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, 407 insertions, 0 deletions

diff --git a/sys/rpc/svc_generic.c b/sys/rpc/svc_generic.c
new file mode 100644
index 0000000..522b413
--- /dev/null
+++ b/sys/rpc/svc_generic.c
@@ -0,0 +1,407 @@
+/*	$NetBSD: svc_generic.c,v 1.3 2000/07/06 03:10:35 christos 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
+ */
+
+/*
+ * Copyright (c) 1986-1991 by Sun Microsystems Inc.
+ */
+
+#if defined(LIBC_SCCS) && !defined(lint)
+#ident	"@(#)svc_generic.c	1.19	94/04/24 SMI" 
+static char sccsid[] = "@(#)svc_generic.c 1.21 89/02/28 Copyr 1988 Sun Micro";
+#endif
+#include <sys/cdefs.h>
+__FBSDID("$FreeBSD$");
+
+/*
+ * svc_generic.c, Server side for RPC.
+ *
+ */
+
+#include "opt_inet6.h"
+
+#include <sys/param.h>
+#include <sys/lock.h>
+#include <sys/kernel.h>
+#include <sys/malloc.h>
+#include <sys/mutex.h>
+#include <sys/protosw.h>
+#include <sys/queue.h>
+#include <sys/socket.h>
+#include <sys/socketvar.h>
+#include <sys/systm.h>
+#include <sys/sx.h>
+#include <sys/ucred.h>
+
+#include <rpc/rpc.h>
+#include <rpc/rpcb_clnt.h>
+#include <rpc/nettype.h>
+
+#include "rpc_com.h"
+
+extern int __svc_vc_setflag(SVCXPRT *, int);
+
+/*
+ * The highest level interface for server creation.
+ * It tries for all the nettokens in that particular class of token
+ * and returns the number of handles it can create and/or find.
+ *
+ * It creates a link list of all the handles it could create.
+ * If svc_create() is called multiple times, it uses the handle
+ * created earlier instead of creating a new handle every time.
+ */
+int
+svc_create(
+	SVCPOOL *pool,
+	void (*dispatch)(struct svc_req *, SVCXPRT *),
+	rpcprog_t prognum,		/* Program number */
+	rpcvers_t versnum,		/* Version number */
+	const char *nettype)		/* Networktype token */
+{
+	int num = 0;
+	SVCXPRT *xprt;
+	struct netconfig *nconf;
+	void *handle;
+
+	if ((handle = __rpc_setconf(nettype)) == NULL) {
+		printf("svc_create: unknown protocol");
+		return (0);
+	}
+	while ((nconf = __rpc_getconf(handle)) != NULL) {
+		mtx_lock(&pool->sp_lock);
+		TAILQ_FOREACH(xprt, &pool->sp_xlist, xp_link) {
+			if (strcmp(xprt->xp_netid, nconf->nc_netid) == 0) {
+				/* Found an old one, use it */
+				mtx_unlock(&pool->sp_lock);
+				(void) rpcb_unset(prognum, versnum, nconf);
+				if (svc_reg(xprt, prognum, versnum,
+					dispatch, nconf) == FALSE) {
+					printf(
+		"svc_create: could not register prog %u vers %u on %s\n",
+					(unsigned)prognum, (unsigned)versnum,
+					 nconf->nc_netid);
+					mtx_lock(&pool->sp_lock);
+				} else {
+					num++;
+					mtx_lock(&pool->sp_lock);
+					break;
+				}
+			}
+		}
+		mtx_unlock(&pool->sp_lock);
+		if (xprt == NULL) {
+			/* It was not found. Now create a new one */
+			xprt = svc_tp_create(pool, dispatch, prognum, versnum,
+			    NULL, nconf);
+			if (xprt)
+				num++;
+		}
+	}
+	__rpc_endconf(handle);
+	/*
+	 * In case of num == 0; the error messages are generated by the
+	 * underlying layers; and hence not needed here.
+	 */
+	return (num);
+}
+
+/*
+ * The high level interface to svc_tli_create().
