Merge tag 'nfsd-5.7' of git://git.linux-nfs.org/projects/cel/cel-2.6

Pull nfsd updates from Chuck Lever:

 - Fix EXCHANGE_ID response when NFSD runs in a container

 - A battery of new static trace points

 - Socket transports now use bio_vec to send Replies

 - NFS/RDMA now supports filesystems with no .splice_read method

 - Favor memcpy() over DMA mapping for small RPC/RDMA Replies

 - Add pre-requisites for supporting multiple Write chunks

 - Numerous minor fixes and clean-ups

[ Chuck is filling in for Bruce this time while he and his family settle
  into a new house ]

* tag 'nfsd-5.7' of git://git.linux-nfs.org/projects/cel/cel-2.6: (39 commits)
  svcrdma: Fix leak of transport addresses
  SUNRPC: Fix a potential buffer overflow in 'svc_print_xprts()'
  SUNRPC/cache: don't allow invalid entries to be flushed
  nfsd: fsnotify on rmdir under nfsd/clients/
  nfsd4: kill warnings on testing stateids with mismatched clientids
  nfsd: remove read permission bit for ctl sysctl
  NFSD: Fix NFS server build errors
  sunrpc: Add tracing for cache events
  SUNRPC/cache: Allow garbage collection of invalid cache entries
  nfsd: export upcalls must not return ESTALE when mountd is down
  nfsd: Add tracepoints for update of the expkey and export cache entries
  nfsd: Add tracepoints for exp_find_key() and exp_get_by_name()
  nfsd: Add tracing to nfsd_set_fh_dentry()
  nfsd: Don't add locks to closed or closing open stateids
  SUNRPC: Teach server to use xprt_sock_sendmsg for socket sends
  SUNRPC: Refactor xs_sendpages()
  svcrdma: Avoid DMA mapping small RPC Replies
  svcrdma: Fix double sync of transport header buffer
  svcrdma: Refactor chunk list encoders
  SUNRPC: Add encoders for list item discriminators
  ...

fs/nfs/dns_resolve.c

@@ -152,12 +152,13 @@ static int nfs_dns_upcall(struct cache_detail *cd,
 		struct cache_head *ch)
 {
 	struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h);
-	int ret;
 
-	ret = nfs_cache_upcall(cd, key->hostname);
-	if (ret)
-		ret = sunrpc_cache_pipe_upcall(cd, ch);
-	return ret;
+	if (test_and_set_bit(CACHE_PENDING, &ch->flags))
+		return 0;
+	if (!nfs_cache_upcall(cd, key->hostname))
+		return 0;
+	clear_bit(CACHE_PENDING, &ch->flags);
+	return sunrpc_cache_pipe_upcall_timeout(cd, ch);
 }
 
 static int nfs_dns_match(struct cache_head *ca,

fs/nfsd/Kconfig

@@ -136,7 +136,7 @@ config NFSD_FLEXFILELAYOUT
 
 config NFSD_V4_2_INTER_SSC
 	bool "NFSv4.2 inter server to server COPY"
-	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2
+	depends on NFSD_V4 && NFS_V4_1 && NFS_V4_2 && NFS_FS=y
 	help
 	  This option enables support for NFSv4.2 inter server to
 	  server copy where the destination server calls the NFSv4.2

fs/nfsd/export.c

@@ -23,6 +23,7 @@
 #include "netns.h"
 #include "pnfs.h"
 #include "filecache.h"
+#include "trace.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
@@ -50,6 +51,11 @@ static void expkey_put(struct kref *ref)
 	kfree_rcu(key, ek_rcu);
 }
 
+static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h);
+}
+
 static void expkey_request(struct cache_detail *cd,
 			   struct cache_head *h,
 			   char **bpp, int *blen)
@@ -140,7 +146,9 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 	if (len == 0) {
 		set_bit(CACHE_NEGATIVE, &key.h.flags);
 		ek = svc_expkey_update(cd, &key, ek);
-		if (!ek)
+		if (ek)
+			trace_nfsd_expkey_update(ek, NULL);
+		else
 			err = -ENOMEM;
 	} else {
 		err = kern_path(buf, 0, &key.ek_path);
@@ -150,7 +158,9 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 		dprintk("Found the path %s\n", buf);
 
 		ek = svc_expkey_update(cd, &key, ek);
-		if (!ek)
+		if (ek)
+			trace_nfsd_expkey_update(ek, buf);
+		else
 			err = -ENOMEM;
 		path_put(&key.ek_path);
 	}
@@ -249,6 +259,7 @@ static const struct cache_detail svc_expkey_cache_template = {
 	.hash_size	= EXPKEY_HASHMAX,
 	.name		= "nfsd.fh",
 	.cache_put	= expkey_put,
+	.cache_upcall	= expkey_upcall,
 	.cache_request	= expkey_request,
 	.cache_parse	= expkey_parse,
 	.cache_show	= expkey_show,
@@ -330,6 +341,11 @@ static void svc_export_put(struct kref *ref)
 	kfree_rcu(exp, ex_rcu);
 }
 
