Merge tag 'nfs-for-6.18-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "New Features:
   - Add a Kconfig option to redirect dfprintk() to the trace buffer
   - Enable use of the RWF_DONTCACHE flag on the NFS client
   - Add striped layout handling to pNFS flexfiles
   - Add proper localio handling for READ and WRITE O_DIRECT

  Bugfixes:
   - Handle NFS4ERR_GRACE errors during delegation recall
   - Fix NFSv4.1 backchannel max_resp_sz verification check
   - Fix mount hang after CREATE_SESSION failure
   - Fix d_parent->d_inode locking in nfs4_setup_readdir()

  Other Cleanups and Improvements:
   - Improvements to write handling tracepoints
   - Fix a few trivial spelling mistakes
   - Cleanups to the rpcbind cleanup call sites
   - Convert the SUNRPC xdr_buf to use a scratch folio instead of
     scratch page
   - Remove unused NFS_WBACK_BUSY() macro
   - Remove __GFP_NOWARN flags
   - Unexport rpc_malloc() and rpc_free()"

* tag 'nfs-for-6.18-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (46 commits)
  NFS: add basic STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
  nfs/localio: add tracepoints for misaligned DIO READ and WRITE support
  nfs/localio: add proper O_DIRECT support for READ and WRITE
  nfs/localio: refactor iocb initialization
  nfs/localio: refactor iocb and iov_iter_bvec initialization
  nfs/localio: avoid issuing misaligned IO using O_DIRECT
  nfs/localio: make trace_nfs_local_open_fh more useful
  NFSD: filecache: add STATX_DIOALIGN and STATX_DIO_READ_ALIGN support
  sunrpc: unexport rpc_malloc() and rpc_free()
  NFSv4/flexfiles: Add support for striped layouts
  NFSv4/flexfiles: Update layout stats & error paths for striped layouts
  NFSv4/flexfiles: Write path updates for striped layouts
  NFSv4/flexfiles: Commit path updates for striped layouts
  NFSv4/flexfiles: Read path updates for striped layouts
  NFSv4/flexfiles: Update low level helper functions to be DS stripe aware.
  NFSv4/flexfiles: Add data structure support for striped layouts
  NFSv4/flexfiles: Use ds_commit_idx when marking a write commit
  NFSv4/flexfiles: Remove cred local variable dependency
  nfs4_setup_readdir(): insufficient locking for ->d_parent->d_inode dereferencing
  NFS: Enable use of the RWF_DONTCACHE flag on the NFS client
  ...

31 files changed, 1359 insertions, 491 deletions

diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index e80262a51884..d68afa196535 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -216,8 +216,7 @@ out_err:
 	if (warned++ == 0)
 		printk(KERN_WARNING
 			"lockd_up: makesock failed, error=%d\n", err);
-	svc_xprt_destroy_all(serv, net);
-	svc_rpcb_cleanup(serv, net);
+	svc_xprt_destroy_all(serv, net, true);
 	return err;
 }
 
@@ -255,8 +254,7 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 			nlm_shutdown_hosts_net(net);
 			cancel_delayed_work_sync(&ln->grace_period_end);
 			locks_end_grace(&ln->lockd_manager);
-			svc_xprt_destroy_all(serv, net);
-			svc_rpcb_cleanup(serv, net);
+			svc_xprt_destroy_all(serv, net, true);
 		}
 	} else {
 		pr_err("%s: no users! net=%x\n",
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 5d6edafbed20..0e4c67373e4f 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -676,7 +676,7 @@ bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
 	struct pnfs_layout_segment *lseg;
 	struct xdr_buf buf;
 	struct xdr_stream xdr;
-	struct page *scratch;
+	struct folio *scratch;
 	int status, i;
 	uint32_t count;
 	__be32 *p;
@@ -689,13 +689,13 @@ bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr,
 		return ERR_PTR(-ENOMEM);
 
 	status = -ENOMEM;
-	scratch = alloc_page(gfp_mask);
+	scratch = folio_alloc(gfp_mask, 0);
 	if (!scratch)
 		goto out;
 
