diff --git a/fs/Kconfig b/fs/Kconfig
index 89a750d292ba..141a856c50e7 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -338,8 +338,8 @@ config NFS_COMMON
 	default y
 
 config NFS_V4_2_SSC_HELPER
-	tristate
-	default y if NFS_V4=y || NFS_FS=y
+	bool
+	default y if NFS_V4_2
 
 source "net/sunrpc/Kconfig"
 source "fs/ceph/Kconfig"
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index f7786e00a6a7..ed9d580826f5 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -137,12 +137,12 @@ static struct inode *nfs_layout_find_inode_by_stateid(struct nfs_client *clp,
 		list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) {
 			if (!pnfs_layout_is_valid(lo))
 				continue;
-			if (stateid != NULL &&
-			    !nfs4_stateid_match_other(stateid, &lo->plh_stateid))
+			if (!nfs4_stateid_match_other(stateid, &lo->plh_stateid))
 				continue;
-			if (!nfs_sb_active(server->super))
-				continue;
-			inode = igrab(lo->plh_inode);
+			if (nfs_sb_active(server->super))
+				inode = igrab(lo->plh_inode);
+			else
+				inode = ERR_PTR(-EAGAIN);
 			rcu_read_unlock();
 			if (inode)
 				return inode;
@@ -176,9 +176,10 @@ static struct inode *nfs_layout_find_inode_by_fh(struct nfs_client *clp,
 				continue;
 			if (nfsi->layout != lo)
 				continue;
-			if (!nfs_sb_active(server->super))
-				continue;
-			inode = igrab(lo->plh_inode);
+			if (nfs_sb_active(server->super))
+				inode = igrab(lo->plh_inode);
+			else
+				inode = ERR_PTR(-EAGAIN);
 			rcu_read_unlock();
 			if (inode)
 				return inode;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index ff5c4d0d6d13..cfeaadf56bf0 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -476,7 +476,6 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 			to->to_maxval = to->to_initval;
 		to->to_exponential = 0;
 		break;
-#ifndef CONFIG_NFS_DISABLE_UDP_SUPPORT
 	case XPRT_TRANSPORT_UDP:
 		if (retrans == NFS_UNSPEC_RETRANS)
 			to->to_retries = NFS_DEF_UDP_RETRANS;
@@ -487,7 +486,6 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 		to->to_maxval = NFS_MAX_UDP_TIMEOUT;
 		to->to_exponential = 1;
 		break;
-#endif
 	default:
 		BUG();
 	}
@@ -698,9 +696,18 @@ static int nfs_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = ctx->flags;
 	server->options = ctx->options;
-	server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
-		NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
-		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
+	server->caps |= NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+
+	switch (clp->rpc_ops->version) {
+	case 2:
+		server->fattr_valid = NFS_ATTR_FATTR_V2;
+		break;
+	case 3:
+		server->fattr_valid = NFS_ATTR_FATTR_V3;
+		break;
+	default:
+		server->fattr_valid = NFS_ATTR_FATTR_V4;
+	}
 
 	if (ctx->rsize)
 		server->rsize = nfs_block_size(ctx->rsize, NULL);
@@ -794,6 +801,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 	server->maxfilesize = fsinfo->maxfilesize;
 
 	server->time_delta = fsinfo->time_delta;
+	server->change_attr_type = fsinfo->change_attr_type;
 
 	server->clone_blksize = fsinfo->clone_blksize;
 	/* We're airborne Set socket buffersize */
@@ -935,6 +943,8 @@ struct nfs_server *nfs_alloc_server(void)
 		return NULL;
 	}
 
+	server->change_attr_type = NFS4_CHANGE_TYPE_IS_UNDEFINED;
+
 	ida_init(&server->openowner_id);
 	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 04bf8066980c..e6ec6f09ac6e 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -114,7 +114,7 @@ nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
 	return ret;
 }
 /**
- * nfs_have_delegation - check if inode has a delegation, mark it
+ * nfs4_have_delegation - check if inode has a delegation, mark it
  * NFS_DELEGATION_REFERENCED if there is one.
  * @inode: inode to check
  * @flags: delegation types to check for
@@ -481,6 +481,22 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
 	if (freeme == NULL)
 		goto out;
 add_new:
+	/*
+	 * If we didn't revalidate the change attribute before setting
+	 * the delegation, then pre-emptively ask for a full attribute
+	 * cache revalidation.
+	 */
+	spin_lock(&inode->i_lock);
+	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_CHANGE)
+		nfs_set_cache_invalid(inode,
+			NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
+			NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
+			NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK |
+			NFS_INO_INVALID_OTHER | NFS_INO_INVALID_DATA |
+			NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL |
+			NFS_INO_INVALID_XATTR);
+	spin_unlock(&inode->i_lock);
+
 	list_add_tail_rcu(&delegation->super_list, &server->delegations);
 	rcu_assign_pointer(nfsi->delegation, delegation);
 	delegation = NULL;
@@ -488,11 +504,6 @@ add_new:
 	atomic_long_inc(&nfs_active_delegations);
 
 	trace_nfs4_set_delegation(inode, type);
-
-	spin_lock(&inode->i_lock);
-	if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME))
-		NFS_I(inode)->cache_validity |= NFS_INO_REVAL_FORCED;
-	spin_unlock(&inode->i_lock);
 out:
 	spin_unlock(&clp->cl_lock);
 	if (delegation != NULL)
@@ -674,7 +685,7 @@ void nfs_inode_evict_delegation(struct inode *inode)
 }
 
 /**
- * nfs_inode_return_delegation - synchronously return a delegation
+ * nfs4_inode_return_delegation - synchronously return a delegation
  * @inode: inode to process
  *
  * This routine will always flush any dirty data to disk on the
@@ -697,7 +708,7 @@ int nfs4_inode_return_delegation(struct inode *inode)
 }
 
 /**
- * nfs_inode_return_delegation_on_close - asynchronously return a delegation
+ * nfs4_inode_return_delegation_on_close - asynchronously return a delegation
  * @inode: inode to process
  *
  * This routine is called on file close in order to determine if the
@@ -811,7 +822,7 @@ void nfs_expire_all_delegations(struct nfs_client *clp)
 }
 
 /**
- * nfs_super_return_all_delegations - return delegations for one superblock
+ * nfs_server_return_all_delegations - return delegations for one superblock
  * @server: pointer to nfs_server to process
  *
  */
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9b00a0b7f832..c19b4fd20781 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -84,8 +84,7 @@ int nfs4_inode_make_writeable(struct inode *inode);
 
 static inline int nfs_have_delegated_attributes(struct inode *inode)
 {
-	return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) &&
-		!(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED);
+	return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ);
 }
 
 #endif
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 3d8e3698d3df..1a6d2867fba4 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -866,6 +866,8 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
 			break;
 		}
 
+		verf_arg = verf_res;
+
 		status = nfs_readdir_page_filler(desc, entry, pages, pglen,
 						 arrays, narrays);
 	} while (!status && nfs_readdir_page_needs_filling(page));
@@ -927,7 +929,12 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
 			}
 			return res;
 		}
-		memcpy(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf));
+		/*
+		 * Set the cookie verifier if the page cache was empty
+		 */
+		if (desc->page_index == 0)
+			memcpy(nfsi->cookieverf, verf,
+			       sizeof(nfsi->cookieverf));
 	}
 	res = nfs_readdir_search_array(desc);
 	if (res == 0) {
@@ -974,10 +981,10 @@ static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
 /*
  * Once we've found the start of the dirent within a page: fill 'er up...
  */
-static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
+static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
+			   const __be32 *verf)
 {
 	struct file	*file = desc->file;
-	struct nfs_inode *nfsi = NFS_I(file_inode(file));
 	struct nfs_cache_array *array;
 	unsigned int i = 0;
 
@@ -991,7 +998,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc)
 			desc->eof = true;
 			break;
 		}
-		memcpy(desc->verf, nfsi->cookieverf, sizeof(desc->verf));
+		memcpy(desc->verf, verf, sizeof(desc->verf));
 		if (i < (array->size-1))
 			desc->dir_cookie = array->array[i+1].cookie;
 		else
@@ -1048,7 +1055,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
 
 	for (i = 0; !desc->eof && i < sz && arrays[i]; i++) {
 		desc->page = arrays[i];
-		nfs_do_filldir(desc);
+		nfs_do_filldir(desc, verf);
 	}
 	desc->page = NULL;
 
@@ -1069,6 +1076,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry	*dentry = file_dentry(file);
 	struct inode	*inode = d_inode(dentry);
+	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_dir_context *dir_ctx = file->private_data;
 	struct nfs_readdir_descriptor *desc;
 	int res;
@@ -1122,7 +1130,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 			break;
 		}
 		if (res == -ETOOSMALL && desc->plus) {
-			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
+			clear_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
 			nfs_zap_caches(inode);
 			desc->page_index = 0;
 			desc->plus = false;
@@ -1132,7 +1140,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 		if (res < 0)
 			break;
 
-		nfs_do_filldir(desc);
+		nfs_do_filldir(desc, nfsi->cookieverf);
 		nfs_readdir_page_unlock_and_put_cached(desc);
 	} while (!desc->eof);
 
@@ -1703,7 +1711,7 @@ static void nfs_drop_nlink(struct inode *inode)
 	NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_set_cache_invalid(
 		inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
-			       NFS_INO_INVALID_OTHER | NFS_INO_REVAL_FORCED);
+			       NFS_INO_INVALID_NLINK);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -2940,7 +2948,7 @@ static int nfs_execute_ok(struct inode *inode, int mask)
 
 	if (S_ISDIR(inode->i_mode))
 		return 0;
-	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_OTHER)) {
+	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_MODE)) {
 		if (mask & MAY_NOT_BLOCK)
 			return -ECHILD;
 		ret = __nfs_revalidate_inode(server, inode);
@@ -2998,7 +3006,8 @@ out_notsup:
 	if (mask & MAY_NOT_BLOCK)
 		return -ECHILD;
 
-	res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	res = nfs_revalidate_inode(inode, NFS_INO_INVALID_MODE |
+						  NFS_INO_INVALID_OTHER);
 	if (res == 0)
 		res = generic_permission(&init_user_ns, inode, mask);
 	goto out;
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index f2b34cfe286c..37a1a88df771 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -169,19 +169,8 @@ out:
 
 static u64 nfs_fetch_iversion(struct inode *inode)
 {
-	struct nfs_server *server = NFS_SERVER(inode);
-
-	/* Is this the right call?: */
-	nfs_revalidate_inode(server, inode);
-	/*
-	 * Also, note we're ignoring any returned error.  That seems to be
-	 * the practice for cache consistency information elsewhere in
-	 * the server, but I'm not sure why.
-	 */
-	if (server->nfs_client->rpc_ops->version >= 4)
-		return inode_peek_iversion_raw(inode);
-	else
-		return time_to_chattr(&inode->i_ctime);
+	nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
+	return inode_peek_iversion_raw(inode);
 }
 
 const struct export_operations nfs_export_ops = {
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 16ad5050e046..1fef107961bc 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -105,7 +105,7 @@ static int nfs_revalidate_file_size(struct inode *inode, struct file *filp)
 
 	if (filp->f_flags & O_DIRECT)
 		goto force_reval;
-	if (nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE))
+	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_SIZE))
 		goto force_reval;
 	return 0;
 force_reval:
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 872112bffcab..d383de00d486 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -106,7 +106,7 @@ static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh)
 	if (unlikely(!p))
 		return -ENOBUFS;
 	fh->size = be32_to_cpup(p++);
-	if (fh->size > sizeof(struct nfs_fh)) {
+	if (fh->size > NFS_MAXFHSIZE) {
 		printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n",
 		       fh->size);
 		return -EOVERFLOW;
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index a06d213d7689..d95c9a39bc70 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -283,20 +283,40 @@ static int nfs_verify_server_address(struct sockaddr *addr)
 	return 0;
 }
 
+#ifdef CONFIG_NFS_DISABLE_UDP_SUPPORT
+static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx)
+{
+	return true;
+}
+#else
+static bool nfs_server_transport_udp_invalid(const struct nfs_fs_context *ctx)
+{
+	if (ctx->version == 4)
+		return true;
+	return false;
+}
+#endif
+
 /*
  * Sanity check the NFS transport protocol.
- *
  */
-static void nfs_validate_transport_protocol(struct nfs_fs_context *ctx)
+static int nfs_validate_transport_protocol(struct fs_context *fc,
+					   struct nfs_fs_context *ctx)
 {
 	switch (ctx->nfs_server.protocol) {
 	case XPRT_TRANSPORT_UDP:
+		if (nfs_server_transport_udp_invalid(ctx))
+			goto out_invalid_transport_udp;
+		break;
 	case XPRT_TRANSPORT_TCP:
 	case XPRT_TRANSPORT_RDMA:
 		break;
 	default:
 		ctx->nfs_server.protocol = XPRT_TRANSPORT_TCP;
 	}
+	return 0;
+out_invalid_transport_udp:
+	return nfs_invalf(fc, "NFS: Unsupported transport protocol udp");
 }
 
 /*
@@ -305,8 +325,6 @@ static void nfs_validate_transport_protocol(struct nfs_fs_context *ctx)
  */
 static void nfs_set_mount_transport_protocol(struct nfs_fs_context *ctx)
 {
-	nfs_validate_transport_protocol(ctx);
-
 	if (ctx->mount_server.protocol == XPRT_TRANSPORT_UDP ||
 	    ctx->mount_server.protocol == XPRT_TRANSPORT_TCP)
 			return;
@@ -932,6 +950,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 	struct nfs_fh *mntfh = ctx->mntfh;
 	struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address;
 	int extra_flags = NFS_MOUNT_LEGACY_INTERFACE;
+	int ret;
 
 	if (data == NULL)
 		goto out_no_data;
@@ -976,6 +995,15 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 			memset(mntfh->data + mntfh->size, 0,
 			       sizeof(mntfh->data) - mntfh->size);
 
+		/*
+		 * for proto == XPRT_TRANSPORT_UDP, which is what uses
+		 * to_exponential, implying shift: limit the shift value
+		 * to BITS_PER_LONG (majortimeo is unsigned long)
+		 */
+		if (!(data->flags & NFS_MOUNT_TCP)) /* this will be UDP */
+			if (data->retrans >= 64) /* shift value is too large */
+				goto out_invalid_data;
+
 		/*
 		 * Translate to nfs_fs_context, which nfs_fill_super
 		 * can deal with.
@@ -1048,6 +1076,10 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
 		goto generic;
 	}
 
+	ret = nfs_validate_transport_protocol(fc, ctx);
+	if (ret)
+		return ret;
+
 	ctx->skip_reconfig_option_check = true;
 	return 0;
 
@@ -1076,6 +1108,9 @@ out_no_address:
 
 out_invalid_fh:
 	return nfs_invalf(fc, "NFS: invalid root filehandle");
+
+out_invalid_data:
+	return nfs_invalf(fc, "NFS: invalid binary mount data");
 }
 
 #if IS_ENABLED(CONFIG_NFS_V4)
@@ -1146,6 +1181,7 @@ static int nfs4_parse_monolithic(struct fs_context *fc,
 {
 	struct nfs_fs_context *ctx = nfs_fc2context(fc);
 	struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address;
+	int ret;
 	char *c;
 
 	if (!data) {
@@ -1218,9 +1254,9 @@ static int nfs4_parse_monolithic(struct fs_context *fc,
 	ctx->acdirmin	= data->acdirmin;
 	ctx->acdirmax	= data->acdirmax;
 	ctx->nfs_server.protocol = data->proto;
-	nfs_validate_transport_protocol(ctx);
-	if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP)
-		goto out_invalid_transport_udp;
+	ret = nfs_validate_transport_protocol(fc, ctx);
+	if (ret)
+		return ret;
 done:
 	ctx->skip_reconfig_option_check = true;
 	return 0;
@@ -1231,9 +1267,6 @@ out_inval_auth:
 
 out_no_address:
 	return nfs_invalf(fc, "NFS4: mount program didn't pass remote address");
-
-out_invalid_transport_udp:
-	return nfs_invalf(fc, "NFS: Unsupported transport protocol udp");
 }
 #endif
 
@@ -1298,6 +1331,10 @@ static int nfs_fs_context_validate(struct fs_context *fc)
 	if (!nfs_verify_server_address(sap))
 		goto out_no_address;
 
+	ret = nfs_validate_transport_protocol(fc, ctx);
+	if (ret)
+		return ret;
+
 	if (ctx->version == 4) {
 		if (IS_ENABLED(CONFIG_NFS_V4)) {
 			if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA)
@@ -1306,9 +1343,6 @@ static int nfs_fs_context_validate(struct fs_context *fc)
 				port = NFS_PORT;
 			max_namelen = NFS4_MAXNAMLEN;
 			max_pathlen = NFS4_MAXPATHLEN;
-			nfs_validate_transport_protocol(ctx);
-			if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP)
-				goto out_invalid_transport_udp;
 			ctx->flags &= ~(NFS_MOUNT_NONLM | NFS_MOUNT_NOACL |
 					NFS_MOUNT_VER3 | NFS_MOUNT_LOCAL_FLOCK |
 					NFS_MOUNT_LOCAL_FCNTL);
@@ -1317,10 +1351,6 @@ static int nfs_fs_context_validate(struct fs_context *fc)
 		}
 	} else {
 		nfs_set_mount_transport_protocol(ctx);
-#ifdef CONFIG_NFS_DISABLE_UDP_SUPPORT
-	       if (ctx->nfs_server.protocol == XPRT_TRANSPORT_UDP)
-		       goto out_invalid_transport_udp;
-#endif
 		if (ctx->nfs_server.protocol == XPRT_TRANSPORT_RDMA)
 			port = NFS_RDMA_PORT;
 	}
@@ -1354,8 +1384,6 @@ out_no_device_name:
 out_v4_not_compiled:
 	nfs_errorf(fc, "NFS: NFSv4 is not compiled into kernel");
 	return -EPROTONOSUPPORT;
-out_invalid_transport_udp:
-	return nfs_invalf(fc, "NFS: Unsupported transport protocol udp");
 out_no_address:
 	return nfs_invalf(fc, "NFS: mount program didn't pass remote address");
 out_mountproto_mismatch:
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5a8854de0c19..529c4099f482 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -164,34 +164,19 @@ static int nfs_attribute_timeout(struct inode *inode)
 	return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
 }
 
-static bool nfs_check_cache_invalid_delegated(struct inode *inode, unsigned long flags)
+static bool nfs_check_cache_flags_invalid(struct inode *inode,
+					  unsigned long flags)
 {
 	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
 
-	/* Special case for the pagecache or access cache */
-	if (flags == NFS_INO_REVAL_PAGECACHE &&
-	    !(cache_validity & NFS_INO_REVAL_FORCED))
-		return false;
 	return (cache_validity & flags) != 0;
 }
 