+static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h);
+}
+
 static void svc_export_request(struct cache_detail *cd,
 			       struct cache_head *h,
 			       char **bpp, int *blen)
@@ -643,15 +659,17 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 	}
 
 	expp = svc_export_lookup(&exp);
-	if (expp)
-		expp = svc_export_update(&exp, expp);
-	else
-		err = -ENOMEM;
-	cache_flush();
-	if (expp == NULL)
+	if (!expp) {
 		err = -ENOMEM;
-	else
+		goto out4;
+	}
+	expp = svc_export_update(&exp, expp);
+	if (expp) {
+		trace_nfsd_export_update(expp);
+		cache_flush();
 		exp_put(expp);
+	} else
+		err = -ENOMEM;
 out4:
 	nfsd4_fslocs_free(&exp.ex_fslocs);
 	kfree(exp.ex_uuid);
@@ -767,6 +785,7 @@ static const struct cache_detail svc_export_cache_template = {
 	.hash_size	= EXPORT_HASHMAX,
 	.name		= "nfsd.export",
 	.cache_put	= svc_export_put,
+	.cache_upcall	= svc_export_upcall,
 	.cache_request	= svc_export_request,
 	.cache_parse	= svc_export_parse,
 	.cache_show	= svc_export_show,
@@ -832,8 +851,10 @@ exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type,
 	if (ek == NULL)
 		return ERR_PTR(-ENOMEM);
 	err = cache_check(cd, &ek->h, reqp);
-	if (err)
+	if (err) {
+		trace_nfsd_exp_find_key(&key, err);
 		return ERR_PTR(err);
+	}
 	return ek;
 }
 
@@ -855,8 +876,10 @@ exp_get_by_name(struct cache_detail *cd, struct auth_domain *clp,
 	if (exp == NULL)
 		return ERR_PTR(-ENOMEM);
 	err = cache_check(cd, &exp->h, reqp);
-	if (err)
+	if (err) {
+		trace_nfsd_exp_get_by_name(&key, err);
 		return ERR_PTR(err);
+	}
 	return exp;
 }
 

fs/nfsd/filecache.c

@@ -890,7 +890,7 @@ nfsd_file_find_locked(struct inode *inode, unsigned int may_flags,
 	unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
 
 	hlist_for_each_entry_rcu(nf, &nfsd_file_hashtbl[hashval].nfb_head,
-				 nf_node) {
+				 nf_node, lockdep_is_held(&nfsd_file_hashtbl[hashval].nfb_lock)) {
 		if ((need & nf->nf_may) != need)
 			continue;
 		if (nf->nf_inode != inode)

fs/nfsd/netns.h

@@ -172,6 +172,8 @@ struct nfsd_net {
 	unsigned int             longest_chain_cachesize;
 
 	struct shrinker		nfsd_reply_cache_shrinker;
+	/* utsname taken from the the process that starts the server */
+	char			nfsd_name[UNX_MAXNODENAME+1];
 };
 
 /* Simple check to find out if a given net was properly initialized */

fs/nfsd/nfs4idmap.c

@@ -122,6 +122,12 @@ idtoname_hash(struct ent *ent)
 	return hash;
 }
 
+static int
+idtoname_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall_timeout(cd, h);
+}
+
 static void
 idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
     int *blen)
@@ -184,6 +190,7 @@ static const struct cache_detail idtoname_cache_template = {
 	.hash_size	= ENT_HASHMAX,
 	.name		= "nfs4.idtoname",
 	.cache_put	= ent_put,
+	.cache_upcall	= idtoname_upcall,
 	.cache_request	= idtoname_request,
 	.cache_parse	= idtoname_parse,
 	.cache_show	= idtoname_show,
@@ -295,6 +302,12 @@ nametoid_hash(struct ent *ent)
 	return hash_str(ent->name, ENT_HASHBITS);
 }
 
+static int
+nametoid_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall_timeout(cd, h);
+}
+
 static void
 nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
     int *blen)
@@ -347,6 +360,7 @@ static const struct cache_detail nametoid_cache_template = {
 	.hash_size	= ENT_HASHMAX,
 	.name		= "nfs4.nametoid",
 	.cache_put	= ent_put,
+	.cache_upcall	= nametoid_upcall,
 	.cache_request	= nametoid_request,
 	.cache_parse	= nametoid_parse,
 	.cache_show	= nametoid_show,

fs/nfsd/nfs4state.c

@@ -494,6 +494,8 @@ find_any_file(struct nfs4_file *f)
 {
 	struct nfsd_file *ret;
 
+	if (!f)
+		return NULL;
 	spin_lock(&f->fi_lock);
 	ret = __nfs4_get_fd(f, O_RDWR);
 	if (!ret) {
@@ -1309,6 +1311,12 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
 	nfs4_free_stateowner(sop);
 }
 
+static bool
+nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp)
+{
+	return list_empty(&stp->st_perfile);
+}
+
 static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp)
 {
 	struct nfs4_file *fp = stp->st_stid.sc_file;
@@ -1379,9 +1387,11 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp)
 {
 	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
 
