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++;

fs/nfsd/nfs4proc.c

@@ -68,7 +68,6 @@ check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		   u32 *bmval, u32 *writable)
 {
 	struct dentry *dentry = cstate->current_fh.fh_dentry;
-	struct svc_export *exp = cstate->current_fh.fh_export;
 
 	/*
 	 * Check about attributes are supported by the NFSv4 server or not.
@@ -80,17 +79,13 @@ check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_attrnotsupp;
 
 	/*
-	 * Check FATTR4_WORD0_ACL & FATTR4_WORD0_FS_LOCATIONS can be supported
+	 * Check FATTR4_WORD0_ACL can be supported
 	 * in current environment or not.
 	 */
 	if (bmval[0] & FATTR4_WORD0_ACL) {
 		if (!IS_POSIXACL(dentry->d_inode))
 			return nfserr_attrnotsupp;
 	}
-	if (bmval[0] & FATTR4_WORD0_FS_LOCATIONS) {
-		if (exp->ex_fslocs.locations == NULL)
-			return nfserr_attrnotsupp;
-	}
 
 	/*
 	 * According to spec, read-only attributes return ERR_INVAL.
@@ -123,6 +118,35 @@ nfsd4_check_open_attributes(struct svc_rqst *rqstp,
 	return status;
 }
 
+static int
+is_create_with_attrs(struct nfsd4_open *open)
+{
+	return open->op_create == NFS4_OPEN_CREATE
+		&& (open->op_createmode == NFS4_CREATE_UNCHECKED
+		    || open->op_createmode == NFS4_CREATE_GUARDED
+		    || open->op_createmode == NFS4_CREATE_EXCLUSIVE4_1);
+}
+
+/*
+ * if error occurs when setting the acl, just clear the acl bit
+ * in the returned attr bitmap.
+ */
+static void
+do_set_nfs4_acl(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct nfs4_acl *acl, u32 *bmval)
+{
+	__be32 status;
+
+	status = nfsd4_set_nfs4_acl(rqstp, fhp, acl);
+	if (status)
+		/*
+		 * We should probably fail the whole open at this point,
+		 * but we've already created the file, so it's too late;
+		 * So this seems the least of evils:
+		 */
+		bmval[0] &= ~FATTR4_WORD0_ACL;
+}
+
 static inline void
 fh_dup2(struct svc_fh *dst, struct svc_fh *src)
 {
@@ -206,6 +230,9 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 	if (status)
 		goto out;
 
+	if (is_create_with_attrs(open) && open->op_acl != NULL)
+		do_set_nfs4_acl(rqstp, &resfh, open->op_acl, open->op_bmval);
+
 	set_change_info(&open->op_cinfo, current_fh);
 	fh_dup2(current_fh, &resfh);
 
@@ -536,12 +563,17 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_badtype;
 	}
 
-	if (!status) {
-		fh_unlock(&cstate->current_fh);
-		set_change_info(&create->cr_cinfo, &cstate->current_fh);
-		fh_dup2(&cstate->current_fh, &resfh);
-	}
+	if (status)
+		goto out;
+
+	if (create->cr_acl != NULL)
+		do_set_nfs4_acl(rqstp, &resfh, create->cr_acl,
+				create->cr_bmval);
 
+	fh_unlock(&cstate->current_fh);
+	set_change_info(&create->cr_cinfo, &cstate->current_fh);
+	fh_dup2(&cstate->current_fh, &resfh);
+out:
 	fh_put(&resfh);
 	return status;
 }
@@ -946,34 +978,6 @@ static struct nfsd4_operation nfsd4_ops[];
 
 static const char *nfsd4_op_name(unsigned opnum);
 
-/*
- * This is a replay of a compound for which no cache entry pages
- * were used. Encode the sequence operation, and if cachethis is FALSE
- * encode the uncache rep error on the next operation.
- */
-static __be32
-nfsd4_enc_uncached_replay(struct nfsd4_compoundargs *args,
-			 struct nfsd4_compoundres *resp)
-{
-	struct nfsd4_op *op;
-
-	dprintk("--> %s resp->opcnt %d ce_cachethis %u \n", __func__,
-		resp->opcnt, resp->cstate.slot->sl_cache_entry.ce_cachethis);
-
-	/* Encode the replayed sequence operation */
-	BUG_ON(resp->opcnt != 1);
-	op = &args->ops[resp->opcnt - 1];
-	nfsd4_encode_operation(resp, op);
-
-	/*return nfserr_retry_uncached_rep in next operation. */
-	if (resp->cstate.slot->sl_cache_entry.ce_cachethis == 0) {
-		op = &args->ops[resp->opcnt++];
-		op->status = nfserr_retry_uncached_rep;
-		nfsd4_encode_operation(resp, op);
-	}
-	return op->status;
-}
-
 /*
  * Enforce NFSv4.1 COMPOUND ordering rules.
  *
@@ -1083,13 +1087,10 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			BUG_ON(op->status == nfs_ok);
 
 encode_op:
-		/* Only from SEQUENCE or CREATE_SESSION */
+		/* Only from SEQUENCE */
 		if (resp->cstate.status == nfserr_replay_cache) {
 			dprintk("%s NFS4.1 replay from cache\n", __func__);
-			if (nfsd4_not_cached(resp))
-				status = nfsd4_enc_uncached_replay(args, resp);
-			else
-				status = op->status;
+			status = op->status;
 			goto out;
 		}
 		if (op->status == nfserr_replay_me) {

fs/nfsd/nfs4xdr.c

@@ -1599,7 +1599,8 @@ static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location,
 static char *nfsd4_path(struct svc_rqst *rqstp, struct svc_export *exp, __be32 *stat)
 {
 	struct svc_fh tmp_fh;
-	char *path, *rootpath;
+	char *path = NULL, *rootpath;
+	size_t rootlen;
 
 	fh_init(&tmp_fh, NFS4_FHSIZE);
 	*stat = exp_pseudoroot(rqstp, &tmp_fh);
@@ -1609,14 +1610,18 @@ static char *nfsd4_path(struct svc_rqst *rqstp, struct svc_export *exp, __be32 *
 
 	path = exp->ex_pathname;
 
-	if (strncmp(path, rootpath, strlen(rootpath))) {
+	rootlen = strlen(rootpath);
+	if (strncmp(path, rootpath, rootlen)) {
 		dprintk("nfsd: fs_locations failed;"
 			"%s is not contained in %s\n", path, rootpath);
 		*stat = nfserr_notsupp;
-		return NULL;
+		path = NULL;
+		goto out;
 	}
-
-	return path + strlen(rootpath);
+	path += rootlen;
+out:
+	fh_put(&tmp_fh);
+	return path;
 }
 
 /*
@@ -1793,11 +1798,6 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 				goto out_nfserr;
 		}
 	}
-	if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) {
-		if (exp->ex_fslocs.locations == NULL) {
-			bmval0 &= ~FATTR4_WORD0_FS_LOCATIONS;
-		}
-	}
 	if ((buflen -= 16) < 0)
 		goto out_resource;
 
@@ -1825,8 +1825,6 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 			goto out_resource;
 		if (!aclsupport)
 			word0 &= ~FATTR4_WORD0_ACL;
-		if (!exp->ex_fslocs.locations)
-			word0 &= ~FATTR4_WORD0_FS_LOCATIONS;
 		if (!word2) {
 			WRITE32(2);
 			WRITE32(word0);
@@ -3064,6 +3062,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
 	WRITE32(0);
 
 	ADJUST_ARGS();
+	resp->cstate.datap = p; /* DRC cache data pointer */
 	return 0;
 }
 
@@ -3166,7 +3165,7 @@ static int nfsd4_check_drc_limit(struct nfsd4_compoundres *resp)
 		return status;
 
 	session = resp->cstate.session;
-	if (session == NULL || slot->sl_cache_entry.ce_cachethis == 0)
+	if (session == NULL || slot->sl_cachethis == 0)
 		return status;
 
 	if (resp->opcnt >= args->opcnt)
@@ -3291,6 +3290,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
 	/*
 	 * All that remains is to write the tag and operation count...
 	 */
+	struct nfsd4_compound_state *cs = &resp->cstate;
 	struct kvec *iov;
 	p = resp->tagp;
 	*p++ = htonl(resp->taglen);
@@ -3304,17 +3304,11 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
 		iov = &rqstp->rq_res.head[0];
 	iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
 	BUG_ON(iov->iov_len > PAGE_SIZE);
-	if (nfsd4_has_session(&resp->cstate)) {
-		if (resp->cstate.status == nfserr_replay_cache &&
-				!nfsd4_not_cached(resp)) {
-			iov->iov_len = resp->cstate.iovlen;
-		} else {
-			nfsd4_store_cache_entry(resp);
-			dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
-			resp->cstate.slot->sl_inuse = 0;
-		}
-		if (resp->cstate.session)
-			nfsd4_put_session(resp->cstate.session);
+	if (nfsd4_has_session(cs) && cs->status != nfserr_replay_cache) {
+		nfsd4_store_cache_entry(resp);
+		dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
+		resp->cstate.slot->sl_inuse = false;
+		nfsd4_put_session(resp->cstate.session);
 	}
 	return 1;
 }

fs/nfsd/nfsctl.c

@@ -174,12 +174,13 @@ static const struct file_operations exports_operations = {
 };
 
 extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
+extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
 
 static struct file_operations pool_stats_operations = {
 	.open		= nfsd_pool_stats_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= seq_release,
+	.release	= nfsd_pool_stats_release,
 	.owner		= THIS_MODULE,
 };
 
