Merge branch 'server-cluster-locking-api' of git://linux-nfs.org/~bfields/linux

* 'server-cluster-locking-api' of git://linux-nfs.org/~bfields/linux:
  gfs2: nfs lock support for gfs2
  lockd: add code to handle deferred lock requests
  lockd: always preallocate block in nlmsvc_lock()
  lockd: handle test_lock deferrals
  lockd: pass cookie in nlmsvc_testlock
  lockd: handle fl_grant callbacks
  lockd: save lock state on deferral
  locks: add fl_grant callback for asynchronous lock return
  nfsd4: Convert NFSv4 to new lock interface
  locks: add lock cancel command
  locks: allow {vfs,posix}_lock_file to return conflicting lock
  locks: factor out generic/filesystem switch from setlock code
  locks: factor out generic/filesystem switch from test_lock
  locks: give posix_test_lock same interface as ->lock
  locks: make ->lock release private data before returning in GETLK case
  locks: create posix-to-flock helper functions
  locks: trivial removal of unnecessary parentheses

4 files changed, 240 insertions, 50 deletions

diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 47a66aa5d55..bf27b6c6cb6 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -99,7 +99,9 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
 	/* Now check for conflicting locks */
-	resp->status = nlmsvc_testlock(file, &argp->lock, &resp->lock);
+	resp->status = nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie);
+	if (resp->status == nlm_drop_reply)
+		return rpc_drop_reply;
 
 	dprintk("lockd: TEST4          status %d\n", ntohl(resp->status));
 	nlm_release_host(host);
@@ -143,6 +145,8 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	/* Now try to lock the file */
 	resp->status = nlmsvc_lock(rqstp, file, &argp->lock,
 					argp->block, &argp->cookie);
+	if (resp->status == nlm_drop_reply)
+		return rpc_drop_reply;
 
 	dprintk("lockd: LOCK          status %d\n", ntohl(resp->status));
 	nlm_release_host(host);
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index cf51f849e76..b3efa4536cc 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -173,7 +173,7 @@ found:
  */
 static inline struct nlm_block *
 nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_file *file,
-				struct nlm_lock *lock, struct nlm_cookie *cookie)
+		struct nlm_lock *lock, struct nlm_cookie *cookie)
 {
 	struct nlm_block	*block;
 	struct nlm_host		*host;
@@ -210,6 +210,7 @@ nlmsvc_create_block(struct svc_rqst *rqstp, struct nlm_file *file,
 	block->b_daemon = rqstp->rq_server;
 	block->b_host   = host;
 	block->b_file   = file;
+	block->b_fl = NULL;
 	file->f_count++;
 
 	/* Add to file's list of blocks */
@@ -261,6 +262,7 @@ static void nlmsvc_free_block(struct kref *kref)
 	nlmsvc_freegrantargs(block->b_call);
 	nlm_release_call(block->b_call);
 	nlm_release_file(block->b_file);
+	kfree(block->b_fl);
 	kfree(block);
 }
 
@@ -331,6 +333,31 @@ static void nlmsvc_freegrantargs(struct nlm_rqst *call)
 }
 
 /*
+ * Deferred lock request handling for non-blocking lock
+ */
+static u32
+nlmsvc_defer_lock_rqst(struct svc_rqst *rqstp, struct nlm_block *block)
+{
+	u32 status = nlm_lck_denied_nolocks;
+
+	block->b_flags |= B_QUEUED;
+
+	nlmsvc_insert_block(block, NLM_TIMEOUT);
+
+	block->b_cache_req = &rqstp->rq_chandle;
+	if (rqstp->rq_chandle.defer) {
+		block->b_deferred_req =
+			rqstp->rq_chandle.defer(block->b_cache_req);
+		if (block->b_deferred_req != NULL)
+			status = nlm_drop_reply;
+	}
+	dprintk("lockd: nlmsvc_defer_lock_rqst block %p flags %d status %d\n",
+		block, block->b_flags, status);
+
+	return status;
+}
+
+/*
  * Attempt to establish a lock, and if it can't be granted, block it
  * if required.
  */
@@ -338,7 +365,7 @@ __be32
 nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 			struct nlm_lock *lock, int wait, struct nlm_cookie *cookie)
 {
-	struct nlm_block	*block, *newblock = NULL;
+	struct nlm_block	*block = NULL;
 	int			error;
 	__be32			ret;
 
