Merge tag 'nfs-for-5.10-1' of git://git.linux-nfs.org/projects/anna/linux-nfs

Pull NFS client updates from Anna Schumaker:
 "Stable Fixes:
   - Wait for stateid updates after CLOSE/OPEN_DOWNGRADE # v5.4+
   - Fix nfs_path in case of a rename retry
   - Support EXCHID4_FLAG_SUPP_FENCE_OPS v4.2 EXCHANGE_ID flag

  New features and improvements:
   - Replace dprintk() calls with tracepoints
   - Make cache consistency bitmap dynamic
   - Added support for the NFS v4.2 READ_PLUS operation
   - Improvements to net namespace uniquifier

  Other bugfixes and cleanups:
   - Remove redundant clnt pointer
   - Don't update timeout values on connection resets
   - Remove redundant tracepoints
   - Various cleanups to comments
   - Fix oops when trying to use copy_file_range with v4.0 source server
   - Improvements to flexfiles mirrors
   - Add missing 'local_lock=posix' mount option"

* tag 'nfs-for-5.10-1' of git://git.linux-nfs.org/projects/anna/linux-nfs: (55 commits)
  NFSv4.2: support EXCHGID4_FLAG_SUPP_FENCE_OPS 4.2 EXCHANGE_ID flag
  NFSv4: Fix up RCU annotations for struct nfs_netns_client
  NFS: Only reference user namespace from nfs4idmap struct instead of cred
  nfs: add missing "posix" local_lock constant table definition
  NFSv4: Use the net namespace uniquifier if it is set
  NFSv4: Clean up initialisation of uniquified client id strings
  NFS: Decode a full READ_PLUS reply
  SUNRPC: Add an xdr_align_data() function
  NFS: Add READ_PLUS hole segment decoding
  SUNRPC: Add the ability to expand holes in data pages
  SUNRPC: Split out _shift_data_right_tail()
  SUNRPC: Split out xdr_realign_pages() from xdr_align_pages()
  NFS: Add READ_PLUS data segment support
  NFS: Use xdr_page_pos() in NFSv4 decode_getacl()
  SUNRPC: Implement a xdr_page_pos() function
  SUNRPC: Split out a function for setting current page
  NFS: fix nfs_path in case of a rename retry
  fs: nfs: return per memcg count for xattr shrinkers
  NFSv4: Wait for stateid updates after CLOSE/OPEN_DOWNGRADE
  nfs: remove incorrect fallthrough label
  ...

16 files changed, 397 insertions, 115 deletions

diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 1eabd91870e6..1d9488cf0534 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -417,7 +417,7 @@ void nsm_release(struct nsm_handle *nsm)
 /*
  * XDR functions for NSM.
  *
- * See http://www.opengroup.org/ for details on the Network
+ * See https://www.opengroup.org/ for details on the Network
  * Status Monitor wire protocol.
  */
 
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 222afba70bc0..29ec8b09a52d 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -94,6 +94,7 @@ enum {
 static const struct constant_table nfs_param_enums_local_lock[] = {
 	{ "all",		Opt_local_lock_all },
 	{ "flock",	Opt_local_lock_flock },
+	{ "posix",	Opt_local_lock_posix },
 	{ "none",		Opt_local_lock_none },
 	{}
 };
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 6b063227e34e..2bcbe38afe2e 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -32,9 +32,9 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
 /*
  * nfs_path - reconstruct the path given an arbitrary dentry
  * @base - used to return pointer to the end of devname part of path
- * @dentry - pointer to dentry
+ * @dentry_in - pointer to dentry
  * @buffer - result buffer
- * @buflen - length of buffer
+ * @buflen_in - length of buffer
  * @flags - options (see below)
  *
  * Helper function for constructing the server pathname
@@ -49,15 +49,19 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ;
  *		       the original device (export) name
  *		       (if unset, the original name is returned verbatim)
  */
-char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen,
-	       unsigned flags)
+char *nfs_path(char **p, struct dentry *dentry_in, char *buffer,
+	       ssize_t buflen_in, unsigned flags)
 {
 	char *end;
 	int namelen;
 	unsigned seq;
 	const char *base;
+	struct dentry *dentry;
+	ssize_t buflen;
 
 rename_retry:
+	buflen = buflen_in;
+	dentry = dentry_in;
 	end = buffer+buflen;
 	*--end = '\0';
 	buflen--;
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index 86777996cfec..b51424ff8159 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -67,7 +67,6 @@ struct nfs4_xattr_bucket {
 
 struct nfs4_xattr_cache {
 	struct kref ref;
-	spinlock_t hash_lock;	/* protects hashtable and lru */
 	struct nfs4_xattr_bucket buckets[NFS4_XATTR_HASH_SIZE];
 	struct list_head lru;
 	struct list_head dispose;
@@ -882,7 +881,7 @@ nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc)
 {
 	unsigned long count;
 
