Merge tag 'nfs-for-3.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

   - stable fix for an infinite loop in RPC state machine
   - stable fix for a use after free situation in the NFSv4 trunking discovery
   - stable fix for error handling in the NFSv4 trunking discovery
   - stable fix for the page write update code
   - stable fix for the NFSv4.1 mount time security negotiation
   - stable fix for the NFSv4 open code.
   - O_DIRECT locking fixes
   - fix an Oops in the pnfs file commit code
   - RPC layer needs finer grained handling of connection errors
   - more RPC GSS upcall fixes"

* tag 'nfs-for-3.14-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (30 commits)
  pnfs: Proper delay for NFS4ERR_RECALLCONFLICT in layout_get_done
  pnfs: fix BUG in filelayout_recover_commit_reqs
  nfs4: fix discover_server_trunking use after free
  NFSv4.1: Handle errors correctly in nfs41_walk_client_list
  nfs: always make sure page is up-to-date before extending a write to cover the entire page
  nfs: page cache invalidation for dio
  nfs: take i_mutex during direct I/O reads
  nfs: merge nfs_direct_write into nfs_file_direct_write
  nfs: merge nfs_direct_read into nfs_file_direct_read
  nfs: increment i_dio_count for reads, too
  nfs: defer inode_dio_done call until size update is done
  nfs: fix size updates for aio writes
  nfs4.1: properly handle ENOTSUP in SECINFO_NO_NAME
  NFSv4.1: Fix a race in nfs4_write_inode
  NFSv4.1: Don't trust attributes if a pNFS LAYOUTCOMMIT is outstanding
  point to the right include file in a comment (left over from a9004abc3)
  NFS: dprintk() should not print negative fileids and inode numbers
  nfs: fix dead code of ipv6_addr_scope
  sunrpc: Fix infinite loop in RPC state machine
  SUNRPC: Add tracepoint for socket errors
  ...

7 files changed, 231 insertions, 28 deletions

diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 42fdfc6..0a2aee0 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -536,8 +536,7 @@ static void warn_gssd(void)
 	unsigned long now = jiffies;
 
 	if (time_after(now, ratelimit)) {
-		printk(KERN_WARNING "RPC: AUTH_GSS upcall timed out.\n"
-				"Please check user daemon is running.\n");
+		pr_warn("RPC: AUTH_GSS upcall failed. Please check user daemon is running.\n");
 		ratelimit = now + 15*HZ;
 	}
 }
@@ -600,7 +599,6 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
 	struct rpc_pipe *pipe;
 	struct rpc_cred *cred = &gss_cred->gc_base;
 	struct gss_upcall_msg *gss_msg;
-	unsigned long timeout;
 	DEFINE_WAIT(wait);
 	int err;
 
@@ -608,17 +606,16 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
 		__func__, from_kuid(&init_user_ns, cred->cr_uid));
 retry:
 	err = 0;
-	/* Default timeout is 15s unless we know that gssd is not running */
-	timeout = 15 * HZ;
-	if (!sn->gssd_running)
-		timeout = HZ >> 2;
+	/* if gssd is down, just skip upcalling altogether */
+	if (!gssd_running(net)) {
+		warn_gssd();
+		return -EACCES;
+	}
 	gss_msg = gss_setup_upcall(gss_auth, cred);
 	if (PTR_ERR(gss_msg) == -EAGAIN) {
 		err = wait_event_interruptible_timeout(pipe_version_waitqueue,
-				sn->pipe_version >= 0, timeout);
+				sn->pipe_version >= 0, 15 * HZ);
 		if (sn->pipe_version < 0) {
-			if (err == 0)
-				sn->gssd_running = 0;
 			warn_gssd();
 			err = -EACCES;
 		}
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index f09b7db..0edada9 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1529,9 +1529,13 @@ call_refreshresult(struct rpc_task *task)
 	task->tk_action = call_refresh;
 	switch (status) {
 	case 0:
-		if (rpcauth_uptodatecred(task))
+		if (rpcauth_uptodatecred(task)) {
 			task->tk_action = call_allocate;
-		return;
+			return;
+		}
+		/* Use rate-limiting and a max number of retries if refresh
+		 * had status 0 but failed to update the cred.
+		 */
 	case -ETIMEDOUT:
 		rpc_delay(task, 3*HZ);
 	case -EAGAIN:
@@ -1729,6 +1733,7 @@ call_bind_status(struct rpc_task *task)
 		return;
 	case -ECONNREFUSED:		/* connection problems */
 	case -ECONNRESET:
+	case -ECONNABORTED:
 	case -ENOTCONN:
 	case -EHOSTDOWN:
 	case -EHOSTUNREACH:
@@ -1799,7 +1804,9 @@ call_connect_status(struct rpc_task *task)
 		return;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
+	case -ECONNABORTED:
 	case -ENETUNREACH:
+	case -EHOSTUNREACH:
 		/* retry with existing socket, after a delay */
 		rpc_delay(task, 3*HZ);
 		if (RPC_IS_SOFTCONN(task))
@@ -1902,6 +1909,7 @@ call_transmit_status(struct rpc_task *task)
 			break;
 		}
 	case -ECONNRESET:
+	case -ECONNABORTED:
 	case -ENOTCONN:
 	case -EPIPE:
 		rpc_task_force_reencode(task);
@@ -2011,8 +2019,9 @@ call_status(struct rpc_task *task)
 			xprt_conditional_disconnect(req->rq_xprt,
 					req->rq_connect_cookie);
 		break;
-	case -ECONNRESET:
 	case -ECONNREFUSED:
+	case -ECONNRESET:
+	case -ECONNABORTED:
 		rpc_force_rebind(clnt);
 		rpc_delay(task, 3*HZ);
 	case -EPIPE:
diff --git a/net/sunrpc/netns.h b/net/sunrpc/netns.h
index 779742c..94e506f 100644
--- a/net/sunrpc/netns.h
+++ b/net/sunrpc/netns.h
@@ -14,6 +14,7 @@ struct sunrpc_net {
 	struct cache_detail *rsi_cache;
 
