summaryrefslogtreecommitdiffstats
path: root/src/vnet/tcp/tcp_output.c
AgeCommit message (Collapse)AuthorFilesLines
2018-04-20tcp: improve statsFlorin Coras1-0/+6
Change-Id: I9ab11ba9f958c679112eb22c8db39cb269a29dc7 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-03-29tcp: fix fib index buffer taggingFlorin Coras1-13/+17
Change-Id: I373cc252df3621d44879b8eca70aed17d7752a2a Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-03-23tcp/session: sprinkle prefetchesFlorin Coras1-0/+8
Change-Id: Idef3c665580c13d72e99f43d16b8b13cc6ab746f Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-03-02session: first approximation implementation of tlsFlorin Coras1-1/+1
It consists of two main parts. First, add an application transport type whereby applications can offer transport to other applications. For instance, a tls app can offer transport services to other applications. And second, a tls transport app that leverages the mbedtls library for tls protocol implementation. Change-Id: I616996c6e6539a9e2368fab8a1ac874d7c5d9838 Signed-off-by: Florin Coras <fcoras@cisco.com>
2018-02-07Refactor vlib_buffer flagsDamjan Marion1-2/+2
Change-Id: I853386aebfe488ebb10328435b81b6e3403c5dd0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-02-01tcp: tcp_output.c failed to compile when VLIB_BUFFER_TRACE_TRAJECTORY is enabledSteven1-1/+1
Fixed a typo in tcp_push_header(). The typo only kicks in when the macro VLIB_BUFFER_TRACE_TRAJECTORY is enabled. Change-Id: I62832a4932ec5b14e3063d5eac113780851aae59 Signed-off-by: Steven <sluong@cisco.com>
2017-12-11session: generalize handling of network transportsFlorin Coras1-0/+1
- compute session type out of transport and network protos - make session, session lookup and session queue code network protocol agnostic This does not update the session layer to support non-ip network layer protocols Change-Id: Ifc2f92845e158b649d59462eb7d51c12af536691 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-11-29session: fix preallocation of local endpoint tableFlorin Coras1-3/+1
Change-Id: I67a73e31bda9e497859297fcc1765e880572884a Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-11-28tcp: fix retransmissions under buffer shortageFlorin Coras1-28/+28
- add debugging scaffolding for simulating buffer shortage Change-Id: Ice519d74f9c4e4094c4586c548185135b7bb5f2d Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-10-10session: add support for application namespacingFlorin Coras1-2/+1
Applications are now provided the option to select the namespace they are to be attached to and the scope of their attachement. Application namespaces are meant to: 1) constrain the scope of communication through the network by association with source interfaces and/or fib tables that provide the source ips to be used and limit the scope of routing 2) provide a namespace local scope to session layer communication, as opposed to the global scope provided by 1). That is, sessions can be established without assistance from transport and network layers. Albeit, zero/local-host ip addresses must still be provided in session establishment messages due to existing application idiosyncrasies. This mode of communication uses shared-memory fifos (cut-through sessions) exclusively. If applications request no namespace, they are assigned to the default one, which at its turn uses the default fib. Applications can request access to both local and global scopes for a namespace. If no scope is specified, session layer defaults to the global one. When a sw_if_index is provided for a namespace, zero-ip (INADDR_ANY) binds are converted to binds to the requested interface. Change-Id: Ia0f660bbf7eec7f89673f75b4821fc7c3d58e3d1 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-10-04[aarch64] Fixes CLI crashes on dpaa2 platform.Christophe Fontaine1-1/+1
- always use 'va_args' as pointer in all format_* functions - u32 for all 'indent' params as it's declaration was inconsistent Change-Id: Ic5799309a6b104c9b50fec309cba789c8da99e79 Signed-off-by: Christophe Fontaine <christophe.fontaine@enea.com>
2017-10-03tcp: updates to connection closing procedure (VPP-996)Florin Coras1-2/+13
- add separate TIME_WAIT time constant - fix output node for TIME_WAIT acks - ensure snd_nxt is snd_una_max after retransmitting fin - debugging improvements Change-Id: Ic947153346979853f2526824b229126e47aead86 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-09-26tcp: update snd_nxt after congestion recoveryFlorin Coras1-9/+5