-	count = list_lru_count(&nfs4_xattr_cache_lru);
+	count = list_lru_shrink_count(&nfs4_xattr_cache_lru, sc);
 	return vfs_pressure_ratio(count);
 }
 
@@ -976,7 +975,7 @@ nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc)
 	lru = (shrink == &nfs4_xattr_large_entry_shrinker) ?
 	    &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru;
 
-	count = list_lru_count(lru);
+	count = list_lru_shrink_count(lru, sc);
 	return vfs_pressure_ratio(count);
 }
 
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index cc50085e151c..0dc31ad2362e 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -45,6 +45,15 @@
 #define encode_deallocate_maxsz		(op_encode_hdr_maxsz + \
 					 encode_fallocate_maxsz)
 #define decode_deallocate_maxsz		(op_decode_hdr_maxsz)
+#define encode_read_plus_maxsz		(op_encode_hdr_maxsz + \
+					 encode_stateid_maxsz + 3)
+#define NFS42_READ_PLUS_SEGMENT_SIZE	(1 /* data_content4 */ + \
+					 2 /* data_info4.di_offset */ + \
+					 2 /* data_info4.di_length */)
+#define decode_read_plus_maxsz		(op_decode_hdr_maxsz + \
+					 1 /* rpr_eof */ + \
+					 1 /* rpr_contents count */ + \
+					 2 * NFS42_READ_PLUS_SEGMENT_SIZE)
 #define encode_seek_maxsz		(op_encode_hdr_maxsz + \
 					 encode_stateid_maxsz + \
 					 2 /* offset */ + \
@@ -128,6 +137,14 @@
 					 decode_putfh_maxsz + \
 					 decode_deallocate_maxsz + \
 					 decode_getattr_maxsz)
+#define NFS4_enc_read_plus_sz		(compound_encode_hdr_maxsz + \
+					 encode_sequence_maxsz + \
+					 encode_putfh_maxsz + \
+					 encode_read_plus_maxsz)
+#define NFS4_dec_read_plus_sz		(compound_decode_hdr_maxsz + \
+					 decode_sequence_maxsz + \
+					 decode_putfh_maxsz + \
+					 decode_read_plus_maxsz)
 #define NFS4_enc_seek_sz		(compound_encode_hdr_maxsz + \
 					 encode_sequence_maxsz + \
 					 encode_putfh_maxsz + \
@@ -324,6 +341,16 @@ static void encode_deallocate(struct xdr_stream *xdr,
 	encode_fallocate(xdr, args);
 }
 
+static void encode_read_plus(struct xdr_stream *xdr,
+			     const struct nfs_pgio_args *args,
+			     struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_READ_PLUS, decode_read_plus_maxsz, hdr);
+	encode_nfs4_stateid(xdr, &args->stateid);
+	encode_uint64(xdr, args->offset);
+	encode_uint32(xdr, args->count);
+}
+
 static void encode_seek(struct xdr_stream *xdr,
 			const struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
@@ -723,6 +750,28 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 }
 
 /*
+ * Encode READ_PLUS request
+ */
+static void nfs4_xdr_enc_read_plus(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const void *data)
+{
+	const struct nfs_pgio_args *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_read_plus(xdr, args, &hdr);
+
+	rpc_prepare_reply_pages(req, args->pages, args->pgbase,
+				args->count, hdr.replen);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode SEEK request
  */
 static void nfs4_xdr_enc_seek(struct rpc_rqst *req,
@@ -970,6 +1019,97 @@ static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *re
 	return decode_op_hdr(xdr, OP_DEALLOCATE);
 }
 
