17 files changed, 444 insertions, 361 deletions

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index f033f3a69a3b..07b839560576 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -93,7 +93,7 @@ int nfs4_check_delegation(struct inode *inode, fmode_t flags)
 	return nfs4_do_check_delegation(inode, flags, false);
 }
 
-static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
+static int nfs_delegation_claim_locks(struct nfs4_state *state, const nfs4_stateid *stateid)
 {
 	struct inode *inode = state->inode;
 	struct file_lock *fl;
@@ -108,7 +108,7 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
 	spin_lock(&flctx->flc_lock);
 restart:
 	list_for_each_entry(fl, list, fl_list) {
-		if (nfs_file_open_context(fl->fl_file) != ctx)
+		if (nfs_file_open_context(fl->fl_file)->state != state)
 			continue;
 		spin_unlock(&flctx->flc_lock);
 		status = nfs4_lock_delegation_recall(fl, state, stateid);
@@ -136,8 +136,8 @@ static int nfs_delegation_claim_opens(struct inode *inode,
 	int err;
 
 again:
-	spin_lock(&inode->i_lock);
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
 		state = ctx->state;
 		if (state == NULL)
 			continue;
@@ -147,15 +147,16 @@ again:
 			continue;
 		if (!nfs4_stateid_match(&state->stateid, stateid))
 			continue;
-		get_nfs_open_context(ctx);
-		spin_unlock(&inode->i_lock);
+		if (!get_nfs_open_context(ctx))
+			continue;
+		rcu_read_unlock();
 		sp = state->owner;
 		/* Block nfs4_proc_unlck */
 		mutex_lock(&sp->so_delegreturn_mutex);
 		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
 		err = nfs4_open_delegation_recall(ctx, state, stateid, type);
 		if (!err)
-			err = nfs_delegation_claim_locks(ctx, state, stateid);
+			err = nfs_delegation_claim_locks(state, stateid);
 		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
 			err = -EAGAIN;
 		mutex_unlock(&sp->so_delegreturn_mutex);
@@ -164,7 +165,7 @@ again:
 			return err;
 		goto again;
 	}
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8bfaa658b2c1..71b2e390becf 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1072,6 +1072,100 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
 	return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU);
 }
 
+static int
+nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
+			   struct inode *inode, int error)
+{
+	switch (error) {
+	case 1:
+		dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n",
+			__func__, dentry);
+		return 1;
+	case 0:
+		nfs_mark_for_revalidate(dir);
+		if (inode && S_ISDIR(inode->i_mode)) {
+			/* Purge readdir caches. */
+			nfs_zap_caches(inode);
+			/*
+			 * We can't d_drop the root of a disconnected tree:
+			 * its d_hash is on the s_anon list and d_drop() would hide
+			 * it from shrink_dcache_for_unmount(), leading to busy
+			 * inodes on unmount and further oopses.
+			 */
+			if (IS_ROOT(dentry))
+				return 1;
+		}
+		dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
+				__func__, dentry);
+		return 0;
+	}
+	dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n",
+				__func__, dentry, error);
+	return error;
+}
+
+static int
+nfs_lookup_revalidate_negative(struct inode *dir, struct dentry *dentry,
+			       unsigned int flags)
+{
+	int ret = 1;
+	if (nfs_neg_need_reval(dir, dentry, flags)) {
+		if (flags & LOOKUP_RCU)
+			return -ECHILD;
+		ret = 0;
+	}
+	return nfs_lookup_revalidate_done(dir, dentry, NULL, ret);
+}
+
+static int
+nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry,
+				struct inode *inode)
+{
+	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
+}
+
+static int
+nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
+			     struct inode *inode)
+{
+	struct nfs_fh *fhandle;
+	struct nfs_fattr *fattr;
+	struct nfs4_label *label;
+	int ret;
+
+	ret = -ENOMEM;
+	fhandle = nfs_alloc_fhandle();
+	fattr = nfs_alloc_fattr();
+	label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL);
+	if (fhandle == NULL || fattr == NULL || IS_ERR(label))
+		goto out;
+
+	ret = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
+	if (ret < 0) {
+		if (ret == -ESTALE || ret == -ENOENT)
+			ret = 0;
+		goto out;
+	}
+	ret = 0;
+	if (nfs_compare_fh(NFS_FH(inode), fhandle))
+		goto out;
+	if (nfs_refresh_inode(inode, fattr) < 0)
+		goto out;
+
+	nfs_setsecurity(inode, fattr, label);
+	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+
+	/* set a readdirplus hint that we had a cache miss */
+	nfs_force_use_readdirplus(dir);
+	ret = 1;
+out:
+	nfs_free_fattr(fattr);
+	nfs_free_fhandle(fhandle);
+	nfs4_label_free(label);
+	return nfs_lookup_revalidate_done(dir, dentry, inode, ret);
+}
+
 /*
  * This is called every time the dcache has a lookup hit,
  * and we should check whether we can really trust that
@@ -1083,58 +1177,36 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
  * If the parent directory is seen to have changed, we throw out the
  * cached dentry and do a new lookup.
  */
-static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+static int
+nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
+			 unsigned int flags)
 {
-	struct inode *dir;
 	struct inode *inode;
-	struct dentry *parent;
-	struct nfs_fh *fhandle = NULL;
-	struct nfs_fattr *fattr = NULL;
-	struct nfs4_label *label = NULL;
 	int error;
 
-	if (flags & LOOKUP_RCU) {
-		parent = READ_ONCE(dentry->d_parent);
-		dir = d_inode_rcu(parent);
-		if (!dir)
-			return -ECHILD;
-	} else {
-		parent = dget_parent(dentry);
-		dir = d_inode(parent);
-	}
 	nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
 	inode = d_inode(dentry);
 
-	if (!inode) {
-		if (nfs_neg_need_reval(dir, dentry, flags)) {
-			if (flags & LOOKUP_RCU)
-				return -ECHILD;
-			goto out_bad;
-		}
-		goto out_valid;
-	}
+	if (!inode)
+		return nfs_lookup_revalidate_negative(dir, dentry, flags);
 
 	if (is_bad_inode(inode)) {
-		if (flags & LOOKUP_RCU)
-			return -ECHILD;
 		dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n",
 				__func__, dentry);
 		goto out_bad;
 	}
 
 	if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
-		goto out_set_verifier;
+		return nfs_lookup_revalidate_delegated(dir, dentry, inode);
 