+	if (!unhash_ol_stateid(stp))
+		return false;
 	list_del_init(&stp->st_locks);
 	nfs4_unhash_stid(&stp->st_stid);
-	return unhash_ol_stateid(stp);
+	return true;
 }
 
 static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -1446,13 +1456,12 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
 static bool unhash_open_stateid(struct nfs4_ol_stateid *stp,
 				struct list_head *reaplist)
 {
-	bool unhashed;
-
 	lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
 
-	unhashed = unhash_ol_stateid(stp);
+	if (!unhash_ol_stateid(stp))
+		return false;
 	release_open_stateid_locks(stp, reaplist);
-	return unhashed;
+	return true;
 }
 
 static void release_open_stateid(struct nfs4_ol_stateid *stp)
@@ -2636,7 +2645,7 @@ static const struct file_operations client_ctl_fops = {
 static const struct tree_descr client_files[] = {
 	[0] = {"info", &client_info_fops, S_IRUSR},
 	[1] = {"states", &client_states_fops, S_IRUSR},
-	[2] = {"ctl", &client_ctl_fops, S_IRUSR|S_IWUSR},
+	[2] = {"ctl", &client_ctl_fops, S_IWUSR},
 	[3] = {""},
 };
 
@@ -4343,7 +4352,8 @@ find_file_locked(struct knfsd_fh *fh, unsigned int hashval)
 {
 	struct nfs4_file *fp;
 
-	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) {
+	hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash,
+				lockdep_is_held(&state_lock)) {
 		if (fh_match(&fp->fi_fhandle, fh)) {
 			if (refcount_inc_not_zero(&fp->fi_ref))
 				return fp;
@@ -5521,15 +5531,8 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) ||
 		CLOSE_STATEID(stateid))
 		return status;
-	/* Client debugging aid. */
-	if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) {
-		char addr_str[INET6_ADDRSTRLEN];
-		rpc_ntop((struct sockaddr *)&cl->cl_addr, addr_str,
-				 sizeof(addr_str));
-		pr_warn_ratelimited("NFSD: client %s testing state ID "
-					"with incorrect client ID\n", addr_str);
+	if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid))
 		return status;
-	}
 	spin_lock(&cl->cl_lock);
 	s = find_stateid_locked(cl, stateid);
 	if (!s)
@@ -6393,21 +6396,21 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
 }
 
 static struct nfs4_ol_stateid *
-find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
+find_lock_stateid(const struct nfs4_lockowner *lo,
+		  const struct nfs4_ol_stateid *ost)
 {
 	struct nfs4_ol_stateid *lst;
-	struct nfs4_client *clp = lo->lo_owner.so_client;
 
-	lockdep_assert_held(&clp->cl_lock);
+	lockdep_assert_held(&ost->st_stid.sc_client->cl_lock);
 
-	list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
-		if (lst->st_stid.sc_type != NFS4_LOCK_STID)
-			continue;
-		if (lst->st_stid.sc_file == fp) {
-			refcount_inc(&lst->st_stid.sc_count);
-			return lst;
+	/* If ost is not hashed, ost->st_locks will not be valid */
+	if (!nfs4_ol_stateid_unhashed(ost))
+		list_for_each_entry(lst, &ost->st_locks, st_locks) {
+			if (lst->st_stateowner == &lo->lo_owner) {
+				refcount_inc(&lst->st_stid.sc_count);
+				return lst;
+			}
 		}
-	}
 	return NULL;
 }
 
@@ -6423,11 +6426,11 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX);
 retry:
 	spin_lock(&clp->cl_lock);
-	spin_lock(&fp->fi_lock);
-	retstp = find_lock_stateid(lo, fp);
+	if (nfs4_ol_stateid_unhashed(open_stp))
+		goto out_close;
+	retstp = find_lock_stateid(lo, open_stp);
 	if (retstp)
-		goto out_unlock;
-
+		goto out_found;
 	refcount_inc(&stp->st_stid.sc_count);
 	stp->st_stid.sc_type = NFS4_LOCK_STID;
 	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
@@ -6436,22 +6439,26 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
+	spin_lock(&fp->fi_lock);
 	list_add(&stp->st_locks, &open_stp->st_locks);
 	list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
 	list_add(&stp->st_perfile, &fp->fi_stateids);
-out_unlock:
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&clp->cl_lock);
-	if (retstp) {
-		if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
-			nfs4_put_stid(&retstp->st_stid);
-			goto retry;
-		}
-		/* To keep mutex tracking happy */
-		mutex_unlock(&stp->st_mutex);
-		stp = retstp;
-	}
 	return stp;
+out_found:
+	spin_unlock(&clp->cl_lock);
+	if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) {
+		nfs4_put_stid(&retstp->st_stid);
+		goto retry;
+	}
+	/* To keep mutex tracking happy */
+	mutex_unlock(&stp->st_mutex);
+	return retstp;
+out_close:
+	spin_unlock(&clp->cl_lock);
+	mutex_unlock(&stp->st_mutex);
+	return NULL;
 }
 
 static struct nfs4_ol_stateid *
@@ -6466,7 +6473,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
 
 	*new = false;
 	spin_lock(&clp->cl_lock);
-	lst = find_lock_stateid(lo, fi);
+	lst = find_lock_stateid(lo, ost);
 	spin_unlock(&clp->cl_lock);
 	if (lst != NULL) {
 		if (nfsd4_lock_ol_stateid(lst) == nfs_ok)

fs/nfsd/nfs4xdr.c

@@ -3591,23 +3591,22 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	__be32 nfserr;
 	__be32 tmp;
 	__be32 *p;
-	u32 zzz = 0;
 	int pad;
 
