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

fs/fuse/file.c

@@ -738,8 +738,7 @@ static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	if (cmd == F_GETLK) {
 		if (fc->no_lock) {
-			if (!posix_test_lock(file, fl, fl))
-				fl->fl_type = F_UNLCK;
+			posix_test_lock(file, fl);
 			err = 0;
 		} else
 			err = fuse_getlk(file, fl);

fs/gfs2/locking/dlm/plock.c

@@ -25,6 +25,15 @@ struct plock_op {
 	struct gdlm_plock_info info;
 };
 
+struct plock_xop {
+	struct plock_op xop;
+	void *callback;
+	void *fl;
+	void *file;
+	struct file_lock flc;
+};
+
+
 static inline void set_version(struct gdlm_plock_info *info)
 {
 	info->version[0] = GDLM_PLOCK_VERSION_MAJOR;
@@ -64,12 +73,14 @@ int gdlm_plock(void *lockspace, struct lm_lockname *name,
 {
 	struct gdlm_ls *ls = lockspace;
 	struct plock_op *op;
+	struct plock_xop *xop;
 	int rv;
 
-	op = kzalloc(sizeof(*op), GFP_KERNEL);
-	if (!op)
+	xop = kzalloc(sizeof(*xop), GFP_KERNEL);
+	if (!xop)
 		return -ENOMEM;
 
+	op = &xop->xop;
 	op->info.optype		= GDLM_PLOCK_OP_LOCK;
 	op->info.pid		= fl->fl_pid;
 	op->info.ex		= (fl->fl_type == F_WRLCK);
@@ -79,9 +90,21 @@ int gdlm_plock(void *lockspace, struct lm_lockname *name,
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
 	op->info.owner		= (__u64)(long) fl->fl_owner;
+	if (fl->fl_lmops && fl->fl_lmops->fl_grant) {
+		xop->callback	= fl->fl_lmops->fl_grant;
+		locks_init_lock(&xop->flc);
+		locks_copy_lock(&xop->flc, fl);
+		xop->fl		= fl;
+		xop->file	= file;
+	} else
+		xop->callback	= NULL;
 
 	send_op(op);
+
+	if (xop->callback == NULL)
 		wait_event(recv_wq, (op->done != 0));
+	else
+		return -EINPROGRESS;
 
 	spin_lock(&ops_lock);
 	if (!list_empty(&op->list)) {
@@ -99,7 +122,63 @@ int gdlm_plock(void *lockspace, struct lm_lockname *name,
 				  (unsigned long long)name->ln_number);
 	}
 
-	kfree(op);
+	kfree(xop);
+	return rv;
+}
+
+/* Returns failure iff a succesful lock operation should be canceled */
+static int gdlm_plock_callback(struct plock_op *op)
+{
+	struct file *file;
+	struct file_lock *fl;
+	struct file_lock *flc;
+	int (*notify)(void *, void *, int) = NULL;
+	struct plock_xop *xop = (struct plock_xop *)op;
+	int rv = 0;
+
+	spin_lock(&ops_lock);
+	if (!list_empty(&op->list)) {
+		printk(KERN_INFO "plock op on list\n");
+		list_del(&op->list);
+	}
+	spin_unlock(&ops_lock);
+
+	/* check if the following 2 are still valid or make a copy */
+	file = xop->file;
+	flc = &xop->flc;
+	fl = xop->fl;
+	notify = xop->callback;
+
+	if (op->info.rv) {
+		notify(flc, NULL, op->info.rv);
+		goto out;
+	}
+
+	/* got fs lock; bookkeep locally as well: */
+	flc->fl_flags &= ~FL_SLEEP;
+	if (posix_lock_file(file, flc, NULL)) {
+		/*
+		 * This can only happen in the case of kmalloc() failure.
+		 * The filesystem's own lock is the authoritative lock,
+		 * so a failure to get the lock locally is not a disaster.
+		 * As long as GFS cannot reliably cancel locks (especially
+		 * in a low-memory situation), we're better off ignoring
+		 * this failure than trying to recover.
+		 */
+		log_error("gdlm_plock: vfs lock error file %p fl %p",
+				file, fl);
+	}
+
+	rv = notify(flc, NULL, 0);
+	if (rv) {
+		/* XXX: We need to cancel the fs lock here: */
+		printk("gfs2 lock granted after lock request failed;"
+						" dangling lock!\n");
+		goto out;
+	}
+
+out:
+	kfree(xop);
 	return rv;
 }
 
