Merge tag 'nfs-for-3.10-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:

 - Stable fix to prevent an rpc_task wakeup race
 - Fix a NFSv4.1 session drain deadlock
 - Fix a NFSv4/v4.1 mount regression when not running rpc.gssd
 - Ensure auth_gss pipe detection works in namespaces
 - Fix SETCLIENTID fallback if rpcsec_gss is not available

* tag 'nfs-for-3.10-3' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS: Fix SETCLIENTID fallback if GSS is not available
  SUNRPC: Prevent an rpc_task wakeup race
  NFSv4.1 Fix a pNFS session draining deadlock
  SUNRPC: Convert auth_gss pipe detection to work in namespaces
  SUNRPC: Faster detection if gssd is actually running
  SUNRPC: Fix a bug in gss_create_upcall

fs/nfs/callback_proc.c

@@ -414,7 +414,7 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
 
 	spin_lock(&tbl->slot_tbl_lock);
 	/* state manager is resetting the session */
-	if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) {
+	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
 		spin_unlock(&tbl->slot_tbl_lock);
 		status = htonl(NFS4ERR_DELAY);
 		/* Return NFS4ERR_BADSESSION if we're draining the session

fs/nfs/callback_xdr.c

@@ -763,7 +763,7 @@ static void nfs4_callback_free_slot(struct nfs4_session *session)
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
 	tbl->highest_used_slotid = NFS4_NO_SLOT;
-	nfs4_session_drain_complete(session, tbl);
+	nfs4_slot_tbl_drain_complete(tbl);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 

fs/nfs/nfs4client.c

@@ -203,7 +203,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
 	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
 	if (error == -EINVAL)
-		error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_NULL);
+		error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
 	if (error < 0)
 		goto error;
 

fs/nfs/nfs4proc.c

@@ -572,7 +572,7 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 	task->tk_timeout = 0;
 
 	spin_lock(&tbl->slot_tbl_lock);
-	if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) &&
+	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state) &&
 	    !args->sa_privileged) {
 		/* The state manager will wait until the slot table is empty */
 		dprintk("%s session is draining\n", __func__);

fs/nfs/nfs4session.c

@@ -73,7 +73,7 @@ void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot)
 			tbl->highest_used_slotid = new_max;
 		else {
 			tbl->highest_used_slotid = NFS4_NO_SLOT;
-			nfs4_session_drain_complete(tbl->session, tbl);
+			nfs4_slot_tbl_drain_complete(tbl);
 		}
 	}
 	dprintk("%s: slotid %u highest_used_slotid %d\n", __func__,
@@ -226,7 +226,7 @@ static bool nfs41_assign_slot(struct rpc_task *task, void *pslot)
 	struct nfs4_slot *slot = pslot;
 	struct nfs4_slot_table *tbl = slot->table;
 
-	if (nfs4_session_draining(tbl->session) && !args->sa_privileged)
+	if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged)
 		return false;
 	slot->generation = tbl->generation;
 	args->sa_slot = slot;

fs/nfs/nfs4session.h

@@ -25,6 +25,10 @@ struct nfs4_slot {
 };
 
 /* Sessions */
+enum nfs4_slot_tbl_state {
+	NFS4_SLOT_TBL_DRAINING,
+};
+
 #define SLOT_TABLE_SZ DIV_ROUND_UP(NFS4_MAX_SLOT_TABLE, 8*sizeof(long))
 struct nfs4_slot_table {
 	struct nfs4_session *session;		/* Parent session */
@@ -43,6 +47,7 @@ struct nfs4_slot_table {
 	unsigned long	generation;		/* Generation counter for
 						   target_highest_slotid */
 	struct completion complete;
+	unsigned long	slot_tbl_state;
 };
 
 /*
@@ -68,7 +73,6 @@ struct nfs4_session {
 
 enum nfs4_session_state {
 	NFS4_SESSION_INITING,
-	NFS4_SESSION_DRAINING,
 };
 
 #if defined(CONFIG_NFS_V4_1)
@@ -88,12 +92,11 @@ extern void nfs4_destroy_session(struct nfs4_session *session);
 extern int nfs4_init_session(struct nfs_server *server);
 extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);
 
-extern void nfs4_session_drain_complete(struct nfs4_session *session,
-		struct nfs4_slot_table *tbl);
+extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
 