 	/* Force a full look up iff the parent directory has changed */
 	if (!(flags & (LOOKUP_EXCL | LOOKUP_REVAL)) &&
 	    nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
 		error = nfs_lookup_verify_inode(inode, flags);
 		if (error) {
-			if (flags & LOOKUP_RCU)
-				return -ECHILD;
 			if (error == -ESTALE)
-				goto out_zap_parent;
-			goto out_error;
+				nfs_zap_caches(dir);
+			goto out_bad;
 		}
 		nfs_advise_use_readdirplus(dir);
 		goto out_valid;
@@ -1146,81 +1218,45 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	if (NFS_STALE(inode))
 		goto out_bad;
 
-	error = -ENOMEM;
-	fhandle = nfs_alloc_fhandle();
-	fattr = nfs_alloc_fattr();
-	if (fhandle == NULL || fattr == NULL)
-		goto out_error;
-
-	label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT);
-	if (IS_ERR(label))
-		goto out_error;
-
 	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
-	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
+	error = nfs_lookup_revalidate_dentry(dir, dentry, inode);
 	trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
-	if (error == -ESTALE || error == -ENOENT)
-		goto out_bad;
-	if (error)
-		goto out_error;
-	if (nfs_compare_fh(NFS_FH(inode), fhandle))
-		goto out_bad;
-	if ((error = nfs_refresh_inode(inode, fattr)) != 0)
-		goto out_bad;
-
-	nfs_setsecurity(inode, fattr, label);
-
-	nfs_free_fattr(fattr);
-	nfs_free_fhandle(fhandle);
-	nfs4_label_free(label);
+	return error;
+out_valid:
+	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
+out_bad:
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+	return nfs_lookup_revalidate_done(dir, dentry, inode, 0);
+}
 
-	/* set a readdirplus hint that we had a cache miss */
-	nfs_force_use_readdirplus(dir);
+static int
+__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags,
+			int (*reval)(struct inode *, struct dentry *, unsigned int))
+{
+	struct dentry *parent;
+	struct inode *dir;
+	int ret;
 
-out_set_verifier:
-	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- out_valid:
 	if (flags & LOOKUP_RCU) {
+		parent = READ_ONCE(dentry->d_parent);
+		dir = d_inode_rcu(parent);
+		if (!dir)
+			return -ECHILD;
+		ret = reval(dir, dentry, flags);
 		if (parent != READ_ONCE(dentry->d_parent))
 			return -ECHILD;
-	} else
+	} else {
+		parent = dget_parent(dentry);
+		ret = reval(d_inode(parent), dentry, flags);
 		dput(parent);
-	dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is valid\n",
-			__func__, dentry);
-	return 1;
-out_zap_parent:
-	nfs_zap_caches(dir);
- out_bad:
-	WARN_ON(flags & LOOKUP_RCU);
-	nfs_free_fattr(fattr);
-	nfs_free_fhandle(fhandle);
-	nfs4_label_free(label);
-	nfs_mark_for_revalidate(dir);
-	if (inode && S_ISDIR(inode->i_mode)) {
-		/* Purge readdir caches. */
-		nfs_zap_caches(inode);
-		/*
-		 * We can't d_drop the root of a disconnected tree:
-		 * its d_hash is on the s_anon list and d_drop() would hide
-		 * it from shrink_dcache_for_unmount(), leading to busy
-		 * inodes on unmount and further oopses.
-		 */
-		if (IS_ROOT(dentry))
-			goto out_valid;
 	}
-	dput(parent);
-	dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
-			__func__, dentry);
-	return 0;
-out_error:
-	WARN_ON(flags & LOOKUP_RCU);
-	nfs_free_fattr(fattr);
-	nfs_free_fhandle(fhandle);
-	nfs4_label_free(label);
-	dput(parent);
-	dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) lookup returned error %d\n",
-			__func__, dentry, error);
-	return error;
+	return ret;
+}
+
+static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate);
 }
 
 /*
@@ -1579,62 +1615,55 @@ no_open:
 }
 EXPORT_SYMBOL_GPL(nfs_atomic_open);
 
-static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+static int
+nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
+			  unsigned int flags)
 {
 	struct inode *inode;
-	int ret = 0;
 
 	if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
-		goto no_open;
+		goto full_reval;
 	if (d_mountpoint(dentry))
-		goto no_open;
-	if (NFS_SB(dentry->d_sb)->caps & NFS_CAP_ATOMIC_OPEN_V1)
-		goto no_open;
+		goto full_reval;
 
 	inode = d_inode(dentry);
 
 	/* We can't create new files in nfs_open_revalidate(), so we
 	 * optimize away revalidation of negative dentries.
 	 */
-	if (inode == NULL) {
-		struct dentry *parent;
-		struct inode *dir;
-
-		if (flags & LOOKUP_RCU) {
-			parent = READ_ONCE(dentry->d_parent);
-			dir = d_inode_rcu(parent);
-			if (!dir)
-				return -ECHILD;
-		} else {
-			parent = dget_parent(dentry);
-			dir = d_inode(parent);
-		}
-		if (!nfs_neg_need_reval(dir, dentry, flags))
-			ret = 1;
-		else if (flags & LOOKUP_RCU)
-			ret = -ECHILD;
-		if (!(flags & LOOKUP_RCU))
-			dput(parent);
-		else if (parent != READ_ONCE(dentry->d_parent))
-			return -ECHILD;
-		goto out;
-	}
+	if (inode == NULL)
+		goto full_reval;
+
+	if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
+		return nfs_lookup_revalidate_delegated(dir, dentry, inode);
 
