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, 200 insertions, 0 deletions

diff --git a/sys/rpc/rpc_callmsg.c b/sys/rpc/rpc_callmsg.c
new file mode 100644
index 0000000..65637c5
--- /dev/null
+++ b/sys/rpc/rpc_callmsg.c
@@ -0,0 +1,200 @@
+/*	$NetBSD: rpc_callmsg.c,v 1.16 2000/07/14 08:40:42 fvdl Exp $	*/
+
+/*
+ * Sun RPC is a product of Sun Microsystems, Inc. and is provided for
+ * unrestricted use provided that this legend is included on all tape
+ * media and as a part of the software program in whole or part.  Users
+ * may copy or modify Sun RPC without charge, but are not authorized
+ * to license or distribute it to anyone else except as part of a product or
+ * program developed by the user.
+ *
+ * SUN RPC IS PROVIDED AS IS WITH NO WARRANTIES OF ANY KIND INCLUDING THE
+ * WARRANTIES OF DESIGN, MERCHANTIBILITY AND FITNESS FOR A PARTICULAR
+ * PURPOSE, OR ARISING FROM A COURSE OF DEALING, USAGE OR TRADE PRACTICE.
+ *
+ * Sun RPC is provided with no support and without any obligation on the
+ * part of Sun Microsystems, Inc. to assist in its use, correction,
+ * modification or enhancement.
+ *
+ * SUN MICROSYSTEMS, INC. SHALL HAVE NO LIABILITY WITH RESPECT TO THE
+ * INFRINGEMENT OF COPYRIGHTS, TRADE SECRETS OR ANY PATENTS BY SUN RPC
+ * OR ANY PART THEREOF.
+ *
+ * In no event will Sun Microsystems, Inc. be liable for any lost revenue
+ * or profits or other special, indirect and consequential damages, even if
+ * Sun has been advised of the possibility of such damages.
+ *
+ * Sun Microsystems, Inc.
+ * 2550 Garcia Avenue
+ * Mountain View, California  94043
+ */
+
+#if defined(LIBC_SCCS) && !defined(lint)
+static char *sccsid2 = "@(#)rpc_callmsg.c 1.4 87/08/11 Copyr 1984 Sun Micro";
+static char *sccsid = "@(#)rpc_callmsg.c	2.1 88/07/29 4.0 RPCSRC";
+#endif
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD$");
+
+/*
+ * rpc_callmsg.c
+ *
+ * Copyright (C) 1984, Sun Microsystems, Inc.
+ *
+ */
+
+#include <sys/param.h>
+#include <sys/systm.h>
+#include <sys/malloc.h>
+
+#include <rpc/rpc.h>
+
+/*
+ * XDR a call message
+ */
+bool_t
+xdr_callmsg(XDR *xdrs, struct rpc_msg *cmsg)
+{
+	enum msg_type *prm_direction;
+	int32_t *buf;
+	struct opaque_auth *oa;
+
+	if (xdrs->x_op == XDR_ENCODE) {
+		if (cmsg->rm_call.cb_cred.oa_length > MAX_AUTH_BYTES) {
+			return (FALSE);
+		}
+		if (cmsg->rm_call.cb_verf.oa_length > MAX_AUTH_BYTES) {
+			return (FALSE);
+		}
+		buf = XDR_INLINE(xdrs, 8 * BYTES_PER_XDR_UNIT
+			+ RNDUP(cmsg->rm_call.cb_cred.oa_length)
+			+ 2 * BYTES_PER_XDR_UNIT
+			+ RNDUP(cmsg->rm_call.cb_verf.oa_length));
+		if (buf != NULL) {
+			IXDR_PUT_INT32(buf, cmsg->rm_xid);
+			IXDR_PUT_ENUM(buf, cmsg->rm_direction);
+			if (cmsg->rm_direction != CALL) {
+				return (FALSE);
+			}
+			IXDR_PUT_INT32(buf, cmsg->rm_call.cb_rpcvers);
+			if (cmsg->rm_call.cb_rpcvers != RPC_MSG_VERSION) {
+				return (FALSE);
+			}
+			IXDR_PUT_INT32(buf, cmsg->rm_call.cb_prog);
+			IXDR_PUT_INT32(buf, cmsg->rm_call.cb_vers);
+			IXDR_PUT_INT32(buf, cmsg->rm_call.cb_proc);
+			oa = &cmsg->rm_call.cb_cred;
+			IXDR_PUT_ENUM(buf, oa->oa_flavor);
+			IXDR_PUT_INT32(buf, oa->oa_length);
+			if (oa->oa_length) {
+				memcpy(buf, oa->oa_base, oa->oa_length);
+				buf += RNDUP(oa->oa_length) / sizeof (int32_t);
+			}
+			oa = &cmsg->rm_call.cb_verf;
+			IXDR_PUT_ENUM(buf, oa->oa_flavor);
+			IXDR_PUT_INT32(buf, oa->oa_length);
+			if (oa->oa_length) {
+				memcpy(buf, oa->oa_base, oa->oa_length);
+				/* no real need....
