Merge branch 'nfs-for-2.6.36' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* 'nfs-for-2.6.36' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (42 commits)
  NFS: NFSv4.1 is no longer a "developer only" feature
  NFS: NFS_V4 is no longer an EXPERIMENTAL feature
  NFS: Fix /proc/mount for legacy binary interface
  NFS: Fix the locking in nfs4_callback_getattr
  SUNRPC: Defer deleting the security context until gss_do_free_ctx()
  SUNRPC: prevent task_cleanup running on freed xprt
  SUNRPC: Reduce asynchronous RPC task stack usage
  SUNRPC: Move the bound cred to struct rpc_rqst
  SUNRPC: Clean up of rpc_bindcred()
  SUNRPC: Move remaining RPC client related task initialisation into clnt.c
  SUNRPC: Ensure that rpc_exit() always wakes up a sleeping task
  SUNRPC: Make the credential cache hashtable size configurable
  SUNRPC: Store the hashtable size in struct rpc_cred_cache
  NFS: Ensure the AUTH_UNIX credcache is allocated dynamically
  NFS: Fix the NFS users of rpc_restart_call()
  SUNRPC: The function rpc_restart_call() should return success/failure
  NFSv4: Get rid of the bogus RPC_ASSASSINATED(task) checks
  NFSv4: Clean up the process of renewing the NFSv4 lease
  NFSv4.1: Handle NFS4ERR_DELAY on SEQUENCE correctly
  NFS: nfs_rename() should not have to flush out writebacks
  ...

fs/nfs/Kconfig

@@ -61,8 +61,8 @@ config NFS_V3_ACL
 	  If unsure, say N.
 
 config NFS_V4
-	bool "NFS client support for NFS version 4 (EXPERIMENTAL)"
-	depends on NFS_FS && EXPERIMENTAL
+	bool "NFS client support for NFS version 4"
+	depends on NFS_FS
 	select RPCSEC_GSS_KRB5
 	help
 	  This option enables support for version 4 of the NFS protocol
@@ -72,16 +72,16 @@ config NFS_V4
 	  space programs which can be found in the Linux nfs-utils package,
 	  available from http://linux-nfs.org/.
 
-	  If unsure, say N.
+	  If unsure, say Y.
 
 config NFS_V4_1
-	bool "NFS client support for NFSv4.1 (DEVELOPER ONLY)"
+	bool "NFS client support for NFSv4.1 (EXPERIMENTAL)"
 	depends on NFS_V4 && EXPERIMENTAL
 	help
 	  This option enables support for minor version 1 of the NFSv4 protocol
 	  (draft-ietf-nfsv4-minorversion1) in the kernel's NFS client.
 
-	  Unless you're an NFS developer, say N.
+	  If unsure, say N.
 
 config ROOT_NFS
 	bool "Root file system on NFS"

fs/nfs/callback_proc.c

@@ -37,8 +37,8 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *
 	if (inode == NULL)
 		goto out_putclient;
 	nfsi = NFS_I(inode);
-	down_read(&nfsi->rwsem);
-	delegation = nfsi->delegation;
+	rcu_read_lock();
+	delegation = rcu_dereference(nfsi->delegation);
 	if (delegation == NULL || (delegation->type & FMODE_WRITE) == 0)
 		goto out_iput;
 	res->size = i_size_read(inode);
@@ -53,7 +53,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *
 		args->bitmap[1];
 	res->status = 0;
 out_iput:
-	up_read(&nfsi->rwsem);
+	rcu_read_unlock();
 	iput(inode);
 out_putclient:
 	nfs_put_client(clp);
@@ -62,16 +62,6 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_getattrres *
 	return res->status;
 }
 
-static int (*nfs_validate_delegation_stateid(struct nfs_client *clp))(struct nfs_delegation *, const nfs4_stateid *)
-{
-#if defined(CONFIG_NFS_V4_1)
-	if (clp->cl_minorversion > 0)
-		return nfs41_validate_delegation_stateid;
-#endif
-	return nfs4_validate_delegation_stateid;
-}
-
-
 __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 {
 	struct nfs_client *clp;
@@ -92,8 +82,7 @@ __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy)
 		inode = nfs_delegation_find_inode(clp, &args->fh);
 		if (inode != NULL) {
 			/* Set up a helper thread to actually return the delegation */
-			switch (nfs_async_inode_return_delegation(inode, &args->stateid,
-								  nfs_validate_delegation_stateid(clp))) {
+			switch (nfs_async_inode_return_delegation(inode, &args->stateid)) {
 				case 0:
 					res = 0;
 					break;

fs/nfs/client.c

@@ -150,6 +150,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_boot_time = CURRENT_TIME;
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
 	clp->cl_minorversion = cl_init->minorversion;
+	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
 #endif
 	cred = rpc_lookup_machine_cred();
 	if (!IS_ERR(cred))
@@ -178,7 +179,7 @@ static void nfs4_clear_client_minor_version(struct nfs_client *clp)
 		clp->cl_session = NULL;
 	}
 
-	clp->cl_call_sync = _nfs4_call_sync;
+	clp->cl_mvops = nfs_v4_minor_ops[0];
 #endif /* CONFIG_NFS_V4_1 */
 }
 
@@ -188,7 +189,7 @@ static void nfs4_clear_client_minor_version(struct nfs_client *clp)
 static void nfs4_destroy_callback(struct nfs_client *clp)
 {
 	if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state))
-		nfs_callback_down(clp->cl_minorversion);
+		nfs_callback_down(clp->cl_mvops->minor_version);
 }
 
 static void nfs4_shutdown_client(struct nfs_client *clp)
@@ -1126,7 +1127,7 @@ static int nfs4_init_callback(struct nfs_client *clp)
 				return error;
 		}
 
-		error = nfs_callback_up(clp->cl_minorversion,
+		error = nfs_callback_up(clp->cl_mvops->minor_version,
 					clp->cl_rpcclient->cl_xprt);
 		if (error < 0) {
 			dprintk("%s: failed to start callback. Error = %d\n",
@@ -1143,10 +1144,8 @@ static int nfs4_init_callback(struct nfs_client *clp)
  */
 static int nfs4_init_client_minor_version(struct nfs_client *clp)
 {
-	clp->cl_call_sync = _nfs4_call_sync;
-
 #if defined(CONFIG_NFS_V4_1)
-	if (clp->cl_minorversion) {
+	if (clp->cl_mvops->minor_version) {
 		struct nfs4_session *session = NULL;
 		/*
 		 * Create the session and mark it expired.
@@ -1158,7 +1157,13 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
 			return -ENOMEM;
 
 		clp->cl_session = session;
-		clp->cl_call_sync = _nfs4_call_sync_session;
+		/*
+		 * The create session reply races with the server back
+		 * channel probe. Mark the client NFS_CS_SESSION_INITING
+		 * so that the client back channel can find the
+		 * nfs_client struct
+		 */
+		clp->cl_cons_state = NFS_CS_SESSION_INITING;
 	}
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -1454,7 +1459,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 				data->authflavor,
 				parent_server->client->cl_xprt->prot,
 				parent_server->client->cl_timeout,
-				parent_client->cl_minorversion);
+				parent_client->cl_mvops->minor_version);
 	if (error < 0)
 		goto error;
 

fs/nfs/delegation.c

@@ -268,14 +268,6 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	return status;
 }
 
-/* Sync all data to disk upon delegation return */
-static void nfs_msync_inode(struct inode *inode)
-{
-	filemap_fdatawrite(inode->i_mapping);
-	nfs_wb_all(inode);
-	filemap_fdatawait(inode->i_mapping);
-}
-
 /*
  * Basic procedure for returning a delegation to the server
  */
@@ -367,7 +359,7 @@ int nfs_inode_return_delegation(struct inode *inode)
 		delegation = nfs_detach_delegation_locked(nfsi, NULL, clp);
 		spin_unlock(&clp->cl_lock);
 		if (delegation != NULL) {
-			nfs_msync_inode(inode);
+			nfs_wb_all(inode);
 			err = __nfs_inode_return_delegation(inode, delegation, 1);
 		}
 	}
@@ -471,9 +463,7 @@ void nfs_expire_unreferenced_delegations(struct nfs_client *clp)
 /*
  * Asynchronous delegation recall!
  */
-int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid,
-				      int (*validate_stateid)(struct nfs_delegation *delegation,
-							      const nfs4_stateid *stateid))
+int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid)
 {
 	struct nfs_client *clp = NFS_SERVER(inode)->nfs_client;
 	struct nfs_delegation *delegation;
@@ -481,7 +471,7 @@ int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *s
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
 
-	if (!validate_stateid(delegation, stateid)) {
+	if (!clp->cl_mvops->validate_stateid(delegation, stateid)) {
 		rcu_read_unlock();
 		return -ENOENT;
 	}

fs/nfs/delegation.h

@@ -34,9 +34,7 @@ enum {
 int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
 void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res);
 int nfs_inode_return_delegation(struct inode *inode);
-int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid,
-				      int (*validate_stateid)(struct nfs_delegation *delegation,
-							      const nfs4_stateid *stateid));
+int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 void nfs_inode_return_delegation_noreclaim(struct inode *inode);
 
 struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);

fs/nfs/dir.c

@@ -1652,16 +1652,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
-	/*
-	 * ... prune child dentries and writebacks if needed.
-	 */
-	if (atomic_read(&old_dentry->d_count) > 1) {
-		if (S_ISREG(old_inode->i_mode))
-			nfs_wb_all(old_inode);
-		shrink_dcache_parent(old_dentry);
-	}
 	nfs_inode_return_delegation(old_inode);
-
 	if (new_inode != NULL)
 		nfs_inode_return_delegation(new_inode);
 

fs/nfs/direct.c

@@ -69,6 +69,7 @@ struct nfs_direct_req {
 
 	/* I/O parameters */
 	struct nfs_open_context	*ctx;		/* file open context info */
+	struct nfs_lock_context *l_ctx;		/* Lock context info */
 	struct kiocb *		iocb;		/* controlling i/o request */
 	struct inode *		inode;		/* target file of i/o */
 
@@ -160,6 +161,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 	INIT_LIST_HEAD(&dreq->rewrite_list);
 	dreq->iocb = NULL;
 	dreq->ctx = NULL;
+	dreq->l_ctx = NULL;
 	spin_lock_init(&dreq->lock);
 	atomic_set(&dreq->io_count, 0);
 	dreq->count = 0;
@@ -173,6 +175,8 @@ static void nfs_direct_req_free(struct kref *kref)
 {
 	struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref);
 
+	if (dreq->l_ctx != NULL)
+		nfs_put_lock_context(dreq->l_ctx);
 	if (dreq->ctx != NULL)
 		put_nfs_open_context(dreq->ctx);
 	kmem_cache_free(nfs_direct_cachep, dreq);
@@ -336,6 +340,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
 		data->cred = msg.rpc_cred;
 		data->args.fh = NFS_FH(inode);
 		data->args.context = ctx;
+		data->args.lock_context = dreq->l_ctx;
 		data->args.offset = pos;
 		data->args.pgbase = pgbase;
 		data->args.pages = data->pagevec;
@@ -416,24 +421,28 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
 			       unsigned long nr_segs, loff_t pos)
 {
-	ssize_t result = 0;
+	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct nfs_direct_req *dreq;
 
 	dreq = nfs_direct_req_alloc();
-	if (!dreq)
-		return -ENOMEM;
+	if (dreq == NULL)
+		goto out;
 
 	dreq->inode = inode;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
+	dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
+	if (dreq->l_ctx == NULL)
+		goto out_release;
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
 	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
 	if (!result)
 		result = nfs_direct_wait(dreq);
+out_release:
 	nfs_direct_req_release(dreq);
-
+out:
 	return result;
 }
 
@@ -574,6 +583,7 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq)
 	data->args.offset = 0;
 	data->args.count = 0;
 	data->args.context = dreq->ctx;
+	data->args.lock_context = dreq->l_ctx;
 	data->res.count = 0;
 	data->res.fattr = &data->fattr;
 	data->res.verf = &data->verf;
@@ -761,6 +771,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
 		data->cred = msg.rpc_cred;
 		data->args.fh = NFS_FH(inode);
 		data->args.context = ctx;
+		data->args.lock_context = dreq->l_ctx;
 		data->args.offset = pos;
 		data->args.pgbase = pgbase;
 		data->args.pages = data->pagevec;
@@ -845,7 +856,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos,
 				size_t count)
 {
-	ssize_t result = 0;
+	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct nfs_direct_req *dreq;
 	size_t wsize = NFS_SERVER(inode)->wsize;
@@ -853,7 +864,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 	dreq = nfs_direct_req_alloc();
 	if (!dreq)
-		return -ENOMEM;
+		goto out;
 	nfs_alloc_commit_data(dreq);
 
 	if (dreq->commit_data == NULL || count < wsize)
@@ -861,14 +872,18 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 	dreq->inode = inode;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
+	dreq->l_ctx = nfs_get_lock_context(dreq->ctx);
+	if (dreq->l_ctx != NULL)
+		goto out_release;
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
 	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, sync);
 	if (!result)
 		result = nfs_direct_wait(dreq);
+out_release:
 	nfs_direct_req_release(dreq);
-
+out:
 	return result;
 }
 

fs/nfs/file.c

@@ -202,38 +202,12 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 	return loff;
 }
 