 	/* NFS only supports OPEN on regular files */
 	if (!S_ISREG(inode->i_mode))
-		goto no_open;
+		goto full_reval;
+
 	/* We cannot do exclusive creation on a positive dentry */
-	if (flags & LOOKUP_EXCL)
-		goto no_open;
+	if (flags & (LOOKUP_EXCL | LOOKUP_REVAL))
+		goto reval_dentry;
+
+	/* Check if the directory changed */
+	if (!nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU))
+		goto reval_dentry;
 
 	/* Let f_op->open() actually open (and revalidate) the file */
-	ret = 1;
+	return 1;
+reval_dentry:
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+	return nfs_lookup_revalidate_dentry(dir, dentry, inode);;
 
-out:
-	return ret;
+full_reval:
+	return nfs_do_lookup_revalidate(dir, dentry, flags);
+}
 
-no_open:
-	return nfs_lookup_revalidate(dentry, flags);
+static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	return __nfs_lookup_revalidate(dentry, flags,
+			nfs4_do_lookup_revalidate);
 }
 
 #endif /* CONFIG_NFSV4 */
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index d175724ff566..61f46facb39c 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -1164,6 +1164,7 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.id			= LAYOUT_NFSV4_1_FILES,
 	.name			= "LAYOUT_NFSV4_1_FILES",
 	.owner			= THIS_MODULE,
+	.max_layoutget_response	= 4096, /* 1 page or so... */
 	.alloc_layout_hdr	= filelayout_alloc_layout_hdr,
 	.free_layout_hdr	= filelayout_free_layout_hdr,
 	.alloc_lseg		= filelayout_alloc_lseg,
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index cae43333ef16..86bcba40ca61 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -2356,6 +2356,7 @@ static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.name			= "LAYOUT_FLEX_FILES",
 	.owner			= THIS_MODULE,
 	.flags			= PNFS_LAYOUTGET_ON_OPEN,
+	.max_layoutget_response	= 4096, /* 1 page or so... */
 	.set_layoutdriver	= ff_layout_set_layoutdriver,
 	.alloc_layout_hdr	= ff_layout_alloc_layout_hdr,
 	.free_layout_hdr	= ff_layout_free_layout_hdr,
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index 59aa04976331..74d8d5352438 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -453,7 +453,7 @@ ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx,
 	struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
 	struct rpc_cred *cred;
 
-	if (mirror) {
+	if (mirror && !mirror->mirror_ds->ds_versions[0].tightly_coupled) {
 		cred = ff_layout_get_mirror_cred(mirror, lseg->pls_range.iomode);
 		if (!cred)
 			cred = get_rpccred(mdscred);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b65aee481d13..5b1eee4952b7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -857,15 +857,14 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
 
 static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
 {
-	struct nfs_lock_context *head = &ctx->lock_context;
-	struct nfs_lock_context *pos = head;
+	struct nfs_lock_context *pos;
 
-	do {
+	list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) {
 		if (pos->lockowner != current->files)
 			continue;
-		refcount_inc(&pos->count);
-		return pos;
-	} while ((pos = list_entry(pos->list.next, typeof(*pos), list)) != head);
+		if (refcount_inc_not_zero(&pos->count))
+			return pos;
+	}
 	return NULL;
 }
 
@@ -874,10 +873,10 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
 	struct nfs_lock_context *res, *new = NULL;
 	struct inode *inode = d_inode(ctx->dentry);
 
-	spin_lock(&inode->i_lock);
+	rcu_read_lock();
 	res = __nfs_find_lock_context(ctx);
+	rcu_read_unlock();
 	if (res == NULL) {
-		spin_unlock(&inode->i_lock);
 		new = kmalloc(sizeof(*new), GFP_KERNEL);
 		if (new == NULL)
 			return ERR_PTR(-ENOMEM);
@@ -885,14 +884,14 @@ struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
 		spin_lock(&inode->i_lock);
 		res = __nfs_find_lock_context(ctx);
 		if (res == NULL) {
-			list_add_tail(&new->list, &ctx->lock_context.list);
+			list_add_tail_rcu(&new->list, &ctx->lock_context.list);
 			new->open_context = ctx;
 			res = new;
 			new = NULL;
 		}
+		spin_unlock(&inode->i_lock);
+		kfree(new);
 	}
-	spin_unlock(&inode->i_lock);
-	kfree(new);
 	return res;
 }
 EXPORT_SYMBOL_GPL(nfs_get_lock_context);
@@ -904,9 +903,9 @@ void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
 
 	if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock))
 		return;
-	list_del(&l_ctx->list);
+	list_del_rcu(&l_ctx->list);
 	spin_unlock(&inode->i_lock);
-	kfree(l_ctx);
+	kfree_rcu(l_ctx, rcu_head);
 }
 EXPORT_SYMBOL_GPL(nfs_put_lock_context);
 
@@ -978,9 +977,9 @@ EXPORT_SYMBOL_GPL(alloc_nfs_open_context);
 
 struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 {
-	if (ctx != NULL)
-		refcount_inc(&ctx->lock_context.count);
-	return ctx;
+	if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count))
+		return ctx;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(get_nfs_open_context);
 
@@ -989,13 +988,13 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	struct inode *inode = d_inode(ctx->dentry);
 	struct super_block *sb = ctx->dentry->d_sb;
 
+	if (!refcount_dec_and_test(&ctx->lock_context.count))
+		return;
 	if (!list_empty(&ctx->list)) {
-		if (!refcount_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
-			return;
-		list_del(&ctx->list);
+		spin_lock(&inode->i_lock);
+		list_del_rcu(&ctx->list);
 		spin_unlock(&inode->i_lock);
-	} else if (!refcount_dec_and_test(&ctx->lock_context.count))
-		return;
+	}
 	if (inode != NULL)
 		NFS_PROTO(inode)->close_context(ctx, is_sync);
 	if (ctx->cred != NULL)
@@ -1003,7 +1002,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 	dput(ctx->dentry);
 	nfs_sb_deactive(sb);
 	kfree(ctx->mdsthreshold);
-	kfree(ctx);
+	kfree_rcu(ctx, rcu_head);
 }
 
 void put_nfs_open_context(struct nfs_open_context *ctx)
@@ -1027,10 +1026,7 @@ void nfs_inode_attach_open_context(struct nfs_open_context *ctx)
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	spin_lock(&inode->i_lock);
-	if (ctx->mode & FMODE_WRITE)
-		list_add(&ctx->list, &nfsi->open_files);
-	else
-		list_add_tail(&ctx->list, &nfsi->open_files);
+	list_add_tail_rcu(&ctx->list, &nfsi->open_files);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context);
@@ -1051,16 +1047,17 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_c
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_context *pos, *ctx = NULL;
 
