Merge tag 'nfs-for-4.0-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

   - Fix a regression in the NFSv4 open state recovery code
   - Fix a regression in the NFSv4 close code
   - Fix regressions and side-effects of the loop-back mounted NFS fixes
     in 3.18, that cause the NFS read() syscall to return EBUSY.
   - Fix regressions around the readdirplus code and how it interacts
     with the VFS lazy unmount changes that went into v3.18.
   - Fix issues with out-of-order RPC call replies replacing updated
     attributes with stale ones (particularly after a truncate()).
   - Fix an underflow checking issue with RPC/RDMA credits
   - Fix a number of issues with the NFSv4 delegation return/free code.
   - Fix issues around stale NFSv4.1 leases when doing a mount"

* tag 'nfs-for-4.0-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (24 commits)
  NFSv4.1: Clear the old state by our client id before establishing a new lease
  NFSv4: Fix a race in NFSv4.1 server trunking discovery
  NFS: Don't write enable new pages while an invalidation is proceeding
  NFS: Fix a regression in the read() syscall
  NFSv4: Ensure we skip delegations that are already being returned
  NFSv4: Pin the superblock while we're returning the delegation
  NFSv4: Ensure we honour NFS_DELEGATION_RETURNING in nfs_inode_set_delegation()
  NFSv4: Ensure that we don't reap a delegation that is being returned
  NFS: Fix stateid used for NFS v4 closes
  NFSv4: Don't call put_rpccred() under the rcu_read_lock()
  NFS: Don't require a filehandle to refresh the inode in nfs_prime_dcache()
  NFSv3: Use the readdir fileid as the mounted-on-fileid
  NFS: Don't invalidate a submounted dentry in nfs_prime_dcache()
  NFSv4: Set a barrier in the update_changeattr() helper
  NFS: Fix nfs_post_op_update_inode() to set an attribute barrier
  NFS: Remove size hack in nfs_inode_attrs_need_update()
  NFSv4: Add attribute update barriers to delegreturn and pNFS layoutcommit
  NFS: Add attribute update barriers to NFS writebacks
  NFS: Set an attribute barrier on all updates
  NFS: Add attribute update barriers to nfs_setattr_update_inode()
  ...

17 files changed, 244 insertions, 62 deletions

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index f9f4845db98..19874151e95 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -433,7 +433,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 
 static bool nfs_client_init_is_complete(const struct nfs_client *clp)
 {
-	return clp->cl_cons_state != NFS_CS_INITING;
+	return clp->cl_cons_state <= NFS_CS_READY;
 }
 
 int nfs_wait_client_init_complete(const struct nfs_client *clp)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index a1f0685b42f..a6ad6886588 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -181,8 +181,8 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred,
 			clear_bit(NFS_DELEGATION_NEED_RECLAIM,
 				  &delegation->flags);
 			spin_unlock(&delegation->lock);
-			put_rpccred(oldcred);
 			rcu_read_unlock();
+			put_rpccred(oldcred);
 			trace_nfs4_reclaim_delegation(inode, res->delegation_type);
 		} else {
 			/* We appear to have raced with a delegation return. */
@@ -370,7 +370,10 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 			delegation = NULL;
 			goto out;
 		}
-		freeme = nfs_detach_delegation_locked(nfsi, 
+		if (test_and_set_bit(NFS_DELEGATION_RETURNING,
+					&old_delegation->flags))
+			goto out;
+		freeme = nfs_detach_delegation_locked(nfsi,
 				old_delegation, clp);
 		if (freeme == NULL)
 			goto out;
@@ -433,6 +436,8 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 {
 	bool ret = false;
 
+	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
+		goto out;
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) {
@@ -444,6 +449,7 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 			ret = true;
 		spin_unlock(&delegation->lock);
 	}
+out:
 	return ret;
 }
 