+				buf += RNDUP(oa->oa_length) / sizeof (int32_t);
+				*/
+			}
+			return (TRUE);
+		}
+	}
+	if (xdrs->x_op == XDR_DECODE) {
+		buf = XDR_INLINE(xdrs, 8 * BYTES_PER_XDR_UNIT);
+		if (buf != NULL) {
+			cmsg->rm_xid = IXDR_GET_UINT32(buf);
+			cmsg->rm_direction = IXDR_GET_ENUM(buf, enum msg_type);
+			if (cmsg->rm_direction != CALL) {
+				return (FALSE);
+			}
+			cmsg->rm_call.cb_rpcvers = IXDR_GET_UINT32(buf);
+			if (cmsg->rm_call.cb_rpcvers != RPC_MSG_VERSION) {
+				return (FALSE);
+			}
+			cmsg->rm_call.cb_prog = IXDR_GET_UINT32(buf);
+			cmsg->rm_call.cb_vers = IXDR_GET_UINT32(buf);
+			cmsg->rm_call.cb_proc = IXDR_GET_UINT32(buf);
+			oa = &cmsg->rm_call.cb_cred;
+			oa->oa_flavor = IXDR_GET_ENUM(buf, enum_t);
+			oa->oa_length = (u_int)IXDR_GET_UINT32(buf);
+			if (oa->oa_length) {
+				if (oa->oa_length > MAX_AUTH_BYTES) {
+					return (FALSE);
+				}
+				if (oa->oa_base == NULL) {
+					oa->oa_base = (caddr_t)
+					    mem_alloc(oa->oa_length);
+					if (oa->oa_base == NULL)
+						return (FALSE);
+				}
+				buf = XDR_INLINE(xdrs, RNDUP(oa->oa_length));
+				if (buf == NULL) {
+					if (xdr_opaque(xdrs, oa->oa_base,
+					    oa->oa_length) == FALSE) {
+						return (FALSE);
+					}
+				} else {
+					memcpy(oa->oa_base, buf,
+					    oa->oa_length);
+					/* no real need....
+					buf += RNDUP(oa->oa_length) /
+						sizeof (int32_t);
+					*/
+				}
+			}
+			oa = &cmsg->rm_call.cb_verf;
+			buf = XDR_INLINE(xdrs, 2 * BYTES_PER_XDR_UNIT);
+			if (buf == NULL) {
+				if (xdr_enum(xdrs, &oa->oa_flavor) == FALSE ||
+				    xdr_u_int(xdrs, &oa->oa_length) == FALSE) {
+					return (FALSE);
+				}
+			} else {
+				oa->oa_flavor = IXDR_GET_ENUM(buf, enum_t);
+				oa->oa_length = (u_int)IXDR_GET_UINT32(buf);
+			}
+			if (oa->oa_length) {
+				if (oa->oa_length > MAX_AUTH_BYTES) {
+					return (FALSE);
+				}
+				if (oa->oa_base == NULL) {
+					oa->oa_base = (caddr_t)
+					    mem_alloc(oa->oa_length);
+					if (oa->oa_base == NULL)
+						return (FALSE);
+				}
+				buf = XDR_INLINE(xdrs, RNDUP(oa->oa_length));
+				if (buf == NULL) {
+					if (xdr_opaque(xdrs, oa->oa_base,
+					    oa->oa_length) == FALSE) {
+						return (FALSE);
+					}
+				} else {
+					memcpy(oa->oa_base, buf,
+					    oa->oa_length);
+					/* no real need...
+					buf += RNDUP(oa->oa_length) /
+						sizeof (int32_t);
+					*/
+				}
+			}
+			return (TRUE);
+		}
+	}
+	prm_direction = &cmsg->rm_direction;
+	if (
+	    xdr_uint32_t(xdrs, &(cmsg->rm_xid)) &&
+	    xdr_enum(xdrs, (enum_t *) prm_direction) &&
+	    (cmsg->rm_direction == CALL) &&
+	    xdr_uint32_t(xdrs, &(cmsg->rm_call.cb_rpcvers)) &&
+	    (cmsg->rm_call.cb_rpcvers == RPC_MSG_VERSION) &&
+	    xdr_uint32_t(xdrs, &(cmsg->rm_call.cb_prog)) &&
+	    xdr_uint32_t(xdrs, &(cmsg->rm_call.cb_vers)) &&
+	    xdr_uint32_t(xdrs, &(cmsg->rm_call.cb_proc)) &&
+	    xdr_opaque_auth(xdrs, &(cmsg->rm_call.cb_cred)) )
+		return (xdr_opaque_auth(xdrs, &(cmsg->rm_call.cb_verf)));
+	return (FALSE);
+}