@@ -776,10 +777,7 @@ static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
 		size -= len;
 		mesg += len;
 	}
-
-	mutex_unlock(&nfsd_mutex);
-	return (mesg-buf);
-
+	rv = mesg - buf;
 out_free:
 	kfree(nthreads);
 	mutex_unlock(&nfsd_mutex);

fs/nfsd/nfsfh.c

@@ -397,44 +397,51 @@ static inline void _fh_update_old(struct dentry *dentry,
 		fh->ofh_dirino = 0;
 }
 
-__be32
-fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
-	   struct svc_fh *ref_fh)
+static bool is_root_export(struct svc_export *exp)
 {
-	/* ref_fh is a reference file handle.
-	 * if it is non-null and for the same filesystem, then we should compose
-	 * a filehandle which is of the same version, where possible.
-	 * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
-	 * Then create a 32byte filehandle using nfs_fhbase_old
-	 *
-	 */
+	return exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root;
+}
 
-	u8 version;
-	u8 fsid_type = 0;
-	struct inode * inode = dentry->d_inode;
-	struct dentry *parent = dentry->d_parent;
-	__u32 *datap;
-	dev_t ex_dev = exp->ex_path.dentry->d_inode->i_sb->s_dev;
-	int root_export = (exp->ex_path.dentry == exp->ex_path.dentry->d_sb->s_root);
+static struct super_block *exp_sb(struct svc_export *exp)
+{
+	return exp->ex_path.dentry->d_inode->i_sb;
+}
 
-	dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %s/%s, ino=%ld)\n",
-		MAJOR(ex_dev), MINOR(ex_dev),
-		(long) exp->ex_path.dentry->d_inode->i_ino,
-		parent->d_name.name, dentry->d_name.name,
-		(inode ? inode->i_ino : 0));
+static bool fsid_type_ok_for_exp(u8 fsid_type, struct svc_export *exp)
+{
+	switch (fsid_type) {
+	case FSID_DEV:
+		if (!old_valid_dev(exp_sb(exp)->s_dev))
+			return 0;
+		/* FALL THROUGH */
+	case FSID_MAJOR_MINOR:
+	case FSID_ENCODE_DEV:
+		return exp_sb(exp)->s_type->fs_flags & FS_REQUIRES_DEV;
+	case FSID_NUM:
+		return exp->ex_flags & NFSEXP_FSID;
+	case FSID_UUID8:
+	case FSID_UUID16:
+		if (!is_root_export(exp))
+			return 0;
+		/* fall through */
+	case FSID_UUID4_INUM:
+	case FSID_UUID16_INUM:
+		return exp->ex_uuid != NULL;
+	}
+	return 1;
+}
 
-	/* Choose filehandle version and fsid type based on
-	 * the reference filehandle (if it is in the same export)
-	 * or the export options.
-	 */
- retry:
+
+static void set_version_and_fsid_type(struct svc_fh *fhp, struct svc_export *exp, struct svc_fh *ref_fh)
+{
+	u8 version;
+	u8 fsid_type;
+retry:
 	version = 1;
 	if (ref_fh && ref_fh->fh_export == exp) {
 		version = ref_fh->fh_handle.fh_version;
 		fsid_type = ref_fh->fh_handle.fh_fsid_type;
 
-		if (ref_fh == fhp)
-			fh_put(ref_fh);
 		ref_fh = NULL;
 
 		switch (version) {
@@ -447,58 +454,66 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 			goto retry;
 		}
 
-		/* Need to check that this type works for this
-		 * export point.  As the fsid -> filesystem mapping
-		 * was guided by user-space, there is no guarantee
-		 * that the filesystem actually supports that fsid
-		 * type. If it doesn't we loop around again without
-		 * ref_fh set.
+		/*
+		 * As the fsid -> filesystem mapping was guided by
+		 * user-space, there is no guarantee that the filesystem
+		 * actually supports that fsid type. If it doesn't we
+		 * loop around again without ref_fh set.
 		 */
-		switch(fsid_type) {
-		case FSID_DEV:
-			if (!old_valid_dev(ex_dev))
-				goto retry;
-			/* FALL THROUGH */
-		case FSID_MAJOR_MINOR:
-		case FSID_ENCODE_DEV:
-			if (!(exp->ex_path.dentry->d_inode->i_sb->s_type->fs_flags
-			      & FS_REQUIRES_DEV))
-				goto retry;
-			break;
-		case FSID_NUM:
-			if (! (exp->ex_flags & NFSEXP_FSID))
-				goto retry;
-			break;
-		case FSID_UUID8:
-		case FSID_UUID16:
-			if (!root_export)
-				goto retry;
-			/* fall through */
-		case FSID_UUID4_INUM:
-		case FSID_UUID16_INUM:
-			if (exp->ex_uuid == NULL)
-				goto retry;
-			break;
-		}
+		if (!fsid_type_ok_for_exp(fsid_type, exp))
+			goto retry;
 	} else if (exp->ex_flags & NFSEXP_FSID) {
 		fsid_type = FSID_NUM;
 	} else if (exp->ex_uuid) {
 		if (fhp->fh_maxsize >= 64) {
-			if (root_export)
+			if (is_root_export(exp))
 				fsid_type = FSID_UUID16;
 			else
 				fsid_type = FSID_UUID16_INUM;
 		} else {
-			if (root_export)
+			if (is_root_export(exp))
 				fsid_type = FSID_UUID8;
 			else
 				fsid_type = FSID_UUID4_INUM;
 		}
-	} else if (!old_valid_dev(ex_dev))
+	} else if (!old_valid_dev(exp_sb(exp)->s_dev))
 		/* for newer device numbers, we must use a newer fsid format */
 		fsid_type = FSID_ENCODE_DEV;
 	else
 		fsid_type = FSID_DEV;
+	fhp->fh_handle.fh_version = version;
+	if (version)
+		fhp->fh_handle.fh_fsid_type = fsid_type;
+}
+
+__be32
+fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
+	   struct svc_fh *ref_fh)
+{
+	/* ref_fh is a reference file handle.
+	 * if it is non-null and for the same filesystem, then we should compose
+	 * a filehandle which is of the same version, where possible.
+	 * Currently, that means that if ref_fh->fh_handle.fh_version == 0xca
+	 * Then create a 32byte filehandle using nfs_fhbase_old
+	 *
+	 */
+
+	struct inode * inode = dentry->d_inode;
+	struct dentry *parent = dentry->d_parent;
+	__u32 *datap;
+	dev_t ex_dev = exp_sb(exp)->s_dev;
+
+	dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %s/%s, ino=%ld)\n",
+		MAJOR(ex_dev), MINOR(ex_dev),
+		(long) exp->ex_path.dentry->d_inode->i_ino,
+		parent->d_name.name, dentry->d_name.name,
+		(inode ? inode->i_ino : 0));
+
+	/* Choose filehandle version and fsid type based on
+	 * the reference filehandle (if it is in the same export)
+	 * or the export options.
+	 */
+	 set_version_and_fsid_type(fhp, exp, ref_fh);
 
 	if (ref_fh == fhp)
 		fh_put(ref_fh);
@@ -516,7 +531,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	fhp->fh_export = exp;
 	cache_get(&exp->h);
 
-	if (version == 0xca) {
+	if (fhp->fh_handle.fh_version == 0xca) {
 		/* old style filehandle please */
 		memset(&fhp->fh_handle.fh_base, 0, NFS_FHSIZE);
 		fhp->fh_handle.fh_size = NFS_FHSIZE;
@@ -530,22 +545,22 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 			_fh_update_old(dentry, exp, &fhp->fh_handle);
 	} else {
 		int len;
-		fhp->fh_handle.fh_version = 1;
 		fhp->fh_handle.fh_auth_type = 0;
 		datap = fhp->fh_handle.fh_auth+0;
-		fhp->fh_handle.fh_fsid_type = fsid_type;
-		mk_fsid(fsid_type, datap, ex_dev,
+		mk_fsid(fhp->fh_handle.fh_fsid_type, datap, ex_dev,
 			exp->ex_path.dentry->d_inode->i_ino,
 			exp->ex_fsid, exp->ex_uuid);
 
