summaryrefslogtreecommitdiffhomepage
path: root/pkg/tcpip
AgeCommit message (Collapse)Author
2019-03-28netstack/fdbased: add generic segmentation offload (GSO) supportAndrei Vagin
The linux packet socket can handle GSO packets, so we can segment packets to 64K instead of the MTU which is usually 1500. Here are numbers for the nginx-1m test: runsc: 579330.01 [Kbytes/sec] received runsc-gso: 1794121.66 [Kbytes/sec] received runc: 2122139.06 [Kbytes/sec] received and for tcp_benchmark: $ tcp_benchmark --duration 15 --ideal [ 4] 0.0-15.0 sec 86647 MBytes 48456 Mbits/sec $ tcp_benchmark --client --duration 15 --ideal [ 4] 0.0-15.0 sec 2173 MBytes 1214 Mbits/sec $ tcp_benchmark --client --duration 15 --ideal --gso 65536 [ 4] 0.0-15.0 sec 19357 MBytes 10825 Mbits/sec PiperOrigin-RevId: 240809103 Change-Id: I2637f104db28b5d4c64e1e766c610162a195775a
2019-03-27Avoid mutating memory passed to DeliverTransportPacketTamir Duberstein
PiperOrigin-RevId: 240642903 Change-Id: I16625015123a827d267d60b328a202057264bbd6
2019-03-26Remove polling from ICMP testTamir Duberstein
PiperOrigin-RevId: 240483396 Change-Id: Ie75d3ae38af83f1d92f167ff9ba58fa10f5b372b
2019-03-26netstack: Don't exclude length when a pseudo-header checksum is calculatedAndrei Vagin
This is a preparation for GSO changes (cl/234508902). RELNOTES[gofers]: Refactor checksum code to include length, which it already did, but in a convoluted way. Should be a no-op. PiperOrigin-RevId: 240460794 Change-Id: I537381bc670b5a9f5d70a87aa3eb7252e8f5ace2
2019-03-26Remove echoReplierTamir Duberstein
Mirror the ICMPv6 echo implementation in ICMPv4 echo. This removes unnecessary asynchrony, reduces copying, and reduces complexity. PiperOrigin-RevId: 240394525 Change-Id: If8f53254154f86772f5e51159765aa23b3b328b8
2019-03-20netstack: adjust the sequence number after trimming the packetAndrei Vagin
PiperOrigin-RevId: 239417224 Change-Id: I14a9adc31a6330a79a6156c105969cd5f1f63d20
2019-03-19netstack: reduce MSS from SYN to account tcp optionsAndrei Vagin
See: https://tools.ietf.org/html/rfc6691#section-2 PiperOrigin-RevId: 239305632 Change-Id: Ie8eb912a43332e6490045dc95570709c5b81855e
2019-03-19Add layer 2 stats (tx, rx) X (packets, bytes) to netstackBert Muthalaly
PiperOrigin-RevId: 239194420 Change-Id: Ie193e8ac2b7a6db21195ac85824a335930483971
2019-03-14Remove duplicate TCP flag definitionsTamir Duberstein
PiperOrigin-RevId: 238467634 Change-Id: If4cd8efff7386fbee1195f051d15549b495910a9
2019-03-13Remove unused function.Kevin Krakauer
PiperOrigin-RevId: 238336475 Change-Id: I8131e04699028246ebc233953ebb3feca5673940
2019-03-13Reduce PACKET_RX_RING memory usageFabricio Voznika
Previous memory allocation was excessive (80 MB). Changed it to use 2 MB instead. There is no drop in perfomance due to this change: ab -n 100 -c 10 http://server/latin10m.txt ==> 10 MB file 80 MB: 178 MB/s 2 MB: 181 MB/s PiperOrigin-RevId: 238321594 Change-Id: I1c8aed13cad5d75f4506d2b406b305117055fbe5
2019-03-12Make gonet.PacketConn implement net.Conn.Noah Gold
gonet.PacketConn now implements net.Conn, allowing it to be returned from net.Dial.Dialer functions. PiperOrigin-RevId: 238111980 Change-Id: I174884385ff4d9b8e9918fac7bbb5b93ca366ba7
2019-03-12Make HandleLocal apply to all non-loopback interfaces.Ian Gudger
HandleLocal is very similar conceptually to MULTICAST_LOOP, so we can unify the implementations. This has the benefit of making HandleLocal apply even when the fdbased link endpoint isn't in use. In addition, move looping logic to route creation so that it doesn't need to be run for each packet. This should improve performance. PiperOrigin-RevId: 238099480 Change-Id: I72839f16f25310471453bc9d3fb8544815b25c23
2019-03-08Validate multicast addresses in multicast group operations.Ian Gudger
PiperOrigin-RevId: 237559843 Change-Id: I93a9d83a08cd3d49d5fc7fcad5b0710d0aa04aaa
2019-03-08Implement IP_MULTICAST_LOOP.Ian Gudger
IP_MULTICAST_LOOP controls whether or not multicast packets sent on the default route are looped back. In order to implement this switch, support for sending and looping back multicast packets on the default route had to be implemented. For now we only support IPv4 multicast. PiperOrigin-RevId: 237534603 Change-Id: I490ac7ff8e8ebef417c7eb049a919c29d156ac1c
2019-03-05Add new retransmissions and recovery related metrics.Bhasker Hariharan
PiperOrigin-RevId: 236945145 Change-Id: I051760d95154ea5574c8bb6aea526f488af5e07b
2019-03-05Remove unused commit() function argument to Bind.Kevin Krakauer
PiperOrigin-RevId: 236926132 Change-Id: I5cf103f22766e6e65a581de780c7bb9ca0fa3181
2019-02-28Map IPv{4,6} addresses to ethernet addressesTamir Duberstein
...in accordance with RFCs 1112 and 2464. Fixes IPv4 multicast when IP_MULTICAST_IF is specified. Don't return ErrNoRoute when no route is needed. Don't set Route.NextHop when no route is needed. PiperOrigin-RevId: 236199813 Change-Id: I48ed33e1b7f760deaa37e18ad7f1b8b62819ab43
2019-02-27Ping support via IPv4 raw sockets.Kevin Krakauer
Broadly, this change: * Enables sockets to be created via `socket(AF_INET, SOCK_RAW, IPPROTO_ICMP)`. * Passes the network-layer (IP) header up the stack to the transport endpoint, which can pass it up to the socket layer. This allows a raw socket to return the entire IP packet to users. * Adds functions to stack.TransportProtocol, stack.Stack, stack.transportDemuxer that enable incoming packets to be delivered to raw endpoints. New raw sockets of other protocols (not ICMP) just need to register with the stack. * Enables ping.endpoint to return IP headers when created via SOCK_RAW. PiperOrigin-RevId: 235993280 Change-Id: I60ed994f5ff18b2cbd79f063a7fdf15d093d845a
2019-02-26Adds a WriteRawPacket method to the InjectableLinkEndpoint interface.Googler
Also exposes ipv4.MaxTotalSize since it is a generally useful constant. PiperOrigin-RevId: 235799755 Change-Id: I1fa8d5294bf355acf5527cfdf274b3687d3c8b13
2019-02-26Use more conservative locking in NIC.DeliverNetworkPacketAmanda Tait
An earlier CL excessively minimizes the period in which it holds a lock on NIC. This earlier CL had done this out of the mistaken impression it fixed a broken test, when in fact it just reduced the rate of failure of a flaky test in tcp_test.go. This new change holds the lock on NIC for the duration of the loop over n.endpoints. PiperOrigin-RevId: 235732487 Change-Id: I53ee6df264f093ddc4d29e9acdcba6b4838cb112
2019-02-25Add a SACK scoreboard to TCP endpoints.Bhasker Hariharan
This change does not make use of SACK information but adds support to track SACK information and store it in the endpoint. The actual SACK based recovery will be in a separate CL. Part of commits to add RFC 6675 support to Netstack. PiperOrigin-RevId: 235612264 Change-Id: I261f94844d7bad5abda803152ce6cc6125a467ff
2019-02-25Fix race condition in NIC.DeliverNetworkPacketAmanda Tait
cl/234850781 introduced a race condition in NIC.DeliverNetworkPacket by failing to hold a lock. This change fixes this regressesion by acquiring a read lock before iterating through n.endpoints, and then releasing the lock once iteration is complete. PiperOrigin-RevId: 235549770 Change-Id: Ib0133288be512d478cf759c3314dc95ec3205d4b
2019-02-22Rename ping endpoints to icmp endpoints.Kevin Krakauer
PiperOrigin-RevId: 235248572 Change-Id: I5b0538b6feb365a98712c2a2d56d856fe80a8a09
2019-02-20Implement Broadcast supportAmanda Tait
This change adds support for the SO_BROADCAST socket option in gVisor Netstack. This support includes getsockopt()/setsockopt() functionality for both UDP and TCP endpoints (the latter being a NOOP), dispatching broadcast messages up and down the stack, and route finding/creation for broadcast packets. Finally, a suite of tests have been implemented, exercising this functionality through the Linux syscall API. PiperOrigin-RevId: 234850781 Change-Id: If3e666666917d39f55083741c78314a06defb26c
2019-02-19Updates tcp_proxy to use an AF_PACKET and veth devices.Bhasker Hariharan
tcp_proxy now uses an AF_PACKET socket as the FD for netstack link layer endpoint instead of a tap device. It also changes the link layer endpoint to use PacketMMap dispatch instead of Readv. This reduces overall cpu and reflects the current runsc setup which uses PacketMMap and also uses veth devices to receive packets. Also fixed a bug in gonet where Read() was not doing coalescing read and would read small amounts at a time. PiperOrigin-RevId: 234714768 Change-Id: Idabf8e600e4512489d3ba441c4096dc74deba5d7
2019-02-15Implement IP_MULTICAST_IF.Ian Gudger
This allows setting a default send interface for IPv4 multicast. IPv6 support will come later. PiperOrigin-RevId: 234251379 Change-Id: I65922341cd8b8880f690fae3eeb7ddfa47c8c173
2019-02-15Move SO_TIMESTAMP from different transport endpoints to epsocket.Kevin Krakauer
SO_TIMESTAMP is reimplemented in ping and UDP sockets (and needs to be added for TCP), but can just be implemented in epsocket for simplicity. This will also make SIOCGSTAMP easier to implement. PiperOrigin-RevId: 234179300 Change-Id: Ib5ea0b1261dc218c1a8b15a65775de0050fe3230
2019-02-14Internal change.Googler
PiperOrigin-RevId: 234011346 Change-Id: Ic69375ddb3794dd0d3d6e62ee4dc60fdf4baf2c7
2019-02-13Add support for using PACKET_RX_RING to receive packets.Bhasker Hariharan
PACKET_RX_RING allows the use of an mmapped buffer to receive packets from the kernel. This should cut down the number of host syscalls that need to be made to receive packets when the underlying fd is a socket of the AF_PACKET type. PiperOrigin-RevId: 233834998 Change-Id: I8060025c6ced206986e94cc46b8f382b81bfa47f
2019-02-11Do not drop packets w/ missing TCP timestamps.Bhasker Hariharan
RFC7323 recommends that if the timestamp option was negotiated then all packets should carry a TCP Timestamp and any packets that do not should be dropped. Netstack implemented this behaviour. Linux OTOH does not and will accept such packets. This change makes Netstack behaviour compatible with Linux. Also now that we allow such packets, we do need to update RTO calculations based on these packets even if timestamp option is enabled. PiperOrigin-RevId: 233432268 Change-Id: I9f4742ae6b63930ac3b5e37d8c238761e6a4b29f
2019-02-08Fix build error.Ian Gudger
PiperOrigin-RevId: 233139020 Change-Id: I2e7089fa25d20e5662eb941054a684d41f5d3e12
2019-02-07Plumb IP_ADD_MEMBERSHIP and IP_DROP_MEMBERSHIP to netstack.Ian Gudger
Also includes a few fixes for IPv4 multicast support. IPv6 support is coming in a followup CL. PiperOrigin-RevId: 233008638 Change-Id: If7dae6222fef43fda48033f0292af77832d95e82
2019-02-07Internal change.Googler
PiperOrigin-RevId: 232937200 Change-Id: I5c3709cc8f1313313ff618a45e48c14a3a111cb4
2019-01-31Remove license commentsMichael Pratt
Nothing reads them and they can simply get stale. Generated with: $ sed -i "s/licenses(\(.*\)).*/licenses(\1)/" **/BUILD PiperOrigin-RevId: 231818945 Change-Id: Ibc3f9838546b7e94f13f217060d31f4ada9d4bf0
2019-01-29Fix IsLost check to match the description in RFC6675.Bhasker Hariharan
quoting what "rscheff@gmx.at" pointed out over email. "IsLost in RFC3517 is defined as >= (DupThresh * SMSS) while RFC6675 improves upon this, and defines IsLost as > ((DupThresh - 1) * SMSS + 1). The latter addresses situations where partial segments (size < MSS) are sent (eg. last segment of a http protocol message sent with PSH being less than MSS is common)." PiperOrigin-RevId: 231512331 Change-Id: I1addd4a92e3e7baeb0bdda46463ebfae435da958
2019-01-29Fix NIC endpoint forwarding.Ian Gudger
Also adds a test for regular NIC forwarding. PiperOrigin-RevId: 231495279 Change-Id: Ic7edec249568e9ad0280cea77eac14478c9073e1
2019-01-29Use recvmmsg() instead of readv() to read packets from NIC.Bhasker Hariharan
This should reduce the number of syscalls required to process packets significantly and improve throughputs. PiperOrigin-RevId: 231366886 Change-Id: I8b38077262bf9c53176bc4a94b530188d3d7c0ca
2019-01-15test: Tag tcp_test as flaky.Kevin Krakauer
PiperOrigin-RevId: 229427852 Change-Id: I9de8ed63f4a7672dacd3b282c863c599d00acd52
2019-01-14netstack: release port inline for listening sockets only.Zhaozhong Ni
PiperOrigin-RevId: 229243918 Change-Id: Ie14ef34e66ae851ed080f57b7d26a369a66f7664
2019-01-11Internal change.Googler
PiperOrigin-RevId: 228979583 Change-Id: I69bd82def48ceb19bc8558c890622b8528d98764
2019-01-08Implement Stringer for tcpip.StatCounterBert Muthalaly
This enables formatting tcpip.Stats readably with %+v. PiperOrigin-RevId: 228379088 Change-Id: I6a9876454a22f151ee752cf94589b4188729458f
2018-12-28Implement SO_REUSEPORT for TCP and UDP socketsAndrei Vagin
This option allows multiple sockets to be bound to the same port. Incoming packets are distributed to sockets using a hash based on source and destination addresses. This means that all packets from one sender will be received by the same server socket. PiperOrigin-RevId: 227153413 Change-Id: I59b6edda9c2209d5b8968671e9129adb675920cf
2018-12-21Stub out SO_OOBINLINE.Ian Gudger
We don't explicitly support out-of-band data and treat it like normal in-band data. This is equilivent to SO_OOBINLINE being enabled, so always report that it is enabled. PiperOrigin-RevId: 226572742 Change-Id: I4c30ccb83265e76c30dea631cbf86822e6ee1c1b
2018-12-21Internal ChangeMichael Pratt
PiperOrigin-RevId: 226542979 Change-Id: Ife11ebd0a85b8a63078e6daa71b4a99a82080ac9
2018-12-21Implement SO_KEEPALIVE, TCP_KEEPIDLE, and TCP_KEEPINTVL.Ian Gudger
Within gVisor, plumb new socket options to netstack. Within netstack, fix GetSockOpt and SetSockOpt return value logic. PiperOrigin-RevId: 226532229 Change-Id: If40734e119eed633335f40b4c26facbebc791c74
2018-12-16Allow sending of multicast and IPv6 link-local packets w/o route.Chris Kuiper
Same as with broadcast packets, sending of a multicast packet shouldn't require accessing the route table. The same applies to IPv6 link-local addresses, which aren't routable at all (they don't belong to any subnet by definition). PiperOrigin-RevId: 225775870 Change-Id: Ic53e6560c125a83be2be9c3d112e66b36e8dfe7b
2018-12-13transport/tcp: remove unused error return valuesIan Gudger
PiperOrigin-RevId: 225421480 Change-Id: I1e9259b0b7e8490164e830b73338a615129c7f0e
2018-12-09Stub out TCP_QUICKACKIan Gudger
PiperOrigin-RevId: 224696233 Change-Id: I45c425d9e32adee5dcce29ca7439a06567b26014
2018-12-06Allow sending of broadcast packets w/o route.Chris Kuiper
Currently sending a broadcast packet (for DHCP, e.g.) requires a "default route" of the format "0.0.0.0/0 via 0.0.0.0 <intf>". There is no good reason for this and on devices with several ports this creates a rather akward route table with lots of such default routes (which defeats the purpose of a default route). PiperOrigin-RevId: 224378769 Change-Id: Icd7ec8a206eb08083cff9a837f6f9ab231c73a19
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-04 21:58:43 +0000