@@ -471,14 +477,20 @@ restart:
 								super_list) {
 			if (!nfs_delegation_need_return(delegation))
 				continue;
-			inode = nfs_delegation_grab_inode(delegation);
-			if (inode == NULL)
+			if (!nfs_sb_active(server->super))
 				continue;
+			inode = nfs_delegation_grab_inode(delegation);
+			if (inode == NULL) {
+				rcu_read_unlock();
+				nfs_sb_deactive(server->super);
+				goto restart;
+			}
 			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 			rcu_read_unlock();
 
 			err = nfs_end_delegation_return(inode, delegation, 0);
 			iput(inode);
+			nfs_sb_deactive(server->super);
 			if (!err)
 				goto restart;
 			set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state);
@@ -809,19 +821,30 @@ restart:
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
 		list_for_each_entry_rcu(delegation, &server->delegations,
 								super_list) {
+			if (test_bit(NFS_DELEGATION_RETURNING,
+						&delegation->flags))
+				continue;
 			if (test_bit(NFS_DELEGATION_NEED_RECLAIM,
 						&delegation->flags) == 0)
 				continue;
-			inode = nfs_delegation_grab_inode(delegation);
-			if (inode == NULL)
+			if (!nfs_sb_active(server->super))
 				continue;
-			delegation = nfs_detach_delegation(NFS_I(inode),
-					delegation, server);
+			inode = nfs_delegation_grab_inode(delegation);
+			if (inode == NULL) {
+				rcu_read_unlock();
+				nfs_sb_deactive(server->super);
+				goto restart;
+			}
+			delegation = nfs_start_delegation_return_locked(NFS_I(inode));
 			rcu_read_unlock();
-
-			if (delegation != NULL)
-				nfs_free_delegation(delegation);
+			if (delegation != NULL) {
+				delegation = nfs_detach_delegation(NFS_I(inode),
+					delegation, server);
+				if (delegation != NULL)
+					nfs_free_delegation(delegation);
+			}
 			iput(inode);
+			nfs_sb_deactive(server->super);
 			goto restart;
 		}
 	}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9b0c55cb2a2..c19e16f0b2d 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -408,14 +408,22 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc,
 	return 0;
 }
 
+/* Match file and dirent using either filehandle or fileid
+ * Note: caller is responsible for checking the fsid
+ */
 static
 int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
 {
+	struct nfs_inode *nfsi;
+
 	if (dentry->d_inode == NULL)
 		goto different;
-	if (nfs_compare_fh(entry->fh, NFS_FH(dentry->d_inode)) != 0)
-		goto different;
-	return 1;
+
+	nfsi = NFS_I(dentry->d_inode);
+	if (entry->fattr->fileid == nfsi->fileid)
+		return 1;
+	if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0)
+		return 1;
 different:
 	return 0;
 }
@@ -469,6 +477,10 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 	struct inode *inode;
 	int status;
 
+	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FILEID))
+		return;
+	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FSID))
+		return;
 	if (filename.name[0] == '.') {
 		if (filename.len == 1)
 			return;
@@ -479,6 +491,10 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 
 	dentry = d_lookup(parent, &filename);
 	if (dentry != NULL) {
+		/* Is there a mountpoint here? If so, just exit */
+		if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid,
+					&entry->fattr->fsid))
+			goto out;
 		if (nfs_same_file(dentry, entry)) {
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			status = nfs_refresh_inode(dentry->d_inode, entry->fattr);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 94712fc781f..e679d24c39d 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -178,7 +178,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 		iocb->ki_filp,
 		iov_iter_count(to), (unsigned long) iocb->ki_pos);
 
-	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
+	result = nfs_revalidate_mapping_protected(inode, iocb->ki_filp->f_mapping);
 	if (!result) {
 		result = generic_file_read_iter(iocb, to);
 		if (result > 0)
@@ -199,7 +199,7 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	dprintk("NFS: splice_read(%pD2, %lu@%Lu)\n",
 		filp, (unsigned long) count, (unsigned long long) *ppos);
 
