mirror of
https://git.FreeBSD.org/src.git
synced 2024-12-27 11:55:06 +00:00
dfdcada31e
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
188 lines
5.0 KiB
C
188 lines
5.0 KiB
C
/*
|
|
* Copyright (c) 2004 by Internet Systems Consortium, Inc. ("ISC")
|
|
* Copyright (c) 1996-1999 by Internet Software Consortium.
|
|
*
|
|
* Permission to use, copy, modify, and distribute this software for any
|
|
* purpose with or without fee is hereby granted, provided that the above
|
|
* copyright notice and this permission notice appear in all copies.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS" AND ISC DISCLAIMS ALL WARRANTIES
|
|
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
|
|
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL ISC BE LIABLE FOR
|
|
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
|
|
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
|
|
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
|
|
* OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
|
|
*/
|
|
|
|
#if defined(LIBC_SCCS) && !defined(lint)
|
|
static const char rcsid[] = "$Id: inet_ntop.c,v 1.3.18.2 2005/11/03 23:02:22 marka Exp $";
|
|
#endif /* LIBC_SCCS and not lint */
|
|
#include <sys/cdefs.h>
|
|
__FBSDID("$FreeBSD$");
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/types.h>
|
|
#include <sys/socket.h>
|
|
#include <sys/systm.h>
|
|
|
|
#include <rpc/types.h>
|
|
#include "rpc_com.h"
|
|
|
|
/*%
|
|
* WARNING: Don't even consider trying to compile this on a system where
|
|
* sizeof(int) < 4. sizeof(int) > 4 is fine; all the world's not a VAX.
|
|
*/
|
|
|
|
static const char *inet_ntop4(const u_char *src, char *dst, socklen_t size);
|
|
static const char *inet_ntop6(const u_char *src, char *dst, socklen_t size);
|
|
|
|
/* char *
|
|
* inet_ntop(af, src, dst, size)
|
|
* convert a network format address to presentation format.
|
|
* return:
|
|
* pointer to presentation format address (`dst'), or NULL (see errno).
|
|
* author:
|
|
* Paul Vixie, 1996.
|
|
*/
|
|
const char *
|
|
__rpc_inet_ntop(int af, const void * __restrict src, char * __restrict dst,
|
|
socklen_t size)
|
|
{
|
|
switch (af) {
|
|
case AF_INET:
|
|
return (inet_ntop4(src, dst, size));
|
|
case AF_INET6:
|
|
return (inet_ntop6(src, dst, size));
|
|
default:
|
|
return (NULL);
|
|
}
|
|
/* NOTREACHED */
|
|
}
|
|
|
|
/* const char *
|
|
* inet_ntop4(src, dst, size)
|
|
* format an IPv4 address
|
|
* return:
|
|
* `dst' (as a const)
|
|
* notes:
|
|
* (1) uses no statics
|
|
* (2) takes a u_char* not an in_addr as input
|
|
* author:
|
|
* Paul Vixie, 1996.
|
|
*/
|
|
static const char *
|
|
inet_ntop4(const u_char *src, char *dst, socklen_t size)
|
|
{
|
|
static const char fmt[] = "%u.%u.%u.%u";
|
|
char tmp[sizeof "255.255.255.255"];
|
|
int l;
|
|
|
|
l = snprintf(tmp, sizeof(tmp), fmt, src[0], src[1], src[2], src[3]);
|
|
if (l <= 0 || (socklen_t) l >= size) {
|
|
return (NULL);
|
|
}
|
|
strlcpy(dst, tmp, size);
|
|
return (dst);
|
|
}
|
|
|
|
/* const char *
|
|
* inet_ntop6(src, dst, size)
|
|
* convert IPv6 binary address into presentation (printable) format
|
|
* author:
|
|
* Paul Vixie, 1996.
|
|
*/
|
|
static const char *
|
|
inet_ntop6(const u_char *src, char *dst, socklen_t size)
|
|
{
|
|
/*
|
|
* Note that int32_t and int16_t need only be "at least" large enough
|
|
* to contain a value of the specified size. On some systems, like
|
|
* Crays, there is no such thing as an integer variable with 16 bits.
|
|
* Keep this in mind if you think this function should have been coded
|
|
* to use pointer overlays. All the world's not a VAX.
|
|
*/
|
|
char tmp[sizeof "ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255"], *tp;
|
|
struct { int base, len; } best, cur;
|
|
#define NS_IN6ADDRSZ 16
|
|
#define NS_INT16SZ 2
|
|
u_int words[NS_IN6ADDRSZ / NS_INT16SZ];
|
|
int i;
|
|
|
|
/*
|
|
* Preprocess:
|
|
* Copy the input (bytewise) array into a wordwise array.
|
|
* Find the longest run of 0x00's in src[] for :: shorthanding.
|
|
*/
|
|
memset(words, '\0', sizeof words);
|
|
for (i = 0; i < NS_IN6ADDRSZ; i++)
|
|
words[i / 2] |= (src[i] << ((1 - (i % 2)) << 3));
|
|
best.base = -1;
|
|
best.len = 0;
|
|
cur.base = -1;
|
|
cur.len = 0;
|
|
for (i = 0; i < (NS_IN6ADDRSZ / NS_INT16SZ); i++) {
|
|
if (words[i] == 0) {
|
|
if (cur.base == -1)
|
|
cur.base = i, cur.len = 1;
|
|
else
|
|
cur.len++;
|
|
} else {
|
|
if (cur.base != -1) {
|
|
if (best.base == -1 || cur.len > best.len)
|
|
best = cur;
|
|
cur.base = -1;
|
|
}
|
|
}
|
|
}
|
|
if (cur.base != -1) {
|
|
if (best.base == -1 || cur.len > best.len)
|
|
best = cur;
|
|
}
|
|
if (best.base != -1 && best.len < 2)
|
|
best.base = -1;
|
|
|
|
/*
|
|
* Format the result.
|
|
*/
|
|
tp = tmp;
|
|
for (i = 0; i < (NS_IN6ADDRSZ / NS_INT16SZ); i++) {
|
|
/* Are we inside the best run of 0x00's? */
|
|
if (best.base != -1 && i >= best.base &&
|
|
i < (best.base + best.len)) {
|
|
if (i == best.base)
|
|
*tp++ = ':';
|
|
continue;
|
|
}
|
|
/* Are we following an initial run of 0x00s or any real hex? */
|
|
if (i != 0)
|
|
*tp++ = ':';
|
|
/* Is this address an encapsulated IPv4? */
|
|
if (i == 6 && best.base == 0 && (best.len == 6 ||
|
|
(best.len == 7 && words[7] != 0x0001) ||
|
|
(best.len == 5 && words[5] == 0xffff))) {
|
|
if (!inet_ntop4(src+12, tp, sizeof tmp - (tp - tmp)))
|
|
return (NULL);
|
|
tp += strlen(tp);
|
|
break;
|
|
}
|
|
tp += sprintf(tp, "%x", words[i]);
|
|
}
|
|
/* Was it a trailing run of 0x00's? */
|
|
if (best.base != -1 && (best.base + best.len) ==
|
|
(NS_IN6ADDRSZ / NS_INT16SZ))
|
|
*tp++ = ':';
|
|
*tp++ = '\0';
|
|
|
|
/*
|
|
* Check for overflow, copy, and we're done.
|
|
*/
|
|
if ((socklen_t)(tp - tmp) > size) {
|
|
return (NULL);
|
|
}
|
|
strcpy(dst, tmp);
|
|
return (dst);
|
|
}
|
|
|
|
/*! \file */
|