Merge tag 'nfs-for-4.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable bugfixes:
   - Fix mirror allocation in the writeback code to avoid a use after
     free
   - Fix the O_DSYNC writes to use the correct byte range
   - Fix 2 use after free issues in the I/O code

  Features:
   - Writeback fixes to split up the inode->i_lock in order to reduce
     contention
   - RPC client receive fixes to reduce the amount of time the
     xprt->transport_lock is held when receiving data from a socket into
     am XDR buffer.
   - Ditto fixes to reduce contention between call side users of the
     rdma rb_lock, and its use in rpcrdma_reply_handler.
   - Re-arrange rdma stats to reduce false cacheline sharing.
   - Various rdma cleanups and optimisations.
   - Refactor the NFSv4.1 exchange id code and clean up the code.
   - Const-ify all instances of struct rpc_xprt_ops

  Bugfixes:
   - Fix the NFSv2 'sec=' mount option.
   - NFSv4.1: don't use machine credentials for CLOSE when using
     'sec=sys'
   - Fix the NFSv3 GRANT callback when the port changes on the server.
   - Fix livelock issues with COMMIT
   - NFSv4: Use correct inode in _nfs4_opendata_to_nfs4_state() when
     doing and NFSv4.1 open by filehandle"

* tag 'nfs-for-4.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (69 commits)
  NFS: Count the bytes of skipped subrequests in nfs_lock_and_join_requests()
  NFS: Don't hold the group lock when calling nfs_release_request()
  NFS: Remove pnfs_generic_transfer_commit_list()
  NFS: nfs_lock_and_join_requests and nfs_scan_commit_list can deadlock
  NFS: Fix 2 use after free issues in the I/O code
  NFS: Sync the correct byte range during synchronous writes
  lockd: Delete an error message for a failed memory allocation in reclaimer()
  NFS: remove jiffies field from access cache
  NFS: flush data when locking a file to ensure cache coherence for mmap.
  SUNRPC: remove some dead code.
  NFS: don't expect errors from mempool_alloc().
  xprtrdma: Use xprt_pin_rqst in rpcrdma_reply_handler
  xprtrdma: Re-arrange struct rx_stats
  NFS: Fix NFSv2 security settings
  NFSv4.1: don't use machine credentials for CLOSE when using 'sec=sys'
  SUNRPC: ECONNREFUSED should cause a rebind.
  NFS: Remove unused parameter gfp_flags from nfs_pageio_init()
  NFSv4: Fix up mirror allocation
  SUNRPC: Add a separate spinlock to protect the RPC request receive list
  SUNRPC: Cleanup xs_tcp_read_common()
  ...

16 files changed, 490 insertions, 565 deletions

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 5427cdf04c5a..14358de173fb 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -51,7 +51,7 @@ __be32 nfs4_callback_getattr(void *argp, void *resp,
 		goto out_iput;
 	res->size = i_size_read(inode);
 	res->change_attr = delegation->change_attr;
-	if (nfsi->nrequests != 0)
+	if (nfs_have_writebacks(inode))
 		res->change_attr++;
 	res->ctime = inode->i_ctime;
 	res->mtime = inode->i_mtime;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index d7df5e67b0c1..606dd3871f66 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -1089,7 +1089,7 @@ bool nfs4_delegation_flush_on_close(const struct inode *inode)
 	delegation = rcu_dereference(nfsi->delegation);
 	if (delegation == NULL || !(delegation->type & FMODE_WRITE))
 		goto out;
-	if (nfsi->nrequests < delegation->pagemod_limit)
+	if (atomic_long_read(&nfsi->nrequests) < delegation->pagemod_limit)
 		ret = false;
 out:
 	rcu_read_unlock();
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 3522b1249019..5ceaeb1f6fb6 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2260,7 +2260,6 @@ static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, str
 		spin_lock(&inode->i_lock);
 		retry = false;
 	}
-	res->jiffies = cache->jiffies;
 	res->cred = cache->cred;
 	res->mask = cache->mask;
 	list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru);
@@ -2296,7 +2295,6 @@ static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred,
 		goto out;
 	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
 		goto out;
-	res->jiffies = cache->jiffies;
 	res->cred = cache->cred;
 	res->mask = cache->mask;
 	err = 0;
@@ -2344,7 +2342,6 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
 	if (cache == NULL)
 		return;
 	RB_CLEAR_NODE(&cache->rb_node);
-	cache->jiffies = set->jiffies;
 	cache->cred = get_rpccred(set->cred);
 	cache->mask = set->mask;
 
