Merge v6.15.3

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

81 files changed, 1229 insertions, 763 deletions

diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 32619d146cbc..862164181bac 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -59,7 +59,7 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq)
 	len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
 	if (len > 0)
 		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
-	netfs_write_subrequest_terminated(subreq, len ?: err, false);
+	netfs_write_subrequest_terminated(subreq, len ?: err);
 }
 
 /**
@@ -77,7 +77,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 
 	/* if we just extended the file size, any portion not in
 	 * cache won't be on server and is zeroes */
-	if (subreq->rreq->origin != NETFS_DIO_READ)
+	if (subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
+	    subreq->rreq->origin != NETFS_DIO_READ)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 	if (pos + total >= i_size_read(rreq->inode))
 		__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);
@@ -164,4 +165,5 @@ const struct address_space_operations v9fs_addr_operations = {
 	.invalidate_folio	= netfs_invalidate_folio,
 	.direct_IO		= noop_direct_IO,
 	.writepages		= netfs_writepages,
+	.migrate_folio		= filemap_migrate_folio,
 };
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 18b0a9f1615e..2e7526ea883a 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -120,17 +120,17 @@ static void afs_issue_write_worker(struct work_struct *work)
 
 #if 0 // Error injection
 	if (subreq->debug_index == 3)
-		return netfs_write_subrequest_terminated(subreq, -ENOANO, false);
+		return netfs_write_subrequest_terminated(subreq, -ENOANO);
 
 	if (!subreq->retry_count) {
 		set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
-		return netfs_write_subrequest_terminated(subreq, -EAGAIN, false);
+		return netfs_write_subrequest_terminated(subreq, -EAGAIN);
 	}
 #endif
 
 	op = afs_alloc_operation(wreq->netfs_priv, vnode->volume);
 	if (IS_ERR(op))
-		return netfs_write_subrequest_terminated(subreq, -EAGAIN, false);
+		return netfs_write_subrequest_terminated(subreq, -EAGAIN);
 
 	afs_op_set_vnode(op, 0, vnode);
 	op->file[0].dv_delta	= 1;
@@ -166,7 +166,7 @@ static void afs_issue_write_worker(struct work_struct *work)
 		break;
 	}
 
-	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len, false);
+	netfs_write_subrequest_terminated(subreq, ret < 0 ? ret : subreq->len);
 }
 
 void afs_issue_write(struct netfs_io_subrequest *subreq)
@@ -202,6 +202,7 @@ void afs_retry_request(struct netfs_io_request *wreq, struct netfs_io_stream *st
 	case NETFS_READ_GAPS:
 	case NETFS_READ_SINGLE:
 	case NETFS_READ_FOR_WRITE:
+	case NETFS_UNBUFFERED_READ:
 	case NETFS_DIO_READ:
 		return;
 	default:
diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index 13de6af279e5..b5b44ea91f99 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -1252,8 +1252,11 @@ hit_next:
 		if (!prealloc)
 			goto search_again;
 		ret = split_state(tree, state, prealloc, end + 1);
-		if (ret)
+		if (ret) {
 			extent_io_tree_panic(tree, state, "split", ret);
+			prealloc = NULL;
+			goto out;
+		}
 
 		set_state_bits(tree, prealloc, bits, changeset);
 		cache_state(prealloc, cached_state);
@@ -1456,6 +1459,7 @@ hit_next:
 		if (IS_ERR(inserted_state)) {
 			ret = PTR_ERR(inserted_state);
 			extent_io_tree_panic(tree, prealloc, "insert", ret);
+			goto out;
 		}
 		cache_state(inserted_state, cached_state);
 		if (inserted_state == prealloc)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 71b8a825c447..22455fbcb29e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1862,7 +1862,7 @@ again:
 		if (reserved_space < fsize) {
 			end = page_start + reserved_space - 1;
 			btrfs_delalloc_release_space(BTRFS_I(inode),
-					data_reserved, page_start,
+					data_reserved, end + 1,
 					fsize - reserved_space, true);
 		}
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 90f5da3c520a..8a3f44302788 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4849,8 +4849,11 @@ again:
 	folio = __filemap_get_folio(mapping, index,
 				    FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mask);
 	if (IS_ERR(folio)) {
-		btrfs_delalloc_release_space(inode, data_reserved, block_start,
-					     blocksize, true);
+		if (only_release_metadata)
+			btrfs_delalloc_release_metadata(inode, blocksize, true);
+		else
+			btrfs_delalloc_release_space(inode, data_reserved,
+						     block_start, blocksize, true);
 		btrfs_delalloc_release_extents(inode, blocksize);
 		ret = -ENOMEM;
 		goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index c3b2e29e3e01..4c525a040812 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -153,12 +153,14 @@ struct scrub_stripe {
 	unsigned int init_nr_io_errors;
 	unsigned int init_nr_csum_errors;
 	unsigned int init_nr_meta_errors;
+	unsigned int init_nr_meta_gen_errors;
 
 	/*
 	 * The following error bitmaps are all for the current status.
 	 * Every time we submit a new read, these bitmaps may be updated.
 	 *
-	 * error_bitmap = io_error_bitmap | csum_error_bitmap | meta_error_bitmap;
+	 * error_bitmap = io_error_bitmap | csum_error_bitmap |
+	 *		  meta_error_bitmap | meta_generation_bitmap;
 	 *
 	 * IO and csum errors can happen for both metadata and data.
 	 */
@@ -166,6 +168,7 @@ struct scrub_stripe {
 	unsigned long io_error_bitmap;
 	unsigned long csum_error_bitmap;
 	unsigned long meta_error_bitmap;
+	unsigned long meta_gen_error_bitmap;
 
 	/* For writeback (repair or replace) error reporting. */
 	unsigned long write_error_bitmap;
@@ -616,7 +619,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 	memcpy(on_disk_csum, header->csum, fs_info->csum_size);
 
 	if (logical != btrfs_stack_header_bytenr(header)) {
-		bitmap_set(&stripe->csum_error_bitmap, sector_nr, sectors_per_tree);
+		bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree);
 		bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
 		"tree block %llu mirror %u has bad bytenr, has %llu want %llu",
@@ -672,7 +675,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 	}
 	if (stripe->sectors[sector_nr].generation !=
 	    btrfs_stack_header_generation(header)) {
-		bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree);
+		bitmap_set(&stripe->meta_gen_error_bitmap, sector_nr, sectors_per_tree);
 		bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
 		"tree block %llu mirror %u has bad generation, has %llu want %llu",
@@ -684,6 +687,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 	bitmap_clear(&stripe->error_bitmap, sector_nr, sectors_per_tree);
 	bitmap_clear(&stripe->csum_error_bitmap, sector_nr, sectors_per_tree);
 	bitmap_clear(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree);
+	bitmap_clear(&stripe->meta_gen_error_bitmap, sector_nr, sectors_per_tree);
 }
 
 static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr)
@@ -972,8 +976,22 @@ skip:
 			if (__ratelimit(&rs) && dev)
 				scrub_print_common_warning("header error", dev, false,
 						     stripe->logical, physical);
+		if (test_bit(sector_nr, &stripe->meta_gen_error_bitmap))
+			if (__ratelimit(&rs) && dev)
+				scrub_print_common_warning("generation error", dev, false,
+						     stripe->logical, physical);
 	}
 
+	/* Update the device stats. */
+	for (int i = 0; i < stripe->init_nr_io_errors; i++)
+		btrfs_dev_stat_inc_and_print(stripe->dev, BTRFS_DEV_STAT_READ_ERRS);
+	for (int i = 0; i < stripe->init_nr_csum_errors; i++)
+		btrfs_dev_stat_inc_and_print(stripe->dev, BTRFS_DEV_STAT_CORRUPTION_ERRS);
+	/* Generation mismatch error is based on each metadata, not each block. */
+	for (int i = 0; i < stripe->init_nr_meta_gen_errors;
+	     i += (fs_info->nodesize >> fs_info->sectorsize_bits))
+		btrfs_dev_stat_inc_and_print(stripe->dev, BTRFS_DEV_STAT_GENERATION_ERRS);
+
 	spin_lock(&sctx->stat_lock);
 	sctx->stat.data_extents_scrubbed += stripe->nr_data_extents;
 	sctx->stat.tree_extents_scrubbed += stripe->nr_meta_extents;
@@ -982,7 +1000,8 @@ skip:
 	sctx->stat.no_csum += nr_nodatacsum_sectors;
 	sctx->stat.read_errors += stripe->init_nr_io_errors;
 	sctx->stat.csum_errors += stripe->init_nr_csum_errors;
-	sctx->stat.verify_errors += stripe->init_nr_meta_errors;
+	sctx->stat.verify_errors += stripe->init_nr_meta_errors +
+				    stripe->init_nr_meta_gen_errors;
 	sctx->stat.uncorrectable_errors +=
 		bitmap_weight(&stripe->error_bitmap, stripe->nr_sectors);
 	sctx->stat.corrected_errors += nr_repaired_sectors;
@@ -1028,6 +1047,8 @@ static void scrub_stripe_read_repair_worker(struct work_struct *work)
 						    stripe->nr_sectors);
 	stripe->init_nr_meta_errors = bitmap_weight(&stripe->meta_error_bitmap,
 						    stripe->nr_sectors);
+	stripe->init_nr_meta_gen_errors = bitmap_weight(&stripe->meta_gen_error_bitmap,
+							stripe->nr_sectors);
 
 	if (bitmap_empty(&stripe->init_error_bitmap, stripe->nr_sectors))
 		goto out;
@@ -1142,6 +1163,9 @@ static void scrub_write_endio(struct btrfs_bio *bbio)
 		bitmap_set(&stripe->write_error_bitmap, sector_nr,
 			   bio_size >> fs_info->sectorsize_bits);
 		spin_unlock_irqrestore(&stripe->write_error_lock, flags);
+		for (int i = 0; i < (bio_size >> fs_info->sectorsize_bits); i++)
+			btrfs_dev_stat_inc_and_print(stripe->dev,
+						     BTRFS_DEV_STAT_WRITE_ERRS);
 	}
 	bio_put(&bbio->bio);
 
@@ -1508,10 +1532,12 @@ static void scrub_stripe_reset_bitmaps(struct scrub_stripe *stripe)
 	stripe->init_nr_io_errors = 0;
 	stripe->init_nr_csum_errors = 0;
 	stripe->init_nr_meta_errors = 0;
+	stripe->init_nr_meta_gen_errors = 0;
 	stripe->error_bitmap = 0;
 	stripe->io_error_bitmap = 0;
 	stripe->csum_error_bitmap = 0;
 	stripe->meta_error_bitmap = 0;
+	stripe->meta_gen_error_bitmap = 0;
 }
 
 /*
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 90dc094cfa5e..f5af11565b87 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -6583,6 +6583,19 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		btrfs_log_get_delayed_items(inode, &delayed_ins_list,
 					    &delayed_del_list);
 
+	/*
+	 * If we are fsyncing a file with 0 hard links, then commit the delayed
+	 * inode because the last inode ref (or extref) item may still be in the
+	 * subvolume tree and if we log it the file will still exist after a log
+	 * replay. So commit the delayed inode to delete that last ref and we
+	 * skip logging it.
+	 */
+	if (inode->vfs_inode.i_nlink == 0) {
+		ret = btrfs_commit_inode_delayed_inode(inode);
+		if (ret)
+			goto out_unlock;
+	}
+
 	ret = copy_inode_items_to_log(trans, inode, &min_key, &max_key,
 				      path, dst_path, logged_isize,
 				      inode_only, ctx,
@@ -7051,14 +7064,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	if (btrfs_root_generation(&root->root_item) == trans->transid)
 		return BTRFS_LOG_FORCE_COMMIT;
 
-	/*
-	 * Skip already logged inodes or inodes corresponding to tmpfiles
-	 * (since logging them is pointless, a link count of 0 means they
-	 * will never be accessible).
-	 */
-	if ((btrfs_inode_in_log(inode, trans->transid) &&
-	     list_empty(&ctx->ordered_extents)) ||
-	    inode->vfs_inode.i_nlink == 0)
+	/* Skip already logged inodes and without new extents. */
+	if (btrfs_inode_in_log(inode, trans->transid) &&
+	    list_empty(&ctx->ordered_extents))
 		return BTRFS_NO_LOG_SYNC;
 
 	ret = start_log_trans(trans, root, ctx);
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 92058ae43488..c08e4a66ac07 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -63,7 +63,7 @@ static void cachefiles_read_complete(struct kiocb *iocb, long ret)
 				ret = -ESTALE;
 		}
 
-		ki->term_func(ki->term_func_priv, ret, ki->was_async);
+		ki->term_func(ki->term_func_priv, ret);
 	}
 
 	cachefiles_put_kiocb(ki);
@@ -188,7 +188,7 @@ in_progress:
 
 presubmission_error:
 	if (term_func)
-		term_func(term_func_priv, ret < 0 ? ret : skipped, false);
+		term_func(term_func_priv, ret < 0 ? ret : skipped);
 	return ret;
 }
 
@@ -271,7 +271,7 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret)
 	atomic_long_sub(ki->b_writing, &object->volume->cache->b_writing);
 	set_bit(FSCACHE_COOKIE_HAVE_DATA, &object->cookie->flags);
 	if (ki->term_func)
-		ki->term_func(ki->term_func_priv, ret, ki->was_async);
+		ki->term_func(ki->term_func_priv, ret);
 	cachefiles_put_kiocb(ki);
 }
 
@@ -301,7 +301,7 @@ int __cachefiles_write(struct cachefiles_object *object,
 	ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL);
 	if (!ki) {
 		if (term_func)
-			term_func(term_func_priv, -ENOMEM, false);
+			term_func(term_func_priv, -ENOMEM);
 		return -ENOMEM;
 	}
 
@@ -366,7 +366,7 @@ static int cachefiles_write(struct netfs_cache_resources *cres,
 {
 	if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) {
 		if (term_func)
-			term_func(term_func_priv, -ENOBUFS, false);
+			term_func(term_func_priv, -ENOBUFS);
 		trace_netfs_sreq(term_func_priv, netfs_sreq_trace_cache_nowrite);
 		return -ENOBUFS;
 	}
@@ -665,7 +665,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 		pre = CACHEFILES_DIO_BLOCK_SIZE - off;
 		if (pre >= len) {
 			fscache_count_dio_misfit();
-			netfs_write_subrequest_terminated(subreq, len, false);
+			netfs_write_subrequest_terminated(subreq, len);
 			return;
 		}
 		subreq->transferred += pre;
@@ -691,7 +691,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 		len -= post;
 		if (len == 0) {
 			fscache_count_dio_misfit();
-			netfs_write_subrequest_terminated(subreq, post, false);
+			netfs_write_subrequest_terminated(subreq, post);
 			return;
 		}
 		iov_iter_truncate(&subreq->io_iter, len);
@@ -703,7 +703,7 @@ static void cachefiles_issue_write(struct netfs_io_subrequest *subreq)
 					 &start, &len, len, true);
 	cachefiles_end_secure(cache, saved_cred);
 	if (ret < 0) {
-		netfs_write_subrequest_terminated(subreq, ret, false);
+		netfs_write_subrequest_terminated(subreq, ret);
 		return;
 	}
 
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 29be367905a1..b95c4cb21c13 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -238,6 +238,7 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 		if (sparse && err > 0)
 			err = ceph_sparse_ext_map_end(op);
 		if (err < subreq->len &&
+		    subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
 		    subreq->rreq->origin != NETFS_DIO_READ)
 			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 		if (IS_ENCRYPTED(inode) && err > 0) {
@@ -281,7 +282,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	size_t len;
 	int mode;
 
-	if (rreq->origin != NETFS_DIO_READ)
+	if (rreq->origin != NETFS_UNBUFFERED_READ &&
+	    rreq->origin != NETFS_DIO_READ)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 	__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
 
@@ -539,7 +541,7 @@ static void ceph_set_page_fscache(struct page *page)
 	folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
 }
 
-static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
+static void ceph_fscache_write_terminated(void *priv, ssize_t error)
 {
 	struct inode *inode = priv;
 
diff --git a/fs/dax.c b/fs/dax.c
index 676303419e9e..f8d8b1afd232 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -257,7 +257,7 @@ static void *wait_entry_unlocked_exclusive(struct xa_state *xas, void *entry)
 		wq = dax_entry_waitqueue(xas, entry, &ewait.key);
 		prepare_to_wait_exclusive(wq, &ewait.wait,
 					TASK_UNINTERRUPTIBLE);
-		xas_pause(xas);
+		xas_reset(xas);
 		xas_unlock_irq(xas);
 		schedule();
 		finish_wait(wq, &ewait.wait);
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 9c9129bca346..34517ca9df91 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -102,8 +102,7 @@ static void erofs_fscache_req_io_put(struct erofs_fscache_io *io)
 		erofs_fscache_req_put(req);
 }
 
-static void erofs_fscache_req_end_io(void *priv,
-		ssize_t transferred_or_error, bool was_async)
+static void erofs_fscache_req_end_io(void *priv, ssize_t transferred_or_error)
 {
 	struct erofs_fscache_io *io = priv;
 	struct erofs_fscache_rq *req = io->private;
@@ -180,8 +179,7 @@ struct erofs_fscache_bio {
 	struct bio_vec bvecs[BIO_MAX_VECS];
 };
 
-static void erofs_fscache_bio_endio(void *priv,
-		ssize_t transferred_or_error, bool was_async)
+static void erofs_fscache_bio_endio(void *priv, ssize_t transferred_or_error)
 {
 	struct erofs_fscache_bio *io = priv;
 
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index da6ee7c39290..6e57b9cc6ed2 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -165,8 +165,11 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
 				filp_open(dif->path, O_RDONLY | O_LARGEFILE, 0) :
 				bdev_file_open_by_path(dif->path,
 						BLK_OPEN_READ, sb->s_type, NULL);
-		if (IS_ERR(file))
+		if (IS_ERR(file)) {
+			if (file == ERR_PTR(-ENOTBLK))
+				return -EINVAL;
 			return PTR_ERR(file);
+		}
 
 		if (!erofs_is_fileio_mode(sbi)) {
 			dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file),
@@ -510,24 +513,52 @@ static int erofs_fc_parse_param(struct fs_context *fc,
 	return 0;
 }
 
