freebsd-skq/sys/xdr/xdr_mbuf.c
Doug Rabson dfdcada31e 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
2008-03-26 15:23:12 +00:00

239 lines
5.4 KiB
C

/*-
* Copyright (c) 2008 Isilon Inc http://www.isilon.com/
* Authors: Doug Rabson <dfr@rabson.org>
* Developed with Red Inc: Alfred Perlstein <alfred@freebsd.org>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <rpc/types.h>
#include <rpc/xdr.h>
static void xdrmbuf_destroy(XDR *);
static bool_t xdrmbuf_getlong(XDR *, long *);
static bool_t xdrmbuf_putlong(XDR *, const long *);
static bool_t xdrmbuf_getbytes(XDR *, char *, u_int);
static bool_t xdrmbuf_putbytes(XDR *, const char *, u_int);
/* XXX: w/64-bit pointers, u_int not enough! */
static u_int xdrmbuf_getpos(XDR *);
static bool_t xdrmbuf_setpos(XDR *, u_int);
static int32_t *xdrmbuf_inline(XDR *, u_int);
static const struct xdr_ops xdrmbuf_ops = {
xdrmbuf_getlong,
xdrmbuf_putlong,
xdrmbuf_getbytes,
xdrmbuf_putbytes,
xdrmbuf_getpos,
xdrmbuf_setpos,
xdrmbuf_inline,
xdrmbuf_destroy
};
/*
* The procedure xdrmbuf_create initializes a stream descriptor for a
* mbuf.
*/
void
xdrmbuf_create(XDR *xdrs, struct mbuf *m, enum xdr_op op)
{
xdrs->x_op = op;
xdrs->x_ops = &xdrmbuf_ops;
xdrs->x_base = (char *) m;
if (op == XDR_ENCODE) {
m = m_last(m);
xdrs->x_private = m;
xdrs->x_handy = m->m_len;
} else {
xdrs->x_private = m;
xdrs->x_handy = 0;
}
}
static void
xdrmbuf_destroy(XDR *xdrs)
{
if (xdrs->x_op == XDR_DECODE && xdrs->x_base) {
m_freem((struct mbuf *) xdrs->x_base);
xdrs->x_base = NULL;
xdrs->x_private = NULL;
}
}
static bool_t
xdrmbuf_getlong(XDR *xdrs, long *lp)
{
int32_t t;
xdrmbuf_getbytes(xdrs, (char *) &t, sizeof(int32_t));
*lp = ntohl(t);
return (TRUE);
}
static bool_t
xdrmbuf_putlong(xdrs, lp)
XDR *xdrs;
const long *lp;
{
int32_t t = htonl(*lp);
xdrmbuf_putbytes(xdrs, (char *) &t, sizeof(int32_t));
return (TRUE);
}
static bool_t
xdrmbuf_getbytes(XDR *xdrs, char *addr, u_int len)
{
struct mbuf *m = (struct mbuf *) xdrs->x_private;
size_t sz;
while (len > 0) {
/*
* Make sure we haven't hit the end.
*/
if (!m) {
return (FALSE);
}
/*
* See how much we can get from this mbuf.
*/
sz = m->m_len - xdrs->x_handy;
if (sz > len)
sz = len;
memcpy(addr, mtod(m, const char *) + xdrs->x_handy, sz);
addr += sz;
xdrs->x_handy += sz;
len -= sz;
if (xdrs->x_handy == m->m_len) {
m = m->m_next;
xdrs->x_private = (void *) m;
xdrs->x_handy = 0;
}
}
return (TRUE);
}
static bool_t
xdrmbuf_putbytes(XDR *xdrs, const char *addr, u_int len)
{
struct mbuf *m = (struct mbuf *) xdrs->x_private;
struct mbuf *n;
size_t sz;
while (len > 0) {
sz = M_TRAILINGSPACE(m) + (m->m_len - xdrs->x_handy);
if (sz > len)
sz = len;
memcpy(mtod(m, char *) + xdrs->x_handy, addr, sz);
addr += sz;
xdrs->x_handy += sz;
if (xdrs->x_handy > m->m_len)
m->m_len = xdrs->x_handy;
len -= sz;
if (xdrs->x_handy == m->m_len && M_TRAILINGSPACE(m) == 0) {
if (!m->m_next) {
MGET(n, M_TRYWAIT, m->m_type);
m->m_next = n;
}
m = m->m_next;
xdrs->x_private = (void *) m;
xdrs->x_handy = 0;
}
}
return (TRUE);
}
static u_int
xdrmbuf_getpos(XDR *xdrs)
{
struct mbuf *m0 = (struct mbuf *) xdrs->x_base;
struct mbuf *m = (struct mbuf *) xdrs->x_private;
u_int pos = 0;
while (m0 && m0 != m) {
pos += m0->m_len;
m0 = m0->m_next;
}
KASSERT(m0, ("Corrupted mbuf chain"));
return (pos + xdrs->x_handy);
}
static bool_t
xdrmbuf_setpos(XDR *xdrs, u_int pos)
{
struct mbuf *m = (struct mbuf *) xdrs->x_base;
while (m && pos > m->m_len) {
pos -= m->m_len;
m = m->m_next;
}
KASSERT(m, ("Corrupted mbuf chain"));
xdrs->x_private = (void *) m;
xdrs->x_handy = pos;
return (TRUE);
}
static int32_t *
xdrmbuf_inline(XDR *xdrs, u_int len)
{
struct mbuf *m = (struct mbuf *) xdrs->x_private;
size_t available;
char *p;
if (xdrs->x_op == XDR_ENCODE) {
available = M_TRAILINGSPACE(m) + (m->m_len - xdrs->x_handy);
} else {
available = m->m_len - xdrs->x_handy;
}
if (available >= len) {
p = mtod(m, char *) + xdrs->x_handy;
if (((uintptr_t) p) & (sizeof(int32_t) - 1))
return (0);
xdrs->x_handy += len;
if (xdrs->x_handy > m->m_len)
m->m_len = xdrs->x_handy;
return ((int32_t *) p);
}
return (0);
}