Change-Id: I2cf4c4850b9c3c093a7dce0cec89b9f710f69393 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-09-25tcp: do not sample rtt for retransmitted segmentsFlorin Coras1-2/+19
Change-Id: I365c31607332a944ef498369881332b515894ed7 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-09-19session/tcp: improve preallocated segment handlingFlorin Coras1-18/+73
- add preallocated segment flag - don't remove pre-allocated segments except if application detaches - when preallocating fifos in multiple segments, completely fill a segment before moving to the next - detach server application from segment-managers when deleting app - batch syn/syn-ack/fin (re)transmissions - loosen up close-wait and time-wait times Change-Id: I412f53ce601cc83b3acc26aeffd7fa2d52d73b03 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-09-15dpdk: cli to check for buffer leakageFlorin Coras1-4/+6
Use buffer pre_data and existing buffer trace trajectory code to find out dpdk buffer leakages. Change-Id: I26a5d8bd2f23d01cb6070ffc3ddcc6d3d863b575 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-09-12tcp: horizontal scaling improvmentsFlorin Coras1-113/+99
- do not scale syn-ack window - fix the max number of outstanding syns in builtin client - fix syn-sent ack validation to use modulo arithmetic - improve retransmit timer handler - fix output buffer allocator leakeage - improved debugging Change-Id: Iac3bc0eadf7d0b494a93e22d210a3153b61b3273 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-09-01Add fixed-size, preallocated pool supportDave Barach1-14/+28
Simply call pool_init_fixed(...) before using the pool. Note that fixed, preallocated pools live in individually-mmap'ed address segments, except for the free element bitmap. A large fixed pool can exceed 4gb. Fix tcp buffer allocator leak, remove broken assert Change-Id: I4421082e12a77c41c6e20f7747f3150dcd01fc26 Signed-off-by: Dave Barach <dave@barachs.net>
2017-08-30tcp: re-enable persist timer if no data available to sendFlorin Coras1-4/+18
Additionally, flush rx fifos for closed sessions. Change-Id: If2cc563fbda0451e7572650e98b15f0a694a0ff9 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-08-25tcp: retransmit and multi-buffer segment fixes and improvementsFlorin Coras1-112/+152
- set session state as closed on session manager delete - enable retransmit as opposed to persist timer after persist timer completes - properly discard buffer chain bytes when new data overlaps ooo segments - don't use rxt bytes in snd space estimate used on tx path Change-Id: Id9cab686e532e5fe70c775d5440260e8eb890a9f Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-08-18session: fix multi-buffer segmentsFlorin Coras1-14/+17
Change-Id: I0e22c85ea570b934b9c78dc5e86d86d690bdae5e Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-08-16tcp: fix v6 sessionsroot1-4/+2
Change-Id: Ia6dd5e948b17b2f3866fe70838eabb09e35415e1 Signed-off-by: Dave Barach <dbarach@cisco.com> Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-08-14TCP: Update time_now once per burstFlorin Coras1-1/+1
Change-Id: I58089d7a9867ede9d8a36b2aea62edef04cb5b81 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-08-11Fix tcp multi buffer segments retransmissionFlorin Coras1-106/+184
- Fix tcp/udp sw checksum computation - Fix allocation of multi buffer tcp segments for retransmits - Send FIN only if/when tx fifo is empty Change-Id: I2e43a14b87a72c9e547b4339b9a51811cf5732c4 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-08-02Fix tcp tx buffer allocationFlorin Coras1-61/+127
- Make tcp output buffer allocation macro an inline function - Use per ip version per thread tx frames for retransmits and timer events - Fix / parameterize tcp data structure preallocation - Add a couple of gdb-callable show commands - Fix local endpoint cleanup Change-Id: I67b47b7570aa14cb4634b6fd93c57cd2eacbfa29 Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dave@barachs.net>
2017-08-02Make ip csum configurable in vlib buffer functionsFlorin Coras1-6/+7
Also fixes csum computation for lisp control plane 4o6 encapsulated control messages. Change-Id: I991e0b5c0d16dc51e0b5bdc79e1d752270b34765 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-07-30Make tcp active open data structures thread safeFlorin Coras1-3/+16
- Cleanup half-open connections and timers on the right thread - Ensure half-open connection and transport endpoint pools are thread safe - Enqueue TX events to the correct vpp thread in the builtin client - Use transport proto in transport connections instead of session type Change-Id: Id13239a206afbff6f34a38afa510fe014e4b2049 Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dave@barachs.net>