-static struct inode *erofs_nfs_get_inode(struct super_block *sb,
-					 u64 ino, u32 generation)
+static int erofs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
+			   struct inode *parent)
 {
-	return erofs_iget(sb, ino);
+	erofs_nid_t nid = EROFS_I(inode)->nid;
+	int len = parent ? 6 : 3;
+
+	if (*max_len < len) {
+		*max_len = len;
+		return FILEID_INVALID;
+	}
+
+	fh[0] = (u32)(nid >> 32);
+	fh[1] = (u32)(nid & 0xffffffff);
+	fh[2] = inode->i_generation;
+
+	if (parent) {
+		nid = EROFS_I(parent)->nid;
+
+		fh[3] = (u32)(nid >> 32);
+		fh[4] = (u32)(nid & 0xffffffff);
+		fh[5] = parent->i_generation;
+	}
+
+	*max_len = len;
+	return parent ? FILEID_INO64_GEN_PARENT : FILEID_INO64_GEN;
 }
 
 static struct dentry *erofs_fh_to_dentry(struct super_block *sb,
 		struct fid *fid, int fh_len, int fh_type)
 {
-	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
-				    erofs_nfs_get_inode);
+	if ((fh_type != FILEID_INO64_GEN &&
+	     fh_type != FILEID_INO64_GEN_PARENT) || fh_len < 3)
+		return NULL;
+
+	return d_obtain_alias(erofs_iget(sb,
+		((u64)fid->raw[0] << 32) | fid->raw[1]));
 }
 
 static struct dentry *erofs_fh_to_parent(struct super_block *sb,
 		struct fid *fid, int fh_len, int fh_type)
 {
-	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
-				    erofs_nfs_get_inode);
+	if (fh_type != FILEID_INO64_GEN_PARENT || fh_len < 6)
+		return NULL;
+
+	return d_obtain_alias(erofs_iget(sb,
+		((u64)fid->raw[3] << 32) | fid->raw[4]));
 }
 
 static struct dentry *erofs_get_parent(struct dentry *child)
@@ -543,7 +574,7 @@ static struct dentry *erofs_get_parent(struct dentry *child)
 }
 
 static const struct export_operations erofs_export_ops = {
-	.encode_fh = generic_encode_ino32_fh,
+	.encode_fh = erofs_encode_fh,
 	.fh_to_dentry = erofs_fh_to_dentry,
 	.fh_to_parent = erofs_fh_to_parent,
 	.get_parent = erofs_get_parent,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 54f89f0ee69b..b0b8748ae287 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -53,8 +53,8 @@ bool f2fs_is_cp_guaranteed(struct page *page)
 	struct inode *inode;
 	struct f2fs_sb_info *sbi;
 
-	if (!mapping)
-		return false;
+	if (fscrypt_is_bounce_page(page))
+		return page_private_gcing(fscrypt_pagecache_page(page));
 
 	inode = mapping->host;
 	sbi = F2FS_I_SB(inode);
@@ -3966,7 +3966,7 @@ retry:
 
 		if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec ||
 				nr_pblocks % blks_per_sec ||
-				!f2fs_valid_pinned_area(sbi, pblock)) {
+				f2fs_is_sequential_zone_area(sbi, pblock)) {
 			bool last_extent = false;
 
 			not_aligned++;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index f1576dc6ec67..4f34a7d9760a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1780,7 +1780,7 @@ struct f2fs_sb_info {
 	unsigned int dirty_device;		/* for checkpoint data flush */
 	spinlock_t dev_lock;			/* protect dirty_device */
 	bool aligned_blksize;			/* all devices has the same logical blksize */
-	unsigned int first_zoned_segno;		/* first zoned segno */
+	unsigned int first_seq_zone_segno;	/* first segno in sequential zone */
 
 	/* For write statistics */
 	u64 sectors_written_start;
@@ -2518,8 +2518,14 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;
 
 	spin_lock(&sbi->stat_lock);
-	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
-	sbi->total_valid_block_count -= (block_t)count;
+	if (unlikely(sbi->total_valid_block_count < count)) {
+		f2fs_warn(sbi, "Inconsistent total_valid_block_count:%u, ino:%lu, count:%u",
+			  sbi->total_valid_block_count, inode->i_ino, count);
+		sbi->total_valid_block_count = 0;
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+	} else {
+		sbi->total_valid_block_count -= count;
+	}
 	if (sbi->reserved_blocks &&
 		sbi->current_reserved_blocks < sbi->reserved_blocks)
 		sbi->current_reserved_blocks = min(sbi->reserved_blocks,
@@ -4622,12 +4628,16 @@ F2FS_FEATURE_FUNCS(readonly, RO);
 F2FS_FEATURE_FUNCS(device_alias, DEVICE_ALIAS);
 
 #ifdef CONFIG_BLK_DEV_ZONED
-static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
-				    block_t blkaddr)
+static inline bool f2fs_zone_is_seq(struct f2fs_sb_info *sbi, int devi,
+							unsigned int zone)
 {
-	unsigned int zno = blkaddr / sbi->blocks_per_blkz;
+	return test_bit(zone, FDEV(devi).blkz_seq);
+}
 
-	return test_bit(zno, FDEV(devi).blkz_seq);
+static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
+								block_t blkaddr)
+{
+	return f2fs_zone_is_seq(sbi, devi, blkaddr / sbi->blocks_per_blkz);
 }
 #endif
 
@@ -4699,15 +4709,31 @@ static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi)
 	return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS;
 }
 
-static inline bool f2fs_valid_pinned_area(struct f2fs_sb_info *sbi,
+static inline bool f2fs_is_sequential_zone_area(struct f2fs_sb_info *sbi,
 					  block_t blkaddr)
 {
 	if (f2fs_sb_has_blkzoned(sbi)) {
+#ifdef CONFIG_BLK_DEV_ZONED
 		int devi = f2fs_target_device_index(sbi, blkaddr);
 
-		return !bdev_is_zoned(FDEV(devi).bdev);
+		if (!bdev_is_zoned(FDEV(devi).bdev))
+			return false;
+
+		if (f2fs_is_multi_device(sbi)) {
+			if (blkaddr < FDEV(devi).start_blk ||
+				blkaddr > FDEV(devi).end_blk) {
+				f2fs_err(sbi, "Invalid block %x", blkaddr);
+				return false;
+			}
+			blkaddr -= FDEV(devi).start_blk;
+		}
+
+		return f2fs_blkz_is_seq(sbi, devi, blkaddr);
+#else
+		return false;
+#endif
 	}
-	return true;
+	return false;
 }
 
 static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 2b8f9239bede..8b5a55b72264 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -2066,6 +2066,9 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi,
 			.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
 		};
 
+		if (IS_CURSEC(sbi, GET_SEC_FROM_SEG(sbi, segno)))
+			continue;
+
 		do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false);
 		put_gc_inode(&gc_list);
 
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 8f8b9b843bdf..28137d499f8f 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -414,7 +414,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 
 	if (is_inode_flag_set(dir, FI_PROJ_INHERIT) &&
 			(!projid_eq(F2FS_I(dir)->i_projid,
-			F2FS_I(old_dentry->d_inode)->i_projid)))
+			F2FS_I(inode)->i_projid)))
 		return -EXDEV;
 
 	err = f2fs_dquot_initialize(dir);
@@ -914,7 +914,7 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 
 	if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
 			(!projid_eq(F2FS_I(new_dir)->i_projid,
-			F2FS_I(old_dentry->d_inode)->i_projid)))
+			F2FS_I(old_inode)->i_projid)))
 		return -EXDEV;
 
 	/*
@@ -1107,10 +1107,10 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
 			!projid_eq(F2FS_I(new_dir)->i_projid,
-			F2FS_I(old_dentry->d_inode)->i_projid)) ||
-	    (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+			F2FS_I(old_inode)->i_projid)) ||
+	    (is_inode_flag_set(old_dir, FI_PROJ_INHERIT) &&
 			!projid_eq(F2FS_I(old_dir)->i_projid,
-			F2FS_I(new_dentry->d_inode)->i_projid)))
+			F2FS_I(new_inode)->i_projid)))
 		return -EXDEV;
 
 	err = f2fs_dquot_initialize(old_dir);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 396ef71f41e3..41ca73622c8d 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -424,7 +424,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	if (need && excess_cached_nats(sbi))
 		f2fs_balance_fs_bg(sbi, false);
 
-	if (!f2fs_is_checkpoint_ready(sbi))
+	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		return;
 
 	/*
@@ -2777,7 +2777,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi,
 		if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV || pinning)
 			segno = 0;
 		else
-			segno = max(sbi->first_zoned_segno, *newseg);
+			segno = max(sbi->first_seq_zone_segno, *newseg);
 		hint = GET_SEC_FROM_SEG(sbi, segno);
 	}
 #endif
@@ -2789,7 +2789,7 @@ find_other_zone:
 	if (secno >= MAIN_SECS(sbi) && f2fs_sb_has_blkzoned(sbi)) {
 		/* Write only to sequential zones */
 		if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_ONLY_SEQ) {
-			hint = GET_SEC_FROM_SEG(sbi, sbi->first_zoned_segno);
+			hint = GET_SEC_FROM_SEG(sbi, sbi->first_seq_zone_segno);
 			secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
 		} else
 			secno = find_first_zero_bit(free_i->free_secmap,
@@ -2838,9 +2838,9 @@ got_it:
 	/* set it as dirty segment in free segmap */
 	f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
 
-	/* no free section in conventional zone */
+	/* no free section in conventional device or conventional zone */
 	if (new_sec && pinning &&
-		!f2fs_valid_pinned_area(sbi, START_BLOCK(sbi, segno))) {
+		f2fs_is_sequential_zone_area(sbi, START_BLOCK(sbi, segno))) {
 		ret = -EAGAIN;
 		goto out_unlock;
 	}
@@ -3311,7 +3311,7 @@ retry:
 
 	if (f2fs_sb_has_blkzoned(sbi) && err == -EAGAIN && gc_required) {
 		f2fs_down_write(&sbi->gc_lock);
-		err = f2fs_gc_range(sbi, 0, GET_SEGNO(sbi, FDEV(0).end_blk),
+		err = f2fs_gc_range(sbi, 0, sbi->first_seq_zone_segno - 1,
 				true, ZONED_PIN_SEC_REQUIRED_COUNT);
 		f2fs_up_write(&sbi->gc_lock);
 
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 0465dc00b349..503f6df690bf 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -429,7 +429,6 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
-	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi);
 
 	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
@@ -437,7 +436,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 
 	next = find_next_bit(free_i->free_segmap,
 			start_segno + SEGS_PER_SEC(sbi), start_segno);
-	if (next >= start_segno + usable_segs) {
+	if (next >= start_segno + f2fs_usable_segs_in_sec(sbi)) {
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
@@ -463,22 +462,36 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
-	unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi);
+	bool ret;
 
 	spin_lock(&free_i->segmap_lock);
-	if (test_and_clear_bit(segno, free_i->free_segmap)) {
-		free_i->free_segments++;
-
-		if (!inmem && IS_CURSEC(sbi, secno))
-			goto skip_free;
-		next = find_next_bit(free_i->free_segmap,
-				start_segno + SEGS_PER_SEC(sbi), start_segno);
-		if (next >= start_segno + usable_segs) {
-			if (test_and_clear_bit(secno, free_i->free_secmap))
-				free_i->free_sections++;
-		}
-	}
-skip_free:
+	ret = test_and_clear_bit(segno, free_i->free_segmap);
+	if (!ret)
+		goto unlock_out;
+
+	free_i->free_segments++;
+
+	if (!inmem && IS_CURSEC(sbi, secno))
+		goto unlock_out;
+
+	/* check large section */
+	next = find_next_bit(free_i->free_segmap,
+			     start_segno + SEGS_PER_SEC(sbi), start_segno);
+	if (next < start_segno + f2fs_usable_segs_in_sec(sbi))
+		goto unlock_out;
+
+	ret = test_and_clear_bit(secno, free_i->free_secmap);
+	if (!ret)
+		goto unlock_out;
+
+	free_i->free_sections++;
+
+	if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[BG_GC]) == secno)
+		sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
+	if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[FG_GC]) == secno)
+		sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
+
+unlock_out:
 	spin_unlock(&free_i->segmap_lock);
 }
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f087b2b71c89..386326f7a440 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1882,9 +1882,9 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_fsid    = u64_to_fsid(id);
 
 #ifdef CONFIG_QUOTA
-	if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) &&
+	if (is_inode_flag_set(d_inode(dentry), FI_PROJ_INHERIT) &&
 			sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
-		f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf);
+		f2fs_statfs_project(sb, F2FS_I(d_inode(dentry))->i_projid, buf);
 	}
 #endif
 	return 0;
@@ -4304,14 +4304,35 @@ static void f2fs_record_error_work(struct work_struct *work)
 	f2fs_record_stop_reason(sbi);
 }
 
-static inline unsigned int get_first_zoned_segno(struct f2fs_sb_info *sbi)
+static inline unsigned int get_first_seq_zone_segno(struct f2fs_sb_info *sbi)
 {
+#ifdef CONFIG_BLK_DEV_ZONED
+	unsigned int zoneno, total_zones;
 	int devi;
 
-	for (devi = 0; devi < sbi->s_ndevs; devi++)
-		if (bdev_is_zoned(FDEV(devi).bdev))
-			return GET_SEGNO(sbi, FDEV(devi).start_blk);
-	return 0;
+	if (!f2fs_sb_has_blkzoned(sbi))
+		return NULL_SEGNO;
+
+	for (devi = 0; devi < sbi->s_ndevs; devi++) {
+		if (!bdev_is_zoned(FDEV(devi).bdev))
+			continue;
+
+		total_zones = GET_ZONE_FROM_SEG(sbi, FDEV(devi).total_segments);
+
+		for (zoneno = 0; zoneno < total_zones; zoneno++) {
+			unsigned int segs, blks;
+
+			if (!f2fs_zone_is_seq(sbi, devi, zoneno))
+				continue;
+
+			segs = GET_SEG_FROM_SEC(sbi,
+					zoneno * sbi->secs_per_zone);
+			blks = SEGS_TO_BLKS(sbi, segs);
+			return GET_SEGNO(sbi, FDEV(devi).start_blk + blks);
+		}
+	}
+#endif
+	return NULL_SEGNO;
 }
 
 static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
@@ -4348,6 +4369,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 #endif
 
 	for (i = 0; i < max_devices; i++) {
+		if (max_devices == 1) {
+			FDEV(i).total_segments =
+				le32_to_cpu(raw_super->segment_count_main);
+			FDEV(i).start_blk = 0;
+			FDEV(i).end_blk = FDEV(i).total_segments *
+						BLKS_PER_SEG(sbi);
+		}
+
 		if (i == 0)
 			FDEV(0).bdev_file = sbi->sb->s_bdev_file;
 		else if (!RDEV(i).path[0])
@@ -4718,7 +4747,7 @@ try_onemore:
 	sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
 
 	/* get segno of first zoned block device */
-	sbi->first_zoned_segno = get_first_zoned_segno(sbi);
+	sbi->first_seq_zone_segno = get_first_seq_zone_segno(sbi);
 
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
diff --git a/fs/filesystems.c b/fs/filesystems.c
index 58b9067b2391..95e5256821a5 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -156,15 +156,19 @@ static int fs_index(const char __user * __name)
 static int fs_name(unsigned int index, char __user * buf)
 {
 	struct file_system_type * tmp;
-	int len, res;
+	int len, res = -EINVAL;
 
 	read_lock(&file_systems_lock);
-	for (tmp = file_systems; tmp; tmp = tmp->next, index--)
-		if (index <= 0 && try_module_get(tmp->owner))
+	for (tmp = file_systems; tmp; tmp = tmp->next, index--) {
+		if (index == 0) {
+			if (try_module_get(tmp->owner))
+				res = 0;
 			break;
+		}
+	}
 	read_unlock(&file_systems_lock);
-	if (!tmp)
-		return -EINVAL;
+	if (res)
+		return res;
 
 	/* OK, we got the reference, so we can safely block */
 	len = strlen(tmp->name) + 1;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 68fc8af14700..eb4270e82ef8 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -37,27 +37,6 @@
 #include "aops.h"
 
 
-void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio,
-			     size_t from, size_t len)
-{
-	struct buffer_head *head = folio_buffers(folio);
-	unsigned int bsize = head->b_size;
-	struct buffer_head *bh;
-	size_t to = from + len;
-	size_t start, end;
-
-	for (bh = head, start = 0; bh != head || !start;
-	     bh = bh->b_this_page, start = end) {
-		end = start + bsize;
-		if (end <= from)
-			continue;
-		if (start >= to)
-			break;
-		set_buffer_uptodate(bh);
-		gfs2_trans_add_data(ip->i_gl, bh);
-	}
-}
-
 /**
  * gfs2_get_block_noalloc - Fills in a buffer head with details about a block
  * @inode: The inode
@@ -133,12 +112,43 @@ static int __gfs2_jdata_write_folio(struct folio *folio,
 					inode->i_sb->s_blocksize,
 					BIT(BH_Dirty)|BIT(BH_Uptodate));
 		}
-		gfs2_trans_add_databufs(ip, folio, 0, folio_size(folio));
+		gfs2_trans_add_databufs(ip->i_gl, folio, 0, folio_size(folio));
 	}
 	return gfs2_write_jdata_folio(folio, wbc);
 }
 
 /**
+ * gfs2_jdata_writeback - Write jdata folios to the log
+ * @mapping: The mapping to write
+ * @wbc: The writeback control
+ *
+ * Returns: errno
+ */
+int gfs2_jdata_writeback(struct address_space *mapping, struct writeback_control *wbc)
+{
+	struct inode *inode = mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+	struct folio *folio = NULL;
+	int error;
+
+	BUG_ON(current->journal_info);
+	if (gfs2_assert_withdraw(sdp, ip->i_gl->gl_state == LM_ST_EXCLUSIVE))
+		return 0;
+
+	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
+		if (folio_test_checked(folio)) {
+			folio_redirty_for_writepage(wbc, folio);
+			folio_unlock(folio);
+			continue;
+		}
+		error = __gfs2_jdata_write_folio(folio, wbc);
+	}
+
+	return error;
+}
+
+/**
  * gfs2_writepages - Write a bunch of dirty pages back to disk
  * @mapping: The mapping to write
  * @wbc: Write-back control
diff --git a/fs/gfs2/aops.h b/fs/gfs2/aops.h
index a10c4334d248..bf002522a782 100644
--- a/fs/gfs2/aops.h
+++ b/fs/gfs2/aops.h
@@ -9,7 +9,6 @@
 #include "incore.h"
 
 void adjust_fs_space(struct inode *inode);
-void gfs2_trans_add_databufs(struct gfs2_inode *ip, struct folio *folio,
-			     size_t from, size_t len);
+int gfs2_jdata_writeback(struct address_space *mapping, struct writeback_control *wbc);
 