-static bool nfs_check_cache_invalid_not_delegated(struct inode *inode, unsigned long flags)
-{
-	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
-
-	if ((cache_validity & flags) != 0)
-		return true;
-	if (nfs_attribute_timeout(inode))
-		return true;
-	return false;
-}
-
 bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags)
 {
-	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
-		return nfs_check_cache_invalid_delegated(inode, flags);
-
-	return nfs_check_cache_invalid_not_delegated(inode, flags);
+	if (nfs_check_cache_flags_invalid(inode, flags))
+		return true;
+	return nfs_attribute_cache_expired(inode);
 }
 EXPORT_SYMBOL_GPL(nfs_check_cache_invalid);
 
@@ -214,20 +199,21 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 
 	if (have_delegation) {
 		if (!(flags & NFS_INO_REVAL_FORCED))
-			flags &= ~NFS_INO_INVALID_OTHER;
-		flags &= ~(NFS_INO_INVALID_CHANGE
-				| NFS_INO_INVALID_SIZE
-				| NFS_INO_REVAL_PAGECACHE
-				| NFS_INO_INVALID_XATTR);
-	}
+			flags &= ~(NFS_INO_INVALID_MODE |
+				   NFS_INO_INVALID_OTHER |
+				   NFS_INO_INVALID_XATTR);
+		flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE);
+	} else if (flags & NFS_INO_REVAL_PAGECACHE)
+		flags |= NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE;
 
 	if (!nfs_has_xattr_cache(nfsi))
 		flags &= ~NFS_INO_INVALID_XATTR;
-	if (inode->i_mapping->nrpages == 0)
-		flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
-	nfsi->cache_validity |= flags;
 	if (flags & NFS_INO_INVALID_DATA)
 		nfs_fscache_invalidate(inode);
+	if (inode->i_mapping->nrpages == 0)
+		flags &= ~(NFS_INO_INVALID_DATA|NFS_INO_DATA_INVAL_DEFER);
+	flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED);
+	nfsi->cache_validity |= flags;
 }
 EXPORT_SYMBOL_GPL(nfs_set_cache_invalid);
 
@@ -452,6 +438,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		.fattr	= fattr
 	};
 	struct inode *inode = ERR_PTR(-ENOENT);
+	u64 fattr_supported = NFS_SB(sb)->fattr_valid;
 	unsigned long hash;
 
 	nfs_attr_check_mountpoint(sb, fattr);
@@ -484,8 +471,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		inode->i_mode = fattr->mode;
 		nfsi->cache_validity = 0;
 		if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
-				&& nfs_server_capable(inode, NFS_CAP_MODE))
-			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+				&& (fattr_supported & NFS_ATTR_FATTR_MODE))
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
 		/* Why so? Because we want revalidate for devices/FIFOs, and
 		 * that's precisely what we have in nfs_file_inode_operations.
 		 */
@@ -530,15 +517,15 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		nfsi->attr_gencount = fattr->gencount;
 		if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 			inode->i_atime = fattr->atime;
-		else if (nfs_server_capable(inode, NFS_CAP_ATIME))
+		else if (fattr_supported & NFS_ATTR_FATTR_ATIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
 		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
 			inode->i_mtime = fattr->mtime;
-		else if (nfs_server_capable(inode, NFS_CAP_MTIME))
+		else if (fattr_supported & NFS_ATTR_FATTR_MTIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
 			inode->i_ctime = fattr->ctime;
-		else if (nfs_server_capable(inode, NFS_CAP_CTIME))
+		else if (fattr_supported & NFS_ATTR_FATTR_CTIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode_set_iversion_raw(inode, fattr->change_attr);
@@ -550,29 +537,31 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_SIZE);
 		if (fattr->valid & NFS_ATTR_FATTR_NLINK)
 			set_nlink(inode, fattr->nlink);
-		else if (nfs_server_capable(inode, NFS_CAP_NLINK))
-			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+		else if (fattr_supported & NFS_ATTR_FATTR_NLINK)
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK);
 		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
 			inode->i_uid = fattr->uid;
-		else if (nfs_server_capable(inode, NFS_CAP_OWNER))
+		else if (fattr_supported & NFS_ATTR_FATTR_OWNER)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
 		if (fattr->valid & NFS_ATTR_FATTR_GROUP)
 			inode->i_gid = fattr->gid;
-		else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
+		else if (fattr_supported & NFS_ATTR_FATTR_GROUP)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
 		if (nfs_server_capable(inode, NFS_CAP_XATTR))
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 			inode->i_blocks = fattr->du.nfs2.blocks;
+		else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED &&
+			 fattr->size != 0)
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
 		if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
 			/*
 			 * report the blocks in 512byte units
 			 */
 			inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
-		}
-
-		if (nfsi->cache_validity != 0)
-			nfsi->cache_validity |= NFS_INO_REVAL_FORCED;
+		} else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED &&
+			   fattr->size != 0)
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS);
 
 		nfs_setsecurity(inode, fattr, label);
 
@@ -634,8 +623,7 @@ nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 	}
 
 	/* Optimization: if the end result is no change, don't RPC */
-	attr->ia_valid &= NFS_VALID_ATTRS;
-	if ((attr->ia_valid & ~(ATTR_FILE|ATTR_OPEN)) == 0)
+	if (((attr->ia_valid & NFS_VALID_ATTRS) & ~(ATTR_FILE|ATTR_OPEN)) == 0)
 		return 0;
 
 	trace_nfs_setattr_enter(inode);
@@ -710,12 +698,20 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
 	spin_lock(&inode->i_lock);
 	NFS_I(inode)->attr_gencount = fattr->gencount;
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
-		nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME);
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME |
+						     NFS_INO_INVALID_BLOCKS);
 		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
 	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
 		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_CTIME;
+		if ((attr->ia_valid & ATTR_KILL_SUID) != 0 &&
+		    inode->i_mode & S_ISUID)
+			inode->i_mode &= ~S_ISUID;
+		if ((attr->ia_valid & ATTR_KILL_SGID) != 0 &&
+		    (inode->i_mode & (S_ISGID | S_IXGRP)) ==
+		     (S_ISGID | S_IXGRP))
+			inode->i_mode &= ~S_ISGID;
 		if ((attr->ia_valid & ATTR_MODE) != 0) {
 			int mode = attr->ia_mode & S_IALLUGO;
 			mode |= inode->i_mode & ~S_IALLUGO;
@@ -793,14 +789,28 @@ static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
 	dput(parent);
 }
 
-static bool nfs_need_revalidate_inode(struct inode *inode)
+static u32 nfs_get_valid_attrmask(struct inode *inode)
 {
-	if (NFS_I(inode)->cache_validity &
-			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
-		return true;
-	if (nfs_attribute_cache_expired(inode))
-		return true;
-	return false;
+	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+	u32 reply_mask = STATX_INO | STATX_TYPE;
+
+	if (!(cache_validity & NFS_INO_INVALID_ATIME))
+		reply_mask |= STATX_ATIME;
+	if (!(cache_validity & NFS_INO_INVALID_CTIME))
+		reply_mask |= STATX_CTIME;
+	if (!(cache_validity & NFS_INO_INVALID_MTIME))
+		reply_mask |= STATX_MTIME;
+	if (!(cache_validity & NFS_INO_INVALID_SIZE))
+		reply_mask |= STATX_SIZE;
+	if (!(cache_validity & NFS_INO_INVALID_NLINK))
+		reply_mask |= STATX_NLINK;
+	if (!(cache_validity & NFS_INO_INVALID_MODE))
+		reply_mask |= STATX_MODE;
+	if (!(cache_validity & NFS_INO_INVALID_OTHER))
+		reply_mask |= STATX_UID | STATX_GID;
+	if (!(cache_validity & NFS_INO_INVALID_BLOCKS))
+		reply_mask |= STATX_BLOCKS;
+	return reply_mask;
 }
 
 int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
@@ -815,9 +825,13 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 
 	trace_nfs_getattr_enter(inode);
 
+	request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID |
+			STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME |
+			STATX_INO | STATX_SIZE | STATX_BLOCKS;
+
 	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
 		nfs_readdirplus_parent_cache_hit(path->dentry);
-		goto out_no_update;
+		goto out_no_revalidate;
 	}
 
 	/* Flush out writes to the server in order to update c/mtime.  */
@@ -850,14 +864,24 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 	/* Check whether the cached attributes are stale */
 	do_update |= force_sync || nfs_attribute_cache_expired(inode);
 	cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
-	do_update |= cache_validity &
-		(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL);
+	do_update |= cache_validity & NFS_INO_INVALID_CHANGE;
 	if (request_mask & STATX_ATIME)
 		do_update |= cache_validity & NFS_INO_INVALID_ATIME;
-	if (request_mask & (STATX_CTIME|STATX_MTIME))
-		do_update |= cache_validity & NFS_INO_REVAL_PAGECACHE;
+	if (request_mask & STATX_CTIME)
+		do_update |= cache_validity & NFS_INO_INVALID_CTIME;
+	if (request_mask & STATX_MTIME)
+		do_update |= cache_validity & NFS_INO_INVALID_MTIME;
+	if (request_mask & STATX_SIZE)
+		do_update |= cache_validity & NFS_INO_INVALID_SIZE;
+	if (request_mask & STATX_NLINK)
+		do_update |= cache_validity & NFS_INO_INVALID_NLINK;
+	if (request_mask & STATX_MODE)
+		do_update |= cache_validity & NFS_INO_INVALID_MODE;
+	if (request_mask & (STATX_UID | STATX_GID))
+		do_update |= cache_validity & NFS_INO_INVALID_OTHER;
 	if (request_mask & STATX_BLOCKS)
 		do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
+
 	if (do_update) {
 		/* Update the attribute cache */
 		if (!(server->flags & NFS_MOUNT_NOAC))
@@ -871,8 +895,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
 		nfs_readdirplus_parent_cache_hit(path->dentry);
 out_no_revalidate:
 	/* Only return attributes that were revalidated. */
-	stat->result_mask &= request_mask;
-out_no_update:
+	stat->result_mask = nfs_get_valid_attrmask(inode) | request_mask;
+
 	generic_fillattr(&init_user_ns, inode, stat);
 	stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
 	if (S_ISDIR(inode->i_mode))
@@ -963,7 +987,6 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
 {
 	struct nfs_inode *nfsi;
 	struct inode *inode;
-	struct nfs_server *server;
 
 	if (!(ctx->mode & FMODE_WRITE))
 		return;
@@ -979,10 +1002,10 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync)
 		return;
 	if (!list_empty(&nfsi->open_files))
 		return;
-	server = NFS_SERVER(inode);
-	if (server->flags & NFS_MOUNT_NOCTO)
+	if (NFS_SERVER(inode)->flags & NFS_MOUNT_NOCTO)
 		return;
-	nfs_revalidate_inode(server, inode);
+	nfs_revalidate_inode(inode,
+			     NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE);
 }
 EXPORT_SYMBOL_GPL(nfs_close_context);
 
@@ -1237,16 +1260,16 @@ int nfs_attribute_cache_expired(struct inode *inode)
 
 /**
  * nfs_revalidate_inode - Revalidate the inode attributes
- * @server: pointer to nfs_server struct
  * @inode: pointer to inode struct
+ * @flags: cache flags to check
  *
  * Updates inode attribute information by retrieving the data from the server.
  */
-int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
+int nfs_revalidate_inode(struct inode *inode, unsigned long flags)
 {
-	if (!nfs_need_revalidate_inode(inode))
+	if (!nfs_check_cache_invalid(inode, flags))
 		return NFS_STALE(inode) ? -ESTALE : 0;
-	return __nfs_revalidate_inode(server, inode);
+	return __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 }
 EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 
@@ -1332,7 +1355,7 @@ out:
 
 bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 {
-	return nfs_check_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE) ||
+	return nfs_check_cache_invalid(inode, NFS_INO_INVALID_CHANGE) ||
 		NFS_STALE(inode);
 }
 
@@ -1468,8 +1491,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	if (!nfs_file_has_buffered_writers(nfsi)) {
 		/* Verify a few of the more important attributes */
 		if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr))
-			invalid |= NFS_INO_INVALID_CHANGE
-				| NFS_INO_REVAL_PAGECACHE;
+			invalid |= NFS_INO_INVALID_CHANGE;
 
 		ts = inode->i_mtime;
 		if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime))
@@ -1483,28 +1505,21 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 			cur_size = i_size_read(inode);
 			new_isize = nfs_size_to_loff_t(fattr->size);
 			if (cur_size != new_isize)
-				invalid |= NFS_INO_INVALID_SIZE
-					| NFS_INO_REVAL_PAGECACHE;
+				invalid |= NFS_INO_INVALID_SIZE;
 		}
 	}
 
 	/* Have any file permissions changed? */
 	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
-		invalid |= NFS_INO_INVALID_ACCESS
-			| NFS_INO_INVALID_ACL
-			| NFS_INO_INVALID_OTHER;
+		invalid |= NFS_INO_INVALID_MODE;
 	if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid))
-		invalid |= NFS_INO_INVALID_ACCESS
-			| NFS_INO_INVALID_ACL
-			| NFS_INO_INVALID_OTHER;
+		invalid |= NFS_INO_INVALID_OTHER;
 	if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid))
-		invalid |= NFS_INO_INVALID_ACCESS
-			| NFS_INO_INVALID_ACL
-			| NFS_INO_INVALID_OTHER;
+		invalid |= NFS_INO_INVALID_OTHER;
 
 	/* Has the link count changed? */
 	if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink)
-		invalid |= NFS_INO_INVALID_OTHER;
+		invalid |= NFS_INO_INVALID_NLINK;
 
 	ts = inode->i_atime;
 	if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime))
@@ -1642,41 +1657,142 @@ EXPORT_SYMBOL_GPL(_nfs_display_fhandle);
 #endif
 
 /**
- * nfs_inode_attrs_need_update - check if the inode attributes need updating
- * @inode: pointer to inode
+ * nfs_inode_attrs_cmp_generic - compare attributes
  * @fattr: attributes
+ * @inode: pointer to inode
+ *
+ * Attempt to divine whether or not an RPC call reply carrying stale
+ * attributes got scheduled after another call carrying updated ones.
+ * Note also the check for wraparound of 'attr_gencount'
+ *
+ * The function returns '1' if it thinks the attributes in @fattr are
+ * more recent than the ones cached in @inode. Otherwise it returns
+ * the value '0'.
+ */
+static int nfs_inode_attrs_cmp_generic(const struct nfs_fattr *fattr,
+				       const struct inode *inode)
+{
+	unsigned long attr_gencount = NFS_I(inode)->attr_gencount;
+
+	return (long)(fattr->gencount - attr_gencount) > 0 ||
+	       (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0;
+}
+
+/**
+ * nfs_inode_attrs_cmp_monotonic - compare attributes
+ * @fattr: attributes
+ * @inode: pointer to inode
  *
  * Attempt to divine whether or not an RPC call reply carrying stale
  * attributes got scheduled after another call carrying updated ones.
  *
- * To do so, the function first assumes that a more recent ctime means
- * that the attributes in fattr are newer, however it also attempt to
- * catch the case where ctime either didn't change, or went backwards
- * (if someone reset the clock on the server) by looking at whether
- * or not this RPC call was started after the inode was last updated.
- * Note also the check for wraparound of 'attr_gencount'
- *
- * The function returns 'true' if it thinks the attributes in 'fattr' are
- * more recent than the ones cached in the inode.
- *
+ * We assume that the server observes monotonic semantics for
+ * the change attribute, so a larger value means that the attributes in
+ * @fattr are more recent, in which case the function returns the
+ * value '1'.
+ * A return value of '0' indicates no measurable change
+ * A return value of '-1' means that the attributes in @inode are
+ * more recent.
  */
-static int nfs_inode_attrs_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
+static int nfs_inode_attrs_cmp_monotonic(const struct nfs_fattr *fattr,
+					 const struct inode *inode)
 {
-	const struct nfs_inode *nfsi = NFS_I(inode);
-
-	return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
-		((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
+	s64 diff = fattr->change_attr - inode_peek_iversion_raw(inode);
+	if (diff > 0)
+		return 1;
+	return diff == 0 ? 0 : -1;
 }
 
-static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
+/**
+ * nfs_inode_attrs_cmp_strict_monotonic - compare attributes
+ * @fattr: attributes
+ * @inode: pointer to inode
+ *
+ * Attempt to divine whether or not an RPC call reply carrying stale
+ * attributes got scheduled after another call carrying updated ones.
+ *
+ * We assume that the server observes strictly monotonic semantics for
+ * the change attribute, so a larger value means that the attributes in
+ * @fattr are more recent, in which case the function returns the
+ * value '1'.
+ * A return value of '-1' means that the attributes in @inode are
+ * more recent or unchanged.
+ */
+static int nfs_inode_attrs_cmp_strict_monotonic(const struct nfs_fattr *fattr,
+						const struct inode *inode)
 {
-	int ret;
+	return  nfs_inode_attrs_cmp_monotonic(fattr, inode) > 0 ? 1 : -1;
+}
+
+/**
+ * nfs_inode_attrs_cmp - compare attributes
+ * @fattr: attributes
+ * @inode: pointer to inode
+ *
+ * This function returns '1' if it thinks the attributes in @fattr are
+ * more recent than the ones cached in @inode. It returns '-1' if
+ * the attributes in @inode are more recent than the ones in @fattr,
+ * and it returns 0 if not sure.
+ */
+static int nfs_inode_attrs_cmp(const struct nfs_fattr *fattr,
+			       const struct inode *inode)
+{
+	if (nfs_inode_attrs_cmp_generic(fattr, inode) > 0)
+		return 1;
+	switch (NFS_SERVER(inode)->change_attr_type) {
+	case NFS4_CHANGE_TYPE_IS_UNDEFINED:
+		break;
+	case NFS4_CHANGE_TYPE_IS_TIME_METADATA:
+		if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE))
+			break;
+		return nfs_inode_attrs_cmp_monotonic(fattr, inode);
+	default:
+		if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE))
+			break;
+		return nfs_inode_attrs_cmp_strict_monotonic(fattr, inode);
+	}
+	return 0;
+}
+
+/**
+ * nfs_inode_finish_partial_attr_update - complete a previous inode update
+ * @fattr: attributes
+ * @inode: pointer to inode
+ *
+ * Returns '1' if the last attribute update left the inode cached
+ * attributes in a partially unrevalidated state, and @fattr
+ * matches the change attribute of that partial update.
+ * Otherwise returns '0'.
+ */
+static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr,
+						const struct inode *inode)
+{
+	const unsigned long check_valid =
+		NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
+		NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
+		NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER |
+		NFS_INO_INVALID_NLINK;
+	unsigned long cache_validity = NFS_I(inode)->cache_validity;
+
+	if (!(cache_validity & NFS_INO_INVALID_CHANGE) &&
+	    (cache_validity & check_valid) != 0 &&
+	    (fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 &&
+	    nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0)
+		return 1;
+	return 0;
+}
+
+static int nfs_refresh_inode_locked(struct inode *inode,
+				    struct nfs_fattr *fattr)
+{
+	int attr_cmp = nfs_inode_attrs_cmp(fattr, inode);
+	int ret = 0;
 
 	trace_nfs_refresh_inode_enter(inode);
 