-	spin_lock(&inode->i_lock);
-	list_for_each_entry(pos, &nfsi->open_files, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(pos, &nfsi->open_files, list) {
 		if (cred != NULL && pos->cred != cred)
 			continue;
 		if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode)
 			continue;
 		ctx = get_nfs_open_context(pos);
-		break;
+		if (ctx)
+			break;
 	}
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 	return ctx;
 }
 
@@ -1078,9 +1075,6 @@ void nfs_file_clear_open_context(struct file *filp)
 		if (ctx->error < 0)
 			invalidate_inode_pages2(inode->i_mapping);
 		filp->private_data = NULL;
-		spin_lock(&inode->i_lock);
-		list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
-		spin_unlock(&inode->i_lock);
 		put_nfs_open_context_sync(ctx);
 	}
 }
@@ -1329,19 +1323,11 @@ static bool nfs_file_has_writers(struct nfs_inode *nfsi)
 {
 	struct inode *inode = &nfsi->vfs_inode;
 
-	assert_spin_locked(&inode->i_lock);
-
 	if (!S_ISREG(inode->i_mode))
 		return false;
 	if (list_empty(&nfsi->open_files))
 		return false;
-	/* Note: This relies on nfsi->open_files being ordered with writers
-	 *       being placed at the head of the list.
-	 *       See nfs_inode_attach_open_context()
-	 */
-	return (list_first_entry(&nfsi->open_files,
-			struct nfs_open_context,
-			list)->mode & FMODE_WRITE) == FMODE_WRITE;
+	return inode_is_open_for_write(inode);
 }
 
 static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi)
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index ec8a9efa268f..71bc16225b98 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -786,6 +786,7 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
+	struct nfs_server *server = NFS_SERVER(inode);
 
 	if (hdr->pgio_done_cb != NULL)
 		return hdr->pgio_done_cb(task, hdr);
@@ -793,6 +794,9 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 
+	if (task->tk_status >= 0 && !server->read_hdrsize)
+		cmpxchg(&server->read_hdrsize, 0, hdr->res.replen);
+
 	nfs_invalidate_atime(inode);
 	nfs_refresh_inode(inode, &hdr->fattr);
 	return 0;
@@ -802,6 +806,7 @@ static void nfs3_proc_read_setup(struct nfs_pgio_header *hdr,
 				 struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
+	hdr->args.replen = NFS_SERVER(hdr->inode)->read_hdrsize;
 }
 
 static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 64e4fa33d89f..78df4eb60f85 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -983,10 +983,11 @@ static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
 				   const void *data)
 {
 	const struct nfs_pgio_args *args = data;
+	unsigned int replen = args->replen ? args->replen : NFS3_readres_sz;
 
 	encode_read3args(xdr, args);
 	prepare_reply_buffer(req, args->pages, args->pgbase,
-					args->count, NFS3_readres_sz);
+					args->count, replen);
 	req->rq_rcv_buf.flags |= XDRBUF_READ;
 }
 
@@ -1364,10 +1365,12 @@ static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req,
 
 	encode_nfs_fh3(xdr, args->fh);
 	encode_uint32(xdr, args->mask);
-	if (args->mask & (NFS_ACL | NFS_DFACL))
+	if (args->mask & (NFS_ACL | NFS_DFACL)) {
 		prepare_reply_buffer(req, args->pages, 0,
 					NFSACL_MAXPAGES << PAGE_SHIFT,
 					ACL3_getaclres_sz);
+		req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES;
+	}
 }
 
 static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
@@ -1673,9 +1676,11 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 				 void *data)
 {
 	struct nfs_pgio_res *result = data;
+	unsigned int pos;
 	enum nfs_stat status;
 	int error;
 
+	pos = xdr_stream_pos(xdr);
 	error = decode_nfsstat3(xdr, &status);
 	if (unlikely(error))
 		goto out;
@@ -1685,6 +1690,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
+	result->replen = 3 + ((xdr_stream_pos(xdr) - pos) >> 2);
 	error = decode_read3resok(xdr, result);
 out:
 	return error;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 3a6904173214..8d59c9655ec4 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -188,9 +188,10 @@ struct nfs4_state {
 	unsigned int n_wronly;		/* Number of write-only references */
 	unsigned int n_rdwr;		/* Number of read/write references */
 	fmode_t state;			/* State on the server (R,W, or RW) */
-	atomic_t count;
+	refcount_t count;
 
 	wait_queue_head_t waitq;
+	struct rcu_head rcu_head;
 };
 
 
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 146e30862234..8f53455c4765 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -950,10 +950,10 @@ EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
 
 /*
  * Session has been established, and the client marked ready.
- * Set the mount rsize and wsize with negotiated fore channel
- * attributes which will be bound checked in nfs_server_set_fsinfo.
+ * Limit the mount rsize, wsize and dtsize using negotiated fore
+ * channel attributes.
  */
-static void nfs4_session_set_rwsize(struct nfs_server *server)
+static void nfs4_session_limit_rwsize(struct nfs_server *server)
 {
 #ifdef CONFIG_NFS_V4_1
 	struct nfs4_session *sess;
@@ -966,9 +966,11 @@ static void nfs4_session_set_rwsize(struct nfs_server *server)
 	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
 	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
 
-	if (!server->rsize || server->rsize > server_resp_sz)
+	if (server->dtsize > server_resp_sz)
+		server->dtsize = server_resp_sz;
+	if (server->rsize > server_resp_sz)
 		server->rsize = server_resp_sz;
-	if (!server->wsize || server->wsize > server_rqst_sz)
+	if (server->wsize > server_rqst_sz)
 		server->wsize = server_rqst_sz;
 #endif /* CONFIG_NFS_V4_1 */
 }
@@ -1015,12 +1017,12 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 			(unsigned long long) server->fsid.minor);
 	nfs_display_fhandle(mntfh, "Pseudo-fs root FH");
 