 #endif /* __AOPS_DOT_H__ */
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 366516b98b3f..b81984def58e 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -988,7 +988,8 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos,
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
 	if (!gfs2_is_stuffed(ip))
-		gfs2_trans_add_databufs(ip, folio, offset_in_folio(folio, pos),
+		gfs2_trans_add_databufs(ip->i_gl, folio,
+					offset_in_folio(folio, pos),
 					copied);
 
 	folio_unlock(folio);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index d7220a6fe8f5..ba25b884169e 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1166,7 +1166,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		   const struct gfs2_glock_operations *glops, int create,
 		   struct gfs2_glock **glp)
 {
-	struct super_block *s = sdp->sd_vfs;
 	struct lm_lockname name = { .ln_number = number,
 				    .ln_type = glops->go_type,
 				    .ln_sbd = sdp };
@@ -1229,7 +1228,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	mapping = gfs2_glock2aspace(gl);
 	if (mapping) {
                 mapping->a_ops = &gfs2_meta_aops;
-		mapping->host = s->s_bdev->bd_mapping->host;
+		mapping->host = sdp->sd_inode;
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_NOFS);
 		mapping->i_private_data = NULL;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index eb4714f299ef..116efe335c32 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -168,7 +168,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 static int gfs2_rgrp_metasync(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct address_space *metamapping = &sdp->sd_aspace;
+	struct address_space *metamapping = gfs2_aspace(sdp);
 	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
 	const unsigned bsize = sdp->sd_sb.sb_bsize;
 	loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK;
@@ -225,7 +225,7 @@ static int rgrp_go_sync(struct gfs2_glock *gl)
 static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct address_space *mapping = &sdp->sd_aspace;
+	struct address_space *mapping = gfs2_aspace(sdp);
 	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
 	const unsigned bsize = sdp->sd_sb.sb_bsize;
 	loff_t start, end;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 74abbd4970f8..0a41c4e76b32 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -795,7 +795,7 @@ struct gfs2_sbd {
 
 	/* Log stuff */
 
-	struct address_space sd_aspace;
+	struct inode *sd_inode;
 
 	spinlock_t sd_log_lock;
 
@@ -851,6 +851,13 @@ struct gfs2_sbd {
 	unsigned long sd_glock_dqs_held;
 };
 
+#define GFS2_BAD_INO 1
+
+static inline struct address_space *gfs2_aspace(struct gfs2_sbd *sdp)
+{
+	return sdp->sd_inode->i_mapping;
+}
+
 static inline void gfs2_glstats_inc(struct gfs2_glock *gl, int which)
 {
 	gl->gl_stats.stats[which]++;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 198a8cbaf5e5..8fd81444ffea 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -439,6 +439,74 @@ out:
 	return error;
 }
 
+static void gfs2_final_release_pages(struct gfs2_inode *ip)
+{
+	struct inode *inode = &ip->i_inode;
+	struct gfs2_glock *gl = ip->i_gl;
+
+	if (unlikely(!gl)) {
+		/* This can only happen during incomplete inode creation. */
+		BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags));
+		return;
+	}
+
+	truncate_inode_pages(gfs2_glock2aspace(gl), 0);
+	truncate_inode_pages(&inode->i_data, 0);
+
+	if (atomic_read(&gl->gl_revokes) == 0) {
+		clear_bit(GLF_LFLUSH, &gl->gl_flags);
+		clear_bit(GLF_DIRTY, &gl->gl_flags);
+	}
+}
+
+int gfs2_dinode_dealloc(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_holder gh;
+	int error;
+
+	if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
+		gfs2_consist_inode(ip);
+		return -EIO;
+	}
+
+	gfs2_rindex_update(sdp);
+
+	error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
+	if (error)
+		return error;
+
+	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
+	if (!rgd) {
+		gfs2_consist_inode(ip);
+		error = -EIO;
+		goto out_qs;
+	}
+
+	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+				   LM_FLAG_NODE_SCOPE, &gh);
+	if (error)
+		goto out_qs;
+
+	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
+				 sdp->sd_jdesc->jd_blocks);
+	if (error)
+		goto out_rg_gunlock;
+
+	gfs2_free_di(rgd, ip);
+
+	gfs2_final_release_pages(ip);
+
+	gfs2_trans_end(sdp);
+
+out_rg_gunlock:
+	gfs2_glock_dq_uninit(&gh);
+out_qs:
+	gfs2_quota_unhold(ip);
+	return error;
+}
+
 static void gfs2_init_dir(struct buffer_head *dibh,
 			  const struct gfs2_inode *parent)
 {
@@ -629,10 +697,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	struct gfs2_inode *dip = GFS2_I(dir), *ip;
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_glock *io_gl;
-	int error;
+	int error, dealloc_error;
 	u32 aflags = 0;
 	unsigned blocks = 1;
 	struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
+	bool xattr_initialized = false;
 
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return -ENAMETOOLONG;
@@ -659,7 +728,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (!IS_ERR(inode)) {
 		if (S_ISDIR(inode->i_mode)) {
 			iput(inode);
-			inode = ERR_PTR(-EISDIR);
+			inode = NULL;
+			error = -EISDIR;
 			goto fail_gunlock;
 		}
 		d_instantiate(dentry, inode);
@@ -744,11 +814,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
 	if (error)
-		goto fail_free_inode;
+		goto fail_dealloc_inode;
 
 	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
 	if (error)
-		goto fail_free_inode;
+		goto fail_dealloc_inode;
 	gfs2_cancel_delete_work(io_gl);
 	io_gl->gl_no_formal_ino = ip->i_no_formal_ino;
 
@@ -772,8 +842,10 @@ retry:
 	if (error)
 		goto fail_gunlock3;
 
-	if (blocks > 1)
+	if (blocks > 1) {
 		gfs2_init_xattr(ip);
+		xattr_initialized = true;
+	}
 	init_dinode(dip, ip, symname);
 	gfs2_trans_end(sdp);
 
@@ -828,6 +900,18 @@ fail_gunlock3:
 	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 fail_gunlock2:
 	gfs2_glock_put(io_gl);
+fail_dealloc_inode:
+	set_bit(GIF_ALLOC_FAILED, &ip->i_flags);
+	dealloc_error = 0;
+	if (ip->i_eattr)
+		dealloc_error = gfs2_ea_dealloc(ip, xattr_initialized);
+	clear_nlink(inode);
+	mark_inode_dirty(inode);
+	if (!dealloc_error)
+		dealloc_error = gfs2_dinode_dealloc(ip);
+	if (dealloc_error)
+		fs_warn(sdp, "%s: %d\n", __func__, dealloc_error);
+	ip->i_no_addr = 0;
 fail_free_inode:
 	if (ip->i_gl) {
 		gfs2_glock_put(ip->i_gl);
@@ -842,10 +926,6 @@ fail_gunlock:
 	gfs2_dir_no_add(&da);
 	gfs2_glock_dq_uninit(&d_gh);
 	if (!IS_ERR_OR_NULL(inode)) {
-		set_bit(GIF_ALLOC_FAILED, &ip->i_flags);
-		clear_nlink(inode);
-		if (ip->i_no_addr)
-			mark_inode_dirty(inode);
 		if (inode->i_state & I_NEW)
 			iget_failed(inode);
 		else
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 9e5e1622d50a..eafe123617e6 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -92,6 +92,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type,
 struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
 				  u64 no_formal_ino,
 				  unsigned int blktype);
+int gfs2_dinode_dealloc(struct gfs2_inode *ip);
 
 struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
 			   int is_root);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index f9c5089783d2..115c4ac457e9 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -31,6 +31,7 @@
 #include "dir.h"
 #include "trace_gfs2.h"
 #include "trans.h"
+#include "aops.h"
 
 static void gfs2_log_shutdown(struct gfs2_sbd *sdp);
 
@@ -131,7 +132,11 @@ __acquires(&sdp->sd_ail_lock)
 		if (!mapping)
 			continue;
 		spin_unlock(&sdp->sd_ail_lock);
-		ret = mapping->a_ops->writepages(mapping, wbc);
+		BUG_ON(GFS2_SB(mapping->host) != sdp);
+		if (gfs2_is_jdata(GFS2_I(mapping->host)))
+			ret = gfs2_jdata_writeback(mapping, wbc);
+		else
+			ret = mapping->a_ops->writepages(mapping, wbc);
 		if (need_resched()) {
 			blk_finish_plug(plug);
 			cond_resched();
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 198cc7056637..9dc8885c95d0 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -132,7 +132,7 @@ struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
 	unsigned int bufnum;
 
 	if (mapping == NULL)
-		mapping = &sdp->sd_aspace;
+		mapping = gfs2_aspace(sdp);
 
 	shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift;
 	index = blkno >> shift;             /* convert block to page */
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 831d988c2ceb..b7c8a6684d02 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -44,9 +44,7 @@ static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
 		struct gfs2_glock_aspace *gla =
 			container_of(mapping, struct gfs2_glock_aspace, mapping);
 		return gla->glock.gl_name.ln_sbd;
-	} else if (mapping->a_ops == &gfs2_rgrp_aops)
-		return container_of(mapping, struct gfs2_sbd, sd_aspace);
-	else
+	} else
 		return inode->i_sb->s_fs_info;
 }
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index e83d293c3614..4a0f7de41b2b 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -64,15 +64,17 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
 
 void free_sbd(struct gfs2_sbd *sdp)
 {
+	struct super_block *sb = sdp->sd_vfs;
+
 	if (sdp->sd_lkstats)
 		free_percpu(sdp->sd_lkstats);
+	sb->s_fs_info = NULL;
 	kfree(sdp);
 }
 
 static struct gfs2_sbd *init_sbd(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp;
-	struct address_space *mapping;
 
 	sdp = kzalloc(sizeof(struct gfs2_sbd), GFP_KERNEL);
 	if (!sdp)
@@ -109,16 +111,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	INIT_LIST_HEAD(&sdp->sd_sc_inodes_list);
 
-	mapping = &sdp->sd_aspace;
-
-	address_space_init_once(mapping);
-	mapping->a_ops = &gfs2_rgrp_aops;
-	mapping->host = sb->s_bdev->bd_mapping->host;
-	mapping->flags = 0;
-	mapping_set_gfp_mask(mapping, GFP_NOFS);
-	mapping->i_private_data = NULL;
-	mapping->writeback_index = 0;
-
 	spin_lock_init(&sdp->sd_log_lock);
 	atomic_set(&sdp->sd_log_pinned, 0);
 	INIT_LIST_HEAD(&sdp->sd_log_revokes);
@@ -1135,6 +1127,7 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 	int silent = fc->sb_flags & SB_SILENT;
 	struct gfs2_sbd *sdp;
 	struct gfs2_holder mount_gh;
+	struct address_space *mapping;
 	int error;
 
 	sdp = init_sbd(sb);
@@ -1156,6 +1149,7 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_flags |= SB_NOSEC;
 	sb->s_magic = GFS2_MAGIC;
 	sb->s_op = &gfs2_super_ops;
+
 	sb->s_d_op = &gfs2_dops;
 	sb->s_export_op = &gfs2_export_ops;
 	sb->s_qcop = &gfs2_quotactl_ops;
@@ -1181,9 +1175,21 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 		sdp->sd_tune.gt_statfs_quantum = 30;
 	}
 
+	/* Set up an address space for metadata writes */
+	sdp->sd_inode = new_inode(sb);
+	error = -ENOMEM;
+	if (!sdp->sd_inode)
+		goto fail_free;
+	sdp->sd_inode->i_ino = GFS2_BAD_INO;
+	sdp->sd_inode->i_size = OFFSET_MAX;
+
+	mapping = gfs2_aspace(sdp);
+	mapping->a_ops = &gfs2_rgrp_aops;
+	mapping_set_gfp_mask(mapping, GFP_NOFS);
+
 	error = init_names(sdp, silent);
 	if (error)
-		goto fail_free;
+		goto fail_iput;
 
 	snprintf(sdp->sd_fsname, sizeof(sdp->sd_fsname), "%s", sdp->sd_table_name);
 
@@ -1192,7 +1198,7 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_FREEZABLE, 0,
 			sdp->sd_fsname);
 	if (!sdp->sd_glock_wq)
-		goto fail_free;
+		goto fail_iput;
 
 	sdp->sd_delete_wq = alloc_workqueue("gfs2-delete/%s",
 			WQ_MEM_RECLAIM | WQ_FREEZABLE, 0, sdp->sd_fsname);
@@ -1309,9 +1315,10 @@ fail_delete_wq:
 fail_glock_wq:
 	if (sdp->sd_glock_wq)
 		destroy_workqueue(sdp->sd_glock_wq);
+fail_iput:
+	iput(sdp->sd_inode);
 fail_free:
 	free_sbd(sdp);
-	sb->s_fs_info = NULL;
 	return error;
 }
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 44e5658b896c..0bd7827e6371 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -648,7 +648,7 @@ restart:
 	gfs2_jindex_free(sdp);
 	/*  Take apart glock structures and buffer lists  */
 	gfs2_gl_hash_clear(sdp);
-	truncate_inode_pages_final(&sdp->sd_aspace);
+	iput(sdp->sd_inode);
 	gfs2_delete_debugfs_file(sdp);
 
 	gfs2_sys_fs_del(sdp);
@@ -674,7 +674,7 @@ static int gfs2_sync_fs(struct super_block *sb, int wait)
 	return sdp->sd_log_error;
 }
 
-static int gfs2_do_thaw(struct gfs2_sbd *sdp)
+static int gfs2_do_thaw(struct gfs2_sbd *sdp, enum freeze_holder who)
 {
 	struct super_block *sb = sdp->sd_vfs;
 	int error;
@@ -682,7 +682,7 @@ static int gfs2_do_thaw(struct gfs2_sbd *sdp)
 	error = gfs2_freeze_lock_shared(sdp);
 	if (error)
 		goto fail;
-	error = thaw_super(sb, FREEZE_HOLDER_USERSPACE);
+	error = thaw_super(sb, who);
 	if (!error)
 		return 0;
 
@@ -710,7 +710,7 @@ void gfs2_freeze_func(struct work_struct *work)
 	gfs2_freeze_unlock(sdp);
 	set_bit(SDF_FROZEN, &sdp->sd_flags);
 
-	error = gfs2_do_thaw(sdp);
+	error = gfs2_do_thaw(sdp, FREEZE_HOLDER_USERSPACE);
 	if (error)
 		goto out;
 
@@ -728,6 +728,7 @@ out:
 /**
  * gfs2_freeze_super - prevent further writes to the filesystem
  * @sb: the VFS structure for the filesystem
+ * @who: freeze flags
  *
  */
 
@@ -744,7 +745,7 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who)
 	}
 
 	for (;;) {
-		error = freeze_super(sb, FREEZE_HOLDER_USERSPACE);
+		error = freeze_super(sb, who);
 		if (error) {
 			fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n",
 				error);
@@ -758,7 +759,7 @@ static int gfs2_freeze_super(struct super_block *sb, enum freeze_holder who)
 			break;
 		}
 
-		error = gfs2_do_thaw(sdp);
+		error = gfs2_do_thaw(sdp, who);
 		if (error)
 			goto out;
 
@@ -796,6 +797,7 @@ static int gfs2_freeze_fs(struct super_block *sb)
 /**
  * gfs2_thaw_super - reallow writes to the filesystem
  * @sb: the VFS structure for the filesystem
+ * @who: freeze flags
  *
  */
 
@@ -814,7 +816,7 @@ static int gfs2_thaw_super(struct super_block *sb, enum freeze_holder who)
 	atomic_inc(&sb->s_active);
 	gfs2_freeze_unlock(sdp);
 
-	error = gfs2_do_thaw(sdp);
+	error = gfs2_do_thaw(sdp, who);
 
 	if (!error) {
 		clear_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags);
@@ -1173,74 +1175,6 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root)
 	return 0;
 }
 
-static void gfs2_final_release_pages(struct gfs2_inode *ip)
-{
-	struct inode *inode = &ip->i_inode;
-	struct gfs2_glock *gl = ip->i_gl;
-
-	if (unlikely(!gl)) {
-		/* This can only happen during incomplete inode creation. */
-		BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags));
-		return;
-	}
-
-	truncate_inode_pages(gfs2_glock2aspace(gl), 0);
-	truncate_inode_pages(&inode->i_data, 0);
-
-	if (atomic_read(&gl->gl_revokes) == 0) {
-		clear_bit(GLF_LFLUSH, &gl->gl_flags);
-		clear_bit(GLF_DIRTY, &gl->gl_flags);
-	}
-}
-
-static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_rgrpd *rgd;
-	struct gfs2_holder gh;
-	int error;
-
-	if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
-		gfs2_consist_inode(ip);
-		return -EIO;
-	}
-
-	gfs2_rindex_update(sdp);
-
-	error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
-	if (error)
-		return error;
-
-	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr, 1);
-	if (!rgd) {
-		gfs2_consist_inode(ip);
-		error = -EIO;
-		goto out_qs;
-	}
-
-	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
-				   LM_FLAG_NODE_SCOPE, &gh);
-	if (error)
-		goto out_qs;
-
-	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
-				 sdp->sd_jdesc->jd_blocks);
-	if (error)
-		goto out_rg_gunlock;
-
-	gfs2_free_di(rgd, ip);
-
-	gfs2_final_release_pages(ip);
-
-	gfs2_trans_end(sdp);
-
-out_rg_gunlock:
-	gfs2_glock_dq_uninit(&gh);
-out_qs:
-	gfs2_quota_unhold(ip);
-	return error;
-}
-
 /**
  * gfs2_glock_put_eventually
  * @gl:	The glock to put
@@ -1326,9 +1260,6 @@ static enum evict_behavior evict_should_delete(struct inode *inode,
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	int ret;
 
-	if (unlikely(test_bit(GIF_ALLOC_FAILED, &ip->i_flags)))
-		goto should_delete;
-
 	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
 	    test_bit(GLF_DEFER_DELETE, &ip->i_iopen_gh.gh_gl->gl_flags))
 		return EVICT_SHOULD_DEFER_DELETE;
@@ -1358,7 +1289,6 @@ static enum evict_behavior evict_should_delete(struct inode *inode,
 	if (inode->i_nlink)
 		return EVICT_SHOULD_SKIP_DELETE;
 
-should_delete:
 	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
 	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
 		return gfs2_upgrade_iopen_glock(inode);
@@ -1382,7 +1312,7 @@ static int evict_unlinked_inode(struct inode *inode)
 	}
 
 	if (ip->i_eattr) {
-		ret = gfs2_ea_dealloc(ip);
+		ret = gfs2_ea_dealloc(ip, true);
 		if (ret)
 			goto out;
 	}
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index ecc699f8d9fc..628618302102 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -764,7 +764,6 @@ fail_reg:
 	fs_err(sdp, "error %d adding sysfs files\n", error);
 	kobject_put(&sdp->sd_kobj);
 	wait_for_completion(&sdp->sd_kobj_unregister);
-	sb->s_fs_info = NULL;
 	return error;
 }
 
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index f8ae2c666fd6..075f7e9abe47 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -226,6 +226,27 @@ out:
 	unlock_buffer(bh);
 }
 
+void gfs2_trans_add_databufs(struct gfs2_glock *gl, struct folio *folio,
+			     size_t from, size_t len)
+{
+	struct buffer_head *head = folio_buffers(folio);
+	unsigned int bsize = head->b_size;
+	struct buffer_head *bh;
+	size_t to = from + len;
+	size_t start, end;
+
+	for (bh = head, start = 0; bh != head || !start;
+	     bh = bh->b_this_page, start = end) {
+		end = start + bsize;
+		if (end <= from)
+			continue;
+		if (start >= to)
+			break;
+		set_buffer_uptodate(bh);
+		gfs2_trans_add_data(gl, bh);
+	}
+}
+
 void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 {
 