-		len = key_len(fsid_type);
+		len = key_len(fhp->fh_handle.fh_fsid_type);
 		datap += len/4;
 		fhp->fh_handle.fh_size = 4 + len;
 
 		if (inode)
 			_fh_update(fhp, exp, dentry);
-		if (fhp->fh_handle.fh_fileid_type == 255)
+		if (fhp->fh_handle.fh_fileid_type == 255) {
+			fh_put(fhp);
 			return nfserr_opnotsupp;
+		}
 	}
 
 	return 0;
@@ -639,8 +654,7 @@ enum fsid_source fsid_source(struct svc_fh *fhp)
 	case FSID_DEV:
 	case FSID_ENCODE_DEV:
 	case FSID_MAJOR_MINOR:
-		if (fhp->fh_export->ex_path.dentry->d_inode->i_sb->s_type->fs_flags
-		    & FS_REQUIRES_DEV)
+		if (exp_sb(fhp->fh_export)->s_type->fs_flags & FS_REQUIRES_DEV)
 			return FSIDSOURCE_DEV;
 		break;
 	case FSID_NUM:

fs/nfsd/nfssvc.c

@@ -34,6 +34,7 @@
 #include <linux/nfsd/syscall.h>
 #include <linux/lockd/bind.h>
 #include <linux/nfsacl.h>
+#include <linux/seq_file.h>
 
 #define NFSDDBG_FACILITY	NFSDDBG_SVC
 
@@ -66,6 +67,16 @@ struct timeval			nfssvc_boot;
 DEFINE_MUTEX(nfsd_mutex);
 struct svc_serv 		*nfsd_serv;
 
+/*
+ * nfsd_drc_lock protects nfsd_drc_max_pages and nfsd_drc_pages_used.
+ * nfsd_drc_max_pages limits the total amount of memory available for
+ * version 4.1 DRC caches.
+ * nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
+ */
+spinlock_t	nfsd_drc_lock;
+unsigned int	nfsd_drc_max_mem;
+unsigned int	nfsd_drc_mem_used;
+
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat	nfsd_acl_svcstats;
 static struct svc_version *	nfsd_acl_version[] = {
@@ -235,13 +246,12 @@ void nfsd_reset_versions(void)
  */
 static void set_max_drc(void)
 {
-	/* The percent of nr_free_buffer_pages used by the V4.1 server DRC */
-	#define NFSD_DRC_SIZE_SHIFT	7
-	nfsd_serv->sv_drc_max_pages = nr_free_buffer_pages()
-						>> NFSD_DRC_SIZE_SHIFT;
-	nfsd_serv->sv_drc_pages_used = 0;
-	dprintk("%s svc_drc_max_pages %u\n", __func__,
-		nfsd_serv->sv_drc_max_pages);
+	#define NFSD_DRC_SIZE_SHIFT	10
+	nfsd_drc_max_mem = (nr_free_buffer_pages()
+					>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
+	nfsd_drc_mem_used = 0;
+	spin_lock_init(&nfsd_drc_lock);
+	dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
 }
 
 int nfsd_create_serv(void)
@@ -401,7 +411,9 @@ nfsd_svc(unsigned short port, int nrservs)
 	error =	nfsd_racache_init(2*nrservs);
 	if (error<0)
 		goto out;
-	nfs4_state_start();
+	error = nfs4_state_start();
+	if (error)
+		goto out;
 
 	nfsd_reset_versions();
 
@@ -569,10 +581,6 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 		+ rqstp->rq_res.head[0].iov_len;
 	rqstp->rq_res.head[0].iov_len += sizeof(__be32);
 
-	/* NFSv4.1 DRC requires statp */
-	if (rqstp->rq_vers == 4)
-		nfsd4_set_statp(rqstp, statp);
-
 	/* Now call the procedure handler, and encode NFS status. */
 	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
@@ -607,7 +615,25 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 
 int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 {
-	if (nfsd_serv == NULL)
+	int ret;
+	mutex_lock(&nfsd_mutex);
+	if (nfsd_serv == NULL) {
+		mutex_unlock(&nfsd_mutex);
 		return -ENODEV;
-	return svc_pool_stats_open(nfsd_serv, file);
+	}
+	/* bump up the psudo refcount while traversing */
+	svc_get(nfsd_serv);
+	ret = svc_pool_stats_open(nfsd_serv, file);
+	mutex_unlock(&nfsd_mutex);
+	return ret;
+}
+
+int nfsd_pool_stats_release(struct inode *inode, struct file *file)
+{
+	int ret = seq_release(inode, file);
+	mutex_lock(&nfsd_mutex);
+	/* this function really, really should have been called svc_put() */
+	svc_destroy(nfsd_serv);
+	mutex_unlock(&nfsd_mutex);
+	return ret;
 }

fs/nfsd/vfs.c

@@ -89,6 +89,12 @@ struct raparm_hbucket {
 #define RAPARM_HASH_MASK	(RAPARM_HASH_SIZE-1)
 static struct raparm_hbucket	raparm_hash[RAPARM_HASH_SIZE];
 
+static inline int
+nfsd_v4client(struct svc_rqst *rq)
+{
+    return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
+}
+
 /* 
  * Called from nfsd_lookup and encode_dirent. Check if we have crossed 
  * a mount point.
@@ -115,7 +121,8 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 		path_put(&path);
 		goto out;
 	}
-	if ((exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
+	if (nfsd_v4client(rqstp) ||
+		(exp->ex_flags & NFSEXP_CROSSMOUNT) || EX_NOHIDE(exp2)) {
 		/* successfully crossed mount point */
 		/*
 		 * This is subtle: path.dentry is *not* on path.mnt

include/linux/lockd/lockd.h

@@ -338,49 +338,6 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp)
 	}
 }
 
-static inline int __nlm_cmp_addr4(const struct sockaddr *sap1,
-				  const struct sockaddr *sap2)
-{
-	const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sap1;
-	const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sap2;
-	return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr;
-}
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
-				  const struct sockaddr *sap2)
-{
-	const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1;
-	const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2;
-	return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr);
-}
-#else	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
-static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
-				  const struct sockaddr *sap2)
-{
-	return 0;
-}
-#endif	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
-
-/*
- * Compare two host addresses
- *
- * Return TRUE if the addresses are the same; otherwise FALSE.
- */
-static inline int nlm_cmp_addr(const struct sockaddr *sap1,
-			       const struct sockaddr *sap2)
-{
-	if (sap1->sa_family == sap2->sa_family) {
-		switch (sap1->sa_family) {
-		case AF_INET:
-			return __nlm_cmp_addr4(sap1, sap2);
-		case AF_INET6:
-			return __nlm_cmp_addr6(sap1, sap2);
-		}
-	}
-	return 0;
-}
-
 /*
  * Compare two NLM locks.
  * When the second lock is of type F_UNLCK, this acts like a wildcard.

include/linux/nfs4.h

@@ -234,7 +234,7 @@ enum nfs_opnum4 {
 Needs to be updated if more operations are defined in future.*/
 
 #define FIRST_NFS4_OP	OP_ACCESS
-#define LAST_NFS4_OP 	OP_RELEASE_LOCKOWNER
+#define LAST_NFS4_OP 	OP_RECLAIM_COMPLETE
 
 enum nfsstat4 {
 	NFS4_OK = 0,

include/linux/nfsd/nfsd.h

@@ -56,6 +56,9 @@ extern struct svc_version	nfsd_version2, nfsd_version3,
 extern u32			nfsd_supported_minorversion;
 extern struct mutex		nfsd_mutex;
 extern struct svc_serv		*nfsd_serv;
+extern spinlock_t		nfsd_drc_lock;
+extern unsigned int		nfsd_drc_max_mem;
+extern unsigned int		nfsd_drc_mem_used;
 
 extern struct seq_operations nfs_exports_op;
 
@@ -163,7 +166,7 @@ extern int nfsd_max_blksize;
 extern unsigned int max_delegations;
 int nfs4_state_init(void);
 void nfsd4_free_slabs(void);
-void nfs4_state_start(void);
+int nfs4_state_start(void);
 void nfs4_state_shutdown(void);
 time_t nfs4_lease_time(void);
 void nfs4_reset_lease(time_t leasetime);
@@ -171,7 +174,7 @@ int nfs4_reset_recoverydir(char *recdir);
 #else
 static inline int nfs4_state_init(void) { return 0; }
 static inline void nfsd4_free_slabs(void) { }
-static inline void nfs4_state_start(void) { }
+static inline int nfs4_state_start(void) { return 0; }
 static inline void nfs4_state_shutdown(void) { }
 static inline time_t nfs4_lease_time(void) { return 0; }
 static inline void nfs4_reset_lease(time_t leasetime) { }

include/linux/nfsd/state.h

@@ -60,6 +60,12 @@ typedef struct {
 #define si_stateownerid   si_opaque.so_stateownerid
 #define si_fileid         si_opaque.so_fileid
 
+struct nfsd4_cb_sequence {
+	/* args/res */
+	u32			cbs_minorversion;
+	struct nfs4_client	*cbs_clp;
+};
+
 struct nfs4_delegation {
 	struct list_head	dl_perfile;
 	struct list_head	dl_perclnt;
@@ -81,38 +87,35 @@ struct nfs4_delegation {
 /* client delegation callback info */
 struct nfs4_cb_conn {
 	/* SETCLIENTID info */
-	u32                     cb_addr;
-	unsigned short          cb_port;
+	struct sockaddr_storage	cb_addr;
+	size_t			cb_addrlen;
 	u32                     cb_prog;
 	u32			cb_minorversion;
 	u32                     cb_ident;	/* minorversion 0 only */
 	/* RPC client info */
 	atomic_t		cb_set;     /* successful CB_NULL call */
 	struct rpc_clnt *       cb_client;
-	struct rpc_cred	*	cb_cred;
 };
 