+	/*
+	 * svcrdma requires every READ payload to start somewhere
+	 * in xdr->pages.
+	 */
+	if (xdr->iov == xdr->buf->head) {
+		xdr->iov = NULL;
+		xdr->end = xdr->p;
+	}
+
 	len = maxcount;
 	v = 0;
-
-	thislen = min_t(long, len, ((void *)xdr->end - (void *)xdr->p));
-	p = xdr_reserve_space(xdr, (thislen+3)&~3);
-	WARN_ON_ONCE(!p);
-	resp->rqstp->rq_vec[v].iov_base = p;
-	resp->rqstp->rq_vec[v].iov_len = thislen;
-	v++;
-	len -= thislen;
-
 	while (len) {
 		thislen = min_t(long, len, PAGE_SIZE);
-		p = xdr_reserve_space(xdr, (thislen+3)&~3);
+		p = xdr_reserve_space(xdr, thislen);
 		WARN_ON_ONCE(!p);
 		resp->rqstp->rq_vec[v].iov_base = p;
 		resp->rqstp->rq_vec[v].iov_len = thislen;
@@ -3616,23 +3615,25 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
 	}
 	read->rd_vlen = v;
 
-	len = maxcount;
 	nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset,
 			    resp->rqstp->rq_vec, read->rd_vlen, &maxcount,
 			    &eof);
 	read->rd_length = maxcount;
 	if (nfserr)
 		return nfserr;
-	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
+	if (svc_encode_read_payload(resp->rqstp, starting_len + 8, maxcount))
+		return nfserr_io;
+	xdr_truncate_encode(xdr, starting_len + 8 + xdr_align_size(maxcount));
 
 	tmp = htonl(eof);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len    , &tmp, 4);
 	tmp = htonl(maxcount);
 	write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
 
+	tmp = xdr_zero;
 	pad = (maxcount&3) ? 4 - (maxcount&3) : 0;
 	write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount,
-								&zzz, pad);
+								&tmp, pad);
 	return 0;
 
 }
@@ -4005,11 +4006,12 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	int major_id_sz;
 	int server_scope_sz;
 	uint64_t minor_id = 0;
+	struct nfsd_net *nn = net_generic(SVC_NET(resp->rqstp), nfsd_net_id);
 
-	major_id = utsname()->nodename;
-	major_id_sz = strlen(major_id);
-	server_scope = utsname()->nodename;
-	server_scope_sz = strlen(server_scope);
+	major_id = nn->nfsd_name;
+	major_id_sz = strlen(nn->nfsd_name);
+	server_scope = nn->nfsd_name;
+	server_scope_sz = strlen(nn->nfsd_name);
 
 	p = xdr_reserve_space(xdr,
 		8 /* eir_clientid */ +

fs/nfsd/nfsctl.c

@@ -1333,6 +1333,7 @@ void nfsd_client_rmdir(struct dentry *dentry)
 	dget(dentry);
 	ret = simple_rmdir(dir, dentry);
 	WARN_ON_ONCE(ret);
+	fsnotify_rmdir(dir, dentry);
 	d_delete(dentry);
 	inode_unlock(dir);
 }

fs/nfsd/nfsfh.c

@@ -14,6 +14,7 @@
 #include "nfsd.h"
 #include "vfs.h"
 #include "auth.h"
+#include "trace.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_FH
 
@@ -209,11 +210,14 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	}
 
 	error = nfserr_stale;
-	if (PTR_ERR(exp) == -ENOENT)
-		return error;
+	if (IS_ERR(exp)) {
+		trace_nfsd_set_fh_dentry_badexport(rqstp, fhp, PTR_ERR(exp));
+
+		if (PTR_ERR(exp) == -ENOENT)
+			return error;
 
-	if (IS_ERR(exp))
 		return nfserrno(PTR_ERR(exp));
+	}
 
 	if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
 		/* Elevate privileges so that the lack of 'r' or 'x'
@@ -267,6 +271,9 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 		dentry = exportfs_decode_fh(exp->ex_path.mnt, fid,
 				data_left, fileid_type,
 				nfsd_acceptable, exp);
+		if (IS_ERR_OR_NULL(dentry))
+			trace_nfsd_set_fh_dentry_badhandle(rqstp, fhp,
+					dentry ?  PTR_ERR(dentry) : -ESTALE);
 	}
 	if (dentry == NULL)
 		goto out;

fs/nfsd/nfssvc.c

@@ -749,6 +749,9 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred)
 	if (nrservs == 0 && nn->nfsd_serv == NULL)
 		goto out;
 
+	strlcpy(nn->nfsd_name, utsname()->nodename,
+		sizeof(nn->nfsd_name));
+
 	error = nfsd_create_serv(net);
 	if (error)
 		goto out;

fs/nfsd/trace.h

@@ -9,6 +9,7 @@
 #define _NFSD_TRACE_H
 
 #include <linux/tracepoint.h>
+#include "export.h"
 #include "nfsfh.h"
 