 	xdr_init_decode_pages(&xdr, &buf,
 			lgr->layoutp->pages, lgr->layoutp->len);
-	xdr_set_scratch_page(&xdr, scratch);
+	xdr_set_scratch_folio(&xdr, scratch);
 
 	status = -EIO;
 	p = xdr_inline_decode(&xdr, 4);
@@ -744,7 +744,7 @@ process_extents:
 	}
 
 out_free_scratch:
-	__free_page(scratch);
+	folio_put(scratch);
 out:
 	dprintk("%s returns %d\n", __func__, status);
 	switch (status) {
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index 44306ac22353..ab76120705e2 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -541,16 +541,16 @@ bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct pnfs_block_dev *top;
 	struct xdr_stream xdr;
 	struct xdr_buf buf;
-	struct page *scratch;
+	struct folio *scratch;
 	int nr_volumes, ret, i;
 	__be32 *p;
 
-	scratch = alloc_page(gfp_mask);
+	scratch = folio_alloc(gfp_mask, 0);
 	if (!scratch)
 		goto out;
 
 	xdr_init_decode_pages(&xdr, &buf, pdev->pages, pdev->pglen);
-	xdr_set_scratch_page(&xdr, scratch);
+	xdr_set_scratch_folio(&xdr, scratch);
 
 	p = xdr_inline_decode(&xdr, sizeof(__be32));
 	if (!p)
@@ -582,7 +582,7 @@ bl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 out_free_volumes:
 	kfree(volumes);
 out_free_scratch:
-	__free_page(scratch);
+	folio_put(scratch);
 out:
 	return node;
 }
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 86bdc7d23fb9..c8b837006bb2 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -136,7 +136,7 @@ static void nfs_callback_down_net(u32 minorversion, struct svc_serv *serv, struc
 		return;
 
 	dprintk("NFS: destroy per-net callback data; net=%x\n", net->ns.inum);
-	svc_xprt_destroy_all(serv, net);
+	svc_xprt_destroy_all(serv, net, false);
 }
 
 static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
@@ -153,7 +153,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 	ret = svc_bind(serv, net);
 	if (ret < 0) {
 		printk(KERN_WARNING "NFS: bind callback service failed\n");
-		goto err_bind;
+		goto err;
 	}
 
 	ret = 0;
@@ -166,13 +166,11 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv,
 
 	if (ret < 0) {
 		printk(KERN_ERR "NFS: callback service start failed\n");
-		goto err_socks;
+		goto err;
 	}
 	return 0;
 
-err_socks:
-	svc_rpcb_cleanup(serv, net);
-err_bind:
+err:
 	nn->cb_users[minorversion]--;
 	dprintk("NFS: Couldn't create callback socket: err = %d; "
 			"net = %x\n", ret, net->ns.inum);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 5f7d9be6f022..46d9c65d50f8 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -829,17 +829,17 @@ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc,
 	struct address_space *mapping = desc->file->f_mapping;
 	struct folio *new, *folio = *arrays;
 	struct xdr_stream stream;
-	struct page *scratch;
+	struct folio *scratch;
 	struct xdr_buf buf;
 	u64 cookie;
 	int status;
 
-	scratch = alloc_page(GFP_KERNEL);
+	scratch = folio_alloc(GFP_KERNEL, 0);
 	if (scratch == NULL)
 		return -ENOMEM;
 
 	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
-	xdr_set_scratch_page(&stream, scratch);
+	xdr_set_scratch_folio(&stream, scratch);
 
 	do {
 		status = nfs_readdir_entry_decode(desc, entry, &stream);
@@ -891,7 +891,7 @@ static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc,
 	if (folio != *arrays)
 		nfs_readdir_folio_unlock_and_put(folio);
 
-	put_page(scratch);
+	folio_put(scratch);
 	return status;
 }
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 8059ece82468..d020aab40c64 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -161,6 +161,8 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t result;
 
+	trace_nfs_file_read(iocb, to);
+
 	if (iocb->ki_flags & IOCB_DIRECT)
 		return nfs_file_direct_read(iocb, to, false);
 