-	if (nfs_inode_attrs_need_update(inode, fattr))
+	if (attr_cmp > 0 || nfs_inode_finish_partial_attr_update(fattr, inode))
 		ret = nfs_update_inode(inode, fattr);
-	else
+	else if (attr_cmp == 0)
 		ret = nfs_check_inode_attributes(inode, fattr);
 
 	trace_nfs_refresh_inode_exit(inode, ret);
@@ -1761,11 +1877,13 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
  */
 int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
+	int attr_cmp = nfs_inode_attrs_cmp(fattr, inode);
 	int status;
 
 	/* Don't do a WCC update if these attributes are already stale */
-	if ((fattr->valid & NFS_ATTR_FATTR) == 0 ||
-			!nfs_inode_attrs_need_update(inode, fattr)) {
+	if (attr_cmp < 0)
+		return 0;
+	if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !attr_cmp) {
 		fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE
 				| NFS_ATTR_FATTR_PRESIZE
 				| NFS_ATTR_FATTR_PREMTIME
@@ -1839,9 +1957,10 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
  */
 static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
-	struct nfs_server *server;
+	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs_inode *nfsi = NFS_I(inode);
 	loff_t cur_isize, new_isize;
+	u64 fattr_supported = server->fattr_valid;
 	unsigned long invalid = 0;
 	unsigned long now = jiffies;
 	unsigned long save_cache_validity;
@@ -1885,7 +2004,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		goto out_err;
 	}
 
-	server = NFS_SERVER(inode);
 	/* Update the fsid? */
 	if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) &&
 			!nfs_fsid_equal(&server->fsid, &fattr->fsid) &&
@@ -1904,14 +2022,17 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
 			| NFS_INO_INVALID_ATIME
 			| NFS_INO_REVAL_FORCED
-			| NFS_INO_REVAL_PAGECACHE
 			| NFS_INO_INVALID_BLOCKS);
 
 	/* Do atomic weak cache consistency updates */
 	nfs_wcc_update_inode(inode, fattr);
 
 	if (pnfs_layoutcommit_outstanding(inode)) {
-		nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATTR;
+		nfsi->cache_validity |=
+			save_cache_validity &
+			(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
+			 NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
+			 NFS_INO_INVALID_BLOCKS);
 		cache_revalidated = false;
 	}
 
@@ -1928,6 +2049,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				save_cache_validity |= NFS_INO_INVALID_CTIME
 					| NFS_INO_INVALID_MTIME
 					| NFS_INO_INVALID_SIZE
+					| NFS_INO_INVALID_BLOCKS
+					| NFS_INO_INVALID_NLINK
+					| NFS_INO_INVALID_MODE
 					| NFS_INO_INVALID_OTHER;
 				if (S_ISDIR(inode->i_mode))
 					nfs_force_lookup_revalidate(inode);
@@ -1940,28 +2064,24 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			attr_changed = true;
 		}
 	} else {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_CHANGE
-				| NFS_INO_REVAL_PAGECACHE
-				| NFS_INO_REVAL_FORCED);
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_CHANGE;
 		cache_revalidated = false;
 	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
 		inode->i_mtime = fattr->mtime;
-	} else if (server->caps & NFS_CAP_MTIME) {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_MTIME
-				| NFS_INO_REVAL_FORCED);
+	} else if (fattr_supported & NFS_ATTR_FATTR_MTIME) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_MTIME;
 		cache_revalidated = false;
 	}
 
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
 		inode->i_ctime = fattr->ctime;
-	} else if (server->caps & NFS_CAP_CTIME) {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_CTIME
-				| NFS_INO_REVAL_FORCED);
+	} else if (fattr_supported & NFS_ATTR_FATTR_CTIME) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_CTIME;
 		cache_revalidated = false;
 	}
 
@@ -1985,21 +2105,23 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					(long long)cur_isize,
 					(long long)new_isize);
 		}
+		if (new_isize == 0 &&
+		    !(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED |
+				      NFS_ATTR_FATTR_BLOCKS_USED))) {
+			fattr->du.nfs3.used = 0;
+			fattr->valid |= NFS_ATTR_FATTR_SPACE_USED;
+		}
 	} else {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_SIZE
-				| NFS_INO_REVAL_PAGECACHE
-				| NFS_INO_REVAL_FORCED);
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_SIZE;
 		cache_revalidated = false;
 	}
 
-
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 		inode->i_atime = fattr->atime;
-	else if (server->caps & NFS_CAP_ATIME) {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_ATIME
-				| NFS_INO_REVAL_FORCED);
+	else if (fattr_supported & NFS_ATTR_FATTR_ATIME) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_ATIME;
 		cache_revalidated = false;
 	}
 
@@ -2012,10 +2134,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				| NFS_INO_INVALID_ACL;
 			attr_changed = true;
 		}
-	} else if (server->caps & NFS_CAP_MODE) {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_OTHER
-				| NFS_INO_REVAL_FORCED);
+	} else if (fattr_supported & NFS_ATTR_FATTR_MODE) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_MODE;
 		cache_revalidated = false;
 	}
 
@@ -2026,10 +2147,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_uid = fattr->uid;
 			attr_changed = true;
 		}
-	} else if (server->caps & NFS_CAP_OWNER) {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_OTHER
-				| NFS_INO_REVAL_FORCED);
+	} else if (fattr_supported & NFS_ATTR_FATTR_OWNER) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_OTHER;
 		cache_revalidated = false;
 	}
 
@@ -2040,10 +2160,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_gid = fattr->gid;
 			attr_changed = true;
 		}
-	} else if (server->caps & NFS_CAP_OWNER_GROUP) {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_OTHER
-				| NFS_INO_REVAL_FORCED);
+	} else if (fattr_supported & NFS_ATTR_FATTR_GROUP) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_OTHER;
 		cache_revalidated = false;
 	}
 
@@ -2054,10 +2173,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 			attr_changed = true;
 		}
-	} else if (server->caps & NFS_CAP_NLINK) {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_OTHER
-				| NFS_INO_REVAL_FORCED);
+	} else if (fattr_supported & NFS_ATTR_FATTR_NLINK) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_NLINK;
 		cache_revalidated = false;
 	}
 
@@ -2066,18 +2184,22 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		 * report the blocks in 512byte units
 		 */
 		inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
-	} else if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
+	} else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_BLOCKS;
+		cache_revalidated = false;
+	}
+
+	if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) {
 		inode->i_blocks = fattr->du.nfs2.blocks;
-	else {
-		nfsi->cache_validity |= save_cache_validity &
-				(NFS_INO_INVALID_BLOCKS
-				| NFS_INO_REVAL_FORCED);
+	} else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED) {
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_BLOCKS;
 		cache_revalidated = false;
 	}
 
 	/* Update attrtimeo value if we're out of the unstable period */
 	if (attr_changed) {
-		invalid &= ~NFS_INO_INVALID_ATTR;
 		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = now;
@@ -2094,7 +2216,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			nfsi->attrtimeo_timestamp = now;
 		}
 		/* Set the barrier to be more recent than this fattr */
-		if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
+		if ((long)(fattr->gencount - nfsi->attr_gencount) > 0)
 			nfsi->attr_gencount = fattr->gencount;
 	}
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7395d0977b7d..a36af04188c2 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -181,7 +181,7 @@ struct nfs_mount_request {
 	struct net		*net;
 };
 
-extern int nfs_mount(struct nfs_mount_request *info);
+extern int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans);
 extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
index 5088fda9b453..b5551ed8f648 100644
--- a/fs/nfs/io.c
+++ b/fs/nfs/io.c
@@ -104,7 +104,7 @@ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode)
 }
 
 /**
- * nfs_end_io_direct - declare the file is being used for direct i/o
+ * nfs_start_io_direct - declare the file is being used for direct i/o
  * @inode: file inode
  *
  * Declare that a direct I/O operation is about to start, and ensure
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index dda5c3e65d8d..c5e3b6b3366a 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -136,14 +136,16 @@ struct mnt_fhstatus {
 /**
  * nfs_mount - Obtain an NFS file handle for the given host and path
  * @info: pointer to mount request arguments
+ * @timeo: deciseconds the mount waits for a response before it retries
+ * @retrans: number of times the mount retries a request
  *
- * Uses default timeout parameters specified by underlying transport. On
- * successful return, the auth_flavs list and auth_flav_len will be populated
- * with the list from the server or a faked-up list if the server didn't
- * provide one.
+ * Uses timeout parameters specified by caller. On successful return, the
+ * auth_flavs list and auth_flav_len will be populated with the list from the
+ * server or a faked-up list if the server didn't provide one.
  */
-int nfs_mount(struct nfs_mount_request *info)
+int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans)
 {
+	struct rpc_timeout mnt_timeout;
 	struct mountres	result = {
 		.fh		= info->fh,
 		.auth_count	= info->auth_flav_len,
@@ -158,6 +160,7 @@ int nfs_mount(struct nfs_mount_request *info)
 		.protocol	= info->protocol,
 		.address	= info->sap,
 		.addrsize	= info->salen,
+		.timeout	= &mnt_timeout,
 		.servername	= info->hostname,
 		.program	= &mnt_program,
 		.version	= info->version,
@@ -177,6 +180,7 @@ int nfs_mount(struct nfs_mount_request *info)
 	if (info->noresvport)
 		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
 
+	nfs_init_timeout_values(&mnt_timeout, info->protocol, timeo, retrans);
 	mnt_clnt = rpc_create(&args);
 	if (IS_ERR(mnt_clnt))
 		goto out_clnt_err;
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index bb386a691e69..9ec560aa4a50 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -65,7 +65,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	status = nfs_revalidate_inode(server, inode);
+	status = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
 	if (status < 0)
 		return ERR_PTR(status);
 
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index ed1c83738c30..e6eca1d7481b 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -433,7 +433,7 @@ static int decode_nfs_fh3(struct xdr_stream *xdr, struct nfs_fh *fh)
 	if (unlikely(!p))
 		return -EIO;
 	length = be32_to_cpup(p++);
-	if (unlikely(length > NFS3_FHSIZE))
+	if (unlikely(length > NFS3_FHSIZE || length == 0))
 		goto out_toobig;
 	p = xdr_inline_decode(xdr, length);
 	if (unlikely(!p))
@@ -442,7 +442,7 @@ static int decode_nfs_fh3(struct xdr_stream *xdr, struct nfs_fh *fh)
 	memcpy(fh->data, p, length);
 	return 0;
 out_toobig:
-	dprintk("NFS: file handle size (%u) too big\n", length);
+	trace_nfs_xdr_bad_filehandle(xdr, NFSERR_BADHANDLE);
 	return -E2BIG;
 }
 
@@ -2227,6 +2227,7 @@ static int decode_fsinfo3resok(struct xdr_stream *xdr,
 
 	/* ignore properties */
 	result->lease_time = 0;
+	result->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA;
 	return 0;
 }
 
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 094024b0aca1..a24349512ffe 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -46,11 +46,12 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs_server *server = NFS_SERVER(inode);
+	u32 bitmask[3];
 	struct nfs42_falloc_args args = {
 		.falloc_fh	= NFS_FH(inode),
 		.falloc_offset	= offset,
 		.falloc_length	= len,
-		.falloc_bitmask	= nfs4_fattr_bitmap,
+		.falloc_bitmask	= bitmask,
 	};
 	struct nfs42_falloc_res res = {
 		.falloc_server	= server,
@@ -68,6 +69,10 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 		return status;
 	}
 
+	memcpy(bitmask, server->cache_consistency_bitmask, sizeof(bitmask));
+	if (server->attr_bitmask[1] & FATTR4_WORD1_SPACE_USED)
+		bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+
 	res.falloc_fattr = nfs_alloc_fattr();
 	if (!res.falloc_fattr)
 		return -ENOMEM;
@@ -75,7 +80,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	status = nfs4_call_sync(server->client, server, msg,
 				&args.seq_args, &res.seq_res, 0);
 	if (status == 0)
-		status = nfs_post_op_update_inode(inode, res.falloc_fattr);
+		status = nfs_post_op_update_inode_force_wcc(inode,
+							    res.falloc_fattr);
 
 	kfree(res.falloc_fattr);
 	return status;
@@ -84,7 +90,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 				loff_t offset, loff_t len)
 {
-	struct nfs_server *server = NFS_SERVER(file_inode(filep));
+	struct inode *inode = file_inode(filep);
+	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs4_exception exception = { };
 	struct nfs_lock_context *lock;
 	int err;
@@ -93,9 +100,13 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	if (IS_ERR(lock))
 		return PTR_ERR(lock);
 
-	exception.inode = file_inode(filep);
+	exception.inode = inode;
 	exception.state = lock->open_context->state;
 
+	err = nfs_sync_inode(inode);
+	if (err)
+		goto out;
+
 	do {
 		err = _nfs42_proc_fallocate(msg, filep, lock, offset, len);
 		if (err == -ENOTSUPP) {
@@ -104,7 +115,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 		}
 		err = nfs4_handle_exception(server, err, &exception);
 	} while (exception.retry);
-
+out:
 	nfs_put_lock_context(lock);
 	return err;
 }
@@ -142,16 +153,13 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 		return -EOPNOTSUPP;
 
 	inode_lock(inode);
-	err = nfs_sync_inode(inode);
-	if (err)
-		goto out_unlock;
 
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
 	if (err == 0)
 		truncate_pagecache_range(inode, offset, (offset + len) -1);
 	if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_DEALLOCATE;
-out_unlock:
+
 	inode_unlock(inode);
 	return err;
 }
@@ -261,6 +269,33 @@ out:
 	return status;
 }
 
+/**
+ * nfs42_copy_dest_done - perform inode cache updates after clone/copy offload
+ * @inode: pointer to destination inode
+ * @pos: destination offset
+ * @len: copy length
+ *
+ * Punch a hole in the inode page cache, so that the NFS client will
+ * know to retrieve new data.
+ * Update the file size if necessary, and then mark the inode as having
+ * invalid cached values for change attribute, ctime, mtime and space used.
+ */
+static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len)
+{
+	loff_t newsize = pos + len;
+	loff_t end = newsize - 1;
+
+	truncate_pagecache_range(inode, pos, end);
+	spin_lock(&inode->i_lock);
+	if (newsize > i_size_read(inode))
+		i_size_write(inode, newsize);
+	nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+					     NFS_INO_INVALID_CTIME |
+					     NFS_INO_INVALID_MTIME |
+					     NFS_INO_INVALID_BLOCKS);
+	spin_unlock(&inode->i_lock);
+}
+
 static ssize_t _nfs42_proc_copy(struct file *src,
 				struct nfs_lock_context *src_lock,
 				struct file *dst,
@@ -354,19 +389,8 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 			goto out;
 	}
 
-	truncate_pagecache_range(dst_inode, pos_dst,
-				 pos_dst + res->write_res.count);
-	spin_lock(&dst_inode->i_lock);
-	nfs_set_cache_invalid(
-		dst_inode, NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED |
-				   NFS_INO_INVALID_SIZE | NFS_INO_INVALID_ATTR |
-				   NFS_INO_INVALID_DATA);
-	spin_unlock(&dst_inode->i_lock);
-	spin_lock(&src_inode->i_lock);
-	nfs_set_cache_invalid(src_inode, NFS_INO_REVAL_PAGECACHE |
-						 NFS_INO_REVAL_FORCED |
-						 NFS_INO_INVALID_ATIME);
-	spin_unlock(&src_inode->i_lock);
+	nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count);
+	nfs_invalidate_atime(src_inode);
 	status = res->write_res.count;
 out:
 	if (args->sync)
@@ -659,7 +683,10 @@ static loff_t _nfs42_proc_llseek(struct file *filep,
 	if (status)
 		return status;
 
-	return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
+	if (whence == SEEK_DATA && res.sr_eof)
+		return -NFS4ERR_NXIO;
+	else
+		return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
 }
 
 loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
@@ -1044,8 +1071,10 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
 
 	status = nfs4_call_sync(server->client, server, msg,
 				&args.seq_args, &res.seq_res, 0);
-	if (status == 0)
+	if (status == 0) {
+		nfs42_copy_dest_done(dst_inode, dst_offset, count);
 		status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
+	}
 
 	kfree(res.dst_fattr);
 	return status;
diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c
index 6c2ce799150f..1c4d2a05b401 100644
--- a/fs/nfs/nfs42xattr.c
+++ b/fs/nfs/nfs42xattr.c
@@ -168,7 +168,7 @@ nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry)
  *	   make it easier to copy the value after an RPC, even if
  *	   the value will not be passed up to application (e.g.
  *	   for a 'query' getxattr with NULL buffer).
- * @len:   Length of the value. Can be 0 for zero-length attribues.
+ * @len:   Length of the value. Can be 0 for zero-length attributes.
  *         @value and @pages will be NULL if @len is 0.
  */
 static struct nfs4_xattr_entry *
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 441a2fa073c8..57b3821d975a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -420,9 +420,7 @@ static const struct nfs4_ssc_client_ops nfs4_ssc_clnt_ops_tbl = {
  */
 void nfs42_ssc_register_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs42_ssc_register(&nfs4_ssc_clnt_ops_tbl);
-#endif
 }
 
 /**
@@ -433,9 +431,7 @@ void nfs42_ssc_register_ops(void)
  */
 void nfs42_ssc_unregister_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs42_ssc_unregister(&nfs4_ssc_clnt_ops_tbl);
-#endif
 }
 #endif /* CONFIG_NFS_V4_2 */
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 545010d6cbf3..87d04f2c9385 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -108,9 +108,10 @@ 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);
+static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ],
+			     const __u32 *src, struct inode *inode,
+			     struct nfs_server *server,
+			     struct nfs4_label *label);
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 static inline struct nfs4_label *
@@ -263,6 +264,7 @@ const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
 			| FATTR4_WORD1_FS_LAYOUT_TYPES,
 			FATTR4_WORD2_LAYOUT_BLKSIZE
 			| FATTR4_WORD2_CLONE_BLKSIZE
+			| FATTR4_WORD2_CHANGE_ATTR_TYPE
 			| FATTR4_WORD2_XATTR_SUPPORT
 };
 
@@ -283,7 +285,7 @@ const u32 nfs4_fs_locations_bitmap[3] = {
 };
 
 static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
-		struct inode *inode)
+				    struct inode *inode, unsigned long flags)
 {
 	unsigned long cache_validity;
 
@@ -291,22 +293,20 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
 	if (!inode || !nfs4_have_delegation(inode, FMODE_READ))
 		return;
 
-	cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
-	if (!(cache_validity & NFS_INO_REVAL_FORCED))
-		cache_validity &= ~(NFS_INO_INVALID_CHANGE
-				| NFS_INO_INVALID_SIZE);
+	cache_validity = READ_ONCE(NFS_I(inode)->cache_validity) | flags;
 
