52cd27cb58
struct inpcbgroup. pcbgroups, or "connection groups", supplement the existing inpcbinfo connection hash table, which when pcbgroups are enabled, might now be thought of more usefully as a per-protocol 4-tuple reservation table. Connections are assigned to connection groups base on a hash of their 4-tuple; wildcard sockets require special handling, and are members of all connection groups. During a connection lookup, a per-connection group lock is employed rather than the global pcbinfo lock. By aligning connection groups with input path processing, connection groups take on an effective CPU affinity, especially when aligned with RSS work placement (see a forthcoming commit for details). This eliminates cache line migration associated with global, protocol-layer data structures in steady state TCP and UDP processing (with the exception of protocol-layer statistics; further commit to follow). Elements of this approach were inspired by Willman, Rixner, and Cox's 2006 USENIX paper, "An Evaluation of Network Stack Parallelization Strategies in Modern Operating Systems". However, there are also significant differences: we maintain the inpcb lock, rather than using the connection group lock for per-connection state. Likewise, the focus of this implementation is alignment with NIC packet distribution strategies such as RSS, rather than pure software strategies. Despite that focus, software distribution is supported through the parallel netisr implementation, and works well in configurations where the number of hardware threads is greater than the number of NIC input queues, such as in the RMI XLR threaded MIPS architecture. Another important difference is the continued maintenance of existing hash tables as "reservation tables" -- these are useful both to distinguish the resource allocation aspect of protocol name management and the more common-case lookup aspect. In configurations where connection tables are aligned with hardware hashes, it is desirable to use the traditional lookup tables for loopback or encapsulated traffic rather than take the expense of hardware hashes that are hard to implement efficiently in software (such as RSS Toeplitz). Connection group support is enabled by compiling "options PCBGROUP" into your kernel configuration; for the time being, this is an experimental feature, and hence is not enabled by default. Subject to the limited MFCability of change dependencies in inpcb, and its change to the inpcbinfo init function signature, this change in principle could be merged to FreeBSD 8.x. Reviewed by: bz Sponsored by: Juniper Networks, Inc.
104 lines
3.0 KiB
C
104 lines
3.0 KiB
C
/*-
|
|
* Copyright (c) 2010-2011 Juniper Networks, Inc.
|
|
* All rights reserved.
|
|
*
|
|
* This software was developed by Robert N. M. Watson under contract
|
|
* to Juniper Networks, Inc.
|
|
*
|
|
* 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 "opt_inet6.h"
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/mbuf.h>
|
|
|
|
#include <netinet/in.h>
|
|
#include <netinet/in_pcb.h>
|
|
#ifdef INET6
|
|
#include <netinet6/in6_pcb.h>
|
|
#endif /* INET6 */
|
|
|
|
/*
|
|
* Given a hash of whatever the covered tuple might be, return a pcbgroup
|
|
* index.
|
|
*/
|
|
static __inline u_int
|
|
in6_pcbgroup_getbucket(struct inpcbinfo *pcbinfo, uint32_t hash)
|
|
{
|
|
|
|
return (hash % pcbinfo->ipi_npcbgroups);
|
|
}
|
|
|
|
/*
|
|
* Map a (hashtype, hash) tuple into a connection group, or NULL if the hash
|
|
* information is insufficient to identify the pcbgroup.
|
|
*/
|
|
struct inpcbgroup *
|
|
in6_pcbgroup_byhash(struct inpcbinfo *pcbinfo, u_int hashtype, uint32_t hash)
|
|
{
|
|
|
|
return (NULL);
|
|
}
|
|
|
|
struct inpcbgroup *
|
|
in6_pcbgroup_bymbuf(struct inpcbinfo *pcbinfo, struct mbuf *m)
|
|
{
|
|
|
|
return (in6_pcbgroup_byhash(pcbinfo, M_HASHTYPE_GET(m),
|
|
m->m_pkthdr.flowid));
|
|
}
|
|
|
|
struct inpcbgroup *
|
|
in6_pcbgroup_bytuple(struct inpcbinfo *pcbinfo, const struct in6_addr *laddrp,
|
|
u_short lport, const struct in6_addr *faddrp, u_short fport)
|
|
{
|
|
uint32_t hash;
|
|
|
|
switch (pcbinfo->ipi_hashfields) {
|
|
case IPI_HASHFIELDS_4TUPLE:
|
|
hash = faddrp->s6_addr32[3] ^ fport;
|
|
break;
|
|
|
|
case IPI_HASHFIELDS_2TUPLE:
|
|
hash = faddrp->s6_addr32[3] ^ laddrp->s6_addr32[3];
|
|
break;
|
|
|
|
default:
|
|
hash = 0;
|
|
}
|
|
return (&pcbinfo->ipi_pcbgroups[in6_pcbgroup_getbucket(pcbinfo,
|
|
hash)]);
|
|
}
|
|
|
|
struct inpcbgroup *
|
|
in6_pcbgroup_byinpcb(struct inpcb *inp)
|
|
{
|
|
|
|
return (in6_pcbgroup_bytuple(inp->inp_pcbinfo, &inp->in6p_laddr,
|
|
inp->inp_lport, &inp->in6p_faddr, inp->inp_fport));
|
|
}
|