-	nfs4_session_set_rwsize(server);
-
 	error = nfs_probe_fsinfo(server, mntfh, fattr);
 	if (error < 0)
 		goto out;
 
+	nfs4_session_limit_rwsize(server);
+
 	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
 		server->namelen = NFS4_MAXNAMLEN;
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8220a168282e..db84b4adbc49 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1349,12 +1349,20 @@ static bool nfs4_mode_match_open_stateid(struct nfs4_state *state,
 	return false;
 }
 
-static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode)
+static int can_open_cached(struct nfs4_state *state, fmode_t mode,
+		int open_mode, enum open_claim_type4 claim)
 {
 	int ret = 0;
 
 	if (open_mode & (O_EXCL|O_TRUNC))
 		goto out;
+	switch (claim) {
+	case NFS4_OPEN_CLAIM_NULL:
+	case NFS4_OPEN_CLAIM_FH:
+		goto out;
+	default:
+		break;
+	}
 	switch (mode & (FMODE_READ|FMODE_WRITE)) {
 		case FMODE_READ:
 			ret |= test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0
@@ -1747,7 +1755,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 
 	for (;;) {
 		spin_lock(&state->owner->so_lock);
-		if (can_open_cached(state, fmode, open_mode)) {
+		if (can_open_cached(state, fmode, open_mode, claim)) {
 			update_open_stateflags(state, fmode);
 			spin_unlock(&state->owner->so_lock);
 			goto out_return_state;
@@ -1777,7 +1785,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 out:
 	return ERR_PTR(ret);
 out_return_state:
-	atomic_inc(&state->count);
+	refcount_inc(&state->count);
 	return state;
 }
 
@@ -1849,7 +1857,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data)
 update:
 	update_open_stateid(state, &data->o_res.stateid, NULL,
 			    data->o_arg.fmode);
-	atomic_inc(&state->count);
+	refcount_inc(&state->count);
 
 	return state;
 }
@@ -1887,7 +1895,7 @@ nfs4_opendata_find_nfs4_state(struct nfs4_opendata *data)
 		return ERR_CAST(inode);
 	if (data->state != NULL && data->state->inode == inode) {
 		state = data->state;
-		atomic_inc(&state->count);
+		refcount_inc(&state->count);
 	} else
 		state = nfs4_get_open_state(inode, data->owner);
 	iput(inode);
@@ -1933,23 +1941,41 @@ nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
 	return ret;
 }
 
-static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
+static struct nfs_open_context *
+nfs4_state_find_open_context_mode(struct nfs4_state *state, fmode_t mode)
 {
 	struct nfs_inode *nfsi = NFS_I(state->inode);
 	struct nfs_open_context *ctx;
 
-	spin_lock(&state->inode->i_lock);
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
 		if (ctx->state != state)
 			continue;
-		get_nfs_open_context(ctx);
-		spin_unlock(&state->inode->i_lock);
+		if ((ctx->mode & mode) != mode)
+			continue;
+		if (!get_nfs_open_context(ctx))
+			continue;
+		rcu_read_unlock();
 		return ctx;
 	}
-	spin_unlock(&state->inode->i_lock);
+	rcu_read_unlock();
 	return ERR_PTR(-ENOENT);
 }
 
+static struct nfs_open_context *
+nfs4_state_find_open_context(struct nfs4_state *state)
+{
+	struct nfs_open_context *ctx;
+
+	ctx = nfs4_state_find_open_context_mode(state, FMODE_READ|FMODE_WRITE);
+	if (!IS_ERR(ctx))
+		return ctx;
+	ctx = nfs4_state_find_open_context_mode(state, FMODE_WRITE);
+	if (!IS_ERR(ctx))
+		return ctx;
+	return nfs4_state_find_open_context_mode(state, FMODE_READ);
+}
+
 static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx,
 		struct nfs4_state *state, enum open_claim_type4 claim)
 {
@@ -1960,7 +1986,7 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context
 	if (opendata == NULL)
 		return ERR_PTR(-ENOMEM);
 	opendata->state = state;
-	atomic_inc(&state->count);
+	refcount_inc(&state->count);
 	return opendata;
 }
 
@@ -2276,7 +2302,8 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 	if (data->state != NULL) {
 		struct nfs_delegation *delegation;
 
-		if (can_open_cached(data->state, data->o_arg.fmode, data->o_arg.open_flags))
+		if (can_open_cached(data->state, data->o_arg.fmode,
+					data->o_arg.open_flags, claim))
 			goto out_no_action;
 		rcu_read_lock();
 		delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 40a08cd483f0..62ae0fd345ad 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -655,7 +655,7 @@ nfs4_alloc_open_state(void)
 	state = kzalloc(sizeof(*state), GFP_NOFS);
 	if (!state)
 		return NULL;
-	atomic_set(&state->count, 1);
+	refcount_set(&state->count, 1);
 	INIT_LIST_HEAD(&state->lock_states);
 	spin_lock_init(&state->state_lock);
 	seqlock_init(&state->seqlock);
@@ -684,12 +684,12 @@ __nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs4_state *state;
 
-	list_for_each_entry(state, &nfsi->open_states, inode_states) {
+	list_for_each_entry_rcu(state, &nfsi->open_states, inode_states) {
 		if (state->owner != owner)
 			continue;
 		if (!nfs4_valid_open_stateid(state))
 			continue;
-		if (atomic_inc_not_zero(&state->count))
+		if (refcount_inc_not_zero(&state->count))
 			return state;
 	}
 	return NULL;
@@ -698,7 +698,7 @@ __nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner)
 static void
 nfs4_free_open_state(struct nfs4_state *state)
 {
-	kfree(state);
+	kfree_rcu(state, rcu_head);
 }
 
 struct nfs4_state *
@@ -707,9 +707,9 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner)
 	struct nfs4_state *state, *new;
 	struct nfs_inode *nfsi = NFS_I(inode);
 