+	/* Remove the attributes over which we have full control */
+	dst[1] &= ~FATTR4_WORD1_RAWDEV;
 	if (!(cache_validity & NFS_INO_INVALID_SIZE))
 		dst[0] &= ~FATTR4_WORD0_SIZE;
 
 	if (!(cache_validity & NFS_INO_INVALID_CHANGE))
 		dst[0] &= ~FATTR4_WORD0_CHANGE;
-}
 
-static void nfs4_bitmap_copy_adjust_setattr(__u32 *dst,
-		const __u32 *src, struct inode *inode)
-{
-	nfs4_bitmap_copy_adjust(dst, src, inode);
+	if (!(cache_validity & NFS_INO_INVALID_MODE))
+		dst[1] &= ~FATTR4_WORD1_MODE;
+	if (!(cache_validity & NFS_INO_INVALID_OTHER))
+		dst[1] &= ~(FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP);
 }
 
 static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dentry,
@@ -1169,14 +1169,26 @@ int nfs4_call_sync(struct rpc_clnt *clnt,
 static void
 nfs4_inc_nlink_locked(struct inode *inode)
 {
-	nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+	nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+					     NFS_INO_INVALID_CTIME |
+					     NFS_INO_INVALID_NLINK);
 	inc_nlink(inode);
 }
 
+static void
+nfs4_inc_nlink(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	nfs4_inc_nlink_locked(inode);
+	spin_unlock(&inode->i_lock);
+}
+
 static void
 nfs4_dec_nlink_locked(struct inode *inode)
 {
-	nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+	nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+					     NFS_INO_INVALID_CTIME |
+					     NFS_INO_INVALID_NLINK);
 	drop_nlink(inode);
 }
 
@@ -1186,11 +1198,23 @@ nfs4_update_changeattr_locked(struct inode *inode,
 		unsigned long timestamp, unsigned long cache_validity)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
+	u64 change_attr = inode_peek_iversion_raw(inode);
 
 	cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
 
-	if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(inode)) {
-		nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE;
+	switch (NFS_SERVER(inode)->change_attr_type) {
+	case NFS4_CHANGE_TYPE_IS_UNDEFINED:
+		break;
+	case NFS4_CHANGE_TYPE_IS_TIME_METADATA:
+		if ((s64)(change_attr - cinfo->after) > 0)
+			goto out;
+		break;
+	default:
+		if ((s64)(change_attr - cinfo->after) >= 0)
+			goto out;
+	}
+
+	if (cinfo->atomic && cinfo->before == change_attr) {
 		nfsi->attrtimeo_timestamp = jiffies;
 	} else {
 		if (S_ISDIR(inode->i_mode)) {
@@ -1202,7 +1226,7 @@ nfs4_update_changeattr_locked(struct inode *inode,
 				cache_validity |= NFS_INO_REVAL_PAGECACHE;
 		}
 
-		if (cinfo->before != inode_peek_iversion_raw(inode))
+		if (cinfo->before != change_attr)
 			cache_validity |= NFS_INO_INVALID_ACCESS |
 					  NFS_INO_INVALID_ACL |
 					  NFS_INO_INVALID_XATTR;
@@ -1210,8 +1234,9 @@ nfs4_update_changeattr_locked(struct inode *inode,
 	inode_set_iversion_raw(inode, cinfo->after);
 	nfsi->read_cache_jiffies = timestamp;
 	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
-	nfs_set_cache_invalid(inode, cache_validity);
 	nfsi->cache_validity &= ~NFS_INO_INVALID_CHANGE;
+out:
+	nfs_set_cache_invalid(inode, cache_validity);
 }
 
 void
@@ -3344,12 +3369,17 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred,
 		.inode = inode,
 		.stateid = &arg.stateid,
 	};
+	unsigned long adjust_flags = NFS_INO_INVALID_CHANGE;
 	int err;
 
+	if (sattr->ia_valid & (ATTR_MODE | ATTR_KILL_SUID | ATTR_KILL_SGID))
+		adjust_flags |= NFS_INO_INVALID_MODE;
+	if (sattr->ia_valid & (ATTR_UID | ATTR_GID))
+		adjust_flags |= NFS_INO_INVALID_OTHER;
+
 	do {
-		nfs4_bitmap_copy_adjust_setattr(bitmask,
-				nfs4_bitmask(server, olabel),
-				inode);
+		nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, olabel),
+					inode, adjust_flags);
 
 		err = _nfs4_do_setattr(inode, &arg, &res, cred, ctx);
 		switch (err) {
@@ -3591,6 +3621,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
 	struct inode *inode = calldata->inode;
+	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
 	bool is_rdonly, is_wronly, is_rdwr;
 	int call_close = 0;
@@ -3647,8 +3678,10 @@ 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)) {
-			calldata->arg.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
-			nfs4_bitmask_adjust(calldata->arg.bitmask, inode, NFS_SERVER(inode), NULL);
+			nfs4_bitmask_set(calldata->arg.bitmask_store,
+					 server->cache_consistency_bitmask,
+					 inode, server, NULL);
+			calldata->arg.bitmask = calldata->arg.bitmask_store;
 		} else
 			calldata->arg.bitmask = NULL;
 	}
@@ -3835,12 +3868,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 			res.attr_bitmask[2] &= FATTR4_WORD2_NFS42_MASK;
 		}
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
-		server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS|
-				NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
-				NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|
-				NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
-				NFS_CAP_CTIME|NFS_CAP_MTIME|
-				NFS_CAP_SECURITY_LABEL);
+		server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS |
+				  NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL);
+		server->fattr_valid = NFS_ATTR_FATTR_V4;
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
 				res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
 			server->caps |= NFS_CAP_ACLS;
@@ -3848,25 +3878,29 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 			server->caps |= NFS_CAP_HARDLINKS;
 		if (res.has_symlinks != 0)
 			server->caps |= NFS_CAP_SYMLINKS;
-		if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID)
-			server->caps |= NFS_CAP_FILEID;
-		if (res.attr_bitmask[1] & FATTR4_WORD1_MODE)
-			server->caps |= NFS_CAP_MODE;
-		if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS)
-			server->caps |= NFS_CAP_NLINK;
-		if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER)
-			server->caps |= NFS_CAP_OWNER;
-		if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP)
-			server->caps |= NFS_CAP_OWNER_GROUP;
-		if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS)
-			server->caps |= NFS_CAP_ATIME;
-		if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA)
-			server->caps |= NFS_CAP_CTIME;
-		if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)
-			server->caps |= NFS_CAP_MTIME;
+		if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_MODE;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_NLINK;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_OWNER))
+			server->fattr_valid &= ~(NFS_ATTR_FATTR_OWNER |
+				NFS_ATTR_FATTR_OWNER_NAME);
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP))
+			server->fattr_valid &= ~(NFS_ATTR_FATTR_GROUP |
+				NFS_ATTR_FATTR_GROUP_NAME);
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_SPACE_USED))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_SPACE_USED;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_ATIME;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_CTIME;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME;
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
-		if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL)
-			server->caps |= NFS_CAP_SECURITY_LABEL;
+		if (!(res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_V4_SECURITY_LABEL;
 #endif
 		memcpy(server->attr_bitmask_nl, res.attr_bitmask,
 				sizeof(server->attr_bitmask));
@@ -4154,8 +4188,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 	if (inode && (server->flags & NFS_MOUNT_SOFTREVAL))
 		task_flags |= RPC_TASK_TIMEOUT;
 
-	nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode);
-
+	nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode, 0);
 	nfs_fattr_init(fattr);
 	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
 	return nfs4_do_call_sync(server->client, server, &msg,
@@ -4582,11 +4615,11 @@ _nfs4_proc_remove(struct inode *dir, const struct qstr *name, u32 ftype)
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
 	if (status == 0) {
 		spin_lock(&dir->i_lock);
-		nfs4_update_changeattr_locked(dir, &res.cinfo, timestamp,
-					      NFS_INO_INVALID_DATA);
 		/* Removing a directory decrements nlink in the parent */
 		if (ftype == NF4DIR && dir->i_nlink > 2)
 			nfs4_dec_nlink_locked(dir);
+		nfs4_update_changeattr_locked(dir, &res.cinfo, timestamp,
+					      NFS_INO_INVALID_DATA);
 		spin_unlock(&dir->i_lock);
 	}
 	return status;
@@ -4715,11 +4748,11 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 			/* Note: If we moved a directory, nlink will change */
 			nfs4_update_changeattr(old_dir, &res->old_cinfo,
 					res->old_fattr->time_start,
-					NFS_INO_INVALID_OTHER |
+					NFS_INO_INVALID_NLINK |
 					    NFS_INO_INVALID_DATA);
 			nfs4_update_changeattr(new_dir, &res->new_cinfo,
 					res->new_fattr->time_start,
-					NFS_INO_INVALID_OTHER |
+					NFS_INO_INVALID_NLINK |
 					    NFS_INO_INVALID_DATA);
 		} else
 			nfs4_update_changeattr(old_dir, &res->old_cinfo,
@@ -4761,12 +4794,13 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct
 	}
 
 	nfs4_inode_make_writeable(inode);
-	nfs4_bitmap_copy_adjust_setattr(bitmask, nfs4_bitmask(server, res.label), inode);
-
+	nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.label), inode,
+				NFS_INO_INVALID_CHANGE);
 	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 	if (!status) {
 		nfs4_update_changeattr(dir, &res.cinfo, res.fattr->time_start,
 				       NFS_INO_INVALID_DATA);
+		nfs4_inc_nlink(inode);
 		status = nfs_post_op_update_inode(inode, res.fattr);
 		if (!status)
 			nfs_setsecurity(inode, res.fattr, res.label);
@@ -4844,12 +4878,12 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
 				    &data->arg.seq_args, &data->res.seq_res, 1);
 	if (status == 0) {
 		spin_lock(&dir->i_lock);
-		nfs4_update_changeattr_locked(dir, &data->res.dir_cinfo,
-				data->res.fattr->time_start,
-				NFS_INO_INVALID_DATA);
 		/* Creating a directory bumps nlink in the parent */
 		if (data->arg.ftype == NF4DIR)
 			nfs4_inc_nlink_locked(dir);
+		nfs4_update_changeattr_locked(dir, &data->res.dir_cinfo,
+					      data->res.fattr->time_start,
+					      NFS_INO_INVALID_DATA);
 		spin_unlock(&dir->i_lock);
 		status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label);
 	}
@@ -5416,37 +5450,39 @@ 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)
+static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src,
+			     struct inode *inode, struct nfs_server *server,
+			     struct nfs4_label *label)
 {
-
 	unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+	unsigned int i;
 
-	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);
+	memcpy(bitmask, src, sizeof(*bitmask) * NFS4_BITMASK_SZ);
 
-	if (cache_validity & NFS_INO_INVALID_ATIME)
-		bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
-	if (cache_validity & NFS_INO_INVALID_OTHER)
-		bitmask[1] |= FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER |
-				FATTR4_WORD1_OWNER_GROUP |
-				FATTR4_WORD1_NUMLINKS;
-	if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL)
-		bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
 	if (cache_validity & NFS_INO_INVALID_CHANGE)
 		bitmask[0] |= FATTR4_WORD0_CHANGE;
+	if (cache_validity & NFS_INO_INVALID_ATIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_ACCESS;
+	if (cache_validity & NFS_INO_INVALID_MODE)
+		bitmask[1] |= FATTR4_WORD1_MODE;
+	if (cache_validity & NFS_INO_INVALID_OTHER)
+		bitmask[1] |= FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP;
+	if (cache_validity & NFS_INO_INVALID_NLINK)
+		bitmask[1] |= FATTR4_WORD1_NUMLINKS;
+	if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL)
+		bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
 	if (cache_validity & NFS_INO_INVALID_CTIME)
 		bitmask[1] |= FATTR4_WORD1_TIME_METADATA;
 	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;
+
+	if (cache_validity & NFS_INO_INVALID_SIZE)
+		bitmask[0] |= FATTR4_WORD0_SIZE;
+
+	for (i = 0; i < NFS4_BITMASK_SZ; i++)
+		bitmask[i] &= server->attr_bitmask[i];
 }
 
 static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
@@ -5459,8 +5495,10 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 		hdr->args.bitmask = NULL;
 		hdr->res.fattr = NULL;
 	} else {
-		hdr->args.bitmask = server->cache_consistency_bitmask;
-		nfs4_bitmask_adjust(hdr->args.bitmask, hdr->inode, server, NULL);
+		nfs4_bitmask_set(hdr->args.bitmask_store,
+				 server->cache_consistency_bitmask,
+				 hdr->inode, server, NULL);
+		hdr->args.bitmask = hdr->args.bitmask_store;
 	}
 
 	if (!hdr->pgio_done_cb)
@@ -5858,7 +5896,7 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 
 	if (!nfs4_server_supports_acls(server))
 		return -EOPNOTSUPP;
-	ret = nfs_revalidate_inode(server, inode);
+	ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
 	if (ret < 0)
 		return ret;
 	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
@@ -6502,8 +6540,10 @@ 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);
+	nfs4_bitmask_set(data->args.bitmask_store,
+			 server->cache_consistency_bitmask, inode, server,
+			 NULL);
+	data->args.bitmask = data->args.bitmask_store;
 	nfs_copy_fh(&data->fh, NFS_FH(inode));
 	nfs4_stateid_copy(&data->stateid, stateid);
 	data->res.fattr = &data->fattr;
@@ -7250,22 +7290,22 @@ nfs4_retry_setlk_simple(struct nfs4_state *state, int cmd,
 
 #ifdef CONFIG_NFS_V4_1
 struct nfs4_lock_waiter {
-	struct task_struct	*task;
 	struct inode		*inode;
-	struct nfs_lowner	*owner;
+	struct nfs_lowner	owner;
+	wait_queue_entry_t	wait;
 };
 
 static int
 nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, void *key)
 {
-	int ret;
-	struct nfs4_lock_waiter	*waiter	= wait->private;
+	struct nfs4_lock_waiter	*waiter	=
+		container_of(wait, struct nfs4_lock_waiter, wait);
 
 	/* NULL key means to wake up everyone */
 	if (key) {
 		struct cb_notify_lock_args	*cbnl = key;
 		struct nfs_lowner		*lowner = &cbnl->cbnl_owner,
-						*wowner = waiter->owner;
+						*wowner = &waiter->owner;
 
 		/* Only wake if the callback was for the same owner. */
 		if (lowner->id != wowner->id || lowner->s_dev != wowner->s_dev)
@@ -7276,53 +7316,45 @@ nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, vo
 			return 0;
 	}
 
-	/* override "private" so we can use default_wake_function */
-	wait->private = waiter->task;
-	ret = woken_wake_function(wait, mode, flags, key);
-	if (ret)
-		list_del_init(&wait->entry);
-	wait->private = waiter;
-	return ret;
+	return woken_wake_function(wait, mode, flags, key);
 }
 
 static int
 nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 {
-	int status = -ERESTARTSYS;
 	struct nfs4_lock_state *lsp = request->fl_u.nfs4_fl.owner;
 	struct nfs_server *server = NFS_SERVER(state->inode);
 	struct nfs_client *clp = server->nfs_client;
 	wait_queue_head_t *q = &clp->cl_lock_waitq;
-	struct nfs_lowner owner = { .clientid = clp->cl_clientid,
-				    .id = lsp->ls_seqid.owner_id,
-				    .s_dev = server->s_dev };
-	struct nfs4_lock_waiter waiter = { .task  = current,
-					   .inode = state->inode,
-					   .owner = &owner};
-	wait_queue_entry_t wait;
+	struct nfs4_lock_waiter waiter = {
+		.inode = state->inode,
+		.owner = { .clientid = clp->cl_clientid,
+			   .id = lsp->ls_seqid.owner_id,
+			   .s_dev = server->s_dev },
+	};
+	int status;
 
 	/* Don't bother with waitqueue if we don't expect a callback */
 	if (!test_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags))
 		return nfs4_retry_setlk_simple(state, cmd, request);
 
-	init_wait(&wait);
-	wait.private = &waiter;
-	wait.func = nfs4_wake_lock_waiter;
+	init_wait(&waiter.wait);
+	waiter.wait.func = nfs4_wake_lock_waiter;
+	add_wait_queue(q, &waiter.wait);
 
-	while(!signalled()) {
-		add_wait_queue(q, &wait);
+	do {
 		status = nfs4_proc_setlk(state, cmd, request);
-		if ((status != -EAGAIN) || IS_SETLK(cmd)) {
-			finish_wait(q, &wait);
+		if (status != -EAGAIN || IS_SETLK(cmd))
 			break;
-		}
 
 		status = -ERESTARTSYS;
 		freezer_do_not_count();
-		wait_woken(&wait, TASK_INTERRUPTIBLE, NFS4_LOCK_MAXTIMEOUT);
+		wait_woken(&waiter.wait, TASK_INTERRUPTIBLE,
+			   NFS4_LOCK_MAXTIMEOUT);
 		freezer_count();
-		finish_wait(q, &wait);
-	}
+	} while (!signalled());
+
+	remove_wait_queue(q, &waiter.wait);
 
 	return status;
 }
@@ -7615,7 +7647,7 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler,
 			return -EACCES;
 	}
 
-	ret = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
 	if (ret)
 		return ret;
 
@@ -7646,7 +7678,7 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len)
 			return 0;
 	}
 
-	ret = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	ret = nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE);
 	if (ret)
 		return ret;
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2eec5bbb55c8..f22818a80c2c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -645,7 +645,7 @@ void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head)
 }
 
 /**
- * nfs4_purge_state_owners - Release all cached state owners
+ * nfs4_free_state_owners - Release all cached state owners
  * @head: resulting list of state owners
  *
  * Frees a list of state owners that was generated by
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 48d761e593fb..2ef75caad6da 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -666,7 +666,42 @@ TRACE_EVENT(nfs4_state_mgr_failed,
 		)
 )
 
-TRACE_EVENT(nfs4_xdr_status,
+TRACE_EVENT(nfs4_xdr_bad_operation,
+		TP_PROTO(
+			const struct xdr_stream *xdr,
+			u32 op,
+			u32 expected
+		),
+
+		TP_ARGS(xdr, op, expected),
+
+		TP_STRUCT__entry(
+			__field(unsigned int, task_id)
+			__field(unsigned int, client_id)
+			__field(u32, xid)
+			__field(u32, op)
+			__field(u32, expected)
+		),
+
+		TP_fast_assign(
+			const struct rpc_rqst *rqstp = xdr->rqst;
+			const struct rpc_task *task = rqstp->rq_task;
+
+			__entry->task_id = task->tk_pid;
+			__entry->client_id = task->tk_client->cl_clid;
+			__entry->xid = be32_to_cpu(rqstp->rq_xid);
+			__entry->op = op;
+			__entry->expected = expected;
+		),
+
+		TP_printk(
+			"task:%u@%d xid=0x%08x operation=%u, expected=%u",
+			__entry->task_id, __entry->client_id, __entry->xid,
+			__entry->op, __entry->expected
+		)
+);
+
+DECLARE_EVENT_CLASS(nfs4_xdr_event,
 		TP_PROTO(
 			const struct xdr_stream *xdr,
 			u32 op,
@@ -701,6 +736,16 @@ TRACE_EVENT(nfs4_xdr_status,
 			__entry->op
 		)
 );
+#define DEFINE_NFS4_XDR_EVENT(name) \
+	DEFINE_EVENT(nfs4_xdr_event, name, \
+			TP_PROTO( \
+				const struct xdr_stream *xdr, \
+				u32 op, \
+				u32 error \
+			), \
+			TP_ARGS(xdr, op, error))
+DEFINE_NFS4_XDR_EVENT(nfs4_xdr_status);
+DEFINE_NFS4_XDR_EVENT(nfs4_xdr_bad_filehandle);
 
