Merge tag 'nfs-for-3.9-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:
 "We've just concluded another Connectathon interoperability testing
  week, and so here are the fixes for the bugs that were discovered:

   - Don't allow NFS silly-renamed files to be deleted
   - Don't start the retransmission timer when out of socket space
   - Fix a couple of pnfs-related Oopses.
   - Fix one more NFSv4 state recovery deadlock
   - Don't loop forever when LAYOUTGET returns NFS4ERR_LAYOUTTRYLATER"

* tag 'nfs-for-3.9-2' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  SUNRPC: One line comment fix
  NFSv4.1: LAYOUTGET EDELAY loops timeout to the MDS
  SUNRPC: add call to get configured timeout
  PNFS: set the default DS timeout to 60 seconds
  NFSv4: Fix another open/open_recovery deadlock
  nfs: don't allow nfs_find_actor to match inodes of the wrong type
  NFSv4.1: Hold reference to layout hdr in layoutget
  pnfs: fix resend_to_mds for directio
  SUNRPC: Don't start the retransmission timer when out of socket space
  NFS: Don't allow NFS silly-renamed files to be deleted, no signal

11 files changed, 77 insertions, 24 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b586fe9af47..1f941674b08 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -237,6 +237,8 @@ nfs_find_actor(struct inode *inode, void *opaque)
 
 	if (NFS_FILEID(inode) != fattr->fileid)
 		return 0;
+	if ((S_IFMT & inode->i_mode) != (S_IFMT & fattr->mode))
+		return 0;
 	if (nfs_compare_fh(NFS_FH(inode), fh))
 		return 0;
 	if (is_bad_inode(inode) || NFS_STALE(inode))
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 194c4841033..49eeb044c10 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -99,7 +99,8 @@ static void filelayout_reset_write(struct nfs_write_data *data)
 
 		task->tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
 							&hdr->pages,
-							hdr->completion_ops);
+							hdr->completion_ops,
+							hdr->dreq);
 	}
 }
 
@@ -119,7 +120,8 @@ static void filelayout_reset_read(struct nfs_read_data *data)
 
 		task->tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
 							&hdr->pages,
-							hdr->completion_ops);
+							hdr->completion_ops,
+							hdr->dreq);
 	}
 }
 
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 8c07241fe52..b8da95548d3 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -36,7 +36,7 @@
  * Default data server connection timeout and retrans vaules.
  * Set by module paramters dataserver_timeo and dataserver_retrans.
  */
-#define NFS4_DEF_DS_TIMEO   60
+#define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
 #define NFS4_DEF_DS_RETRANS 5
 
 /*
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index eae83bf96c6..b2671cb0f90 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -93,6 +93,8 @@ static int nfs4_map_errors(int err)
 		return err;
 	switch (err) {
 	case -NFS4ERR_RESOURCE:
+	case -NFS4ERR_LAYOUTTRYLATER:
+	case -NFS4ERR_RECALLCONFLICT:
 		return -EREMOTEIO;
 	case -NFS4ERR_WRONGSEC:
 		return -EPERM;
@@ -1158,6 +1160,7 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
 			data->o_arg.fmode);
 	iput(inode);
 out:
+	nfs_release_seqid(data->o_arg.seqid);
 	return state;
 err_put_inode:
 	iput(inode);
@@ -6045,6 +6048,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layout_hdr *lo;
 	struct nfs4_state *state = NULL;
+	unsigned long timeo, giveup;
 
 	dprintk("--> %s\n", __func__);
 
@@ -6056,7 +6060,10 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
 		goto out;
 	case -NFS4ERR_LAYOUTTRYLATER:
 	case -NFS4ERR_RECALLCONFLICT:
-		task->tk_status = -NFS4ERR_DELAY;
+		timeo = rpc_get_timeout(task->tk_client);
+		giveup = lgp->args.timestamp + timeo;
+		if (time_after(giveup, jiffies))
+			task->tk_status = -NFS4ERR_DELAY;
 		break;
 	case -NFS4ERR_EXPIRED:
 	case -NFS4ERR_BAD_STATEID:
@@ -6129,11 +6136,13 @@ static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags)
 static void nfs4_layoutget_release(void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
-	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	struct inode *inode = lgp->args.inode;
+	struct nfs_server *server = NFS_SERVER(inode);
 	size_t max_pages = max_response_pages(server);
 
 	dprintk("--> %s\n", __func__);
 	nfs4_free_pages(lgp->args.layout.pages, max_pages);
+	pnfs_put_layout_hdr(NFS_I(inode)->layout);
 	put_nfs_open_context(lgp->args.ctx);
 	kfree(calldata);
 	dprintk("<-- %s\n", __func__);
@@ -6148,7 +6157,8 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
 struct pnfs_layout_segment *
 nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 {
-	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
+	struct inode *inode = lgp->args.inode;
+	struct nfs_server *server = NFS_SERVER(inode);
 	size_t max_pages = max_response_pages(server);
 	struct rpc_task *task;
 	struct rpc_message msg = {
@@ -6174,10 +6184,15 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
 		return ERR_PTR(-ENOMEM);
 	}
 	lgp->args.layout.pglen = max_pages * PAGE_SIZE;
+	lgp->args.timestamp = jiffies;
 
 	lgp->res.layoutp = &lgp->args.layout;
 	lgp->res.seq_res.sr_slot = NULL;
 	nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0);
+
+	/* nfs4_layoutget_release calls pnfs_put_layout_hdr */
+	pnfs_get_layout_hdr(NFS_I(inode)->layout);
+
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return ERR_CAST(task);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 6be70f622b6..48ac5aad625 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1181,7 +1181,7 @@ pnfs_update_layout(struct inode *ino,
 	struct nfs_client *clp = server->nfs_client;
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg = NULL;
-	bool first = false;
+	bool first;
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
 		goto out;
@@ -1215,10 +1215,9 @@ pnfs_update_layout(struct inode *ino,
 		goto out_unlock;
 	atomic_inc(&lo->plh_outstanding);
 