-	spin_lock(&inode->i_lock);
+	rcu_read_lock();
 	state = __nfs4_find_state_byowner(inode, owner);
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 	if (state)
 		goto out;
 	new = nfs4_alloc_open_state();
@@ -720,7 +720,7 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner)
 		state = new;
 		state->owner = owner;
 		atomic_inc(&owner->so_count);
-		list_add(&state->inode_states, &nfsi->open_states);
+		list_add_rcu(&state->inode_states, &nfsi->open_states);
 		ihold(inode);
 		state->inode = inode;
 		spin_unlock(&inode->i_lock);
@@ -743,10 +743,10 @@ void nfs4_put_open_state(struct nfs4_state *state)
 	struct inode *inode = state->inode;
 	struct nfs4_state_owner *owner = state->owner;
 
-	if (!atomic_dec_and_lock(&state->count, &owner->so_lock))
+	if (!refcount_dec_and_lock(&state->count, &owner->so_lock))
 		return;
 	spin_lock(&inode->i_lock);
-	list_del(&state->inode_states);
+	list_del_rcu(&state->inode_states);
 	list_del(&state->open_states);
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&owner->so_lock);
@@ -1437,8 +1437,8 @@ void nfs_inode_find_state_and_recover(struct inode *inode,
 	struct nfs4_state *state;
 	bool found = false;
 
-	spin_lock(&inode->i_lock);
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
 		state = ctx->state;
 		if (state == NULL)
 			continue;
@@ -1456,7 +1456,7 @@ void nfs_inode_find_state_and_recover(struct inode *inode,
 		    nfs4_state_mark_reclaim_nograce(clp, state))
 			found = true;
 	}
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 
 	nfs_inode_find_delegation_state_and_recover(inode, stateid);
 	if (found)
@@ -1469,13 +1469,13 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_context *ctx;
 
-	spin_lock(&inode->i_lock);
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
 		if (ctx->state != state)
 			continue;
 		set_bit(NFS_CONTEXT_BAD, &ctx->flags);
 	}
-	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 }
 
 static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error)
@@ -1549,10 +1549,62 @@ out:
 	return status;
 }
 
+#ifdef CONFIG_NFS_V4_2
+static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state *state)
+{
+	struct nfs4_copy_state *copy;
+
+	if (!test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags))
+		return;
+
+	spin_lock(&sp->so_server->nfs_client->cl_lock);
+	list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
+		if (nfs4_stateid_match_other(&state->stateid, &copy->parent_state->stateid))
+			continue;
+		copy->flags = 1;
+		complete(&copy->completion);
+		break;
+	}
+	spin_unlock(&sp->so_server->nfs_client->cl_lock);
+}
+#else /* !CONFIG_NFS_V4_2 */
+static inline void nfs42_complete_copies(struct nfs4_state_owner *sp,
+					 struct nfs4_state *state)
+{
+}
+#endif /* CONFIG_NFS_V4_2 */
+
+static int __nfs4_reclaim_open_state(struct nfs4_state_owner *sp, struct nfs4_state *state,
+				     const struct nfs4_state_recovery_ops *ops)
+{
+	struct nfs4_lock_state *lock;
+	int status;
+
+	status = ops->recover_open(sp, state);
+	if (status < 0)
+		return status;
+
+	status = nfs4_reclaim_locks(state, ops);
+	if (status < 0)
+		return status;
+
+	if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
+		spin_lock(&state->state_lock);
+		list_for_each_entry(lock, &state->lock_states, ls_locks) {
+			if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
+				pr_warn_ratelimited("NFS: %s: Lock reclaim failed!\n", __func__);
+		}
+		spin_unlock(&state->state_lock);
+	}
+
+	nfs42_complete_copies(sp, state);
+	clear_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags);
+	return status;
+}
+
 static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops)
 {
 	struct nfs4_state *state;
-	struct nfs4_lock_state *lock;
 	int status = 0;
 