 DECLARE_EVENT_CLASS(nfs4_cb_error_class,
 		TP_PROTO(
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index d4fd3be0e8ca..a8cff19c6f00 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -144,7 +144,17 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
  * layout types will be returned.
  */
 #define decode_fsinfo_maxsz	(op_decode_hdr_maxsz + \
-				 nfs4_fattr_bitmap_maxsz + 4 + 8 + 5)
+				 nfs4_fattr_bitmap_maxsz + 1 + \
+				 1 /* lease time */ + \
+				 2 /* max filesize */ + \
+				 2 /* max read */ + \
+				 2 /* max write */ + \
+				 nfstime4_maxsz /* time delta */ + \
+				 5 /* fs layout types */ + \
+				 1 /* layout blksize */ + \
+				 1 /* clone blksize */ + \
+				 1 /* change attr type */ + \
+				 1 /* xattr support */)
 #define encode_renew_maxsz	(op_encode_hdr_maxsz + 3)
 #define decode_renew_maxsz	(op_decode_hdr_maxsz)
 #define encode_setclientid_maxsz \
@@ -3200,9 +3210,7 @@ out_status:
 	*nfs_retval = nfs4_stat_to_errno(nfserr);
 	return true;
 out_bad_operation:
-	dprintk("nfs: Server returned operation"
-		" %d but we issued a request for %d\n",
-			opnum, expected);
+	trace_nfs4_xdr_bad_operation(xdr, opnum, expected);
 	*nfs_retval = -EREMOTEIO;
 	return false;
 out_overflow:
@@ -3487,8 +3495,11 @@ static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, stru
 		if (unlikely(!p))
 			return -EIO;
 		len = be32_to_cpup(p);
-		if (len > NFS4_FHSIZE)
-			return -EIO;
+		if (len > NFS4_FHSIZE || len == 0) {
+			trace_nfs4_xdr_bad_filehandle(xdr, OP_READDIR,
+						      NFS4ERR_BADHANDLE);
+			return -EREMOTEIO;
+		}
 		p = xdr_inline_decode(xdr, len);
 		if (unlikely(!p))
 			return -EIO;
@@ -4837,6 +4848,32 @@ static int decode_attr_clone_blksize(struct xdr_stream *xdr, uint32_t *bitmap,
 	return 0;
 }
 
+static int decode_attr_change_attr_type(struct xdr_stream *xdr,
+					uint32_t *bitmap,
+					enum nfs4_change_attr_type *res)
+{
+	u32 tmp = NFS4_CHANGE_TYPE_IS_UNDEFINED;
+
+	dprintk("%s: bitmap is %x\n", __func__, bitmap[2]);
+	if (bitmap[2] & FATTR4_WORD2_CHANGE_ATTR_TYPE) {
+		if (xdr_stream_decode_u32(xdr, &tmp))
+			return -EIO;
+		bitmap[2] &= ~FATTR4_WORD2_CHANGE_ATTR_TYPE;
+	}
+
+	switch(tmp) {
+	case NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR:
+	case NFS4_CHANGE_TYPE_IS_VERSION_COUNTER:
+	case NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS:
+	case NFS4_CHANGE_TYPE_IS_TIME_METADATA:
+		*res = tmp;
+		break;
+	default:
+		*res = NFS4_CHANGE_TYPE_IS_UNDEFINED;
+	}
+	return 0;
+}
+
 static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 {
 	unsigned int savep;
@@ -4885,6 +4922,11 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo)
 	if (status)
 		goto xdr_error;
 
+	status = decode_attr_change_attr_type(xdr, bitmap,
+					      &fsinfo->change_attr_type);
+	if (status)
+		goto xdr_error;
+
 	status = decode_attr_xattrsupport(xdr, bitmap,
 					  &fsinfo->xattr_support);
 	if (status)
@@ -4913,8 +4955,10 @@ static int decode_getfh(struct xdr_stream *xdr, struct nfs_fh *fh)
 	if (unlikely(!p))
 		return -EIO;
 	len = be32_to_cpup(p);
-	if (len > NFS4_FHSIZE)
-		return -EIO;
+	if (len > NFS4_FHSIZE || len == 0) {
+		trace_nfs4_xdr_bad_filehandle(xdr, OP_GETFH, NFS4ERR_BADHANDLE);
+		return -EREMOTEIO;
+	}
 	fh->size = len;
 	p = xdr_inline_decode(xdr, len);
 	if (unlikely(!p))
diff --git a/fs/nfs/nfstrace.c b/fs/nfs/nfstrace.c
index a90b363500c2..5d1bfccbb4da 100644
--- a/fs/nfs/nfstrace.c
+++ b/fs/nfs/nfstrace.c
@@ -12,3 +12,4 @@
 EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_enter);
 EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_fsync_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_xdr_status);
+EXPORT_TRACEPOINT_SYMBOL_GPL(nfs_xdr_bad_filehandle);
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 5a59dcdce0b2..eb1ef3462e84 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -45,6 +45,11 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_CTIME);
 TRACE_DEFINE_ENUM(NFS_INO_INVALID_MTIME);
 TRACE_DEFINE_ENUM(NFS_INO_INVALID_SIZE);
 TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
+TRACE_DEFINE_ENUM(NFS_INO_DATA_INVAL_DEFER);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_BLOCKS);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_XATTR);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_NLINK);
+TRACE_DEFINE_ENUM(NFS_INO_INVALID_MODE);
 
 #define nfs_show_cache_validity(v) \
 	__print_flags(v, "|", \
@@ -60,7 +65,11 @@ TRACE_DEFINE_ENUM(NFS_INO_INVALID_OTHER);
 			{ NFS_INO_INVALID_MTIME, "INVALID_MTIME" }, \
 			{ NFS_INO_INVALID_SIZE, "INVALID_SIZE" }, \
 			{ NFS_INO_INVALID_OTHER, "INVALID_OTHER" }, \
-			{ NFS_INO_INVALID_XATTR, "INVALID_XATTR" })
+			{ NFS_INO_DATA_INVAL_DEFER, "DATA_INVAL_DEFER" }, \
+			{ NFS_INO_INVALID_BLOCKS, "INVALID_BLOCKS" }, \
+			{ NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \
+			{ NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \
+			{ NFS_INO_INVALID_MODE, "INVALID_MODE" })
 
 TRACE_DEFINE_ENUM(NFS_INO_ADVISE_RDPLUS);
 TRACE_DEFINE_ENUM(NFS_INO_STALE);
@@ -1392,7 +1401,7 @@ TRACE_DEFINE_ENUM(NFSERR_JUKEBOX);
 			{ NFSERR_BADTYPE, "BADTYPE" }, \
 			{ NFSERR_JUKEBOX, "JUKEBOX" })
 
-TRACE_EVENT(nfs_xdr_status,
+DECLARE_EVENT_CLASS(nfs_xdr_event,
 		TP_PROTO(
 			const struct xdr_stream *xdr,
 			int error
@@ -1434,6 +1443,15 @@ TRACE_EVENT(nfs_xdr_status,
 			nfs_show_status(__entry->error)
 		)
 );
+#define DEFINE_NFS_XDR_EVENT(name) \
+	DEFINE_EVENT(nfs_xdr_event, name, \
+			TP_PROTO( \
+				const struct xdr_stream *xdr, \
+				int error \
+			), \
+			TP_ARGS(xdr, error))
+DEFINE_NFS_XDR_EVENT(nfs_xdr_status);
+DEFINE_NFS_XDR_EVENT(nfs_xdr_bad_filehandle);
 
 #endif /* _TRACE_NFS_H */
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 78c9c4bdef2b..6c20b28d9d7c 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -577,7 +577,7 @@ static void nfs_clear_request(struct nfs_page *req)
 }
 
 /**
- * nfs_release_request - Release the count on an NFS read/write request
+ * nfs_free_request - Release the count on an NFS read/write request
  * @req: request to release
  *
  * Note: Should never be called with the spinlock held!
@@ -1152,7 +1152,7 @@ nfs_pageio_cleanup_request(struct nfs_pageio_descriptor *desc,
 }
 
 /**
- * nfs_pageio_add_request - Attempt to coalesce a request into a page list.
+ * __nfs_pageio_add_request - Attempt to coalesce a request into a page list.
  * @desc: destination io descriptor
  * @req: request
  *
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 102b66e0bdef..03e0b34c4a64 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1344,7 +1344,7 @@ _pnfs_return_layout(struct inode *ino)
 	}
 	valid_layout = pnfs_layout_is_valid(lo);
 	pnfs_clear_layoutcommit(ino, &tmp_list);
-	pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL, 0);
+	pnfs_mark_matching_lsegs_return(lo, &tmp_list, NULL, 0);
 
 	if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
 		struct pnfs_layout_range range = {
@@ -2410,9 +2410,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 			.iomode = IOMODE_ANY,
 			.length = NFS4_MAX_UINT64,
 		};
-		pnfs_set_plh_return_info(lo, IOMODE_ANY, 0);
-		pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
-						&range, 0);
+		pnfs_mark_matching_lsegs_return(lo, &free_me, &range, 0);
 		goto out_forget;
 	} else {
 		/* We have a completely new layout */
@@ -2468,6 +2466,9 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 
 	assert_spin_locked(&lo->plh_inode->i_lock);
 
+	if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
+		tmp_list = &lo->plh_return_segs;
+
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
 		if (pnfs_match_lseg_recall(lseg, return_range, seq)) {
 			dprintk("%s: marking lseg %p iomode %d "
@@ -2475,6 +2476,8 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
 				lseg, lseg->pls_range.iomode,
 				lseg->pls_range.offset,
 				lseg->pls_range.length);
+			if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+				tmp_list = &lo->plh_return_segs;
 			if (mark_lseg_invalid(lseg, tmp_list))
 				continue;
 			remaining++;
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index 73ab7c59d3a7..ea19dbf12301 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -91,6 +91,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 	info->dtpref = fsinfo.tsize;
 	info->maxfilesize = 0x7FFFFFFF;
 	info->lease_time = 0;
+	info->change_attr_type = NFS4_CHANGE_TYPE_IS_TIME_METADATA;
 	return 0;
 }
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 4aaa1f5dd381..19a212f9725d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -116,16 +116,12 @@ static void unregister_nfs4_fs(void)
 #ifdef CONFIG_NFS_V4_2
 static void nfs_ssc_register_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs_ssc_register(&nfs_ssc_clnt_ops_tbl);
-#endif
 }
 
 static void nfs_ssc_unregister_ops(void)
 {
-#ifdef CONFIG_NFSD_V4
 	nfs_ssc_unregister(&nfs_ssc_clnt_ops_tbl);
-#endif
 }
 #endif /* CONFIG_NFS_V4_2 */
 
@@ -867,7 +863,7 @@ static int nfs_request_mount(struct fs_context *fc,
 	 * Now ask the mount server to map our export path
 	 * to a file handle.
 	 */
-	status = nfs_mount(&request);
+	status = nfs_mount(&request, ctx->timeo, ctx->retrans);
 	if (status != 0) {
 		dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
 				request.hostname, status);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f05a90338a76..3bf82178166a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -764,9 +764,6 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	 * with invalidate/truncate.
 	 */
 	spin_lock(&mapping->private_lock);
-	if (!nfs_have_writebacks(inode) &&
-	    NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
-		inode_inc_iversion_raw(inode);
 	if (likely(!PageSwapCache(req->wb_page))) {
 		set_bit(PG_MAPPED, &req->wb_flags);
 		SetPagePrivate(req->wb_page);
@@ -1293,7 +1290,7 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode,
 	if (nfs_have_delegated_attributes(inode))
 		goto out;
 	if (nfsi->cache_validity &
-	    (NFS_INO_REVAL_PAGECACHE | NFS_INO_INVALID_SIZE))
+	    (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE))
 		return false;
 	smp_rmb();
 	if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags) && pagelen != 0)
@@ -1604,7 +1601,7 @@ static int nfs_writeback_done(struct rpc_task *task,
 	/* Deal with the suid/sgid bit corner case */
 	if (nfs_should_remove_suid(inode)) {
 		spin_lock(&inode->i_lock);
-		nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
 		spin_unlock(&inode->i_lock);
 	}
 	return 0;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 5fa38ad9e7e3..f229172652be 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -138,7 +138,7 @@ config NFSD_FLEXFILELAYOUT
 
 config NFSD_V4_2_INTER_SSC
 	bool "NFSv4.2 inter server to server COPY"
-	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
+	depends on NFSD_V4 && NFS_V4_2
 	help
 	  This option enables support for NFSv4.2 inter server to
 	  server copy where the destination server calls the NFSv4.2
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 5b4c67c91f56..15004c469807 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -452,6 +452,7 @@ enum lock_type4 {
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_CLONE_BLKSIZE	(1UL << 13)
+#define FATTR4_WORD2_CHANGE_ATTR_TYPE	(1UL << 15)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
 #define FATTR4_WORD2_MODE_UMASK		(1UL << 17)
 #define FATTR4_WORD2_XATTR_SUPPORT	(1UL << 18)
@@ -709,6 +710,14 @@ struct nl4_server {
 	} u;
 };
 
+enum nfs4_change_attr_type {
+	NFS4_CHANGE_TYPE_IS_MONOTONIC_INCR = 0,
+	NFS4_CHANGE_TYPE_IS_VERSION_COUNTER = 1,
+	NFS4_CHANGE_TYPE_IS_VERSION_COUNTER_NOPNFS = 2,
+	NFS4_CHANGE_TYPE_IS_TIME_METADATA = 3,
+	NFS4_CHANGE_TYPE_IS_UNDEFINED = 4,
+};
+
 /*
  * Options for setxattr. These match the flags for setxattr(2).
  */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index eadaabd18dc7..ffba254d2098 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -246,11 +246,15 @@ struct nfs4_copy_state {
 				BIT(13)		/* Deferred cache invalidation */
 #define NFS_INO_INVALID_BLOCKS	BIT(14)         /* cached blocks are invalid */
 #define NFS_INO_INVALID_XATTR	BIT(15)		/* xattrs are invalid */
+#define NFS_INO_INVALID_NLINK	BIT(16)		/* cached nlinks is invalid */
+#define NFS_INO_INVALID_MODE	BIT(17)		/* cached mode is invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
 		| NFS_INO_INVALID_MTIME \
 		| NFS_INO_INVALID_SIZE \
+		| NFS_INO_INVALID_NLINK \
+		| NFS_INO_INVALID_MODE \
 		| NFS_INO_INVALID_OTHER)	/* inode metadata is invalid */
 
 /*
@@ -386,7 +390,7 @@ extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
 extern int nfs_permission(struct user_namespace *, struct inode *, int);
 extern int nfs_open(struct inode *, struct file *);
 extern int nfs_attribute_cache_expired(struct inode *inode);
-extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
+extern int nfs_revalidate_inode(struct inode *inode, unsigned long flags);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern int nfs_clear_invalid_mapping(struct address_space *mapping);
 extern bool nfs_mapping_need_revalidate_inode(struct inode *inode);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a28d71b45b5f..d71a0e90faeb 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -156,6 +156,7 @@ struct nfs_server {
 #define NFS_MOUNT_WRITE_EAGER		0x01000000
 #define NFS_MOUNT_WRITE_WAIT		0x02000000
 
+	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
 	unsigned int		rsize;		/* read size */
 	unsigned int		rpages;		/* read size (in pages) */
@@ -180,6 +181,9 @@ struct nfs_server {
 #define NFS_OPTION_FSCACHE	0x00000001	/* - local caching enabled */
 #define NFS_OPTION_MIGRATION	0x00000002	/* - NFSv4 migration enabled */
 
+	enum nfs4_change_attr_type
+				change_attr_type;/* Description of change attribute */
+
 	struct nfs_fsid		fsid;
 	__u64			maxfilesize;	/* maximum file size */
 	struct timespec64	time_delta;	/* smallest time granularity */
@@ -265,16 +269,7 @@ struct nfs_server {
 #define NFS_CAP_SYMLINKS	(1U << 2)
 #define NFS_CAP_ACLS		(1U << 3)
 #define NFS_CAP_ATOMIC_OPEN	(1U << 4)
-/* #define NFS_CAP_CHANGE_ATTR	(1U << 5) */
 #define NFS_CAP_LGOPEN		(1U << 5)
-#define NFS_CAP_FILEID		(1U << 6)
-#define NFS_CAP_MODE		(1U << 7)
-#define NFS_CAP_NLINK		(1U << 8)
-#define NFS_CAP_OWNER		(1U << 9)
-#define NFS_CAP_OWNER_GROUP	(1U << 10)
-#define NFS_CAP_ATIME		(1U << 11)
-#define NFS_CAP_CTIME		(1U << 12)
-#define NFS_CAP_MTIME		(1U << 13)
 #define NFS_CAP_POSIX_LOCK	(1U << 14)
 #define NFS_CAP_UIDGID_NOMAP	(1U << 15)
 #define NFS_CAP_STATEID_NFSV41	(1U << 16)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 3327239fa2f9..717ecc87c9e7 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -15,6 +15,8 @@
 #define NFS_DEF_FILE_IO_SIZE	(4096U)
 #define NFS_MIN_FILE_IO_SIZE	(1024U)
 
+#define NFS_BITMASK_SZ		3
+
 struct nfs4_string {
 	unsigned int len;
 	char *data;
@@ -150,6 +152,8 @@ struct nfs_fsinfo {
 	__u32			layouttype[NFS_MAX_LAYOUT_TYPES]; /* supported pnfs layout driver */
 	__u32			blksize; /* preferred pnfs io block size */
 	__u32			clone_blksize; /* granularity of a CLONE operation */
+	enum nfs4_change_attr_type
+				change_attr_type; /* Info about change attr */
 	__u32			xattr_support; /* User xattrs supported */
 };
 
@@ -525,7 +529,8 @@ struct nfs_closeargs {
 	struct nfs_seqid *	seqid;
 	fmode_t			fmode;
 	u32			share_access;
-	u32 *			bitmask;
+	const u32 *		bitmask;
+	u32			bitmask_store[NFS_BITMASK_SZ];
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -608,7 +613,8 @@ struct nfs4_delegreturnargs {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
 	const nfs4_stateid *stateid;
-	u32 * bitmask;
+	const u32 *bitmask;
+	u32 bitmask_store[NFS_BITMASK_SZ];
 	struct nfs4_layoutreturn_args *lr_args;
 };
 