@@ -2432,7 +2429,6 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 	cache.mask = NFS_MAY_LOOKUP | NFS_MAY_EXECUTE
 		     | NFS_MAY_WRITE | NFS_MAY_READ;
 	cache.cred = cred;
-	cache.jiffies = jiffies;
 	status = NFS_PROTO(inode)->access(inode, &cache);
 	if (status != 0) {
 		if (status == -ESTALE) {
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 6fb9fad2d1e6..d2972d537469 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -616,13 +616,13 @@ nfs_direct_write_scan_commit_list(struct inode *inode,
 				  struct list_head *list,
 				  struct nfs_commit_info *cinfo)
 {
-	spin_lock(&cinfo->inode->i_lock);
+	mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
 #ifdef CONFIG_NFS_V4_1
 	if (cinfo->ds != NULL && cinfo->ds->nwritten != 0)
 		NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
 #endif
 	nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0);
-	spin_unlock(&cinfo->inode->i_lock);
+	mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
 }
 
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index af330c31f627..a385d1c3f146 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -631,11 +631,11 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 	if (result <= 0)
 		goto out;
 
-	result = generic_write_sync(iocb, result);
-	if (result < 0)
-		goto out;
 	written = result;
 	iocb->ki_pos += written;
+	result = generic_write_sync(iocb, written);
+	if (result < 0)
+		goto out;
 
 	/* Return error values */
 	if (nfs_need_check_write(file, inode)) {
@@ -744,15 +744,18 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 		goto out;
 
 	/*
-	 * Revalidate the cache if the server has time stamps granular
-	 * enough to detect subsecond changes.  Otherwise, clear the
-	 * cache to prevent missing any changes.
+	 * Invalidate cache to prevent missing any changes.  If
+	 * the file is mapped, clear the page cache as well so
+	 * those mappings will be loaded.
 	 *
 	 * This makes locking act as a cache coherency point.
 	 */
 	nfs_sync_mapping(filp->f_mapping);
-	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
+	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) {
 		nfs_zap_caches(inode);
+		if (mapping_mapped(filp->f_mapping))
+			nfs_revalidate_mapping(inode, filp->f_mapping);
+	}
 out:
 	return status;
 }
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 109279d6d91b..134d9f560240 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1285,7 +1285,6 @@ static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi)
 
 static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
 	unsigned long ret = 0;
 
 	if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
@@ -1315,7 +1314,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 	if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
 			&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			&& i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
-			&& nfsi->nrequests == 0) {
+			&& !nfs_have_writebacks(inode)) {
 		i_size_write(inode, nfs_size_to_loff_t(fattr->size));
 		ret |= NFS_INO_INVALID_ATTR;
 	}
@@ -1823,7 +1822,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		if (new_isize != cur_isize) {
 			/* Do we perhaps have any outstanding writes, or has
 			 * the file grown beyond our last write? */
-			if (nfsi->nrequests == 0 || new_isize > cur_isize) {
+			if (!nfs_have_writebacks(inode) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				if (!have_writers)
 					invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
@@ -2012,10 +2011,11 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
 	INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
 	INIT_LIST_HEAD(&nfsi->commit_info.list);
-	nfsi->nrequests = 0;
-	nfsi->commit_info.ncommit = 0;
+	atomic_long_set(&nfsi->nrequests, 0);
+	atomic_long_set(&nfsi->commit_info.ncommit, 0);
 	atomic_set(&nfsi->commit_info.rpcs_out, 0);
 	init_rwsem(&nfsi->rmdir_sem);
+	mutex_init(&nfsi->commit_mutex);
 	nfs4_init_once(nfsi);
 }
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index dc456416d2be..68cc22083639 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -251,7 +251,6 @@ int nfs_iocounter_wait(struct nfs_lock_context *l_ctx);
 extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
 struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
 void nfs_pgio_header_free(struct nfs_pgio_header *);
-void nfs_pgio_data_destroy(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
 int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 40bd05f05e74..ac4f10b7f6c1 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -303,6 +303,17 @@ _nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode,
 	struct rpc_cred *newcred = NULL;
 	rpc_authflavor_t flavor;
 
