Merge branch 'for-linus' of git://linux-nfs.org/~bfields/linux

* 'for-linus' of git://linux-nfs.org/~bfields/linux: (52 commits)
  knfsd: clear both setuid and setgid whenever a chown is done
  knfsd: get rid of imode variable in nfsd_setattr
  SUNRPC: Use unsigned loop and array index in svc_init_buffer()
  SUNRPC: Use unsigned index when looping over arrays
  SUNRPC: Update RPC server's TCP record marker decoder
  SUNRPC: RPC server still uses 2.4 method for disabling TCP Nagle
  NLM: don't let lockd exit on unexpected svc_recv errors (try #2)
  NFS: don't let nfs_callback_svc exit on unexpected svc_recv errors (try #2)
  Use a zero sized array for raw field in struct fid
  nfsd: use static memory for callback program and stats
  SUNRPC: remove svc_create_thread()
  nfsd: fix comment
  lockd: Fix stale nlmsvc_unlink_block comment
  NFSD: Strip __KERNEL__ testing from unexported header files.
  sunrpc: make token header values less confusing
  gss_krb5: consistently use unsigned for seqnum
  NFSD: Remove NFSv4 dependency on NFSv3
  SUNRPC: Remove PROC_FS dependency
  NFSD: Use "depends on" for PROC_FS dependency
  nfsd: move most of fh_verify to separate function
  ...

4 files changed, 111 insertions, 121 deletions

diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index f1ef49fff118..c7854791898f 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -19,12 +19,11 @@
 
 
 #define NLMDBG_FACILITY		NLMDBG_HOSTCACHE
-#define NLM_HOST_MAX		64
 #define NLM_HOST_NRHASH		32
 #define NLM_ADDRHASH(addr)	(ntohl(addr) & (NLM_HOST_NRHASH-1))
 #define NLM_HOST_REBIND		(60 * HZ)
-#define NLM_HOST_EXPIRE		((nrhosts > NLM_HOST_MAX)? 300 * HZ : 120 * HZ)
-#define NLM_HOST_COLLECT	((nrhosts > NLM_HOST_MAX)? 120 * HZ :  60 * HZ)
+#define NLM_HOST_EXPIRE		(300 * HZ)
+#define NLM_HOST_COLLECT	(120 * HZ)
 
 static struct hlist_head	nlm_hosts[NLM_HOST_NRHASH];
 static unsigned long		next_gc;
@@ -142,9 +141,7 @@ nlm_lookup_host(int server, const struct sockaddr_in *sin,
 	INIT_LIST_HEAD(&host->h_granted);
 	INIT_LIST_HEAD(&host->h_reclaim);
 
-	if (++nrhosts > NLM_HOST_MAX)
-		next_gc = 0;
-
+	nrhosts++;
 out:
 	mutex_unlock(&nlm_host_mutex);
 	return host;
@@ -460,7 +457,7 @@ nlm_gc_hosts(void)
  * Manage NSM handles
  */
 static LIST_HEAD(nsm_handles);
-static DEFINE_MUTEX(nsm_mutex);
+static DEFINE_SPINLOCK(nsm_lock);
 
 static struct nsm_handle *
 __nsm_find(const struct sockaddr_in *sin,
@@ -468,7 +465,7 @@ __nsm_find(const struct sockaddr_in *sin,
 		int create)
 {
 	struct nsm_handle *nsm = NULL;
-	struct list_head *pos;
+	struct nsm_handle *pos;
 
 	if (!sin)
 		return NULL;
@@ -482,38 +479,43 @@ __nsm_find(const struct sockaddr_in *sin,
 		return NULL;
 	}
 
-	mutex_lock(&nsm_mutex);
-	list_for_each(pos, &nsm_handles) {
-		nsm = list_entry(pos, struct nsm_handle, sm_link);
+retry:
+	spin_lock(&nsm_lock);
+	list_for_each_entry(pos, &nsm_handles, sm_link) {
 