@@ -648,7 +654,8 @@ struct nfs_pgio_args {
 	union {
 		unsigned int		replen;			/* used by read */
 		struct {
-			u32 *			bitmask;	/* used by write */
+			const u32 *		bitmask;	/* used by write */
+			u32 bitmask_store[NFS_BITMASK_SZ];	/* used by write */
 			enum nfs3_stable_how	stable;		/* used by write */
 		};
 	};
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index d2e97ee802af..d81fe8b364d0 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -247,6 +247,7 @@ struct rpc_xprt {
 	struct rpc_task *	snd_task;	/* Task blocked in send */
 
 	struct list_head	xmit_queue;	/* Send queue */
+	atomic_long_t		xmit_queuelen;
 
 	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h
index c838e7ac1c2d..bd55908c1bef 100644
--- a/include/trace/events/rpcrdma.h
+++ b/include/trace/events/rpcrdma.h
@@ -60,6 +60,46 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class,
 				),					\
 				TP_ARGS(wc, cid))
 
+DECLARE_EVENT_CLASS(rpcrdma_mr_completion_class,
+	TP_PROTO(
+		const struct ib_wc *wc,
+		const struct rpc_rdma_cid *cid
+	),
+
+	TP_ARGS(wc, cid),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, completion_id)
+		__field(unsigned long, status)
+		__field(unsigned int, vendor_err)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cid->ci_queue_id;
+		__entry->completion_id = cid->ci_completion_id;
+		__entry->status = wc->status;
+		if (wc->status)
+			__entry->vendor_err = wc->vendor_err;
+		else
+			__entry->vendor_err = 0;
+	),
+
+	TP_printk("cq.id=%u mr.id=%d status=%s (%lu/0x%x)",
+		__entry->cq_id, __entry->completion_id,
+		rdma_show_wc_status(__entry->status),
+		__entry->status, __entry->vendor_err
+	)
+);
+
+#define DEFINE_MR_COMPLETION_EVENT(name)				\
+		DEFINE_EVENT(rpcrdma_mr_completion_class, name,		\
+				TP_PROTO(				\
+					const struct ib_wc *wc,		\
+					const struct rpc_rdma_cid *cid	\
+				),					\
+				TP_ARGS(wc, cid))
+
 DECLARE_EVENT_CLASS(rpcrdma_receive_completion_class,
 	TP_PROTO(
 		const struct ib_wc *wc,
@@ -150,19 +190,17 @@ DECLARE_EVENT_CLASS(xprtrdma_rxprt,
 	TP_ARGS(r_xprt),
 
 	TP_STRUCT__entry(
-		__field(const void *, r_xprt)
 		__string(addr, rpcrdma_addrstr(r_xprt))
 		__string(port, rpcrdma_portstr(r_xprt))
 	),
 
 	TP_fast_assign(
-		__entry->r_xprt = r_xprt;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s r_xprt=%p",
-		__get_str(addr), __get_str(port), __entry->r_xprt
+	TP_printk("peer=[%s]:%s",
+		__get_str(addr), __get_str(port)
 	)
 );
 
@@ -182,7 +220,6 @@ DECLARE_EVENT_CLASS(xprtrdma_connect_class,
 	TP_ARGS(r_xprt, rc),
 
 	TP_STRUCT__entry(
-		__field(const void *, r_xprt)
 		__field(int, rc)
 		__field(int, connect_status)
 		__string(addr, rpcrdma_addrstr(r_xprt))
@@ -190,15 +227,14 @@ DECLARE_EVENT_CLASS(xprtrdma_connect_class,
 	),
 
 	TP_fast_assign(
-		__entry->r_xprt = r_xprt;
 		__entry->rc = rc;
 		__entry->connect_status = r_xprt->rx_ep->re_connect_status;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s r_xprt=%p: rc=%d connection status=%d",
-		__get_str(addr), __get_str(port), __entry->r_xprt,
+	TP_printk("peer=[%s]:%s rc=%d connection status=%d",
+		__get_str(addr), __get_str(port),
 		__entry->rc, __entry->connect_status
 	)
 );
@@ -343,7 +379,7 @@ DECLARE_EVENT_CLASS(xprtrdma_mr_class,
 
 		__entry->task_id = task->tk_pid;
 		__entry->client_id = task->tk_client->cl_clid;
-		__entry->mr_id  = mr->frwr.fr_mr->res.id;
+		__entry->mr_id  = mr->mr_ibmr->res.id;
 		__entry->nents  = mr->mr_nents;
 		__entry->handle = mr->mr_handle;
 		__entry->length = mr->mr_length;
@@ -384,7 +420,7 @@ DECLARE_EVENT_CLASS(xprtrdma_anonymous_mr_class,
 	),
 
 	TP_fast_assign(
-		__entry->mr_id  = mr->frwr.fr_mr->res.id;
+		__entry->mr_id  = mr->mr_ibmr->res.id;
 		__entry->nents  = mr->mr_nents;
 		__entry->handle = mr->mr_handle;
 		__entry->length = mr->mr_length;
@@ -495,22 +531,19 @@ TRACE_EVENT(xprtrdma_op_connect,
 	TP_ARGS(r_xprt, delay),
 
 	TP_STRUCT__entry(
-		__field(const void *, r_xprt)
 		__field(unsigned long, delay)
 		__string(addr, rpcrdma_addrstr(r_xprt))
 		__string(port, rpcrdma_portstr(r_xprt))
 	),
 
 	TP_fast_assign(
-		__entry->r_xprt = r_xprt;
 		__entry->delay = delay;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s r_xprt=%p delay=%lu",
-		__get_str(addr), __get_str(port), __entry->r_xprt,
-		__entry->delay
+	TP_printk("peer=[%s]:%s delay=%lu",
+		__get_str(addr), __get_str(port), __entry->delay
 	)
 );
 
@@ -525,7 +558,6 @@ TRACE_EVENT(xprtrdma_op_set_cto,
 	TP_ARGS(r_xprt, connect, reconnect),
 
 	TP_STRUCT__entry(
-		__field(const void *, r_xprt)
 		__field(unsigned long, connect)
 		__field(unsigned long, reconnect)
 		__string(addr, rpcrdma_addrstr(r_xprt))
@@ -533,51 +565,18 @@ TRACE_EVENT(xprtrdma_op_set_cto,
 	),
 
 	TP_fast_assign(
-		__entry->r_xprt = r_xprt;
 		__entry->connect = connect;
 		__entry->reconnect = reconnect;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s r_xprt=%p: connect=%lu reconnect=%lu",
-		__get_str(addr), __get_str(port), __entry->r_xprt,
+	TP_printk("peer=[%s]:%s connect=%lu reconnect=%lu",
+		__get_str(addr), __get_str(port),
 		__entry->connect / HZ, __entry->reconnect / HZ
 	)
 );
 
-TRACE_EVENT(xprtrdma_qp_event,
-	TP_PROTO(
-		const struct rpcrdma_ep *ep,
-		const struct ib_event *event
-	),
-
-	TP_ARGS(ep, event),
-
-	TP_STRUCT__entry(
-		__field(unsigned long, event)
-		__string(name, event->device->name)
-		__array(unsigned char, srcaddr, sizeof(struct sockaddr_in6))
-		__array(unsigned char, dstaddr, sizeof(struct sockaddr_in6))
-	),
-
-	TP_fast_assign(
-		const struct rdma_cm_id *id = ep->re_id;
-
-		__entry->event = event->event;
-		__assign_str(name, event->device->name);
-		memcpy(__entry->srcaddr, &id->route.addr.src_addr,
-		       sizeof(struct sockaddr_in6));
-		memcpy(__entry->dstaddr, &id->route.addr.dst_addr,
-		       sizeof(struct sockaddr_in6));
-	),
-
-	TP_printk("%pISpc -> %pISpc device=%s %s (%lu)",
-		__entry->srcaddr, __entry->dstaddr, __get_str(name),
-		rdma_show_ib_event(__entry->event), __entry->event
-	)
-);
-
 /**
  ** Call events
  **/
@@ -591,22 +590,19 @@ TRACE_EVENT(xprtrdma_createmrs,
 	TP_ARGS(r_xprt, count),
 
 	TP_STRUCT__entry(
-		__field(const void *, r_xprt)
 		__string(addr, rpcrdma_addrstr(r_xprt))
 		__string(port, rpcrdma_portstr(r_xprt))
 		__field(unsigned int, count)
 	),
 
 	TP_fast_assign(
-		__entry->r_xprt = r_xprt;
 		__entry->count = count;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s r_xprt=%p: created %u MRs",
-		__get_str(addr), __get_str(port), __entry->r_xprt,
-		__entry->count
+	TP_printk("peer=[%s]:%s created %u MRs",
+		__get_str(addr), __get_str(port), __entry->count
 	)
 );
 
@@ -829,7 +825,7 @@ TRACE_EVENT(xprtrdma_post_recvs,
 	TP_ARGS(r_xprt, count, status),
 
 	TP_STRUCT__entry(
-		__field(const void *, r_xprt)
+		__field(u32, cq_id)
 		__field(unsigned int, count)
 		__field(int, status)
 		__field(int, posted)
@@ -838,16 +834,18 @@ TRACE_EVENT(xprtrdma_post_recvs,
 	),
 
 	TP_fast_assign(
-		__entry->r_xprt = r_xprt;
+		const struct rpcrdma_ep *ep = r_xprt->rx_ep;
+
+		__entry->cq_id = ep->re_attr.recv_cq->res.id;
 		__entry->count = count;
 		__entry->status = status;
-		__entry->posted = r_xprt->rx_ep->re_receive_count;
+		__entry->posted = ep->re_receive_count;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s r_xprt=%p: %u new recvs, %d active (rc %d)",
-		__get_str(addr), __get_str(port), __entry->r_xprt,
+	TP_printk("peer=[%s]:%s cq.id=%d %u new recvs, %d active (rc %d)",
+		__get_str(addr), __get_str(port), __entry->cq_id,
 		__entry->count, __entry->posted, __entry->status
 	)
 );
@@ -886,10 +884,10 @@ TRACE_EVENT(xprtrdma_post_linv_err,
 DEFINE_RECEIVE_COMPLETION_EVENT(xprtrdma_wc_receive);
 
 DEFINE_COMPLETION_EVENT(xprtrdma_wc_send);
-DEFINE_COMPLETION_EVENT(xprtrdma_wc_fastreg);
-DEFINE_COMPLETION_EVENT(xprtrdma_wc_li);
-DEFINE_COMPLETION_EVENT(xprtrdma_wc_li_wake);
-DEFINE_COMPLETION_EVENT(xprtrdma_wc_li_done);
+DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_fastreg);
+DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_li);
+DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_li_wake);
+DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_li_done);
 
 TRACE_EVENT(xprtrdma_frwr_alloc,
 	TP_PROTO(
@@ -905,7 +903,7 @@ TRACE_EVENT(xprtrdma_frwr_alloc,
 	),
 
 	TP_fast_assign(
-		__entry->mr_id = mr->frwr.fr_mr->res.id;
+		__entry->mr_id = mr->mr_ibmr->res.id;
 		__entry->rc = rc;
 	),
 
@@ -933,7 +931,7 @@ TRACE_EVENT(xprtrdma_frwr_dereg,
 	),
 
 	TP_fast_assign(
-		__entry->mr_id  = mr->frwr.fr_mr->res.id;
+		__entry->mr_id  = mr->mr_ibmr->res.id;
 		__entry->nents  = mr->mr_nents;
 		__entry->handle = mr->mr_handle;
 		__entry->length = mr->mr_length;
@@ -966,7 +964,7 @@ TRACE_EVENT(xprtrdma_frwr_sgerr,
 	),
 
 	TP_fast_assign(
-		__entry->mr_id = mr->frwr.fr_mr->res.id;
+		__entry->mr_id = mr->mr_ibmr->res.id;
 		__entry->addr = mr->mr_sg->dma_address;
 		__entry->dir = mr->mr_dir;
 		__entry->nents = sg_nents;
@@ -996,7 +994,7 @@ TRACE_EVENT(xprtrdma_frwr_maperr,
 	),
 
 	TP_fast_assign(
-		__entry->mr_id = mr->frwr.fr_mr->res.id;
+		__entry->mr_id = mr->mr_ibmr->res.id;
 		__entry->addr = mr->mr_sg->dma_address;
 		__entry->dir = mr->mr_dir;
 		__entry->num_mapped = num_mapped;
@@ -1010,11 +1008,12 @@ TRACE_EVENT(xprtrdma_frwr_maperr,
 	)
 );
 
+DEFINE_MR_EVENT(fastreg);
 DEFINE_MR_EVENT(localinv);
+DEFINE_MR_EVENT(reminv);
 DEFINE_MR_EVENT(map);
 
 DEFINE_ANON_MR_EVENT(unmap);
-DEFINE_ANON_MR_EVENT(recycle);
 
 TRACE_EVENT(xprtrdma_dma_maperr,
 	TP_PROTO(
@@ -1248,22 +1247,19 @@ TRACE_EVENT(xprtrdma_cb_setup,
 	TP_ARGS(r_xprt, reqs),
 
 	TP_STRUCT__entry(
-		__field(const void *, r_xprt)
 		__field(unsigned int, reqs)
 		__string(addr, rpcrdma_addrstr(r_xprt))
 		__string(port, rpcrdma_portstr(r_xprt))
 	),
 
 	TP_fast_assign(
-		__entry->r_xprt = r_xprt;
 		__entry->reqs = reqs;
 		__assign_str(addr, rpcrdma_addrstr(r_xprt));
 		__assign_str(port, rpcrdma_portstr(r_xprt));
 	),
 
-	TP_printk("peer=[%s]:%s r_xprt=%p: %u reqs",
-		__get_str(addr), __get_str(port),
-		__entry->r_xprt, __entry->reqs
+	TP_printk("peer=[%s]:%s %u reqs",
+		__get_str(addr), __get_str(port), __entry->reqs
 	)
 );
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index bda16e9e6ba7..d02e01a27b69 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1079,6 +1079,46 @@ TRACE_EVENT(xprt_transmit,
 		__entry->seqno, __entry->status)
 );
 
+TRACE_EVENT(xprt_retransmit,
+	TP_PROTO(
+		const struct rpc_rqst *rqst
+	),
+
+	TP_ARGS(rqst),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, task_id)
+		__field(unsigned int, client_id)
+		__field(u32, xid)
+		__field(int, ntrans)
+		__field(int, version)
+		__string(progname,
+			 rqst->rq_task->tk_client->cl_program->name)
+		__string(procedure,
+			 rqst->rq_task->tk_msg.rpc_proc->p_name)
+	),
+
+	TP_fast_assign(
+		struct rpc_task *task = rqst->rq_task;
+
+		__entry->task_id = task->tk_pid;
+		__entry->client_id = task->tk_client ?
+			task->tk_client->cl_clid : -1;
+		__entry->xid = be32_to_cpu(rqst->rq_xid);
+		__entry->ntrans = rqst->rq_ntrans;
+		__assign_str(progname,
+			     task->tk_client->cl_program->name)
+		__entry->version = task->tk_client->cl_vers;
+		__assign_str(procedure, task->tk_msg.rpc_proc->p_name)
+	),
+
+	TP_printk(
+		"task:%u@%u xid=0x%08x %sv%d %s ntrans=%d",
+		__entry->task_id, __entry->client_id, __entry->xid,
+		__get_str(progname), __entry->version, __get_str(procedure),
+		__entry->ntrans)
+);
+
 TRACE_EVENT(xprt_ping,
 	TP_PROTO(const struct rpc_xprt *xprt, int status),
 
@@ -1141,7 +1181,6 @@ DECLARE_EVENT_CLASS(xprt_writelock_event,
 
 DEFINE_WRITELOCK_EVENT(reserve_xprt);
 DEFINE_WRITELOCK_EVENT(release_xprt);
-DEFINE_WRITELOCK_EVENT(transmit_queued);
 
 DECLARE_EVENT_CLASS(xprt_cong_event,
 	TP_PROTO(
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 612f0a641f4c..f555d335e910 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1799,7 +1799,6 @@ call_allocate(struct rpc_task *task)
 
 	status = xprt->ops->buf_alloc(task);
 	trace_rpc_buf_alloc(task, status);
-	xprt_inject_disconnect(xprt);
 	if (status == 0)
 		return;
 	if (status != -ENOMEM) {
@@ -2457,12 +2456,6 @@ call_decode(struct rpc_task *task)
 		task->tk_flags &= ~RPC_CALL_MAJORSEEN;
 	}
 
-	/*
-	 * Ensure that we see all writes made by xprt_complete_rqst()
-	 * before it changed req->rq_reply_bytes_recvd.
-	 */
-	smp_rmb();
-
 	/*
 	 * Did we ever call xprt_complete_rqst()? If not, we should assume
 	 * the message is incomplete.
@@ -2471,6 +2464,11 @@ call_decode(struct rpc_task *task)
 	if (!req->rq_reply_bytes_recvd)
 		goto out;
 
+	/* Ensure that we see all writes made by xprt_complete_rqst()
+	 * before it changed req->rq_reply_bytes_recvd.
+	 */
+	smp_rmb();
+
 	req->rq_rcv_buf.len = req->rq_private_buf.len;
 	trace_rpc_xdr_recvfrom(task, &req->rq_rcv_buf);
 
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 38fe2ce8a5aa..647b323cc1d5 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -344,13 +344,15 @@ static struct rpc_clnt *rpcb_create(struct net *net, const char *nodename,
 				    const char *hostname,
 				    struct sockaddr *srvaddr, size_t salen,
 				    int proto, u32 version,
-				    const struct cred *cred)
+				    const struct cred *cred,
+				    const struct rpc_timeout *timeo)
 {
 	struct rpc_create_args args = {
 		.net		= net,
 		.protocol	= proto,
 		.address	= srvaddr,
 		.addrsize	= salen,
+		.timeout	= timeo,
 		.servername	= hostname,
 		.nodename	= nodename,
 		.program	= &rpcb_program,
@@ -705,7 +707,8 @@ void rpcb_getport_async(struct rpc_task *task)
 				clnt->cl_nodename,
 				xprt->servername, sap, salen,
 				xprt->prot, bind_version,
-				clnt->cl_cred);
+				clnt->cl_cred,
+				task->tk_client->cl_timeout);
 	if (IS_ERR(rpcb_clnt)) {
 		status = PTR_ERR(rpcb_clnt);
 		goto bailout_nofree;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 691ccf8049a4..e5b5a960a69b 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -698,9 +698,9 @@ int xprt_adjust_timeout(struct rpc_rqst *req)
 	const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout;
 	int status = 0;
 