+static int decode_read_plus_data(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint32_t count, recvd;
+	uint64_t offset;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	count = be32_to_cpup(p);
+	recvd = xdr_align_data(xdr, res->count, count);
+	res->count += recvd;
+
+	if (count > recvd) {
+		dprintk("NFS: server cheating in read reply: "
+				"count %u > recvd %u\n", count, recvd);
+		*eof = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int decode_read_plus_hole(struct xdr_stream *xdr, struct nfs_pgio_res *res,
+				 uint32_t *eof)
+{
+	uint64_t offset, length, recvd;
+	__be32 *p;
+
+	p = xdr_inline_decode(xdr, 8 + 8);
+	if (unlikely(!p))
+		return -EIO;
+
+	p = xdr_decode_hyper(p, &offset);
+	p = xdr_decode_hyper(p, &length);
+	recvd = xdr_expand_hole(xdr, res->count, length);
+	res->count += recvd;
+
+	if (recvd < length) {
+		*eof = 0;
+		return 1;
+	}
+	return 0;
+}
+
+static int decode_read_plus(struct xdr_stream *xdr, struct nfs_pgio_res *res)
+{
+	uint32_t eof, segments, type;
+	int status, i;
+	__be32 *p;
+
+	status = decode_op_hdr(xdr, OP_READ_PLUS);
+	if (status)
+		return status;
+
+	p = xdr_inline_decode(xdr, 4 + 4);
+	if (unlikely(!p))
+		return -EIO;
+
+	eof = be32_to_cpup(p++);
+	segments = be32_to_cpup(p++);
+	if (segments == 0)
+		goto out;
+
+	for (i = 0; i < segments; i++) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			return -EIO;
+
+		type = be32_to_cpup(p++);
+		if (type == NFS4_CONTENT_DATA)
+			status = decode_read_plus_data(xdr, res, &eof);
+		else if (type == NFS4_CONTENT_HOLE)
+			status = decode_read_plus_hole(xdr, res, &eof);
+		else
+			return -EINVAL;
+
+		if (status < 0)
+			return status;
+		if (status > 0)
+			break;
+	}
+
+out:
+	res->eof = eof;
+	return 0;
+}
+
 static int decode_seek(struct xdr_stream *xdr, struct nfs42_seek_res *res)
 {
 	int status;
@@ -1147,6 +1287,33 @@ out:
 }
 
 /*
+ * Decode READ_PLUS request
+ */
+static int nfs4_xdr_dec_read_plus(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfs_pgio_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_read_plus(xdr, res);
+	if (!status)
+		status = res->count;
+out:
+	return status;
+}
+
+/*
  * Decode SEEK request
  */
 static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 0c9505dc852c..065cb04222a1 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -599,6 +599,14 @@ static inline bool nfs4_stateid_is_newer(const nfs4_stateid *s1, const nfs4_stat
 	return (s32)(be32_to_cpu(s1->seqid) - be32_to_cpu(s2->seqid)) > 0;
 }
 
+static inline bool nfs4_stateid_is_next(const nfs4_stateid *s1, const nfs4_stateid *s2)
+{
+	u32 seq1 = be32_to_cpu(s1->seqid);
+	u32 seq2 = be32_to_cpu(s2->seqid);
+
+	return seq2 == seq1 + 1U || (seq2 == 1U && seq1 == 0xffffffffU);
+}
+
 static inline bool nfs4_stateid_match_or_older(const nfs4_stateid *dst, const nfs4_stateid *src)
 {
 	return nfs4_stateid_match_other(dst, src) &&
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index daacc78a3d48..be7915c861ce 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1045,6 +1045,8 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 	server->caps |= server->nfs_client->cl_mvops->init_caps;
 	if (server->flags & NFS_MOUNT_NORDIRPLUS)
 			server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
 	/*
 	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
 	 * authentication.
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index fdfc77486ace..91be7f628e4a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -145,7 +145,8 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	/* Only offload copy if superblock is the same */
 	if (file_in->f_op != &nfs4_file_operations)
 		return -EXDEV;
-	if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
+	if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY) ||
+	    !nfs_server_capable(file_inode(file_in), NFS_CAP_COPY))
 		return -EOPNOTSUPP;
 	if (file_inode(file_in) == file_inode(file_out))
 		return -EOPNOTSUPP;
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 62e6eea5c516..8d8aba305ecc 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -46,6 +46,7 @@
 #include <keys/user-type.h>
 #include <keys/request_key_auth-type.h>
 #include <linux/module.h>
+#include <linux/user_namespace.h>
 
 #include "internal.h"
 #include "netns.h"
@@ -69,13 +70,13 @@ struct idmap {
 	struct rpc_pipe		*idmap_pipe;
 	struct idmap_legacy_upcalldata *idmap_upcall_data;
 	struct mutex		idmap_mutex;
-	const struct cred	*cred;
+	struct user_namespace	*user_ns;
 };
 
 static struct user_namespace *idmap_userns(const struct idmap *idmap)
 {
-	if (idmap && idmap->cred)
-		return idmap->cred->user_ns;
+	if (idmap && idmap->user_ns)
+		return idmap->user_ns;
 	return &init_user_ns;
 }
 
@@ -286,7 +287,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen,
 	if (ret < 0)
 		return ERR_PTR(ret);
 