-/*
- * Helper for nfs_file_flush() and nfs_file_fsync()
- *
- * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
- * disk, but it retrieves and clears ctx->error after synching, despite
- * the two being set at the same time in nfs_context_set_write_error().
- * This is because the former is used to notify the _next_ call to
- * nfs_file_write() that a write error occured, and hence cause it to
- * fall back to doing a synchronous write.
- */
-static int nfs_do_fsync(struct nfs_open_context *ctx, struct inode *inode)
-{
-	int have_error, status;
-	int ret = 0;
-
-	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
-	status = nfs_wb_all(inode);
-	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
-	if (have_error)
-		ret = xchg(&ctx->error, 0);
-	if (!ret)
-		ret = status;
-	return ret;
-}
-
 /*
  * Flush all dirty pages, and check for write errors.
  */
 static int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
-	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct dentry	*dentry = file->f_path.dentry;
 	struct inode	*inode = dentry->d_inode;
 
@@ -246,7 +220,7 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 		return 0;
 
 	/* Flush writes to the server and return any errors */
-	return nfs_do_fsync(ctx, inode);
+	return vfs_fsync(file, 0);
 }
 
 static ssize_t
@@ -321,6 +295,13 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
  * Flush any dirty pages for this process, and check for write errors.
  * The return status from this call provides a reliable indication of
  * whether any write errors occurred for this process.
+ *
+ * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
+ * disk, but it retrieves and clears ctx->error after synching, despite
+ * the two being set at the same time in nfs_context_set_write_error().
+ * This is because the former is used to notify the _next_ call to
+ * nfs_file_write() that a write error occured, and hence cause it to
+ * fall back to doing a synchronous write.
  */
 static int
 nfs_file_fsync(struct file *file, int datasync)
@@ -328,13 +309,23 @@ nfs_file_fsync(struct file *file, int datasync)
 	struct dentry *dentry = file->f_path.dentry;
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode *inode = dentry->d_inode;
+	int have_error, status;
+	int ret = 0;
+
 
 	dprintk("NFS: fsync file(%s/%s) datasync %d\n",
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			datasync);
 
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
-	return nfs_do_fsync(ctx, inode);
+	have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
+	status = nfs_commit_inode(inode, FLUSH_SYNC);
+	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
+	if (have_error)
+		ret = xchg(&ctx->error, 0);
+	if (!ret)
+		ret = status;
+	return ret;
 }
 
 /*
@@ -648,7 +639,7 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 
 	/* Return error values for O_DSYNC and IS_SYNC() */
 	if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
-		int err = nfs_do_fsync(nfs_file_open_context(iocb->ki_filp), inode);
+		int err = vfs_fsync(iocb->ki_filp, 0);
 		if (err < 0)
 			result = err;
 	}
@@ -684,7 +675,7 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
 		written = ret;
 
 	if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
-		int err = nfs_do_fsync(nfs_file_open_context(filp), inode);
+		int err = vfs_fsync(filp, 0);
 		if (err < 0)
 			ret = err;
 	}

fs/nfs/inode.c

@@ -413,10 +413,8 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 		return 0;
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode)) {
-		filemap_write_and_wait(inode->i_mapping);
+	if (S_ISREG(inode->i_mode))
 		nfs_wb_all(inode);
-	}
 
 	fattr = nfs_alloc_fattr();
 	if (fattr == NULL)
@@ -530,6 +528,68 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	return err;
 }
 
+static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
+{
+	atomic_set(&l_ctx->count, 1);
+	l_ctx->lockowner = current->files;
+	l_ctx->pid = current->tgid;
+	INIT_LIST_HEAD(&l_ctx->list);
+}
+
+static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
+{
+	struct nfs_lock_context *pos;
+
+	list_for_each_entry(pos, &ctx->lock_context.list, list) {
+		if (pos->lockowner != current->files)
+			continue;
+		if (pos->pid != current->tgid)
+			continue;
+		atomic_inc(&pos->count);
+		return pos;
+	}
+	return NULL;
+}
+
+struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx)
+{
+	struct nfs_lock_context *res, *new = NULL;
+	struct inode *inode = ctx->path.dentry->d_inode;
+
+	spin_lock(&inode->i_lock);
+	res = __nfs_find_lock_context(ctx);
+	if (res == NULL) {
+		spin_unlock(&inode->i_lock);
+		new = kmalloc(sizeof(*new), GFP_KERNEL);
+		if (new == NULL)
+			return NULL;
+		nfs_init_lock_context(new);
+		spin_lock(&inode->i_lock);
+		res = __nfs_find_lock_context(ctx);
+		if (res == NULL) {
+			list_add_tail(&new->list, &ctx->lock_context.list);
+			new->open_context = ctx;
+			res = new;
+			new = NULL;
+		}
+	}
+	spin_unlock(&inode->i_lock);
+	kfree(new);
+	return res;
+}
+
+void nfs_put_lock_context(struct nfs_lock_context *l_ctx)
+{
+	struct nfs_open_context *ctx = l_ctx->open_context;
+	struct inode *inode = ctx->path.dentry->d_inode;
+
+	if (!atomic_dec_and_lock(&l_ctx->count, &inode->i_lock))
+		return;
+	list_del(&l_ctx->list);
+	spin_unlock(&inode->i_lock);
+	kfree(l_ctx);
+}
+
 /**
  * nfs_close_context - Common close_context() routine NFSv2/v3
  * @ctx: pointer to context
@@ -566,11 +626,11 @@ static struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct
 		path_get(&ctx->path);
 		ctx->cred = get_rpccred(cred);
 		ctx->state = NULL;
-		ctx->lockowner = current->files;
 		ctx->flags = 0;
 		ctx->error = 0;
 		ctx->dir_cookie = 0;
-		atomic_set(&ctx->count, 1);
+		nfs_init_lock_context(&ctx->lock_context);
+		ctx->lock_context.open_context = ctx;
 	}
 	return ctx;
 }
@@ -578,7 +638,7 @@ static struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct
 struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
 {
 	if (ctx != NULL)
-		atomic_inc(&ctx->count);
+		atomic_inc(&ctx->lock_context.count);
 	return ctx;
 }
 
@@ -586,7 +646,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 {
 	struct inode *inode = ctx->path.dentry->d_inode;
 
-	if (!atomic_dec_and_lock(&ctx->count, &inode->i_lock))
+	if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock))
 		return;
 	list_del(&ctx->list);
 	spin_unlock(&inode->i_lock);

fs/nfs/internal.h

@@ -370,10 +370,9 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
  * Helper for restarting RPC calls in the possible presence of NFSv4.1
  * sessions.
  */
-static inline void nfs_restart_rpc(struct rpc_task *task, const struct nfs_client *clp)
+static inline int nfs_restart_rpc(struct rpc_task *task, const struct nfs_client *clp)
 {
 	if (nfs4_has_session(clp))
-		rpc_restart_call_prepare(task);
-	else
-		rpc_restart_call(task);
+		return rpc_restart_call_prepare(task);
+	return rpc_restart_call(task);
 }

fs/nfs/nfs2xdr.c

@@ -233,7 +233,7 @@ nfs_xdr_removeargs(struct rpc_rqst *req, __be32 *p, const struct nfs_removeargs
 static int
 nfs_xdr_readargs(struct rpc_rqst *req, __be32 *p, struct nfs_readargs *args)
 {
-	struct rpc_auth	*auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth	*auth = req->rq_cred->cr_auth;
 	unsigned int replen;
 	u32 offset = (u32)args->offset;
 	u32 count = args->count;
@@ -393,8 +393,7 @@ nfs_xdr_symlinkargs(struct rpc_rqst *req, __be32 *p, struct nfs_symlinkargs *arg
 static int
 nfs_xdr_readdirargs(struct rpc_rqst *req, __be32 *p, struct nfs_readdirargs *args)
 {
-	struct rpc_task	*task = req->rq_task;
-	struct rpc_auth	*auth = task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth	*auth = req->rq_cred->cr_auth;
 	unsigned int replen;
 	u32 count = args->count;
 
@@ -575,7 +574,7 @@ nfs_xdr_diropres(struct rpc_rqst *req, __be32 *p, struct nfs_diropok *res)
 static int
 nfs_xdr_readlinkargs(struct rpc_rqst *req, __be32 *p, struct nfs_readlinkargs *args)
 {
-	struct rpc_auth	*auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth	*auth = req->rq_cred->cr_auth;
 	unsigned int replen;
 
 	p = xdr_encode_fhandle(p, args->fh);

fs/nfs/nfs3xdr.c

@@ -330,7 +330,7 @@ nfs3_xdr_accessargs(struct rpc_rqst *req, __be32 *p, struct nfs3_accessargs *arg
 static int
 nfs3_xdr_readargs(struct rpc_rqst *req, __be32 *p, struct nfs_readargs *args)
 {
-	struct rpc_auth	*auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth	*auth = req->rq_cred->cr_auth;
 	unsigned int replen;
 	u32 count = args->count;
 
@@ -471,7 +471,7 @@ nfs3_xdr_linkargs(struct rpc_rqst *req, __be32 *p, struct nfs3_linkargs *args)
 static int
 nfs3_xdr_readdirargs(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirargs *args)
 {
-	struct rpc_auth	*auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth	*auth = req->rq_cred->cr_auth;
 	unsigned int replen;
 	u32 count = args->count;
 
@@ -675,7 +675,7 @@ static int
 nfs3_xdr_getaclargs(struct rpc_rqst *req, __be32 *p,
 		    struct nfs3_getaclargs *args)
 {
-	struct rpc_auth	*auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth	*auth = req->rq_cred->cr_auth;
 	unsigned int replen;
 
 	p = xdr_encode_fhandle(p, args->fh);
@@ -802,7 +802,7 @@ nfs3_xdr_accessres(struct rpc_rqst *req, __be32 *p, struct nfs3_accessres *res)
 static int
 nfs3_xdr_readlinkargs(struct rpc_rqst *req, __be32 *p, struct nfs3_readlinkargs *args)
 {
-	struct rpc_auth	*auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth	*auth = req->rq_cred->cr_auth;
 	unsigned int replen;
 
 	p = xdr_encode_fhandle(p, args->fh);

fs/nfs/nfs4_fs.h

@@ -45,10 +45,29 @@ enum nfs4_client_state {
 	NFS4CLNT_RECLAIM_NOGRACE,
 	NFS4CLNT_DELEGRETURN,
 	NFS4CLNT_SESSION_RESET,
-	NFS4CLNT_SESSION_DRAINING,
 	NFS4CLNT_RECALL_SLOT,
 };
 
+enum nfs4_session_state {
+	NFS4_SESSION_INITING,
+	NFS4_SESSION_DRAINING,
+};
+
+struct nfs4_minor_version_ops {
+	u32	minor_version;
+
+	int	(*call_sync)(struct nfs_server *server,
+			struct rpc_message *msg,
+			struct nfs4_sequence_args *args,
+			struct nfs4_sequence_res *res,
+			int cache_reply);
+	int	(*validate_stateid)(struct nfs_delegation *,
+			const nfs4_stateid *);
+	const struct nfs4_state_recovery_ops *reboot_recovery_ops;
+	const struct nfs4_state_recovery_ops *nograce_recovery_ops;
+	const struct nfs4_state_maintenance_ops *state_renewal_ops;
+};
+
 /*
  * struct rpc_sequence ensures that RPC calls are sent in the exact
  * order that they appear on the list.
@@ -89,7 +108,6 @@ struct nfs_unique_id {
  */
 struct nfs4_state_owner {
 	struct nfs_unique_id so_owner_id;
-	struct nfs_client    *so_client;
 	struct nfs_server    *so_server;
 	struct rb_node	     so_client_node;
 
@@ -99,7 +117,6 @@ struct nfs4_state_owner {
 	atomic_t	     so_count;
 	unsigned long	     so_flags;
 	struct list_head     so_states;
-	struct list_head     so_delegations;
 	struct nfs_seqid_counter so_seqid;
 	struct rpc_sequence  so_sequence;
 };
@@ -125,10 +142,20 @@ enum {
  * LOCK: one nfs4_state (LOCK) to hold the lock stateid nfs4_state(OPEN)
  */
 