@@ -351,29 +378,58 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 				wait);
 
 
-	lock->fl.fl_flags &= ~FL_SLEEP;
-again:
 	/* Lock file against concurrent access */
 	mutex_lock(&file->f_mutex);
-	/* Get existing block (in case client is busy-waiting) */
+	/* Get existing block (in case client is busy-waiting)
+	 * or create new block
+	 */
 	block = nlmsvc_lookup_block(file, lock);
 	if (block == NULL) {
-		if (newblock != NULL)
-			lock = &newblock->b_call->a_args.lock;
-	} else
+		block = nlmsvc_create_block(rqstp, file, lock, cookie);
+		ret = nlm_lck_denied_nolocks;
+		if (block == NULL)
+			goto out;
 		lock = &block->b_call->a_args.lock;
+	} else
+		lock->fl.fl_flags &= ~FL_SLEEP;
 
-	error = posix_lock_file(file->f_file, &lock->fl);
-	lock->fl.fl_flags &= ~FL_SLEEP;
+	if (block->b_flags & B_QUEUED) {
+		dprintk("lockd: nlmsvc_lock deferred block %p flags %d\n",
+							block, block->b_flags);
+		if (block->b_granted) {
+			nlmsvc_unlink_block(block);
+			ret = nlm_granted;
+			goto out;
+		}
+		if (block->b_flags & B_TIMED_OUT) {
+			nlmsvc_unlink_block(block);
+			ret = nlm_lck_denied;
+			goto out;
+		}
+		ret = nlm_drop_reply;
+		goto out;
+	}
 
-	dprintk("lockd: posix_lock_file returned %d\n", error);
+	if (!wait)
+		lock->fl.fl_flags &= ~FL_SLEEP;
+	error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
+	lock->fl.fl_flags &= ~FL_SLEEP;
 
+	dprintk("lockd: vfs_lock_file returned %d\n", error);
 	switch(error) {
 		case 0:
 			ret = nlm_granted;
 			goto out;
 		case -EAGAIN:
+			ret = nlm_lck_denied;
 			break;
+		case -EINPROGRESS:
+			if (wait)
+				break;
+			/* Filesystem lock operation is in progress
+			   Add it to the queue waiting for callback */
+			ret = nlmsvc_defer_lock_rqst(rqstp, block);
+			goto out;
 		case -EDEADLK:
 			ret = nlm_deadlock;
 			goto out;
@@ -387,26 +443,11 @@ again:
 		goto out;
 
 	ret = nlm_lck_blocked;
-	if (block != NULL)
-		goto out;
-
-	/* If we don't have a block, create and initialize it. Then
-	 * retry because we may have slept in kmalloc. */
-	/* We have to release f_mutex as nlmsvc_create_block may try to
-	 * to claim it while doing host garbage collection */
-	if (newblock == NULL) {
-		mutex_unlock(&file->f_mutex);
-		dprintk("lockd: blocking on this lock (allocating).\n");
-		if (!(newblock = nlmsvc_create_block(rqstp, file, lock, cookie)))
-			return nlm_lck_denied_nolocks;
-		goto again;
-	}
 