@@ -361,6 +363,8 @@ static bool nfs_want_read_modify_write(struct file *file, struct folio *folio,
 
 	if (pnfs_ld_read_whole_page(file_inode(file)))
 		return true;
+	if (folio_test_dropbehind(folio))
+		return false;
 	/* Open for reading too? */
 	if (file->f_mode & FMODE_READ)
 		return true;
@@ -380,22 +384,23 @@ static int nfs_write_begin(const struct kiocb *iocb,
 			   loff_t pos, unsigned len, struct folio **foliop,
 			   void **fsdata)
 {
-	fgf_t fgp = FGP_WRITEBEGIN;
 	struct folio *folio;
 	struct file *file = iocb->ki_filp;
 	int once_thru = 0;
 	int ret;
 
+	trace_nfs_write_begin(file_inode(file), pos, len);
+
 	dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
 		file, mapping->host->i_ino, len, (long long) pos);
 	nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos);
 
-	fgp |= fgf_set_order(len);
 start:
-	folio = __filemap_get_folio(mapping, pos >> PAGE_SHIFT, fgp,
-				    mapping_gfp_mask(mapping));
-	if (IS_ERR(folio))
-		return PTR_ERR(folio);
+	folio = write_begin_get_folio(iocb, mapping, pos >> PAGE_SHIFT, len);
+	if (IS_ERR(folio)) {
+		ret = PTR_ERR(folio);
+		goto out;
+	}
 	*foliop = folio;
 
 	ret = nfs_flush_incompatible(file, folio);
@@ -405,11 +410,14 @@ start:
 	} else if (!once_thru &&
 		   nfs_want_read_modify_write(file, folio, pos, len)) {
 		once_thru = 1;
+		folio_clear_dropbehind(folio);
 		ret = nfs_read_folio(file, folio);
 		folio_put(folio);
 		if (!ret)
 			goto start;
 	}
+out:
+	trace_nfs_write_begin_done(file_inode(file), pos, len, ret);
 	return ret;
 }
 
@@ -423,6 +431,7 @@ static int nfs_write_end(const struct kiocb *iocb,
 	unsigned offset = offset_in_folio(folio, pos);
 	int status;
 
+	trace_nfs_write_end(file_inode(file), pos, len);
 	dfprintk(PAGECACHE, "NFS: write_end(%pD2(%lu), %u@%lld)\n",
 		file, mapping->host->i_ino, len, (long long) pos);
 
@@ -451,13 +460,16 @@ static int nfs_write_end(const struct kiocb *iocb,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (status < 0)
+	if (status < 0) {
+		trace_nfs_write_end_done(file_inode(file), pos, len, status);
 		return status;
+	}
 	NFS_I(mapping->host)->write_io += copied;
 
 	if (nfs_ctx_key_to_expire(ctx, mapping->host))
 		nfs_wb_all(mapping->host);
 
+	trace_nfs_write_end_done(file_inode(file), pos, len, copied);
 	return copied;
 }
 
@@ -690,6 +702,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	errseq_t since;
 	int error;
 
+	trace_nfs_file_write(iocb, from);
+
 	result = nfs_key_timeout_notify(file, inode);
 	if (result)
 		return result;
@@ -949,5 +963,6 @@ const struct file_operations nfs_file_operations = {
 	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= simple_nosetlease,
+	.fop_flags	= FOP_DONTCACHE,
 };
 EXPORT_SYMBOL_GPL(nfs_file_operations);
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index d39a1f58e18d..5c4551117c58 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -646,19 +646,19 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 {
 	struct xdr_stream stream;
 	struct xdr_buf buf;
-	struct page *scratch;
+	struct folio *scratch;
 	__be32 *p;
 	uint32_t nfl_util;
 	int i;
 
 	dprintk("%s: set_layout_map Begin\n", __func__);
 
-	scratch = alloc_page(gfp_flags);
+	scratch = folio_alloc(gfp_flags, 0);
 	if (!scratch)
 		return -ENOMEM;
 
 	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
-	xdr_set_scratch_page(&stream, scratch);
+	xdr_set_scratch_folio(&stream, scratch);
 
 	/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
 	 * num_fh (4) */
@@ -724,11 +724,11 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 			fl->fh_array[i]->size);
 	}
 
