Merge tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:

   - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC
     request

   - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR()
     dereference

   - Revert buggy NFS readdirplus optimisation

   - NFSv4: Handle the special Linux file open access mode

   - pnfs: Fix a problem where we gratuitously start doing I/O through
     the MDS

  Features:

   - Allow NFS client to set up multiple TCP connections to the server
     using a new 'nconnect=X' mount option. Queue length is used to
     balance load.

   - Enhance statistics reporting to report on all transports when using
     multiple connections.

   - Speed up SUNRPC by removing bh-safe spinlocks

   - Add a mechanism to allow NFSv4 to request that containers set a
     unique per-host identifier for when the hostname is not set.

   - Ensure NFSv4 updates the lease_time after a clientid update

  Bugfixes and cleanup:

   - Fix use-after-free in rpcrdma_post_recvs

   - Fix a memory leak when nfs_match_client() is interrupted

   - Fix buggy file access checking in NFSv4 open for execute

   - disable unsupported client side deduplication

   - Fix spurious client disconnections

   - Fix occasional RDMA transport deadlock

   - Various RDMA cleanups

   - Various tracepoint fixes

   - Fix the TCP callback channel to guarantee the server can actually
     send the number of callback requests that was negotiated at mount
     time"

* tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (68 commits)
  pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS
  pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
  SUNRPC: Optimise transport balancing code
  SUNRPC: Ensure the bvecs are reset when we re-encode the RPC request
  pnfs/flexfiles: Fix PTR_ERR() dereferences in ff_layout_track_ds_error
  NFSv4: Don't use the zero stateid with layoutget
  SUNRPC: Fix up backchannel slot table accounting
  SUNRPC: Fix initialisation of struct rpc_xprt_switch
  SUNRPC: Skip zero-refcount transports
  SUNRPC: Replace division by multiplication in calculation of queue length
  NFSv4: Validate the stateid before applying it to state recovery
  nfs4.0: Refetch lease_time after clientid update
  nfs4: Rename nfs41_setup_state_renewal
  nfs4: Make nfs4_proc_get_lease_time available for nfs4.0
  nfs: Fix copy-and-paste error in debug message
  NFS: Replace 16 seq_printf() calls by seq_puts()
  NFS: Use seq_putc() in nfs_show_stats()
  Revert "NFS: readdirplus optimization by cache mechanism" (memleak)
  SUNRPC: Fix transport accounting when caller specifies an rpc_xprt
  NFS: Record task, client ID, and XID in xdr_status trace points
  ...

27 files changed, 885 insertions, 336 deletions

diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index c587e3c4c6a6..34cdeaecccf6 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -8,7 +8,8 @@ obj-$(CONFIG_NFS_FS) += nfs.o
 CFLAGS_nfstrace.o += -I$(src)
 nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 			   io.o direct.o pagelist.o read.o symlink.o unlink.o \
-			   write.o namespace.o mount_clnt.o nfstrace.o export.o
+			   write.o namespace.o mount_clnt.o nfstrace.o \
+			   export.o sysfs.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_SYSCTL)	+= sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 315967354954..f39924ba050b 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -414,27 +414,39 @@ static __be32
 validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
 		const struct cb_sequenceargs * args)
 {
+	__be32 ret;
+
+	ret = cpu_to_be32(NFS4ERR_BADSLOT);
 	if (args->csa_slotid > tbl->server_highest_slotid)
-		return htonl(NFS4ERR_BADSLOT);
+		goto out_err;
 
 	/* Replay */
 	if (args->csa_sequenceid == slot->seq_nr) {
+		ret = cpu_to_be32(NFS4ERR_DELAY);
 		if (nfs4_test_locked_slot(tbl, slot->slot_nr))
-			return htonl(NFS4ERR_DELAY);
+			goto out_err;
+
 		/* Signal process_op to set this error on next op */
+		ret = cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP);
 		if (args->csa_cachethis == 0)
-			return htonl(NFS4ERR_RETRY_UNCACHED_REP);
+			goto out_err;
 
 		/* Liar! We never allowed you to set csa_cachethis != 0 */
-		return htonl(NFS4ERR_SEQ_FALSE_RETRY);
+		ret = cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY);
+		goto out_err;
 	}
 
