linux/include/net/inet_sock.h

253 lines
6.2 KiB
C
Raw Normal View History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for inet_sock
*
* Authors: Many, reorganised here by
* Arnaldo Carvalho de Melo <acme@mandriva.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _INET_SOCK_H
#define _INET_SOCK_H
#include <linux/kmemcheck.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/jhash.h>
rfs: Receive Flow Steering This patch implements receive flow steering (RFS). RFS steers received packets for layer 3 and 4 processing to the CPU where the application for the corresponding flow is running. RFS is an extension of Receive Packet Steering (RPS). The basic idea of RFS is that when an application calls recvmsg (or sendmsg) the application's running CPU is stored in a hash table that is indexed by the connection's rxhash which is stored in the socket structure. The rxhash is passed in skb's received on the connection from netif_receive_skb. For each received packet, the associated rxhash is used to look up the CPU in the hash table, if a valid CPU is set then the packet is steered to that CPU using the RPS mechanisms. The convolution of the simple approach is that it would potentially allow OOO packets. If threads are thrashing around CPUs or multiple threads are trying to read from the same sockets, a quickly changing CPU value in the hash table could cause rampant OOO packets-- we consider this a non-starter. To avoid OOO packets, this solution implements two types of hash tables: rps_sock_flow_table and rps_dev_flow_table. rps_sock_table is a global hash table. Each entry is just a CPU number and it is populated in recvmsg and sendmsg as described above. This table contains the "desired" CPUs for flows. rps_dev_flow_table is specific to each device queue. Each entry contains a CPU and a tail queue counter. The CPU is the "current" CPU for a matching flow. The tail queue counter holds the value of a tail queue counter for the associated CPU's backlog queue at the time of last enqueue for a flow matching the entry. Each backlog queue has a queue head counter which is incremented on dequeue, and so a queue tail counter is computed as queue head count + queue length. When a packet is enqueued on a backlog queue, the current value of the queue tail counter is saved in the hash entry of the rps_dev_flow_table. And now the trick: when selecting the CPU for RPS (get_rps_cpu) the rps_sock_flow table and the rps_dev_flow table for the RX queue are consulted. When the desired CPU for the flow (found in the rps_sock_flow table) does not match the current CPU (found in the rps_dev_flow table), the current CPU is changed to the desired CPU if one of the following is true: - The current CPU is unset (equal to RPS_NO_CPU) - Current CPU is offline - The current CPU's queue head counter >= queue tail counter in the rps_dev_flow table. This checks if the queue tail has advanced beyond the last packet that was enqueued using this table entry. This guarantees that all packets queued using this entry have been dequeued, thus preserving in order delivery. Making each queue have its own rps_dev_flow table has two advantages: 1) the tail queue counters will be written on each receive, so keeping the table local to interrupting CPU s good for locality. 2) this allows lockless access to the table-- the CPU number and queue tail counter need to be accessed together under mutual exclusion from netif_receive_skb, we assume that this is only called from device napi_poll which is non-reentrant. This patch implements RFS for TCP and connected UDP sockets. It should be usable for other flow oriented protocols. There are two configuration parameters for RFS. The "rps_flow_entries" kernel init parameter sets the number of entries in the rps_sock_flow_table, the per rxqueue sysfs entry "rps_flow_cnt" contains the number of entries in the rps_dev_flow table for the rxqueue. Both are rounded to power of two. The obvious benefit of RFS (over just RPS) is that it achieves CPU locality between the receive processing for a flow and the applications processing; this can result in increased performance (higher pps, lower latency). The benefits of RFS are dependent on cache hierarchy, application load, and other factors. On simple benchmarks, we don't necessarily see improvement and sometimes see degradation. However, for more complex benchmarks and for applications where cache pressure is much higher this technique seems to perform very well. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. The RPC test is an request/response test similar in structure to netperf RR test ith 100 threads on each host, but does more work in userspace that netperf. e1000e on 8 core Intel No RFS or RPS 104K tps at 30% CPU No RFS (best RPS config): 290K tps at 63% CPU RFS 303K tps at 61% CPU RPC test tps CPU% 50/90/99% usec latency Latency StdDev No RFS/RPS 103K 48% 757/900/3185 4472.35 RPS only: 174K 73% 415/993/2468 491.66 RFS 223K 73% 379/651/1382 315.61 Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-16 23:01:27 +00:00