-	if (time_before(jiffies, req->rq_minortimeo))
-		return status;
 	if (time_before(jiffies, req->rq_majortimeo)) {
+		if (time_before(jiffies, req->rq_minortimeo))
+			return status;
 		if (to->to_exponential)
 			req->rq_timeout <<= 1;
 		else
@@ -1352,6 +1352,7 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 		list_add_tail(&req->rq_xmit, &xprt->xmit_queue);
 		INIT_LIST_HEAD(&req->rq_xmit2);
 out:
+		atomic_long_inc(&xprt->xmit_queuelen);
 		set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate);
 		spin_unlock(&xprt->queue_lock);
 	}
@@ -1381,6 +1382,7 @@ xprt_request_dequeue_transmit_locked(struct rpc_task *task)
 		}
 	} else
 		list_del(&req->rq_xmit2);
+	atomic_long_dec(&req->rq_xprt->xmit_queuelen);
 }
 
 /**
@@ -1469,8 +1471,6 @@ bool xprt_prepare_transmit(struct rpc_task *task)
 	struct rpc_xprt	*xprt = req->rq_xprt;
 
 	if (!xprt_lock_write(xprt, task)) {
-		trace_xprt_transmit_queued(xprt, task);
-
 		/* Race breaker: someone may have transmitted us */
 		if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate))
 			rpc_wake_up_queued_task_set_status(&xprt->sending,
@@ -1483,7 +1483,10 @@ bool xprt_prepare_transmit(struct rpc_task *task)
 
 void xprt_end_transmit(struct rpc_task *task)
 {
-	xprt_release_write(task->tk_rqstp->rq_xprt, task);
+	struct rpc_xprt	*xprt = task->tk_rqstp->rq_xprt;
+
+	xprt_inject_disconnect(xprt);
+	xprt_release_write(xprt, task);
 }
 
 /**
@@ -1537,8 +1540,10 @@ xprt_request_transmit(struct rpc_rqst *req, struct rpc_task *snd_task)
 		return status;
 	}
 
-	if (is_retrans)
+	if (is_retrans) {
 		task->tk_client->cl_stats->rpcretrans++;
+		trace_xprt_retransmit(req);
+	}
 
 	xprt_inject_disconnect(xprt);
 
@@ -1885,7 +1890,6 @@ void xprt_release(struct rpc_task *task)
 	spin_unlock(&xprt->transport_lock);
 	if (req->rq_buffer)
 		xprt->ops->buf_free(task);
-	xprt_inject_disconnect(xprt);
 	xdr_free_bvec(&req->rq_rcv_buf);
 	xdr_free_bvec(&req->rq_snd_buf);
 	if (req->rq_cred != NULL)
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index a249837d6a55..1151efd09b27 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -155,9 +155,11 @@ void xprt_rdma_bc_destroy(struct rpc_xprt *xprt, unsigned int reqs)
 void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst)
 {
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
+	struct rpcrdma_rep *rep = req->rl_reply;
 	struct rpc_xprt *xprt = rqst->rq_xprt;
+	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 
-	rpcrdma_recv_buffer_put(req->rl_reply);
+	rpcrdma_rep_put(&r_xprt->rx_buf, rep);
 	req->rl_reply = NULL;
 
 	spin_lock(&xprt->bc_pa_lock);
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 766a1048a48a..229fcc9a9064 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -49,20 +49,13 @@
 # define RPCDBG_FACILITY	RPCDBG_TRANS
 #endif
 
-/**
- * frwr_release_mr - Destroy one MR
- * @mr: MR allocated by frwr_mr_init
- *
- */
-void frwr_release_mr(struct rpcrdma_mr *mr)
+static void frwr_cid_init(struct rpcrdma_ep *ep,
+			  struct rpcrdma_mr *mr)
 {
-	int rc;
+	struct rpc_rdma_cid *cid = &mr->mr_cid;
 
-	rc = ib_dereg_mr(mr->frwr.fr_mr);
-	if (rc)
-		trace_xprtrdma_frwr_dereg(mr, rc);
-	kfree(mr->mr_sg);
-	kfree(mr);
+	cid->ci_queue_id = ep->re_attr.send_cq->res.id;
+	cid->ci_completion_id = mr->mr_ibmr->res.id;
 }
 
 static void frwr_mr_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr)
@@ -75,20 +68,22 @@ static void frwr_mr_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr)
 	}
 }
 
-static void frwr_mr_recycle(struct rpcrdma_mr *mr)
+/**
+ * frwr_mr_release - Destroy one MR
+ * @mr: MR allocated by frwr_mr_init
+ *
+ */
+void frwr_mr_release(struct rpcrdma_mr *mr)
 {
-	struct rpcrdma_xprt *r_xprt = mr->mr_xprt;
+	int rc;
 
-	trace_xprtrdma_mr_recycle(mr);
+	frwr_mr_unmap(mr->mr_xprt, mr);
 
-	frwr_mr_unmap(r_xprt, mr);
-
-	spin_lock(&r_xprt->rx_buf.rb_lock);
-	list_del(&mr->mr_all);
-	r_xprt->rx_stats.mrs_recycled++;
-	spin_unlock(&r_xprt->rx_buf.rb_lock);
-
-	frwr_release_mr(mr);
+	rc = ib_dereg_mr(mr->mr_ibmr);
+	if (rc)
+		trace_xprtrdma_frwr_dereg(mr, rc);
+	kfree(mr->mr_sg);
+	kfree(mr);
 }
 
 static void frwr_mr_put(struct rpcrdma_mr *mr)
@@ -144,10 +139,11 @@ int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr)
 		goto out_list_err;
 
 	mr->mr_xprt = r_xprt;
-	mr->frwr.fr_mr = frmr;
+	mr->mr_ibmr = frmr;
 	mr->mr_device = NULL;
 	INIT_LIST_HEAD(&mr->mr_list);
-	init_completion(&mr->frwr.fr_linv_done);
+	init_completion(&mr->mr_linv_done);
+	frwr_cid_init(ep, mr);
 
 	sg_init_table(sg, depth);
 	mr->mr_sg = sg;
@@ -257,6 +253,7 @@ int frwr_query_device(struct rpcrdma_ep *ep, const struct ib_device *device)
 	ep->re_attr.cap.max_send_wr += 1; /* for ib_drain_sq */
 	ep->re_attr.cap.max_recv_wr = ep->re_max_requests;
 	ep->re_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
+	ep->re_attr.cap.max_recv_wr += RPCRDMA_MAX_RECV_BATCH;
 	ep->re_attr.cap.max_recv_wr += 1; /* for ib_drain_rq */
 
 	ep->re_max_rdma_segs =
@@ -326,7 +323,7 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 		goto out_dmamap_err;
 	mr->mr_device = ep->re_id->device;
 
-	ibmr = mr->frwr.fr_mr;
+	ibmr = mr->mr_ibmr;
 	n = ib_map_mr_sg(ibmr, mr->mr_sg, dma_nents, NULL, PAGE_SIZE);
 	if (n != dma_nents)
 		goto out_mapmr_err;
@@ -336,7 +333,7 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	key = (u8)(ibmr->rkey & 0x000000FF);
 	ib_update_fast_reg_key(ibmr, ++key);
 
-	reg_wr = &mr->frwr.fr_regwr;
+	reg_wr = &mr->mr_regwr;
 	reg_wr->mr = ibmr;
 	reg_wr->key = ibmr->rkey;
 	reg_wr->access = writing ?
@@ -364,29 +361,19 @@ out_mapmr_err:
  * @cq: completion queue
  * @wc: WCE for a completed FastReg WR
  *
+ * Each flushed MR gets destroyed after the QP has drained.
  */
 static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct ib_cqe *cqe = wc->wr_cqe;
-	struct rpcrdma_frwr *frwr =
-		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
+	struct rpcrdma_mr *mr = container_of(cqe, struct rpcrdma_mr, mr_cqe);
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_fastreg(wc, &frwr->fr_cid);
-	/* The MR will get recycled when the associated req is retransmitted */
+	trace_xprtrdma_wc_fastreg(wc, &mr->mr_cid);
 
 	rpcrdma_flush_disconnect(cq->cq_context, wc);
 }
 
-static void frwr_cid_init(struct rpcrdma_ep *ep,
-			  struct rpcrdma_frwr *frwr)
-{
-	struct rpc_rdma_cid *cid = &frwr->fr_cid;
-
-	cid->ci_queue_id = ep->re_attr.send_cq->res.id;
-	cid->ci_completion_id = frwr->fr_mr->res.id;
-}
-
 /**
  * frwr_send - post Send WRs containing the RPC Call message
  * @r_xprt: controlling transport instance
@@ -403,27 +390,36 @@ static void frwr_cid_init(struct rpcrdma_ep *ep,
  */
 int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
+	struct ib_send_wr *post_wr, *send_wr = &req->rl_wr;
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
-	struct ib_send_wr *post_wr;
 	struct rpcrdma_mr *mr;
+	unsigned int num_wrs;
 
-	post_wr = &req->rl_wr;
+	num_wrs = 1;
+	post_wr = send_wr;
 	list_for_each_entry(mr, &req->rl_registered, mr_list) {
-		struct rpcrdma_frwr *frwr;
+		trace_xprtrdma_mr_fastreg(mr);
 
-		frwr = &mr->frwr;
-
-		frwr->fr_cqe.done = frwr_wc_fastreg;
-		frwr_cid_init(ep, frwr);
-		frwr->fr_regwr.wr.next = post_wr;
-		frwr->fr_regwr.wr.wr_cqe = &frwr->fr_cqe;
-		frwr->fr_regwr.wr.num_sge = 0;
-		frwr->fr_regwr.wr.opcode = IB_WR_REG_MR;
-		frwr->fr_regwr.wr.send_flags = 0;
-
-		post_wr = &frwr->fr_regwr.wr;
+		mr->mr_cqe.done = frwr_wc_fastreg;
+		mr->mr_regwr.wr.next = post_wr;
+		mr->mr_regwr.wr.wr_cqe = &mr->mr_cqe;
+		mr->mr_regwr.wr.num_sge = 0;
+		mr->mr_regwr.wr.opcode = IB_WR_REG_MR;
+		mr->mr_regwr.wr.send_flags = 0;
+		post_wr = &mr->mr_regwr.wr;
+		++num_wrs;
 	}
 
+	if ((kref_read(&req->rl_kref) > 1) || num_wrs > ep->re_send_count) {
+		send_wr->send_flags |= IB_SEND_SIGNALED;
+		ep->re_send_count = min_t(unsigned int, ep->re_send_batch,
+					  num_wrs - ep->re_send_count);
+	} else {
+		send_wr->send_flags &= ~IB_SEND_SIGNALED;
+		ep->re_send_count -= num_wrs;
+	}
+
+	trace_xprtrdma_post_send(req);
 	return ib_post_send(ep->re_id->qp, post_wr, NULL);
 }
 
@@ -440,6 +436,7 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs)
 	list_for_each_entry(mr, mrs, mr_list)
 		if (mr->mr_handle == rep->rr_inv_rkey) {
 			list_del_init(&mr->mr_list);
+			trace_xprtrdma_mr_reminv(mr);
 			frwr_mr_put(mr);
 			break;	/* only one invalidated MR per RPC */
 		}
@@ -447,9 +444,7 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs)
 
 static void frwr_mr_done(struct ib_wc *wc, struct rpcrdma_mr *mr)
 {
-	if (wc->status != IB_WC_SUCCESS)
-		frwr_mr_recycle(mr);
-	else
+	if (likely(wc->status == IB_WC_SUCCESS))
 		frwr_mr_put(mr);
 }
 
@@ -462,12 +457,10 @@ static void frwr_mr_done(struct ib_wc *wc, struct rpcrdma_mr *mr)
 static void frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct ib_cqe *cqe = wc->wr_cqe;
-	struct rpcrdma_frwr *frwr =
-		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
-	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
+	struct rpcrdma_mr *mr = container_of(cqe, struct rpcrdma_mr, mr_cqe);
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_li(wc, &frwr->fr_cid);
+	trace_xprtrdma_wc_li(wc, &mr->mr_cid);
 	frwr_mr_done(wc, mr);
 
 	rpcrdma_flush_disconnect(cq->cq_context, wc);
@@ -483,14 +476,12 @@ static void frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc)
 static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct ib_cqe *cqe = wc->wr_cqe;
-	struct rpcrdma_frwr *frwr =
-		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
-	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
+	struct rpcrdma_mr *mr = container_of(cqe, struct rpcrdma_mr, mr_cqe);
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_li_wake(wc, &frwr->fr_cid);
+	trace_xprtrdma_wc_li_wake(wc, &mr->mr_cid);
 	frwr_mr_done(wc, mr);
-	complete(&frwr->fr_linv_done);
+	complete(&mr->mr_linv_done);
 
 	rpcrdma_flush_disconnect(cq->cq_context, wc);
 }
@@ -511,7 +502,6 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	struct ib_send_wr *first, **prev, *last;
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	const struct ib_send_wr *bad_wr;
-	struct rpcrdma_frwr *frwr;
 	struct rpcrdma_mr *mr;
 	int rc;
 
@@ -520,35 +510,34 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * Chain the LOCAL_INV Work Requests and post them with
 	 * a single ib_post_send() call.
 	 */
-	frwr = NULL;
 	prev = &first;
 	while ((mr = rpcrdma_mr_pop(&req->rl_registered))) {
 
 		trace_xprtrdma_mr_localinv(mr);
 		r_xprt->rx_stats.local_inv_needed++;
 
-		frwr = &mr->frwr;
-		frwr->fr_cqe.done = frwr_wc_localinv;
-		frwr_cid_init(ep, frwr);
-		last = &frwr->fr_invwr;
+		last = &mr->mr_invwr;
 		last->next = NULL;
-		last->wr_cqe = &frwr->fr_cqe;
+		last->wr_cqe = &mr->mr_cqe;
 		last->sg_list = NULL;
 		last->num_sge = 0;
 		last->opcode = IB_WR_LOCAL_INV;
 		last->send_flags = IB_SEND_SIGNALED;
 		last->ex.invalidate_rkey = mr->mr_handle;
 
+		last->wr_cqe->done = frwr_wc_localinv;
+
 		*prev = last;
 		prev = &last->next;
 	}
+	mr = container_of(last, struct rpcrdma_mr, mr_invwr);
 
 	/* Strong send queue ordering guarantees that when the
 	 * last WR in the chain completes, all WRs in the chain
 	 * are complete.
 	 */
-	frwr->fr_cqe.done = frwr_wc_localinv_wake;
-	reinit_completion(&frwr->fr_linv_done);
+	last->wr_cqe->done = frwr_wc_localinv_wake;
+	reinit_completion(&mr->mr_linv_done);
 
 	/* Transport disconnect drains the receive CQ before it
 	 * replaces the QP. The RPC reply handler won't call us
@@ -562,22 +551,12 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * not happen, so don't wait in that case.
 	 */
 	if (bad_wr != first)
-		wait_for_completion(&frwr->fr_linv_done);
+		wait_for_completion(&mr->mr_linv_done);
 	if (!rc)
 		return;
 
-	/* Recycle MRs in the LOCAL_INV chain that did not get posted.
-	 */
+	/* On error, the MRs get destroyed once the QP has drained. */
 	trace_xprtrdma_post_linv_err(req, rc);
-	while (bad_wr) {
-		frwr = container_of(bad_wr, struct rpcrdma_frwr,
-				    fr_invwr);
-		mr = container_of(frwr, struct rpcrdma_mr, frwr);
-		bad_wr = bad_wr->next;
-
-		list_del_init(&mr->mr_list);
-		frwr_mr_recycle(mr);
-	}
 }
 
 /**
@@ -589,20 +568,24 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct ib_cqe *cqe = wc->wr_cqe;
-	struct rpcrdma_frwr *frwr =
-		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
-	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
-	struct rpcrdma_rep *rep = mr->mr_req->rl_reply;
+	struct rpcrdma_mr *mr = container_of(cqe, struct rpcrdma_mr, mr_cqe);
+	struct rpcrdma_rep *rep;
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_li_done(wc, &frwr->fr_cid);
-	frwr_mr_done(wc, mr);
+	trace_xprtrdma_wc_li_done(wc, &mr->mr_cid);
 
-	/* Ensure @rep is generated before frwr_mr_done */
+	/* Ensure that @rep is generated before the MR is released */
+	rep = mr->mr_req->rl_reply;
 	smp_rmb();
-	rpcrdma_complete_rqst(rep);
 
-	rpcrdma_flush_disconnect(cq->cq_context, wc);
+	if (wc->status != IB_WC_SUCCESS) {
+		if (rep)
+			rpcrdma_unpin_rqst(rep);
+		rpcrdma_flush_disconnect(cq->cq_context, wc);
+		return;
+	}
+	frwr_mr_put(mr);
+	rpcrdma_complete_rqst(rep);
 }
 
 /**
@@ -619,33 +602,29 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
 	struct ib_send_wr *first, *last, **prev;
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
-	const struct ib_send_wr *bad_wr;
-	struct rpcrdma_frwr *frwr;
 	struct rpcrdma_mr *mr;
 	int rc;
 
 	/* Chain the LOCAL_INV Work Requests and post them with
 	 * a single ib_post_send() call.
 	 */
-	frwr = NULL;
 	prev = &first;
 	while ((mr = rpcrdma_mr_pop(&req->rl_registered))) {
 
 		trace_xprtrdma_mr_localinv(mr);
 		r_xprt->rx_stats.local_inv_needed++;
 
-		frwr = &mr->frwr;
-		frwr->fr_cqe.done = frwr_wc_localinv;
-		frwr_cid_init(ep, frwr);
-		last = &frwr->fr_invwr;
+		last = &mr->mr_invwr;
 		last->next = NULL;
-		last->wr_cqe = &frwr->fr_cqe;
+		last->wr_cqe = &mr->mr_cqe;
 		last->sg_list = NULL;
 		last->num_sge = 0;
 		last->opcode = IB_WR_LOCAL_INV;
 		last->send_flags = IB_SEND_SIGNALED;
 		last->ex.invalidate_rkey = mr->mr_handle;
 
+		last->wr_cqe->done = frwr_wc_localinv;
+
 		*prev = last;
 		prev = &last->next;
 	}
@@ -655,31 +634,23 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * are complete. The last completion will wake up the
 	 * RPC waiter.
 	 */
-	frwr->fr_cqe.done = frwr_wc_localinv_done;
+	last->wr_cqe->done = frwr_wc_localinv_done;
 
 	/* Transport disconnect drains the receive CQ before it
 	 * replaces the QP. The RPC reply handler won't call us
 	 * unless re_id->qp is a valid pointer.
 	 */
-	bad_wr = NULL;
-	rc = ib_post_send(ep->re_id->qp, first, &bad_wr);
+	rc = ib_post_send(ep->re_id->qp, first, NULL);
 	if (!rc)
 		return;
 