 	/* Append to list of blocked */
-	nlmsvc_insert_block(newblock, NLM_NEVER);
+	nlmsvc_insert_block(block, NLM_NEVER);
 out:
 	mutex_unlock(&file->f_mutex);
-	nlmsvc_release_block(newblock);
 	nlmsvc_release_block(block);
 	dprintk("lockd: nlmsvc_lock returned %u\n", ret);
 	return ret;
@@ -416,9 +457,14 @@ out:
  * Test for presence of a conflicting lock.
  */
 __be32
-nlmsvc_testlock(struct nlm_file *file, struct nlm_lock *lock,
-				       struct nlm_lock *conflock)
+nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
+		struct nlm_lock *lock, struct nlm_lock *conflock,
+		struct nlm_cookie *cookie)
 {
+	struct nlm_block 	*block = NULL;
+	int			error;
+	__be32			ret;
+
 	dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",
 				file->f_file->f_path.dentry->d_inode->i_sb->s_id,
 				file->f_file->f_path.dentry->d_inode->i_ino,
@@ -426,19 +472,70 @@ nlmsvc_testlock(struct nlm_file *file, struct nlm_lock *lock,
 				(long long)lock->fl.fl_start,
 				(long long)lock->fl.fl_end);
 
-	if (posix_test_lock(file->f_file, &lock->fl, &conflock->fl)) {
-		dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
-				conflock->fl.fl_type,
-				(long long)conflock->fl.fl_start,
-				(long long)conflock->fl.fl_end);
-		conflock->caller = "somehost";	/* FIXME */
-		conflock->len = strlen(conflock->caller);
-		conflock->oh.len = 0;		/* don't return OH info */
-		conflock->svid = conflock->fl.fl_pid;
-		return nlm_lck_denied;
+	/* Get existing block (in case client is busy-waiting) */
+	block = nlmsvc_lookup_block(file, lock);
+
+	if (block == NULL) {
+		struct file_lock *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
+
+		if (conf == NULL)
+			return nlm_granted;
+		block = nlmsvc_create_block(rqstp, file, lock, cookie);
+		if (block == NULL) {
+			kfree(conf);
+			return nlm_granted;
+		}
+		block->b_fl = conf;
+	}
+	if (block->b_flags & B_QUEUED) {
+		dprintk("lockd: nlmsvc_testlock deferred block %p flags %d fl %p\n",
+			block, block->b_flags, block->b_fl);
+		if (block->b_flags & B_TIMED_OUT) {
+			nlmsvc_unlink_block(block);
+			return nlm_lck_denied;
+		}
+		if (block->b_flags & B_GOT_CALLBACK) {
+			if (block->b_fl != NULL
+					&& block->b_fl->fl_type != F_UNLCK) {
+				lock->fl = *block->b_fl;
+				goto conf_lock;
+			}
+			else {
+				nlmsvc_unlink_block(block);
+				return nlm_granted;
+			}
+		}
+		return nlm_drop_reply;
 	}
 
-	return nlm_granted;
+	error = vfs_test_lock(file->f_file, &lock->fl);
+	if (error == -EINPROGRESS)
+		return nlmsvc_defer_lock_rqst(rqstp, block);
+	if (error) {
+		ret = nlm_lck_denied_nolocks;
+		goto out;
+	}
+	if (lock->fl.fl_type == F_UNLCK) {
+		ret = nlm_granted;
+		goto out;
+	}
+
+conf_lock:
+	dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n",
+		lock->fl.fl_type, (long long)lock->fl.fl_start,
+		(long long)lock->fl.fl_end);
+	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->fl.fl_type = lock->fl.fl_type;
+	conflock->fl.fl_start = lock->fl.fl_start;
+	conflock->fl.fl_end = lock->fl.fl_end;
+	ret = nlm_lck_denied;
+out:
+	if (block)
+		nlmsvc_release_block(block);
+	return ret;
 }
 
 /*
@@ -464,7 +561,7 @@ nlmsvc_unlock(struct nlm_file *file, struct nlm_lock *lock)
 	nlmsvc_cancel_blocked(file, lock);
 
 	lock->fl.fl_type = F_UNLCK;
-	error = posix_lock_file(file->f_file, &lock->fl);
+	error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
 
 	return (error < 0)? nlm_lck_denied_nolocks : nlm_granted;
 }
@@ -493,6 +590,8 @@ nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
 	block = nlmsvc_lookup_block(file, lock);
 	mutex_unlock(&file->f_mutex);
 	if (block != NULL) {
+		vfs_cancel_lock(block->b_file->f_file,
+				&block->b_call->a_args.lock.fl);
 		status = nlmsvc_unlink_block(block);
 		nlmsvc_release_block(block);
 	}
@@ -500,6 +599,63 @@ nlmsvc_cancel_blocked(struct nlm_file *file, struct nlm_lock *lock)
 }
 
 /*
+ * This is a callback from the filesystem for VFS file lock requests.
+ * It will be used if fl_grant is defined and the filesystem can not
+ * respond to the request immediately.
+ * For GETLK request it will copy the reply to the nlm_block.
+ * For SETLK or SETLKW request it will get the local posix lock.
+ * In all cases it will move the block to the head of nlm_blocked q where
+ * nlmsvc_retry_blocked() can send back a reply for SETLKW or revisit the
+ * deferred rpc for GETLK and SETLK.
+ */
+static void
+nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
+			     int result)
+{
+	block->b_flags |= B_GOT_CALLBACK;
+	if (result == 0)
+		block->b_granted = 1;
+	else
+		block->b_flags |= B_TIMED_OUT;
+	if (conf) {
+		if (block->b_fl)
+			locks_copy_lock(block->b_fl, conf);
+	}
+}
+
+static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
+					int result)
+{
+	struct nlm_block *block;
+	int rc = -ENOENT;
+
+	lock_kernel();
+	list_for_each_entry(block, &nlm_blocked, b_list) {
+		if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
+			dprintk("lockd: nlmsvc_notify_blocked block %p flags %d\n",
+							block, block->b_flags);
+			if (block->b_flags & B_QUEUED) {
+				if (block->b_flags & B_TIMED_OUT) {
+					rc = -ENOLCK;
+					break;
+				}
+				nlmsvc_update_deferred_block(block, conf, result);
+			} else if (result == 0)
+				block->b_granted = 1;
+
+			nlmsvc_insert_block(block, 0);
+			svc_wake_up(block->b_daemon);
+			rc = 0;
+			break;
+		}
+	}
+	unlock_kernel();
+	if (rc == -ENOENT)
+		printk(KERN_WARNING "lockd: grant for unknown block\n");
+	return rc;
+}
+
+/*
  * Unblock a blocked lock request. This is a callback invoked from the
  * VFS layer when a lock on which we blocked is removed.
  *
@@ -531,6 +687,7 @@ static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2)
 struct lock_manager_operations nlmsvc_lock_operations = {
 	.fl_compare_owner = nlmsvc_same_owner,
 	.fl_notify = nlmsvc_notify_blocked,
+	.fl_grant = nlmsvc_grant_deferred,
 };
 
 /*
@@ -553,6 +710,8 @@ nlmsvc_grant_blocked(struct nlm_block *block)
 
 	dprintk("lockd: grant blocked lock %p\n", block);
 
+	kref_get(&block->b_count);
+
 	/* Unlink block request from list */
 	nlmsvc_unlink_block(block);
 
@@ -566,20 +725,23 @@ nlmsvc_grant_blocked(struct nlm_block *block)
 
 	/* Try the lock operation again */
 	lock->fl.fl_flags |= FL_SLEEP;
-	error = posix_lock_file(file->f_file, &lock->fl);
+	error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
 	lock->fl.fl_flags &= ~FL_SLEEP;
 
 	switch (error) {
 	case 0:
 		break;
 	case -EAGAIN:
-		dprintk("lockd: lock still blocked\n");
+	case -EINPROGRESS:
+		dprintk("lockd: lock still blocked error %d\n", error);
 		nlmsvc_insert_block(block, NLM_NEVER);
+		nlmsvc_release_block(block);
 		return;
 	default:
 		printk(KERN_WARNING "lockd: unexpected error %d in %s!\n",
 				-error, __FUNCTION__);
 		nlmsvc_insert_block(block, 10 * HZ);
+		nlmsvc_release_block(block);
 		return;
 	}
 