+struct nfs4_lock_owner {
+	unsigned int lo_type;
+#define NFS4_ANY_LOCK_TYPE	(0U)
+#define NFS4_FLOCK_LOCK_TYPE	(1U << 0)
+#define NFS4_POSIX_LOCK_TYPE	(1U << 1)
+	union {
+		fl_owner_t posix_owner;
+		pid_t flock_owner;
+	} lo_u;
+};
+
 struct nfs4_lock_state {
 	struct list_head	ls_locks;	/* Other lock stateids */
 	struct nfs4_state *	ls_state;	/* Pointer to open state */
-	fl_owner_t		ls_owner;	/* POSIX lock owner */
 #define NFS_LOCK_INITIALIZED 1
 	int			ls_flags;
 	struct nfs_seqid_counter	ls_seqid;
@@ -136,6 +163,7 @@ struct nfs4_lock_state {
 	struct nfs_unique_id	ls_id;
 	nfs4_stateid		ls_stateid;
 	atomic_t		ls_count;
+	struct nfs4_lock_owner	ls_owner;
 };
 
 /* bits for nfs4_state->flags */
@@ -219,11 +247,15 @@ extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nam
 extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
 extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name,
 		struct nfs4_fs_locations *fs_locations, struct page *page);
+extern void nfs4_release_lockowner(const struct nfs4_lock_state *);
 
-extern struct nfs4_state_recovery_ops *nfs4_reboot_recovery_ops[];
-extern struct nfs4_state_recovery_ops *nfs4_nograce_recovery_ops[];
 #if defined(CONFIG_NFS_V4_1)
-extern int nfs4_setup_sequence(struct nfs_client *clp,
+static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
+{
+	return server->nfs_client->cl_session;
+}
+
+extern int nfs4_setup_sequence(const struct nfs_server *server,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		int cache_reply, struct rpc_task *task);
 extern void nfs4_destroy_session(struct nfs4_session *session);
@@ -234,7 +266,12 @@ extern int nfs4_init_session(struct nfs_server *server);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
 #else /* CONFIG_NFS_v4_1 */
-static inline int nfs4_setup_sequence(struct nfs_client *clp,
+static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
+{
+	return NULL;
+}
+
+static inline int nfs4_setup_sequence(const struct nfs_server *server,
 		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
 		int cache_reply, struct rpc_task *task)
 {
@@ -247,7 +284,7 @@ static inline int nfs4_init_session(struct nfs_server *server)
 }
 #endif /* CONFIG_NFS_V4_1 */
 
-extern struct nfs4_state_maintenance_ops *nfs4_state_renewal_ops[];
+extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[];
 
 extern const u32 nfs4_fattr_bitmap[2];
 extern const u32 nfs4_statfs_bitmap[2];
@@ -284,7 +321,7 @@ extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
 extern void nfs41_handle_recall_slot(struct nfs_client *clp);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
-extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t);
+extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t, pid_t);
 
 extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
 extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);

fs/nfs/nfs4renewd.c

@@ -54,14 +54,14 @@
 void
 nfs4_renew_state(struct work_struct *work)
 {
-	struct nfs4_state_maintenance_ops *ops;
+	const struct nfs4_state_maintenance_ops *ops;
 	struct nfs_client *clp =
 		container_of(work, struct nfs_client, cl_renewd.work);
 	struct rpc_cred *cred;
 	long lease;
 	unsigned long last, now;
 
-	ops = nfs4_state_renewal_ops[clp->cl_minorversion];
+	ops = clp->cl_mvops->state_renewal_ops;
 	dprintk("%s: start\n", __func__);
 	/* Are there any active superblocks? */
 	if (list_empty(&clp->cl_superblocks))

fs/nfs/nfs4state.c

@@ -145,7 +145,9 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 	struct nfs4_session *ses = clp->cl_session;
 	int max_slots;
 
-	if (test_and_clear_bit(NFS4CLNT_SESSION_DRAINING, &clp->cl_state)) {
+	if (ses == NULL)
+		return;
+	if (test_and_clear_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
 		spin_lock(&ses->fc_slot_table.slot_tbl_lock);
 		max_slots = ses->fc_slot_table.max_slots;
 		while (max_slots--) {
@@ -167,7 +169,7 @@ static int nfs4_begin_drain_session(struct nfs_client *clp)
 	struct nfs4_slot_table *tbl = &ses->fc_slot_table;
 
 	spin_lock(&tbl->slot_tbl_lock);
-	set_bit(NFS4CLNT_SESSION_DRAINING, &clp->cl_state);
+	set_bit(NFS4_SESSION_DRAINING, &ses->session_state);
 	if (tbl->highest_used_slotid != -1) {
 		INIT_COMPLETION(ses->complete);
 		spin_unlock(&tbl->slot_tbl_lock);
@@ -371,7 +373,6 @@ nfs4_alloc_state_owner(void)
 		return NULL;
 	spin_lock_init(&sp->so_lock);
 	INIT_LIST_HEAD(&sp->so_states);
-	INIT_LIST_HEAD(&sp->so_delegations);
 	rpc_init_wait_queue(&sp->so_sequence.wait, "Seqid_waitqueue");
 	sp->so_seqid.sequence = &sp->so_sequence;
 	spin_lock_init(&sp->so_sequence.lock);
@@ -384,7 +385,7 @@ static void
 nfs4_drop_state_owner(struct nfs4_state_owner *sp)
 {
 	if (!RB_EMPTY_NODE(&sp->so_client_node)) {
-		struct nfs_client *clp = sp->so_client;
+		struct nfs_client *clp = sp->so_server->nfs_client;
 
 		spin_lock(&clp->cl_lock);
 		rb_erase(&sp->so_client_node, &clp->cl_state_owners);
@@ -406,7 +407,6 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct
 	new = nfs4_alloc_state_owner();
 	if (new == NULL)
 		return NULL;
-	new->so_client = clp;
 	new->so_server = server;
 	new->so_cred = cred;
 	spin_lock(&clp->cl_lock);
@@ -423,7 +423,7 @@ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, struct
 
 void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 {
-	struct nfs_client *clp = sp->so_client;
+	struct nfs_client *clp = sp->so_server->nfs_client;
 	struct rpc_cred *cred = sp->so_cred;
 
 	if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
@@ -602,12 +602,21 @@ void nfs4_close_sync(struct path *path, struct nfs4_state *state, fmode_t fmode)
  * that is compatible with current->files
  */
 static struct nfs4_lock_state *
-__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
+__nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
 {
 	struct nfs4_lock_state *pos;
 	list_for_each_entry(pos, &state->lock_states, ls_locks) {
-		if (pos->ls_owner != fl_owner)
+		if (type != NFS4_ANY_LOCK_TYPE && pos->ls_owner.lo_type != type)
 			continue;
+		switch (pos->ls_owner.lo_type) {
+		case NFS4_POSIX_LOCK_TYPE:
+			if (pos->ls_owner.lo_u.posix_owner != fl_owner)
+				continue;
+			break;
+		case NFS4_FLOCK_LOCK_TYPE:
+			if (pos->ls_owner.lo_u.flock_owner != fl_pid)
+				continue;
+		}
 		atomic_inc(&pos->ls_count);
 		return pos;
 	}
@@ -619,10 +628,10 @@ __nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
+static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid, unsigned int type)
 {
 	struct nfs4_lock_state *lsp;
-	struct nfs_client *clp = state->owner->so_client;
+	struct nfs_client *clp = state->owner->so_server->nfs_client;
 
 	lsp = kzalloc(sizeof(*lsp), GFP_NOFS);
 	if (lsp == NULL)
@@ -633,7 +642,18 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 	lsp->ls_seqid.sequence = &lsp->ls_sequence;
 	atomic_set(&lsp->ls_count, 1);
 	lsp->ls_state = state;
-	lsp->ls_owner = fl_owner;
+	lsp->ls_owner.lo_type = type;
+	switch (lsp->ls_owner.lo_type) {
+	case NFS4_FLOCK_LOCK_TYPE:
+		lsp->ls_owner.lo_u.flock_owner = fl_pid;
+		break;
+	case NFS4_POSIX_LOCK_TYPE:
+		lsp->ls_owner.lo_u.posix_owner = fl_owner;
+		break;
+	default:
+		kfree(lsp);
+		return NULL;
+	}
 	spin_lock(&clp->cl_lock);
 	nfs_alloc_unique_id(&clp->cl_lockowner_id, &lsp->ls_id, 1, 64);
 	spin_unlock(&clp->cl_lock);
@@ -643,7 +663,7 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
 
 static void nfs4_free_lock_state(struct nfs4_lock_state *lsp)
 {
-	struct nfs_client *clp = lsp->ls_state->owner->so_client;
+	struct nfs_client *clp = lsp->ls_state->owner->so_server->nfs_client;
 
 	spin_lock(&clp->cl_lock);
 	nfs_free_unique_id(&clp->cl_lockowner_id, &lsp->ls_id);
@@ -657,13 +677,13 @@ static void nfs4_free_lock_state(struct nfs4_lock_state *lsp)
  * exists, return an uninitialized one.
  *
  */
-static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner)
+static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner, pid_t pid, unsigned int type)
 {
 	struct nfs4_lock_state *lsp, *new = NULL;
 	
 	for(;;) {
 		spin_lock(&state->state_lock);
-		lsp = __nfs4_find_lock_state(state, owner);
+		lsp = __nfs4_find_lock_state(state, owner, pid, type);
 		if (lsp != NULL)
 			break;
 		if (new != NULL) {
@@ -674,7 +694,7 @@ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_
 			break;
 		}
 		spin_unlock(&state->state_lock);
-		new = nfs4_alloc_lock_state(state, owner);
+		new = nfs4_alloc_lock_state(state, owner, pid, type);
 		if (new == NULL)
 			return NULL;
 	}
@@ -701,6 +721,8 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
 	if (list_empty(&state->lock_states))
 		clear_bit(LK_STATE_IN_USE, &state->flags);
 	spin_unlock(&state->state_lock);
+	if (lsp->ls_flags & NFS_LOCK_INITIALIZED)
+		nfs4_release_lockowner(lsp);
 	nfs4_free_lock_state(lsp);
 }
 
@@ -728,7 +750,12 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
 
 	if (fl->fl_ops != NULL)
 		return 0;
-	lsp = nfs4_get_lock_state(state, fl->fl_owner);
+	if (fl->fl_flags & FL_POSIX)
+		lsp = nfs4_get_lock_state(state, fl->fl_owner, 0, NFS4_POSIX_LOCK_TYPE);
+	else if (fl->fl_flags & FL_FLOCK)
+		lsp = nfs4_get_lock_state(state, 0, fl->fl_pid, NFS4_FLOCK_LOCK_TYPE);
+	else
+		return -EINVAL;
 	if (lsp == NULL)
 		return -ENOMEM;
 	fl->fl_u.nfs4_fl.owner = lsp;
@@ -740,7 +767,7 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
  * Byte-range lock aware utility to initialize the stateid of read/write
  * requests.
  */
-void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t fl_owner)
+void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t fl_owner, pid_t fl_pid)
 {
 	struct nfs4_lock_state *lsp;
 	int seq;
@@ -753,7 +780,7 @@ void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t f
 		return;
 
 	spin_lock(&state->state_lock);
-	lsp = __nfs4_find_lock_state(state, fl_owner);
+	lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
 	if (lsp != NULL && (lsp->ls_flags & NFS_LOCK_INITIALIZED) != 0)
 		memcpy(dst, &lsp->ls_stateid, sizeof(*dst));
 	spin_unlock(&state->state_lock);
@@ -1041,11 +1068,11 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 			case -NFS4ERR_BAD_STATEID:
 			case -NFS4ERR_RECLAIM_BAD:
 			case -NFS4ERR_RECLAIM_CONFLICT:
-				nfs4_state_mark_reclaim_nograce(sp->so_client, state);
+				nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
 				break;
 			case -NFS4ERR_EXPIRED:
 			case -NFS4ERR_NO_GRACE:
-				nfs4_state_mark_reclaim_nograce(sp->so_client, state);
+				nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
 			case -NFS4ERR_STALE_CLIENTID:
 			case -NFS4ERR_BADSESSION:
 			case -NFS4ERR_BADSLOT:
@@ -1120,8 +1147,7 @@ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
 	if (!test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))
 		return;
 
-	nfs4_reclaim_complete(clp,
-		nfs4_reboot_recovery_ops[clp->cl_minorversion]);
+	nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops);
 
 	for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) {
 		sp = rb_entry(pos, struct nfs4_state_owner, so_client_node);
@@ -1211,8 +1237,8 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 static int nfs4_check_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
-	struct nfs4_state_maintenance_ops *ops =
-		nfs4_state_renewal_ops[clp->cl_minorversion];
+	const struct nfs4_state_maintenance_ops *ops =
+		clp->cl_mvops->state_renewal_ops;
 	int status = -NFS4ERR_EXPIRED;
 