-	res = nfs_revalidate_mapping(inode, filp->f_mapping);
+	res = nfs_revalidate_mapping_protected(inode, filp->f_mapping);
 	if (!res) {
 		res = generic_file_splice_read(filp, ppos, pipe, count, flags);
 		if (res > 0)
@@ -372,6 +372,10 @@ start:
 				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (ret)
 		return ret;
+	/*
+	 * Wait for O_DIRECT to complete
+	 */
+	nfs_inode_dio_wait(mapping->host);
 
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
@@ -619,6 +623,9 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	/* make sure the cache has finished storing the page */
 	nfs_fscache_wait_on_page_write(NFS_I(inode), page);
 
+	wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING,
+			nfs_wait_bit_killable, TASK_KILLABLE);
+
 	lock_page(page);
 	mapping = page_file_mapping(page);
 	if (mapping != inode->i_mapping)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 83107be3dd0..d42dff6d5e9 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -556,6 +556,7 @@ EXPORT_SYMBOL_GPL(nfs_setattr);
  * This is a copy of the common vmtruncate, but with the locking
  * corrected to take into account the fact that NFS requires
  * inode->i_size to be updated under the inode->i_lock.
+ * Note: must be called with inode->i_lock held!
  */
 static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 {
@@ -565,14 +566,14 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 	if (err)
 		goto out;
 
-	spin_lock(&inode->i_lock);
 	i_size_write(inode, offset);
 	/* Optimisation */
 	if (offset == 0)
 		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA;
-	spin_unlock(&inode->i_lock);
 
+	spin_unlock(&inode->i_lock);
 	truncate_pagecache(inode, offset);
+	spin_lock(&inode->i_lock);
 out:
 	return err;
 }
@@ -585,10 +586,15 @@ out:
  * Note: we do this in the *proc.c in order to ensure that
  *       it works for things like exclusive creates too.
  */
-void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
+void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
+		struct nfs_fattr *fattr)
 {
+	/* Barrier: bump the attribute generation count. */
+	nfs_fattr_set_barrier(fattr);
+
+	spin_lock(&inode->i_lock);
+	NFS_I(inode)->attr_gencount = fattr->gencount;
 	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
-		spin_lock(&inode->i_lock);
 		if ((attr->ia_valid & ATTR_MODE) != 0) {
 			int mode = attr->ia_mode & S_IALLUGO;
 			mode |= inode->i_mode & ~S_IALLUGO;
@@ -600,12 +606,13 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 			inode->i_gid = attr->ia_gid;
 		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL);
-		spin_unlock(&inode->i_lock);
 	}
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
 		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
 		nfs_vmtruncate(inode, attr->ia_size);
 	}
+	nfs_update_inode(inode, fattr);
+	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
@@ -1028,6 +1035,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 
 	if (mapping->nrpages != 0) {
 		if (S_ISREG(inode->i_mode)) {
+			unmap_mapping_range(mapping, 0, 0, 0);
 			ret = nfs_sync_mapping(mapping);
 			if (ret < 0)
 				return ret;
@@ -1060,11 +1068,14 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
 }
 
 /**
- * nfs_revalidate_mapping - Revalidate the pagecache
+ * __nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
  * @mapping - pointer to mapping
+ * @may_lock - take inode->i_mutex?
  */
-int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+static int __nfs_revalidate_mapping(struct inode *inode,
+		struct address_space *mapping,
+		bool may_lock)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	unsigned long *bitlock = &nfsi->flags;
@@ -1113,7 +1124,12 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
 	spin_unlock(&inode->i_lock);
 	trace_nfs_invalidate_mapping_enter(inode);
-	ret = nfs_invalidate_mapping(inode, mapping);
+	if (may_lock) {
+		mutex_lock(&inode->i_mutex);
+		ret = nfs_invalidate_mapping(inode, mapping);
+		mutex_unlock(&inode->i_mutex);
+	} else
+		ret = nfs_invalidate_mapping(inode, mapping);
 	trace_nfs_invalidate_mapping_exit(inode, ret);
 