-	/* Recycle MRs in the LOCAL_INV chain that did not get posted.
-	 */
+	/* On error, the MRs get destroyed once the QP has drained. */
 	trace_xprtrdma_post_linv_err(req, rc);
-	while (bad_wr) {
-		frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr);
-		mr = container_of(frwr, struct rpcrdma_mr, frwr);
-		bad_wr = bad_wr->next;
-
-		frwr_mr_recycle(mr);
-	}
 
 	/* The final LOCAL_INV WR in the chain is supposed to
-	 * do the wake. If it was never posted, the wake will
-	 * not happen, so wake here in that case.
+	 * do the wake. If it was never posted, the wake does
+	 * not happen. Unpin the rqst in preparation for its
+	 * retransmission.
 	 */
-	rpcrdma_complete_rqst(req->rl_reply);
+	rpcrdma_unpin_rqst(req->rl_reply);
 }
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 292f066d006e..649f7d8b9733 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1326,9 +1326,35 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep,
 	return -EIO;
 }
 
-/* Perform XID lookup, reconstruction of the RPC reply, and
- * RPC completion while holding the transport lock to ensure
- * the rep, rqst, and rq_task pointers remain stable.
+/**
+ * rpcrdma_unpin_rqst - Release rqst without completing it
+ * @rep: RPC/RDMA Receive context
+ *
+ * This is done when a connection is lost so that a Reply
+ * can be dropped and its matching Call can be subsequently
+ * retransmitted on a new connection.
+ */
+void rpcrdma_unpin_rqst(struct rpcrdma_rep *rep)
+{
+	struct rpc_xprt *xprt = &rep->rr_rxprt->rx_xprt;
+	struct rpc_rqst *rqst = rep->rr_rqst;
+	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
+
+	req->rl_reply = NULL;
+	rep->rr_rqst = NULL;
+
+	spin_lock(&xprt->queue_lock);
+	xprt_unpin_rqst(rqst);
+	spin_unlock(&xprt->queue_lock);
+}
+
+/**
+ * rpcrdma_complete_rqst - Pass completed rqst back to RPC
+ * @rep: RPC/RDMA Receive context
+ *
+ * Reconstruct the RPC reply and complete the transaction
+ * while @rqst is still pinned to ensure the rep, rqst, and
+ * rq_task pointers remain stable.
  */
 void rpcrdma_complete_rqst(struct rpcrdma_rep *rep)
 {
@@ -1430,13 +1456,14 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 		credits = 1;	/* don't deadlock */
 	else if (credits > r_xprt->rx_ep->re_max_requests)
 		credits = r_xprt->rx_ep->re_max_requests;
+	rpcrdma_post_recvs(r_xprt, credits + (buf->rb_bc_srv_max_requests << 1),
+			   false);
 	if (buf->rb_credits != credits)
 		rpcrdma_update_cwnd(r_xprt, credits);
-	rpcrdma_post_recvs(r_xprt, false);
 
 	req = rpcr_to_rdmar(rqst);
 	if (unlikely(req->rl_reply))
-		rpcrdma_recv_buffer_put(req->rl_reply);
+		rpcrdma_rep_put(buf, req->rl_reply);
 	req->rl_reply = rep;
 	rep->rr_rqst = rqst;
 
@@ -1464,5 +1491,5 @@ out_shortreply:
 	trace_xprtrdma_reply_short_err(rep);
 
 out:
-	rpcrdma_recv_buffer_put(rep);
+	rpcrdma_rep_put(buf, rep);
 }
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 78d29d1bcc20..09953597d055 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -262,8 +262,10 @@ xprt_rdma_connect_worker(struct work_struct *work)
  * xprt_rdma_inject_disconnect - inject a connection fault
  * @xprt: transport context
  *
- * If @xprt is connected, disconnect it to simulate spurious connection
- * loss.
+ * If @xprt is connected, disconnect it to simulate spurious
+ * connection loss. Caller must hold @xprt's send lock to
+ * ensure that data structures and hardware resources are
+ * stable during the rdma_disconnect() call.
  */
 static void
 xprt_rdma_inject_disconnect(struct rpc_xprt *xprt)
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index ec912cf9c618..1e965a380896 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -101,6 +101,12 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt)
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	struct rdma_cm_id *id = ep->re_id;
 
+	/* Wait for rpcrdma_post_recvs() to leave its critical
+	 * section.
+	 */
+	if (atomic_inc_return(&ep->re_receiving) > 1)
+		wait_for_completion(&ep->re_done);
+
 	/* Flush Receives, then wait for deferred Reply work
 	 * to complete.
 	 */
@@ -114,22 +120,6 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt)
 	rpcrdma_ep_put(ep);
 }
 
-/**
- * rpcrdma_qp_event_handler - Handle one QP event (error notification)
- * @event: details of the event
- * @context: ep that owns QP where event occurred
- *
- * Called from the RDMA provider (device driver) possibly in an interrupt
- * context. The QP is always destroyed before the ID, so the ID will be
- * reliably available when this handler is invoked.
- */
-static void rpcrdma_qp_event_handler(struct ib_event *event, void *context)
-{
-	struct rpcrdma_ep *ep = context;
-
-	trace_xprtrdma_qp_event(ep, event);
-}
-
 /* Ensure xprt_force_disconnect() is invoked exactly once when a
  * connection is closed or lost. (The important thing is it needs
  * to be invoked "at least" once).
@@ -205,7 +195,7 @@ static void rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 
 out_flushed:
 	rpcrdma_flush_disconnect(r_xprt, wc);
-	rpcrdma_rep_destroy(rep);
+	rpcrdma_rep_put(&r_xprt->rx_buf, rep);
 }
 
 static void rpcrdma_update_cm_private(struct rpcrdma_ep *ep,
@@ -414,6 +404,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 	__module_get(THIS_MODULE);
 	device = id->device;
 	ep->re_id = id;
+	reinit_completion(&ep->re_done);
 
 	ep->re_max_requests = r_xprt->rx_xprt.max_reqs;
 	ep->re_inline_send = xprt_rdma_max_inline_write;
@@ -424,8 +415,6 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt)
 
 	r_xprt->rx_buf.rb_max_requests = cpu_to_be32(ep->re_max_requests);
 
-	ep->re_attr.event_handler = rpcrdma_qp_event_handler;
-	ep->re_attr.qp_context = ep;
 	ep->re_attr.srq = NULL;
 	ep->re_attr.cap.max_inline_data = 0;
 	ep->re_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
@@ -535,7 +524,7 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt)
 	 * outstanding Receives.
 	 */
 	rpcrdma_ep_get(ep);
-	rpcrdma_post_recvs(r_xprt, true);
+	rpcrdma_post_recvs(r_xprt, 1, true);
 
 	rc = rdma_connect(ep->re_id, &ep->re_remote_cma);
 	if (rc)
@@ -954,13 +943,11 @@ static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt)
 		rpcrdma_req_reset(req);
 }
 
-/* No locking needed here. This function is called only by the
- * Receive completion handler.
- */
 static noinline
 struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt,
 				       bool temp)
 {
+	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	struct rpcrdma_rep *rep;
 
 	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
@@ -987,7 +974,10 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt,
 	rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
 	rep->rr_recv_wr.num_sge = 1;
 	rep->rr_temp = temp;
-	list_add(&rep->rr_all, &r_xprt->rx_buf.rb_all_reps);
+
+	spin_lock(&buf->rb_lock);
+	list_add(&rep->rr_all, &buf->rb_all_reps);
+	spin_unlock(&buf->rb_lock);
 	return rep;
 
 out_free_regbuf:
@@ -998,16 +988,23 @@ out:
 	return NULL;
 }
 
-/* No locking needed here. This function is invoked only by the
- * Receive completion handler, or during transport shutdown.
- */
-static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep)
+static void rpcrdma_rep_free(struct rpcrdma_rep *rep)
 {
-	list_del(&rep->rr_all);
 	rpcrdma_regbuf_free(rep->rr_rdmabuf);
 	kfree(rep);
 }
 
+static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep)
+{
+	struct rpcrdma_buffer *buf = &rep->rr_rxprt->rx_buf;
+
+	spin_lock(&buf->rb_lock);
+	list_del(&rep->rr_all);
+	spin_unlock(&buf->rb_lock);
+
+	rpcrdma_rep_free(rep);
+}
+
 static struct rpcrdma_rep *rpcrdma_rep_get_locked(struct rpcrdma_buffer *buf)
 {
 	struct llist_node *node;
@@ -1019,12 +1016,21 @@ static struct rpcrdma_rep *rpcrdma_rep_get_locked(struct rpcrdma_buffer *buf)
 	return llist_entry(node, struct rpcrdma_rep, rr_node);
 }
 
-static void rpcrdma_rep_put(struct rpcrdma_buffer *buf,
-			    struct rpcrdma_rep *rep)
+/**
+ * rpcrdma_rep_put - Release rpcrdma_rep back to free list
+ * @buf: buffer pool
+ * @rep: rep to release
+ *
+ */
+void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep)
 {
 	llist_add(&rep->rr_node, &buf->rb_free_reps);
 }
 
+/* Caller must ensure the QP is quiescent (RQ is drained) before
+ * invoking this function, to guarantee rb_all_reps is not
+ * changing.
+ */
 static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt)
 {
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
@@ -1032,7 +1038,7 @@ static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt)
 
 	list_for_each_entry(rep, &buf->rb_all_reps, rr_all) {
 		rpcrdma_regbuf_dma_unmap(rep->rr_rdmabuf);
-		rep->rr_temp = true;
+		rep->rr_temp = true;	/* Mark this rep for destruction */
 	}
 }
 
@@ -1040,8 +1046,18 @@ static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf)
 {
 	struct rpcrdma_rep *rep;
 
-	while ((rep = rpcrdma_rep_get_locked(buf)) != NULL)
-		rpcrdma_rep_destroy(rep);
+	spin_lock(&buf->rb_lock);
+	while ((rep = list_first_entry_or_null(&buf->rb_all_reps,
+					       struct rpcrdma_rep,
+					       rr_all)) != NULL) {
+		list_del(&rep->rr_all);
+		spin_unlock(&buf->rb_lock);
+
+		rpcrdma_rep_free(rep);
+
+		spin_lock(&buf->rb_lock);
+	}
+	spin_unlock(&buf->rb_lock);
 }
 
 /**
@@ -1104,7 +1120,7 @@ void rpcrdma_req_destroy(struct rpcrdma_req *req)
 		list_del(&mr->mr_all);
 		spin_unlock(&buf->rb_lock);
 
-		frwr_release_mr(mr);
+		frwr_mr_release(mr);
 	}
 
 	rpcrdma_regbuf_free(req->rl_recvbuf);
@@ -1135,7 +1151,7 @@ static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt)
 		list_del(&mr->mr_all);
 		spin_unlock(&buf->rb_lock);
 
-		frwr_release_mr(mr);
+		frwr_mr_release(mr);
 
 		spin_lock(&buf->rb_lock);
 	}
@@ -1221,17 +1237,6 @@ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req)
 	spin_unlock(&buffers->rb_lock);
 }
 
-/**
- * rpcrdma_recv_buffer_put - Release rpcrdma_rep back to free list
- * @rep: rep to release
- *
- * Used after error conditions.
- */
-void rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
-{
-	rpcrdma_rep_put(&rep->rr_rxprt->rx_buf, rep);
-}
-
 /* Returns a pointer to a rpcrdma_regbuf object, or NULL.
  *
  * xprtrdma uses a regbuf for posting an outgoing RDMA SEND, or for
@@ -1342,21 +1347,7 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb)
  */
 int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
-	struct ib_send_wr *send_wr = &req->rl_wr;
-	struct rpcrdma_ep *ep = r_xprt->rx_ep;
-	int rc;
-
-	if (!ep->re_send_count || kref_read(&req->rl_kref) > 1) {
-		send_wr->send_flags |= IB_SEND_SIGNALED;
-		ep->re_send_count = ep->re_send_batch;
-	} else {
-		send_wr->send_flags &= ~IB_SEND_SIGNALED;
-		--ep->re_send_count;
-	}
-
-	trace_xprtrdma_post_send(req);
-	rc = frwr_send(r_xprt, req);
-	if (rc)
+	if (frwr_send(r_xprt, req))
 		return -ENOTCONN;
 	return 0;
 }
@@ -1364,27 +1355,30 @@ int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 /**
  * rpcrdma_post_recvs - Refill the Receive Queue
  * @r_xprt: controlling transport instance
- * @temp: mark Receive buffers to be deleted after use
+ * @needed: current credit grant
+ * @temp: mark Receive buffers to be deleted after one use
  *
  */
-void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp)
 {
 	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
 	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	struct ib_recv_wr *wr, *bad_wr;
 	struct rpcrdma_rep *rep;
-	int needed, count, rc;
+	int count, rc;
 
 	rc = 0;
 	count = 0;
 
-	needed = buf->rb_credits + (buf->rb_bc_srv_max_requests << 1);
 	if (likely(ep->re_receive_count > needed))
 		goto out;
 	needed -= ep->re_receive_count;
 	if (!temp)
 		needed += RPCRDMA_MAX_RECV_BATCH;
 
+	if (atomic_inc_return(&ep->re_receiving) > 1)
+		goto out;
+
 	/* fast path: all needed reps can be found on the free list */
 	wr = NULL;
 	while (needed) {
@@ -1410,6 +1404,9 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
 
 	rc = ib_post_recv(ep->re_id->qp, wr,
 			  (const struct ib_recv_wr **)&bad_wr);
+	if (atomic_dec_return(&ep->re_receiving) > 0)
+		complete(&ep->re_done);
+
 out:
 	trace_xprtrdma_post_recvs(r_xprt, count, rc);
 	if (rc) {
@@ -1418,7 +1415,7 @@ out:
 
 			rep = container_of(wr, struct rpcrdma_rep, rr_recv_wr);
 			wr = wr->next;
-			rpcrdma_recv_buffer_put(rep);
+			rpcrdma_rep_put(buf, rep);
 			--count;
 		}
 	}
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index fe3be985e239..436ad7312614 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -83,6 +83,7 @@ struct rpcrdma_ep {
 	unsigned int		re_max_inline_recv;
 	int			re_async_rc;
 	int			re_connect_status;
+	atomic_t		re_receiving;
 	atomic_t		re_force_disconnect;
 	struct ib_qp_init_attr	re_attr;
 	wait_queue_head_t       re_connect_wait;
@@ -228,31 +229,28 @@ struct rpcrdma_sendctx {
  * An external memory region is any buffer or page that is registered
  * on the fly (ie, not pre-registered).
  */
-struct rpcrdma_frwr {
-	struct ib_mr			*fr_mr;
-	struct ib_cqe			fr_cqe;
-	struct rpc_rdma_cid		fr_cid;
-	struct completion		fr_linv_done;
-	union {
-		struct ib_reg_wr	fr_regwr;
-		struct ib_send_wr	fr_invwr;
-	};
-};
-
 struct rpcrdma_req;
 struct rpcrdma_mr {
 	struct list_head	mr_list;
 	struct rpcrdma_req	*mr_req;
+
+	struct ib_mr		*mr_ibmr;
 	struct ib_device	*mr_device;
 	struct scatterlist	*mr_sg;
 	int			mr_nents;
 	enum dma_data_direction	mr_dir;
-	struct rpcrdma_frwr	frwr;
+	struct ib_cqe		mr_cqe;
+	struct completion	mr_linv_done;
+	union {
+		struct ib_reg_wr	mr_regwr;
+		struct ib_send_wr	mr_invwr;
+	};
 	struct rpcrdma_xprt	*mr_xprt;
 	u32			mr_handle;
 	u32			mr_length;
 	u64			mr_offset;
 	struct list_head	mr_all;
+	struct rpc_rdma_cid	mr_cid;
 };
 
 /*
@@ -461,7 +459,7 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt);
 void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt);
 
 int rpcrdma_post_sends(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req);
-void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp);
+void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp);
 
 /*
  * Buffer calls - xprtrdma/verbs.c
@@ -480,7 +478,7 @@ void rpcrdma_mrs_refresh(struct rpcrdma_xprt *r_xprt);
 struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
 void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers,
 			struct rpcrdma_req *req);
-void rpcrdma_recv_buffer_put(struct rpcrdma_rep *);
+void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep);
 
 bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size,
 			    gfp_t flags);
@@ -527,7 +525,7 @@ rpcrdma_data_dir(bool writing)
 void frwr_reset(struct rpcrdma_req *req);
 int frwr_query_device(struct rpcrdma_ep *ep, const struct ib_device *device);
 int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr);
-void frwr_release_mr(struct rpcrdma_mr *mr);
+void frwr_mr_release(struct rpcrdma_mr *mr);
 struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 				struct rpcrdma_mr_seg *seg,
 				int nsegs, bool writing, __be32 xid,
@@ -560,6 +558,7 @@ int rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst);
 void rpcrdma_set_max_header_sizes(struct rpcrdma_ep *ep);
 void rpcrdma_reset_cwnd(struct rpcrdma_xprt *r_xprt);
 void rpcrdma_complete_rqst(struct rpcrdma_rep *rep);
+void rpcrdma_unpin_rqst(struct rpcrdma_rep *rep);
 void rpcrdma_reply_handler(struct rpcrdma_rep *rep);
 
 static inline void rpcrdma_set_xdrlen(struct xdr_buf *xdr, size_t len)
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index e35760f238a4..47aa47a2b07c 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -558,6 +558,10 @@ xs_read_stream_call(struct sock_xprt *transport, struct msghdr *msg, int flags)
 	struct rpc_rqst *req;
 	ssize_t ret;
 
+	/* Is this transport associated with the backchannel? */
+	if (!xprt->bc_serv)
+		return -ESHUTDOWN;
+
 	/* Look up and lock the request corresponding to the given XID */
 	req = xprt_lookup_bc_request(xprt, transport->recv.xid);
 	if (!req) {
@@ -1018,6 +1022,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
 	 * to cope with writespace callbacks arriving _after_ we have
 	 * called sendmsg(). */
 	req->rq_xtime = ktime_get();
+	tcp_sock_set_cork(transport->inet, true);
 	while (1) {
 		status = xprt_sock_sendmsg(transport->sock, &msg, xdr,
 					   transport->xmit.offset, rm, &sent);
@@ -1032,6 +1037,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req)
 		if (likely(req->rq_bytes_sent >= msglen)) {
 			req->rq_xmit_bytes_sent += transport->xmit.offset;
 			transport->xmit.offset = 0;
+			if (atomic_long_read(&xprt->xmit_queuelen) == 1)
+				tcp_sock_set_cork(transport->inet, false);
 			return 0;
 		}
 
@@ -2163,6 +2170,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		}
 
 		xs_tcp_set_socket_timeouts(xprt, sock);
+		tcp_sock_set_nodelay(sk);
 
 		write_lock_bh(&sk->sk_callback_lock);
 
@@ -2177,7 +2185,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 
 		/* socket options */
 		sock_reset_flag(sk, SOCK_LINGER);
-		tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
 
 		xprt_clear_connected(xprt);