+	if (sp4_mode == NFS_SP4_MACH_CRED_CLEANUP ||
+	    sp4_mode == NFS_SP4_MACH_CRED_PNFS_CLEANUP) {
+		/* Using machine creds for cleanup operations
+		 * is only relevent if the client credentials
+		 * might expire. So don't bother for
+		 * RPC_AUTH_UNIX.  If file was only exported to
+		 * sec=sys, the PUTFH would fail anyway.
+		 */
+		if ((*clntp)->cl_auth->au_flavor == RPC_AUTH_UNIX)
+			return false;
+	}
 	if (test_bit(sp4_mode, &clp->cl_sp4_flags)) {
 		spin_lock(&clp->cl_lock);
 		if (clp->cl_machine_cred != NULL)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d90132642340..6c61e2b99635 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1659,12 +1659,52 @@ update:
 	return state;
 }
 
+static struct inode *
+nfs4_opendata_get_inode(struct nfs4_opendata *data)
+{
+	struct inode *inode;
+
+	switch (data->o_arg.claim) {
+	case NFS4_OPEN_CLAIM_NULL:
+	case NFS4_OPEN_CLAIM_DELEGATE_CUR:
+	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
+		if (!(data->f_attr.valid & NFS_ATTR_FATTR))
+			return ERR_PTR(-EAGAIN);
+		inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh,
+				&data->f_attr, data->f_label);
+		break;
+	default:
+		inode = d_inode(data->dentry);
+		ihold(inode);
+		nfs_refresh_inode(inode, &data->f_attr);
+	}
+	return inode;
+}
+
 static struct nfs4_state *
-_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
+nfs4_opendata_find_nfs4_state(struct nfs4_opendata *data)
 {
+	struct nfs4_state *state;
 	struct inode *inode;
-	struct nfs4_state *state = NULL;
-	int ret;
+
+	inode = nfs4_opendata_get_inode(data);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+	if (data->state != NULL && data->state->inode == inode) {
+		state = data->state;
+		atomic_inc(&state->count);
+	} else
+		state = nfs4_get_open_state(inode, data->owner);
+	iput(inode);
+	if (state == NULL)
+		state = ERR_PTR(-ENOMEM);
+	return state;
+}
+
+static struct nfs4_state *
+_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
+{
+	struct nfs4_state *state;
 
 	if (!data->rpc_done) {
 		state = nfs4_try_open_cached(data);
@@ -1672,29 +1712,17 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
 		goto out;
 	}
 
-	ret = -EAGAIN;
-	if (!(data->f_attr.valid & NFS_ATTR_FATTR))
-		goto err;
-	inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, &data->f_attr, data->f_label);
-	ret = PTR_ERR(inode);
-	if (IS_ERR(inode))
-		goto err;
-	ret = -ENOMEM;
-	state = nfs4_get_open_state(inode, data->owner);
-	if (state == NULL)
-		goto err_put_inode;
+	state = nfs4_opendata_find_nfs4_state(data);
+	if (IS_ERR(state))
+		goto out;
+
 	if (data->o_res.delegation_type != 0)
 		nfs4_opendata_check_deleg(data, state);
 	update_open_stateid(state, &data->o_res.stateid, NULL,
 			data->o_arg.fmode);
-	iput(inode);
 out:
 	nfs_release_seqid(data->o_arg.seqid);
 	return state;
-err_put_inode:
-	iput(inode);
-err:
-	return ERR_PTR(ret);
 }
 
 static struct nfs4_state *
@@ -2071,7 +2099,6 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 		data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0];
 	case NFS4_OPEN_CLAIM_FH:
 		task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
-		nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
 	}
 	data->timestamp = jiffies;
 	if (nfs4_setup_sequence(data->o_arg.server->nfs_client,
@@ -2258,7 +2285,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 		mask = NFS4_ACCESS_READ;
 
 	cache.cred = cred;
-	cache.jiffies = jiffies;
 	nfs_access_set_mask(&cache, opendata->o_res.access_result);
 	nfs_access_add_cache(state->inode, &cache);
 