-	if (!idmap->cred || idmap->cred->user_ns == &init_user_ns)
+	if (!idmap->user_ns || idmap->user_ns == &init_user_ns)
 		rkey = request_key(&key_type_id_resolver, desc, "");
 	if (IS_ERR(rkey)) {
 		mutex_lock(&idmap->idmap_mutex);
@@ -462,7 +463,7 @@ nfs_idmap_new(struct nfs_client *clp)
 		return -ENOMEM;
 
 	mutex_init(&idmap->idmap_mutex);
-	idmap->cred = get_cred(clp->cl_rpcclient->cl_cred);
+	idmap->user_ns = get_user_ns(clp->cl_rpcclient->cl_cred->user_ns);
 
 	rpc_init_pipe_dir_object(&idmap->idmap_pdo,
 			&nfs_idmap_pipe_dir_object_ops,
@@ -486,7 +487,7 @@ nfs_idmap_new(struct nfs_client *clp)
 err_destroy_pipe:
 	rpc_destroy_pipe_data(idmap->idmap_pipe);
 err:
-	put_cred(idmap->cred);
+	get_user_ns(idmap->user_ns);
 	kfree(idmap);
 	return error;
 }
@@ -503,7 +504,7 @@ nfs_idmap_delete(struct nfs_client *clp)
 			&clp->cl_rpcclient->cl_pipedir_objects,
 			&idmap->idmap_pdo);
 	rpc_destroy_pipe_data(idmap->idmap_pipe);
-	put_cred(idmap->cred);
+	put_user_ns(idmap->user_ns);
 	kfree(idmap);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6e95c85fe395..9e0ca9b2b210 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -63,6 +63,7 @@
 #include "callback.h"
 #include "pnfs.h"
 #include "netns.h"
+#include "sysfs.h"
 #include "nfs4idmap.h"
 #include "nfs4session.h"
 #include "fscache.h"
@@ -70,6 +71,10 @@
 
 #include "nfs4trace.h"
 
+#ifdef CONFIG_NFS_V4_2
+#include "nfs42.h"
+#endif /* CONFIG_NFS_V4_2 */
+
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
 #define NFS4_BITMASK_SZ		3
@@ -107,6 +112,9 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
 static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
 		const struct cred *, bool);
 #endif
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+		struct nfs_server *server,
+		struct nfs4_label *label);
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 static inline struct nfs4_label *
@@ -1547,19 +1555,6 @@ static void nfs_state_log_update_open_stateid(struct nfs4_state *state)
 		wake_up_all(&state->waitq);
 }
 
-static void nfs_state_log_out_of_order_open_stateid(struct nfs4_state *state,
-		const nfs4_stateid *stateid)
-{
-	u32 state_seqid = be32_to_cpu(state->open_stateid.seqid);
-	u32 stateid_seqid = be32_to_cpu(stateid->seqid);
-
-	if (stateid_seqid == state_seqid + 1U ||
-	    (stateid_seqid == 1U && state_seqid == 0xffffffffU))
-		nfs_state_log_update_open_stateid(state);
-	else
-		set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
-}
-
 static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
 {
 	struct nfs_client *clp = state->owner->so_server->nfs_client;
@@ -1585,21 +1580,19 @@ static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
  * i.e. The stateid seqids have to be initialised to 1, and
  * are then incremented on every state transition.
  */
-static bool nfs_need_update_open_stateid(struct nfs4_state *state,
+static bool nfs_stateid_is_sequential(struct nfs4_state *state,
 		const nfs4_stateid *stateid)
 {
-	if (test_bit(NFS_OPEN_STATE, &state->flags) == 0 ||
-	    !nfs4_stateid_match_other(stateid, &state->open_stateid)) {
+	if (test_bit(NFS_OPEN_STATE, &state->flags)) {
+		/* The common case - we're updating to a new sequence number */
+		if (nfs4_stateid_match_other(stateid, &state->open_stateid) &&
+			nfs4_stateid_is_next(&state->open_stateid, stateid)) {
+			return true;
+		}
+	} else {
+		/* This is the first OPEN in this generation */
 		if (stateid->seqid == cpu_to_be32(1))
-			nfs_state_log_update_open_stateid(state);
-		else
-			set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
-		return true;
-	}
-
-	if (nfs4_stateid_is_newer(stateid, &state->open_stateid)) {
-		nfs_state_log_out_of_order_open_stateid(state, stateid);
-		return true;
+			return true;
 	}
 	return false;
 }
@@ -1673,16 +1666,16 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state,
 	int status = 0;
 	for (;;) {
 
-		if (!nfs_need_update_open_stateid(state, stateid))
-			return;
-		if (!test_bit(NFS_STATE_CHANGE_WAIT, &state->flags))
+		if (nfs_stateid_is_sequential(state, stateid))
 			break;
+
 		if (status)
 			break;
 		/* Rely on seqids for serialisation with NFSv4.0 */
 		if (!nfs4_has_session(NFS_SERVER(state->inode)->nfs_client))
 			break;
 