-	__free_page(scratch);
+	folio_put(scratch);
 	return 0;
 
 out_err:
-	__free_page(scratch);
+	folio_put(scratch);
 	return -EIO;
 }
 
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 29d9234d5c08..df79aeb68db4 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -73,18 +73,18 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
 	struct xdr_stream stream;
 	struct xdr_buf buf;
-	struct page *scratch;
+	struct folio *scratch;
 	struct list_head dsaddrs;
 	struct nfs4_pnfs_ds_addr *da;
 	struct net *net = server->nfs_client->cl_net;
 
 	/* set up xdr stream */
-	scratch = alloc_page(gfp_flags);
+	scratch = folio_alloc(gfp_flags, 0);
 	if (!scratch)
 		goto out_err;
 
 	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
-	xdr_set_scratch_page(&stream, scratch);
+	xdr_set_scratch_folio(&stream, scratch);
 
 	/* Get the stripe count (number of stripe index) */
 	p = xdr_inline_decode(&stream, 4);
@@ -186,7 +186,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 		}
 	}
 
-	__free_page(scratch);
+	folio_put(scratch);
 	return dsaddr;
 
 out_err_drain_dsaddrs:
@@ -204,7 +204,7 @@ out_err_free_deviceid:
 out_err_free_stripe_indices:
 	kfree(stripe_indices);
 out_err_free_scratch:
-	__free_page(scratch);
+	folio_put(scratch);
 out_err:
 	dprintk("%s ERROR: returning NULL\n", __func__);
 	return NULL;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 9edb5f9b0c4e..df01d2876b68 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -47,7 +47,7 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
 			       int dev_limit, enum nfs4_ff_op_type type);
 static void ff_layout_encode_ff_layoutupdate(struct xdr_stream *xdr,
 			      const struct nfs42_layoutstat_devinfo *devinfo,
-			      struct nfs4_ff_layout_mirror *mirror);
+			      struct nfs4_ff_layout_ds_stripe *dss_info);
 
 static struct pnfs_layout_hdr *
 ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
@@ -164,31 +164,32 @@ decode_name(struct xdr_stream *xdr, u32 *id)
 }
 
 static struct nfsd_file *
-ff_local_open_fh(struct pnfs_layout_segment *lseg, u32 ds_idx,
+ff_local_open_fh(struct pnfs_layout_segment *lseg, u32 ds_idx, u32 dss_id,
 		 struct nfs_client *clp, const struct cred *cred,
 		 struct nfs_fh *fh, fmode_t mode)
 {
 #if IS_ENABLED(CONFIG_NFS_LOCALIO)
 	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
 
-	return nfs_local_open_fh(clp, cred, fh, &mirror->nfl, mode);
+	return nfs_local_open_fh(clp, cred, fh, &mirror->dss[dss_id].nfl, mode);
 #else
 	return NULL;
 #endif
 }
 
-static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
-		const struct nfs4_ff_layout_mirror *m2)
+static bool ff_dss_match_fh(const struct nfs4_ff_layout_ds_stripe *dss1,
+		const struct nfs4_ff_layout_ds_stripe *dss2)
 {
 	int i, j;
 
-	if (m1->fh_versions_cnt != m2->fh_versions_cnt)
+	if (dss1->fh_versions_cnt != dss2->fh_versions_cnt)
 		return false;
-	for (i = 0; i < m1->fh_versions_cnt; i++) {
+
+	for (i = 0; i < dss1->fh_versions_cnt; i++) {
 		bool found_fh = false;
-		for (j = 0; j < m2->fh_versions_cnt; j++) {
-			if (nfs_compare_fh(&m1->fh_versions[i],
-					&m2->fh_versions[j]) == 0) {
+		for (j = 0; j < dss2->fh_versions_cnt; j++) {
+			if (nfs_compare_fh(&dss1->fh_versions[i],
+					&dss2->fh_versions[j]) == 0) {
 				found_fh = true;
 				break;
 			}
@@ -199,6 +200,38 @@ static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
 	return true;
 }
 