 		if (hostname && nsm_use_hostnames) {
-			if (strlen(nsm->sm_name) != hostname_len
-			 || memcmp(nsm->sm_name, hostname, hostname_len))
+			if (strlen(pos->sm_name) != hostname_len
+			 || memcmp(pos->sm_name, hostname, hostname_len))
 				continue;
-		} else if (!nlm_cmp_addr(&nsm->sm_addr, sin))
+		} else if (!nlm_cmp_addr(&pos->sm_addr, sin))
 			continue;
-		atomic_inc(&nsm->sm_count);
-		goto out;
+		atomic_inc(&pos->sm_count);
+		kfree(nsm);
+		nsm = pos;
+		goto found;
 	}
-
-	if (!create) {
-		nsm = NULL;
-		goto out;
+	if (nsm) {
+		list_add(&nsm->sm_link, &nsm_handles);
+		goto found;
 	}
+	spin_unlock(&nsm_lock);
+
+	if (!create)
+		return NULL;
 
 	nsm = kzalloc(sizeof(*nsm) + hostname_len + 1, GFP_KERNEL);
-	if (nsm != NULL) {
-		nsm->sm_addr = *sin;
-		nsm->sm_name = (char *) (nsm + 1);
-		memcpy(nsm->sm_name, hostname, hostname_len);
-		nsm->sm_name[hostname_len] = '\0';
-		atomic_set(&nsm->sm_count, 1);
+	if (nsm == NULL)
+		return NULL;
 
-		list_add(&nsm->sm_link, &nsm_handles);
-	}
+	nsm->sm_addr = *sin;
+	nsm->sm_name = (char *) (nsm + 1);
+	memcpy(nsm->sm_name, hostname, hostname_len);
+	nsm->sm_name[hostname_len] = '\0';
+	atomic_set(&nsm->sm_count, 1);
+	goto retry;
 
-out:
-	mutex_unlock(&nsm_mutex);
+found:
+	spin_unlock(&nsm_lock);
 	return nsm;
 }
 
@@ -532,12 +534,9 @@ nsm_release(struct nsm_handle *nsm)
 {
 	if (!nsm)
 		return;
-	if (atomic_dec_and_test(&nsm->sm_count)) {
-		mutex_lock(&nsm_mutex);
-		if (atomic_read(&nsm->sm_count) == 0) {
-			list_del(&nsm->sm_link);
-			kfree(nsm);
-		}
-		mutex_unlock(&nsm_mutex);
+	if (atomic_dec_and_lock(&nsm->sm_count, &nsm_lock)) {
+		list_del(&nsm->sm_link);
+		spin_unlock(&nsm_lock);
+		kfree(nsm);
 	}
 }
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 1ed8bd4de941..cf977bbcf303 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -25,6 +25,7 @@
 #include <linux/smp.h>
 #include <linux/smp_lock.h>
 #include <linux/mutex.h>
+#include <linux/kthread.h>
 #include <linux/freezer.h>
 
 #include <linux/sunrpc/types.h>
@@ -48,14 +49,11 @@ EXPORT_SYMBOL(nlmsvc_ops);
 
 static DEFINE_MUTEX(nlmsvc_mutex);
 static unsigned int		nlmsvc_users;
-static pid_t			nlmsvc_pid;
+static struct task_struct	*nlmsvc_task;
 static struct svc_serv		*nlmsvc_serv;
 int				nlmsvc_grace_period;
 unsigned long			nlmsvc_timeout;
 
-static DECLARE_COMPLETION(lockd_start_done);
-static DECLARE_WAIT_QUEUE_HEAD(lockd_exit);
-
 /*
  * These can be set at insmod time (useful for NFS as root filesystem),
  * and also changed through the sysctl interface.  -- Jamie Lokier, Aug 2003
@@ -111,35 +109,30 @@ static inline void clear_grace_period(void)
 /*
  * This is the lockd kernel thread
  */
-static void
-lockd(struct svc_rqst *rqstp)
+static int
+lockd(void *vrqstp)
 {
-	int		err = 0;
+	int		err = 0, preverr = 0;
+	struct svc_rqst *rqstp = vrqstp;
 	unsigned long grace_period_expire;
 
-	/* Lock module and set up kernel thread */
-	/* lockd_up is waiting for us to startup, so will
-	 * be holding a reference to this module, so it
-	 * is safe to just claim another reference
-	 */
-	__module_get(THIS_MODULE);
-	lock_kernel();
-
-	/*
-	 * Let our maker know we're running.
-	 */
-	nlmsvc_pid = current->pid;
-	nlmsvc_serv = rqstp->rq_server;
-	complete(&lockd_start_done);
-
-	daemonize("lockd");
+	/* try_to_freeze() is called from svc_recv() */
 	set_freezable();
 