+		set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
 		prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE);
 		/*
 		 * Ensure we process the state changes in the same order
@@ -1693,6 +1686,7 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state,
 		spin_unlock(&state->owner->so_lock);
 		rcu_read_unlock();
 		trace_nfs4_open_stateid_update_wait(state->inode, stateid, 0);
+
 		if (!signal_pending(current)) {
 			if (schedule_timeout(5*HZ) == 0)
 				status = -EAGAIN;
@@ -3435,7 +3429,8 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst,
 	__be32 seqid_open;
 	u32 dst_seqid;
 	bool ret;
-	int seq;
+	int seq, status = -EAGAIN;
+	DEFINE_WAIT(wait);
 
 	for (;;) {
 		ret = false;
@@ -3447,15 +3442,41 @@ static bool nfs4_refresh_open_old_stateid(nfs4_stateid *dst,
 				continue;
 			break;
 		}
+
+		write_seqlock(&state->seqlock);
 		seqid_open = state->open_stateid.seqid;
-		if (read_seqretry(&state->seqlock, seq))
-			continue;
 
 		dst_seqid = be32_to_cpu(dst->seqid);
-		if ((s32)(dst_seqid - be32_to_cpu(seqid_open)) >= 0)
-			dst->seqid = cpu_to_be32(dst_seqid + 1);
-		else
+
+		/* Did another OPEN bump the state's seqid?  try again: */
+		if ((s32)(be32_to_cpu(seqid_open) - dst_seqid) > 0) {
 			dst->seqid = seqid_open;
+			write_sequnlock(&state->seqlock);
+			ret = true;
+			break;
+		}
+
+		/* server says we're behind but we haven't seen the update yet */
+		set_bit(NFS_STATE_CHANGE_WAIT, &state->flags);
+		prepare_to_wait(&state->waitq, &wait, TASK_KILLABLE);
+		write_sequnlock(&state->seqlock);
+		trace_nfs4_close_stateid_update_wait(state->inode, dst, 0);
+
+		if (signal_pending(current))
+			status = -EINTR;
+		else
+			if (schedule_timeout(5*HZ) != 0)
+				status = 0;
+
+		finish_wait(&state->waitq, &wait);
+
+		if (!status)
+			continue;
+		if (status == -EINTR)
+			break;
+
+		/* we slept the whole 5 seconds, we must have lost a seqid */
+		dst->seqid = cpu_to_be32(dst_seqid + 1);
 		ret = true;
 		break;
 	}
@@ -3632,9 +3653,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 
 	if (calldata->arg.fmode == 0 || calldata->arg.fmode == FMODE_READ) {
 		/* Close-to-open cache consistency revalidation */
-		if (!nfs4_have_delegation(inode, FMODE_READ))
+		if (!nfs4_have_delegation(inode, FMODE_READ)) {
 			calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
-		else
+			nfs4_bitmask_adjust(calldata->arg.bitmask, inode, NFS_SERVER(inode), NULL);
+		} else
 			calldata->arg.bitmask = NULL;
 	}
 
@@ -5255,28 +5277,60 @@ static bool nfs4_read_stateid_changed(struct rpc_task *task,
 	return true;
 }
 
-static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+static bool nfs4_read_plus_not_supported(struct rpc_task *task,
+					 struct nfs_pgio_header *hdr)
 {
+	struct nfs_server *server = NFS_SERVER(hdr->inode);
+	struct rpc_message *msg = &task->tk_msg;
 
+	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] &&
+	    server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) {
+		server->caps &= ~NFS_CAP_READ_PLUS;
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+		rpc_restart_call_prepare(task);
+		return true;
+	}
+	return false;
+}
+
+static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
+{
 	dprintk("--> %s\n", __func__);
 
 	if (!nfs4_sequence_done(task, &hdr->res.seq_res))
 		return -EAGAIN;
 	if (nfs4_read_stateid_changed(task, &hdr->args))
 		return -EAGAIN;
+	if (nfs4_read_plus_not_supported(task, hdr))
+		return -EAGAIN;
 	if (task->tk_status > 0)
 		nfs_invalidate_atime(hdr->inode);
 	return hdr->pgio_done_cb ? hdr->pgio_done_cb(task, hdr) :
 				    nfs4_read_done_cb(task, hdr);
 }
 
+#ifdef CONFIG_NFS_V4_2
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	if (server->caps & NFS_CAP_READ_PLUS)
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS];
+	else
+		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#else
+static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
+{
+	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+}
+#endif /* CONFIG_NFS_V4_2 */
+
 static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr,
 				 struct rpc_message *msg)
 {
 	hdr->timestamp   = jiffies;
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_read_done_cb;
-	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
+	nfs42_read_plus_support(NFS_SERVER(hdr->inode), msg);
 	nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0);
 }
 