 	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
@@ -1123,6 +1139,29 @@ out:
 	return ret;
 }
 
+/**
+ * nfs_revalidate_mapping - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ */
+int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
+{
+	return __nfs_revalidate_mapping(inode, mapping, false);
+}
+
+/**
+ * nfs_revalidate_mapping_protected - Revalidate the pagecache
+ * @inode - pointer to host inode
+ * @mapping - pointer to mapping
+ *
+ * Differs from nfs_revalidate_mapping() in that it grabs the inode->i_mutex
+ * while invalidating the mapping.
+ */
+int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping)
+{
+	return __nfs_revalidate_mapping(inode, mapping, true);
+}
+
 static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -1231,13 +1270,6 @@ static int nfs_ctime_need_update(const struct inode *inode, const struct nfs_fat
 	return timespec_compare(&fattr->ctime, &inode->i_ctime) > 0;
 }
 
-static int nfs_size_need_update(const struct inode *inode, const struct nfs_fattr *fattr)
-{
-	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
-		return 0;
-	return nfs_size_to_loff_t(fattr->size) > i_size_read(inode);
-}
-
 static atomic_long_t nfs_attr_generation_counter;
 
 static unsigned long nfs_read_attr_generation_counter(void)
@@ -1249,6 +1281,7 @@ unsigned long nfs_inc_attr_generation_counter(void)
 {
 	return atomic_long_inc_return(&nfs_attr_generation_counter);
 }
+EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter);
 
 void nfs_fattr_init(struct nfs_fattr *fattr)
 {
@@ -1260,6 +1293,22 @@ void nfs_fattr_init(struct nfs_fattr *fattr)
 }
 EXPORT_SYMBOL_GPL(nfs_fattr_init);
 
+/**
+ * nfs_fattr_set_barrier
+ * @fattr: attributes
+ *
+ * Used to set a barrier after an attribute was updated. This
+ * barrier ensures that older attributes from RPC calls that may
+ * have raced with our update cannot clobber these new values.
+ * Note that you are still responsible for ensuring that other
+ * operations which change the attribute on the server do not
+ * collide.
+ */
+void nfs_fattr_set_barrier(struct nfs_fattr *fattr)
+{
+	fattr->gencount = nfs_inc_attr_generation_counter();
+}
+
 struct nfs_fattr *nfs_alloc_fattr(void)
 {
 	struct nfs_fattr *fattr;
@@ -1370,7 +1419,6 @@ static int nfs_inode_attrs_need_update(const struct inode *inode, const struct n
 
 	return ((long)fattr->gencount - (long)nfsi->attr_gencount) > 0 ||
 		nfs_ctime_need_update(inode, fattr) ||
-		nfs_size_need_update(inode, fattr) ||
 		((long)nfsi->attr_gencount - (long)nfs_read_attr_generation_counter() > 0);
 }
 
@@ -1460,6 +1508,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	int status;
 
 	spin_lock(&inode->i_lock);
+	nfs_fattr_set_barrier(fattr);
 	status = nfs_post_op_update_inode_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
 
@@ -1468,7 +1517,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
 
 /**
- * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache
  * @inode - pointer to inode
  * @fattr - updated attributes
  *
@@ -1478,11 +1527,10 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode);
  *
  * This function is mainly designed to be used by the ->write_done() functions.
  */
-int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
 	int status;
 
