linux/net/ipv4/proc.c

543 lines
20 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.
*
* This file implements the various access functions for the
* PROC file system. It is mainly used for debugging and
* statistics.
*
* Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Gerald J. Heim, <heim@peanuts.informatik.uni-tuebingen.de>
* Fred Baumgarten, <dc6iq@insu1.etec.uni-karlsruhe.de>
* Erik Schoenfelder, <schoenfr@ibr.cs.tu-bs.de>
*
* Fixes:
* Alan Cox : UDP sockets show the rxqueue/txqueue
* using hint flag for the netinfo.
* Pauline Middelink : identd support
* Alan Cox : Make /proc safer.
* Erik Schoenfelder : /proc/net/snmp
* Alan Cox : Handle dead sockets properly.
* Gerhard Koerting : Show both timers
* Alan Cox : Allow inode to be NULL (kernel socket)
* Andi Kleen : Add support for open_requests and
* split functions for more readibility.
* Andi Kleen : Add support for /proc/net/netstat
* Arnaldo C. Melo : Convert to seq_file
*
* 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.
*/
#include <linux/types.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <net/udp.h>
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 19:10:57 +00:00
#include <net/udplite.h>
#include <linux/bottom_half.h>
#include <linux/inetdevice.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/export.h>
#include <net/sock.h>
#include <net/raw.h>
/*
* Report socket allocation statistics [mea@utu.fi]
*/
static int sockstat_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
unsigned int frag_mem;
int orphans, sockets;
local_bh_disable();
orphans = percpu_counter_sum_positive(&tcp_orphan_count);
sockets = proto_sockets_allocated_sum_positive(&tcp_prot);
local_bh_enable();
socket_seq_show(seq);
seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
sock_prot_inuse_get(net, &tcp_prot), orphans,
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 01:51:09 +00:00
atomic_read(&tcp_death_row.tw_count), sockets,
proto_memory_allocated(&tcp_prot));
seq_printf(seq, "UDP: inuse %d mem %ld\n",
sock_prot_inuse_get(net, &udp_prot),
proto_memory_allocated(&udp_prot));
seq_printf(seq, "UDPLITE: inuse %d\n",
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
frag_mem = ip_frag_mem(net);
seq_printf(seq, "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
return 0;
}
static int sockstat_seq_open(struct inode *inode, struct file *file)
{
return single_open_net(inode, file, sockstat_seq_show);
}
static const struct file_operations sockstat_seq_fops = {
.owner = THIS_MODULE,
.open = sockstat_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release_net,
};
/* snmp items */
static const struct snmp_mib snmp4_ipstats_list[] = {
SNMP_MIB_ITEM("InReceives", IPSTATS_MIB_INPKTS),
SNMP_MIB_ITEM("InHdrErrors", IPSTATS_MIB_INHDRERRORS),
SNMP_MIB_ITEM("InAddrErrors", IPSTATS_MIB_INADDRERRORS),
SNMP_MIB_ITEM("ForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS),
SNMP_MIB_ITEM("InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS),
SNMP_MIB_ITEM("InDiscards", IPSTATS_MIB_INDISCARDS),
SNMP_MIB_ITEM("InDelivers", IPSTATS_MIB_INDELIVERS),
SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTPKTS),
SNMP_MIB_ITEM("OutDiscards", IPSTATS_MIB_OUTDISCARDS),
SNMP_MIB_ITEM("OutNoRoutes", IPSTATS_MIB_OUTNOROUTES),
SNMP_MIB_ITEM("ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT),
SNMP_MIB_ITEM("ReasmReqds", IPSTATS_MIB_REASMREQDS),
SNMP_MIB_ITEM("ReasmOKs", IPSTATS_MIB_REASMOKS),
SNMP_MIB_ITEM("ReasmFails", IPSTATS_MIB_REASMFAILS),
SNMP_MIB_ITEM("FragOKs", IPSTATS_MIB_FRAGOKS),
SNMP_MIB_ITEM("FragFails", IPSTATS_MIB_FRAGFAILS),
SNMP_MIB_ITEM("FragCreates", IPSTATS_MIB_FRAGCREATES),
SNMP_MIB_SENTINEL
};
/* Following items are displayed in /proc/net/netstat */
static const struct snmp_mib snmp4_ipextstats_list[] = {
SNMP_MIB_ITEM("InNoRoutes", IPSTATS_MIB_INNOROUTES),
SNMP_MIB_ITEM("InTruncatedPkts", IPSTATS_MIB_INTRUNCATEDPKTS),
SNMP_MIB_ITEM("InMcastPkts", IPSTATS_MIB_INMCASTPKTS),
SNMP_MIB_ITEM("OutMcastPkts", IPSTATS_MIB_OUTMCASTPKTS),
SNMP_MIB_ITEM("InBcastPkts", IPSTATS_MIB_INBCASTPKTS),
SNMP_MIB_ITEM("OutBcastPkts", IPSTATS_MIB_OUTBCASTPKTS),
SNMP_MIB_ITEM("InOctets", IPSTATS_MIB_INOCTETS),
SNMP_MIB_ITEM("OutOctets", IPSTATS_MIB_OUTOCTETS),
SNMP_MIB_ITEM("InMcastOctets", IPSTATS_MIB_INMCASTOCTETS),
SNMP_MIB_ITEM("OutMcastOctets", IPSTATS_MIB_OUTMCASTOCTETS),
SNMP_MIB_ITEM("InBcastOctets", IPSTATS_MIB_INBCASTOCTETS),
SNMP_MIB_ITEM("OutBcastOctets", IPSTATS_MIB_OUTBCASTOCTETS),
/* Non RFC4293 fields */
SNMP_MIB_ITEM("InCsumErrors", IPSTATS_MIB_CSUMERRORS),
SNMP_MIB_ITEM("InNoECTPkts", IPSTATS_MIB_NOECTPKTS),
SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
SNMP_MIB_SENTINEL
};
static const struct {
const char *name;
int index;
} icmpmibmap[] = {
{ "DestUnreachs", ICMP_DEST_UNREACH },
{ "TimeExcds", ICMP_TIME_EXCEEDED },
{ "ParmProbs", ICMP_PARAMETERPROB },
{ "SrcQuenchs", ICMP_SOURCE_QUENCH },
{ "Redirects", ICMP_REDIRECT },
{ "Echos", ICMP_ECHO },
{ "EchoReps", ICMP_ECHOREPLY },
{ "Timestamps", ICMP_TIMESTAMP },
{ "TimestampReps", ICMP_TIMESTAMPREPLY },
{ "AddrMasks", ICMP_ADDRESS },
{ "AddrMaskReps", ICMP_ADDRESSREPLY },
{ NULL, 0 }
};
static const struct snmp_mib snmp4_tcp_list[] = {
SNMP_MIB_ITEM("RtoAlgorithm", TCP_MIB_RTOALGORITHM),
SNMP_MIB_ITEM("RtoMin", TCP_MIB_RTOMIN),
SNMP_MIB_ITEM("RtoMax", TCP_MIB_RTOMAX),
SNMP_MIB_ITEM("MaxConn", TCP_MIB_MAXCONN),
SNMP_MIB_ITEM("ActiveOpens", TCP_MIB_ACTIVEOPENS),
SNMP_MIB_ITEM("PassiveOpens", TCP_MIB_PASSIVEOPENS),
SNMP_MIB_ITEM("AttemptFails", TCP_MIB_ATTEMPTFAILS),
SNMP_MIB_ITEM("EstabResets", TCP_MIB_ESTABRESETS),
SNMP_MIB_ITEM("CurrEstab", TCP_MIB_CURRESTAB),
SNMP_MIB_ITEM("InSegs", TCP_MIB_INSEGS),
SNMP_MIB_ITEM("OutSegs", TCP_MIB_OUTSEGS),
SNMP_MIB_ITEM("RetransSegs", TCP_MIB_RETRANSSEGS),
SNMP_MIB_ITEM("InErrs", TCP_MIB_INERRS),
SNMP_MIB_ITEM("OutRsts", TCP_MIB_OUTRSTS),
SNMP_MIB_ITEM("InCsumErrors", TCP_MIB_CSUMERRORS),
SNMP_MIB_SENTINEL
};
static const struct snmp_mib snmp4_udp_list[] = {
SNMP_MIB_ITEM("InDatagrams", UDP_MIB_INDATAGRAMS),
SNMP_MIB_ITEM("NoPorts", UDP_MIB_NOPORTS),
SNMP_MIB_ITEM("InErrors", UDP_MIB_INERRORS),
SNMP_MIB_ITEM("OutDatagrams", UDP_MIB_OUTDATAGRAMS),
SNMP_MIB_ITEM("RcvbufErrors", UDP_MIB_RCVBUFERRORS),
SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS),
SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS),
SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI),
SNMP_MIB_SENTINEL
};
static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("SyncookiesSent", LINUX_MIB_SYNCOOKIESSENT),
SNMP_MIB_ITEM("SyncookiesRecv", LINUX_MIB_SYNCOOKIESRECV),
SNMP_MIB_ITEM("SyncookiesFailed", LINUX_MIB_SYNCOOKIESFAILED),
SNMP_MIB_ITEM("EmbryonicRsts", LINUX_MIB_EMBRYONICRSTS),
SNMP_MIB_ITEM("PruneCalled", LINUX_MIB_PRUNECALLED),
SNMP_MIB_ITEM("RcvPruned", LINUX_MIB_RCVPRUNED),
SNMP_MIB_ITEM("OfoPruned", LINUX_MIB_OFOPRUNED),
SNMP_MIB_ITEM("OutOfWindowIcmps", LINUX_MIB_OUTOFWINDOWICMPS),
SNMP_MIB_ITEM("LockDroppedIcmps", LINUX_MIB_LOCKDROPPEDICMPS),
SNMP_MIB_ITEM("ArpFilter", LINUX_MIB_ARPFILTER),
SNMP_MIB_ITEM("TW", LINUX_MIB_TIMEWAITED),
SNMP_MIB_ITEM("TWRecycled", LINUX_MIB_TIMEWAITRECYCLED),
SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED),
SNMP_MIB_ITEM("PAWSPassive", LINUX_MIB_PAWSPASSIVEREJECTED),
SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED),
SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED),
SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS),
SNMP_MIB_ITEM("DelayedACKLocked", LINUX_MIB_DELAYEDACKLOCKED),
SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST),
SNMP_MIB_ITEM("ListenOverflows", LINUX_MIB_LISTENOVERFLOWS),
SNMP_MIB_ITEM("ListenDrops", LINUX_MIB_LISTENDROPS),
SNMP_MIB_ITEM("TCPPrequeued", LINUX_MIB_TCPPREQUEUED),
SNMP_MIB_ITEM("TCPDirectCopyFromBacklog", LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG),
SNMP_MIB_ITEM("TCPDirectCopyFromPrequeue", LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE),
SNMP_MIB_ITEM("TCPPrequeueDropped", LINUX_MIB_TCPPREQUEUEDROPPED),
SNMP_MIB_ITEM("TCPHPHits", LINUX_MIB_TCPHPHITS),
SNMP_MIB_ITEM("TCPHPHitsToUser", LINUX_MIB_TCPHPHITSTOUSER),
SNMP_MIB_ITEM("TCPPureAcks", LINUX_MIB_TCPPUREACKS),
SNMP_MIB_ITEM("TCPHPAcks", LINUX_MIB_TCPHPACKS),
SNMP_MIB_ITEM("TCPRenoRecovery", LINUX_MIB_TCPRENORECOVERY),
SNMP_MIB_ITEM("TCPSackRecovery", LINUX_MIB_TCPSACKRECOVERY),
SNMP_MIB_ITEM("TCPSACKReneging", LINUX_MIB_TCPSACKRENEGING),
SNMP_MIB_ITEM("TCPFACKReorder", LINUX_MIB_TCPFACKREORDER),
SNMP_MIB_ITEM("TCPSACKReorder", LINUX_MIB_TCPSACKREORDER),
SNMP_MIB_ITEM("TCPRenoReorder", LINUX_MIB_TCPRENOREORDER),
SNMP_MIB_ITEM("TCPTSReorder", LINUX_MIB_TCPTSREORDER),
SNMP_MIB_ITEM("TCPFullUndo", LINUX_MIB_TCPFULLUNDO),
SNMP_MIB_ITEM("TCPPartialUndo", LINUX_MIB_TCPPARTIALUNDO),
SNMP_MIB_ITEM("TCPDSACKUndo", LINUX_MIB_TCPDSACKUNDO),
SNMP_MIB_ITEM("TCPLossUndo", LINUX_MIB_TCPLOSSUNDO),
SNMP_MIB_ITEM("TCPLostRetransmit", LINUX_MIB_TCPLOSTRETRANSMIT),
SNMP_MIB_ITEM("TCPRenoFailures", LINUX_MIB_TCPRENOFAILURES),
SNMP_MIB_ITEM("TCPSackFailures", LINUX_MIB_TCPSACKFAILURES),
SNMP_MIB_ITEM("TCPLossFailures", LINUX_MIB_TCPLOSSFAILURES),
SNMP_MIB_ITEM("TCPFastRetrans", LINUX_MIB_TCPFASTRETRANS),
SNMP_MIB_ITEM("TCPForwardRetrans", LINUX_MIB_TCPFORWARDRETRANS),
SNMP_MIB_ITEM("TCPSlowStartRetrans", LINUX_MIB_TCPSLOWSTARTRETRANS),
SNMP_MIB_ITEM("TCPTimeouts", LINUX_MIB_TCPTIMEOUTS),
tcp: Tail loss probe (TLP) This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-11 10:00:43 +00:00
SNMP_MIB_ITEM("TCPLossProbes", LINUX_MIB_TCPLOSSPROBES),
SNMP_MIB_ITEM("TCPLossProbeRecovery", LINUX_MIB_TCPLOSSPROBERECOVERY),
SNMP_MIB_ITEM("TCPRenoRecoveryFail", LINUX_MIB_TCPRENORECOVERYFAIL),
SNMP_MIB_ITEM("TCPSackRecoveryFail", LINUX_MIB_TCPSACKRECOVERYFAIL),
SNMP_MIB_ITEM("TCPSchedulerFailed", LINUX_MIB_TCPSCHEDULERFAILED),
SNMP_MIB_ITEM("TCPRcvCollapsed", LINUX_MIB_TCPRCVCOLLAPSED),
SNMP_MIB_ITEM("TCPDSACKOldSent", LINUX_MIB_TCPDSACKOLDSENT),
SNMP_MIB_ITEM("TCPDSACKOfoSent", LINUX_MIB_TCPDSACKOFOSENT),
SNMP_MIB_ITEM("TCPDSACKRecv", LINUX_MIB_TCPDSACKRECV),
SNMP_MIB_ITEM("TCPDSACKOfoRecv", LINUX_MIB_TCPDSACKOFORECV),
SNMP_MIB_ITEM("TCPAbortOnData", LINUX_MIB_TCPABORTONDATA),
SNMP_MIB_ITEM("TCPAbortOnClose", LINUX_MIB_TCPABORTONCLOSE),
SNMP_MIB_ITEM("TCPAbortOnMemory", LINUX_MIB_TCPABORTONMEMORY),
SNMP_MIB_ITEM("TCPAbortOnTimeout", LINUX_MIB_TCPABORTONTIMEOUT),
SNMP_MIB_ITEM("TCPAbortOnLinger", LINUX_MIB_TCPABORTONLINGER),
SNMP_MIB_ITEM("TCPAbortFailed", LINUX_MIB_TCPABORTFAILED),
SNMP_MIB_ITEM("TCPMemoryPressures", LINUX_MIB_TCPMEMORYPRESSURES),
SNMP_MIB_ITEM("TCPSACKDiscard", LINUX_MIB_TCPSACKDISCARD),
SNMP_MIB_ITEM("TCPDSACKIgnoredOld", LINUX_MIB_TCPDSACKIGNOREDOLD),
SNMP_MIB_ITEM("TCPDSACKIgnoredNoUndo", LINUX_MIB_TCPDSACKIGNOREDNOUNDO),
SNMP_MIB_ITEM("TCPSpuriousRTOs", LINUX_MIB_TCPSPURIOUSRTOS),
SNMP_MIB_ITEM("TCPMD5NotFound", LINUX_MIB_TCPMD5NOTFOUND),
SNMP_MIB_ITEM("TCPMD5Unexpected", LINUX_MIB_TCPMD5UNEXPECTED),
SNMP_MIB_ITEM("TCPSackShifted", LINUX_MIB_SACKSHIFTED),
SNMP_MIB_ITEM("TCPSackMerged", LINUX_MIB_SACKMERGED),
SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK),
SNMP_MIB_ITEM("TCPBacklogDrop", LINUX_MIB_TCPBACKLOGDROP),
SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP),
SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP),
SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER),
SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW),
SNMP_MIB_ITEM("TCPReqQFullDoCookies", LINUX_MIB_TCPREQQFULLDOCOOKIES),
SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP),
SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL),
SNMP_MIB_ITEM("TCPRcvCoalesce", LINUX_MIB_TCPRCVCOALESCE),
SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE),
SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP),
SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE),
SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE),
SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE),
SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL),
SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE),
SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL),
SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
tcp: auto corking With the introduction of TCP Small Queues, TSO auto sizing, and TCP pacing, we can implement Automatic Corking in the kernel, to help applications doing small write()/sendmsg() to TCP sockets. Idea is to change tcp_push() to check if the current skb payload is under skb optimal size (a multiple of MSS bytes) If under 'size_goal', and at least one packet is still in Qdisc or NIC TX queues, set the TCP Small Queue Throttled bit, so that the push will be delayed up to TX completion time. This delay might allow the application to coalesce more bytes in the skb in following write()/sendmsg()/sendfile() system calls. The exact duration of the delay is depending on the dynamics of the system, and might be zero if no packet for this flow is actually held in Qdisc or NIC TX ring. Using FQ/pacing is a way to increase the probability of autocorking being triggered. Add a new sysctl (/proc/sys/net/ipv4/tcp_autocorking) to control this feature and default it to 1 (enabled) Add a new SNMP counter : nstat -a | grep TcpExtTCPAutoCorking This counter is incremented every time we detected skb was under used and its flush was deferred. Tested: Interesting effects when using line buffered commands under ssh. Excellent performance results in term of cpu usage and total throughput. lpq83:~# echo 1 >/proc/sys/net/ipv4/tcp_autocorking lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128 9410.39 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128': 35209.439626 task-clock # 2.901 CPUs utilized 2,294 context-switches # 0.065 K/sec 101 CPU-migrations # 0.003 K/sec 4,079 page-faults # 0.116 K/sec 97,923,241,298 cycles # 2.781 GHz [83.31%] 51,832,908,236 stalled-cycles-frontend # 52.93% frontend cycles idle [83.30%] 25,697,986,603 stalled-cycles-backend # 26.24% backend cycles idle [66.70%] 102,225,978,536 instructions # 1.04 insns per cycle # 0.51 stalled cycles per insn [83.38%] 18,657,696,819 branches # 529.906 M/sec [83.29%] 91,679,646 branch-misses # 0.49% of all branches [83.40%] 12.136204899 seconds time elapsed lpq83:~# echo 0 >/proc/sys/net/ipv4/tcp_autocorking lpq83:~# perf stat ./super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128 6624.89 Performance counter stats for './super_netperf 4 -t TCP_STREAM -H lpq84 -- -m 128': 40045.864494 task-clock # 3.301 CPUs utilized 171 context-switches # 0.004 K/sec 53 CPU-migrations # 0.001 K/sec 4,080 page-faults # 0.102 K/sec 111,340,458,645 cycles # 2.780 GHz [83.34%] 61,778,039,277 stalled-cycles-frontend # 55.49% frontend cycles idle [83.31%] 29,295,522,759 stalled-cycles-backend # 26.31% backend cycles idle [66.67%] 108,654,349,355 instructions # 0.98 insns per cycle # 0.57 stalled cycles per insn [83.34%] 19,552,170,748 branches # 488.244 M/sec [83.34%] 157,875,417 branch-misses # 0.81% of all branches [83.34%] 12.130267788 seconds time elapsed Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-06 06:36:05 +00:00
SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING),
SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV),
SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV),
SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV),
SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS),
SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT),
SNMP_MIB_ITEM("TCPHystartTrainDetect", LINUX_MIB_TCPHYSTARTTRAINDETECT),
SNMP_MIB_ITEM("TCPHystartTrainCwnd", LINUX_MIB_TCPHYSTARTTRAINCWND),
SNMP_MIB_ITEM("TCPHystartDelayDetect", LINUX_MIB_TCPHYSTARTDELAYDETECT),
SNMP_MIB_ITEM("TCPHystartDelayCwnd", LINUX_MIB_TCPHYSTARTDELAYCWND),
tcp: helpers to mitigate ACK loops by rate-limiting out-of-window dupacks Helpers for mitigating ACK loops by rate-limiting dupacks sent in response to incoming out-of-window packets. This patch includes: - rate-limiting logic - sysctl to control how often we allow dupacks to out-of-window packets - SNMP counter for cases where we rate-limited our dupack sending The rate-limiting logic in this patch decides to not send dupacks in response to out-of-window segments if (a) they are SYNs or pure ACKs and (b) the remote endpoint is sending them faster than the configured rate limit. We rate-limit our responses rather than blocking them entirely or resetting the connection, because legitimate connections can rely on dupacks in response to some out-of-window segments. For example, zero window probes are typically sent with a sequence number that is below the current window, and ZWPs thus expect to thus elicit a dupack in response. We allow dupacks in response to TCP segments with data, because these may be spurious retransmissions for which the remote endpoint wants to receive DSACKs. This is safe because segments with data can't realistically be part of ACK loops, which by their nature consist of each side sending pure/data-less ACKs to each other. The dupack interval is controlled by a new sysctl knob, tcp_invalid_ratelimit, given in milliseconds, in case an administrator needs to dial this upward in the face of a high-rate DoS attack. The name and units are chosen to be analogous to the existing analogous knob for ICMP, icmp_ratelimit. The default value for tcp_invalid_ratelimit is 500ms, which allows at most one such dupack per 500ms. This is chosen to be 2x faster than the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule 2.4). We allow the extra 2x factor because network delay variations can cause packets sent at 1 second intervals to be compressed and arrive much closer. Reported-by: Avery Fay <avery@mixpanel.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-02-06 21:04:38 +00:00
SNMP_MIB_ITEM("TCPACKSkippedSynRecv", LINUX_MIB_TCPACKSKIPPEDSYNRECV),
SNMP_MIB_ITEM("TCPACKSkippedPAWS", LINUX_MIB_TCPACKSKIPPEDPAWS),
SNMP_MIB_ITEM("TCPACKSkippedSeq", LINUX_MIB_TCPACKSKIPPEDSEQ),
SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2),
SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT),
SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE),
SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE),
SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE),
SNMP_MIB_SENTINEL
};
static void icmpmsg_put_line(struct seq_file *seq, unsigned long *vals,
unsigned short *type, int count)
{
int j;
if (count) {
seq_puts(seq, "\nIcmpMsg:");
for (j = 0; j < count; ++j)
seq_printf(seq, " %sType%u",
type[j] & 0x100 ? "Out" : "In",
type[j] & 0xff);
seq_puts(seq, "\nIcmpMsg:");
for (j = 0; j < count; ++j)
seq_printf(seq, " %lu", vals[j]);
}
}
static void icmpmsg_put(struct seq_file *seq)
{
#define PERLINE 16
int i, count;
unsigned short type[PERLINE];
unsigned long vals[PERLINE], val;
struct net *net = seq->private;
count = 0;
for (i = 0; i < ICMPMSG_MIB_MAX; i++) {
val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]);
if (val) {
type[count] = i;
vals[count++] = val;
}
if (count == PERLINE) {
icmpmsg_put_line(seq, vals, type, count);
count = 0;
}
}
icmpmsg_put_line(seq, vals, type, count);
#undef PERLINE
}
static void icmp_put(struct seq_file *seq)
{
int i;
struct net *net = seq->private;
atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs;
seq_puts(seq, "\nIcmp: InMsgs InErrors InCsumErrors");
for (i = 0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " In%s", icmpmibmap[i].name);
seq_puts(seq, " OutMsgs OutErrors");
for (i = 0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " Out%s", icmpmibmap[i].name);
seq_printf(seq, "\nIcmp: %lu %lu %lu",
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INMSGS),
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INERRORS),
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS));
for (i = 0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " %lu",
atomic_long_read(ptr + icmpmibmap[i].index));
seq_printf(seq, " %lu %lu",
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
for (i = 0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " %lu",
atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
}
/*
* Called from the PROCfs module. This outputs /proc/net/snmp.
*/
static int snmp_seq_show(struct seq_file *seq, void *v)
{
int i;
struct net *net = seq->private;
seq_puts(seq, "Ip: Forwarding DefaultTTL");
for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
seq_printf(seq, " %s", snmp4_ipstats_list[i].name);
seq_printf(seq, "\nIp: %d %d",
IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2,
sysctl_ip_default_ttl);
BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
seq_printf(seq, " %llu",
snmp_fold_field64(net->mib.ip_statistics,
snmp4_ipstats_list[i].entry,
offsetof(struct ipstats_mib, syncp)));
icmp_put(seq); /* RFC 2011 compatibility */
icmpmsg_put(seq);
seq_puts(seq, "\nTcp:");
for (i = 0; snmp4_tcp_list[i].name != NULL; i++)
seq_printf(seq, " %s", snmp4_tcp_list[i].name);
seq_puts(seq, "\nTcp:");
for (i = 0; snmp4_tcp_list[i].name != NULL; i++) {
/* MaxConn field is signed, RFC 2012 */
if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN)
seq_printf(seq, " %ld",
snmp_fold_field(net->mib.tcp_statistics,
snmp4_tcp_list[i].entry));
else
seq_printf(seq, " %lu",
snmp_fold_field(net->mib.tcp_statistics,
snmp4_tcp_list[i].entry));
}
seq_puts(seq, "\nUdp:");
for (i = 0; snmp4_udp_list[i].name != NULL; i++)
seq_printf(seq, " %s", snmp4_udp_list[i].name);
seq_puts(seq, "\nUdp:");
for (i = 0; snmp4_udp_list[i].name != NULL; i++)
seq_printf(seq, " %lu",
snmp_fold_field(net->mib.udp_statistics,
snmp4_udp_list[i].entry));
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 19:10:57 +00:00
/* the UDP and UDP-Lite MIBs are the same */
seq_puts(seq, "\nUdpLite:");
for (i = 0; snmp4_udp_list[i].name != NULL; i++)
seq_printf(seq, " %s", snmp4_udp_list[i].name);
seq_puts(seq, "\nUdpLite:");
for (i = 0; snmp4_udp_list[i].name != NULL; i++)
seq_printf(seq, " %lu",
snmp_fold_field(net->mib.udplite_statistics,
snmp4_udp_list[i].entry));
seq_putc(seq, '\n');
return 0;
}
static int snmp_seq_open(struct inode *inode, struct file *file)
{
return single_open_net(inode, file, snmp_seq_show);
}
static const struct file_operations snmp_seq_fops = {
.owner = THIS_MODULE,
.open = snmp_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release_net,
};
/*
* Output /proc/net/netstat
*/
static int netstat_seq_show(struct seq_file *seq, void *v)
{
int i;
struct net *net = seq->private;
seq_puts(seq, "TcpExt:");
for (i = 0; snmp4_net_list[i].name != NULL; i++)
seq_printf(seq, " %s", snmp4_net_list[i].name);
seq_puts(seq, "\nTcpExt:");
for (i = 0; snmp4_net_list[i].name != NULL; i++)
seq_printf(seq, " %lu",
snmp_fold_field(net->mib.net_statistics,
snmp4_net_list[i].entry));
seq_puts(seq, "\nIpExt:");
for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
seq_printf(seq, " %s", snmp4_ipextstats_list[i].name);
seq_puts(seq, "\nIpExt:");
for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
seq_printf(seq, " %llu",
snmp_fold_field64(net->mib.ip_statistics,
snmp4_ipextstats_list[i].entry,
offsetof(struct ipstats_mib, syncp)));
seq_putc(seq, '\n');
return 0;
}
static int netstat_seq_open(struct inode *inode, struct file *file)
{
return single_open_net(inode, file, netstat_seq_show);
}
static const struct file_operations netstat_seq_fops = {
.owner = THIS_MODULE,
.open = netstat_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release_net,
};
static __net_init int ip_proc_init_net(struct net *net)
{
if (!proc_create("sockstat", S_IRUGO, net->proc_net,
&sockstat_seq_fops))
goto out_sockstat;
if (!proc_create("netstat", S_IRUGO, net->proc_net, &netstat_seq_fops))
goto out_netstat;
if (!proc_create("snmp", S_IRUGO, net->proc_net, &snmp_seq_fops))
goto out_snmp;
return 0;
out_snmp:
remove_proc_entry("netstat", net->proc_net);
out_netstat:
remove_proc_entry("sockstat", net->proc_net);
out_sockstat:
return -ENOMEM;
}
static __net_exit void ip_proc_exit_net(struct net *net)
{
remove_proc_entry("snmp", net->proc_net);
remove_proc_entry("netstat", net->proc_net);
remove_proc_entry("sockstat", net->proc_net);
}
static __net_initdata struct pernet_operations ip_proc_ops = {
.init = ip_proc_init_net,
.exit = ip_proc_exit_net,
};
int __init ip_misc_proc_init(void)
{
return register_pernet_subsys(&ip_proc_ops);
}