 	struct super_block *pipefs_sb;
+	struct rpc_pipe *gssd_dummy;
 	struct mutex pipefs_sb_lock;
 
 	struct list_head all_clients;
@@ -32,8 +33,6 @@ struct sunrpc_net {
 	int pipe_version;
 	atomic_t pipe_users;
 	struct proc_dir_entry *use_gssp_proc;
-
-	unsigned int gssd_running;
 };
 
 extern int sunrpc_net_id;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index bf04b30..b185548 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -17,6 +17,7 @@
 #include <linux/fsnotify.h>
 #include <linux/kernel.h>
 #include <linux/rcupdate.h>
+#include <linux/utsname.h>
 
 #include <asm/ioctls.h>
 #include <linux/poll.h>
@@ -38,7 +39,7 @@
 #define NET_NAME(net)	((net == &init_net) ? " (init_net)" : "")
 
 static struct file_system_type rpc_pipe_fs_type;
-
+static const struct rpc_pipe_ops gssd_dummy_pipe_ops;
 
 static struct kmem_cache *rpc_inode_cachep __read_mostly;
 
@@ -216,14 +217,11 @@ rpc_destroy_inode(struct inode *inode)
 static int
 rpc_pipe_open(struct inode *inode, struct file *filp)
 {
-	struct net *net = inode->i_sb->s_fs_info;
-	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	struct rpc_pipe *pipe;
 	int first_open;
 	int res = -ENXIO;
 
 	mutex_lock(&inode->i_mutex);
-	sn->gssd_running = 1;
 	pipe = RPC_I(inode)->pipe;
 	if (pipe == NULL)
 		goto out;
@@ -1159,6 +1157,7 @@ enum {
 	RPCAUTH_nfsd4_cb,
 	RPCAUTH_cache,
 	RPCAUTH_nfsd,
+	RPCAUTH_gssd,
 	RPCAUTH_RootEOF
 };
 
@@ -1195,6 +1194,10 @@ static const struct rpc_filelist files[] = {
 		.name = "nfsd",
 		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
 	},
+	[RPCAUTH_gssd] = {
+		.name = "gssd",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
 };
 
 /*
@@ -1208,13 +1211,24 @@ struct dentry *rpc_d_lookup_sb(const struct super_block *sb,
 }
 EXPORT_SYMBOL_GPL(rpc_d_lookup_sb);
 
-void rpc_pipefs_init_net(struct net *net)
+int rpc_pipefs_init_net(struct net *net)
 {
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 
+	sn->gssd_dummy = rpc_mkpipe_data(&gssd_dummy_pipe_ops, 0);
+	if (IS_ERR(sn->gssd_dummy))
+		return PTR_ERR(sn->gssd_dummy);
+
 	mutex_init(&sn->pipefs_sb_lock);
-	sn->gssd_running = 1;
 	sn->pipe_version = -1;
+	return 0;
+}
+
+void rpc_pipefs_exit_net(struct net *net)
+{
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+
+	rpc_destroy_pipe_data(sn->gssd_dummy);
 }
 
 /*
@@ -1244,11 +1258,134 @@ void rpc_put_sb_net(const struct net *net)
 }
 EXPORT_SYMBOL_GPL(rpc_put_sb_net);
 