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index f8ce5302280d..790c55f59e61 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -42,6 +42,8 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 
 void gfs2_trans_end(struct gfs2_sbd *sdp);
 void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh);
+void gfs2_trans_add_databufs(struct gfs2_glock *gl, struct folio *folio,
+			     size_t from, size_t len);
 void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh);
 void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
 void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len);
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 17ae5070a90e..df9c93de94c7 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1383,7 +1383,7 @@ out:
 	return error;
 }
 
-static int ea_dealloc_block(struct gfs2_inode *ip)
+static int ea_dealloc_block(struct gfs2_inode *ip, bool initialized)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *rgd;
@@ -1416,7 +1416,7 @@ static int ea_dealloc_block(struct gfs2_inode *ip)
 	ip->i_eattr = 0;
 	gfs2_add_inode_blocks(&ip->i_inode, -1);
 
-	if (likely(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags))) {
+	if (initialized) {
 		error = gfs2_meta_inode_buffer(ip, &dibh);
 		if (!error) {
 			gfs2_trans_add_meta(ip->i_gl, dibh);
@@ -1435,11 +1435,12 @@ out_gunlock:
 /**
  * gfs2_ea_dealloc - deallocate the extended attribute fork
  * @ip: the inode
+ * @initialized: xattrs have been initialized
  *
  * Returns: errno
  */
 
-int gfs2_ea_dealloc(struct gfs2_inode *ip)
+int gfs2_ea_dealloc(struct gfs2_inode *ip, bool initialized)
 {
 	int error;
 
@@ -1451,7 +1452,7 @@ int gfs2_ea_dealloc(struct gfs2_inode *ip)
 	if (error)
 		return error;
 
-	if (likely(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags))) {
+	if (initialized) {
 		error = ea_foreach(ip, ea_dealloc_unstuffed, NULL);
 		if (error)
 			goto out_quota;
@@ -1463,7 +1464,7 @@ int gfs2_ea_dealloc(struct gfs2_inode *ip)
 		}
 	}
 
-	error = ea_dealloc_block(ip);
+	error = ea_dealloc_block(ip, initialized);
 
 out_quota:
 	gfs2_quota_unhold(ip);
diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h
index eb12eb7e37c1..3c9788e0e137 100644
--- a/fs/gfs2/xattr.h
+++ b/fs/gfs2/xattr.h
@@ -54,7 +54,7 @@ int __gfs2_xattr_set(struct inode *inode, const char *name,
 		     const void *value, size_t size,
 		     int flags, int type);
 ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size);
-int gfs2_ea_dealloc(struct gfs2_inode *ip);
+int gfs2_ea_dealloc(struct gfs2_inode *ip, bool initialized);
 
 /* Exported to acl.c */
 
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 5b08bd417b28..0ac474888a02 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1675,6 +1675,8 @@ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
 		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
 	if (wpc->iomap.flags & IOMAP_F_SHARED)
 		ioend_flags |= IOMAP_IOEND_SHARED;
+	if (folio_test_dropbehind(folio))
+		ioend_flags |= IOMAP_IOEND_DONTCACHE;
 	if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
 		ioend_flags |= IOMAP_IOEND_BOUNDARY;
 
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index fc70d72c3fe8..43487fa83eae 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -1580,8 +1580,9 @@ void kernfs_break_active_protection(struct kernfs_node *kn)
  * invoked before finishing the kernfs operation.  Note that while this
  * function restores the active reference, it doesn't and can't actually
  * restore the active protection - @kn may already or be in the process of
- * being removed.  Once kernfs_break_active_protection() is invoked, that
- * protection is irreversibly gone for the kernfs operation instance.
+ * being drained and removed.  Once kernfs_break_active_protection() is
+ * invoked, that protection is irreversibly gone for the kernfs operation
+ * instance.
  *
  * While this function may be called at any point after
  * kernfs_break_active_protection() is invoked, its most useful location
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 66fe8fe41f06..a6c692cac616 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -778,8 +778,9 @@ bool kernfs_should_drain_open_files(struct kernfs_node *kn)
 	/*
 	 * @kn being deactivated guarantees that @kn->attr.open can't change
 	 * beneath us making the lockless test below safe.
+	 * Callers post kernfs_unbreak_active_protection may be counted in
+	 * kn->active by now, do not WARN_ON because of them.
 	 */
-	WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
 
 	rcu_read_lock();
 	on = rcu_dereference(kn->attr.open);
diff --git a/fs/mount.h b/fs/mount.h
index 7aecf2a60472..ad7173037924 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -7,10 +7,6 @@
 
 extern struct list_head notify_list;
 
-typedef __u32 __bitwise mntns_flags_t;
-
-#define MNTNS_PROPAGATING	((__force mntns_flags_t)(1 << 0))
-
 struct mnt_namespace {
 	struct ns_common	ns;
 	struct mount *	root;
@@ -37,7 +33,6 @@ struct mnt_namespace {
 	struct rb_node		mnt_ns_tree_node; /* node in the mnt_ns_tree */
 	struct list_head	mnt_ns_list; /* entry in the sequential list of mounts namespace */
 	refcount_t		passive; /* number references not pinning @mounts */
-	mntns_flags_t		mntns_flags;
 } __randomize_layout;
 
 struct mnt_pcp {
diff --git a/fs/namespace.c b/fs/namespace.c
index 1b466c54a357..d6ac7e533b02 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2424,7 +2424,7 @@ void drop_collected_mounts(struct vfsmount *mnt)
 	namespace_unlock();
 }
 
-bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
 {
 	struct mount *child;
 
@@ -2438,6 +2438,16 @@ bool has_locked_children(struct mount *mnt, struct dentry *dentry)
 	return false;
 }
 
+bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+{
+	bool res;
+
+	read_seqlock_excl(&mount_lock);
+	res = __has_locked_children(mnt, dentry);
+	read_sequnlock_excl(&mount_lock);
+	return res;
+}
+
 /*
  * Check that there aren't references to earlier/same mount namespaces in the
  * specified subtree.  Such references can act as pins for mount namespaces
@@ -2482,23 +2492,27 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	if (IS_MNT_UNBINDABLE(old_mnt))
 		return ERR_PTR(-EINVAL);
 
-	if (mnt_has_parent(old_mnt)) {
-		if (!check_mnt(old_mnt))
-			return ERR_PTR(-EINVAL);
-	} else {
-		if (!is_mounted(&old_mnt->mnt))
-			return ERR_PTR(-EINVAL);
-
-		/* Make sure this isn't something purely kernel internal. */
-		if (!is_anon_ns(old_mnt->mnt_ns))
+	/*
+	 * Make sure the source mount is acceptable.
+	 * Anything mounted in our mount namespace is allowed.
+	 * Otherwise, it must be the root of an anonymous mount
+	 * namespace, and we need to make sure no namespace
+	 * loops get created.
+	 */
+	if (!check_mnt(old_mnt)) {
+		if (!is_mounted(&old_mnt->mnt) ||
+			!is_anon_ns(old_mnt->mnt_ns) ||
+			mnt_has_parent(old_mnt))
 			return ERR_PTR(-EINVAL);
 
-		/* Make sure we don't create mount namespace loops. */
 		if (!check_for_nsfs_mounts(old_mnt))
 			return ERR_PTR(-EINVAL);
 	}
 
-	if (has_locked_children(old_mnt, path->dentry))
+        if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	if (__has_locked_children(old_mnt, path->dentry))
 		return ERR_PTR(-EINVAL);
 
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
@@ -2944,6 +2958,10 @@ static int do_change_type(struct path *path, int ms_flags)
 		return -EINVAL;
 
 	namespace_lock();
+	if (!check_mnt(mnt)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (type == MS_SHARED) {
 		err = invent_group_ids(mnt, recurse);
 		if (err)
@@ -3035,7 +3053,7 @@ static struct mount *__do_loopback(struct path *old_path, int recurse)
 	if (!may_copy_tree(old_path))
 		return mnt;
 
-	if (!recurse && has_locked_children(old, old_path->dentry))
+	if (!recurse && __has_locked_children(old, old_path->dentry))
 		return mnt;
 
 	if (recurse)
@@ -3428,7 +3446,7 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 		goto out;
 
 	/* From mount should not have locked children in place of To's root */
-	if (has_locked_children(from, to->mnt.mnt_root))
+	if (__has_locked_children(from, to->mnt.mnt_root))
 		goto out;
 
 	/* Setting sharing groups is only allowed on private mounts */
@@ -3442,7 +3460,7 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 	if (IS_MNT_SLAVE(from)) {
 		struct mount *m = from->mnt_master;
 
-		list_add(&to->mnt_slave, &m->mnt_slave_list);
+		list_add(&to->mnt_slave, &from->mnt_slave);
 		to->mnt_master = m;
 	}
 
@@ -3467,18 +3485,25 @@ out:
  * Check if path is overmounted, i.e., if there's a mount on top of
  * @path->mnt with @path->dentry as mountpoint.
  *
- * Context: This function expects namespace_lock() to be held.
+ * Context: namespace_sem must be held at least shared.
+ * MUST NOT be called under lock_mount_hash() (there one should just
+ * call __lookup_mnt() and check if it returns NULL).
  * Return: If path is overmounted true is returned, false if not.
  */
 static inline bool path_overmounted(const struct path *path)
 {
+	unsigned seq = read_seqbegin(&mount_lock);
+	bool no_child;
+
 	rcu_read_lock();
-	if (unlikely(__lookup_mnt(path->mnt, path->dentry))) {
-		rcu_read_unlock();
-		return true;
-	}
+	no_child = !__lookup_mnt(path->mnt, path->dentry);
 	rcu_read_unlock();
-	return false;
+	if (need_seqretry(&mount_lock, seq)) {
+		read_seqlock_excl(&mount_lock);
+		no_child = !__lookup_mnt(path->mnt, path->dentry);
+		read_sequnlock_excl(&mount_lock);
+	}
+	return unlikely(!no_child);
 }
 
 /**
@@ -3637,46 +3662,41 @@ static int do_move_mount(struct path *old_path,
 	ns = old->mnt_ns;
 
 	err = -EINVAL;
-	if (!may_use_mount(p))
-		goto out;
-
 	/* The thing moved must be mounted... */
 	if (!is_mounted(&old->mnt))
 		goto out;
 
-	/* ... and either ours or the root of anon namespace */
-	if (!(attached ? check_mnt(old) : is_anon_ns(ns)))
-		goto out;
-
-	if (is_anon_ns(ns)) {
+	if (check_mnt(old)) {
+		/* if the source is in our namespace... */
+		/* ... it should be detachable from parent */
+		if (!mnt_has_parent(old) || IS_MNT_LOCKED(old))
+			goto out;
+		/* ... and the target should be in our namespace */
+		if (!check_mnt(p))
+			goto out;
+	} else {
 		/*
-		 * Ending up with two files referring to the root of the
-		 * same anonymous mount namespace would cause an error
-		 * as this would mean trying to move the same mount
-		 * twice into the mount tree which would be rejected
-		 * later. But be explicit about it right here.
+		 * otherwise the source must be the root of some anon namespace.
+		 * AV: check for mount being root of an anon namespace is worth
+		 * an inlined predicate...
 		 */
-		if ((is_anon_ns(p->mnt_ns) && ns == p->mnt_ns))
+		if (!is_anon_ns(ns) || mnt_has_parent(old))
 			goto out;
-
 		/*
-		 * If this is an anonymous mount tree ensure that mount
-		 * propagation can detect mounts that were just
-		 * propagated to the target mount tree so we don't
-		 * propagate onto them.
+		 * Bail out early if the target is within the same namespace -
+		 * subsequent checks would've rejected that, but they lose
+		 * some corner cases if we check it early.
 		 */
-		ns->mntns_flags |= MNTNS_PROPAGATING;
-	} else if (is_anon_ns(p->mnt_ns)) {
+		if (ns == p->mnt_ns)
+			goto out;
 		/*
-		 * Don't allow moving an attached mount tree to an
-		 * anonymous mount tree.
+		 * Target should be either in our namespace or in an acceptable
+		 * anon namespace, sensu check_anonymous_mnt().
 		 */
-		goto out;
+		if (!may_use_mount(p))
+			goto out;
 	}
 
-	if (old->mnt.mnt_flags & MNT_LOCKED)
-		goto out;
-
 	if (!path_mounted(old_path))
 		goto out;
 
@@ -3722,8 +3742,6 @@ static int do_move_mount(struct path *old_path,
 	if (attached)
 		put_mountpoint(old_mp);
 out:
-	if (is_anon_ns(ns))
-		ns->mntns_flags &= ~MNTNS_PROPAGATING;
 	unlock_mount(mp);
 	if (!err) {
 		if (attached) {
diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 0d1b6d35ff3b..fd4619275801 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -262,9 +262,9 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
 				if (ret < 0) {
 					subreq->error = ret;
 					/* Not queued - release both refs. */
-					netfs_put_subrequest(subreq, false,
+					netfs_put_subrequest(subreq,
 							     netfs_sreq_trace_put_cancel);
-					netfs_put_subrequest(subreq, false,
+					netfs_put_subrequest(subreq,
 							     netfs_sreq_trace_put_cancel);
 					break;
 				}
@@ -297,8 +297,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
 			subreq->error = ret;
 			trace_netfs_sreq(subreq, netfs_sreq_trace_cancel);
 			/* Not queued - release both refs. */
-			netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel);
-			netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel);
+			netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
+			netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
 			break;
 		}
 		size -= slice;
@@ -312,7 +312,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq)
 	if (unlikely(size > 0)) {
 		smp_wmb(); /* Write lists before ALL_QUEUED. */
 		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
-		netfs_wake_read_collector(rreq);
+		netfs_wake_collector(rreq);
 	}
 
 	/* Defer error return as we may need to wait for outstanding I/O. */
@@ -365,12 +365,10 @@ void netfs_readahead(struct readahead_control *ractl)
 		goto cleanup_free;
 	netfs_read_to_pagecache(rreq);
 
-	netfs_put_request(rreq, true, netfs_rreq_trace_put_return);
-	return;
+	return netfs_put_request(rreq, netfs_rreq_trace_put_return);
 
 cleanup_free:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_failed);
-	return;
+	return netfs_put_request(rreq, netfs_rreq_trace_put_failed);
 }
 EXPORT_SYMBOL(netfs_readahead);
 
@@ -470,11 +468,11 @@ static int netfs_read_gaps(struct file *file, struct folio *folio)
 		folio_mark_uptodate(folio);
 	}
 	folio_unlock(folio);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
 
 discard:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+	netfs_put_request(rreq, netfs_rreq_trace_put_discard);
 alloc_error:
 	folio_unlock(folio);
 	return ret;
@@ -530,11 +528,11 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 
 	netfs_read_to_pagecache(rreq);
 	ret = netfs_wait_for_read(rreq);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
 
 discard:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+	netfs_put_request(rreq, netfs_rreq_trace_put_discard);
 alloc_error:
 	folio_unlock(folio);
 	return ret;
@@ -689,7 +687,7 @@ retry:
 	ret = netfs_wait_for_read(rreq);
 	if (ret < 0)
 		goto error;
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 
 have_folio:
 	ret = folio_wait_private_2_killable(folio);
@@ -701,7 +699,7 @@ have_folio_no_wait:
 	return 0;
 
 error_put:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_failed);
+	netfs_put_request(rreq, netfs_rreq_trace_put_failed);
 error:
 	if (folio) {
 		folio_unlock(folio);
@@ -752,11 +750,11 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 
 	netfs_read_to_pagecache(rreq);
 	ret = netfs_wait_for_read(rreq);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret < 0 ? ret : 0;
 
 error_put:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
+	netfs_put_request(rreq, netfs_rreq_trace_put_discard);
 error:
 	_leave(" = %d", ret);
 	return ret;
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index b4826360a411..dbb544e183d1 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -386,7 +386,7 @@ out:
 		wbc_detach_inode(&wbc);
 		if (ret2 == -EIOCBQUEUED)
 			return ret2;
-		if (ret == 0)
+		if (ret == 0 && ret2 < 0)
 			ret = ret2;
 	}
 
diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c
index 5e3f0aeb51f3..9902766195d7 100644
--- a/fs/netfs/direct_read.c
+++ b/fs/netfs/direct_read.c
@@ -85,7 +85,7 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 		if (rreq->netfs_ops->prepare_read) {
 			ret = rreq->netfs_ops->prepare_read(subreq);
 			if (ret < 0) {
-				netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel);
+				netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
 				break;
 			}
 		}
@@ -103,7 +103,7 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 		rreq->netfs_ops->issue_read(subreq);
 
 		if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
-			netfs_wait_for_pause(rreq);
+			netfs_wait_for_paused_read(rreq);
 		if (test_bit(NETFS_RREQ_FAILED, &rreq->flags))
 			break;
 		if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
@@ -115,7 +115,7 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq)
 	if (unlikely(size > 0)) {
 		smp_wmb(); /* Write lists before ALL_QUEUED. */
 		set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
-		netfs_wake_read_collector(rreq);
+		netfs_wake_collector(rreq);
 	}
 
 	return ret;
@@ -144,7 +144,7 @@ static ssize_t netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync)
 	ret = netfs_dispatch_unbuffered_reads(rreq);
 
 	if (!rreq->submitted) {
-		netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit);
+		netfs_put_request(rreq, netfs_rreq_trace_put_no_submit);
 		inode_dio_end(rreq->inode);
 		ret = 0;
 		goto out;
@@ -188,7 +188,8 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i
 
 	rreq = netfs_alloc_request(iocb->ki_filp->f_mapping, iocb->ki_filp,
 				   iocb->ki_pos, orig_count,
-				   NETFS_DIO_READ);
+				   iocb->ki_flags & IOCB_DIRECT ?
+				   NETFS_DIO_READ : NETFS_UNBUFFERED_READ);
 	if (IS_ERR(rreq))
 		return PTR_ERR(rreq);
 
@@ -236,7 +237,7 @@ ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *i
 	}
 
 out:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	if (ret > 0)
 		orig_count -= ret;
 	return ret;
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 42ce53cc216e..fa9a5bf3c6d5 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -87,6 +87,8 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	}
 
 	__set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags);
+	if (async)
+		__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
 
 	/* Copy the data into the bounce buffer and encrypt it. */
 	// TODO
@@ -105,19 +107,15 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 
 	if (!async) {
 		trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip);
-		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS,
-			    TASK_UNINTERRUPTIBLE);
-		ret = wreq->error;
-		if (ret == 0) {
-			ret = wreq->transferred;
+		ret = netfs_wait_for_write(wreq);
+		if (ret > 0)
 			iocb->ki_pos += ret;
-		}
 	} else {
 		ret = -EIOCBQUEUED;
 	}
 
 out:
-	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	return ret;
 }
 EXPORT_SYMBOL(netfs_unbuffered_write_iter_locked);
diff --git a/fs/netfs/fscache_io.c b/fs/netfs/fscache_io.c
index b1722a82c03d..e4308457633c 100644
--- a/fs/netfs/fscache_io.c
+++ b/fs/netfs/fscache_io.c
@@ -192,8 +192,7 @@ EXPORT_SYMBOL(__fscache_clear_page_bits);
 /*
  * Deal with the completion of writing the data to the cache.
  */
-static void fscache_wreq_done(void *priv, ssize_t transferred_or_error,
-			      bool was_async)
+static void fscache_wreq_done(void *priv, ssize_t transferred_or_error)
 {
 	struct fscache_write_request *wreq = priv;
 
