Merge branch 'for-2.6.32' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.32' of git://linux-nfs.org/~bfields/linux: (68 commits)
  nfsd4: nfsv4 clients should cross mountpoints
  nfsd: revise 4.1 status documentation
  sunrpc/cache: avoid variable over-loading in cache_defer_req
  sunrpc/cache: use list_del_init for the list_head entries in cache_deferred_req
  nfsd: return success for non-NFS4 nfs4_state_start
  nfsd41: Refactor create_client()
  nfsd41: modify nfsd4.1 backchannel to use new xprt class
  nfsd41: Backchannel: Implement cb_recall over NFSv4.1
  nfsd41: Backchannel: cb_sequence callback
  nfsd41: Backchannel: Setup sequence information
  nfsd41: Backchannel: Server backchannel RPC wait queue
  nfsd41: Backchannel: Add sequence arguments to callback RPC arguments
  nfsd41: Backchannel: callback infrastructure
  nfsd4: use common rpc_cred for all callbacks
  nfsd4: allow nfs4 state startup to fail
  SUNRPC: Defer the auth_gss upcall when the RPC call is asynchronous
  nfsd4: fix null dereference creating nfsv4 callback client
  nfsd4: fix whitespace in NFSPROC4_CLNT_CB_NULL definition
  nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel
  sunrpc/cache: simplify cache_fresh_locked and cache_fresh_unlocked.
  ...

Documentation/filesystems/nfs41-server.txt

@@ -11,6 +11,11 @@ the /proc/fs/nfsd/versions control file.  Note that to write this
 control file, the nfsd service must be taken down.  Use your user-mode
 nfs-utils to set this up; see rpc.nfsd(8)
 
+(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and
+"-4", respectively.  Therefore, code meant to work on both new and old
+kernels must turn 4.1 on or off *before* turning support for version 4
+on or off; rpc.nfsd does this correctly.)
+
 The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
 on the latest NFSv4.1 Internet Draft:
 http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
@@ -25,6 +30,49 @@ are still under development out of tree.
 See http://wiki.linux-nfs.org/wiki/index.php/PNFS_prototype_design
 for more information.
 
+The current implementation is intended for developers only: while it
+does support ordinary file operations on clients we have tested against
+(including the linux client), it is incomplete in ways which may limit
+features unexpectedly, cause known bugs in rare cases, or cause
+interoperability problems with future clients.  Known issues:
+
+	- gss support is questionable: currently mounts with kerberos
+	  from a linux client are possible, but we aren't really
+	  conformant with the spec (for example, we don't use kerberos
+	  on the backchannel correctly).
+	- no trunking support: no clients currently take advantage of
+	  trunking, but this is a mandatory failure, and its use is
+	  recommended to clients in a number of places.  (E.g. to ensure
+	  timely renewal in case an existing connection's retry timeouts
+	  have gotten too long; see section 8.3 of the draft.)
+	  Therefore, lack of this feature may cause future clients to
+	  fail.
+	- Incomplete backchannel support: incomplete backchannel gss
+	  support and no support for BACKCHANNEL_CTL mean that
+	  callbacks (hence delegations and layouts) may not be
+	  available and clients confused by the incomplete
+	  implementation may fail.
+	- Server reboot recovery is unsupported; if the server reboots,
+	  clients may fail.
+	- We do not support SSV, which provides security for shared
+	  client-server state (thus preventing unauthorized tampering
+	  with locks and opens, for example).  It is mandatory for
+	  servers to support this, though no clients use it yet.
+	- Mandatory operations which we do not support, such as
+	  DESTROY_CLIENTID, FREE_STATEID, SECINFO_NO_NAME, and
+	  TEST_STATEID, are not currently used by clients, but will be
+	  (and the spec recommends their uses in common cases), and
+	  clients should not be expected to know how to recover from the
+	  case where they are not supported.  This will eventually cause
+	  interoperability failures.
+
+In addition, some limitations are inherited from the current NFSv4
+implementation:
+
+	- Incomplete delegation enforcement: if a file is renamed or
+	  unlinked, a client holding a delegation may continue to
+	  indefinitely allow opens of the file under the old name.
+
 The table below, taken from the NFSv4.1 document, lists
 the operations that are mandatory to implement (REQ), optional
 (OPT), and NFSv4.0 operations that are required not to implement (MNI)
@@ -142,6 +190,12 @@ NS*| CB_WANTS_CANCELLED      | OPT       | FDELG,      | Section 20.10 |
 
 Implementation notes:
 
+DELEGPURGE:
+* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or
+  CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that
+  persist across client reboots).  Thus we need not implement this for
+  now.
+
 EXCHANGE_ID:
 * only SP4_NONE state protection supported
 * implementation ids are ignored

fs/lockd/clntlock.c

@@ -166,7 +166,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 		 */
 		if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid)
 			continue;
-		if (!nlm_cmp_addr(nlm_addr(block->b_host), addr))
+		if (!rpc_cmp_addr(nlm_addr(block->b_host), addr))
 			continue;
 		if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0)
 			continue;

fs/lockd/host.c

@@ -111,7 +111,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 	 */
 	chain = &nlm_hosts[nlm_hash_address(ni->sap)];
 	hlist_for_each_entry(host, pos, chain, h_hash) {
-		if (!nlm_cmp_addr(nlm_addr(host), ni->sap))
+		if (!rpc_cmp_addr(nlm_addr(host), ni->sap))
 			continue;
 
 		/* See if we have an NSM handle for this client */
@@ -125,7 +125,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 		if (host->h_server != ni->server)
 			continue;
 		if (ni->server &&
-		    !nlm_cmp_addr(nlm_srcaddr(host), ni->src_sap))
+		    !rpc_cmp_addr(nlm_srcaddr(host), ni->src_sap))
 			continue;
 