-	spin_lock(&inode->i_lock);
 	/* 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)) {
@@ -1514,6 +1562,27 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 	}
 out_noforce:
 	status = nfs_post_op_update_inode_locked(inode, fattr);
+	return status;
+}
+
+/**
+ * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache
+ * @inode - pointer to inode
+ * @fattr - updated attributes
+ *
+ * After an operation that has changed the inode metadata, mark the
+ * attribute cache as being invalid, then try to update it. Fake up
+ * weak cache consistency data, if none exist.
+ *
+ * This function is mainly designed to be used by the ->write_done() functions.
+ */
+int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr)
+{
+	int status;
+
+	spin_lock(&inode->i_lock);
+	nfs_fattr_set_barrier(fattr);
+	status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
 	return status;
 }
@@ -1715,6 +1784,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 		nfsi->attrtimeo_timestamp = now;
+		/* Set barrier to be more recent than all outstanding updates */
 		nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	} else {
 		if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) {
@@ -1722,6 +1792,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode);
 			nfsi->attrtimeo_timestamp = now;
 		}
+		/* Set the barrier to be more recent than this fattr */
+		if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
+			nfsi->attr_gencount = fattr->gencount;
 	}
 	invalid &= ~NFS_INO_INVALID_ATTR;
 	/* Don't invalidate the data if we were to blame */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b802fb3a2d9..9e6475bc5ba 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -459,6 +459,7 @@ void nfs_mark_request_commit(struct nfs_page *req,
 			     struct nfs_commit_info *cinfo,
 			     u32 ds_commit_idx);
 int nfs_write_need_commit(struct nfs_pgio_header *);
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 78e557c3ab8..1f11d2533ee 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -138,7 +138,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 	dprintk("NFS reply setattr: %d\n", status);
 	return status;
 }
@@ -834,7 +834,7 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 2a932fdc57c..53852a4bd88 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1987,6 +1987,11 @@ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
 		if (entry->fattr->valid & NFS_ATTR_FATTR_V3)
 			entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
 
+		if (entry->fattr->fileid != entry->ino) {
+			entry->fattr->mounted_on_fileid = entry->ino;
+			entry->fattr->valid |= NFS_ATTR_FATTR_MOUNTED_ON_FILEID;
+		}
+
 		/* In fact, a post_op_fh3: */
 		p = xdr_inline_decode(xdr, 4);
 		if (unlikely(p == NULL))
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8646af9b11d..86d6214ea02 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -621,6 +621,9 @@ int nfs41_walk_client_list(struct nfs_client *new,
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
 
+		if (pos == new)
+			goto found;
+
 		if (pos->rpc_ops != new->rpc_ops)
 			continue;
 
@@ -639,10 +642,6 @@ int nfs41_walk_client_list(struct nfs_client *new,
 			prev = pos;
 
 			status = nfs_wait_client_init_complete(pos);
-			if (pos->cl_cons_state == NFS_CS_SESSION_INITING) {
-				nfs4_schedule_lease_recovery(pos);
-				status = nfs4_wait_clnt_recover(pos);
-			}
 			spin_lock(&nn->nfs_client_lock);
 			if (status < 0)
 				break;
@@ -668,7 +667,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		 */
 		if (!nfs4_match_client_owner_id(pos, new))
 			continue;
-
+found:
 		atomic_inc(&pos->cl_count);
 		*result = pos;
 		status = 0;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 88180ac5ea0..627f37c4445 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -901,6 +901,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 	if (!cinfo->atomic || cinfo->before != dir->i_version)
 		nfs_force_lookup_revalidate(dir);
 	dir->i_version = cinfo->after;
+	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_fscache_invalidate(dir);
 	spin_unlock(&dir->i_lock);
 }
@@ -1552,6 +1553,9 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
 