@@ -7318,7 +7344,9 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp,
 		      1 << (OP_DESTROY_SESSION - 32) |
 		      1 << (OP_DESTROY_CLIENTID - 32)
 	};
+	unsigned long flags = 0;
 	unsigned int i;
+	int ret = 0;
 
 	if (sp->how == SP4_MACH_CRED) {
 		/* Print state protect result */
@@ -7334,7 +7362,8 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp,
 		for (i = 0; i < NFS4_OP_MAP_NUM_WORDS; i++) {
 			if (sp->enforce.u.words[i] & ~supported_enforce[i]) {
 				dfprintk(MOUNT, "sp4_mach_cred: disabled\n");
-				return -EINVAL;
+				ret = -EINVAL;
+				goto out;
 			}
 		}
 
@@ -7353,10 +7382,11 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp,
 		    test_bit(OP_DESTROY_CLIENTID, sp->enforce.u.longs)) {
 			dfprintk(MOUNT, "sp4_mach_cred:\n");
 			dfprintk(MOUNT, "  minimal mode enabled\n");
-			set_bit(NFS_SP4_MACH_CRED_MINIMAL, &clp->cl_sp4_flags);
+			__set_bit(NFS_SP4_MACH_CRED_MINIMAL, &flags);
 		} else {
 			dfprintk(MOUNT, "sp4_mach_cred: disabled\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out;
 		}
 
 		if (test_bit(OP_CLOSE, sp->allow.u.longs) &&
@@ -7364,110 +7394,46 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp,
 		    test_bit(OP_DELEGRETURN, sp->allow.u.longs) &&
 		    test_bit(OP_LOCKU, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  cleanup mode enabled\n");
-			set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags);
+			__set_bit(NFS_SP4_MACH_CRED_CLEANUP, &flags);
 		}
 
 		if (test_bit(OP_LAYOUTRETURN, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  pnfs cleanup mode enabled\n");
-			set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP,
-				&clp->cl_sp4_flags);
+			__set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP, &flags);
 		}
 
 		if (test_bit(OP_SECINFO, sp->allow.u.longs) &&
 		    test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  secinfo mode enabled\n");
-			set_bit(NFS_SP4_MACH_CRED_SECINFO, &clp->cl_sp4_flags);
+			__set_bit(NFS_SP4_MACH_CRED_SECINFO, &flags);
 		}
 
 		if (test_bit(OP_TEST_STATEID, sp->allow.u.longs) &&
 		    test_bit(OP_FREE_STATEID, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  stateid mode enabled\n");
-			set_bit(NFS_SP4_MACH_CRED_STATEID, &clp->cl_sp4_flags);
+			__set_bit(NFS_SP4_MACH_CRED_STATEID, &flags);
 		}
 
 		if (test_bit(OP_WRITE, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  write mode enabled\n");
-			set_bit(NFS_SP4_MACH_CRED_WRITE, &clp->cl_sp4_flags);
+			__set_bit(NFS_SP4_MACH_CRED_WRITE, &flags);
 		}
 
 		if (test_bit(OP_COMMIT, sp->allow.u.longs)) {
 			dfprintk(MOUNT, "  commit mode enabled\n");
-			set_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags);
+			__set_bit(NFS_SP4_MACH_CRED_COMMIT, &flags);
 		}
 	}
-
+out:
+	clp->cl_sp4_flags = flags;
 	return 0;
 }
 
 struct nfs41_exchange_id_data {
 	struct nfs41_exchange_id_res res;
 	struct nfs41_exchange_id_args args;
-	struct rpc_xprt *xprt;
-	int rpc_status;
 };
 