 TRACE_EVENT(nfsd_compound,
@@ -50,6 +51,127 @@ TRACE_EVENT(nfsd_compound_status,
 		__get_str(name), __entry->status)
 )
 
+DECLARE_EVENT_CLASS(nfsd_fh_err_class,
+	TP_PROTO(struct svc_rqst *rqstp,
+		 struct svc_fh	*fhp,
+		 int		status),
+	TP_ARGS(rqstp, fhp, status),
+	TP_STRUCT__entry(
+		__field(u32, xid)
+		__field(u32, fh_hash)
+		__field(int, status)
+	),
+	TP_fast_assign(
+		__entry->xid = be32_to_cpu(rqstp->rq_xid);
+		__entry->fh_hash = knfsd_fh_hash(&fhp->fh_handle);
+		__entry->status = status;
+	),
+	TP_printk("xid=0x%08x fh_hash=0x%08x status=%d",
+		  __entry->xid, __entry->fh_hash,
+		  __entry->status)
+)
+
+#define DEFINE_NFSD_FH_ERR_EVENT(name)		\
+DEFINE_EVENT(nfsd_fh_err_class, nfsd_##name,	\
+	TP_PROTO(struct svc_rqst *rqstp,	\
+		 struct svc_fh	*fhp,		\
+		 int		status),	\
+	TP_ARGS(rqstp, fhp, status))
+
+DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badexport);
+DEFINE_NFSD_FH_ERR_EVENT(set_fh_dentry_badhandle);
+
+TRACE_EVENT(nfsd_exp_find_key,
+	TP_PROTO(const struct svc_expkey *key,
+		 int status),
+	TP_ARGS(key, status),
+	TP_STRUCT__entry(
+		__field(int, fsidtype)
+		__array(u32, fsid, 6)
+		__string(auth_domain, key->ek_client->name)
+		__field(int, status)
+	),
+	TP_fast_assign(
+		__entry->fsidtype = key->ek_fsidtype;
+		memcpy(__entry->fsid, key->ek_fsid, 4*6);
+		__assign_str(auth_domain, key->ek_client->name);
+		__entry->status = status;
+	),
+	TP_printk("fsid=%x::%s domain=%s status=%d",
+		__entry->fsidtype,
+		__print_array(__entry->fsid, 6, 4),
+		__get_str(auth_domain),
+		__entry->status
+	)
+);
+
+TRACE_EVENT(nfsd_expkey_update,
+	TP_PROTO(const struct svc_expkey *key, const char *exp_path),
+	TP_ARGS(key, exp_path),
+	TP_STRUCT__entry(
+		__field(int, fsidtype)
+		__array(u32, fsid, 6)
+		__string(auth_domain, key->ek_client->name)
+		__string(path, exp_path)
+		__field(bool, cache)
+	),
+	TP_fast_assign(
+		__entry->fsidtype = key->ek_fsidtype;
+		memcpy(__entry->fsid, key->ek_fsid, 4*6);
+		__assign_str(auth_domain, key->ek_client->name);
+		__assign_str(path, exp_path);
+		__entry->cache = !test_bit(CACHE_NEGATIVE, &key->h.flags);
+	),
+	TP_printk("fsid=%x::%s domain=%s path=%s cache=%s",
+		__entry->fsidtype,
+		__print_array(__entry->fsid, 6, 4),
+		__get_str(auth_domain),
+		__get_str(path),
+		__entry->cache ? "pos" : "neg"
+	)
+);
+
+TRACE_EVENT(nfsd_exp_get_by_name,
+	TP_PROTO(const struct svc_export *key,
+		 int status),
+	TP_ARGS(key, status),
+	TP_STRUCT__entry(
+		__string(path, key->ex_path.dentry->d_name.name)
+		__string(auth_domain, key->ex_client->name)
+		__field(int, status)
+	),
+	TP_fast_assign(
+		__assign_str(path, key->ex_path.dentry->d_name.name);
+		__assign_str(auth_domain, key->ex_client->name);
+		__entry->status = status;
+	),
+	TP_printk("path=%s domain=%s status=%d",
+		__get_str(path),
+		__get_str(auth_domain),
+		__entry->status
+	)
+);
+
+TRACE_EVENT(nfsd_export_update,
+	TP_PROTO(const struct svc_export *key),
+	TP_ARGS(key),
+	TP_STRUCT__entry(
+		__string(path, key->ex_path.dentry->d_name.name)
+		__string(auth_domain, key->ex_client->name)
+		__field(bool, cache)
+	),
+	TP_fast_assign(
+		__assign_str(path, key->ex_path.dentry->d_name.name);
+		__assign_str(auth_domain, key->ex_client->name);
+		__entry->cache = !test_bit(CACHE_NEGATIVE, &key->h.flags);
+	),
+	TP_printk("path=%s domain=%s cache=%s",
+		__get_str(path),
+		__get_str(auth_domain),
+		__entry->cache ? "pos" : "neg"
+	)
+);
+
 DECLARE_EVENT_CLASS(nfsd_io_class,
 	TP_PROTO(struct svc_rqst *rqstp,
 		 struct svc_fh	*fhp,

