Add the new kernel-mode NFS Lock Manager. To use it instead of the

user-mode lock manager, build a kernel with the NFSLOCKD option and
add '-k' to 'rpc_lockd_flags' in rc.conf.

Highlights include:

* Thread-safe kernel RPC client - many threads can use the same RPC
  client handle safely with replies being de-multiplexed at the socket
  upcall (typically driven directly by the NIC interrupt) and handed
  off to whichever thread matches the reply. For UDP sockets, many RPC
  clients can share the same socket. This allows the use of a single
  privileged UDP port number to talk to an arbitrary number of remote
  hosts.

* Single-threaded kernel RPC server. Adding support for multi-threaded
  server would be relatively straightforward and would follow
  approximately the Solaris KPI. A single thread should be sufficient
  for the NLM since it should rarely block in normal operation.

* Kernel mode NLM server supporting cancel requests and granted
  callbacks. I've tested the NLM server reasonably extensively - it
  passes both my own tests and the NFS Connectathon locking tests
  running on Solaris, Mac OS X and Ubuntu Linux.

* Userland NLM client supported. While the NLM server doesn't have
  support for the local NFS client's locking needs, it does have to
  field async replies and granted callbacks from remote NLMs that the
  local client has contacted. We relay these replies to the userland
  rpc.lockd over a local domain RPC socket.

* Robust deadlock detection for the local lock manager. In particular
  it will detect deadlocks caused by a lock request that covers more
  than one blocking request. As required by the NLM protocol, all
  deadlock detection happens synchronously - a user is guaranteed that
  if a lock request isn't rejected immediately, the lock will
  eventually be granted. The old system allowed for a 'deferred
  deadlock' condition where a blocked lock request could wake up and
  find that some other deadlock-causing lock owner had beaten them to
  the lock.

* Since both local and remote locks are managed by the same kernel
  locking code, local and remote processes can safely use file locks
  for mutual exclusion. Local processes have no fairness advantage
  compared to remote processes when contending to lock a region that
  has just been unlocked - the local lock manager enforces a strict
  first-come first-served model for both local and remote lockers.

Sponsored by:	Isilon Systems
PR:		95247 107555 115524 116679
MFC after:	2 weeks

1 files changed, 23 insertions, 3 deletions

diff --git a/sys/sys/fcntl.h b/sys/sys/fcntl.h
index ea8531a..29c7796 100644
--- a/sys/sys/fcntl.h
+++ b/sys/sys/fcntl.h
@@ -178,10 +178,14 @@ typedef	__pid_t		pid_t;
 #define	F_GETOWN	5		/* get SIGIO/SIGURG proc/pgrp */
 #define F_SETOWN	6		/* set SIGIO/SIGURG proc/pgrp */
 #endif
-#define	F_GETLK		7		/* get record locking information */
-#define	F_SETLK		8		/* set record locking information */
-#define	F_SETLKW	9		/* F_SETLK; wait if blocked */
+#define	F_OGETLK	7		/* get record locking information */
+#define	F_OSETLK	8		/* set record locking information */
+#define	F_OSETLKW	9		/* F_SETLK; wait if blocked */
 #define	F_DUP2FD	10		/* duplicate file descriptor to arg */
+#define	F_GETLK		11		/* get record locking information */
+#define	F_SETLK		12		/* set record locking information */
+#define	F_SETLKW	13		/* F_SETLK; wait if blocked */
+#define	F_SETLK_REMOTE	14		/* debugging support for remote locks */
 
 /* file descriptor flags (F_GETFD, F_SETFD) */
 #define	FD_CLOEXEC	1		/* close-on-exec flag */
@@ -190,10 +194,13 @@ typedef	__pid_t		pid_t;
 #define	F_RDLCK		1		/* shared or read lock */
 #define	F_UNLCK		2		/* unlock */
 #define	F_WRLCK		3		/* exclusive or write lock */
+#define	F_UNLCKSYS	4		/* purge locks for a given system ID */ 
+#define	F_CANCEL	5		/* cancel an async lock request */
 #ifdef _KERNEL
 #define	F_WAIT		0x010		/* Wait until lock is granted */
 #define	F_FLOCK		0x020	 	/* Use flock(2) semantics for lock */
 #define	F_POSIX		0x040	 	/* Use POSIX semantics for lock */
+#define	F_REMOTE	0x080		/* Lock owner is remote NFS client */
 #endif
 
 /*
@@ -206,6 +213,19 @@ struct flock {
 	pid_t	l_pid;		/* lock owner */
 	short	l_type;		/* lock type: read/write, etc. */
 	short	l_whence;	/* type of l_start */
+	int	l_sysid;	/* remote system id or zero for local */
+};
+
+/*
+ * Old advisory file segment locking data type,
+ * before adding l_sysid.
+ */
+struct oflock {
+	off_t	l_start;	/* starting offset */
+	off_t	l_len;		/* len = 0 means until end of file */
+	pid_t	l_pid;		/* lock owner */
+	short	l_type;		/* lock type: read/write, etc. */
+	short	l_whence;	/* type of l_start */
 };