@@ -202,8 +201,7 @@ static void fscache_wreq_done(void *priv, ssize_t transferred_or_error,
 					wreq->set_bits);
 
 	if (wreq->term_func)
-		wreq->term_func(wreq->term_func_priv, transferred_or_error,
-				was_async);
+		wreq->term_func(wreq->term_func_priv, transferred_or_error);
 	fscache_end_operation(&wreq->cache_resources);
 	kfree(wreq);
 }
@@ -255,14 +253,14 @@ void __fscache_write_to_cache(struct fscache_cookie *cookie,
 	return;
 
 abandon_end:
-	return fscache_wreq_done(wreq, ret, false);
+	return fscache_wreq_done(wreq, ret);
 abandon_free:
 	kfree(wreq);
 abandon:
 	if (using_pgpriv2)
 		fscache_clear_page_bits(mapping, start, len, cond);
 	if (term_func)
-		term_func(term_func_priv, ret, false);
+		term_func(term_func_priv, ret);
 }
 EXPORT_SYMBOL(__fscache_write_to_cache);
 
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 1c4f953c3d68..e2ee9183392b 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -23,7 +23,7 @@
 /*
  * buffered_read.c
  */
-void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async);
+void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error);
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len);
 
@@ -62,6 +62,14 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
 struct folio_queue *netfs_buffer_make_space(struct netfs_io_request *rreq,
 					    enum netfs_folioq_trace trace);
 void netfs_reset_iter(struct netfs_io_subrequest *subreq);
+void netfs_wake_collector(struct netfs_io_request *rreq);
+void netfs_subreq_clear_in_progress(struct netfs_io_subrequest *subreq);
+void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
+				       struct netfs_io_stream *stream);
+ssize_t netfs_wait_for_read(struct netfs_io_request *rreq);
+ssize_t netfs_wait_for_write(struct netfs_io_request *rreq);
+void netfs_wait_for_paused_read(struct netfs_io_request *rreq);
+void netfs_wait_for_paused_write(struct netfs_io_request *rreq);
 
 /*
  * objects.c
@@ -71,9 +79,8 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 					     loff_t start, size_t len,
 					     enum netfs_io_origin origin);
 void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what);
-void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async);
-void netfs_put_request(struct netfs_io_request *rreq, bool was_async,
-		       enum netfs_rreq_ref_trace what);
+void netfs_clear_subrequests(struct netfs_io_request *rreq);
+void netfs_put_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what);
 struct netfs_io_subrequest *netfs_alloc_subrequest(struct netfs_io_request *rreq);
 
 static inline void netfs_see_request(struct netfs_io_request *rreq,
@@ -92,11 +99,9 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq,
 /*
  * read_collect.c
  */
+bool netfs_read_collection(struct netfs_io_request *rreq);
 void netfs_read_collection_worker(struct work_struct *work);
-void netfs_wake_read_collector(struct netfs_io_request *rreq);
-void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async);
-ssize_t netfs_wait_for_read(struct netfs_io_request *rreq);
-void netfs_wait_for_pause(struct netfs_io_request *rreq);
+void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error);
 
 /*
  * read_pgpriv2.c
@@ -176,8 +181,8 @@ static inline void netfs_stat_d(atomic_t *stat)
  * write_collect.c
  */
 int netfs_folio_written_back(struct folio *folio);
+bool netfs_write_collection(struct netfs_io_request *wreq);
 void netfs_write_collection_worker(struct work_struct *work);
-void netfs_wake_write_collector(struct netfs_io_request *wreq, bool was_async);
 
 /*
  * write_issue.c
@@ -198,8 +203,8 @@ struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len
 int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
 			       struct folio *folio, size_t copied, bool to_page_end,
 			       struct folio **writethrough_cache);
-int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
-			   struct folio *writethrough_cache);
+ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
+			       struct folio *writethrough_cache);
 int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len);
 
 /*
@@ -255,6 +260,21 @@ static inline void netfs_put_group_many(struct netfs_group *netfs_group, int nr)
 }
 
 /*
+ * Clear and wake up a NETFS_RREQ_* flag bit on a request.
+ */
+static inline void netfs_wake_rreq_flag(struct netfs_io_request *rreq,
+					unsigned int rreq_flag,
+					enum netfs_rreq_trace trace)
+{
+	if (test_bit(rreq_flag, &rreq->flags)) {
+		trace_netfs_rreq(rreq, trace);
+		clear_bit_unlock(rreq_flag, &rreq->flags);
+		smp_mb__after_atomic(); /* Set flag before task state */
+		wake_up(&rreq->waitq);
+	}
+}
+
+/*
  * fscache-cache.c
  */
 #ifdef CONFIG_PROC_FS
diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 70ecc8f5f210..3db401d269e7 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -39,6 +39,7 @@ static const char *netfs_origins[nr__netfs_io_origin] = {
 	[NETFS_READ_GAPS]		= "RG",
 	[NETFS_READ_SINGLE]		= "R1",
 	[NETFS_READ_FOR_WRITE]		= "RW",
+	[NETFS_UNBUFFERED_READ]		= "UR",
 	[NETFS_DIO_READ]		= "DR",
 	[NETFS_WRITEBACK]		= "WB",
 	[NETFS_WRITEBACK_SINGLE]	= "W1",
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 7099aa07737a..43b67a28a8fa 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -313,3 +313,222 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp)
 	return true;
 }
 EXPORT_SYMBOL(netfs_release_folio);
+
+/*
+ * Wake the collection work item.
+ */
+void netfs_wake_collector(struct netfs_io_request *rreq)
+{
+	if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags) &&
+	    !test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) {
+		queue_work(system_unbound_wq, &rreq->work);
+	} else {
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wake_queue);
+		wake_up(&rreq->waitq);
+	}
+}
+
+/*
+ * Mark a subrequest as no longer being in progress and, if need be, wake the
+ * collector.
+ */
+void netfs_subreq_clear_in_progress(struct netfs_io_subrequest *subreq)
+{
+	struct netfs_io_request *rreq = subreq->rreq;
+	struct netfs_io_stream *stream = &rreq->io_streams[subreq->stream_nr];
+
+	clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+	smp_mb__after_atomic(); /* Clear IN_PROGRESS before task state */
+
+	/* If we are at the head of the queue, wake up the collector. */
+	if (list_is_first(&subreq->rreq_link, &stream->subrequests) ||
+	    test_bit(NETFS_RREQ_RETRYING, &rreq->flags))
+		netfs_wake_collector(rreq);
+}
+
+/*
+ * Wait for all outstanding I/O in a stream to quiesce.
+ */
+void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
+				       struct netfs_io_stream *stream)
+{
+	struct netfs_io_subrequest *subreq;
+	DEFINE_WAIT(myself);
+
+	list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
+		if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
+			continue;
+
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
+		for (;;) {
+			prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
+
+			if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
+				break;
+
+			trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for);
+			schedule();
+			trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
+		}
+	}
+
+	finish_wait(&rreq->waitq, &myself);
+}
+
+/*
+ * Perform collection in app thread if not offloaded to workqueue.
+ */
+static int netfs_collect_in_app(struct netfs_io_request *rreq,
+				bool (*collector)(struct netfs_io_request *rreq))
+{
+	bool need_collect = false, inactive = true;
+
+	for (int i = 0; i < NR_IO_STREAMS; i++) {
+		struct netfs_io_subrequest *subreq;
+		struct netfs_io_stream *stream = &rreq->io_streams[i];
+
+		if (!stream->active)
+			continue;
+		inactive = false;
+		trace_netfs_collect_stream(rreq, stream);
+		subreq = list_first_entry_or_null(&stream->subrequests,
+						  struct netfs_io_subrequest,
+						  rreq_link);
+		if (subreq &&
+		    (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) ||
+		     test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) {
+			need_collect = true;
+			break;
+		}
+	}
+
+	if (!need_collect && !inactive)
+		return 0; /* Sleep */
+
+	__set_current_state(TASK_RUNNING);
+	if (collector(rreq)) {
+		/* Drop the ref from the NETFS_RREQ_IN_PROGRESS flag. */
+		netfs_put_request(rreq, netfs_rreq_trace_put_work_ip);
+		return 1; /* Done */
+	}
+
+	if (inactive) {
+		WARN(true, "Failed to collect inactive req R=%08x\n",
+		     rreq->debug_id);
+		cond_resched();
+	}
+	return 2; /* Again */
+}
+
+/*
+ * Wait for a request to complete, successfully or otherwise.
+ */
+static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq,
+				      bool (*collector)(struct netfs_io_request *rreq))
+{
+	DEFINE_WAIT(myself);
+	ssize_t ret;
+
+	for (;;) {
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
+		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
+
+		if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) {
+			switch (netfs_collect_in_app(rreq, collector)) {
+			case 0:
+				break;
+			case 1:
+				goto all_collected;
+			case 2:
+				continue;
+			}
+		}
+
+		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
+			break;
+
+		schedule();
+		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
+	}
+
+all_collected:
+	finish_wait(&rreq->waitq, &myself);
+
+	ret = rreq->error;
+	if (ret == 0) {
+		ret = rreq->transferred;
+		switch (rreq->origin) {
+		case NETFS_DIO_READ:
+		case NETFS_DIO_WRITE:
+		case NETFS_READ_SINGLE:
+		case NETFS_UNBUFFERED_READ:
+		case NETFS_UNBUFFERED_WRITE:
+			break;
+		default:
+			if (rreq->submitted < rreq->len) {
+				trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
+				ret = -EIO;
+			}
+			break;
+		}
+	}
+
+	return ret;
+}
+
+ssize_t netfs_wait_for_read(struct netfs_io_request *rreq)
+{
+	return netfs_wait_for_request(rreq, netfs_read_collection);
+}
+
+ssize_t netfs_wait_for_write(struct netfs_io_request *rreq)
+{
+	return netfs_wait_for_request(rreq, netfs_write_collection);
+}
+
+/*
+ * Wait for a paused operation to unpause or complete in some manner.
+ */
+static void netfs_wait_for_pause(struct netfs_io_request *rreq,
+				 bool (*collector)(struct netfs_io_request *rreq))
+{
+	DEFINE_WAIT(myself);
+
+	trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause);
+
+	for (;;) {
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
+		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
+
+		if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) {
+			switch (netfs_collect_in_app(rreq, collector)) {
+			case 0:
+				break;
+			case 1:
+				goto all_collected;
+			case 2:
+				continue;
+			}
+		}
+
+		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags) ||
+		    !test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
+			break;
+
+		schedule();
+		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
+	}
+
+all_collected:
+	finish_wait(&rreq->waitq, &myself);
+}
+
+void netfs_wait_for_paused_read(struct netfs_io_request *rreq)
+{
+	return netfs_wait_for_pause(rreq, netfs_read_collection);
+}
+
+void netfs_wait_for_paused_write(struct netfs_io_request *rreq)
+{
+	return netfs_wait_for_pause(rreq, netfs_write_collection);
+}
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index dc6b41ef18b0..31fa0c81e2a4 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -10,6 +10,8 @@
 #include <linux/delay.h>
 #include "internal.h"
 
+static void netfs_free_request(struct work_struct *work);
+
 /*
  * Allocate an I/O request and initialise it.
  */
@@ -34,6 +36,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	}
 
 	memset(rreq, 0, kmem_cache_size(cache));
+	INIT_WORK(&rreq->cleanup_work, netfs_free_request);
 	rreq->start	= start;
 	rreq->len	= len;
 	rreq->origin	= origin;
@@ -49,13 +52,14 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	INIT_LIST_HEAD(&rreq->io_streams[0].subrequests);
 	INIT_LIST_HEAD(&rreq->io_streams[1].subrequests);
 	init_waitqueue_head(&rreq->waitq);
-	refcount_set(&rreq->ref, 1);
+	refcount_set(&rreq->ref, 2);
 
 	if (origin == NETFS_READAHEAD ||
 	    origin == NETFS_READPAGE ||
 	    origin == NETFS_READ_GAPS ||
 	    origin == NETFS_READ_SINGLE ||
 	    origin == NETFS_READ_FOR_WRITE ||
+	    origin == NETFS_UNBUFFERED_READ ||
 	    origin == NETFS_DIO_READ) {
 		INIT_WORK(&rreq->work, netfs_read_collection_worker);
 		rreq->io_streams[0].avail = true;
@@ -63,7 +67,9 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 		INIT_WORK(&rreq->work, netfs_write_collection_worker);
 	}
 
+	/* The IN_PROGRESS flag comes with a ref. */
 	__set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+
 	if (file && file->f_flags & O_NONBLOCK)
 		__set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags);
 	if (rreq->netfs_ops->init_request) {
@@ -75,7 +81,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping,
 	}
 
 	atomic_inc(&ctx->io_count);
-	trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new);
+	trace_netfs_rreq_ref(rreq->debug_id, refcount_read(&rreq->ref), netfs_rreq_trace_new);
 	netfs_proc_add_rreq(rreq);
 	netfs_stat(&netfs_n_rh_rreq);
 	return rreq;
@@ -89,7 +95,7 @@ void netfs_get_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace
 	trace_netfs_rreq_ref(rreq->debug_id, r + 1, what);
 }
 
-void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async)
+void netfs_clear_subrequests(struct netfs_io_request *rreq)
 {
 	struct netfs_io_subrequest *subreq;
 	struct netfs_io_stream *stream;
@@ -101,8 +107,7 @@ void netfs_clear_subrequests(struct netfs_io_request *rreq, bool was_async)
 			subreq = list_first_entry(&stream->subrequests,
 						  struct netfs_io_subrequest, rreq_link);
 			list_del(&subreq->rreq_link);
-			netfs_put_subrequest(subreq, was_async,
-					     netfs_sreq_trace_put_clear);
+			netfs_put_subrequest(subreq, netfs_sreq_trace_put_clear);
 		}
 	}
 }
@@ -118,13 +123,19 @@ static void netfs_free_request_rcu(struct rcu_head *rcu)
 static void netfs_free_request(struct work_struct *work)
 {
 	struct netfs_io_request *rreq =
-		container_of(work, struct netfs_io_request, work);
+		container_of(work, struct netfs_io_request, cleanup_work);
 	struct netfs_inode *ictx = netfs_inode(rreq->inode);
 	unsigned int i;
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_free);
+
+	/* Cancel/flush the result collection worker.  That does not carry a
+	 * ref of its own, so we must wait for it somewhere.
+	 */
+	cancel_work_sync(&rreq->work);
+
 	netfs_proc_del_rreq(rreq);
-	netfs_clear_subrequests(rreq, false);
+	netfs_clear_subrequests(rreq);
 	if (rreq->netfs_ops->free_request)
 		rreq->netfs_ops->free_request(rreq);
 	if (rreq->cache_resources.ops)
@@ -145,8 +156,7 @@ static void netfs_free_request(struct work_struct *work)
 	call_rcu(&rreq->rcu, netfs_free_request_rcu);
 }
 
-void netfs_put_request(struct netfs_io_request *rreq, bool was_async,
-		       enum netfs_rreq_ref_trace what)
+void netfs_put_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace what)
 {
 	unsigned int debug_id;
 	bool dead;
@@ -156,15 +166,8 @@ void netfs_put_request(struct netfs_io_request *rreq, bool was_async,
 		debug_id = rreq->debug_id;
 		dead = __refcount_dec_and_test(&rreq->ref, &r);
 		trace_netfs_rreq_ref(debug_id, r - 1, what);
-		if (dead) {
-			if (was_async) {
-				rreq->work.func = netfs_free_request;
-				if (!queue_work(system_unbound_wq, &rreq->work))
-					WARN_ON(1);
-			} else {
-				netfs_free_request(&rreq->work);
-			}
-		}
+		if (dead)
+			WARN_ON(!queue_work(system_unbound_wq, &rreq->cleanup_work));
 	}
 }
 
@@ -206,8 +209,7 @@ void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			     what);
 }
 
-static void netfs_free_subrequest(struct netfs_io_subrequest *subreq,
-				  bool was_async)
+static void netfs_free_subrequest(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
 
@@ -216,10 +218,10 @@ static void netfs_free_subrequest(struct netfs_io_subrequest *subreq,
 		rreq->netfs_ops->free_subrequest(subreq);
 	mempool_free(subreq, rreq->netfs_ops->subrequest_pool ?: &netfs_subrequest_pool);
 	netfs_stat_d(&netfs_n_rh_sreq);
-	netfs_put_request(rreq, was_async, netfs_rreq_trace_put_subreq);
+	netfs_put_request(rreq, netfs_rreq_trace_put_subreq);
 }
 
-void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async,
+void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what)
 {
 	unsigned int debug_index = subreq->debug_index;
@@ -230,5 +232,5 @@ void netfs_put_subrequest(struct netfs_io_subrequest *subreq, bool was_async,
 	dead = __refcount_dec_and_test(&subreq->ref, &r);
 	trace_netfs_sreq_ref(debug_id, debug_index, r - 1, what);
 	if (dead)
-		netfs_free_subrequest(subreq, was_async);
+		netfs_free_subrequest(subreq);
 }
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index 23c75755ad4e..bad677e58a42 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -280,9 +280,13 @@ reassess:
 			stream->need_retry = true;
 			notes |= NEED_RETRY | MADE_PROGRESS;
 			break;
+		} else if (test_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags)) {
+			notes |= MADE_PROGRESS;
 		} else {
 			if (!stream->failed)
-				stream->transferred = stream->collected_to - rreq->start;
+				stream->transferred += transferred;
+			if (front->transferred < front->len)
+				set_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags);
 			notes |= MADE_PROGRESS;
 		}
 
@@ -297,7 +301,7 @@ reassess:
 						 struct netfs_io_subrequest, rreq_link);
 		stream->front = front;
 		spin_unlock(&rreq->lock);
-		netfs_put_subrequest(remove, false,
+		netfs_put_subrequest(remove,
 				     notes & ABANDON_SREQ ?
 				     netfs_sreq_trace_put_abandon :
 				     netfs_sreq_trace_put_done);
@@ -311,14 +315,8 @@ reassess:
 
 	if (notes & NEED_RETRY)
 		goto need_retry;
-	if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_unpause);
-		clear_bit_unlock(NETFS_RREQ_PAUSE, &rreq->flags);
-		smp_mb__after_atomic(); /* Set PAUSE before task state */
-		wake_up(&rreq->waitq);
-	}
-
 	if (notes & MADE_PROGRESS) {
+		netfs_wake_rreq_flag(rreq, NETFS_RREQ_PAUSE, netfs_rreq_trace_unpause);
 		//cond_resched();
 		goto reassess;
 	}
@@ -342,24 +340,10 @@ need_retry:
  */
 static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
 {
-	struct netfs_io_subrequest *subreq;
-	struct netfs_io_stream *stream = &rreq->io_streams[0];
 	unsigned int i;
 
