Merge tag 'nfsd-5.3' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Highlights:

   - Add a new /proc/fs/nfsd/clients/ directory which exposes some
     long-requested information about NFSv4 clients (like open files)
     and allows forced revocation of client state.

   - Replace the global duplicate reply cache by a cache per network
     namespace; previously, a request in one network namespace could
     incorrectly match an entry from another, though we haven't seen
     this in production. This is the last remaining container bug that
     I'm aware of; at this point you should be able to run separate
     nfsd's in each network namespace, each with their own set of
     exports, and everything should work.

   - Cleanup and modify lock code to show the pid of lockd as the owner
     of NLM locks. This is the correct version of the bugfix originally
     attempted in b8eee0e90f97 ("lockd: Show pid of lockd for remote
     locks")"

* tag 'nfsd-5.3' of git://linux-nfs.org/~bfields/linux: (34 commits)
  nfsd: Make __get_nfsdfs_client() static
  nfsd: Make two functions static
  nfsd: Fix misuse of strlcpy
  sunrpc/cache: remove the exporting of cache_seq_next
  nfsd: decode implementation id
  nfsd: create xdr_netobj_dup helper
  nfsd: allow forced expiration of NFSv4 clients
  nfsd: create get_nfsdfs_clp helper
  nfsd4: show layout stateids
  nfsd: show lock and deleg stateids
  nfsd4: add file to display list of client's opens
  nfsd: add more information to client info file
  nfsd: escape high characters in binary data
  nfsd: copy client's address including port number to cl_addr
  nfsd4: add a client info file
  nfsd: make client/ directory names small ints
  nfsd: add nfsd/clients directory
  nfsd4: use reference count to free client
  nfsd: rename cl_refcount
  nfsd: persist nfsd filesystem across mounts
  ...

7 files changed, 136 insertions, 39 deletions

diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 62f98225abb3..b11f2afa84f1 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -47,13 +47,14 @@ void nlmclnt_next_cookie(struct nlm_cookie *c)
 	c->len=4;
 }
 
-static struct nlm_lockowner *nlm_get_lockowner(struct nlm_lockowner *lockowner)
+static struct nlm_lockowner *
+nlmclnt_get_lockowner(struct nlm_lockowner *lockowner)
 {
 	refcount_inc(&lockowner->count);
 	return lockowner;
 }
 
-static void nlm_put_lockowner(struct nlm_lockowner *lockowner)
+static void nlmclnt_put_lockowner(struct nlm_lockowner *lockowner)
 {
 	if (!refcount_dec_and_lock(&lockowner->count, &lockowner->host->h_lock))
 		return;
@@ -82,28 +83,28 @@ static inline uint32_t __nlm_alloc_pid(struct nlm_host *host)
 	return res;
 }
 
-static struct nlm_lockowner *__nlm_find_lockowner(struct nlm_host *host, fl_owner_t owner)
+static struct nlm_lockowner *__nlmclnt_find_lockowner(struct nlm_host *host, fl_owner_t owner)
 {
 	struct nlm_lockowner *lockowner;
 	list_for_each_entry(lockowner, &host->h_lockowners, list) {
 		if (lockowner->owner != owner)
 			continue;
-		return nlm_get_lockowner(lockowner);
+		return nlmclnt_get_lockowner(lockowner);
 	}
 	return NULL;
 }
 
-static struct nlm_lockowner *nlm_find_lockowner(struct nlm_host *host, fl_owner_t owner)
+static struct nlm_lockowner *nlmclnt_find_lockowner(struct nlm_host *host, fl_owner_t owner)
 {
 	struct nlm_lockowner *res, *new = NULL;
 