@@ -5360,6 +5414,38 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr)
 	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
+static void nfs4_bitmask_adjust(__u32 *bitmask, struct inode *inode,
+				struct nfs_server *server,
+				struct nfs4_label *label)
+{
+
+	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+
+	if ((cache_validity & NFS_INO_INVALID_DATA) ||
+		(cache_validity & NFS_INO_REVAL_PAGECACHE) ||
+		(cache_validity & NFS_INO_REVAL_FORCED) ||
+		(cache_validity & NFS_INO_INVALID_OTHER))
+		nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode);
+
+	if (cache_validity & NFS_INO_INVALID_ATIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
+	if (cache_validity & NFS_INO_INVALID_ACCESS)
+		bitmask[0] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
+				FATTR4_WORD1_OWNER_GROUP;
+	if (cache_validity & NFS_INO_INVALID_ACL)
+		bitmask[0] |= FATTR4_WORD0_ACL;
+	if (cache_validity & NFS_INO_INVALID_LABEL)
+		bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
+	if (cache_validity & NFS_INO_INVALID_CTIME)
+		bitmask[0] |= FATTR4_WORD0_CHANGE;
+	if (cache_validity & NFS_INO_INVALID_MTIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
+	if (cache_validity & NFS_INO_INVALID_SIZE)
+		bitmask[0] |= FATTR4_WORD0_SIZE;
+	if (cache_validity & NFS_INO_INVALID_BLOCKS)
+		bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+}
+
 static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 				  struct rpc_message *msg,
 				  struct rpc_clnt **clnt)
@@ -5369,8 +5455,10 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 	if (!nfs4_write_need_cache_consistency_data(hdr)) {
 		hdr->args.bitmask = NULL;
 		hdr->res.fattr = NULL;
-	} else
+	} else {
 		hdr->args.bitmask = server->cache_consistency_bitmask;
+		nfs4_bitmask_adjust(hdr->args.bitmask, hdr->inode, server, NULL);
+	}
 
 	if (!hdr->pgio_done_cb)
 		hdr->pgio_done_cb = nfs4_write_done_cb;
@@ -6006,9 +6094,34 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp,
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
+static size_t
+nfs4_get_uniquifier(struct nfs_client *clp, char *buf, size_t buflen)
+{
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+	struct nfs_netns_client *nn_clp = nn->nfs_client;
+	const char *id;
+
+	buf[0] = '\0';
+
+	if (nn_clp) {
+		rcu_read_lock();
+		id = rcu_dereference(nn_clp->identifier);
+		if (id)
+			strscpy(buf, id, buflen);
+		rcu_read_unlock();
+	}
+
+	if (nfs4_client_id_uniquifier[0] != '\0' && buf[0] == '\0')
+		strscpy(buf, nfs4_client_id_uniquifier, buflen);
+
+	return strlen(buf);
+}
+
 static int
 nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 {
+	char buf[NFS4_CLIENT_ID_UNIQ_LEN];
+	size_t buflen;
 	size_t len;
 	char *str;
 
@@ -6022,8 +6135,11 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 		strlen(rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR)) +
 		1;
 	rcu_read_unlock();
-	if (nfs4_client_id_uniquifier[0] != '\0')
-		len += strlen(nfs4_client_id_uniquifier) + 1;
+
+	buflen = nfs4_get_uniquifier(clp, buf, sizeof(buf));
+	if (buflen)
+		len += buflen + 1;
+
 	if (len > NFS4_OPAQUE_LIMIT + 1)
 		return -EINVAL;
 
@@ -6037,10 +6153,9 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 		return -ENOMEM;
 
 	rcu_read_lock();
-	if (nfs4_client_id_uniquifier[0] != '\0')
+	if (buflen)
 		scnprintf(str, len, "Linux NFSv4.0 %s/%s/%s",
-			  clp->cl_rpcclient->cl_nodename,
-			  nfs4_client_id_uniquifier,
+			  clp->cl_rpcclient->cl_nodename, buf,
 			  rpc_peeraddr2str(clp->cl_rpcclient,
 					   RPC_DISPLAY_ADDR));
 	else
@@ -6055,50 +6170,23 @@ nfs4_init_nonuniform_client_string(struct nfs_client *clp)
 }
 