 	/* Note: we rely on the sp->so_states list being ordered 
@@ -1573,79 +1625,45 @@ restart:
 			continue;
 		if (state->state == 0)
 			continue;
-		atomic_inc(&state->count);
+		refcount_inc(&state->count);
 		spin_unlock(&sp->so_lock);
-		status = ops->recover_open(sp, state);
-		if (status >= 0) {
-			status = nfs4_reclaim_locks(state, ops);
-			if (status >= 0) {
-				if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) {
-					spin_lock(&state->state_lock);
-					list_for_each_entry(lock, &state->lock_states, ls_locks) {
-						if (!test_bit(NFS_LOCK_INITIALIZED, &lock->ls_flags))
-							pr_warn_ratelimited("NFS: "
-									    "%s: Lock reclaim "
-									    "failed!\n", __func__);
-					}
-					spin_unlock(&state->state_lock);
-				}
-				clear_bit(NFS_STATE_RECLAIM_NOGRACE,
-					&state->flags);
-#ifdef CONFIG_NFS_V4_2
-				if (test_bit(NFS_CLNT_DST_SSC_COPY_STATE, &state->flags)) {
-					struct nfs4_copy_state *copy;
-
-					spin_lock(&sp->so_server->nfs_client->cl_lock);
-					list_for_each_entry(copy, &sp->so_server->ss_copies, copies) {
-						if (memcmp(&state->stateid.other, &copy->parent_state->stateid.other, NFS4_STATEID_SIZE))
-							continue;
-						copy->flags = 1;
-						complete(&copy->completion);
-						printk("AGLO: server rebooted waking up the copy\n");
-						break;
-					}
-					spin_unlock(&sp->so_server->nfs_client->cl_lock);
-				}
-#endif /* CONFIG_NFS_V4_2 */
-				nfs4_put_open_state(state);
-				spin_lock(&sp->so_lock);
-				goto restart;
-			}
-		}
+		status = __nfs4_reclaim_open_state(sp, state, ops);
+
 		switch (status) {
-			default:
-				printk(KERN_ERR "NFS: %s: unhandled error %d\n",
-					__func__, status);
-				/* Fall through */
-			case -ENOENT:
-			case -ENOMEM:
-			case -EACCES:
-			case -EROFS:
-			case -EIO:
-			case -ESTALE:
-				/* Open state on this file cannot be recovered */
-				nfs4_state_mark_recovery_failed(state, status);
-				break;
-			case -EAGAIN:
-				ssleep(1);
-				/* Fall through */
-			case -NFS4ERR_ADMIN_REVOKED:
-			case -NFS4ERR_STALE_STATEID:
-			case -NFS4ERR_OLD_STATEID:
-			case -NFS4ERR_BAD_STATEID:
-			case -NFS4ERR_RECLAIM_BAD:
-			case -NFS4ERR_RECLAIM_CONFLICT:
-				nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+		default:
+			if (status >= 0)
 				break;
-			case -NFS4ERR_EXPIRED:
-			case -NFS4ERR_NO_GRACE:
-				nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
-			case -NFS4ERR_STALE_CLIENTID:
-			case -NFS4ERR_BADSESSION:
-			case -NFS4ERR_BADSLOT:
-			case -NFS4ERR_BAD_HIGH_SLOT:
-			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-				goto out_err;
+			printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status);
+			/* Fall through */
+		case -ENOENT:
+		case -ENOMEM:
+		case -EACCES:
+		case -EROFS:
+		case -EIO:
+		case -ESTALE:
+			/* Open state on this file cannot be recovered */
+			nfs4_state_mark_recovery_failed(state, status);
+			break;
+		case -EAGAIN:
+			ssleep(1);
+			/* Fall through */
+		case -NFS4ERR_ADMIN_REVOKED:
+		case -NFS4ERR_STALE_STATEID:
+		case -NFS4ERR_OLD_STATEID:
+		case -NFS4ERR_BAD_STATEID:
+		case -NFS4ERR_RECLAIM_BAD:
+		case -NFS4ERR_RECLAIM_CONFLICT:
+			nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+			break;
+		case -NFS4ERR_EXPIRED:
+		case -NFS4ERR_NO_GRACE:
+			nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+		case -NFS4ERR_STALE_CLIENTID:
+		case -NFS4ERR_BADSESSION:
+		case -NFS4ERR_BADSLOT:
+		case -NFS4ERR_BAD_HIGH_SLOT:
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+			goto out_err;
 		}
 		nfs4_put_open_state(state);
 		spin_lock(&sp->so_lock);
@@ -1795,38 +1813,38 @@ static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp)
 static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 {
 	switch (error) {
-		case 0:
-			break;
-		case -NFS4ERR_CB_PATH_DOWN:
-			nfs40_handle_cb_pathdown(clp);
-			break;
-		case -NFS4ERR_NO_GRACE:
-			nfs4_state_end_reclaim_reboot(clp);
-			break;
-		case -NFS4ERR_STALE_CLIENTID:
-			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
-			nfs4_state_start_reclaim_reboot(clp);
-			break;
-		case -NFS4ERR_EXPIRED:
-			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
-			nfs4_state_start_reclaim_nograce(clp);
-			break;
-		case -NFS4ERR_BADSESSION:
-		case -NFS4ERR_BADSLOT:
-		case -NFS4ERR_BAD_HIGH_SLOT:
-		case -NFS4ERR_DEADSESSION:
-		case -NFS4ERR_SEQ_FALSE_RETRY:
-		case -NFS4ERR_SEQ_MISORDERED:
-			set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
-			/* Zero session reset errors */
-			break;
-		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-			set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
-			break;
-		default:
-			dprintk("%s: failed to handle error %d for server %s\n",
-					__func__, error, clp->cl_hostname);
-			return error;
+	case 0:
+		break;
+	case -NFS4ERR_CB_PATH_DOWN:
+		nfs40_handle_cb_pathdown(clp);
+		break;
+	case -NFS4ERR_NO_GRACE:
+		nfs4_state_end_reclaim_reboot(clp);
+		break;
+	case -NFS4ERR_STALE_CLIENTID:
+		set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		nfs4_state_start_reclaim_reboot(clp);
+		break;
+	case -NFS4ERR_EXPIRED:
+		set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		nfs4_state_start_reclaim_nograce(clp);
+		break;
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_BADSLOT:
+	case -NFS4ERR_BAD_HIGH_SLOT:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_SEQ_FALSE_RETRY:
+	case -NFS4ERR_SEQ_MISORDERED:
+		set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		/* Zero session reset errors */
+		break;
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
+		break;
+	default:
+		dprintk("%s: failed to handle error %d for server %s\n",
+				__func__, error, clp->cl_hostname);
+		return error;
 	}
 	dprintk("%s: handled error %d for server %s\n", __func__, error,
 			clp->cl_hostname);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index b7bde12d8cd5..2fc8f6fa25e4 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3516,7 +3516,7 @@ static int decode_attr_exclcreat_supported(struct xdr_stream *xdr,
 static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fh *fh)
 {
 	__be32 *p;
-	int len;
+	u32 len;
 
 	if (fh != NULL)
 		memset(fh, 0, sizeof(*fh));
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index bb5476a6d264..5c4568a0804b 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -63,14 +63,14 @@ EXPORT_SYMBOL_GPL(nfs_pgheader_init);
 
 void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
 {
-	spin_lock(&hdr->lock);
-	if (!test_and_set_bit(NFS_IOHDR_ERROR, &hdr->flags)
-	    || pos < hdr->io_start + hdr->good_bytes) {
+	unsigned int new = pos - hdr->io_start;
+
+	if (hdr->good_bytes > new) {
+		hdr->good_bytes = new;
 		clear_bit(NFS_IOHDR_EOF, &hdr->flags);
-		hdr->good_bytes = pos - hdr->io_start;
-		hdr->error = error;
+		if (!test_and_set_bit(NFS_IOHDR_ERROR, &hdr->flags))
+			hdr->error = error;
 	}
-	spin_unlock(&hdr->lock);
 }
 
 static inline struct nfs_page *
@@ -494,7 +494,6 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops)
 
 	if (hdr) {
 		INIT_LIST_HEAD(&hdr->pages);
-		spin_lock_init(&hdr->lock);
 		hdr->rw_ops = ops;
 	}
 	return hdr;
@@ -1111,6 +1110,20 @@ static int nfs_pageio_add_request_mirror(struct nfs_pageio_descriptor *desc,
 	return ret;
 }
 