-/* Maximum number of slots per session. 128 is useful for long haul TCP */
-#define NFSD_MAX_SLOTS_PER_SESSION	128
-/* Maximum number of pages per slot cache entry */
-#define NFSD_PAGES_PER_SLOT	1
+/* Maximum number of slots per session. 160 is useful for long haul TCP */
+#define NFSD_MAX_SLOTS_PER_SESSION     160
 /* Maximum number of operations per session compound */
 #define NFSD_MAX_OPS_PER_COMPOUND	16
-
-struct nfsd4_cache_entry {
-	__be32		ce_status;
-	struct kvec	ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */
-	struct page	*ce_respages[NFSD_PAGES_PER_SLOT + 1];
-	int		ce_cachethis;
-	short		ce_resused;
-	int		ce_opcnt;
-	int		ce_rpchdrlen;
-};
+/* Maximum  session per slot cache size */
+#define NFSD_SLOT_CACHE_SIZE		1024
+/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
+#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION	32
+#define NFSD_MAX_MEM_PER_SESSION  \
+		(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
 
 struct nfsd4_slot {
-	bool				sl_inuse;
-	u32				sl_seqid;
-	struct nfsd4_cache_entry	sl_cache_entry;
+	bool	sl_inuse;
+	bool	sl_cachethis;
+	u16	sl_opcnt;
+	u32	sl_seqid;
+	__be32	sl_status;
+	u32	sl_datalen;
+	char	sl_data[];
 };
 
 struct nfsd4_channel_attrs {
@@ -126,6 +129,25 @@ struct nfsd4_channel_attrs {
 	u32		rdma_attrs;
 };
 
+struct nfsd4_create_session {
+	clientid_t			clientid;
+	struct nfs4_sessionid		sessionid;
+	u32				seqid;
+	u32				flags;
+	struct nfsd4_channel_attrs	fore_channel;
+	struct nfsd4_channel_attrs	back_channel;
+	u32				callback_prog;
+	u32				uid;
+	u32				gid;
+};
+
+/* The single slot clientid cache structure */
+struct nfsd4_clid_slot {
+	u32				sl_seqid;
+	__be32				sl_status;
+	struct nfsd4_create_session	sl_cr_ses;
+};
+
 struct nfsd4_session {
 	struct kref		se_ref;
 	struct list_head	se_hash;	/* hash by sessionid */
@@ -135,7 +157,7 @@ struct nfsd4_session {
 	struct nfs4_sessionid	se_sessionid;
 	struct nfsd4_channel_attrs se_fchannel;
 	struct nfsd4_channel_attrs se_bchannel;
-	struct nfsd4_slot	se_slots[];	/* forward channel slots */
+	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
 };
 
 static inline void
@@ -180,7 +202,7 @@ struct nfs4_client {
 	char                    cl_recdir[HEXDIR_LEN]; /* recovery dir */
 	nfs4_verifier		cl_verifier; 	/* generated by client */
 	time_t                  cl_time;        /* time of last lease renewal */
-	__be32			cl_addr; 	/* client ipaddress */
+	struct sockaddr_storage	cl_addr; 	/* client ipaddress */
 	u32			cl_flavor;	/* setclientid pseudoflavor */
 	char			*cl_principal;	/* setclientid principal name */
 	struct svc_cred		cl_cred; 	/* setclientid principal */
@@ -192,9 +214,17 @@ struct nfs4_client {
 
 	/* for nfs41 */
 	struct list_head	cl_sessions;
-	struct nfsd4_slot	cl_slot;	/* create_session slot */
+	struct nfsd4_clid_slot	cl_cs_slot;	/* create_session slot */
 	u32			cl_exchange_flags;
 	struct nfs4_sessionid	cl_sessionid;
+
+	/* for nfs41 callbacks */
+	/* We currently support a single back channel with a single slot */
+	unsigned long		cl_cb_slot_busy;
+	u32			cl_cb_seq_nr;
+	struct svc_xprt		*cl_cb_xprt;	/* 4.1 callback transport */
+	struct rpc_wait_queue	cl_cb_waitq;	/* backchannel callers may */
+						/* wait here for slots */
 };
 
 /* struct nfs4_client_reset
@@ -345,6 +375,7 @@ extern int nfs4_in_grace(void);
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
 extern void put_nfs4_client(struct nfs4_client *clp);
 extern void nfs4_free_stateowner(struct kref *kref);
+extern int set_callback_cred(void);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
 extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
 extern void nfs4_put_delegation(struct nfs4_delegation *dp);

include/linux/nfsd/xdr4.h

@@ -51,7 +51,7 @@ struct nfsd4_compound_state {
 	/* For sessions DRC */
 	struct nfsd4_session	*session;
 	struct nfsd4_slot	*slot;
-	__be32			*statp;
+	__be32			*datap;
 	size_t			iovlen;
 	u32			minorversion;
 	u32			status;
@@ -366,18 +366,6 @@ struct nfsd4_exchange_id {
 	int		spa_how;
 };
 
-struct nfsd4_create_session {
-	clientid_t		clientid;
-	struct nfs4_sessionid	sessionid;
-	u32			seqid;
-	u32			flags;
-	struct nfsd4_channel_attrs fore_channel;
-	struct nfsd4_channel_attrs back_channel;
-	u32			callback_prog;
-	u32			uid;
-	u32			gid;
-};
-
 struct nfsd4_sequence {
 	struct nfs4_sessionid	sessionid;		/* request/response */
 	u32			seqid;			/* request/response */
@@ -479,13 +467,12 @@ struct nfsd4_compoundres {
 static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp)
 {
 	struct nfsd4_compoundargs *args = resp->rqstp->rq_argp;
-	return args->opcnt == 1;
+	return resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE;
 }
 
 static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
 {
-	return !resp->cstate.slot->sl_cache_entry.ce_cachethis ||
-			nfsd4_is_solo_sequence(resp);
+	return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp);
 }
 
 #define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)

include/linux/sunrpc/auth.h

@@ -111,7 +111,7 @@ struct rpc_credops {
 	void			(*crdestroy)(struct rpc_cred *);
 
 	int			(*crmatch)(struct auth_cred *, struct rpc_cred *, int);
-	void			(*crbind)(struct rpc_task *, struct rpc_cred *);
+	void			(*crbind)(struct rpc_task *, struct rpc_cred *, int);
 	__be32 *		(*crmarshal)(struct rpc_task *, __be32 *);
 	int			(*crrefresh)(struct rpc_task *);
 	__be32 *		(*crvalidate)(struct rpc_task *, __be32 *);
@@ -140,7 +140,7 @@ struct rpc_cred *	rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *
 void			rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *);
 struct rpc_cred *	rpcauth_lookupcred(struct rpc_auth *, int);
 void			rpcauth_bindcred(struct rpc_task *, struct rpc_cred *, int);
-void			rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *);
+void			rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int);
 void			put_rpccred(struct rpc_cred *);
 void			rpcauth_unbindcred(struct rpc_task *);
 __be32 *		rpcauth_marshcred(struct rpc_task *, __be32 *);

include/linux/sunrpc/clnt.h

@@ -22,6 +22,7 @@
 #include <linux/sunrpc/timer.h>
 #include <asm/signal.h>
 #include <linux/path.h>
+#include <net/ipv6.h>
 
 struct rpc_inode;
 
@@ -113,6 +114,7 @@ struct rpc_create_args {
 	rpc_authflavor_t	authflavor;
 	unsigned long		flags;
 	char			*client_name;
+	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
 };
 
 /* Values for "flags" field */
@@ -188,5 +190,117 @@ static inline void rpc_set_port(struct sockaddr *sap,
 #define IPV6_SCOPE_DELIMITER		'%'
 #define IPV6_SCOPE_ID_LEN		sizeof("%nnnnnnnnnn")
 