-	if (list_empty(&lo->plh_segs))
-		first = true;
-
+	first = list_empty(&lo->plh_layouts) ? true : false;
 	spin_unlock(&ino->i_lock);
+
 	if (first) {
 		/* The lo must be on the clp list if there is any
 		 * chance of a CB_LAYOUTRECALL(FILE) coming in.
@@ -1422,13 +1421,15 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 
 int pnfs_write_done_resend_to_mds(struct inode *inode,
 				struct list_head *head,
-				const struct nfs_pgio_completion_ops *compl_ops)
+				const struct nfs_pgio_completion_ops *compl_ops,
+				struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor pgio;
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
 	nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops);
+	pgio.pg_dreq = dreq;
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1463,7 +1464,8 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
 		data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
 							&hdr->pages,
-							hdr->completion_ops);
+							hdr->completion_ops,
+							hdr->dreq);
 }
 
 /*
@@ -1578,13 +1580,15 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
 
 int pnfs_read_done_resend_to_mds(struct inode *inode,
 				struct list_head *head,
-				const struct nfs_pgio_completion_ops *compl_ops)
+				const struct nfs_pgio_completion_ops *compl_ops,
+				struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor pgio;
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
 	nfs_pageio_init_read(&pgio, inode, compl_ops);
+	pgio.pg_dreq = dreq;
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1615,7 +1619,8 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
 	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
 		data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
 							&hdr->pages,
-							hdr->completion_ops);
+							hdr->completion_ops,
+							hdr->dreq);
 }
 
 /*
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 97cb358bb88..94ba8041774 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -230,9 +230,11 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 
 void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
 int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head,
-			const struct nfs_pgio_completion_ops *compl_ops);
+			const struct nfs_pgio_completion_ops *compl_ops,
+			struct nfs_direct_req *dreq);
 int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head,
-			const struct nfs_pgio_completion_ops *compl_ops);
+			const struct nfs_pgio_completion_ops *compl_ops,
+			struct nfs_direct_req *dreq);
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
 
 /* nfs4_deviceid_flags */
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index d26a32f5b53..1f1f38f0c5d 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -335,20 +335,14 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 	struct inode *old_dir = data->old_dir;
 	struct inode *new_dir = data->new_dir;
 	struct dentry *old_dentry = data->old_dentry;
-	struct dentry *new_dentry = data->new_dentry;
 
 	if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) {
 		rpc_restart_call_prepare(task);
 		return;
 	}
 
-	if (task->tk_status != 0) {
+	if (task->tk_status != 0)
 		nfs_cancel_async_unlink(old_dentry);
-		return;
-	}
-
-	d_drop(old_dentry);
-	d_drop(new_dentry);
 }
 
 /**
@@ -549,6 +543,18 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 	error = rpc_wait_for_completion_task(task);
 	if (error == 0)
 		error = task->tk_status;
+	switch (error) {
+	case 0:
+		/* The rename succeeded */
+		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+		d_move(dentry, sdentry);
+		break;
+	case -ERESTARTSYS:
+		/* The result of the rename is unknown. Play it safe by
+		 * forcing a new lookup */
+		d_drop(dentry);
+		d_drop(sdentry);
+	}
 	rpc_put_task(task);
 out_dput:
 	dput(sdentry);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 13441ddac33..4b993d358da 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -233,6 +233,7 @@ struct nfs4_layoutget_args {
 	struct inode *inode;
 	struct nfs_open_context *ctx;
 	nfs4_stateid stateid;
+	unsigned long timestamp;
 	struct nfs4_layoutdriver_data layout;
 };
 
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 4a4abde000c..2cf4ffaa3cd 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -160,6 +160,7 @@ void		rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
 int		rpc_protocol(struct rpc_clnt *);
 struct net *	rpc_net_ns(struct rpc_clnt *);
 size_t		rpc_max_payload(struct rpc_clnt *);
+unsigned long	rpc_get_timeout(struct rpc_clnt *clnt);
 void		rpc_force_rebind(struct rpc_clnt *);
 size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
 const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index d7a369e6108..dcc446e7fbf 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1197,6 +1197,21 @@ size_t rpc_max_payload(struct rpc_clnt *clnt)
 EXPORT_SYMBOL_GPL(rpc_max_payload);
 
 /**
+ * rpc_get_timeout - Get timeout for transport in units of HZ
+ * @clnt: RPC client to query
+ */
+unsigned long rpc_get_timeout(struct rpc_clnt *clnt)
+{
+	unsigned long ret;
+
+	rcu_read_lock();
+	ret = rcu_dereference(clnt->cl_xprt)->timeout->to_initval;
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rpc_get_timeout);
+
+/**
  * rpc_force_rebind - force transport to check that remote port is unchanged
  * @clnt: client to rebind
  *
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 846c34fdee9..b7478d5e7ff 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -487,13 +487,17 @@ EXPORT_SYMBOL_GPL(xprt_wake_pending_tasks);
  * xprt_wait_for_buffer_space - wait for transport output buffer to clear
  * @task: task to be put to sleep
  * @action: function pointer to be executed after wait
+ *
+ * Note that we only set the timer for the case of RPC_IS_SOFT(), since
+ * we don't in general want to force a socket disconnection due to
+ * an incomplete RPC call transmission.
  */
 void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 
-	task->tk_timeout = req->rq_timeout;
+	task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0;
 	rpc_sleep_on(&xprt->pending, task, action);
 }
 EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space);