-static void nfs4_exchange_id_done(struct rpc_task *task, void *data)
-{
-	struct nfs41_exchange_id_data *cdata =
-					(struct nfs41_exchange_id_data *)data;
-	struct nfs_client *clp = cdata->args.client;
-	int status = task->tk_status;
-
-	trace_nfs4_exchange_id(clp, status);
-
-	if (status == 0)
-		status = nfs4_check_cl_exchange_flags(cdata->res.flags);
-
-	if (cdata->xprt && status == 0) {
-		status = nfs4_detect_session_trunking(clp, &cdata->res,
-						      cdata->xprt);
-		goto out;
-	}
-
-	if (status  == 0)
-		status = nfs4_sp4_select_mode(clp, &cdata->res.state_protect);
-
-	if (status == 0) {
-		clp->cl_clientid = cdata->res.clientid;
-		clp->cl_exchange_flags = cdata->res.flags;
-		clp->cl_seqid = cdata->res.seqid;
-		/* Client ID is not confirmed */
-		if (!(cdata->res.flags & EXCHGID4_FLAG_CONFIRMED_R))
-			clear_bit(NFS4_SESSION_ESTABLISHED,
-				  &clp->cl_session->session_state);
-
-		kfree(clp->cl_serverowner);
-		clp->cl_serverowner = cdata->res.server_owner;
-		cdata->res.server_owner = NULL;
-
-		/* use the most recent implementation id */
-		kfree(clp->cl_implid);
-		clp->cl_implid = cdata->res.impl_id;
-		cdata->res.impl_id = NULL;
-
-		if (clp->cl_serverscope != NULL &&
-		    !nfs41_same_server_scope(clp->cl_serverscope,
-					cdata->res.server_scope)) {
-			dprintk("%s: server_scope mismatch detected\n",
-				__func__);
-			set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state);
-			kfree(clp->cl_serverscope);
-			clp->cl_serverscope = NULL;
-		}
-
-		if (clp->cl_serverscope == NULL) {
-			clp->cl_serverscope = cdata->res.server_scope;
-			cdata->res.server_scope = NULL;
-		}
-		/* Save the EXCHANGE_ID verifier session trunk tests */
-		memcpy(clp->cl_confirm.data, cdata->args.verifier.data,
-		       sizeof(clp->cl_confirm.data));
-	}
-out:
-	cdata->rpc_status = status;
-	return;
-}
-
 static void nfs4_exchange_id_release(void *data)
 {
 	struct nfs41_exchange_id_data *cdata =
@@ -7481,7 +7447,6 @@ static void nfs4_exchange_id_release(void *data)
 }
 
 static const struct rpc_call_ops nfs4_exchange_id_call_ops = {
-	.rpc_call_done = nfs4_exchange_id_done,
 	.rpc_release = nfs4_exchange_id_release,
 };
 
@@ -7490,7 +7455,8 @@ static const struct rpc_call_ops nfs4_exchange_id_call_ops = {
  *
  * Wrapper for EXCHANGE_ID operation.
  */
-static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
+static struct rpc_task *
+nfs4_run_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 			u32 sp4_how, struct rpc_xprt *xprt)
 {
 	struct rpc_message msg = {
@@ -7504,17 +7470,15 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 		.flags = RPC_TASK_TIMEOUT,
 	};
 	struct nfs41_exchange_id_data *calldata;
-	struct rpc_task *task;
 	int status;
 
 	if (!atomic_inc_not_zero(&clp->cl_count))
-		return -EIO;
+		return ERR_PTR(-EIO);
 
+	status = -ENOMEM;
 	calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
-	if (!calldata) {
-		nfs_put_client(clp);
-		return -ENOMEM;
-	}
+	if (!calldata)
+		goto out;
 
 	nfs4_init_boot_verifier(clp, &calldata->args.verifier);
 