@@ -138,6 +217,9 @@ int gdlm_punlock(void *lockspace, struct lm_lockname *name,
 
 	rv = op->info.rv;
 
+	if (rv == -ENOENT)
+		rv = 0;
+
 	kfree(op);
 	return rv;
 }
@@ -161,6 +243,7 @@ int gdlm_plock_get(void *lockspace, struct lm_lockname *name,
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
 
+
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));
 
@@ -173,9 +256,10 @@ int gdlm_plock_get(void *lockspace, struct lm_lockname *name,
 
 	rv = op->info.rv;
 
-	if (rv == 0)
 	fl->fl_type = F_UNLCK;
-	else if (rv > 0) {
+	if (rv == -ENOENT)
+		rv = 0;
+	else if (rv == 0 && op->info.pid != fl->fl_pid) {
 		fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
 		fl->fl_pid = op->info.pid;
 		fl->fl_start = op->info.start;
@@ -243,9 +327,14 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
 	}
 	spin_unlock(&ops_lock);
 
-	if (found)
-		wake_up(&recv_wq);
+	if (found) {
+		struct plock_xop *xop;
+		xop = (struct plock_xop *)op;
+		if (xop->callback)
+			count = gdlm_plock_callback(op);
 		else
+			wake_up(&recv_wq);
+	} else
 		printk(KERN_INFO "gdlm dev_write no op %x %llx\n", info.fsid,
 			(unsigned long long)info.number);
 	return count;

fs/gfs2/locking/nolock/main.c

@@ -164,13 +164,7 @@ static void nolock_unhold_lvb(void *lock, char *lvb)
 static int nolock_plock_get(void *lockspace, struct lm_lockname *name,
 			    struct file *file, struct file_lock *fl)
 {
-	struct file_lock tmp;
-	int ret;
-
-	ret = posix_test_lock(file, fl, &tmp);
-	fl->fl_type = F_UNLCK;
-	if (ret)
-		memcpy(fl, &tmp, sizeof(struct file_lock));
+	posix_test_lock(file, fl);
 
 	return 0;
 }

fs/gfs2/ops_file.c

@@ -513,18 +513,18 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	if (sdp->sd_args.ar_localflocks) {
 		if (IS_GETLK(cmd)) {
-			struct file_lock tmp;
-			int ret;
-			ret = posix_test_lock(file, fl, &tmp);
-			fl->fl_type = F_UNLCK;
-			if (ret)
-				memcpy(fl, &tmp, sizeof(struct file_lock));
+			posix_test_lock(file, fl);
 			return 0;
 		} else {
 			return posix_lock_file_wait(file, fl);
 		}
 	}
 
+	if (cmd == F_CANCELLK) {
+		/* Hack: */
+		cmd = F_SETLK;
+		fl->fl_type = F_UNLCK;
+	}
 	if (IS_GETLK(cmd))
 		return gfs2_lm_plock_get(sdp, &name, file, fl);
 	else if (fl->fl_type == F_UNLCK)

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);