 	spin_lock(&host->h_lock);
-	res = __nlm_find_lockowner(host, owner);
+	res = __nlmclnt_find_lockowner(host, owner);
 	if (res == NULL) {
 		spin_unlock(&host->h_lock);
 		new = kmalloc(sizeof(*new), GFP_KERNEL);
 		spin_lock(&host->h_lock);
-		res = __nlm_find_lockowner(host, owner);
+		res = __nlmclnt_find_lockowner(host, owner);
 		if (res == NULL && new != NULL) {
 			res = new;
 			refcount_set(&new->count, 1);
@@ -457,7 +458,7 @@ static void nlmclnt_locks_copy_lock(struct file_lock *new, struct file_lock *fl)
 {
 	spin_lock(&fl->fl_u.nfs_fl.owner->host->h_lock);
 	new->fl_u.nfs_fl.state = fl->fl_u.nfs_fl.state;
-	new->fl_u.nfs_fl.owner = nlm_get_lockowner(fl->fl_u.nfs_fl.owner);
+	new->fl_u.nfs_fl.owner = nlmclnt_get_lockowner(fl->fl_u.nfs_fl.owner);
 	list_add_tail(&new->fl_u.nfs_fl.list, &fl->fl_u.nfs_fl.owner->host->h_granted);
 	spin_unlock(&fl->fl_u.nfs_fl.owner->host->h_lock);
 }
@@ -467,7 +468,7 @@ static void nlmclnt_locks_release_private(struct file_lock *fl)
 	spin_lock(&fl->fl_u.nfs_fl.owner->host->h_lock);
 	list_del(&fl->fl_u.nfs_fl.list);
 	spin_unlock(&fl->fl_u.nfs_fl.owner->host->h_lock);
-	nlm_put_lockowner(fl->fl_u.nfs_fl.owner);
+	nlmclnt_put_lockowner(fl->fl_u.nfs_fl.owner);
 }
 
 static const struct file_lock_operations nlmclnt_lock_ops = {
@@ -478,7 +479,7 @@ static const struct file_lock_operations nlmclnt_lock_ops = {
 static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host)
 {
 	fl->fl_u.nfs_fl.state = 0;
-	fl->fl_u.nfs_fl.owner = nlm_find_lockowner(host, fl->fl_owner);
+	fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host, fl->fl_owner);
 	INIT_LIST_HEAD(&fl->fl_u.nfs_fl.list);
 	fl->fl_ops = &nlmclnt_lock_ops;
 }
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 1bddf70d9656..e4d3f783e06a 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -46,8 +46,14 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 		/* Set up the missing parts of the file_lock structure */
 		lock->fl.fl_file  = file->f_file;
-		lock->fl.fl_owner = (fl_owner_t) host;
+		lock->fl.fl_pid = current->tgid;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
+		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
+		if (!lock->fl.fl_owner) {
+			/* lockowner allocation has failed */
+			nlmsvc_release_host(host);
+			return nlm_lck_denied_nolocks;
+		}
 	}
 
 	return 0;
@@ -94,6 +100,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 	else
 		dprintk("lockd: TEST4        status %d\n", ntohl(resp->status));
 
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rc;
@@ -142,6 +149,7 @@ __nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
 	else
 		dprintk("lockd: LOCK         status %d\n", ntohl(resp->status));
 
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rc;
@@ -178,6 +186,7 @@ __nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 	resp->status = nlmsvc_cancel_blocked(SVC_NET(rqstp), file, &argp->lock);
 
 	dprintk("lockd: CANCEL        status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
@@ -217,6 +226,7 @@ __nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 	resp->status = nlmsvc_unlock(SVC_NET(rqstp), file, &argp->lock);
 
 	dprintk("lockd: UNLOCK        status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
@@ -365,6 +375,7 @@ nlm4svc_proc_share(struct svc_rqst *rqstp)
 	resp->status = nlmsvc_share_file(host, file, argp);
 
 	dprintk("lockd: SHARE         status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
@@ -399,6 +410,7 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp)
 	resp->status = nlmsvc_unshare_file(host, file, argp);
 
 	dprintk("lockd: UNSHARE       status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index ea719cdd6a36..61d3cc2283dc 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -332,6 +332,93 @@ restart:
 	mutex_unlock(&file->f_mutex);
 }
 
