svn commit: r191259 - head/sys/netinet

[Robert Watson]

On Sun, 19 Apr 2009, Kip Macy wrote:

> Author: kmacy
> Date: Sun Apr 19 04:44:05 2009
> New Revision: 191259
> URL: http://svn.freebsd.org/changeset/base/191259
>
> Log:
>  - Allocate a small flowtable in ip_input.c (changeable by tuneable)
>  - Use for accelerating ip_output

If you anticipate the flowtable being used with many types, I wonder if the 
flowtable sysctl to enable/disable it by policy should be on the consumer 
side, rather than the producer side?  That way you could say "use the 
flowtable for ipv4 and ipv6 but not ipx", which might well be helpful for 
debugging when adding flowtable support for those protocols.  Also, is it the 
case that when the flowtable is disabled, it isn't allocated, or is the basic 
table always allocated regardless of policy?

Robert N M Watson
Computer Laboratory
University of Cambridge

>
> Modified:
>  head/sys/netinet/ip_input.c
>  head/sys/netinet/ip_output.c
>  head/sys/netinet/vinet.h
>
> Modified: head/sys/netinet/ip_input.c
> ==============================================================================
> --- head/sys/netinet/ip_input.c	Sun Apr 19 04:39:42 2009	(r191258)
> +++ head/sys/netinet/ip_input.c	Sun Apr 19 04:44:05 2009	(r191259)
> @@ -64,6 +64,7 @@ __FBSDID("$FreeBSD$");
> #include <net/route.h>
> #include <net/netisr.h>
> #include <net/vnet.h>
> +#include <net/flowtable.h>
>
> #include <netinet/in.h>
> #include <netinet/in_systm.h>
> @@ -211,6 +212,11 @@ SYSCTL_INT(_net_inet_ip, IPCTL_DEFMTU, m
> SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_ip, OID_AUTO, stealth, CTLFLAG_RW,
>     ipstealth, 0, "IP stealth mode, no TTL decrementation on forwarding");
> #endif
> +static int ip_output_flowtable_size = 2048;
> +TUNABLE_INT("net.inet.ip.output_flowtable_size", &ip_output_flowtable_size);
> +SYSCTL_V_INT(V_NET, vnet_inet, _net_inet_ip, OID_AUTO, output_flowtable_size,
> +    CTLFLAG_RDTUN, ip_output_flowtable_size, 2048,
> +    "number of entries in the per-cpu output flow caches");
>
> /*
>  * ipfw_ether and ipfw_bridge hooks.
> @@ -221,6 +227,7 @@ ip_dn_io_t *ip_dn_io_ptr = NULL;
> #ifdef VIMAGE_GLOBALS
> int fw_one_pass;
> #endif
> +struct flowtable *ip_ft;
>
> static void	ip_freef(struct ipqhead *, struct ipq *);
>
> @@ -342,6 +349,8 @@ ip_init(void)
> 	ipintrq.ifq_maxlen = ipqmaxlen;
> 	mtx_init(&ipintrq.ifq_mtx, "ip_inq", NULL, MTX_DEF);
> 	netisr_register(NETISR_IP, ip_input, &ipintrq, 0);
> +
> +	ip_ft = flowtable_alloc(ip_output_flowtable_size, FL_PCPU);
> }
>
> void
>
> Modified: head/sys/netinet/ip_output.c
> ==============================================================================
> --- head/sys/netinet/ip_output.c	Sun Apr 19 04:39:42 2009	(r191258)
> +++ head/sys/netinet/ip_output.c	Sun Apr 19 04:44:05 2009	(r191259)
> @@ -59,6 +59,7 @@ __FBSDID("$FreeBSD$");
> #include <net/netisr.h>
> #include <net/pfil.h>
> #include <net/route.h>
> +#include <net/flowtable.h>
> #ifdef RADIX_MPATH
> #include <net/radix_mpath.h>
> #endif
> @@ -135,6 +136,7 @@ ip_output(struct mbuf *m, struct mbuf *o
> 	int hlen = sizeof (struct ip);
> 	int mtu;
> 	int len, error = 0;
> +	int nortfree = 0;
> 	struct sockaddr_in *dst = NULL;	/* keep compiler happy */
> 	struct in_ifaddr *ia = NULL;
> 	int isbroadcast, sw_csum;
> @@ -158,6 +160,10 @@ ip_output(struct mbuf *m, struct mbuf *o
> 			m->m_flags |= M_FLOWID;
> 		}
> 	}
> +	if ((ro == &iproute) && (ro->ro_rt == NULL) && (ro->ro_lle == NULL)) {
> +		if (flowtable_lookup(ip_ft, m, ro) == 0)
> +			nortfree = 1;
> +	}
>
> 	if (opt) {
> 		len = 0;
> @@ -199,7 +205,8 @@ again:
> 	if (ro->ro_rt && ((ro->ro_rt->rt_flags & RTF_UP) == 0 ||
> 			  dst->sin_family != AF_INET ||
> 			  dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
> -		RTFREE(ro->ro_rt);
> +		if (!nortfree)
> +			RTFREE(ro->ro_rt);
> 		ro->ro_rt = (struct rtentry *)NULL;
> 	}
> #ifdef IPFIREWALL_FORWARD
> @@ -638,7 +645,7 @@ passout:
> 		IPSTAT_INC(ips_fragmented);
>
> done:
> -	if (ro == &iproute && ro->ro_rt) {
> +	if (ro == &iproute && ro->ro_rt && !nortfree) {
> 		RTFREE(ro->ro_rt);
> 	}
> 	return (error);
>
> Modified: head/sys/netinet/vinet.h
> ==============================================================================
> --- head/sys/netinet/vinet.h	Sun Apr 19 04:39:42 2009	(r191258)
> +++ head/sys/netinet/vinet.h	Sun Apr 19 04:44:05 2009	(r191259)
> @@ -72,6 +72,7 @@ struct vnet_inet {
> 	int	_ip_sendsourcequench;
> 	int	_ip_do_randomid;
> 	int	_ip_checkinterface;
> +	int	_ip_output_flowtable_size;
> 	u_short	_ip_id;
>
> 	uma_zone_t _ipq_zone;
>