+static const struct rpc_filelist gssd_dummy_clnt_dir[] = {
+	[0] = {
+		.name = "clntXX",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+};
+
+static ssize_t
+dummy_downcall(struct file *filp, const char __user *src, size_t len)
+{
+	return -EINVAL;
+}
+
+static const struct rpc_pipe_ops gssd_dummy_pipe_ops = {
+	.upcall		= rpc_pipe_generic_upcall,
+	.downcall	= dummy_downcall,
+};
+
+/*
+ * Here we present a bogus "info" file to keep rpc.gssd happy. We don't expect
+ * that it will ever use this info to handle an upcall, but rpc.gssd expects
+ * that this file will be there and have a certain format.
+ */
+static int
+rpc_show_dummy_info(struct seq_file *m, void *v)
+{
+	seq_printf(m, "RPC server: %s\n", utsname()->nodename);
+	seq_printf(m, "service: foo (1) version 0\n");
+	seq_printf(m, "address: 127.0.0.1\n");
+	seq_printf(m, "protocol: tcp\n");
+	seq_printf(m, "port: 0\n");
+	return 0;
+}
+
+static int
+rpc_dummy_info_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, rpc_show_dummy_info, NULL);
+}
+
+static const struct file_operations rpc_dummy_info_operations = {
+	.owner		= THIS_MODULE,
+	.open		= rpc_dummy_info_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const struct rpc_filelist gssd_dummy_info_file[] = {
+	[0] = {
+		.name = "info",
+		.i_fop = &rpc_dummy_info_operations,
+		.mode = S_IFREG | S_IRUSR,
+	},
+};
+
+/**
+ * rpc_gssd_dummy_populate - create a dummy gssd pipe
+ * @root:	root of the rpc_pipefs filesystem
+ * @pipe_data:	pipe data created when netns is initialized
+ *
+ * Create a dummy set of directories and a pipe that gssd can hold open to
+ * indicate that it is up and running.
+ */
+static struct dentry *
+rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
+{
+	int ret = 0;
+	struct dentry *gssd_dentry;
+	struct dentry *clnt_dentry = NULL;
+	struct dentry *pipe_dentry = NULL;
+	struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name,
+				  strlen(files[RPCAUTH_gssd].name));
+
+	/* We should never get this far if "gssd" doesn't exist */
+	gssd_dentry = d_hash_and_lookup(root, &q);
+	if (!gssd_dentry)
+		return ERR_PTR(-ENOENT);
+
+	ret = rpc_populate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1, NULL);
+	if (ret) {
+		pipe_dentry = ERR_PTR(ret);
+		goto out;
+	}
+
+	q.name = gssd_dummy_clnt_dir[0].name;
+	q.len = strlen(gssd_dummy_clnt_dir[0].name);
+	clnt_dentry = d_hash_and_lookup(gssd_dentry, &q);
+	if (!clnt_dentry) {
+		pipe_dentry = ERR_PTR(-ENOENT);
+		goto out;
+	}
+
+	ret = rpc_populate(clnt_dentry, gssd_dummy_info_file, 0, 1, NULL);
+	if (ret) {
+		__rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
+		pipe_dentry = ERR_PTR(ret);
+		goto out;
+	}
+
+	pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data);
+	if (IS_ERR(pipe_dentry)) {
+		__rpc_depopulate(clnt_dentry, gssd_dummy_info_file, 0, 1);
+		__rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1);
+	}
+out:
+	dput(clnt_dentry);
+	dput(gssd_dentry);
+	return pipe_dentry;
+}
+
+static void
+rpc_gssd_dummy_depopulate(struct dentry *pipe_dentry)
+{
+	struct dentry *clnt_dir = pipe_dentry->d_parent;
+	struct dentry *gssd_dir = clnt_dir->d_parent;
+
+	__rpc_rmpipe(clnt_dir->d_inode, pipe_dentry);
+	__rpc_depopulate(clnt_dir, gssd_dummy_info_file, 0, 1);
+	__rpc_depopulate(gssd_dir, gssd_dummy_clnt_dir, 0, 1);
+	dput(pipe_dentry);
+}
+
 static int
 rpc_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct inode *inode;
-	struct dentry *root;
+	struct dentry *root, *gssd_dentry;
 	struct net *net = data;
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	int err;
@@ -1266,6 +1403,13 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
 		return -ENOMEM;
+
+	gssd_dentry = rpc_gssd_dummy_populate(root, sn->gssd_dummy);
+	if (IS_ERR(gssd_dentry)) {
+		__rpc_depopulate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF);
+		return PTR_ERR(gssd_dentry);
+	}
+
 	dprintk("RPC:       sending pipefs MOUNT notification for net %p%s\n",
 		net, NET_NAME(net));
 	mutex_lock(&sn->pipefs_sb_lock);
@@ -1280,6 +1424,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 	return 0;
 
 err_depopulate:
+	rpc_gssd_dummy_depopulate(gssd_dentry);
 	blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
 					   RPC_PIPEFS_UMOUNT,
 					   sb);
@@ -1289,6 +1434,16 @@ err_depopulate:
 	return err;
 }
 