 	/* Is the client already known to have an expired lease? */
@@ -1235,8 +1261,8 @@ static int nfs4_check_lease(struct nfs_client *clp)
 static int nfs4_reclaim_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
-	struct nfs4_state_recovery_ops *ops =
-		nfs4_reboot_recovery_ops[clp->cl_minorversion];
+	const struct nfs4_state_recovery_ops *ops =
+		clp->cl_mvops->reboot_recovery_ops;
 	int status = -ENOENT;
 
 	cred = ops->get_clid_cred(clp);
@@ -1444,7 +1470,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 		/* First recover reboot state... */
 		if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
 			status = nfs4_do_reclaim(clp,
-				nfs4_reboot_recovery_ops[clp->cl_minorversion]);
+				clp->cl_mvops->reboot_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
 			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state))
 				continue;
@@ -1458,7 +1484,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
 		/* Now recover expired state... */
 		if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
 			status = nfs4_do_reclaim(clp,
-				nfs4_nograce_recovery_ops[clp->cl_minorversion]);
+				clp->cl_mvops->nograce_recovery_ops);
 			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) ||
 			    test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) ||
 			    test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state))

fs/nfs/nfs4xdr.c

@@ -202,14 +202,17 @@ static int nfs4_stat_to_errno(int);
 #define encode_link_maxsz	(op_encode_hdr_maxsz + \
 				nfs4_name_maxsz)
 #define decode_link_maxsz	(op_decode_hdr_maxsz + decode_change_info_maxsz)
+#define encode_lockowner_maxsz	(7)
 #define encode_lock_maxsz	(op_encode_hdr_maxsz + \
 				 7 + \
-				 1 + encode_stateid_maxsz + 8)
+				 1 + encode_stateid_maxsz + 1 + \
+				 encode_lockowner_maxsz)
 #define decode_lock_denied_maxsz \
 				(8 + decode_lockowner_maxsz)
 #define decode_lock_maxsz	(op_decode_hdr_maxsz + \
 				 decode_lock_denied_maxsz)
-#define encode_lockt_maxsz	(op_encode_hdr_maxsz + 12)
+#define encode_lockt_maxsz	(op_encode_hdr_maxsz + 5 + \
+				encode_lockowner_maxsz)
 #define decode_lockt_maxsz	(op_decode_hdr_maxsz + \
 				 decode_lock_denied_maxsz)
 #define encode_locku_maxsz	(op_encode_hdr_maxsz + 3 + \
@@ -217,6 +220,11 @@ static int nfs4_stat_to_errno(int);
 				 4)
 #define decode_locku_maxsz	(op_decode_hdr_maxsz + \
 				 decode_stateid_maxsz)
+#define encode_release_lockowner_maxsz \
+				(op_encode_hdr_maxsz + \
+				 encode_lockowner_maxsz)
+#define decode_release_lockowner_maxsz \
+				(op_decode_hdr_maxsz)
 #define encode_access_maxsz	(op_encode_hdr_maxsz + 1)
 #define decode_access_maxsz	(op_decode_hdr_maxsz + 2)
 #define encode_symlink_maxsz	(op_encode_hdr_maxsz + \
@@ -471,6 +479,12 @@ static int nfs4_stat_to_errno(int);
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_locku_maxsz)
+#define NFS4_enc_release_lockowner_sz \
+				(compound_encode_hdr_maxsz + \
+				 encode_lockowner_maxsz)
+#define NFS4_dec_release_lockowner_sz \
+				(compound_decode_hdr_maxsz + \
+				 decode_lockowner_maxsz)
 #define NFS4_enc_access_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
@@ -744,7 +758,7 @@ static void encode_compound_hdr(struct xdr_stream *xdr,
 				struct compound_hdr *hdr)
 {
 	__be32 *p;
-	struct rpc_auth *auth = req->rq_task->tk_msg.rpc_cred->cr_auth;
+	struct rpc_auth *auth = req->rq_cred->cr_auth;
 
 	/* initialize running count of expected bytes in reply.
 	 * NOTE: the replied tag SHOULD be the same is the one sent,
@@ -1042,6 +1056,17 @@ static inline uint64_t nfs4_lock_length(struct file_lock *fl)
 	return fl->fl_end - fl->fl_start + 1;
 }
 
+static void encode_lockowner(struct xdr_stream *xdr, const struct nfs_lowner *lowner)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 28);
+	p = xdr_encode_hyper(p, lowner->clientid);
+	*p++ = cpu_to_be32(16);
+	p = xdr_encode_opaque_fixed(p, "lock id:", 8);
+	xdr_encode_hyper(p, lowner->id);
+}
+
 /*
  * opcode,type,reclaim,offset,length,new_lock_owner = 32
  * open_seqid,open_stateid,lock_seqid,lock_owner.clientid, lock_owner.id = 40
@@ -1058,14 +1083,11 @@ static void encode_lock(struct xdr_stream *xdr, const struct nfs_lock_args *args
 	p = xdr_encode_hyper(p, nfs4_lock_length(args->fl));
 	*p = cpu_to_be32(args->new_lock_owner);
 	if (args->new_lock_owner){
-		p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+32);
+		p = reserve_space(xdr, 4+NFS4_STATEID_SIZE+4);
 		*p++ = cpu_to_be32(args->open_seqid->sequence->counter);
 		p = xdr_encode_opaque_fixed(p, args->open_stateid->data, NFS4_STATEID_SIZE);
 		*p++ = cpu_to_be32(args->lock_seqid->sequence->counter);
-		p = xdr_encode_hyper(p, args->lock_owner.clientid);
-		*p++ = cpu_to_be32(16);
-		p = xdr_encode_opaque_fixed(p, "lock id:", 8);
-		xdr_encode_hyper(p, args->lock_owner.id);
+		encode_lockowner(xdr, &args->lock_owner);
 	}
 	else {
 		p = reserve_space(xdr, NFS4_STATEID_SIZE+4);
@@ -1080,15 +1102,12 @@ static void encode_lockt(struct xdr_stream *xdr, const struct nfs_lockt_args *ar
 {
 	__be32 *p;
 
-	p = reserve_space(xdr, 52);
+	p = reserve_space(xdr, 24);
 	*p++ = cpu_to_be32(OP_LOCKT);
 	*p++ = cpu_to_be32(nfs4_lock_type(args->fl, 0));
 	p = xdr_encode_hyper(p, args->fl->fl_start);
 	p = xdr_encode_hyper(p, nfs4_lock_length(args->fl));
-	p = xdr_encode_hyper(p, args->lock_owner.clientid);
-	*p++ = cpu_to_be32(16);
-	p = xdr_encode_opaque_fixed(p, "lock id:", 8);
-	xdr_encode_hyper(p, args->lock_owner.id);
+	encode_lockowner(xdr, &args->lock_owner);
 	hdr->nops++;
 	hdr->replen += decode_lockt_maxsz;
 }
@@ -1108,6 +1127,17 @@ static void encode_locku(struct xdr_stream *xdr, const struct nfs_locku_args *ar
 	hdr->replen += decode_locku_maxsz;
 }
 
+static void encode_release_lockowner(struct xdr_stream *xdr, const struct nfs_lowner *lowner, struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	p = reserve_space(xdr, 4);
+	*p = cpu_to_be32(OP_RELEASE_LOCKOWNER);
+	encode_lockowner(xdr, lowner);
+	hdr->nops++;
+	hdr->replen += decode_release_lockowner_maxsz;
+}
+
 static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struct compound_hdr *hdr)
 {
 	int len = name->len;
@@ -1172,7 +1202,7 @@ static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_op
 		break;
 	default:
 		clp = arg->server->nfs_client;
-		if (clp->cl_minorversion > 0) {
+		if (clp->cl_mvops->minor_version > 0) {
 			if (nfs4_has_persistent_session(clp)) {
 				*p = cpu_to_be32(NFS4_CREATE_GUARDED);
 				encode_attrs(xdr, arg->u.attrs, arg->server);
@@ -1324,14 +1354,14 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	hdr->replen += decode_putrootfh_maxsz;
 }
 
-static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context *ctx)
+static void encode_stateid(struct xdr_stream *xdr, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx)
 {
 	nfs4_stateid stateid;
 	__be32 *p;
 
 	p = reserve_space(xdr, NFS4_STATEID_SIZE);
 	if (ctx->state != NULL) {
-		nfs4_copy_stateid(&stateid, ctx->state, ctx->lockowner);
+		nfs4_copy_stateid(&stateid, ctx->state, l_ctx->lockowner, l_ctx->pid);
 		xdr_encode_opaque_fixed(p, stateid.data, NFS4_STATEID_SIZE);
 	} else
 		xdr_encode_opaque_fixed(p, zero_stateid.data, NFS4_STATEID_SIZE);
@@ -1344,7 +1374,7 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args,
 	p = reserve_space(xdr, 4);
 	*p = cpu_to_be32(OP_READ);
 
-	encode_stateid(xdr, args->context);
+	encode_stateid(xdr, args->context, args->lock_context);
 
 	p = reserve_space(xdr, 12);
 	p = xdr_encode_hyper(p, args->offset);
@@ -1523,7 +1553,7 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg
 	p = reserve_space(xdr, 4);
 	*p = cpu_to_be32(OP_WRITE);
 
-	encode_stateid(xdr, args->context);
+	encode_stateid(xdr, args->context, args->lock_context);
 
 	p = reserve_space(xdr, 16);
 	p = xdr_encode_hyper(p, args->offset);
@@ -1704,7 +1734,7 @@ static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args)
 {
 #if defined(CONFIG_NFS_V4_1)
 	if (args->sa_session)
-		return args->sa_session->clp->cl_minorversion;
+		return args->sa_session->clp->cl_mvops->minor_version;
 #endif /* CONFIG_NFS_V4_1 */
 	return 0;
 }
@@ -2048,6 +2078,20 @@ static int nfs4_xdr_enc_locku(struct rpc_rqst *req, __be32 *p, struct nfs_locku_
 	return 0;
 }
 
+static int nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, __be32 *p, struct nfs_release_lockowner_args *args)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr = {
+		.minorversion = 0,
+	};
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	encode_compound_hdr(&xdr, req, &hdr);
+	encode_release_lockowner(&xdr, &args->lock_owner, &hdr);
+	encode_nops(&hdr);
+	return 0;
+}
+
 /*
  * Encode a READLINK request
  */
@@ -2395,7 +2439,7 @@ static int nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, uint32_t *p,
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.minorversion = args->client->cl_minorversion,
+		.minorversion = args->client->cl_mvops->minor_version,
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
@@ -2413,7 +2457,7 @@ static int nfs4_xdr_enc_create_session(struct rpc_rqst *req, uint32_t *p,
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.minorversion = args->client->cl_minorversion,
+		.minorversion = args->client->cl_mvops->minor_version,
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
@@ -2431,7 +2475,7 @@ static int nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, uint32_t *p,
 {
 	struct xdr_stream xdr;
 	struct compound_hdr hdr = {
-		.minorversion = session->clp->cl_minorversion,
+		.minorversion = session->clp->cl_mvops->minor_version,
 	};
 
 	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
@@ -3973,6 +4017,11 @@ static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res)
 	return status;
 }
 
+static int decode_release_lockowner(struct xdr_stream *xdr)
+{
+	return decode_op_hdr(xdr, OP_RELEASE_LOCKOWNER);
+}
+
 static int decode_lookup(struct xdr_stream *xdr)
 {
 	return decode_op_hdr(xdr, OP_LOOKUP);
@@ -5259,6 +5308,19 @@ static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, __be32 *p, struct nfs_lock
 	return status;
 }
 