+static struct nlm_lockowner *
+nlmsvc_get_lockowner(struct nlm_lockowner *lockowner)
+{
+	refcount_inc(&lockowner->count);
+	return lockowner;
+}
+
+static void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner)
+{
+	if (!refcount_dec_and_lock(&lockowner->count, &lockowner->host->h_lock))
+		return;
+	list_del(&lockowner->list);
+	spin_unlock(&lockowner->host->h_lock);
+	nlmsvc_release_host(lockowner->host);
+	kfree(lockowner);
+}
+
+static struct nlm_lockowner *__nlmsvc_find_lockowner(struct nlm_host *host, pid_t pid)
+{
+	struct nlm_lockowner *lockowner;
+	list_for_each_entry(lockowner, &host->h_lockowners, list) {
+		if (lockowner->pid != pid)
+			continue;
+		return nlmsvc_get_lockowner(lockowner);
+	}
+	return NULL;
+}
+
+static struct nlm_lockowner *nlmsvc_find_lockowner(struct nlm_host *host, pid_t pid)
+{
+	struct nlm_lockowner *res, *new = NULL;
+
+	spin_lock(&host->h_lock);
+	res = __nlmsvc_find_lockowner(host, pid);
+
+	if (res == NULL) {
+		spin_unlock(&host->h_lock);
+		new = kmalloc(sizeof(*res), GFP_KERNEL);
+		spin_lock(&host->h_lock);
+		res = __nlmsvc_find_lockowner(host, pid);
+		if (res == NULL && new != NULL) {
+			res = new;
+			/* fs/locks.c will manage the refcount through lock_ops */
+			refcount_set(&new->count, 1);
+			new->pid = pid;
+			new->host = nlm_get_host(host);
+			list_add(&new->list, &host->h_lockowners);
+			new = NULL;
+		}
+	}
+
+	spin_unlock(&host->h_lock);
+	kfree(new);
+	return res;
+}
+
+void
+nlmsvc_release_lockowner(struct nlm_lock *lock)
+{
+	if (lock->fl.fl_owner)
+		nlmsvc_put_lockowner(lock->fl.fl_owner);
+}
+
+static void nlmsvc_locks_copy_lock(struct file_lock *new, struct file_lock *fl)
+{
+	struct nlm_lockowner *nlm_lo = (struct nlm_lockowner *)fl->fl_owner;
+	new->fl_owner = nlmsvc_get_lockowner(nlm_lo);
+}
+
+static void nlmsvc_locks_release_private(struct file_lock *fl)
+{
+	nlmsvc_put_lockowner((struct nlm_lockowner *)fl->fl_owner);
+}
+
+static const struct file_lock_operations nlmsvc_lock_ops = {
+	.fl_copy_lock = nlmsvc_locks_copy_lock,
+	.fl_release_private = nlmsvc_locks_release_private,
+};
+
+void nlmsvc_locks_init_private(struct file_lock *fl, struct nlm_host *host,
+						pid_t pid)
+{
+	fl->fl_owner = nlmsvc_find_lockowner(host, pid);
+	if (fl->fl_owner != NULL)
+		fl->fl_ops = &nlmsvc_lock_ops;
+}
+
 /*
  * Initialize arguments for GRANTED call. The nlm_rqst structure
  * has been cleared already.
@@ -345,7 +432,7 @@ static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock)
 
 	/* set default data area */
 	call->a_args.lock.oh.data = call->a_owner;
-	call->a_args.lock.svid = lock->fl.fl_pid;
+	call->a_args.lock.svid = ((struct nlm_lockowner *)lock->fl.fl_owner)->pid;
 
 	if (lock->oh.len > NLMCLNT_OHSIZE) {
 		void *data = kmalloc(lock->oh.len, GFP_KERNEL);
@@ -509,6 +596,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 {
 	int			error;
 	__be32			ret;
+	struct nlm_lockowner	*test_owner;
 
 	dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
 				locks_inode(file->f_file)->i_sb->s_id,
@@ -522,6 +610,9 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		goto out;
 	}
 
+	/* If there's a conflicting lock, remember to clean up the test lock */
+	test_owner = (struct nlm_lockowner *)lock->fl.fl_owner;
+
 	error = vfs_test_lock(file->f_file, &lock->fl);
 	if (error) {
 		/* We can't currently deal with deferred test requests */
@@ -543,11 +634,16 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 	conflock->caller = "somehost";	/* FIXME */
 	conflock->len = strlen(conflock->caller);
 	conflock->oh.len = 0;		/* don't return OH info */
-	conflock->svid = lock->fl.fl_pid;
+	conflock->svid = ((struct nlm_lockowner *)lock->fl.fl_owner)->pid;
 	conflock->fl.fl_type = lock->fl.fl_type;
 	conflock->fl.fl_start = lock->fl.fl_start;
 	conflock->fl.fl_end = lock->fl.fl_end;
 	locks_release_private(&lock->fl);
+
+	/* Clean up the test lock */
+	lock->fl.fl_owner = NULL;
+	nlmsvc_put_lockowner(test_owner);
+
 	ret = nlm_lck_denied;
 out:
 	return ret;
@@ -692,25 +788,7 @@ nlmsvc_notify_blocked(struct file_lock *fl)
 	printk(KERN_WARNING "lockd: notification for unknown block!\n");
 }
 