 	/* Note: wraparound relies on seq_nr being of type u32 */
-	if (likely(args->csa_sequenceid == slot->seq_nr + 1))
-		return htonl(NFS4_OK);
-
 	/* Misordered request */
-	return htonl(NFS4ERR_SEQ_MISORDERED);
+	ret = cpu_to_be32(NFS4ERR_SEQ_MISORDERED);
+	if (args->csa_sequenceid != slot->seq_nr + 1)
+		goto out_err;
+
+	return cpu_to_be32(NFS4_OK);
+
+out_err:
+	trace_nfs4_cb_seqid_err(args, ret);
+	return ret;
 }
 
 /*
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index d7e4f0848e28..30838304a0bf 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -49,6 +49,7 @@
 #include "pnfs.h"
 #include "nfs.h"
 #include "netns.h"
+#include "sysfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
@@ -175,6 +176,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
 	clp->cl_rpcclient = ERR_PTR(-EINVAL);
 
 	clp->cl_proto = cl_init->proto;
+	clp->cl_nconnect = cl_init->nconnect;
 	clp->cl_net = get_net(cl_init->net);
 
 	clp->cl_principal = "*";
@@ -192,7 +194,7 @@ error_0:
 EXPORT_SYMBOL_GPL(nfs_alloc_client);
 
 #if IS_ENABLED(CONFIG_NFS_V4)
-void nfs_cleanup_cb_ident_idr(struct net *net)
+static void nfs_cleanup_cb_ident_idr(struct net *net)
 {
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
 
@@ -214,7 +216,7 @@ static void pnfs_init_server(struct nfs_server *server)
 }
 
 #else
-void nfs_cleanup_cb_ident_idr(struct net *net)
+static void nfs_cleanup_cb_ident_idr(struct net *net)
 {
 }
 
@@ -406,10 +408,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
 		clp = nfs_match_client(cl_init);
 		if (clp) {
 			spin_unlock(&nn->nfs_client_lock);
-			if (IS_ERR(clp))
-				return clp;
 			if (new)
 				new->rpc_ops->free_client(new);
+			if (IS_ERR(clp))
+				return clp;
 			return nfs_found_client(cl_init, clp);
 		}
 		if (new) {
@@ -493,6 +495,7 @@ int nfs_create_rpc_client(struct nfs_client *clp,
 	struct rpc_create_args args = {
 		.net		= clp->cl_net,
 		.protocol	= clp->cl_proto,
+		.nconnect	= clp->cl_nconnect,
 		.address	= (struct sockaddr *)&clp->cl_addr,
 		.addrsize	= clp->cl_addrlen,
 		.timeout	= cl_init->timeparms,
@@ -658,6 +661,7 @@ static int nfs_init_server(struct nfs_server *server,
 		.net = data->net,
 		.timeparms = &timeparms,
 		.cred = server->cred,
+		.nconnect = data->nfs_server.nconnect,
 	};
 	struct nfs_client *clp;
 	int error;
@@ -1072,6 +1076,18 @@ void nfs_clients_init(struct net *net)
 #endif
 	spin_lock_init(&nn->nfs_client_lock);
 	nn->boot_time = ktime_get_real();
+
+	nfs_netns_sysfs_setup(nn, net);
+}
+
+void nfs_clients_exit(struct net *net)
+{
+	struct nfs_net *nn = net_generic(net, nfs_net_id);
+
+	nfs_netns_sysfs_destroy(nn);
+	nfs_cleanup_cb_ident_idr(net);
+	WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
+	WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 57b6a45576ad..8d501093660f 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -80,6 +80,10 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
 		ctx->dup_cookie = 0;
 		ctx->cred = get_cred(cred);
 		spin_lock(&dir->i_lock);
+		if (list_empty(&nfsi->open_files) &&
+		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
+			nfsi->cache_validity |= NFS_INO_INVALID_DATA |
+				NFS_INO_REVAL_FORCED;
 		list_add(&ctx->list, &nfsi->open_files);
 		spin_unlock(&dir->i_lock);
 		return ctx;
@@ -140,19 +144,12 @@ struct nfs_cache_array {
 	struct nfs_cache_array_entry array[0];
 };
 