2017-07-21Improvements to tcp rx path and debuggingFlorin Coras1-20/+31
- Increment rcv_nxt for fin packets - Call tcp_segment_rcv only if buffer has data - Parse rcv opts before deleting half-open connection - Fix initial rcv_wnd - Improved event logging Change-Id: I9b83c04f432c4cec832c480b03e534deff02c3b1 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-07-18TCP/UDP checksum offload APIDave Barach1-3/+13
Change-Id: I2cb6ce4e29813f6602b14e6e61713fb381fbcef8 Signed-off-by: Dave Barach <dave@barachs.net>
2017-07-14vnet_buffer_t flags cleanupDamjan Marion1-4/+4
Change-Id: I123eccea98abafeb31f25d2a162501e2eded60d4 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-07-11Horizontal (nSessions) scaling draftDave Barach1-19/+34
- Data structure preallocation. - Input state machine fixes for mid-stream 3-way handshake retries. - Batch connections in the builtin_client - Multiple private fifo segment support - Fix elog simultaneous event type registration - Fix sacks when segment hole is added after highest sacked - Add "accepting" session state for sessions pending accept - Add ssvm non-recursive locking - Estimate RTT for syn-ack - Don't init fifo pointers. We're using relative offsets for ooo segments - CLI to dump individual session Change-Id: Ie0598563fd246537bafba4feed7985478ea1d415 Signed-off-by: Dave Barach <dbarach@cisco.com> Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-06-22Improve svm fifo and tcp tx path performance (VPP-846)Florin Coras1-8/+21
- multiarch on svm fifo - avoid ip lookup on tx Change-Id: Iab0d85204a710979417bca1d692cc47877131203 Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dbarach@cisco.com>
2017-06-19Overall tcp performance improvements (VPP-846)Florin Coras1-6/+4
- limit minimum rto per connection - cleanup sack scoreboard - switched svm fifo out-of-order data handling from absolute offsets to relative offsets. - improve cwnd handling when using sacks - add cc event debug stats - improved uri tcp test client/server: bugfixes and added half-duplex mode - expanded builtin client/server - updated uri socket client/server code to work in half-duplex - ensure session node unsets fifo event for empty fifo - fix session detach Change-Id: Ia446972340e32a65e0694ee2844355167d0c170d Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-06-09Implement sack based tcp loss recovery (RFC 6675)Florin Coras1-98/+189
- refactor existing congestion control code (RFC 6582/5681). Handling of ack feedback now consists of: ack parsing, cc event detection, event handling, congestion control update - extend sack scoreboard to support sack based retransmissions - basic implementation of Eifel detection algorithm (RFC 3522) for detecting spurious retransmissions - actually initialize the per-thread frame freelist hash tables - increase worker stack size to 2mb - fix session queue node out-of-buffer handling - ensure that the local buffer cache vec_len matches reality - avoid 2x spurious event requeues when short of buffers - count out-of-buffer events - make the builtin server thread-safe - fix bihash template threading issue: need to paint -1 across uninitialized working_copy_length vector elements (via rebase from master) Change-Id: I646cb9f1add9a67d08f4a87badbcb117980ebfc4 Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dbarach@cisco.com>
2017-05-20Improve session debuggingFlorin Coras1-2/+10
Also improves builtin client code. Change-Id: I8bca1aa632028f95c373726efb0abf2ee0eff414 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-05-10Improve TCP option handling, VPP-757Florin Coras1-4/+12
Change-Id: Ica634536387d1196366ec96c52770287fcab0768 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-05-10Ignore data in RST segments, VPP-723Florin Coras1-44/+30
Change-Id: I01650b3b10b79ec549be0d5eceb0e318c06fcb50 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-05-09Add support for tcp/session buffer chainsFlorin Coras1-2/+2
Change-Id: I01c6e3dc3a1b2785df37bb66b19c4b5cbb8f3211 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-05-07Include TCP options in segment size computationFlorin Coras1-35/+69
Ensure that TCP data plus options does not exceed peer's advertised MSS. Change-Id: I0de824cb3619346f0394dd694942fc1cf33a82b7 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-05-07Fix TCP loss recovery, VPP-745Florin Coras1-27/+17