+static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
+		const struct nfs4_ff_layout_mirror *m2)
+{
+	u32 dss_id;
+
+	if (m1->dss_count != m2->dss_count)
+		return false;
+
+	for (dss_id = 0; dss_id < m1->dss_count; dss_id++)
+		if (!ff_dss_match_fh(&m1->dss[dss_id], &m2->dss[dss_id]))
+			return false;
+
+	return true;
+}
+
+static bool ff_mirror_match_devid(const struct nfs4_ff_layout_mirror *m1,
+		const struct nfs4_ff_layout_mirror *m2)
+{
+	u32 dss_id;
+
+	if (m1->dss_count != m2->dss_count)
+		return false;
+
+	for (dss_id = 0; dss_id < m1->dss_count; dss_id++)
+		if (memcmp(&m1->dss[dss_id].devid,
+			   &m2->dss[dss_id].devid,
+			   sizeof(m1->dss[dss_id].devid)) != 0)
+			return false;
+
+	return true;
+}
+
 static struct nfs4_ff_layout_mirror *
 ff_layout_add_mirror(struct pnfs_layout_hdr *lo,
 		struct nfs4_ff_layout_mirror *mirror)
@@ -209,7 +242,7 @@ ff_layout_add_mirror(struct pnfs_layout_hdr *lo,
 
 	spin_lock(&inode->i_lock);
 	list_for_each_entry(pos, &ff_layout->mirrors, mirrors) {
-		if (memcmp(&mirror->devid, &pos->devid, sizeof(pos->devid)) != 0)
+		if (!ff_mirror_match_devid(mirror, pos))
 			continue;
 		if (!ff_mirror_match_fh(mirror, pos))
 			continue;
@@ -240,29 +273,37 @@ ff_layout_remove_mirror(struct nfs4_ff_layout_mirror *mirror)
 static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
 {
 	struct nfs4_ff_layout_mirror *mirror;
+	u32 dss_id;
 
 	mirror = kzalloc(sizeof(*mirror), gfp_flags);
 	if (mirror != NULL) {
 		spin_lock_init(&mirror->lock);
 		refcount_set(&mirror->ref, 1);
 		INIT_LIST_HEAD(&mirror->mirrors);
-		nfs_localio_file_init(&mirror->nfl);
+		for (dss_id = 0; dss_id < mirror->dss_count; dss_id++)
+			nfs_localio_file_init(&mirror->dss[dss_id].nfl);
 	}
 	return mirror;
 }
 
 static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
 {
-	const struct cred *cred;
+	const struct cred	*cred;
+	u32 dss_id;
 
 	ff_layout_remove_mirror(mirror);
-	kfree(mirror->fh_versions);
-	nfs_close_local_fh(&mirror->nfl);
-	cred = rcu_access_pointer(mirror->ro_cred);
-	put_cred(cred);
-	cred = rcu_access_pointer(mirror->rw_cred);
-	put_cred(cred);
-	nfs4_ff_layout_put_deviceid(mirror->mirror_ds);
+
+	for (dss_id = 0; dss_id < mirror->dss_count; dss_id++) {
+		kfree(mirror->dss[dss_id].fh_versions);
+		cred = rcu_access_pointer(mirror->dss[dss_id].ro_cred);
+		put_cred(cred);
+		cred = rcu_access_pointer(mirror->dss[dss_id].rw_cred);
+		put_cred(cred);
+		nfs_close_local_fh(&mirror->dss[dss_id].nfl);
+		nfs4_ff_layout_put_deviceid(mirror->dss[dss_id].mirror_ds);
+	}
+
+	kfree(mirror->dss);
 	kfree(mirror);
 }
 
@@ -366,14 +407,24 @@ ff_layout_add_lseg(struct pnfs_layout_hdr *lo,
 			free_me);
 }
 