-struct readdirvec {
-	unsigned long nr;
-	unsigned long index;
-	struct page *pages[NFS_MAX_READDIR_RAPAGES];
-};
-
 typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool);
 typedef struct {
 	struct file	*file;
 	struct page	*page;
 	struct dir_context *ctx;
 	unsigned long	page_index;
-	struct readdirvec pvec;
 	u64		*dir_cookie;
 	u64		last_cookie;
 	loff_t		current_index;
@@ -532,10 +529,6 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 	struct nfs_cache_array *array;
 	unsigned int count = 0;
 	int status;
-	int max_rapages = NFS_MAX_READDIR_RAPAGES;
-
-	desc->pvec.index = desc->page_index;
-	desc->pvec.nr = 0;
 
 	scratch = alloc_page(GFP_KERNEL);
 	if (scratch == NULL)
@@ -560,40 +553,20 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 		if (desc->plus)
 			nfs_prime_dcache(file_dentry(desc->file), entry);
 
-		status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]);
-		if (status == -ENOSPC) {
-			desc->pvec.nr++;
-			if (desc->pvec.nr == max_rapages)
-				break;
-			status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]);
-		}
+		status = nfs_readdir_add_to_array(entry, page);
 		if (status != 0)
 			break;
 	} while (!entry->eof);
 
-	/*
-	 * page and desc->pvec.pages[0] are valid, don't need to check
-	 * whether or not to be NULL.
-	 */
-	copy_highpage(page, desc->pvec.pages[0]);
-
 out_nopages:
 	if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
-		array = kmap_atomic(desc->pvec.pages[desc->pvec.nr]);
+		array = kmap(page);
 		array->eof_index = array->size;
 		status = 0;
-		kunmap_atomic(array);
+		kunmap(page);
 	}
 
 	put_page(scratch);
-
-	/*
-	 * desc->pvec.nr > 0 means at least one page was completely filled,
-	 * we should return -ENOSPC. Otherwise function
-	 * nfs_readdir_xdr_to_array will enter infinite loop.
-	 */
-	if (desc->pvec.nr > 0)
-		return -ENOSPC;
 	return status;
 }
 
@@ -627,24 +600,6 @@ out_freepages:
 	return -ENOMEM;
 }
 
-/*
- * nfs_readdir_rapages_init initialize rapages by nfs_cache_array structure.
- */
-static
-void nfs_readdir_rapages_init(nfs_readdir_descriptor_t *desc)
-{
-	struct nfs_cache_array *array;
-	int max_rapages = NFS_MAX_READDIR_RAPAGES;
-	int index;
-
-	for (index = 0; index < max_rapages; index++) {
-		array = kmap_atomic(desc->pvec.pages[index]);
-		memset(array, 0, sizeof(struct nfs_cache_array));
-		array->eof_index = -1;
-		kunmap_atomic(array);
-	}
-}
-
 static
 int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode)
 {
@@ -655,12 +610,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
 	int status = -ENOMEM;
 	unsigned int array_size = ARRAY_SIZE(pages);
 
-	/*
-	 * This means we hit readdir rdpages miss, the preallocated rdpages
-	 * are useless, the preallocate rdpages should be reinitialized.
-	 */
-	nfs_readdir_rapages_init(desc);
-
 	entry.prev_cookie = 0;
 	entry.cookie = desc->last_cookie;
 	entry.eof = 0;
@@ -721,24 +670,9 @@ int nfs_readdir_filler(void *data, struct page* page)
 	struct inode	*inode = file_inode(desc->file);
 	int ret;
 
