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
  ...

Author: torvalds

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)