include/linux/sunrpc/cache.h

@@ -179,6 +179,9 @@ sunrpc_cache_update(struct cache_detail *detail,
 
 extern int
 sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h);
+extern int
+sunrpc_cache_pipe_upcall_timeout(struct cache_detail *detail,
+				 struct cache_head *h);
 
 
 extern void cache_clean_deferred(void *owner);
@@ -206,11 +209,11 @@ static inline void cache_put(struct cache_head *h, struct cache_detail *cd)
 
 static inline bool cache_is_expired(struct cache_detail *detail, struct cache_head *h)
 {
+	if (h->expiry_time < seconds_since_boot())
+		return true;
 	if (!test_bit(CACHE_VALID, &h->flags))
 		return false;
-
-	return  (h->expiry_time < seconds_since_boot()) ||
-		(detail->flush_time >= h->last_refresh);
+	return detail->flush_time >= h->last_refresh;
 }
 
 extern int cache_check(struct cache_detail *detail,

include/linux/sunrpc/rpc_rdma.h

@@ -58,7 +58,8 @@ enum {
 enum {
 	rpcrdma_fixed_maxsz	= 4,
 	rpcrdma_segment_maxsz	= 4,
-	rpcrdma_readchunk_maxsz	= 2 + rpcrdma_segment_maxsz,
+	rpcrdma_readseg_maxsz	= 1 + rpcrdma_segment_maxsz,
+	rpcrdma_readchunk_maxsz	= 1 + rpcrdma_readseg_maxsz,
 };
 
 /*

include/linux/sunrpc/svc.h

@@ -380,7 +380,7 @@ struct svc_deferred_req {
 	struct cache_deferred_req handle;
 	size_t			xprt_hlen;
 	int			argslen;
-	__be32			args[0];
+	__be32			args[];
 };
 
 struct svc_process_info {
@@ -517,6 +517,9 @@ void		   svc_wake_up(struct svc_serv *);
 void		   svc_reserve(struct svc_rqst *rqstp, int space);
 struct svc_pool *  svc_pool_for_cpu(struct svc_serv *serv, int cpu);
 char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
+int		   svc_encode_read_payload(struct svc_rqst *rqstp,
+					   unsigned int offset,
+					   unsigned int length);
 unsigned int	   svc_fill_write_vector(struct svc_rqst *rqstp,
 					 struct page **pages,
 					 struct kvec *first, size_t total);

include/linux/sunrpc/svc_rdma.h

@@ -52,6 +52,7 @@
 
 /* Default and maximum inline threshold sizes */
 enum {
+	RPCRDMA_PULLUP_THRESH = RPCRDMA_V1_DEF_INLINE_SIZE >> 1,
 	RPCRDMA_DEF_INLINE_THRESH = 4096,
 	RPCRDMA_MAX_INLINE_THRESH = 65536
 };
@@ -132,11 +133,16 @@ struct svc_rdma_recv_ctxt {
 	struct ib_sge		rc_recv_sge;
 	void			*rc_recv_buf;
 	struct xdr_buf		rc_arg;
+	struct xdr_stream	rc_stream;
 	bool			rc_temp;
 	u32			rc_byte_len;
 	unsigned int		rc_page_count;
 	unsigned int		rc_hdr_count;
 	u32			rc_inv_rkey;
+	__be32			*rc_write_list;
+	__be32			*rc_reply_chunk;
+	unsigned int		rc_read_payload_offset;
+	unsigned int		rc_read_payload_length;
 	struct page		*rc_pages[RPCSVC_MAXPAGES];
 };
 
@@ -144,6 +150,8 @@ struct svc_rdma_send_ctxt {
 	struct list_head	sc_list;
 	struct ib_send_wr	sc_send_wr;
 	struct ib_cqe		sc_cqe;
+	struct xdr_buf		sc_hdrbuf;
+	struct xdr_stream	sc_stream;
 	void			*sc_xprt_buf;
 	int			sc_page_count;
 	int			sc_cur_sge_no;
@@ -170,9 +178,11 @@ extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma,
 				    struct svc_rqst *rqstp,
 				    struct svc_rdma_recv_ctxt *head, __be32 *p);
 extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
-				     __be32 *wr_ch, struct xdr_buf *xdr);
+				     __be32 *wr_ch, struct xdr_buf *xdr,
+				     unsigned int offset,
+				     unsigned long length);
 extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
-				     __be32 *rp_ch, bool writelist,
+				     const struct svc_rdma_recv_ctxt *rctxt,
 				     struct xdr_buf *xdr);
 
 /* svc_rdma_sendto.c */
@@ -182,13 +192,13 @@ extern struct svc_rdma_send_ctxt *
 extern void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma,
 				   struct svc_rdma_send_ctxt *ctxt);
 extern int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr);
-extern void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma,
-				    struct svc_rdma_send_ctxt *ctxt,
-				    unsigned int len);
 extern int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
-				  struct svc_rdma_send_ctxt *ctxt,
-				  struct xdr_buf *xdr, __be32 *wr_lst);
+				  struct svc_rdma_send_ctxt *sctxt,
+				  const struct svc_rdma_recv_ctxt *rctxt,
+				  struct xdr_buf *xdr);
 extern int svc_rdma_sendto(struct svc_rqst *);
+extern int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
+				 unsigned int length);
 