 static int
-nfs4_init_uniquifier_client_string(struct nfs_client *clp)
-{
-	size_t len;
-	char *str;
-
-	len = 10 + 10 + 1 + 10 + 1 +
-		strlen(nfs4_client_id_uniquifier) + 1 +
-		strlen(clp->cl_rpcclient->cl_nodename) + 1;
-
-	if (len > NFS4_OPAQUE_LIMIT + 1)
-		return -EINVAL;
-
-	/*
-	 * Since this string is allocated at mount time, and held until the
-	 * nfs_client is destroyed, we can use GFP_KERNEL here w/o worrying
-	 * about a memory-reclaim deadlock.
-	 */
-	str = kmalloc(len, GFP_KERNEL);
-	if (!str)
-		return -ENOMEM;
-
-	scnprintf(str, len, "Linux NFSv%u.%u %s/%s",
-			clp->rpc_ops->version, clp->cl_minorversion,
-			nfs4_client_id_uniquifier,
-			clp->cl_rpcclient->cl_nodename);
-	clp->cl_owner_id = str;
-	return 0;
-}
-
-static int
 nfs4_init_uniform_client_string(struct nfs_client *clp)
 {
+	char buf[NFS4_CLIENT_ID_UNIQ_LEN];
+	size_t buflen;
 	size_t len;
 	char *str;
 
 	if (clp->cl_owner_id != NULL)
 		return 0;
 
-	if (nfs4_client_id_uniquifier[0] != '\0')
-		return nfs4_init_uniquifier_client_string(clp);
-
 	len = 10 + 10 + 1 + 10 + 1 +
 		strlen(clp->cl_rpcclient->cl_nodename) + 1;
 
+	buflen = nfs4_get_uniquifier(clp, buf, sizeof(buf));
+	if (buflen)
+		len += buflen + 1;
+
 	if (len > NFS4_OPAQUE_LIMIT + 1)
 		return -EINVAL;
 
@@ -6111,9 +6199,14 @@ nfs4_init_uniform_client_string(struct nfs_client *clp)
 	if (!str)
 		return -ENOMEM;
 
-	scnprintf(str, len, "Linux NFSv%u.%u %s",
-			clp->rpc_ops->version, clp->cl_minorversion,
-			clp->cl_rpcclient->cl_nodename);
+	if (buflen)
+		scnprintf(str, len, "Linux NFSv%u.%u %s/%s",
+			  clp->rpc_ops->version, clp->cl_minorversion,
+			  buf, clp->cl_rpcclient->cl_nodename);
+	else
+		scnprintf(str, len, "Linux NFSv%u.%u %s",
+			  clp->rpc_ops->version, clp->cl_minorversion,
+			  clp->cl_rpcclient->cl_nodename);
 	clp->cl_owner_id = str;
 	return 0;
 }
@@ -6406,6 +6499,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
 	data->args.fhandle = &data->fh;
 	data->args.stateid = &data->stateid;
 	data->args.bitmask = server->cache_consistency_bitmask;
+	nfs4_bitmask_adjust(data->args.bitmask, inode, server, NULL);
 	nfs_copy_fh(&data->fh, NFS_FH(inode));
 	nfs4_stateid_copy(&data->stateid, stateid);
 	data->res.fattr = &data->fattr;
@@ -7440,7 +7534,7 @@ nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len)
 
 	if (nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) {
 		len = security_inode_listsecurity(inode, list, list_len);
-		if (list_len && len > list_len)
+		if (len >= 0 && list_len && len > list_len)
 			return -ERANGE;
 	}
 	return len;
@@ -8039,9 +8133,11 @@ int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name,
  * both PNFS and NON_PNFS flags set, and not having one of NON_PNFS, PNFS, or
  * DS flags set.
  */
-static int nfs4_check_cl_exchange_flags(u32 flags)
+static int nfs4_check_cl_exchange_flags(u32 flags, u32 version)
 {
-	if (flags & ~EXCHGID4_FLAG_MASK_R)
+	if (version >= 2 && (flags & ~EXCHGID4_2_FLAG_MASK_R))
+		goto out_inval;
+	else if (version < 2 && (flags & ~EXCHGID4_FLAG_MASK_R))
 		goto out_inval;
 	if ((flags & EXCHGID4_FLAG_USE_PNFS_MDS) &&
 	    (flags & EXCHGID4_FLAG_USE_NON_PNFS))
@@ -8454,7 +8550,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
 	if (status  != 0)
 		goto out;
 
-	status = nfs4_check_cl_exchange_flags(resp->flags);
+	status = nfs4_check_cl_exchange_flags(resp->flags,
+			clp->cl_mvops->minor_version);
 	if (status  != 0)
 		goto out;
 