+static int nfs4_xdr_dec_release_lockowner(struct rpc_rqst *rqstp, __be32 *p, void *dummy)
+{
+	struct xdr_stream xdr;
+	struct compound_hdr hdr;
+	int status;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	status = decode_compound_hdr(&xdr, &hdr);
+	if (!status)
+		status = decode_release_lockowner(&xdr);
+	return status;
+}
+
 /*
  * Decode READLINK response
  */
@@ -5866,6 +5928,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
   PROC(GETACL,		enc_getacl,	dec_getacl),
   PROC(SETACL,		enc_setacl,	dec_setacl),
   PROC(FS_LOCATIONS,	enc_fs_locations, dec_fs_locations),
+  PROC(RELEASE_LOCKOWNER, enc_release_lockowner, dec_release_lockowner),
 #if defined(CONFIG_NFS_V4_1)
   PROC(EXCHANGE_ID,	enc_exchange_id,	dec_exchange_id),
   PROC(CREATE_SESSION,	enc_create_session,	dec_create_session),

fs/nfs/pagelist.c

@@ -79,6 +79,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 	req->wb_pgbase	= offset;
 	req->wb_bytes   = count;
 	req->wb_context = get_nfs_open_context(ctx);
+	req->wb_lock_context = nfs_get_lock_context(ctx);
 	kref_init(&req->wb_kref);
 	return req;
 }
@@ -141,11 +142,16 @@ void nfs_clear_request(struct nfs_page *req)
 {
 	struct page *page = req->wb_page;
 	struct nfs_open_context *ctx = req->wb_context;
+	struct nfs_lock_context *l_ctx = req->wb_lock_context;
 
 	if (page != NULL) {
 		page_cache_release(page);
 		req->wb_page = NULL;
 	}
+	if (l_ctx != NULL) {
+		nfs_put_lock_context(l_ctx);
+		req->wb_lock_context = NULL;
+	}
 	if (ctx != NULL) {
 		put_nfs_open_context(ctx);
 		req->wb_context = NULL;
@@ -235,7 +241,7 @@ static int nfs_can_coalesce_requests(struct nfs_page *prev,
 {
 	if (req->wb_context->cred != prev->wb_context->cred)
 		return 0;
-	if (req->wb_context->lockowner != prev->wb_context->lockowner)
+	if (req->wb_lock_context->lockowner != prev->wb_lock_context->lockowner)
 		return 0;
 	if (req->wb_context->state != prev->wb_context->state)
 		return 0;

fs/nfs/read.c

@@ -190,6 +190,7 @@ static int nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
 	data->args.pages  = data->pagevec;
 	data->args.count  = count;
 	data->args.context = get_nfs_open_context(req->wb_context);
+	data->args.lock_context = req->wb_lock_context;
 
 	data->res.fattr   = &data->fattr;
 	data->res.count   = count;
@@ -410,7 +411,7 @@ void nfs_read_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs_read_data *data = calldata;
 
-	if (nfs4_setup_sequence(NFS_SERVER(data->inode)->nfs_client,
+	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
 				&data->args.seq_args, &data->res.seq_res,
 				0, task))
 		return;

fs/nfs/super.c

@@ -546,6 +546,9 @@ static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
 {
 	struct sockaddr *sap = (struct sockaddr *)&nfss->mountd_address;
 
+	if (nfss->flags & NFS_MOUNT_LEGACY_INTERFACE)
+		return;
+
 	switch (sap->sa_family) {
 	case AF_INET: {
 		struct sockaddr_in *sin = (struct sockaddr_in *)sap;
@@ -1780,6 +1783,7 @@ static int nfs_validate_mount_data(void *options,
 		 * can deal with.
 		 */
 		args->flags		= data->flags & NFS_MOUNT_FLAGMASK;
+		args->flags		|= NFS_MOUNT_LEGACY_INTERFACE;
 		args->rsize		= data->rsize;
 		args->wsize		= data->wsize;
 		args->timeo		= data->timeo;

fs/nfs/unlink.c

@@ -110,7 +110,7 @@ void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
 	struct nfs_unlinkdata *data = calldata;
 	struct nfs_server *server = NFS_SERVER(data->dir);
 
-	if (nfs4_setup_sequence(server->nfs_client, &data->args.seq_args,
+	if (nfs4_setup_sequence(server, &data->args.seq_args,
 				&data->res.seq_res, 1, task))
 		return;
 	rpc_call_start(task);

fs/nfs/write.c

@@ -700,7 +700,9 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		req = nfs_page_find_request(page);
 		if (req == NULL)
 			return 0;
-		do_flush = req->wb_page != page || req->wb_context != ctx;
+		do_flush = req->wb_page != page || req->wb_context != ctx ||
+			req->wb_lock_context->lockowner != current->files ||
+			req->wb_lock_context->pid != current->tgid;
 		nfs_release_request(req);
 		if (!do_flush)
 			return 0;
@@ -824,6 +826,7 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
 	data->args.pages  = data->pagevec;
 	data->args.count  = count;
 	data->args.context = get_nfs_open_context(req->wb_context);
+	data->args.lock_context = req->wb_lock_context;
 	data->args.stable  = NFS_UNSTABLE;
 	if (how & FLUSH_STABLE) {
 		data->args.stable = NFS_DATA_SYNC;
@@ -1047,9 +1050,9 @@ static void nfs_writeback_release_partial(void *calldata)
 void nfs_write_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs_write_data *data = calldata;
-	struct nfs_client *clp = (NFS_SERVER(data->inode))->nfs_client;
 
-	if (nfs4_setup_sequence(clp, &data->args.seq_args,
+	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+				&data->args.seq_args,
 				&data->res.seq_res, 1, task))
 		return;
 	rpc_call_start(task);

include/linux/nfs4.h

@@ -523,6 +523,7 @@ enum {
 	NFSPROC4_CLNT_GETACL,
 	NFSPROC4_CLNT_SETACL,
 	NFSPROC4_CLNT_FS_LOCATIONS,
+	NFSPROC4_CLNT_RELEASE_LOCKOWNER,
 
 	/* nfs41 */
 	NFSPROC4_CLNT_EXCHANGE_ID,

include/linux/nfs_fs.h

@@ -72,13 +72,20 @@ struct nfs_access_entry {
 	int			mask;
 };
 
+struct nfs_lock_context {
+	atomic_t count;
+	struct list_head list;
+	struct nfs_open_context *open_context;
+	fl_owner_t lockowner;
+	pid_t pid;
+};
+
 struct nfs4_state;
 struct nfs_open_context {
-	atomic_t count;
+	struct nfs_lock_context lock_context;
 	struct path path;
 	struct rpc_cred *cred;
 	struct nfs4_state *state;
-	fl_owner_t lockowner;
 	fmode_t mode;
 
 	unsigned long flags;
@@ -353,6 +360,8 @@ extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr);
 extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx);
 extern void put_nfs_open_context(struct nfs_open_context *ctx);
 extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode);
+extern struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx);
+extern void nfs_put_lock_context(struct nfs_lock_context *l_ctx);
 extern u64 nfs_compat_user_ino64(u64 fileid);
 extern void nfs_fattr_init(struct nfs_fattr *fattr);
 

include/linux/nfs_fs_sb.h

@@ -15,6 +15,7 @@ struct nlm_host;
 struct nfs4_sequence_args;
 struct nfs4_sequence_res;
 struct nfs_server;
+struct nfs4_minor_version_ops;
 
 /*
  * The nfs_client identifies our client state to the server.
@@ -70,11 +71,7 @@ struct nfs_client {
 	 */
 	char			cl_ipaddr[48];
 	unsigned char		cl_id_uniquifier;
-	int		     (* cl_call_sync)(struct nfs_server *server,
-					      struct rpc_message *msg,
-					      struct nfs4_sequence_args *args,
-					      struct nfs4_sequence_res *res,
-					      int cache_reply);
+	const struct nfs4_minor_version_ops *cl_mvops;
 #endif /* CONFIG_NFS_V4 */
 
 #ifdef CONFIG_NFS_V4_1

include/linux/nfs_mount.h

@@ -69,5 +69,6 @@ struct nfs_mount_data {
 #define NFS_MOUNT_LOOKUP_CACHE_NONEG	0x10000
 #define NFS_MOUNT_LOOKUP_CACHE_NONE	0x20000
 #define NFS_MOUNT_NORESVPORT		0x40000
+#define NFS_MOUNT_LEGACY_INTERFACE	0x80000
 
 #endif

include/linux/nfs_page.h

@@ -39,6 +39,7 @@ struct nfs_page {
 	struct list_head	wb_list;	/* Defines state of page: */
 	struct page		*wb_page;	/* page to read in/write out */
 	struct nfs_open_context	*wb_context;	/* File state context info */
+	struct nfs_lock_context	*wb_lock_context;	/* lock context info */
 	atomic_t		wb_complete;	/* i/os we're waiting for */
 	pgoff_t			wb_index;	/* Offset >> PAGE_CACHE_SHIFT */
 	unsigned int		wb_offset,	/* Offset & ~PAGE_CACHE_MASK */

include/linux/nfs_xdr.h

@@ -196,8 +196,10 @@ struct nfs_openargs {
 	__u64                   clientid;
 	__u64                   id;
 	union {
-		struct iattr *  attrs;    /* UNCHECKED, GUARDED */
-		nfs4_verifier   verifier; /* EXCLUSIVE */
+		struct {
+			struct iattr *  attrs;    /* UNCHECKED, GUARDED */
+			nfs4_verifier   verifier; /* EXCLUSIVE */
+		};
 		nfs4_stateid	delegation;		/* CLAIM_DELEGATE_CUR */
 		fmode_t		delegation_type;	/* CLAIM_PREVIOUS */
 	} u;
@@ -313,6 +315,10 @@ struct nfs_lockt_res {
 	struct nfs4_sequence_res	seq_res;
 };
 
+struct nfs_release_lockowner_args {
+	struct nfs_lowner	lock_owner;
+};
+
 struct nfs4_delegreturnargs {
 	const struct nfs_fh *fhandle;
 	const nfs4_stateid *stateid;
@@ -332,6 +338,7 @@ struct nfs4_delegreturnres {
 struct nfs_readargs {
 	struct nfs_fh *		fh;
 	struct nfs_open_context *context;
+	struct nfs_lock_context *lock_context;
 	__u64			offset;
 	__u32			count;
 	unsigned int		pgbase;
@@ -352,6 +359,7 @@ struct nfs_readres {
 struct nfs_writeargs {
 	struct nfs_fh *		fh;
 	struct nfs_open_context *context;
+	struct nfs_lock_context *lock_context;
 	__u64			offset;
 	__u32			count;
 	enum nfs3_stable_how	stable;

include/linux/sunrpc/auth.h

@@ -61,13 +61,7 @@ struct rpc_cred {
 /*
  * Client authentication handle
  */
-#define RPC_CREDCACHE_HASHBITS	4
-#define RPC_CREDCACHE_NR	(1 << RPC_CREDCACHE_HASHBITS)
-struct rpc_cred_cache {
-	struct hlist_head	hashtable[RPC_CREDCACHE_NR];
-	spinlock_t		lock;
-};
-
+struct rpc_cred_cache;
 struct rpc_authops;
 struct rpc_auth {
 	unsigned int		au_cslack;	/* call cred size estimate */
@@ -112,7 +106,7 @@ 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 *, int);
+	struct rpc_cred *	(*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 *);
@@ -125,11 +119,12 @@ struct rpc_credops {
 extern const struct rpc_authops	authunix_ops;
 extern const struct rpc_authops	authnull_ops;
 
-void __init		rpc_init_authunix(void);
-void __init		rpc_init_generic_auth(void);
-void __init		rpcauth_init_module(void);
+int __init		rpc_init_authunix(void);
+int __init		rpc_init_generic_auth(void);
+int __init		rpcauth_init_module(void);
 void __exit		rpcauth_remove_module(void);
 void __exit		rpc_destroy_generic_auth(void);
+void 			rpc_destroy_authunix(void);
 
 struct rpc_cred *	rpc_lookup_cred(void);
 struct rpc_cred *	rpc_lookup_machine_cred(void);
@@ -140,10 +135,8 @@ void			rpcauth_release(struct rpc_auth *);
 struct rpc_cred *	rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int);
 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 *, int);
+struct rpc_cred *	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 *);
 __be32 *		rpcauth_checkverf(struct rpc_task *, __be32 *);
 int			rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp, __be32 *data, void *obj);

include/linux/sunrpc/clnt.h

@@ -131,6 +131,7 @@ struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 struct rpc_clnt *rpc_clone_client(struct rpc_clnt *);
 void		rpc_shutdown_client(struct rpc_clnt *);
 void		rpc_release_client(struct rpc_clnt *);
+void		rpc_task_release_client(struct rpc_task *);
 
 int		rpcb_register(u32, u32, int, unsigned short);
 int		rpcb_v4_register(const u32 program, const u32 version,
@@ -148,8 +149,8 @@ int		rpc_call_sync(struct rpc_clnt *clnt,
 			      const struct rpc_message *msg, int flags);
 struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred,
 			       int flags);
-void		rpc_restart_call_prepare(struct rpc_task *);
-void		rpc_restart_call(struct rpc_task *);
+int		rpc_restart_call_prepare(struct rpc_task *);
+int		rpc_restart_call(struct rpc_task *);
 void		rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
 size_t		rpc_max_payload(struct rpc_clnt *);
 void		rpc_force_rebind(struct rpc_clnt *);

include/linux/sunrpc/sched.h

@@ -213,6 +213,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req,
 				const struct rpc_call_ops *ops);
 void		rpc_put_task(struct rpc_task *);
 void		rpc_exit_task(struct rpc_task *);
+void		rpc_exit(struct rpc_task *, int);
 void		rpc_release_calldata(const struct rpc_call_ops *, void *);
 void		rpc_killall_tasks(struct rpc_clnt *);
 void		rpc_execute(struct rpc_task *);
@@ -241,12 +242,6 @@ void		rpc_destroy_mempool(void);
 extern struct workqueue_struct *rpciod_workqueue;
 void		rpc_prepare_task(struct rpc_task *task);
 