-	/* Collect unbuffered reads and direct reads, adding up the transfer
-	 * sizes until we find the first short or failed subrequest.
-	 */
-	list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
-		rreq->transferred += subreq->transferred;
-
-		if (subreq->transferred < subreq->len ||
-		    test_bit(NETFS_SREQ_FAILED, &subreq->flags)) {
-			rreq->error = subreq->error;
-			break;
-		}
-	}
-
-	if (rreq->origin == NETFS_DIO_READ) {
+	if (rreq->origin == NETFS_UNBUFFERED_READ ||
+	    rreq->origin == NETFS_DIO_READ) {
 		for (i = 0; i < rreq->direct_bv_count; i++) {
 			flush_dcache_page(rreq->direct_bv[i].bv_page);
 			// TODO: cifs marks pages in the destination buffer
@@ -377,7 +361,8 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
 	}
 	if (rreq->netfs_ops->done)
 		rreq->netfs_ops->done(rreq);
-	if (rreq->origin == NETFS_DIO_READ)
+	if (rreq->origin == NETFS_UNBUFFERED_READ ||
+	    rreq->origin == NETFS_DIO_READ)
 		inode_dio_end(rreq->inode);
 }
 
@@ -410,7 +395,7 @@ static void netfs_rreq_assess_single(struct netfs_io_request *rreq)
  * Note that we're in normal kernel thread context at this point, possibly
  * running on a workqueue.
  */
-static void netfs_read_collection(struct netfs_io_request *rreq)
+bool netfs_read_collection(struct netfs_io_request *rreq)
 {
 	struct netfs_io_stream *stream = &rreq->io_streams[0];
 
@@ -420,11 +405,11 @@ static void netfs_read_collection(struct netfs_io_request *rreq)
 	 * queue is empty.
 	 */
 	if (!test_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags))
-		return;
+		return false;
 	smp_rmb(); /* Read ALL_QUEUED before subreq lists. */
 
 	if (!list_empty(&stream->subrequests))
-		return;
+		return false;
 
 	/* Okay, declare that all I/O is complete. */
 	rreq->transferred = stream->transferred;
@@ -433,6 +418,7 @@ static void netfs_read_collection(struct netfs_io_request *rreq)
 	//netfs_rreq_is_still_valid(rreq);
 
 	switch (rreq->origin) {
+	case NETFS_UNBUFFERED_READ:
 	case NETFS_DIO_READ:
 	case NETFS_READ_GAPS:
 		netfs_rreq_assess_dio(rreq);
@@ -445,14 +431,15 @@ static void netfs_read_collection(struct netfs_io_request *rreq)
 	}
 	task_io_account_read(rreq->transferred);
 
-	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
-	clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+	netfs_wake_rreq_flag(rreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
+	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_done);
-	netfs_clear_subrequests(rreq, false);
+	netfs_clear_subrequests(rreq);
 	netfs_unlock_abandoned_read_pages(rreq);
 	if (unlikely(rreq->copy_to_cache))
 		netfs_pgpriv2_end_copy_to_cache(rreq);
+	return true;
 }
 
 void netfs_read_collection_worker(struct work_struct *work)
@@ -460,26 +447,12 @@ void netfs_read_collection_worker(struct work_struct *work)
 	struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work);
 
 	netfs_see_request(rreq, netfs_rreq_trace_see_work);
-	if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
-		netfs_read_collection(rreq);
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_work);
-}
-
-/*
- * Wake the collection work item.
- */
-void netfs_wake_read_collector(struct netfs_io_request *rreq)
-{
-	if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags) &&
-	    !test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) {
-		if (!work_pending(&rreq->work)) {
-			netfs_get_request(rreq, netfs_rreq_trace_get_work);
-			if (!queue_work(system_unbound_wq, &rreq->work))
-				netfs_put_request(rreq, true, netfs_rreq_trace_put_work_nq);
-		}
-	} else {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wake_queue);
-		wake_up(&rreq->waitq);
+	if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) {
+		if (netfs_read_collection(rreq))
+			/* Drop the ref from the IN_PROGRESS flag. */
+			netfs_put_request(rreq, netfs_rreq_trace_put_work_ip);
+		else
+			netfs_see_request(rreq, netfs_rreq_trace_see_work_complete);
 	}
 }
 
@@ -511,7 +484,7 @@ void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq)
 	    list_is_first(&subreq->rreq_link, &stream->subrequests)
 	    ) {
 		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
-		netfs_wake_read_collector(rreq);
+		netfs_wake_collector(rreq);
 	}
 }
 EXPORT_SYMBOL(netfs_read_subreq_progress);
@@ -535,7 +508,6 @@ EXPORT_SYMBOL(netfs_read_subreq_progress);
 void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *rreq = subreq->rreq;
-	struct netfs_io_stream *stream = &rreq->io_streams[0];
 
 	switch (subreq->source) {
 	case NETFS_READ_FROM_CACHE:
@@ -582,23 +554,15 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq)
 	}
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
-
-	clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-	smp_mb__after_atomic(); /* Clear IN_PROGRESS before task state */
-
-	/* If we are at the head of the queue, wake up the collector. */
-	if (list_is_first(&subreq->rreq_link, &stream->subrequests) ||
-	    test_bit(NETFS_RREQ_RETRYING, &rreq->flags))
-		netfs_wake_read_collector(rreq);
-
-	netfs_put_subrequest(subreq, true, netfs_sreq_trace_put_terminated);
+	netfs_subreq_clear_in_progress(subreq);
+	netfs_put_subrequest(subreq, netfs_sreq_trace_put_terminated);
 }
 EXPORT_SYMBOL(netfs_read_subreq_terminated);
 
 /*
  * Handle termination of a read from the cache.
  */
-void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool was_async)
+void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error)
 {
 	struct netfs_io_subrequest *subreq = priv;
 
@@ -613,94 +577,3 @@ void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error, bool
 	}
 	netfs_read_subreq_terminated(subreq);
 }
-
-/*
- * Wait for the read operation to complete, successfully or otherwise.
- */
-ssize_t netfs_wait_for_read(struct netfs_io_request *rreq)
-{
-	struct netfs_io_subrequest *subreq;
-	struct netfs_io_stream *stream = &rreq->io_streams[0];
-	DEFINE_WAIT(myself);
-	ssize_t ret;
-
-	for (;;) {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
-		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
-
-		subreq = list_first_entry_or_null(&stream->subrequests,
-						  struct netfs_io_subrequest, rreq_link);
-		if (subreq &&
-		    (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) ||
-		     test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) {
-			__set_current_state(TASK_RUNNING);
-			netfs_read_collection(rreq);
-			continue;
-		}
-
-		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
-			break;
-
-		schedule();
-		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
-	}
-
-	finish_wait(&rreq->waitq, &myself);
-
-	ret = rreq->error;
-	if (ret == 0) {
-		ret = rreq->transferred;
-		switch (rreq->origin) {
-		case NETFS_DIO_READ:
-		case NETFS_READ_SINGLE:
-			ret = rreq->transferred;
-			break;
-		default:
-			if (rreq->submitted < rreq->len) {
-				trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
-				ret = -EIO;
-			}
-			break;
-		}
-	}
-
-	return ret;
-}
-
-/*
- * Wait for a paused read operation to unpause or complete in some manner.
- */
-void netfs_wait_for_pause(struct netfs_io_request *rreq)
-{
-	struct netfs_io_subrequest *subreq;
-	struct netfs_io_stream *stream = &rreq->io_streams[0];
-	DEFINE_WAIT(myself);
-
-	trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause);
-
-	for (;;) {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
-		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
-
-		if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) {
-			subreq = list_first_entry_or_null(&stream->subrequests,
-							  struct netfs_io_subrequest, rreq_link);
-			if (subreq &&
-			    (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) ||
-			     test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) {
-				__set_current_state(TASK_RUNNING);
-				netfs_read_collection(rreq);
-				continue;
-			}
-		}
-
-		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags) ||
-		    !test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
-			break;
-
-		schedule();
-		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
-	}
-
-	finish_wait(&rreq->waitq, &myself);
-}
diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c
index cf7727060215..5bbe906a551d 100644
--- a/fs/netfs/read_pgpriv2.c
+++ b/fs/netfs/read_pgpriv2.c
@@ -116,7 +116,7 @@ static struct netfs_io_request *netfs_pgpriv2_begin_copy_to_cache(
 	return creq;
 
 cancel_put:
-	netfs_put_request(creq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(creq, netfs_rreq_trace_put_return);
 cancel:
 	rreq->copy_to_cache = ERR_PTR(-ENOBUFS);
 	clear_bit(NETFS_RREQ_FOLIO_COPY_TO_CACHE, &rreq->flags);
@@ -155,7 +155,7 @@ void netfs_pgpriv2_end_copy_to_cache(struct netfs_io_request *rreq)
 	smp_wmb(); /* Write lists before ALL_QUEUED. */
 	set_bit(NETFS_RREQ_ALL_QUEUED, &creq->flags);
 
-	netfs_put_request(creq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(creq, netfs_rreq_trace_put_return);
 	creq->copy_to_cache = NULL;
 }
 
diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c
index 0f294b26e08c..b99e84a8170a 100644
--- a/fs/netfs/read_retry.c
+++ b/fs/netfs/read_retry.c
@@ -173,7 +173,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq)
 						      &stream->subrequests, rreq_link) {
 				trace_netfs_sreq(subreq, netfs_sreq_trace_superfluous);
 				list_del(&subreq->rreq_link);
-				netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done);
+				netfs_put_subrequest(subreq, netfs_sreq_trace_put_done);
 				if (subreq == to)
 					break;
 			}
@@ -257,35 +257,15 @@ abandon:
  */
 void netfs_retry_reads(struct netfs_io_request *rreq)
 {
-	struct netfs_io_subrequest *subreq;
 	struct netfs_io_stream *stream = &rreq->io_streams[0];
-	DEFINE_WAIT(myself);
 
 	netfs_stat(&netfs_n_rh_retry_read_req);
 
-	set_bit(NETFS_RREQ_RETRYING, &rreq->flags);
-
 	/* Wait for all outstanding I/O to quiesce before performing retries as
 	 * we may need to renegotiate the I/O sizes.
 	 */
-	list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
-		if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
-			continue;
-
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
-		for (;;) {
-			prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
-
-			if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
-				break;
-
-			trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for);
-			schedule();
-			trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
-		}
-
-		finish_wait(&rreq->waitq, &myself);
-	}
+	set_bit(NETFS_RREQ_RETRYING, &rreq->flags);
+	netfs_wait_for_in_progress_stream(rreq, stream);
 	clear_bit(NETFS_RREQ_RETRYING, &rreq->flags);
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit);
diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c
index fea0ecdecc53..fa622a6cd56d 100644
--- a/fs/netfs/read_single.c
+++ b/fs/netfs/read_single.c
@@ -142,7 +142,7 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq)
 	set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags);
 	return ret;
 cancel:
-	netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel);
+	netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel);
 	return ret;
 }
 
@@ -185,11 +185,11 @@ ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_ite
 	netfs_single_dispatch_read(rreq);
 
 	ret = netfs_wait_for_read(rreq);
-	netfs_put_request(rreq, true, netfs_rreq_trace_put_return);
+	netfs_put_request(rreq, netfs_rreq_trace_put_return);
 	return ret;
 
 cleanup_free:
-	netfs_put_request(rreq, false, netfs_rreq_trace_put_failed);
+	netfs_put_request(rreq, netfs_rreq_trace_put_failed);
 	return ret;
 }
 EXPORT_SYMBOL(netfs_read_single);
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 3fca59e6475d..0ce7b53e7fe8 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -280,7 +280,7 @@ reassess_streams:
 							 struct netfs_io_subrequest, rreq_link);
 			stream->front = front;
 			spin_unlock(&wreq->lock);
-			netfs_put_subrequest(remove, false,
+			netfs_put_subrequest(remove,
 					     notes & SAW_FAILURE ?
 					     netfs_sreq_trace_put_cancel :
 					     netfs_sreq_trace_put_done);
@@ -321,18 +321,14 @@ reassess_streams:
 
 	if (notes & NEED_RETRY)
 		goto need_retry;
-	if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) {
-		trace_netfs_rreq(wreq, netfs_rreq_trace_unpause);
-		clear_bit_unlock(NETFS_RREQ_PAUSE, &wreq->flags);
-		smp_mb__after_atomic(); /* Set PAUSE before task state */
-		wake_up(&wreq->waitq);
-	}
 
-	if (notes & NEED_REASSESS) {
+	if (notes & MADE_PROGRESS) {
+		netfs_wake_rreq_flag(wreq, NETFS_RREQ_PAUSE, netfs_rreq_trace_unpause);
 		//cond_resched();
 		goto reassess_streams;
 	}
-	if (notes & MADE_PROGRESS) {
+
+	if (notes & NEED_REASSESS) {
 		//cond_resched();
 		goto reassess_streams;
 	}
@@ -356,30 +352,21 @@ need_retry:
 /*
  * Perform the collection of subrequests, folios and encryption buffers.
  */
-void netfs_write_collection_worker(struct work_struct *work)
+bool netfs_write_collection(struct netfs_io_request *wreq)
 {
-	struct netfs_io_request *wreq = container_of(work, struct netfs_io_request, work);
 	struct netfs_inode *ictx = netfs_inode(wreq->inode);
 	size_t transferred;
 	int s;
 
 	_enter("R=%x", wreq->debug_id);
 
-	netfs_see_request(wreq, netfs_rreq_trace_see_work);
-	if (!test_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags)) {
-		netfs_put_request(wreq, false, netfs_rreq_trace_put_work);
-		return;
-	}
-
 	netfs_collect_write_results(wreq);
 
 	/* We're done when the app thread has finished posting subreqs and all
 	 * the queues in all the streams are empty.
 	 */
-	if (!test_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags)) {
-		netfs_put_request(wreq, false, netfs_rreq_trace_put_work);
-		return;
-	}
+	if (!test_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags))
+		return false;
 	smp_rmb(); /* Read ALL_QUEUED before lists. */
 
 	transferred = LONG_MAX;
@@ -387,10 +374,8 @@ void netfs_write_collection_worker(struct work_struct *work)
 		struct netfs_io_stream *stream = &wreq->io_streams[s];
 		if (!stream->active)
 			continue;
-		if (!list_empty(&stream->subrequests)) {
-			netfs_put_request(wreq, false, netfs_rreq_trace_put_work);
-			return;
-		}
+		if (!list_empty(&stream->subrequests))
+			return false;
 		if (stream->transferred < transferred)
 			transferred = stream->transferred;
 	}
@@ -428,8 +413,8 @@ void netfs_write_collection_worker(struct work_struct *work)
 		inode_dio_end(wreq->inode);
 
 	_debug("finished");
-	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
-	clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
+	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
+	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
 
 	if (wreq->iocb) {
 		size_t written = min(wreq->transferred, wreq->len);
@@ -440,19 +425,21 @@ void netfs_write_collection_worker(struct work_struct *work)
 		wreq->iocb = VFS_PTR_POISON;
 	}
 
-	netfs_clear_subrequests(wreq, false);
-	netfs_put_request(wreq, false, netfs_rreq_trace_put_work_complete);
+	netfs_clear_subrequests(wreq);
+	return true;
 }
 
-/*
- * Wake the collection work item.
- */
-void netfs_wake_write_collector(struct netfs_io_request *wreq, bool was_async)
+void netfs_write_collection_worker(struct work_struct *work)
 {
-	if (!work_pending(&wreq->work)) {
-		netfs_get_request(wreq, netfs_rreq_trace_get_work);
-		if (!queue_work(system_unbound_wq, &wreq->work))
-			netfs_put_request(wreq, was_async, netfs_rreq_trace_put_work_nq);
+	struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work);
+
+	netfs_see_request(rreq, netfs_rreq_trace_see_work);
+	if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) {
+		if (netfs_write_collection(rreq))
+			/* Drop the ref from the IN_PROGRESS flag. */
+			netfs_put_request(rreq, netfs_rreq_trace_put_work_ip);
+		else
+			netfs_see_request(rreq, netfs_rreq_trace_see_work_complete);
 	}
 }
 
@@ -460,7 +447,6 @@ void netfs_wake_write_collector(struct netfs_io_request *wreq, bool was_async)
  * netfs_write_subrequest_terminated - Note the termination of a write operation.
  * @_op: The I/O request that has terminated.
  * @transferred_or_error: The amount of data transferred or an error code.
- * @was_async: The termination was asynchronous
  *
  * This tells the library that a contributory write I/O operation has
  * terminated, one way or another, and that it should collect the results.
@@ -470,21 +456,16 @@ void netfs_wake_write_collector(struct netfs_io_request *wreq, bool was_async)
  * negative error code.  The library will look after reissuing I/O operations
  * as appropriate and writing downloaded data to the cache.
  *
- * If @was_async is true, the caller might be running in softirq or interrupt
- * context and we can't sleep.
- *
  * When this is called, ownership of the subrequest is transferred back to the
  * library, along with a ref.
  *
  * Note that %_op is a void* so that the function can be passed to
  * kiocb::term_func without the need for a casting wrapper.
  */
-void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
-				       bool was_async)
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error)
 {
 	struct netfs_io_subrequest *subreq = _op;
 	struct netfs_io_request *wreq = subreq->rreq;
-	struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
 
 	_enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
 
@@ -536,15 +517,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
 	}
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
-
-	clear_and_wake_up_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-
-	/* If we are at the head of the queue, wake up the collector,
-	 * transferring a ref to it if we were the ones to do so.
-	 */
-	if (list_is_first(&subreq->rreq_link, &stream->subrequests))
-		netfs_wake_write_collector(wreq, was_async);
-
-	netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+	netfs_subreq_clear_in_progress(subreq);
+	netfs_put_subrequest(subreq, netfs_sreq_trace_put_terminated);
 }
 EXPORT_SYMBOL(netfs_write_subrequest_terminated);
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 77279fc5b5a7..50bee2c4130d 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -134,7 +134,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 	return wreq;
 nomem:
 	wreq->error = -ENOMEM;
-	netfs_put_request(wreq, false, netfs_rreq_trace_put_failed);
+	netfs_put_request(wreq, netfs_rreq_trace_put_failed);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -233,7 +233,7 @@ static void netfs_do_issue_write(struct netfs_io_stream *stream,
 	_enter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len);
 
 	if (test_bit(NETFS_SREQ_FAILED, &subreq->flags))
-		return netfs_write_subrequest_terminated(subreq, subreq->error, false);
+		return netfs_write_subrequest_terminated(subreq, subreq->error);
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	stream->issue_write(subreq);
@@ -542,7 +542,7 @@ static void netfs_end_issue_write(struct netfs_io_request *wreq)
 	}
 
 	if (needs_poke)
-		netfs_wake_write_collector(wreq, false);
+		netfs_wake_collector(wreq);
 }
 