 	opendata->o_arg.open_flags = 0;
 	opendata->o_arg.fmode = fmode;
+	opendata->o_arg.share_access = nfs4_map_atomic_open_share(
+			NFS_SB(opendata->dentry->d_sb),
+			fmode, 0);
 	memset(&opendata->o_res, 0, sizeof(opendata->o_res));
 	memset(&opendata->c_res, 0, sizeof(opendata->c_res));
 	nfs4_init_opendata_res(opendata);
@@ -2413,8 +2417,8 @@ static int _nfs4_do_open(struct inode *dir,
 				opendata->o_res.f_attr, sattr,
 				state, label, olabel);
 		if (status == 0) {
-			nfs_setattr_update_inode(state->inode, sattr);
-			nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr);
+			nfs_setattr_update_inode(state->inode, sattr,
+					opendata->o_res.f_attr);
 			nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
 		}
 	}
@@ -2651,7 +2655,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 		case -NFS4ERR_BAD_STATEID:
 		case -NFS4ERR_EXPIRED:
 			if (!nfs4_stateid_match(&calldata->arg.stateid,
-						&state->stateid)) {
+						&state->open_stateid)) {
 				rpc_restart_call_prepare(task);
 				goto out_release;
 			}
@@ -2687,7 +2691,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
 	is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
 	is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
-	nfs4_stateid_copy(&calldata->arg.stateid, &state->stateid);
+	nfs4_stateid_copy(&calldata->arg.stateid, &state->open_stateid);
 	/* Calculate the change in open mode */
 	calldata->arg.fmode = 0;
 	if (state->n_rdwr == 0) {
@@ -3288,7 +3292,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 
 	status = nfs4_do_setattr(inode, cred, fattr, sattr, state, NULL, label);
 	if (status == 0) {
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 		nfs_setsecurity(inode, fattr, label);
 	}
 	nfs4_label_free(label);
@@ -4234,7 +4238,7 @@ static int nfs4_write_done_cb(struct rpc_task *task,
 	}
 	if (task->tk_status >= 0) {
 		renew_lease(NFS_SERVER(inode), hdr->timestamp);
-		nfs_post_op_update_inode_force_wcc(inode, &hdr->fattr);
+		nfs_writeback_update_inode(hdr);
 	}
 	return 0;
 }
@@ -6893,9 +6897,13 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 
 	if (status == 0) {
 		clp->cl_clientid = res.clientid;
-		clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R);
-		if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R))
+		clp->cl_exchange_flags = res.flags;
+		/* Client ID is not confirmed */
+		if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) {
+			clear_bit(NFS4_SESSION_ESTABLISHED,
+					&clp->cl_session->session_state);
 			clp->cl_seqid = res.seqid;
+		}
 
 		kfree(clp->cl_serverowner);
 		clp->cl_serverowner = res.server_owner;
@@ -7227,6 +7235,9 @@ static void nfs4_update_session(struct nfs4_session *session,
 		struct nfs41_create_session_res *res)
 {
 	nfs4_copy_sessionid(&session->sess_id, &res->sessionid);
+	/* Mark client id and session as being confirmed */
+	session->clp->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R;
+	set_bit(NFS4_SESSION_ESTABLISHED, &session->session_state);
 	session->flags = res->flags;
 	memcpy(&session->fc_attrs, &res->fc_attrs, sizeof(session->fc_attrs));
 	if (res->flags & SESSION4_BACK_CHAN)
@@ -7322,8 +7333,8 @@ int nfs4_proc_destroy_session(struct nfs4_session *session,
 	dprintk("--> nfs4_proc_destroy_session\n");
 
 	/* session is still being setup */
-	if (session->clp->cl_cons_state != NFS_CS_READY)
-		return status;
+	if (!test_and_clear_bit(NFS4_SESSION_ESTABLISHED, &session->session_state))
+		return 0;
 