+static inline bool __rpc_cmp_addr4(const struct sockaddr *sap1,
+				   const struct sockaddr *sap2)
+{
+	const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sap1;
+	const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sap2;
+
+	return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr;
+}
+
+static inline bool __rpc_copy_addr4(struct sockaddr *dst,
+				    const struct sockaddr *src)
+{
+	const struct sockaddr_in *ssin = (struct sockaddr_in *) src;
+	struct sockaddr_in *dsin = (struct sockaddr_in *) dst;
+
+	dsin->sin_family = ssin->sin_family;
+	dsin->sin_addr.s_addr = ssin->sin_addr.s_addr;
+	return true;
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
+				   const struct sockaddr *sap2)
+{
+	const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1;
+	const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2;
+	return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr);
+}
+
+static inline bool __rpc_copy_addr6(struct sockaddr *dst,
+				    const struct sockaddr *src)
+{
+	const struct sockaddr_in6 *ssin6 = (const struct sockaddr_in6 *) src;
+	struct sockaddr_in6 *dsin6 = (struct sockaddr_in6 *) dst;
+
+	dsin6->sin6_family = ssin6->sin6_family;
+	ipv6_addr_copy(&dsin6->sin6_addr, &ssin6->sin6_addr);
+	return true;
+}
+#else	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
+				   const struct sockaddr *sap2)
+{
+	return false;
+}
+
+static inline bool __rpc_copy_addr6(struct sockaddr *dst,
+				    const struct sockaddr *src)
+{
+	return false;
+}
+#endif	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+
+/**
+ * rpc_cmp_addr - compare the address portion of two sockaddrs.
+ * @sap1: first sockaddr
+ * @sap2: second sockaddr
+ *
+ * Just compares the family and address portion. Ignores port, scope, etc.
+ * Returns true if the addrs are equal, false if they aren't.
+ */
+static inline bool rpc_cmp_addr(const struct sockaddr *sap1,
+				const struct sockaddr *sap2)
+{
+	if (sap1->sa_family == sap2->sa_family) {
+		switch (sap1->sa_family) {
+		case AF_INET:
+			return __rpc_cmp_addr4(sap1, sap2);
+		case AF_INET6:
+			return __rpc_cmp_addr6(sap1, sap2);
+		}
+	}
+	return false;
+}
+
+/**
+ * rpc_copy_addr - copy the address portion of one sockaddr to another
+ * @dst: destination sockaddr
+ * @src: source sockaddr
+ *
+ * Just copies the address portion and family. Ignores port, scope, etc.
+ * Caller is responsible for making certain that dst is large enough to hold
+ * the address in src. Returns true if address family is supported. Returns
+ * false otherwise.
+ */
+static inline bool rpc_copy_addr(struct sockaddr *dst,
+				 const struct sockaddr *src)
+{
+	switch (src->sa_family) {
+	case AF_INET:
+		return __rpc_copy_addr4(dst, src);
+	case AF_INET6:
+		return __rpc_copy_addr6(dst, src);
+	}
+	return false;
+}
+
+/**
+ * rpc_get_scope_id - return scopeid for a given sockaddr
+ * @sa: sockaddr to get scopeid from
+ *
+ * Returns the value of the sin6_scope_id for AF_INET6 addrs, or 0 if
+ * not an AF_INET6 address.
+ */
+static inline u32 rpc_get_scope_id(const struct sockaddr *sa)
+{
+	if (sa->sa_family != AF_INET6)
+		return 0;
+
+	return ((struct sockaddr_in6 *) sa)->sin6_scope_id;
+}
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */

include/linux/sunrpc/svc.h

@@ -94,8 +94,6 @@ struct svc_serv {
 	struct module *		sv_module;	/* optional module to count when
 						 * adding threads */
 	svc_thread_fn		sv_function;	/* main function for threads */
-	unsigned int		sv_drc_max_pages; /* Total pages for DRC */
-	unsigned int		sv_drc_pages_used;/* DRC pages used */
 #if defined(CONFIG_NFS_V4_1)
 	struct list_head	sv_cb_list;	/* queue for callback requests
 						 * that arrive over the same

include/linux/sunrpc/svc_xprt.h

@@ -65,6 +65,7 @@ struct svc_xprt {
 	size_t			xpt_locallen;	/* length of address */
 	struct sockaddr_storage	xpt_remote;	/* remote peer's address */
 	size_t			xpt_remotelen;	/* length of address */
+	struct rpc_wait_queue	xpt_bc_pending;	/* backchannel wait queue */
 };
 
 int	svc_reg_xprt_class(struct svc_xprt_class *);

include/linux/sunrpc/svcsock.h

@@ -28,6 +28,7 @@ struct svc_sock {
 	/* private TCP part */
 	u32			sk_reclen;	/* length of record */
 	u32			sk_tcplen;	/* current read length */
+	struct rpc_xprt		*sk_bc_xprt;	/* NFSv4.1 backchannel xprt */
 };
 
 /*

include/linux/sunrpc/xprt.h

@@ -124,6 +124,23 @@ struct rpc_xprt_ops {
 	void		(*print_stats)(struct rpc_xprt *xprt, struct seq_file *seq);
 };
 
+/*
+ * RPC transport identifiers
+ *
+ * To preserve compatibility with the historical use of raw IP protocol
+ * id's for transport selection, UDP and TCP identifiers are specified
+ * with the previous values. No such restriction exists for new transports,
+ * except that they may not collide with these values (17 and 6,
+ * respectively).
+ */
+#define XPRT_TRANSPORT_BC       (1 << 31)
+enum xprt_transports {
+	XPRT_TRANSPORT_UDP	= IPPROTO_UDP,
+	XPRT_TRANSPORT_TCP	= IPPROTO_TCP,
+	XPRT_TRANSPORT_BC_TCP	= IPPROTO_TCP | XPRT_TRANSPORT_BC,
+	XPRT_TRANSPORT_RDMA	= 256
+};
+
 struct rpc_xprt {
 	struct kref		kref;		/* Reference count */
 	struct rpc_xprt_ops *	ops;		/* transport methods */
@@ -179,6 +196,7 @@ struct rpc_xprt {
 	spinlock_t		reserve_lock;	/* lock slot table */
 	u32			xid;		/* Next XID value to use */
 	struct rpc_task *	snd_task;	/* Task blocked in send */
+	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
 #if defined(CONFIG_NFS_V4_1)
 	struct svc_serv		*bc_serv;       /* The RPC service which will */
 						/* process the callback */
@@ -231,6 +249,7 @@ struct xprt_create {
 	struct sockaddr *	srcaddr;	/* optional local address */
 	struct sockaddr *	dstaddr;	/* remote peer address */
 	size_t			addrlen;
+	struct svc_xprt		*bc_xprt;	/* NFSv4.1 backchannel */
 };
 
 struct xprt_class {

include/linux/sunrpc/xprtrdma.h

@@ -40,11 +40,6 @@
 #ifndef _LINUX_SUNRPC_XPRTRDMA_H
 #define _LINUX_SUNRPC_XPRTRDMA_H
 
-/*
- * RPC transport identifier for RDMA
- */
-#define XPRT_TRANSPORT_RDMA	256
-
 /*
  * rpcbind (v3+) RDMA netid.
  */

include/linux/sunrpc/xprtsock.h

@@ -12,17 +12,6 @@
 int		init_socket_xprt(void);
 void		cleanup_socket_xprt(void);
 
-/*
- * RPC transport identifiers for UDP, TCP
- *
- * To preserve compatibility with the historical use of raw IP protocol
- * id's for transport selection, these are specified with the previous
- * values. No such restriction exists for new transports, except that
- * they may not collide with these values (17 and 6, respectively).
- */
-#define XPRT_TRANSPORT_UDP	IPPROTO_UDP
-#define XPRT_TRANSPORT_TCP	IPPROTO_TCP
-
 /*
  * RPC slot table sizes for UDP, TCP transports
  */

net/sunrpc/auth.c

@@ -385,7 +385,7 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
 EXPORT_SYMBOL_GPL(rpcauth_init_cred);
 
 void
-rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred)
+rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags)
 {
 	task->tk_msg.rpc_cred = get_rpccred(cred);
 	dprintk("RPC: %5u holding %s cred %p\n", task->tk_pid,
@@ -394,7 +394,7 @@ rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred)
 EXPORT_SYMBOL_GPL(rpcauth_generic_bind_cred);
 
 static void
-rpcauth_bind_root_cred(struct rpc_task *task)
+rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
 {
 	struct rpc_auth *auth = task->tk_client->cl_auth;
 	struct auth_cred acred = {
@@ -405,7 +405,7 @@ rpcauth_bind_root_cred(struct rpc_task *task)
 
 	dprintk("RPC: %5u looking up %s cred\n",
 		task->tk_pid, task->tk_client->cl_auth->au_ops->au_name);
-	ret = auth->au_ops->lookup_cred(auth, &acred, 0);
+	ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags);
 	if (!IS_ERR(ret))
 		task->tk_msg.rpc_cred = ret;
 	else
@@ -413,14 +413,14 @@ rpcauth_bind_root_cred(struct rpc_task *task)
 }
 
 static void
-rpcauth_bind_new_cred(struct rpc_task *task)
+rpcauth_bind_new_cred(struct rpc_task *task, int lookupflags)
 {
 	struct rpc_auth *auth = task->tk_client->cl_auth;
 	struct rpc_cred *ret;
 
 	dprintk("RPC: %5u looking up %s cred\n",
 		task->tk_pid, auth->au_ops->au_name);
-	ret = rpcauth_lookupcred(auth, 0);
+	ret = rpcauth_lookupcred(auth, lookupflags);
 	if (!IS_ERR(ret))
 		task->tk_msg.rpc_cred = ret;
 	else
@@ -430,12 +430,16 @@ rpcauth_bind_new_cred(struct rpc_task *task)
 void
 rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
 {
+	int lookupflags = 0;
+
+	if (flags & RPC_TASK_ASYNC)
+		lookupflags |= RPCAUTH_LOOKUP_NEW;
 	if (cred != NULL)
-		cred->cr_ops->crbind(task, cred);
+		cred->cr_ops->crbind(task, cred, lookupflags);
 	else if (flags & RPC_TASK_ROOTCREDS)
-		rpcauth_bind_root_cred(task);
+		rpcauth_bind_root_cred(task, lookupflags);
 	else
-		rpcauth_bind_new_cred(task);
+		rpcauth_bind_new_cred(task, lookupflags);
 }
 
 void

net/sunrpc/auth_generic.c

@@ -55,13 +55,13 @@ struct rpc_cred *rpc_lookup_machine_cred(void)
 EXPORT_SYMBOL_GPL(rpc_lookup_machine_cred);
 
 static void
-generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred)
+generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags)
 {
 	struct rpc_auth *auth = task->tk_client->cl_auth;
 	struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred;
 	struct rpc_cred *ret;
 