-static inline bool nfs4_session_draining(struct nfs4_session *session)
+static inline bool nfs4_slot_tbl_draining(struct nfs4_slot_table *tbl)
 {
-	return !!test_bit(NFS4_SESSION_DRAINING, &session->session_state);
+	return !!test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
 }
 
 bool nfs41_wake_and_assign_slot(struct nfs4_slot_table *tbl,

fs/nfs/nfs4state.c

@@ -241,7 +241,7 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 	if (ses == NULL)
 		return;
 	tbl = &ses->fc_slot_table;
-	if (test_and_clear_bit(NFS4_SESSION_DRAINING, &ses->session_state)) {
+	if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
 		spin_lock(&tbl->slot_tbl_lock);
 		nfs41_wake_slot_table(tbl);
 		spin_unlock(&tbl->slot_tbl_lock);
@@ -251,15 +251,15 @@ static void nfs4_end_drain_session(struct nfs_client *clp)
 /*
  * Signal state manager thread if session fore channel is drained
  */
-void nfs4_session_drain_complete(struct nfs4_session *session,
-		struct nfs4_slot_table *tbl)
+void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl)
 {
-	if (nfs4_session_draining(session))
+	if (nfs4_slot_tbl_draining(tbl))
 		complete(&tbl->complete);
 }
 
-static int nfs4_wait_on_slot_tbl(struct nfs4_slot_table *tbl)
+static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl)
 {
+	set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
 	spin_lock(&tbl->slot_tbl_lock);
 	if (tbl->highest_used_slotid != NFS4_NO_SLOT) {
 		INIT_COMPLETION(tbl->complete);
@@ -275,13 +275,12 @@ static int nfs4_begin_drain_session(struct nfs_client *clp)
 	struct nfs4_session *ses = clp->cl_session;
 	int ret = 0;
 
-	set_bit(NFS4_SESSION_DRAINING, &ses->session_state);
 	/* back channel */
-	ret = nfs4_wait_on_slot_tbl(&ses->bc_slot_table);
+	ret = nfs4_drain_slot_tbl(&ses->bc_slot_table);
 	if (ret)
 		return ret;
 	/* fore channel */
-	return nfs4_wait_on_slot_tbl(&ses->fc_slot_table);
+	return nfs4_drain_slot_tbl(&ses->fc_slot_table);
 }
 
 static void nfs41_finish_session_reset(struct nfs_client *clp)

net/sunrpc/auth_gss/auth_gss.c

@@ -52,6 +52,8 @@
 #include <linux/sunrpc/gss_api.h>
 #include <asm/uaccess.h>
 
+#include "../netns.h"
+
 static const struct rpc_authops authgss_ops;
 
 static const struct rpc_credops gss_credops;
@@ -85,8 +87,6 @@ struct gss_auth {
 };
 
 /* pipe_version >= 0 if and only if someone has a pipe open. */
-static int pipe_version = -1;
-static atomic_t pipe_users = ATOMIC_INIT(0);
 static DEFINE_SPINLOCK(pipe_version_lock);
 static struct rpc_wait_queue pipe_version_rpc_waitqueue;
 static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
@@ -266,24 +266,27 @@ struct gss_upcall_msg {
 	char databuf[UPCALL_BUF_LEN];
 };
 
-static int get_pipe_version(void)
+static int get_pipe_version(struct net *net)
 {
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	int ret;
 
 	spin_lock(&pipe_version_lock);
-	if (pipe_version >= 0) {
-		atomic_inc(&pipe_users);
-		ret = pipe_version;
+	if (sn->pipe_version >= 0) {
+		atomic_inc(&sn->pipe_users);
+		ret = sn->pipe_version;
 	} else
 		ret = -EAGAIN;
 	spin_unlock(&pipe_version_lock);
 	return ret;
 }
 
-static void put_pipe_version(void)
+static void put_pipe_version(struct net *net)
 {
-	if (atomic_dec_and_lock(&pipe_users, &pipe_version_lock)) {
-		pipe_version = -1;
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+
+	if (atomic_dec_and_lock(&sn->pipe_users, &pipe_version_lock)) {
+		sn->pipe_version = -1;
 		spin_unlock(&pipe_version_lock);
 	}
 }
@@ -291,9 +294,10 @@ static void put_pipe_version(void)
 static void
 gss_release_msg(struct gss_upcall_msg *gss_msg)
 {
+	struct net *net = rpc_net_ns(gss_msg->auth->client);
 	if (!atomic_dec_and_test(&gss_msg->count))
 		return;
-	put_pipe_version();
+	put_pipe_version(net);
 	BUG_ON(!list_empty(&gss_msg->list));
 	if (gss_msg->ctx != NULL)
 		gss_put_ctx(gss_msg->ctx);
@@ -439,7 +443,10 @@ static void gss_encode_msg(struct gss_upcall_msg *gss_msg,
 				struct rpc_clnt *clnt,
 				const char *service_name)
 {
-	if (pipe_version == 0)
+	struct net *net = rpc_net_ns(clnt);
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
+
+	if (sn->pipe_version == 0)
 		gss_encode_v0_msg(gss_msg);
 	else /* pipe_version == 1 */
 		gss_encode_v1_msg(gss_msg, clnt, service_name);
@@ -455,7 +462,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, struct rpc_clnt *clnt,
 	gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS);
 	if (gss_msg == NULL)
 		return ERR_PTR(-ENOMEM);
-	vers = get_pipe_version();
+	vers = get_pipe_version(rpc_net_ns(clnt));
 	if (vers < 0) {
 		kfree(gss_msg);
 		return ERR_PTR(vers);
@@ -559,24 +566,34 @@ gss_refresh_upcall(struct rpc_task *task)
 static inline int
 gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
 {
+	struct net *net = rpc_net_ns(gss_auth->client);
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	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 = 0;
+	int err;
 
