fs_info->endio_meta_write_workers =
-		btrfs_alloc_workqueue(fs_info, "endio-meta-write", flags,
-				      max_active, 2);
+		alloc_workqueue("btrfs-endio-meta", flags, max_active);
 	fs_info->endio_raid56_workers =
-		btrfs_alloc_workqueue(fs_info, "endio-raid56", flags,
-				      max_active, 4);
+		alloc_workqueue("btrfs-endio-raid56", flags, max_active);
 	fs_info->rmw_workers = alloc_workqueue("btrfs-rmw", flags, max_active);
 	fs_info->endio_write_workers =
 		btrfs_alloc_workqueue(fs_info, "endio-write", flags,
 				      max_active, 2);
+	fs_info->compressed_write_workers =
+		alloc_workqueue("btrfs-compressed-write", flags, max_active);
 	fs_info->endio_freespace_worker =
 		btrfs_alloc_workqueue(fs_info, "freespace-write", flags,
 				      max_active, 0);
@@ -2495,7 +2320,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info)
 	if (!(fs_info->workers && fs_info->hipri_workers &&
 	      fs_info->delalloc_workers && fs_info->flush_workers &&
 	      fs_info->endio_workers && fs_info->endio_meta_workers &&
-	      fs_info->endio_meta_write_workers &&
+	      fs_info->compressed_write_workers &&
 	      fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
 	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
 	      fs_info->caching_workers && fs_info->fixup_workers &&
@@ -2522,6 +2347,9 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type)
 
 	fs_info->csum_shash = csum_shash;
 
+	btrfs_info(fs_info, "using %s (%s) checksum algorithm",
+			btrfs_super_csum_name(csum_type),
+			crypto_shash_driver_name(csum_shash));
 	return 0;
 }
 
@@ -3134,8 +2962,8 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 
 void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 {
-	xa_init_flags(&fs_info->fs_roots, GFP_ATOMIC);
-	xa_init_flags(&fs_info->extent_buffers, GFP_ATOMIC);
+	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+	INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
 	INIT_LIST_HEAD(&fs_info->trans_list);
 	INIT_LIST_HEAD(&fs_info->dead_roots);
 	INIT_LIST_HEAD(&fs_info->delayed_iputs);
@@ -3143,7 +2971,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&fs_info->caching_block_groups);
 	spin_lock_init(&fs_info->delalloc_root_lock);
 	spin_lock_init(&fs_info->trans_lock);
-	spin_lock_init(&fs_info->fs_roots_lock);
+	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
 	spin_lock_init(&fs_info->super_lock);
@@ -3240,6 +3068,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	init_waitqueue_head(&fs_info->transaction_blocked_wait);
 	init_waitqueue_head(&fs_info->async_submit_wait);
 	init_waitqueue_head(&fs_info->delayed_iputs_wait);
+	init_waitqueue_head(&fs_info->zone_finish_wait);
 
 	/* Usable values until the real ones are cached from the superblock */
 	fs_info->nodesize = 4096;
@@ -3247,6 +3076,8 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	fs_info->sectorsize_bits = ilog2(4096);
 	fs_info->stripesize = 4096;
 
+	fs_info->max_extent_size = BTRFS_MAX_EXTENT_SIZE;
+
 	spin_lock_init(&fs_info->swapfile_pins_lock);
 	fs_info->swapfile_pins = RB_ROOT;
 
@@ -3374,7 +3205,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 	/*
 	 * btrfs_find_orphan_roots() is responsible for finding all the dead
 	 * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
-	 * them into the fs_info->fs_roots. This must be done before
+	 * them into the fs_info->fs_roots_radix tree. This must be done before
 	 * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
 	 * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
 	 * item before the root's tree is deleted - this means that if we unmount
@@ -3578,16 +3409,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	 */
 	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
 
-	/*
-	 * Flag our filesystem as having big metadata blocks if they are bigger
-	 * than the page size.
-	 */
-	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
-		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
-			btrfs_info(fs_info,
-				"flagging fs with big metadata feature");
-		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
-	}
 
 	/* Set up fs_info before parsing mount options */
 	nodesize = btrfs_super_nodesize(disk_super);
@@ -3625,8 +3446,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
 		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD;
 
-	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
-		btrfs_info(fs_info, "has skinny extents");
+	/*
+	 * Flag our filesystem as having big metadata blocks if they are bigger
+	 * than the page size.
+	 */
+	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE)
+		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
 
 	/*
 	 * mixed block groups end up with duplicate but slightly offset
@@ -3655,6 +3480,20 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		err = -EINVAL;
 		goto fail_alloc;
 	}
+	/*
+	 * We have unsupported RO compat features, although RO mounted, we
+	 * should not cause any metadata write, including log replay.
+	 * Or we could screw up whatever the new feature requires.
+	 */
+	if (unlikely(features && btrfs_super_log_root(disk_super) &&
+		     !btrfs_test_opt(fs_info, NOLOGREPLAY))) {
+		btrfs_err(fs_info,
+"cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay",
+			  features);
+		err = -EINVAL;
+		goto fail_alloc;
+	}
+
 
 	if (sectorsize < PAGE_SIZE) {
 		struct btrfs_subpage_info *subpage_info;
@@ -4499,11 +4338,12 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 {
 	bool drop_ref = false;
 