-static inline void rpc_exit(struct rpc_task *task, int status)
-{
-	task->tk_status = status;
-	task->tk_action = rpc_exit_task;
-}
-
 static inline int rpc_wait_for_completion_task(struct rpc_task *task)
 {
 	return __rpc_wait_for_completion_task(task, NULL);

include/linux/sunrpc/xprt.h

@@ -64,6 +64,7 @@ struct rpc_rqst {
 	 * This is the private part
 	 */
 	struct rpc_task *	rq_task;	/* RPC task data */
+	struct rpc_cred *	rq_cred;	/* Bound cred */
 	__be32			rq_xid;		/* request XID */
 	int			rq_cong;	/* has incremented xprt->cong */
 	u32			rq_seqno;	/* gss seq no. used on req. */

net/sunrpc/auth.c

@@ -19,6 +19,15 @@
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
+#define RPC_CREDCACHE_DEFAULT_HASHBITS	(4)
+struct rpc_cred_cache {
+	struct hlist_head	*hashtable;
+	unsigned int		hashbits;
+	spinlock_t		lock;
+};
+
+static unsigned int auth_hashbits = RPC_CREDCACHE_DEFAULT_HASHBITS;
+
 static DEFINE_SPINLOCK(rpc_authflavor_lock);
 static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = {
 	&authnull_ops,		/* AUTH_NULL */
@@ -29,6 +38,42 @@ static const struct rpc_authops *auth_flavors[RPC_AUTH_MAXFLAVOR] = {
 static LIST_HEAD(cred_unused);
 static unsigned long number_cred_unused;
 
+#define MAX_HASHTABLE_BITS (10) 
+static int param_set_hashtbl_sz(const char *val, struct kernel_param *kp)
+{
+	unsigned long num;
+	unsigned int nbits;
+	int ret;
+
+	if (!val)
+		goto out_inval;
+	ret = strict_strtoul(val, 0, &num);
+	if (ret == -EINVAL)
+		goto out_inval;
+	nbits = fls(num);
+	if (num > (1U << nbits))
+		nbits++;
+	if (nbits > MAX_HASHTABLE_BITS || nbits < 2)
+		goto out_inval;
+	*(unsigned int *)kp->arg = nbits;
+	return 0;
+out_inval:
+	return -EINVAL;
+}
+
+static int param_get_hashtbl_sz(char *buffer, struct kernel_param *kp)
+{
+	unsigned int nbits;
+
+	nbits = *(unsigned int *)kp->arg;
+	return sprintf(buffer, "%u", 1U << nbits);
+}
+
+#define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int);
+
+module_param_named(auth_hashtable_size, auth_hashbits, hashtbl_sz, 0644);
+MODULE_PARM_DESC(auth_hashtable_size, "RPC credential cache hashtable size");
+
 static u32
 pseudoflavor_to_flavor(u32 flavor) {
 	if (flavor >= RPC_AUTH_MAXFLAVOR)
@@ -145,16 +190,23 @@ int
 rpcauth_init_credcache(struct rpc_auth *auth)
 {
 	struct rpc_cred_cache *new;
-	int i;
+	unsigned int hashsize;
 
 	new = kmalloc(sizeof(*new), GFP_KERNEL);
 	if (!new)
-		return -ENOMEM;
-	for (i = 0; i < RPC_CREDCACHE_NR; i++)
-		INIT_HLIST_HEAD(&new->hashtable[i]);
+		goto out_nocache;
+	new->hashbits = auth_hashbits;
+	hashsize = 1U << new->hashbits;
+	new->hashtable = kcalloc(hashsize, sizeof(new->hashtable[0]), GFP_KERNEL);
+	if (!new->hashtable)
+		goto out_nohashtbl;
 	spin_lock_init(&new->lock);
 	auth->au_credcache = new;
 	return 0;
+out_nohashtbl:
+	kfree(new);
+out_nocache:
+	return -ENOMEM;
 }
 EXPORT_SYMBOL_GPL(rpcauth_init_credcache);
 
@@ -183,11 +235,12 @@ rpcauth_clear_credcache(struct rpc_cred_cache *cache)
 	LIST_HEAD(free);
 	struct hlist_head *head;
 	struct rpc_cred	*cred;
+	unsigned int hashsize = 1U << cache->hashbits;
 	int		i;
 
 	spin_lock(&rpc_credcache_lock);
 	spin_lock(&cache->lock);
-	for (i = 0; i < RPC_CREDCACHE_NR; i++) {
+	for (i = 0; i < hashsize; i++) {
 		head = &cache->hashtable[i];
 		while (!hlist_empty(head)) {
 			cred = hlist_entry(head->first, struct rpc_cred, cr_hash);
@@ -216,6 +269,7 @@ rpcauth_destroy_credcache(struct rpc_auth *auth)
 	if (cache) {
 		auth->au_credcache = NULL;
 		rpcauth_clear_credcache(cache);
+		kfree(cache->hashtable);
 		kfree(cache);
 	}
 }
@@ -297,7 +351,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred,
 			*entry, *new;
 	unsigned int nr;
 
-	nr = hash_long(acred->uid, RPC_CREDCACHE_HASHBITS);
+	nr = hash_long(acred->uid, cache->hashbits);
 
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(entry, pos, &cache->hashtable[nr], cr_hash) {
@@ -390,16 +444,16 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
 }
 EXPORT_SYMBOL_GPL(rpcauth_init_cred);
 
-void
+struct rpc_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,
 			cred->cr_auth->au_ops->au_name, cred);
+	return get_rpccred(cred);
 }
 EXPORT_SYMBOL_GPL(rpcauth_generic_bind_cred);
 
-static void
+static struct rpc_cred *
 rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
 {
 	struct rpc_auth *auth = task->tk_client->cl_auth;
@@ -407,45 +461,43 @@ rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags)
 		.uid = 0,
 		.gid = 0,
 	};
-	struct rpc_cred *ret;
 
 	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, lookupflags);
-	if (!IS_ERR(ret))
-		task->tk_msg.rpc_cred = ret;
-	else
-		task->tk_status = PTR_ERR(ret);
+	return auth->au_ops->lookup_cred(auth, &acred, lookupflags);
 }
 
-static void
+static struct rpc_cred *
 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, lookupflags);
-	if (!IS_ERR(ret))
-		task->tk_msg.rpc_cred = ret;
-	else
-		task->tk_status = PTR_ERR(ret);
+	return rpcauth_lookupcred(auth, lookupflags);
 }
 
-void
+static int
 rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags)
 {
+	struct rpc_rqst *req = task->tk_rqstp;
+	struct rpc_cred *new;
 	int lookupflags = 0;
 
 	if (flags & RPC_TASK_ASYNC)
 		lookupflags |= RPCAUTH_LOOKUP_NEW;
 	if (cred != NULL)
-		cred->cr_ops->crbind(task, cred, lookupflags);
+		new = cred->cr_ops->crbind(task, cred, lookupflags);
 	else if (flags & RPC_TASK_ROOTCREDS)
-		rpcauth_bind_root_cred(task, lookupflags);
+		new = rpcauth_bind_root_cred(task, lookupflags);
 	else
-		rpcauth_bind_new_cred(task, lookupflags);
+		new = rpcauth_bind_new_cred(task, lookupflags);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+	if (req->rq_cred != NULL)
+		put_rpccred(req->rq_cred);
+	req->rq_cred = new;
+	return 0;
 }
 
 void
@@ -484,22 +536,10 @@ put_rpccred(struct rpc_cred *cred)
 }
 EXPORT_SYMBOL_GPL(put_rpccred);
 
-void
-rpcauth_unbindcred(struct rpc_task *task)
-{
-	struct rpc_cred	*cred = task->tk_msg.rpc_cred;
-
-	dprintk("RPC: %5u releasing %s cred %p\n",
-		task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
-
-	put_rpccred(cred);
-	task->tk_msg.rpc_cred = NULL;
-}
-
 __be32 *
 rpcauth_marshcred(struct rpc_task *task, __be32 *p)
 {
-	struct rpc_cred	*cred = task->tk_msg.rpc_cred;
+	struct rpc_cred	*cred = task->tk_rqstp->rq_cred;
 
 	dprintk("RPC: %5u marshaling %s cred %p\n",
 		task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -510,7 +550,7 @@ rpcauth_marshcred(struct rpc_task *task, __be32 *p)
 __be32 *
 rpcauth_checkverf(struct rpc_task *task, __be32 *p)
 {
-	struct rpc_cred	*cred = task->tk_msg.rpc_cred;
+	struct rpc_cred	*cred = task->tk_rqstp->rq_cred;
 
 	dprintk("RPC: %5u validating %s cred %p\n",
 		task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -522,7 +562,7 @@ int
 rpcauth_wrap_req(struct rpc_task *task, kxdrproc_t encode, void *rqstp,
 		__be32 *data, void *obj)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 
 	dprintk("RPC: %5u using %s cred %p to wrap rpc data\n",
 			task->tk_pid, cred->cr_ops->cr_name, cred);
@@ -536,7 +576,7 @@ int
 rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
 		__be32 *data, void *obj)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 
 	dprintk("RPC: %5u using %s cred %p to unwrap rpc data\n",
 			task->tk_pid, cred->cr_ops->cr_name, cred);
@@ -550,13 +590,21 @@ rpcauth_unwrap_resp(struct rpc_task *task, kxdrproc_t decode, void *rqstp,
 int
 rpcauth_refreshcred(struct rpc_task *task)
 {
-	struct rpc_cred	*cred = task->tk_msg.rpc_cred;
+	struct rpc_cred	*cred = task->tk_rqstp->rq_cred;
 	int err;
 
+	cred = task->tk_rqstp->rq_cred;
+	if (cred == NULL) {
+		err = rpcauth_bindcred(task, task->tk_msg.rpc_cred, task->tk_flags);
+		if (err < 0)
+			goto out;
+		cred = task->tk_rqstp->rq_cred;
+	};
 	dprintk("RPC: %5u refreshing %s cred %p\n",
 		task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
 
 	err = cred->cr_ops->crrefresh(task);
+out:
 	if (err < 0)
 		task->tk_status = err;
 	return err;
@@ -565,7 +613,7 @@ rpcauth_refreshcred(struct rpc_task *task)
 void
 rpcauth_invalcred(struct rpc_task *task)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 
 	dprintk("RPC: %5u invalidating %s cred %p\n",
 		task->tk_pid, cred->cr_auth->au_ops->au_name, cred);
@@ -576,7 +624,7 @@ rpcauth_invalcred(struct rpc_task *task)
 int
 rpcauth_uptodatecred(struct rpc_task *task)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 
 	return cred == NULL ||
 		test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0;
@@ -587,14 +635,27 @@ static struct shrinker rpc_cred_shrinker = {
 	.seeks = DEFAULT_SEEKS,
 };
 
-void __init rpcauth_init_module(void)
+int __init rpcauth_init_module(void)
 {
-	rpc_init_authunix();
-	rpc_init_generic_auth();
+	int err;
+
+	err = rpc_init_authunix();
+	if (err < 0)
+		goto out1;
+	err = rpc_init_generic_auth();
+	if (err < 0)
+		goto out2;
 	register_shrinker(&rpc_cred_shrinker);
+	return 0;
+out2:
+	rpc_destroy_authunix();
+out1:
+	return err;
 }
 
 void __exit rpcauth_remove_module(void)
 {
+	rpc_destroy_authunix();
+	rpc_destroy_generic_auth();
 	unregister_shrinker(&rpc_cred_shrinker);
 }

net/sunrpc/auth_generic.c

@@ -27,7 +27,6 @@ struct generic_cred {
 };
 
 static struct rpc_auth generic_auth;
-static struct rpc_cred_cache generic_cred_cache;
 static const struct rpc_credops generic_credops;
 
 /*
@@ -55,18 +54,13 @@ 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, int lookupflags)
+static struct rpc_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, lookupflags);
-	if (!IS_ERR(ret))
-		task->tk_msg.rpc_cred = ret;
-	else
-		task->tk_status = PTR_ERR(ret);
+	return auth->au_ops->lookup_cred(auth, acred, lookupflags);
 }
 
 /*
@@ -159,20 +153,16 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags)
 	return 0;
 }
 
-void __init rpc_init_generic_auth(void)
+int __init rpc_init_generic_auth(void)
 {
-	spin_lock_init(&generic_cred_cache.lock);
+	return rpcauth_init_credcache(&generic_auth);
 }
 
 void __exit rpc_destroy_generic_auth(void)
 {
-	rpcauth_clear_credcache(&generic_cred_cache);
+	rpcauth_destroy_credcache(&generic_auth);
 }
 
