Merge tag 'nfs-for-3.20-1' of git://git.linux-nfs.org/projects/trondm…

…y/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights incluse:

  Features:
   - Removing the forced serialisation of open()/close() calls in
     NFSv4.x (x>0) makes for a significant performance improvement in
     metadata intensive workloads.
   - Full support for the pNFS "flexible files" layout type
   - Further RPC/RDMA client improvements from Chuck

  Bugfixes:
   - Stable fix: NFSv4.1 backchannel calls blocking operations with !TASK_RUNNING
   - Stable fix: pnfs_generic_pg_init_read/write can be called with lseg == NULL
   - Stable fix: Fix an Oopsable condition when nsm_mon_unmon is called
     as part of the namespace cleanup,
   - Stable fix: Ensure we reference the inode for return-on-close in
     delegreturn
   - Use SO_REUSEPORT to ensure that NFSv3 TCP connections can rebind to
     the same source address/port combination during a disconnect/
     reconnect event.  This is a requirement imposed by most NFSv3
     server duplicate reply cache implementations.

  Optimisations:
   - Ask for no NFSv4.1 delegations on OPEN if using O_DIRECT

  Other:
   - Add Anna Schumaker as co-maintainer for the NFS client"

* tag 'nfs-for-3.20-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (119 commits)
  SUNRPC: Cleanup to remove xs_tcp_close()
  pnfs: delete an unintended goto
  pnfs/flexfiles: Do not dprintk after the free
  SUNRPC: Fix stupid typo in xs_sock_set_reuseport
  SUNRPC: Define xs_tcp_fin_timeout only if CONFIG_SUNRPC_DEBUG
  SUNRPC: Handle connection reset more efficiently.
  SUNRPC: Remove the redundant XPRT_CONNECTION_CLOSE flag
  SUNRPC: Make xs_tcp_close() do a socket shutdown rather than a sock_release
  SUNRPC: Ensure xs_tcp_shutdown() requests a full close of the connection
  SUNRPC: Cleanup to remove remaining uses of XPRT_CONNECTION_ABORT
  SUNRPC: Remove TCP socket linger code
  SUNRPC: Remove TCP client connection reset hack
  SUNRPC: TCP/UDP always close the old socket before reconnecting
  SUNRPC: Add helpers to prevent socket create from racing
  SUNRPC: Ensure xs_reset_transport() resets the close connection flags
  SUNRPC: Do not clear the source port in xs_reset_transport
  SUNRPC: Handle EADDRINUSE on connect
  SUNRPC: Set SO_REUSEPORT socket option for TCP connections
  NFSv4.1: Fix pnfs_put_lseg races
  NFSv4.1: pnfs_send_layoutreturn should use GFP_NOFS
  ...

Documentation/filesystems/nfs/pnfs.txt

@@ -57,15 +57,16 @@ bit is set, preventing any new lsegs from being added.
 layout drivers
 --------------
 
-PNFS utilizes what is called layout drivers. The STD defines 3 basic
-layout types: "files" "objects" and "blocks". For each of these types
-there is a layout-driver with a common function-vectors table which
-are called by the nfs-client pnfs-core to implement the different layout
-types.
+PNFS utilizes what is called layout drivers. The STD defines 4 basic
+layout types: "files", "objects", "blocks", and "flexfiles". For each
+of these types there is a layout-driver with a common function-vectors
+table which are called by the nfs-client pnfs-core to implement the
+different layout types.
 
-Files-layout-driver code is in: fs/nfs/nfs4filelayout.c && nfs4filelayoutdev.c
+Files-layout-driver code is in: fs/nfs/filelayout/.. directory
 Objects-layout-deriver code is in: fs/nfs/objlayout/.. directory
 Blocks-layout-deriver code is in: fs/nfs/blocklayout/.. directory
+Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
 
 objects-layout setup
 --------------------

MAINTAINERS

@@ -6777,6 +6777,7 @@ F:	Documentation/devicetree/bindings/net/nfc/
 
 NFS, SUNRPC, AND LOCKD CLIENTS
 M:	Trond Myklebust <[email protected]>
+M:	Anna Schumaker <[email protected]>
 L:	[email protected]
 W:	http://client.linux-nfs.org
 T:	git git://git.linux-nfs.org/projects/trondmy/linux-nfs.git

fs/lockd/mon.c

@@ -65,7 +65,7 @@ static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
 	return (struct sockaddr *)&nsm->sm_addr;
 }
 
-static struct rpc_clnt *nsm_create(struct net *net)
+static struct rpc_clnt *nsm_create(struct net *net, const char *nodename)
 {
 	struct sockaddr_in sin = {
 		.sin_family		= AF_INET,
@@ -77,6 +77,7 @@ static struct rpc_clnt *nsm_create(struct net *net)
 		.address		= (struct sockaddr *)&sin,
 		.addrsize		= sizeof(sin),
 		.servername		= "rpc.statd",
+		.nodename		= nodename,
 		.program		= &nsm_program,
 		.version		= NSM_VERSION,
 		.authflavor		= RPC_AUTH_NULL,
@@ -102,7 +103,7 @@ static struct rpc_clnt *nsm_client_set(struct lockd_net *ln,
 	return clnt;
 }
 