-	spin_lock(&fs_info->fs_roots_lock);
-	xa_erase(&fs_info->fs_roots, (unsigned long)root->root_key.objectid);
-	if (test_and_clear_bit(BTRFS_ROOT_REGISTERED, &root->state))
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	radix_tree_delete(&fs_info->fs_roots_radix,
+			  (unsigned long)root->root_key.objectid);
+	if (test_and_clear_bit(BTRFS_ROOT_IN_RADIX, &root->state))
 		drop_ref = true;
-	spin_unlock(&fs_info->fs_roots_lock);
+	spin_unlock(&fs_info->fs_roots_radix_lock);
 
 	if (BTRFS_FS_ERROR(fs_info)) {
 		ASSERT(root->log_root == NULL);
@@ -4519,48 +4359,50 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_root *roots[8];
-	unsigned long index = 0;
-	int i;
+	u64 root_objectid = 0;
+	struct btrfs_root *gang[8];
+	int i = 0;
 	int err = 0;
-	int grabbed;
+	unsigned int ret = 0;
 
 	while (1) {
-		struct btrfs_root *root;
-
-		spin_lock(&fs_info->fs_roots_lock);
-		if (!xa_find(&fs_info->fs_roots, &index, ULONG_MAX, XA_PRESENT)) {
-			spin_unlock(&fs_info->fs_roots_lock);
-			return err;
+		spin_lock(&fs_info->fs_roots_radix_lock);
+		ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+					     (void **)gang, root_objectid,
+					     ARRAY_SIZE(gang));
+		if (!ret) {
+			spin_unlock(&fs_info->fs_roots_radix_lock);
+			break;
 		}
+		root_objectid = gang[ret - 1]->root_key.objectid + 1;
 
-		grabbed = 0;
-		xa_for_each_start(&fs_info->fs_roots, index, root, index) {
-			/* Avoid grabbing roots in dead_roots */
-			if (btrfs_root_refs(&root->root_item) > 0)
-				roots[grabbed++] = btrfs_grab_root(root);
-			if (grabbed >= ARRAY_SIZE(roots))
-				break;
+		for (i = 0; i < ret; i++) {
+			/* Avoid to grab roots in dead_roots */
+			if (btrfs_root_refs(&gang[i]->root_item) == 0) {
+				gang[i] = NULL;
+				continue;
+			}
+			/* grab all the search result for later use */
+			gang[i] = btrfs_grab_root(gang[i]);
 		}
-		spin_unlock(&fs_info->fs_roots_lock);
+		spin_unlock(&fs_info->fs_roots_radix_lock);
 
-		for (i = 0; i < grabbed; i++) {
-			if (!roots[i])
+		for (i = 0; i < ret; i++) {
+			if (!gang[i])
 				continue;
-			index = roots[i]->root_key.objectid;
-			err = btrfs_orphan_cleanup(roots[i]);
+			root_objectid = gang[i]->root_key.objectid;
+			err = btrfs_orphan_cleanup(gang[i]);
 			if (err)
-				goto out;
-			btrfs_put_root(roots[i]);
+				break;
+			btrfs_put_root(gang[i]);
 		}
-		index++;
+		root_objectid++;
 	}
 
-out:
-	/* Release the roots that remain uncleaned due to error */
-	for (; i < grabbed; i++) {
-		if (roots[i])
-			btrfs_put_root(roots[i]);
+	/* release the uncleaned roots due to error */
+	for (; i < ret; i++) {
+		if (gang[i])
+			btrfs_put_root(gang[i]);
 	}
 	return err;
 }
@@ -4879,28 +4721,31 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
 
 static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
 {
-	unsigned long index = 0;
-	int grabbed = 0;
-	struct btrfs_root *roots[8];
+	struct btrfs_root *gang[8];
+	u64 root_objectid = 0;
+	int ret;
+
+	spin_lock(&fs_info->fs_roots_radix_lock);
+	while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+					     (void **)gang, root_objectid,
+					     ARRAY_SIZE(gang))) != 0) {
+		int i;
 
-	spin_lock(&fs_info->fs_roots_lock);
-	while ((grabbed = xa_extract(&fs_info->fs_roots, (void **)roots, index,
-				     ULONG_MAX, 8, XA_PRESENT))) {
-		for (int i = 0; i < grabbed; i++)
-			roots[i] = btrfs_grab_root(roots[i]);
-		spin_unlock(&fs_info->fs_roots_lock);
+		for (i = 0; i < ret; i++)
+			gang[i] = btrfs_grab_root(gang[i]);
+		spin_unlock(&fs_info->fs_roots_radix_lock);
 
-		for (int i = 0; i < grabbed; i++) {
-			if (!roots[i])
+		for (i = 0; i < ret; i++) {
+			if (!gang[i])
 				continue;
-			index = roots[i]->root_key.objectid;
-			btrfs_free_log(NULL, roots[i]);
-			btrfs_put_root(roots[i]);
+			root_objectid = gang[i]->root_key.objectid;
+			btrfs_free_log(NULL, gang[i]);
+			btrfs_put_root(gang[i]);
 		}
-		index++;
-		spin_lock(&fs_info->fs_roots_lock);
+		root_objectid++;
+		spin_lock(&fs_info->fs_roots_radix_lock);
 	}
-	spin_unlock(&fs_info->fs_roots_lock);
+	spin_unlock(&fs_info->fs_roots_radix_lock);
 	btrfs_free_log_root_tree(NULL, fs_info);
 }