 /* svc_rdma_transport.c */
 extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);

include/linux/sunrpc/svc_xprt.h

@@ -21,6 +21,8 @@ struct svc_xprt_ops {
 	int		(*xpo_has_wspace)(struct svc_xprt *);
 	int		(*xpo_recvfrom)(struct svc_rqst *);
 	int		(*xpo_sendto)(struct svc_rqst *);
+	int		(*xpo_read_payload)(struct svc_rqst *, unsigned int,
+					    unsigned int);
 	void		(*xpo_release_rqst)(struct svc_rqst *);
 	void		(*xpo_detach)(struct svc_xprt *);
 	void		(*xpo_free)(struct svc_xprt *);

include/linux/sunrpc/xdr.h

@@ -188,20 +188,6 @@ extern int xdr_buf_read_mic(struct xdr_buf *, struct xdr_netobj *, unsigned int)
 extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int);
 
-/*
- * Helper structure for copying from an sk_buff.
- */
-struct xdr_skb_reader {
-	struct sk_buff	*skb;
-	unsigned int	offset;
-	size_t		count;
-	__wsum		csum;
-};
-
-typedef size_t (*xdr_skb_read_actor)(struct xdr_skb_reader *desc, void *to, size_t len);
-
-extern int csum_partial_copy_to_xdr(struct xdr_buf *, struct sk_buff *);
-
 extern int xdr_encode_word(struct xdr_buf *, unsigned int, u32);
 extern int xdr_decode_word(struct xdr_buf *, unsigned int, u32 *);
 
@@ -300,6 +286,59 @@ xdr_align_size(size_t n)
 	return (n + mask) & ~mask;
 }
 
+/**
+ * xdr_pad_size - Calculate size of an object's pad
+ * @n: Size of an object being XDR encoded (in bytes)
+ *
+ * This implementation avoids the need for conditional
+ * branches or modulo division.
+ *
+ * Return value:
+ *   Size (in bytes) of the needed XDR pad
+ */
+static inline size_t xdr_pad_size(size_t n)
+{
+	return xdr_align_size(n) - n;
+}
+
+/**
+ * xdr_stream_encode_item_present - Encode a "present" list item
+ * @xdr: pointer to xdr_stream
+ *
+ * Return values:
+ *   On success, returns length in bytes of XDR buffer consumed
+ *   %-EMSGSIZE on XDR buffer overflow
+ */
+static inline ssize_t xdr_stream_encode_item_present(struct xdr_stream *xdr)
+{
+	const size_t len = sizeof(__be32);
+	__be32 *p = xdr_reserve_space(xdr, len);
+
+	if (unlikely(!p))
+		return -EMSGSIZE;
+	*p = xdr_one;
+	return len;
+}
+
+/**
+ * xdr_stream_encode_item_absent - Encode a "not present" list item
+ * @xdr: pointer to xdr_stream
+ *
+ * Return values:
+ *   On success, returns length in bytes of XDR buffer consumed
+ *   %-EMSGSIZE on XDR buffer overflow
+ */
+static inline int xdr_stream_encode_item_absent(struct xdr_stream *xdr)
+{
+	const size_t len = sizeof(__be32);
+	__be32 *p = xdr_reserve_space(xdr, len);
+
+	if (unlikely(!p))
+		return -EMSGSIZE;
+	*p = xdr_zero;
+	return len;
+}
+
 /**
  * xdr_stream_encode_u32 - Encode a 32-bit integer
  * @xdr: pointer to xdr_stream

include/trace/events/rpcgss.h

@@ -126,7 +126,7 @@ DEFINE_GSSAPI_EVENT(verify_mic);
 DEFINE_GSSAPI_EVENT(wrap);
 DEFINE_GSSAPI_EVENT(unwrap);
 
-TRACE_EVENT(rpcgss_accept_upcall,
+TRACE_EVENT(rpcgss_svc_accept_upcall,
 	TP_PROTO(
 		__be32 xid,
 		u32 major_status,
@@ -154,6 +154,29 @@ TRACE_EVENT(rpcgss_accept_upcall,
 	)
 );
 
+TRACE_EVENT(rpcgss_svc_accept,
+	TP_PROTO(
+		__be32 xid,
+		size_t len
+	),
+
+	TP_ARGS(xid, len),
+
+	TP_STRUCT__entry(
+		__field(u32, xid)
+		__field(size_t, len)
+	),
+
+	TP_fast_assign(
+		__entry->xid = be32_to_cpu(xid);
+		__entry->len = len;
+	),
+
+	TP_printk("xid=0x%08x len=%zu",
+		__entry->xid, __entry->len
+	)
+);
+
 
 /**
  ** GSS auth unwrap failures
@@ -268,6 +291,40 @@ TRACE_EVENT(rpcgss_need_reencode,
 		__entry->ret ? "" : "un")
 );
 