-	ret = auth->au_ops->lookup_cred(auth, acred, 0);
+	ret = auth->au_ops->lookup_cred(auth, acred, lookupflags);
 	if (!IS_ERR(ret))
 		task->tk_msg.rpc_cred = ret;
 	else

net/sunrpc/auth_gss/svcauth_gss.c

@@ -1374,8 +1374,10 @@ svcauth_gss_release(struct svc_rqst *rqstp)
 		if (stat)
 			goto out_err;
 		break;
-	default:
-		goto out_err;
+	/*
+	 * For any other gc_svc value, svcauth_gss_accept() already set
+	 * the auth_error appropriately; just fall through:
+	 */
 	}
 
 out:

net/sunrpc/cache.c

@@ -103,23 +103,21 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 EXPORT_SYMBOL_GPL(sunrpc_cache_lookup);
 
 
-static void queue_loose(struct cache_detail *detail, struct cache_head *ch);
+static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch);
 
-static int cache_fresh_locked(struct cache_head *head, time_t expiry)
+static void cache_fresh_locked(struct cache_head *head, time_t expiry)
 {
 	head->expiry_time = expiry;
 	head->last_refresh = get_seconds();
-	return !test_and_set_bit(CACHE_VALID, &head->flags);
+	set_bit(CACHE_VALID, &head->flags);
 }
 
 static void cache_fresh_unlocked(struct cache_head *head,
-			struct cache_detail *detail, int new)
+				 struct cache_detail *detail)
 {
-	if (new)
-		cache_revisit_request(head);
 	if (test_and_clear_bit(CACHE_PENDING, &head->flags)) {
 		cache_revisit_request(head);
-		queue_loose(detail, head);
+		cache_dequeue(detail, head);
 	}
 }
 
@@ -132,7 +130,6 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	 */
 	struct cache_head **head;
 	struct cache_head *tmp;
-	int is_new;
 
 	if (!test_bit(CACHE_VALID, &old->flags)) {
 		write_lock(&detail->hash_lock);
@@ -141,9 +138,9 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 				set_bit(CACHE_NEGATIVE, &old->flags);
 			else
 				detail->update(old, new);
-			is_new = cache_fresh_locked(old, new->expiry_time);
+			cache_fresh_locked(old, new->expiry_time);
 			write_unlock(&detail->hash_lock);
-			cache_fresh_unlocked(old, detail, is_new);
+			cache_fresh_unlocked(old, detail);
 			return old;
 		}
 		write_unlock(&detail->hash_lock);
@@ -167,11 +164,11 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	*head = tmp;
 	detail->entries++;
 	cache_get(tmp);
-	is_new = cache_fresh_locked(tmp, new->expiry_time);
+	cache_fresh_locked(tmp, new->expiry_time);
 	cache_fresh_locked(old, 0);
 	write_unlock(&detail->hash_lock);
-	cache_fresh_unlocked(tmp, detail, is_new);
-	cache_fresh_unlocked(old, detail, 0);
+	cache_fresh_unlocked(tmp, detail);
+	cache_fresh_unlocked(old, detail);
 	cache_put(old, detail);
 	return tmp;
 }
@@ -184,6 +181,22 @@ static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h)
 	return cd->cache_upcall(cd, h);
 }
 
+static inline int cache_is_valid(struct cache_detail *detail, struct cache_head *h)
+{
+	if (!test_bit(CACHE_VALID, &h->flags) ||
+	    h->expiry_time < get_seconds())
+		return -EAGAIN;
+	else if (detail->flush_time > h->last_refresh)
+		return -EAGAIN;
+	else {
+		/* entry is valid */
+		if (test_bit(CACHE_NEGATIVE, &h->flags))
+			return -ENOENT;
+		else
+			return 0;
+	}
+}
+
 /*
  * This is the generic cache management routine for all
  * the authentication caches.
@@ -192,8 +205,10 @@ static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h)
  *
  *
  * Returns 0 if the cache_head can be used, or cache_puts it and returns
- * -EAGAIN if upcall is pending,
- * -ETIMEDOUT if upcall failed and should be retried,
+ * -EAGAIN if upcall is pending and request has been queued
+ * -ETIMEDOUT if upcall failed or request could not be queue or
+ *           upcall completed but item is still invalid (implying that
+ *           the cache item has been replaced with a newer one).
  * -ENOENT if cache entry was negative
  */
 int cache_check(struct cache_detail *detail,
@@ -203,17 +218,7 @@ int cache_check(struct cache_detail *detail,
 	long refresh_age, age;
 
 	/* First decide return status as best we can */
-	if (!test_bit(CACHE_VALID, &h->flags) ||
-	    h->expiry_time < get_seconds())
-		rv = -EAGAIN;
-	else if (detail->flush_time > h->last_refresh)
-		rv = -EAGAIN;
-	else {
-		/* entry is valid */
-		if (test_bit(CACHE_NEGATIVE, &h->flags))
-			rv = -ENOENT;
-		else rv = 0;
-	}
+	rv = cache_is_valid(detail, h);
 
 	/* now see if we want to start an upcall */
 	refresh_age = (h->expiry_time - h->last_refresh);
@@ -229,10 +234,11 @@ int cache_check(struct cache_detail *detail,
 			switch (cache_make_upcall(detail, h)) {
 			case -EINVAL:
 				clear_bit(CACHE_PENDING, &h->flags);
+				cache_revisit_request(h);
 				if (rv == -EAGAIN) {
 					set_bit(CACHE_NEGATIVE, &h->flags);
-					cache_fresh_unlocked(h, detail,
-					     cache_fresh_locked(h, get_seconds()+CACHE_NEW_EXPIRY));
+					cache_fresh_locked(h, get_seconds()+CACHE_NEW_EXPIRY);
+					cache_fresh_unlocked(h, detail);
 					rv = -ENOENT;
 				}
 				break;
@@ -245,10 +251,14 @@ int cache_check(struct cache_detail *detail,
 		}
 	}
 
-	if (rv == -EAGAIN)
-		if (cache_defer_req(rqstp, h) != 0)
-			rv = -ETIMEDOUT;
-
+	if (rv == -EAGAIN) {
+		if (cache_defer_req(rqstp, h) < 0) {
+			/* Request is not deferred */
+			rv = cache_is_valid(detail, h);
+			if (rv == -EAGAIN)
+				rv = -ETIMEDOUT;
+		}
+	}
 	if (rv)
 		cache_put(h, detail);
 	return rv;
@@ -396,7 +406,7 @@ static int cache_clean(void)
 				)
 				continue;
 			if (test_and_clear_bit(CACHE_PENDING, &ch->flags))
-				queue_loose(current_detail, ch);
+				cache_dequeue(current_detail, ch);
 
 			if (atomic_read(&ch->ref.refcount) == 1)
 				break;
@@ -412,8 +422,10 @@ static int cache_clean(void)
 		if (!ch)
 			current_index ++;
 		spin_unlock(&cache_list_lock);
-		if (ch)
+		if (ch) {
+			cache_revisit_request(ch);
 			cache_put(ch, d);
+		}
 	} else
 		spin_unlock(&cache_list_lock);
 
@@ -488,7 +500,7 @@ static int cache_defer_cnt;
 
 static int cache_defer_req(struct cache_req *req, struct cache_head *item)
 {
-	struct cache_deferred_req *dreq;
+	struct cache_deferred_req *dreq, *discard;
 	int hash = DFR_HASH(item);
 
 	if (cache_defer_cnt >= DFR_MAX) {
@@ -496,11 +508,11 @@ static int cache_defer_req(struct cache_req *req, struct cache_head *item)
 		 * or continue and drop the oldest below
 		 */
 		if (net_random()&1)
-			return -ETIMEDOUT;
+			return -ENOMEM;
 	}
 	dreq = req->defer(req);
 	if (dreq == NULL)
-		return -ETIMEDOUT;
+		return -ENOMEM;
 
 	dreq->item = item;
 
@@ -513,23 +525,24 @@ static int cache_defer_req(struct cache_req *req, struct cache_head *item)
 	list_add(&dreq->hash, &cache_defer_hash[hash]);
 
 	/* it is in, now maybe clean up */
-	dreq = NULL;
+	discard = NULL;
 	if (++cache_defer_cnt > DFR_MAX) {
-		dreq = list_entry(cache_defer_list.prev,
-				  struct cache_deferred_req, recent);
-		list_del(&dreq->recent);
-		list_del(&dreq->hash);
+		discard = list_entry(cache_defer_list.prev,
+				     struct cache_deferred_req, recent);
+		list_del_init(&discard->recent);
+		list_del_init(&discard->hash);
 		cache_defer_cnt--;
 	}
 	spin_unlock(&cache_defer_lock);
 