-static struct rpc_cred_cache generic_cred_cache = {
-	{{ NULL, },},
-};
-
 static const struct rpc_authops generic_auth_ops = {
 	.owner = THIS_MODULE,
 	.au_name = "Generic",
@@ -183,7 +173,6 @@ static const struct rpc_authops generic_auth_ops = {
 static struct rpc_auth generic_auth = {
 	.au_ops = &generic_auth_ops,
 	.au_count = ATOMIC_INIT(0),
-	.au_credcache = &generic_cred_cache,
 };
 
 static const struct rpc_credops generic_credops = {

net/sunrpc/auth_gss/auth_gss.c

@@ -373,7 +373,7 @@ gss_handle_downcall_result(struct gss_cred *gss_cred, struct gss_upcall_msg *gss
 static void
 gss_upcall_callback(struct rpc_task *task)
 {
-	struct gss_cred *gss_cred = container_of(task->tk_msg.rpc_cred,
+	struct gss_cred *gss_cred = container_of(task->tk_rqstp->rq_cred,
 			struct gss_cred, gc_base);
 	struct gss_upcall_msg *gss_msg = gss_cred->gc_upcall;
 	struct inode *inode = &gss_msg->inode->vfs_inode;
@@ -502,7 +502,7 @@ static void warn_gssd(void)
 static inline int
 gss_refresh_upcall(struct rpc_task *task)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	struct gss_auth *gss_auth = container_of(cred->cr_auth,
 			struct gss_auth, rpc_auth);
 	struct gss_cred *gss_cred = container_of(cred,
@@ -928,6 +928,7 @@ gss_do_free_ctx(struct gss_cl_ctx *ctx)
 {
 	dprintk("RPC:       gss_free_ctx\n");
 
+	gss_delete_sec_context(&ctx->gc_gss_ctx);
 	kfree(ctx->gc_wire_ctx.data);
 	kfree(ctx);
 }
@@ -942,13 +943,7 @@ gss_free_ctx_callback(struct rcu_head *head)
 static void
 gss_free_ctx(struct gss_cl_ctx *ctx)
 {
-	struct gss_ctx *gc_gss_ctx;
-
-	gc_gss_ctx = rcu_dereference(ctx->gc_gss_ctx);
-	rcu_assign_pointer(ctx->gc_gss_ctx, NULL);
 	call_rcu(&ctx->gc_rcu, gss_free_ctx_callback);
-	if (gc_gss_ctx)
-		gss_delete_sec_context(&gc_gss_ctx);
 }
 
 static void
@@ -1064,12 +1059,12 @@ gss_match(struct auth_cred *acred, struct rpc_cred *rc, int flags)
 static __be32 *
 gss_marshal(struct rpc_task *task, __be32 *p)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_rqst *req = task->tk_rqstp;
+	struct rpc_cred *cred = req->rq_cred;
 	struct gss_cred	*gss_cred = container_of(cred, struct gss_cred,
 						 gc_base);
 	struct gss_cl_ctx	*ctx = gss_cred_get_ctx(cred);
 	__be32		*cred_len;
-	struct rpc_rqst *req = task->tk_rqstp;
 	u32             maj_stat = 0;
 	struct xdr_netobj mic;
 	struct kvec	iov;
@@ -1119,7 +1114,7 @@ gss_marshal(struct rpc_task *task, __be32 *p)
 
 static int gss_renew_cred(struct rpc_task *task)
 {
-	struct rpc_cred *oldcred = task->tk_msg.rpc_cred;
+	struct rpc_cred *oldcred = task->tk_rqstp->rq_cred;
 	struct gss_cred *gss_cred = container_of(oldcred,
 						 struct gss_cred,
 						 gc_base);
@@ -1133,7 +1128,7 @@ static int gss_renew_cred(struct rpc_task *task)
 	new = gss_lookup_cred(auth, &acred, RPCAUTH_LOOKUP_NEW);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
-	task->tk_msg.rpc_cred = new;
+	task->tk_rqstp->rq_cred = new;
 	put_rpccred(oldcred);
 	return 0;
 }
@@ -1161,7 +1156,7 @@ static int gss_cred_is_negative_entry(struct rpc_cred *cred)
 static int
 gss_refresh(struct rpc_task *task)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	int ret = 0;
 
 	if (gss_cred_is_negative_entry(cred))
@@ -1172,7 +1167,7 @@ gss_refresh(struct rpc_task *task)
 		ret = gss_renew_cred(task);
 		if (ret < 0)
 			goto out;
-		cred = task->tk_msg.rpc_cred;
+		cred = task->tk_rqstp->rq_cred;
 	}
 
 	if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags))
@@ -1191,7 +1186,7 @@ gss_refresh_null(struct rpc_task *task)
 static __be32 *
 gss_validate(struct rpc_task *task, __be32 *p)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
 	__be32		seq;
 	struct kvec	iov;
@@ -1400,7 +1395,7 @@ static int
 gss_wrap_req(struct rpc_task *task,
 	     kxdrproc_t encode, void *rqstp, __be32 *p, void *obj)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	struct gss_cred	*gss_cred = container_of(cred, struct gss_cred,
 			gc_base);
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
@@ -1503,7 +1498,7 @@ static int
 gss_unwrap_resp(struct rpc_task *task,
 		kxdrproc_t decode, void *rqstp, __be32 *p, void *obj)
 {
-	struct rpc_cred *cred = task->tk_msg.rpc_cred;
+	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	struct gss_cred *gss_cred = container_of(cred, struct gss_cred,
 			gc_base);
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);

net/sunrpc/auth_null.c

@@ -75,7 +75,7 @@ nul_marshal(struct rpc_task *task, __be32 *p)
 static int
 nul_refresh(struct rpc_task *task)
 {
-	set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_msg.rpc_cred->cr_flags);
+	set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags);
 	return 0;
 }
 

net/sunrpc/auth_unix.c

@@ -29,7 +29,6 @@ struct unx_cred {
 #endif
 
 static struct rpc_auth		unix_auth;
-static struct rpc_cred_cache	unix_cred_cache;
 static const struct rpc_credops	unix_credops;
 
 static struct rpc_auth *
@@ -141,7 +140,7 @@ static __be32 *
 unx_marshal(struct rpc_task *task, __be32 *p)
 {
 	struct rpc_clnt	*clnt = task->tk_client;
-	struct unx_cred	*cred = container_of(task->tk_msg.rpc_cred, struct unx_cred, uc_base);
+	struct unx_cred	*cred = container_of(task->tk_rqstp->rq_cred, struct unx_cred, uc_base);
 	__be32		*base, *hold;
 	int		i;
 
@@ -174,7 +173,7 @@ unx_marshal(struct rpc_task *task, __be32 *p)
 static int
 unx_refresh(struct rpc_task *task)
 {
-	set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_msg.rpc_cred->cr_flags);
+	set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags);
 	return 0;
 }
 
@@ -197,15 +196,20 @@ unx_validate(struct rpc_task *task, __be32 *p)
 		printk("RPC: giant verf size: %u\n", size);
 		return NULL;
 	}
-	task->tk_msg.rpc_cred->cr_auth->au_rslack = (size >> 2) + 2;
+	task->tk_rqstp->rq_cred->cr_auth->au_rslack = (size >> 2) + 2;
 	p += (size >> 2);
 
 	return p;
 }
 
-void __init rpc_init_authunix(void)
+int __init rpc_init_authunix(void)
 {
-	spin_lock_init(&unix_cred_cache.lock);
+	return rpcauth_init_credcache(&unix_auth);
+}
+
+void rpc_destroy_authunix(void)
+{
+	rpcauth_destroy_credcache(&unix_auth);
 }
 
 const struct rpc_authops authunix_ops = {
@@ -218,10 +222,6 @@ const struct rpc_authops authunix_ops = {
 	.crcreate	= unx_create_cred,
 };
 
-static
-struct rpc_cred_cache	unix_cred_cache = {
-};
-
 static
 struct rpc_auth		unix_auth = {
 	.au_cslack	= UNX_WRITESLACK,
@@ -229,7 +229,6 @@ struct rpc_auth		unix_auth = {
 	.au_ops		= &authunix_ops,
 	.au_flavor	= RPC_AUTH_UNIX,
 	.au_count	= ATOMIC_INIT(0),
-	.au_credcache	= &unix_cred_cache,
 };
 
 static

net/sunrpc/clnt.c

@@ -413,6 +413,35 @@ rpc_clone_client(struct rpc_clnt *clnt)
 }
 EXPORT_SYMBOL_GPL(rpc_clone_client);
 
+/*
+ * Kill all tasks for the given client.
+ * XXX: kill their descendants as well?
+ */
+void rpc_killall_tasks(struct rpc_clnt *clnt)
+{
+	struct rpc_task	*rovr;
+
+
+	if (list_empty(&clnt->cl_tasks))
+		return;
+	dprintk("RPC:       killing all tasks for client %p\n", clnt);
+	/*
+	 * Spin lock all_tasks to prevent changes...
+	 */
+	spin_lock(&clnt->cl_lock);
+	list_for_each_entry(rovr, &clnt->cl_tasks, tk_task) {
+		if (!RPC_IS_ACTIVATED(rovr))
+			continue;
+		if (!(rovr->tk_flags & RPC_TASK_KILLED)) {
+			rovr->tk_flags |= RPC_TASK_KILLED;
+			rpc_exit(rovr, -EIO);
+			rpc_wake_up_queued_task(rovr->tk_waitqueue, rovr);
+		}
+	}
+	spin_unlock(&clnt->cl_lock);
+}
+EXPORT_SYMBOL_GPL(rpc_killall_tasks);
+
 /*
  * Properly shut down an RPC client, terminating all outstanding
  * requests.
@@ -538,6 +567,49 @@ struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *old,
 }
 EXPORT_SYMBOL_GPL(rpc_bind_new_program);
 
+void rpc_task_release_client(struct rpc_task *task)
+{
+	struct rpc_clnt *clnt = task->tk_client;
+
+	if (clnt != NULL) {
+		/* Remove from client task list */
+		spin_lock(&clnt->cl_lock);
+		list_del(&task->tk_task);
+		spin_unlock(&clnt->cl_lock);
+		task->tk_client = NULL;
+
+		rpc_release_client(clnt);
+	}
+}
+
+static
+void rpc_task_set_client(struct rpc_task *task, struct rpc_clnt *clnt)
+{
+	if (clnt != NULL) {
+		rpc_task_release_client(task);
+		task->tk_client = clnt;
+		kref_get(&clnt->cl_kref);
+		if (clnt->cl_softrtry)
+			task->tk_flags |= RPC_TASK_SOFT;
+		/* Add to the client's list of all tasks */
+		spin_lock(&clnt->cl_lock);
+		list_add_tail(&task->tk_task, &clnt->cl_tasks);
+		spin_unlock(&clnt->cl_lock);
+	}
+}
+
+static void
+rpc_task_set_rpc_message(struct rpc_task *task, const struct rpc_message *msg)
+{
+	if (msg != NULL) {
+		task->tk_msg.rpc_proc = msg->rpc_proc;
+		task->tk_msg.rpc_argp = msg->rpc_argp;
+		task->tk_msg.rpc_resp = msg->rpc_resp;
+		if (msg->rpc_cred != NULL)
+			task->tk_msg.rpc_cred = get_rpccred(msg->rpc_cred);
+	}
+}
+
 /*
  * Default callback for async RPC calls
  */
@@ -562,6 +634,18 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data)
 	if (IS_ERR(task))
 		goto out;
 
+	rpc_task_set_client(task, task_setup_data->rpc_client);
+	rpc_task_set_rpc_message(task, task_setup_data->rpc_message);
+
+	if (task->tk_status != 0) {
+		int ret = task->tk_status;
+		rpc_put_task(task);
+		return ERR_PTR(ret);
+	}
+
+	if (task->tk_action == NULL)
+		rpc_call_start(task);
+
 	atomic_inc(&task->tk_count);
 	rpc_execute(task);
 out:
@@ -756,12 +840,13 @@ EXPORT_SYMBOL_GPL(rpc_force_rebind);
  * Restart an (async) RPC call from the call_prepare state.
  * Usually called from within the exit handler.
  */
-void
+int
 rpc_restart_call_prepare(struct rpc_task *task)
 {
 	if (RPC_ASSASSINATED(task))
-		return;
+		return 0;
 	task->tk_action = rpc_prepare_task;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(rpc_restart_call_prepare);
 