+ * It tries to create a server for "nconf" and registers the service
+ * with the rpcbind. It calls svc_tli_create();
+ */
+SVCXPRT *
+svc_tp_create(
+	SVCPOOL *pool,
+	void (*dispatch)(struct svc_req *, SVCXPRT *),
+	rpcprog_t prognum,		/* Program number */
+	rpcvers_t versnum,		/* Version number */
+	const char *uaddr,		/* Address (or null for default) */
+	const struct netconfig *nconf) /* Netconfig structure for the network */
+{
+	struct netconfig nconfcopy;
+	struct netbuf *taddr;
+	struct t_bind bind;
+	SVCXPRT *xprt;
+
+	if (nconf == NULL) {
+		printf(
+	"svc_tp_create: invalid netconfig structure for prog %u vers %u\n",
+				(unsigned)prognum, (unsigned)versnum);
+		return (NULL);
+	}
+	if (uaddr) {
+		taddr = uaddr2taddr(nconf, uaddr);
+		bind.addr = *taddr;
+		free(taddr, M_RPC);
+		bind.qlen = SOMAXCONN;
+		xprt = svc_tli_create(pool, NULL, nconf, &bind, 0, 0);
+		free(bind.addr.buf, M_RPC);
+	} else {
+		xprt = svc_tli_create(pool, NULL, nconf, NULL, 0, 0);
+	}
+	if (xprt == NULL) {
+		return (NULL);
+	}
+	/*LINTED const castaway*/
+	nconfcopy = *nconf;
+	(void) rpcb_unset(prognum, versnum, &nconfcopy);
+	if (svc_reg(xprt, prognum, versnum, dispatch, nconf) == FALSE) {
+		printf(
+		"svc_tp_create: Could not register prog %u vers %u on %s\n",
+				(unsigned)prognum, (unsigned)versnum,
+				nconf->nc_netid);
+		SVC_DESTROY(xprt);
+		return (NULL);
+	}
+	return (xprt);
+}
+
+/*
+ * Bind a socket to a privileged IP port
+ */
+int bindresvport(struct socket *so, struct sockaddr *sa);
+int
+bindresvport(struct socket *so, struct sockaddr *sa)
+{
+	int old, error, af;
+	bool_t freesa = FALSE;
+	struct sockaddr_in *sin;
+#ifdef INET6
+	struct sockaddr_in6 *sin6;
+#endif
+	struct sockopt opt;
+	int proto, portrange, portlow;
+	u_int16_t *portp;
+	socklen_t salen;
+
+	if (sa == NULL) {
+		error = so->so_proto->pr_usrreqs->pru_sockaddr(so, &sa);
+		if (error)
+			return (error);
+		freesa = TRUE;
+		af = sa->sa_family;
+		salen = sa->sa_len;
+		memset(sa, 0, sa->sa_len);
+	} else {
+		af = sa->sa_family;
+		salen = sa->sa_len;
+	}
+
+	switch (af) {
+	case AF_INET:
+		proto = IPPROTO_IP;
+		portrange = IP_PORTRANGE;
+		portlow = IP_PORTRANGE_LOW;
+		sin = (struct sockaddr_in *)sa;
+		portp = &sin->sin_port;
+		break;
+#ifdef INET6
+	case AF_INET6:
+		proto = IPPROTO_IPV6;
+		portrange = IPV6_PORTRANGE;
+		portlow = IPV6_PORTRANGE_LOW;
+		sin6 = (struct sockaddr_in6 *)sa;
+		portp = &sin6->sin6_port;
+		break;
+#endif
+	default:
+		return (EPFNOSUPPORT);
+	}
+
+	sa->sa_family = af;
+	sa->sa_len = salen;
+
+	if (*portp == 0) {
+		bzero(&opt, sizeof(opt));
+		opt.sopt_dir = SOPT_GET;
+		opt.sopt_level = proto;
+		opt.sopt_name = portrange;
+		opt.sopt_val = &old;
+		opt.sopt_valsize = sizeof(old);
+		error = sogetopt(so, &opt);
+		if (error)
+			goto out;
+
+		opt.sopt_dir = SOPT_SET;
+		opt.sopt_val = &portlow;
+		error = sosetopt(so, &opt);
+		if (error)
+			goto out;
+	}
+
+	error = sobind(so, sa, curthread);
+
+	if (*portp == 0) {
+		if (error) {
+			opt.sopt_dir = SOPT_SET;
+			opt.sopt_val = &old;
+			sosetopt(so, &opt);
+		}
+	}
+out:
+	if (freesa)
+		free(sa, M_SONAME);
+
+	return (error);
+}
+
+/*
+ * If so is NULL, then it opens a socket for the given transport
+ * provider (nconf cannot be NULL then). If the t_state is T_UNBND and
+ * bindaddr is NON-NULL, it performs a t_bind using the bindaddr. For
+ * NULL bindadr and Connection oriented transports, the value of qlen
+ * is set to 8.