-	if (dreq) {
+	if (discard)
 		/* there was one too many */
-		dreq->revisit(dreq, 1);
-	}
+		discard->revisit(discard, 1);
+
 	if (!test_bit(CACHE_PENDING, &item->flags)) {
 		/* must have just been validated... */
 		cache_revisit_request(item);
+		return -EAGAIN;
 	}
 	return 0;
 }
@@ -551,7 +564,7 @@ static void cache_revisit_request(struct cache_head *item)
 			dreq = list_entry(lp, struct cache_deferred_req, hash);
 			lp = lp->next;
 			if (dreq->item == item) {
-				list_del(&dreq->hash);
+				list_del_init(&dreq->hash);
 				list_move(&dreq->recent, &pending);
 				cache_defer_cnt--;
 			}
@@ -577,7 +590,7 @@ void cache_clean_deferred(void *owner)
 
 	list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) {
 		if (dreq->owner == owner) {
-			list_del(&dreq->hash);
+			list_del_init(&dreq->hash);
 			list_move(&dreq->recent, &pending);
 			cache_defer_cnt--;
 		}
@@ -887,7 +900,7 @@ static int cache_release(struct inode *inode, struct file *filp,
 
 
 
-static void queue_loose(struct cache_detail *detail, struct cache_head *ch)
+static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch)
 {
 	struct cache_queue *cq;
 	spin_lock(&queue_lock);

net/sunrpc/clnt.c

@@ -288,6 +288,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 		.srcaddr = args->saddress,
 		.dstaddr = args->address,
 		.addrlen = args->addrsize,
+		.bc_xprt = args->bc_xprt,
 	};
 	char servername[48];
 

net/sunrpc/sched.c

@@ -21,6 +21,8 @@
 
 #include <linux/sunrpc/clnt.h>
 
+#include "sunrpc.h"
+
 #ifdef RPC_DEBUG
 #define RPCDBG_FACILITY		RPCDBG_SCHED
 #define RPC_TASK_MAGIC_ID	0xf00baa
@@ -711,11 +713,6 @@ static void rpc_async_schedule(struct work_struct *work)
 	__rpc_execute(container_of(work, struct rpc_task, u.tk_work));
 }
 
-struct rpc_buffer {
-	size_t	len;
-	char	data[];
-};
-
 /**
  * rpc_malloc - allocate an RPC buffer
  * @task: RPC task that will use this buffer

net/sunrpc/sunrpc.h

@@ -27,11 +27,25 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #ifndef _NET_SUNRPC_SUNRPC_H
 #define _NET_SUNRPC_SUNRPC_H
 
+#include <linux/net.h>
+
+/*
+ * Header for dynamically allocated rpc buffers.
+ */
+struct rpc_buffer {
+	size_t	len;
+	char	data[];
+};
+
 static inline int rpc_reply_expected(struct rpc_task *task)
 {
 	return (task->tk_msg.rpc_proc != NULL) &&
 		(task->tk_msg.rpc_proc->p_decode != NULL);
 }
 
+int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
+		    struct page *headpage, unsigned long headoffset,
+		    struct page *tailpage, unsigned long tailoffset);
+
 #endif /* _NET_SUNRPC_SUNRPC_H */
 

net/sunrpc/svc_xprt.c

@@ -160,6 +160,7 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
 	mutex_init(&xprt->xpt_mutex);
 	spin_lock_init(&xprt->xpt_lock);
 	set_bit(XPT_BUSY, &xprt->xpt_flags);
+	rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending");
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
@@ -710,10 +711,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	spin_unlock_bh(&pool->sp_lock);
 
 	len = 0;
-	if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
-		dprintk("svc_recv: found XPT_CLOSE\n");
-		svc_delete_xprt(xprt);
-	} else if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
+	if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
 		struct svc_xprt *newxpt;
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt) {
@@ -739,7 +737,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 			svc_xprt_received(newxpt);
 		}
 		svc_xprt_received(xprt);
-	} else {
+	} else if (!test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
 			rqstp, pool->sp_id, xprt,
 			atomic_read(&xprt->xpt_ref.refcount));
@@ -752,6 +750,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		dprintk("svc: got len=%d\n", len);
 	}
 
+	if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
+		dprintk("svc_recv: found XPT_CLOSE\n");
+		svc_delete_xprt(xprt);
+	}
+
 	/* No data, incomplete (TCP) read, or accept() */
 	if (len == 0 || len == -EAGAIN) {
 		rqstp->rq_res.len = 0;
@@ -808,6 +811,7 @@ int svc_send(struct svc_rqst *rqstp)
 	else
 		len = xprt->xpt_ops->xpo_sendto(rqstp);
 	mutex_unlock(&xprt->xpt_mutex);
+	rpc_wake_up(&xprt->xpt_bc_pending);
 	svc_xprt_release(rqstp);
 
 	if (len == -ECONNREFUSED || len == -ENOTCONN || len == -EAGAIN)
@@ -1166,11 +1170,6 @@ static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos)
 
 	dprintk("svc_pool_stats_start, *pidx=%u\n", pidx);
 
-	lock_kernel();
-	/* bump up the pseudo refcount while traversing */
-	svc_get(serv);
-	unlock_kernel();
-
 	if (!pidx)
 		return SEQ_START_TOKEN;
 	return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]);
@@ -1198,12 +1197,6 @@ static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos)
 
 static void svc_pool_stats_stop(struct seq_file *m, void *p)
 {
-	struct svc_serv *serv = m->private;
-
-	lock_kernel();
-	/* this function really, really should have been called svc_put() */
-	svc_destroy(serv);
-	unlock_kernel();
 }
 
 static int svc_pool_stats_show(struct seq_file *m, void *p)

net/sunrpc/svcauth_unix.c

@@ -668,6 +668,7 @@ static int unix_gid_find(uid_t uid, struct group_info **gip,
 	case 0:
 		*gip = ug->gi;
 		get_group_info(*gip);
+		cache_put(&ug->h, &unix_gid_cache);
 		return 0;
 	default:
 		return -EAGAIN;

net/sunrpc/xprt.c

@@ -832,6 +832,11 @@ static void xprt_timer(struct rpc_task *task)
 	spin_unlock_bh(&xprt->transport_lock);
 }
 
+static inline int xprt_has_timer(struct rpc_xprt *xprt)
+{
+	return xprt->idle_timeout != 0;
+}
+
 /**
  * xprt_prepare_transmit - reserve the transport before sending a request
  * @task: RPC task about to send a request
@@ -1013,7 +1018,7 @@ void xprt_release(struct rpc_task *task)
 	if (!list_empty(&req->rq_list))
 		list_del(&req->rq_list);
 	xprt->last_used = jiffies;
-	if (list_empty(&xprt->recv))
+	if (list_empty(&xprt->recv) && xprt_has_timer(xprt))
 		mod_timer(&xprt->timer,
 				xprt->last_used + xprt->idle_timeout);
 	spin_unlock_bh(&xprt->transport_lock);
@@ -1082,8 +1087,11 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
 #endif /* CONFIG_NFS_V4_1 */
 
 	INIT_WORK(&xprt->task_cleanup, xprt_autoclose);
-	setup_timer(&xprt->timer, xprt_init_autodisconnect,
-			(unsigned long)xprt);
+	if (xprt_has_timer(xprt))
+		setup_timer(&xprt->timer, xprt_init_autodisconnect,
+			    (unsigned long)xprt);
+	else
+		init_timer(&xprt->timer);
 	xprt->last_used = jiffies;
 	xprt->cwnd = RPC_INITCWND;
 	xprt->bind_index = 0;
@@ -1102,7 +1110,6 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
 
 	dprintk("RPC:       created transport %p with %u slots\n", xprt,
 			xprt->max_reqs);
-
 	return xprt;
 }
 

net/sunrpc/xprtrdma/svc_rdma_transport.c

@@ -730,12 +730,12 @@ static struct svc_rdma_fastreg_mr *rdma_alloc_frmr(struct svcxprt_rdma *xprt)
 		goto err;
 
 	mr = ib_alloc_fast_reg_mr(xprt->sc_pd, RPCSVC_MAXPAGES);
-	if (!mr)
+	if (IS_ERR(mr))
 		goto err_free_frmr;
 
 	pl = ib_alloc_fast_reg_page_list(xprt->sc_cm_id->device,
 					 RPCSVC_MAXPAGES);
-	if (!pl)
+	if (IS_ERR(pl))
 		goto err_free_mr;
 
 	frmr->mr = mr;

net/sunrpc/xprtsock.c

@@ -32,6 +32,7 @@
 #include <linux/tcp.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/xprtsock.h>
 #include <linux/file.h>
 #ifdef CONFIG_NFS_V4_1
@@ -43,6 +44,7 @@
 #include <net/udp.h>
 #include <net/tcp.h>
 
+#include "sunrpc.h"
 /*
  * xprtsock tunables
  */
@@ -2098,6 +2100,134 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 			xprt->stat.bklog_u);
 }
 