+static u32 ff_mirror_efficiency_sum(const struct nfs4_ff_layout_mirror *mirror)
+{
+	u32 dss_id, sum = 0;
+
+	for (dss_id = 0; dss_id < mirror->dss_count; dss_id++)
+		sum += mirror->dss[dss_id].efficiency;
+
+	return sum;
+}
+
 static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls)
 {
 	int i, j;
 
 	for (i = 0; i < fls->mirror_array_cnt - 1; i++) {
 		for (j = i + 1; j < fls->mirror_array_cnt; j++)
-			if (fls->mirror_array[i]->efficiency <
-			    fls->mirror_array[j]->efficiency)
+			if (ff_mirror_efficiency_sum(fls->mirror_array[i]) <
+			    ff_mirror_efficiency_sum(fls->mirror_array[j]))
 				swap(fls->mirror_array[i],
 				     fls->mirror_array[j]);
 	}
@@ -388,20 +439,21 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 	struct nfs4_ff_layout_segment *fls = NULL;
 	struct xdr_stream stream;
 	struct xdr_buf buf;
-	struct page *scratch;
+	struct folio *scratch;
 	u64 stripe_unit;
 	u32 mirror_array_cnt;
 	__be32 *p;
 	int i, rc;
+	struct nfs4_ff_layout_ds_stripe *dss_info;
 
 	dprintk("--> %s\n", __func__);
-	scratch = alloc_page(gfp_flags);
+	scratch = folio_alloc(gfp_flags, 0);
 	if (!scratch)
 		return ERR_PTR(-ENOMEM);
 
 	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages,
 			      lgr->layoutp->len);
-	xdr_set_scratch_page(&stream, scratch);
+	xdr_set_scratch_folio(&stream, scratch);
 
 	/* stripe unit and mirror_array_cnt */
 	rc = -EIO;
@@ -427,23 +479,32 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 	fls->mirror_array_cnt = mirror_array_cnt;
 	fls->stripe_unit = stripe_unit;
 
+	u32 dss_count = 0;
 	for (i = 0; i < fls->mirror_array_cnt; i++) {
 		struct nfs4_ff_layout_mirror *mirror;
 		struct cred *kcred;
 		const struct cred __rcu *cred;
 		kuid_t uid;
 		kgid_t gid;
-		u32 ds_count, fh_count, id;
-		int j;
+		u32 fh_count, id;
+		int j, dss_id;
 
 		rc = -EIO;
 		p = xdr_inline_decode(&stream, 4);
 		if (!p)
 			goto out_err_free;
-		ds_count = be32_to_cpup(p);
 
-		/* FIXME: allow for striping? */
-		if (ds_count != 1)
+		// Ensure all mirrors have same stripe count.
+		if (dss_count == 0)
+			dss_count = be32_to_cpup(p);
+		else if (dss_count != be32_to_cpup(p))
+			goto out_err_free;
+
+		if (dss_count > NFS4_FLEXFILE_LAYOUT_MAX_STRIPE_CNT ||
+		    dss_count == 0)
+			goto out_err_free;
+
+		if (dss_count > 1 && stripe_unit == 0)
 			goto out_err_free;
 
 		fls->mirror_array[i] = ff_layout_alloc_mirror(gfp_flags);
@@ -452,91 +513,105 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 			goto out_err_free;
 		}
 
-		fls->mirror_array[i]->ds_count = ds_count;
+		fls->mirror_array[i]->dss_count = dss_count;
+		fls->mirror_array[i]->dss =
+		    kcalloc(dss_count, sizeof(struct nfs4_ff_layout_ds_stripe),
+			    gfp_flags);
 
-		/* deviceid */
-		rc = decode_deviceid(&stream, &fls->mirror_array[i]->devid);
-		if (rc)
-			goto out_err_free;
+		for (dss_id = 0; dss_id < dss_count; dss_id++) {
+			dss_info = &fls->mirror_array[i]->dss[dss_id];
+			dss_info->mirror = fls->mirror_array[i];
 
-		/* efficiency */
-		rc = -EIO;
-		p = xdr_inline_decode(&stream, 4);
-		if (!p)
-			goto out_err_free;
-		fls->mirror_array[i]->efficiency = be32_to_cpup(p);
+			/* deviceid */
+			rc = decode_deviceid(&stream, &dss_info->devid);
+			if (rc)
+				goto out_err_free;
 
-		/* stateid */
-		rc = decode_pnfs_stateid(&stream, &fls->mirror_array[i]->stateid);
-		if (rc)
-			goto out_err_free;
+			/* efficiency */
+			rc = -EIO;
+			p = xdr_inline_decode(&stream, 4);
+			if (!p)
+				goto out_err_free;
+			dss_info->efficiency = be32_to_cpup(p);
 