+bool
+gssd_running(struct net *net)
+{
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+	struct rpc_pipe *pipe = sn->gssd_dummy;
+
+	return pipe->nreaders || pipe->nwriters;
+}
+EXPORT_SYMBOL_GPL(gssd_running);
+
 static struct dentry *
 rpc_mount(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *data)
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 3d6498a..cd30120 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -44,12 +44,17 @@ static __net_init int sunrpc_init_net(struct net *net)
 	if (err)
 		goto err_unixgid;
 
-	rpc_pipefs_init_net(net);
+	err = rpc_pipefs_init_net(net);
+	if (err)
+		goto err_pipefs;
+
 	INIT_LIST_HEAD(&sn->all_clients);
 	spin_lock_init(&sn->rpc_client_lock);
 	spin_lock_init(&sn->rpcb_clnt_lock);
 	return 0;
 
+err_pipefs:
+	unix_gid_cache_destroy(net);
 err_unixgid:
 	ip_map_cache_destroy(net);
 err_ipmap:
@@ -60,6 +65,7 @@ err_proc:
 
 static __net_exit void sunrpc_exit_net(struct net *net)
 {
+	rpc_pipefs_exit_net(net);
 	unix_gid_cache_destroy(net);
 	ip_map_cache_destroy(net);
 	rpc_proc_exit(net);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 1750048..7d4df99 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -749,6 +749,11 @@ static void xprt_connect_status(struct rpc_task *task)
 	}
 
 	switch (task->tk_status) {
+	case -ECONNREFUSED:
+	case -ECONNRESET:
+	case -ECONNABORTED:
+	case -ENETUNREACH:
+	case -EHOSTUNREACH:
 	case -EAGAIN:
 		dprintk("RPC: %5u xprt_connect_status: retrying\n", task->tk_pid);
 		break;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 75b045e..2a7ca8f 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -257,6 +257,7 @@ struct sock_xprt {
 	void			(*old_data_ready)(struct sock *, int);
 	void			(*old_state_change)(struct sock *);
 	void			(*old_write_space)(struct sock *);
+	void			(*old_error_report)(struct sock *);
 };
 
 /*
@@ -274,6 +275,11 @@ struct sock_xprt {
  */
 #define TCP_RPC_REPLY		(1UL << 6)
 
+static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
+{
+	return (struct rpc_xprt *) sk->sk_user_data;
+}
+
 static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
 {
 	return (struct sockaddr *) &xprt->addr;
@@ -799,6 +805,7 @@ static void xs_save_old_callbacks(struct sock_xprt *transport, struct sock *sk)
 	transport->old_data_ready = sk->sk_data_ready;
 	transport->old_state_change = sk->sk_state_change;
 	transport->old_write_space = sk->sk_write_space;
+	transport->old_error_report = sk->sk_error_report;
 }
 
 static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *sk)
@@ -806,6 +813,34 @@ static void xs_restore_old_callbacks(struct sock_xprt *transport, struct sock *s
 	sk->sk_data_ready = transport->old_data_ready;
 	sk->sk_state_change = transport->old_state_change;
 	sk->sk_write_space = transport->old_write_space;
+	sk->sk_error_report = transport->old_error_report;
+}
+
+/**
+ * xs_error_report - callback to handle TCP socket state errors
+ * @sk: socket
+ *
+ * Note: we don't call sock_error() since there may be a rpc_task
+ * using the socket, and so we don't want to clear sk->sk_err.
+ */
+static void xs_error_report(struct sock *sk)
+{
+	struct rpc_xprt *xprt;
+	int err;
+
+	read_lock_bh(&sk->sk_callback_lock);
+	if (!(xprt = xprt_from_sock(sk)))
+		goto out;
+
+	err = -sk->sk_err;
+	if (err == 0)
+		goto out;
+	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
+			xprt, -err);
+	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+	xprt_wake_pending_tasks(xprt, err);
+ out:
+	read_unlock_bh(&sk->sk_callback_lock);
 }
 
 static void xs_reset_transport(struct sock_xprt *transport)
@@ -885,11 +920,6 @@ static void xs_destroy(struct rpc_xprt *xprt)
 	module_put(THIS_MODULE);
 }
 
-static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
-{
-	return (struct rpc_xprt *) sk->sk_user_data;
-}
-
 static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
 {
 	struct xdr_skb_reader desc = {
@@ -1869,6 +1899,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt,
 		sk->sk_user_data = xprt;
 		sk->sk_data_ready = xs_local_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
+		sk->sk_error_report = xs_error_report;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		xprt_clear_connected(xprt);
@@ -2146,6 +2177,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_data_ready = xs_tcp_data_ready;
 		sk->sk_state_change = xs_tcp_state_change;
 		sk->sk_write_space = xs_tcp_write_space;
+		sk->sk_error_report = xs_error_report;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		/* socket options */