 		/* Move to head of hash chain. */

fs/lockd/mon.c

@@ -209,7 +209,7 @@ static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap)
 	struct nsm_handle *nsm;
 
 	list_for_each_entry(nsm, &nsm_handles, sm_link)
-		if (nlm_cmp_addr(nsm_addr(nsm), sap))
+		if (rpc_cmp_addr(nsm_addr(nsm), sap))
 			return nsm;
 	return NULL;
 }

fs/lockd/svcsubs.c

@@ -417,7 +417,7 @@ EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_sb);
 static int
 nlmsvc_match_ip(void *datap, struct nlm_host *host)
 {
-	return nlm_cmp_addr(nlm_srcaddr(host), datap);
+	return rpc_cmp_addr(nlm_srcaddr(host), datap);
 }
 
 /**

fs/nfsd/export.c

@@ -1341,6 +1341,8 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	if (rv)
 		goto out;
 	rv = check_nfsd_access(exp, rqstp);
+	if (rv)
+		fh_put(fhp);
 out:
 	exp_put(exp);
 	return rv;

fs/nfsd/nfs3xdr.c

@@ -814,17 +814,6 @@ encode_entry_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name,
 	return p;
 }
 
-static __be32 *
-encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p,
-		struct svc_fh *fhp)
-{
-	p = encode_post_op_attr(cd->rqstp, p, fhp);
-	*p++ = xdr_one;			/* yes, a file handle follows */
-	p = encode_fh(p, fhp);
-	fh_put(fhp);
-	return p;
-}
-
 static int
 compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
 		const char *name, int namlen)
@@ -836,29 +825,54 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
 	dparent = cd->fh.fh_dentry;
 	exp  = cd->fh.fh_export;
 
-	fh_init(fhp, NFS3_FHSIZE);
 	if (isdotent(name, namlen)) {
 		if (namlen == 2) {
 			dchild = dget_parent(dparent);
 			if (dchild == dparent) {
 				/* filesystem root - cannot return filehandle for ".." */
 				dput(dchild);
-				return 1;
+				return -ENOENT;
 			}
 		} else
 			dchild = dget(dparent);
 	} else
 		dchild = lookup_one_len(name, dparent, namlen);
 	if (IS_ERR(dchild))
-		return 1;
-	if (d_mountpoint(dchild) ||
-	    fh_compose(fhp, exp, dchild, &cd->fh) != 0 ||
-	    !dchild->d_inode)
-		rv = 1;
+		return -ENOENT;
+	rv = -ENOENT;
+	if (d_mountpoint(dchild))
+		goto out;
+	rv = fh_compose(fhp, exp, dchild, &cd->fh);
+	if (rv)
+		goto out;
+	if (!dchild->d_inode)
+		goto out;
+	rv = 0;
+out:
 	dput(dchild);
 	return rv;
 }
 
+__be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
+{
+	struct svc_fh	fh;
+	int err;
+
+	fh_init(&fh, NFS3_FHSIZE);
+	err = compose_entry_fh(cd, &fh, name, namlen);
+	if (err) {
+		*p++ = 0;
+		*p++ = 0;
+		goto out;
+	}
+	p = encode_post_op_attr(cd->rqstp, p, &fh);
+	*p++ = xdr_one;			/* yes, a file handle follows */
+	p = encode_fh(p, &fh);
+out:
+	fh_put(&fh);
+	return p;
+}
+
 /*
  * Encode a directory entry. This one works for both normal readdir
  * and readdirplus.
@@ -929,16 +943,8 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 
 		p = encode_entry_baggage(cd, p, name, namlen, ino);
 
-		/* throw in readdirplus baggage */
-		if (plus) {
-			struct svc_fh	fh;
-
-			if (compose_entry_fh(cd, &fh, name, namlen) > 0) {
-				*p++ = 0;
-				*p++ = 0;
-			} else
-				p = encode_entryplus_baggage(cd, p, &fh);
-		}
+		if (plus)
+			p = encode_entryplus_baggage(cd, p, name, namlen);
 		num_entry_words = p - cd->buffer;
 	} else if (cd->rqstp->rq_respages[pn+1] != NULL) {
 		/* temporarily encode entry into next page, then move back to
@@ -951,17 +957,8 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 
 		p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
 
-		/* throw in readdirplus baggage */
-		if (plus) {
-			struct svc_fh	fh;
-
-			if (compose_entry_fh(cd, &fh, name, namlen) > 0) {
-				/* zero out the filehandle */
-				*p1++ = 0;
-				*p1++ = 0;
-			} else
-				p1 = encode_entryplus_baggage(cd, p1, &fh);
-		}
+		if (plus)
+			p = encode_entryplus_baggage(cd, p1, name, namlen);
 
 		/* determine entry word length and lengths to go in pages */
 		num_entry_words = p1 - tmp;

fs/nfsd/nfs4acl.c

@@ -321,7 +321,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
 	deny = ~pas.group & pas.other;
 	if (deny) {
 		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
-		ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+		ace->flag = eflag;
 		ace->access_mask = deny_mask_from_posix(deny, flags);
 		ace->whotype = NFS4_ACL_WHO_GROUP;
 		ace++;
@@ -335,7 +335,7 @@ _posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
 		if (deny) {
 			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
 			ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
-			ace->access_mask = mask_from_posix(deny, flags);
+			ace->access_mask = deny_mask_from_posix(deny, flags);
 			ace->whotype = NFS4_ACL_WHO_NAMED;
 			ace->who = pa->e_id;
 			ace++;