@@ -769,13 +854,13 @@ EXPORT_SYMBOL_GPL(rpc_restart_call_prepare);
  * Restart an (async) RPC call. Usually called from within the
  * exit handler.
  */
-void
+int
 rpc_restart_call(struct rpc_task *task)
 {
 	if (RPC_ASSASSINATED(task))
-		return;
-
+		return 0;
 	task->tk_action = call_start;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(rpc_restart_call);
 
@@ -824,11 +909,6 @@ call_reserve(struct rpc_task *task)
 {
 	dprint_status(task);
 
-	if (!rpcauth_uptodatecred(task)) {
-		task->tk_action = call_refresh;
-		return;
-	}
-
 	task->tk_status  = 0;
 	task->tk_action  = call_reserveresult;
 	xprt_reserve(task);
@@ -892,7 +972,7 @@ call_reserveresult(struct rpc_task *task)
 static void
 call_allocate(struct rpc_task *task)
 {
-	unsigned int slack = task->tk_msg.rpc_cred->cr_auth->au_cslack;
+	unsigned int slack = task->tk_client->cl_auth->au_cslack;
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = task->tk_xprt;
 	struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
@@ -900,7 +980,7 @@ call_allocate(struct rpc_task *task)
 	dprint_status(task);
 
 	task->tk_status = 0;
-	task->tk_action = call_bind;
+	task->tk_action = call_refresh;
 
 	if (req->rq_buffer)
 		return;
@@ -937,6 +1017,47 @@ call_allocate(struct rpc_task *task)
 	rpc_exit(task, -ERESTARTSYS);
 }
 
+/*
+ * 2a.	Bind and/or refresh the credentials
+ */
+static void
+call_refresh(struct rpc_task *task)
+{
+	dprint_status(task);
+
+	task->tk_action = call_refreshresult;
+	task->tk_status = 0;
+	task->tk_client->cl_stats->rpcauthrefresh++;
+	rpcauth_refreshcred(task);
+}
+
+/*
+ * 2b.	Process the results of a credential refresh
+ */
+static void
+call_refreshresult(struct rpc_task *task)
+{
+	int status = task->tk_status;
+
+	dprint_status(task);
+
+	task->tk_status = 0;
+	task->tk_action = call_bind;
+	if (status >= 0 && rpcauth_uptodatecred(task))
+		return;
+	switch (status) {
+	case -EACCES:
+		rpc_exit(task, -EACCES);
+		return;
+	case -ENOMEM:
+		rpc_exit(task, -ENOMEM);
+		return;
+	case -ETIMEDOUT:
+		rpc_delay(task, 3*HZ);
+	}
+	task->tk_action = call_refresh;
+}
+
 static inline int
 rpc_task_need_encode(struct rpc_task *task)
 {
@@ -1472,43 +1593,6 @@ call_decode(struct rpc_task *task)
 	}
 }
 
-/*
- * 8.	Refresh the credentials if rejected by the server
- */
-static void
-call_refresh(struct rpc_task *task)
-{
-	dprint_status(task);
-
-	task->tk_action = call_refreshresult;
-	task->tk_status = 0;
-	task->tk_client->cl_stats->rpcauthrefresh++;
-	rpcauth_refreshcred(task);
-}
-
-/*
- * 8a.	Process the results of a credential refresh
- */
-static void
-call_refreshresult(struct rpc_task *task)
-{
-	int status = task->tk_status;
-
-	dprint_status(task);
-
-	task->tk_status = 0;
-	task->tk_action = call_reserve;
-	if (status >= 0 && rpcauth_uptodatecred(task))
-		return;
-	if (status == -EACCES) {
-		rpc_exit(task, -EACCES);
-		return;
-	}
-	task->tk_action = call_refresh;
-	if (status != -ETIMEDOUT)
-		rpc_delay(task, 3*HZ);
-}
-
 static __be32 *
 rpc_encode_header(struct rpc_task *task)
 {

net/sunrpc/sched.c

@@ -246,17 +246,8 @@ static inline void rpc_task_set_debuginfo(struct rpc_task *task)
 
 static void rpc_set_active(struct rpc_task *task)
 {
-	struct rpc_clnt *clnt;
-	if (test_and_set_bit(RPC_TASK_ACTIVE, &task->tk_runstate) != 0)
-		return;
 	rpc_task_set_debuginfo(task);
-	/* Add to global list of all tasks */
-	clnt = task->tk_client;
-	if (clnt != NULL) {
-		spin_lock(&clnt->cl_lock);
-		list_add_tail(&task->tk_task, &clnt->cl_tasks);
-		spin_unlock(&clnt->cl_lock);
-	}
+	set_bit(RPC_TASK_ACTIVE, &task->tk_runstate);
 }
 
 /*
@@ -319,11 +310,6 @@ static void __rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
 	dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n",
 			task->tk_pid, rpc_qname(q), jiffies);
 
-	if (!RPC_IS_ASYNC(task) && !RPC_IS_ACTIVATED(task)) {
-		printk(KERN_ERR "RPC: Inactive synchronous task put to sleep!\n");
-		return;
-	}
-
 	__rpc_add_wait_queue(q, task);
 
 	BUG_ON(task->tk_callback != NULL);
@@ -334,8 +320,8 @@ static void __rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
 void rpc_sleep_on(struct rpc_wait_queue *q, struct rpc_task *task,
 				rpc_action action)
 {
-	/* Mark the task as being activated if so needed */
-	rpc_set_active(task);
+	/* We shouldn't ever put an inactive task to sleep */
+	BUG_ON(!RPC_IS_ACTIVATED(task));
 
 	/*
 	 * Protect the queue operations.
@@ -405,14 +391,6 @@ void rpc_wake_up_queued_task(struct rpc_wait_queue *queue, struct rpc_task *task
 }
 EXPORT_SYMBOL_GPL(rpc_wake_up_queued_task);
 
-/*
- * Wake up the specified task
- */
-static void rpc_wake_up_task(struct rpc_task *task)
-{
-	rpc_wake_up_queued_task(task->tk_waitqueue, task);
-}
-
 /*
  * Wake up the next task on a priority queue.
  */
@@ -600,7 +578,15 @@ void rpc_exit_task(struct rpc_task *task)
 		}
 	}
 }
-EXPORT_SYMBOL_GPL(rpc_exit_task);
+
+void rpc_exit(struct rpc_task *task, int status)
+{
+	task->tk_status = status;
+	task->tk_action = rpc_exit_task;
+	if (RPC_IS_QUEUED(task))
+		rpc_wake_up_queued_task(task->tk_waitqueue, task);
+}
+EXPORT_SYMBOL_GPL(rpc_exit);
 
 void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
 {
@@ -690,7 +676,6 @@ static void __rpc_execute(struct rpc_task *task)
 			dprintk("RPC: %5u got signal\n", task->tk_pid);
 			task->tk_flags |= RPC_TASK_KILLED;
 			rpc_exit(task, -ERESTARTSYS);
-			rpc_wake_up_task(task);
 		}
 		rpc_set_running(task);
 		dprintk("RPC: %5u sync task resuming\n", task->tk_pid);
@@ -714,8 +699,9 @@ static void __rpc_execute(struct rpc_task *task)
 void rpc_execute(struct rpc_task *task)
 {
 	rpc_set_active(task);
-	rpc_set_running(task);
-	__rpc_execute(task);
+	rpc_make_runnable(task);
+	if (!RPC_IS_ASYNC(task))
+		__rpc_execute(task);
 }
 
 static void rpc_async_schedule(struct work_struct *work)
@@ -808,26 +794,9 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
 	/* Initialize workqueue for async tasks */
 	task->tk_workqueue = task_setup_data->workqueue;
 
-	task->tk_client = task_setup_data->rpc_client;
-	if (task->tk_client != NULL) {
-		kref_get(&task->tk_client->cl_kref);
-		if (task->tk_client->cl_softrtry)
-			task->tk_flags |= RPC_TASK_SOFT;
-	}
-
 	if (task->tk_ops->rpc_call_prepare != NULL)
 		task->tk_action = rpc_prepare_task;
 
-	if (task_setup_data->rpc_message != NULL) {
-		task->tk_msg.rpc_proc = task_setup_data->rpc_message->rpc_proc;
-		task->tk_msg.rpc_argp = task_setup_data->rpc_message->rpc_argp;
-		task->tk_msg.rpc_resp = task_setup_data->rpc_message->rpc_resp;
-		/* Bind the user cred */
-		rpcauth_bindcred(task, task_setup_data->rpc_message->rpc_cred, task_setup_data->flags);
-		if (task->tk_action == NULL)
-			rpc_call_start(task);
-	}
-
 	/* starting timestamp */
 	task->tk_start = ktime_get();
 
@@ -896,11 +865,8 @@ void rpc_put_task(struct rpc_task *task)
 	if (task->tk_rqstp)
 		xprt_release(task);
 	if (task->tk_msg.rpc_cred)
-		rpcauth_unbindcred(task);
-	if (task->tk_client) {
-		rpc_release_client(task->tk_client);
-		task->tk_client = NULL;
-	}
+		put_rpccred(task->tk_msg.rpc_cred);
+	rpc_task_release_client(task);
 	if (task->tk_workqueue != NULL) {
 		INIT_WORK(&task->u.tk_work, rpc_async_release);
 		queue_work(task->tk_workqueue, &task->u.tk_work);
@@ -913,13 +879,6 @@ static void rpc_release_task(struct rpc_task *task)
 {
 	dprintk("RPC: %5u release task\n", task->tk_pid);
 
-	if (!list_empty(&task->tk_task)) {
-		struct rpc_clnt *clnt = task->tk_client;
-		/* Remove from client task list */
-		spin_lock(&clnt->cl_lock);
-		list_del(&task->tk_task);
-		spin_unlock(&clnt->cl_lock);
-	}
 	BUG_ON (RPC_IS_QUEUED(task));
 
 	/* Wake up anyone who is waiting for task completion */
@@ -928,35 +887,6 @@ static void rpc_release_task(struct rpc_task *task)
 	rpc_put_task(task);
 }
 
-/*
- * Kill all tasks for the given client.
- * XXX: kill their descendants as well?
- */
-void rpc_killall_tasks(struct rpc_clnt *clnt)
-{
-	struct rpc_task	*rovr;
-
-
-	if (list_empty(&clnt->cl_tasks))
-		return;
-	dprintk("RPC:       killing all tasks for client %p\n", clnt);
-	/*
-	 * Spin lock all_tasks to prevent changes...
-	 */
-	spin_lock(&clnt->cl_lock);
-	list_for_each_entry(rovr, &clnt->cl_tasks, tk_task) {
-		if (! RPC_IS_ACTIVATED(rovr))
-			continue;
-		if (!(rovr->tk_flags & RPC_TASK_KILLED)) {
-			rovr->tk_flags |= RPC_TASK_KILLED;
-			rpc_exit(rovr, -EIO);
-			rpc_wake_up_task(rovr);
-		}
-	}
-	spin_unlock(&clnt->cl_lock);
-}
-EXPORT_SYMBOL_GPL(rpc_killall_tasks);
-
 int rpciod_up(void)
 {
 	return try_module_get(THIS_MODULE) ? 0 : -EINVAL;

net/sunrpc/sunrpc_syms.c

@@ -33,10 +33,11 @@ init_sunrpc(void)
 	if (err)
 		goto out;
 	err = rpc_init_mempool();
-	if (err) {
-		unregister_rpc_pipefs();
-		goto out;
-	}
+	if (err)
+		goto out2;
+	err = rpcauth_init_module();
+	if (err)
+		goto out3;
 #ifdef RPC_DEBUG
 	rpc_register_sysctl();
 #endif
@@ -47,7 +48,11 @@ init_sunrpc(void)
 	cache_register(&unix_gid_cache);
 	svc_init_xprt_sock();	/* svc sock transport */
 	init_socket_xprt();	/* clnt sock transport */
-	rpcauth_init_module();
+	return 0;
+out3:
+	rpc_destroy_mempool();
+out2:
+	unregister_rpc_pipefs();
 out:
 	return err;
 }

net/sunrpc/xprt.c

@@ -1032,6 +1032,8 @@ void xprt_release(struct rpc_task *task)
 	spin_unlock_bh(&xprt->transport_lock);
 	if (req->rq_buffer)
 		xprt->ops->buf_free(req->rq_buffer);
+	if (req->rq_cred != NULL)
+		put_rpccred(req->rq_cred);
 	task->tk_rqstp = NULL;
 	if (req->rq_release_snd_buf)
 		req->rq_release_snd_buf(req);
@@ -1129,6 +1131,7 @@ static void xprt_destroy(struct kref *kref)
 	rpc_destroy_wait_queue(&xprt->sending);
 	rpc_destroy_wait_queue(&xprt->resend);
 	rpc_destroy_wait_queue(&xprt->backlog);
+	cancel_work_sync(&xprt->task_cleanup);
 	/*
 	 * Tear down transport state and free the rpc_xprt
 	 */