+DECLARE_EVENT_CLASS(rpcgss_svc_seqno_class,
+	TP_PROTO(
+		__be32 xid,
+		u32 seqno
+	),
+
+	TP_ARGS(xid, seqno),
+
+	TP_STRUCT__entry(
+		__field(u32, xid)
+		__field(u32, seqno)
+	),
+
+	TP_fast_assign(
+		__entry->xid = be32_to_cpu(xid);
+		__entry->seqno = seqno;
+	),
+
+	TP_printk("xid=0x%08x seqno=%u, request discarded",
+		__entry->xid, __entry->seqno)
+);
+
+#define DEFINE_SVC_SEQNO_EVENT(name)					\
+	DEFINE_EVENT(rpcgss_svc_seqno_class, rpcgss_svc_##name,		\
+			TP_PROTO(					\
+				__be32 xid,				\
+				u32 seqno				\
+			),						\
+			TP_ARGS(xid, seqno))
+
+DEFINE_SVC_SEQNO_EVENT(large_seqno);
+DEFINE_SVC_SEQNO_EVENT(old_seqno);
+
+
 /**
  ** gssd upcall related trace events
  **/

include/trace/events/rpcrdma.h

@@ -1469,7 +1469,7 @@ DECLARE_EVENT_CLASS(svcrdma_segment_event,
 );
 
 #define DEFINE_SEGMENT_EVENT(name)					\
-		DEFINE_EVENT(svcrdma_segment_event, svcrdma_encode_##name,\
+		DEFINE_EVENT(svcrdma_segment_event, svcrdma_##name,\
 				TP_PROTO(				\
 					u32 handle,			\
 					u32 length,			\
@@ -1477,8 +1477,11 @@ DECLARE_EVENT_CLASS(svcrdma_segment_event,
 				),					\
 				TP_ARGS(handle, length, offset))
 
-DEFINE_SEGMENT_EVENT(rseg);
-DEFINE_SEGMENT_EVENT(wseg);
+DEFINE_SEGMENT_EVENT(decode_wseg);
+DEFINE_SEGMENT_EVENT(encode_rseg);
+DEFINE_SEGMENT_EVENT(send_rseg);
+DEFINE_SEGMENT_EVENT(encode_wseg);
+DEFINE_SEGMENT_EVENT(send_wseg);
 
 DECLARE_EVENT_CLASS(svcrdma_chunk_event,
 	TP_PROTO(
@@ -1501,17 +1504,19 @@ DECLARE_EVENT_CLASS(svcrdma_chunk_event,
 );
 
 #define DEFINE_CHUNK_EVENT(name)					\
-		DEFINE_EVENT(svcrdma_chunk_event, svcrdma_encode_##name,\
+		DEFINE_EVENT(svcrdma_chunk_event, svcrdma_##name,	\
 				TP_PROTO(				\
 					u32 length			\
 				),					\
 				TP_ARGS(length))
 
-DEFINE_CHUNK_EVENT(pzr);
-DEFINE_CHUNK_EVENT(write);
-DEFINE_CHUNK_EVENT(reply);
+DEFINE_CHUNK_EVENT(send_pzr);
+DEFINE_CHUNK_EVENT(encode_write_chunk);
+DEFINE_CHUNK_EVENT(send_write_chunk);
+DEFINE_CHUNK_EVENT(encode_read_chunk);
+DEFINE_CHUNK_EVENT(send_reply_chunk);
 
-TRACE_EVENT(svcrdma_encode_read,
+TRACE_EVENT(svcrdma_send_read_chunk,
 	TP_PROTO(
 		u32 length,
 		u32 position
@@ -1634,6 +1639,24 @@ TRACE_EVENT(svcrdma_dma_map_rwctx,
 	)
 );
 
+TRACE_EVENT(svcrdma_send_pullup,
+	TP_PROTO(
+		unsigned int len
+	),
+
+	TP_ARGS(len),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, len)
+	),
+
+	TP_fast_assign(
+		__entry->len = len;
+	),
+
+	TP_printk("len=%u", __entry->len)
+);
+
 TRACE_EVENT(svcrdma_send_failed,
 	TP_PROTO(
 		const struct svc_rqst *rqst,
@@ -1813,34 +1836,6 @@ TRACE_EVENT(svcrdma_post_rw,
 DEFINE_SENDCOMP_EVENT(read);
 DEFINE_SENDCOMP_EVENT(write);
 
-TRACE_EVENT(svcrdma_cm_event,
-	TP_PROTO(
-		const struct rdma_cm_event *event,
-		const struct sockaddr *sap
-	),
-
-	TP_ARGS(event, sap),
-
-	TP_STRUCT__entry(
-		__field(unsigned int, event)
-		__field(int, status)
-		__array(__u8, addr, INET6_ADDRSTRLEN + 10)
-	),
-
-	TP_fast_assign(
-		__entry->event = event->event;
-		__entry->status = event->status;
-		snprintf(__entry->addr, sizeof(__entry->addr) - 1,
-			 "%pISpc", sap);
-	),
-
-	TP_printk("addr=%s event=%s (%u/%d)",
-		__entry->addr,
-		rdma_show_cm_event(__entry->event),
-		__entry->event, __entry->status
-	)
-);
-
 TRACE_EVENT(svcrdma_qp_error,
 	TP_PROTO(
 		const struct ib_event *event,