Allows pure loss recovery retransmits only on timeout. Change-Id: I563cdbf9e7b890a6569350bdbda4f746ace0544e Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-05-01TCP ooo reception fixesFlorin Coras1-1/+3
- Improve svm fifo handling of out-of-order segments - Ensure tsval_recent is updated only if rcv_las falls withing the segments's sequence space - Avoid directly dropping old ACKs - Improve debugging Change-Id: I88dbe2394a0ad7eb389a4cc12d013a13733953aa Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-04-24Session layer improvementsFlorin Coras1-6/+0
Among others: - Moved app event queue to shared memory segment - Use private memory segment for builtin apps - Remove pid from svm fifo - Protect session fifo (de)allocation - Use fifo event for session disconnects - Have session queue node poll in all wk threads Change-Id: I89dbf7fdfebef12f5ef2b34ba3ef3c2c07f49ff2 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-04-15Set lower bound on persist timerFlorin Coras1-5/+5
Change-Id: Ie98ecb8944e4d27e943797948fad41ec074d6720 Signed-off-by: Florin Coras <fcoras@cisco.com>
2017-04-14tcp: completed trace functionsClement Durand1-7/+38
* Populated the trace struct that weren't used before * Modified and created format functions to format tcp packets and connections * Completed the node definitions to add the format_trace function * Filled the tracing parts with `vlib_add_trace' calls in each tcp node function For the nodes in tcp_input.c, there is a verbose trace and a non-verbose trace. Each packet goes through tcp[4-6]-input which is traced with `format_tcp_rx_trace', and the other nodes are traced with `format_tcp_rx_trace_short'. Change-Id: I4f2eed023f5973c14343132a33b06131cf063aa2 Signed-off-by: Pierre Pfister <ppfister@cisco.com> Signed-off-by: Clement Durand <clement.durand@polytechnique.edu>
2017-04-06Use thread local storage for thread indexDamjan Marion1-10/+10
This patch deprecates stack-based thread identification, Also removes requirement that thread stacks are adjacent. Finally, possibly annoying for some folks, it renames all occurences of cpu_index and cpu_number with thread index. Using word "cpu" is misleading here as thread can be migrated ti different CPU, and also it is not related to linux cpu index. Change-Id: I68cdaf661e701d2336fc953dcb9978d10a70f7c1 Signed-off-by: Damjan Marion <damarion@cisco.com>
2017-04-02TCP cc/window management fixes and debuggingFlorin Coras1-13/+66
- added persist timer - update rcv_las whenever sending an ack - moved fifo size to its own cache line - improved session and builtin client debugging Change-Id: Ia649cf942cf0c061a713e8b67f0eb6974a6cd55b Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dave@barachs.net>
2017-03-27TCP/session improvementsFlorin Coras1-93/+202
- Added svm fifo flag for tracking fifo dequeue events (replaces event length). Updated all code to switch to the new scheme. - More session debugging - Fix peek index wrap - Add a trivial socket test client - Fast retransmit/cc fixes - tx and rx SACK fixes and unit testing - SRTT computation fix - remove dupack/ack burst filters - improve ack rx - improved segment rx - builtin client test code Change-Id: Ic4eb2d5ca446eb2260ccd3ccbcdaa73c64e7f4e1 Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dbarach@cisco.com>
2017-03-13VPP-659 Improve tcp/session debugging and testingFlorin Coras1-37/+39
- event-logging support for tcp and session layer - improvements to uri test code - builtin_server on port 1234 - use the CLOSEWAIT timer when we rx FIN in FIN_WAIT_2 state Change-Id: Ibc445f164b2086b20323bf89c77cffd3059f570f Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dbarach@cisco.com> Signed-off-by: Dave Barach <dave@barachs.net>
2017-03-10VPP-659 TCP improvementsFlorin Coras1-9/+38
- builtin test echo server - fix SYN-ACK retransmit canceling - avoid sending spurious ACK if in LAST_ACK - improved client dummy test app - renamed tx fifo dequeuing and sending functions to avoid confusion - improved RST handling Change-Id: Ia14aad3df319540dcf6e6a4e18a9f8d423a4b83b Signed-off-by: Florin Coras <fcoras@cisco.com> Signed-off-by: Dave Barach <dave@barachs.net>
2017-03-04Cleanup URI code and TCP bugfixingFlorin Coras1-28/+62
- Add CLI/API to enable session layer, by default it's disabled - Improve rcv wnd computation - Improvements to tx path - URI code cleanup - Builtin test tcp server - Improve src port allocation Change-Id: I2ace498e76a0771d4c31a8075cc14fe33d7dfa38 Signed-off-by: Florin Coras <fcoras@cisco.com>