+ *
+ * If sendsz or recvsz are zero, their default values are chosen.
+ */
+SVCXPRT *
+svc_tli_create(
+	SVCPOOL *pool,
+	struct socket *so,		/* Connection end point */
+	const struct netconfig *nconf,	/* Netconfig struct for nettoken */
+	const struct t_bind *bindaddr,	/* Local bind address */
+	size_t sendsz,			/* Max sendsize */
+	size_t recvsz)			/* Max recvsize */
+{
+	SVCXPRT *xprt = NULL;		/* service handle */
+	bool_t madeso = FALSE;		/* whether so opened here  */
+	struct __rpc_sockinfo si;
+	struct sockaddr_storage ss;
+
+	if (!so) {
+		if (nconf == NULL) {
+			printf("svc_tli_create: invalid netconfig\n");
+			return (NULL);
+		}
+		so = __rpc_nconf2socket(nconf);
+		if (!so) {
+			printf(
+			    "svc_tli_create: could not open connection for %s\n",
+					nconf->nc_netid);
+			return (NULL);
+		}
+		__rpc_nconf2sockinfo(nconf, &si);
+		madeso = TRUE;
+	} else {
+		/*
+		 * It is an open socket. Get the transport info.
+		 */
+		if (!__rpc_socket2sockinfo(so, &si)) {
+			printf(
+		"svc_tli_create: could not get transport information\n");
+			return (NULL);
+		}
+	}
+
+	/*
+	 * If the socket is unbound, try to bind it.
+	 */
+	if (madeso || !__rpc_sockisbound(so)) {
+		if (bindaddr == NULL) {
+			if (bindresvport(so, NULL)) {
+				memset(&ss, 0, sizeof ss);
+				ss.ss_family = si.si_af;
+				ss.ss_len = si.si_alen;
+				if (sobind(so, (struct sockaddr *)&ss,
+					curthread)) {
+					printf(
+			"svc_tli_create: could not bind to anonymous port\n");
+					goto freedata;
+				}
+			}
+			solisten(so, SOMAXCONN, curthread);
+		} else {
+			if (bindresvport(so,
+				(struct sockaddr *)bindaddr->addr.buf)) {
+				printf(
+		"svc_tli_create: could not bind to requested address\n");
+				goto freedata;
+			}
+			solisten(so, (int)bindaddr->qlen, curthread);
+		}
+			
+	}
+	/*
+	 * call transport specific function.
+	 */
+	switch (si.si_socktype) {
+		case SOCK_STREAM:
+#if 0
+			slen = sizeof ss;
+			if (_getpeername(fd, (struct sockaddr *)(void *)&ss, &slen)
+			    == 0) {
+				/* accepted socket */
+				xprt = svc_fd_create(fd, sendsz, recvsz);
+			} else
+#endif
+				xprt = svc_vc_create(pool, so, sendsz, recvsz);
+			if (!nconf || !xprt)
+				break;
+#if 0
+			/* XXX fvdl */
+			if (strcmp(nconf->nc_protofmly, "inet") == 0 ||
+			    strcmp(nconf->nc_protofmly, "inet6") == 0)
+				(void) __svc_vc_setflag(xprt, TRUE);
+#endif
+			break;
+		case SOCK_DGRAM:
+			xprt = svc_dg_create(pool, so, sendsz, recvsz);
+			break;
+		default:
+			printf("svc_tli_create: bad service type");
+			goto freedata;
+	}
+
+	if (xprt == NULL)
+		/*
+		 * The error messages here are spitted out by the lower layers:
+		 * svc_vc_create(), svc_fd_create() and svc_dg_create().
+		 */
+		goto freedata;
+
+	/* Fill in type of service */
+	xprt->xp_type = __rpc_socktype2seman(si.si_socktype);
+
+	if (nconf) {
+		xprt->xp_netid = strdup(nconf->nc_netid, M_RPC);
+	}
+	return (xprt);
+
+freedata:
+	if (madeso)
+		(void)soclose(so);
+	if (xprt) {
+		if (!madeso) /* so that svc_destroy doesnt close fd */
+			xprt->xp_socket = NULL;
+		SVC_DESTROY(xprt);
+	}
+	return (NULL);
+}