-		/* fh */
-		rc = -EIO;
-		p = xdr_inline_decode(&stream, 4);
-		if (!p)
-			goto out_err_free;
-		fh_count = be32_to_cpup(p);
+			/* stateid */
+			rc = decode_pnfs_stateid(&stream, &dss_info->stateid);
+			if (rc)
+				goto out_err_free;
 
-		fls->mirror_array[i]->fh_versions =
-			kcalloc(fh_count, sizeof(struct nfs_fh),
-				gfp_flags);
-		if (fls->mirror_array[i]->fh_versions == NULL) {
-			rc = -ENOMEM;
-			goto out_err_free;
-		}
+			/* fh */
+			rc = -EIO;
+			p = xdr_inline_decode(&stream, 4);
+			if (!p)
+				goto out_err_free;
+			fh_count = be32_to_cpup(p);
 
-		for (j = 0; j < fh_count; j++) {
-			rc = decode_nfs_fh(&stream,
-					   &fls->mirror_array[i]->fh_versions[j]);
+			dss_info->fh_versions =
+			    kcalloc(fh_count, sizeof(struct nfs_fh),
+				    gfp_flags);
+			if (dss_info->fh_versions == NULL) {
+				rc = -ENOMEM;
+				goto out_err_free;
+			}
+
+			for (j = 0; j < fh_count; j++) {
+				rc = decode_nfs_fh(&stream,
+						   &dss_info->fh_versions[j]);
+				if (rc)
+					goto out_err_free;
+			}
+
+			dss_info->fh_versions_cnt = fh_count;
+
+			/* user */
+			rc = decode_name(&stream, &id);
 			if (rc)
 				goto out_err_free;
-		}
 
-		fls->mirror_array[i]->fh_versions_cnt = fh_count;
+			uid = make_kuid(&init_user_ns, id);
 
-		/* user */
-		rc = decode_name(&stream, &id);
-		if (rc)
-			goto out_err_free;
+			/* group */
+			rc = decode_name(&stream, &id);
+			if (rc)
+				goto out_err_free;
 
-		uid = make_kuid(&init_user_ns, id);
+			gid = make_kgid(&init_user_ns, id);
 
-		/* group */
-		rc = decode_name(&stream, &id);
-		if (rc)
-			goto out_err_free;
+			if (gfp_flags & __GFP_FS)
+				kcred = prepare_kernel_cred(&init_task);
+			else {
+				unsigned int nofs_flags = memalloc_nofs_save();
 
-		gid = make_kgid(&init_user_ns, id);
+				kcred = prepare_kernel_cred(&init_task);
+				memalloc_nofs_restore(nofs_flags);
+			}
+			rc = -ENOMEM;
+			if (!kcred)
+				goto out_err_free;
+			kcred->fsuid = uid;
+			kcred->fsgid = gid;
+			cred = RCU_INITIALIZER(kcred);
 
-		if (gfp_flags & __GFP_FS)
-			kcred = prepare_kernel_cred(&init_task);
-		else {
-			unsigned int nofs_flags = memalloc_nofs_save();
-			kcred = prepare_kernel_cred(&init_task);
-			memalloc_nofs_restore(nofs_flags);
+			if (lgr->range.iomode == IOMODE_READ)
+				rcu_assign_pointer(dss_info->ro_cred, cred);
+			else
+				rcu_assign_pointer(dss_info->rw_cred, cred);
 		}
-		rc = -ENOMEM;
-		if (!kcred)
-			goto out_err_free;
-		kcred->fsuid = uid;
-		kcred->fsgid = gid;
-		cred = RCU_INITIALIZER(kcred);
-
-		if (lgr->range.iomode == IOMODE_READ)
-			rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
-		else
-			rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
 
 		mirror = ff_layout_add_mirror(lh, fls->mirror_array[i]);
 		if (mirror != fls->mirror_array[i]) {
-			/* swap cred ptrs so free_mirror will clean up old */
-			if (lgr->range.iomode == IOMODE_READ) {
-				cred = xchg(&mirror->ro_cred, cred);
-				rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
-			} else {
-				cred = xchg(&mirror->rw_cred, cred);
-				rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);