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);

fs/lockd/svcsubs.c

@@ -182,7 +182,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file,
 			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;

fs/nfs/file.c

@@ -391,17 +391,12 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 
 static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
 {
-	struct file_lock cfl;
 	struct inode *inode = filp->f_mapping->host;
 	int status = 0;
 
 	lock_kernel();
 	/* Try local locking first */
-	if (posix_test_lock(filp, fl, &cfl)) {
-		fl->fl_start = cfl.fl_start;
-		fl->fl_end = cfl.fl_end;
-		fl->fl_type = cfl.fl_type;
-		fl->fl_pid = cfl.fl_pid;
+	if (posix_test_lock(filp, fl)) {
 		goto out;
 	}
 

fs/nfs/nfs4proc.c

@@ -3017,6 +3017,7 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 		case -NFS4ERR_DENIED:
 			status = 0;
 	}
+	request->fl_ops->fl_release_private(request);
 out:
 	up_read(&clp->cl_sem);
 	return status;

fs/nfsd/nfs4state.c

@@ -50,6 +50,7 @@
 #include <linux/nfsd/xdr4.h>
 #include <linux/namei.h>
 #include <linux/mutex.h>
+#include <linux/lockd/bind.h>
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -2657,6 +2658,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct file_lock conflock;
 	__be32 status = 0;
 	unsigned int strhashval;
+	unsigned int cmd;
 	int err;
 
 	dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n",
@@ -2739,10 +2741,12 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		case NFS4_READ_LT:
 		case NFS4_READW_LT:
 			file_lock.fl_type = F_RDLCK;
+			cmd = F_SETLK;
 		break;
 		case NFS4_WRITE_LT:
 		case NFS4_WRITEW_LT:
 			file_lock.fl_type = F_WRLCK;
+			cmd = F_SETLK;
 		break;
 		default:
 			status = nfserr_inval;
@@ -2769,9 +2773,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	/* XXX?: Just to divert the locks_release_private at the start of
 	 * locks_copy_lock: */
-	conflock.fl_ops = NULL;
-	conflock.fl_lmops = NULL;
-	err = posix_lock_file_conf(filp, &file_lock, &conflock);
+	locks_init_lock(&conflock);
+	err = vfs_lock_file(filp, cmd, &file_lock, &conflock);
 	switch (-err) {
 	case 0: /* success! */
 		update_stateid(&lock_stp->st_stateid);
@@ -2788,7 +2791,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfserr_deadlock;
 		break;
 	default:        
-		dprintk("NFSD: nfsd4_lock: posix_lock_file_conf() failed! status %d\n",err);
+		dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err);
 		status = nfserr_resource;
 		break;
 	}
@@ -2813,7 +2816,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct inode *inode;
 	struct file file;
 	struct file_lock file_lock;
-	struct file_lock conflock;
+	int error;
 	__be32 status;
 
 	if (nfs4_in_grace())
@@ -2869,18 +2872,23 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	nfs4_transform_lock_offset(&file_lock);
 
-	/* posix_test_lock uses the struct file _only_ to resolve the inode.
+	/* vfs_test_lock uses the struct file _only_ to resolve the inode.
 	 * since LOCKT doesn't require an OPEN, and therefore a struct
-	 * file may not exist, pass posix_test_lock a struct file with
+	 * file may not exist, pass vfs_test_lock a struct file with
 	 * only the dentry:inode set.
 	 */
 	memset(&file, 0, sizeof (struct file));
 	file.f_path.dentry = cstate->current_fh.fh_dentry;
 
 	status = nfs_ok;
-	if (posix_test_lock(&file, &file_lock, &conflock)) {
+	error = vfs_test_lock(&file, &file_lock);
+	if (error) {
+		status = nfserrno(error);
+		goto out;
+	}
+	if (file_lock.fl_type != F_UNLCK) {
 		status = nfserr_denied;
-		nfs4_set_lock_denied(&conflock, &lockt->lt_denied);
+		nfs4_set_lock_denied(&file_lock, &lockt->lt_denied);
 	}
 out:
 	nfs4_unlock_state();
@@ -2933,9 +2941,9 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	/*
 	*  Try to unlock the file in the VFS.
 	*/
-	err = posix_lock_file(filp, &file_lock);
+	err = vfs_lock_file(filp, F_SETLK, &file_lock, NULL);
 	if (err) {
-		dprintk("NFSD: nfs4_locku: posix_lock_file failed!\n");
+		dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n");
 		goto out_nfserr;
 	}
 	/*