@@ -592,7 +754,6 @@ callback:
 	nlmsvc_insert_block(block, 30 * HZ);
 
 	/* Call the client */
-	kref_get(&block->b_count);
 	nlm_async_call(block->b_call, NLMPROC_GRANTED_MSG, &nlmsvc_grant_ops);
 }
 
@@ -665,6 +826,23 @@ nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
 	nlmsvc_release_block(block);
 }
 
+/* Helper function to handle retry of a deferred block.
+ * If it is a blocking lock, call grant_blocked.
+ * For a non-blocking lock or test lock, revisit the request.
+ */
+static void
+retry_deferred_block(struct nlm_block *block)
+{
+	if (!(block->b_flags & B_GOT_CALLBACK))
+		block->b_flags |= B_TIMED_OUT;
+	nlmsvc_insert_block(block, NLM_TIMEOUT);
+	dprintk("revisit block %p flags %d\n",	block, block->b_flags);
+	if (block->b_deferred_req) {
+		block->b_deferred_req->revisit(block->b_deferred_req, 0);
+		block->b_deferred_req = NULL;
+	}
+}
+
 /*
  * Retry all blocked locks that have been notified. This is where lockd
  * picks up locks that can be granted, or grant notifications that must
@@ -688,9 +866,12 @@ nlmsvc_retry_blocked(void)
 
 		dprintk("nlmsvc_retry_blocked(%p, when=%ld)\n",
 			block, block->b_when);
-		kref_get(&block->b_count);
-		nlmsvc_grant_blocked(block);
-		nlmsvc_release_block(block);
+		if (block->b_flags & B_QUEUED) {
+			dprintk("nlmsvc_retry_blocked delete block (%p, granted=%d, flags=%d)\n",
+				block, block->b_granted, block->b_flags);
+			retry_deferred_block(block);
+		} else
+			nlmsvc_grant_blocked(block);
 	}
 
 	return timeout;
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 31cb4842573..9cd5c8b3759 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -33,6 +33,7 @@ cast_to_nlm(__be32 status, u32 vers)
 		case nlm_lck_denied_nolocks:
 		case nlm_lck_blocked:
 		case nlm_lck_denied_grace_period:
+		case nlm_drop_reply:
 			break;
 		case nlm4_deadlock:
 			status = nlm_lck_denied;
@@ -127,7 +128,9 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 		return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success;
 
 	/* Now check for conflicting locks */
-	resp->status = cast_status(nlmsvc_testlock(file, &argp->lock, &resp->lock));
+	resp->status = cast_status(nlmsvc_testlock(rqstp, file, &argp->lock, &resp->lock, &resp->cookie));
+	if (resp->status == nlm_drop_reply)
+		return rpc_drop_reply;
 
 	dprintk("lockd: TEST          status %d vers %d\n",
 		ntohl(resp->status), rqstp->rq_vers);
@@ -172,6 +175,8 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	/* Now try to lock the file */
 	resp->status = cast_status(nlmsvc_lock(rqstp, file, &argp->lock,
 					       argp->block, &argp->cookie));
+	if (resp->status == nlm_drop_reply)
+		return rpc_drop_reply;
 
 	dprintk("lockd: LOCK          status %d\n", ntohl(resp->status));
 	nlm_release_host(host);
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index c0df00c74ce..84ebba33b98 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -182,7 +182,7 @@ again:
 			lock.fl_type  = F_UNLCK;
 			lock.fl_start = 0;
 			lock.fl_end   = OFFSET_MAX;
-			if (posix_lock_file(file->f_file, &lock) < 0) {
+			if (vfs_lock_file(file->f_file, F_SETLK, &lock, NULL) < 0) {
 				printk("lockd: unlock failure in %s:%d\n",
 						__FILE__, __LINE__);
 				return 1;