+static void nfs_pageio_error_cleanup(struct nfs_pageio_descriptor *desc)
+{
+	u32 midx;
+	struct nfs_pgio_mirror *mirror;
+
+	if (!desc->pg_error)
+		return;
+
+	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
+		mirror = &desc->pg_mirrors[midx];
+		desc->pg_completion_ops->error_cleanup(&mirror->pg_list);
+	}
+}
+
 int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			   struct nfs_page *req)
 {
@@ -1161,25 +1174,7 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 	return 1;
 
 out_failed:
-	/*
-	 * We might have failed before sending any reqs over wire.
-	 * Clean up rest of the reqs in mirror pg_list.
-	 */
-	if (desc->pg_error) {
-		struct nfs_pgio_mirror *mirror;
-		void (*func)(struct list_head *);
-
-		/* remember fatal errors */
-		if (nfs_error_is_fatal(desc->pg_error))
-			nfs_context_set_write_error(req->wb_context,
-						    desc->pg_error);
-
-		func = desc->pg_completion_ops->error_cleanup;
-		for (midx = 0; midx < desc->pg_mirror_count; midx++) {
-			mirror = &desc->pg_mirrors[midx];
-			func(&mirror->pg_list);
-		}
-	}
+	nfs_pageio_error_cleanup(desc);
 	return 0;
 }
 
@@ -1251,6 +1246,8 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
 	for (midx = 0; midx < desc->pg_mirror_count; midx++)
 		nfs_pageio_complete_mirror(desc, midx);
 
+	if (desc->pg_error < 0)
+		nfs_pageio_error_cleanup(desc);
 	if (desc->pg_ops->pg_cleanup)
 		desc->pg_ops->pg_cleanup(desc);
 	nfs_pageio_cleanup_mirroring(desc);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 7d9a51e6b847..06cb90e9bc6e 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -965,7 +965,7 @@ static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags)
 	struct page **pages;
 	int i;
 
-	pages = kcalloc(size, sizeof(struct page *), gfp_flags);
+	pages = kmalloc_array(size, sizeof(struct page *), gfp_flags);
 	if (!pages) {
 		dprintk("%s: can't alloc array of %zu pages\n", __func__, size);
 		return NULL;
@@ -975,7 +975,7 @@ static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags)
 		pages[i] = alloc_page(gfp_flags);
 		if (!pages[i]) {
 			dprintk("%s: failed to allocate page\n", __func__);
-			nfs4_free_pages(pages, size);
+			nfs4_free_pages(pages, i);
 			return NULL;
 		}
 	}
@@ -991,6 +991,7 @@ pnfs_alloc_init_layoutget_args(struct inode *ino,
 	   gfp_t gfp_flags)
 {
 	struct nfs_server *server = pnfs_find_server(ino, ctx);
+	size_t max_reply_sz = server->pnfs_curr_ld->max_layoutget_response;
 	size_t max_pages = max_response_pages(server);
 	struct nfs4_layoutget *lgp;
 
@@ -1000,6 +1001,12 @@ pnfs_alloc_init_layoutget_args(struct inode *ino,
 	if (lgp == NULL)
 		return NULL;
 
+	if (max_reply_sz) {
+		size_t npages = (max_reply_sz + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		if (npages < max_pages)
+			max_pages = npages;
+	}
+
 	lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags);
 	if (!lgp->args.layout.pages) {
 		kfree(lgp);
@@ -1332,6 +1339,7 @@ bool pnfs_roc(struct inode *ino,
 	if (!nfs_have_layout(ino))
 		return false;
 retry:
+	rcu_read_lock();
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
 	if (!lo || !pnfs_layout_is_valid(lo) ||
@@ -1342,6 +1350,7 @@ retry:
 	pnfs_get_layout_hdr(lo);
 	if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) {
 		spin_unlock(&ino->i_lock);
+		rcu_read_unlock();
 		wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN,
 				TASK_UNINTERRUPTIBLE);
 		pnfs_put_layout_hdr(lo);
@@ -1355,7 +1364,7 @@ retry:
 		skip_read = true;
 	}
 
-	list_for_each_entry(ctx, &nfsi->open_files, list) {
+	list_for_each_entry_rcu(ctx, &nfsi->open_files, list) {
 		state = ctx->state;
 		if (state == NULL)
 			continue;
@@ -1403,6 +1412,7 @@ retry:
 
 out_noroc:
 	spin_unlock(&ino->i_lock);
+	rcu_read_unlock();
 	pnfs_layoutcommit_inode(ino, true);
 	if (roc) {
 		struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index ece367ebde69..e2e9fcd5341d 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -125,6 +125,7 @@ struct pnfs_layoutdriver_type {
 	struct module *owner;
 	unsigned flags;
 	unsigned max_deviceinfo_size;
+	unsigned max_layoutget_response;
 
 	int (*set_layoutdriver) (struct nfs_server *, const struct nfs_fh *);
 	int (*clear_layoutdriver) (struct nfs_server *);
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 48d7277c60a9..f9f19784db82 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -276,16 +276,14 @@ static void nfs_readpage_result(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
 	if (hdr->res.eof) {
-		loff_t bound;
+		loff_t pos = hdr->args.offset + hdr->res.count;
+		unsigned int new = pos - hdr->io_start;
 
-		bound = hdr->args.offset + hdr->res.count;
-		spin_lock(&hdr->lock);
-		if (bound < hdr->io_start + hdr->good_bytes) {
+		if (hdr->good_bytes > new) {
+			hdr->good_bytes = new;
 			set_bit(NFS_IOHDR_EOF, &hdr->flags);
 			clear_bit(NFS_IOHDR_ERROR, &hdr->flags);
-			hdr->good_bytes = bound - hdr->io_start;
 		}
-		spin_unlock(&hdr->lock);
 	} else if (hdr->res.count < hdr->args.count)
 		nfs_readpage_retry(task, hdr);
 }