-	/* Process request with signals blocked, but allow SIGKILL.  */
+	/* Allow SIGKILL to tell lockd to drop all of its locks */
 	allow_signal(SIGKILL);
 
 	dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n");
 
+	/*
+	 * FIXME: it would be nice if lockd didn't spend its entire life
+	 * running under the BKL. At the very least, it would be good to
+	 * have someone clarify what it's intended to protect here. I've
+	 * seen some handwavy posts about posix locking needing to be
+	 * done under the BKL, but it's far from clear.
+	 */
+	lock_kernel();
+
 	if (!nlm_timeout)
 		nlm_timeout = LOCKD_DFLT_TIMEO;
 	nlmsvc_timeout = nlm_timeout * HZ;
@@ -148,10 +141,9 @@ lockd(struct svc_rqst *rqstp)
 
 	/*
 	 * The main request loop. We don't terminate until the last
-	 * NFS mount or NFS daemon has gone away, and we've been sent a
-	 * signal, or else another process has taken over our job.
+	 * NFS mount or NFS daemon has gone away.
 	 */
-	while ((nlmsvc_users || !signalled()) && nlmsvc_pid == current->pid) {
+	while (!kthread_should_stop()) {
 		long timeout = MAX_SCHEDULE_TIMEOUT;
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
 
@@ -161,6 +153,7 @@ lockd(struct svc_rqst *rqstp)
 				nlmsvc_invalidate_all();
 				grace_period_expire = set_grace_period();
 			}
+			continue;
 		}
 
 		/*
@@ -179,14 +172,20 @@ lockd(struct svc_rqst *rqstp)
 		 * recvfrom routine.
 		 */
 		err = svc_recv(rqstp, timeout);
-		if (err == -EAGAIN || err == -EINTR)
+		if (err == -EAGAIN || err == -EINTR) {
+			preverr = err;
 			continue;
+		}
 		if (err < 0) {
-			printk(KERN_WARNING
-			       "lockd: terminating on error %d\n",
-			       -err);
-			break;
+			if (err != preverr) {
+				printk(KERN_WARNING "%s: unexpected error "
+					"from svc_recv (%d)\n", __func__, err);
+				preverr = err;
+			}
+			schedule_timeout_interruptible(HZ);
+			continue;
 		}
+		preverr = err;
 
 		dprintk("lockd: request from %s\n",
 				svc_print_addr(rqstp, buf, sizeof(buf)));
@@ -195,28 +194,19 @@ lockd(struct svc_rqst *rqstp)
 	}
 
 	flush_signals(current);
+	if (nlmsvc_ops)
+		nlmsvc_invalidate_all();
+	nlm_shutdown_hosts();
 
-	/*
-	 * Check whether there's a new lockd process before
-	 * shutting down the hosts and clearing the slot.
-	 */
-	if (!nlmsvc_pid || current->pid == nlmsvc_pid) {
-		if (nlmsvc_ops)
-			nlmsvc_invalidate_all();
-		nlm_shutdown_hosts();
-		nlmsvc_pid = 0;
-		nlmsvc_serv = NULL;
-	} else
-		printk(KERN_DEBUG
-			"lockd: new process, skipping host shutdown\n");
-	wake_up(&lockd_exit);
+	unlock_kernel();
+
+	nlmsvc_task = NULL;
+	nlmsvc_serv = NULL;
 
 	/* Exit the RPC thread */
 	svc_exit_thread(rqstp);
 
-	/* Release module */
-	unlock_kernel();
-	module_put_and_exit(0);
+	return 0;
 }
 
 /*
@@ -261,14 +251,15 @@ static int make_socks(struct svc_serv *serv, int proto)
 int
 lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
 {
-	struct svc_serv *	serv;
-	int			error = 0;
+	struct svc_serv *serv;
+	struct svc_rqst *rqstp;
+	int		error = 0;
 