-static struct rpc_clnt *nsm_client_get(struct net *net)
+static struct rpc_clnt *nsm_client_get(struct net *net, const char *nodename)
 {
 	struct rpc_clnt	*clnt, *new;
 	struct lockd_net *ln = net_generic(net, lockd_net_id);
@@ -111,7 +112,7 @@ static struct rpc_clnt *nsm_client_get(struct net *net)
 	if (clnt != NULL)
 		goto out;
 
-	clnt = new = nsm_create(net);
+	clnt = new = nsm_create(net, nodename);
 	if (IS_ERR(clnt))
 		goto out;
 
@@ -190,19 +191,23 @@ int nsm_monitor(const struct nlm_host *host)
 	struct nsm_res	res;
 	int		status;
 	struct rpc_clnt *clnt;
+	const char *nodename = NULL;
 
 	dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
 
 	if (nsm->sm_monitored)
 		return 0;
 
+	if (host->h_rpcclnt)
+		nodename = host->h_rpcclnt->cl_nodename;
+
 	/*
 	 * Choose whether to record the caller_name or IP address of
 	 * this peer in the local rpc.statd's database.
 	 */
 	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
-	clnt = nsm_client_get(host->net);
+	clnt = nsm_client_get(host->net, nodename);
 	if (IS_ERR(clnt)) {
 		status = PTR_ERR(clnt);
 		dprintk("lockd: failed to create NSM upcall transport, "

fs/nfs/Kconfig

@@ -128,6 +128,11 @@ config PNFS_OBJLAYOUT
 	depends on NFS_V4_1 && SCSI_OSD_ULD
 	default NFS_V4
 
+config PNFS_FLEXFILE_LAYOUT
+	tristate
+	depends on NFS_V4_1 && NFS_V3
+	default m
+
 config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
 	string "NFSv4.1 Implementation ID Domain"
 	depends on NFS_V4_1

fs/nfs/Makefile

@@ -27,9 +27,10 @@ nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o
 	  dns_resolve.o nfs4trace.o
 nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
-nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
+nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
 nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
+obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/

fs/nfs/blocklayout/blocklayout.c

@@ -860,12 +860,14 @@ static const struct nfs_pageio_ops bl_pg_read_ops = {
 	.pg_init = bl_pg_init_read,
 	.pg_test = bl_pg_test_read,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
 	.pg_init = bl_pg_init_write,
 	.pg_test = bl_pg_test_write,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static struct pnfs_layoutdriver_type blocklayout_type = {

fs/nfs/callback.c

@@ -128,22 +128,24 @@ nfs41_callback_svc(void *vrqstp)
 		if (try_to_freeze())
 			continue;
 
-		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
+		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_UNINTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
 		if (!list_empty(&serv->sv_cb_list)) {
 			req = list_first_entry(&serv->sv_cb_list,
 					struct rpc_rqst, rq_bc_list);
 			list_del(&req->rq_bc_list);
 			spin_unlock_bh(&serv->sv_cb_lock);
+			finish_wait(&serv->sv_cb_waitq, &wq);
 			dprintk("Invoking bc_svc_process()\n");
 			error = bc_svc_process(serv, req, rqstp);
 			dprintk("bc_svc_process() returned w/ error code= %d\n",
 				error);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
-			schedule();
+			/* schedule_timeout to game the hung task watchdog */
+			schedule_timeout(60 * HZ);
+			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
-		finish_wait(&serv->sv_cb_waitq, &wq);
 	}
 	return 0;
 }

fs/nfs/delegation.c

@@ -306,6 +306,17 @@ nfs_inode_detach_delegation(struct inode *inode)
 	return nfs_detach_delegation(nfsi, delegation, server);
 }
 
+static void
+nfs_update_inplace_delegation(struct nfs_delegation *delegation,
+		const struct nfs_delegation *update)
+{
+	if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) {
+		delegation->stateid.seqid = update->stateid.seqid;
+		smp_wmb();
+		delegation->type = update->type;
+	}
+}
+
 /**
  * nfs_inode_set_delegation - set up a delegation on an inode
  * @inode: inode to which delegation applies
@@ -339,9 +350,12 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct
 	old_delegation = rcu_dereference_protected(nfsi->delegation,
 					lockdep_is_held(&clp->cl_lock));
 	if (old_delegation != NULL) {
-		if (nfs4_stateid_match(&delegation->stateid,
-					&old_delegation->stateid) &&
-				delegation->type == old_delegation->type) {
+		/* Is this an update of the existing delegation? */
+		if (nfs4_stateid_match_other(&old_delegation->stateid,
+					&delegation->stateid)) {
+			nfs_update_inplace_delegation(old_delegation,
+					delegation);
+			nfsi->delegation_state = old_delegation->type;
 			goto out;
 		}
 		/*