 /*
@@ -576,6 +576,7 @@ int netfs_writepages(struct address_space *mapping,
 		goto couldnt_start;
 	}
 
+	__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
 	trace_netfs_write(wreq, netfs_write_trace_writeback);
 	netfs_stat(&netfs_n_wh_writepages);
 
@@ -599,8 +600,9 @@ int netfs_writepages(struct address_space *mapping,
 	netfs_end_issue_write(wreq);
 
 	mutex_unlock(&ictx->wb_lock);
+	netfs_wake_collector(wreq);
 
-	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	_leave(" = %d", error);
 	return error;
 
@@ -673,11 +675,11 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c
 /*
  * End a write operation used when writing through the pagecache.
  */
-int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
-			   struct folio *writethrough_cache)
+ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
+			       struct folio *writethrough_cache)
 {
 	struct netfs_inode *ictx = netfs_inode(wreq->inode);
-	int ret;
+	ssize_t ret;
 
 	_enter("R=%x", wreq->debug_id);
 
@@ -688,13 +690,11 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr
 
 	mutex_unlock(&ictx->wb_lock);
 
-	if (wreq->iocb) {
+	if (wreq->iocb)
 		ret = -EIOCBQUEUED;
-	} else {
-		wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE);
-		ret = wreq->error;
-	}
-	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	else
+		ret = netfs_wait_for_write(wreq);
+	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	return ret;
 }
 
@@ -722,10 +722,8 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t
 		start += part;
 		len -= part;
 		rolling_buffer_advance(&wreq->buffer, part);
-		if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) {
-			trace_netfs_rreq(wreq, netfs_rreq_trace_wait_pause);
-			wait_event(wreq->waitq, !test_bit(NETFS_RREQ_PAUSE, &wreq->flags));
-		}
+		if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags))
+			netfs_wait_for_paused_write(wreq);
 		if (test_bit(NETFS_RREQ_FAILED, &wreq->flags))
 			break;
 	}
@@ -885,7 +883,8 @@ int netfs_writeback_single(struct address_space *mapping,
 		goto couldnt_start;
 	}
 
-	trace_netfs_write(wreq, netfs_write_trace_writeback);
+	__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
+	trace_netfs_write(wreq, netfs_write_trace_writeback_single);
 	netfs_stat(&netfs_n_wh_writepages);
 
 	if (__test_and_set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
@@ -914,8 +913,9 @@ stop:
 	set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags);
 
 	mutex_unlock(&ictx->wb_lock);
+	netfs_wake_collector(wreq);
 
-	netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	_leave(" = %d", ret);
 	return ret;
 
diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c
index 545d33079a77..9d1d8a8bab72 100644
--- a/fs/netfs/write_retry.c
+++ b/fs/netfs/write_retry.c
@@ -39,9 +39,10 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq,
 			if (test_bit(NETFS_SREQ_FAILED, &subreq->flags))
 				break;
 			if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
-				struct iov_iter source = subreq->io_iter;
+				struct iov_iter source;
 
-				iov_iter_revert(&source, subreq->len - source.count);
+				netfs_reset_iter(subreq);
+				source = subreq->io_iter;
 				netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
 				netfs_reissue_write(stream, subreq, &source);
 			}
@@ -131,7 +132,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq,
 						      &stream->subrequests, rreq_link) {
 				trace_netfs_sreq(subreq, netfs_sreq_trace_discard);
 				list_del(&subreq->rreq_link);
-				netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done);
+				netfs_put_subrequest(subreq, netfs_sreq_trace_put_done);
 				if (subreq == to)
 					break;
 			}
@@ -199,7 +200,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq,
  */
 void netfs_retry_writes(struct netfs_io_request *wreq)
 {
-	struct netfs_io_subrequest *subreq;
 	struct netfs_io_stream *stream;
 	int s;
 
@@ -208,16 +208,13 @@ void netfs_retry_writes(struct netfs_io_request *wreq)
 	/* Wait for all outstanding I/O to quiesce before performing retries as
 	 * we may need to renegotiate the I/O sizes.
 	 */
+	set_bit(NETFS_RREQ_RETRYING, &wreq->flags);
 	for (s = 0; s < NR_IO_STREAMS; s++) {
 		stream = &wreq->io_streams[s];
-		if (!stream->active)
-			continue;
-
-		list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
-			wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS,
-				    TASK_UNINTERRUPTIBLE);
-		}
+		if (stream->active)
+			netfs_wait_for_in_progress_stream(wreq, stream);
 	}
+	clear_bit(NETFS_RREQ_RETRYING, &wreq->flags);
 
 	// TODO: Enc: Fetch changed partial pages
 	// TODO: Enc: Reencrypt content if needed.
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index e278a1ad1ca3..8b0785178731 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -367,6 +367,7 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
 
 	sreq = netfs->sreq;
 	if (test_bit(NFS_IOHDR_EOF, &hdr->flags) &&
+	    sreq->rreq->origin != NETFS_UNBUFFERED_READ &&
 	    sreq->rreq->origin != NETFS_DIO_READ)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags);
 
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 4ec952f9f47d..e6d36b3d3fc0 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -207,14 +207,16 @@ void nfs_local_probe_async(struct nfs_client *clp)
 }
 EXPORT_SYMBOL_GPL(nfs_local_probe_async);
 
-static inline struct nfsd_file *nfs_local_file_get(struct nfsd_file *nf)
+static inline void nfs_local_file_put(struct nfsd_file *localio)
 {
-	return nfs_to->nfsd_file_get(nf);
-}
+	/* nfs_to_nfsd_file_put_local() expects an __rcu pointer
+	 * but we have a __kernel pointer.  It is always safe
+	 * to cast a __kernel pointer to an __rcu pointer
+	 * because the cast only weakens what is known about the pointer.
+	 */
+	struct nfsd_file __rcu *nf = (struct nfsd_file __rcu*) localio;
 
-static inline void nfs_local_file_put(struct nfsd_file *nf)
-{
-	nfs_to->nfsd_file_put(nf);
+	nfs_to_nfsd_file_put_local(&nf);
 }
 
 /*
@@ -226,12 +228,13 @@ static inline void nfs_local_file_put(struct nfsd_file *nf)
 static struct nfsd_file *
 __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		    struct nfs_fh *fh, struct nfs_file_localio *nfl,
+		    struct nfsd_file __rcu **pnf,
 		    const fmode_t mode)
 {
 	struct nfsd_file *localio;
 
 	localio = nfs_open_local_fh(&clp->cl_uuid, clp->cl_rpcclient,
-				    cred, fh, nfl, mode);
+				    cred, fh, nfl, pnf, mode);
 	if (IS_ERR(localio)) {
 		int status = PTR_ERR(localio);
 		trace_nfs_local_open_fh(fh, mode, status);
@@ -258,7 +261,7 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		  struct nfs_fh *fh, struct nfs_file_localio *nfl,
 		  const fmode_t mode)
 {
-	struct nfsd_file *nf, *new, __rcu **pnf;
+	struct nfsd_file *nf, __rcu **pnf;
 
 	if (!nfs_server_is_local(clp))
 		return NULL;
@@ -270,29 +273,9 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 	else
 		pnf = &nfl->ro_file;
 
-	new = NULL;
-	rcu_read_lock();
-	nf = rcu_dereference(*pnf);
-	if (!nf) {
-		rcu_read_unlock();
-		new = __nfs_local_open_fh(clp, cred, fh, nfl, mode);
-		if (IS_ERR(new))
-			return NULL;
-		rcu_read_lock();
-		/* try to swap in the pointer */
-		spin_lock(&clp->cl_uuid.lock);
-		nf = rcu_dereference_protected(*pnf, 1);
-		if (!nf) {
-			nf = new;
-			new = NULL;
-			rcu_assign_pointer(*pnf, nf);
-		}
-		spin_unlock(&clp->cl_uuid.lock);
-	}
-	nf = nfs_local_file_get(nf);
-	rcu_read_unlock();
-	if (new)
-		nfs_to_nfsd_file_put_local(new);
+	nf = __nfs_local_open_fh(clp, cred, fh, nfl, pnf, mode);
+	if (IS_ERR(nf))
+		return NULL;
 	return nf;
 }
 EXPORT_SYMBOL_GPL(nfs_local_open_fh);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b1d2122bd5a7..4b123bca65e1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5164,13 +5164,15 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
 }
 
 static struct dentry *nfs4_do_mkdir(struct inode *dir, struct dentry *dentry,
-				    struct nfs4_createdata *data)
+				    struct nfs4_createdata *data, int *statusp)
 {
-	int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
+	struct dentry *ret;
+
+	*statusp = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
 				    &data->arg.seq_args, &data->res.seq_res, 1);
 
-	if (status)
-		return ERR_PTR(status);
+	if (*statusp)
+		return NULL;
 
 	spin_lock(&dir->i_lock);
 	/* Creating a directory bumps nlink in the parent */
@@ -5179,7 +5181,11 @@ static struct dentry *nfs4_do_mkdir(struct inode *dir, struct dentry *dentry,
 				      data->res.fattr->time_start,
 				      NFS_INO_INVALID_DATA);
 	spin_unlock(&dir->i_lock);
-	return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr);
+	ret = nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr);
+	if (!IS_ERR(ret))
+		return ret;
+	*statusp = PTR_ERR(ret);
+	return NULL;
 }
 
 static void nfs4_free_createdata(struct nfs4_createdata *data)
@@ -5240,17 +5246,18 @@ static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
 
 static struct dentry *_nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 				       struct iattr *sattr,
-				       struct nfs4_label *label)
+				       struct nfs4_label *label, int *statusp)
 {
 	struct nfs4_createdata *data;
-	struct dentry *ret = ERR_PTR(-ENOMEM);
+	struct dentry *ret = NULL;
 
+	*statusp = -ENOMEM;
 	data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4DIR);
 	if (data == NULL)
 		goto out;
 
 	data->arg.label = label;
-	ret = nfs4_do_mkdir(dir, dentry, data);
+	ret = nfs4_do_mkdir(dir, dentry, data, statusp);
 
 	nfs4_free_createdata(data);
 out:
@@ -5273,11 +5280,12 @@ static struct dentry *nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 	if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK))
 		sattr->ia_mode &= ~current_umask();
 	do {
-		alias = _nfs4_proc_mkdir(dir, dentry, sattr, label);
-		err = PTR_ERR_OR_ZERO(alias);
+		alias = _nfs4_proc_mkdir(dir, dentry, sattr, label, &err);
 		trace_nfs4_mkdir(dir, &dentry->d_name, err);
-		err = nfs4_handle_exception(NFS_SERVER(dir), err,
-				&exception);
+		if (err)
+			alias = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir),
+							      err,
+							      &exception));
 	} while (exception.retry);
 	nfs4_label_release_security(label);
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 9eea9e62afc9..91b5503b6f74 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1052,6 +1052,16 @@ int nfs_reconfigure(struct fs_context *fc)
 	sync_filesystem(sb);
 
 	/*
+	 * The SB_RDONLY flag has been removed from the superblock during
+	 * mounts to prevent interference between different filesystems.
+	 * Similarly, it is also necessary to ignore the SB_RDONLY flag
+	 * during reconfiguration; otherwise, it may also result in the
+	 * creation of redundant superblocks when mounting a directory with
+	 * different rw and ro flags multiple times.
+	 */
+	fc->sb_flags_mask &= ~SB_RDONLY;
+
+	/*
 	 * Userspace mount programs that send binary options generally send
 	 * them populated with default values. We have no way to know which
 	 * ones were explicitly specified. Fall back to legacy behavior and
@@ -1308,8 +1318,17 @@ int nfs_get_tree_common(struct fs_context *fc)
 	if (IS_ERR(server))
 		return PTR_ERR(server);
 
+	/*
+	 * When NFS_MOUNT_UNSHARED is not set, NFS forces the sharing of a
+	 * superblock among each filesystem that mounts sub-directories
+	 * belonging to a single exported root path.
+	 * To prevent interference between different filesystems, the
+	 * SB_RDONLY flag should be removed from the superblock.
+	 */
 	if (server->flags & NFS_MOUNT_UNSHARED)
 		compare_super = NULL;
+	else
+		fc->sb_flags &= ~SB_RDONLY;
 
 	/* -o noac implies -o sync */
 	if (server->flags & NFS_MOUNT_NOAC)
diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c
index 6a0bdea6d644..05c7c16e37ab 100644
--- a/fs/nfs_common/nfslocalio.c
+++ b/fs/nfs_common/nfslocalio.c
@@ -151,8 +151,7 @@ EXPORT_SYMBOL_GPL(nfs_localio_enable_client);
  */
 static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid)
 {
-	LIST_HEAD(local_files);
-	struct nfs_file_localio *nfl, *tmp;
+	struct nfs_file_localio *nfl;
 
 	spin_lock(&nfs_uuid->lock);
 	if (unlikely(!rcu_access_pointer(nfs_uuid->net))) {
@@ -166,17 +165,42 @@ static bool nfs_uuid_put(nfs_uuid_t *nfs_uuid)
 		nfs_uuid->dom = NULL;
 	}
 
-	list_splice_init(&nfs_uuid->files, &local_files);
-	spin_unlock(&nfs_uuid->lock);
-
 	/* Walk list of files and ensure their last references dropped */
-	list_for_each_entry_safe(nfl, tmp, &local_files, list) {
-		nfs_close_local_fh(nfl);
+
+	while ((nfl = list_first_entry_or_null(&nfs_uuid->files,
+					       struct nfs_file_localio,
+					       list)) != NULL) {
+		/* If nfs_uuid is already NULL, nfs_close_local_fh is
+		 * closing and we must wait, else we unlink and close.
+		 */
+		if (rcu_access_pointer(nfl->nfs_uuid) == NULL) {
+			/* nfs_close_local_fh() is doing the
+			 * close and we must wait. until it unlinks
+			 */
+			wait_var_event_spinlock(nfl,
+						list_first_entry_or_null(
+							&nfs_uuid->files,
+							struct nfs_file_localio,
+							list) != nfl,
+						&nfs_uuid->lock);
+			continue;
+		}
+
+		/* Remove nfl from nfs_uuid->files list */
+		list_del_init(&nfl->list);
+		spin_unlock(&nfs_uuid->lock);
+
+		nfs_to_nfsd_file_put_local(&nfl->ro_file);
+		nfs_to_nfsd_file_put_local(&nfl->rw_file);
 		cond_resched();
-	}
 
-	spin_lock(&nfs_uuid->lock);
-	BUG_ON(!list_empty(&nfs_uuid->files));
+		spin_lock(&nfs_uuid->lock);
+		/* Now we can allow racing nfs_close_local_fh() to
+		 * skip the locking.
+		 */
+		RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
+		wake_up_var_locked(&nfl->nfs_uuid, &nfs_uuid->lock);
+	}
 
 	/* Remove client from nn->local_clients */
 	if (nfs_uuid->list_lock) {
@@ -237,6 +261,7 @@ static void nfs_uuid_add_file(nfs_uuid_t *nfs_uuid, struct nfs_file_localio *nfl
 struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 		   struct rpc_clnt *rpc_clnt, const struct cred *cred,
 		   const struct nfs_fh *nfs_fh, struct nfs_file_localio *nfl,
+		   struct nfsd_file __rcu **pnf,
 		   const fmode_t fmode)
 {
 	struct net *net;
@@ -261,10 +286,9 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid,
 	rcu_read_unlock();
 	/* We have an implied reference to net thanks to nfsd_net_try_get */
 	localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt,
-					     cred, nfs_fh, fmode);
-	if (IS_ERR(localio))
-		nfs_to_nfsd_net_put(net);
-	else
+					     cred, nfs_fh, pnf, fmode);
+	nfs_to_nfsd_net_put(net);
+	if (!IS_ERR(localio))
 		nfs_uuid_add_file(uuid, nfl);
 
 	return localio;
@@ -273,8 +297,6 @@ EXPORT_SYMBOL_GPL(nfs_open_local_fh);
 
 void nfs_close_local_fh(struct nfs_file_localio *nfl)
 {
-	struct nfsd_file *ro_nf = NULL;
-	struct nfsd_file *rw_nf = NULL;
 	nfs_uuid_t *nfs_uuid;
 
 	rcu_read_lock();
@@ -285,28 +307,39 @@ void nfs_close_local_fh(struct nfs_file_localio *nfl)
 		return;
 	}
 
-	ro_nf = rcu_access_pointer(nfl->ro_file);
-	rw_nf = rcu_access_pointer(nfl->rw_file);
-	if (ro_nf || rw_nf) {
-		spin_lock(&nfs_uuid->lock);
-		if (ro_nf)
-			ro_nf = rcu_dereference_protected(xchg(&nfl->ro_file, NULL), 1);
-		if (rw_nf)
-			rw_nf = rcu_dereference_protected(xchg(&nfl->rw_file, NULL), 1);
-
-		/* Remove nfl from nfs_uuid->files list */
-		RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
-		list_del_init(&nfl->list);
+	spin_lock(&nfs_uuid->lock);
+	if (!rcu_access_pointer(nfl->nfs_uuid)) {
+		/* nfs_uuid_put has finished here */
 		spin_unlock(&nfs_uuid->lock);
 		rcu_read_unlock();
-
-		if (ro_nf)
-			nfs_to_nfsd_file_put_local(ro_nf);
-		if (rw_nf)
-			nfs_to_nfsd_file_put_local(rw_nf);
 		return;
 	}
+	if (list_empty(&nfs_uuid->files)) {
+		/* nfs_uuid_put() has started closing files, wait for it
+		 * to finished
+		 */
+		spin_unlock(&nfs_uuid->lock);
+		rcu_read_unlock();
+		wait_var_event(&nfl->nfs_uuid,
+			       rcu_access_pointer(nfl->nfs_uuid) == NULL);
+		return;
+	}
+	/* tell nfs_uuid_put() to wait for us */
+	RCU_INIT_POINTER(nfl->nfs_uuid, NULL);
+	spin_unlock(&nfs_uuid->lock);
 	rcu_read_unlock();
+
+	nfs_to_nfsd_file_put_local(&nfl->ro_file);
+	nfs_to_nfsd_file_put_local(&nfl->rw_file);
+
+	/* Remove nfl from nfs_uuid->files list and signal nfs_uuid_put()
+	 * that we are done.  The moment we drop the spinlock the
+	 * nfs_uuid could be freed.
+	 */
+	spin_lock(&nfs_uuid->lock);
+	list_del_init(&nfl->list);
+	wake_up_var_locked(&nfl->nfs_uuid, &nfs_uuid->lock);
+	spin_unlock(&nfs_uuid->lock);
 }
 EXPORT_SYMBOL_GPL(nfs_close_local_fh);
 