-	/*
-	 * If desc->page_index in range desc->pvec.index and
-	 * desc->pvec.index + desc->pvec.nr, we get readdir cache hit.
-	 */
-	if (desc->page_index >= desc->pvec.index &&
-		desc->page_index < (desc->pvec.index + desc->pvec.nr)) {
-		/*
-		 * page and desc->pvec.pages[x] are valid, don't need to check
-		 * whether or not to be NULL.
-		 */
-		copy_highpage(page, desc->pvec.pages[desc->page_index - desc->pvec.index]);
-		ret = 0;
-	} else {
-		ret = nfs_readdir_xdr_to_array(desc, page, inode);
-		if (ret < 0)
-			goto error;
-	}
-
+	ret = nfs_readdir_xdr_to_array(desc, page, inode);
+	if (ret < 0)
+		goto error;
 	SetPageUptodate(page);
 
 	if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
@@ -903,7 +837,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 			*desc = &my_desc;
 	struct nfs_open_dir_context *dir_ctx = file->private_data;
 	int res = 0;
-	int max_rapages = NFS_MAX_READDIR_RAPAGES;
 
 	dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
 			file, (long long)ctx->pos);
@@ -923,12 +856,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->decode = NFS_PROTO(inode)->decode_dirent;
 	desc->plus = nfs_use_readdirplus(inode, ctx);
 
-	res = nfs_readdir_alloc_pages(desc->pvec.pages, max_rapages);
-	if (res < 0)
-		return -ENOMEM;
-
-	nfs_readdir_rapages_init(desc);
-
 	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
 	if (res < 0)
@@ -964,7 +891,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 			break;
 	} while (!desc->eof);
 out:
-	nfs_readdir_free_pages(desc->pvec.pages, max_rapages);
 	if (res > 0)
 		res = 0;
 	dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index bcff3bf5ae09..b04e20d28162 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -934,6 +934,10 @@ out_nolseg:
 	if (pgio->pg_error < 0)
 		return;
 out_mds:
+	trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode,
+			0, NFS4_MAX_UINT64, IOMODE_READ,
+			NFS_I(pgio->pg_inode)->layout,
+			pgio->pg_lseg);
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
 	nfs_pageio_reset_read_mds(pgio);
@@ -1000,6 +1004,10 @@ retry:
 	return;
 
 out_mds:
+	trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode,
+			0, NFS4_MAX_UINT64, IOMODE_RW,
+			NFS_I(pgio->pg_inode)->layout,
+			pgio->pg_lseg);
 	pnfs_put_lseg(pgio->pg_lseg);
 	pgio->pg_lseg = NULL;
 	nfs_pageio_reset_write_mds(pgio);
@@ -1026,6 +1034,10 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
 	if (pgio->pg_lseg)
 		return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);
 
+	trace_pnfs_mds_fallback_pg_get_mirror_count(pgio->pg_inode,
+			0, NFS4_MAX_UINT64, IOMODE_RW,
+			NFS_I(pgio->pg_inode)->layout,
+			pgio->pg_lseg);
 	/* no lseg means that pnfs is not in use, so no mirroring here */
 	nfs_pageio_reset_write_mds(pgio);
 out:
@@ -1075,6 +1087,10 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
+		trace_pnfs_mds_fallback_write_done(hdr->inode,
+				hdr->args.offset, hdr->args.count,
+				IOMODE_RW, NFS_I(hdr->inode)->layout,
+				hdr->lseg);
 		task->tk_status = pnfs_write_done_resend_to_mds(hdr);
 	}
 }
@@ -1094,6 +1110,10 @@ static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
 			hdr->args.count,
 			(unsigned long long)hdr->args.offset);
 
+		trace_pnfs_mds_fallback_read_done(hdr->inode,
+				hdr->args.offset, hdr->args.count,
+				IOMODE_READ, NFS_I(hdr->inode)->layout,
+				hdr->lseg);
 		task->tk_status = pnfs_read_done_resend_to_mds(hdr);
 	}
 }
@@ -1827,6 +1847,9 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 out_failed:
 	if (ff_layout_avoid_mds_available_ds(lseg))
 		return PNFS_TRY_AGAIN;
+	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
+			hdr->args.offset, hdr->args.count,
+			IOMODE_READ, NFS_I(hdr->inode)->layout, lseg);
 	return PNFS_NOT_ATTEMPTED;
 }
 
@@ -1892,6 +1915,9 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 out_failed:
 	if (ff_layout_avoid_mds_available_ds(lseg))
 		return PNFS_TRY_AGAIN;
+	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
+			hdr->args.offset, hdr->args.count,
+			IOMODE_RW, NFS_I(hdr->inode)->layout, lseg);
 	return PNFS_NOT_ATTEMPTED;
 }
 