 	mutex_lock(&nlmsvc_mutex);
 	/*
 	 * Check whether we're already up and running.
 	 */
-	if (nlmsvc_pid) {
+	if (nlmsvc_serv) {
 		if (proto)
 			error = make_socks(nlmsvc_serv, proto);
 		goto out;
@@ -295,13 +286,28 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
 	/*
 	 * Create the kernel thread and wait for it to start.
 	 */
-	error = svc_create_thread(lockd, serv);
-	if (error) {
+	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]);
+	if (IS_ERR(rqstp)) {
+		error = PTR_ERR(rqstp);
+		printk(KERN_WARNING
+			"lockd_up: svc_rqst allocation failed, error=%d\n",
+			error);
+		goto destroy_and_out;
+	}
+
+	svc_sock_update_bufs(serv);
+	nlmsvc_serv = rqstp->rq_server;
+
+	nlmsvc_task = kthread_run(lockd, rqstp, serv->sv_name);
+	if (IS_ERR(nlmsvc_task)) {
+		error = PTR_ERR(nlmsvc_task);
+		nlmsvc_task = NULL;
+		nlmsvc_serv = NULL;
 		printk(KERN_WARNING
-			"lockd_up: create thread failed, error=%d\n", error);
+			"lockd_up: kthread_run failed, error=%d\n", error);
+		svc_exit_thread(rqstp);
 		goto destroy_and_out;
 	}
-	wait_for_completion(&lockd_start_done);
 
 	/*
 	 * Note: svc_serv structures have an initial use count of 1,
@@ -323,37 +329,21 @@ EXPORT_SYMBOL(lockd_up);
 void
 lockd_down(void)
 {
-	static int warned;
-
 	mutex_lock(&nlmsvc_mutex);
 	if (nlmsvc_users) {
 		if (--nlmsvc_users)
 			goto out;
-	} else
-		printk(KERN_WARNING "lockd_down: no users! pid=%d\n", nlmsvc_pid);
-
-	if (!nlmsvc_pid) {
-		if (warned++ == 0)
-			printk(KERN_WARNING "lockd_down: no lockd running.\n"); 
-		goto out;
+	} else {
+		printk(KERN_ERR "lockd_down: no users! task=%p\n",
+			nlmsvc_task);
+		BUG();
 	}
-	warned = 0;
 
-	kill_proc(nlmsvc_pid, SIGKILL, 1);
-	/*
-	 * Wait for the lockd process to exit, but since we're holding
-	 * the lockd semaphore, we can't wait around forever ...
-	 */
-	clear_thread_flag(TIF_SIGPENDING);
-	interruptible_sleep_on_timeout(&lockd_exit, HZ);
-	if (nlmsvc_pid) {
-		printk(KERN_WARNING 
-			"lockd_down: lockd failed to exit, clearing pid\n");
-		nlmsvc_pid = 0;
+	if (!nlmsvc_task) {
+		printk(KERN_ERR "lockd_down: no lockd running.\n");
+		BUG();
 	}
-	spin_lock_irq(&current->sighand->siglock);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	kthread_stop(nlmsvc_task);
 out:
 	mutex_unlock(&nlmsvc_mutex);
 }
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index fe9bdb4a220c..1f122c1940af 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -29,6 +29,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/nlm.h>
 #include <linux/lockd/lockd.h>
+#include <linux/kthread.h>
 
 #define NLMDBG_FACILITY		NLMDBG_SVCLOCK
 
@@ -226,8 +227,7 @@ failed:
 }
 
 /*
- * Delete a block. If the lock was cancelled or the grant callback
- * failed, unlock is set to 1.
+ * Delete a block.
  * It is the caller's responsibility to check whether the file
  * can be closed hereafter.
  */
@@ -887,7 +887,7 @@ nlmsvc_retry_blocked(void)
 	unsigned long	timeout = MAX_SCHEDULE_TIMEOUT;
 	struct nlm_block *block;
 
-	while (!list_empty(&nlm_blocked)) {
+	while (!list_empty(&nlm_blocked) && !kthread_should_stop()) {
 		block = list_entry(nlm_blocked.next, struct nlm_block, b_list);
 
 		if (block->b_when == NLM_NEVER)
diff --git a/fs/lockd/svcshare.c b/fs/lockd/svcshare.c
index 068886de4dda..b0ae07008700 100644
--- a/fs/lockd/svcshare.c
+++ b/fs/lockd/svcshare.c
@@ -71,7 +71,8 @@ nlmsvc_unshare_file(struct nlm_host *host, struct nlm_file *file,
 	struct nlm_share	*share, **shpp;
 	struct xdr_netobj	*oh = &argp->lock.oh;
 
-	for (shpp = &file->f_shares; (share = *shpp) != 0; shpp = &share->s_next) {
+	for (shpp = &file->f_shares; (share = *shpp) != NULL;
+					shpp = &share->s_next) {
 		if (share->s_host == host && nlm_cmp_owner(share, oh)) {
 			*shpp = share->s_next;
 			kfree(share);