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_destroy_session(session->clp, status);
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index fc46c745589..e3ea2c5324d 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -70,6 +70,7 @@ struct nfs4_session {
 
 enum nfs4_session_state {
 	NFS4_SESSION_INITING,
+	NFS4_SESSION_ESTABLISHED,
 };
 
 extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 5ad908e9ce9..f95e3b58bbc 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -346,9 +346,23 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 	status = nfs4_proc_exchange_id(clp, cred);
 	if (status != NFS4_OK)
 		return status;
-	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 
-	return nfs41_walk_client_list(clp, result, cred);
+	status = nfs41_walk_client_list(clp, result, cred);
+	if (status < 0)
+		return status;
+	if (clp != *result)
+		return 0;
+
+	/* Purge state if the client id was established in a prior instance */
+	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)
+		set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+	else
+		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+	status = nfs_wait_client_init_complete(clp);
+	if (status < 0)
+		nfs_put_client(clp);
+	return status;
 }
 
 #endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index b09cc23d6f4..c63189acd05 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -139,7 +139,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
-		nfs_setattr_update_inode(inode, sattr);
+		nfs_setattr_update_inode(inode, sattr, fattr);
 	dprintk("NFS reply setattr: %d\n", status);
 	return status;
 }
@@ -609,10 +609,8 @@ static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task,
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
-	struct inode *inode = hdr->inode;
-
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(inode, hdr->res.fattr);
+		nfs_writeback_update_inode(hdr);
 	return 0;
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 595d81e354d..849ed784d6a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1377,6 +1377,36 @@ static int nfs_should_remove_suid(const struct inode *inode)
 	return 0;
 }
 
+static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
+		struct nfs_fattr *fattr)
+{
+	struct nfs_pgio_args *argp = &hdr->args;
+	struct nfs_pgio_res *resp = &hdr->res;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+		return;
+	if (argp->offset + resp->count != fattr->size)
+		return;
+	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode))
+		return;
+	/* Set attribute barrier */
+	nfs_fattr_set_barrier(fattr);
+}
+
+void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
+{
+	struct nfs_fattr *fattr = hdr->res.fattr;
+	struct inode *inode = hdr->inode;
+
+	if (fattr == NULL)
+		return;
+	spin_lock(&inode->i_lock);
+	nfs_writeback_check_extend(hdr, fattr);
+	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
+	spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL_GPL(nfs_writeback_update_inode);
+
 /*
  * This function is called when the WRITE call is complete.
  */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 2f77e0c651c..b01ccf371fd 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -343,6 +343,7 @@ extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *,
 extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *);
 extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr);
+extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr);
 extern int nfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *);
 extern void nfs_access_set_mask(struct nfs_access_entry *, u32);
@@ -355,8 +356,9 @@ extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode);
 extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode);
 extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *);
 extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping);
+extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping);
 extern int nfs_setattr(struct dentry *, struct iattr *);
-extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr);
+extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *);
 extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 				struct nfs4_label *label);
 extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
@@ -369,6 +371,7 @@ extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ct
 extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx);
 extern u64 nfs_compat_user_ino64(u64 fileid);
 extern void nfs_fattr_init(struct nfs_fattr *fattr);
+extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr);
 extern unsigned long nfs_inc_attr_generation_counter(void);
 
 extern struct nfs_fattr *nfs_alloc_fattr(void);
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 7e9acd9361c..91ffde82fa0 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -738,8 +738,9 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	struct rpc_xprt *xprt = rep->rr_xprt;
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	__be32 *iptr;
-	int credits, rdmalen, status;
+	int rdmalen, status;
 	unsigned long cwnd;
+	u32 credits;
 
 	/* Check status. If bad, signal disconnect and return rep to pool */
 	if (rep->rr_len == ~0U) {
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index d1b70397c60..0a16fb6f088 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -285,7 +285,7 @@ rpcr_to_rdmar(struct rpc_rqst *rqst)
  */
 struct rpcrdma_buffer {
 	spinlock_t	rb_lock;	/* protects indexes */
-	int		rb_max_requests;/* client max requests */
+	u32		rb_max_requests;/* client max requests */
 	struct list_head rb_mws;	/* optional memory windows/fmrs/frmrs */
 	struct list_head rb_all;
 	int		rb_send_index;