 	dprintk("RPC:       %s for uid %u\n",
 		__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;
 	gss_msg = gss_setup_upcall(gss_auth->client, gss_auth, cred);
 	if (PTR_ERR(gss_msg) == -EAGAIN) {
 		err = wait_event_interruptible_timeout(pipe_version_waitqueue,
-				pipe_version >= 0, 15*HZ);
-		if (pipe_version < 0) {
+				sn->pipe_version >= 0, timeout);
+		if (sn->pipe_version < 0) {
+			if (err == 0)
+				sn->gssd_running = 0;
 			warn_gssd();
 			err = -EACCES;
 		}
-		if (err)
+		if (err < 0)
 			goto out;
 		goto retry;
 	}
@@ -707,20 +724,22 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 
 static int gss_pipe_open(struct inode *inode, int new_version)
 {
+	struct net *net = inode->i_sb->s_fs_info;
+	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	int ret = 0;
 
 	spin_lock(&pipe_version_lock);
-	if (pipe_version < 0) {
+	if (sn->pipe_version < 0) {
 		/* First open of any gss pipe determines the version: */
-		pipe_version = new_version;
+		sn->pipe_version = new_version;
 		rpc_wake_up(&pipe_version_rpc_waitqueue);
 		wake_up(&pipe_version_waitqueue);
-	} else if (pipe_version != new_version) {
+	} else if (sn->pipe_version != new_version) {
 		/* Trying to open a pipe of a different version */
 		ret = -EBUSY;
 		goto out;
 	}
-	atomic_inc(&pipe_users);
+	atomic_inc(&sn->pipe_users);
 out:
 	spin_unlock(&pipe_version_lock);
 	return ret;
@@ -740,6 +759,7 @@ static int gss_pipe_open_v1(struct inode *inode)
 static void
 gss_pipe_release(struct inode *inode)
 {
+	struct net *net = inode->i_sb->s_fs_info;
 	struct rpc_pipe *pipe = RPC_I(inode)->pipe;
 	struct gss_upcall_msg *gss_msg;
 
@@ -758,7 +778,7 @@ gss_pipe_release(struct inode *inode)
 	}
 	spin_unlock(&pipe->lock);
 
-	put_pipe_version();
+	put_pipe_version(net);
 }
 
 static void

net/sunrpc/netns.h

@@ -28,7 +28,11 @@ struct sunrpc_net {
 	wait_queue_head_t gssp_wq;
 	struct rpc_clnt *gssp_clnt;
 	int use_gss_proxy;
+	int pipe_version;
+	atomic_t pipe_users;
 	struct proc_dir_entry *use_gssp_proc;
+
+	unsigned int gssd_running;
 };
 
 extern int sunrpc_net_id;

net/sunrpc/rpc_pipe.c

@@ -216,11 +216,14 @@ 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;
@@ -1069,6 +1072,8 @@ void rpc_pipefs_init_net(struct net *net)
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 
 	mutex_init(&sn->pipefs_sb_lock);
+	sn->gssd_running = 1;
+	sn->pipe_version = -1;
 }
 
 /*

net/sunrpc/sched.c

@@ -324,11 +324,17 @@ EXPORT_SYMBOL_GPL(__rpc_wait_for_completion_task);
  * Note: If the task is ASYNC, and is being made runnable after sitting on an
  * rpc_wait_queue, this must be called with the queue spinlock held to protect
  * the wait queue operation.
+ * Note the ordering of rpc_test_and_set_running() and rpc_clear_queued(),
+ * which is needed to ensure that __rpc_execute() doesn't loop (due to the
+ * lockless RPC_IS_QUEUED() test) before we've had a chance to test
+ * the RPC_TASK_RUNNING flag.
  */
 static void rpc_make_runnable(struct rpc_task *task)
 {
+	bool need_wakeup = !rpc_test_and_set_running(task);
+
 	rpc_clear_queued(task);
-	if (rpc_test_and_set_running(task))
+	if (!need_wakeup)
 		return;
 	if (RPC_IS_ASYNC(task)) {
 		INIT_WORK(&task->u.tk_work, rpc_async_schedule);