#include <linux/netdevice.h>
#include <net/flow.h>
#include <net/sock.h>
#include <net/request_sock.h>
#include <net/netns/hash.h>
/** struct ip_options - IP Options
*
* @faddr - Saved first hop address
* @nexthop - Saved nexthop address in LSRR and SSRR
* @is_strictroute - Strict source route
* @srr_is_hit - Packet destination addr was our one
* @is_changed - IP checksum more not valid
* @rr_needaddr - Need to record addr of outgoing dev
* @ts_needtime - Need to record timestamp
* @ts_needaddr - Need to record addr of outgoing dev
*/
struct ip_options {
__be32 faddr;
__be32 nexthop;
unsigned char optlen;
unsigned char srr;
unsigned char rr;
unsigned char ts;
unsigned char is_strictroute:1,
srr_is_hit:1,
is_changed:1,
rr_needaddr:1,
ts_needtime:1,
ts_needaddr:1;
unsigned char router_alert;
unsigned char cipso;
unsigned char __pad2;
unsigned char __data[0];
};
struct ip_options_rcu {
struct rcu_head rcu;
struct ip_options opt;
};
struct ip_options_data {
struct ip_options_rcu opt;
char data[40];
};
struct inet_request_sock {
struct request_sock req;
#if IS_ENABLED(CONFIG_IPV6)
u16 inet6_rsk_offset;
#endif
__be16 loc_port;
__be32 loc_addr;
__be32 rmt_addr;
__be16 rmt_port;
kmemcheck_bitfield_begin(flags);
u16 snd_wscale : 4,
rcv_wscale : 4,
tstamp_ok : 1,
sack_ok : 1,
wscale_ok : 1,
ecn_ok : 1,
acked : 1,
no_srccheck: 1;
kmemcheck_bitfield_end(flags);
struct ip_options_rcu *opt;
};
static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
{
return (struct inet_request_sock *)sk;
}
struct inet_cork {
unsigned int flags;
__be32 addr;
struct ip_options *opt;
unsigned int fragsize;
int length; /* Total length of all frames */
net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Alexander Duyck <alexander.h.duyck@intel.com> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-23 23:04:42 +00:00
struct dst_entry *dst;
u8 tx_flags;
};
struct inet_cork_full {
struct inet_cork base;
struct flowi fl;
};
struct ip_mc_socklist;
struct ipv6_pinfo;
struct rtable;
/** struct inet_sock - representation of INET sockets
*
* @sk - ancestor class
* @pinet6 - pointer to IPv6 control block
* @inet_daddr - Foreign IPv4 addr
* @inet_rcv_saddr - Bound local IPv4 addr
* @inet_dport - Destination port
* @inet_num - Local port
* @inet_saddr - Sending source
* @uc_ttl - Unicast TTL
* @inet_sport - Source port
* @inet_id - ID counter for DF pkts
* @tos - TOS
* @mc_ttl - Multicasting TTL
* @is_icsk - is this an inet_connection_sock?
ipv4: Implement IP_UNICAST_IF socket option. The IP_UNICAST_IF feature is needed by the Wine project. This patch implements the feature by setting the outgoing interface in a similar fashion to that of IP_MULTICAST_IF. A separate option is needed to handle this feature since the existing options do not provide all of the characteristics required by IP_UNICAST_IF, a summary is provided below. SO_BINDTODEVICE: * SO_BINDTODEVICE requires administrative privileges, IP_UNICAST_IF does not. From reading some old mailing list articles my understanding is that SO_BINDTODEVICE requires administrative privileges because it can override the administrator's routing settings. * The SO_BINDTODEVICE option restricts both outbound and inbound traffic, IP_UNICAST_IF only impacts outbound traffic. IP_PKTINFO: * Since IP_PKTINFO and IP_UNICAST_IF are independent options, implementing IP_UNICAST_IF with IP_PKTINFO will likely break some applications. * Implementing IP_UNICAST_IF on top of IP_PKTINFO significantly complicates the Wine codebase and reduces the socket performance (doing this requires a lot of extra communication between the "server" and "user" layers). bind(): * bind() does not work on broadcast packets, IP_UNICAST_IF is specifically intended to work with broadcast packets. * Like SO_BINDTODEVICE, bind() restricts both outbound and inbound traffic. Signed-off-by: Erich E. Hoover <ehoover@mines.edu> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-08 09:11:07 +00:00
* @uc_index - Unicast outgoing device index
* @mc_index - Multicast device index
* @mc_list - Group array
* @cork - info to build ip hdr on each ip frag while socket is corked
*/
struct inet_sock {
/* sk and pinet6 has to be the first two members of inet_sock */
struct sock sk;
#if IS_ENABLED(CONFIG_IPV6)
struct ipv6_pinfo *pinet6;
#endif
/* Socket demultiplex comparisons on incoming packets. */
#define inet_daddr sk.__sk_common.skc_daddr
#define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 09:49:27 +00:00
#define inet_addrpair sk.__sk_common.skc_addrpair
#define inet_dport sk.__sk_common.skc_dport
#define inet_num sk.__sk_common.skc_num
#define inet_portpair sk.__sk_common.skc_portpair
__be32 inet_saddr;
__s16 uc_ttl;
__u16 cmsg_flags;
__be16 inet_sport;
__u16 inet_id;
struct ip_options_rcu __rcu *inet_opt;
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 09:49:27 +00:00
int rx_dst_ifindex;
__u8 tos;
__u8 min_ttl;
__u8 mc_ttl;
__u8 pmtudisc;
__u8 recverr:1,
is_icsk:1,
freebind:1,
hdrincl:1,
mc_loop:1,
transparent:1,
mc_all:1,
nodefrag:1;
__u8 rcv_tos;
ipv4: Implement IP_UNICAST_IF socket option. The IP_UNICAST_IF feature is needed by the Wine project. This patch implements the feature by setting the outgoing interface in a similar fashion to that of IP_MULTICAST_IF. A separate option is needed to handle this feature since the existing options do not provide all of the characteristics required by IP_UNICAST_IF, a summary is provided below. SO_BINDTODEVICE: * SO_BINDTODEVICE requires administrative privileges, IP_UNICAST_IF does not. From reading some old mailing list articles my understanding is that SO_BINDTODEVICE requires administrative privileges because it can override the administrator's routing settings. * The SO_BINDTODEVICE option restricts both outbound and inbound traffic, IP_UNICAST_IF only impacts outbound traffic. IP_PKTINFO: * Since IP_PKTINFO and IP_UNICAST_IF are independent options, implementing IP_UNICAST_IF with IP_PKTINFO will likely break some applications. * Implementing IP_UNICAST_IF on top of IP_PKTINFO significantly complicates the Wine codebase and reduces the socket performance (doing this requires a lot of extra communication between the "server" and "user" layers). bind(): * bind() does not work on broadcast packets, IP_UNICAST_IF is specifically intended to work with broadcast packets. * Like SO_BINDTODEVICE, bind() restricts both outbound and inbound traffic. Signed-off-by: Erich E. Hoover <ehoover@mines.edu> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-08 09:11:07 +00:00
int uc_index;
int mc_index;
__be32 mc_addr;
struct ip_mc_socklist __rcu *mc_list;
struct inet_cork_full cork;
};
#define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */
#define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */
static inline struct inet_sock *inet_sk(const struct sock *sk)
{
return (struct inet_sock *)sk;
}
static inline void __inet_sk_copy_descendant(struct sock *sk_to,
const struct sock *sk_from,
const int ancestor_size)
{
memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
sk_from->sk_prot->obj_size - ancestor_size);
}
#if !(IS_ENABLED(CONFIG_IPV6))
static inline void inet_sk_copy_descendant(struct sock *sk_to,
const struct sock *sk_from)
{
__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
}
#endif
extern int inet_sk_rebuild_header(struct sock *sk);
extern u32 inet_ehash_secret;
extern u32 ipv6_hash_secret;
extern void build_ehash_secret(void);
static inline unsigned int inet_ehashfn(struct net *net,
const __be32 laddr, const __u16 lport,
const __be32 faddr, const __be16 fport)
{
return jhash_3words((__force __u32) laddr,
(__force __u32) faddr,
((__u32) lport) << 16 | (__force __u32)fport,
inet_ehash_secret + net_hash_mix(net));
}
static inline int inet_sk_ehashfn(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const __be32 laddr = inet->inet_rcv_saddr;
const __u16 lport = inet->inet_num;
const __be32 faddr = inet->inet_daddr;
const __be16 fport = inet->inet_dport;
struct net *net = sock_net(sk);
return inet_ehashfn(net, laddr, lport, faddr, fport);
}
static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops)
{
struct request_sock *req = reqsk_alloc(ops);
struct inet_request_sock *ireq = inet_rsk(req);
if (req != NULL) {
kmemcheck_annotate_bitfield(ireq, flags);
ireq->opt = NULL;
}
return req;
}
static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
{
__u8 flags = 0;
if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl)
flags |= FLOWI_FLAG_ANYSRC;
return flags;
}
#endif /* _INET_SOCK_H */