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 19f856f45689..3eda40a320a5 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -257,7 +257,7 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
 	if (status == 0)
 		return 0;
 
-	if (mirror->mirror_ds == NULL)
+	if (IS_ERR_OR_NULL(mirror->mirror_ds))
 		return -EINVAL;
 
 	dserr = kmalloc(sizeof(*dserr), gfp_flags);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 0b4a1a974411..8a1758200b57 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -51,6 +51,7 @@
 #include "pnfs.h"
 #include "nfs.h"
 #include "netns.h"
+#include "sysfs.h"
 
 #include "nfstrace.h"
 
@@ -208,7 +209,7 @@ static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 	}
 
 	if (inode->i_mapping->nrpages == 0)
-		flags &= ~NFS_INO_INVALID_DATA;
+		flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
 	nfsi->cache_validity |= flags;
 	if (flags & NFS_INO_INVALID_DATA)
 		nfs_fscache_invalidate(inode);
@@ -652,7 +653,8 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 	i_size_write(inode, offset);
 	/* Optimisation */
 	if (offset == 0)
-		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA;
+		NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_DATA |
+				NFS_INO_DATA_INVAL_DEFER);
 	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
 
 	spin_unlock(&inode->i_lock);
@@ -1032,6 +1034,10 @@ void nfs_inode_attach_open_context(struct nfs_open_context *ctx)
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	spin_lock(&inode->i_lock);
+	if (list_empty(&nfsi->open_files) &&
+	    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
+		nfsi->cache_validity |= NFS_INO_INVALID_DATA |
+			NFS_INO_REVAL_FORCED;
 	list_add_tail_rcu(&ctx->list, &nfsi->open_files);
 	spin_unlock(&inode->i_lock);
 }
@@ -1100,6 +1106,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 	nfs_fscache_open_file(inode, filp);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nfs_open);
 
 /*
  * This function is called whenever some part of NFS notices that
@@ -1312,7 +1319,8 @@ int nfs_revalidate_mapping(struct inode *inode,
 
 	set_bit(NFS_INO_INVALIDATING, bitlock);
 	smp_wmb();
-	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+	nfsi->cache_validity &= ~(NFS_INO_INVALID_DATA|
+			NFS_INO_DATA_INVAL_DEFER);
 	spin_unlock(&inode->i_lock);
 	trace_nfs_invalidate_mapping_enter(inode);
 	ret = nfs_invalidate_mapping(inode, mapping);
@@ -1870,7 +1878,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				dprintk("NFS: change_attr change on server for file %s/%ld\n",
 						inode->i_sb->s_id,
 						inode->i_ino);
-			}
+			} else if (!have_delegation)
+				nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER;
 			inode_set_iversion_raw(inode, fattr->change_attr);
 			attr_changed = true;
 		}
@@ -2159,12 +2168,8 @@ static int nfs_net_init(struct net *net)
 
 static void nfs_net_exit(struct net *net)
 {
-	struct nfs_net *nn = net_generic(net, nfs_net_id);
-
 	nfs_fs_proc_net_exit(net);
-	nfs_cleanup_cb_ident_idr(net);
-	WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));
-	WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));
+	nfs_clients_exit(net);
 }
 
 static struct pernet_operations nfs_net_ops = {
@@ -2181,6 +2186,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_sysfs_init();
+	if (err < 0)
+		goto out10;
+
 	err = register_pernet_subsys(&nfs_net_ops);
 	if (err < 0)
 		goto out9;
@@ -2244,6 +2253,8 @@ out7:
 out8:
 	unregister_pernet_subsys(&nfs_net_ops);
 out9:
+	nfs_sysfs_exit();
+out10:
 	return err;
 }
 
@@ -2260,6 +2271,7 @@ static void __exit exit_nfs_fs(void)
 	unregister_nfs_fs();
 	nfs_fs_proc_exit();
 	nfsiod_stop();
+	nfs_sysfs_exit();
 }
 