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ab85e6a2454f..e108b6c705b4 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -378,15 +378,41 @@ nfsd_file_put(struct nfsd_file *nf)
  * the reference of the nfsd_file.
  */
 struct net *
-nfsd_file_put_local(struct nfsd_file *nf)
+nfsd_file_put_local(struct nfsd_file __rcu **pnf)
 {
-	struct net *net = nf->nf_net;
+	struct nfsd_file *nf;
+	struct net *net = NULL;
 
-	nfsd_file_put(nf);
+	nf = unrcu_pointer(xchg(pnf, NULL));
+	if (nf) {
+		net = nf->nf_net;
+		nfsd_file_put(nf);
+	}
 	return net;
 }
 
 /**
+ * nfsd_file_get_local - get nfsd_file reference and reference to net
+ * @nf: nfsd_file of which to put the reference
+ *
+ * Get reference to both the nfsd_file and nf->nf_net.
+ */
+struct nfsd_file *
+nfsd_file_get_local(struct nfsd_file *nf)
+{
+	struct net *net = nf->nf_net;
+
+	if (nfsd_net_try_get(net)) {
+		nf = nfsd_file_get(nf);
+		if (!nf)
+			nfsd_net_put(net);
+	} else {
+		nf = NULL;
+	}
+	return nf;
+}
+
+/**
  * nfsd_file_file - get the backing file of an nfsd_file
  * @nf: nfsd_file of which to access the backing file.
  *
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index 5865f9c72712..722b26c71e45 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -62,7 +62,8 @@ void nfsd_file_cache_shutdown(void);
 int nfsd_file_cache_start_net(struct net *net);
 void nfsd_file_cache_shutdown_net(struct net *net);
 void nfsd_file_put(struct nfsd_file *nf);
-struct net *nfsd_file_put_local(struct nfsd_file *nf);
+struct net *nfsd_file_put_local(struct nfsd_file __rcu **nf);
+struct nfsd_file *nfsd_file_get_local(struct nfsd_file *nf);
 struct nfsd_file *nfsd_file_get(struct nfsd_file *nf);
 struct file *nfsd_file_file(struct nfsd_file *nf);
 void nfsd_file_close_inode_sync(struct inode *inode);
diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c
index 238647fa379e..80d9ff6608a7 100644
--- a/fs/nfsd/localio.c
+++ b/fs/nfsd/localio.c
@@ -24,21 +24,6 @@
 #include "filecache.h"
 #include "cache.h"
 
-static const struct nfsd_localio_operations nfsd_localio_ops = {
-	.nfsd_net_try_get  = nfsd_net_try_get,
-	.nfsd_net_put  = nfsd_net_put,
-	.nfsd_open_local_fh = nfsd_open_local_fh,
-	.nfsd_file_put_local = nfsd_file_put_local,
-	.nfsd_file_get = nfsd_file_get,
-	.nfsd_file_put = nfsd_file_put,
-	.nfsd_file_file = nfsd_file_file,
-};
-
-void nfsd_localio_ops_init(void)
-{
-	nfs_to = &nfsd_localio_ops;
-}
-
 /**
  * nfsd_open_local_fh - lookup a local filehandle @nfs_fh and map to nfsd_file
  *
@@ -47,6 +32,7 @@ void nfsd_localio_ops_init(void)
  * @rpc_clnt: rpc_clnt that the client established
  * @cred: cred that the client established
  * @nfs_fh: filehandle to lookup
+ * @nfp: place to find the nfsd_file, or store it if it was non-NULL
  * @fmode: fmode_t to use for open
  *
  * This function maps a local fh to a path on a local filesystem.
@@ -57,10 +43,11 @@ void nfsd_localio_ops_init(void)
  * set. Caller (NFS client) is responsible for calling nfsd_net_put and
  * nfsd_file_put (via nfs_to_nfsd_file_put_local).
  */
-struct nfsd_file *
+static struct nfsd_file *
 nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
 		   struct rpc_clnt *rpc_clnt, const struct cred *cred,
-		   const struct nfs_fh *nfs_fh, const fmode_t fmode)
+		   const struct nfs_fh *nfs_fh, struct nfsd_file __rcu **pnf,
+		   const fmode_t fmode)
 {
 	int mayflags = NFSD_MAY_LOCALIO;
 	struct svc_cred rq_cred;
@@ -71,6 +58,15 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
 	if (nfs_fh->size > NFS4_FHSIZE)
 		return ERR_PTR(-EINVAL);
 
+	if (!nfsd_net_try_get(net))
+		return ERR_PTR(-ENXIO);
+
+	rcu_read_lock();
+	localio = nfsd_file_get(rcu_dereference(*pnf));
+	rcu_read_unlock();
+	if (localio)
+		return localio;
+
 	/* nfs_fh -> svc_fh */
 	fh_init(&fh, NFS4_FHSIZE);
 	fh.fh_handle.fh_size = nfs_fh->size;
@@ -92,9 +88,47 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom,
 	if (rq_cred.cr_group_info)
 		put_group_info(rq_cred.cr_group_info);
 
+	if (!IS_ERR(localio)) {
+		struct nfsd_file *new;
+		if (!nfsd_net_try_get(net)) {
+			nfsd_file_put(localio);
+			nfsd_net_put(net);
+			return ERR_PTR(-ENXIO);
+		}
+		nfsd_file_get(localio);
+	again:
+		new = unrcu_pointer(cmpxchg(pnf, NULL, RCU_INITIALIZER(localio)));
+		if (new) {
+			/* Some other thread installed an nfsd_file */
+			if (nfsd_file_get(new) == NULL)
+				goto again;
+			/*
+			 * Drop the ref we were going to install and the
+			 * one we were going to return.
+			 */
+			nfsd_file_put(localio);
+			nfsd_file_put(localio);
+			localio = new;
+		}
+	} else
+		nfsd_net_put(net);
+
 	return localio;
 }
-EXPORT_SYMBOL_GPL(nfsd_open_local_fh);
+
+static const struct nfsd_localio_operations nfsd_localio_ops = {
+	.nfsd_net_try_get  = nfsd_net_try_get,
+	.nfsd_net_put  = nfsd_net_put,
+	.nfsd_open_local_fh = nfsd_open_local_fh,
+	.nfsd_file_put_local = nfsd_file_put_local,
+	.nfsd_file_get_local = nfsd_file_get_local,
+	.nfsd_file_file = nfsd_file_file,
+};
+
+void nfsd_localio_ops_init(void)
+{
+	nfs_to = &nfsd_localio_ops;
+}
 
 /*
  * UUID_IS_LOCAL XDR functions
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 0d8f7fb15c2e..dd0c8e560ef6 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -2102,11 +2102,13 @@ static int nilfs_btree_propagate(struct nilfs_bmap *btree,
 
 	ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0);
 	if (ret < 0) {
-		if (unlikely(ret == -ENOENT))
+		if (unlikely(ret == -ENOENT)) {
 			nilfs_crit(btree->b_inode->i_sb,
 				   "writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d",
 				   btree->b_inode->i_ino,
 				   (unsigned long long)key, level);
+			ret = -EINVAL;
+		}
 		goto out;
 	}
 
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index 893ab36824cc..2d8dc6b35b54 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -273,6 +273,9 @@ static int nilfs_direct_propagate(struct nilfs_bmap *bmap,
 	dat = nilfs_bmap_get_dat(bmap);
 	key = nilfs_bmap_data_get_key(bmap, bh);
 	ptr = nilfs_direct_get_ptr(bmap, key);
+	if (ptr == NILFS_BMAP_INVALID_PTR)
+		return -EINVAL;
+
 	if (!buffer_nilfs_volatile(bh)) {
 		oldreq.pr_entry_nr = ptr;
 		newreq.pr_entry_nr = ptr;
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index 78d20e4baa2c..1bf2a6593dec 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -2182,6 +2182,10 @@ static int indx_get_entry_to_replace(struct ntfs_index *indx,
 
 		e = hdr_first_de(&n->index->ihdr);
 		fnd_push(fnd, n, e);
+		if (!e) {
+			err = -EINVAL;
+			goto out;
+		}
 
 		if (!de_is_last(e)) {
 			/*
@@ -2203,6 +2207,10 @@ static int indx_get_entry_to_replace(struct ntfs_index *indx,
 
 	n = fnd->nodes[level];
 	te = hdr_first_de(&n->index->ihdr);
+	if (!te) {
+		err = -EINVAL;
+		goto out;
+	}
 	/* Copy the candidate entry into the replacement entry buffer. */
 	re = kmalloc(le16_to_cpu(te->size) + sizeof(u64), GFP_NOFS);
 	if (!re) {
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 3e2957a1e360..0f0d27d4644a 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -805,6 +805,10 @@ static ssize_t ntfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		ret = 0;
 		goto out;
 	}
+	if (is_compressed(ni)) {
+		ret = 0;
+		goto out;
+	}
 
 	ret = blockdev_direct_IO(iocb, inode, iter,
 				 wr ? ntfs_get_block_direct_IO_W :
@@ -2068,5 +2072,6 @@ const struct address_space_operations ntfs_aops_cmpr = {
 	.read_folio	= ntfs_read_folio,
 	.readahead	= ntfs_readahead,
 	.dirty_folio	= block_dirty_folio,
+	.direct_IO	= ntfs_direct_IO,
 };
 // clang-format on
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index e272429da3db..de7f12858729 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -674,7 +674,7 @@ out_put:
 			break;
 	}
 out:
-	kfree(rec);
+	ocfs2_free_quota_recovery(rec);
 	return status;
 }
 
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 50e69a9e104a..87a53d2ae4bb 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -336,7 +336,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 	kinfo.pid = task_pid_vnr(task);
 	kinfo.mask |= PIDFD_INFO_PID;
 
-	if (kinfo.pid == 0 || kinfo.tgid == 0 || (kinfo.ppid == 0 && kinfo.pid != 1))
+	if (kinfo.pid == 0 || kinfo.tgid == 0)
 		return -ESRCH;
 
 copy_out:
diff --git a/fs/pnode.c b/fs/pnode.c
index fb77427df39e..ffd429b760d5 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -231,8 +231,8 @@ static int propagate_one(struct mount *m, struct mountpoint *dest_mp)
 	/* skip if mountpoint isn't visible in m */
 	if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root))
 		return 0;
-	/* skip if m is in the anon_ns we are emptying */
-	if (m->mnt_ns->mntns_flags & MNTNS_PROPAGATING)
+	/* skip if m is in the anon_ns */
+	if (is_anon_ns(m->mnt_ns))
 		return 0;
 
 	if (peers(m, last_dest)) {
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index ecf774a8f1ca..66093fa78aed 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -151,8 +151,7 @@ extern bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 eof,
 				   bool from_readdir);
 extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
 			    unsigned int bytes_written);
-void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result,
-				      bool was_async);
+void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result);
 extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int);
 extern int cifs_get_writable_file(struct cifsInodeInfo *cifs_inode,
 				  int flags,
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index f55457b4b82e..a3ba3346ed31 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1725,7 +1725,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
 			      server->credits, server->in_flight,
 			      0, cifs_trace_rw_credits_write_response_clear);
 	wdata->credits.value = 0;
-	cifs_write_subrequest_terminated(wdata, result, true);
+	cifs_write_subrequest_terminated(wdata, result);
 	release_mid(mid);
 	trace_smb3_rw_credits(credits.rreq_debug_id, credits.rreq_debug_index, 0,
 			      server->credits, server->in_flight,
@@ -1813,7 +1813,7 @@ async_writev_out:
 out:
 	if (rc) {
 		add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
-		cifs_write_subrequest_terminated(wdata, rc, false);
+		cifs_write_subrequest_terminated(wdata, rc);
 	}
 }
 
@@ -2753,10 +2753,10 @@ int cifs_query_reparse_point(const unsigned int xid,
 
 	io_req->TotalParameterCount = 0;
 	io_req->TotalDataCount = 0;
-	io_req->MaxParameterCount = cpu_to_le32(2);
+	io_req->MaxParameterCount = cpu_to_le32(0);
 	/* BB find exact data count max from sess structure BB */
 	io_req->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00);
-	io_req->MaxSetupCount = 4;
+	io_req->MaxSetupCount = 1;
 	io_req->Reserved = 0;
 	io_req->ParameterOffset = 0;
 	io_req->DataCount = 0;
@@ -2783,6 +2783,22 @@ int cifs_query_reparse_point(const unsigned int xid,
 		goto error;
 	}
 
+	/* SetupCount must be 1, otherwise offset to ByteCount is incorrect. */
+	if (io_rsp->SetupCount != 1) {
+		rc = -EIO;
+		goto error;
+	}
+
+	/*
+	 * ReturnedDataLen is output length of executed IOCTL.
+	 * DataCount is output length transferred over network.
+	 * Check that we have full FSCTL_GET_REPARSE_POINT buffer.
+	 */
+	if (data_count != le16_to_cpu(io_rsp->ReturnedDataLen)) {
+		rc = -EIO;
+		goto error;
+	}
+
 	end = 2 + get_bcc(&io_rsp->hdr) + (__u8 *)&io_rsp->ByteCount;
 	start = (__u8 *)&io_rsp->hdr.Protocol + data_offset;
 	if (start >= end) {
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 950aa4f912f5..9835672267d2 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -130,7 +130,7 @@ fail:
 	else
 		trace_netfs_sreq(subreq, netfs_sreq_trace_fail);
 	add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
-	cifs_write_subrequest_terminated(wdata, rc, false);
+	cifs_write_subrequest_terminated(wdata, rc);
 	goto out;
 }
 
@@ -219,7 +219,8 @@ static void cifs_issue_read(struct netfs_io_subrequest *subreq)
 			goto failed;
 	}
 
-	if (subreq->rreq->origin != NETFS_DIO_READ)
+	if (subreq->rreq->origin != NETFS_UNBUFFERED_READ &&
+	    subreq->rreq->origin != NETFS_DIO_READ)
 		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
@@ -998,15 +999,18 @@ int cifs_open(struct inode *inode, struct file *file)
 		rc = cifs_get_readable_path(tcon, full_path, &cfile);
 	}
 	if (rc == 0) {
-		if (file->f_flags == cfile->f_flags) {
+		unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+		unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+
+		if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) &&
+		    (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) {
 			file->private_data = cfile;
 			spin_lock(&CIFS_I(inode)->deferred_lock);
 			cifs_del_deferred_close(cfile);
 			spin_unlock(&CIFS_I(inode)->deferred_lock);
 			goto use_cache;
-		} else {
-			_cifsFileInfo_put(cfile, true, false);
 		}
+		_cifsFileInfo_put(cfile, true, false);
 	} else {
 		/* hard link on the defeered close file */
 		rc = cifs_get_hardlink_path(tcon, inode, file);
@@ -2423,8 +2427,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
 	return rc;
 }
 
-void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result,
-				      bool was_async)
+void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result)
 {
 	struct netfs_io_request *wreq = wdata->rreq;
 	struct netfs_inode *ictx = netfs_inode(wreq->inode);
@@ -2441,7 +2444,7 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t
 			netfs_resize_file(ictx, wrend, true);
 	}
 
-	netfs_write_subrequest_terminated(&wdata->subreq, result, was_async);
+	netfs_write_subrequest_terminated(&wdata->subreq, result);
 }
 
 struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 4e28632b5fd6..399185ca7cac 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4888,7 +4888,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
 			      0, cifs_trace_rw_credits_write_response_clear);
 	wdata->credits.value = 0;
 	trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress);
-	cifs_write_subrequest_terminated(wdata, result ?: written, true);
+	cifs_write_subrequest_terminated(wdata, result ?: written);
 	release_mid(mid);
 	trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
 			      server->credits, server->in_flight,
@@ -5061,7 +5061,7 @@ out:
 				      -(int)wdata->credits.value,
 				      cifs_trace_rw_credits_write_response_clear);
 		add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
-		cifs_write_subrequest_terminated(wdata, rc, true);
+		cifs_write_subrequest_terminated(wdata, rc);
 	}
 }
 
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 67c55fe32ce8..992ea0e37257 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -202,6 +202,11 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	msblk->panic_on_errors = (opts->errors == Opt_errors_panic);
 
 	msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
+	if (!msblk->devblksize) {
+		errorf(fc, "squashfs: unable to set blocksize\n");
+		return -EINVAL;
+	}
+
 	msblk->devblksize_log2 = ffz(~msblk->devblksize);
 
 	mutex_init(&msblk->meta_index_mutex);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 26a04a783489..63151feb9c3f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -436,6 +436,25 @@ allocate_blocks:
 	return 0;
 }
 
+static bool
+xfs_ioend_needs_wq_completion(
+	struct iomap_ioend	*ioend)
+{
+	/* Changing inode size requires a transaction. */
+	if (xfs_ioend_is_append(ioend))
+		return true;
+
+	/* Extent manipulation requires a transaction. */
+	if (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED))
+		return true;
+
+	/* Page cache invalidation cannot be done in irq context. */
+	if (ioend->io_flags & IOMAP_IOEND_DONTCACHE)
+		return true;
+
+	return false;
+}
+
 static int
 xfs_submit_ioend(
 	struct iomap_writepage_ctx *wpc,
@@ -460,8 +479,7 @@ xfs_submit_ioend(
 	memalloc_nofs_restore(nofs_flag);
 
 	/* send ioends that might require a transaction to the completion wq */
-	if (xfs_ioend_is_append(ioend) ||
-	    (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED)))
+	if (xfs_ioend_needs_wq_completion(ioend))
 		ioend->io_bio.bi_end_io = xfs_end_bio;
 
 	if (status)
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index c1a306268ae4..94d0873bcd62 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -167,6 +167,14 @@ xfs_discard_extents(
 	return error;
 }
 
+/*
+ * Care must be taken setting up the trim cursor as the perags may not have been
+ * initialised when the cursor is initialised. e.g. a clean mount which hasn't
+ * read in AGFs and the first operation run on the mounted fs is a trim. This
+ * can result in perag fields that aren't initialised until
+ * xfs_trim_gather_extents() calls xfs_alloc_read_agf() to lock down the AG for
+ * the free space search.
+ */
 struct xfs_trim_cur {
 	xfs_agblock_t	start;
 	xfs_extlen_t	count;
@@ -204,6 +212,14 @@ xfs_trim_gather_extents(
 	if (error)
 		goto out_trans_cancel;
 
+	/*
+	 * First time through tcur->count will not have been initialised as
+	 * pag->pagf_longest is not guaranteed to be valid before we read
+	 * the AGF buffer above.
+	 */
+	if (!tcur->count)
+		tcur->count = pag->pagf_longest;
+
 	if (tcur->by_bno) {
 		/* sub-AG discard request always starts at tcur->start */
 		cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag);
@@ -350,7 +366,6 @@ xfs_trim_perag_extents(
 {
 	struct xfs_trim_cur	tcur = {
 		.start		= start,
-		.count		= pag->pagf_longest,
 		.end		= end,
 		.minlen		= minlen,
 	};