-static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2)
-{
-	return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid;
-}
-
-/*
- * Since NLM uses two "keys" for tracking locks, we need to hash them down
- * to one for the blocked_hash. Here, we're just xor'ing the host address
- * with the pid in order to create a key value for picking a hash bucket.
- */
-static unsigned long
-nlmsvc_owner_key(struct file_lock *fl)
-{
-	return (unsigned long)fl->fl_owner ^ (unsigned long)fl->fl_pid;
-}
-
 const struct lock_manager_operations nlmsvc_lock_operations = {
-	.lm_compare_owner = nlmsvc_same_owner,
-	.lm_owner_key = nlmsvc_owner_key,
 	.lm_notify = nlmsvc_notify_blocked,
 	.lm_grant = nlmsvc_grant_deferred,
 };
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index ea77c66d3cc3..d0bb7a6bf005 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -76,8 +76,14 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 		/* Set up the missing parts of the file_lock structure */
 		lock->fl.fl_file  = file->f_file;
-		lock->fl.fl_owner = (fl_owner_t) host;
+		lock->fl.fl_pid = current->tgid;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
+		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);
+		if (!lock->fl.fl_owner) {
+			/* lockowner allocation has failed */
+			nlmsvc_release_host(host);
+			return nlm_lck_denied_nolocks;
+		}
 	}
 
 	return 0;
@@ -125,6 +131,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 		dprintk("lockd: TEST          status %d vers %d\n",
 			ntohl(resp->status), rqstp->rq_vers);
 
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rc;
@@ -173,6 +180,7 @@ __nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
 	else
 		dprintk("lockd: LOCK         status %d\n", ntohl(resp->status));
 
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rc;
@@ -210,6 +218,7 @@ __nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 	resp->status = cast_status(nlmsvc_cancel_blocked(net, file, &argp->lock));
 
 	dprintk("lockd: CANCEL        status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
@@ -250,6 +259,7 @@ __nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 	resp->status = cast_status(nlmsvc_unlock(net, file, &argp->lock));
 
 	dprintk("lockd: UNLOCK        status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
@@ -408,6 +418,7 @@ nlmsvc_proc_share(struct svc_rqst *rqstp)
 	resp->status = cast_status(nlmsvc_share_file(host, file, argp));
 
 	dprintk("lockd: SHARE         status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
@@ -442,6 +453,7 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp)
 	resp->status = cast_status(nlmsvc_unshare_file(host, file, argp));
 
 	dprintk("lockd: UNSHARE       status %d\n", ntohl(resp->status));
+	nlmsvc_release_lockowner(&argp->lock);
 	nlmsvc_release_host(host);
 	nlm_release_file(file);
 	return rpc_success;
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 0e610f422406..028fc152da22 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -180,7 +180,7 @@ again:
 		/* update current lock count */
 		file->f_locks++;
 
-		lockhost = (struct nlm_host *) fl->fl_owner;
+		lockhost = ((struct nlm_lockowner *)fl->fl_owner)->host;
 		if (match(lockhost, host)) {
 			struct file_lock lock = *fl;
 
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 7147e4aebecc..982629f7b120 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -126,8 +126,6 @@ nlm_decode_lock(__be32 *p, struct nlm_lock *lock)
 	lock->svid  = ntohl(*p++);
 
 	locks_init_lock(fl);
-	fl->fl_owner = current->files;
-	fl->fl_pid   = (pid_t)lock->svid;
 	fl->fl_flags = FL_POSIX;
 	fl->fl_type  = F_RDLCK;		/* as good as anything else */
 	start = ntohl(*p++);
@@ -269,7 +267,6 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 	memset(lock, 0, sizeof(*lock));
 	locks_init_lock(&lock->fl);
 	lock->svid = ~(u32) 0;
-	lock->fl.fl_pid = (pid_t)lock->svid;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie))
 	 || !(p = xdr_decode_string_inplace(p, &lock->caller,
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index 7ed9edf9aed4..5fa9f48a9dba 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -118,8 +118,6 @@ nlm4_decode_lock(__be32 *p, struct nlm_lock *lock)
 	lock->svid  = ntohl(*p++);
 
 	locks_init_lock(fl);
-	fl->fl_owner = current->files;
-	fl->fl_pid   = (pid_t)lock->svid;
 	fl->fl_flags = FL_POSIX;
 	fl->fl_type  = F_RDLCK;		/* as good as anything else */
 	p = xdr_decode_hyper(p, &start);
@@ -266,7 +264,6 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 	memset(lock, 0, sizeof(*lock));
 	locks_init_lock(&lock->fl);
 	lock->svid = ~(u32) 0;
-	lock->fl.fl_pid = (pid_t)lock->svid;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie))
 	 || !(p = xdr_decode_string_inplace(p, &lock->caller,