@@ -7553,34 +7517,22 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 		goto out_impl_id;
 	}
 	if (xprt) {
-		calldata->xprt = xprt;
 		task_setup_data.rpc_xprt = xprt;
 		task_setup_data.flags |= RPC_TASK_SOFTCONN;
 		memcpy(calldata->args.verifier.data, clp->cl_confirm.data,
 				sizeof(calldata->args.verifier.data));
 	}
 	calldata->args.client = clp;
-#ifdef CONFIG_NFS_V4_1_MIGRATION
 	calldata->args.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
-	EXCHGID4_FLAG_BIND_PRINC_STATEID |
-	EXCHGID4_FLAG_SUPP_MOVED_MIGR,
-#else
-	calldata->args.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
-	EXCHGID4_FLAG_BIND_PRINC_STATEID,
+	EXCHGID4_FLAG_BIND_PRINC_STATEID;
+#ifdef CONFIG_NFS_V4_1_MIGRATION
+	calldata->args.flags |= EXCHGID4_FLAG_SUPP_MOVED_MIGR;
 #endif
 	msg.rpc_argp = &calldata->args;
 	msg.rpc_resp = &calldata->res;
 	task_setup_data.callback_data = calldata;
 
-	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task))
-		return PTR_ERR(task);
-
-	status = calldata->rpc_status;
-
-	rpc_put_task(task);
-out:
-	return status;
+	return rpc_run_task(&task_setup_data);
 
 out_impl_id:
 	kfree(calldata->res.impl_id);
@@ -7590,8 +7542,69 @@ out_server_owner:
 	kfree(calldata->res.server_owner);
 out_calldata:
 	kfree(calldata);
+out:
 	nfs_put_client(clp);
-	goto out;
+	return ERR_PTR(status);
+}
+
+/*
+ * _nfs4_proc_exchange_id()
+ *
+ * Wrapper for EXCHANGE_ID operation.
+ */
+static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
+			u32 sp4_how)
+{
+	struct rpc_task *task;
+	struct nfs41_exchange_id_args *argp;
+	struct nfs41_exchange_id_res *resp;
+	int status;
+
+	task = nfs4_run_exchange_id(clp, cred, sp4_how, NULL);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+
+	argp = task->tk_msg.rpc_argp;
+	resp = task->tk_msg.rpc_resp;
+	status = task->tk_status;
+	if (status  != 0)
+		goto out;
+
+	status = nfs4_check_cl_exchange_flags(resp->flags);
+	if (status  != 0)
+		goto out;
+
+	status = nfs4_sp4_select_mode(clp, &resp->state_protect);
+	if (status != 0)
+		goto out;
+
+	clp->cl_clientid = resp->clientid;
+	clp->cl_exchange_flags = resp->flags;
+	clp->cl_seqid = resp->seqid;
+	/* Client ID is not confirmed */
+	if (!(resp->flags & EXCHGID4_FLAG_CONFIRMED_R))
+		clear_bit(NFS4_SESSION_ESTABLISHED,
+			  &clp->cl_session->session_state);
+
+	if (clp->cl_serverscope != NULL &&
+	    !nfs41_same_server_scope(clp->cl_serverscope,
+				resp->server_scope)) {
+		dprintk("%s: server_scope mismatch detected\n",
+			__func__);
+		set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state);
+	}
+
+	swap(clp->cl_serverowner, resp->server_owner);
+	swap(clp->cl_serverscope, resp->server_scope);
+	swap(clp->cl_implid, resp->impl_id);
+
+	/* Save the EXCHANGE_ID verifier session trunk tests */
+	memcpy(clp->cl_confirm.data, argp->verifier.data,
+	       sizeof(clp->cl_confirm.data));
+out:
+	trace_nfs4_exchange_id(clp, status);
+	rpc_put_task(task);
+	return status;
 }
 
 /*
@@ -7614,13 +7627,13 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 	/* try SP4_MACH_CRED if krb5i/p	*/
 	if (authflavor == RPC_AUTH_GSS_KRB5I ||
 	    authflavor == RPC_AUTH_GSS_KRB5P) {
-		status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED, NULL);
+		status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED);
 		if (!status)
 			return 0;
 	}
 
 	/* try SP4_NONE */
-	return _nfs4_proc_exchange_id(clp, cred, SP4_NONE, NULL);
+	return _nfs4_proc_exchange_id(clp, cred, SP4_NONE);
 }
 
 /**
@@ -7642,6 +7655,9 @@ int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt,
 			    void *data)
 {
 	struct nfs4_add_xprt_data *adata = (struct nfs4_add_xprt_data *)data;
+	struct rpc_task *task;
+	int status;
+
 	u32 sp4_how;
 
 	dprintk("--> %s try %s\n", __func__,
@@ -7650,7 +7666,17 @@ int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt,
 	sp4_how = (adata->clp->cl_sp4_flags == 0 ? SP4_NONE : SP4_MACH_CRED);
 
 	/* Test connection for session trunking. Async exchange_id call */
-	return  _nfs4_proc_exchange_id(adata->clp, adata->cred, sp4_how, xprt);
+	task = nfs4_run_exchange_id(adata->clp, adata->cred, sp4_how, xprt);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+
+	status = task->tk_status;
+	if (status == 0)
+		status = nfs4_detect_session_trunking(adata->clp,
+				task->tk_msg.rpc_resp, xprt);
+
+	rpc_put_task(task);
+	return status;
 }
 EXPORT_SYMBOL_GPL(nfs4_test_session_trunk);
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index de9066a92c0d..bec120ec1967 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -134,19 +134,14 @@ EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait);
 /*
  * nfs_page_group_lock - lock the head of the page group
  * @req - request in group that is to be locked
- * @nonblock - if true don't block waiting for lock
  *
- * this lock must be held if modifying the page group list
+ * this lock must be held when traversing or modifying the page
+ * group list
  *
- * return 0 on success, < 0 on error: -EDELAY if nonblocking or the
- * result from wait_on_bit_lock
- *
- * NOTE: calling with nonblock=false should always have set the
- *       lock bit (see fs/buffer.c and other uses of wait_on_bit_lock
- *       with TASK_UNINTERRUPTIBLE), so there is no need to check the result.
+ * return 0 on success, < 0 on error
  */
 int
-nfs_page_group_lock(struct nfs_page *req, bool nonblock)
+nfs_page_group_lock(struct nfs_page *req)
 {
 	struct nfs_page *head = req->wb_head;
 
@@ -155,35 +150,10 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock)
 	if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
 		return 0;
 
-	if (!nonblock) {
-		set_bit(PG_CONTENDED1, &head->wb_flags);
-		smp_mb__after_atomic();
-		return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
-				TASK_UNINTERRUPTIBLE);
-	}
-
-	return -EAGAIN;
-}
-
-/*
- * nfs_page_group_lock_wait - wait for the lock to clear, but don't grab it
- * @req - a request in the group
- *
- * This is a blocking call to wait for the group lock to be cleared.
- */
-void
-nfs_page_group_lock_wait(struct nfs_page *req)
-{
-	struct nfs_page *head = req->wb_head;
-
-	WARN_ON_ONCE(head != head->wb_head);
-
-	if (!test_bit(PG_HEADLOCK, &head->wb_flags))
-		return;
 	set_bit(PG_CONTENDED1, &head->wb_flags);
 	smp_mb__after_atomic();
-	wait_on_bit(&head->wb_flags, PG_HEADLOCK,
-		TASK_UNINTERRUPTIBLE);
+	return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
+				TASK_UNINTERRUPTIBLE);
 }
 
 /*
@@ -246,7 +216,7 @@ bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit)
 {
 	bool ret;
 
-	nfs_page_group_lock(req, false);
+	nfs_page_group_lock(req);
 	ret = nfs_page_group_sync_on_bit_locked(req, bit);
 	nfs_page_group_unlock(req);
 
@@ -288,9 +258,7 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
 			inode = page_file_mapping(req->wb_page)->host;
 			set_bit(PG_INODE_REF, &req->wb_flags);
 			kref_get(&req->wb_kref);
-			spin_lock(&inode->i_lock);
-			NFS_I(inode)->nrequests++;
-			spin_unlock(&inode->i_lock);
+			atomic_long_inc(&NFS_I(inode)->nrequests);
 		}
 	}
 }
@@ -306,14 +274,11 @@ static void
 nfs_page_group_destroy(struct kref *kref)
 {
 	struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
+	struct nfs_page *head = req->wb_head;
 	struct nfs_page *tmp, *next;
 