 /* Not quite true; I just maintain it */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 498fab72f70b..a2346a2f8361 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -69,8 +69,7 @@ struct nfs_clone_mount {
  * Maximum number of pages that readdir can use for creating
  * a vmapped array of pages.
  */
-#define NFS_MAX_READDIR_PAGES 64
-#define NFS_MAX_READDIR_RAPAGES 8
+#define NFS_MAX_READDIR_PAGES 8
 
 struct nfs_client_initdata {
 	unsigned long init_flags;
@@ -82,6 +81,7 @@ struct nfs_client_initdata {
 	struct nfs_subversion *nfs_mod;
 	int proto;
 	u32 minorversion;
+	unsigned int nconnect;
 	struct net *net;
 	const struct rpc_timeout *timeparms;
 	const struct cred *cred;
@@ -123,6 +123,7 @@ struct nfs_parsed_mount_data {
 		char			*export_path;
 		int			port;
 		unsigned short		protocol;
+		unsigned short		nconnect;
 	} nfs_server;
 
 	void			*lsm_opts;
@@ -158,6 +159,7 @@ extern void nfs_umount(const struct nfs_mount_request *info);
 /* client.c */
 extern const struct rpc_program nfs_program;
 extern void nfs_clients_init(struct net *net);
+extern void nfs_clients_exit(struct net *net);
 extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *);
 int nfs_create_rpc_client(struct nfs_client *, const struct nfs_client_initdata *, rpc_authflavor_t);
 struct nfs_client *nfs_get_client(const struct nfs_client_initdata *);
@@ -170,7 +172,6 @@ int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
 struct nfs_server *nfs_alloc_server(void);
 void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *);
 
-extern void nfs_cleanup_cb_ident_idr(struct net *);
 extern void nfs_put_client(struct nfs_client *);
 extern void nfs_free_client(struct nfs_client *);
 extern struct nfs_client *nfs4_find_client_ident(struct net *, int);
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index fc9978c58265..c8374f74dce1 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -15,6 +15,8 @@ struct bl_dev_msg {
 	uint32_t major, minor;
 };
 
+struct nfs_netns_client;
+
 struct nfs_net {
 	struct cache_detail *nfs_dns_resolve;
 	struct rpc_pipe *bl_device_pipe;
@@ -29,6 +31,7 @@ struct nfs_net {
 	unsigned short nfs_callback_tcpport6;
 	int cb_users[NFS4_MAX_MINOR_VERSION + 1];
 #endif
+	struct nfs_netns_client *nfs_client;
 	spinlock_t nfs_client_lock;
 	ktime_t boot_time;
 #ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 572794dab4b1..cbc17a203248 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -151,7 +151,7 @@ static int decode_stat(struct xdr_stream *xdr, enum nfs_stat *status)
 	return 0;
 out_status:
 	*status = be32_to_cpup(p);
-	trace_nfs_xdr_status((int)*status);
+	trace_nfs_xdr_status(xdr, (int)*status);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index fb0c425b5d45..148ceb74d27c 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -102,6 +102,9 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 		return ERR_PTR(-EINVAL);
 	cl_init.hostname = buf;
 
+	if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP)
+		cl_init.nconnect = mds_clp->cl_nconnect;
+
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index abbbdde97e31..602767850b36 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -343,7 +343,7 @@ static int decode_nfsstat3(struct xdr_stream *xdr, enum nfs_stat *status)
 	return 0;
 out_status:
 	*status = be32_to_cpup(p);
-	trace_nfs_xdr_status((int)*status);
+	trace_nfs_xdr_status(xdr, (int)*status);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 8a38a254f516..d778dad9a75e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -312,12 +312,12 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid,
 		const struct nfs_lock_context *l_ctx,
 		fmode_t fmode);
 
+extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
+		struct nfs_fsinfo *fsinfo);
 #if defined(CONFIG_NFS_V4_1)
 extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
 extern int nfs4_proc_create_session(struct nfs_client *, const struct cred *);
 extern int nfs4_proc_destroy_session(struct nfs4_session *, const struct cred *);
-extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
-		struct nfs_fsinfo *fsinfo);
 extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data,
 				  bool sync);
 extern int nfs4_detect_session_trunking(struct nfs_client *clp,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 81b9b6d7927a..616393a01c06 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -859,7 +859,8 @@ static int nfs4_set_client(struct nfs_server *server,
 		const size_t addrlen,
 		const char *ip_addr,
 		int proto, const struct rpc_timeout *timeparms,
-		u32 minorversion, struct net *net)
+		u32 minorversion, unsigned int nconnect,
+		struct net *net)
 {
 	struct nfs_client_initdata cl_init = {
 		.hostname = hostname,
@@ -875,6 +876,8 @@ static int nfs4_set_client(struct nfs_server *server,
 	};
 	struct nfs_client *clp;
 
+	if (minorversion > 0 && proto == XPRT_TRANSPORT_TCP)
+		cl_init.nconnect = nconnect;
 	if (server->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 	if (server->options & NFS_OPTION_MIGRATION)
@@ -941,6 +944,9 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 		return ERR_PTR(-EINVAL);
 	cl_init.hostname = buf;
 
+	if (mds_clp->cl_nconnect > 1 && ds_proto == XPRT_TRANSPORT_TCP)
+		cl_init.nconnect = mds_clp->cl_nconnect;
+
 	if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
 		__set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
@@ -1074,6 +1080,7 @@ static int nfs4_init_server(struct nfs_server *server,
 			data->nfs_server.protocol,
 			&timeparms,
 			data->minorversion,
+			data->nfs_server.nconnect,
 			data->net);
 	if (error < 0)
 		return error;
@@ -1163,6 +1170,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 				XPRT_TRANSPORT_RDMA,
 				parent_server->client->cl_timeout,
 				parent_client->cl_mvops->minor_version,
+				parent_client->cl_nconnect,
 				parent_client->cl_net);
 	if (!error)
 		goto init_server;
@@ -1176,6 +1184,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 				XPRT_TRANSPORT_TCP,
 				parent_server->client->cl_timeout,
 				parent_client->cl_mvops->minor_version,
+				parent_client->cl_nconnect,
 				parent_client->cl_net);
 	if (error < 0)
 		goto error;
@@ -1271,7 +1280,8 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 	set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	error = nfs4_set_client(server, hostname, sap, salen, buf,
 				clp->cl_proto, clnt->cl_timeout,
-				clp->cl_minorversion, net);
+				clp->cl_minorversion,
+				clp->cl_nconnect, net);
 	clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	if (error != 0) {
 		nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index f4157eb1f69d..96db471ca2e5 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -49,7 +49,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 		return err;
 
 	if ((openflags & O_ACCMODE) == 3)
-		openflags--;
+		return nfs_open(inode, filp);
 
 	/* We can't create new files here */
 	openflags &= ~(O_CREAT|O_EXCL);
@@ -204,7 +204,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 	bool same_inode = false;
 	int ret;
 
-	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+	/* NFS does not support deduplication. */
+	if (remap_flags & REMAP_FILE_DEDUP)
+		return -EOPNOTSUPP;
+
+	if (remap_flags & ~REMAP_FILE_ADVISORY)
 		return -EINVAL;
 
 	/* check alignment w.r.t. clone_blksize */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6418cb6c079b..39896afc6edf 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -428,6 +428,22 @@ static int nfs4_delay(long *timeout, bool interruptible)
 	return nfs4_delay_killable(timeout);
 }
 
+static const nfs4_stateid *
+nfs4_recoverable_stateid(const nfs4_stateid *stateid)
+{
+	if (!stateid)
+		return NULL;
+	switch (stateid->type) {
+	case NFS4_OPEN_STATEID_TYPE:
+	case NFS4_LOCK_STATEID_TYPE:
+	case NFS4_DELEGATION_STATEID_TYPE:
+		return stateid;
+	default:
+		break;
+	}
+	return NULL;
+}
+
 /* This is the error handling routine for processes that are allowed
  * to sleep.
  */
@@ -436,7 +452,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state *state = exception->state;
-	const nfs4_stateid *stateid = exception->stateid;
+	const nfs4_stateid *stateid;
 	struct inode *inode = exception->inode;
 	int ret = errorcode;