include/linux/fcntl.h

@@ -3,6 +3,10 @@
 
 #include <asm/fcntl.h>
 
+/* Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace: */
+#define F_CANCELLK	(F_LINUX_SPECIFIC_BASE+5)
+
 #define F_SETLEASE	(F_LINUX_SPECIFIC_BASE+0)
 #define F_GETLEASE	(F_LINUX_SPECIFIC_BASE+1)
 

include/linux/fs.h

@@ -786,6 +786,7 @@ struct file_lock_operations {
 struct lock_manager_operations {
 	int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
 	void (*fl_notify)(struct file_lock *);	/* unblock callback */
+	int (*fl_grant)(struct file_lock *, struct file_lock *, int);
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
 	void (*fl_release_private)(struct file_lock *);
 	void (*fl_break)(struct file_lock *);
@@ -857,11 +858,13 @@ extern void locks_init_lock(struct file_lock *);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
 extern void locks_remove_flock(struct file *);
-extern int posix_test_lock(struct file *, struct file_lock *, struct file_lock *);
-extern int posix_lock_file_conf(struct file *, struct file_lock *, struct file_lock *);
-extern int posix_lock_file(struct file *, struct file_lock *);
+extern int posix_test_lock(struct file *, struct file_lock *);
+extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
 extern int posix_lock_file_wait(struct file *, struct file_lock *);
 extern int posix_unblock_lock(struct file *, struct file_lock *);
+extern int vfs_test_lock(struct file *, struct file_lock *);
+extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
+extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
 extern int __break_lease(struct inode *inode, unsigned int flags);
 extern void lease_get_mtime(struct inode *, struct timespec *time);

include/linux/lockd/lockd.h

@@ -119,6 +119,9 @@ struct nlm_file {
  * couldn't be granted because of a conflicting lock).
  */
 #define NLM_NEVER		(~(unsigned long) 0)
+/* timeout on non-blocking call: */
+#define NLM_TIMEOUT		(7 * HZ)
+
 struct nlm_block {
 	struct kref		b_count;	/* Reference count */
 	struct list_head	b_list;		/* linked list of all blocks */
@@ -130,6 +133,13 @@ struct nlm_block {
 	unsigned int		b_id;		/* block id */
 	unsigned char		b_granted;	/* VFS granted lock */
 	struct nlm_file *	b_file;		/* file in question */
+	struct cache_req *	b_cache_req;	/* deferred request handling */
+	struct file_lock *	b_fl;		/* set for GETLK */
+	struct cache_deferred_req * b_deferred_req;
+	unsigned int		b_flags;	/* block flags */
+#define B_QUEUED		1	/* lock queued */
+#define B_GOT_CALLBACK		2	/* got lock or conflicting lock */
+#define B_TIMED_OUT		4	/* filesystem too slow to respond */
 };
 
 /*
@@ -185,8 +195,8 @@ typedef int	  (*nlm_host_match_fn_t)(struct nlm_host *cur, struct nlm_host *ref)
 __be32		  nlmsvc_lock(struct svc_rqst *, struct nlm_file *,
 					struct nlm_lock *, int, struct nlm_cookie *);
 __be32		  nlmsvc_unlock(struct nlm_file *, struct nlm_lock *);
-__be32		  nlmsvc_testlock(struct nlm_file *, struct nlm_lock *,
-					struct nlm_lock *);
+__be32		  nlmsvc_testlock(struct svc_rqst *, struct nlm_file *,
+			struct nlm_lock *, struct nlm_lock *, struct nlm_cookie *);
 __be32		  nlmsvc_cancel_blocked(struct nlm_file *, struct nlm_lock *);
 unsigned long	  nlmsvc_retry_blocked(void);
 void		  nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *,