linux-sg2042/include/net/inet_timewait_sock.h

128 lines
3.8 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 a generic INET TIMEWAIT sock
*
* From code originally in net/tcp.h
*
* 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_TIMEWAIT_SOCK_
#define _INET_TIMEWAIT_SOCK_
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/timewait_sock.h>
#include <linux/atomic.h>
struct inet_bind_bucket;
/*
* This is a TIME_WAIT sock. It works around the memory consumption
* problems of sockets in such a state on heavily loaded servers, but
* without violating the protocol specification.
*/
struct inet_timewait_sock {
/*
* Now struct sock also uses sock_common, so please just
* don't add nothing before this first member (__tw_common) --acme
*/
struct sock_common __tw_common;
#define tw_family __tw_common.skc_family
#define tw_state __tw_common.skc_state
#define tw_reuse __tw_common.skc_reuse
#define tw_ipv6only __tw_common.skc_ipv6only
#define tw_bound_dev_if __tw_common.skc_bound_dev_if
#define tw_node __tw_common.skc_nulls_node
#define tw_bind_node __tw_common.skc_bind_node
#define tw_refcnt __tw_common.skc_refcnt
[INET]: speedup inet (tcp/dccp) lookups Arnaldo and I agreed it could be applied now, because I have other pending patches depending on this one (Thank you Arnaldo) (The other important patch moves skc_refcnt in a separate cache line, so that the SMP/NUMA performance doesnt suffer from cache line ping pongs) 1) First some performance data : -------------------------------- tcp_v4_rcv() wastes a *lot* of time in __inet_lookup_established() The most time critical code is : sk_for_each(sk, node, &head->chain) { if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif)) goto hit; /* You sunk my battleship! */ } The sk_for_each() does use prefetch() hints but only the begining of "struct sock" is prefetched. As INET_MATCH first comparison uses inet_sk(__sk)->daddr, wich is far away from the begining of "struct sock", it has to bring into CPU cache cold cache line. Each iteration has to use at least 2 cache lines. This can be problematic if some chains are very long. 2) The goal ----------- The idea I had is to change things so that INET_MATCH() may return FALSE in 99% of cases only using the data already in the CPU cache, using one cache line per iteration. 3) Description of the patch --------------------------- Adds a new 'unsigned int skc_hash' field in 'struct sock_common', filling a 32 bits hole on 64 bits platform. struct sock_common { unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse; int skc_bound_dev_if; struct hlist_node skc_node; struct hlist_node skc_bind_node; atomic_t skc_refcnt; + unsigned int skc_hash; struct proto *skc_prot; }; Store in this 32 bits field the full hash, not masked by (ehash_size - 1) Using this full hash as the first comparison done in INET_MATCH permits us immediatly skip the element without touching a second cache line in case of a miss. Suppress the sk_hashent/tw_hashent fields since skc_hash (aliased to sk_hash and tw_hash) already contains the slot number if we mask with (ehash_size - 1) File include/net/inet_hashtables.h 64 bits platforms : #define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) ((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie)) && \ ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) 32bits platforms: #define TCP_IPV4_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) && \ (inet_sk(__sk)->daddr == (__saddr)) && \ (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) - Adds a prefetch(head->chain.first) in __inet_lookup_established()/__tcp_v4_check_established() and __inet6_lookup_established()/__tcp_v6_check_established() and __dccp_v4_check_established() to bring into cache the first element of the list, before the {read|write}_lock(&head->lock); Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-04 05:13:38 +08:00
#define tw_hash __tw_common.skc_hash
#define tw_prot __tw_common.skc_prot
#define tw_net __tw_common.skc_net
#define tw_daddr __tw_common.skc_daddr
#define tw_v6_daddr __tw_common.skc_v6_daddr
#define tw_rcv_saddr __tw_common.skc_rcv_saddr
#define tw_v6_rcv_saddr __tw_common.skc_v6_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 17:49:27 +08:00
#define tw_dport __tw_common.skc_dport
#define tw_num __tw_common.skc_num
#define tw_cookie __tw_common.skc_cookie
#define tw_dr __tw_common.skc_tw_dr
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 17:49:27 +08:00
int tw_timeout;
volatile unsigned char tw_substate;
unsigned char tw_rcv_wscale;
/* Socket demultiplex comparisons on incoming packets. */
/* these three are in inet_sock */
__be16 tw_sport;
/* And these are ours. */
tcp/dccp: get rid of central timewait timer Using a timer wheel for timewait sockets was nice ~15 years ago when memory was expensive and machines had a single processor. This does not scale, code is ugly and source of huge latencies (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.) We can afford to use an extra 64 bytes per timewait sock and spread timewait load to all cpus to have better behavior. Tested: On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1 on the target (lpaa24) Before patch : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 419594 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 437171 While test is running, we can observe 25 or even 33 ms latencies. lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2 lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2 After patch : About 90% increase of throughput : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 810442 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 800992 And latencies are kept to minimal values during this load, even if network utilization is 90% higher : lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-13 09:51:09 +08:00
unsigned int tw_kill : 1,
tw_transparent : 1,
tw_flowlabel : 20,
tw_pad : 2, /* 2 bits hole */
tw_tos : 8;
tcp/dccp: get rid of central timewait timer Using a timer wheel for timewait sockets was nice ~15 years ago when memory was expensive and machines had a single processor. This does not scale, code is ugly and source of huge latencies (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.) We can afford to use an extra 64 bytes per timewait sock and spread timewait load to all cpus to have better behavior. Tested: On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1 on the target (lpaa24) Before patch : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 419594 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 437171 While test is running, we can observe 25 or even 33 ms latencies. lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2 lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2 After patch : About 90% increase of throughput : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 810442 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 800992 And latencies are kept to minimal values during this load, even if network utilization is 90% higher : lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-13 09:51:09 +08:00
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
};
#define tw_tclass tw_tos
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
{
return (struct inet_timewait_sock *)sk;
}
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 15:22:02 +08:00
void inet_twsk_free(struct inet_timewait_sock *tw);
void inet_twsk_put(struct inet_timewait_sock *tw);
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo);
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
tcp/dccp: get rid of central timewait timer Using a timer wheel for timewait sockets was nice ~15 years ago when memory was expensive and machines had a single processor. This does not scale, code is ugly and source of huge latencies (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.) We can afford to use an extra 64 bytes per timewait sock and spread timewait load to all cpus to have better behavior. Tested: On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1 on the target (lpaa24) Before patch : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 419594 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 437171 While test is running, we can observe 25 or even 33 ms latencies. lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2 lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2 After patch : About 90% increase of throughput : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 810442 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 800992 And latencies are kept to minimal values during this load, even if network utilization is 90% higher : lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-13 09:51:09 +08:00
struct inet_timewait_death_row *dr,
const int state);
void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
struct inet_hashinfo *hashinfo);
void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
bool rearm);
static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
{
__inet_twsk_schedule(tw, timeo, false);
}
static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
{
__inet_twsk_schedule(tw, timeo, true);
}
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family);
netns : fix kernel panic in timewait socket destruction How to reproduce ? - create a network namespace - use tcp protocol and get timewait socket - exit the network namespace - after a moment (when the timewait socket is destroyed), the kernel panics. # BUG: unable to handle kernel NULL pointer dereference at 0000000000000007 IP: [<ffffffff821e394d>] inet_twdr_do_twkill_work+0x6e/0xb8 PGD 119985067 PUD 11c5c0067 PMD 0 Oops: 0000 [1] SMP CPU 1 Modules linked in: ipv6 button battery ac loop dm_mod tg3 libphy ext3 jbd edd fan thermal processor thermal_sys sg sata_svw libata dock serverworks sd_mod scsi_mod ide_disk ide_core [last unloaded: freq_table] Pid: 0, comm: swapper Not tainted 2.6.27-rc2 #3 RIP: 0010:[<ffffffff821e394d>] [<ffffffff821e394d>] inet_twdr_do_twkill_work+0x6e/0xb8 RSP: 0018:ffff88011ff7fed0 EFLAGS: 00010246 RAX: ffffffffffffffff RBX: ffffffff82339420 RCX: ffff88011ff7ff30 RDX: 0000000000000001 RSI: ffff88011a4d03c0 RDI: ffff88011ac2fc00 RBP: ffffffff823392e0 R08: 0000000000000000 R09: ffff88002802a200 R10: ffff8800a5c4b000 R11: ffffffff823e4080 R12: ffff88011ac2fc00 R13: 0000000000000001 R14: 0000000000000001 R15: 0000000000000000 FS: 0000000041cbd940(0000) GS:ffff8800bff839c0(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 0000000000000007 CR3: 00000000bd87c000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 0, threadinfo ffff8800bff9e000, task ffff88011ff76690) Stack: ffffffff823392e0 0000000000000100 ffffffff821e3a3a 0000000000000008 0000000000000000 ffffffff821e3a61 ffff8800bff7c000 ffffffff8203c7e7 ffff88011ff7ff10 ffff88011ff7ff10 0000000000000021 ffffffff82351108 Call Trace: <IRQ> [<ffffffff821e3a3a>] ? inet_twdr_hangman+0x0/0x9e [<ffffffff821e3a61>] ? inet_twdr_hangman+0x27/0x9e [<ffffffff8203c7e7>] ? run_timer_softirq+0x12c/0x193 [<ffffffff820390d1>] ? __do_softirq+0x5e/0xcd [<ffffffff8200d08c>] ? call_softirq+0x1c/0x28 [<ffffffff8200e611>] ? do_softirq+0x2c/0x68 [<ffffffff8201a055>] ? smp_apic_timer_interrupt+0x8e/0xa9 [<ffffffff8200cad6>] ? apic_timer_interrupt+0x66/0x70 <EOI> [<ffffffff82011f4c>] ? default_idle+0x27/0x3b [<ffffffff8200abbd>] ? cpu_idle+0x5f/0x7d Code: e8 01 00 00 4c 89 e7 41 ff c5 e8 8d fd ff ff 49 8b 44 24 38 4c 89 e7 65 8b 14 25 24 00 00 00 89 d2 48 8b 80 e8 00 00 00 48 f7 d0 <48> 8b 04 d0 48 ff 40 58 e8 fc fc ff ff 48 89 df e8 c0 5f 04 00 RIP [<ffffffff821e394d>] inet_twdr_do_twkill_work+0x6e/0xb8 RSP <ffff88011ff7fed0> CR2: 0000000000000007 This patch provides a function to purge all timewait sockets related to a network namespace. The timewait sockets life cycle is not tied with the network namespace, that means the timewait sockets stay alive while the network namespace dies. The timewait sockets are for avoiding to receive a duplicate packet from the network, if the network namespace is freed, the network stack is removed, so no chance to receive any packets from the outside world. Furthermore, having a pending destruction timer on these sockets with a network namespace freed is not safe and will lead to an oops if the timer callback which try to access data belonging to the namespace like for example in: inet_twdr_do_twkill_work -> NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITED); Purging the timewait sockets at the network namespace destruction will: 1) speed up memory freeing for the namespace 2) fix kernel panic on asynchronous timewait destruction Signed-off-by: Daniel Lezcano <dlezcano@fr.ibm.com> Acked-by: Denis V. Lunev <den@openvz.org> Acked-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-09 04:17:27 +08:00
static inline
struct net *twsk_net(const struct inet_timewait_sock *twsk)
{
return read_pnet(&twsk->tw_net);
}
static inline
void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net)
{
write_pnet(&twsk->tw_net, net);
}
#endif /* _INET_TIMEWAIT_SOCK_ */