-	/* subrequests must release the ref on the head request */
-	if (req->wb_head != req)
-		nfs_release_request(req->wb_head);
-
 	if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN))
-		return;
+		goto out;
 
 	tmp = req;
 	do {
@@ -324,6 +289,10 @@ nfs_page_group_destroy(struct kref *kref)
 		nfs_free_request(tmp);
 		tmp = next;
 	} while (tmp != req);
+out:
+	/* subrequests must release the ref on the head request */
+	if (head != req)
+		nfs_release_request(head);
 }
 
 /**
@@ -465,6 +434,7 @@ void nfs_release_request(struct nfs_page *req)
 {
 	kref_put(&req->wb_kref, nfs_page_group_destroy);
 }
+EXPORT_SYMBOL_GPL(nfs_release_request);
 
 /**
  * nfs_wait_on_request - Wait for a request to complete.
@@ -483,6 +453,7 @@ nfs_wait_on_request(struct nfs_page *req)
 	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
 			      TASK_UNINTERRUPTIBLE);
 }
+EXPORT_SYMBOL_GPL(nfs_wait_on_request);
 
 /*
  * nfs_generic_pg_test - determine if requests can be coalesced
@@ -530,16 +501,6 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops)
 }
 EXPORT_SYMBOL_GPL(nfs_pgio_header_alloc);
 
-/*
- * nfs_pgio_header_free - Free a read or write header
- * @hdr: The header to free
- */
-void nfs_pgio_header_free(struct nfs_pgio_header *hdr)
-{
-	hdr->rw_ops->rw_free_header(hdr);
-}
-EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
-
 /**
  * nfs_pgio_data_destroy - make @hdr suitable for reuse
  *
@@ -548,14 +509,24 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
  *
  * @hdr: A header that has had nfs_generic_pgio called
  */
-void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
+static void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr)
 {
 	if (hdr->args.context)
 		put_nfs_open_context(hdr->args.context);
 	if (hdr->page_array.pagevec != hdr->page_array.page_array)
 		kfree(hdr->page_array.pagevec);
 }
-EXPORT_SYMBOL_GPL(nfs_pgio_data_destroy);
+
+/*
+ * nfs_pgio_header_free - Free a read or write header
+ * @hdr: The header to free
+ */
+void nfs_pgio_header_free(struct nfs_pgio_header *hdr)
+{
+	nfs_pgio_data_destroy(hdr);
+	hdr->rw_ops->rw_free_header(hdr);
+}
+EXPORT_SYMBOL_GPL(nfs_pgio_header_free);
 
 /**
  * nfs_pgio_rpcsetup - Set up arguments for a pageio call
@@ -669,7 +640,6 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio);
 static void nfs_pgio_error(struct nfs_pgio_header *hdr)
 {
 	set_bit(NFS_IOHDR_REDO, &hdr->flags);
-	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
 }
 
@@ -680,7 +650,6 @@ static void nfs_pgio_error(struct nfs_pgio_header *hdr)
 static void nfs_pgio_release(void *calldata)
 {
 	struct nfs_pgio_header *hdr = calldata;
-	nfs_pgio_data_destroy(hdr);
 	hdr->completion_ops->completion(hdr);
 }
 
@@ -711,12 +680,8 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		     const struct nfs_pgio_completion_ops *compl_ops,
 		     const struct nfs_rw_ops *rw_ops,
 		     size_t bsize,
-		     int io_flags,
-		     gfp_t gfp_flags)
+		     int io_flags)
 {
-	struct nfs_pgio_mirror *new;
-	int i;
-
 	desc->pg_moreio = 0;
 	desc->pg_inode = inode;
 	desc->pg_ops = pg_ops;
@@ -732,23 +697,10 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_mirror_count = 1;
 	desc->pg_mirror_idx = 0;
 
-	if (pg_ops->pg_get_mirror_count) {
-		/* until we have a request, we don't have an lseg and no
-		 * idea how many mirrors there will be */
-		new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX,
-			      sizeof(struct nfs_pgio_mirror), gfp_flags);
-		desc->pg_mirrors_dynamic = new;
-		desc->pg_mirrors = new;
-
-		for (i = 0; i < NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX; i++)
-			nfs_