+/*
+ * Allocate a bunch of pages for a scratch buffer for the rpc code. The reason
+ * we allocate pages instead doing a kmalloc like rpc_malloc is because we want
+ * to use the server side send routines.
+ */
+void *bc_malloc(struct rpc_task *task, size_t size)
+{
+	struct page *page;
+	struct rpc_buffer *buf;
+
+	BUG_ON(size > PAGE_SIZE - sizeof(struct rpc_buffer));
+	page = alloc_page(GFP_KERNEL);
+
+	if (!page)
+		return NULL;
+
+	buf = page_address(page);
+	buf->len = PAGE_SIZE;
+
+	return buf->data;
+}
+
+/*
+ * Free the space allocated in the bc_alloc routine
+ */
+void bc_free(void *buffer)
+{
+	struct rpc_buffer *buf;
+
+	if (!buffer)
+		return;
+
+	buf = container_of(buffer, struct rpc_buffer, data);
+	free_page((unsigned long)buf);
+}
+
+/*
+ * Use the svc_sock to send the callback. Must be called with svsk->sk_mutex
+ * held. Borrows heavily from svc_tcp_sendto and xs_tcp_send_request.
+ */
+static int bc_sendto(struct rpc_rqst *req)
+{
+	int len;
+	struct xdr_buf *xbufp = &req->rq_snd_buf;
+	struct rpc_xprt *xprt = req->rq_xprt;
+	struct sock_xprt *transport =
+				container_of(xprt, struct sock_xprt, xprt);
+	struct socket *sock = transport->sock;
+	unsigned long headoff;
+	unsigned long tailoff;
+
+	/*
+	 * Set up the rpc header and record marker stuff
+	 */
+	xs_encode_tcp_record_marker(xbufp);
+
+	tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK;
+	headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK;
+	len = svc_send_common(sock, xbufp,
+			      virt_to_page(xbufp->head[0].iov_base), headoff,
+			      xbufp->tail[0].iov_base, tailoff);
+
+	if (len != xbufp->len) {
+		printk(KERN_NOTICE "Error sending entire callback!\n");
+		len = -EAGAIN;
+	}
+
+	return len;
+}
+
+/*
+ * The send routine. Borrows from svc_send
+ */
+static int bc_send_request(struct rpc_task *task)
+{
+	struct rpc_rqst *req = task->tk_rqstp;
+	struct svc_xprt	*xprt;
+	struct svc_sock         *svsk;
+	u32                     len;
+
+	dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid));
+	/*
+	 * Get the server socket associated with this callback xprt
+	 */
+	xprt = req->rq_xprt->bc_xprt;
+	svsk = container_of(xprt, struct svc_sock, sk_xprt);
+
+	/*
+	 * Grab the mutex to serialize data as the connection is shared
+	 * with the fore channel
+	 */
+	if (!mutex_trylock(&xprt->xpt_mutex)) {
+		rpc_sleep_on(&xprt->xpt_bc_pending, task, NULL);
+		if (!mutex_trylock(&xprt->xpt_mutex))
+			return -EAGAIN;
+		rpc_wake_up_queued_task(&xprt->xpt_bc_pending, task);
+	}
+	if (test_bit(XPT_DEAD, &xprt->xpt_flags))
+		len = -ENOTCONN;
+	else
+		len = bc_sendto(req);
+	mutex_unlock(&xprt->xpt_mutex);
+
+	if (len > 0)
+		len = 0;
+
+	return len;
+}
+
+/*
+ * The close routine. Since this is client initiated, we do nothing
+ */
+
+static void bc_close(struct rpc_xprt *xprt)
+{
+	return;
+}
+
+/*
+ * The xprt destroy routine. Again, because this connection is client
+ * initiated, we do nothing
+ */
+
+static void bc_destroy(struct rpc_xprt *xprt)
+{
+	return;
+}
+
 static struct rpc_xprt_ops xs_udp_ops = {
 	.set_buffer_size	= xs_udp_set_buffer_size,
 	.reserve_xprt		= xprt_reserve_xprt_cong,
@@ -2134,6 +2264,22 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 	.print_stats		= xs_tcp_print_stats,
 };
 
+/*
+ * The rpc_xprt_ops for the server backchannel
+ */
+
+static struct rpc_xprt_ops bc_tcp_ops = {
+	.reserve_xprt		= xprt_reserve_xprt,
+	.release_xprt		= xprt_release_xprt,
+	.buf_alloc		= bc_malloc,
+	.buf_free		= bc_free,
+	.send_request		= bc_send_request,
+	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
+	.close			= bc_close,
+	.destroy		= bc_destroy,
+	.print_stats		= xs_tcp_print_stats,
+};
+
 static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
 				      unsigned int slot_table_size)
 {
@@ -2322,11 +2468,93 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
 	return ERR_PTR(-EINVAL);
 }
 
+/**
+ * xs_setup_bc_tcp - Set up transport to use a TCP backchannel socket
+ * @args: rpc transport creation arguments
+ *
+ */
+static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
+{
+	struct sockaddr *addr = args->dstaddr;
+	struct rpc_xprt *xprt;
+	struct sock_xprt *transport;
+	struct svc_sock *bc_sock;
+
+	if (!args->bc_xprt)
+		ERR_PTR(-EINVAL);
+
+	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries);
+	if (IS_ERR(xprt))
+		return xprt;
+	transport = container_of(xprt, struct sock_xprt, xprt);
+
+	xprt->prot = IPPROTO_TCP;
+	xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
+	xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
+	xprt->timeout = &xs_tcp_default_timeout;
+
+	/* backchannel */
+	xprt_set_bound(xprt);
+	xprt->bind_timeout = 0;
+	xprt->connect_timeout = 0;
+	xprt->reestablish_timeout = 0;
+	xprt->idle_timeout = 0;
+
+	/*
+	 * The backchannel uses the same socket connection as the
+	 * forechannel
+	 */
+	xprt->bc_xprt = args->bc_xprt;
+	bc_sock = container_of(args->bc_xprt, struct svc_sock, sk_xprt);
+	bc_sock->sk_bc_xprt = xprt;
+	transport->sock = bc_sock->sk_sock;
+	transport->inet = bc_sock->sk_sk;
+
+	xprt->ops = &bc_tcp_ops;
+
+	switch (addr->sa_family) {
+	case AF_INET:
+		xs_format_peer_addresses(xprt, "tcp",
+					 RPCBIND_NETID_TCP);
+		break;
+	case AF_INET6:
+		xs_format_peer_addresses(xprt, "tcp",
+				   RPCBIND_NETID_TCP6);
+		break;
+	default:
+		kfree(xprt);
+		return ERR_PTR(-EAFNOSUPPORT);
+	}
+
+	if (xprt_bound(xprt))
+		dprintk("RPC:       set up xprt to %s (port %s) via %s\n",
+				xprt->address_strings[RPC_DISPLAY_ADDR],
+				xprt->address_strings[RPC_DISPLAY_PORT],
+				xprt->address_strings[RPC_DISPLAY_PROTO]);
+	else
+		dprintk("RPC:       set up xprt to %s (autobind) via %s\n",
+				xprt->address_strings[RPC_DISPLAY_ADDR],
+				xprt->address_strings[RPC_DISPLAY_PROTO]);
+
+	/*
+	 * Since we don't want connections for the backchannel, we set
+	 * the xprt status to connected
+	 */
+	xprt_set_connected(xprt);
+
+
+	if (try_module_get(THIS_MODULE))
+		return xprt;
+	kfree(xprt->slot);
+	kfree(xprt);
+	return ERR_PTR(-EINVAL);
+}
+
 static struct xprt_class	xs_udp_transport = {
 	.list		= LIST_HEAD_INIT(xs_udp_transport.list),
 	.name		= "udp",
 	.owner		= THIS_MODULE,
-	.ident		= IPPROTO_UDP,
+	.ident		= XPRT_TRANSPORT_UDP,
 	.setup		= xs_setup_udp,
 };
 
@@ -2334,10 +2562,18 @@ static struct xprt_class	xs_tcp_transport = {
 	.list		= LIST_HEAD_INIT(xs_tcp_transport.list),
 	.name		= "tcp",
 	.owner		= THIS_MODULE,
-	.ident		= IPPROTO_TCP,
+	.ident		= XPRT_TRANSPORT_TCP,
 	.setup		= xs_setup_tcp,
 };
 
+static struct xprt_class	xs_bc_tcp_transport = {
+	.list		= LIST_HEAD_INIT(xs_bc_tcp_transport.list),
+	.name		= "tcp NFSv4.1 backchannel",
+	.owner		= THIS_MODULE,
+	.ident		= XPRT_TRANSPORT_BC_TCP,
+	.setup		= xs_setup_bc_tcp,
+};
+
 /**
  * init_socket_xprt - set up xprtsock's sysctls, register with RPC client
  *
@@ -2351,6 +2587,7 @@ int init_socket_xprt(void)
 
 	xprt_register_transport(&xs_udp_transport);
 	xprt_register_transport(&xs_tcp_transport);
+	xprt_register_transport(&xs_bc_tcp_transport);
 
 	return 0;
 }
@@ -2370,6 +2607,7 @@ void cleanup_socket_xprt(void)
 
 	xprt_unregister_transport(&xs_udp_transport);
 	xprt_unregister_transport(&xs_tcp_transport);
+	xprt_unregister_transport(&xs_bc_tcp_transport);
 }
 
 static int param_set_uint_minmax(const char *val, struct kernel_param *kp,