@@ -9693,7 +9790,6 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	struct rpc_clnt *clnt = server->client;
 	struct nfs4_call_sync_data data = {
 		.seq_server = server,
 		.seq_args = &args.seq_args,
@@ -9710,8 +9806,7 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle,
 	int status;
 
 	if (use_integrity) {
-		clnt = server->nfs_client->cl_rpcclient;
-		task_setup.rpc_client = clnt;
+		task_setup.rpc_client = server->nfs_client->cl_rpcclient;
 
 		cred = nfs4_get_clid_cred(server->nfs_client);
 		msg.rpc_cred = cred;
@@ -10165,7 +10260,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 		| NFS_CAP_SEEK
 		| NFS_CAP_LAYOUTSTATS
 		| NFS_CAP_CLONE
-		| NFS_CAP_LAYOUTERROR,
+		| NFS_CAP_LAYOUTERROR
+		| NFS_CAP_READ_PLUS,
 	.init_client = nfs41_init_client,
 	.shutdown_client = nfs41_shutdown_client,
 	.match_stateid = nfs41_match_stateid,
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index b4f852d4d099..484c1da96dea 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -1511,6 +1511,7 @@ DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_setattr);
 DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_delegreturn);
 DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update);
 DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_open_stateid_update_wait);
+DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_close_stateid_update_wait);
 
 DECLARE_EVENT_CLASS(nfs4_getattr_event,
 		TP_PROTO(
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 0b3510f62623..c6dbfcae7517 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5308,7 +5308,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 	uint32_t attrlen,
 		 bitmap[3] = {0};
 	int status;
-	unsigned int pg_offset;
 
 	res->acl_len = 0;
 	if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0)
@@ -5316,9 +5315,6 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 
 	xdr_enter_page(xdr, xdr->buf->page_len);
 
-	/* Calculate the offset of the page data */
-	pg_offset = xdr->buf->head[0].iov_len;
-
 	if ((status = decode_attr_bitmap(xdr, bitmap)) != 0)
 		goto out;
 	if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0)
@@ -5331,7 +5327,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		/* The bitmap (xdr len + bitmaps) and the attr xdr len words
 		 * are stored with the acl data to handle the problem of
 		 * variable length bitmaps.*/
-		res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset;
+		res->acl_data_offset = xdr_page_pos(xdr);
 		res->acl_len = attrlen;
 
 		/* Check for receive buffer overflow */
@@ -7619,6 +7615,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC42(SETXATTR,	enc_setxattr,		dec_setxattr),
 	PROC42(LISTXATTRS,	enc_listxattrs,		dec_listxattrs),
 	PROC42(REMOVEXATTR,	enc_removexattr,	dec_removexattr),
+	PROC42(READ_PLUS,	enc_read_plus,		dec_read_plus),
 };
 
 static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 71f7741126b6..0e50b9d45c32 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -902,7 +902,7 @@ restart:
 }
 
 /*
- * Called by the state manger to remove all layouts established under an
+ * Called by the state manager to remove all layouts established under an
  * expired lease.
  */
 void
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index f943e37853fa..78c46a517fcf 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -889,7 +889,7 @@ static struct nfs_server *nfs_try_mount_request(struct fs_context *fc)
 		default:
 			if (rpcauth_get_gssinfo(flavor, &info) != 0)
 				continue;
-			/* Fallthrough */
+			break;
 		}
 		dfprintk(MOUNT, "NFS: attempting to use auth flavor %u\n", flavor);
 		ctx->selected_flavor = flavor;
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index c489496b5659..8cb70755e3c9 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -79,7 +79,12 @@ static ssize_t nfs_netns_identifier_show(struct kobject *kobj,
 	struct nfs_netns_client *c = container_of(kobj,
 			struct nfs_netns_client,
 			kobject);
-	return scnprintf(buf, PAGE_SIZE, "%s\n", c->identifier);
+	ssize_t ret;
+
+	rcu_read_lock();
+	ret = scnprintf(buf, PAGE_SIZE, "%s\n", rcu_dereference(c->identifier));
+	rcu_read_unlock();
+	return ret;
 }
 
 /* Strip trailing '\n' */
@@ -107,7 +112,7 @@ static ssize_t nfs_netns_identifier_store(struct kobject *kobj,
 	p = kmemdup_nul(buf, len, GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
-	old = xchg(&c->identifier, p);
+	old = rcu_dereference_protected(xchg(&c->identifier, (char __rcu *)p), 1);
 	if (old) {
 		synchronize_rcu();
 		kfree(old);
@@ -121,7 +126,7 @@ static void nfs_netns_client_release(struct kobject *kobj)
 			struct nfs_netns_client,
 			kobject);
 
-	kfree(c->identifier);
+	kfree(rcu_dereference_raw(c->identifier));
 	kfree(c);
 }
 
diff --git a/fs/nfs/sysfs.h b/fs/nfs/sysfs.h
index ebcbdc40483b..5501ef573c32 100644
--- a/fs/nfs/sysfs.h
+++ b/fs/nfs/sysfs.h
@@ -11,7 +11,7 @@
 struct nfs_netns_client {
 	struct kobject kobject;
 	struct net *net;
-	const char *identifier;
+	const char __rcu *identifier;
 };
 
 extern struct kobject *nfs_client_kobj;